From 022fc5315b7aff69d3df2c953b892a6232642d50 Mon Sep 17 00:00:00 2001 From: Martijn van de Streek Date: Fri, 16 Oct 2020 08:38:05 +0200 Subject: HID: uclogic: Add ID for Trust Flex Design Tablet The Trust Flex Design Tablet has an UGTizer USB ID and requires the same initialization as the UGTizer GP0610 to be detected as a graphics tablet instead of a mouse. Signed-off-by: Martijn van de Streek Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-uclogic-core.c | 2 ++ drivers/hid/hid-uclogic-params.c | 2 ++ 3 files changed, 5 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index d69842f79fc6..49d68bbf4852 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -1298,6 +1298,7 @@ #define USB_VENDOR_ID_UGTIZER 0x2179 #define USB_DEVICE_ID_UGTIZER_TABLET_GP0610 0x0053 +#define USB_DEVICE_ID_UGTIZER_TABLET_GT5040 0x0077 #define USB_VENDOR_ID_VIEWSONIC 0x0543 #define USB_DEVICE_ID_VIEWSONIC_PD1011 0xe621 diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index 86b568037cb8..8e9c9e646cb7 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -385,6 +385,8 @@ static const struct hid_device_id uclogic_devices[] = { USB_DEVICE_ID_UCLOGIC_DRAWIMAGE_G3) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610) }, + { HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, + USB_DEVICE_ID_UGTIZER_TABLET_GT5040) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_TABLET_G5) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c index 7d20d1fcf8d2..d26d8cd98efc 100644 --- a/drivers/hid/hid-uclogic-params.c +++ b/drivers/hid/hid-uclogic-params.c @@ -997,6 +997,8 @@ int uclogic_params_init(struct uclogic_params *params, break; case VID_PID(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610): + case VID_PID(USB_VENDOR_ID_UGTIZER, + USB_DEVICE_ID_UGTIZER_TABLET_GT5040): case VID_PID(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_G540): case VID_PID(USB_VENDOR_ID_UGEE, -- cgit v1.2.3 From b59f38dbfd5d19eb7e03d8b639f0c0d385ba8cc5 Mon Sep 17 00:00:00 2001 From: Harry Cutts Date: Wed, 21 Oct 2020 06:56:12 -0700 Subject: HID: logitech-hidpp: Add PID for MX Anywhere 2 It seems that the PID 0x4072 was missing from the list Logitech gave me for this mouse, as I found one with it in the wild (with which I tested this patch). Fixes: 4435ff2f09a2 ("HID: logitech: Enable high-resolution scrolling on Logitech mice") Signed-off-by: Harry Cutts Acked-by: Peter Hutterer Signed-off-by: Jiri Kosina --- drivers/hid/hid-logitech-hidpp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index b8b53dc95e86..730036650f7d 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -3947,6 +3947,7 @@ static const struct hid_device_id hidpp_devices[] = { LDJ_DEVICE(0x405e), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, { /* Mouse Logitech MX Anywhere 2 */ LDJ_DEVICE(0x404a), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { LDJ_DEVICE(0x4072), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, { LDJ_DEVICE(0xb013), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, { LDJ_DEVICE(0xb018), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, { LDJ_DEVICE(0xb01f), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, -- cgit v1.2.3 From 3c785a06dee99501a17f8e8cf29b2b7e3f1e94ea Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 19 Oct 2020 09:48:14 +0200 Subject: HID: ite: Replace ABS_MISC 120/121 events with touchpad on/off keypresses The usb-hid keyboard-dock for the Acer Switch 10 SW5-012 model declares an application and hid-usage page of 0x0088 for the INPUT(4) report which it sends. This reports contains 2 8-bit fields which are declared as HID_MAIN_ITEM_VARIABLE. The keyboard-touchpad combo never actually generates this report, except when the touchpad is toggled on/off with the Fn + F7 hotkey combo. The toggle on/off is handled inside the keyboard-dock, when the touchpad is toggled off it simply stops sending events. When the touchpad is toggled on/off an INPUT(4) report is generated with the first content byte set to 120/121, before this commit the kernel would report this as ABS_MISC 120/121 events. Patch the descriptor to replace the HID_MAIN_ITEM_VARIABLE with HID_MAIN_ITEM_RELATIVE (because no key-presss release events are send) and add mappings for the 0x00880078 and 0x00880079 usages to generate touchpad on/off key events when the touchpad is toggled on/off. Signed-off-by: Hans de Goede Signed-off-by: Jiri Kosina --- drivers/hid/hid-ite.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 60 insertions(+), 1 deletion(-) diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 044a93f3c117..742c052b0110 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -11,6 +11,48 @@ #include "hid-ids.h" +#define QUIRK_TOUCHPAD_ON_OFF_REPORT BIT(0) + +static __u8 *ite_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) +{ + unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); + + if (quirks & QUIRK_TOUCHPAD_ON_OFF_REPORT) { + if (*rsize == 188 && rdesc[162] == 0x81 && rdesc[163] == 0x02) { + hid_info(hdev, "Fixing up ITE keyboard report descriptor\n"); + rdesc[163] = HID_MAIN_ITEM_RELATIVE; + } + } + + return rdesc; +} + +static int ite_input_mapping(struct hid_device *hdev, + struct hid_input *hi, struct hid_field *field, + struct hid_usage *usage, unsigned long **bit, + int *max) +{ + + unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); + + if ((quirks & QUIRK_TOUCHPAD_ON_OFF_REPORT) && + (usage->hid & HID_USAGE_PAGE) == 0x00880000) { + if (usage->hid == 0x00880078) { + /* Touchpad on, userspace expects F22 for this */ + hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_F22); + return 1; + } + if (usage->hid == 0x00880079) { + /* Touchpad off, userspace expects F23 for this */ + hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_F23); + return 1; + } + return -1; + } + + return 0; +} + static int ite_event(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage, __s32 value) { @@ -37,13 +79,27 @@ static int ite_event(struct hid_device *hdev, struct hid_field *field, return 0; } +static int ite_probe(struct hid_device *hdev, const struct hid_device_id *id) +{ + int ret; + + hid_set_drvdata(hdev, (void *)id->driver_data); + + ret = hid_open_report(hdev); + if (ret) + return ret; + + return hid_hw_start(hdev, HID_CONNECT_DEFAULT); +} + static const struct hid_device_id ite_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) }, { HID_USB_DEVICE(USB_VENDOR_ID_258A, USB_DEVICE_ID_258A_6A88) }, /* ITE8595 USB kbd ctlr, with Synaptics touchpad connected to it. */ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_SYNAPTICS, - USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) }, + USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012), + .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, /* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_SYNAPTICS, @@ -55,6 +111,9 @@ MODULE_DEVICE_TABLE(hid, ite_devices); static struct hid_driver ite_driver = { .name = "itetech", .id_table = ite_devices, + .probe = ite_probe, + .report_fixup = ite_report_fixup, + .input_mapping = ite_input_mapping, .event = ite_event, }; module_hid_driver(ite_driver); -- cgit v1.2.3 From 652f3d00de523a17b0cebe7b90debccf13aa8c31 Mon Sep 17 00:00:00 2001 From: Frank Yang Date: Fri, 21 Aug 2020 03:16:50 +0900 Subject: HID: cypress: Support Varmilo Keyboards' media hotkeys The Varmilo VA104M Keyboard (04b4:07b1, reported as Varmilo Z104M) exposes media control hotkeys as a USB HID consumer control device, but these keys do not work in the current (5.8-rc1) kernel due to the incorrect HID report descriptor. Fix the problem by modifying the internal HID report descriptor. More specifically, the keyboard report descriptor specifies the logical boundary as 572~10754 (0x023c ~ 0x2a02) while the usage boundary is specified as 0~10754 (0x00 ~ 0x2a02). This results in an incorrect interpretation of input reports, causing inputs to be ignored. By setting the Logical Minimum to zero, we align the logical boundary with the Usage ID boundary. Some notes: * There seem to be multiple variants of the VA104M keyboard. This patch specifically targets 04b4:07b1 variant. * The device works out-of-the-box on Windows platform with the generic consumer control device driver (hidserv.inf). This suggests that Windows either ignores the Logical Minimum/Logical Maximum or interprets the Usage ID assignment differently from the linux implementation; Maybe there are other devices out there that only works on Windows due to this problem? Signed-off-by: Frank Yang Signed-off-by: Jiri Kosina --- drivers/hid/hid-cypress.c | 44 +++++++++++++++++++++++++++++++++++++++----- drivers/hid/hid-ids.h | 2 ++ 2 files changed, 41 insertions(+), 5 deletions(-) diff --git a/drivers/hid/hid-cypress.c b/drivers/hid/hid-cypress.c index a50ba4a4a1d7..b88f889b3932 100644 --- a/drivers/hid/hid-cypress.c +++ b/drivers/hid/hid-cypress.c @@ -23,19 +23,17 @@ #define CP_2WHEEL_MOUSE_HACK 0x02 #define CP_2WHEEL_MOUSE_HACK_ON 0x04 +#define VA_INVAL_LOGICAL_BOUNDARY 0x08 + /* * Some USB barcode readers from cypress have usage min and usage max in * the wrong order */ -static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static __u8 *cp_rdesc_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { - unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); unsigned int i; - if (!(quirks & CP_RDESC_SWAPPED_MIN_MAX)) - return rdesc; - if (*rsize < 4) return rdesc; @@ -48,6 +46,40 @@ static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc, return rdesc; } +static __u8 *va_logical_boundary_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) +{ + /* + * Varmilo VA104M (with VID Cypress and device ID 07B1) incorrectly + * reports Logical Minimum of its Consumer Control device as 572 + * (0x02 0x3c). Fix this by setting its Logical Minimum to zero. + */ + if (*rsize == 25 && + rdesc[0] == 0x05 && rdesc[1] == 0x0c && + rdesc[2] == 0x09 && rdesc[3] == 0x01 && + rdesc[6] == 0x19 && rdesc[7] == 0x00 && + rdesc[11] == 0x16 && rdesc[12] == 0x3c && rdesc[13] == 0x02) { + hid_info(hdev, + "fixing up varmilo VA104M consumer control report descriptor\n"); + rdesc[12] = 0x00; + rdesc[13] = 0x00; + } + return rdesc; +} + +static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) +{ + unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); + + if (quirks & CP_RDESC_SWAPPED_MIN_MAX) + rdesc = cp_rdesc_fixup(hdev, rdesc, rsize); + if (quirks & VA_INVAL_LOGICAL_BOUNDARY) + rdesc = va_logical_boundary_fixup(hdev, rdesc, rsize); + + return rdesc; +} + static int cp_input_mapped(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) @@ -128,6 +160,8 @@ static const struct hid_device_id cp_devices[] = { .driver_data = CP_RDESC_SWAPPED_MIN_MAX }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_MOUSE), .driver_data = CP_2WHEEL_MOUSE_HACK }, + { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_VARMILO_VA104M_07B1), + .driver_data = VA_INVAL_LOGICAL_BOUNDARY }, { } }; MODULE_DEVICE_TABLE(hid, cp_devices); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 49d68bbf4852..81d99c47c2e5 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -331,6 +331,8 @@ #define USB_DEVICE_ID_CYPRESS_BARCODE_4 0xed81 #define USB_DEVICE_ID_CYPRESS_TRUETOUCH 0xc001 +#define USB_DEVICE_ID_CYPRESS_VARMILO_VA104M_07B1 0X07b1 + #define USB_VENDOR_ID_DATA_MODUL 0x7374 #define USB_VENDOR_ID_DATA_MODUL_EASYMAXTOUCH 0x1201 -- cgit v1.2.3 From 1811977cb11354aef8cbd13e35ff50db716728a4 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Wed, 30 Sep 2020 22:52:31 +0200 Subject: HID: add support for Sega Saturn MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This device needs HID_QUIRK_MULTI_INPUT in order to be presented to userspace in a consistent way. Reported-and-tested-by: David Gámiz Jiménez Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-quirks.c | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 81d99c47c2e5..28ecd635edc1 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -487,6 +487,7 @@ #define USB_DEVICE_ID_PENPOWER 0x00f4 #define USB_VENDOR_ID_GREENASIA 0x0e8f +#define USB_DEVICE_ID_GREENASIA_DUAL_SAT_ADAPTOR 0x3010 #define USB_DEVICE_ID_GREENASIA_DUAL_USB_JOYPAD 0x3013 #define USB_VENDOR_ID_GRETAGMACBETH 0x0971 diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 7a2be0205dfd..b154e11d43bf 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -83,6 +83,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_FUTABA, USB_DEVICE_ID_LED_DISPLAY), HID_QUIRK_NO_INIT_REPORTS }, + { HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_SAT_ADAPTOR), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_USB_JOYPAD), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_DRIVING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FIGHTING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT }, -- cgit v1.2.3 From fbc81ec5b85d43a4b22e49ec0e643fa7dec2ea40 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sat, 3 Oct 2020 17:28:27 +0200 Subject: efi/arm: set HSCTLR Thumb2 bit correctly for HVC calls from HYP Commit db227c19e68db353 ("ARM: 8985/1: efi/decompressor: deal with HYP mode boot gracefully") updated the EFI entry code to permit firmware to invoke the EFI stub loader in HYP mode, with the MMU either enabled or disabled, neither of which is permitted by the EFI spec, but which does happen in the field. In the MMU on case, we remain in HYP mode as configured by the firmware, and rely on the fact that any HVC instruction issued in this mode will be dispatched via the SVC slot in the HYP vector table. However, this slot will point to a Thumb2 symbol if the kernel is built in Thumb2 mode, and so we have to configure HSCTLR to ensure that the exception handlers are invoked in Thumb2 mode as well. Fixes: db227c19e68db353 ("ARM: 8985/1: efi/decompressor: deal with HYP mode boot gracefully") Signed-off-by: Ard Biesheuvel --- arch/arm/boot/compressed/head.S | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 2e04ec5b5446..caa27322a0ab 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -1472,6 +1472,9 @@ ENTRY(efi_enter_kernel) @ issued from HYP mode take us to the correct handler code. We @ will disable the MMU before jumping to the kernel proper. @ + ARM( bic r1, r1, #(1 << 30) ) @ clear HSCTLR.TE + THUMB( orr r1, r1, #(1 << 30) ) @ set HSCTLR.TE + mcr p15, 4, r1, c1, c0, 0 adr r0, __hyp_reentry_vectors mcr p15, 4, r0, c12, c0, 0 @ set HYP vector base (HVBAR) isb -- cgit v1.2.3 From fe5186cf12e30facfe261e9be6c7904a170bd822 Mon Sep 17 00:00:00 2001 From: Vamshi K Sthambamkadi Date: Fri, 23 Oct 2020 17:24:39 +0530 Subject: efivarfs: fix memory leak in efivarfs_create() kmemleak report: unreferenced object 0xffff9b8915fcb000 (size 4096): comm "efivarfs.sh", pid 2360, jiffies 4294920096 (age 48.264s) hex dump (first 32 bytes): 2d 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 -............... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000cc4d897c>] kmem_cache_alloc_trace+0x155/0x4b0 [<000000007d1dfa72>] efivarfs_create+0x6e/0x1a0 [<00000000e6ee18fc>] path_openat+0xe4b/0x1120 [<000000000ad0414f>] do_filp_open+0x91/0x100 [<00000000ce93a198>] do_sys_openat2+0x20c/0x2d0 [<000000002a91be6d>] do_sys_open+0x46/0x80 [<000000000a854999>] __x64_sys_openat+0x20/0x30 [<00000000c50d89c9>] do_syscall_64+0x38/0x90 [<00000000cecd6b5f>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 In efivarfs_create(), inode->i_private is setup with efivar_entry object which is never freed. Cc: Signed-off-by: Vamshi K Sthambamkadi Link: https://lore.kernel.org/r/20201023115429.GA2479@cosmos Signed-off-by: Ard Biesheuvel --- fs/efivarfs/super.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 15880a68faad..f943fd0b0699 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -21,6 +21,7 @@ LIST_HEAD(efivarfs_list); static void efivarfs_evict_inode(struct inode *inode) { clear_inode(inode); + kfree(inode->i_private); } static const struct super_operations efivarfs_ops = { -- cgit v1.2.3 From c20782ad4eb9dfa7f41cb2d85f218d0940f7cef1 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 26 Oct 2020 10:08:47 +0200 Subject: ARM: OMAP2+: Fix location for select PM_GENERIC_DOMAINS I accidentally misplaced select PM_GENERIC_DOMAINS, it should be selected for all the SoCs instead. Fixes: 58cbff023bfa ("soc: ti: omap-prm: Add basic power domain support") Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 3ee7bdff86b2..68ba5adfaa23 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -7,7 +7,6 @@ config ARCH_OMAP2 depends on ARCH_MULTI_V6 select ARCH_OMAP2PLUS select CPU_V6 - select PM_GENERIC_DOMAINS if PM select SOC_HAS_OMAP2_SDRC config ARCH_OMAP3 @@ -106,6 +105,7 @@ config ARCH_OMAP2PLUS select OMAP_DM_TIMER select OMAP_GPMC select PINCTRL + select PM_GENERIC_DOMAINS if PM select RESET_CONTROLLER select SOC_BUS select TI_SYSC -- cgit v1.2.3 From b69fd00120f8e3348273323099669cb058668263 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 26 Oct 2020 10:08:47 +0200 Subject: ARM: OMAP2+: Fix missing select PM_GENERIC_DOMAINS_OF We should select also PM_GENERIC_DOMAINS_OF in addition to PM_GENERIC_DOMAINS to have device tree based PM domain providers enabled. Fixes: 58cbff023bfa ("soc: ti: omap-prm: Add basic power domain support") Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 68ba5adfaa23..3f62a0c9450d 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -106,6 +106,7 @@ config ARCH_OMAP2PLUS select OMAP_GPMC select PINCTRL select PM_GENERIC_DOMAINS if PM + select PM_GENERIC_DOMAINS_OF if PM select RESET_CONTROLLER select SOC_BUS select TI_SYSC -- cgit v1.2.3 From e275d2109cdaea8b4554b9eb8a828bdb8f8ba068 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 26 Oct 2020 10:08:47 +0200 Subject: bus: ti-sysc: Fix reset status check for modules with quirks Commit d46f9fbec719 ("bus: ti-sysc: Use optional clocks on for enable and wait for softreset bit") started showing a "OCP softreset timed out" warning on enable if the interconnect target module is not out of reset. This caused the warning to be often triggered for i2c and hdq while the devices are working properly. Turns out that some interconnect target modules seem to have an unusable reset status bits unless the module specific reset quirks are activated. Let's just skip the reset status check for those modules as we only want to activate the reset quirks when doing a reset, and not on enable. This way we don't see the bogus "OCP softreset timed out" warnings during boot. Fixes: d46f9fbec719 ("bus: ti-sysc: Use optional clocks on for enable and wait for softreset bit") Signed-off-by: Tony Lindgren --- drivers/bus/ti-sysc.c | 24 +++++++++++++++--------- include/linux/platform_data/ti-sysc.h | 1 + 2 files changed, 16 insertions(+), 9 deletions(-) diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index efb088df1276..88a751c11677 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -970,9 +970,15 @@ static int sysc_enable_module(struct device *dev) return error; } } - error = sysc_wait_softreset(ddata); - if (error) - dev_warn(ddata->dev, "OCP softreset timed out\n"); + /* + * Some modules like i2c and hdq1w have unusable reset status unless + * the module reset quirk is enabled. Skip status check on enable. + */ + if (!(ddata->cfg.quirks & SYSC_MODULE_QUIRK_ENA_RESETDONE)) { + error = sysc_wait_softreset(ddata); + if (error) + dev_warn(ddata->dev, "OCP softreset timed out\n"); + } if (ddata->cfg.quirks & SYSC_QUIRK_OPT_CLKS_IN_RESET) sysc_disable_opt_clocks(ddata); @@ -1373,17 +1379,17 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK("hdmi", 0, 0, 0x10, -ENODEV, 0x50030200, 0xffffffff, SYSC_QUIRK_OPT_CLKS_NEEDED), SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x00000006, 0xffffffff, - SYSC_MODULE_QUIRK_HDQ1W), + SYSC_MODULE_QUIRK_HDQ1W | SYSC_MODULE_QUIRK_ENA_RESETDONE), SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x0000000a, 0xffffffff, - SYSC_MODULE_QUIRK_HDQ1W), + SYSC_MODULE_QUIRK_HDQ1W | SYSC_MODULE_QUIRK_ENA_RESETDONE), SYSC_QUIRK("i2c", 0, 0, 0x20, 0x10, 0x00000036, 0x000000ff, - SYSC_MODULE_QUIRK_I2C), + SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE), SYSC_QUIRK("i2c", 0, 0, 0x20, 0x10, 0x0000003c, 0x000000ff, - SYSC_MODULE_QUIRK_I2C), + SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE), SYSC_QUIRK("i2c", 0, 0, 0x20, 0x10, 0x00000040, 0x000000ff, - SYSC_MODULE_QUIRK_I2C), + SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE), SYSC_QUIRK("i2c", 0, 0, 0x10, 0x90, 0x5040000a, 0xfffff0f0, - SYSC_MODULE_QUIRK_I2C), + SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE), SYSC_QUIRK("gpu", 0x50000000, 0x14, -ENODEV, -ENODEV, 0x00010201, 0xffffffff, 0), SYSC_QUIRK("gpu", 0x50000000, 0xfe00, 0xfe10, -ENODEV, 0x40000000 , 0xffffffff, SYSC_MODULE_QUIRK_SGX), diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index c59999ce044e..240dce553a0b 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -50,6 +50,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_MODULE_QUIRK_ENA_RESETDONE BIT(25) #define SYSC_MODULE_QUIRK_PRUSS BIT(24) #define SYSC_MODULE_QUIRK_DSS_RESET BIT(23) #define SYSC_MODULE_QUIRK_RTC_UNLOCK BIT(22) -- cgit v1.2.3 From e7ae08d398e094e1305dee823435b1f996d39106 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 26 Oct 2020 10:08:47 +0200 Subject: bus: ti-sysc: Fix bogus resetdone warning on enable for cpsw Bail out early from sysc_wait_softreset() just like we do in sysc_reset() if there's no sysstatus srst_shift to fix a bogus resetdone warning on enable as suggested by Grygorii Strashko . We do not currently handle resets for modules that need writing to the sysstatus register. If we at some point add that, we also need to add SYSS_QUIRK_RESETDONE_INVERTED flag for cpsw as the sysstatus bit is low when reset is done as described in the am335x TRM "Table 14-202 SOFT_RESET Register Field Descriptions" Fixes: d46f9fbec719 ("bus: ti-sysc: Use optional clocks on for enable and wait for softreset bit") Suggested-by: Grygorii Strashko Acked-by: Grygorii Strashko Signed-off-by: Tony Lindgren --- drivers/bus/ti-sysc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 88a751c11677..16132e6e91f8 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -227,6 +227,9 @@ static int sysc_wait_softreset(struct sysc *ddata) u32 sysc_mask, syss_done, rstval; int syss_offset, error = 0; + if (ddata->cap->regbits->srst_shift < 0) + return 0; + syss_offset = ddata->offsets[SYSC_SYSSTATUS]; sysc_mask = BIT(ddata->cap->regbits->srst_shift); -- cgit v1.2.3 From fdc24d722f353610b6aad23d99147632a19a6138 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Fri, 9 Oct 2020 09:44:23 +0200 Subject: MAINTAINERS: Add Jernej Škrabec as a reviewer for Allwinner SoCs support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Jernej has helped a lot by reviewing patches recently, so let's make it official. Signed-off-by: Maxime Ripard Acked-by: Chen-Yu Tsai Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20201009074423.10708-1-maxime@cerno.tech --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index e73636b75f29..b5c4163577fb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1546,6 +1546,7 @@ F: drivers/clk/sunxi/ ARM/Allwinner sunXi SoC support M: Maxime Ripard M: Chen-Yu Tsai +R: Jernej Skrabec L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git -- cgit v1.2.3 From a2089ac7f8dc682ef52ed74b52997d36cde76d05 Mon Sep 17 00:00:00 2001 From: Clément Péron Date: Sun, 11 Oct 2020 23:15:14 +0200 Subject: arm64: dts: allwinner: pinetab: Drop unnecessary address/size-cells information MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit make dtbs_check warm about unknown address/size-cells property in the pinetab device-tree. This is because these information are not necessary. Drop them. Signed-off-by: Clément Péron Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20201011211514.155266-1-peron.clem@gmail.com --- arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts index 3ab0f0347bc9..0494bfaf2ffa 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts @@ -122,9 +122,6 @@ status = "okay"; port { - #address-cells = <1>; - #size-cells = <0>; - csi_ep: endpoint { remote-endpoint = <&ov5640_ep>; bus-width = <8>; -- cgit v1.2.3 From 97a38c1c213b162aa577299de698f39c18ba696b Mon Sep 17 00:00:00 2001 From: Clément Péron Date: Sun, 18 Oct 2020 19:24:09 +0200 Subject: arm64: dts: allwinner: beelink-gs1: Enable both RGMII RX/TX delay MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Before the commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config"), the software overwrite for RX/TX delays of the RTL8211e were not working properly and the Beelink GS1 had both RX/TX delay of RGMII interface set using pull-up on the TXDLY and RXDLY pins. Now that these delays are working properly they overwrite the HW config and set this to 'rgmii' meaning no delay on both RX/TX. This makes the ethernet of this board not working anymore. Set the phy-mode to 'rgmii-id' meaning RGMII with RX/TX delays in the device-tree to keep the correct configuration. Fixes: 089bee8dd119 ("arm64: dts: allwinner: h6: Introduce Beelink GS1 board") Signed-off-by: Clément Péron Signed-off-by: Maxime Ripard Acked-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20201018172409.1754775-1-peron.clem@gmail.com --- arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts index 3f7ceeb1a767..7c9dbde645b5 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts @@ -97,7 +97,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&ext_rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_aldo2>; status = "okay"; -- cgit v1.2.3 From 419c65f5000a6c25597ea52488528d75b287cbd0 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Mon, 19 Oct 2020 06:34:49 +0000 Subject: arm64: dts: allwinner: Pine H64: Enable both RGMII RX/TX delay Since commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config"), the network is unusable on PineH64 model A. This is due to phy-mode incorrectly set to rgmii instead of rgmii-id. Fixes: 729e1ffcf47e ("arm64: allwinner: h6: add support for the Ethernet on Pine H64") Signed-off-by: Corentin Labbe Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20201019063449.33316-1-clabbe@baylibre.com --- arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts index af85b2074867..961732c52aa0 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts @@ -100,7 +100,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&ext_rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_gmac_3v3>; allwinner,rx-delay-ps = <200>; -- cgit v1.2.3 From d7cdff444579e6659459b2fe04340ebb27628d5e Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Thu, 22 Oct 2020 20:58:39 +0200 Subject: arm64: dts: allwinner: a64: OrangePi Win: Fix ethernet node RX/TX delay on OrangePi Win board is set on PHY. Reflect that in ethernet node. Fixes: 93d6a27cfcc0 ("arm64: dts: allwinner: a64: Orange Pi Win: Add Ethernet node") Signed-off-by: Jernej Skrabec Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20201022185839.2779245-1-jernej.skrabec@siol.net --- arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts index d894ec5fa8a1..70e31743f0ba 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts @@ -120,7 +120,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_gmac_3v3>; status = "okay"; -- cgit v1.2.3 From 927f42fcc1b4f7d04a2ac5cf02f25612aa8923a4 Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Thu, 22 Oct 2020 23:13:01 +0200 Subject: arm64: dts: allwinner: a64: Pine64 Plus: Fix ethernet node According to board schematic, PHY provides both, RX and TX delays. However, according to "fix" Realtek provided for this board, only TX delay should be provided by PHY. Tests show that both variants work but TX only PHY delay works slightly better. Update ethernet node to reflect the fact that PHY provides TX delay. Fixes: 94f442886711 ("arm64: dts: allwinner: A64: Restore EMAC changes") Signed-off-by: Jernej Skrabec Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20201022211301.3548422-1-jernej.skrabec@siol.net --- arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts index b26181cf9095..b54099b654c8 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts @@ -13,7 +13,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-txid"; phy-handle = <&ext_rgmii_phy>; status = "okay"; }; -- cgit v1.2.3 From b34bf9f6a623ddb82600a5ed5c644224122395e1 Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Fri, 23 Oct 2020 20:48:58 +0200 Subject: arm64: dts: allwinner: h5: OrangePi PC2: Fix ethernet node RX and TX delay are provided by ethernet PHY. Reflect that in ethernet node. Fixes: 44a94c7ef989 ("arm64: dts: allwinner: H5: Restore EMAC changes") Signed-off-by: Jernej Skrabec Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20201023184858.3272918-1-jernej.skrabec@siol.net --- arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts index 7d7aad18f078..8bf2db9dcbda 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts @@ -123,7 +123,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; -- cgit v1.2.3 From b3eec3212e66ece33f69be0de98d54e67834e798 Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Sun, 25 Oct 2020 09:19:49 +0100 Subject: ARM: dts: sun8i: r40: bananapi-m2-ultra: Fix ethernet node Ethernet PHY on BananaPi M2 Ultra provides RX and TX delays. Fix ethernet node to reflect that fact. Fixes: c36fd5a48bd2 ("ARM: dts: sun8i: r40: bananapi-m2-ultra: Enable GMAC ethernet controller") Signed-off-by: Jernej Skrabec Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20201025081949.783443-1-jernej.skrabec@siol.net --- arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts index 2fc62ef0cb3e..a6a1087a0c9b 100644 --- a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts +++ b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts @@ -129,7 +129,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_dc1sw>; status = "okay"; }; -- cgit v1.2.3 From 8d80e2f00a42ef10b54e1b2d9e97314f8fd046c0 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sun, 25 Oct 2020 00:25:06 +0800 Subject: Revert "arm: sun8i: orangepi-pc-plus: Set EMAC activity LEDs to active high" This reverts commit 75ee680cbd2e4d0156b94f9fec50076361ab12f2. Turns out the activity and link LEDs on the RJ45 port are active low, just like on the Orange Pi PC. Revert the commit that says otherwise. Fixes: 75ee680cbd2e ("arm: sun8i: orangepi-pc-plus: Set EMAC activity LEDs to active high") Fixes: 4904337fe34f ("ARM: dts: sunxi: Restore EMAC changes (boards)") Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard Tested-by: Jernej Skrabec Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20201024162515.30032-1-wens@kernel.org --- arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts index 71fb73208939..babf4cf1b2f6 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts @@ -53,11 +53,6 @@ }; }; -&emac { - /* LEDs changed to active high on the plus */ - /delete-property/ allwinner,leds-active-low; -}; - &mmc1 { vmmc-supply = <®_vcc3v3>; bus-width = <4>; -- cgit v1.2.3 From e76724153f5b4539802cc21b2c6131058668a1c6 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sun, 25 Oct 2020 00:25:07 +0800 Subject: ARM: dts: sun6i: a31-hummingbird: Enable RGMII RX/TX delay on Ethernet PHY The Ethernet PHY on the A31 Hummingbird has the RX and TX delays enabled on the PHY, using pull-ups on the RXDLY and TXDLY pins. Fix the phy-mode description to correct reflect this so that the implementation doesn't reconfigure the delays incorrectly. This happened with commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config"). Fixes: c220aec2bb79 ("ARM: dts: sun6i: Add Merrii A31 Hummingbird support") Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20201024162515.30032-2-wens@kernel.org --- arch/arm/boot/dts/sun6i-a31-hummingbird.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts index 049e6ab3cf56..73de34ae37fd 100644 --- a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts +++ b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts @@ -154,7 +154,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; -- cgit v1.2.3 From 353c3de1303fc93032164402c0eb8550ecd6f154 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sun, 25 Oct 2020 00:25:08 +0800 Subject: ARM: dts: sun7i: cubietruck: Enable RGMII RX/TX delay on Ethernet PHY MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Ethernet PHY on the Cubietruck has the RX and TX delays enabled on the PHY, using pull-ups on the RXDLY and TXDLY pins. Fix the phy-mode description to correct reflect this so that the implementation doesn't reconfigure the delays incorrectly. This happened with commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config"). Fixes: 67073d97672d ("ARM: dts: sun7i: cubietruck: Enable the GMAC") Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard Tested-by: Emilio López Reviewed-by: Emilio López Link: https://lore.kernel.org/r/20201024162515.30032-3-wens@kernel.org --- arch/arm/boot/dts/sun7i-a20-cubietruck.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts index 8c8dee6ea461..9109ca0919ad 100644 --- a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts +++ b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts @@ -151,7 +151,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; -- cgit v1.2.3 From f94f78bd93f567c022f594589dbeecdf59931365 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sun, 25 Oct 2020 00:25:09 +0800 Subject: ARM: dts: sun7i: bananapi-m1-plus: Enable RGMII RX/TX delay on Ethernet PHY The Ethernet PHY on the Bananapi M1+ has the RX and TX delays enabled on the PHY, using pull-ups on the RXDLY and TXDLY pins. Fix the phy-mode description to correct reflect this so that the implementation doesn't reconfigure the delays incorrectly. This happened with commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config"). Fixes: 04c85ecad32a ("ARM: dts: sun7i: Add dts file for Bananapi M1 Plus board") Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20201024162515.30032-4-wens@kernel.org --- arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts index 32d5d45a35c0..8945dbb114a2 100644 --- a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts +++ b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts @@ -130,7 +130,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_gmac_3v3>; status = "okay"; }; -- cgit v1.2.3 From e080ab31a0aa126b0a7e4f67f2b01b371b852c88 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sun, 25 Oct 2020 00:25:10 +0800 Subject: ARM: dts: sun8i: h3: orangepi-plus2e: Enable RGMII RX/TX delay on Ethernet PHY The Ethernet PHY on the Orange Pi Plus 2E has the RX and TX delays enabled on the PHY, using pull-ups on the RXDLY and TXDLY pins. Fix the phy-mode description to correct reflect this so that the implementation doesn't reconfigure the delays incorrectly. This happened with commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config"). Fixes: 4904337fe34f ("ARM: dts: sunxi: Restore EMAC changes (boards)") Fixes: 7a78ef92cdc5 ("ARM: sun8i: h3: Enable EMAC with external PHY on Orange Pi Plus 2E") Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard Tested-by: Jernej Skrabec Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20201024162515.30032-5-wens@kernel.org --- arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts index 6dbf7b2e0c13..b6ca45d18e51 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts @@ -67,7 +67,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; -- cgit v1.2.3 From 57dbe558457bf4042169bc1f334e3b53a8480a1c Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sun, 25 Oct 2020 00:25:11 +0800 Subject: ARM: dts: sun8i: a83t: Enable both RGMII RX/TX delay on Ethernet PHY The Ethernet PHY on the Bananapi M3 and Cubietruck Plus have the RX and TX delays enabled on the PHY, using pull-ups on the RXDLY and TXDLY pins. Fix the phy-mode description to correct reflect this so that the implementation doesn't reconfigure the delays incorrectly. This happened with commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config"). Fixes: 039359948a4b ("ARM: dts: sun8i: a83t: Enable Ethernet on two boards") Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20201024162515.30032-6-wens@kernel.org --- arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts | 2 +- arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts index 9d34eabba121..431f70234d36 100644 --- a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts +++ b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts @@ -131,7 +131,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_sw>; phy-handle = <&rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; allwinner,rx-delay-ps = <700>; allwinner,tx-delay-ps = <700>; status = "okay"; diff --git a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts index d9be511f054f..d8326a5c681d 100644 --- a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts +++ b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts @@ -183,7 +183,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_dldo4>; phy-handle = <&rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; -- cgit v1.2.3 From b1064037e8ecf09d587b7b4966eebe0c362908e5 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sun, 25 Oct 2020 00:25:12 +0800 Subject: ARM: dts: sun9i: Enable both RGMII RX/TX delay on Ethernet PHY The Ethernet PHY on the Cubieboard 4 and A80 Optimus have the RX and TX delays enabled on the PHY, using pull-ups on the RXDLY and TXDLY pins. Fix the phy-mode description to correct reflect this so that the implementation doesn't reconfigure the delays incorrectly. This happened with commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config"). Fixes: 98048143b7f8 ("ARM: dts: sun9i: cubieboard4: Enable GMAC") Fixes: bc9bd03a44f9 ("ARM: dts: sun9i: a80-optimus: Enable GMAC") Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20201024162515.30032-7-wens@kernel.org --- arch/arm/boot/dts/sun9i-a80-cubieboard4.dts | 2 +- arch/arm/boot/dts/sun9i-a80-optimus.dts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts index d3b337b043a1..484b93df20cb 100644 --- a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts +++ b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts @@ -129,7 +129,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_cldo1>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun9i-a80-optimus.dts b/arch/arm/boot/dts/sun9i-a80-optimus.dts index bbc6335e5631..5c3580d712e4 100644 --- a/arch/arm/boot/dts/sun9i-a80-optimus.dts +++ b/arch/arm/boot/dts/sun9i-a80-optimus.dts @@ -124,7 +124,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_cldo1>; status = "okay"; }; -- cgit v1.2.3 From 3914160ffc0bf762d6d605d4b27036b7b89367ea Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sun, 25 Oct 2020 00:25:13 +0800 Subject: ARM: dts: sunxi: bananapi-m2-plus: Enable RGMII RX/TX delay on Ethernet PHY The Ethernet PHY on the Bananapi M2+ has the RX and TX delays enabled on the PHY, using pull-ups on the RXDLY and TXDLY pins. Fix the phy-mode description to correct reflect this so that the implementation doesn't reconfigure the delays incorrectly. This happened with commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config"). Fixes: 8c7ba536e709 ("ARM: sun8i: bananapi-m2-plus: Enable dwmac-sun8i") Fixes: 4904337fe34f ("ARM: dts: sunxi: Restore EMAC changes (boards)") Fixes: aa8fee415f46 ("ARM: dts: sun8i: h3: Split out non-SoC-specific parts of Bananapi M2 Plus") Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard Tested-by: Jernej Skrabec Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20201024162515.30032-8-wens@kernel.org --- arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi b/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi index 39263e74fbb5..8e5cb3b3fd68 100644 --- a/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi +++ b/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi @@ -126,7 +126,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; -- cgit v1.2.3 From 2bd8570d20c88909b8be3251727a26476b02652c Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sun, 25 Oct 2020 00:25:14 +0800 Subject: arm64: dts: allwinner: h5: libretech-all-h5-cc: Enable RGMII RX/TX delay on PHY The Ethernet PHY on the Libre Computer ALL-H5-CC has the RX and TX delays enabled on the PHY, using pull-ups on the RXDLY and TXDLY pins. Fix the phy-mode description to correct reflect this so that the implementation doesn't reconfigure the delays incorrectly. This happened with commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config"). Fixes: 60d0426d7603 ("arm64: dts: allwinner: h5: Add Libre Computer ALL-H5-CC H5 board") Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20201024162515.30032-9-wens@kernel.org --- arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts index df1b9263ad0e..6e30a564c87f 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts @@ -36,7 +36,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; /delete-property/ allwinner,leds-active-low; status = "okay"; }; -- cgit v1.2.3 From 1a9a8910b2153cd3c4f3f2f8defcb853ead3b1fd Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sun, 25 Oct 2020 00:25:15 +0800 Subject: arm64: dts: allwinner: a64: bananapi-m64: Enable RGMII RX/TX delay on PHY The Ethernet PHY on the Bananapi M64 has the RX and TX delays enabled on the PHY, using pull-ups on the RXDLY and TXDLY pins. Fix the phy-mode description to correct reflect this so that the implementation doesn't reconfigure the delays incorrectly. This happened with commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config"). Fixes: e7295499903d ("arm64: allwinner: bananapi-m64: Enable dwmac-sun8i") Fixes: 94f442886711 ("arm64: dts: allwinner: A64: Restore EMAC changes") Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard Tested-by: Corentin Labbe Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20201024162515.30032-10-wens@kernel.org --- arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts index 3ea5182ca489..e5e840b9fbb4 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts @@ -105,7 +105,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_dc1sw>; status = "okay"; -- cgit v1.2.3 From 33b6c39e747c552fa770eecebd1776f1f4a222b1 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 26 Oct 2020 17:10:09 -0700 Subject: Input: adxl34x - clean up a data type in adxl34x_probe() The "revid" is used to store negative error codes so it should be an int type. Fixes: e27c729219ad ("Input: add driver for ADXL345/346 Digital Accelerometers") Signed-off-by: Dan Carpenter Acked-by: Michael Hennerich Link: https://lore.kernel.org/r/20201026072824.GA1620546@mwanda Signed-off-by: Dmitry Torokhov --- drivers/input/misc/adxl34x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/misc/adxl34x.c b/drivers/input/misc/adxl34x.c index 5fe92d4ba3f0..4cc4e8ff42b3 100644 --- a/drivers/input/misc/adxl34x.c +++ b/drivers/input/misc/adxl34x.c @@ -696,7 +696,7 @@ struct adxl34x *adxl34x_probe(struct device *dev, int irq, struct input_dev *input_dev; const struct adxl34x_platform_data *pdata; int err, range, i; - unsigned char revid; + int revid; if (!irq) { dev_err(dev, "no IRQ?\n"); -- cgit v1.2.3 From b1884583fcd17d6a1b1bba94bbb5826e6b5c6e17 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 26 Oct 2020 20:53:57 -0700 Subject: Input: i8042 - allow insmod to succeed on devices without an i8042 controller The i8042 module exports several symbols which may be used by other modules. Before this commit it would refuse to load (when built as a module itself) on systems without an i8042 controller. This is a problem specifically for the asus-nb-wmi module. Many Asus laptops support the Asus WMI interface. Some of them have an i8042 controller and need to use i8042_install_filter() to filter some kbd events. Other models do not have an i8042 controller (e.g. they use an USB attached kbd). Before this commit the asus-nb-wmi driver could not be loaded on Asus models without an i8042 controller, when the i8042 code was built as a module (as Arch Linux does) because the module_init function of the i8042 module would fail with -ENODEV and thus the i8042_install_filter symbol could not be loaded. This commit fixes this by exiting from module_init with a return code of 0 if no controller is found. It also adds a i8042_present bool to make the module_exit function a no-op in this case and also adds a check for i8042_present to the exported i8042_command function. The latter i8042_present check should not really be necessary because when builtin that function can already be used on systems without an i8042 controller, but better safe then sorry. Reported-and-tested-by: Marius Iacob Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20201008112628.3979-2-hdegoede@redhat.com Signed-off-by: Dmitry Torokhov --- drivers/input/serio/i8042.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index d3eda48032e3..944cbb519c6d 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -122,6 +122,7 @@ module_param_named(unmask_kbd_data, i8042_unmask_kbd_data, bool, 0600); MODULE_PARM_DESC(unmask_kbd_data, "Unconditional enable (may reveal sensitive data) of normally sanitize-filtered kbd data traffic debug log [pre-condition: i8042.debug=1 enabled]"); #endif +static bool i8042_present; static bool i8042_bypass_aux_irq_test; static char i8042_kbd_firmware_id[128]; static char i8042_aux_firmware_id[128]; @@ -343,6 +344,9 @@ int i8042_command(unsigned char *param, int command) unsigned long flags; int retval; + if (!i8042_present) + return -1; + spin_lock_irqsave(&i8042_lock, flags); retval = __i8042_command(param, command); spin_unlock_irqrestore(&i8042_lock, flags); @@ -1612,12 +1616,15 @@ static int __init i8042_init(void) err = i8042_platform_init(); if (err) - return err; + return (err == -ENODEV) ? 0 : err; err = i8042_controller_check(); if (err) goto err_platform_exit; + /* Set this before creating the dev to allow i8042_command to work right away */ + i8042_present = true; + pdev = platform_create_bundle(&i8042_driver, i8042_probe, NULL, 0, NULL, 0); if (IS_ERR(pdev)) { err = PTR_ERR(pdev); @@ -1636,6 +1643,9 @@ static int __init i8042_init(void) static void __exit i8042_exit(void) { + if (!i8042_present) + return; + platform_device_unregister(i8042_platform_device); platform_driver_unregister(&i8042_driver); i8042_platform_exit(); -- cgit v1.2.3 From 294a3317bef52b189139c813b50dd14d344fa9ec Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 28 Oct 2020 08:03:17 +0200 Subject: ARM: OMAP2+: Manage MPU state properly for omap_enter_idle_coupled() Based on more testing, commit 8ca5ee624b4c ("ARM: OMAP2+: Restore MPU power domain if cpu_cluster_pm_enter() fails") is a poor fix for handling cpu_cluster_pm_enter() returned errors. We should not override the cpuidle states with a hardcoded PWRDM_POWER_ON value. Instead, we should use a configured idle state that does not cause the context to be lost. Otherwise we end up configuring a potentially improper state for the MPUSS. We also want to update the returned state index for the selected state. Let's just select the highest power idle state C1 to ensure no context loss is allowed on cpu_cluster_pm_enter() errors. With these changes we can now unconditionally call omap4_enter_lowpower() for WFI like we did earlier before commit 55be2f50336f ("ARM: OMAP2+: Handle errors for cpu_pm"). And we can return the selected state index. Fixes: 8f04aea048d5 ("ARM: OMAP2+: Restore MPU power domain if cpu_cluster_pm_enter() fails") Fixes: 55be2f50336f ("ARM: OMAP2+: Handle errors for cpu_pm") Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/cpuidle44xx.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index a92d277f81a0..c8d317fafe2e 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -175,8 +175,11 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, if (mpuss_can_lose_context) { error = cpu_cluster_pm_enter(); if (error) { - omap_set_pwrdm_state(mpu_pd, PWRDM_POWER_ON); - goto cpu_cluster_pm_out; + index = 0; + cx = state_ptr + index; + pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state); + omap_set_pwrdm_state(mpu_pd, cx->mpu_state); + mpuss_can_lose_context = 0; } } } @@ -184,7 +187,6 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, omap4_enter_lowpower(dev->cpu, cx->cpu_state); cpu_done[dev->cpu] = true; -cpu_cluster_pm_out: /* Wakeup CPU1 only if it is not offlined */ if (dev->cpu == 0 && cpumask_test_cpu(1, cpu_online_mask)) { -- cgit v1.2.3 From 31b4d8e172f614adc53ddecb4b6b2f6411a49b84 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 23 Oct 2020 12:44:40 -0700 Subject: MIPS: export has_transparent_hugepage() for modules MIPS should export its local version of "has_transparent_hugepage" so that loadable modules (dax) can use it. Fixes this build error: ERROR: modpost: "has_transparent_hugepage" [drivers/dax/dax.ko] undefined! Fixes: fd8cfd300019 ("arch: fix has_transparent_hugepage()") Reported-by: kernel test robot Signed-off-by: Randy Dunlap Cc: Thomas Bogendoerfer Cc: linux-mips@vger.kernel.org Cc: Dan Williams Cc: Vishal Verma Cc: Dave Jiang Cc: linux-nvdimm@lists.01.org Cc: Hugh Dickins Cc: Andrew Morton Signed-off-by: Thomas Bogendoerfer --- arch/mips/mm/tlb-r4k.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index 38e2894d5fa3..1b939abbe4ca 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -438,6 +438,7 @@ int has_transparent_hugepage(void) } return mask == PM_HUGE_MASK; } +EXPORT_SYMBOL(has_transparent_hugepage); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -- cgit v1.2.3 From 484f910e93b48c1d8890d8330a87e34ae61f4782 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Tue, 27 Oct 2020 14:34:09 -0700 Subject: dmaengine: idxd: fix wq config registers offset programming DSA spec v1.1 [1] updated to include a stride size register for WQ configuration that will specify how much space is reserved for the WQ configuration register set. This change is expected to be in the final gen1 DSA hardware. Fix the driver to use WQCFG_OFFSET() for all WQ offset calculation and fixup WQCFG_OFFSET() to use the new calculated wq size. [1]: https://software.intel.com/content/www/us/en/develop/download/intel-data-streaming-accelerator-preliminary-architecture-specification.html Fixes: bfe1d56091c1 ("dmaengine: idxd: Init and probe for Intel data accelerators") Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/160383444959.48058.14249265538404901781.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/device.c | 29 ++++++++++++++--------------- drivers/dma/idxd/idxd.h | 3 ++- drivers/dma/idxd/init.c | 5 +++++ drivers/dma/idxd/registers.h | 23 ++++++++++++++++++++++- 4 files changed, 43 insertions(+), 17 deletions(-) diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 200b9109cacf..506ac85c4a7f 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -295,7 +295,7 @@ void idxd_wq_disable_cleanup(struct idxd_wq *wq) int i, wq_offset; lockdep_assert_held(&idxd->dev_lock); - memset(&wq->wqcfg, 0, sizeof(wq->wqcfg)); + memset(wq->wqcfg, 0, idxd->wqcfg_size); wq->type = IDXD_WQT_NONE; wq->size = 0; wq->group = NULL; @@ -304,8 +304,8 @@ void idxd_wq_disable_cleanup(struct idxd_wq *wq) clear_bit(WQ_FLAG_DEDICATED, &wq->flags); memset(wq->name, 0, WQ_NAME_SIZE); - for (i = 0; i < 8; i++) { - wq_offset = idxd->wqcfg_offset + wq->id * 32 + i * sizeof(u32); + for (i = 0; i < WQCFG_STRIDES(idxd); i++) { + wq_offset = WQCFG_OFFSET(idxd, wq->id, i); iowrite32(0, idxd->reg_base + wq_offset); dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n", wq->id, i, wq_offset, @@ -539,10 +539,10 @@ static int idxd_wq_config_write(struct idxd_wq *wq) if (!wq->group) return 0; - memset(&wq->wqcfg, 0, sizeof(union wqcfg)); + memset(wq->wqcfg, 0, idxd->wqcfg_size); /* byte 0-3 */ - wq->wqcfg.wq_size = wq->size; + wq->wqcfg->wq_size = wq->size; if (wq->size == 0) { dev_warn(dev, "Incorrect work queue size: 0\n"); @@ -550,22 +550,21 @@ static int idxd_wq_config_write(struct idxd_wq *wq) } /* bytes 4-7 */ - wq->wqcfg.wq_thresh = wq->threshold; + wq->wqcfg->wq_thresh = wq->threshold; /* byte 8-11 */ - wq->wqcfg.priv = !!(wq->type == IDXD_WQT_KERNEL); - wq->wqcfg.mode = 1; - - wq->wqcfg.priority = wq->priority; + wq->wqcfg->priv = !!(wq->type == IDXD_WQT_KERNEL); + wq->wqcfg->mode = 1; + wq->wqcfg->priority = wq->priority; /* bytes 12-15 */ - wq->wqcfg.max_xfer_shift = ilog2(wq->max_xfer_bytes); - wq->wqcfg.max_batch_shift = ilog2(wq->max_batch_size); + wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes); + wq->wqcfg->max_batch_shift = ilog2(wq->max_batch_size); dev_dbg(dev, "WQ %d CFGs\n", wq->id); - for (i = 0; i < 8; i++) { - wq_offset = idxd->wqcfg_offset + wq->id * 32 + i * sizeof(u32); - iowrite32(wq->wqcfg.bits[i], idxd->reg_base + wq_offset); + for (i = 0; i < WQCFG_STRIDES(idxd); i++) { + wq_offset = WQCFG_OFFSET(idxd, wq->id, i); + iowrite32(wq->wqcfg->bits[i], idxd->reg_base + wq_offset); dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n", wq->id, i, wq_offset, ioread32(idxd->reg_base + wq_offset)); diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index c64df197e724..d48f193daacc 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -103,7 +103,7 @@ struct idxd_wq { u32 priority; enum idxd_wq_state state; unsigned long flags; - union wqcfg wqcfg; + union wqcfg *wqcfg; u32 vec_ptr; /* interrupt steering */ struct dsa_hw_desc **hw_descs; int num_descs; @@ -183,6 +183,7 @@ struct idxd_device { int max_wq_size; int token_limit; int nr_tokens; /* non-reserved tokens */ + unsigned int wqcfg_size; union sw_err_reg sw_err; wait_queue_head_t cmd_waitq; diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 11e5ce168177..0a4432b063b5 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -178,6 +178,9 @@ static int idxd_setup_internals(struct idxd_device *idxd) wq->idxd_cdev.minor = -1; wq->max_xfer_bytes = idxd->max_xfer_bytes; wq->max_batch_size = idxd->max_batch_size; + wq->wqcfg = devm_kzalloc(dev, idxd->wqcfg_size, GFP_KERNEL); + if (!wq->wqcfg) + return -ENOMEM; } for (i = 0; i < idxd->max_engines; i++) { @@ -251,6 +254,8 @@ static void idxd_read_caps(struct idxd_device *idxd) dev_dbg(dev, "total workqueue size: %u\n", idxd->max_wq_size); idxd->max_wqs = idxd->hw.wq_cap.num_wqs; dev_dbg(dev, "max workqueues: %u\n", idxd->max_wqs); + idxd->wqcfg_size = 1 << (idxd->hw.wq_cap.wqcfg_size + IDXD_WQCFG_MIN); + dev_dbg(dev, "wqcfg size: %u\n", idxd->wqcfg_size); /* reading operation capabilities */ for (i = 0; i < 4; i++) { diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index a39e7ae6b3d9..aef5a902829e 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -43,7 +43,8 @@ union wq_cap_reg { struct { u64 total_wq_size:16; u64 num_wqs:8; - u64 rsvd:24; + u64 wqcfg_size:4; + u64 rsvd:20; u64 shared_mode:1; u64 dedicated_mode:1; u64 rsvd2:1; @@ -55,6 +56,7 @@ union wq_cap_reg { u64 bits; } __packed; #define IDXD_WQCAP_OFFSET 0x20 +#define IDXD_WQCFG_MIN 5 union group_cap_reg { struct { @@ -333,4 +335,23 @@ union wqcfg { }; u32 bits[8]; } __packed; + +/* + * This macro calculates the offset into the WQCFG register + * idxd - struct idxd * + * n - wq id + * ofs - the index of the 32b dword for the config register + * + * The WQCFG register block is divided into groups per each wq. The n index + * allows us to move to the register group that's for that particular wq. + * Each register is 32bits. The ofs gives us the number of register to access. + */ +#define WQCFG_OFFSET(_idxd_dev, n, ofs) \ +({\ + typeof(_idxd_dev) __idxd_dev = (_idxd_dev); \ + (__idxd_dev)->wqcfg_offset + (n) * (__idxd_dev)->wqcfg_size + sizeof(u32) * (ofs); \ +}) + +#define WQCFG_STRIDES(_idxd_dev) ((_idxd_dev)->wqcfg_size / sizeof(u32)) + #endif -- cgit v1.2.3 From 768664114b1ac9184f1dc6217d9c930a08ffbfa8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 26 Oct 2020 17:01:15 +0100 Subject: dmaengine: ti: k3-udma: fix -Wenum-conversion warning gcc warns about a mismatch argument type when passing 'false' into a function that expects an enum: drivers/dma/ti/k3-udma-private.c: In function 'xudma_tchan_get': drivers/dma/ti/k3-udma-private.c:86:34: warning: implicit conversion from 'enum ' to 'enum udma_tp_level' [-Wenum-conversion] 86 | return __udma_reserve_##res(ud, false, id); \ | ^~~~~ drivers/dma/ti/k3-udma-private.c:95:1: note: in expansion of macro 'XUDMA_GET_PUT_RESOURCE' 95 | XUDMA_GET_PUT_RESOURCE(tchan); | ^~~~~~~~~~~~~~~~~~~~~~ In this case, false has the same numerical value as UDMA_TP_NORMAL, so passing that is most likely the correct way to avoid the warning without changing the behavior. Fixes: d70241913413 ("dmaengine: ti: k3-udma: Add glue layer for non DMAengine users") Signed-off-by: Arnd Bergmann Acked-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20201026160123.3704531-1-arnd@kernel.org Signed-off-by: Vinod Koul --- drivers/dma/ti/k3-udma-private.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c index aa24e554f7b4..8563a392f30b 100644 --- a/drivers/dma/ti/k3-udma-private.c +++ b/drivers/dma/ti/k3-udma-private.c @@ -83,7 +83,7 @@ EXPORT_SYMBOL(xudma_rflow_is_gp); #define XUDMA_GET_PUT_RESOURCE(res) \ struct udma_##res *xudma_##res##_get(struct udma_dev *ud, int id) \ { \ - return __udma_reserve_##res(ud, false, id); \ + return __udma_reserve_##res(ud, UDMA_TP_NORMAL, id); \ } \ EXPORT_SYMBOL(xudma_##res##_get); \ \ -- cgit v1.2.3 From 209c805835b29495cf66cc705b206da8f4a68e6e Mon Sep 17 00:00:00 2001 From: Al Cooper Date: Fri, 2 Oct 2020 15:01:15 -0400 Subject: phy: usb: Fix incorrect clearing of tca_drv_sel bit in SETUP reg for 7211 The 7211a0 has a tca_drv_sel bit in the USB SETUP register that should never be enabled. This feature is only used if there is a USB Type-C PHY, and the 7211 does not have one. If the bit is enabled, the VBUS signal will never be asserted. In the 7211a0, the bit was incorrectly defaulted to on so the driver had to clear the bit. In the 7211c0 the state was inverted so the driver should no longer clear the bit. This hasn't been a problem because all current 7211 boards don't use the VBUS signal, but there are some future customer boards that may use it. Signed-off-by: Al Cooper Acked-by: Florian Fainelli Link: https://lore.kernel.org/r/20201002190115.48017-1-alcooperx@gmail.com Signed-off-by: Vinod Koul --- drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c index 456dc4a100c2..e63457e145c7 100644 --- a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c +++ b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c @@ -270,11 +270,6 @@ static void usb_init_common_7211b0(struct brcm_usb_init_params *params) reg |= params->mode << USB_PHY_UTMI_CTL_1_PHY_MODE_SHIFT; brcm_usb_writel(reg, usb_phy + USB_PHY_UTMI_CTL_1); - /* Fix the incorrect default */ - reg = brcm_usb_readl(ctrl + USB_CTRL_SETUP); - reg &= ~USB_CTRL_SETUP_tca_drv_sel_MASK; - brcm_usb_writel(reg, ctrl + USB_CTRL_SETUP); - usb_init_common(params); /* -- cgit v1.2.3 From eb9c4dd9bdfdebaa13846c16a8c79b5b336066b6 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 13 Oct 2020 10:58:20 +0100 Subject: phy: tegra: xusb: Fix dangling pointer on probe failure If, for some reason, the xusb PHY fails to probe, it leaves a dangling pointer attached to the platform device structure. This would normally be harmless, but the Tegra XHCI driver then goes and extract that pointer from the PHY device. Things go downhill from there: 8.752082] [004d554e5145533c] address between user and kernel address ranges [ 8.752085] Internal error: Oops: 96000004 [#1] PREEMPT SMP [ 8.752088] Modules linked in: max77620_regulator(E+) xhci_tegra(E+) sdhci_tegra(E+) xhci_hcd(E) sdhci_pltfm(E) cqhci(E) fixed(E) usbcore(E) scsi_mod(E) sdhci(E) host1x(E+) [ 8.752103] CPU: 4 PID: 158 Comm: systemd-udevd Tainted: G S W E 5.9.0-rc7-00298-gf6337624c4fe #1980 [ 8.752105] Hardware name: NVIDIA Jetson TX2 Developer Kit (DT) [ 8.752108] pstate: 20000005 (nzCv daif -PAN -UAO BTYPE=--) [ 8.752115] pc : kobject_put+0x1c/0x21c [ 8.752120] lr : put_device+0x20/0x30 [ 8.752121] sp : ffffffc012eb3840 [ 8.752122] x29: ffffffc012eb3840 x28: ffffffc010e82638 [ 8.752125] x27: ffffffc008d56440 x26: 0000000000000000 [ 8.752128] x25: ffffff81eb508200 x24: 0000000000000000 [ 8.752130] x23: ffffff81eb538800 x22: 0000000000000000 [ 8.752132] x21: 00000000fffffdfb x20: ffffff81eb538810 [ 8.752134] x19: 3d4d554e51455300 x18: 0000000000000020 [ 8.752136] x17: ffffffc008d00270 x16: ffffffc008d00c94 [ 8.752138] x15: 0000000000000004 x14: ffffff81ebd4ae90 [ 8.752140] x13: 0000000000000000 x12: ffffff81eb86a4e8 [ 8.752142] x11: ffffff81eb86a480 x10: ffffff81eb862fea [ 8.752144] x9 : ffffffc01055fb28 x8 : ffffff81eb86a4a8 [ 8.752146] x7 : 0000000000000001 x6 : 0000000000000001 [ 8.752148] x5 : ffffff81dff8bc38 x4 : 0000000000000000 [ 8.752150] x3 : 0000000000000001 x2 : 0000000000000001 [ 8.752152] x1 : 0000000000000002 x0 : 3d4d554e51455300 [ 8.752155] Call trace: [ 8.752157] kobject_put+0x1c/0x21c [ 8.752160] put_device+0x20/0x30 [ 8.752164] tegra_xusb_padctl_put+0x24/0x3c [ 8.752170] tegra_xusb_probe+0x8b0/0xd10 [xhci_tegra] [ 8.752174] platform_drv_probe+0x60/0xb4 [ 8.752176] really_probe+0xf0/0x504 [ 8.752179] driver_probe_device+0x100/0x170 [ 8.752181] device_driver_attach+0xcc/0xd4 [ 8.752183] __driver_attach+0xb0/0x17c [ 8.752185] bus_for_each_dev+0x7c/0xd4 [ 8.752187] driver_attach+0x30/0x3c [ 8.752189] bus_add_driver+0x154/0x250 [ 8.752191] driver_register+0x84/0x140 [ 8.752193] __platform_driver_register+0x54/0x60 [ 8.752197] tegra_xusb_init+0x40/0x1000 [xhci_tegra] [ 8.752201] do_one_initcall+0x54/0x2d0 [ 8.752205] do_init_module+0x68/0x29c [ 8.752207] load_module+0x2178/0x26c0 [ 8.752209] __do_sys_finit_module+0xb0/0x120 [ 8.752211] __arm64_sys_finit_module+0x2c/0x40 [ 8.752215] el0_svc_common.constprop.0+0x80/0x240 [ 8.752218] do_el0_svc+0x30/0xa0 [ 8.752220] el0_svc+0x18/0x50 [ 8.752223] el0_sync_handler+0x90/0x318 [ 8.752225] el0_sync+0x158/0x180 [ 8.752230] Code: a9bd7bfd 910003fd a90153f3 aa0003f3 (3940f000) [ 8.752232] ---[ end trace 90f6c89d62d85ff5 ]--- Reset the pointer on probe failure fixes the issue. Fixes: 53d2a715c2403 ("phy: Add Tegra XUSB pad controller support") Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20201013095820.311376-1-maz@kernel.org Signed-off-by: Vinod Koul --- drivers/phy/tegra/xusb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index de4a46fe1763..ad88d74c1884 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -1242,6 +1242,7 @@ power_down: reset: reset_control_assert(padctl->rst); remove: + platform_set_drvdata(pdev, NULL); soc->ops->remove(padctl); return err; } -- cgit v1.2.3 From fcea94ac6154545dd13b17c947c07f5e0a54c121 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 26 Oct 2020 13:59:42 -0700 Subject: phy: qcom-qmp: Initialize another pointer to NULL This probe function is too complicated and should be refactored. For now let's just set this variable to NULL and keep the static analysis tools happy. Fixes: 52e013d0bffa ("phy: qcom-qmp: Add support for DP in USB3+DP combo phy") Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20201026205942.2861828-1-swboyd@chromium.org Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-qmp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.c b/drivers/phy/qualcomm/phy-qcom-qmp.c index 5d33ad4d06f2..0cda16846962 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp.c @@ -3926,7 +3926,7 @@ static int qcom_qmp_phy_probe(struct platform_device *pdev) struct phy_provider *phy_provider; void __iomem *serdes; void __iomem *usb_serdes; - void __iomem *dp_serdes; + void __iomem *dp_serdes = NULL; const struct qmp_phy_combo_cfg *combo_cfg = NULL; const struct qmp_phy_cfg *cfg = NULL; const struct qmp_phy_cfg *usb_cfg = NULL; -- cgit v1.2.3 From 25d76fed7ffecca47be0249a5d5ec0a5dd92af67 Mon Sep 17 00:00:00 2001 From: Zou Wei Date: Wed, 28 Oct 2020 16:59:09 +0800 Subject: phy: cpcap-usb: Use IRQF_ONESHOT Fixes coccicheck error: ./drivers/phy/motorola/phy-cpcap-usb.c:365:9-34: ERROR: Threaded IRQ with no primary handler requested without IRQF_ONESHOT Reported-by: Hulk Robot Signed-off-by: Zou Wei Link: https://lore.kernel.org/r/1603875549-107500-1-git-send-email-zou_wei@huawei.com Signed-off-by: Vinod Koul --- drivers/phy/motorola/phy-cpcap-usb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/phy/motorola/phy-cpcap-usb.c b/drivers/phy/motorola/phy-cpcap-usb.c index 089db0dea703..442522ba487f 100644 --- a/drivers/phy/motorola/phy-cpcap-usb.c +++ b/drivers/phy/motorola/phy-cpcap-usb.c @@ -364,7 +364,8 @@ static int cpcap_usb_init_irq(struct platform_device *pdev, error = devm_request_threaded_irq(ddata->dev, irq, NULL, cpcap_phy_irq_thread, - IRQF_SHARED, + IRQF_SHARED | + IRQF_ONESHOT, name, ddata); if (error) { dev_err(ddata->dev, "could not get irq %s: %i\n", -- cgit v1.2.3 From 424f5ca7c8515a4b6e3b0812899ddda082f42fd5 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 16 Oct 2020 17:15:25 +0200 Subject: MAINTAINERS: move Kamil Debski to credits Kamil Debski has not been active on LKML since 2017: https://lore.kernel.org/lkml/?q=f%3A%22Kamil+Debski%22 Move Kamil Debski to the CREDITS file. Thank you for the effort you put in to the upstream Linux kernel work. Signed-off-by: Krzysztof Kozlowski Acked-by: Mauro Carvalho Chehab Cc: Kamil Debski Cc: Andrzej Hajda Cc: Bartlomiej Zolnierkiewicz Cc: Sylwester Nawrocki Link: https://lore.kernel.org/r/20201016151528.7553-1-krzk@kernel.org --- CREDITS | 6 ++++++ MAINTAINERS | 4 ---- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/CREDITS b/CREDITS index cb02b9923a52..f95e46f7a428 100644 --- a/CREDITS +++ b/CREDITS @@ -849,6 +849,12 @@ D: trivial hack to add variable address length routing to Rose. D: AX25-HOWTO, HAM-HOWTO, IPX-HOWTO, NET-2-HOWTO D: ax25-utils maintainer. +N: Kamil Debski +E: kamil@wypas.org +D: Samsung S5P 2D graphics acceleration and Multi Format Codec drivers +D: Samsung USB2 phy drivers +D: PWM fan driver + N: Helge Deller E: deller@gmx.de W: http://www.parisc-linux.org/ diff --git a/MAINTAINERS b/MAINTAINERS index e73636b75f29..b8ce3f209144 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2412,7 +2412,6 @@ F: arch/arm/mach-s5pv210/ ARM/SAMSUNG S5P SERIES 2D GRAPHICS ACCELERATION (G2D) SUPPORT M: Kyungmin Park -M: Kamil Debski M: Andrzej Hajda L: linux-arm-kernel@lists.infradead.org L: linux-media@vger.kernel.org @@ -2438,7 +2437,6 @@ F: drivers/media/platform/s5p-jpeg/ ARM/SAMSUNG S5P SERIES Multi Format Codec (MFC) SUPPORT M: Kyungmin Park -M: Kamil Debski M: Jeongtae Park M: Andrzej Hajda L: linux-arm-kernel@lists.infradead.org @@ -14230,7 +14228,6 @@ F: drivers/media/usb/pwc/* F: include/trace/events/pwc.h PWM FAN DRIVER -M: Kamil Debski M: Bartlomiej Zolnierkiewicz L: linux-hwmon@vger.kernel.org S: Supported @@ -15515,7 +15512,6 @@ T: git https://github.com/lmajewski/linux-samsung-thermal.git F: drivers/thermal/samsung/ SAMSUNG USB2 PHY DRIVER -M: Kamil Debski M: Sylwester Nawrocki L: linux-kernel@vger.kernel.org S: Supported -- cgit v1.2.3 From 215f06d7efc263d4e8150e0b97c49dd9914b59d7 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 16 Oct 2020 17:16:17 +0200 Subject: MAINTAINERS: move Kyungmin Park to credits Kyungmin Park maintained and contributed to some of the upstreamed S5Pv210 and Exynos4210 machines - as described in commit 10ffa96407b2 ("MAINTAINERS: add maintainer of Samsung Mobile Machine support"). However the entry in maintainers got slightly twisted by commit 004bbd3c01d4 ("MAINTAINERS: remove non existent files") - the directory matching pattern was changed from specific machines to the entire S5Pv210. Anyway since long time, all S5Pv210 maintenance is covered by the Samsung ARM architectures maintainer entry and Krzysztof Kozlowski, so move Kyungmin Park to the CREDITS. There was also no activity on LKML regarding other maintained drivers: https://lore.kernel.org/lkml/?q=f%3A%22Kyungmin+Park%22 Dear Kyungmin Park, thank you for all the effort you put in to the upstream Samsung support. Signed-off-by: Krzysztof Kozlowski Cc: Kyungmin Park Cc: Andrzej Hajda Cc: Sylwester Nawrocki Cc: Arnd Bergmann Cc: Olof Johansson Link: https://lore.kernel.org/r/20201016151528.7553-1-krzk@kernel.org --- CREDITS | 4 ++++ MAINTAINERS | 13 +------------ 2 files changed, 5 insertions(+), 12 deletions(-) diff --git a/CREDITS b/CREDITS index f95e46f7a428..205ed442b8e6 100644 --- a/CREDITS +++ b/CREDITS @@ -2849,6 +2849,10 @@ D: IPX development and support N: Venkatesh Pallipadi (Venki) D: x86/HPET +N: Kyungmin Park +E: kyungmin.park@samsung.com +D: Samsung S5Pv210 and Exynos4210 mobile platforms + N: David Parsons E: orc@pell.chi.il.us D: improved memory detection code. diff --git a/MAINTAINERS b/MAINTAINERS index b8ce3f209144..f7824667ff9d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2374,7 +2374,7 @@ F: drivers/i2c/busses/i2c-rk3x.c F: sound/soc/rockchip/ N: rockchip -ARM/SAMSUNG EXYNOS ARM ARCHITECTURES +ARM/SAMSUNG S3C, S5P AND EXYNOS ARM ARCHITECTURES M: Kukjin Kim M: Krzysztof Kozlowski L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -2404,14 +2404,7 @@ N: s3c2410 N: s3c64xx N: s5pv210 -ARM/SAMSUNG MOBILE MACHINE SUPPORT -M: Kyungmin Park -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained -F: arch/arm/mach-s5pv210/ - ARM/SAMSUNG S5P SERIES 2D GRAPHICS ACCELERATION (G2D) SUPPORT -M: Kyungmin Park M: Andrzej Hajda L: linux-arm-kernel@lists.infradead.org L: linux-media@vger.kernel.org @@ -2436,7 +2429,6 @@ S: Maintained F: drivers/media/platform/s5p-jpeg/ ARM/SAMSUNG S5P SERIES Multi Format Codec (MFC) SUPPORT -M: Kyungmin Park M: Jeongtae Park M: Andrzej Hajda L: linux-arm-kernel@lists.infradead.org @@ -15438,14 +15430,12 @@ F: Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml F: drivers/nfc/s3fwrn5 SAMSUNG S5C73M3 CAMERA DRIVER -M: Kyungmin Park M: Andrzej Hajda L: linux-media@vger.kernel.org S: Supported F: drivers/media/i2c/s5c73m3/* SAMSUNG S5K5BAF CAMERA DRIVER -M: Kyungmin Park M: Andrzej Hajda L: linux-media@vger.kernel.org S: Supported @@ -15463,7 +15453,6 @@ F: Documentation/devicetree/bindings/crypto/samsung-sss.yaml F: drivers/crypto/s5p-sss.c SAMSUNG S5P/EXYNOS4 SOC SERIES CAMERA SUBSYSTEM DRIVERS -M: Kyungmin Park M: Sylwester Nawrocki L: linux-media@vger.kernel.org S: Supported -- cgit v1.2.3 From d5a69b6ba186d01cb036074d337e5171d27e9c72 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 16 Oct 2020 17:15:27 +0200 Subject: MAINTAINERS: remove Jeongtae Park from Samsung MFC entry Jeongtae Park has not been active on LKML: https://lore.kernel.org/lkml/?q=f%3A%22Jeongtae+Park%22 Remove him from the Samsung S5P MFC driver entry. Signed-off-by: Krzysztof Kozlowski Cc: Jeongtae Park Cc: Andrzej Hajda Link: https://lore.kernel.org/r/20201016151528.7553-3-krzk@kernel.org --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index f7824667ff9d..40b4a582b4cc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2429,7 +2429,6 @@ S: Maintained F: drivers/media/platform/s5p-jpeg/ ARM/SAMSUNG S5P SERIES Multi Format Codec (MFC) SUPPORT -M: Jeongtae Park M: Andrzej Hajda L: linux-arm-kernel@lists.infradead.org L: linux-media@vger.kernel.org -- cgit v1.2.3 From cd12e4f14f7cca7d04fbcf0da2dc116070d7f26f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 16 Oct 2020 17:15:28 +0200 Subject: CREDITS: remove trailing white spaces Remove trailing white spaces. No functional/substantive change. Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20201016151528.7553-4-krzk@kernel.org --- CREDITS | 52 ++++++++++++++++++++++++++-------------------------- 1 file changed, 26 insertions(+), 26 deletions(-) diff --git a/CREDITS b/CREDITS index 205ed442b8e6..b11224ae7235 100644 --- a/CREDITS +++ b/CREDITS @@ -98,7 +98,7 @@ N: Erik Andersen E: andersen@codepoet.org W: https://www.codepoet.org/ P: 1024D/30D39057 1BC4 2742 E885 E4DE 9301 0C82 5F9B 643E 30D3 9057 -D: Maintainer of ide-cd and Uniform CD-ROM driver, +D: Maintainer of ide-cd and Uniform CD-ROM driver, D: ATAPI CD-Changer support, Major 2.1.x CD-ROM update. S: 352 North 525 East S: Springville, Utah 84663 @@ -263,7 +263,7 @@ N: Paul Barton-Davis E: pbd@op.net D: Driver for WaveFront soundcards (Turtle Beach Maui, Tropez, Tropez+) D: Various bugfixes and changes to sound drivers -S: USA +S: USA N: Carlos Henrique Bauer E: chbauer@acm.org @@ -1205,7 +1205,7 @@ N: Daniel J. Frasnelli E: dfrasnel@alphalinux.org W: http://www.alphalinux.org/ P: 1024/3EF87611 B9 F1 44 50 D3 E8 C2 80 DA E5 55 AA 56 7C 42 DA -D: DEC Alpha hacker +D: DEC Alpha hacker D: Miscellaneous bug squisher N: Jim Freeman @@ -1305,7 +1305,7 @@ S: P.O. Box 76, Epping S: New South Wales, 2121 S: Australia -N: Carlos E. Gorges +N: Carlos E. Gorges E: carlos@techlinux.com.br D: fix smp support on cmpci driver P: 2048G/EA3C4B19 FF31 33A6 0362 4915 B7EB E541 17D0 0379 EA3C 4B19 @@ -1346,7 +1346,7 @@ E: wgreathouse@smva.com E: wgreathouse@myfavoritei.com D: Current Belkin USB Serial Adapter F5U103 hacker D: Kernel hacker, embedded systems -S: 7802 Fitzwater Road +S: 7802 Fitzwater Road S: Brecksville, OH 44141-1334 S: USA @@ -1387,7 +1387,7 @@ N: Grant Guenther E: grant@torque.net W: http://www.torque.net/linux-pp.html D: original author of ppa driver for parallel port ZIP drive -D: original architect of the parallel-port sharing scheme +D: original architect of the parallel-port sharing scheme D: PARIDE subsystem: drivers for parallel port IDE & ATAPI devices S: 44 St. Joseph Street, Suite 506 S: Toronto, Ontario, M4Y 2W4 @@ -1529,7 +1529,7 @@ N: Benjamin Herrenschmidt E: benh@kernel.crashing.org D: Various parts of PPC/PPC64 & PowerMac S: 312/107 Canberra Avenue -S: Griffith, ACT 2603 +S: Griffith, ACT 2603 S: Australia N: Andreas Herrmann @@ -1831,7 +1831,7 @@ S: Hungary N: Bernhard Kaindl E: bkaindl@netway.at E: edv@bartelt.via.at -D: Author of a menu based configuration tool, kmenu, which +D: Author of a menu based configuration tool, kmenu, which D: is the predecessor of 'make menuconfig' and 'make xconfig'. D: digiboard driver update(modularisation work and 2.1.x upd) S: Tallak 95 @@ -2013,7 +2013,7 @@ W: http://www.xos.nl/ D: IP transparent proxy support S: X/OS Experts in Open Systems BV S: Kruislaan 419 -S: 1098 VA Amsterdam +S: 1098 VA Amsterdam S: The Netherlands N: Goran Koruga @@ -2085,7 +2085,7 @@ S: Germany N: Andrzej M. Krzysztofowicz E: ankry@mif.pg.gda.pl -D: Some 8-bit XT disk driver and devfs hacking +D: Some 8-bit XT disk driver and devfs hacking D: Aladdin 1533/1543(C) chipset IDE D: PIIX chipset IDE S: ul. Matemblewska 1B/10 @@ -2460,7 +2460,7 @@ E: mge@EZ-Darmstadt.Telekom.de D: Logical Volume Manager S: Bartningstr. 12 S: 64289 Darmstadt -S: Germany +S: Germany N: Mark W. McClelland E: mmcclell@bigfoot.com @@ -2544,7 +2544,7 @@ E: meskes@debian.org P: 1024/04B6E8F5 6C 77 33 CA CC D6 22 03 AB AB 15 A3 AE AD 39 7D D: Kernel hacker. PostgreSQL hacker. Software watchdog daemon. D: Maintainer of several Debian packages -S: Th.-Heuss-Str. 61 +S: Th.-Heuss-Str. 61 S: D-41812 Erkelenz S: Germany @@ -2782,7 +2782,7 @@ E: neuffer@goofy.zdv.uni-mainz.de W: http://www.i-Connect.Net/~mike/ D: Developer and maintainer of the EATA-DMA SCSI driver D: Co-developer EATA-PIO SCSI driver -D: /proc/scsi and assorted other snippets +D: /proc/scsi and assorted other snippets S: Zum Schiersteiner Grund 2 S: 55127 Mainz S: Germany @@ -3020,7 +3020,7 @@ D: Embedded PowerPC 4xx/6xx/7xx/74xx support S: Chandler, Arizona 85249 S: USA -N: Frederic Potter +N: Frederic Potter E: fpotter@cirpack.com D: Some PCI kernel support @@ -3453,21 +3453,21 @@ S: Klosterweg 28 / i309 S: 76131 Karlsruhe S: Germany -N: James Simmons +N: James Simmons E: jsimmons@infradead.org -E: jsimmons@users.sf.net +E: jsimmons@users.sf.net D: Frame buffer device maintainer D: input layer development D: tty/console layer -D: various mipsel devices -S: 115 Carmel Avenue +D: various mipsel devices +S: 115 Carmel Avenue S: El Cerrito CA 94530 -S: USA +S: USA N: Jaspreet Singh E: jaspreet@sangoma.com W: www.sangoma.com -D: WANPIPE drivers & API Support for Sangoma S508/FT1 cards +D: WANPIPE drivers & API Support for Sangoma S508/FT1 cards S: Sangoma Technologies Inc., S: 1001 Denison Street S: Suite 101 @@ -3491,7 +3491,7 @@ N: Craig Small E: csmall@triode.apana.org.au E: vk2xlz@gonzo.vk2xlz.ampr.org (packet radio) D: Gracilis PackeTwin device driver -D: RSPF daemon +D: RSPF daemon S: 10 Stockalls Place S: Minto, NSW, 2566 S: Australia @@ -3701,7 +3701,7 @@ N: Tsu-Sheng Tsao E: tsusheng@scf.usc.edu D: IGMP(Internet Group Management Protocol) version 2 S: 2F 14 ALY 31 LN 166 SEC 1 SHIH-PEI RD -S: Taipei +S: Taipei S: Taiwan 112 S: Republic of China S: 24335 Delta Drive @@ -3862,7 +3862,7 @@ D: Produced the Slackware distribution, updated the SVGAlib D: patches for ghostscript, worked on color 'ls', etc. S: 301 15th Street S. S: Moorhead, Minnesota 56560 -S: USA +S: USA N: Jos Vos E: jos@xos.nl @@ -3870,7 +3870,7 @@ W: http://www.xos.nl/ D: Various IP firewall updates, ipfwadm S: X/OS Experts in Open Systems BV S: Kruislaan 419 -S: 1098 VA Amsterdam +S: 1098 VA Amsterdam S: The Netherlands N: Jeroen Vreeken @@ -4108,7 +4108,7 @@ S: People's Repulic of China N: Victor Yodaiken E: yodaiken@fsmlabs.com D: RTLinux (RealTime Linux) -S: POB 1822 +S: POB 1822 S: Socorro NM, 87801 S: USA @@ -4206,7 +4206,7 @@ D: EISA/sysfs subsystem S: France # Don't add your name here, unless you really _are_ after Marc -# alphabetically. Leonard used to be very proud of being the +# alphabetically. Leonard used to be very proud of being the # last entry, and he'll get positively pissed if he can't even # be second-to-last. (and this file really _is_ supposed to be # in alphabetic order) -- cgit v1.2.3 From 107954afc5df667da438644aa4982606663f9b17 Mon Sep 17 00:00:00 2001 From: Nenad Peric Date: Wed, 28 Oct 2020 12:58:17 +0100 Subject: arm64: dts: allwinner: h5: OrangePi Prime: Fix ethernet node RX and TX delay are provided by ethernet PHY. Reflect that in ethernet node. Fixes: 44a94c7ef989 ("arm64: dts: allwinner: H5: Restore EMAC changes") Signed-off-by: Nenad Peric Signed-off-by: Maxime Ripard Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20201028115817.68113-1-nperic@gmail.com --- arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts index cb44bfa5981f..33ab44072e6d 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts @@ -124,7 +124,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; -- cgit v1.2.3 From 5c7e02a896689407555b3a10d6ed87369c70916e Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 26 Oct 2020 16:46:06 +0100 Subject: HID: i2c-hid: Put ACPI enumerated devices in D3 on shutdown The i2c-hid driver would quietly fail to probe the i2c-hid sensor-hub with an ACPI device-id of SMO91D0 every other boot. Specifically, the i2c_smbus_read_byte() "Make sure there is something at this address" check would fail every other boot. It seems that the BIOS does not properly reset/power-cycle the device leaving it in a confused state where it refuses to respond to i2c-xfers. On boots where probing the device failed, the driver-core puts the device in D3 after the probe-failure, which causes the probe to succeed the next boot. Putting the device in D3 from the shutdown-handler fixes the sensors not working every other boot. This has been tested on both a Lenovo Miix 2-10 and a Dell Venue 8 Pro 5830 both of which use an i2c-hid sensor-hub with an ACPI id of SMO91D0. Note that it is safe to call acpi_device_set_power() with a NULL pointer as first argument, so on none ACPI enumerated devices this change is a no-op. Cc: Kai-Heng Feng Signed-off-by: Hans de Goede Acked-by: Kai-Heng Feng Signed-off-by: Jiri Kosina --- drivers/hid/i2c-hid/i2c-hid-core.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 786e3e9af1c9..aeff1ffb0c8b 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -943,6 +943,11 @@ static void i2c_hid_acpi_enable_wakeup(struct device *dev) } } +static void i2c_hid_acpi_shutdown(struct device *dev) +{ + acpi_device_set_power(ACPI_COMPANION(dev), ACPI_STATE_D3_COLD); +} + static const struct acpi_device_id i2c_hid_acpi_match[] = { {"ACPI0C50", 0 }, {"PNP0C50", 0 }, @@ -959,6 +964,8 @@ static inline int i2c_hid_acpi_pdata(struct i2c_client *client, static inline void i2c_hid_acpi_fix_up_power(struct device *dev) {} static inline void i2c_hid_acpi_enable_wakeup(struct device *dev) {} + +static inline void i2c_hid_acpi_shutdown(struct device *dev) {} #endif #ifdef CONFIG_OF @@ -1175,6 +1182,8 @@ static void i2c_hid_shutdown(struct i2c_client *client) i2c_hid_set_power(client, I2C_HID_PWR_SLEEP); free_irq(client->irq, ihid); + + i2c_hid_acpi_shutdown(&client->dev); } #ifdef CONFIG_PM_SLEEP -- cgit v1.2.3 From 00203737867c8b63ca247e71ada1b32bb0b0dd3d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 27 Sep 2020 18:59:42 +0200 Subject: arm64: dts: imx8mm-var-som: fix missing PMIC's interrupt line pull-up The PMIC's interrupt is level low and should be pulled up. The PMIC's device node had pinctrl-0 property but it lacked pinctrl-names which is required to apply the pin configuration. The actual problem in DTS was pointed out by Felix Radensky from Variscite. Reported-by: Felix Radensky Fixes: 5f67317bd967 ("arm64: dts: imx8mm: correct interrupt flags") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Robin Gong Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi index 4107fe914d08..49082529764f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi @@ -135,13 +135,10 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio2>; - /* - * The interrupt is not correct. It should be level low, - * however with internal pull up this causes IRQ storm. - */ - interrupts = <8 IRQ_TYPE_EDGE_RISING>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; rohm,reset-snvs-powered; #clock-cells = <0>; @@ -398,7 +395,7 @@ pinctrl_pmic: pmicirqgrp { fsl,pins = < - MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8 0x41 + MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8 0x141 >; }; -- cgit v1.2.3 From 0710e4385c9c978952333393396061ed1672d145 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 27 Sep 2020 18:59:43 +0200 Subject: arm64: dts: imx8mm-beacon-som: fix missing PMIC's interrupt line pull-up The PMIC's interrupt is level low and should be pulled up. The PMIC's device node had pinctrl-0 property but it lacked pinctrl-names which is required to apply the pin configuration. Fixes: 5f67317bd967 ("arm64: dts: imx8mm: correct interrupt flags") Fixes: 593816fa2f35 ("arm64: dts: imx: Add Beacon i.MX8m-Mini development kit") Signed-off-by: Krzysztof Kozlowski Tested-by: Adam Ford Reviewed-by: Robin Gong Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi index 6de86a4f0ec4..55b36bddd513 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi @@ -72,6 +72,7 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; -- cgit v1.2.3 From ce6fc31f388d45b9f7135169f911cd27f4d21126 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 27 Sep 2020 18:59:44 +0200 Subject: arm64: dts: imx8mm-evk: fix missing PMIC's interrupt line pull-up The PMIC's interrupt is level low and should be pulled up. The PMIC's device node had pinctrl-0 property but it lacked pinctrl-names which is required to apply the pin configuration. Fixes: 5f67317bd967 ("arm64: dts: imx8mm: correct interrupt flags") Fixes: aa71d0648318 ("arm64: dts: imx8mm: Split the imx8mm evk board dts to a common dtsi") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Robin Gong Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi index f305a530ff6f..521eb3a5a12e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi @@ -121,6 +121,7 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; -- cgit v1.2.3 From 34a1c5e39b670fd7a324b5620c9ad4ac80c2f018 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 27 Sep 2020 18:59:45 +0200 Subject: arm64: dts: imx8mn-var-som: fix missing PMIC's interrupt line pull-up The PMIC's interrupt is level low and should be pulled up. The PMIC's device node had pinctrl-0 property but it lacked pinctrl-names which is required to apply the pin configuration. The actual problem in DTS was pointed out by Felix Radensky from Variscite. Reported-by: Felix Radensky Fixes: ade0176dd8a0 ("arm64: dts: imx8mn-var-som: Add Variscite VAR-SOM-MX8MN System on Module") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Robin Gong Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index a2d0190921e4..7f356edf9f91 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -116,13 +116,10 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio2>; - /* - * The interrupt is not correct. It should be level low, - * however with internal pull up this causes IRQ storm. - */ - interrupts = <8 IRQ_TYPE_EDGE_RISING>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; rohm,reset-snvs-powered; regulators { @@ -388,7 +385,7 @@ pinctrl_pmic: pmicirqgrp { fsl,pins = < - MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8 0x101 + MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8 0x141 >; }; -- cgit v1.2.3 From 4d20fa1dac2e3cf5aa0cd317b3436f4fda680b04 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 27 Sep 2020 18:59:46 +0200 Subject: arm64: dts: imx8mn-ddr4-evk: fix missing PMIC's interrupt line pull-up The PMIC's interrupt is level low and should be pulled up. The PMIC's device node had pinctrl-0 property but it lacked pinctrl-names which is required to apply the pin configuration. Fixes: 4153f7811a9b ("arm64: dts: imx8mn: correct interrupt flags") Fixes: 3e44dd09736d ("arm64: dts: imx8mn-ddr4-evk: Add rohm,bd71847 PMIC support") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Robin Gong Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts index 46e76cf32b2f..7dfee715a2c4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts @@ -53,6 +53,7 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; -- cgit v1.2.3 From 6efb099a1da4e954409e241b47257a637120e5c2 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 27 Sep 2020 18:59:47 +0200 Subject: arm64: dts: imx8mn-evk: fix missing PMIC's interrupt line pull-up The PMIC's interrupt is level low and should be pulled up. The PMIC's device node had pinctrl-0 property but it lacked pinctrl-names which is required to apply the pin configuration. Fixes: 4153f7811a9b ("arm64: dts: imx8mn: correct interrupt flags") Fixes: 6386156eb279 ("arm64: dts: imx8mn-evk: add pca9450 for i.mx8mn-evk board") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Robin Gong Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mn-evk.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/freescale/imx8mn-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-evk.dts index 707d8486b4d8..8311b95dee49 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-evk.dts @@ -18,6 +18,7 @@ pmic: pmic@25 { compatible = "nxp,pca9450b"; reg = <0x25>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; -- cgit v1.2.3 From d92454287ee25d78f1caac3734a1864f8a5a5275 Mon Sep 17 00:00:00 2001 From: Biwen Li Date: Tue, 29 Sep 2020 09:30:21 +0800 Subject: arm64: dts: fsl: fix endianness issue of rcpm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add little-endian property to RCPM node (for ls1028a,ls1088a,ls208xa), otherwise RCPM driver will program hardware with incorrect setting, causing system (such as LS1028ARDB) failed to be waked by wakeup source. Fixes: 791c88ca5713 (“arm64: dts: ls1028a: Add ftm_alarm0 DT node”) Fixes: f4fe3a8665495 (“arm64: dts: layerscape: add ftm_alarm0 node”) Signed-off-by: Biwen Li Signed-off-by: Ran Wang Acked-by: Li Yang Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi | 1 + arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi | 1 + arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi | 1 + 3 files changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 73e4f9466887..7a6fb7e1fb82 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -1012,6 +1012,7 @@ compatible = "fsl,ls1028a-rcpm", "fsl,qoriq-rcpm-2.1+"; reg = <0x0 0x1e34040 0x0 0x1c>; #fsl,rcpm-wakeup-cells = <7>; + little-endian; }; ftm_alarm0: timer@2800000 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi index ff5805206a28..692d8f4a206d 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi @@ -805,6 +805,7 @@ compatible = "fsl,ls1088a-rcpm", "fsl,qoriq-rcpm-2.1+"; reg = <0x0 0x1e34040 0x0 0x18>; #fsl,rcpm-wakeup-cells = <6>; + little-endian; }; ftm_alarm0: timer@2800000 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi index bf72918fe545..e7abb74bd816 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi @@ -892,6 +892,7 @@ compatible = "fsl,ls208xa-rcpm", "fsl,qoriq-rcpm-2.1+"; reg = <0x0 0x1e34040 0x0 0x18>; #fsl,rcpm-wakeup-cells = <6>; + little-endian; }; ftm_alarm0: timer@2800000 { -- cgit v1.2.3 From 054b5d97448714ae4a0bcd6f36b0515ac7aed21e Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Mon, 5 Oct 2020 15:46:39 +0300 Subject: arm64: dts: fsl: DPAA FMan DMA operations are coherent Although the DPAA 1 FMan operations are coherent, the device tree node for the FMan does not indicate that, resulting in a needless loss of performance. Adding the missing dma-coherent property. Fixes: 1ffbecdd8321 ("arm64: dts: add DPAA FMan nodes") Signed-off-by: Madalin Bucur Tested-by: Camelia Groza Acked-by: Li Yang Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi index 8bc6caa9167d..4338db14c5da 100644 --- a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi @@ -19,6 +19,7 @@ fman0: fman@1a00000 { clock-names = "fmanclk"; fsl,qman-channel-range = <0x800 0x10>; ptimer-handle = <&ptp_timer0>; + dma-coherent; muram@0 { compatible = "fsl,fman-muram"; -- cgit v1.2.3 From 587258edd94c305077923ec458e04c032fca83e6 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Wed, 7 Oct 2020 08:02:37 -0500 Subject: arm64: dts: imx8mm-beacon-som: Fix Choppy BT audio When streaming bluetooth audio, the sound is choppy due to the fact that the default baud rate of the HCI interface is too slow to handle 16-bit stereo at 48KHz. The Bluetooth chip is capable of up to 4M baud on the serial port, so this patch sets the max-speed to 4000000 in order to properly stream audio over the Bluetooth. Fixes: 593816fa2f35 ("arm64: dts: imx: Add Beacon i.MX8m-Mini development kit") Signed-off-by: Adam Ford Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi index 55b36bddd513..b88c3c99b007 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi @@ -211,6 +211,7 @@ host-wakeup-gpios = <&gpio2 8 GPIO_ACTIVE_HIGH>; device-wakeup-gpios = <&gpio2 7 GPIO_ACTIVE_HIGH>; clocks = <&osc_32k>; + max-speed = <4000000>; clock-names = "extclk"; }; }; -- cgit v1.2.3 From cf5abb0132193767c07c83e06f91b777d22ba495 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Thu, 8 Oct 2020 13:33:00 -0500 Subject: arm64: dts imx8mn: Remove non-existent USB OTG2 According to the i.MX8MN TRM, there is only one OTG port. The address for OTG2 is reserved on Nano. This patch removes the non-existent OTG2, usbphynop2, and the usbmisc2 nodes. Fixes: 6c3debcbae47 ("arm64: dts: freescale: Add i.MX8MN dtsi support") Signed-off-by: Adam Ford Reviewed-by: Krzysztof Kozlowski Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mn.dtsi | 30 ------------------------------ 1 file changed, 30 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index 746faf1cf2fb..16c7202885d7 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -790,28 +790,6 @@ #index-cells = <1>; reg = <0x32e40200 0x200>; }; - - usbotg2: usb@32e50000 { - compatible = "fsl,imx8mn-usb", "fsl,imx7d-usb"; - reg = <0x32e50000 0x200>; - interrupts = ; - clocks = <&clk IMX8MN_CLK_USB1_CTRL_ROOT>; - clock-names = "usb1_ctrl_root_clk"; - assigned-clocks = <&clk IMX8MN_CLK_USB_BUS>, - <&clk IMX8MN_CLK_USB_CORE_REF>; - assigned-clock-parents = <&clk IMX8MN_SYS_PLL2_500M>, - <&clk IMX8MN_SYS_PLL1_100M>; - fsl,usbphy = <&usbphynop2>; - fsl,usbmisc = <&usbmisc2 0>; - status = "disabled"; - }; - - usbmisc2: usbmisc@32e50200 { - compatible = "fsl,imx8mn-usbmisc", "fsl,imx7d-usbmisc"; - #index-cells = <1>; - reg = <0x32e50200 0x200>; - }; - }; dma_apbh: dma-controller@33000000 { @@ -876,12 +854,4 @@ assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>; clock-names = "main_clk"; }; - - usbphynop2: usbphynop2 { - compatible = "usb-nop-xceiv"; - clocks = <&clk IMX8MN_CLK_USB_PHY_REF>; - assigned-clocks = <&clk IMX8MN_CLK_USB_PHY_REF>; - assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>; - clock-names = "main_clk"; - }; }; -- cgit v1.2.3 From b0c0aa7aa4b919e02e0a24aa3a46dfbf2bbc34dc Mon Sep 17 00:00:00 2001 From: David Bauer Date: Mon, 26 Oct 2020 17:27:21 +0100 Subject: arm64: dts: rockchip: fix NanoPi R2S GMAC clock name This commit fixes the name for the GMAC clock to gmac_clkin, as this is the name of the clock provided by the rk3328-clk driver. Without this commit, the GMAC will not work in TX direction. Fixes: f1ec83f880db ("arm64: dts: rockchip: Add support for FriendlyARM NanoPi R2S") Suggested-by: Tobias Waldvogel Signed-off-by: David Bauer Link: https://lore.kernel.org/r/20201026162721.70672-1-mail@david-bauer.net Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts index be7a31d81632..2ee07d15a6e3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts @@ -20,7 +20,7 @@ gmac_clk: gmac-clock { compatible = "fixed-clock"; clock-frequency = <125000000>; - clock-output-names = "gmac_clk"; + clock-output-names = "gmac_clkin"; #clock-cells = <0>; }; -- cgit v1.2.3 From 01fe332800d0d2f94337b45c1973f4cf28ae6195 Mon Sep 17 00:00:00 2001 From: Maciej Matuszczyk Date: Fri, 23 Oct 2020 20:16:29 +0200 Subject: arm64: dts: rockchip: Remove system-power-controller from pmic on Odroid Go Advance This fixes a poweroff issue when this is supposed to happen via PSCI. Signed-off-by: Maciej Matuszczyk Link: https://lore.kernel.org/r/20201023181629.119727-1-maccraft123mc@gmail.com Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts index 35bd6b904b9c..337681038519 100644 --- a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts +++ b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts @@ -243,7 +243,6 @@ interrupts = ; pinctrl-names = "default"; pinctrl-0 = <&pmic_int>; - rockchip,system-power-controller; wakeup-source; #clock-cells = <1>; clock-output-names = "rk808-clkout1", "xin32k"; -- cgit v1.2.3 From 56e4f2dda23c6d39d327944faa89efaa4eb290d1 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 30 Jun 2020 08:37:30 -0700 Subject: iio: cros_ec: Use default frequencies when EC returns invalid information Minimal and maximal frequencies supported by a sensor is queried. On some older machines, these frequencies are not returned properly and the EC returns 0 instead. When returned maximal frequency is 0, ignore the information and use default frequencies instead. Fixes: ae7b02ad2f32 ("iio: common: cros_ec_sensors: Expose cros_ec_sensors frequency range via iio sysfs") Signed-off-by: Gwendal Grignou Reviewed-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20200630153730.3302889-1-gwendal@chromium.org CC: Signed-off-by: Jonathan Cameron --- .../iio/common/cros_ec_sensors/cros_ec_sensors_core.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c index c62cacc04672..e3f507771f17 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c @@ -256,7 +256,7 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, struct cros_ec_sensorhub *sensor_hub = dev_get_drvdata(dev->parent); struct cros_ec_dev *ec = sensor_hub->ec; struct cros_ec_sensor_platform *sensor_platform = dev_get_platdata(dev); - u32 ver_mask; + u32 ver_mask, temp; int frequencies[ARRAY_SIZE(state->frequencies) / 2] = { 0 }; int ret, i; @@ -311,10 +311,16 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, &frequencies[2], &state->fifo_max_event_count); } else { - frequencies[1] = state->resp->info_3.min_frequency; - frequencies[2] = state->resp->info_3.max_frequency; - state->fifo_max_event_count = - state->resp->info_3.fifo_max_event_count; + if (state->resp->info_3.max_frequency == 0) { + get_default_min_max_freq(state->resp->info.type, + &frequencies[1], + &frequencies[2], + &temp); + } else { + frequencies[1] = state->resp->info_3.min_frequency; + frequencies[2] = state->resp->info_3.max_frequency; + } + state->fifo_max_event_count = state->resp->info_3.fifo_max_event_count; } for (i = 0; i < ARRAY_SIZE(frequencies); i++) { state->frequencies[2 * i] = frequencies[i] / 1000; -- cgit v1.2.3 From 15207a92e019803d62687455d8aa2ff9eb3dc82c Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Sun, 18 Oct 2020 21:46:44 +0200 Subject: iio: adc: mediatek: fix unset field dev_comp field is used in a couple of places but it is never set. This results in kernel oops when dereferencing a NULL pointer. Set the `dev_comp` field correctly in the probe function. Fixes: 6d97024dce23 ("iio: adc: mediatek: mt6577-auxadc, add mt6765 support") Signed-off-by: Fabien Parent Reviewed-by: Matthias Brugger Cc: Link: https://lore.kernel.org/r/20201018194644.3366846-1-fparent@baylibre.com Signed-off-by: Jonathan Cameron --- drivers/iio/adc/mt6577_auxadc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iio/adc/mt6577_auxadc.c b/drivers/iio/adc/mt6577_auxadc.c index ac415cb089cd..79c1dd68b909 100644 --- a/drivers/iio/adc/mt6577_auxadc.c +++ b/drivers/iio/adc/mt6577_auxadc.c @@ -9,9 +9,9 @@ #include #include #include -#include -#include +#include #include +#include #include #include #include @@ -276,6 +276,8 @@ static int mt6577_auxadc_probe(struct platform_device *pdev) goto err_disable_clk; } + adc_dev->dev_comp = device_get_match_data(&pdev->dev); + mutex_init(&adc_dev->lock); mt6577_auxadc_mod_reg(adc_dev->reg_base + MT6577_AUXADC_MISC, -- cgit v1.2.3 From 695e2f5c289bb7f8b85351dcfa35fa236e0200a4 Mon Sep 17 00:00:00 2001 From: Olivier Moysan Date: Wed, 21 Oct 2020 10:53:13 +0200 Subject: iio: adc: stm32-adc: fix a regression when using dma and irq Since overrun interrupt support has been added, there's a regression when two ADCs are used at the same time, with: - an ADC configured to use IRQs. EOCIE bit is set. The handler is normally called in this case. - an ADC configured to use DMA. EOCIE bit isn't set. EOC triggers the DMA request. It's then automatically cleared by DMA read. But the handler gets called due to status bit is temporarily set (IRQ triggered by the other ADC). This is a regression as similar issue had been fixed earlier by commit dcb10920179a ("iio: adc: stm32-adc: fix a race when using several adcs with dma and irq"). Issue is that stm32_adc_eoc_enabled() returns non-zero value (always) since OVR bit has been added and enabled for both DMA and IRQ case. Remove OVR mask in IER register, and rely only on CSR status for overrun. To avoid subsequent calls to interrupt routine on overrun, CSR OVR bit has to be cleared. CSR OVR bit cannot be cleared directly by software. To do this ADC must be stopped first, and OVR bit in ADC ISR has to be cleared. Also add a check in ADC IRQ handler to report spurious IRQs. Fixes: cc06e67d8fa5 ("iio: adc: stm32-adc: Add check on overrun interrupt") Signed-off-by: Olivier Moysan Signed-off-by: Fabrice Gasnier Cc: Link: https://lore.kernel.org/r/20201021085313.5335-1-olivier.moysan@st.com Signed-off-by: Jonathan Cameron --- drivers/iio/adc/stm32-adc-core.c | 41 ++++++++++++++------------------ drivers/iio/adc/stm32-adc.c | 50 ++++++++++++++++++++++++++++++++++++++-- 2 files changed, 65 insertions(+), 26 deletions(-) diff --git a/drivers/iio/adc/stm32-adc-core.c b/drivers/iio/adc/stm32-adc-core.c index cd870c089182..a83199b212a4 100644 --- a/drivers/iio/adc/stm32-adc-core.c +++ b/drivers/iio/adc/stm32-adc-core.c @@ -41,18 +41,16 @@ * struct stm32_adc_common_regs - stm32 common registers * @csr: common status register offset * @ccr: common control register offset - * @eoc1_msk: adc1 end of conversion flag in @csr - * @eoc2_msk: adc2 end of conversion flag in @csr - * @eoc3_msk: adc3 end of conversion flag in @csr + * @eoc_msk: array of eoc (end of conversion flag) masks in csr for adc1..n + * @ovr_msk: array of ovr (overrun flag) masks in csr for adc1..n * @ier: interrupt enable register offset for each adc * @eocie_msk: end of conversion interrupt enable mask in @ier */ struct stm32_adc_common_regs { u32 csr; u32 ccr; - u32 eoc1_msk; - u32 eoc2_msk; - u32 eoc3_msk; + u32 eoc_msk[STM32_ADC_MAX_ADCS]; + u32 ovr_msk[STM32_ADC_MAX_ADCS]; u32 ier; u32 eocie_msk; }; @@ -282,21 +280,20 @@ out: static const struct stm32_adc_common_regs stm32f4_adc_common_regs = { .csr = STM32F4_ADC_CSR, .ccr = STM32F4_ADC_CCR, - .eoc1_msk = STM32F4_EOC1 | STM32F4_OVR1, - .eoc2_msk = STM32F4_EOC2 | STM32F4_OVR2, - .eoc3_msk = STM32F4_EOC3 | STM32F4_OVR3, + .eoc_msk = { STM32F4_EOC1, STM32F4_EOC2, STM32F4_EOC3}, + .ovr_msk = { STM32F4_OVR1, STM32F4_OVR2, STM32F4_OVR3}, .ier = STM32F4_ADC_CR1, - .eocie_msk = STM32F4_EOCIE | STM32F4_OVRIE, + .eocie_msk = STM32F4_EOCIE, }; /* STM32H7 common registers definitions */ static const struct stm32_adc_common_regs stm32h7_adc_common_regs = { .csr = STM32H7_ADC_CSR, .ccr = STM32H7_ADC_CCR, - .eoc1_msk = STM32H7_EOC_MST | STM32H7_OVR_MST, - .eoc2_msk = STM32H7_EOC_SLV | STM32H7_OVR_SLV, + .eoc_msk = { STM32H7_EOC_MST, STM32H7_EOC_SLV}, + .ovr_msk = { STM32H7_OVR_MST, STM32H7_OVR_SLV}, .ier = STM32H7_ADC_IER, - .eocie_msk = STM32H7_EOCIE | STM32H7_OVRIE, + .eocie_msk = STM32H7_EOCIE, }; static const unsigned int stm32_adc_offset[STM32_ADC_MAX_ADCS] = { @@ -318,6 +315,7 @@ static void stm32_adc_irq_handler(struct irq_desc *desc) { struct stm32_adc_priv *priv = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); + int i; u32 status; chained_irq_enter(chip, desc); @@ -335,17 +333,12 @@ static void stm32_adc_irq_handler(struct irq_desc *desc) * before invoking the interrupt handler (e.g. call ISR only for * IRQ-enabled ADCs). */ - if (status & priv->cfg->regs->eoc1_msk && - stm32_adc_eoc_enabled(priv, 0)) - generic_handle_irq(irq_find_mapping(priv->domain, 0)); - - if (status & priv->cfg->regs->eoc2_msk && - stm32_adc_eoc_enabled(priv, 1)) - generic_handle_irq(irq_find_mapping(priv->domain, 1)); - - if (status & priv->cfg->regs->eoc3_msk && - stm32_adc_eoc_enabled(priv, 2)) - generic_handle_irq(irq_find_mapping(priv->domain, 2)); + for (i = 0; i < priv->cfg->num_irqs; i++) { + if ((status & priv->cfg->regs->eoc_msk[i] && + stm32_adc_eoc_enabled(priv, i)) || + (status & priv->cfg->regs->ovr_msk[i])) + generic_handle_irq(irq_find_mapping(priv->domain, i)); + } chained_irq_exit(chip, desc); }; diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index b3f31f147347..16c02c30dec7 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -154,6 +154,7 @@ struct stm32_adc; * @start_conv: routine to start conversions * @stop_conv: routine to stop conversions * @unprepare: optional unprepare routine (disable, power-down) + * @irq_clear: routine to clear irqs * @smp_cycles: programmable sampling time (ADC clock cycles) */ struct stm32_adc_cfg { @@ -166,6 +167,7 @@ struct stm32_adc_cfg { void (*start_conv)(struct iio_dev *, bool dma); void (*stop_conv)(struct iio_dev *); void (*unprepare)(struct iio_dev *); + void (*irq_clear)(struct iio_dev *indio_dev, u32 msk); const unsigned int *smp_cycles; }; @@ -621,6 +623,13 @@ static void stm32f4_adc_stop_conv(struct iio_dev *indio_dev) STM32F4_ADON | STM32F4_DMA | STM32F4_DDS); } +static void stm32f4_adc_irq_clear(struct iio_dev *indio_dev, u32 msk) +{ + struct stm32_adc *adc = iio_priv(indio_dev); + + stm32_adc_clr_bits(adc, adc->cfg->regs->isr_eoc.reg, msk); +} + static void stm32h7_adc_start_conv(struct iio_dev *indio_dev, bool dma) { struct stm32_adc *adc = iio_priv(indio_dev); @@ -659,6 +668,13 @@ static void stm32h7_adc_stop_conv(struct iio_dev *indio_dev) stm32_adc_clr_bits(adc, STM32H7_ADC_CFGR, STM32H7_DMNGT_MASK); } +static void stm32h7_adc_irq_clear(struct iio_dev *indio_dev, u32 msk) +{ + struct stm32_adc *adc = iio_priv(indio_dev); + /* On STM32H7 IRQs are cleared by writing 1 into ISR register */ + stm32_adc_set_bits(adc, adc->cfg->regs->isr_eoc.reg, msk); +} + static int stm32h7_adc_exit_pwr_down(struct iio_dev *indio_dev) { struct stm32_adc *adc = iio_priv(indio_dev); @@ -1235,17 +1251,40 @@ static int stm32_adc_read_raw(struct iio_dev *indio_dev, } } +static void stm32_adc_irq_clear(struct iio_dev *indio_dev, u32 msk) +{ + struct stm32_adc *adc = iio_priv(indio_dev); + + adc->cfg->irq_clear(indio_dev, msk); +} + static irqreturn_t stm32_adc_threaded_isr(int irq, void *data) { struct iio_dev *indio_dev = data; struct stm32_adc *adc = iio_priv(indio_dev); const struct stm32_adc_regspec *regs = adc->cfg->regs; u32 status = stm32_adc_readl(adc, regs->isr_eoc.reg); + u32 mask = stm32_adc_readl(adc, regs->ier_eoc.reg); - if (status & regs->isr_ovr.mask) + /* Check ovr status right now, as ovr mask should be already disabled */ + if (status & regs->isr_ovr.mask) { + /* + * Clear ovr bit to avoid subsequent calls to IRQ handler. + * This requires to stop ADC first. OVR bit state in ISR, + * is propaged to CSR register by hardware. + */ + adc->cfg->stop_conv(indio_dev); + stm32_adc_irq_clear(indio_dev, regs->isr_ovr.mask); dev_err(&indio_dev->dev, "Overrun, stopping: restart needed\n"); + return IRQ_HANDLED; + } - return IRQ_HANDLED; + if (!(status & mask)) + dev_err_ratelimited(&indio_dev->dev, + "Unexpected IRQ: IER=0x%08x, ISR=0x%08x\n", + mask, status); + + return IRQ_NONE; } static irqreturn_t stm32_adc_isr(int irq, void *data) @@ -1254,6 +1293,10 @@ static irqreturn_t stm32_adc_isr(int irq, void *data) struct stm32_adc *adc = iio_priv(indio_dev); const struct stm32_adc_regspec *regs = adc->cfg->regs; u32 status = stm32_adc_readl(adc, regs->isr_eoc.reg); + u32 mask = stm32_adc_readl(adc, regs->ier_eoc.reg); + + if (!(status & mask)) + return IRQ_WAKE_THREAD; if (status & regs->isr_ovr.mask) { /* @@ -2046,6 +2089,7 @@ static const struct stm32_adc_cfg stm32f4_adc_cfg = { .start_conv = stm32f4_adc_start_conv, .stop_conv = stm32f4_adc_stop_conv, .smp_cycles = stm32f4_adc_smp_cycles, + .irq_clear = stm32f4_adc_irq_clear, }; static const struct stm32_adc_cfg stm32h7_adc_cfg = { @@ -2057,6 +2101,7 @@ static const struct stm32_adc_cfg stm32h7_adc_cfg = { .prepare = stm32h7_adc_prepare, .unprepare = stm32h7_adc_unprepare, .smp_cycles = stm32h7_adc_smp_cycles, + .irq_clear = stm32h7_adc_irq_clear, }; static const struct stm32_adc_cfg stm32mp1_adc_cfg = { @@ -2069,6 +2114,7 @@ static const struct stm32_adc_cfg stm32mp1_adc_cfg = { .prepare = stm32h7_adc_prepare, .unprepare = stm32h7_adc_unprepare, .smp_cycles = stm32h7_adc_smp_cycles, + .irq_clear = stm32h7_adc_irq_clear, }; static const struct of_device_id stm32_adc_of_match[] = { -- cgit v1.2.3 From 271b339236e1c0e6448bc1cafeaedcb529324bf0 Mon Sep 17 00:00:00 2001 From: David Lechner Date: Sun, 25 Oct 2020 11:51:22 -0500 Subject: counter/ti-eqep: Fix regmap max_register The values given were the offset of the register after the last register instead of the actual last register in each range. Fix by using the correct last register of each range. Fixes: f213729f6796 ("counter: new TI eQEP driver") Signed-off-by: David Lechner Acked-by: William Breathitt Gray Link: https://lore.kernel.org/r/20201025165122.607866-1-david@lechnology.com Signed-off-by: Jonathan Cameron --- drivers/counter/ti-eqep.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/counter/ti-eqep.c b/drivers/counter/ti-eqep.c index e27771df8e23..a60aee1a1a29 100644 --- a/drivers/counter/ti-eqep.c +++ b/drivers/counter/ti-eqep.c @@ -368,7 +368,7 @@ static const struct regmap_config ti_eqep_regmap32_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, - .max_register = 0x24, + .max_register = QUPRD, }; static const struct regmap_config ti_eqep_regmap16_config = { @@ -376,7 +376,7 @@ static const struct regmap_config ti_eqep_regmap16_config = { .reg_bits = 16, .val_bits = 16, .reg_stride = 2, - .max_register = 0x1e, + .max_register = QCPRDLAT, }; static int ti_eqep_probe(struct platform_device *pdev) -- cgit v1.2.3 From fe0b980ffd1dd8b10c09f82385514819ba2a661d Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sun, 1 Nov 2020 17:21:18 +0100 Subject: iio: imu: st_lsm6dsx: set 10ms as min shub slave timeout Set 10ms as minimum i2c slave configuration timeout since st_lsm6dsx relies on accel ODR for i2c master clock and at high sample rates (e.g. 833Hz or 416Hz) the slave sensor occasionally may need more cycles than i2c master timeout (2s/833Hz + 1 ~ 3ms) to apply the configuration resulting in an uncomplete slave configuration and a constant reading from the i2c slave connected to st_lsm6dsx i2c master. Fixes: 8f9a5249e3d9 ("iio: imu: st_lsm6dsx: enable 833Hz sample frequency for tagged sensors") Fixes: c91c1c844ebd ("iio: imu: st_lsm6dsx: add i2c embedded controller support") Signed-off-by: Lorenzo Bianconi Cc: Link: https://lore.kernel.org/r/a69c8236bf16a1569966815ed71710af2722ed7d.1604247274.git.lorenzo@kernel.org Signed-off-by: Jonathan Cameron --- drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c index 8c8d8870ca07..99562ba85ee4 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c @@ -156,11 +156,13 @@ static const struct st_lsm6dsx_ext_dev_settings st_lsm6dsx_ext_dev_table[] = { static void st_lsm6dsx_shub_wait_complete(struct st_lsm6dsx_hw *hw) { struct st_lsm6dsx_sensor *sensor; - u32 odr; + u32 odr, timeout; sensor = iio_priv(hw->iio_devs[ST_LSM6DSX_ID_ACC]); odr = (hw->enable_mask & BIT(ST_LSM6DSX_ID_ACC)) ? sensor->odr : 12500; - msleep((2000000U / odr) + 1); + /* set 10ms as minimum timeout for i2c slave configuration */ + timeout = max_t(u32, 2000000U / odr + 1, 10); + msleep(timeout); } /* -- cgit v1.2.3 From 7dd8f0ba88fce98e2953267a66af74c6f4792a56 Mon Sep 17 00:00:00 2001 From: Sergey Matyukevich Date: Sat, 24 Oct 2020 23:11:20 +0300 Subject: arm: dts: imx6qdl-udoo: fix rgmii phy-mode for ksz9031 phy Commit bcf3440c6dd7 ("net: phy: micrel: add phy-mode support for the KSZ9031 PHY") fixed micrel phy driver adding proper support for phy modes. Adapt imx6q-udoo board phy settings : explicitly set required delay configuration using "rgmii-id". Fixes: cbd54fe0b2bc ("ARM: dts: imx6dl-udoo: Add board support based off imx6q-udoo") Signed-off-by: Sergey Matyukevich Reviewed-by: Fabio Estevam Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6qdl-udoo.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6qdl-udoo.dtsi b/arch/arm/boot/dts/imx6qdl-udoo.dtsi index 828dd20cd27d..d07d8f83456d 100644 --- a/arch/arm/boot/dts/imx6qdl-udoo.dtsi +++ b/arch/arm/boot/dts/imx6qdl-udoo.dtsi @@ -98,7 +98,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; -- cgit v1.2.3 From f8b5a33707c9a19ec905d2826be0acd151997a09 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Fri, 30 Oct 2020 01:55:28 +0100 Subject: ARM: dts: vf610-zii-dev-rev-b: Fix MDIO over clocking The ZII devel B board has two generations of Marvell Switches. The mv88e6352 supports an MDIO clock of 12MHz. However the older 88e6185 does not like 12MHz, and often fails to probe. Reduce the clock speed to 5MHz, which seems to work reliably. Cc: Chris Healy Fixes: b955387667ec ("ARM: dts: ZII: update MDIO speed and preamble") Signed-off-by: Andrew Lunn Reviewed-by: Chris Healy Signed-off-by: Shawn Guo --- arch/arm/boot/dts/vf610-zii-dev-rev-b.dts | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts index e500911ce0a5..6f1e0f0d4f0a 100644 --- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts +++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts @@ -406,6 +406,9 @@ }; }; +&mdio1 { + clock-frequency = <5000000>; +}; &iomuxc { pinctrl_gpio_e6185_eeprom_sel: pinctrl-gpio-e6185-eeprom-spi0 { -- cgit v1.2.3 From e402599e5e5e0b2758d7766fd9f6d7953d4ccd85 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 12 Oct 2020 09:18:16 +0200 Subject: ARM: dts: imx6q-prti6q: fix PHY address Due to bug in the bootloader, the PHY has floating address and may randomly change on each PHY reset. To avoid it, the updated bootloader with the following patch[0] should be used: | ARM: protonic: disable on-die termination to fix PHY bootstrapping | | If on-die termination is enabled, the RXC pin of iMX6 will be pulled | high. Since we already have an 10K pull-down on board, the RXC level on | PHY reset will be ~800mV, which is mostly interpreted as 1. On some | reboots we get 0 instead and kernel can't detect the PHY properly. | | Since the default 0x020e07ac value is 0, it is sufficient to remove this | entry from the affected imxcfg files. | | Since we get stable 0 on pin PHYADDR[2], the PHY address is changed from | 4 to 0. With latest bootloader update, the PHY address will be fixed to "0". [0] https://git.pengutronix.de/cgit/barebox/commit/?id=93f7dcf631edfcda19e7757b28d66017ea274b81 Fixes: 0d446a505592 ("ARM: dts: add Protonic PRTI6Q board") Signed-off-by: Oleksij Rempel Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6q-prti6q.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/imx6q-prti6q.dts b/arch/arm/boot/dts/imx6q-prti6q.dts index d112b50f8c5d..b4605edfd2ab 100644 --- a/arch/arm/boot/dts/imx6q-prti6q.dts +++ b/arch/arm/boot/dts/imx6q-prti6q.dts @@ -213,8 +213,8 @@ #size-cells = <0>; /* Microchip KSZ9031RNX PHY */ - rgmii_phy: ethernet-phy@4 { - reg = <4>; + rgmii_phy: ethernet-phy@0 { + reg = <0>; interrupts-extended = <&gpio1 28 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; reset-assert-us = <10000>; -- cgit v1.2.3 From d9b5665fb3c822730857ba9119ead8b5e5ff967d Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 23 Oct 2020 13:57:32 +0200 Subject: kbuild: remove unused OBJSIZE The "size" tool has been solely used by s390 to enforce .bss section usage restrictions in early startup code. Since commit 980d5f9ab36b ("s390/boot: enable .bss section for compressed kernel") and commit 2e83e0eb85ca ("s390: clean .bss before running uncompressed kernel") these restrictions have been lifted for the decompressor and uncompressed kernel and the size tool is now unused. Signed-off-by: Vasily Gorbik Reviewed-by: Nathan Chancellor Signed-off-by: Masahiro Yamada --- Documentation/kbuild/llvm.rst | 5 ++--- Makefile | 4 +--- 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst index cf3ca236d2cc..21c847890d03 100644 --- a/Documentation/kbuild/llvm.rst +++ b/Documentation/kbuild/llvm.rst @@ -57,9 +57,8 @@ to enable them. :: They can be enabled individually. The full list of the parameters: :: make CC=clang LD=ld.lld AR=llvm-ar NM=llvm-nm STRIP=llvm-strip \ - OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump OBJSIZE=llvm-size \ - READELF=llvm-readelf HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar \ - HOSTLD=ld.lld + OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump READELF=llvm-readelf \ + HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar HOSTLD=ld.lld Currently, the integrated assembler is disabled by default. You can pass ``LLVM_IAS=1`` to enable it. diff --git a/Makefile b/Makefile index 9e7fd6a065a7..f353886dbf44 100644 --- a/Makefile +++ b/Makefile @@ -433,7 +433,6 @@ NM = llvm-nm OBJCOPY = llvm-objcopy OBJDUMP = llvm-objdump READELF = llvm-readelf -OBJSIZE = llvm-size STRIP = llvm-strip else CC = $(CROSS_COMPILE)gcc @@ -443,7 +442,6 @@ NM = $(CROSS_COMPILE)nm OBJCOPY = $(CROSS_COMPILE)objcopy OBJDUMP = $(CROSS_COMPILE)objdump READELF = $(CROSS_COMPILE)readelf -OBJSIZE = $(CROSS_COMPILE)size STRIP = $(CROSS_COMPILE)strip endif PAHOLE = pahole @@ -509,7 +507,7 @@ KBUILD_LDFLAGS := CLANG_FLAGS := export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE LD CC -export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL +export CPP AR NM STRIP OBJCOPY OBJDUMP READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL export PERL PYTHON PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ ZSTD export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE -- cgit v1.2.3 From d1889589a4f54b2d1d7075d608b596d6fcfd3d96 Mon Sep 17 00:00:00 2001 From: Sven Joachim Date: Mon, 26 Oct 2020 20:32:16 +0100 Subject: builddeb: Fix rootless build in setuid/setgid directory Building 5.10-rc1 in a setgid directory failed with the following error: dpkg-deb: error: control directory has bad permissions 2755 (must be >=0755 and <=0775) When building with fakeroot, the earlier chown call would have removed the setgid bits, but in a rootless build they remain. Fixes: 3e8541803624 ("builddeb: Enable rootless builds") Cc: Guillem Jover Signed-off-by: Sven Joachim Signed-off-by: Masahiro Yamada --- scripts/package/builddeb | 2 ++ 1 file changed, 2 insertions(+) diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 1b11f8993629..91a502bb97e8 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -45,6 +45,8 @@ create_package() { chmod -R go-w "$pdir" # in case we are in a restrictive umask environment like 0077 chmod -R a+rX "$pdir" + # in case we build in a setuid/setgid directory + chmod -R ug-s "$pdir" # Create the package dpkg-gencontrol -p$pname -P"$pdir" -- cgit v1.2.3 From 544cc3f8573bf9a82e8f348741f2f68d2a8376fb Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Sun, 1 Nov 2020 08:26:09 +0100 Subject: arm64: dts: allwinner: h6: orangepi-one-plus: Fix ethernet RX/TX delay on OrangePi One Plus board is set on PHY. Reflect that in ethernet node. Fixes: 7ee32a17e0d6 ("arm64: dts: allwinner: h6: orangepi-one-plus: Enable ethernet") Signed-off-by: Jernej Skrabec Signed-off-by: Maxime Ripard Tested-by: Marcus Cooper Link: https://lore.kernel.org/r/20201101072609.1681891-1-jernej.skrabec@siol.net --- arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-one-plus.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-one-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-one-plus.dts index fceb298bfd53..29a081e72a9b 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-one-plus.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-one-plus.dts @@ -27,7 +27,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&ext_rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_gmac_3v3>; allwinner,rx-delay-ps = <200>; -- cgit v1.2.3 From ad2091f893bd5dfe2824f0d6819600d120698e9f Mon Sep 17 00:00:00 2001 From: Paul Kocialkowski Date: Sat, 31 Oct 2020 19:21:29 +0100 Subject: ARM: sunxi: Add machine match for the Allwinner V3 SoC The Allwinner V3 SoC shares the same base as the V3s but comes with extra pins and features available. As a result, it has its dedicated compatible string (already used in device trees), which is added here. Signed-off-by: Paul Kocialkowski Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20201031182137.1879521-2-contact@paulk.fr --- arch/arm/mach-sunxi/sunxi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-sunxi/sunxi.c b/arch/arm/mach-sunxi/sunxi.c index 06da2747a90b..19635721013d 100644 --- a/arch/arm/mach-sunxi/sunxi.c +++ b/arch/arm/mach-sunxi/sunxi.c @@ -66,6 +66,7 @@ static const char * const sun8i_board_dt_compat[] = { "allwinner,sun8i-h2-plus", "allwinner,sun8i-h3", "allwinner,sun8i-r40", + "allwinner,sun8i-v3", "allwinner,sun8i-v3s", NULL, }; -- cgit v1.2.3 From 6ab48105aae79b9d8062e9bc922baaeff80918d7 Mon Sep 17 00:00:00 2001 From: Matteo Scordino Date: Fri, 30 Oct 2020 23:43:25 +0000 Subject: ARM: dts: s3: pinecube: align compatible property to other S3 boards The compatible string in the Pine64 Pinecube dts diverges from the ones used in other S3 based boards, like the LicheePi and the Elimo Impetus and Initium. Discussion on LKML decided the PineCube should align to the others. Signed-off-by: Matteo Scordino Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20201030234325.5865-7-matteo.scordino@gmail.com --- arch/arm/boot/dts/sun8i-s3-pinecube.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sun8i-s3-pinecube.dts b/arch/arm/boot/dts/sun8i-s3-pinecube.dts index 9bab6b7f4014..4aa0ee897a0a 100644 --- a/arch/arm/boot/dts/sun8i-s3-pinecube.dts +++ b/arch/arm/boot/dts/sun8i-s3-pinecube.dts @@ -10,7 +10,7 @@ / { model = "PineCube IP Camera"; - compatible = "pine64,pinecube", "allwinner,sun8i-s3"; + compatible = "pine64,pinecube", "sochip,s3", "allwinner,sun8i-v3"; aliases { serial0 = &uart2; -- cgit v1.2.3 From f51778db088b2407ec177f2f4da0f6290602aa3f Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Mon, 2 Nov 2020 12:43:27 +1100 Subject: swiotlb: using SIZE_MAX needs limits.h included After merging the drm-misc tree, linux-next build (arm multi_v7_defconfig) failed like this: In file included from drivers/gpu/drm/nouveau/nouveau_ttm.c:26: include/linux/swiotlb.h: In function 'swiotlb_max_mapping_size': include/linux/swiotlb.h:99:9: error: 'SIZE_MAX' undeclared (first use in this function) 99 | return SIZE_MAX; | ^~~~~~~~ include/linux/swiotlb.h:7:1: note: 'SIZE_MAX' is defined in header ''; did you forget to '#include '? 6 | #include +++ |+#include 7 | #include include/linux/swiotlb.h:99:9: note: each undeclared identifier is reported only once for each function it appears in 99 | return SIZE_MAX; | ^~~~~~~~ Caused by commit abe420bfae52 ("swiotlb: Introduce swiotlb_max_mapping_size()") but only exposed by commit "drm/nouveu: fix swiotlb include" Fix it by including linux/limits.h as appropriate. Fixes: abe420bfae52 ("swiotlb: Introduce swiotlb_max_mapping_size()") Signed-off-by: Stephen Rothwell Link: https://lore.kernel.org/r/20201102124327.2f82b2a7@canb.auug.org.au Signed-off-by: Michael S. Tsirkin --- include/linux/swiotlb.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 046bb94bd4d6..fa5122c6711e 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -5,6 +5,7 @@ #include #include #include +#include struct device; struct page; -- cgit v1.2.3 From 8c9cb4094ccf242eddd140efba13872c55f68a87 Mon Sep 17 00:00:00 2001 From: Pablo Greco Date: Mon, 2 Nov 2020 11:16:40 -0300 Subject: ARM: dts: sun7i: bananapi: Enable RGMII RX/TX delay on Ethernet PHY The Ethernet PHY on the Bananapi M1 has the RX and TX delays enabled on the PHY, using pull-ups on the RXDLY and TXDLY pins. Fix the phy-mode description to correct reflect this so that the implementation doesn't reconfigure the delays incorrectly. This happened with commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config"). Fixes: 8a5b272fbf44 ("ARM: dts: sun7i: Add Banana Pi board") Signed-off-by: Pablo Greco Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/1604326600-39544-1-git-send-email-pgreco@centosproject.org --- arch/arm/boot/dts/sun7i-a20-bananapi.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sun7i-a20-bananapi.dts b/arch/arm/boot/dts/sun7i-a20-bananapi.dts index bb3987e101c2..0b3d9ae75650 100644 --- a/arch/arm/boot/dts/sun7i-a20-bananapi.dts +++ b/arch/arm/boot/dts/sun7i-a20-bananapi.dts @@ -132,7 +132,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_gmac_3v3>; status = "okay"; }; -- cgit v1.2.3 From bd5cdcdc66e1f7179ff6d172d1e5f55e43403aa8 Mon Sep 17 00:00:00 2001 From: Pablo Greco Date: Mon, 2 Nov 2020 11:19:14 -0300 Subject: ARM: dts: sun8i: r40: bananapi-m2-berry: Fix dcdc1 regulator DCDC1 regulator powers many different subsystems. While some of them can work at 3.0 V, some of them can not. For example, VCC-HDMI can only work between 3.24 V and 3.36 V. According to OS images provided by the board manufacturer this regulator should be set to 3.3 V. Set DCDC1 and DCDC1SW to 3.3 V in order to fix this. Fixes: 23edc168bd98 ("ARM: dts: sun8i: Add board dts file for Banana Pi M2 Berry") Fixes: 27e81e1970a8 ("ARM: dts: sun8i: v40: bananapi-m2-berry: Enable GMAC ethernet controller") Signed-off-by: Pablo Greco Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/1604326755-39742-1-git-send-email-pgreco@centosproject.org --- arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts b/arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts index 15c22b06fc4b..84eb08295718 100644 --- a/arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts +++ b/arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts @@ -198,16 +198,16 @@ }; ®_dc1sw { - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-name = "vcc-gmac-phy"; }; ®_dcdc1 { regulator-always-on; - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; - regulator-name = "vcc-3v0"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vcc-3v3"; }; ®_dcdc2 { -- cgit v1.2.3 From 8a82d91fa275aaea49be06d7f5b1407ce1c0dd4b Mon Sep 17 00:00:00 2001 From: Pablo Greco Date: Mon, 2 Nov 2020 11:19:29 -0300 Subject: ARM: dts: sun8i: v40: bananapi-m2-berry: Fix ethernet node Ethernet PHY on BananaPi M2 Berry provides RX and TX delays. Fix ethernet node to reflect that fact. Fixes: 27e81e1970a8 ("ARM: dts: sun8i: v40: bananapi-m2-berry: Enable GMAC ethernet controller") Signed-off-by: Pablo Greco Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/1604326769-39802-1-git-send-email-pgreco@centosproject.org --- arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts b/arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts index 84eb08295718..47954551f573 100644 --- a/arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts +++ b/arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts @@ -120,7 +120,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_dc1sw>; status = "okay"; }; -- cgit v1.2.3 From f126b6702e7354d6247a36f20b9172457af5c15a Mon Sep 17 00:00:00 2001 From: Dinh Nguyen Date: Sun, 1 Nov 2020 14:02:56 -0600 Subject: arm64: dts: agilex/stratix10: Fix qspi node compatible The QSPI flash node needs to have the required "jedec,spi-nor" in the compatible string. Fixes: 0cb140d07fc7 ("arm64: dts: stratix10: Add QSPI support for Stratix10") Cc: stable@vger.kernel.org Suggested-by: Vignesh Raghavendra Signed-off-by: Dinh Nguyen --- arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts | 2 +- arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts | 2 +- arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts index feadd21bc0dc..46e558ab7729 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts @@ -159,7 +159,7 @@ flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00a"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts index c07966740e14..f9b4a39683cf 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts @@ -192,7 +192,7 @@ flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00a"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts index 96c50d48289d..a7a83f29f00b 100644 --- a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts +++ b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts @@ -110,7 +110,7 @@ flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "mt25qu02g"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; -- cgit v1.2.3 From ddcd945e556e2cc6be8f88ef0271b56927ffbe98 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 11 Oct 2020 08:54:38 -0700 Subject: rtw88: fix fw_fifo_addr check The clang build reports this warning fw.c:1485:21: warning: address of array 'rtwdev->chip->fw_fifo_addr' will always evaluate to 'true' if (!rtwdev->chip->fw_fifo_addr) { fw_fifo_addr is an array in rtw_chip_info so it is always nonzero. A better check is if the first element of the array is nonzero. In the cases where fw_fifo_addr is initialized by rtw88b and rtw88c, the first array element is 0x780. Fixes: 0fbc2f0f34cc ("rtw88: add dump firmware fifo support") Signed-off-by: Tom Rix Reviewed-by: Nathan Chancellor Acked-by: Tzu-En Huang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20201011155438.15892-1-trix@redhat.com --- drivers/net/wireless/realtek/rtw88/fw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c index 042015bc8055..b2fd87834f23 100644 --- a/drivers/net/wireless/realtek/rtw88/fw.c +++ b/drivers/net/wireless/realtek/rtw88/fw.c @@ -1482,7 +1482,7 @@ static bool rtw_fw_dump_check_size(struct rtw_dev *rtwdev, int rtw_fw_dump_fifo(struct rtw_dev *rtwdev, u8 fifo_sel, u32 addr, u32 size, u32 *buffer) { - if (!rtwdev->chip->fw_fifo_addr) { + if (!rtwdev->chip->fw_fifo_addr[0]) { rtw_dbg(rtwdev, RTW_DBG_FW, "chip not support dump fw fifo\n"); return -ENOTSUPP; } -- cgit v1.2.3 From 04516706bb99889986ddfa3a769ed50d2dc7ac13 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 22 Oct 2020 16:51:03 +0300 Subject: iwlwifi: pcie: limit memory read spin time When we read device memory, we lock a spinlock, write the address we want to read from the device and then spin in a loop reading the data in 32-bit quantities from another register. As the description makes clear, this is rather inefficient, incurring a PCIe bus transaction for every read. In a typical device today, we want to read 786k SMEM if it crashes, leading to 192k register reads. Occasionally, we've seen the whole loop take over 20 seconds and then triggering the soft lockup detector. Clearly, it is unreasonable to spin here for such extended periods of time. To fix this, break the loop down into an outer and an inner loop, and break out of the inner loop if more than half a second elapsed. To avoid too much overhead, check for that only every 128 reads, though there's no particular reason for that number. Then, unlock and relock to obtain NIC access again, reprogram the start address and continue. This will keep (interrupt) latencies on the CPU down to a reasonable time. Signed-off-by: Johannes Berg Signed-off-by: Mordechay Goodstein Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/iwlwifi.20201022165103.45878a7e49aa.I3b9b9c5a10002915072312ce75b68ed5b3dc6e14@changeid --- drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 36 ++++++++++++++++++------- 1 file changed, 27 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index d2e69ad53b27..2fffbbc8462f 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -2156,18 +2156,36 @@ static int iwl_trans_pcie_read_mem(struct iwl_trans *trans, u32 addr, void *buf, int dwords) { unsigned long flags; - int offs, ret = 0; + int offs = 0; u32 *vals = buf; - if (iwl_trans_grab_nic_access(trans, &flags)) { - iwl_write32(trans, HBUS_TARG_MEM_RADDR, addr); - for (offs = 0; offs < dwords; offs++) - vals[offs] = iwl_read32(trans, HBUS_TARG_MEM_RDAT); - iwl_trans_release_nic_access(trans, &flags); - } else { - ret = -EBUSY; + while (offs < dwords) { + /* limit the time we spin here under lock to 1/2s */ + ktime_t timeout = ktime_add_us(ktime_get(), 500 * USEC_PER_MSEC); + + if (iwl_trans_grab_nic_access(trans, &flags)) { + iwl_write32(trans, HBUS_TARG_MEM_RADDR, + addr + 4 * offs); + + while (offs < dwords) { + vals[offs] = iwl_read32(trans, + HBUS_TARG_MEM_RDAT); + offs++; + + /* calling ktime_get is expensive so + * do it once in 128 reads + */ + if (offs % 128 == 0 && ktime_after(ktime_get(), + timeout)) + break; + } + iwl_trans_release_nic_access(trans, &flags); + } else { + return -EBUSY; + } } - return ret; + + return 0; } static int iwl_trans_pcie_write_mem(struct iwl_trans *trans, u32 addr, -- cgit v1.2.3 From 0f7636e1654338c34e3c220c02b2ffad78b6ccc0 Mon Sep 17 00:00:00 2001 From: Paul Menzel Date: Tue, 11 Aug 2020 11:29:23 +0200 Subject: init/Kconfig: Fix CPU number in LOG_CPU_MAX_BUF_SHIFT description Currently, LOG_BUF_SHIFT defaults to 17, which is 2 ^ 17 bytes = 128 KB, and LOG_CPU_MAX_BUF_SHIFT defaults to 12, which is 2 ^ 12 bytes = 4 KB. Half of 128 KB is 64 KB, so more than 16 CPUs are required for the value to be used, as then the sum of contributions is greater than 64 KB for the first time. My guess is, that the description was written with the configuration values used in the SUSE in mind. Fixes: 23b2899f7f194f06e ("printk: allow increasing the ring buffer depending on the number of CPUs") Cc: Luis R. Rodriguez Cc: linux-kernel@vger.kernel.org Signed-off-by: Paul Menzel Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20200811092924.6256-1-pmenzel@molgen.mpg.de --- init/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/init/Kconfig b/init/Kconfig index c9446911cf41..02d13ae27abb 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -719,7 +719,7 @@ config LOG_CPU_MAX_BUF_SHIFT with more CPUs. Therefore this value is used only when the sum of contributions is greater than the half of the default kernel ring buffer as defined by LOG_BUF_SHIFT. The default values are set - so that more than 64 CPUs are needed to trigger the allocation. + so that more than 16 CPUs are needed to trigger the allocation. Also this option is ignored when "log_buf_len" kernel parameter is used as it forces an exact (power of two) size of the ring buffer. -- cgit v1.2.3 From 46b97aed5484a3f44584a10f9e0691bf89d29064 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Mon, 5 Oct 2020 18:22:41 +0200 Subject: drm/mediatek: mtk_dpi: Fix unused variable 'mtk_dpi_encoder_funcs' Commit f89c696e7f63 ("drm/mediatek: mtk_dpi: Convert to bridge driver") introduced the following build warning with W=1 drivers/gpu/drm/mediatek/mtk_dpi.c:530:39: warning: unused variable 'mtk_dpi_encoder_funcs' [-Wunused-const-variable] static const struct drm_encoder_funcs mtk_dpi_encoder_funcs = { This struct is and the 'mtk_dpi_encoder_destroy()' are not needed anymore, so remove them. Fixes: f89c696e7f63 ("drm/mediatek: mtk_dpi: Convert to bridge driver") Reported-by: kernel test robot Signed-off-by: Enric Balletbo i Serra Signed-off-by: Chun-Kuang Hu --- drivers/gpu/drm/mediatek/mtk_dpi.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index cf11c4850b40..52f11a63a330 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -522,15 +522,6 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi, return 0; } -static void mtk_dpi_encoder_destroy(struct drm_encoder *encoder) -{ - drm_encoder_cleanup(encoder); -} - -static const struct drm_encoder_funcs mtk_dpi_encoder_funcs = { - .destroy = mtk_dpi_encoder_destroy, -}; - static int mtk_dpi_bridge_attach(struct drm_bridge *bridge, enum drm_bridge_attach_flags flags) { -- cgit v1.2.3 From 34a9fa2025d9d3177c99351c7aaf256c5f50691f Mon Sep 17 00:00:00 2001 From: Pablo Ceballos Date: Mon, 2 Nov 2020 19:29:39 -0500 Subject: HID: hid-sensor-hub: Fix issue with devices with no report ID Some HID devices don't use a report ID because they only have a single report. In those cases, the report ID in struct hid_report will be zero and the data for the report will start at the first byte, so don't skip over the first byte. Signed-off-by: Pablo Ceballos Acked-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina --- drivers/hid/hid-sensor-hub.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 94c7398b5c27..3dd7d3246737 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -483,7 +483,8 @@ static int sensor_hub_raw_event(struct hid_device *hdev, return 1; ptr = raw_data; - ptr++; /* Skip report id */ + if (report->id) + ptr++; /* Skip report id */ spin_lock_irqsave(&pdata->lock, flags); -- cgit v1.2.3 From 567b8e9fed8add9e20885be38ecd73bb0e07406b Mon Sep 17 00:00:00 2001 From: Lars Povlsen Date: Wed, 4 Nov 2020 23:02:23 +0100 Subject: HID: mcp2221: Fix GPIO output handling The mcp2221 driver GPIO output handling has has several issues. * A wrong value is used for the GPIO direction. * Wrong offsets are calculated for some GPIO set value/set direction operations, when offset is larger than 0. This has been fixed by introducing proper manifest constants for the direction encoding, and using 'offsetof' when calculating GPIO register offsets. The updated driver has been tested with the Sparx5 pcb134/pcb135 board, which has the mcp2221 device with several (output) GPIO's. Fixes: 328de1c519c5c092 ("HID: mcp2221: add GPIO functionality support") Reviewed-by: Rishi Gupta Signed-off-by: Lars Povlsen Signed-off-by: Jiri Kosina --- drivers/hid/hid-mcp2221.c | 48 ++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 39 insertions(+), 9 deletions(-) diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c index 0d27ccb55dd9..4211b9839209 100644 --- a/drivers/hid/hid-mcp2221.c +++ b/drivers/hid/hid-mcp2221.c @@ -49,6 +49,36 @@ enum { MCP2221_ALT_F_NOT_GPIOD = 0xEF, }; +/* MCP GPIO direction encoding */ +enum { + MCP2221_DIR_OUT = 0x00, + MCP2221_DIR_IN = 0x01, +}; + +#define MCP_NGPIO 4 + +/* MCP GPIO set command layout */ +struct mcp_set_gpio { + u8 cmd; + u8 dummy; + struct { + u8 change_value; + u8 value; + u8 change_direction; + u8 direction; + } gpio[MCP_NGPIO]; +} __packed; + +/* MCP GPIO get command layout */ +struct mcp_get_gpio { + u8 cmd; + u8 dummy; + struct { + u8 direction; + u8 value; + } gpio[MCP_NGPIO]; +} __packed; + /* * There is no way to distinguish responses. Therefore next command * is sent only after response to previous has been received. Mutex @@ -542,7 +572,7 @@ static int mcp_gpio_get(struct gpio_chip *gc, mcp->txbuf[0] = MCP2221_GPIO_GET; - mcp->gp_idx = (offset + 1) * 2; + mcp->gp_idx = offsetof(struct mcp_get_gpio, gpio[offset].value); mutex_lock(&mcp->lock); ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1); @@ -559,7 +589,7 @@ static void mcp_gpio_set(struct gpio_chip *gc, memset(mcp->txbuf, 0, 18); mcp->txbuf[0] = MCP2221_GPIO_SET; - mcp->gp_idx = ((offset + 1) * 4) - 1; + mcp->gp_idx = offsetof(struct mcp_set_gpio, gpio[offset].value); mcp->txbuf[mcp->gp_idx - 1] = 1; mcp->txbuf[mcp->gp_idx] = !!value; @@ -575,7 +605,7 @@ static int mcp_gpio_dir_set(struct mcp2221 *mcp, memset(mcp->txbuf, 0, 18); mcp->txbuf[0] = MCP2221_GPIO_SET; - mcp->gp_idx = (offset + 1) * 5; + mcp->gp_idx = offsetof(struct mcp_set_gpio, gpio[offset].direction); mcp->txbuf[mcp->gp_idx - 1] = 1; mcp->txbuf[mcp->gp_idx] = val; @@ -590,7 +620,7 @@ static int mcp_gpio_direction_input(struct gpio_chip *gc, struct mcp2221 *mcp = gpiochip_get_data(gc); mutex_lock(&mcp->lock); - ret = mcp_gpio_dir_set(mcp, offset, 0); + ret = mcp_gpio_dir_set(mcp, offset, MCP2221_DIR_IN); mutex_unlock(&mcp->lock); return ret; @@ -603,7 +633,7 @@ static int mcp_gpio_direction_output(struct gpio_chip *gc, struct mcp2221 *mcp = gpiochip_get_data(gc); mutex_lock(&mcp->lock); - ret = mcp_gpio_dir_set(mcp, offset, 1); + ret = mcp_gpio_dir_set(mcp, offset, MCP2221_DIR_OUT); mutex_unlock(&mcp->lock); /* Can't configure as output, bailout early */ @@ -623,7 +653,7 @@ static int mcp_gpio_get_direction(struct gpio_chip *gc, mcp->txbuf[0] = MCP2221_GPIO_GET; - mcp->gp_idx = (offset + 1) * 2; + mcp->gp_idx = offsetof(struct mcp_get_gpio, gpio[offset].direction); mutex_lock(&mcp->lock); ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1); @@ -632,7 +662,7 @@ static int mcp_gpio_get_direction(struct gpio_chip *gc, if (ret) return ret; - if (mcp->gpio_dir) + if (mcp->gpio_dir == MCP2221_DIR_IN) return GPIO_LINE_DIRECTION_IN; return GPIO_LINE_DIRECTION_OUT; @@ -758,7 +788,7 @@ static int mcp2221_raw_event(struct hid_device *hdev, mcp->status = -ENOENT; } else { mcp->status = !!data[mcp->gp_idx]; - mcp->gpio_dir = !!data[mcp->gp_idx + 1]; + mcp->gpio_dir = data[mcp->gp_idx + 1]; } break; default: @@ -860,7 +890,7 @@ static int mcp2221_probe(struct hid_device *hdev, mcp->gc->get_direction = mcp_gpio_get_direction; mcp->gc->set = mcp_gpio_set; mcp->gc->get = mcp_gpio_get; - mcp->gc->ngpio = 4; + mcp->gc->ngpio = MCP_NGPIO; mcp->gc->base = -1; mcp->gc->can_sleep = 1; mcp->gc->parent = &hdev->dev; -- cgit v1.2.3 From 46233e91fa24a91bffca0680b1c55282ba601918 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Tue, 13 Oct 2020 14:44:27 +0200 Subject: media: mtk-vcodec: move firmware implementations into their own files mtk-vcodec supports two kinds of firmware, VPU and SCP. Both were supported from the same source files, but this is clearly unclean and makes it more difficult to disable support for one or the other. Move these implementations into their own file, after adding the necessary private interfaces. [hverkuil: smatch fix: mtk_vcodec_fw_vpu_init() error: uninitialized symbol 'rst_id'.] Signed-off-by: Alexandre Courbot Signed-off-by: Hans Verkuil Fixes: bf1d556ad4e0 ("media: mtk-vcodec: abstract firmware interface") Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/mtk-vcodec/Makefile | 4 +- .../media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c | 2 +- .../media/platform/mtk-vcodec/mtk_vcodec_enc_drv.c | 2 +- drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.c | 174 +-------------------- drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.h | 7 +- .../media/platform/mtk-vcodec/mtk_vcodec_fw_priv.h | 34 ++++ .../media/platform/mtk-vcodec/mtk_vcodec_fw_scp.c | 73 +++++++++ .../media/platform/mtk-vcodec/mtk_vcodec_fw_vpu.c | 110 +++++++++++++ 8 files changed, 233 insertions(+), 173 deletions(-) create mode 100644 drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_priv.h create mode 100644 drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_scp.c create mode 100644 drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_vpu.c diff --git a/drivers/media/platform/mtk-vcodec/Makefile b/drivers/media/platform/mtk-vcodec/Makefile index f679c6e1a3e9..6e1ea3a9f052 100644 --- a/drivers/media/platform/mtk-vcodec/Makefile +++ b/drivers/media/platform/mtk-vcodec/Makefile @@ -24,4 +24,6 @@ mtk-vcodec-enc-y := venc/venc_vp8_if.o \ mtk-vcodec-common-y := mtk_vcodec_intr.o \ mtk_vcodec_util.o \ - mtk_vcodec_fw.o + mtk_vcodec_fw.o \ + mtk_vcodec_fw_vpu.o \ + mtk_vcodec_fw_scp.o diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c index d14bc208ea5e..145686d2c219 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c @@ -241,7 +241,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev) } dma_set_max_seg_size(&pdev->dev, DMA_BIT_MASK(32)); - dev->fw_handler = mtk_vcodec_fw_select(dev, fw_type, VPU_RST_DEC); + dev->fw_handler = mtk_vcodec_fw_select(dev, fw_type, DECODER); if (IS_ERR(dev->fw_handler)) return PTR_ERR(dev->fw_handler); diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_drv.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_drv.c index dcfa2c2d4def..3be8a04c4c67 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_drv.c +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_drv.c @@ -293,7 +293,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev) } dma_set_max_seg_size(&pdev->dev, DMA_BIT_MASK(32)); - dev->fw_handler = mtk_vcodec_fw_select(dev, fw_type, VPU_RST_ENC); + dev->fw_handler = mtk_vcodec_fw_select(dev, fw_type, ENCODER); if (IS_ERR(dev->fw_handler)) return PTR_ERR(dev->fw_handler); diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.c index 6c2a2568d844..94b39ae5c2e1 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.c +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.c @@ -1,193 +1,29 @@ // SPDX-License-Identifier: GPL-2.0 #include "mtk_vcodec_fw.h" +#include "mtk_vcodec_fw_priv.h" #include "mtk_vcodec_util.h" #include "mtk_vcodec_drv.h" -struct mtk_vcodec_fw_ops { - int (*load_firmware)(struct mtk_vcodec_fw *fw); - unsigned int (*get_vdec_capa)(struct mtk_vcodec_fw *fw); - unsigned int (*get_venc_capa)(struct mtk_vcodec_fw *fw); - void * (*map_dm_addr)(struct mtk_vcodec_fw *fw, u32 dtcm_dmem_addr); - int (*ipi_register)(struct mtk_vcodec_fw *fw, int id, - mtk_vcodec_ipi_handler handler, const char *name, void *priv); - int (*ipi_send)(struct mtk_vcodec_fw *fw, int id, void *buf, - unsigned int len, unsigned int wait); -}; - -struct mtk_vcodec_fw { - enum mtk_vcodec_fw_type type; - const struct mtk_vcodec_fw_ops *ops; - struct platform_device *pdev; - struct mtk_scp *scp; -}; - -static int mtk_vcodec_vpu_load_firmware(struct mtk_vcodec_fw *fw) -{ - return vpu_load_firmware(fw->pdev); -} - -static unsigned int mtk_vcodec_vpu_get_vdec_capa(struct mtk_vcodec_fw *fw) -{ - return vpu_get_vdec_hw_capa(fw->pdev); -} - -static unsigned int mtk_vcodec_vpu_get_venc_capa(struct mtk_vcodec_fw *fw) -{ - return vpu_get_venc_hw_capa(fw->pdev); -} - -static void *mtk_vcodec_vpu_map_dm_addr(struct mtk_vcodec_fw *fw, - u32 dtcm_dmem_addr) -{ - return vpu_mapping_dm_addr(fw->pdev, dtcm_dmem_addr); -} - -static int mtk_vcodec_vpu_set_ipi_register(struct mtk_vcodec_fw *fw, int id, - mtk_vcodec_ipi_handler handler, - const char *name, void *priv) -{ - /* - * The handler we receive takes a void * as its first argument. We - * cannot change this because it needs to be passed down to the rproc - * subsystem when SCP is used. VPU takes a const argument, which is - * more constrained, so the conversion below is safe. - */ - ipi_handler_t handler_const = (ipi_handler_t)handler; - - return vpu_ipi_register(fw->pdev, id, handler_const, name, priv); -} - -static int mtk_vcodec_vpu_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf, - unsigned int len, unsigned int wait) -{ - return vpu_ipi_send(fw->pdev, id, buf, len); -} - -static const struct mtk_vcodec_fw_ops mtk_vcodec_vpu_msg = { - .load_firmware = mtk_vcodec_vpu_load_firmware, - .get_vdec_capa = mtk_vcodec_vpu_get_vdec_capa, - .get_venc_capa = mtk_vcodec_vpu_get_venc_capa, - .map_dm_addr = mtk_vcodec_vpu_map_dm_addr, - .ipi_register = mtk_vcodec_vpu_set_ipi_register, - .ipi_send = mtk_vcodec_vpu_ipi_send, -}; - -static int mtk_vcodec_scp_load_firmware(struct mtk_vcodec_fw *fw) -{ - return rproc_boot(scp_get_rproc(fw->scp)); -} - -static unsigned int mtk_vcodec_scp_get_vdec_capa(struct mtk_vcodec_fw *fw) -{ - return scp_get_vdec_hw_capa(fw->scp); -} - -static unsigned int mtk_vcodec_scp_get_venc_capa(struct mtk_vcodec_fw *fw) -{ - return scp_get_venc_hw_capa(fw->scp); -} - -static void *mtk_vcodec_vpu_scp_dm_addr(struct mtk_vcodec_fw *fw, - u32 dtcm_dmem_addr) -{ - return scp_mapping_dm_addr(fw->scp, dtcm_dmem_addr); -} - -static int mtk_vcodec_scp_set_ipi_register(struct mtk_vcodec_fw *fw, int id, - mtk_vcodec_ipi_handler handler, - const char *name, void *priv) -{ - return scp_ipi_register(fw->scp, id, handler, priv); -} - -static int mtk_vcodec_scp_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf, - unsigned int len, unsigned int wait) -{ - return scp_ipi_send(fw->scp, id, buf, len, wait); -} - -static const struct mtk_vcodec_fw_ops mtk_vcodec_rproc_msg = { - .load_firmware = mtk_vcodec_scp_load_firmware, - .get_vdec_capa = mtk_vcodec_scp_get_vdec_capa, - .get_venc_capa = mtk_vcodec_scp_get_venc_capa, - .map_dm_addr = mtk_vcodec_vpu_scp_dm_addr, - .ipi_register = mtk_vcodec_scp_set_ipi_register, - .ipi_send = mtk_vcodec_scp_ipi_send, -}; - -static void mtk_vcodec_reset_handler(void *priv) -{ - struct mtk_vcodec_dev *dev = priv; - struct mtk_vcodec_ctx *ctx; - - mtk_v4l2_err("Watchdog timeout!!"); - - mutex_lock(&dev->dev_mutex); - list_for_each_entry(ctx, &dev->ctx_list, list) { - ctx->state = MTK_STATE_ABORT; - mtk_v4l2_debug(0, "[%d] Change to state MTK_STATE_ABORT", - ctx->id); - } - mutex_unlock(&dev->dev_mutex); -} - struct mtk_vcodec_fw *mtk_vcodec_fw_select(struct mtk_vcodec_dev *dev, enum mtk_vcodec_fw_type type, - enum rst_id rst_id) + enum mtk_vcodec_fw_use fw_use) { - const struct mtk_vcodec_fw_ops *ops; - struct mtk_vcodec_fw *fw; - struct platform_device *fw_pdev = NULL; - struct mtk_scp *scp = NULL; - switch (type) { case VPU: - ops = &mtk_vcodec_vpu_msg; - fw_pdev = vpu_get_plat_device(dev->plat_dev); - if (!fw_pdev) { - mtk_v4l2_err("firmware device is not ready"); - return ERR_PTR(-EINVAL); - } - vpu_wdt_reg_handler(fw_pdev, mtk_vcodec_reset_handler, - dev, rst_id); - break; + return mtk_vcodec_fw_vpu_init(dev, fw_use); case SCP: - ops = &mtk_vcodec_rproc_msg; - scp = scp_get(dev->plat_dev); - if (!scp) { - mtk_v4l2_err("could not get vdec scp handle"); - return ERR_PTR(-EPROBE_DEFER); - } - break; + return mtk_vcodec_fw_scp_init(dev); default: mtk_v4l2_err("invalid vcodec fw type"); return ERR_PTR(-EINVAL); } - - fw = devm_kzalloc(&dev->plat_dev->dev, sizeof(*fw), GFP_KERNEL); - if (!fw) - return ERR_PTR(-EINVAL); - - fw->type = type; - fw->ops = ops; - fw->pdev = fw_pdev; - fw->scp = scp; - - return fw; } EXPORT_SYMBOL_GPL(mtk_vcodec_fw_select); void mtk_vcodec_fw_release(struct mtk_vcodec_fw *fw) { - switch (fw->type) { - case VPU: - put_device(&fw->pdev->dev); - break; - case SCP: - scp_put(fw->scp); - break; - } + fw->ops->release(fw); } EXPORT_SYMBOL_GPL(mtk_vcodec_fw_release); diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.h index fadbbe6ba6cd..539bb626772c 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.h +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.h @@ -15,6 +15,11 @@ enum mtk_vcodec_fw_type { SCP, }; +enum mtk_vcodec_fw_use { + DECODER, + ENCODER, +}; + struct mtk_vcodec_fw; typedef void (*mtk_vcodec_ipi_handler) (void *data, @@ -22,7 +27,7 @@ typedef void (*mtk_vcodec_ipi_handler) (void *data, struct mtk_vcodec_fw *mtk_vcodec_fw_select(struct mtk_vcodec_dev *dev, enum mtk_vcodec_fw_type type, - enum rst_id rst_id); + enum mtk_vcodec_fw_use fw_use); void mtk_vcodec_fw_release(struct mtk_vcodec_fw *fw); int mtk_vcodec_fw_load_firmware(struct mtk_vcodec_fw *fw); diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_priv.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_priv.h new file mode 100644 index 000000000000..51f1694a7c7d --- /dev/null +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_priv.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _MTK_VCODEC_FW_PRIV_H_ +#define _MTK_VCODEC_FW_PRIV_H_ + +#include "mtk_vcodec_fw.h" + +struct mtk_vcodec_dev; + +struct mtk_vcodec_fw { + enum mtk_vcodec_fw_type type; + const struct mtk_vcodec_fw_ops *ops; + struct platform_device *pdev; + struct mtk_scp *scp; +}; + +struct mtk_vcodec_fw_ops { + int (*load_firmware)(struct mtk_vcodec_fw *fw); + unsigned int (*get_vdec_capa)(struct mtk_vcodec_fw *fw); + unsigned int (*get_venc_capa)(struct mtk_vcodec_fw *fw); + void *(*map_dm_addr)(struct mtk_vcodec_fw *fw, u32 dtcm_dmem_addr); + int (*ipi_register)(struct mtk_vcodec_fw *fw, int id, + mtk_vcodec_ipi_handler handler, const char *name, + void *priv); + int (*ipi_send)(struct mtk_vcodec_fw *fw, int id, void *buf, + unsigned int len, unsigned int wait); + void (*release)(struct mtk_vcodec_fw *fw); +}; + +struct mtk_vcodec_fw *mtk_vcodec_fw_vpu_init(struct mtk_vcodec_dev *dev, + enum mtk_vcodec_fw_use fw_use); +struct mtk_vcodec_fw *mtk_vcodec_fw_scp_init(struct mtk_vcodec_dev *dev); + +#endif /* _MTK_VCODEC_FW_PRIV_H_ */ diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_scp.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_scp.c new file mode 100644 index 000000000000..d8e66b645bd8 --- /dev/null +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_scp.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "mtk_vcodec_fw_priv.h" +#include "mtk_vcodec_util.h" +#include "mtk_vcodec_drv.h" + +static int mtk_vcodec_scp_load_firmware(struct mtk_vcodec_fw *fw) +{ + return rproc_boot(scp_get_rproc(fw->scp)); +} + +static unsigned int mtk_vcodec_scp_get_vdec_capa(struct mtk_vcodec_fw *fw) +{ + return scp_get_vdec_hw_capa(fw->scp); +} + +static unsigned int mtk_vcodec_scp_get_venc_capa(struct mtk_vcodec_fw *fw) +{ + return scp_get_venc_hw_capa(fw->scp); +} + +static void *mtk_vcodec_vpu_scp_dm_addr(struct mtk_vcodec_fw *fw, + u32 dtcm_dmem_addr) +{ + return scp_mapping_dm_addr(fw->scp, dtcm_dmem_addr); +} + +static int mtk_vcodec_scp_set_ipi_register(struct mtk_vcodec_fw *fw, int id, + mtk_vcodec_ipi_handler handler, + const char *name, void *priv) +{ + return scp_ipi_register(fw->scp, id, handler, priv); +} + +static int mtk_vcodec_scp_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf, + unsigned int len, unsigned int wait) +{ + return scp_ipi_send(fw->scp, id, buf, len, wait); +} + +static void mtk_vcodec_scp_release(struct mtk_vcodec_fw *fw) +{ + scp_put(fw->scp); +} + +static const struct mtk_vcodec_fw_ops mtk_vcodec_rproc_msg = { + .load_firmware = mtk_vcodec_scp_load_firmware, + .get_vdec_capa = mtk_vcodec_scp_get_vdec_capa, + .get_venc_capa = mtk_vcodec_scp_get_venc_capa, + .map_dm_addr = mtk_vcodec_vpu_scp_dm_addr, + .ipi_register = mtk_vcodec_scp_set_ipi_register, + .ipi_send = mtk_vcodec_scp_ipi_send, + .release = mtk_vcodec_scp_release, +}; + +struct mtk_vcodec_fw *mtk_vcodec_fw_scp_init(struct mtk_vcodec_dev *dev) +{ + struct mtk_vcodec_fw *fw; + struct mtk_scp *scp; + + scp = scp_get(dev->plat_dev); + if (!scp) { + mtk_v4l2_err("could not get vdec scp handle"); + return ERR_PTR(-EPROBE_DEFER); + } + + fw = devm_kzalloc(&dev->plat_dev->dev, sizeof(*fw), GFP_KERNEL); + fw->type = SCP; + fw->ops = &mtk_vcodec_rproc_msg; + fw->scp = scp; + + return fw; +} diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_vpu.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_vpu.c new file mode 100644 index 000000000000..cd27f637dbe7 --- /dev/null +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_vpu.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "mtk_vcodec_fw_priv.h" +#include "mtk_vcodec_util.h" +#include "mtk_vcodec_drv.h" + +static int mtk_vcodec_vpu_load_firmware(struct mtk_vcodec_fw *fw) +{ + return vpu_load_firmware(fw->pdev); +} + +static unsigned int mtk_vcodec_vpu_get_vdec_capa(struct mtk_vcodec_fw *fw) +{ + return vpu_get_vdec_hw_capa(fw->pdev); +} + +static unsigned int mtk_vcodec_vpu_get_venc_capa(struct mtk_vcodec_fw *fw) +{ + return vpu_get_venc_hw_capa(fw->pdev); +} + +static void *mtk_vcodec_vpu_map_dm_addr(struct mtk_vcodec_fw *fw, + u32 dtcm_dmem_addr) +{ + return vpu_mapping_dm_addr(fw->pdev, dtcm_dmem_addr); +} + +static int mtk_vcodec_vpu_set_ipi_register(struct mtk_vcodec_fw *fw, int id, + mtk_vcodec_ipi_handler handler, + const char *name, void *priv) +{ + /* + * The handler we receive takes a void * as its first argument. We + * cannot change this because it needs to be passed down to the rproc + * subsystem when SCP is used. VPU takes a const argument, which is + * more constrained, so the conversion below is safe. + */ + ipi_handler_t handler_const = (ipi_handler_t)handler; + + return vpu_ipi_register(fw->pdev, id, handler_const, name, priv); +} + +static int mtk_vcodec_vpu_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf, + unsigned int len, unsigned int wait) +{ + return vpu_ipi_send(fw->pdev, id, buf, len); +} + +static void mtk_vcodec_vpu_release(struct mtk_vcodec_fw *fw) +{ + put_device(&fw->pdev->dev); +} + +static void mtk_vcodec_vpu_reset_handler(void *priv) +{ + struct mtk_vcodec_dev *dev = priv; + struct mtk_vcodec_ctx *ctx; + + mtk_v4l2_err("Watchdog timeout!!"); + + mutex_lock(&dev->dev_mutex); + list_for_each_entry(ctx, &dev->ctx_list, list) { + ctx->state = MTK_STATE_ABORT; + mtk_v4l2_debug(0, "[%d] Change to state MTK_STATE_ABORT", + ctx->id); + } + mutex_unlock(&dev->dev_mutex); +} + +static const struct mtk_vcodec_fw_ops mtk_vcodec_vpu_msg = { + .load_firmware = mtk_vcodec_vpu_load_firmware, + .get_vdec_capa = mtk_vcodec_vpu_get_vdec_capa, + .get_venc_capa = mtk_vcodec_vpu_get_venc_capa, + .map_dm_addr = mtk_vcodec_vpu_map_dm_addr, + .ipi_register = mtk_vcodec_vpu_set_ipi_register, + .ipi_send = mtk_vcodec_vpu_ipi_send, + .release = mtk_vcodec_vpu_release, +}; + +struct mtk_vcodec_fw *mtk_vcodec_fw_vpu_init(struct mtk_vcodec_dev *dev, + enum mtk_vcodec_fw_use fw_use) +{ + struct platform_device *fw_pdev; + struct mtk_vcodec_fw *fw; + enum rst_id rst_id; + + switch (fw_use) { + case ENCODER: + rst_id = VPU_RST_ENC; + break; + case DECODER: + default: + rst_id = VPU_RST_DEC; + break; + } + + fw_pdev = vpu_get_plat_device(dev->plat_dev); + if (!fw_pdev) { + mtk_v4l2_err("firmware device is not ready"); + return ERR_PTR(-EINVAL); + } + vpu_wdt_reg_handler(fw_pdev, mtk_vcodec_vpu_reset_handler, dev, rst_id); + + fw = devm_kzalloc(&dev->plat_dev->dev, sizeof(*fw), GFP_KERNEL); + fw->type = VPU; + fw->ops = &mtk_vcodec_vpu_msg; + fw->pdev = fw_pdev; + + return fw; +} -- cgit v1.2.3 From 2da185d6fe969ade346ad03461c3da860c602503 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Tue, 13 Oct 2020 14:44:28 +0200 Subject: media: mtk-vcodec: fix build breakage when one of VPU or SCP is enabled The addition of MT8183 support added a dependency on the SCP remoteproc module. However the initial patch used the "select" Kconfig directive, which may result in the SCP module to not be compiled if remoteproc was disabled. In such a case, mtk-vcodec would try to link against non-existent SCP symbols. "select" was clearly misused here as explained in kconfig-language.txt. Replace this by a "depends" directive on at least one of the VPU and SCP modules, to allow the driver to be compiled as long as one of these is enabled, and adapt the code to support this new scenario. Also adapt the Kconfig text to explain the extra requirements for MT8173 and MT8183. Reported-by: Sakari Ailus Signed-off-by: Alexandre Courbot Signed-off-by: Hans Verkuil Fixes: bf1d556ad4e0 ("media: mtk-vcodec: abstract firmware interface") Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/Kconfig | 28 ++++++++++++++++------ drivers/media/platform/mtk-vcodec/Makefile | 10 ++++++-- .../media/platform/mtk-vcodec/mtk_vcodec_fw_priv.h | 18 ++++++++++++++ 3 files changed, 47 insertions(+), 9 deletions(-) diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig index a3cb104956d5..7e152bbb4fa6 100644 --- a/drivers/media/platform/Kconfig +++ b/drivers/media/platform/Kconfig @@ -253,17 +253,31 @@ config VIDEO_MEDIATEK_VCODEC depends on MTK_IOMMU || COMPILE_TEST depends on VIDEO_DEV && VIDEO_V4L2 depends on ARCH_MEDIATEK || COMPILE_TEST + depends on VIDEO_MEDIATEK_VPU || MTK_SCP + # The two following lines ensure we have the same state ("m" or "y") as + # our dependencies, to avoid missing symbols during link. + depends on VIDEO_MEDIATEK_VPU || !VIDEO_MEDIATEK_VPU + depends on MTK_SCP || !MTK_SCP select VIDEOBUF2_DMA_CONTIG select V4L2_MEM2MEM_DEV - select VIDEO_MEDIATEK_VPU - select MTK_SCP + select VIDEO_MEDIATEK_VCODEC_VPU if VIDEO_MEDIATEK_VPU + select VIDEO_MEDIATEK_VCODEC_SCP if MTK_SCP help - Mediatek video codec driver provides HW capability to - encode and decode in a range of video formats - This driver rely on VPU driver to communicate with VPU. + Mediatek video codec driver provides HW capability to + encode and decode in a range of video formats on MT8173 + and MT8183. + + Note that support for MT8173 requires VIDEO_MEDIATEK_VPU to + also be selected. Support for MT8183 depends on MTK_SCP. + + To compile this driver as modules, choose M here: the + modules will be called mtk-vcodec-dec and mtk-vcodec-enc. + +config VIDEO_MEDIATEK_VCODEC_VPU + bool - To compile this driver as modules, choose M here: the - modules will be called mtk-vcodec-dec and mtk-vcodec-enc. +config VIDEO_MEDIATEK_VCODEC_SCP + bool config VIDEO_MEM2MEM_DEINTERLACE tristate "Deinterlace support" diff --git a/drivers/media/platform/mtk-vcodec/Makefile b/drivers/media/platform/mtk-vcodec/Makefile index 6e1ea3a9f052..4618d43dbbc8 100644 --- a/drivers/media/platform/mtk-vcodec/Makefile +++ b/drivers/media/platform/mtk-vcodec/Makefile @@ -25,5 +25,11 @@ mtk-vcodec-enc-y := venc/venc_vp8_if.o \ mtk-vcodec-common-y := mtk_vcodec_intr.o \ mtk_vcodec_util.o \ mtk_vcodec_fw.o \ - mtk_vcodec_fw_vpu.o \ - mtk_vcodec_fw_scp.o + +ifneq ($(CONFIG_VIDEO_MEDIATEK_VCODEC_VPU),) +mtk-vcodec-common-y += mtk_vcodec_fw_vpu.o +endif + +ifneq ($(CONFIG_VIDEO_MEDIATEK_VCODEC_SCP),) +mtk-vcodec-common-y += mtk_vcodec_fw_scp.o +endif diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_priv.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_priv.h index 51f1694a7c7d..b41e66185cec 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_priv.h +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_priv.h @@ -27,8 +27,26 @@ struct mtk_vcodec_fw_ops { void (*release)(struct mtk_vcodec_fw *fw); }; +#if IS_ENABLED(CONFIG_VIDEO_MEDIATEK_VCODEC_VPU) struct mtk_vcodec_fw *mtk_vcodec_fw_vpu_init(struct mtk_vcodec_dev *dev, enum mtk_vcodec_fw_use fw_use); +#else +static inline struct mtk_vcodec_fw * +mtk_vcodec_fw_vpu_init(struct mtk_vcodec_dev *dev, + enum mtk_vcodec_fw_use fw_use) +{ + return ERR_PTR(-ENODEV); +} +#endif /* CONFIG_VIDEO_MEDIATEK_VCODEC_VPU */ + +#if IS_ENABLED(CONFIG_VIDEO_MEDIATEK_VCODEC_SCP) struct mtk_vcodec_fw *mtk_vcodec_fw_scp_init(struct mtk_vcodec_dev *dev); +#else +static inline struct mtk_vcodec_fw * +mtk_vcodec_fw_scp_init(struct mtk_vcodec_dev *dev) +{ + return ERR_PTR(-ENODEV); +} +#endif /* CONFIG_VIDEO_MEDIATEK_VCODEC_SCP */ #endif /* _MTK_VCODEC_FW_PRIV_H_ */ -- cgit v1.2.3 From e6fcf468c51da28c56ea447e147475a731acbdf1 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 20 Oct 2020 08:02:04 +0200 Subject: media: media/platform/marvell-ccic: fix warnings when CONFIG_PM is not enabled Fix build warnings when CONFIG_PM is not set/enabled: ../drivers/media/platform/marvell-ccic/mmp-driver.c:324:12: warning: 'mmpcam_runtime_suspend' defined but not used [-Wunused-function] 324 | static int mmpcam_runtime_suspend(struct device *dev) ../drivers/media/platform/marvell-ccic/mmp-driver.c:310:12: warning: 'mmpcam_runtime_resume' defined but not used [-Wunused-function] 310 | static int mmpcam_runtime_resume(struct device *dev) Signed-off-by: Randy Dunlap Cc: Jonathan Corbet Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/marvell-ccic/mmp-driver.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/media/platform/marvell-ccic/mmp-driver.c b/drivers/media/platform/marvell-ccic/mmp-driver.c index cd902b180669..63fce1b85d26 100644 --- a/drivers/media/platform/marvell-ccic/mmp-driver.c +++ b/drivers/media/platform/marvell-ccic/mmp-driver.c @@ -307,6 +307,7 @@ static int mmpcam_platform_remove(struct platform_device *pdev) * Suspend/resume support. */ +#ifdef CONFIG_PM static int mmpcam_runtime_resume(struct device *dev) { struct mmp_camera *cam = dev_get_drvdata(dev); @@ -352,6 +353,7 @@ static int __maybe_unused mmpcam_resume(struct device *dev) return mccic_resume(&cam->mcam); return 0; } +#endif static const struct dev_pm_ops mmpcam_pm_ops = { SET_RUNTIME_PM_OPS(mmpcam_runtime_suspend, mmpcam_runtime_resume, NULL) -- cgit v1.2.3 From 9ac924b98728c3733c91c6c59fc410827d0da49f Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Wed, 21 Oct 2020 22:33:25 +0200 Subject: media: cedrus: h264: Fix check for presence of scaling matrix If scaling matrix control is present, VPU should not use default matrix. Fix that. Fixes: b3a23db0e2f8 ("media: cedrus: Use H264_SCALING_MATRIX only when required") Signed-off-by: Jernej Skrabec Acked-by: Maxime Ripard Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/staging/media/sunxi/cedrus/cedrus_h264.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c index 28319351e909..781c84a9b1b7 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c @@ -446,7 +446,7 @@ static void cedrus_set_params(struct cedrus_ctx *ctx, reg |= (pps->second_chroma_qp_index_offset & 0x3f) << 16; reg |= (pps->chroma_qp_index_offset & 0x3f) << 8; reg |= (pps->pic_init_qp_minus26 + 26 + slice->slice_qp_delta) & 0x3f; - if (pps->flags & V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT) + if (!(pps->flags & V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT)) reg |= VE_H264_SHS_QP_SCALING_MATRIX_DEFAULT; cedrus_write(dev, VE_H264_SHS_QP, reg); -- cgit v1.2.3 From 93bd813c17763177cf87e96c2313bd4dd747d234 Mon Sep 17 00:00:00 2001 From: Jack Yu Date: Thu, 5 Nov 2020 11:08:04 +0800 Subject: ASoC: rt1015: add delay to fix pop noise from speaker Add delay to fix pop noise from speaker. Signed-off-by: Jack Yu Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20201105030804.31115-1-jack.yu@realtek.com Signed-off-by: Mark Brown --- Documentation/devicetree/bindings/sound/rt1015.txt | 6 ++++++ include/sound/rt1015.h | 15 +++++++++++++++ sound/soc/codecs/rt1015.c | 20 ++++++++++++++++++++ sound/soc/codecs/rt1015.h | 2 ++ 4 files changed, 43 insertions(+) create mode 100644 include/sound/rt1015.h diff --git a/Documentation/devicetree/bindings/sound/rt1015.txt b/Documentation/devicetree/bindings/sound/rt1015.txt index fcfd02d8d32f..e498966d436f 100644 --- a/Documentation/devicetree/bindings/sound/rt1015.txt +++ b/Documentation/devicetree/bindings/sound/rt1015.txt @@ -8,10 +8,16 @@ Required properties: - reg : The I2C address of the device. +Optional properties: + +- realtek,power-up-delay-ms + Set a delay time for flush work to be completed, + this value is adjustable depending on platform. Example: rt1015: codec@28 { compatible = "realtek,rt1015"; reg = <0x28>; + realtek,power-up-delay-ms = <50>; }; diff --git a/include/sound/rt1015.h b/include/sound/rt1015.h new file mode 100644 index 000000000000..70a7538d4c89 --- /dev/null +++ b/include/sound/rt1015.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/sound/rt1015.h -- Platform data for RT1015 + * + * Copyright 2020 Realtek Microelectronics + */ + +#ifndef __LINUX_SND_RT1015_H +#define __LINUX_SND_RT1015_H + +struct rt1015_platform_data { + unsigned int power_up_delay_ms; +}; + +#endif diff --git a/sound/soc/codecs/rt1015.c b/sound/soc/codecs/rt1015.c index 25fe2ddedd54..967193518349 100644 --- a/sound/soc/codecs/rt1015.c +++ b/sound/soc/codecs/rt1015.c @@ -27,10 +27,15 @@ #include #include #include +#include #include "rl6231.h" #include "rt1015.h" +static const struct rt1015_platform_data i2s_default_platform_data = { + .power_up_delay_ms = 50, +}; + static const struct reg_default rt1015_reg[] = { { 0x0000, 0x0000 }, { 0x0004, 0xa000 }, @@ -650,6 +655,7 @@ static int rt1015_amp_drv_event(struct snd_soc_dapm_widget *w, case SND_SOC_DAPM_POST_PMU: if (rt1015->hw_config == RT1015_HW_28) schedule_delayed_work(&rt1015->flush_work, msecs_to_jiffies(10)); + msleep(rt1015->pdata.power_up_delay_ms); break; default: break; @@ -1067,9 +1073,16 @@ static struct acpi_device_id rt1015_acpi_match[] = { MODULE_DEVICE_TABLE(acpi, rt1015_acpi_match); #endif +static void rt1015_parse_dt(struct rt1015_priv *rt1015, struct device *dev) +{ + device_property_read_u32(dev, "realtek,power-up-delay-ms", + &rt1015->pdata.power_up_delay_ms); +} + static int rt1015_i2c_probe(struct i2c_client *i2c, const struct i2c_device_id *id) { + struct rt1015_platform_data *pdata = dev_get_platdata(&i2c->dev); struct rt1015_priv *rt1015; int ret; unsigned int val; @@ -1081,6 +1094,13 @@ static int rt1015_i2c_probe(struct i2c_client *i2c, i2c_set_clientdata(i2c, rt1015); + rt1015->pdata = i2s_default_platform_data; + + if (pdata) + rt1015->pdata = *pdata; + else + rt1015_parse_dt(rt1015, &i2c->dev); + rt1015->regmap = devm_regmap_init_i2c(i2c, &rt1015_regmap); if (IS_ERR(rt1015->regmap)) { ret = PTR_ERR(rt1015->regmap); diff --git a/sound/soc/codecs/rt1015.h b/sound/soc/codecs/rt1015.h index d3fdd30aca6d..15cadb361ec3 100644 --- a/sound/soc/codecs/rt1015.h +++ b/sound/soc/codecs/rt1015.h @@ -12,6 +12,7 @@ #ifndef __RT1015_H__ #define __RT1015_H__ +#include #define RT1015_DEVICE_ID_VAL 0x1011 #define RT1015_DEVICE_ID_VAL2 0x1015 @@ -380,6 +381,7 @@ enum { struct rt1015_priv { struct snd_soc_component *component; + struct rt1015_platform_data pdata; struct regmap *regmap; int sysclk; int sysclk_src; -- cgit v1.2.3 From 397a973b9978533418892c6453853c52b2ad8ec6 Mon Sep 17 00:00:00 2001 From: Yan-Hsuan Chuang Date: Mon, 12 Oct 2020 16:11:40 +0800 Subject: MAINTAINERS: update Yan-Hsuan's email address Switch my email to gmail.com address. Signed-off-by: Yan-Hsuan Chuang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20201012081140.18085-1-tony0620emma@gmail.com --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index e73636b75f29..bd2d28cfdb4e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14831,7 +14831,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.g F: drivers/net/wireless/realtek/rtlwifi/ REALTEK WIRELESS DRIVER (rtw88) -M: Yan-Hsuan Chuang +M: Yan-Hsuan Chuang L: linux-wireless@vger.kernel.org S: Maintained F: drivers/net/wireless/realtek/rtw88/ -- cgit v1.2.3 From d85b4b2bf2d4229847d76cfd81e48d5beb72f75b Mon Sep 17 00:00:00 2001 From: Chi-Hsien Lin Date: Fri, 30 Oct 2020 03:56:10 -0500 Subject: MAINTAINERS: update maintainers list for Cypress - Update maintainers' email with Infineon hosted email - Add Chung-hsien Hsu as a maintainer Signed-off-by: Chi-Hsien Lin Signed-off-by: Wright Feng Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20201030085610.145679-1-chi-hsien.lin@cypress.com --- MAINTAINERS | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index bd2d28cfdb4e..900ff33789eb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3541,11 +3541,12 @@ BROADCOM BRCM80211 IEEE802.11n WIRELESS DRIVER M: Arend van Spriel M: Franky Lin M: Hante Meuleman -M: Chi-Hsien Lin -M: Wright Feng +M: Chi-hsien Lin +M: Wright Feng +M: Chung-hsien Hsu L: linux-wireless@vger.kernel.org L: brcm80211-dev-list.pdl@broadcom.com -L: brcm80211-dev-list@cypress.com +L: SHA-cyfmac-dev-list@infineon.com S: Supported F: drivers/net/wireless/broadcom/brcm80211/ -- cgit v1.2.3 From 90574a9c02f1ed46d9d8fec222fbcf375eb90e9b Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Fri, 6 Nov 2020 04:40:05 +0100 Subject: printk: remove unneeded dead-store assignment make clang-analyzer on x86_64 defconfig caught my attention with: kernel/printk/printk_ringbuffer.c:885:3: warning: Value stored to 'desc' is never read [clang-analyzer-deadcode.DeadStores] desc = to_desc(desc_ring, head_id); ^ Commit b6cf8b3f3312 ("printk: add lockless ringbuffer") introduced desc_reserve() with this unneeded dead-store assignment. As discussed with John Ogness privately, this is probably just some minor left-over from previous iterations of the ringbuffer implementation. So, simply remove this unneeded dead assignment to make clang-analyzer happy. As compilers will detect this unneeded assignment and optimize this anyway, the resulting object code is identical before and after this change. No functional change. No change to object code. Signed-off-by: Lukas Bulwahn Reviewed-by: Sergey Senozhatsky Reviewed-by: John Ogness Reviewed-by: Nathan Chancellor Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20201106034005.18822-1-lukas.bulwahn@gmail.com --- kernel/printk/printk_ringbuffer.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c index 24a960a89aa8..dd43c4cf16fb 100644 --- a/kernel/printk/printk_ringbuffer.c +++ b/kernel/printk/printk_ringbuffer.c @@ -882,8 +882,6 @@ static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out) head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */ do { - desc = to_desc(desc_ring, head_id); - id = DESC_ID(head_id + 1); id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id); -- cgit v1.2.3 From e2b2e4386cb7a5e935dff388cf8961317daf39ce Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 2 Nov 2020 21:25:15 +0100 Subject: staging: mt7621-pci: avoid to request pci bus resources After upgrading kernel to version 5.9.x the driver was not working anymore showing the following kernel trace: ... mt7621-pci 1e140000.pcie: resource collision: [mem 0x60000000-0x6fffffff] conflicts with pcie@1e140000 [mem 0x60000000-0x6fffffff] ------------[ cut here ]------------ WARNING: CPU: 2 PID: 73 at kernel/resource.c:1400 devm_request_resource+0xfc/0x10c Modules linked in: CPU: 2 PID: 73 Comm: kworker/2:1 Not tainted 5.9.2 #0 Workqueue: events deferred_probe_work_func Stack : 00000000 81590000 807d0a1c 808a0000 8fd49080 807d0000 00000009 808ac820 00000001 808338d0 7fff0001 800839dc 00000049 00000001 8fe51b00 367204ab 00000000 00000000 807d0a1c 807c0000 00000001 80082358 8fe50000 00559000 00000000 8fe519f1 ffffffff 00000005 00000000 00000001 00000000 807d0000 00000009 808ac820 00000001 808338d0 00000001 803bf1b0 00000008 81390008 Call Trace: [<8000d018>] show_stack+0x30/0x100 [<8032e66c>] dump_stack+0xa4/0xd4 [<8002db1c>] __warn+0xc0/0x134 [<8002dbec>] warn_slowpath_fmt+0x5c/0xac [<80033b34>] devm_request_resource+0xfc/0x10c [<80365ff8>] devm_request_pci_bus_resources+0x58/0xdc [<8048e13c>] mt7621_pci_probe+0x8dc/0xe48 [<803d2140>] platform_drv_probe+0x40/0x94 [<803cfd94>] really_probe+0x108/0x4ec [<803cd958>] bus_for_each_drv+0x70/0xb0 [<803d0388>] __device_attach+0xec/0x164 [<803cec8c>] bus_probe_device+0xa4/0xc0 [<803cf1c4>] deferred_probe_work_func+0x80/0xc4 [<80048444>] process_one_work+0x260/0x510 [<80048a4c>] worker_thread+0x358/0x5cc [<8004f7d0>] kthread+0x134/0x13c [<80007478>] ret_from_kernel_thread+0x14/0x1c ---[ end trace a9dd2e37537510d3 ]--- mt7621-pci 1e140000.pcie: Error requesting resources mt7621-pci: probe of 1e140000.pcie failed with error -16 ... With commit 669cbc708122 ("PCI: Move DT resource setup into devm_pci_alloc_host_bridge()"), the DT 'ranges' is parsed and populated into resources when the host bridge is allocated. The resources are requested as well, but that happens a 2nd time for this driver in mt7621_pcie_request_resources(). Hence we should avoid this second request. Also, the bus ranges was also populated by default, so we can remove it from mt7621_pcie_request_resources() to avoid the following trace if we don't avoid it: pci_bus 0000:00: busn_res: can not insert [bus 00-ff] under domain [bus 00-ff] (conflicts with (null) [bus 00-ff]) Function 'mt7621_pcie_request_resources' has been renamed into 'mt7621_pcie_add_resources' which now is a more accurate name for this function. Cc: stable@vger.kernel.org #5.9.x- Signed-off-by: Sergio Paracuellos Link: https://lore.kernel.org/r/20201102202515.19073-1-sergio.paracuellos@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/mt7621-pci/pci-mt7621.c | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) diff --git a/drivers/staging/mt7621-pci/pci-mt7621.c b/drivers/staging/mt7621-pci/pci-mt7621.c index f961b353c22e..8831db383fad 100644 --- a/drivers/staging/mt7621-pci/pci-mt7621.c +++ b/drivers/staging/mt7621-pci/pci-mt7621.c @@ -653,16 +653,11 @@ static int mt7621_pcie_init_virtual_bridges(struct mt7621_pcie *pcie) return 0; } -static int mt7621_pcie_request_resources(struct mt7621_pcie *pcie, - struct list_head *res) +static void mt7621_pcie_add_resources(struct mt7621_pcie *pcie, + struct list_head *res) { - struct device *dev = pcie->dev; - pci_add_resource_offset(res, &pcie->io, pcie->offset.io); pci_add_resource_offset(res, &pcie->mem, pcie->offset.mem); - pci_add_resource(res, &pcie->busn); - - return devm_request_pci_bus_resources(dev, res); } static int mt7621_pcie_register_host(struct pci_host_bridge *host, @@ -738,11 +733,7 @@ static int mt7621_pci_probe(struct platform_device *pdev) setup_cm_memory_region(pcie); - err = mt7621_pcie_request_resources(pcie, &res); - if (err) { - dev_err(dev, "Error requesting resources\n"); - return err; - } + mt7621_pcie_add_resources(pcie, &res); err = mt7621_pcie_register_host(bridge, &res); if (err) { -- cgit v1.2.3 From 06ea594051707c6b8834ef5b24e9b0730edd391b Mon Sep 17 00:00:00 2001 From: Necip Fazil Yildiran Date: Wed, 4 Nov 2020 21:15:23 +0300 Subject: staging: ralink-gdma: fix kconfig dependency bug for DMA_RALINK When DMA_RALINK is enabled and DMADEVICES is disabled, it results in the following Kbuild warnings: WARNING: unmet direct dependencies detected for DMA_ENGINE Depends on [n]: DMADEVICES [=n] Selected by [y]: - DMA_RALINK [=y] && STAGING [=y] && RALINK [=y] && !SOC_RT288X [=n] WARNING: unmet direct dependencies detected for DMA_VIRTUAL_CHANNELS Depends on [n]: DMADEVICES [=n] Selected by [y]: - DMA_RALINK [=y] && STAGING [=y] && RALINK [=y] && !SOC_RT288X [=n] The reason is that DMA_RALINK selects DMA_ENGINE and DMA_VIRTUAL_CHANNELS without depending on or selecting DMADEVICES while DMA_ENGINE and DMA_VIRTUAL_CHANNELS are subordinate to DMADEVICES. This can also fail building the kernel as demonstrated in a bug report. Honor the kconfig dependency to remove unmet direct dependency warnings and avoid any potential build failures. Link: https://bugzilla.kernel.org/show_bug.cgi?id=210055 Signed-off-by: Necip Fazil Yildiran Link: https://lore.kernel.org/r/20201104181522.43567-1-fazilyildiran@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/ralink-gdma/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/staging/ralink-gdma/Kconfig b/drivers/staging/ralink-gdma/Kconfig index 54e8029e6b1a..0017376234e2 100644 --- a/drivers/staging/ralink-gdma/Kconfig +++ b/drivers/staging/ralink-gdma/Kconfig @@ -2,6 +2,7 @@ config DMA_RALINK tristate "RALINK DMA support" depends on RALINK && !SOC_RT288X + depends on DMADEVICES select DMA_ENGINE select DMA_VIRTUAL_CHANNELS -- cgit v1.2.3 From aee9dccc5b64e878cf1b18207436e73f66d74157 Mon Sep 17 00:00:00 2001 From: Brian O'Keefe Date: Fri, 6 Nov 2020 10:10:34 -0500 Subject: staging: rtl8723bs: Add 024c:0627 to the list of SDIO device-ids Add 024c:0627 to the list of SDIO device-ids, based on hardware found in the wild. This hardware exists on at least some Acer SW1-011 tablets. Signed-off-by: Brian O'Keefe Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/b9e1523f-2ba7-fb82-646a-37f095b4440e@alum.wpi.edu Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/os_dep/sdio_intf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/staging/rtl8723bs/os_dep/sdio_intf.c b/drivers/staging/rtl8723bs/os_dep/sdio_intf.c index 79b55ec827a4..b2208e5f190a 100644 --- a/drivers/staging/rtl8723bs/os_dep/sdio_intf.c +++ b/drivers/staging/rtl8723bs/os_dep/sdio_intf.c @@ -20,6 +20,7 @@ static const struct sdio_device_id sdio_ids[] = { { SDIO_DEVICE(0x024c, 0x0525), }, { SDIO_DEVICE(0x024c, 0x0623), }, { SDIO_DEVICE(0x024c, 0x0626), }, + { SDIO_DEVICE(0x024c, 0x0627), }, { SDIO_DEVICE(0x024c, 0xb723), }, { /* end: all zeroes */ }, }; -- cgit v1.2.3 From 446b8185f0c39ac3faadbcd8ac156c50f2fd4ffe Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Mon, 2 Nov 2020 15:00:12 +0800 Subject: ALSA: hda/realtek - Add supported for Lenovo ThinkPad Headset Button Add supported for Lenovo ThinkPad Headset Button. Thinkpad P1 Gen 3 (0x22c1) Thinkpad X1 Extreme Gen 3 (0x22c2) Signed-off-by: Kailang Yang Cc: Link: https://lore.kernel.org/r/f39b11d00340408ca2ed2df9b4fc2a09@realtek.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 6899089d132e..c3a02738ead2 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6301,6 +6301,7 @@ enum { ALC274_FIXUP_HP_MIC, ALC274_FIXUP_HP_HEADSET_MIC, ALC256_FIXUP_ASUS_HPE, + ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, }; static const struct hda_fixup alc269_fixups[] = { @@ -7705,6 +7706,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC }, + [ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_headset_jack, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7966,6 +7973,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), + SND_PCI_QUIRK(0x17aa, 0x22c1, "Thinkpad P1 Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK), + SND_PCI_QUIRK(0x17aa, 0x22c2, "Thinkpad X1 Extreme Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), -- cgit v1.2.3 From 0011c6d182774fc781fb9e115ebe8baa356029ae Mon Sep 17 00:00:00 2001 From: Markus Reichl Date: Wed, 4 Nov 2020 17:23:55 +0100 Subject: arm64: dts: rockchip: Assign a fixed index to mmc devices on rk3399 boards. Recently introduced async probe on mmc devices can shuffle block IDs. Pin them to fixed values to ease booting in environments where UUIDs are not practical. Use newly introduced aliases for mmcblk devices from [1]. [1] https://patchwork.kernel.org/patch/11747669/ Signed-off-by: Markus Reichl Reviewed-by: Douglas Anderson Link: https://lore.kernel.org/r/20201104162356.1251-1-m.reichl@fivetechno.de Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3399.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index ada724b12f01..7a9a7aca86c6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -29,6 +29,9 @@ i2c6 = &i2c6; i2c7 = &i2c7; i2c8 = &i2c8; + mmc0 = &sdio0; + mmc1 = &sdmmc; + mmc2 = &sdhci; serial0 = &uart0; serial1 = &uart1; serial2 = &uart2; -- cgit v1.2.3 From 7327c8b98e2e14c47021eea14d1ab268086a6408 Mon Sep 17 00:00:00 2001 From: Markus Reichl Date: Wed, 4 Nov 2020 20:29:31 +0100 Subject: arm64: dts: rockchip: Reorder LED triggers from mmc devices on rk3399-roc-pc. After patch [1] SD-card becomes mmc1 and eMMC becomes mmc2. Correct trigger of LEDs accordingly. [1] https://patchwork.kernel.org/patch/11881427 Signed-off-by: Markus Reichl Link: https://lore.kernel.org/r/20201104192933.1001-1-m.reichl@fivetechno.de Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi index e7a459fa4322..20309076dbac 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi @@ -74,14 +74,14 @@ label = "red:diy"; gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>; default-state = "off"; - linux,default-trigger = "mmc1"; + linux,default-trigger = "mmc2"; }; yellow_led: led-2 { label = "yellow:yellow-led"; gpios = <&gpio0 RK_PA2 GPIO_ACTIVE_HIGH>; default-state = "off"; - linux,default-trigger = "mmc0"; + linux,default-trigger = "mmc1"; }; }; -- cgit v1.2.3 From 01776f070ffcbf336be3bf1672bd3c589548d6c4 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 7 Nov 2020 09:07:40 +0000 Subject: powerpc/32s: Use relocation offset when setting early hash table When calling early_hash_table(), the kernel hasn't been yet relocated to its linking address, so data must be addressed with relocation offset. Add relocation offset to write into Hash in early_hash_table(). Fixes: 69a1593abdbc ("powerpc/32s: Setup the early hash table at all time.") Reported-by: Erhard Furtner Reported-by: Andreas Schwab Signed-off-by: Christophe Leroy Tested-by: Serge Belyshev Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/9e225a856a8b22e0e77587ee22ab7a2f5bca8753.1604740029.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/head_book3s_32.S | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 2aa16d5368e1..a0dda2a1f2df 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -156,6 +156,7 @@ __after_mmu_off: bl initial_bats bl load_segment_registers BEGIN_MMU_FTR_SECTION + bl reloc_offset bl early_hash_table END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) #if defined(CONFIG_BOOTX_TEXT) @@ -920,7 +921,7 @@ early_hash_table: ori r6, r6, 3 /* 256kB table */ mtspr SPRN_SDR1, r6 lis r6, early_hash@h - lis r3, Hash@ha + addis r3, r3, Hash@ha stw r6, Hash@l(r3) blr -- cgit v1.2.3 From c91ebcc578e09783cfa4d85c1b437790f140f29a Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Wed, 4 Nov 2020 19:28:43 +0000 Subject: iio/adc: ingenic: Fix battery VREF for JZ4770 SoC The reference voltage for the battery is clearly marked as 1.2V in the programming manual. With this fixed, the battery channel now returns correct values. Fixes: a515d6488505 ("IIO: Ingenic JZ47xx: Add support for JZ4770 SoC ADC.") Signed-off-by: Paul Cercueil Acked-by: Artur Rojek Cc: Link: https://lore.kernel.org/r/20201104192843.67187-1-paul@crapouillou.net Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ingenic-adc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/ingenic-adc.c b/drivers/iio/adc/ingenic-adc.c index 92b25083e23f..973e84deebea 100644 --- a/drivers/iio/adc/ingenic-adc.c +++ b/drivers/iio/adc/ingenic-adc.c @@ -71,7 +71,7 @@ #define JZ4725B_ADC_BATTERY_HIGH_VREF_BITS 10 #define JZ4740_ADC_BATTERY_HIGH_VREF (7500 * 0.986) #define JZ4740_ADC_BATTERY_HIGH_VREF_BITS 12 -#define JZ4770_ADC_BATTERY_VREF 6600 +#define JZ4770_ADC_BATTERY_VREF 1200 #define JZ4770_ADC_BATTERY_VREF_BITS 12 #define JZ_ADC_IRQ_AUX BIT(0) -- cgit v1.2.3 From 6d6aa2907d59ddd3c0ebb2b93e1ddc84e474485b Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Tue, 3 Nov 2020 20:12:38 +0000 Subject: iio/adc: ingenic: Fix AUX/VBAT readings when touchscreen is used When the command feature of the ADC is used, it is possible to program the ADC, and specify at each step what input should be processed, and in comparison to what reference. This broke the AUX and battery readings when the touchscreen was enabled, most likely because the CMD feature would change the VREF all the time. Now, when AUX or battery are read, we temporarily disable the CMD feature, which means that we won't get touchscreen readings in that time frame. But it now gives correct values for AUX / battery, and the touchscreen isn't disabled for long enough to be an actual issue. Fixes: b96952f498db ("IIO: Ingenic JZ47xx: Add touchscreen mode.") Signed-off-by: Paul Cercueil Acked-by: Artur Rojek Cc: Link: https://lore.kernel.org/r/20201103201238.161083-1-paul@crapouillou.net Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ingenic-adc.c | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) diff --git a/drivers/iio/adc/ingenic-adc.c b/drivers/iio/adc/ingenic-adc.c index 973e84deebea..1aafbe2cfe67 100644 --- a/drivers/iio/adc/ingenic-adc.c +++ b/drivers/iio/adc/ingenic-adc.c @@ -177,13 +177,12 @@ static void ingenic_adc_set_config(struct ingenic_adc *adc, mutex_unlock(&adc->lock); } -static void ingenic_adc_enable(struct ingenic_adc *adc, - int engine, - bool enabled) +static void ingenic_adc_enable_unlocked(struct ingenic_adc *adc, + int engine, + bool enabled) { u8 val; - mutex_lock(&adc->lock); val = readb(adc->base + JZ_ADC_REG_ENABLE); if (enabled) @@ -192,20 +191,41 @@ static void ingenic_adc_enable(struct ingenic_adc *adc, val &= ~BIT(engine); writeb(val, adc->base + JZ_ADC_REG_ENABLE); +} + +static void ingenic_adc_enable(struct ingenic_adc *adc, + int engine, + bool enabled) +{ + mutex_lock(&adc->lock); + ingenic_adc_enable_unlocked(adc, engine, enabled); mutex_unlock(&adc->lock); } static int ingenic_adc_capture(struct ingenic_adc *adc, int engine) { + u32 cfg; u8 val; int ret; - ingenic_adc_enable(adc, engine, true); + /* + * Disable CMD_SEL temporarily, because it causes wrong VBAT readings, + * probably due to the switch of VREF. We must keep the lock here to + * avoid races with the buffer enable/disable functions. + */ + mutex_lock(&adc->lock); + cfg = readl(adc->base + JZ_ADC_REG_CFG); + writel(cfg & ~JZ_ADC_REG_CFG_CMD_SEL, adc->base + JZ_ADC_REG_CFG); + + ingenic_adc_enable_unlocked(adc, engine, true); ret = readb_poll_timeout(adc->base + JZ_ADC_REG_ENABLE, val, !(val & BIT(engine)), 250, 1000); if (ret) - ingenic_adc_enable(adc, engine, false); + ingenic_adc_enable_unlocked(adc, engine, false); + + writel(cfg, adc->base + JZ_ADC_REG_CFG); + mutex_unlock(&adc->lock); return ret; } -- cgit v1.2.3 From 44a146a44f656fc03d368c1b9248d29a128cd053 Mon Sep 17 00:00:00 2001 From: Necip Fazil Yildiran Date: Tue, 3 Nov 2020 01:35:24 +0300 Subject: iio: light: fix kconfig dependency bug for VCNL4035 When VCNL4035 is enabled and IIO_BUFFER is disabled, it results in the following Kbuild warning: WARNING: unmet direct dependencies detected for IIO_TRIGGERED_BUFFER Depends on [n]: IIO [=y] && IIO_BUFFER [=n] Selected by [y]: - VCNL4035 [=y] && IIO [=y] && I2C [=y] The reason is that VCNL4035 selects IIO_TRIGGERED_BUFFER without depending on or selecting IIO_BUFFER while IIO_TRIGGERED_BUFFER depends on IIO_BUFFER. This can also fail building the kernel. Honor the kconfig dependency to remove unmet direct dependency warnings and avoid any potential build failures. Fixes: 55707294c4eb ("iio: light: Add support for vishay vcnl4035") Signed-off-by: Necip Fazil Yildiran Link: https://bugzilla.kernel.org/show_bug.cgi?id=209883 Link: https://lore.kernel.org/r/20201102223523.572461-1-fazilyildiran@gmail.com Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/light/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig index cade6dc0305b..33ad4dd0b5c7 100644 --- a/drivers/iio/light/Kconfig +++ b/drivers/iio/light/Kconfig @@ -544,6 +544,7 @@ config VCNL4000 config VCNL4035 tristate "VCNL4035 combined ALS and proximity sensor" + select IIO_BUFFER select IIO_TRIGGERED_BUFFER select REGMAP_I2C depends on I2C -- cgit v1.2.3 From 77e70d351db7de07a46ac49b87a6c3c7a60fca7e Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Mon, 26 Oct 2020 13:36:17 -0700 Subject: Input: sunkbd - avoid use-after-free in teardown paths We need to make sure we cancel the reinit work before we tear down the driver structures. Reported-by: Bodong Zhao Tested-by: Bodong Zhao Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/sunkbd.c | 41 +++++++++++++++++++++++++++++++++-------- 1 file changed, 33 insertions(+), 8 deletions(-) diff --git a/drivers/input/keyboard/sunkbd.c b/drivers/input/keyboard/sunkbd.c index 27126e621eb6..d450f11b98a7 100644 --- a/drivers/input/keyboard/sunkbd.c +++ b/drivers/input/keyboard/sunkbd.c @@ -99,7 +99,8 @@ static irqreturn_t sunkbd_interrupt(struct serio *serio, switch (data) { case SUNKBD_RET_RESET: - schedule_work(&sunkbd->tq); + if (sunkbd->enabled) + schedule_work(&sunkbd->tq); sunkbd->reset = -1; break; @@ -200,16 +201,12 @@ static int sunkbd_initialize(struct sunkbd *sunkbd) } /* - * sunkbd_reinit() sets leds and beeps to a state the computer remembers they - * were in. + * sunkbd_set_leds_beeps() sets leds and beeps to a state the computer remembers + * they were in. */ -static void sunkbd_reinit(struct work_struct *work) +static void sunkbd_set_leds_beeps(struct sunkbd *sunkbd) { - struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq); - - wait_event_interruptible_timeout(sunkbd->wait, sunkbd->reset >= 0, HZ); - serio_write(sunkbd->serio, SUNKBD_CMD_SETLED); serio_write(sunkbd->serio, (!!test_bit(LED_CAPSL, sunkbd->dev->led) << 3) | @@ -222,11 +219,39 @@ static void sunkbd_reinit(struct work_struct *work) SUNKBD_CMD_BELLOFF - !!test_bit(SND_BELL, sunkbd->dev->snd)); } + +/* + * sunkbd_reinit() wait for the keyboard reset to complete and restores state + * of leds and beeps. + */ + +static void sunkbd_reinit(struct work_struct *work) +{ + struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq); + + /* + * It is OK that we check sunkbd->enabled without pausing serio, + * as we only want to catch true->false transition that will + * happen once and we will be woken up for it. + */ + wait_event_interruptible_timeout(sunkbd->wait, + sunkbd->reset >= 0 || !sunkbd->enabled, + HZ); + + if (sunkbd->reset >= 0 && sunkbd->enabled) + sunkbd_set_leds_beeps(sunkbd); +} + static void sunkbd_enable(struct sunkbd *sunkbd, bool enable) { serio_pause_rx(sunkbd->serio); sunkbd->enabled = enable; serio_continue_rx(sunkbd->serio); + + if (!enable) { + wake_up_interruptible(&sunkbd->wait); + cancel_work_sync(&sunkbd->tq); + } } /* -- cgit v1.2.3 From dbd7ae5154d5fff7e84a9f3010bb06499017ef29 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 2 Nov 2020 16:14:45 +0000 Subject: xfrm/compat: Translate by copying XFRMA_UNSPEC attribute xfrm_xlate32() translates 64-bit message provided by kernel to be sent for 32-bit listener (acknowledge or monitor). Translator code doesn't expect XFRMA_UNSPEC attribute as it doesn't know its payload. Kernel never attaches such attribute, but a user can. I've searched if any opensource does it and the answer is no. Nothing on github and google finds only tfcproject that has such code commented-out. What will happen if a user sends a netlink message with XFRMA_UNSPEC attribute? Ipsec code ignores this attribute. But if there is a monitor-process or 32-bit user requested ack - kernel will try to translate such message and will hit WARN_ONCE() in xfrm_xlate64_attr(). Deal with XFRMA_UNSPEC by copying the attribute payload with xfrm_nla_cpy(). In result, the default switch-case in xfrm_xlate64_attr() becomes an unused code. Leave those 3 lines in case a new xfrm attribute will be added. Fixes: 5461fc0c8d9f ("xfrm/compat: Add 64=>32-bit messages translator") Reported-by: syzbot+a7e701c8385bd8543074@syzkaller.appspotmail.com Signed-off-by: Dmitry Safonov Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_compat.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index e28f0c9ecd6a..17edbf935e35 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -234,6 +234,7 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) case XFRMA_PAD: /* Ignore */ return 0; + case XFRMA_UNSPEC: case XFRMA_ALG_AUTH: case XFRMA_ALG_CRYPT: case XFRMA_ALG_COMP: -- cgit v1.2.3 From d1949d045fd67eab8a32a579a8c1ab1681330854 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 2 Nov 2020 16:14:46 +0000 Subject: xfrm/compat: memset(0) 64-bit padding at right place 32-bit messages translated by xfrm_compat can have attributes attached. For all, but XFRMA_SA, XFRMA_POLICY the size of payload is the same in 32-bit UABI and 64-bit UABI. For XFRMA_SA (struct xfrm_usersa_info) and XFRMA_POLICY (struct xfrm_userpolicy_info) it's only tail-padding that is present in 64-bit payload, but not in 32-bit. The proper size for destination nlattr is already calculated by xfrm_user_rcv_calculate_len64() and allocated with kvmalloc(). xfrm_attr_cpy32() copies 32-bit copy_len into 64-bit attribute translated payload, zero-filling possible padding for SA/POLICY. Due to a typo, *pos already has 64-bit payload size, in a result next memset(0) is called on the memory after the translated attribute, not on the tail-padding of it. Fixes: 5106f4a8acff ("xfrm/compat: Add 32=>64-bit messages translator") Reported-by: syzbot+c43831072e7df506a646@syzkaller.appspotmail.com Signed-off-by: Dmitry Safonov Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_compat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 17edbf935e35..556e9f33b815 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -388,7 +388,7 @@ static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src, memcpy(nla, src, nla_attr_size(copy_len)); nla->nla_len = nla_attr_size(payload); - *pos += nla_attr_size(payload); + *pos += nla_attr_size(copy_len); nlmsg->nlmsg_len += nla->nla_len; memset(dst + *pos, 0, payload - copy_len); -- cgit v1.2.3 From ad37f77fd3659e87fd9833a83692e0e4eba0f5cd Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 2 Nov 2020 16:14:47 +0000 Subject: xfrm/compat: Don't allocate memory with __GFP_ZERO 32-bit to 64-bit messages translator zerofies needed paddings in the translation, the rest is the actual payload. Don't allocate zero pages as they are not needed. Fixes: 5106f4a8acff ("xfrm/compat: Add 32=>64-bit messages translator") Signed-off-by: Dmitry Safonov Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_compat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 556e9f33b815..d8e8a11ca845 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -564,7 +564,7 @@ static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32, return NULL; len += NLMSG_HDRLEN; - h64 = kvmalloc(len, GFP_KERNEL | __GFP_ZERO); + h64 = kvmalloc(len, GFP_KERNEL); if (!h64) return ERR_PTR(-ENOMEM); -- cgit v1.2.3 From ff1f855804cdbbb6db7b9b6df6cab783d1a40d66 Mon Sep 17 00:00:00 2001 From: Rijo Thomas Date: Wed, 4 Nov 2020 11:56:09 +0530 Subject: tee: amdtee: fix memory leak due to reset of global shm list The driver maintains a list of shared memory buffers along with their mapped buffer id's in a global linked list. These buffers need to be unmapped after use by the user-space client. The global shared memory list is initialized to zero entries in the function amdtee_open(). This clearing of list entries can be a source for memory leak on secure side if the global linked list previously held some mapped buffer entries allocated from another TEE context. Fix potential memory leak issue by moving global shared memory list to AMD-TEE driver context data structure. Fixes: 757cc3e9ff1d ("tee: add AMD-TEE driver") Reviewed-by: Devaraj Rangasamy Signed-off-by: Rijo Thomas Signed-off-by: Jens Wiklander --- drivers/tee/amdtee/amdtee_private.h | 7 +++---- drivers/tee/amdtee/core.c | 18 +++++++++++------- 2 files changed, 14 insertions(+), 11 deletions(-) diff --git a/drivers/tee/amdtee/amdtee_private.h b/drivers/tee/amdtee/amdtee_private.h index d7f798c3394b..97df16a17285 100644 --- a/drivers/tee/amdtee/amdtee_private.h +++ b/drivers/tee/amdtee/amdtee_private.h @@ -64,9 +64,12 @@ struct amdtee_session { /** * struct amdtee_context_data - AMD-TEE driver context data * @sess_list: Keeps track of sessions opened in current TEE context + * @shm_list: Keeps track of buffers allocated and mapped in current TEE + * context */ struct amdtee_context_data { struct list_head sess_list; + struct list_head shm_list; }; struct amdtee_driver_data { @@ -89,10 +92,6 @@ struct amdtee_shm_data { u32 buf_id; }; -struct amdtee_shm_context { - struct list_head shmdata_list; -}; - #define LOWER_TWO_BYTE_MASK 0x0000FFFF /** diff --git a/drivers/tee/amdtee/core.c b/drivers/tee/amdtee/core.c index 27b4cd77d0db..ce61c68ec58c 100644 --- a/drivers/tee/amdtee/core.c +++ b/drivers/tee/amdtee/core.c @@ -20,7 +20,6 @@ static struct amdtee_driver_data *drv_data; static DEFINE_MUTEX(session_list_mutex); -static struct amdtee_shm_context shmctx; static void amdtee_get_version(struct tee_device *teedev, struct tee_ioctl_version_data *vers) @@ -42,7 +41,7 @@ static int amdtee_open(struct tee_context *ctx) return -ENOMEM; INIT_LIST_HEAD(&ctxdata->sess_list); - INIT_LIST_HEAD(&shmctx.shmdata_list); + INIT_LIST_HEAD(&ctxdata->shm_list); ctx->data = ctxdata; return 0; @@ -152,10 +151,11 @@ static struct amdtee_session *find_session(struct amdtee_context_data *ctxdata, u32 get_buffer_id(struct tee_shm *shm) { - u32 buf_id = 0; + struct amdtee_context_data *ctxdata = shm->ctx->data; struct amdtee_shm_data *shmdata; + u32 buf_id = 0; - list_for_each_entry(shmdata, &shmctx.shmdata_list, shm_node) + list_for_each_entry(shmdata, &ctxdata->shm_list, shm_node) if (shmdata->kaddr == shm->kaddr) { buf_id = shmdata->buf_id; break; @@ -333,8 +333,9 @@ int amdtee_close_session(struct tee_context *ctx, u32 session) int amdtee_map_shmem(struct tee_shm *shm) { - struct shmem_desc shmem; + struct amdtee_context_data *ctxdata; struct amdtee_shm_data *shmnode; + struct shmem_desc shmem; int rc, count; u32 buf_id; @@ -362,7 +363,8 @@ int amdtee_map_shmem(struct tee_shm *shm) shmnode->kaddr = shm->kaddr; shmnode->buf_id = buf_id; - list_add(&shmnode->shm_node, &shmctx.shmdata_list); + ctxdata = shm->ctx->data; + list_add(&shmnode->shm_node, &ctxdata->shm_list); pr_debug("buf_id :[%x] kaddr[%p]\n", shmnode->buf_id, shmnode->kaddr); @@ -371,6 +373,7 @@ int amdtee_map_shmem(struct tee_shm *shm) void amdtee_unmap_shmem(struct tee_shm *shm) { + struct amdtee_context_data *ctxdata; struct amdtee_shm_data *shmnode; u32 buf_id; @@ -381,7 +384,8 @@ void amdtee_unmap_shmem(struct tee_shm *shm) /* Unmap the shared memory from TEE */ handle_unmap_shmem(buf_id); - list_for_each_entry(shmnode, &shmctx.shmdata_list, shm_node) + ctxdata = shm->ctx->data; + list_for_each_entry(shmnode, &ctxdata->shm_list, shm_node) if (buf_id == shmnode->buf_id) { list_del(&shmnode->shm_node); kfree(shmnode); -- cgit v1.2.3 From be353be27874f40837327d9a39e3ad2149ab66d3 Mon Sep 17 00:00:00 2001 From: Rijo Thomas Date: Wed, 4 Nov 2020 11:56:10 +0530 Subject: tee: amdtee: synchronize access to shm list Synchronize access to shm or shared memory buffer list to prevent race conditions due to concurrent updates to shared shm list by multiple threads. Fixes: 757cc3e9ff1d ("tee: add AMD-TEE driver") Reviewed-by: Devaraj Rangasamy Signed-off-by: Rijo Thomas Signed-off-by: Jens Wiklander --- drivers/tee/amdtee/amdtee_private.h | 1 + drivers/tee/amdtee/core.c | 8 ++++++++ 2 files changed, 9 insertions(+) diff --git a/drivers/tee/amdtee/amdtee_private.h b/drivers/tee/amdtee/amdtee_private.h index 97df16a17285..337c8d82f74e 100644 --- a/drivers/tee/amdtee/amdtee_private.h +++ b/drivers/tee/amdtee/amdtee_private.h @@ -70,6 +70,7 @@ struct amdtee_session { struct amdtee_context_data { struct list_head sess_list; struct list_head shm_list; + struct mutex shm_mutex; /* synchronizes access to @shm_list */ }; struct amdtee_driver_data { diff --git a/drivers/tee/amdtee/core.c b/drivers/tee/amdtee/core.c index ce61c68ec58c..8a6a8f30bb42 100644 --- a/drivers/tee/amdtee/core.c +++ b/drivers/tee/amdtee/core.c @@ -42,6 +42,7 @@ static int amdtee_open(struct tee_context *ctx) INIT_LIST_HEAD(&ctxdata->sess_list); INIT_LIST_HEAD(&ctxdata->shm_list); + mutex_init(&ctxdata->shm_mutex); ctx->data = ctxdata; return 0; @@ -85,6 +86,7 @@ static void amdtee_release(struct tee_context *ctx) list_del(&sess->list_node); release_session(sess); } + mutex_destroy(&ctxdata->shm_mutex); kfree(ctxdata); ctx->data = NULL; @@ -155,11 +157,13 @@ u32 get_buffer_id(struct tee_shm *shm) struct amdtee_shm_data *shmdata; u32 buf_id = 0; + mutex_lock(&ctxdata->shm_mutex); list_for_each_entry(shmdata, &ctxdata->shm_list, shm_node) if (shmdata->kaddr == shm->kaddr) { buf_id = shmdata->buf_id; break; } + mutex_unlock(&ctxdata->shm_mutex); return buf_id; } @@ -364,7 +368,9 @@ int amdtee_map_shmem(struct tee_shm *shm) shmnode->kaddr = shm->kaddr; shmnode->buf_id = buf_id; ctxdata = shm->ctx->data; + mutex_lock(&ctxdata->shm_mutex); list_add(&shmnode->shm_node, &ctxdata->shm_list); + mutex_unlock(&ctxdata->shm_mutex); pr_debug("buf_id :[%x] kaddr[%p]\n", shmnode->buf_id, shmnode->kaddr); @@ -385,12 +391,14 @@ void amdtee_unmap_shmem(struct tee_shm *shm) handle_unmap_shmem(buf_id); ctxdata = shm->ctx->data; + mutex_lock(&ctxdata->shm_mutex); list_for_each_entry(shmnode, &ctxdata->shm_list, shm_node) if (buf_id == shmnode->buf_id) { list_del(&shmnode->shm_node); kfree(shmnode); break; } + mutex_unlock(&ctxdata->shm_mutex); } int amdtee_invoke_func(struct tee_context *ctx, -- cgit v1.2.3 From ce9dfafe29bed86fe3cda330ac6072ce84e1ff81 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 3 Nov 2020 16:55:43 +0100 Subject: s390: fix system call exit path The system call exit path is running with interrupts enabled while checking for TIF/PIF/CIF bits which require special handling. If all bits have been checked interrupts are disabled and the kernel exits to user space. The problem is that after checking all bits and before interrupts are disabled bits can be set already again, due to interrupt handling. This means that the kernel can exit to user space with some TIF/PIF/CIF bits set, which should never happen. E.g. TIF_NEED_RESCHED might be set, which might lead to additional latencies, since that bit will only be recognized with next exit to user space. Fix this by checking the corresponding bits only when interrupts are disabled. Fixes: 0b0ed657fe00 ("s390: remove critical section cleanup from entry.S") Cc: # 5.8 Acked-by: Sven Schnelle Signed-off-by: Heiko Carstens --- arch/s390/kernel/entry.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 86235919c2d1..5346545b9860 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -422,6 +422,7 @@ ENTRY(system_call) #endif LOCKDEP_SYS_EXIT .Lsysc_tif: + DISABLE_INTS TSTMSK __PT_FLAGS(%r11),_PIF_WORK jnz .Lsysc_work TSTMSK __TI_flags(%r12),_TIF_WORK @@ -444,6 +445,7 @@ ENTRY(system_call) # One of the work bits is on. Find out which one. # .Lsysc_work: + ENABLE_INTS TSTMSK __TI_flags(%r12),_TIF_NEED_RESCHED jo .Lsysc_reschedule TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART -- cgit v1.2.3 From 7de8bfaa095fcbc2db2952d4b561be102a41c2a6 Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Wed, 4 Nov 2020 10:55:08 +0000 Subject: arm64: dts: renesas: r8a774e1: Add missing audio_clk_b Add audio_clk_b configured as 0 Hz, this will be overridden by the boards providing the audio clock. Fixes: 8183a7938cfec ("arm64: dts: renesas: r8a774e1: Add audio support") Reported-by: Nobuhiro Iwamatsu Signed-off-by: Lad Prabhakar Link: https://lore.kernel.org/r/20201104105508.21197-1-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Geert Uytterhoeven --- arch/arm64/boot/dts/renesas/r8a774e1.dtsi | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi index 9cbf963aa068..c29643442e91 100644 --- a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi @@ -28,6 +28,12 @@ clock-frequency = <0>; }; + audio_clk_b: audio_clk_b { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + audio_clk_c: audio_clk_c { compatible = "fixed-clock"; #clock-cells = <0>; -- cgit v1.2.3 From f59ee399de4a8ca4d7d19cdcabb4b63e94867f09 Mon Sep 17 00:00:00 2001 From: Chris Ye Date: Sun, 1 Nov 2020 11:34:52 -0800 Subject: HID: add HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE for Gamevice devices Kernel 5.4 introduces HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE, devices need to be set explicitly with this flag. Signed-off-by: Chris Ye Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 4 ++++ drivers/hid/hid-quirks.c | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 28ecd635edc1..af361cd04bf0 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -445,6 +445,10 @@ #define USB_VENDOR_ID_FRUCTEL 0x25B6 #define USB_DEVICE_ID_GAMETEL_MT_MODE 0x0002 +#define USB_VENDOR_ID_GAMEVICE 0x27F8 +#define USB_DEVICE_ID_GAMEVICE_GV186 0x0BBE +#define USB_DEVICE_ID_GAMEVICE_KISHI 0x0BBF + #define USB_VENDOR_ID_GAMERON 0x0810 #define USB_DEVICE_ID_GAMERON_DUAL_PSX_ADAPTOR 0x0001 #define USB_DEVICE_ID_GAMERON_DUAL_PCS_ADAPTOR 0x0002 diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index b154e11d43bf..bf7ecab5d9e5 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -85,6 +85,10 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_FUTABA, USB_DEVICE_ID_LED_DISPLAY), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_SAT_ADAPTOR), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_USB_JOYPAD), HID_QUIRK_MULTI_INPUT }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_GAMEVICE, USB_DEVICE_ID_GAMEVICE_GV186), + HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, + { HID_USB_DEVICE(USB_VENDOR_ID_GAMEVICE, USB_DEVICE_ID_GAMEVICE_KISHI), + HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_DRIVING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FIGHTING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FLYING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT }, -- cgit v1.2.3 From 0ba2df09f1500d3f27398a3382b86d39c3e6abe2 Mon Sep 17 00:00:00 2001 From: Marc Ferland Date: Wed, 4 Nov 2020 12:30:04 +0530 Subject: dmaengine: xilinx_dma: use readl_poll_timeout_atomic variant The xilinx_dma_poll_timeout macro is sometimes called while holding a spinlock (see xilinx_dma_issue_pending() for an example) this means we shouldn't sleep when polling the dma channel registers. To address it in xilinx poll timeout macro use readl_poll_timeout_atomic instead of readl_poll_timeout variant. Signed-off-by: Marc Ferland Signed-off-by: Radhey Shyam Pandey Link: https://lore.kernel.org/r/1604473206-32573-2-git-send-email-radhey.shyam.pandey@xilinx.com Signed-off-by: Vinod Koul --- drivers/dma/xilinx/xilinx_dma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index ecff35402860..d858d540b88a 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -517,8 +517,8 @@ struct xilinx_dma_device { #define to_dma_tx_descriptor(tx) \ container_of(tx, struct xilinx_dma_tx_descriptor, async_tx) #define xilinx_dma_poll_timeout(chan, reg, val, cond, delay_us, timeout_us) \ - readl_poll_timeout(chan->xdev->regs + chan->ctrl_offset + reg, val, \ - cond, delay_us, timeout_us) + readl_poll_timeout_atomic(chan->xdev->regs + chan->ctrl_offset + reg, \ + val, cond, delay_us, timeout_us) /* IO accessors */ static inline u32 dma_read(struct xilinx_dma_chan *chan, u32 reg) -- cgit v1.2.3 From c8ae7932997d0cc92d016829138074c7520248e5 Mon Sep 17 00:00:00 2001 From: Matthew Murrian Date: Wed, 4 Nov 2020 12:30:05 +0530 Subject: dmaengine: xilinx_dma: Fix usage of xilinx_aximcdma_tx_segment Several code sections incorrectly use struct xilinx_axidma_tx_segment instead of struct xilinx_aximcdma_tx_segment when operating as Multichannel DMA. As their structures are similar, this just works. Fixes: 6ccd692bfb7f ("dmaengine: xilinx_dma: Add Xilinx AXI MCDMA Engine driver support") Signed-off-by: Matthew Murrian Signed-off-by: Radhey Shyam Pandey Link: https://lore.kernel.org/r/1604473206-32573-3-git-send-email-radhey.shyam.pandey@xilinx.com Signed-off-by: Vinod Koul --- drivers/dma/xilinx/xilinx_dma.c | 29 ++++++++++++++++++++++++----- 1 file changed, 24 insertions(+), 5 deletions(-) diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index d858d540b88a..9fd924cf2337 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -948,8 +948,10 @@ static u32 xilinx_dma_get_residue(struct xilinx_dma_chan *chan, { struct xilinx_cdma_tx_segment *cdma_seg; struct xilinx_axidma_tx_segment *axidma_seg; + struct xilinx_aximcdma_tx_segment *aximcdma_seg; struct xilinx_cdma_desc_hw *cdma_hw; struct xilinx_axidma_desc_hw *axidma_hw; + struct xilinx_aximcdma_desc_hw *aximcdma_hw; struct list_head *entry; u32 residue = 0; @@ -961,13 +963,23 @@ static u32 xilinx_dma_get_residue(struct xilinx_dma_chan *chan, cdma_hw = &cdma_seg->hw; residue += (cdma_hw->control - cdma_hw->status) & chan->xdev->max_buffer_len; - } else { + } else if (chan->xdev->dma_config->dmatype == + XDMA_TYPE_AXIDMA) { axidma_seg = list_entry(entry, struct xilinx_axidma_tx_segment, node); axidma_hw = &axidma_seg->hw; residue += (axidma_hw->control - axidma_hw->status) & chan->xdev->max_buffer_len; + } else { + aximcdma_seg = + list_entry(entry, + struct xilinx_aximcdma_tx_segment, + node); + aximcdma_hw = &aximcdma_seg->hw; + residue += + (aximcdma_hw->control - aximcdma_hw->status) & + chan->xdev->max_buffer_len; } } @@ -1135,7 +1147,7 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan) upper_32_bits(chan->seg_p + sizeof(*chan->seg_mv) * ((i + 1) % XILINX_DMA_NUM_DESCS)); chan->seg_mv[i].phys = chan->seg_p + - sizeof(*chan->seg_v) * i; + sizeof(*chan->seg_mv) * i; list_add_tail(&chan->seg_mv[i].node, &chan->free_seg_list); } @@ -1560,7 +1572,7 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan) static void xilinx_mcdma_start_transfer(struct xilinx_dma_chan *chan) { struct xilinx_dma_tx_descriptor *head_desc, *tail_desc; - struct xilinx_axidma_tx_segment *tail_segment; + struct xilinx_aximcdma_tx_segment *tail_segment; u32 reg; /* @@ -1582,7 +1594,7 @@ static void xilinx_mcdma_start_transfer(struct xilinx_dma_chan *chan) tail_desc = list_last_entry(&chan->pending_list, struct xilinx_dma_tx_descriptor, node); tail_segment = list_last_entry(&tail_desc->segments, - struct xilinx_axidma_tx_segment, node); + struct xilinx_aximcdma_tx_segment, node); reg = dma_ctrl_read(chan, XILINX_MCDMA_CHAN_CR_OFFSET(chan->tdest)); @@ -1864,6 +1876,7 @@ static void append_desc_queue(struct xilinx_dma_chan *chan, struct xilinx_vdma_tx_segment *tail_segment; struct xilinx_dma_tx_descriptor *tail_desc; struct xilinx_axidma_tx_segment *axidma_tail_segment; + struct xilinx_aximcdma_tx_segment *aximcdma_tail_segment; struct xilinx_cdma_tx_segment *cdma_tail_segment; if (list_empty(&chan->pending_list)) @@ -1885,11 +1898,17 @@ static void append_desc_queue(struct xilinx_dma_chan *chan, struct xilinx_cdma_tx_segment, node); cdma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys; - } else { + } else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) { axidma_tail_segment = list_last_entry(&tail_desc->segments, struct xilinx_axidma_tx_segment, node); axidma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys; + } else { + aximcdma_tail_segment = + list_last_entry(&tail_desc->segments, + struct xilinx_aximcdma_tx_segment, + node); + aximcdma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys; } /* -- cgit v1.2.3 From 96d5d884f78306206d745d856aad322becd100c3 Mon Sep 17 00:00:00 2001 From: Matthew Murrian Date: Wed, 4 Nov 2020 12:30:06 +0530 Subject: dmaengine: xilinx_dma: Fix SG capability check for MCDMA The SG capability is inherently present with Multichannel DMA operation. The register used to check for this capability with other DMA driver types is not defined for MCDMA. Fixes: 6ccd692bfb7f ("dmaengine: xilinx_dma: Add Xilinx AXI MCDMA Engine driver support") Signed-off-by: Matthew Murrian Signed-off-by: Radhey Shyam Pandey Link: https://lore.kernel.org/r/1604473206-32573-4-git-send-email-radhey.shyam.pandey@xilinx.com Signed-off-by: Vinod Koul --- drivers/dma/xilinx/xilinx_dma.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index 9fd924cf2337..22faea653ea8 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -2855,10 +2855,11 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev, chan->stop_transfer = xilinx_dma_stop_transfer; } - /* check if SG is enabled (only for AXIDMA and CDMA) */ + /* check if SG is enabled (only for AXIDMA, AXIMCDMA, and CDMA) */ if (xdev->dma_config->dmatype != XDMA_TYPE_VDMA) { - if (dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) & - XILINX_DMA_DMASR_SG_MASK) + if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA || + dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) & + XILINX_DMA_DMASR_SG_MASK) chan->has_sg = true; dev_dbg(chan->dev, "ch %d: SG %s\n", chan->id, chan->has_sg ? "enabled" : "disabled"); -- cgit v1.2.3 From 52d9edbe6efc5042cf57fae6a25d07572ddf398b Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 8 Oct 2020 21:35:38 +0200 Subject: ARM: dts: stm32: Fix TA3-GPIO-C key on STM32MP1 DHCOM PDK2 On the prototype DHCOM, the TA3-GPIO-C button was connected to pin PI11 of the STM32MP15xx, however on the production SoM this was changed to pin PG0 to free up the IRQ line 11 for LAN8710i PHY IRQ. Update the connection in the DT. Since the IRQ line 0 is used for PMIC as well and cannot be shared with the button, make the button polled. Fixes: 87cabf9405cb ("ARM: dts: stm32: Add GPIO keys for STM32MP1 DHCOM PDK2") Signed-off-by: Marek Vasut Cc: Alexandre Torgue Cc: Maxime Coquelin Cc: Patrice Chotard Cc: Patrick Delaunay Cc: linux-stm32@st-md-mailman.stormreply.com To: linux-arm-kernel@lists.infradead.org Signed-off-by: Alexandre Torgue --- arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi index 5dff24e39af8..9a0a59678097 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi @@ -46,6 +46,16 @@ linux,code = ; gpios = <&gpiof 3 GPIO_ACTIVE_LOW>; }; + + /* + * The EXTi IRQ line 0 is shared with PMIC, + * so mark this as polled GPIO key. + */ + button-2 { + label = "TA3-GPIO-C"; + linux,code = ; + gpios = <&gpiog 0 GPIO_ACTIVE_LOW>; + }; }; gpio-keys { @@ -59,13 +69,6 @@ wakeup-source; }; - button-2 { - label = "TA3-GPIO-C"; - linux,code = ; - gpios = <&gpioi 11 GPIO_ACTIVE_LOW>; - wakeup-source; - }; - button-3 { label = "TA4-GPIO-D"; linux,code = ; -- cgit v1.2.3 From 7e5f3155dcbb4d724386b30cc232002d9b9d81f5 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Wed, 28 Oct 2020 21:46:17 +0100 Subject: ARM: dts: stm32: Fix LED5 on STM32MP1 DHCOM PDK2 On the prototype DHCOM, the LED5 was connected to pin PG2 of the STM32MP15xx, however on the production SoM this was changed to pin PC6. Update the connection in the DT. Fixes: 81d5fc719798 ("ARM: dts: stm32: Add GPIO LEDs for STM32MP1 DHCOM PDK2") Signed-off-by: Marek Vasut Cc: Alexandre Torgue Cc: Maxime Coquelin Cc: Patrice Chotard Cc: Patrick Delaunay Cc: linux-stm32@st-md-mailman.stormreply.com To: linux-arm-kernel@lists.infradead.org Signed-off-by: Alexandre Torgue --- arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi index 9a0a59678097..8456f172d4b1 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi @@ -82,7 +82,7 @@ led-0 { label = "green:led5"; - gpios = <&gpiog 2 GPIO_ACTIVE_HIGH>; + gpios = <&gpioc 6 GPIO_ACTIVE_HIGH>; default-state = "off"; }; -- cgit v1.2.3 From 1f3d7fc279b1a299bb8b1b225d80309a2062ab8a Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 29 Oct 2020 20:46:17 +0100 Subject: ARM: dts: stm32: Define VIO regulator supply on DHCOM The VIO regulator is supplied by PMIC Buck3, describe this in the DT. Fixes: 34e0c7847dcf ("ARM: dts: stm32: Add DH Electronics DHCOM STM32MP1 SoM and PDK2 board") Signed-off-by: Marek Vasut Cc: Alexandre Torgue Cc: Maxime Coquelin Cc: Patrice Chotard Cc: Patrick Delaunay Cc: linux-stm32@st-md-mailman.stormreply.com To: linux-arm-kernel@lists.infradead.org Signed-off-by: Alexandre Torgue --- arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index b4b52cf634af..c89ebfaa115d 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -68,6 +68,7 @@ gpio = <&gpiog 3 GPIO_ACTIVE_LOW>; regulator-always-on; regulator-boot-on; + vin-supply = <&vdd>; }; }; -- cgit v1.2.3 From cb7ff314e1d9f3d6c62fa2c392e41174721ed0b3 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Fri, 6 Nov 2020 09:14:20 +0000 Subject: drm/tegra: sor: Don't warn on probe deferral Deferred probe is an expected return value for tegra_output_probe(). Given that the driver deals with it properly, there's no need to output a warning that may potentially confuse users. Signed-off-by: Jon Hunter Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/sor.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index e88a17c2937f..a5b944dacb35 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -3764,10 +3764,9 @@ static int tegra_sor_probe(struct platform_device *pdev) return err; err = tegra_output_probe(&sor->output); - if (err < 0) { - dev_err(&pdev->dev, "failed to probe output: %d\n", err); - return err; - } + if (err < 0) + return dev_err_probe(&pdev->dev, err, + "failed to probe output\n"); if (sor->ops && sor->ops->probe) { err = sor->ops->probe(sor); -- cgit v1.2.3 From e5ace7f62695656ef8a66ad5a4c3edd055894876 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 24 Sep 2020 01:25:35 +0200 Subject: ARM: dts: stm32: Enable thermal sensor support on stm32mp15xx-dhcor Enable STM32 Digital Thermal Sensor driver for stm32mp15xx-dhcor SoMs. Fixes: 94cafe1b6482 ("ARM: dts: stm32: Add Avenger96 devicetree support based on STM32MP157A") Signed-off-by: Marek Vasut Cc: Alexandre Torgue Cc: Manivannan Sadhasivam Cc: linux-stm32@st-md-mailman.stormreply.com To: linux-arm-kernel@lists.infradead.org Reviewed-by: Manivannan Sadhasivam Signed-off-by: Alexandre Torgue --- arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi index 04fbb324a541..803eb8bc9c85 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi @@ -21,6 +21,10 @@ }; }; +&dts { + status = "okay"; +}; + &i2c4 { pinctrl-names = "default"; pinctrl-0 = <&i2c4_pins_a>; -- cgit v1.2.3 From f4c7fa39415da6db1fa0bc26162ac23a0fbae8bb Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 29 Oct 2020 20:46:52 +0100 Subject: ARM: dts: stm32: Keep VDDA LDO1 always on on DHCOM The VDDA LDO1 PMIC output supplies the analog VDDA input of the STM32MP1 on DHCOM, keep it always on, otherwise there could be leakage through the SoC. Fixes: 34e0c7847dcf ("ARM: dts: stm32: Add DH Electronics DHCOM STM32MP1 SoM and PDK2 board") Signed-off-by: Marek Vasut Cc: Alexandre Torgue Cc: Maxime Coquelin Cc: Patrice Chotard Cc: Patrick Delaunay Cc: linux-stm32@st-md-mailman.stormreply.com To: linux-arm-kernel@lists.infradead.org Signed-off-by: Alexandre Torgue --- arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index c89ebfaa115d..f796a6150313 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -203,6 +203,7 @@ vdda: ldo1 { regulator-name = "vdda"; + regulator-always-on; regulator-min-microvolt = <2900000>; regulator-max-microvolt = <2900000>; interrupts = ; -- cgit v1.2.3 From 65cae18882f943215d0505ddc7e70495877308e6 Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Fri, 6 Nov 2020 20:11:19 -0500 Subject: x86/xen: don't unbind uninitialized lock_kicker_irq When booting a hyperthreaded system with the kernel parameter 'mitigations=auto,nosmt', the following warning occurs: WARNING: CPU: 0 PID: 1 at drivers/xen/events/events_base.c:1112 unbind_from_irqhandler+0x4e/0x60 ... Hardware name: Xen HVM domU, BIOS 4.2.amazon 08/24/2006 ... Call Trace: xen_uninit_lock_cpu+0x28/0x62 xen_hvm_cpu_die+0x21/0x30 takedown_cpu+0x9c/0xe0 ? trace_suspend_resume+0x60/0x60 cpuhp_invoke_callback+0x9a/0x530 _cpu_up+0x11a/0x130 cpu_up+0x7e/0xc0 bringup_nonboot_cpus+0x48/0x50 smp_init+0x26/0x79 kernel_init_freeable+0xea/0x229 ? rest_init+0xaa/0xaa kernel_init+0xa/0x106 ret_from_fork+0x35/0x40 The secondary CPUs are not activated with the nosmt mitigations and only the primary thread on each CPU core is used. In this situation, xen_hvm_smp_prepare_cpus(), and more importantly xen_init_lock_cpu(), is not called, so the lock_kicker_irq is not initialized for the secondary CPUs. Let's fix this by exiting early in xen_uninit_lock_cpu() if the irq is not set to avoid the warning from above for each secondary CPU. Signed-off-by: Brian Masney Link: https://lore.kernel.org/r/20201107011119.631442-1-bmasney@redhat.com Reviewed-by: Juergen Gross Signed-off-by: Boris Ostrovsky --- arch/x86/xen/spinlock.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 799f4eba0a62..043c73dfd2c9 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -93,10 +93,20 @@ void xen_init_lock_cpu(int cpu) void xen_uninit_lock_cpu(int cpu) { + int irq; + if (!xen_pvspin) return; - unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL); + /* + * When booting the kernel with 'mitigations=auto,nosmt', the secondary + * CPUs are not activated, and lock_kicker_irq is not initialized. + */ + irq = per_cpu(lock_kicker_irq, cpu); + if (irq == -1) + return; + + unbind_from_irqhandler(irq, NULL); per_cpu(lock_kicker_irq, cpu) = -1; kfree(per_cpu(irq_name, cpu)); per_cpu(irq_name, cpu) = NULL; -- cgit v1.2.3 From 7372e79c9eb9d7034e498721eb2861ae4fdbc618 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sun, 8 Nov 2020 12:59:06 +0200 Subject: fanotify: fix logic of reporting name info with watched parent The victim inode's parent and name info is required when an event needs to be delivered to a group interested in filename info OR when the inode's parent is interested in an event on its children. Let us call the first condition 'parent_needed' and the second condition 'parent_interested'. In fsnotify_parent(), the condition where the inode's parent is interested in some events on its children, but not necessarily interested the specific event is called 'parent_watched'. fsnotify_parent() tests the condition (!parent_watched && !parent_needed) for sending the event without parent and name info, which is correct. It then wrongly assumes that parent_watched implies !parent_needed and tests the condition (parent_watched && !parent_interested) for sending the event without parent and name info, which is wrong, because parent may still be needed by some group. For example, after initializing a group with FAN_REPORT_DFID_NAME and adding a FAN_MARK_MOUNT with FAN_OPEN mask, open events on non-directory children of "testdir" are delivered with file name info. After adding another mark to the same group on the parent "testdir" with FAN_CLOSE|FAN_EVENT_ON_CHILD mask, open events on non-directory children of "testdir" are no longer delivered with file name info. Fix the logic and use auxiliary variables to clarify the conditions. Fixes: 9b93f33105f5 ("fsnotify: send event with parent/name info to sb/mount/non-dir marks") Cc: stable@vger.kernel.org#v5.9 Link: https://lore.kernel.org/r/20201108105906.8493-1-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fsnotify.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index a960ec3a569a..8d3ad5ef2925 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -178,6 +178,7 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, struct inode *inode = d_inode(dentry); struct dentry *parent; bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED; + bool parent_needed, parent_interested; __u32 p_mask; struct inode *p_inode = NULL; struct name_snapshot name; @@ -193,7 +194,8 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, return 0; parent = NULL; - if (!parent_watched && !fsnotify_event_needs_parent(inode, mnt, mask)) + parent_needed = fsnotify_event_needs_parent(inode, mnt, mask); + if (!parent_watched && !parent_needed) goto notify; /* Does parent inode care about events on children? */ @@ -205,17 +207,17 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, /* * Include parent/name in notification either if some notification - * groups require parent info (!parent_watched case) or the parent is - * interested in this event. + * groups require parent info or the parent is interested in this event. */ - if (!parent_watched || (mask & p_mask & ALL_FSNOTIFY_EVENTS)) { + parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS; + if (parent_needed || parent_interested) { /* When notifying parent, child should be passed as data */ WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type)); /* Notify both parent and child with child name info */ take_dentry_name_snapshot(&name, dentry); file_name = &name.name; - if (parent_watched) + if (parent_interested) mask |= FS_EVENT_ON_CHILD; } -- cgit v1.2.3 From 197afc631413d96dc60acfc7970bdd4125d38cd3 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 6 Nov 2020 16:02:51 -0800 Subject: libbpf: Don't attempt to load unused subprog as an entry-point BPF program If BPF code contains unused BPF subprogram and there are no other subprogram calls (which can realistically happen in real-world applications given sufficiently smart Clang code optimizations), libbpf will erroneously assume that subprograms are entry-point programs and will attempt to load them with UNSPEC program type. Fix by not relying on subcall instructions and rather detect it based on the structure of BPF object's sections. Fixes: 9a94f277c4fb ("tools: libbpf: restore the ability to load programs from .text section") Reported-by: Dmitrii Banshchikov Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20201107000251.256821-1-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 23 ++++++++++++---------- tools/testing/selftests/bpf/prog_tests/subprogs.c | 6 ++++++ .../selftests/bpf/progs/test_subprogs_unused.c | 21 ++++++++++++++++++++ 3 files changed, 40 insertions(+), 10 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/test_subprogs_unused.c diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 313034117070..28baee7ba1ca 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -560,8 +560,6 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, const char *name, size_t sec_idx, const char *sec_name, size_t sec_off, void *insn_data, size_t insn_data_sz) { - int i; - if (insn_data_sz == 0 || insn_data_sz % BPF_INSN_SZ || sec_off % BPF_INSN_SZ) { pr_warn("sec '%s': corrupted program '%s', offset %zu, size %zu\n", sec_name, name, sec_off, insn_data_sz); @@ -600,13 +598,6 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, goto errout; memcpy(prog->insns, insn_data, insn_data_sz); - for (i = 0; i < prog->insns_cnt; i++) { - if (insn_is_subprog_call(&prog->insns[i])) { - obj->has_subcalls = true; - break; - } - } - return 0; errout: pr_warn("sec '%s': failed to allocate memory for prog '%s'\n", sec_name, name); @@ -3280,7 +3271,19 @@ bpf_object__find_program_by_title(const struct bpf_object *obj, static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog) { - return prog->sec_idx == obj->efile.text_shndx && obj->has_subcalls; + /* For legacy reasons, libbpf supports an entry-point BPF programs + * without SEC() attribute, i.e., those in the .text section. But if + * there are 2 or more such programs in the .text section, they all + * must be subprograms called from entry-point BPF programs in + * designated SEC()'tions, otherwise there is no way to distinguish + * which of those programs should be loaded vs which are a subprogram. + * Similarly, if there is a function/program in .text and at least one + * other BPF program with custom SEC() attribute, then we just assume + * .text programs are subprograms (even if they are not called from + * other programs), because libbpf never explicitly supported mixing + * SEC()-designated BPF programs and .text entry-point BPF programs. + */ + return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1; } struct bpf_program * diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs.c b/tools/testing/selftests/bpf/prog_tests/subprogs.c index a00abf58c037..3f3d2ac4dd57 100644 --- a/tools/testing/selftests/bpf/prog_tests/subprogs.c +++ b/tools/testing/selftests/bpf/prog_tests/subprogs.c @@ -3,12 +3,14 @@ #include #include #include "test_subprogs.skel.h" +#include "test_subprogs_unused.skel.h" static int duration; void test_subprogs(void) { struct test_subprogs *skel; + struct test_subprogs_unused *skel2; int err; skel = test_subprogs__open_and_load(); @@ -26,6 +28,10 @@ void test_subprogs(void) CHECK(skel->bss->res3 != 19, "res3", "got %d, exp %d\n", skel->bss->res3, 19); CHECK(skel->bss->res4 != 36, "res4", "got %d, exp %d\n", skel->bss->res4, 36); + skel2 = test_subprogs_unused__open_and_load(); + ASSERT_OK_PTR(skel2, "unused_progs_skel"); + test_subprogs_unused__destroy(skel2); + cleanup: test_subprogs__destroy(skel); } diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_unused.c b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c new file mode 100644 index 000000000000..75d975f8cf90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c @@ -0,0 +1,21 @@ +#include "vmlinux.h" +#include +#include + +const char LICENSE[] SEC("license") = "GPL"; + +__attribute__((maybe_unused)) __noinline int unused1(int x) +{ + return x + 1; +} + +static __attribute__((maybe_unused)) __noinline int unused2(int x) +{ + return x + 2; +} + +SEC("raw_tp/sys_enter") +int main_prog(void *ctx) +{ + return 0; +} -- cgit v1.2.3 From abbaa433de07076fb8ef524b77ce55d94bad5fc5 Mon Sep 17 00:00:00 2001 From: Wang Qing Date: Sat, 7 Nov 2020 15:45:44 +0800 Subject: bpf: Fix passing zero to PTR_ERR() in bpf_btf_printf_prepare There is a bug when passing zero to PTR_ERR() and return. Fix the smatch error. Fixes: c4d0bfb45068 ("bpf: Add bpf_snprintf_btf helper") Signed-off-by: Wang Qing Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/1604735144-686-1-git-send-email-wangqing@vivo.com --- kernel/trace/bpf_trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 4517c8b66518..5113fd423cdf 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1198,7 +1198,7 @@ static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, *btf = bpf_get_btf_vmlinux(); if (IS_ERR_OR_NULL(*btf)) - return PTR_ERR(*btf); + return IS_ERR(*btf) ? PTR_ERR(*btf) : -EINVAL; if (ptr->type_id > 0) *btf_id = ptr->type_id; -- cgit v1.2.3 From d19d2152ca055baf20339cfacbf039c2cfb8d936 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Thu, 5 Nov 2020 18:06:12 +0100 Subject: arm64: dts: imx8mm: fix voltage for 1.6GHz CPU operating point The datasheet for both the industrial and consumer variant of the SoC lists a typical voltage of 0.95V for the 1.6GHz CPU operating point. Fixes: e85c9d0faa75 (arm64: dts: imx8mm: Add cpufreq properties) Signed-off-by: Lucas Stach Reviewed-by: Fabio Estevam Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mm.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index b83f400def8b..05ee062548e4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -129,7 +129,7 @@ opp-1600000000 { opp-hz = /bits/ 64 <1600000000>; - opp-microvolt = <900000>; + opp-microvolt = <950000>; opp-supported-hw = <0xc>, <0x7>; clock-latency-ns = <150000>; opp-suspend; -- cgit v1.2.3 From 33d0d843872c5ddbe28457a92fc6f2487315fb9f Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Thu, 5 Nov 2020 18:13:20 -0300 Subject: ARM: dts: imx50-evk: Fix the chip select 1 IOMUX The SPI chip selects are represented as: cs-gpios = <&gpio4 11 GPIO_ACTIVE_LOW>, <&gpio4 13 GPIO_ACTIVE_LOW>; , which means that they are used in GPIO function instead of native SPI mode. Fix the IOMUX for the chip select 1 to use GPIO4_13 instead of the native CSPI_SSI function. Fixes: c605cbf5e135 ("ARM: dts: imx: add device tree support for Freescale imx50evk board") Signed-off-by: Fabio Estevam Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx50-evk.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx50-evk.dts b/arch/arm/boot/dts/imx50-evk.dts index 878e89c20190..4ea5c23f181b 100644 --- a/arch/arm/boot/dts/imx50-evk.dts +++ b/arch/arm/boot/dts/imx50-evk.dts @@ -59,7 +59,7 @@ MX50_PAD_CSPI_MISO__CSPI_MISO 0x00 MX50_PAD_CSPI_MOSI__CSPI_MOSI 0x00 MX50_PAD_CSPI_SS0__GPIO4_11 0xc4 - MX50_PAD_ECSPI1_MOSI__CSPI_SS1 0xf4 + MX50_PAD_ECSPI1_MOSI__GPIO4_13 0x84 >; }; -- cgit v1.2.3 From 642403e3599e80370f71ba7a8a8c8fa82e5f6706 Mon Sep 17 00:00:00 2001 From: Colin Xu Date: Mon, 9 Nov 2020 15:39:39 +0800 Subject: drm/i915/gvt: Temporarily disable vfio_edid for BXT/APL Some disply regs are not setup correctly during HPD for BXT/APL thus vfio_edid still not working. Temporarily disable the vfio_edid dynamic update until issue fixed. Acked-by: Zhenyu Wang Signed-off-by: Colin Xu Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20201109073939.758302-1-colin.xu@intel.com --- drivers/gpu/drm/i915/gvt/vgpu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index f6d7e33c7099..399582aeeefb 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -439,7 +439,8 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (IS_BROADWELL(dev_priv)) ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B); - else + /* FixMe: Re-enable APL/BXT once vfio_edid enabled */ + else if (!IS_BROXTON(dev_priv)) ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); if (ret) goto out_clean_sched_policy; -- cgit v1.2.3 From 48f486e13ffdb49fbb9b38c21d0e108ed60ab1a2 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 10 Nov 2020 09:14:43 +0800 Subject: net: xfrm: fix memory leak in xfrm_user_policy() if xfrm_get_translator() failed, xfrm_user_policy() return without freeing 'data', which is allocated in memdup_sockptr(). Fixes: 96392ee5a13b ("xfrm/compat: Translate 32-bit user_policy from sockptr") Reported-by: Hulk Robot Signed-off-by: Yu Kuai Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_state.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index a77da7aae6fe..2f1517827995 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2382,8 +2382,10 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) if (in_compat_syscall()) { struct xfrm_translator *xtr = xfrm_get_translator(); - if (!xtr) + if (!xtr) { + kfree(data); return -EOPNOTSUPP; + } err = xtr->xlate_user_policy_sockptr(&data, optlen); xfrm_put_translator(xtr); -- cgit v1.2.3 From 29a25b9246f7f24203d30d59424cbe22bd905dfc Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 9 Nov 2020 17:40:13 +0200 Subject: dmaengine: ti: omap-dma: Block PM if SDMA is busy to fix audio We now use cpu_pm for saving and restoring device context for deeper SoC idle states. But for omap3, we must also block idle if SDMA is busy. If we don't block idle when SDMA is busy, we eventually end up saving and restoring SDMA register state on PER domain idle while SDMA is active and that causes at least audio playback to fail. Fixes: 4c74ecf79227 ("dmaengine: ti: omap-dma: Add device tree match data and use it for cpu_pm") Reported-by: Peter Ujfalusi Signed-off-by: Tony Lindgren Tested-by: Peter Ujfalusi Acked-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20201109154013.11950-1-tony@atomide.com Signed-off-by: Vinod Koul --- drivers/dma/ti/omap-dma.c | 37 ++++++++++++++++++++++++------------- 1 file changed, 24 insertions(+), 13 deletions(-) diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c index c9fe5e3a6b55..268a08058714 100644 --- a/drivers/dma/ti/omap-dma.c +++ b/drivers/dma/ti/omap-dma.c @@ -1522,29 +1522,38 @@ static void omap_dma_free(struct omap_dmadev *od) } } +/* Currently used by omap2 & 3 to block deeper SoC idle states */ +static bool omap_dma_busy(struct omap_dmadev *od) +{ + struct omap_chan *c; + int lch = -1; + + while (1) { + lch = find_next_bit(od->lch_bitmap, od->lch_count, lch + 1); + if (lch >= od->lch_count) + break; + c = od->lch_map[lch]; + if (!c) + continue; + if (omap_dma_chan_read(c, CCR) & CCR_ENABLE) + return true; + } + + return false; +} + /* Currently only used for omap2. For omap1, also a check for lcd_dma is needed */ static int omap_dma_busy_notifier(struct notifier_block *nb, unsigned long cmd, void *v) { struct omap_dmadev *od; - struct omap_chan *c; - int lch = -1; od = container_of(nb, struct omap_dmadev, nb); switch (cmd) { case CPU_CLUSTER_PM_ENTER: - while (1) { - lch = find_next_bit(od->lch_bitmap, od->lch_count, - lch + 1); - if (lch >= od->lch_count) - break; - c = od->lch_map[lch]; - if (!c) - continue; - if (omap_dma_chan_read(c, CCR) & CCR_ENABLE) - return NOTIFY_BAD; - } + if (omap_dma_busy(od)) + return NOTIFY_BAD; break; case CPU_CLUSTER_PM_ENTER_FAILED: case CPU_CLUSTER_PM_EXIT: @@ -1595,6 +1604,8 @@ static int omap_dma_context_notifier(struct notifier_block *nb, switch (cmd) { case CPU_CLUSTER_PM_ENTER: + if (omap_dma_busy(od)) + return NOTIFY_BAD; omap_dma_context_save(od); break; case CPU_CLUSTER_PM_ENTER_FAILED: -- cgit v1.2.3 From c088a4985e5f6f6c2cbe5a6953357dfc30b7c57e Mon Sep 17 00:00:00 2001 From: Pi-Hsun Shih Date: Fri, 6 Nov 2020 14:48:17 +0800 Subject: regulator: core: don't disable regulator if is_enabled return error. In regulator_late_cleanup when is_enabled failed, don't try to disable the regulator since it would likely to fail too and causing confusing error messages. Signed-off-by: Pi-Hsun Shih Link: https://lore.kernel.org/r/20201106064817.3290927-1-pihsun@chromium.org Signed-off-by: Mark Brown --- drivers/regulator/core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index a5ad553da8cd..70168f2a53ed 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5843,13 +5843,14 @@ static int regulator_late_cleanup(struct device *dev, void *data) if (rdev->use_count) goto unlock; - /* If we can't read the status assume it's on. */ + /* If we can't read the status assume it's always on. */ if (ops->is_enabled) enabled = ops->is_enabled(rdev); else enabled = 1; - if (!enabled) + /* But if reading the status failed, assume that it's off. */ + if (enabled <= 0) goto unlock; if (have_full_constraints()) { -- cgit v1.2.3 From 5c1d644c09dbc13b2dc652435786e42b05ac1bb7 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 13 Oct 2020 10:51:58 +0100 Subject: drm/tegra: sor: Ensure regulators are disabled on teardown The Tegra SOR driver uses the devm infrastructure to request regulators, but enables them without registering them with the infrastructure. This results in the following splat if probing fails for any odd resaon (such as dependencies not being available): [ 8.974187] tegra-sor 15580000.sor: cannot get HDMI supply: -517 [ 9.414403] tegra-sor 15580000.sor: failed to probe HDMI: -517 [ 9.421240] ------------[ cut here ]------------ [ 9.425879] WARNING: CPU: 1 PID: 164 at drivers/regulator/core.c:2089 _regulator_put.part.0+0x16c/0x174 [ 9.435259] Modules linked in: tegra_drm(E+) cec(E) ahci_tegra(E) drm_kms_helper(E) drm(E) libahci_platform(E) libahci(E) max77620_regulator(E) xhci_tegra(E+) sdhci_tegra(E) xhci_hcd(E) libata(E) sdhci_pltfm(E) cqhci(E) fixed(E) usbcore(E) scsi_mod(E) sdhci(E) host1x(E) [ 9.459211] CPU: 1 PID: 164 Comm: systemd-udevd Tainted: G S D W E 5.9.0-rc7-00298-gf6337624c4fe #1980 [ 9.469285] Hardware name: NVIDIA Jetson TX2 Developer Kit (DT) [ 9.475202] pstate: 80000005 (Nzcv daif -PAN -UAO BTYPE=--) [ 9.480784] pc : _regulator_put.part.0+0x16c/0x174 [ 9.485581] lr : regulator_put+0x44/0x60 [ 9.489501] sp : ffffffc011d837b0 [ 9.492814] x29: ffffffc011d837b0 x28: ffffff81dd085900 [ 9.498141] x27: ffffff81de1c8ec0 x26: ffffff81de1c8c10 [ 9.503464] x25: ffffff81dd085800 x24: ffffffc008f2c6b0 [ 9.508790] x23: ffffffc0117373f0 x22: 0000000000000005 [ 9.514101] x21: ffffff81dd085900 x20: ffffffc01172b098 [ 9.515822] ata1: SATA link down (SStatus 0 SControl 300) [ 9.519426] x19: ffffff81dd085100 x18: 0000000000000030 [ 9.530122] x17: 0000000000000000 x16: 0000000000000000 [ 9.535453] x15: 0000000000000000 x14: 000000000000038f [ 9.540777] x13: 0000000000000003 x12: 0000000000000040 [ 9.546105] x11: ffffff81eb800000 x10: 0000000000000ae0 [ 9.551417] x9 : ffffffc0106fea24 x8 : ffffff81de83e6c0 [ 9.556728] x7 : 0000000000000018 x6 : 00000000000003c3 [ 9.562064] x5 : 0000000000005660 x4 : 0000000000000000 [ 9.567392] x3 : ffffffc01172b388 x2 : ffffff81de83db80 [ 9.572702] x1 : 0000000000000000 x0 : 0000000000000001 [ 9.578034] Call trace: [ 9.580494] _regulator_put.part.0+0x16c/0x174 [ 9.584940] regulator_put+0x44/0x60 [ 9.588522] devm_regulator_release+0x20/0x2c [ 9.592885] release_nodes+0x1c8/0x2c0 [ 9.596636] devres_release_all+0x44/0x6c [ 9.600649] really_probe+0x1ec/0x504 [ 9.604316] driver_probe_device+0x100/0x170 [ 9.608589] device_driver_attach+0xcc/0xd4 [ 9.612774] __driver_attach+0xb0/0x17c [ 9.616614] bus_for_each_dev+0x7c/0xd4 [ 9.620450] driver_attach+0x30/0x3c [ 9.624027] bus_add_driver+0x154/0x250 [ 9.627867] driver_register+0x84/0x140 [ 9.631719] __platform_register_drivers+0xa0/0x180 [ 9.636660] host1x_drm_init+0x60/0x1000 [tegra_drm] [ 9.641629] do_one_initcall+0x54/0x2d0 [ 9.645490] do_init_module+0x68/0x29c [ 9.649244] load_module+0x2178/0x26c0 [ 9.652997] __do_sys_finit_module+0xb0/0x120 [ 9.657356] __arm64_sys_finit_module+0x2c/0x40 [ 9.661902] el0_svc_common.constprop.0+0x80/0x240 [ 9.666701] do_el0_svc+0x30/0xa0 [ 9.670022] el0_svc+0x18/0x50 [ 9.673081] el0_sync_handler+0x90/0x318 [ 9.677006] el0_sync+0x158/0x180 [ 9.680324] ---[ end trace 90f6c89d62d85ff6 ]--- Instead, let's register a callback that will disable the regulators on teardown. This allows for the removal of the .remove callbacks, which are not needed anymore. Signed-off-by: Marc Zyngier Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/sor.c | 59 ++++++++++++++++++--------------------------- 1 file changed, 24 insertions(+), 35 deletions(-) diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index a5b944dacb35..00656d8b98e2 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -397,7 +397,6 @@ struct tegra_sor; struct tegra_sor_ops { const char *name; int (*probe)(struct tegra_sor *sor); - int (*remove)(struct tegra_sor *sor); void (*audio_enable)(struct tegra_sor *sor); void (*audio_disable)(struct tegra_sor *sor); }; @@ -2942,6 +2941,24 @@ static const struct drm_encoder_helper_funcs tegra_sor_dp_helpers = { .atomic_check = tegra_sor_encoder_atomic_check, }; +static void tegra_sor_disable_regulator(void *data) +{ + struct regulator *reg = data; + + regulator_disable(reg); +} + +static int tegra_sor_enable_regulator(struct tegra_sor *sor, struct regulator *reg) +{ + int err; + + err = regulator_enable(reg); + if (err) + return err; + + return devm_add_action_or_reset(sor->dev, tegra_sor_disable_regulator, reg); +} + static int tegra_sor_hdmi_probe(struct tegra_sor *sor) { int err; @@ -2953,7 +2970,7 @@ static int tegra_sor_hdmi_probe(struct tegra_sor *sor) return PTR_ERR(sor->avdd_io_supply); } - err = regulator_enable(sor->avdd_io_supply); + err = tegra_sor_enable_regulator(sor, sor->avdd_io_supply); if (err < 0) { dev_err(sor->dev, "failed to enable AVDD I/O supply: %d\n", err); @@ -2967,7 +2984,7 @@ static int tegra_sor_hdmi_probe(struct tegra_sor *sor) return PTR_ERR(sor->vdd_pll_supply); } - err = regulator_enable(sor->vdd_pll_supply); + err = tegra_sor_enable_regulator(sor, sor->vdd_pll_supply); if (err < 0) { dev_err(sor->dev, "failed to enable VDD PLL supply: %d\n", err); @@ -2981,7 +2998,7 @@ static int tegra_sor_hdmi_probe(struct tegra_sor *sor) return PTR_ERR(sor->hdmi_supply); } - err = regulator_enable(sor->hdmi_supply); + err = tegra_sor_enable_regulator(sor, sor->hdmi_supply); if (err < 0) { dev_err(sor->dev, "failed to enable HDMI supply: %d\n", err); return err; @@ -2992,19 +3009,9 @@ static int tegra_sor_hdmi_probe(struct tegra_sor *sor) return 0; } -static int tegra_sor_hdmi_remove(struct tegra_sor *sor) -{ - regulator_disable(sor->hdmi_supply); - regulator_disable(sor->vdd_pll_supply); - regulator_disable(sor->avdd_io_supply); - - return 0; -} - static const struct tegra_sor_ops tegra_sor_hdmi_ops = { .name = "HDMI", .probe = tegra_sor_hdmi_probe, - .remove = tegra_sor_hdmi_remove, .audio_enable = tegra_sor_hdmi_audio_enable, .audio_disable = tegra_sor_hdmi_audio_disable, }; @@ -3017,7 +3024,7 @@ static int tegra_sor_dp_probe(struct tegra_sor *sor) if (IS_ERR(sor->avdd_io_supply)) return PTR_ERR(sor->avdd_io_supply); - err = regulator_enable(sor->avdd_io_supply); + err = tegra_sor_enable_regulator(sor, sor->avdd_io_supply); if (err < 0) return err; @@ -3025,25 +3032,16 @@ static int tegra_sor_dp_probe(struct tegra_sor *sor) if (IS_ERR(sor->vdd_pll_supply)) return PTR_ERR(sor->vdd_pll_supply); - err = regulator_enable(sor->vdd_pll_supply); + err = tegra_sor_enable_regulator(sor, sor->vdd_pll_supply); if (err < 0) return err; return 0; } -static int tegra_sor_dp_remove(struct tegra_sor *sor) -{ - regulator_disable(sor->vdd_pll_supply); - regulator_disable(sor->avdd_io_supply); - - return 0; -} - static const struct tegra_sor_ops tegra_sor_dp_ops = { .name = "DP", .probe = tegra_sor_dp_probe, - .remove = tegra_sor_dp_remove, }; static int tegra_sor_init(struct host1x_client *client) @@ -3773,7 +3771,7 @@ static int tegra_sor_probe(struct platform_device *pdev) if (err < 0) { dev_err(&pdev->dev, "failed to probe %s: %d\n", sor->ops->name, err); - goto output; + goto remove; } } @@ -3954,9 +3952,6 @@ unregister: rpm_disable: pm_runtime_disable(&pdev->dev); remove: - if (sor->ops && sor->ops->remove) - sor->ops->remove(sor); -output: tegra_output_remove(&sor->output); return err; } @@ -3975,12 +3970,6 @@ static int tegra_sor_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); - if (sor->ops && sor->ops->remove) { - err = sor->ops->remove(sor); - if (err < 0) - dev_err(&pdev->dev, "failed to remove SOR: %d\n", err); - } - tegra_output_remove(&sor->output); return 0; -- cgit v1.2.3 From c2fe61d8be491ff8188edaf22e838f819999146b Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Tue, 10 Nov 2020 11:39:19 -0500 Subject: efi/x86: Free efi_pgd with free_pages() Commit d9e9a6418065 ("x86/mm/pti: Allocate a separate user PGD") changed the PGD allocation to allocate PGD_ALLOCATION_ORDER pages, so in the error path it should be freed using free_pages() rather than free_page(). Commit 06ace26f4e6f ("x86/efi: Free efi_pgd with free_pages()") fixed one instance of this, but missed another. Move the freeing out-of-line to avoid code duplication and fix this bug. Fixes: d9e9a6418065 ("x86/mm/pti: Allocate a separate user PGD") Link: https://lore.kernel.org/r/20201110163919.1134431-1-nivedita@alum.mit.edu Signed-off-by: Arvind Sankar Signed-off-by: Ard Biesheuvel --- arch/x86/platform/efi/efi_64.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 8f5759df7776..e1e8d4e3a213 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -78,28 +78,30 @@ int __init efi_alloc_page_tables(void) gfp_mask = GFP_KERNEL | __GFP_ZERO; efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER); if (!efi_pgd) - return -ENOMEM; + goto fail; pgd = efi_pgd + pgd_index(EFI_VA_END); p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END); - if (!p4d) { - free_page((unsigned long)efi_pgd); - return -ENOMEM; - } + if (!p4d) + goto free_pgd; pud = pud_alloc(&init_mm, p4d, EFI_VA_END); - if (!pud) { - if (pgtable_l5_enabled()) - free_page((unsigned long) pgd_page_vaddr(*pgd)); - free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); - return -ENOMEM; - } + if (!pud) + goto free_p4d; efi_mm.pgd = efi_pgd; mm_init_cpumask(&efi_mm); init_new_context(NULL, &efi_mm); return 0; + +free_p4d: + if (pgtable_l5_enabled()) + free_page((unsigned long)pgd_page_vaddr(*pgd)); +free_pgd: + free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); +fail: + return -ENOMEM; } /* -- cgit v1.2.3 From c8a2e7a29702fe4626b7aa81149b7b7164e20606 Mon Sep 17 00:00:00 2001 From: Mordechay Goodstein Date: Sat, 7 Nov 2020 10:50:06 +0200 Subject: iwlwifi: sta: set max HE max A-MPDU according to HE capa Currently, our max tpt is limited to max HT A-MPDU for LB, and max VHT A-MPDU for HB. Configure HE exponent value correctly to achieve HE max A-MPDU, both on LB and HB. Signed-off-by: Mordechay Goodstein Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/iwlwifi.20201107104557.4486852ebb56.I9eb0d028e31f183597fb90120e7d4ca87e0dd6cb@changeid --- drivers/net/wireless/intel/iwlwifi/fw/api/sta.h | 10 +++++----- drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 18 ++++++++++++++++++ 2 files changed, 23 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h index d43e0d3f3a12..052413eef059 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h @@ -5,10 +5,9 @@ * * GPL LICENSE SUMMARY * - * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 - 2019 Intel Corporation + * Copyright(c) 2012-2014, 2018 - 2020 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -28,10 +27,9 @@ * * BSD LICENSE * - * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 - 2019 Intel Corporation + * Copyright(c) 2012-2014, 2018 - 2020 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -128,7 +126,9 @@ enum iwl_sta_flags { STA_FLG_MAX_AGG_SIZE_256K = (5 << STA_FLG_MAX_AGG_SIZE_SHIFT), STA_FLG_MAX_AGG_SIZE_512K = (6 << STA_FLG_MAX_AGG_SIZE_SHIFT), STA_FLG_MAX_AGG_SIZE_1024K = (7 << STA_FLG_MAX_AGG_SIZE_SHIFT), - STA_FLG_MAX_AGG_SIZE_MSK = (7 << STA_FLG_MAX_AGG_SIZE_SHIFT), + STA_FLG_MAX_AGG_SIZE_2M = (8 << STA_FLG_MAX_AGG_SIZE_SHIFT), + STA_FLG_MAX_AGG_SIZE_4M = (9 << STA_FLG_MAX_AGG_SIZE_SHIFT), + STA_FLG_MAX_AGG_SIZE_MSK = (0xf << STA_FLG_MAX_AGG_SIZE_SHIFT), STA_FLG_AGG_MPDU_DENS_SHIFT = 23, STA_FLG_AGG_MPDU_DENS_2US = (4 << STA_FLG_AGG_MPDU_DENS_SHIFT), diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 017537944fd0..799d8219463c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -196,6 +196,7 @@ int iwl_mvm_sta_send_to_fw(struct iwl_mvm *mvm, struct ieee80211_sta *sta, mpdu_dens = sta->ht_cap.ampdu_density; } + if (sta->vht_cap.vht_supported) { agg_size = sta->vht_cap.cap & IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; @@ -205,6 +206,23 @@ int iwl_mvm_sta_send_to_fw(struct iwl_mvm *mvm, struct ieee80211_sta *sta, agg_size = sta->ht_cap.ampdu_factor; } + /* D6.0 10.12.2 A-MPDU length limit rules + * A STA indicates the maximum length of the A-MPDU preEOF padding + * that it can receive in an HE PPDU in the Maximum A-MPDU Length + * Exponent field in its HT Capabilities, VHT Capabilities, + * and HE 6 GHz Band Capabilities elements (if present) and the + * Maximum AMPDU Length Exponent Extension field in its HE + * Capabilities element + */ + if (sta->he_cap.has_he) + agg_size += u8_get_bits(sta->he_cap.he_cap_elem.mac_cap_info[3], + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK); + + /* Limit to max A-MPDU supported by FW */ + if (agg_size > (STA_FLG_MAX_AGG_SIZE_4M >> STA_FLG_MAX_AGG_SIZE_SHIFT)) + agg_size = (STA_FLG_MAX_AGG_SIZE_4M >> + STA_FLG_MAX_AGG_SIZE_SHIFT); + add_sta_cmd.station_flags |= cpu_to_le32(agg_size << STA_FLG_MAX_AGG_SIZE_SHIFT); add_sta_cmd.station_flags |= -- cgit v1.2.3 From fb8d1b6e97980057b7ebed444b8950e57f268a67 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sat, 7 Nov 2020 10:50:07 +0200 Subject: iwlwifi: mvm: use the HOT_SPOT_CMD to cancel an AUX ROC The ROC that runs on the AUX ROC (meaning an ROC on the STA vif), was added with the HOT_SPOT_CMD firmware command and must be cancelled with that same command. Signed-off-by: Emmanuel Grumbach Fixes: fe959c7b2049 ("iwlwifi: mvm: use the new session protection command") Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/iwlwifi.20201107104557.a317376154da.I44fa3637373ba4bd421cdff2cabc761bffc0735f@changeid --- drivers/net/wireless/intel/iwlwifi/mvm/time-event.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 7fce79c1c114..a9ebe69a6670 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -988,10 +988,13 @@ void iwl_mvm_stop_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif) IWL_UCODE_TLV_CAPA_SESSION_PROT_CMD)) { mvmvif = iwl_mvm_vif_from_mac80211(vif); - iwl_mvm_cancel_session_protection(mvm, mvmvif); - - if (vif->type == NL80211_IFTYPE_P2P_DEVICE) + if (vif->type == NL80211_IFTYPE_P2P_DEVICE) { + iwl_mvm_cancel_session_protection(mvm, mvmvif); set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status); + } else { + iwl_mvm_remove_aux_roc_te(mvm, mvmvif, + &mvmvif->time_event_data); + } iwl_mvm_roc_finished(mvm); -- cgit v1.2.3 From 1cf260e3a75b87726ec609ad1b6b88f515749786 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sat, 7 Nov 2020 10:50:08 +0200 Subject: iwlwifi: mvm: properly cancel a session protection for P2P We need to feed the configuration id to remove session protection properly. Remember the conf_id when we add the session protection so that we can give it back when we want to remove the session protection. While at it, slightly improve the kernel doc for the conf_id of the notification. Signed-off-by: Emmanuel Grumbach Fixes: fe959c7b2049 ("iwlwifi: mvm: use the new session protection command") Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/iwlwifi.20201107104557.3642f730333d.I01a98ecde62096d00d171cf34ad775bf80cb0277@changeid --- .../net/wireless/intel/iwlwifi/fw/api/time-event.h | 8 +- .../net/wireless/intel/iwlwifi/mvm/time-event.c | 94 +++++++++++++++------- 2 files changed, 68 insertions(+), 34 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h b/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h index a731f28e101a..53b438d709db 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h @@ -8,7 +8,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 - 2019 Intel Corporation + * Copyright(c) 2018 - 2020 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -31,7 +31,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 - 2019 Intel Corporation + * Copyright(c) 2018 - 2020 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -421,12 +421,14 @@ struct iwl_hs20_roc_res { * able to run the GO Negotiation. Will not be fragmented and not * repetitive. Valid only on the P2P Device MAC. Only the duration will * be taken into account. + * @SESSION_PROTECT_CONF_MAX_ID: not used */ enum iwl_mvm_session_prot_conf_id { SESSION_PROTECT_CONF_ASSOC, SESSION_PROTECT_CONF_GO_CLIENT_ASSOC, SESSION_PROTECT_CONF_P2P_DEVICE_DISCOV, SESSION_PROTECT_CONF_P2P_GO_NEGOTIATION, + SESSION_PROTECT_CONF_MAX_ID, }; /* SESSION_PROTECTION_CONF_ID_E_VER_1 */ /** @@ -459,7 +461,7 @@ struct iwl_mvm_session_prot_cmd { * @mac_id: the mac id for which the session protection started / ended * @status: 1 means success, 0 means failure * @start: 1 means the session protection started, 0 means it ended - * @conf_id: the configuration id of the session that started / eneded + * @conf_id: see &enum iwl_mvm_session_prot_conf_id * * Note that any session protection will always get two notifications: start * and end even the firmware could not schedule it. diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index a9ebe69a6670..1db6d8d38822 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -641,11 +641,32 @@ void iwl_mvm_protect_session(struct iwl_mvm *mvm, } } +static void iwl_mvm_cancel_session_protection(struct iwl_mvm *mvm, + struct iwl_mvm_vif *mvmvif) +{ + struct iwl_mvm_session_prot_cmd cmd = { + .id_and_color = + cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->id, + mvmvif->color)), + .action = cpu_to_le32(FW_CTXT_ACTION_REMOVE), + .conf_id = cpu_to_le32(mvmvif->time_event_data.id), + }; + int ret; + + ret = iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(SESSION_PROTECTION_CMD, + MAC_CONF_GROUP, 0), + 0, sizeof(cmd), &cmd); + if (ret) + IWL_ERR(mvm, + "Couldn't send the SESSION_PROTECTION_CMD: %d\n", ret); +} + static bool __iwl_mvm_remove_time_event(struct iwl_mvm *mvm, struct iwl_mvm_time_event_data *te_data, u32 *uid) { u32 id; + struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(te_data->vif); /* * It is possible that by the time we got to this point the time @@ -663,14 +684,29 @@ static bool __iwl_mvm_remove_time_event(struct iwl_mvm *mvm, iwl_mvm_te_clear_data(mvm, te_data); spin_unlock_bh(&mvm->time_event_lock); - /* - * It is possible that by the time we try to remove it, the time event - * has already ended and removed. In such a case there is no need to - * send a removal command. + /* When session protection is supported, the te_data->id field + * is reused to save session protection's configuration. */ - if (id == TE_MAX) { - IWL_DEBUG_TE(mvm, "TE 0x%x has already ended\n", *uid); + if (fw_has_capa(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_SESSION_PROT_CMD)) { + if (mvmvif && id < SESSION_PROTECT_CONF_MAX_ID) { + /* Session protection is still ongoing. Cancel it */ + iwl_mvm_cancel_session_protection(mvm, mvmvif); + if (te_data->vif->type == NL80211_IFTYPE_P2P_DEVICE) { + set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status); + iwl_mvm_roc_finished(mvm); + } + } return false; + } else { + /* It is possible that by the time we try to remove it, the + * time event has already ended and removed. In such a case + * there is no need to send a removal command. + */ + if (id == TE_MAX) { + IWL_DEBUG_TE(mvm, "TE 0x%x has already ended\n", *uid); + return false; + } } return true; @@ -771,6 +807,7 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm, struct iwl_rx_packet *pkt = rxb_addr(rxb); struct iwl_mvm_session_prot_notif *notif = (void *)pkt->data; struct ieee80211_vif *vif; + struct iwl_mvm_vif *mvmvif; rcu_read_lock(); vif = iwl_mvm_rcu_dereference_vif_id(mvm, le32_to_cpu(notif->mac_id), @@ -779,9 +816,10 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm, if (!vif) goto out_unlock; + mvmvif = iwl_mvm_vif_from_mac80211(vif); + /* The vif is not a P2P_DEVICE, maintain its time_event_data */ if (vif->type != NL80211_IFTYPE_P2P_DEVICE) { - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_mvm_time_event_data *te_data = &mvmvif->time_event_data; @@ -816,10 +854,14 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm, if (!le32_to_cpu(notif->status) || !le32_to_cpu(notif->start)) { /* End TE, notify mac80211 */ + mvmvif->time_event_data.id = SESSION_PROTECT_CONF_MAX_ID; ieee80211_remain_on_channel_expired(mvm->hw); set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status); iwl_mvm_roc_finished(mvm); } else if (le32_to_cpu(notif->start)) { + if (WARN_ON(mvmvif->time_event_data.id != + le32_to_cpu(notif->conf_id))) + goto out_unlock; set_bit(IWL_MVM_STATUS_ROC_RUNNING, &mvm->status); ieee80211_ready_on_channel(mvm->hw); /* Start TE */ } @@ -845,20 +887,24 @@ iwl_mvm_start_p2p_roc_session_protection(struct iwl_mvm *mvm, lockdep_assert_held(&mvm->mutex); + /* The time_event_data.id field is reused to save session + * protection's configuration. + */ switch (type) { case IEEE80211_ROC_TYPE_NORMAL: - cmd.conf_id = - cpu_to_le32(SESSION_PROTECT_CONF_P2P_DEVICE_DISCOV); + mvmvif->time_event_data.id = + SESSION_PROTECT_CONF_P2P_DEVICE_DISCOV; break; case IEEE80211_ROC_TYPE_MGMT_TX: - cmd.conf_id = - cpu_to_le32(SESSION_PROTECT_CONF_P2P_GO_NEGOTIATION); + mvmvif->time_event_data.id = + SESSION_PROTECT_CONF_P2P_GO_NEGOTIATION; break; default: WARN_ONCE(1, "Got an invalid ROC type\n"); return -EINVAL; } + cmd.conf_id = cpu_to_le32(mvmvif->time_event_data.id); return iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(SESSION_PROTECTION_CMD, MAC_CONF_GROUP, 0), 0, sizeof(cmd), &cmd); @@ -960,25 +1006,6 @@ void iwl_mvm_cleanup_roc_te(struct iwl_mvm *mvm) __iwl_mvm_remove_time_event(mvm, te_data, &uid); } -static void iwl_mvm_cancel_session_protection(struct iwl_mvm *mvm, - struct iwl_mvm_vif *mvmvif) -{ - struct iwl_mvm_session_prot_cmd cmd = { - .id_and_color = - cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->id, - mvmvif->color)), - .action = cpu_to_le32(FW_CTXT_ACTION_REMOVE), - }; - int ret; - - ret = iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(SESSION_PROTECTION_CMD, - MAC_CONF_GROUP, 0), - 0, sizeof(cmd), &cmd); - if (ret) - IWL_ERR(mvm, - "Couldn't send the SESSION_PROTECTION_CMD: %d\n", ret); -} - void iwl_mvm_stop_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif) { struct iwl_mvm_vif *mvmvif; @@ -1129,10 +1156,15 @@ void iwl_mvm_schedule_session_protection(struct iwl_mvm *mvm, cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->id, mvmvif->color)), .action = cpu_to_le32(FW_CTXT_ACTION_ADD), - .conf_id = cpu_to_le32(SESSION_PROTECT_CONF_ASSOC), .duration_tu = cpu_to_le32(MSEC_TO_TU(duration)), }; + /* The time_event_data.id field is reused to save session + * protection's configuration. + */ + mvmvif->time_event_data.id = SESSION_PROTECT_CONF_ASSOC; + cmd.conf_id = cpu_to_le32(mvmvif->time_event_data.id); + lockdep_assert_held(&mvm->mutex); spin_lock_bh(&mvm->time_event_lock); -- cgit v1.2.3 From 97cc16943f23078535fdbce4f6391b948b4ccc08 Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Sat, 7 Nov 2020 10:50:09 +0200 Subject: iwlwifi: mvm: write queue_sync_state only for sync We use mvm->queue_sync_state to wait for synchronous queue sync messages, but if an async one happens inbetween we shouldn't clear mvm->queue_sync_state after sending the async one, that can run concurrently (at least from the CPU POV) with another synchronous queue sync. Signed-off-by: Johannes Berg Fixes: 3c514bf831ac ("iwlwifi: mvm: add a loose synchronization of the NSSN across Rx queues") Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/iwlwifi.20201107104557.51a3148f2c14.I0772171dbaec87433a11513e9586d98b5d920b5f@changeid --- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 688c1125e67b..62e884f3e29e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -3127,6 +3127,9 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw, goto out_unlock; } + if (vif->type == NL80211_IFTYPE_STATION) + vif->bss_conf.he_support = sta->he_cap.has_he; + if (sta->tdls && (vif->p2p || iwl_mvm_tdls_sta_count(mvm, NULL) == -- cgit v1.2.3 From edb625208d84aef179e3f16590c1c582fc5fdae6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 7 Nov 2020 10:50:10 +0200 Subject: iwlwifi: pcie: set LTR to avoid completion timeout On some platforms, the preset values aren't correct and then we may get a completion timeout in the firmware. Change the LTR configuration to avoid that. The firmware will do some more complex reinit of this later, but for the boot process we use ~250usec. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/iwlwifi.20201107104557.d83d591c05ba.I42885c9fb500bc08b9a4c07c4ff3d436cc7a3c84@changeid --- drivers/net/wireless/intel/iwlwifi/iwl-csr.h | 10 ++++++++++ .../net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c | 20 ++++++++++++++++++++ 2 files changed, 30 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h index cb9e8e189a1a..1d48c7d7fffd 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h @@ -147,6 +147,16 @@ #define CSR_MAC_SHADOW_REG_CTL2 (CSR_BASE + 0x0AC) #define CSR_MAC_SHADOW_REG_CTL2_RX_WAKE 0xFFFF +/* LTR control (since IWL_DEVICE_FAMILY_22000) */ +#define CSR_LTR_LONG_VAL_AD (CSR_BASE + 0x0D4) +#define CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ 0x80000000 +#define CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE 0x1c000000 +#define CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL 0x03ff0000 +#define CSR_LTR_LONG_VAL_AD_SNOOP_REQ 0x00008000 +#define CSR_LTR_LONG_VAL_AD_SNOOP_SCALE 0x00001c00 +#define CSR_LTR_LONG_VAL_AD_SNOOP_VAL 0x000003ff +#define CSR_LTR_LONG_VAL_AD_SCALE_USEC 2 + /* GIO Chicken Bits (PCI Express bus link power management) */ #define CSR_GIO_CHICKEN_BITS (CSR_BASE+0x100) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c index a0352fa873d9..5512e3c630c3 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c @@ -252,6 +252,26 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, iwl_set_bit(trans, CSR_CTXT_INFO_BOOT_CTRL, CSR_AUTO_FUNC_BOOT_ENA); + + if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210) { + /* + * The firmware initializes this again later (to a smaller + * value), but for the boot process initialize the LTR to + * ~250 usec. + */ + u32 val = CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ | + u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, + CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE) | + u32_encode_bits(250, + CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL) | + CSR_LTR_LONG_VAL_AD_SNOOP_REQ | + u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, + CSR_LTR_LONG_VAL_AD_SNOOP_SCALE) | + u32_encode_bits(250, CSR_LTR_LONG_VAL_AD_SNOOP_VAL); + + iwl_write32(trans, CSR_LTR_LONG_VAL_AD, val); + } + if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) iwl_write_umac_prph(trans, UREG_CPU_INIT_RUN, 1); else -- cgit v1.2.3 From fe56d05ee6c87f6a1a8c7267affd92c9438249cc Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Sat, 7 Nov 2020 10:50:11 +0200 Subject: iwlwifi: mvm: fix kernel panic in case of assert during CSA During CSA, we briefly nullify the phy context, in __iwl_mvm_unassign_vif_chanctx. In case we have a FW assert right after it, it remains NULL though. We end up running into endless loop due to mac80211 trying repeatedly to move us to ASSOC state, and we keep returning -EINVAL. Later down the road we hit a kernel panic. Detect and avoid this endless loop. Signed-off-by: Sara Sharon Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/iwlwifi.20201107104557.d64de2c17bff.Iedd0d2afa20a2aacba5259a5cae31cb3a119a4eb@changeid --- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 62e884f3e29e..b627e7da7ac9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -3080,7 +3080,7 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw, /* this would be a mac80211 bug ... but don't crash */ if (WARN_ON_ONCE(!mvmvif->phy_ctxt)) - return -EINVAL; + return test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status) ? 0 : -EINVAL; /* * If we are in a STA removal flow and in DQA mode: -- cgit v1.2.3 From 41f71629b4c432f8dd47d70ace813be5f79d4d75 Mon Sep 17 00:00:00 2001 From: Deepak R Varma Date: Thu, 5 Nov 2020 23:29:28 +0530 Subject: drm/tegra: replace idr_init() by idr_init_base() idr_init() uses base 0 which is an invalid identifier for this driver. The new function idr_init_base allows IDR to set the ID lookup from base 1. This avoids all lookups that otherwise starts from 0 since 0 is always unused. References: commit 6ce711f27500 ("idr: Make 1-based IDRs more efficient") Signed-off-by: Deepak R Varma Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/drm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index ba9d1c3e7cac..e4baf07992a4 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -90,7 +90,7 @@ static int tegra_drm_open(struct drm_device *drm, struct drm_file *filp) if (!fpriv) return -ENOMEM; - idr_init(&fpriv->contexts); + idr_init_base(&fpriv->contexts, 1); mutex_init(&fpriv->lock); filp->driver_priv = fpriv; -- cgit v1.2.3 From c335b4f1f65012713832d988ec06512c7bda5c04 Mon Sep 17 00:00:00 2001 From: Brendan Higgins Date: Thu, 5 Nov 2020 15:24:40 -0800 Subject: kunit: tool: unmark test_data as binary blobs The tools/testing/kunit/test_data/ directory was marked as binary because some of the test_data files cause checkpatch warnings. Fix this by dropping the .gitattributes file. Fixes: afc63da64f1e ("kunit: kunit_parser: make parser more robust") Signed-off-by: Brendan Higgins Signed-off-by: Shuah Khan --- tools/testing/kunit/.gitattributes | 1 - 1 file changed, 1 deletion(-) delete mode 100644 tools/testing/kunit/.gitattributes diff --git a/tools/testing/kunit/.gitattributes b/tools/testing/kunit/.gitattributes deleted file mode 100644 index 5b7da1fc3b8f..000000000000 --- a/tools/testing/kunit/.gitattributes +++ /dev/null @@ -1 +0,0 @@ -test_data/* binary -- cgit v1.2.3 From 3959d0a63b3202ea2aa12b3f6effd5400d773d31 Mon Sep 17 00:00:00 2001 From: David Gow Date: Wed, 21 Oct 2020 00:16:03 -0700 Subject: kunit: Fix kunit.py parse subcommand (use null build_dir) When JSON support was added in [1], the KunitParseRequest tuple was updated to contain a 'build_dir' field, but kunit.py parse doesn't accept --build_dir as an option. The code nevertheless tried to access it, resulting in this error: AttributeError: 'Namespace' object has no attribute 'build_dir' Given that the parser only uses the build_dir variable to set the 'build_environment' json field, we set it to None (which gives the JSON 'null') for now. Ultimately, we probably do want to be able to set this, but since it's new functionality which (for the parse subcommand) never worked, this is the quickest way of getting it back up and running. [1]: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git/commit/?h=kunit-fixes&id=21a6d1780d5bbfca0ce9b8104ca6233502fcbf86 Fixes: 21a6d1780d5b ("kunit: tool: allow generating test results in JSON") Signed-off-by: David Gow Reviewed-by: Brendan Higgins Tested-by: Brendan Higgins Signed-off-by: Shuah Khan --- tools/testing/kunit/kunit.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index ebf5f5763dee..a6d5f219f714 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -337,7 +337,7 @@ def main(argv, linux=None): kunit_output = f.read().splitlines() request = KunitParseRequest(cli_args.raw_output, kunit_output, - cli_args.build_dir, + None, cli_args.json) result = parse_tests(request) if result.status != KunitStatus.SUCCESS: -- cgit v1.2.3 From b7e0b983ff13714d261883e89910b0755eb12169 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Wed, 21 Oct 2020 15:07:52 -0700 Subject: kunit: tool: fix pre-existing python type annotation errors The code uses annotations, but they aren't accurate. Note that type checking in python is a separate process, running `kunit.py run` will not check and complain about invalid types at runtime. Fix pre-existing issues found by running a type checker $ mypy *.py All but one of these were returning `None` without denoting this properly (via `Optional[Type]`). Signed-off-by: Daniel Latypov Reviewed-by: David Gow Signed-off-by: Shuah Khan --- tools/testing/kunit/kunit_parser.py | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index 84a1af2581f5..db0347baa428 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -12,7 +12,7 @@ from collections import namedtuple from datetime import datetime from enum import Enum, auto from functools import reduce -from typing import List +from typing import List, Optional, Tuple TestResult = namedtuple('TestResult', ['status','suites','log']) @@ -151,7 +151,7 @@ def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool: else: return False -def parse_test_case(lines: List[str]) -> TestCase: +def parse_test_case(lines: List[str]) -> Optional[TestCase]: test_case = TestCase() save_non_diagnositic(lines, test_case) while parse_diagnostic(lines, test_case): @@ -163,7 +163,7 @@ def parse_test_case(lines: List[str]) -> TestCase: SUBTEST_HEADER = re.compile(r'^[\s]+# Subtest: (.*)$') -def parse_subtest_header(lines: List[str]) -> str: +def parse_subtest_header(lines: List[str]) -> Optional[str]: consume_non_diagnositic(lines) if not lines: return None @@ -176,7 +176,7 @@ def parse_subtest_header(lines: List[str]) -> str: SUBTEST_PLAN = re.compile(r'[\s]+[0-9]+\.\.([0-9]+)') -def parse_subtest_plan(lines: List[str]) -> int: +def parse_subtest_plan(lines: List[str]) -> Optional[int]: consume_non_diagnositic(lines) match = SUBTEST_PLAN.match(lines[0]) if match: @@ -230,7 +230,7 @@ def bubble_up_test_case_errors(test_suite: TestSuite) -> TestStatus: max_test_case_status = bubble_up_errors(lambda x: x.status, test_suite.cases) return max_status(max_test_case_status, test_suite.status) -def parse_test_suite(lines: List[str], expected_suite_index: int) -> TestSuite: +def parse_test_suite(lines: List[str], expected_suite_index: int) -> Optional[TestSuite]: if not lines: return None consume_non_diagnositic(lines) @@ -271,7 +271,7 @@ def parse_tap_header(lines: List[str]) -> bool: TEST_PLAN = re.compile(r'[0-9]+\.\.([0-9]+)') -def parse_test_plan(lines: List[str]) -> int: +def parse_test_plan(lines: List[str]) -> Optional[int]: consume_non_diagnositic(lines) match = TEST_PLAN.match(lines[0]) if match: @@ -310,7 +310,7 @@ def parse_test_result(lines: List[str]) -> TestResult: else: return TestResult(TestStatus.NO_TESTS, [], lines) -def print_and_count_results(test_result: TestResult) -> None: +def print_and_count_results(test_result: TestResult) -> Tuple[int, int, int]: total_tests = 0 failed_tests = 0 crashed_tests = 0 -- cgit v1.2.3 From fcdb0bc08ced274078f371e1e0fe6421a97fa9f2 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 26 Oct 2020 18:59:25 +0200 Subject: kunit: Do not pollute source directory with generated files (.kunitconfig) When --build_dir is provided use it and do not pollute source directory which even can be mounted over network or read-only. Signed-off-by: Andy Shevchenko Reviewed-by: Brendan Higgins Tested-by: Brendan Higgins Signed-off-by: Shuah Khan --- tools/testing/kunit/kunit.py | 25 ++++++++++++------------- tools/testing/kunit/kunit_kernel.py | 24 +++++++++++++++++++----- 2 files changed, 31 insertions(+), 18 deletions(-) diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index a6d5f219f714..d4f7846d0745 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -11,7 +11,6 @@ import argparse import sys import os import time -import shutil from collections import namedtuple from enum import Enum, auto @@ -44,11 +43,6 @@ class KunitStatus(Enum): BUILD_FAILURE = auto() TEST_FAILURE = auto() -def create_default_kunitconfig(): - if not os.path.exists(kunit_kernel.kunitconfig_path): - shutil.copyfile('arch/um/configs/kunit_defconfig', - kunit_kernel.kunitconfig_path) - def get_kernel_root_path(): parts = sys.argv[0] if not __file__ else __file__ parts = os.path.realpath(parts).split('tools/testing/kunit') @@ -61,7 +55,6 @@ def config_tests(linux: kunit_kernel.LinuxSourceTree, kunit_parser.print_with_timestamp('Configuring KUnit Kernel ...') config_start = time.time() - create_default_kunitconfig() success = linux.build_reconfig(request.build_dir, request.make_options) config_end = time.time() if not success: @@ -262,12 +255,12 @@ def main(argv, linux=None): if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() - if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + request = KunitRequest(cli_args.raw_output, cli_args.timeout, cli_args.jobs, @@ -283,12 +276,12 @@ def main(argv, linux=None): not os.path.exists(cli_args.build_dir)): os.mkdir(cli_args.build_dir) - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() - if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + request = KunitConfigRequest(cli_args.build_dir, cli_args.make_options) result = config_tests(linux, request) @@ -301,6 +294,9 @@ def main(argv, linux=None): if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + request = KunitBuildRequest(cli_args.jobs, cli_args.build_dir, cli_args.alltests, @@ -315,6 +311,9 @@ def main(argv, linux=None): if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + exec_request = KunitExecRequest(cli_args.timeout, cli_args.build_dir, cli_args.alltests) diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index b557b1e93f98..633a2efcfdbd 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -6,10 +6,10 @@ # Author: Felix Guo # Author: Brendan Higgins - import logging import subprocess import os +import shutil import signal from contextlib import ExitStack @@ -18,7 +18,8 @@ import kunit_config import kunit_parser KCONFIG_PATH = '.config' -kunitconfig_path = '.kunitconfig' +KUNITCONFIG_PATH = '.kunitconfig' +DEFAULT_KUNITCONFIG_PATH = 'arch/um/configs/kunit_defconfig' BROKEN_ALLCONFIG_PATH = 'tools/testing/kunit/configs/broken_on_uml.config' class ConfigError(Exception): @@ -99,19 +100,22 @@ class LinuxSourceTreeOperations(object): stderr=subprocess.STDOUT) process.wait(timeout) - def get_kconfig_path(build_dir): kconfig_path = KCONFIG_PATH if build_dir: kconfig_path = os.path.join(build_dir, KCONFIG_PATH) return kconfig_path +def get_kunitconfig_path(build_dir): + kunitconfig_path = KUNITCONFIG_PATH + if build_dir: + kunitconfig_path = os.path.join(build_dir, KUNITCONFIG_PATH) + return kunitconfig_path + class LinuxSourceTree(object): """Represents a Linux kernel source tree with KUnit tests.""" def __init__(self): - self._kconfig = kunit_config.Kconfig() - self._kconfig.read_from_file(kunitconfig_path) self._ops = LinuxSourceTreeOperations() signal.signal(signal.SIGINT, self.signal_handler) @@ -123,6 +127,16 @@ class LinuxSourceTree(object): return False return True + def create_kunitconfig(self, build_dir, defconfig=DEFAULT_KUNITCONFIG_PATH): + kunitconfig_path = get_kunitconfig_path(build_dir) + if not os.path.exists(kunitconfig_path): + shutil.copyfile(defconfig, kunitconfig_path) + + def read_kunitconfig(self, build_dir): + kunitconfig_path = get_kunitconfig_path(build_dir) + self._kconfig = kunit_config.Kconfig() + self._kconfig.read_from_file(kunitconfig_path) + def validate_config(self, build_dir): kconfig_path = get_kconfig_path(build_dir) validated_kconfig = kunit_config.Kconfig() -- cgit v1.2.3 From 128dc4bcc8c0c7c3bab4a3818a1ec608cccb017a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 26 Oct 2020 18:59:26 +0200 Subject: kunit: Do not pollute source directory with generated files (test.log) When --build_dir is provided use it and do not pollute source directory which even can be mounted over network or read-only. Signed-off-by: Andy Shevchenko Reviewed-by: Brendan Higgins Tested-by: Brendan Higgins Signed-off-by: Shuah Khan --- tools/testing/kunit/kunit_kernel.py | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 633a2efcfdbd..b4768fa03ce0 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -21,6 +21,7 @@ KCONFIG_PATH = '.config' KUNITCONFIG_PATH = '.kunitconfig' DEFAULT_KUNITCONFIG_PATH = 'arch/um/configs/kunit_defconfig' BROKEN_ALLCONFIG_PATH = 'tools/testing/kunit/configs/broken_on_uml.config' +OUTFILE_PATH = 'test.log' class ConfigError(Exception): """Represents an error trying to configure the Linux kernel.""" @@ -89,11 +90,12 @@ class LinuxSourceTreeOperations(object): except subprocess.CalledProcessError as e: raise BuildError(e.output.decode()) - def linux_bin(self, params, timeout, build_dir, outfile): + def linux_bin(self, params, timeout, build_dir): """Runs the Linux UML binary. Must be named 'linux'.""" linux_bin = './linux' if build_dir: linux_bin = os.path.join(build_dir, 'linux') + outfile = get_outfile_path(build_dir) with open(outfile, 'w') as output: process = subprocess.Popen([linux_bin] + params, stdout=output, @@ -112,6 +114,12 @@ def get_kunitconfig_path(build_dir): kunitconfig_path = os.path.join(build_dir, KUNITCONFIG_PATH) return kunitconfig_path +def get_outfile_path(build_dir): + outfile_path = OUTFILE_PATH + if build_dir: + outfile_path = os.path.join(build_dir, OUTFILE_PATH) + return outfile_path + class LinuxSourceTree(object): """Represents a Linux kernel source tree with KUnit tests.""" @@ -192,8 +200,8 @@ class LinuxSourceTree(object): def run_kernel(self, args=[], build_dir='', timeout=None): args.extend(['mem=1G']) - outfile = 'test.log' - self._ops.linux_bin(args, timeout, build_dir, outfile) + self._ops.linux_bin(args, timeout, build_dir) + outfile = get_outfile_path(build_dir) subprocess.call(['stty', 'sane']) with open(outfile, 'r') as file: for line in file: -- cgit v1.2.3 From f7766424cf15fd6e03e8230fb17d5612c5b76dbe Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 27 Oct 2020 11:48:53 -0700 Subject: KUnit: Docs: fix a wording typo Fix a wording typo (keyboard glitch). Signed-off-by: Randy Dunlap Cc: David Gow Cc: linux-kselftest@vger.kernel.org Cc: kunit-dev@googlegroups.com Cc: Shuah Khan Cc: Shuah Khan Cc: Brendan Higgins Reviewed-by: David Gow Signed-off-by: Shuah Khan --- Documentation/dev-tools/kunit/faq.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/dev-tools/kunit/faq.rst b/Documentation/dev-tools/kunit/faq.rst index 1628862e7024..8d5029ad210a 100644 --- a/Documentation/dev-tools/kunit/faq.rst +++ b/Documentation/dev-tools/kunit/faq.rst @@ -90,7 +90,7 @@ things to try. re-run kunit_tool. 5. Try to run ``make ARCH=um defconfig`` before running ``kunit.py run``. This may help clean up any residual config items which could be causing problems. -6. Finally, try running KUnit outside UML. KUnit and KUnit tests can run be +6. Finally, try running KUnit outside UML. KUnit and KUnit tests can be built into any kernel, or can be built as a module and loaded at runtime. Doing so should allow you to determine if UML is causing the issue you're seeing. When tests are built-in, they will execute when the kernel boots, and -- cgit v1.2.3 From 1f4dde57125b3d91b900e82ac33a196312be5c8e Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 28 Oct 2020 10:42:18 -0700 Subject: KUnit: Docs: style: fix some Kconfig example issues Fix the Kconfig example to be closer to Kconfig coding style. Also add punctuation and a trailing slash ('/') to a sub-directory name -- this is how the text mostly appears in other Kconfig files. Signed-off-by: Randy Dunlap Cc: David Gow Cc: linux-kselftest@vger.kernel.org Cc: kunit-dev@googlegroups.com Cc: Shuah Khan Cc: Shuah Khan Cc: Brendan Higgins Reviewed-by: David Gow Signed-off-by: Shuah Khan --- Documentation/dev-tools/kunit/style.rst | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/Documentation/dev-tools/kunit/style.rst b/Documentation/dev-tools/kunit/style.rst index da1d6f0ed6bc..8dbcdc552606 100644 --- a/Documentation/dev-tools/kunit/style.rst +++ b/Documentation/dev-tools/kunit/style.rst @@ -175,17 +175,17 @@ An example Kconfig entry: .. code-block:: none - config FOO_KUNIT_TEST - tristate "KUnit test for foo" if !KUNIT_ALL_TESTS - depends on KUNIT - default KUNIT_ALL_TESTS - help - This builds unit tests for foo. + config FOO_KUNIT_TEST + tristate "KUnit test for foo" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + This builds unit tests for foo. - For more information on KUnit and unit tests in general, please refer - to the KUnit documentation in Documentation/dev-tools/kunit + For more information on KUnit and unit tests in general, please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. - If unsure, say N + If unsure, say N. Test File and Module Names -- cgit v1.2.3 From 873ddeb881e055fb0c4e371cc3a006bfd9388f00 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 28 Oct 2020 10:43:19 -0700 Subject: KUnit: Docs: usage: wording fixes Fix minor grammar and punctutation glitches. Hyphenate "architecture-specific" instances. Signed-off-by: Randy Dunlap Cc: David Gow Cc: linux-kselftest@vger.kernel.org Cc: kunit-dev@googlegroups.com Cc: Shuah Khan Cc: Shuah Khan Cc: Brendan Higgins Reviewed-by: David Gow Signed-off-by: Shuah Khan --- Documentation/dev-tools/kunit/usage.rst | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst index 62142a47488c..9c28c518e6a3 100644 --- a/Documentation/dev-tools/kunit/usage.rst +++ b/Documentation/dev-tools/kunit/usage.rst @@ -92,7 +92,7 @@ behavior of a function called ``add``; the first parameter is always of type the second parameter, in this case, is what the value is expected to be; the last value is what the value actually is. If ``add`` passes all of these expectations, the test case, ``add_test_basic`` will pass; if any one of these -expectations fail, the test case will fail. +expectations fails, the test case will fail. It is important to understand that a test case *fails* when any expectation is violated; however, the test will continue running, potentially trying other @@ -202,7 +202,7 @@ Example: kunit_test_suite(example_test_suite); In the above example the test suite, ``example_test_suite``, would run the test -cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``, +cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``; each would have ``example_test_init`` called immediately before it and would have ``example_test_exit`` called immediately after it. ``kunit_test_suite(example_test_suite)`` registers the test suite with the @@ -229,7 +229,7 @@ through some sort of indirection where a function is exposed as part of an API such that the definition of that function can be changed without affecting the rest of the code base. In the kernel this primarily comes from two constructs, classes, structs that contain function pointers that are provided by the -implementer, and architecture specific functions which have definitions selected +implementer, and architecture-specific functions which have definitions selected at compile time. Classes @@ -459,7 +459,7 @@ KUnit on non-UML architectures By default KUnit uses UML as a way to provide dependencies for code under test. Under most circumstances KUnit's usage of UML should be treated as an implementation detail of how KUnit works under the hood. Nevertheless, there -are instances where being able to run architecture specific code or test +are instances where being able to run architecture-specific code or test against real hardware is desirable. For these reasons KUnit supports running on other architectures. @@ -599,7 +599,7 @@ writing normal KUnit tests. One special caveat is that you have to reset hardware state in between test cases; if this is not possible, you may only be able to run one test case per invocation. -.. TODO(brendanhiggins@google.com): Add an actual example of an architecture +.. TODO(brendanhiggins@google.com): Add an actual example of an architecture- dependent KUnit test. KUnit debugfs representation -- cgit v1.2.3 From 390881448b1ff1e9d82896abbbda7cdb8e0be27c Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Thu, 29 Oct 2020 15:09:29 -0700 Subject: kunit: tool: print out stderr from make (like build warnings) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently the tool redirects make stdout + stderr, and only shows them if the make command fails. This means build warnings aren't shown to the user. This change prints the contents of stderr even if make succeeds, under the assumption these are only build warnings or other messages the user likely wants to see. We drop stdout from the raised exception since we can no longer easily collate stdout and stderr and just showing the stderr seems fine. Example with a warning: [14:56:35] Building KUnit Kernel ... ../lib/kunit/kunit-test.c: In function ‘kunit_test_successful_try’: ../lib/kunit/kunit-test.c:19:6: warning: unused variable ‘unused’ [-Wunused-variable] 19 | int unused; | ^~~~~~ [14:56:40] Starting KUnit Kernel ... Note the stderr has a trailing \n, and since we use print, we add another, but it helps separate make and kunit.py output. Example with a build error: [15:02:45] Building KUnit Kernel ... ERROR:root:../lib/kunit/kunit-test.c: In function ‘kunit_test_successful_try’: ../lib/kunit/kunit-test.c:19:2: error: unknown type name ‘invalid_type’ 19 | invalid_type *test = data; | ^~~~~~~~~~~~ ... Signed-off-by: Daniel Latypov Reviewed-by: David Gow Signed-off-by: Shuah Khan --- tools/testing/kunit/kunit_kernel.py | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index b4768fa03ce0..2e3cc0fac726 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -84,11 +84,16 @@ class LinuxSourceTreeOperations(object): if build_dir: command += ['O=' + build_dir] try: - subprocess.check_output(command, stderr=subprocess.STDOUT) + proc = subprocess.Popen(command, + stderr=subprocess.PIPE, + stdout=subprocess.DEVNULL) except OSError as e: - raise BuildError('Could not call execute make: ' + str(e)) - except subprocess.CalledProcessError as e: - raise BuildError(e.output.decode()) + raise BuildError('Could not call make command: ' + str(e)) + _, stderr = proc.communicate() + if proc.returncode != 0: + raise BuildError(stderr.decode()) + if stderr: # likely only due to build warnings + print(stderr.decode()) def linux_bin(self, params, timeout, build_dir): """Runs the Linux UML binary. Must be named 'linux'.""" -- cgit v1.2.3 From 060352e141e4c71ce147a2737f6d30a97f2ec317 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Fri, 30 Oct 2020 15:38:53 -0700 Subject: kunit: tool: fix extra trailing \n in raw + parsed test output For simplcity, strip all trailing whitespace from parsed output. I imagine no one is printing out meaningful trailing whitespace via KUNIT_FAIL() or similar, and that if they are, they really shouldn't. `isolate_kunit_output()` yielded liens with trailing \n, which results in artifacty output like this: $ ./tools/testing/kunit/kunit.py run [16:16:46] [FAILED] example_simple_test [16:16:46] # example_simple_test: EXPECTATION FAILED at lib/kunit/kunit-example-test.c:29 [16:16:46] Expected 1 + 1 == 3, but [16:16:46] 1 + 1 == 2 [16:16:46] 3 == 3 [16:16:46] not ok 1 - example_simple_test [16:16:46] After this change: [16:16:46] # example_simple_test: EXPECTATION FAILED at lib/kunit/kunit-example-test.c:29 [16:16:46] Expected 1 + 1 == 3, but [16:16:46] 1 + 1 == 2 [16:16:46] 3 == 3 [16:16:46] not ok 1 - example_simple_test [16:16:46] We should *not* be expecting lines to end with \n in kunit_tool_test.py for this reason. Do the same for `raw_output()` as well which suffers from the same issue. This is a followup to [1], but rebased onto kunit-fixes to pick up the other raw_output() fix and fixes for kunit_tool_test.py. [1] https://lore.kernel.org/linux-kselftest/20201020233219.4146059-1-dlatypov@google.com/ Signed-off-by: Daniel Latypov Reviewed-by: David Gow Tested-by: David Gow Signed-off-by: Shuah Khan --- tools/testing/kunit/kunit_parser.py | 3 ++- tools/testing/kunit/kunit_tool_test.py | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index db0347baa428..bbfe1b4e4c1c 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -54,6 +54,7 @@ kunit_end_re = re.compile('(List of all partitions:|' def isolate_kunit_output(kernel_output): started = False for line in kernel_output: + line = line.rstrip() # line always has a trailing \n if kunit_start_re.search(line): prefix_len = len(line.split('TAP version')[0]) started = True @@ -65,7 +66,7 @@ def isolate_kunit_output(kernel_output): def raw_output(kernel_output): for line in kernel_output: - print(line) + print(line.rstrip()) DIVIDER = '=' * 60 diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 0b60855fb819..497ab51bc170 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -102,7 +102,7 @@ class KUnitParserTest(unittest.TestCase): 'test_data/test_output_isolated_correctly.log') file = open(log_path) result = kunit_parser.isolate_kunit_output(file.readlines()) - self.assertContains('TAP version 14\n', result) + self.assertContains('TAP version 14', result) self.assertContains(' # Subtest: example', result) self.assertContains(' 1..2', result) self.assertContains(' ok 1 - example_simple_test', result) @@ -115,7 +115,7 @@ class KUnitParserTest(unittest.TestCase): 'test_data/test_pound_sign.log') with open(log_path) as file: result = kunit_parser.isolate_kunit_output(file.readlines()) - self.assertContains('TAP version 14\n', result) + self.assertContains('TAP version 14', result) self.assertContains(' # Subtest: kunit-resource-test', result) self.assertContains(' 1..5', result) self.assertContains(' ok 1 - kunit_resource_test_init_resources', result) -- cgit v1.2.3 From 3084db0e0d5076cd48408274ab0911cd3ccdae88 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Mon, 2 Nov 2020 15:23:04 -0800 Subject: kunit: fix display of failed expectations for strings Currently the following expectation KUNIT_EXPECT_STREQ(test, "hi", "bye"); will produce: Expected "hi" == "bye", but "hi" == 1625079497 "bye" == 1625079500 After this patch: Expected "hi" == "bye", but "hi" == hi "bye" == bye KUNIT_INIT_BINARY_STR_ASSERT_STRUCT() was written but just mistakenly not actually used by KUNIT_EXPECT_STREQ() and friends. Signed-off-by: Daniel Latypov Reviewed-by: Brendan Higgins Tested-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/test.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/kunit/test.h b/include/kunit/test.h index db1b0ae666c4..df60be7e22ca 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -1105,7 +1105,7 @@ do { \ KUNIT_ASSERTION(test, \ strcmp(__left, __right) op 0, \ kunit_binary_str_assert, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT(test, \ + KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(test, \ assert_type, \ #op, \ #left, \ -- cgit v1.2.3 From c583bcb8f5edd48c1798798e341f78afb9bf4f6f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 24 Sep 2020 15:11:55 -0700 Subject: rcu: Don't invoke try_invoke_on_locked_down_task() with irqs disabled The try_invoke_on_locked_down_task() function requires that interrupts be enabled, but it is called with interrupts disabled from rcu_print_task_stall(), resulting in an "IRQs not enabled as expected" diagnostic. This commit therefore updates rcu_print_task_stall() to accumulate a list of the first few tasks while holding the current leaf rcu_node structure's ->lock, then releases that lock and only then uses try_invoke_on_locked_down_task() to attempt to obtain per-task detailed information. Of course, as soon as ->lock is released, the task might exit, so the get_task_struct() function is used to prevent the task structure from going away in the meantime. Link: https://lore.kernel.org/lkml/000000000000903d5805ab908fc4@google.com/ Fixes: 5bef8da66a9c ("rcu: Add per-task state to RCU CPU stall warnings") Reported-by: syzbot+cb3b69ae80afd6535b0e@syzkaller.appspotmail.com Reported-by: syzbot+f04854e1c5c9e913cc27@syzkaller.appspotmail.com Tested-by: Sebastian Andrzej Siewior Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_stall.h | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 0fde39b8daab..ca21d28a0f98 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -249,13 +249,16 @@ static bool check_slow_task(struct task_struct *t, void *arg) /* * Scan the current list of tasks blocked within RCU read-side critical - * sections, printing out the tid of each. + * sections, printing out the tid of each of the first few of them. */ -static int rcu_print_task_stall(struct rcu_node *rnp) +static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags) + __releases(rnp->lock) { + int i = 0; int ndetected = 0; struct rcu_stall_chk_rdr rscr; struct task_struct *t; + struct task_struct *ts[8]; if (!rcu_preempt_blocked_readers_cgp(rnp)) return 0; @@ -264,6 +267,14 @@ static int rcu_print_task_stall(struct rcu_node *rnp) t = list_entry(rnp->gp_tasks->prev, struct task_struct, rcu_node_entry); list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { + get_task_struct(t); + ts[i++] = t; + if (i >= ARRAY_SIZE(ts)) + break; + } + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + for (i--; i; i--) { + t = ts[i]; if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr)) pr_cont(" P%d", t->pid); else @@ -273,6 +284,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp) ".q"[rscr.rs.b.need_qs], ".e"[rscr.rs.b.exp_hint], ".l"[rscr.on_blkd_list]); + put_task_struct(t); ndetected++; } pr_cont("\n"); @@ -293,8 +305,9 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) * Because preemptible RCU does not exist, we never have to check for * tasks blocked within RCU read-side critical sections. */ -static int rcu_print_task_stall(struct rcu_node *rnp) +static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags) { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ @@ -472,7 +485,6 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name); rcu_for_each_leaf_node(rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); - ndetected += rcu_print_task_stall(rnp); if (rnp->qsmask != 0) { for_each_leaf_node_possible_cpu(rnp, cpu) if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) { @@ -480,7 +492,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) ndetected++; } } - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + ndetected += rcu_print_task_stall(rnp, flags); // Releases rnp->lock. } for_each_possible_cpu(cpu) -- cgit v1.2.3 From 99fba3205cd499255a36fd87f1d6064adc622a5b Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Thu, 1 Oct 2020 22:20:23 +0300 Subject: ARM: dts: am437x-l4: fix compatible for cpsw switch dt node Fix compatible the new CPSW switchdev DT node to avoid probing of legacy CPSW driver which fails: [ 2.781009] cpsw 4a100000.switch: invalid resource Fixes: 7bf8f37aea82 ("ARM: dts: am437x-l4: add dt node for new cpsw switchdev driver") Signed-off-by: Grygorii Strashko Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am437x-l4.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/am437x-l4.dtsi b/arch/arm/boot/dts/am437x-l4.dtsi index c220dc3c4e0f..243e35f7a56c 100644 --- a/arch/arm/boot/dts/am437x-l4.dtsi +++ b/arch/arm/boot/dts/am437x-l4.dtsi @@ -521,7 +521,7 @@ ranges = <0x0 0x100000 0x8000>; mac_sw: switch@0 { - compatible = "ti,am4372-cpsw","ti,cpsw-switch"; + compatible = "ti,am4372-cpsw-switch", "ti,cpsw-switch"; reg = <0x0 0x4000>; ranges = <0 0 0x4000>; clocks = <&cpsw_125mhz_gclk>, <&dpll_clksel_mac_clk>; -- cgit v1.2.3 From b5acfe152abaa2721c9ca8aa67f941d7de55d24e Mon Sep 17 00:00:00 2001 From: PeiSen Hou Date: Wed, 11 Nov 2020 08:58:59 +0100 Subject: ALSA: hda/realtek: Add some Clove SSID in the ALC293(ALC1220) Fix "use as headset mic, without its own jack detect" problem. [ Minor coding style fixes by tiwai ] Signed-off-by: PeiSen Hou Cc: Link: https://lore.kernel.org/r/481963e4a5694ff19f27ae1e283d79ad@realtek.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 50 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 49 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index c3a02738ead2..69a952c9e011 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2522,13 +2522,23 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x9506, "Clevo P955HQ", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x950A, "Clevo P955H[PR]", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e3, "Clevo P955[ER]T", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e4, "Clevo P955ER", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e5, "Clevo P955EE6", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e6, "Clevo P950R[CDF]", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x96e1, "Clevo P960[ER][CDFN]-K", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x97e1, "Clevo P970[ER][CDFN]", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x97e2, "Clevo P970RC-M", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65d1, "Clevo PB51[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x65d2, "Clevo PB51R[CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x65e1, "Clevo PB51[ED][DF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), - SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x67e1, "Clevo PB71[DE][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x70d1, "Clevo PC70[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x7714, "Clevo X170", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), @@ -7931,11 +7941,49 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1558, 0x1323, "Clevo N130ZU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x1325, "System76 Darter Pro (darp5)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x1401, "Clevo L140[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x1403, "Clevo N140CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x1404, "Clevo N150CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x14a1, "Clevo L141MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x4018, "Clevo NV40M[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x4019, "Clevo NV40MZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x4020, "Clevo NV40MB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x40a1, "Clevo NL40GU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x40c1, "Clevo NL40[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x40d1, "Clevo NL41DU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50a3, "Clevo NJ51GU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50b3, "Clevo NK50S[BEZ]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50b6, "Clevo NK50S5", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50b8, "Clevo NK50SZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50d5, "Clevo NP50D5", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50f0, "Clevo NH50A[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50f3, "Clevo NH58DPQ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x5101, "Clevo S510WU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x5157, "Clevo W517GU1", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x51a1, "Clevo NS50MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x70a1, "Clevo NB70T[HJK]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x70b3, "Clevo NK70SB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8228, "Clevo NR40BU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8520, "Clevo NH50D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8521, "Clevo NH77D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8535, "Clevo NH50D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8536, "Clevo NH79D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8550, "System76 Gazelle (gaze14)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8551, "System76 Gazelle (gaze14)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8560, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1558, 0x8561, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1558, 0x8668, "Clevo NP50B[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8680, "Clevo NJ50LU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8686, "Clevo NH50[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8a20, "Clevo NH55DCQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8a51, "Clevo NH70RCQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8d50, "Clevo NH55RCQ-M", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x951d, "Clevo N950T[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x961d, "Clevo N960S[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x971d, "Clevo N970T[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0xa500, "Clevo NL53RU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS), SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), -- cgit v1.2.3 From 1ed576a20cd5c93295f57d6b7400357bd8d01b21 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Tue, 20 Oct 2020 06:12:07 -0400 Subject: KVM: s390: pv: Mark mm as protected after the set secure parameters and improve cleanup We can only have protected guest pages after a successful set secure parameters call as only then the UV allows imports and unpacks. By moving the test we can now also check for it in s390_reset_acc() and do an early return if it is 0. Signed-off-by: Janosch Frank Fixes: 29b40f105ec8 ("KVM: s390: protvirt: Add initial vm and cpu lifecycle handling") Reviewed-by: Cornelia Huck Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 2 +- arch/s390/kvm/pv.c | 3 ++- arch/s390/mm/gmap.c | 2 ++ 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 6b74b92c1a58..08ea6c4735cd 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2312,7 +2312,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) struct kvm_s390_pv_unp unp = {}; r = -EINVAL; - if (!kvm_s390_pv_is_protected(kvm)) + if (!kvm_s390_pv_is_protected(kvm) || !mm_is_protected(kvm->mm)) break; r = -EFAULT; diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index eb99e2f95ebe..f5847f9dec7c 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -208,7 +208,6 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) return -EIO; } kvm->arch.gmap->guest_handle = uvcb.guest_handle; - atomic_set(&kvm->mm->context.is_protected, 1); return 0; } @@ -228,6 +227,8 @@ int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, *rrc = uvcb.header.rrc; KVM_UV_EVENT(kvm, 3, "PROTVIRT VM SET PARMS: rc %x rrc %x", *rc, *rrc); + if (!cc) + atomic_set(&kvm->mm->context.is_protected, 1); return cc ? -EINVAL : 0; } diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index cfb0017f33a7..64795d034926 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2690,6 +2690,8 @@ static const struct mm_walk_ops reset_acc_walk_ops = { #include void s390_reset_acc(struct mm_struct *mm) { + if (!mm_is_protected(mm)) + return; /* * we might be called during * reset: we walk the pages and clear -- cgit v1.2.3 From 6cbf1e960fa52e4c63a6dfa4cda8736375b34ccc Mon Sep 17 00:00:00 2001 From: Collin Walling Date: Wed, 4 Nov 2020 13:10:32 -0500 Subject: KVM: s390: remove diag318 reset code The diag318 data must be set to 0 by VM-wide reset events triggered by diag308. As such, KVM should not handle resetting this data via the VCPU ioctls. Fixes: 23a60f834406 ("s390/kvm: diagnose 0x318 sync and reset") Signed-off-by: Collin Walling Reviewed-by: Christian Borntraeger Reviewed-by: Janosch Frank Acked-by: Cornelia Huck Signed-off-by: Christian Borntraeger Link: https://lore.kernel.org/r/20201104181032.109800-1-walling@linux.ibm.com --- arch/s390/kvm/kvm-s390.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 08ea6c4735cd..425d3d75320b 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3564,7 +3564,6 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->pp = 0; vcpu->arch.sie_block->fpf &= ~FPF_BPBC; vcpu->arch.sie_block->todpr = 0; - vcpu->arch.sie_block->cpnc = 0; } } @@ -3582,7 +3581,6 @@ static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu) regs->etoken = 0; regs->etoken_extension = 0; - regs->diag318 = 0; } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) -- cgit v1.2.3 From f16e631333a8f12ae8128826e695db4b2a528407 Mon Sep 17 00:00:00 2001 From: Kaixu Xia Date: Wed, 11 Nov 2020 13:03:46 +0800 Subject: bpf: Fix unsigned 'datasec_id' compared with zero in check_pseudo_btf_id The unsigned variable datasec_id is assigned a return value from the call to check_pseudo_btf_id(), which may return negative error code. This fixes the following coccicheck warning: ./kernel/bpf/verifier.c:9616:5-15: WARNING: Unsigned expression compared with zero: datasec_id > 0 Fixes: eaa6bcb71ef6 ("bpf: Introduce bpf_per_cpu_ptr()") Reported-by: Tosk Robot Signed-off-by: Kaixu Xia Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: John Fastabend Cc: Hao Luo Link: https://lore.kernel.org/bpf/1605071026-25906-1-git-send-email-kaixuxia@tencent.com --- kernel/bpf/verifier.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6200519582a6..6204ec705d80 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9572,12 +9572,13 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_insn_aux_data *aux) { - u32 datasec_id, type, id = insn->imm; const struct btf_var_secinfo *vsi; const struct btf_type *datasec; const struct btf_type *t; const char *sym_name; bool percpu = false; + u32 type, id = insn->imm; + s32 datasec_id; u64 addr; int i; -- cgit v1.2.3 From 92e4dc8b05663d6539b1b8375f3b1cf7b204cfe9 Mon Sep 17 00:00:00 2001 From: Chris Co Date: Tue, 10 Nov 2020 19:01:18 +0000 Subject: Drivers: hv: vmbus: Allow cleanup of VMBUS_CONNECT_CPU if disconnected When invoking kexec() on a Linux guest running on a Hyper-V host, the kernel panics. RIP: 0010:cpuhp_issue_call+0x137/0x140 Call Trace: __cpuhp_remove_state_cpuslocked+0x99/0x100 __cpuhp_remove_state+0x1c/0x30 hv_kexec_handler+0x23/0x30 [hv_vmbus] hv_machine_shutdown+0x1e/0x30 machine_shutdown+0x10/0x20 kernel_kexec+0x6d/0x96 __do_sys_reboot+0x1ef/0x230 __x64_sys_reboot+0x1d/0x20 do_syscall_64+0x6b/0x3d8 entry_SYSCALL_64_after_hwframe+0x44/0xa9 This was due to hv_synic_cleanup() callback returning -EBUSY to cpuhp_issue_call() when tearing down the VMBUS_CONNECT_CPU, even if the vmbus_connection.conn_state = DISCONNECTED. hv_synic_cleanup() should succeed in the case where vmbus_connection.conn_state is DISCONNECTED. Fix is to add an extra condition to test for vmbus_connection.conn_state == CONNECTED on the VMBUS_CONNECT_CPU and only return early if true. This way the kexec() path can still shut everything down while preserving the initial behavior of preventing CPU offlining on the VMBUS_CONNECT_CPU while the VM is running. Fixes: 8a857c55420f29 ("Drivers: hv: vmbus: Always handle the VMBus messages on CPU0") Signed-off-by: Chris Co Reviewed-by: Andrea Parri (Microsoft) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20201110190118.15596-1-chrco@linux.microsoft.com Signed-off-by: Wei Liu --- drivers/hv/hv.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index da69338f92f5..75a8638ff68b 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -244,9 +244,13 @@ int hv_synic_cleanup(unsigned int cpu) /* * Hyper-V does not provide a way to change the connect CPU once - * it is set; we must prevent the connect CPU from going offline. + * it is set; we must prevent the connect CPU from going offline + * while the VM is running normally. But in the panic or kexec() + * path where the vmbus is already disconnected, the CPU must be + * allowed to shut down. */ - if (cpu == VMBUS_CONNECT_CPU) + if (cpu == VMBUS_CONNECT_CPU && + vmbus_connection.conn_state == CONNECTED) return -EBUSY; /* -- cgit v1.2.3 From 365ec8b61689bd64d6a61e129e0319bf71336407 Mon Sep 17 00:00:00 2001 From: Sean Nyekjaer Date: Tue, 10 Nov 2020 18:41:13 +0100 Subject: regulator: pfuze100: limit pfuze-support-disable-sw to pfuze{100,200} Limit the fsl,pfuze-support-disable-sw to the pfuze100 and pfuze200 variants. When enabling fsl,pfuze-support-disable-sw and using a pfuze3000 or pfuze3001, the driver would choose pfuze100_sw_disable_regulator_ops instead of the newly introduced and correct pfuze3000_sw_regulator_ops. Signed-off-by: Sean Nyekjaer Fixes: 6f1cf5257acc ("regualtor: pfuze100: correct sw1a/sw2 on pfuze3000") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20201110174113.2066534-1-sean@geanix.com Signed-off-by: Mark Brown --- drivers/regulator/pfuze100-regulator.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c index 7e8ba9246167..01a12cfcea7c 100644 --- a/drivers/regulator/pfuze100-regulator.c +++ b/drivers/regulator/pfuze100-regulator.c @@ -836,11 +836,14 @@ static int pfuze100_regulator_probe(struct i2c_client *client, * the switched regulator till yet. */ if (pfuze_chip->flags & PFUZE_FLAG_DISABLE_SW) { - if (pfuze_chip->regulator_descs[i].sw_reg) { - desc->ops = &pfuze100_sw_disable_regulator_ops; - desc->enable_val = 0x8; - desc->disable_val = 0x0; - desc->enable_time = 500; + if (pfuze_chip->chip_id == PFUZE100 || + pfuze_chip->chip_id == PFUZE200) { + if (pfuze_chip->regulator_descs[i].sw_reg) { + desc->ops = &pfuze100_sw_disable_regulator_ops; + desc->enable_val = 0x8; + desc->disable_val = 0x0; + desc->enable_time = 500; + } } } -- cgit v1.2.3 From 766c6b63aa044e84b045803b40b14754d69a2a1d Mon Sep 17 00:00:00 2001 From: Sven Van Asbroeck Date: Fri, 6 Nov 2020 10:07:06 -0500 Subject: spi: fix client driver breakages when using GPIO descriptors Commit f3186dd87669 ("spi: Optionally use GPIO descriptors for CS GPIOs") introduced the optional use of GPIO descriptors for chip selects. A side-effect of this change: when a SPI bus uses GPIO descriptors, all its client devices have SPI_CS_HIGH set in spi->mode. This flag is required for the SPI bus to operate correctly. This unfortunately breaks many client drivers, which use the following pattern to configure their underlying SPI bus: static int client_device_probe(struct spi_device *spi) { ... spi->mode = SPI_MODE_0; spi->bits_per_word = 8; err = spi_setup(spi); .. } In short, many client drivers overwrite the SPI_CS_HIGH bit in spi->mode, and break the underlying SPI bus driver. This is especially true for Freescale/NXP imx ecspi, where large numbers of spi client drivers now no longer work. Proposed fix: ------------- When using gpio descriptors, depend on gpiolib to handle CS polarity. Existing quirks in gpiolib ensure that this is handled correctly. Existing gpiolib behaviour will force the polarity of any chip-select gpiod to active-high (if 'spi-active-high' devicetree prop present) or active-low (if 'spi-active-high' absent). Irrespective of whether the gpio is marked GPIO_ACTIVE_[HIGH|LOW] in the devicetree. Loose ends: ----------- If this fix is applied: - is commit 138c9c32f090 ("spi: spidev: Fix CS polarity if GPIO descriptors are used") still necessary / correct ? Fixes: f3186dd87669 ("spi: Optionally use GPIO descriptors for CS GPIOs") Signed-off-by: Sven Van Asbroeck Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20201106150706.29089-1-TheSven73@gmail.com Signed-off-by: Mark Brown --- drivers/spi/spi.c | 23 ++++++----------------- 1 file changed, 6 insertions(+), 17 deletions(-) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 0cab239d8e7f..7566482c052c 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -812,18 +812,16 @@ static void spi_set_cs(struct spi_device *spi, bool enable) enable = !enable; if (spi->cs_gpiod || gpio_is_valid(spi->cs_gpio)) { - /* - * Honour the SPI_NO_CS flag and invert the enable line, as - * active low is default for SPI. Execution paths that handle - * polarity inversion in gpiolib (such as device tree) will - * enforce active high using the SPI_CS_HIGH resulting in a - * double inversion through the code above. - */ if (!(spi->mode & SPI_NO_CS)) { if (spi->cs_gpiod) + /* polarity handled by gpiolib */ gpiod_set_value_cansleep(spi->cs_gpiod, - !enable); + enable1); else + /* + * invert the enable line, as active low is + * default for SPI. + */ gpio_set_value_cansleep(spi->cs_gpio, !enable); } /* Some SPI masters need both GPIO CS & slave_select */ @@ -1992,15 +1990,6 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, } spi->chip_select = value; - /* - * For descriptors associated with the device, polarity inversion is - * handled in the gpiolib, so all gpio chip selects are "active high" - * in the logical sense, the gpiolib will invert the line if need be. - */ - if ((ctlr->use_gpio_descriptors) && ctlr->cs_gpiods && - ctlr->cs_gpiods[spi->chip_select]) - spi->mode |= SPI_CS_HIGH; - /* Device speed */ if (!of_property_read_u32(nc, "spi-max-frequency", &value)) spi->max_speed_hz = value; -- cgit v1.2.3 From ee4ad5d06509b3aea79b6a77bebd09ef891bed8d Mon Sep 17 00:00:00 2001 From: Eddie James Date: Tue, 10 Nov 2020 15:47:36 -0600 Subject: spi: fsi: Fix transfer returning without finalizing message In the case that the SPI mux isn't set, the transfer_one_message function returns without finalizing the message. This means that the transfer never completes, resulting in hung tasks and an eventual kernel panic. Fix it by finalizing the transfer in this case. Fixes: 9211a441e606 ("spi: fsi: Check mux status before transfers") Signed-off-by: Eddie James Reviewed-by: Joel Stanley Link: https://lore.kernel.org/r/20201110214736.25718-1-eajames@linux.ibm.com Signed-off-by: Mark Brown --- drivers/spi/spi-fsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi-fsi.c b/drivers/spi/spi-fsi.c index 8a440c7078ef..3920cd3286d8 100644 --- a/drivers/spi/spi-fsi.c +++ b/drivers/spi/spi-fsi.c @@ -477,7 +477,7 @@ static int fsi_spi_transfer_one_message(struct spi_controller *ctlr, rc = fsi_spi_check_mux(ctx->fsi, ctx->dev); if (rc) - return rc; + goto error; list_for_each_entry(transfer, &mesg->transfers, transfer_list) { struct fsi_spi_sequence seq; -- cgit v1.2.3 From 676650d007e06fddcf3fe38238251d71bd179641 Mon Sep 17 00:00:00 2001 From: Necip Fazil Yildiran Date: Wed, 11 Nov 2020 17:48:52 -0800 Subject: Input: resistive-adc-touch - fix kconfig dependency on IIO_BUFFER When TOUCHSCREEN_ADC is enabled and IIO_BUFFER is disabled, it results in the following Kbuild warning: WARNING: unmet direct dependencies detected for IIO_BUFFER_CB Depends on [n]: IIO [=y] && IIO_BUFFER [=n] Selected by [y]: - TOUCHSCREEN_ADC [=y] && !UML && INPUT [=y] && INPUT_TOUCHSCREEN [=y] && IIO [=y] The reason is that TOUCHSCREEN_ADC selects IIO_BUFFER_CB without depending on or selecting IIO_BUFFER while IIO_BUFFER_CB depends on IIO_BUFFER. This can also fail building the kernel. Honor the kconfig dependency to remove unmet direct dependency warnings and avoid any potential build failures. Fixes: aa132ffb6b0a ("input: touchscreen: resistive-adc-touch: add generic resistive ADC touchscreen") Signed-off-by: Necip Fazil Yildiran Acked-by: Jonathan Cameron Link: https://lore.kernel.org/r/20201102221504.541279-1-fazilyildiran@gmail.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index f012fe746df0..cc18f54ea887 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -96,6 +96,7 @@ config TOUCHSCREEN_AD7879_SPI config TOUCHSCREEN_ADC tristate "Generic ADC based resistive touchscreen" depends on IIO + select IIO_BUFFER select IIO_BUFFER_CB help Say Y here if you want to use the generic ADC -- cgit v1.2.3 From ae3d6083acf60116d4f409677452399547ed2009 Mon Sep 17 00:00:00 2001 From: "jingle.wu" Date: Wed, 11 Nov 2020 20:06:24 -0800 Subject: Input: elan_i2c - fix firmware update on newer ICs The argument to iap page type command depends on the firmware page size. Fixes: bfd9b92bc8f9 ("Input: elan_i2c - handle firmware updated on newer ICs") Signed-off-by: Jingle Wu Signed-off-by: Dmitry Torokhov --- drivers/input/mouse/elan_i2c.h | 2 +- drivers/input/mouse/elan_i2c_core.c | 3 ++- drivers/input/mouse/elan_i2c_i2c.c | 10 +++++----- drivers/input/mouse/elan_i2c_smbus.c | 2 +- 4 files changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/input/mouse/elan_i2c.h b/drivers/input/mouse/elan_i2c.h index c75b00c45d75..36e3cd908671 100644 --- a/drivers/input/mouse/elan_i2c.h +++ b/drivers/input/mouse/elan_i2c.h @@ -78,7 +78,7 @@ struct elan_transport_ops { int (*iap_reset)(struct i2c_client *client); int (*prepare_fw_update)(struct i2c_client *client, u16 ic_type, - u8 iap_version); + u8 iap_version, u16 fw_page_size); int (*write_fw_block)(struct i2c_client *client, u16 fw_page_size, const u8 *page, u16 checksum, int idx); int (*finish_fw_update)(struct i2c_client *client, diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index c599e21a8478..61ed3f5ca219 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -497,7 +497,8 @@ static int __elan_update_firmware(struct elan_tp_data *data, u16 sw_checksum = 0, fw_checksum = 0; error = data->ops->prepare_fw_update(client, data->ic_type, - data->iap_version); + data->iap_version, + data->fw_page_size); if (error) return error; diff --git a/drivers/input/mouse/elan_i2c_i2c.c b/drivers/input/mouse/elan_i2c_i2c.c index 5a496d4ffa49..13dc097eb6c6 100644 --- a/drivers/input/mouse/elan_i2c_i2c.c +++ b/drivers/input/mouse/elan_i2c_i2c.c @@ -517,7 +517,7 @@ static int elan_i2c_set_flash_key(struct i2c_client *client) return 0; } -static int elan_read_write_iap_type(struct i2c_client *client) +static int elan_read_write_iap_type(struct i2c_client *client, u16 fw_page_size) { int error; u16 constant; @@ -526,7 +526,7 @@ static int elan_read_write_iap_type(struct i2c_client *client) do { error = elan_i2c_write_cmd(client, ETP_I2C_IAP_TYPE_CMD, - ETP_I2C_IAP_TYPE_REG); + fw_page_size / 2); if (error) { dev_err(&client->dev, "cannot write iap type: %d\n", error); @@ -543,7 +543,7 @@ static int elan_read_write_iap_type(struct i2c_client *client) constant = le16_to_cpup((__le16 *)val); dev_dbg(&client->dev, "iap type reg: 0x%04x\n", constant); - if (constant == ETP_I2C_IAP_TYPE_REG) + if (constant == fw_page_size / 2) return 0; } while (--retry > 0); @@ -553,7 +553,7 @@ static int elan_read_write_iap_type(struct i2c_client *client) } static int elan_i2c_prepare_fw_update(struct i2c_client *client, u16 ic_type, - u8 iap_version) + u8 iap_version, u16 fw_page_size) { struct device *dev = &client->dev; int error; @@ -594,7 +594,7 @@ static int elan_i2c_prepare_fw_update(struct i2c_client *client, u16 ic_type, } if (ic_type >= 0x0D && iap_version >= 1) { - error = elan_read_write_iap_type(client); + error = elan_read_write_iap_type(client, fw_page_size); if (error) return error; } diff --git a/drivers/input/mouse/elan_i2c_smbus.c b/drivers/input/mouse/elan_i2c_smbus.c index 8ff823751f3b..1820f1cfc1dc 100644 --- a/drivers/input/mouse/elan_i2c_smbus.c +++ b/drivers/input/mouse/elan_i2c_smbus.c @@ -340,7 +340,7 @@ static int elan_smbus_set_flash_key(struct i2c_client *client) } static int elan_smbus_prepare_fw_update(struct i2c_client *client, u16 ic_type, - u8 iap_version) + u8 iap_version, u16 fw_page_size) { struct device *dev = &client->dev; int len; -- cgit v1.2.3 From edb8d77a939c422f3ae57f557cd1d6899d9bafad Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Mon, 21 Sep 2020 02:58:07 -0400 Subject: drm/i915/gvt: Set ENHANCED_FRAME_CAP bit Specification says the bit7 of the DPCD MAX_LANE_COUNT (offset 0x02) must be set to 1 when comes to the displayport version 1.2. This patch respects the definition. W/o this patch, guest i915 driver can only set the resolution to 1024*768, and complains about the unsuccessful link training: [ 5.692193] i915 0000:00:02.0: [drm] *ERROR* index 0, lane_count 1 Link Training Unsuccessful Fixes: e2e02cbb5beb ("drm/i915/gvt: make dpcd_fix_data supports DP1.2") Reviewed-by: Zhenyu Wang Signed-off-by: Tina Zhang Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20200921065807.247847-1-tina.zhang@intel.com --- drivers/gpu/drm/i915/gvt/display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index 7ba16ddfe75f..d7898e87791f 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -164,7 +164,7 @@ static unsigned char virtual_dp_monitor_edid[GVT_EDID_NUM][EDID_SIZE] = { /* let the virtual display supports DP1.2 */ static u8 dpcd_fix_data[DPCD_HEADER_SIZE] = { - 0x12, 0x014, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 + 0x12, 0x014, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; static void emulate_monitor_status_change(struct intel_vgpu *vgpu) -- cgit v1.2.3 From 94e2bd0b259ed39a755fdded47e6734acf1ce464 Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Tue, 10 Nov 2020 16:49:08 +0800 Subject: rfkill: Fix use-after-free in rfkill_resume() If a device is getting removed or reprobed during resume, use-after-free might happen. For example, h5_btrtl_resume() schedules a work queue for device reprobing, which of course requires removal first. If the removal happens in parallel with the device_resume() and wins the race to acquire device_lock(), removal may remove the device from the PM lists and all, but device_resume() is already running and will continue when the lock can be acquired, thus calling rfkill_resume(). During this, if rfkill_set_block() is then called after the corresponding *_unregister() and kfree() are called, there will be an use-after-free in hci_rfkill_set_block(): BUG: KASAN: use-after-free in hci_rfkill_set_block+0x58/0xc0 [bluetooth] ... Call trace: dump_backtrace+0x0/0x154 show_stack+0x20/0x2c dump_stack+0xbc/0x12c print_address_description+0x88/0x4b0 __kasan_report+0x144/0x168 kasan_report+0x10/0x18 check_memory_region+0x19c/0x1ac __kasan_check_write+0x18/0x24 hci_rfkill_set_block+0x58/0xc0 [bluetooth] rfkill_set_block+0x9c/0x120 rfkill_resume+0x34/0x70 dpm_run_callback+0xf0/0x1f4 device_resume+0x210/0x22c Fix this by checking rfkill->registered in rfkill_resume(). device_del() in rfkill_unregister() requires device_lock() and the whole rfkill_resume() is also protected by the same lock via device_resume(), we can make sure either the rfkill->registered is false before rfkill_resume() starts or the rfkill device won't be unregistered before rfkill_resume() returns. As async_resume() holds a reference to the device, at this level there can be no use-after-free; only in the user that doesn't expect this scenario. Fixes: 8589086f4efd ("Bluetooth: hci_h5: Turn off RTL8723BS on suspend, reprobe on resume") Signed-off-by: Claire Chang Link: https://lore.kernel.org/r/20201110084908.219088-1-tientzu@chromium.org [edit commit message for clarity and add more info provided later] Signed-off-by: Johannes Berg --- net/rfkill/core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 971c73c7d34c..97101c55763d 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -876,6 +876,9 @@ static int rfkill_resume(struct device *dev) rfkill->suspended = false; + if (!rfkill->registered) + return 0; + if (!rfkill->persistent) { cur = !!(rfkill->state & RFKILL_BLOCK_SW); rfkill_set_block(rfkill, cur); -- cgit v1.2.3 From 33f16855dcb973f745c51882d0e286601ff3be2b Mon Sep 17 00:00:00 2001 From: Sam Nobs Date: Tue, 10 Nov 2020 09:50:06 +1300 Subject: tty: serial: imx: fix potential deadlock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Enabling the lock dependency validator has revealed that the way spinlocks are used in the IMX serial port could result in a deadlock. Specifically, imx_uart_int() acquires a spinlock without disabling the interrupts, meaning that another interrupt could come along and try to acquire the same spinlock, potentially causing the two to wait for each other indefinitely. Use spin_lock_irqsave() instead to disable interrupts upon acquisition of the spinlock. Fixes: c974991d2620 ("tty:serial:imx: use spin_lock instead of spin_lock_irqsave in isr") Reviewed-by: Uwe Kleine-König Signed-off-by: Sam Nobs Link: https://lore.kernel.org/r/1604955006-9363-1-git-send-email-samuel.nobs@taitradio.com Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/imx.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 1731d9728865..3c53a3c89959 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -942,8 +942,14 @@ static irqreturn_t imx_uart_int(int irq, void *dev_id) struct imx_port *sport = dev_id; unsigned int usr1, usr2, ucr1, ucr2, ucr3, ucr4; irqreturn_t ret = IRQ_NONE; + unsigned long flags = 0; - spin_lock(&sport->port.lock); + /* + * IRQs might not be disabled upon entering this interrupt handler, + * e.g. when interrupt handlers are forced to be threaded. To support + * this scenario as well, disable IRQs when acquiring the spinlock. + */ + spin_lock_irqsave(&sport->port.lock, flags); usr1 = imx_uart_readl(sport, USR1); usr2 = imx_uart_readl(sport, USR2); @@ -1013,7 +1019,7 @@ static irqreturn_t imx_uart_int(int irq, void *dev_id) ret = IRQ_HANDLED; } - spin_unlock(&sport->port.lock); + spin_unlock_irqrestore(&sport->port.lock, flags); return ret; } -- cgit v1.2.3 From d4122754442799187d5d537a9c039a49a67e57f1 Mon Sep 17 00:00:00 2001 From: Samuel Thibault Date: Tue, 10 Nov 2020 19:35:41 +0100 Subject: speakup: Do not let the line discipline be used several times MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Speakup has only one speakup_tty variable to store the tty it is managing. This makes sense since its codebase currently assumes that there is only one user who controls the screen reading. That however means that we have to forbid using the line discipline several times, otherwise the second closure would try to free a NULL ldisc_data, leading to general protection fault: 0000 [#1] SMP KASAN PTI RIP: 0010:spk_ttyio_ldisc_close+0x2c/0x60 Call Trace: tty_ldisc_release+0xa2/0x340 tty_release_struct+0x17/0xd0 tty_release+0x9d9/0xcc0 __fput+0x231/0x740 task_work_run+0x12c/0x1a0 do_exit+0x9b5/0x2230 ? release_task+0x1240/0x1240 ? __do_page_fault+0x562/0xa30 do_group_exit+0xd5/0x2a0 __x64_sys_exit_group+0x35/0x40 do_syscall_64+0x89/0x2b0 ? page_fault+0x8/0x30 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Cc: stable@vger.kernel.org Reported-by: 秦世松 Signed-off-by: Samuel Thibault Tested-by: Shisong Qin Link: https://lore.kernel.org/r/20201110183541.fzgnlwhjpgqzjeth@function Signed-off-by: Greg Kroah-Hartman --- drivers/accessibility/speakup/spk_ttyio.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/accessibility/speakup/spk_ttyio.c b/drivers/accessibility/speakup/spk_ttyio.c index a831ff64f8ba..e69ea0c7aa20 100644 --- a/drivers/accessibility/speakup/spk_ttyio.c +++ b/drivers/accessibility/speakup/spk_ttyio.c @@ -49,15 +49,25 @@ static int spk_ttyio_ldisc_open(struct tty_struct *tty) if (!tty->ops->write) return -EOPNOTSUPP; + + mutex_lock(&speakup_tty_mutex); + if (speakup_tty) { + mutex_unlock(&speakup_tty_mutex); + return -EBUSY; + } speakup_tty = tty; ldisc_data = kmalloc(sizeof(*ldisc_data), GFP_KERNEL); - if (!ldisc_data) + if (!ldisc_data) { + speakup_tty = NULL; + mutex_unlock(&speakup_tty_mutex); return -ENOMEM; + } init_completion(&ldisc_data->completion); ldisc_data->buf_free = true; speakup_tty->disc_data = ldisc_data; + mutex_unlock(&speakup_tty_mutex); return 0; } -- cgit v1.2.3 From e67c139c488e84e7eae6c333231e791f0e89b3fb Mon Sep 17 00:00:00 2001 From: Fugang Duan Date: Wed, 11 Nov 2020 10:51:36 +0800 Subject: tty: serial: imx: keep console clocks always on MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For below code, there has chance to cause deadlock in SMP system: Thread 1: clk_enable_lock(); pr_info("debug message"); clk_enable_unlock(); Thread 2: imx_uart_console_write() clk_enable() clk_enable_lock(); Thread 1: Acuired clk enable_lock -> printk -> console_trylock_spinning Thread 2: console_unlock() -> imx_uart_console_write -> clk_disable -> Acquite clk enable_lock So the patch is to keep console port clocks always on like other console drivers. Fixes: 1cf93e0d5488 ("serial: imx: remove the uart_console() check") Acked-by: Uwe Kleine-König Signed-off-by: Fugang Duan Link: https://lore.kernel.org/r/20201111025136.29818-1-fugang.duan@nxp.com Cc: stable [fix up build warning - gregkh] Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/imx.c | 20 +++----------------- 1 file changed, 3 insertions(+), 17 deletions(-) diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 3c53a3c89959..cacf7266a262 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -2008,16 +2008,6 @@ imx_uart_console_write(struct console *co, const char *s, unsigned int count) unsigned int ucr1; unsigned long flags = 0; int locked = 1; - int retval; - - retval = clk_enable(sport->clk_per); - if (retval) - return; - retval = clk_enable(sport->clk_ipg); - if (retval) { - clk_disable(sport->clk_per); - return; - } if (sport->port.sysrq) locked = 0; @@ -2053,9 +2043,6 @@ imx_uart_console_write(struct console *co, const char *s, unsigned int count) if (locked) spin_unlock_irqrestore(&sport->port.lock, flags); - - clk_disable(sport->clk_ipg); - clk_disable(sport->clk_per); } /* @@ -2156,15 +2143,14 @@ imx_uart_console_setup(struct console *co, char *options) retval = uart_set_options(&sport->port, co, baud, parity, bits, flow); - clk_disable(sport->clk_ipg); if (retval) { - clk_unprepare(sport->clk_ipg); + clk_disable_unprepare(sport->clk_ipg); goto error_console; } - retval = clk_prepare(sport->clk_per); + retval = clk_prepare_enable(sport->clk_per); if (retval) - clk_unprepare(sport->clk_ipg); + clk_disable_unprepare(sport->clk_ipg); error_console: return retval; -- cgit v1.2.3 From 425af483523b76bc78e14674a430579d38b2a593 Mon Sep 17 00:00:00 2001 From: Zheng Zengkai Date: Wed, 11 Nov 2020 20:44:26 +0800 Subject: serial: ar933x_uart: disable clk on error handling path in probe ar933x_uart_probe() does not invoke clk_disable_unprepare() on one error handling path. This patch fixes that. Fixes: 9be1064fe524 ("serial: ar933x_uart: add RS485 support") Reported-by: Hulk Robot Signed-off-by: Zheng Zengkai Link: https://lore.kernel.org/r/20201111124426.42638-1-zhengzengkai@huawei.com Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/ar933x_uart.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c index 0c80a79d7442..c2be7cf91399 100644 --- a/drivers/tty/serial/ar933x_uart.c +++ b/drivers/tty/serial/ar933x_uart.c @@ -789,8 +789,10 @@ static int ar933x_uart_probe(struct platform_device *pdev) goto err_disable_clk; up->gpios = mctrl_gpio_init(port, 0); - if (IS_ERR(up->gpios) && PTR_ERR(up->gpios) != -ENOSYS) - return PTR_ERR(up->gpios); + if (IS_ERR(up->gpios) && PTR_ERR(up->gpios) != -ENOSYS) { + ret = PTR_ERR(up->gpios); + goto err_disable_clk; + } up->rts_gpiod = mctrl_gpio_to_gpiod(up->gpios, UART_GPIO_RTS); -- cgit v1.2.3 From 1d18288555b3265f84d08f1f75582415e4ec343a Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 11 Nov 2020 19:33:57 +0100 Subject: mac80211: fix memory leak on filtered powersave frames After the status rework, ieee80211_tx_status_ext is leaking un-acknowledged packets for stations in powersave mode. To fix this, move the code handling those packets from __ieee80211_tx_status into ieee80211_tx_status_ext Reported-by: Tobias Waldvogel Fixes: 3318111cf63d ("mac80211: reduce duplication in tx status functions") Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20201111183359.43528-1-nbd@nbd.name Signed-off-by: Johannes Berg --- net/mac80211/status.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 6feb45135020..3485610755ef 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -49,7 +49,8 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, int ac; if (info->flags & (IEEE80211_TX_CTL_NO_PS_BUFFER | - IEEE80211_TX_CTL_AMPDU)) { + IEEE80211_TX_CTL_AMPDU | + IEEE80211_TX_CTL_HW_80211_ENCAP)) { ieee80211_free_txskb(&local->hw, skb); return; } @@ -915,15 +916,6 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, ieee80211_mpsp_trigger_process( ieee80211_get_qos_ctl(hdr), sta, true, acked); - if (!acked && test_sta_flag(sta, WLAN_STA_PS_STA)) { - /* - * The STA is in power save mode, so assume - * that this TX packet failed because of that. - */ - ieee80211_handle_filtered_frame(local, sta, skb); - return; - } - if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL) && (ieee80211_is_data(hdr->frame_control)) && (rates_idx != -1)) @@ -1150,6 +1142,12 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, -info->status.ack_signal); } } else if (test_sta_flag(sta, WLAN_STA_PS_STA)) { + /* + * The STA is in power save mode, so assume + * that this TX packet failed because of that. + */ + if (skb) + ieee80211_handle_filtered_frame(local, sta, skb); return; } else if (noack_success) { /* nothing to do here, do not account as lost */ -- cgit v1.2.3 From 4fe40b8e1566dad04c87fbf299049a1d0d4bd58d Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 11 Nov 2020 19:33:58 +0100 Subject: mac80211: minstrel: remove deferred sampling code Deferring sampling attempts to the second stage has some bad interactions with drivers that process the rate table in hardware and use the probe flag to indicate probing packets (e.g. most mt76 drivers). On affected drivers it can lead to probing not working at all. If the link conditions turn worse, it might not be such a good idea to do a lot of sampling for lower rates in this case. Fix this by simply skipping the sample attempt instead of deferring it, but keep the checks that would allow it to be sampled if it was skipped too often, but only if it has less than 95% success probability. Also ensure that IEEE80211_TX_CTL_RATE_CTRL_PROBE is set for all probing packets. Cc: stable@vger.kernel.org Fixes: cccf129f820e ("mac80211: add the 'minstrel' rate control algorithm") Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20201111183359.43528-2-nbd@nbd.name Signed-off-by: Johannes Berg --- net/mac80211/rc80211_minstrel.c | 25 ++++--------------------- net/mac80211/rc80211_minstrel.h | 1 - 2 files changed, 4 insertions(+), 22 deletions(-) diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 86bc469a28bc..a8a940e97a9a 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -287,12 +287,6 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, mi->r[ndx].stats.success += success; } - if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) && (i >= 0)) - mi->sample_packets++; - - if (mi->sample_deferred > 0) - mi->sample_deferred--; - if (time_after(jiffies, mi->last_stats_update + mp->update_interval / (mp->new_avg ? 2 : 1))) minstrel_update_stats(mp, mi); @@ -367,7 +361,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, return; delta = (mi->total_packets * sampling_ratio / 100) - - (mi->sample_packets + mi->sample_deferred / 2); + mi->sample_packets; /* delta < 0: no sampling required */ prev_sample = mi->prev_sample; @@ -376,7 +370,6 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, return; if (mi->total_packets >= 10000) { - mi->sample_deferred = 0; mi->sample_packets = 0; mi->total_packets = 0; } else if (delta > mi->n_rates * 2) { @@ -401,19 +394,8 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, * rate sampling method should be used. * Respect such rates that are not sampled for 20 interations. */ - if (mrr_capable && - msr->perfect_tx_time > mr->perfect_tx_time && - msr->stats.sample_skipped < 20) { - /* Only use IEEE80211_TX_CTL_RATE_CTRL_PROBE to mark - * packets that have the sampling rate deferred to the - * second MRR stage. Increase the sample counter only - * if the deferred sample rate was actually used. - * Use the sample_deferred counter to make sure that - * the sampling is not done in large bursts */ - info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE; - rate++; - mi->sample_deferred++; - } else { + if (msr->perfect_tx_time < mr->perfect_tx_time || + msr->stats.sample_skipped >= 20) { if (!msr->sample_limit) return; @@ -433,6 +415,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, rate->idx = mi->r[ndx].rix; rate->count = minstrel_get_retry_count(&mi->r[ndx], info); + info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE; } diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h index dbb43bcd3c45..86cd80b3ffde 100644 --- a/net/mac80211/rc80211_minstrel.h +++ b/net/mac80211/rc80211_minstrel.h @@ -126,7 +126,6 @@ struct minstrel_sta_info { u8 max_prob_rate; unsigned int total_packets; unsigned int sample_packets; - int sample_deferred; unsigned int sample_row; unsigned int sample_column; -- cgit v1.2.3 From b2911a84396f72149dce310a3b64d8948212c1b3 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 11 Nov 2020 19:33:59 +0100 Subject: mac80211: minstrel: fix tx status processing corner case Some drivers fill the status rate list without setting the rate index after the final rate to -1. minstrel_ht already deals with this, but minstrel doesn't, which causes it to get stuck at the lowest rate on these drivers. Fix this by checking the count as well. Cc: stable@vger.kernel.org Fixes: cccf129f820e ("mac80211: add the 'minstrel' rate control algorithm") Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20201111183359.43528-3-nbd@nbd.name Signed-off-by: Johannes Berg --- net/mac80211/rc80211_minstrel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index a8a940e97a9a..b13b1da19386 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -274,7 +274,7 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, success = !!(info->flags & IEEE80211_TX_STAT_ACK); for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { - if (ar[i].idx < 0) + if (ar[i].idx < 0 || !ar[i].count) break; ndx = rix_to_ndx(mi, ar[i].idx); -- cgit v1.2.3 From 966e7ea434484a006700c144bca629a14f93530c Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 10 Nov 2020 14:46:55 +0100 Subject: s390: update defconfigs Signed-off-by: Heiko Carstens --- arch/s390/configs/debug_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index a4d3c578fbd8..fe6f529ac82c 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -1,3 +1,4 @@ +CONFIG_UAPI_HEADER_TEST=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_WATCH_QUEUE=y -- cgit v1.2.3 From 78d732e1f326f74f240d416af9484928303d9951 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 11 Nov 2020 16:26:25 +0100 Subject: s390/cpum_sf.c: fix file permission for cpum_sfb_size This file is installed by the s390 CPU Measurement sampling facility device driver to export supported minimum and maximum sample buffer sizes. This file is read by lscpumf tool to display the details of the device driver capabilities. The lscpumf tool might be invoked by a non-root user. In this case it does not print anything because the file contents can not be read. Fix this by allowing read access for all users. Reading the file contents is ok, changing the file contents is left to the root user only. For further reference and details see: [1] https://github.com/ibm-s390-tools/s390-tools/issues/97 Fixes: 69f239ed335a ("s390/cpum_sf: Dynamically extend the sampling buffer if overflows occur") Cc: # 3.14 Signed-off-by: Thomas Richter Acked-by: Sumanth Korikkar Signed-off-by: Heiko Carstens --- arch/s390/kernel/perf_cpum_sf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 4f9e4626df55..f100c9209743 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -2228,4 +2228,4 @@ out: } arch_initcall(init_cpum_sampling_pmu); -core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640); +core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0644); -- cgit v1.2.3 From b98467fe96d2415836d154ecfe1cd389bf4147b5 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Thu, 29 Oct 2020 12:03:35 +0200 Subject: thermal: ti-soc-thermal: Disable the CPU PM notifier for OMAP4430 It has been observed that on OMAP4430 (ES2.0, ES2.1 and ES2.3) the enabled notifier causes errors on the DTEMP readout values: ti-soc-thermal 4a002260.bandgap: in range ADC val: 52 ti-soc-thermal 4a002260.bandgap: in range ADC val: 64 ti-soc-thermal 4a002260.bandgap: in range ADC val: 64 ti-soc-thermal 4a002260.bandgap: out of range ADC val: 0 thermal thermal_zone0: failed to read out thermal zone (-5) ti-soc-thermal 4a002260.bandgap: out of range ADC val: 0 thermal thermal_zone0: failed to read out thermal zone (-5) ti-soc-thermal 4a002260.bandgap: out of range ADC val: 4 thermal thermal_zone0: failed to read out thermal zone (-5) ti-soc-thermal 4a002260.bandgap: in range ADC val: 100 raw 100 translates to 133 Celsius on omap4-sdp, triggering shutdown due to critical temperature. When the notifier is disable for OMAP4430 the DTEMP values are stable: ti-soc-thermal 4a002260.bandgap: in range ADC val: 56 ti-soc-thermal 4a002260.bandgap: in range ADC val: 56 ti-soc-thermal 4a002260.bandgap: in range ADC val: 57 ti-soc-thermal 4a002260.bandgap: in range ADC val: 57 ti-soc-thermal 4a002260.bandgap: in range ADC val: 56 Fixes: 5093402e5b44 ("thermal: ti-soc-thermal: Enable addition power management") Signed-off-by: Peter Ujfalusi Tested-by: Tony Lindgren Acked-by: Keerthy Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20201029100335.27665-1-peter.ujfalusi@ti.com --- drivers/thermal/ti-soc-thermal/ti-bandgap.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/ti-soc-thermal/ti-bandgap.c b/drivers/thermal/ti-soc-thermal/ti-bandgap.c index 5e596168ba73..dcac99f327b0 100644 --- a/drivers/thermal/ti-soc-thermal/ti-bandgap.c +++ b/drivers/thermal/ti-soc-thermal/ti-bandgap.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -864,6 +865,17 @@ static struct ti_bandgap *ti_bandgap_build(struct platform_device *pdev) return bgp; } +/* + * List of SoCs on which the CPU PM notifier can cause erros on the DTEMP + * readout. + * Enabled notifier on these machines results in erroneous, random values which + * could trigger unexpected thermal shutdown. + */ +static const struct soc_device_attribute soc_no_cpu_notifier[] = { + { .machine = "OMAP4430" }, + { /* sentinel */ }, +}; + /*** Device driver call backs ***/ static @@ -1020,7 +1032,8 @@ int ti_bandgap_probe(struct platform_device *pdev) #ifdef CONFIG_PM_SLEEP bgp->nb.notifier_call = bandgap_omap_cpu_notifier; - cpu_pm_register_notifier(&bgp->nb); + if (!soc_device_match(soc_no_cpu_notifier)) + cpu_pm_register_notifier(&bgp->nb); #endif return 0; @@ -1056,7 +1069,8 @@ int ti_bandgap_remove(struct platform_device *pdev) struct ti_bandgap *bgp = platform_get_drvdata(pdev); int i; - cpu_pm_unregister_notifier(&bgp->nb); + if (!soc_device_match(soc_no_cpu_notifier)) + cpu_pm_unregister_notifier(&bgp->nb); /* Remove sensor interfaces */ for (i = 0; i < bgp->conf->sensor_count; i++) { -- cgit v1.2.3 From ee5e58418a854755201eb4952b1230d873a457d5 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 2 Nov 2020 14:36:56 +0100 Subject: HID: logitech-dj: Handle quad/bluetooth keyboards with a builtin trackpad Some quad/bluetooth keyboards, such as the Dinovo Edge (Y-RAY81) have a builtin touchpad. In this case when asking the receiver for paired devices, we get only 1 paired device with a device_type of REPORT_TYPE_KEYBOARD. This means that we do not instantiate a second dj_hiddev for the mouse (as we normally would) and thus there is no place for us to forward the mouse input reports to, causing the touchpad part of the keyboard to not work. There is no way for us to detect these keyboards, so this commit adds an array with device-ids for such keyboards and when a keyboard is on this list it adds STD_MOUSE to the reports_supported bitmap for the dj_hiddev created for the keyboard fixing the touchpad not working. Using a list of device-ids for this is not ideal, but there are only very few such keyboards so this should be fine. Besides the Dinovo Edge, other known wireless Logitech keyboards with a builtin touchpad are: * Dinovo Mini (TODO add its device-id to the list) * K400 (uses a unifying receiver so is not affected) * K600 (uses a unifying receiver so is not affected) Cc: stable@vger.kernel.org BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1811424 Fixes: f2113c3020ef ("HID: logitech-dj: add support for Logitech Bluetooth Mini-Receiver") Signed-off-by: Hans de Goede Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-logitech-dj.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 38ee25a813b9..1cafb65428b0 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -866,11 +866,23 @@ static void logi_dj_recv_queue_notification(struct dj_receiver_dev *djrcv_dev, schedule_work(&djrcv_dev->work); } +/* + * Some quad/bluetooth keyboards have a builtin touchpad in this case we see + * only 1 paired device with a device_type of REPORT_TYPE_KEYBOARD. For the + * touchpad to work we must also forward mouse input reports to the dj_hiddev + * created for the keyboard (instead of forwarding them to a second paired + * device with a device_type of REPORT_TYPE_MOUSE as we normally would). + */ +static const u16 kbd_builtin_touchpad_ids[] = { + 0xb309, /* Dinovo Edge */ +}; + static void logi_hidpp_dev_conn_notif_equad(struct hid_device *hdev, struct hidpp_event *hidpp_report, struct dj_workitem *workitem) { struct dj_receiver_dev *djrcv_dev = hid_get_drvdata(hdev); + int i, id; workitem->type = WORKITEM_TYPE_PAIRED; workitem->device_type = hidpp_report->params[HIDPP_PARAM_DEVICE_INFO] & @@ -882,6 +894,13 @@ static void logi_hidpp_dev_conn_notif_equad(struct hid_device *hdev, workitem->reports_supported |= STD_KEYBOARD | MULTIMEDIA | POWER_KEYS | MEDIA_CENTER | HIDPP; + id = (workitem->quad_id_msb << 8) | workitem->quad_id_lsb; + for (i = 0; i < ARRAY_SIZE(kbd_builtin_touchpad_ids); i++) { + if (id == kbd_builtin_touchpad_ids[i]) { + workitem->reports_supported |= STD_MOUSE; + break; + } + } break; case REPORT_TYPE_MOUSE: workitem->reports_supported |= STD_MOUSE | HIDPP; -- cgit v1.2.3 From c27168a04a438a457c100253b1aaf0c779218aae Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 2 Nov 2020 14:36:57 +0100 Subject: HID: logitech-hidpp: Add HIDPP_CONSUMER_VENDOR_KEYS quirk for the Dinovo Edge Like the MX5000 and MX5500 quad/bluetooth keyboards the Dinovo Edge also needs the HIDPP_CONSUMER_VENDOR_KEYS quirk for some special keys to work. Specifically without this the "Phone" and the 'A' - 'D' Smart Keys do not send any events. In addition to fixing these keys not sending any events, adding the Bluetooth match, so that hid-logitech-hidpp is used instead of the generic HID driver, also adds battery monitoring support when the keyboard is connected over Bluetooth. Signed-off-by: Hans de Goede Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-logitech-hidpp.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 730036650f7d..40b7c75b3384 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -3972,6 +3972,9 @@ static const struct hid_device_id hidpp_devices[] = { { /* Keyboard MX5000 (Bluetooth-receiver in HID proxy mode) */ LDJ_DEVICE(0xb305), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, + { /* Dinovo Edge (Bluetooth-receiver in HID proxy mode) */ + LDJ_DEVICE(0xb309), + .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, { /* Keyboard MX5500 (Bluetooth-receiver in HID proxy mode) */ LDJ_DEVICE(0xb30b), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, @@ -4014,6 +4017,9 @@ static const struct hid_device_id hidpp_devices[] = { { /* MX5000 keyboard over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb305), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, + { /* Dinovo Edge keyboard over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb309), + .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, { /* MX5500 keyboard over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb30b), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, -- cgit v1.2.3 From 7940fb035abd88040d56be209962feffa33b03d0 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 2 Nov 2020 14:36:58 +0100 Subject: HID: Add Logitech Dinovo Edge battery quirk The battery status is also being reported by the logitech-hidpp driver, so ignore the standard HID battery status to avoid reporting the same info twice. Note the logitech-hidpp battery driver provides more info, such as properly differentiating between charging and discharging. Also the standard HID battery info seems to be wrong, reporting a capacity of just 26% after fully charging the device. Signed-off-by: Hans de Goede Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-input.c | 3 +++ 2 files changed, 4 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index af361cd04bf0..f170feaac40b 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -750,6 +750,7 @@ #define USB_VENDOR_ID_LOGITECH 0x046d #define USB_DEVICE_ID_LOGITECH_AUDIOHUB 0x0a0e #define USB_DEVICE_ID_LOGITECH_T651 0xb00c +#define USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD 0xb309 #define USB_DEVICE_ID_LOGITECH_C007 0xc007 #define USB_DEVICE_ID_LOGITECH_C077 0xc077 #define USB_DEVICE_ID_LOGITECH_RECEIVER 0xc101 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 9770db624bfa..4dca11392459 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -319,6 +319,9 @@ static const struct hid_device_id hid_battery_quirks[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_T100CHI_KEYBOARD), HID_BATTERY_QUIRK_IGNORE }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, + USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD), + HID_BATTERY_QUIRK_IGNORE }, {} }; -- cgit v1.2.3 From 5e844cc37a5cbaa460e68f9a989d321d63088a89 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 11 Nov 2020 20:07:10 +0100 Subject: spi: Introduce device-managed SPI controller allocation SPI driver probing currently comprises two steps, whereas removal comprises only one step: spi_alloc_master() spi_register_controller() spi_unregister_controller() That's because spi_unregister_controller() calls device_unregister() instead of device_del(), thereby releasing the reference on the spi_controller which was obtained by spi_alloc_master(). An SPI driver's private data is contained in the same memory allocation as the spi_controller struct. Thus, once spi_unregister_controller() has been called, the private data is inaccessible. But some drivers need to access it after spi_unregister_controller() to perform further teardown steps. Introduce devm_spi_alloc_master() and devm_spi_alloc_slave(), which release a reference on the spi_controller struct only after the driver has unbound, thereby keeping the memory allocation accessible. Change spi_unregister_controller() to not release a reference if the spi_controller was allocated by one of these new devm functions. The present commit is small enough to be backportable to stable. It allows fixing drivers which use the private data in their ->remove() hook after it's been freed. It also allows fixing drivers which neglect to release a reference on the spi_controller in the probe error path. Long-term, most SPI drivers shall be moved over to the devm functions introduced herein. The few that can't shall be changed in a treewide commit to explicitly release the last reference on the controller. That commit shall amend spi_unregister_controller() to no longer release a reference, thereby completing the migration. As a result, the behaviour will be less surprising and more consistent with subsystems such as IIO, which also includes the private data in the allocation of the generic iio_dev struct, but calls device_del() in iio_device_unregister(). Signed-off-by: Lukas Wunner Link: https://lore.kernel.org/r/272bae2ef08abd21388c98e23729886663d19192.1605121038.git.lukas@wunner.de Signed-off-by: Mark Brown --- drivers/spi/spi.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++++- include/linux/spi/spi.h | 19 ++++++++++++++++ 2 files changed, 76 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 7566482c052c..05c75f890ace 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2442,6 +2442,49 @@ struct spi_controller *__spi_alloc_controller(struct device *dev, } EXPORT_SYMBOL_GPL(__spi_alloc_controller); +static void devm_spi_release_controller(struct device *dev, void *ctlr) +{ + spi_controller_put(*(struct spi_controller **)ctlr); +} + +/** + * __devm_spi_alloc_controller - resource-managed __spi_alloc_controller() + * @dev: physical device of SPI controller + * @size: how much zeroed driver-private data to allocate + * @slave: whether to allocate an SPI master (false) or SPI slave (true) + * Context: can sleep + * + * Allocate an SPI controller and automatically release a reference on it + * when @dev is unbound from its driver. Drivers are thus relieved from + * having to call spi_controller_put(). + * + * The arguments to this function are identical to __spi_alloc_controller(). + * + * Return: the SPI controller structure on success, else NULL. + */ +struct spi_controller *__devm_spi_alloc_controller(struct device *dev, + unsigned int size, + bool slave) +{ + struct spi_controller **ptr, *ctlr; + + ptr = devres_alloc(devm_spi_release_controller, sizeof(*ptr), + GFP_KERNEL); + if (!ptr) + return NULL; + + ctlr = __spi_alloc_controller(dev, size, slave); + if (ctlr) { + *ptr = ctlr; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return ctlr; +} +EXPORT_SYMBOL_GPL(__devm_spi_alloc_controller); + #ifdef CONFIG_OF static int of_spi_get_gpio_numbers(struct spi_controller *ctlr) { @@ -2778,6 +2821,11 @@ int devm_spi_register_controller(struct device *dev, } EXPORT_SYMBOL_GPL(devm_spi_register_controller); +static int devm_spi_match_controller(struct device *dev, void *res, void *ctlr) +{ + return *(struct spi_controller **)res == ctlr; +} + static int __unregister(struct device *dev, void *null) { spi_unregister_device(to_spi_device(dev)); @@ -2819,7 +2867,15 @@ void spi_unregister_controller(struct spi_controller *ctlr) list_del(&ctlr->list); mutex_unlock(&board_lock); - device_unregister(&ctlr->dev); + device_del(&ctlr->dev); + + /* Release the last reference on the controller if its driver + * has not yet been converted to devm_spi_alloc_master/slave(). + */ + if (!devres_find(ctlr->dev.parent, devm_spi_release_controller, + devm_spi_match_controller, ctlr)) + put_device(&ctlr->dev); + /* free bus id */ mutex_lock(&board_lock); if (found == ctlr) diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 99380c0825db..b390fdac1587 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -734,6 +734,25 @@ static inline struct spi_controller *spi_alloc_slave(struct device *host, return __spi_alloc_controller(host, size, true); } +struct spi_controller *__devm_spi_alloc_controller(struct device *dev, + unsigned int size, + bool slave); + +static inline struct spi_controller *devm_spi_alloc_master(struct device *dev, + unsigned int size) +{ + return __devm_spi_alloc_controller(dev, size, false); +} + +static inline struct spi_controller *devm_spi_alloc_slave(struct device *dev, + unsigned int size) +{ + if (!IS_ENABLED(CONFIG_SPI_SLAVE)) + return NULL; + + return __devm_spi_alloc_controller(dev, size, true); +} + extern int spi_register_controller(struct spi_controller *ctlr); extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); -- cgit v1.2.3 From e1483ac030fb4c57734289742f1c1d38dca61e22 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 11 Nov 2020 20:07:20 +0100 Subject: spi: bcm2835: Fix use-after-free on unbind bcm2835_spi_remove() accesses the driver's private data after calling spi_unregister_controller() even though that function releases the last reference on the spi_controller and thereby frees the private data. Fix by switching over to the new devm_spi_alloc_master() helper which keeps the private data accessible until the driver has unbound. Fixes: f8043872e796 ("spi: add driver for BCM2835") Reported-by: Sascha Hauer Reported-by: Florian Fainelli Signed-off-by: Lukas Wunner Cc: # v3.10+: 123456789abc: spi: Introduce device-managed SPI controller allocation Cc: # v3.10+ Cc: Vladimir Oltean Tested-by: Florian Fainelli Acked-by: Florian Fainelli Link: https://lore.kernel.org/r/ad66e0a0ad96feb848814842ecf5b6a4539ef35c.1605121038.git.lukas@wunner.de Signed-off-by: Mark Brown --- drivers/spi/spi-bcm2835.c | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-) diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index 7104cf17b848..197485f2c2b2 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -1278,7 +1278,7 @@ static int bcm2835_spi_probe(struct platform_device *pdev) struct bcm2835_spi *bs; int err; - ctlr = spi_alloc_master(&pdev->dev, ALIGN(sizeof(*bs), + ctlr = devm_spi_alloc_master(&pdev->dev, ALIGN(sizeof(*bs), dma_get_cache_alignment())); if (!ctlr) return -ENOMEM; @@ -1299,23 +1299,17 @@ static int bcm2835_spi_probe(struct platform_device *pdev) bs->ctlr = ctlr; bs->regs = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(bs->regs)) { - err = PTR_ERR(bs->regs); - goto out_controller_put; - } + if (IS_ERR(bs->regs)) + return PTR_ERR(bs->regs); bs->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(bs->clk)) { - err = dev_err_probe(&pdev->dev, PTR_ERR(bs->clk), - "could not get clk\n"); - goto out_controller_put; - } + if (IS_ERR(bs->clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(bs->clk), + "could not get clk\n"); bs->irq = platform_get_irq(pdev, 0); - if (bs->irq <= 0) { - err = bs->irq ? bs->irq : -ENODEV; - goto out_controller_put; - } + if (bs->irq <= 0) + return bs->irq ? bs->irq : -ENODEV; clk_prepare_enable(bs->clk); @@ -1349,8 +1343,6 @@ out_dma_release: bcm2835_dma_release(ctlr, bs); out_clk_disable: clk_disable_unprepare(bs->clk); -out_controller_put: - spi_controller_put(ctlr); return err; } -- cgit v1.2.3 From e13ee6cc4781edaf8c7321bee19217e3702ed481 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 11 Nov 2020 20:07:30 +0100 Subject: spi: bcm2835aux: Fix use-after-free on unbind bcm2835aux_spi_remove() accesses the driver's private data after calling spi_unregister_master() even though that function releases the last reference on the spi_master and thereby frees the private data. Fix by switching over to the new devm_spi_alloc_master() helper which keeps the private data accessible until the driver has unbound. Fixes: b9dd3f6d4172 ("spi: bcm2835aux: Fix controller unregister order") Signed-off-by: Lukas Wunner Cc: # v4.4+: 123456789abc: spi: Introduce device-managed SPI controller allocation Cc: # v4.4+: b9dd3f6d4172: spi: bcm2835aux: Fix controller unregister order Cc: # v4.4+ Link: https://lore.kernel.org/r/b290b06357d0c0bdee9cecc539b840a90630f101.1605121038.git.lukas@wunner.de Signed-off-by: Mark Brown --- drivers/spi/spi-bcm2835aux.c | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c index 03b034c15d2b..fd58547110e6 100644 --- a/drivers/spi/spi-bcm2835aux.c +++ b/drivers/spi/spi-bcm2835aux.c @@ -494,7 +494,7 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev) unsigned long clk_hz; int err; - master = spi_alloc_master(&pdev->dev, sizeof(*bs)); + master = devm_spi_alloc_master(&pdev->dev, sizeof(*bs)); if (!master) return -ENOMEM; @@ -524,29 +524,24 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev) /* the main area */ bs->regs = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(bs->regs)) { - err = PTR_ERR(bs->regs); - goto out_master_put; - } + if (IS_ERR(bs->regs)) + return PTR_ERR(bs->regs); bs->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(bs->clk)) { - err = PTR_ERR(bs->clk); dev_err(&pdev->dev, "could not get clk: %d\n", err); - goto out_master_put; + return PTR_ERR(bs->clk); } bs->irq = platform_get_irq(pdev, 0); - if (bs->irq <= 0) { - err = bs->irq ? bs->irq : -ENODEV; - goto out_master_put; - } + if (bs->irq <= 0) + return bs->irq ? bs->irq : -ENODEV; /* this also enables the HW block */ err = clk_prepare_enable(bs->clk); if (err) { dev_err(&pdev->dev, "could not prepare clock: %d\n", err); - goto out_master_put; + return err; } /* just checking if the clock returns a sane value */ @@ -581,8 +576,6 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev) out_clk_disable: clk_disable_unprepare(bs->clk); -out_master_put: - spi_master_put(master); return err; } -- cgit v1.2.3 From 63c5395bb7a9777a33f0e7b5906f2c0170a23692 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 11 Nov 2020 20:07:40 +0100 Subject: spi: bcm-qspi: Fix use-after-free on unbind bcm_qspi_remove() calls spi_unregister_master() even though bcm_qspi_probe() calls devm_spi_register_master(). The spi_master is therefore unregistered and freed twice on unbind. Moreover, since commit 0392727c261b ("spi: bcm-qspi: Handle clock probe deferral"), bcm_qspi_probe() leaks the spi_master allocation if the call to devm_clk_get_optional() fails. Fix by switching over to the new devm_spi_alloc_master() helper which keeps the private data accessible until the driver has unbound and also avoids the spi_master leak on probe. While at it, fix an ordering issue in bcm_qspi_remove() wherein spi_unregister_master() is called after uninitializing the hardware, disabling the clock and freeing an IRQ data structure. The correct order is to call spi_unregister_master() *before* those teardown steps because bus accesses may still be ongoing until that function returns. Fixes: fa236a7ef240 ("spi: bcm-qspi: Add Broadcom MSPI driver") Signed-off-by: Lukas Wunner Cc: # v4.9+: 123456789abc: spi: Introduce device-managed SPI controller allocation Cc: # v4.9+ Cc: Kamal Dasu Acked-by: Florian Fainelli Tested-by: Florian Fainelli Link: https://lore.kernel.org/r/5e31a9a59fd1c0d0b795b2fe219f25e5ee855f9d.1605121038.git.lukas@wunner.de Signed-off-by: Mark Brown --- drivers/spi/spi-bcm-qspi.c | 34 ++++++++++++---------------------- 1 file changed, 12 insertions(+), 22 deletions(-) diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 14c9d0133bce..c028446c7460 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -1327,7 +1327,7 @@ int bcm_qspi_probe(struct platform_device *pdev, data = of_id->data; - master = spi_alloc_master(dev, sizeof(struct bcm_qspi)); + master = devm_spi_alloc_master(dev, sizeof(struct bcm_qspi)); if (!master) { dev_err(dev, "error allocating spi_master\n"); return -ENOMEM; @@ -1367,21 +1367,17 @@ int bcm_qspi_probe(struct platform_device *pdev, if (res) { qspi->base[MSPI] = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->base[MSPI])) { - ret = PTR_ERR(qspi->base[MSPI]); - goto qspi_resource_err; - } + if (IS_ERR(qspi->base[MSPI])) + return PTR_ERR(qspi->base[MSPI]); } else { - goto qspi_resource_err; + return 0; } res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "bspi"); if (res) { qspi->base[BSPI] = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->base[BSPI])) { - ret = PTR_ERR(qspi->base[BSPI]); - goto qspi_resource_err; - } + if (IS_ERR(qspi->base[BSPI])) + return PTR_ERR(qspi->base[BSPI]); qspi->bspi_mode = true; } else { qspi->bspi_mode = false; @@ -1392,18 +1388,14 @@ int bcm_qspi_probe(struct platform_device *pdev, res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cs_reg"); if (res) { qspi->base[CHIP_SELECT] = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->base[CHIP_SELECT])) { - ret = PTR_ERR(qspi->base[CHIP_SELECT]); - goto qspi_resource_err; - } + if (IS_ERR(qspi->base[CHIP_SELECT])) + return PTR_ERR(qspi->base[CHIP_SELECT]); } qspi->dev_ids = kcalloc(num_irqs, sizeof(struct bcm_qspi_dev_id), GFP_KERNEL); - if (!qspi->dev_ids) { - ret = -ENOMEM; - goto qspi_resource_err; - } + if (!qspi->dev_ids) + return -ENOMEM; for (val = 0; val < num_irqs; val++) { irq = -1; @@ -1484,7 +1476,7 @@ int bcm_qspi_probe(struct platform_device *pdev, qspi->xfer_mode.addrlen = -1; qspi->xfer_mode.hp = -1; - ret = devm_spi_register_master(&pdev->dev, master); + ret = spi_register_master(master); if (ret < 0) { dev_err(dev, "can't register master\n"); goto qspi_reg_err; @@ -1497,8 +1489,6 @@ qspi_reg_err: clk_disable_unprepare(qspi->clk); qspi_probe_err: kfree(qspi->dev_ids); -qspi_resource_err: - spi_master_put(master); return ret; } /* probe function to be called by SoC specific platform driver probe */ @@ -1508,10 +1498,10 @@ int bcm_qspi_remove(struct platform_device *pdev) { struct bcm_qspi *qspi = platform_get_drvdata(pdev); + spi_unregister_master(qspi->master); bcm_qspi_hw_uninit(qspi); clk_disable_unprepare(qspi->clk); kfree(qspi->dev_ids); - spi_unregister_master(qspi->master); return 0; } -- cgit v1.2.3 From eb73060b971aa04e4f7421b8c9c0363918608b72 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 4 Nov 2020 17:40:59 -0400 Subject: RDMA/cm: Make the local_id_table xarray non-irq The xarray is never mutated from an IRQ handler, only from work queues under a spinlock_irq. Thus there is no reason for it be an IRQ type xarray. This was copied over from the original IDR code, but the recent rework put the xarray inside another spinlock_irq which will unbalance the unlocking. Fixes: c206f8bad15d ("RDMA/cm: Make it clearer how concurrency works in cm_req_handler()") Link: https://lore.kernel.org/r/0-v1-808b6da3bd3f+1857-cm_xarray_no_irq_jgg@nvidia.com Reported-by: Matthew Wilcox Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/cm.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 5740d1ba3568..012156624b82 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -859,8 +859,8 @@ static struct cm_id_private *cm_alloc_id_priv(struct ib_device *device, atomic_set(&cm_id_priv->work_count, -1); refcount_set(&cm_id_priv->refcount, 1); - ret = xa_alloc_cyclic_irq(&cm.local_id_table, &id, NULL, xa_limit_32b, - &cm.local_id_next, GFP_KERNEL); + ret = xa_alloc_cyclic(&cm.local_id_table, &id, NULL, xa_limit_32b, + &cm.local_id_next, GFP_KERNEL); if (ret < 0) goto error; cm_id_priv->id.local_id = (__force __be32)id ^ cm.random_id_operand; @@ -878,8 +878,8 @@ error: */ static void cm_finalize_id(struct cm_id_private *cm_id_priv) { - xa_store_irq(&cm.local_id_table, cm_local_id(cm_id_priv->id.local_id), - cm_id_priv, GFP_KERNEL); + xa_store(&cm.local_id_table, cm_local_id(cm_id_priv->id.local_id), + cm_id_priv, GFP_ATOMIC); } struct ib_cm_id *ib_create_cm_id(struct ib_device *device, @@ -1169,7 +1169,7 @@ retest: spin_unlock(&cm.lock); spin_unlock_irq(&cm_id_priv->lock); - xa_erase_irq(&cm.local_id_table, cm_local_id(cm_id->local_id)); + xa_erase(&cm.local_id_table, cm_local_id(cm_id->local_id)); cm_deref_id(cm_id_priv); wait_for_completion(&cm_id_priv->comp); while ((work = cm_dequeue_work(cm_id_priv)) != NULL) @@ -4482,7 +4482,7 @@ static int __init ib_cm_init(void) cm.remote_id_table = RB_ROOT; cm.remote_qp_table = RB_ROOT; cm.remote_sidr_table = RB_ROOT; - xa_init_flags(&cm.local_id_table, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ); + xa_init_flags(&cm.local_id_table, XA_FLAGS_ALLOC); get_random_bytes(&cm.random_id_operand, sizeof cm.random_id_operand); INIT_LIST_HEAD(&cm.timewait_list); -- cgit v1.2.3 From d035c3f6cdb8e5d5a17adcbb79d7453417a6077d Mon Sep 17 00:00:00 2001 From: Qinglang Miao Date: Wed, 11 Nov 2020 11:22:02 +0800 Subject: RDMA/pvrdma: Fix missing kfree() in pvrdma_register_device() Fix missing kfree in pvrdma_register_device() when failure from ib_device_set_netdev(). Fixes: 4b38da75e089 ("RDMA/drivers: Convert easy drivers to use ib_device_set_netdev()") Link: https://lore.kernel.org/r/20201111032202.17925-1-miaoqinglang@huawei.com Reported-by: Hulk Robot Signed-off-by: Qinglang Miao Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c index fa2a3fa0c3e4..6895bac53990 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c @@ -266,7 +266,7 @@ static int pvrdma_register_device(struct pvrdma_dev *dev) } ret = ib_device_set_netdev(&dev->ib_dev, dev->netdev, 1); if (ret) - return ret; + goto err_srq_free; spin_lock_init(&dev->srq_tbl_lock); rdma_set_device_sysfs_group(&dev->ib_dev, &pvrdma_attr_group); -- cgit v1.2.3 From fd63729cc0a6872bdabd393ee933a969642e4076 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 11 Nov 2020 15:12:15 -0800 Subject: selftests/bpf: Fix unused attribute usage in subprogs_unused test Correct attribute name is "unused". maybe_unused is a C++17 addition. This patch fixes compilation warning during selftests compilation. Fixes: 197afc631413 ("libbpf: Don't attempt to load unused subprog as an entry-point BPF program") Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201111231215.1779147-1-andrii@kernel.org --- tools/testing/selftests/bpf/progs/test_subprogs_unused.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_unused.c b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c index 75d975f8cf90..bc49e050d342 100644 --- a/tools/testing/selftests/bpf/progs/test_subprogs_unused.c +++ b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c @@ -4,12 +4,12 @@ const char LICENSE[] SEC("license") = "GPL"; -__attribute__((maybe_unused)) __noinline int unused1(int x) +__attribute__((unused)) __noinline int unused1(int x) { return x + 1; } -static __attribute__((maybe_unused)) __noinline int unused2(int x) +static __attribute__((unused)) __noinline int unused2(int x) { return x + 2; } -- cgit v1.2.3 From b1e678bf290db5a76f1b6a9f7c381310e03440d6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 6 Nov 2020 19:19:32 +0100 Subject: RMDA/sw: Don't allow drivers using dma_virt_ops on highmem configs dma_virt_ops requires that all pages have a kernel virtual address. Introduce a INFINIBAND_VIRT_DMA Kconfig symbol that depends on !HIGHMEM and make all three drivers depend on the new symbol. Also remove the ARCH_DMA_ADDR_T_64BIT dependency, which has been obsolete since commit 4965a68780c5 ("arch: define the ARCH_DMA_ADDR_T_64BIT config symbol in lib/Kconfig") Fixes: 551199aca1c3 ("lib/dma-virt: Add dma_virt_ops") Link: https://lore.kernel.org/r/20201106181941.1878556-2-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe --- drivers/infiniband/Kconfig | 3 +++ drivers/infiniband/sw/rdmavt/Kconfig | 3 ++- drivers/infiniband/sw/rxe/Kconfig | 2 +- drivers/infiniband/sw/siw/Kconfig | 1 + 4 files changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig index 32a51432ec4f..9325e189a215 100644 --- a/drivers/infiniband/Kconfig +++ b/drivers/infiniband/Kconfig @@ -73,6 +73,9 @@ config INFINIBAND_ADDR_TRANS_CONFIGFS This allows the user to config the default GID type that the CM uses for each device, when initiaing new connections. +config INFINIBAND_VIRT_DMA + def_bool !HIGHMEM + if INFINIBAND_USER_ACCESS || !INFINIBAND_USER_ACCESS source "drivers/infiniband/hw/mthca/Kconfig" source "drivers/infiniband/hw/qib/Kconfig" diff --git a/drivers/infiniband/sw/rdmavt/Kconfig b/drivers/infiniband/sw/rdmavt/Kconfig index 9ef5f5ce1ff6..c8e268082952 100644 --- a/drivers/infiniband/sw/rdmavt/Kconfig +++ b/drivers/infiniband/sw/rdmavt/Kconfig @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only config INFINIBAND_RDMAVT tristate "RDMA verbs transport library" - depends on X86_64 && ARCH_DMA_ADDR_T_64BIT + depends on INFINIBAND_VIRT_DMA + depends on X86_64 depends on PCI select DMA_VIRT_OPS help diff --git a/drivers/infiniband/sw/rxe/Kconfig b/drivers/infiniband/sw/rxe/Kconfig index a0c6c7dfc181..8810bfa68049 100644 --- a/drivers/infiniband/sw/rxe/Kconfig +++ b/drivers/infiniband/sw/rxe/Kconfig @@ -2,7 +2,7 @@ config RDMA_RXE tristate "Software RDMA over Ethernet (RoCE) driver" depends on INET && PCI && INFINIBAND - depends on !64BIT || ARCH_DMA_ADDR_T_64BIT + depends on INFINIBAND_VIRT_DMA select NET_UDP_TUNNEL select CRYPTO_CRC32 select DMA_VIRT_OPS diff --git a/drivers/infiniband/sw/siw/Kconfig b/drivers/infiniband/sw/siw/Kconfig index b622fc62f2cd..3450ba5081df 100644 --- a/drivers/infiniband/sw/siw/Kconfig +++ b/drivers/infiniband/sw/siw/Kconfig @@ -1,6 +1,7 @@ config RDMA_SIW tristate "Software RDMA over TCP/IP (iWARP) driver" depends on INET && INFINIBAND && LIBCRC32C + depends on INFINIBAND_VIRT_DMA select DMA_VIRT_OPS help This driver implements the iWARP RDMA transport over -- cgit v1.2.3 From 4def49da620c84a682d9361d6bef0a97eed46fe0 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sun, 8 Nov 2020 23:41:00 +0100 Subject: spi: lpspi: Fix use-after-free on unbind Normally the last reference on an spi_controller is released by spi_unregister_controller(). In the case of the i.MX lpspi driver, the spi_controller is registered with devm_spi_register_controller(), so spi_unregister_controller() is invoked automatically after the driver has unbound. However the driver already releases the last reference in fsl_lpspi_remove() through a gratuitous call to spi_master_put(), causing a use-after-free when spi_unregister_controller() is subsequently invoked by the devres framework. Fix by dropping the superfluous spi_master_put(). Fixes: 944c01a889d9 ("spi: lpspi: enable runtime pm for lpspi") Signed-off-by: Lukas Wunner Cc: # v5.2+ Cc: Han Xu Link: https://lore.kernel.org/r/ab3c0b18bd820501a12c85e440006e09ec0e275f.1604874488.git.lukas@wunner.de Signed-off-by: Mark Brown --- drivers/spi/spi-fsl-lpspi.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index 986b9793fd3c..a2886ee44e4c 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -938,9 +938,6 @@ static int fsl_lpspi_remove(struct platform_device *pdev) spi_controller_get_devdata(controller); pm_runtime_disable(fsl_lpspi->dev); - - spi_master_put(controller); - return 0; } -- cgit v1.2.3 From 9602182810cc15e241f06c63c90b828ef63d0507 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 12 Nov 2020 10:03:40 -0800 Subject: MAINTAINERS/bpf: Update Andrii's entry. Andrii has been a de-facto maintainer for libbpf and other components. Update maintainers entry to acknowledge his work de-jure. The folks with git write permissions will continue to follow the rule of not applying their own patches unless absolutely trivial. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20201112180340.45265-1-alexei.starovoitov@gmail.com --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index cd123d0a6a2d..008ee2bf753b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3243,10 +3243,10 @@ F: drivers/iio/accel/bma400* BPF (Safe dynamic programs and tools) M: Alexei Starovoitov M: Daniel Borkmann +M: Andrii Nakryiko R: Martin KaFai Lau R: Song Liu R: Yonghong Song -R: Andrii Nakryiko R: John Fastabend R: KP Singh L: netdev@vger.kernel.org -- cgit v1.2.3 From e24a87b54ef3e39261f1d859b7f78416349dfb14 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 4 Nov 2020 17:42:28 +0800 Subject: perf lock: Correct field name "flags" The tracepoint "lock:lock_acquire" contains field "flags" but not "flag". Current code wrongly retrieves value from field "flag" and it always gets zero for the value, thus "perf lock" doesn't report the correct result. This patch replaces the field name "flag" with "flags", so can read out the correct flags for locking. Fixes: e4cef1f65061 ("perf lock: Fix state machine to recognize lock sequence") Signed-off-by: Leo Yan Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20201104094229.17509-1-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-lock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index f0a1dbacb46c..5cecc1ad78e1 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -406,7 +406,7 @@ static int report_lock_acquire_event(struct evsel *evsel, struct lock_seq_stat *seq; const char *name = evsel__strval(evsel, sample, "name"); u64 tmp = evsel__intval(evsel, sample, "lockdep_addr"); - int flag = evsel__intval(evsel, sample, "flag"); + int flag = evsel__intval(evsel, sample, "flags"); memcpy(&addr, &tmp, sizeof(void *)); -- cgit v1.2.3 From b0e5a05cc9e37763c7f19366d94b1a6160c755bc Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 4 Nov 2020 17:42:29 +0800 Subject: perf lock: Don't free "lock_seq_stat" if read_count isn't zero When execute command "perf lock report", it hits failure and outputs log as follows: perf: builtin-lock.c:623: report_lock_release_event: Assertion `!(seq->read_count < 0)' failed. Aborted This is an imbalance issue. The locking sequence structure "lock_seq_stat" contains the reader counter and it is used to check if the locking sequence is balance or not between acquiring and releasing. If the tool wrongly frees "lock_seq_stat" when "read_count" isn't zero, the "read_count" will be reset to zero when allocate a new structure at the next time; thus it causes the wrong counting for reader and finally results in imbalance issue. To fix this issue, if detects "read_count" is not zero (means still have read user in the locking sequence), goto the "end" tag to skip freeing structure "lock_seq_stat". Fixes: e4cef1f65061 ("perf lock: Fix state machine to recognize lock sequence") Signed-off-by: Leo Yan Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20201104094229.17509-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-lock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 5cecc1ad78e1..a2f1e53f37a7 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -621,7 +621,7 @@ static int report_lock_release_event(struct evsel *evsel, case SEQ_STATE_READ_ACQUIRED: seq->read_count--; BUG_ON(seq->read_count < 0); - if (!seq->read_count) { + if (seq->read_count) { ls->nr_release++; goto end; } -- cgit v1.2.3 From db1a8b97a0a36155171dbb805fbcb276e07559f6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 9 Nov 2020 13:59:15 -0300 Subject: tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy' To bring in the change made in this cset: 4d6ffa27b8e5116c ("x86/lib: Change .weak to SYM_FUNC_START_WEAK for arch/x86/lib/mem*_64.S") 6dcc5627f6aec4cb ("x86/asm: Change all ENTRY+ENDPROC to SYM_FUNC_*") I needed to define SYM_FUNC_START_LOCAL() as SYM_L_GLOBAL as mem{cpy,set}_{orig,erms} are used by 'perf bench'. This silences these perf tools build warnings: Warning: Kernel ABI header at 'tools/arch/x86/lib/memcpy_64.S' differs from latest version at 'arch/x86/lib/memcpy_64.S' diff -u tools/arch/x86/lib/memcpy_64.S arch/x86/lib/memcpy_64.S Warning: Kernel ABI header at 'tools/arch/x86/lib/memset_64.S' differs from latest version at 'arch/x86/lib/memset_64.S' diff -u tools/arch/x86/lib/memset_64.S arch/x86/lib/memset_64.S Cc: Adrian Hunter Cc: Borislav Petkov Cc: Fangrui Song Cc: Ian Rogers Cc: Jiri Olsa Cc: Jiri Slaby Cc: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/lib/memcpy_64.S | 8 +++----- tools/arch/x86/lib/memset_64.S | 11 ++++++----- tools/perf/bench/mem-memcpy-x86-64-asm.S | 3 +++ tools/perf/bench/mem-memset-x86-64-asm.S | 3 +++ tools/perf/util/include/linux/linkage.h | 7 +++++++ 5 files changed, 22 insertions(+), 10 deletions(-) diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 0b5b8ae56bd9..1e299ac73c86 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -16,8 +16,6 @@ * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. */ -.weak memcpy - /* * memcpy - Copy a memory block. * @@ -30,7 +28,7 @@ * rax original destination */ SYM_FUNC_START_ALIAS(__memcpy) -SYM_FUNC_START_LOCAL(memcpy) +SYM_FUNC_START_WEAK(memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS @@ -51,14 +49,14 @@ EXPORT_SYMBOL(__memcpy) * memcpy_erms() - enhanced fast string memcpy. This is faster and * simpler than memcpy. Use memcpy_erms when possible. */ -SYM_FUNC_START(memcpy_erms) +SYM_FUNC_START_LOCAL(memcpy_erms) movq %rdi, %rax movq %rdx, %rcx rep movsb ret SYM_FUNC_END(memcpy_erms) -SYM_FUNC_START(memcpy_orig) +SYM_FUNC_START_LOCAL(memcpy_orig) movq %rdi, %rax cmpq $0x20, %rdx diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index fd5d25a474b7..0bfd26e4ca9e 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -4,8 +4,7 @@ #include #include #include - -.weak memset +#include /* * ISO C memset - set a memory block to a byte value. This function uses fast @@ -18,7 +17,7 @@ * * rax original destination */ -SYM_FUNC_START_ALIAS(memset) +SYM_FUNC_START_WEAK(memset) SYM_FUNC_START(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended @@ -44,6 +43,8 @@ SYM_FUNC_START(__memset) ret SYM_FUNC_END(__memset) SYM_FUNC_END_ALIAS(memset) +EXPORT_SYMBOL(memset) +EXPORT_SYMBOL(__memset) /* * ISO C memset - set a memory block to a byte value. This function uses @@ -56,7 +57,7 @@ SYM_FUNC_END_ALIAS(memset) * * rax original destination */ -SYM_FUNC_START(memset_erms) +SYM_FUNC_START_LOCAL(memset_erms) movq %rdi,%r9 movb %sil,%al movq %rdx,%rcx @@ -65,7 +66,7 @@ SYM_FUNC_START(memset_erms) ret SYM_FUNC_END(memset_erms) -SYM_FUNC_START(memset_orig) +SYM_FUNC_START_LOCAL(memset_orig) movq %rdi,%r10 /* expand byte value */ diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 9ad015a1e202..6eb45a2aa8db 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -2,6 +2,9 @@ /* Various wrappers to make the kernel .S file build in user-space: */ +// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memcpy MEMCPY /* don't hide glibc's memcpy() */ #define altinstr_replacement text #define globl p2align 4; .globl diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index d550bd526162..6f093c483842 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memset MEMSET /* don't hide glibc's memset() */ #define altinstr_replacement text #define globl p2align 4; .globl diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index b8a5159361b4..5acf053fca7d 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -25,6 +25,7 @@ /* SYM_L_* -- linkage of symbols */ #define SYM_L_GLOBAL(name) .globl name +#define SYM_L_WEAK(name) .weak name #define SYM_L_LOCAL(name) /* nothing */ #define ALIGN __ALIGN @@ -84,6 +85,12 @@ SYM_END(name, SYM_T_FUNC) #endif +/* SYM_FUNC_START_WEAK -- use for weak functions */ +#ifndef SYM_FUNC_START_WEAK +#define SYM_FUNC_START_WEAK(name) \ + SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN) +#endif + /* * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START, * SYM_FUNC_START_WEAK, ... -- cgit v1.2.3 From db2ac2e49e564c2b219c4b33d9903aa383334256 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Tue, 10 Nov 2020 14:34:16 +0800 Subject: perf test: Fix a typo in cs-etm testing Fix a typo: s/devce_name/device_name. Fixes: fe0aed19b266 ("perf test: Introduce script for Arm CoreSight testing") Signed-off-by: Leo Yan Reviewed-by: Mathieu Poirier Cc: Alexander Shishkin Cc: Jin Yao Cc: Jiri Olsa Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: coresight ml Cc: stable@kernel.org Link: http://lore.kernel.org/lkml/20201110063417.14467-1-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_arm_coresight.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index 8d84fdbed6a6..59d847d4981d 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -105,7 +105,7 @@ arm_cs_iterate_devices() { # `> device_name = 'tmc_etf0' device_name=$(basename $path) - if is_device_sink $path $devce_name; then + if is_device_sink $path $device_name; then record_touch_file $device_name $2 && perf_script_branch_samples touch && -- cgit v1.2.3 From dd94ac807a5e10e0b25b68397c473276905cca73 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Tue, 10 Nov 2020 14:34:17 +0800 Subject: perf test: Update branch sample pattern for cs-etm Since the commit 943b69ac1884 ("perf parse-events: Set exclude_guest=1 for user-space counting"), 'exclude_guest=1' is set for user-space counting; and the branch sample's modifier has been altered, the sample event name has been changed from "branches:u:" to "branches:uH:", which gives out info for "user-space and host counting". But the cs-etm testing's regular expression cannot match the updated branch sample event and leads to test failure. This patch updates the branch sample pattern by using a more flexible expression '.*' to match branch sample's modifiers, so that allows the testing to work as expected. Fixes: 943b69ac1884 ("perf parse-events: Set exclude_guest=1 for user-space counting") Signed-off-by: Leo Yan Reviewed-by: Mathieu Poirier Cc: Alexander Shishkin Cc: Jin Yao Cc: Jiri Olsa Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: coresight ml Cc: stable@kernel.org Link: http://lore.kernel.org/lkml/20201110063417.14467-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_arm_coresight.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index 59d847d4981d..18fde2f179cd 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -44,7 +44,7 @@ perf_script_branch_samples() { # touch 6512 1 branches:u: ffffb22082e0 strcmp+0xa0 (/lib/aarch64-linux-gnu/ld-2.27.so) # touch 6512 1 branches:u: ffffb2208320 strcmp+0xe0 (/lib/aarch64-linux-gnu/ld-2.27.so) perf script -F,-time -i ${perfdata} | \ - egrep " +$1 +[0-9]+ .* +branches:([u|k]:)? +" + egrep " +$1 +[0-9]+ .* +branches:(.*:)? +" } perf_report_branch_samples() { -- cgit v1.2.3 From c3213d260a23e263ef85ba21ac68c9e7578020b5 Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Thu, 12 Nov 2020 15:17:32 -0500 Subject: SUNRPC: Fix oops in the rpc_xdr_buf event class Backchannel rpc tasks don't have task->tk_client set, so it's necessary to check it for NULL before dereferencing. Fixes: c509f15a5801 ("SUNRPC: Split the xdr_buf event class") Signed-off-by: Scott Mayhew Reviewed-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/trace/events/sunrpc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 2477014e3fa6..2a03263b5f9d 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -68,7 +68,8 @@ DECLARE_EVENT_CLASS(rpc_xdr_buf_class, TP_fast_assign( __entry->task_id = task->tk_pid; - __entry->client_id = task->tk_client->cl_clid; + __entry->client_id = task->tk_client ? + task->tk_client->cl_clid : -1; __entry->head_base = xdr->head[0].iov_base; __entry->head_len = xdr->head[0].iov_len; __entry->tail_base = xdr->tail[0].iov_base; -- cgit v1.2.3 From bc551d776b691022f49b5bb5379bd58f7c4eb76a Mon Sep 17 00:00:00 2001 From: Jonathan Liu Date: Sat, 31 Oct 2020 19:17:47 +1100 Subject: drm: bridge: dw-hdmi: Avoid resetting force in the detect function It has been observed that resetting force in the detect function can result in the PHY being powered down in response to hot-plug detect being asserted, even when the HDMI connector is forced on. Enabling debug messages and adding a call to dump_stack() in dw_hdmi_phy_power_off() shows the following in dmesg: [ 160.637413] dwhdmi-rockchip ff940000.hdmi: EVENT=plugin [ 160.637433] dwhdmi-rockchip ff940000.hdmi: PHY powered down in 0 iterations Call trace: dw_hdmi_phy_power_off dw_hdmi_phy_disable dw_hdmi_update_power dw_hdmi_detect dw_hdmi_connector_detect drm_helper_probe_detect_ctx drm_helper_hpd_irq_event dw_hdmi_irq irq_thread_fn irq_thread kthread ret_from_fork Fixes: 381f05a7a842 ("drm: bridge/dw_hdmi: add connector mode forcing") Signed-off-by: Jonathan Liu Reviewed-by: Sam Ravnborg Signed-off-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20201031081747.372599-1-net147@gmail.com --- drivers/gpu/drm/bridge/synopsys/dw-hdmi.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index 748df1cacd2b..0c79a9ba48bb 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -2327,12 +2327,6 @@ static enum drm_connector_status dw_hdmi_detect(struct dw_hdmi *hdmi) { enum drm_connector_status result; - mutex_lock(&hdmi->mutex); - hdmi->force = DRM_FORCE_UNSPECIFIED; - dw_hdmi_update_power(hdmi); - dw_hdmi_update_phy_mask(hdmi); - mutex_unlock(&hdmi->mutex); - result = hdmi->phy.ops->read_hpd(hdmi, hdmi->phy.data); mutex_lock(&hdmi->mutex); -- cgit v1.2.3 From 1922a46b8c18cb09d33e06a6cc2e43844ac1b9d0 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 12 Nov 2020 16:42:10 +1030 Subject: net/ncsi: Fix netlink registration If a user unbinds and re-binds a NC-SI aware driver the kernel will attempt to register the netlink interface at runtime. The structure is marked __ro_after_init so registration fails spectacularly at this point. # echo 1e660000.ethernet > /sys/bus/platform/drivers/ftgmac100/unbind # echo 1e660000.ethernet > /sys/bus/platform/drivers/ftgmac100/bind ftgmac100 1e660000.ethernet: Read MAC address 52:54:00:12:34:56 from chip ftgmac100 1e660000.ethernet: Using NCSI interface 8<--- cut here --- Unable to handle kernel paging request at virtual address 80a8f858 pgd = 8c768dd6 [80a8f858] *pgd=80a0841e(bad) Internal error: Oops: 80d [#1] SMP ARM CPU: 0 PID: 116 Comm: sh Not tainted 5.10.0-rc3-next-20201111-00003-gdd25b227ec1e #51 Hardware name: Generic DT based system PC is at genl_register_family+0x1f8/0x6d4 LR is at 0xff26ffff pc : [<8073f930>] lr : [] psr: 20000153 sp : 8553bc80 ip : 81406244 fp : 8553bd04 r10: 8085d12c r9 : 80a8f73c r8 : 85739000 r7 : 00000017 r6 : 80a8f860 r5 : 80c8ab98 r4 : 80a8f858 r3 : 00000000 r2 : 00000000 r1 : 81406130 r0 : 00000017 Flags: nzCv IRQs on FIQs off Mode SVC_32 ISA ARM Segment none Control: 00c5387d Table: 85524008 DAC: 00000051 Process sh (pid: 116, stack limit = 0x1f1988d6) ... Backtrace: [<8073f738>] (genl_register_family) from [<80860ac0>] (ncsi_init_netlink+0x20/0x48) r10:8085d12c r9:80c8fb0c r8:85739000 r7:00000000 r6:81218000 r5:85739000 r4:8121c000 [<80860aa0>] (ncsi_init_netlink) from [<8085d740>] (ncsi_register_dev+0x1b0/0x210) r5:8121c400 r4:8121c000 [<8085d590>] (ncsi_register_dev) from [<805a8060>] (ftgmac100_probe+0x6e0/0x778) r10:00000004 r9:80950228 r8:8115bc10 r7:8115ab00 r6:9eae2c24 r5:813b6f88 r4:85739000 [<805a7980>] (ftgmac100_probe) from [<805355ec>] (platform_drv_probe+0x58/0xa8) r9:80c76bb0 r8:00000000 r7:80cd4974 r6:80c76bb0 r5:8115bc10 r4:00000000 [<80535594>] (platform_drv_probe) from [<80532d58>] (really_probe+0x204/0x514) r7:80cd4974 r6:00000000 r5:80cd4868 r4:8115bc10 Jakub pointed out that ncsi_register_dev is obviously broken, because there is only one family so it would never work if there was more than one ncsi netdev. Fix the crash by registering the netlink family once on boot, and drop the code to unregister it. Fixes: 955dc68cb9b2 ("net/ncsi: Add generic netlink family") Signed-off-by: Joel Stanley Reviewed-by: Samuel Mendoza-Jonas Link: https://lore.kernel.org/r/20201112061210.914621-1-joel@jms.id.au Signed-off-by: Jakub Kicinski --- net/ncsi/ncsi-manage.c | 5 ----- net/ncsi/ncsi-netlink.c | 22 +++------------------- net/ncsi/ncsi-netlink.h | 3 --- 3 files changed, 3 insertions(+), 27 deletions(-) diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index f1be3e3f6425..a9cb355324d1 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -1726,9 +1726,6 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, ndp->ptype.dev = dev; dev_add_pack(&ndp->ptype); - /* Set up generic netlink interface */ - ncsi_init_netlink(dev); - pdev = to_platform_device(dev->dev.parent); if (pdev) { np = pdev->dev.of_node; @@ -1892,8 +1889,6 @@ void ncsi_unregister_dev(struct ncsi_dev *nd) list_del_rcu(&ndp->node); spin_unlock_irqrestore(&ncsi_dev_lock, flags); - ncsi_unregister_netlink(nd->dev); - kfree(ndp); } EXPORT_SYMBOL_GPL(ncsi_unregister_dev); diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index adddc7707aa4..bb5f1650f11c 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -766,24 +766,8 @@ static struct genl_family ncsi_genl_family __ro_after_init = { .n_small_ops = ARRAY_SIZE(ncsi_ops), }; -int ncsi_init_netlink(struct net_device *dev) +static int __init ncsi_init_netlink(void) { - int rc; - - rc = genl_register_family(&ncsi_genl_family); - if (rc) - netdev_err(dev, "ncsi: failed to register netlink family\n"); - - return rc; -} - -int ncsi_unregister_netlink(struct net_device *dev) -{ - int rc; - - rc = genl_unregister_family(&ncsi_genl_family); - if (rc) - netdev_err(dev, "ncsi: failed to unregister netlink family\n"); - - return rc; + return genl_register_family(&ncsi_genl_family); } +subsys_initcall(ncsi_init_netlink); diff --git a/net/ncsi/ncsi-netlink.h b/net/ncsi/ncsi-netlink.h index 7502723fba83..39a1a9d7bf77 100644 --- a/net/ncsi/ncsi-netlink.h +++ b/net/ncsi/ncsi-netlink.h @@ -22,7 +22,4 @@ int ncsi_send_netlink_err(struct net_device *dev, struct nlmsghdr *nlhdr, int err); -int ncsi_init_netlink(struct net_device *dev); -int ncsi_unregister_netlink(struct net_device *dev); - #endif /* __NCSI_NETLINK_H__ */ -- cgit v1.2.3 From e8aa6d520b448efc88670a98eccd196713639f2f Mon Sep 17 00:00:00 2001 From: Vincent Stehlé Date: Thu, 12 Nov 2020 09:48:33 +0100 Subject: net: ethernet: mtk-star-emac: return ok when xmit drops MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The ndo_start_xmit() method must return NETDEV_TX_OK if the DMA mapping fails, after freeing the socket buffer. Fix the mtk_star_netdev_start_xmit() function accordingly. Fixes: 8c7bd5a454ff ("net: ethernet: mtk-star-emac: new driver") Signed-off-by: Vincent Stehlé Acked-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20201112084833.21842-1-vincent.stehle@laposte.net Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mediatek/mtk_star_emac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index 13250553263b..e56a26f797f2 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -1053,7 +1053,7 @@ static int mtk_star_netdev_start_xmit(struct sk_buff *skb, err_drop_packet: dev_kfree_skb(skb); ndev->stats.tx_dropped++; - return NETDEV_TX_BUSY; + return NETDEV_TX_OK; } /* Returns the number of bytes sent or a negative number on the first -- cgit v1.2.3 From baee1991fad928d6c8dd5be3197ecb413c420c97 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Thu, 12 Nov 2020 19:34:39 +0800 Subject: net: ethernet: mtk-star-emac: fix error return code in mtk_star_enable() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 8c7bd5a454ff ("net: ethernet: mtk-star-emac: new driver") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Acked-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/1605180879-2573-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mediatek/mtk_star_emac.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index e56a26f797f2..a8641a407c06 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -966,6 +966,7 @@ static int mtk_star_enable(struct net_device *ndev) mtk_star_adjust_link, 0, priv->phy_intf); if (!priv->phydev) { netdev_err(ndev, "failed to connect to PHY\n"); + ret = -ENODEV; goto err_free_irq; } -- cgit v1.2.3 From 4ee18c179e5e815fa5575e0d2db0c05795a804ee Mon Sep 17 00:00:00 2001 From: Xie He Date: Thu, 12 Nov 2020 02:35:06 -0800 Subject: net: x25: Increase refcnt of "struct x25_neigh" in x25_rx_call_request The x25_disconnect function in x25_subr.c would decrease the refcount of "x25->neighbour" (struct x25_neigh) and reset this pointer to NULL. However, the x25_rx_call_request function in af_x25.c, which is called when we receive a connection request, does not increase the refcount when it assigns the pointer. Fix this issue by increasing the refcount of "struct x25_neigh" in x25_rx_call_request. This patch fixes frequent kernel crashes when using AF_X25 sockets. Fixes: 4becb7ee5b3d ("net/x25: Fix x25_neigh refcnt leak when x25 disconnect") Cc: Martin Schiller Signed-off-by: Xie He Link: https://lore.kernel.org/r/20201112103506.5875-1-xie.he.0141@gmail.com Signed-off-by: Jakub Kicinski --- net/x25/af_x25.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 046d3fee66a9..a10487e7574c 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1050,6 +1050,7 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, makex25->lci = lci; makex25->dest_addr = dest_addr; makex25->source_addr = source_addr; + x25_neigh_hold(nb); makex25->neighbour = nb; makex25->facilities = facilities; makex25->dte_facilities= dte_facilities; -- cgit v1.2.3 From 4ec2b69da5e1544dbadb30cddb49c8df60209b0c Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Thu, 12 Nov 2020 21:22:32 +0800 Subject: drm/i915/gvt: return error when failing to take the module reference When we fail to take the module reference, we go to the 'undo*' branch and return. But the returned variable 'ret' has been set as zero by the above code. Change 'ret' to '-ENODEV' in this situation. Fixes: 9bdb073464d6 ("drm/i915/gvt: Change KVMGT as self load module") Reviewed-by: Zhenyu Wang Reported-by: Hulk Robot Signed-off-by: Xiongfeng Wang Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/1605187352-51761-1-git-send-email-wangxiongfeng2@huawei.com --- drivers/gpu/drm/i915/gvt/kvmgt.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index ad8a9df49f29..778eb8cab610 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -829,8 +829,10 @@ static int intel_vgpu_open(struct mdev_device *mdev) /* Take a module reference as mdev core doesn't take * a reference for vendor driver. */ - if (!try_module_get(THIS_MODULE)) + if (!try_module_get(THIS_MODULE)) { + ret = -ENODEV; goto undo_group; + } ret = kvmgt_guest_init(mdev); if (ret) -- cgit v1.2.3 From 7bc40aedf24d31d8bea80e1161e996ef4299fb10 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 12 Nov 2020 11:22:04 +0100 Subject: mac80211: free sta in sta_info_insert_finish() on errors If sta_info_insert_finish() fails, we currently keep the station around and free it only in the caller, but there's only one such caller and it always frees it immediately. As syzbot found, another consequence of this split is that we can put things that sleep only into __cleanup_single_sta() and not in sta_info_free(), but this is the only place that requires such of sta_info_free() now. Change this to free the station in sta_info_insert_finish(), in which case we can still sleep. This will also let us unify the cleanup code later. Cc: stable@vger.kernel.org Fixes: dcd479e10a05 ("mac80211: always wind down STA state") Reported-by: syzbot+32c6c38c4812d22f2f0b@syzkaller.appspotmail.com Reported-by: syzbot+4c81fe92e372d26c4246@syzkaller.appspotmail.com Reported-by: syzbot+6a7fe9faf0d1d61bc24a@syzkaller.appspotmail.com Reported-by: syzbot+abed06851c5ffe010921@syzkaller.appspotmail.com Reported-by: syzbot+b7aeb9318541a1c709f1@syzkaller.appspotmail.com Reported-by: syzbot+d5a9416c6cafe53b5dd0@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/20201112112201.ee6b397b9453.I9c31d667a0ea2151441cc64ed6613d36c18a48e0@changeid Signed-off-by: Johannes Berg --- net/mac80211/sta_info.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 4fe284ff1ea3..ec6973ee88ef 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -705,7 +705,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) out_drop_sta: local->num_sta--; synchronize_net(); - __cleanup_single_sta(sta); + cleanup_single_sta(sta); out_err: mutex_unlock(&local->sta_mtx); kfree(sinfo); @@ -724,19 +724,13 @@ int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU) err = sta_info_insert_check(sta); if (err) { + sta_info_free(local, sta); mutex_unlock(&local->sta_mtx); rcu_read_lock(); - goto out_free; + return err; } - err = sta_info_insert_finish(sta); - if (err) - goto out_free; - - return 0; - out_free: - sta_info_free(local, sta); - return err; + return sta_info_insert_finish(sta); } int sta_info_insert(struct sta_info *sta) -- cgit v1.2.3 From a0ccbc5319d57b9efdc55c943a3fde30a0776502 Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Fri, 6 Nov 2020 15:20:38 +0800 Subject: ALSA: hda/realtek - Add supported mute Led for HP HP Pavilion x360 Convertible machine, it supported mute led. GPIO4 high will turn on led. The patch will enable control led via GPIO4 pin. Signed-off-by: Kailang Yang Cc: Link: https://lore.kernel.org/r/1ae4d98e92c147b780ace3911c4e1d73@realtek.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 69a952c9e011..371f6b865439 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4226,6 +4226,12 @@ static void alc286_fixup_hp_gpio_led(struct hda_codec *codec, alc_fixup_hp_gpio_led(codec, action, 0x02, 0x20); } +static void alc287_fixup_hp_gpio_led(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + alc_fixup_hp_gpio_led(codec, action, 0x10, 0); +} + /* turn on/off mic-mute LED per capture hook via VREF change */ static int vref_micmute_led_set(struct led_classdev *led_cdev, enum led_brightness brightness) @@ -6312,6 +6318,7 @@ enum { ALC274_FIXUP_HP_HEADSET_MIC, ALC256_FIXUP_ASUS_HPE, ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, + ALC287_FIXUP_HP_GPIO_LED, }; static const struct hda_fixup alc269_fixups[] = { @@ -7722,6 +7729,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_THINKPAD_ACPI }, + [ALC287_FIXUP_HP_GPIO_LED] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_hp_gpio_led, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7876,6 +7887,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8760, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), -- cgit v1.2.3 From 9e885770277d2ed8d85f9cbd4992515ec324242f Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Tue, 3 Nov 2020 15:30:51 +0800 Subject: ALSA: hda/realtek - HP Headset Mic can't detect after boot System boot or warm boot with plugged headset. If it turn on power save mode, Headset Mic will lose. This patch will solve this issue. Signed-off-by: Kailang Yang Cc: Link: https://lore.kernel.org/r/1ae4d98e92c147b780ace3911c4e1d73@realtek.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 371f6b865439..739dbaf54517 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6319,6 +6319,7 @@ enum { ALC256_FIXUP_ASUS_HPE, ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, ALC287_FIXUP_HP_GPIO_LED, + ALC256_FIXUP_HP_HEADSET_MIC, }; static const struct hda_fixup alc269_fixups[] = { @@ -7733,6 +7734,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc287_fixup_hp_gpio_led, }, + [ALC256_FIXUP_HP_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc274_fixup_hp_headset_mic, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8348,6 +8353,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x19, 0x02a11020}, {0x1a, 0x02a11030}, {0x21, 0x0221101f}), + SND_HDA_PIN_QUIRK(0x10ec0236, 0x103c, "HP", ALC256_FIXUP_HP_HEADSET_MIC, + {0x14, 0x90170110}, + {0x19, 0x02a11020}, + {0x21, 0x02211030}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, {0x14, 0x90170110}, {0x21, 0x02211020}), @@ -8450,6 +8459,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x1a, 0x90a70130}, {0x1b, 0x90170110}, {0x21, 0x03211020}), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x103c, "HP", ALC256_FIXUP_HP_HEADSET_MIC, + {0x14, 0x90170110}, + {0x19, 0x02a11020}, + {0x21, 0x0221101f}), SND_HDA_PIN_QUIRK(0x10ec0274, 0x103c, "HP", ALC274_FIXUP_HP_HEADSET_MIC, {0x17, 0x90170110}, {0x19, 0x03a11030}, -- cgit v1.2.3 From 95a793c3bc75cf888e0e641d656e7d080f487d8b Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Fri, 13 Nov 2020 18:20:43 +0900 Subject: ALSA: ctl: fix error path at adding user-defined element set When processing request to add/replace user-defined element set, check of given element identifier and decision of numeric identifier is done in "__snd_ctl_add_replace()" helper function. When the result of check is wrong, the helper function returns error code. The error code shall be returned to userspace application. Current implementation includes bug to return zero to userspace application regardless of the result. This commit fixes the bug. Cc: Fixes: e1a7bfe38079 ("ALSA: control: Fix race between adding and removing a user element") Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20201113092043.16148-1-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- sound/core/control.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/control.c b/sound/core/control.c index 4373de42a5a0..3b44378b9dec 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1539,7 +1539,7 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, unlock: up_write(&card->controls_rwsem); - return 0; + return err; } static int snd_ctl_elem_add_user(struct snd_ctl_file *file, -- cgit v1.2.3 From 53bf2776e31376f0b6a1fd7c9e1abc61241825a2 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 5 Nov 2020 22:47:02 +0100 Subject: ARM: dts: exynos: revert "add input clock to CMU in Exynos4412 Odroid" This reverts commit eaf2d2f6895d676dda6c95a652b58594f2887720. The commit eaf2d2f6895d ("ARM: dts: exynos: add input clock to CMU in Exynos4412 Odroid") breaks probing of usb3503 USB hub on Odroid U3. It changes the order of clock drivers probe: the clkout (Exynos PMU) driver is probed before the main clk-exynos4 driver. The clkout driver on Exynos4412 depends on clk-exynos4 but it does not support deferred probe, therefore this dependency and changed probe order causes probe failure. The usb3503 USB hub on Odroid U3 on the other hand requires clkout clock. This can be seen in logs: [ 5.007442] usb3503 0-0008: unable to request refclk (-517) Reported-by: Marek Szyprowski Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20200921174818.15525-1-krzk@kernel.org Signed-off-by: Arnd Bergmann --- arch/arm/boot/dts/exynos4412-odroid-common.dtsi | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi index ab291cec650a..2983e91bc7dd 100644 --- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi +++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi @@ -122,7 +122,6 @@ }; &clock { - clocks = <&clock CLK_XUSBXTI>; assigned-clocks = <&clock CLK_FOUT_EPLL>; assigned-clock-rates = <45158401>; }; -- cgit v1.2.3 From 106e6d8df4842d816dae23076c501ae48386afcb Mon Sep 17 00:00:00 2001 From: Shuming Fan Date: Fri, 13 Nov 2020 17:21:25 +0800 Subject: ASoC: rt1015: increase the time to detect BCLK To meet the most platform, the detection time should be increased to avoid that the flushing DAC data fails. Signed-off-by: Shuming Fan Link: https://lore.kernel.org/r/20201113092125.19206-1-shumingf@realtek.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt1015.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/rt1015.c b/sound/soc/codecs/rt1015.c index 967193518349..3db07293c70b 100644 --- a/sound/soc/codecs/rt1015.c +++ b/sound/soc/codecs/rt1015.c @@ -544,7 +544,7 @@ static void rt1015_flush_work(struct work_struct *work) struct rt1015_priv *rt1015 = container_of(work, struct rt1015_priv, flush_work.work); struct snd_soc_component *component = rt1015->component; - unsigned int val, i = 0, count = 20; + unsigned int val, i = 0, count = 200; while (i < count) { usleep_range(1000, 1500); -- cgit v1.2.3 From 57a6ad482af256b2a13de14194fb8f67c1a65f10 Mon Sep 17 00:00:00 2001 From: Michał Mirosław Date: Fri, 13 Nov 2020 01:20:27 +0100 Subject: regulator: fix memory leak with repeated set_machine_constraints() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixed commit introduced a possible second call to set_machine_constraints() and that allocates memory for rdev->constraints. Move the allocation to the caller so it's easier to manage and done once. Fixes: aea6cb99703e ("regulator: resolve supply after creating regulator") Cc: stable@vger.kernel.org Signed-off-by: Michał Mirosław Tested-by: Ahmad Fatoum # stpmic1 Link: https://lore.kernel.org/r/78c3d4016cebc08d441aad18cb924b4e4d9cf9df.1605226675.git.mirq-linux@rere.qmqm.pl Signed-off-by: Mark Brown --- drivers/regulator/core.c | 29 +++++++++++++---------------- 1 file changed, 13 insertions(+), 16 deletions(-) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 70168f2a53ed..84dd0aea97c5 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1315,7 +1315,6 @@ static int _regulator_do_enable(struct regulator_dev *rdev); /** * set_machine_constraints - sets regulator constraints * @rdev: regulator source - * @constraints: constraints to apply * * Allows platform initialisation code to define and constrain * regulator circuits e.g. valid voltage/current ranges, etc. NOTE: @@ -1323,21 +1322,11 @@ static int _regulator_do_enable(struct regulator_dev *rdev); * regulator operations to proceed i.e. set_voltage, set_current_limit, * set_mode. */ -static int set_machine_constraints(struct regulator_dev *rdev, - const struct regulation_constraints *constraints) +static int set_machine_constraints(struct regulator_dev *rdev) { int ret = 0; const struct regulator_ops *ops = rdev->desc->ops; - if (constraints) - rdev->constraints = kmemdup(constraints, sizeof(*constraints), - GFP_KERNEL); - else - rdev->constraints = kzalloc(sizeof(*constraints), - GFP_KERNEL); - if (!rdev->constraints) - return -ENOMEM; - ret = machine_constraints_voltage(rdev, rdev->constraints); if (ret != 0) return ret; @@ -5146,7 +5135,6 @@ struct regulator_dev * regulator_register(const struct regulator_desc *regulator_desc, const struct regulator_config *cfg) { - const struct regulation_constraints *constraints = NULL; const struct regulator_init_data *init_data; struct regulator_config *config = NULL; static atomic_t regulator_no = ATOMIC_INIT(-1); @@ -5285,14 +5273,23 @@ regulator_register(const struct regulator_desc *regulator_desc, /* set regulator constraints */ if (init_data) - constraints = &init_data->constraints; + rdev->constraints = kmemdup(&init_data->constraints, + sizeof(*rdev->constraints), + GFP_KERNEL); + else + rdev->constraints = kzalloc(sizeof(*rdev->constraints), + GFP_KERNEL); + if (!rdev->constraints) { + ret = -ENOMEM; + goto wash; + } if (init_data && init_data->supply_regulator) rdev->supply_name = init_data->supply_regulator; else if (regulator_desc->supply_name) rdev->supply_name = regulator_desc->supply_name; - ret = set_machine_constraints(rdev, constraints); + ret = set_machine_constraints(rdev); if (ret == -EPROBE_DEFER) { /* Regulator might be in bypass mode and so needs its supply * to set the constraints */ @@ -5301,7 +5298,7 @@ regulator_register(const struct regulator_desc *regulator_desc, * that is just being created */ ret = regulator_resolve_supply(rdev); if (!ret) - ret = set_machine_constraints(rdev, constraints); + ret = set_machine_constraints(rdev); else rdev_dbg(rdev, "unable to resolve supply early: %pe\n", ERR_PTR(ret)); -- cgit v1.2.3 From 4b639e254d3d4f15ee4ff2b890a447204cfbeea9 Mon Sep 17 00:00:00 2001 From: Michał Mirosław Date: Fri, 13 Nov 2020 01:20:28 +0100 Subject: regulator: avoid resolve_supply() infinite recursion MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When a regulator's name equals its supply's name the regulator_resolve_supply() recurses indefinitely. Add a check so that debugging the problem is easier. The "fixed" commit just exposed the problem. Fixes: aea6cb99703e ("regulator: resolve supply after creating regulator") Cc: stable@vger.kernel.org Reported-by: Ahmad Fatoum Signed-off-by: Michał Mirosław Tested-by: Ahmad Fatoum # stpmic1 Link: https://lore.kernel.org/r/c6171057cfc0896f950c4d8cb82df0f9f1b89ad9.1605226675.git.mirq-linux@rere.qmqm.pl Signed-off-by: Mark Brown --- drivers/regulator/core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 84dd0aea97c5..d3b96efa20fd 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1841,6 +1841,12 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) } } + if (r == rdev) { + dev_err(dev, "Supply for %s (%s) resolved to itself\n", + rdev->desc->name, rdev->supply_name); + return -EINVAL; + } + /* * If the supply's parent device is not the same as the * regulator's parent device, then ensure the parent device -- cgit v1.2.3 From f5c042b23f7429e5c2ac987b01a31c69059a978b Mon Sep 17 00:00:00 2001 From: Michał Mirosław Date: Fri, 13 Nov 2020 01:20:28 +0100 Subject: regulator: workaround self-referent regulators MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Workaround regulators whose supply name happens to be the same as its own name. This fixes boards that used to work before the early supply resolving was removed. The error message is left in place so that offending drivers can be detected. Fixes: aea6cb99703e ("regulator: resolve supply after creating regulator") Cc: stable@vger.kernel.org Reported-by: Ahmad Fatoum Signed-off-by: Michał Mirosław Tested-by: Ahmad Fatoum # stpmic1 Link: https://lore.kernel.org/r/d703acde2a93100c3c7a81059d716c50ad1b1f52.1605226675.git.mirq-linux@rere.qmqm.pl Signed-off-by: Mark Brown --- drivers/regulator/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index d3b96efa20fd..42bbd99a36ac 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1844,7 +1844,10 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) if (r == rdev) { dev_err(dev, "Supply for %s (%s) resolved to itself\n", rdev->desc->name, rdev->supply_name); - return -EINVAL; + if (!have_full_constraints()) + return -EINVAL; + r = dummy_regulator_rdev; + get_device(&r->dev); } /* -- cgit v1.2.3 From 50431b45685b600fc2851a3f2b53e24643efe6d3 Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Fri, 13 Nov 2020 19:51:52 +0800 Subject: tools, bpftool: Add missing close before bpftool net attach exit progfd is created by prog_parse_fd() in do_attach() and before the latter returns in case of success, the file descriptor should be closed. Fixes: 04949ccc273e ("tools: bpftool: add net attach command to attach XDP on interface") Signed-off-by: Wang Hai Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20201113115152.53178-1-wanghai38@huawei.com --- tools/bpf/bpftool/net.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 910e7bac6e9e..3fae61ef6339 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -578,8 +578,8 @@ static int do_attach(int argc, char **argv) ifindex = net_parse_dev(&argc, &argv); if (ifindex < 1) { - close(progfd); - return -EINVAL; + err = -EINVAL; + goto cleanup; } if (argc) { @@ -587,8 +587,8 @@ static int do_attach(int argc, char **argv) overwrite = true; } else { p_err("expected 'overwrite', got: '%s'?", *argv); - close(progfd); - return -EINVAL; + err = -EINVAL; + goto cleanup; } } @@ -596,17 +596,17 @@ static int do_attach(int argc, char **argv) if (is_prefix("xdp", attach_type_strings[attach_type])) err = do_attach_detach_xdp(progfd, attach_type, ifindex, overwrite); - - if (err < 0) { + if (err) { p_err("interface %s attach failed: %s", attach_type_strings[attach_type], strerror(-err)); - return err; + goto cleanup; } if (json_output) jsonw_null(json_wtr); - - return 0; +cleanup: + close(progfd); + return err; } static int do_detach(int argc, char **argv) -- cgit v1.2.3 From 18db36a073db6377a52e22ec44eb0500f0a0ecc6 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Fri, 6 Nov 2020 18:50:16 +0100 Subject: docs: ABI: testing: iio: stm32: remove re-introduced unsupported ABI Remove unsupported ABI that has been re-introduced due to a rebase hunk. This ABI has been moved in the past in commit b299d00420e2 ("IIO: stm32: Remove quadrature related functions from trigger driver") This also fixes a couple of warnings seen with: ./scripts/get_abi.pl validate 2>&1|grep iio Fixes: 34433332841d ("docs: ABI: testing: make the files compatible with ReST output") Acked-by: Jonathan Cameron Signed-off-by: Fabrice Gasnier Link: https://lore.kernel.org/r/1604685016-2434-1-git-send-email-fabrice.gasnier@st.com Signed-off-by: Greg Kroah-Hartman --- .../ABI/testing/sysfs-bus-iio-timer-stm32 | 24 ---------------------- 1 file changed, 24 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 b/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 index a10a4de3e5fe..c4a4497c249a 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 +++ b/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 @@ -109,30 +109,6 @@ Description: When counting down the counter start from preset value and fire event when reach 0. -What: /sys/bus/iio/devices/iio:deviceX/in_count_quadrature_mode_available -KernelVersion: 4.12 -Contact: benjamin.gaignard@st.com -Description: - Reading returns the list possible quadrature modes. - -What: /sys/bus/iio/devices/iio:deviceX/in_count0_quadrature_mode -KernelVersion: 4.12 -Contact: benjamin.gaignard@st.com -Description: - Configure the device counter quadrature modes: - - channel_A: - Encoder A input servers as the count input and B as - the UP/DOWN direction control input. - - channel_B: - Encoder B input serves as the count input and A as - the UP/DOWN direction control input. - - quadrature: - Encoder A and B inputs are mixed to get direction - and count with a scale of 0.25. - What: /sys/bus/iio/devices/iio:deviceX/in_count_enable_mode_available KernelVersion: 4.12 Contact: benjamin.gaignard@st.com -- cgit v1.2.3 From dabbd6abcdbeb1358a53ec28a244429320eb0e3a Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Fri, 13 Nov 2020 14:42:27 +0800 Subject: IB/hfi1: Fix error return code in hfi1_init_dd() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 4730f4a6c6b2 ("IB/hfi1: Activate the dummy netdev") Link: https://lore.kernel.org/r/1605249747-17942-1-git-send-email-zhangchangzhong@huawei.com Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Acked-by: Mike Marciniszyn Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hfi1/chip.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 7eaf99538216..c87b94ea2939 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -15245,7 +15245,8 @@ int hfi1_init_dd(struct hfi1_devdata *dd) & CCE_REVISION_SW_MASK); /* alloc netdev data */ - if (hfi1_netdev_alloc(dd)) + ret = hfi1_netdev_alloc(dd); + if (ret) goto bail_cleanup; ret = set_up_context_variables(dd); -- cgit v1.2.3 From 02a9c6ee4183af2e438454c55098b828a96085fb Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 13 Nov 2020 13:12:41 +0300 Subject: ALSA: firewire: Clean up a locking issue in copy_resp_to_buf() The spin_lock/unlock_irq() functions cannot be nested. The problem is that presumably we would want the IRQs to be re-enabled on the second call the spin_unlock_irq() but instead it will be enabled at the first call so IRQs will be enabled earlier than expected. In this situation the copy_resp_to_buf() function is only called from one function and it is called with IRQs disabled. We can just use the regular spin_lock/unlock() functions. Fixes: 555e8a8f7f14 ("ALSA: fireworks: Add command/response functionality into hwdep interface") Signed-off-by: Dan Carpenter Acked-by: Takashi Sakamoto Cc: Link: https://lore.kernel.org/r/20201113101241.GB168908@mwanda Signed-off-by: Takashi Iwai --- sound/firewire/fireworks/fireworks_transaction.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/firewire/fireworks/fireworks_transaction.c b/sound/firewire/fireworks/fireworks_transaction.c index 0f533f5bd960..9f8c53b39f95 100644 --- a/sound/firewire/fireworks/fireworks_transaction.c +++ b/sound/firewire/fireworks/fireworks_transaction.c @@ -123,7 +123,7 @@ copy_resp_to_buf(struct snd_efw *efw, void *data, size_t length, int *rcode) t = (struct snd_efw_transaction *)data; length = min_t(size_t, be32_to_cpu(t->length) * sizeof(u32), length); - spin_lock_irq(&efw->lock); + spin_lock(&efw->lock); if (efw->push_ptr < efw->pull_ptr) capacity = (unsigned int)(efw->pull_ptr - efw->push_ptr); @@ -190,7 +190,7 @@ handle_resp_for_user(struct fw_card *card, int generation, int source, copy_resp_to_buf(efw, data, length, rcode); end: - spin_unlock_irq(&instances_lock); + spin_unlock(&instances_lock); } static void -- cgit v1.2.3 From d853b3406903a7dc5b14eb5bada3e8cd677f66a2 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 13 Nov 2020 11:07:02 -0700 Subject: spi: bcm2835aux: Restore err assignment in bcm2835aux_spi_probe Clang warns: drivers/spi/spi-bcm2835aux.c:532:50: warning: variable 'err' is uninitialized when used here [-Wuninitialized] dev_err(&pdev->dev, "could not get clk: %d\n", err); ^~~ ./include/linux/dev_printk.h:112:32: note: expanded from macro 'dev_err' _dev_err(dev, dev_fmt(fmt), ##__VA_ARGS__) ^~~~~~~~~~~ drivers/spi/spi-bcm2835aux.c:495:9: note: initialize the variable 'err' to silence this warning int err; ^ = 0 1 warning generated. Restore the assignment so that the error value can be used in the dev_err statement and there is no uninitialized memory being leaked. Fixes: e13ee6cc4781 ("spi: bcm2835aux: Fix use-after-free on unbind") Link: https://github.com/ClangBuiltLinux/linux/issues/1199 Signed-off-by: Nathan Chancellor Link: https://lore.kernel.org/r/20201113180701.455541-1-natechancellor@gmail.com Signed-off-by: Mark Brown --- drivers/spi/spi-bcm2835aux.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c index fd58547110e6..1a26865c42f8 100644 --- a/drivers/spi/spi-bcm2835aux.c +++ b/drivers/spi/spi-bcm2835aux.c @@ -529,8 +529,9 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev) bs->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(bs->clk)) { + err = PTR_ERR(bs->clk); dev_err(&pdev->dev, "could not get clk: %d\n", err); - return PTR_ERR(bs->clk); + return err; } bs->irq = platform_get_irq(pdev, 0); -- cgit v1.2.3 From 123f01a0c989905a1cef6c1397a022eb321474d8 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 13 Nov 2020 21:38:35 +0100 Subject: drm/tegra: output: Do not put OF node twice The original patch for commit 3d2e7aec7013 ("drm/tegra: output: Don't leak OF node on error") contained this hunk, but it was accidentally dropped during conflict resolution. This causes use-after-free errors on devices that use an I2C controller for HDMI DDC/CI on Tegra210 and later. Fixes: 3d2e7aec7013 ("drm/tegra: output: Don't leak OF node on error") Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/output.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c index 5a4fd0dbf4cf..47d26b5d9945 100644 --- a/drivers/gpu/drm/tegra/output.c +++ b/drivers/gpu/drm/tegra/output.c @@ -129,7 +129,6 @@ int tegra_output_probe(struct tegra_output *output) if (!output->ddc) { err = -EPROBE_DEFER; - of_node_put(ddc); return err; } } -- cgit v1.2.3 From c334730988ee07908ba4eb816ce78d3fe06fecaa Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 4 Nov 2020 11:07:31 +0000 Subject: btrfs: fix missing delalloc new bit for new delalloc ranges When doing a buffered write, through one of the write family syscalls, we look for ranges which currently don't have allocated extents and set the 'delalloc new' bit on them, so that we can report a correct number of used blocks to the stat(2) syscall until delalloc is flushed and ordered extents complete. However there are a few other places where we can do a buffered write against a range that is mapped to a hole (no extent allocated) and where we do not set the 'new delalloc' bit. Those places are: - Doing a memory mapped write against a hole; - Cloning an inline extent into a hole starting at file offset 0; - Calling btrfs_cont_expand() when the i_size of the file is not aligned to the sector size and is located in a hole. For example when cloning to a destination offset beyond EOF. So after such cases, until the corresponding delalloc range is flushed and the respective ordered extents complete, we can report an incorrect number of blocks used through the stat(2) syscall. In some cases we can end up reporting 0 used blocks to stat(2), which is a particular bad value to report as it may mislead tools to think a file is completely sparse when its i_size is not zero, making them skip reading any data, an undesired consequence for tools such as archivers and other backup tools, as reported a long time ago in the following thread (and other past threads): https://lists.gnu.org/archive/html/bug-tar/2016-07/msg00001.html Example reproducer: $ cat reproducer.sh #!/bin/bash MNT=/mnt/sdi DEV=/dev/sdi mkfs.btrfs -f $DEV > /dev/null # mkfs.xfs -f $DEV > /dev/null # mkfs.ext4 -F $DEV > /dev/null # mkfs.f2fs -f $DEV > /dev/null mount $DEV $MNT xfs_io -f -c "truncate 64K" \ -c "mmap -w 0 64K" \ -c "mwrite -S 0xab 0 64K" \ -c "munmap" \ $MNT/foo blocks_used=$(stat -c %b $MNT/foo) echo "blocks used: $blocks_used" if [ $blocks_used -eq 0 ]; then echo "ERROR: blocks used is 0" fi umount $DEV $ ./reproducer.sh blocks used: 0 ERROR: blocks used is 0 So move the logic that decides to set the 'delalloc bit' bit into the function btrfs_set_extent_delalloc(), since that is what we use for all those missing cases as well as for the cases that currently work well. This change is also preparatory work for an upcoming patch that fixes other problems related to tracking and reporting the number of bytes used by an inode. CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/file.c | 57 ------------------------------------------- fs/btrfs/inode.c | 58 ++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/tests/inode-tests.c | 12 ++++++--- 3 files changed, 66 insertions(+), 61 deletions(-) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 87355a38a654..4373da7bcc0d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -452,46 +452,6 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) } } -static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, - const u64 start, - const u64 len, - struct extent_state **cached_state) -{ - u64 search_start = start; - const u64 end = start + len - 1; - - while (search_start < end) { - const u64 search_len = end - search_start + 1; - struct extent_map *em; - u64 em_len; - int ret = 0; - - em = btrfs_get_extent(inode, NULL, 0, search_start, search_len); - if (IS_ERR(em)) - return PTR_ERR(em); - - if (em->block_start != EXTENT_MAP_HOLE) - goto next; - - em_len = em->len; - if (em->start < search_start) - em_len -= search_start - em->start; - if (em_len > search_len) - em_len = search_len; - - ret = set_extent_bit(&inode->io_tree, search_start, - search_start + em_len - 1, - EXTENT_DELALLOC_NEW, - NULL, cached_state, GFP_NOFS); -next: - search_start = extent_map_end(em); - free_extent_map(em); - if (ret) - return ret; - } - return 0; -} - /* * after copy_from_user, pages need to be dirtied and we need to make * sure holes are created between the current EOF and the start of @@ -528,23 +488,6 @@ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, cached); - if (!btrfs_is_free_space_inode(inode)) { - if (start_pos >= isize && - !(inode->flags & BTRFS_INODE_PREALLOC)) { - /* - * There can't be any extents following eof in this case - * so just set the delalloc new bit for the range - * directly. - */ - extra_bits |= EXTENT_DELALLOC_NEW; - } else { - err = btrfs_find_new_delalloc_bytes(inode, start_pos, - num_bytes, cached); - if (err) - return err; - } - } - err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block, extra_bits, cached); if (err) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index da58c58ef9aa..7e8d8169779d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2253,11 +2253,69 @@ static int add_pending_csums(struct btrfs_trans_handle *trans, return 0; } +static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, + const u64 start, + const u64 len, + struct extent_state **cached_state) +{ + u64 search_start = start; + const u64 end = start + len - 1; + + while (search_start < end) { + const u64 search_len = end - search_start + 1; + struct extent_map *em; + u64 em_len; + int ret = 0; + + em = btrfs_get_extent(inode, NULL, 0, search_start, search_len); + if (IS_ERR(em)) + return PTR_ERR(em); + + if (em->block_start != EXTENT_MAP_HOLE) + goto next; + + em_len = em->len; + if (em->start < search_start) + em_len -= search_start - em->start; + if (em_len > search_len) + em_len = search_len; + + ret = set_extent_bit(&inode->io_tree, search_start, + search_start + em_len - 1, + EXTENT_DELALLOC_NEW, + NULL, cached_state, GFP_NOFS); +next: + search_start = extent_map_end(em); + free_extent_map(em); + if (ret) + return ret; + } + return 0; +} + int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state) { WARN_ON(PAGE_ALIGNED(end)); + + if (start >= i_size_read(&inode->vfs_inode) && + !(inode->flags & BTRFS_INODE_PREALLOC)) { + /* + * There can't be any extents following eof in this case so just + * set the delalloc new bit for the range directly. + */ + extra_bits |= EXTENT_DELALLOC_NEW; + } else { + int ret; + + ret = btrfs_find_new_delalloc_bytes(inode, start, + end + 1 - start, + cached_state); + if (ret) + return ret; + } + return set_extent_delalloc(&inode->io_tree, start, end, extra_bits, cached_state); } diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index e6719f7db386..04022069761d 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -983,7 +983,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, BTRFS_MAX_EXTENT_SIZE >> 1, (BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1050,7 +1051,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, BTRFS_MAX_EXTENT_SIZE + sectorsize, BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1082,7 +1084,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) /* Empty */ ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1097,7 +1100,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) out: if (ret) clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); iput(inode); btrfs_free_dummy_root(root); btrfs_free_dummy_fs_info(fs_info); -- cgit v1.2.3 From 6f23277a49e68f8a9355385c846939ad0b1261e7 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 11 Nov 2020 19:38:18 +0800 Subject: btrfs: qgroup: don't commit transaction when we already hold the handle [BUG] When running the following script, btrfs will trigger an ASSERT(): #/bin/bash mkfs.btrfs -f $dev mount $dev $mnt xfs_io -f -c "pwrite 0 1G" $mnt/file sync btrfs quota enable $mnt btrfs quota rescan -w $mnt # Manually set the limit below current usage btrfs qgroup limit 512M $mnt $mnt # Crash happens touch $mnt/file The dmesg looks like this: assertion failed: refcount_read(&trans->use_count) == 1, in fs/btrfs/transaction.c:2022 ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3230! invalid opcode: 0000 [#1] SMP PTI RIP: 0010:assertfail.constprop.0+0x18/0x1a [btrfs] btrfs_commit_transaction.cold+0x11/0x5d [btrfs] try_flush_qgroup+0x67/0x100 [btrfs] __btrfs_qgroup_reserve_meta+0x3a/0x60 [btrfs] btrfs_delayed_update_inode+0xaa/0x350 [btrfs] btrfs_update_inode+0x9d/0x110 [btrfs] btrfs_dirty_inode+0x5d/0xd0 [btrfs] touch_atime+0xb5/0x100 iterate_dir+0xf1/0x1b0 __x64_sys_getdents64+0x78/0x110 do_syscall_64+0x33/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fb5afe588db [CAUSE] In try_flush_qgroup(), we assume we don't hold a transaction handle at all. This is true for data reservation and mostly true for metadata. Since data space reservation always happens before we start a transaction, and for most metadata operation we reserve space in start_transaction(). But there is an exception, btrfs_delayed_inode_reserve_metadata(). It holds a transaction handle, while still trying to reserve extra metadata space. When we hit EDQUOT inside btrfs_delayed_inode_reserve_metadata(), we will join current transaction and commit, while we still have transaction handle from qgroup code. [FIX] Let's check current->journal before we join the transaction. If current->journal is unset or BTRFS_SEND_TRANS_STUB, it means we are not holding a transaction, thus are able to join and then commit transaction. If current->journal is a valid transaction handle, we avoid committing transaction and just end it This is less effective than committing current transaction, as it won't free metadata reserved space, but we may still free some data space before new data writes. Bugzilla: https://bugzilla.suse.com/show_bug.cgi?id=1178634 Fixes: c53e9653605d ("btrfs: qgroup: try to flush qgroup space when we get -EDQUOT") Reviewed-by: Filipe Manana Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/qgroup.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 77c54749f432..4621b8043021 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3512,6 +3512,7 @@ static int try_flush_qgroup(struct btrfs_root *root) { struct btrfs_trans_handle *trans; int ret; + bool can_commit = true; /* * We don't want to run flush again and again, so if there is a running @@ -3523,6 +3524,20 @@ static int try_flush_qgroup(struct btrfs_root *root) return 0; } + /* + * If current process holds a transaction, we shouldn't flush, as we + * assume all space reservation happens before a transaction handle is + * held. + * + * But there are cases like btrfs_delayed_item_reserve_metadata() where + * we try to reserve space with one transction handle already held. + * In that case we can't commit transaction, but at least try to end it + * and hope the started data writes can free some space. + */ + if (current->journal_info && + current->journal_info != BTRFS_SEND_TRANS_STUB) + can_commit = false; + ret = btrfs_start_delalloc_snapshot(root); if (ret < 0) goto out; @@ -3534,7 +3549,10 @@ static int try_flush_qgroup(struct btrfs_root *root) goto out; } - ret = btrfs_commit_transaction(trans); + if (can_commit) + ret = btrfs_commit_transaction(trans); + else + ret = btrfs_end_transaction(trans); out: clear_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state); wake_up(&root->qgroup_flush_wait); -- cgit v1.2.3 From 1a49a97df657c63a4e8ffcd1ea9b6ed95581789b Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Thu, 12 Nov 2020 17:55:06 -0800 Subject: btrfs: tree-checker: add missing return after error in root_item There's a missing return statement after an error is found in the root_item, this can cause further problems when a crafted image triggers the error. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=210181 Fixes: 259ee7754b67 ("btrfs: tree-checker: Add ROOT_ITEM check") CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Qu Wenruo Signed-off-by: Daniel Xu Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/tree-checker.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 8784b74f5232..6cefabd27209 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1068,6 +1068,7 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key, "invalid root item size, have %u expect %zu or %u", btrfs_item_size_nr(leaf, slot), sizeof(ri), btrfs_legacy_root_item_size()); + return -EUCLEAN; } /* -- cgit v1.2.3 From 9f16a66733c90b5f33f624b0b0e36a345b0aaf93 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 13 Nov 2020 21:44:48 +0800 Subject: block: mark flush request as IDLE when it is really finished For avoiding use-after-free on flush request, we call its .end_io() from both timeout code path and __blk_mq_end_request(). When flush request's ref doesn't drop to zero, it is still used, we can't mark it as IDLE, so fix it by marking IDLE when its refcount drops to zero really. Fixes: 65ff5cd04551 ("blk-mq: mark flush request as IDLE in flush_end_io()") Signed-off-by: Ming Lei Cc: Yi Zhang Signed-off-by: Jens Axboe --- block/blk-flush.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/block/blk-flush.c b/block/blk-flush.c index e32958f0b687..fd5cee9f1a3b 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -225,13 +225,18 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) /* release the tag's ownership to the req cloned from */ spin_lock_irqsave(&fq->mq_flush_lock, flags); - WRITE_ONCE(flush_rq->state, MQ_RQ_IDLE); if (!refcount_dec_and_test(&flush_rq->ref)) { fq->rq_status = error; spin_unlock_irqrestore(&fq->mq_flush_lock, flags); return; } + /* + * Flush request has to be marked as IDLE when it is really ended + * because its .end_io() is called from timeout code path too for + * avoiding use-after-free. + */ + WRITE_ONCE(flush_rq->state, MQ_RQ_IDLE); if (fq->rq_status != BLK_STS_OK) error = fq->rq_status; -- cgit v1.2.3 From 2b5668733050fca85f0ab458c5b91732f9496a38 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Thu, 12 Nov 2020 13:15:46 +0200 Subject: net: ethernet: ti: cpsw: fix cpts irq after suspend Depending on the SoC/platform the CPSW can completely lose context after a suspend/resume cycle, including CPSW wrapper (WR) which will cause reset of WR_C0_MISC_EN register, so CPTS IRQ will became disabled. Fix it by moving CPTS IRQ enabling in cpsw_ndo_open() where CPTS is actually started. Fixes: 84ea9c0a95d7 ("net: ethernet: ti: cpsw: enable cpts irq") Reported-by: Tony Lindgren Signed-off-by: Grygorii Strashko Tested-by: Tony Lindgren Link: https://lore.kernel.org/r/20201112111546.20343-1-grygorii.strashko@ti.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/cpsw.c | 10 ++++++---- drivers/net/ethernet/ti/cpsw_new.c | 9 ++++++--- 2 files changed, 12 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 9fd1f77190ad..fa2d1025cbb2 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -838,9 +838,12 @@ static int cpsw_ndo_open(struct net_device *ndev) if (ret < 0) goto err_cleanup; - if (cpts_register(cpsw->cpts)) - dev_err(priv->dev, "error registering cpts device\n"); - + if (cpsw->cpts) { + if (cpts_register(cpsw->cpts)) + dev_err(priv->dev, "error registering cpts device\n"); + else + writel(0x10, &cpsw->wr_regs->misc_en); + } } cpsw_restore(priv); @@ -1716,7 +1719,6 @@ static int cpsw_probe(struct platform_device *pdev) /* Enable misc CPTS evnt_pend IRQ */ cpts_set_irqpoll(cpsw->cpts, false); - writel(0x10, &cpsw->wr_regs->misc_en); skip_cpts: cpsw_notice(priv, probe, diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index f779d2e1b5c5..2f5e0ad23ad7 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -873,8 +873,12 @@ static int cpsw_ndo_open(struct net_device *ndev) if (ret < 0) goto err_cleanup; - if (cpts_register(cpsw->cpts)) - dev_err(priv->dev, "error registering cpts device\n"); + if (cpsw->cpts) { + if (cpts_register(cpsw->cpts)) + dev_err(priv->dev, "error registering cpts device\n"); + else + writel(0x10, &cpsw->wr_regs->misc_en); + } napi_enable(&cpsw->napi_rx); napi_enable(&cpsw->napi_tx); @@ -2006,7 +2010,6 @@ static int cpsw_probe(struct platform_device *pdev) /* Enable misc CPTS evnt_pend IRQ */ cpts_set_irqpoll(cpsw->cpts, false); - writel(0x10, &cpsw->wr_regs->misc_en); skip_cpts: ret = cpsw_register_notifiers(cpsw); -- cgit v1.2.3 From 8cf8821e15cd553339a5b48ee555a0439c2b2742 Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Thu, 12 Nov 2020 20:58:15 -0500 Subject: net: Exempt multicast addresses from five-second neighbor lifetime Commit 58956317c8de ("neighbor: Improve garbage collection") guarantees neighbour table entries a five-second lifetime. Processes which make heavy use of multicast can fill the neighour table with multicast addresses in five seconds. At that point, neighbour entries can't be GC-ed because they aren't five seconds old yet, the kernel log starts to fill up with "neighbor table overflow!" messages, and sends start to fail. This patch allows multicast addresses to be thrown out before they've lived out their five seconds. This makes room for non-multicast addresses and makes messages to all addresses more reliable in these circumstances. Fixes: 58956317c8de ("neighbor: Improve garbage collection") Signed-off-by: Jeff Dike Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20201113015815.31397-1-jdike@akamai.com Signed-off-by: Jakub Kicinski --- include/net/neighbour.h | 1 + net/core/neighbour.c | 2 ++ net/ipv4/arp.c | 6 ++++++ net/ipv6/ndisc.c | 7 +++++++ 4 files changed, 16 insertions(+) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 81ee17594c32..22ced1381ede 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -204,6 +204,7 @@ struct neigh_table { int (*pconstructor)(struct pneigh_entry *); void (*pdestructor)(struct pneigh_entry *); void (*proxy_redo)(struct sk_buff *skb); + int (*is_multicast)(const void *pkey); bool (*allow_add)(const struct net_device *dev, struct netlink_ext_ack *extack); char *id; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8e39e28b0a8d..9500d28a43b0 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -235,6 +235,8 @@ static int neigh_forced_gc(struct neigh_table *tbl) write_lock(&n->lock); if ((n->nud_state == NUD_FAILED) || + (tbl->is_multicast && + tbl->is_multicast(n->primary_key)) || time_after(tref, n->updated)) remove = true; write_unlock(&n->lock); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 687971d83b4e..922dd73e5740 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -125,6 +125,7 @@ static int arp_constructor(struct neighbour *neigh); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb); static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb); static void parp_redo(struct sk_buff *skb); +static int arp_is_multicast(const void *pkey); static const struct neigh_ops arp_generic_ops = { .family = AF_INET, @@ -156,6 +157,7 @@ struct neigh_table arp_tbl = { .key_eq = arp_key_eq, .constructor = arp_constructor, .proxy_redo = parp_redo, + .is_multicast = arp_is_multicast, .id = "arp_cache", .parms = { .tbl = &arp_tbl, @@ -928,6 +930,10 @@ static void parp_redo(struct sk_buff *skb) arp_process(dev_net(skb->dev), NULL, skb); } +static int arp_is_multicast(const void *pkey) +{ + return ipv4_is_multicast(*((__be32 *)pkey)); +} /* * Receive an arp request from the device layer. diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 27f29b957ee7..76717478f173 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -81,6 +81,7 @@ static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); static int pndisc_constructor(struct pneigh_entry *n); static void pndisc_destructor(struct pneigh_entry *n); static void pndisc_redo(struct sk_buff *skb); +static int ndisc_is_multicast(const void *pkey); static const struct neigh_ops ndisc_generic_ops = { .family = AF_INET6, @@ -115,6 +116,7 @@ struct neigh_table nd_tbl = { .pconstructor = pndisc_constructor, .pdestructor = pndisc_destructor, .proxy_redo = pndisc_redo, + .is_multicast = ndisc_is_multicast, .allow_add = ndisc_allow_add, .id = "ndisc_cache", .parms = { @@ -1706,6 +1708,11 @@ static void pndisc_redo(struct sk_buff *skb) kfree_skb(skb); } +static int ndisc_is_multicast(const void *pkey) +{ + return ipv6_addr_is_multicast((struct in6_addr *)pkey); +} + static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); -- cgit v1.2.3 From aa6306a8481e0223f3783d24045daea80897238e Mon Sep 17 00:00:00 2001 From: Steen Hegelund Date: Fri, 13 Nov 2020 10:11:16 +0100 Subject: net: phy: mscc: remove non-MACSec compatible phy Selecting VSC8575 as a MACSec PHY was not correct The relevant datasheet can be found here: - VSC8575: https://www.microchip.com/wwwproducts/en/VSC8575 History: v1 -> v2: - Corrected the sha in the "Fixes:" tag Fixes: 1bbe0ecc2a1a ("net: phy: mscc: macsec initialization") Signed-off-by: Steen Hegelund Reviewed-by: Antoine Tenart Link: https://lore.kernel.org/r/20201113091116.1102450-1-steen.hegelund@microchip.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/mscc/mscc_macsec.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/phy/mscc/mscc_macsec.c b/drivers/net/phy/mscc/mscc_macsec.c index 6cf9b798b710..10be266e48e8 100644 --- a/drivers/net/phy/mscc/mscc_macsec.c +++ b/drivers/net/phy/mscc/mscc_macsec.c @@ -981,7 +981,6 @@ int vsc8584_macsec_init(struct phy_device *phydev) switch (phydev->phy_id & phydev->drv->phy_id_mask) { case PHY_ID_VSC856X: - case PHY_ID_VSC8575: case PHY_ID_VSC8582: case PHY_ID_VSC8584: INIT_LIST_HEAD(&vsc8531->macsec_flows); -- cgit v1.2.3 From 8c07205aea36ccebe9fc5f97287a8bc416cea197 Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Fri, 13 Nov 2020 19:32:36 +0800 Subject: net: marvell: prestera: fix error return code in prestera_pci_probe() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 4c2703dfd7fa ("net: marvell: prestera: Add PCI interface support") Reported-by: Hulk Robot Signed-off-by: Wang Hai Reviewed-by: Vadym Kochan Acked-by: Vadym Kochan Link: https://lore.kernel.org/r/20201113113236.71678-1-wanghai38@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/prestera/prestera_pci.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index 1b97adae542e..be5677623455 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -676,7 +676,8 @@ static int prestera_pci_probe(struct pci_dev *pdev, if (err) return err; - if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(30))) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(30)); + if (err) { dev_err(&pdev->dev, "fail to set DMA mask\n"); goto err_dma_mask; } @@ -702,8 +703,10 @@ static int prestera_pci_probe(struct pci_dev *pdev, dev_info(fw->dev.dev, "Prestera FW is ready\n"); fw->wq = alloc_workqueue("prestera_fw_wq", WQ_HIGHPRI, 1); - if (!fw->wq) + if (!fw->wq) { + err = -ENOMEM; goto err_wq_alloc; + } INIT_WORK(&fw->evt_work, prestera_fw_evt_work_fn); -- cgit v1.2.3 From 81e329e93b860b31c216b40eb5e1373db0ffe0ba Mon Sep 17 00:00:00 2001 From: Wang Qing Date: Thu, 12 Nov 2020 18:45:41 +0200 Subject: net: ethernet: ti: am65-cpts: update ret when ptp_clock is ERROR We always have to update the value of ret, otherwise the error value may be the previous one. Fixes: f6bd59526ca5 ("net: ethernet: ti: introduce am654 common platform time sync driver") Signed-off-by: Wang Qing [grygorii.strashko@ti.com: fix build warn, subj add fixes tag] Signed-off-by: Grygorii Strashko Acked-by: Richard Cochran Link: https://lore.kernel.org/r/20201112164541.3223-1-grygorii.strashko@ti.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/am65-cpts.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index 75056c14b161..5dc60ecabe56 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -1001,8 +1001,7 @@ struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs, if (IS_ERR_OR_NULL(cpts->ptp_clock)) { dev_err(dev, "Failed to register ptp clk %ld\n", PTR_ERR(cpts->ptp_clock)); - if (!cpts->ptp_clock) - ret = -ENODEV; + ret = cpts->ptp_clock ? PTR_ERR(cpts->ptp_clock) : -ENODEV; goto refclk_disable; } cpts->phc_index = ptp_clock_index(cpts->ptp_clock); -- cgit v1.2.3 From 8d4c3e76e3be11a64df95ddee52e99092d42fc19 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 13 Nov 2020 16:47:52 -0700 Subject: proc: don't allow async path resolution of /proc/self components If this is attempted by a kthread, then return -EOPNOTSUPP as we don't currently support that. Once we can get task_pid_ptr() doing the right thing, then this can go away again. Signed-off-by: Jens Axboe --- fs/proc/self.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/proc/self.c b/fs/proc/self.c index 72cd69bcaf4a..cc71ce3466dc 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -16,6 +16,13 @@ static const char *proc_self_get_link(struct dentry *dentry, pid_t tgid = task_tgid_nr_ns(current, ns); char *name; + /* + * Not currently supported. Once we can inherit all of struct pid, + * we can allow this. + */ + if (current->flags & PF_KTHREAD) + return ERR_PTR(-EOPNOTSUPP); + if (!tgid) return ERR_PTR(-ENOENT); /* max length of unsigned int in decimal + NULL term */ -- cgit v1.2.3 From 9c2e14b48119b39446031d29d994044ae958d8fc Mon Sep 17 00:00:00 2001 From: Yi-Hung Wei Date: Tue, 10 Nov 2020 16:16:40 -0800 Subject: ip_tunnels: Set tunnel option flag when tunnel metadata is present Currently, we may set the tunnel option flag when the size of metadata is zero. For example, we set TUNNEL_GENEVE_OPT in the receive function no matter the geneve option is present or not. As this may result in issues on the tunnel flags consumers, this patch fixes the issue. Related discussion: * https://lore.kernel.org/netdev/1604448694-19351-1-git-send-email-yihung.wei@gmail.com/T/#u Fixes: 256c87c17c53 ("net: check tunnel option type in tunnel flags") Signed-off-by: Yi-Hung Wei Link: https://lore.kernel.org/r/1605053800-74072-1-git-send-email-yihung.wei@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/geneve.c | 3 +-- include/net/ip_tunnels.h | 7 ++++--- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index d07008a818df..1426bfc009bc 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -224,8 +224,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, if (ip_tunnel_collect_metadata() || gs->collect_md) { __be16 flags; - flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT | - (gnvh->oam ? TUNNEL_OAM : 0) | + flags = TUNNEL_KEY | (gnvh->oam ? TUNNEL_OAM : 0) | (gnvh->critical ? TUNNEL_CRIT_OPT : 0); tun_dst = udp_tun_rx_dst(skb, geneve_get_sk_family(gs), flags, diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 02ccd32542d0..61620677b034 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -478,9 +478,11 @@ static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, __be16 flags) { - memcpy(ip_tunnel_info_opts(info), from, len); info->options_len = len; - info->key.tun_flags |= flags; + if (len > 0) { + memcpy(ip_tunnel_info_opts(info), from, len); + info->key.tun_flags |= flags; + } } static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) @@ -526,7 +528,6 @@ static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, __be16 flags) { info->options_len = 0; - info->key.tun_flags |= flags; } #endif /* CONFIG_INET */ -- cgit v1.2.3 From ceb736e1d45c253f5e86b185ca9b497cdd43063f Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Thu, 12 Nov 2020 16:09:50 +0800 Subject: ipv6: Fix error path to cancel the meseage genlmsg_cancel() needs to be called in the error path of inet6_fill_ifmcaddr and inet6_fill_ifacaddr to cancel the message. Fixes: 6ecf4c37eb3e ("ipv6: enable IFA_TARGET_NETNSID for RTM_GETADDR") Reported-by: Hulk Robot Signed-off-by: Zhang Qilong Link: https://lore.kernel.org/r/20201112080950.1476302-1-zhangqilong3@huawei.com Signed-off-by: Jakub Kicinski --- net/ipv6/addrconf.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 01146b66d666..8b6eb384bac7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5022,8 +5022,10 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, return -EMSGSIZE; if (args->netnsid >= 0 && - nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) { + nlmsg_cancel(skb, nlh); return -EMSGSIZE; + } put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || @@ -5054,8 +5056,10 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, return -EMSGSIZE; if (args->netnsid >= 0 && - nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) { + nlmsg_cancel(skb, nlh); return -EMSGSIZE; + } put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 || -- cgit v1.2.3 From 0f0d2c876c96d4908a9ef40959a44bec21bdd6cf Mon Sep 17 00:00:00 2001 From: Minwoo Im Date: Thu, 5 Nov 2020 23:28:47 +0900 Subject: nvme: free sq/cq dbbuf pointers when dbbuf set fails If Doorbell Buffer Config command fails even 'dev->dbbuf_dbs != NULL' which means OACS indicates that NVME_CTRL_OACS_DBBUF_SUPP is set, nvme_dbbuf_update_and_check_event() will check event even it's not been successfully set. This patch fixes mismatch among dbbuf for sq/cqs in case that dbbuf command fails. Signed-off-by: Minwoo Im Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 0578ff253c47..3be352403839 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -292,9 +292,21 @@ static void nvme_dbbuf_init(struct nvme_dev *dev, nvmeq->dbbuf_cq_ei = &dev->dbbuf_eis[cq_idx(qid, dev->db_stride)]; } +static void nvme_dbbuf_free(struct nvme_queue *nvmeq) +{ + if (!nvmeq->qid) + return; + + nvmeq->dbbuf_sq_db = NULL; + nvmeq->dbbuf_cq_db = NULL; + nvmeq->dbbuf_sq_ei = NULL; + nvmeq->dbbuf_cq_ei = NULL; +} + static void nvme_dbbuf_set(struct nvme_dev *dev) { struct nvme_command c; + unsigned int i; if (!dev->dbbuf_dbs) return; @@ -308,6 +320,9 @@ static void nvme_dbbuf_set(struct nvme_dev *dev) dev_warn(dev->ctrl.device, "unable to set dbbuf\n"); /* Free memory and continue on */ nvme_dbbuf_dma_free(dev); + + for (i = 1; i <= dev->online_queues; i++) + nvme_dbbuf_free(&dev->queues[i]); } } -- cgit v1.2.3 From f6224b8681326856937420e1db18564a934bf32b Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 13 Nov 2020 10:28:30 -0800 Subject: nvme: directly cache command effects log Remove the struct used for tracking known command effects logs in a list. This is now saved in an xarray that doesn't use these elements. Instead, store the log directly instead of the wrapper struct. Signed-off-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 9 ++++----- drivers/nvme/host/nvme.h | 6 ------ 2 files changed, 4 insertions(+), 11 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 9b01afcb7777..2f96675cc0cf 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2929,7 +2929,7 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi, static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi, struct nvme_effects_log **log) { - struct nvme_cel *cel = xa_load(&ctrl->cels, csi); + struct nvme_effects_log *cel = xa_load(&ctrl->cels, csi); int ret; if (cel) @@ -2940,16 +2940,15 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi, return -ENOMEM; ret = nvme_get_log(ctrl, 0x00, NVME_LOG_CMD_EFFECTS, 0, csi, - &cel->log, sizeof(cel->log), 0); + cel, sizeof(*cel), 0); if (ret) { kfree(cel); return ret; } - cel->csi = csi; - xa_store(&ctrl->cels, cel->csi, cel, GFP_KERNEL); + xa_store(&ctrl->cels, csi, cel, GFP_KERNEL); out: - *log = &cel->log; + *log = cel; return 0; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index bc330bf0d3bd..567f7ad18a91 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -226,12 +226,6 @@ struct nvme_fault_inject { #endif }; -struct nvme_cel { - struct list_head entry; - struct nvme_effects_log log; - u8 csi; -}; - struct nvme_ctrl { bool comp_seen; enum nvme_ctrl_state state; -- cgit v1.2.3 From 8168d23fbcee4f9f6c5a1ce8650417f09aef70eb Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 13 Nov 2020 10:45:45 -0800 Subject: nvme: fix memory leak freeing command effects xa_destroy() frees only internal data. The caller is responsible for freeing the exteranl objects referenced by an xarray. Fixes: 1cf7a12e09aa4 ("nvme: use an xarray to lookup the Commands Supported and Effects log") Signed-off-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 2f96675cc0cf..9a270e49df17 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4373,6 +4373,19 @@ void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_uninit_ctrl); +static void nvme_free_cels(struct nvme_ctrl *ctrl) +{ + struct nvme_effects_log *cel; + unsigned long i; + + xa_for_each (&ctrl->cels, i, cel) { + xa_erase(&ctrl->cels, i); + kfree(cel); + } + + xa_destroy(&ctrl->cels); +} + static void nvme_free_ctrl(struct device *dev) { struct nvme_ctrl *ctrl = @@ -4382,8 +4395,7 @@ static void nvme_free_ctrl(struct device *dev) if (!subsys || ctrl->instance != subsys->instance) ida_simple_remove(&nvme_instance_ida, ctrl->instance); - xa_destroy(&ctrl->cels); - + nvme_free_cels(ctrl); nvme_mpath_uninit(ctrl); __free_page(ctrl->discard_page); -- cgit v1.2.3 From f782e2c300a717233b64697affda3ea7aac00b2b Mon Sep 17 00:00:00 2001 From: Dmitrii Banshchikov Date: Fri, 13 Nov 2020 17:17:56 +0000 Subject: bpf: Relax return code check for subprograms Currently verifier enforces return code checks for subprograms in the same manner as it does for program entry points. This prevents returning arbitrary scalar values from subprograms. Scalar type of returned values is checked by btf_prepare_func_args() and hence it should be safe to allow only scalars for now. Relax return code checks for subprograms and allow any correct scalar values. Fixes: 51c39bb1d5d10 (bpf: Introduce function-by-function verification) Signed-off-by: Dmitrii Banshchikov Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20201113171756.90594-1-me@ubique.spb.ru --- kernel/bpf/verifier.c | 15 +++++++++++++-- .../selftests/bpf/prog_tests/test_global_funcs.c | 1 + tools/testing/selftests/bpf/progs/test_global_func8.c | 19 +++++++++++++++++++ 3 files changed, 33 insertions(+), 2 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/test_global_func8.c diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6204ec705d80..1388bf733071 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7786,9 +7786,11 @@ static int check_return_code(struct bpf_verifier_env *env) struct tnum range = tnum_range(0, 1); enum bpf_prog_type prog_type = resolve_prog_type(env->prog); int err; + const bool is_subprog = env->cur_state->frame[0]->subprogno; /* LSM and struct_ops func-ptr's return type could be "void" */ - if ((prog_type == BPF_PROG_TYPE_STRUCT_OPS || + if (!is_subprog && + (prog_type == BPF_PROG_TYPE_STRUCT_OPS || prog_type == BPF_PROG_TYPE_LSM) && !prog->aux->attach_func_proto->type) return 0; @@ -7808,6 +7810,16 @@ static int check_return_code(struct bpf_verifier_env *env) return -EACCES; } + reg = cur_regs(env) + BPF_REG_0; + if (is_subprog) { + if (reg->type != SCALAR_VALUE) { + verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n", + reg_type_str[reg->type]); + return -EINVAL; + } + return 0; + } + switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || @@ -7861,7 +7873,6 @@ static int check_return_code(struct bpf_verifier_env *env) return 0; } - reg = cur_regs(env) + BPF_REG_0; if (reg->type != SCALAR_VALUE) { verbose(env, "At program exit the register R0 is not a known value (%s)\n", reg_type_str[reg->type]); diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c index 193002b14d7f..32e4348b714b 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -60,6 +60,7 @@ void test_test_global_funcs(void) { "test_global_func5.o" , "expected pointer to ctx, but got PTR" }, { "test_global_func6.o" , "modified ctx ptr R2" }, { "test_global_func7.o" , "foo() doesn't return scalar" }, + { "test_global_func8.o" }, }; libbpf_print_fn_t old_print_fn = NULL; int err, i, duration = 0; diff --git a/tools/testing/selftests/bpf/progs/test_global_func8.c b/tools/testing/selftests/bpf/progs/test_global_func8.c new file mode 100644 index 000000000000..d55a6544b1ab --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func8.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include +#include +#include + +__noinline int foo(struct __sk_buff *skb) +{ + return bpf_get_prandom_u32(); +} + +SEC("cgroup_skb/ingress") +int test_cls(struct __sk_buff *skb) +{ + if (!foo(skb)) + return 0; + + return 1; +} -- cgit v1.2.3 From 944d1444d53f5a213457e5096db370cfd06923d4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 13 Nov 2020 16:48:44 -0700 Subject: io_uring: handle -EOPNOTSUPP on path resolution Any attempt to do path resolution on /proc/self from an async worker will yield -EOPNOTSUPP. We can safely do that resolution from the task itself, and without blocking, so retry it from there. Ideally io_uring would know this upfront and not have to go through the worker thread to find out, but that doesn't currently seem feasible. Signed-off-by: Jens Axboe --- fs/io_uring.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index c77584de68d7..f05978a74ce1 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -478,6 +478,7 @@ struct io_sr_msg { struct io_open { struct file *file; int dfd; + bool ignore_nonblock; struct filename *filename; struct open_how how; unsigned long nofile; @@ -3796,6 +3797,7 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe return ret; } req->open.nofile = rlimit(RLIMIT_NOFILE); + req->open.ignore_nonblock = false; req->flags |= REQ_F_NEED_CLEANUP; return 0; } @@ -3839,7 +3841,7 @@ static int io_openat2(struct io_kiocb *req, bool force_nonblock) struct file *file; int ret; - if (force_nonblock) + if (force_nonblock && !req->open.ignore_nonblock) return -EAGAIN; ret = build_open_flags(&req->open.how, &op); @@ -3854,6 +3856,21 @@ static int io_openat2(struct io_kiocb *req, bool force_nonblock) if (IS_ERR(file)) { put_unused_fd(ret); ret = PTR_ERR(file); + /* + * A work-around to ensure that /proc/self works that way + * that it should - if we get -EOPNOTSUPP back, then assume + * that proc_self_get_link() failed us because we're in async + * context. We should be safe to retry this from the task + * itself with force_nonblock == false set, as it should not + * block on lookup. Would be nice to know this upfront and + * avoid the async dance, but doesn't seem feasible. + */ + if (ret == -EOPNOTSUPP && io_wq_current_is_worker()) { + req->open.ignore_nonblock = true; + refcount_inc(&req->refs); + io_req_task_queue(req); + return 0; + } } else { fsnotify_open(file); fd_install(ret, file); -- cgit v1.2.3 From 11e94f28c3de35d5ad1ac6a242a5b30f4378991a Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 10 Nov 2020 14:38:34 +0100 Subject: iio: accel: kxcjk1013: Replace is_smo8500_device with an acpi_type enum Replace the boolean is_smo8500_device variable with an acpi_type enum. For now this can be either ACPI_GENERIC or ACPI_SMO8500, this is a preparation patch for adding special handling for the KIOX010A ACPI HID, which will add a ACPI_KIOX010A acpi_type to the introduced enum. For stable as needed as precursor for next patch. Signed-off-by: Hans de Goede Fixes: 7f6232e69539 ("iio: accel: kxcjk1013: Add KIOX010A ACPI Hardware-ID") Cc: Link: https://lore.kernel.org/r/20201110133835.129080-2-hdegoede@redhat.com Signed-off-by: Jonathan Cameron --- drivers/iio/accel/kxcjk-1013.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c index beb38d9d607d..abeb0d254046 100644 --- a/drivers/iio/accel/kxcjk-1013.c +++ b/drivers/iio/accel/kxcjk-1013.c @@ -126,6 +126,11 @@ enum kx_chipset { KX_MAX_CHIPS /* this must be last */ }; +enum kx_acpi_type { + ACPI_GENERIC, + ACPI_SMO8500, +}; + struct kxcjk1013_data { struct i2c_client *client; struct iio_trigger *dready_trig; @@ -143,7 +148,7 @@ struct kxcjk1013_data { bool motion_trigger_on; int64_t timestamp; enum kx_chipset chipset; - bool is_smo8500_device; + enum kx_acpi_type acpi_type; }; enum kxcjk1013_axis { @@ -1247,7 +1252,7 @@ static irqreturn_t kxcjk1013_data_rdy_trig_poll(int irq, void *private) static const char *kxcjk1013_match_acpi_device(struct device *dev, enum kx_chipset *chipset, - bool *is_smo8500_device) + enum kx_acpi_type *acpi_type) { const struct acpi_device_id *id; @@ -1256,7 +1261,7 @@ static const char *kxcjk1013_match_acpi_device(struct device *dev, return NULL; if (strcmp(id->id, "SMO8500") == 0) - *is_smo8500_device = true; + *acpi_type = ACPI_SMO8500; *chipset = (enum kx_chipset)id->driver_data; @@ -1299,7 +1304,7 @@ static int kxcjk1013_probe(struct i2c_client *client, } else if (ACPI_HANDLE(&client->dev)) { name = kxcjk1013_match_acpi_device(&client->dev, &data->chipset, - &data->is_smo8500_device); + &data->acpi_type); } else return -ENODEV; @@ -1316,7 +1321,7 @@ static int kxcjk1013_probe(struct i2c_client *client, indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->info = &kxcjk1013_info; - if (client->irq > 0 && !data->is_smo8500_device) { + if (client->irq > 0 && data->acpi_type != ACPI_SMO8500) { ret = devm_request_threaded_irq(&client->dev, client->irq, kxcjk1013_data_rdy_trig_poll, kxcjk1013_event_handler, -- cgit v1.2.3 From e5b1032a656e9aa4c7a4df77cb9156a2a651a5f9 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 10 Nov 2020 14:38:35 +0100 Subject: iio: accel: kxcjk1013: Add support for KIOX010A ACPI DSM for setting tablet-mode Some 360 degree hinges (yoga) style 2-in-1 devices use 2 KXCJ91008-s to allow the OS to determine the angle between the display and the base of the device, so that the OS can determine if the 2-in-1 is in laptop or in tablet-mode. On Windows both accelerometers are read by a special HingeAngleService process; and this process calls a DSM (Device Specific Method) on the ACPI KIOX010A device node for the sensor in the display, to let the embedded-controller (EC) know about the mode so that it can disable the kbd and touchpad to avoid spurious input while folded into tablet-mode. This notifying of the EC is problematic because sometimes the EC comes up thinking that device is in tablet-mode and the kbd and touchpad do not work. This happens for example on Irbis NB111 devices after a suspend / resume cycle (after a complete battery drain / hard reset without having booted Windows at least once). Other 2-in-1s which are likely affected too are e.g. the Teclast F5 and F6 series. The kxcjk-1013 driver may seem like a strange place to deal with this, but since it is *the* driver for the ACPI KIOX010A device, it is also the driver which has access to the ACPI handle needed by the DSM. Add support for calling the DSM and on probe unconditionally tell the EC that the device is laptop mode, fixing the kbd and touchpad sometimes not working. Fixes: 7f6232e69539 ("iio: accel: kxcjk1013: Add KIOX010A ACPI Hardware-ID") Reported-and-tested-by: russianneuromancer Signed-off-by: Hans de Goede Cc: Link: https://lore.kernel.org/r/20201110133835.129080-3-hdegoede@redhat.com Signed-off-by: Jonathan Cameron --- drivers/iio/accel/kxcjk-1013.c | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c index abeb0d254046..560a3373ff20 100644 --- a/drivers/iio/accel/kxcjk-1013.c +++ b/drivers/iio/accel/kxcjk-1013.c @@ -129,6 +129,7 @@ enum kx_chipset { enum kx_acpi_type { ACPI_GENERIC, ACPI_SMO8500, + ACPI_KIOX010A, }; struct kxcjk1013_data { @@ -275,6 +276,32 @@ static const struct { {19163, 1, 0}, {38326, 0, 1} }; +#ifdef CONFIG_ACPI +enum kiox010a_fn_index { + KIOX010A_SET_LAPTOP_MODE = 1, + KIOX010A_SET_TABLET_MODE = 2, +}; + +static int kiox010a_dsm(struct device *dev, int fn_index) +{ + acpi_handle handle = ACPI_HANDLE(dev); + guid_t kiox010a_dsm_guid; + union acpi_object *obj; + + if (!handle) + return -ENODEV; + + guid_parse("1f339696-d475-4e26-8cad-2e9f8e6d7a91", &kiox010a_dsm_guid); + + obj = acpi_evaluate_dsm(handle, &kiox010a_dsm_guid, 1, fn_index, NULL); + if (!obj) + return -EIO; + + ACPI_FREE(obj); + return 0; +} +#endif + static int kxcjk1013_set_mode(struct kxcjk1013_data *data, enum kxcjk1013_mode mode) { @@ -352,6 +379,13 @@ static int kxcjk1013_chip_init(struct kxcjk1013_data *data) { int ret; +#ifdef CONFIG_ACPI + if (data->acpi_type == ACPI_KIOX010A) { + /* Make sure the kbd and touchpad on 2-in-1s using 2 KXCJ91008-s work */ + kiox010a_dsm(&data->client->dev, KIOX010A_SET_LAPTOP_MODE); + } +#endif + ret = i2c_smbus_read_byte_data(data->client, KXCJK1013_REG_WHO_AM_I); if (ret < 0) { dev_err(&data->client->dev, "Error reading who_am_i\n"); @@ -1262,6 +1296,8 @@ static const char *kxcjk1013_match_acpi_device(struct device *dev, if (strcmp(id->id, "SMO8500") == 0) *acpi_type = ACPI_SMO8500; + else if (strcmp(id->id, "KIOX010A") == 0) + *acpi_type = ACPI_KIOX010A; *chipset = (enum kx_chipset)id->driver_data; -- cgit v1.2.3 From b7131ee0bac5e5df73e4098e77bbddb3a31d06ff Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 14 Nov 2020 19:12:46 +0100 Subject: blk-cgroup: fix a hd_struct leak in blkcg_fill_root_iostats disk_get_part needs to be paired with a disk_put_part. Cc: stable@vger.kernel.org Fixes: ef45fe470e1 ("blk-cgroup: show global disk stats in root cgroup io.stat") Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c68bdf58c9a6..54fbe1e80cc4 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -849,6 +849,7 @@ static void blkcg_fill_root_iostats(void) blkg_iostat_set(&blkg->iostat.cur, &tmp); u64_stats_update_end(&blkg->iostat.sync); } + disk_put_part(part); } } -- cgit v1.2.3 From 37344718bd7032639a02053e06b51697f90154ce Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Thu, 12 Nov 2020 19:23:59 +0800 Subject: net: phy: smsc: add missed clk_disable_unprepare in smsc_phy_probe() Add the missing clk_disable_unprepare() before return from smsc_phy_probe() in the error handling case. Fixes: bedd8d78aba3 ("net: phy: smsc: LAN8710/20: add phy refclk in support") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Link: https://lore.kernel.org/r/1605180239-1792-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/smsc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index ec97669be5c2..0fc39ac5ca88 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -291,8 +291,10 @@ static int smsc_phy_probe(struct phy_device *phydev) return ret; ret = clk_set_rate(priv->refclk, 50 * 1000 * 1000); - if (ret) + if (ret) { + clk_disable_unprepare(priv->refclk); return ret; + } return 0; } -- cgit v1.2.3 From 92307069a96c07d9b6e74b96b79390e7cd7d2111 Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Thu, 12 Nov 2020 12:43:35 +0100 Subject: net: dsa: mv88e6xxx: Avoid VTU corruption on 6097 As soon as you add the second port to a VLAN, all other port membership configuration is overwritten with zeroes. The HW interprets this as all ports being "unmodified members" of the VLAN. In the simple case when all ports belong to the same VLAN, switching will still work. But using multiple VLANs or trying to set multiple ports as tagged members will not work. On the 6352, doing a VTU GetNext op, followed by an STU GetNext op will leave you with both the member- and state- data in the VTU/STU data registers. But on the 6097 (which uses the same implementation), the STU GetNext will override the information gathered from the VTU GetNext. Separate the two stages, parsing the result of the VTU GetNext before doing the STU GetNext. We opt to update the existing implementation for all applicable chips, as opposed to creating a separate callback for 6097, because although the previous implementation did work for (at least) 6352, the datasheet does not mention the masking behavior. Fixes: ef6fcea37f01 ("net: dsa: mv88e6xxx: get STU entry on VTU GetNext") Signed-off-by: Tobias Waldekranz Link: https://lore.kernel.org/r/20201112114335.27371-1-tobias@waldekranz.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/mv88e6xxx/global1_vtu.c | 59 +++++++++++++++++++++++++++------ 1 file changed, 49 insertions(+), 10 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/global1_vtu.c b/drivers/net/dsa/mv88e6xxx/global1_vtu.c index 48390b7b18ad..1048509a849b 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_vtu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_vtu.c @@ -125,11 +125,9 @@ static int mv88e6xxx_g1_vtu_vid_write(struct mv88e6xxx_chip *chip, * Offset 0x08: VTU/STU Data Register 2 * Offset 0x09: VTU/STU Data Register 3 */ - -static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip, - struct mv88e6xxx_vtu_entry *entry) +static int mv88e6185_g1_vtu_stu_data_read(struct mv88e6xxx_chip *chip, + u16 *regs) { - u16 regs[3]; int i; /* Read all 3 VTU/STU Data registers */ @@ -142,12 +140,45 @@ static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip, return err; } - /* Extract MemberTag and PortState data */ + return 0; +} + +static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_vtu_entry *entry) +{ + u16 regs[3]; + int err; + int i; + + err = mv88e6185_g1_vtu_stu_data_read(chip, regs); + if (err) + return err; + + /* Extract MemberTag data */ for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) { unsigned int member_offset = (i % 4) * 4; - unsigned int state_offset = member_offset + 2; entry->member[i] = (regs[i / 4] >> member_offset) & 0x3; + } + + return 0; +} + +static int mv88e6185_g1_stu_data_read(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_vtu_entry *entry) +{ + u16 regs[3]; + int err; + int i; + + err = mv88e6185_g1_vtu_stu_data_read(chip, regs); + if (err) + return err; + + /* Extract PortState data */ + for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) { + unsigned int state_offset = (i % 4) * 4 + 2; + entry->state[i] = (regs[i / 4] >> state_offset) & 0x3; } @@ -349,6 +380,10 @@ int mv88e6185_g1_vtu_getnext(struct mv88e6xxx_chip *chip, if (err) return err; + err = mv88e6185_g1_stu_data_read(chip, entry); + if (err) + return err; + /* VTU DBNum[3:0] are located in VTU Operation 3:0 * VTU DBNum[7:4] are located in VTU Operation 11:8 */ @@ -374,16 +409,20 @@ int mv88e6352_g1_vtu_getnext(struct mv88e6xxx_chip *chip, return err; if (entry->valid) { - /* Fetch (and mask) VLAN PortState data from the STU */ - err = mv88e6xxx_g1_vtu_stu_get(chip, entry); + err = mv88e6185_g1_vtu_data_read(chip, entry); if (err) return err; - err = mv88e6185_g1_vtu_data_read(chip, entry); + err = mv88e6xxx_g1_vtu_fid_read(chip, entry); if (err) return err; - err = mv88e6xxx_g1_vtu_fid_read(chip, entry); + /* Fetch VLAN PortState data from the STU */ + err = mv88e6xxx_g1_vtu_stu_get(chip, entry); + if (err) + return err; + + err = mv88e6185_g1_stu_data_read(chip, entry); if (err) return err; } -- cgit v1.2.3 From 65b422d9b61ba12c08150784e8012fa1892ad03e Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Thu, 12 Nov 2020 14:38:37 +0100 Subject: vsock: forward all packets to the host when no H2G is registered Before commit c0cfa2d8a788 ("vsock: add multi-transports support"), if a G2H transport was loaded (e.g. virtio transport), every packets was forwarded to the host, regardless of the destination CID. The H2G transports implemented until then (vhost-vsock, VMCI) always responded with an error, if the destination CID was not VMADDR_CID_HOST. From that commit, we are using the remote CID to decide which transport to use, so packets with remote CID > VMADDR_CID_HOST(2) are sent only through H2G transport. If no H2G is available, packets are discarded directly in the guest. Some use cases (e.g. Nitro Enclaves [1]) rely on the old behaviour to implement sibling VMs communication, so we restore the old behavior when no H2G is registered. It will be up to the host to discard packets if the destination is not the right one. As it was already implemented before adding multi-transport support. Tested with nested QEMU/KVM by me and Nitro Enclaves by Andra. [1] Documentation/virt/ne_overview.rst Cc: Jorgen Hansen Cc: Dexuan Cui Fixes: c0cfa2d8a788 ("vsock: add multi-transports support") Reported-by: Andra Paraschiv Tested-by: Andra Paraschiv Signed-off-by: Stefano Garzarella Link: https://lore.kernel.org/r/20201112133837.34183-1-sgarzare@redhat.com Signed-off-by: Jakub Kicinski --- net/vmw_vsock/af_vsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index b4d7b8aba003..d10916ab4526 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -438,7 +438,7 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) case SOCK_STREAM: if (vsock_use_local_transport(remote_cid)) new_transport = transport_local; - else if (remote_cid <= VMADDR_CID_HOST) + else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g) new_transport = transport_g2h; else new_transport = transport_h2g; -- cgit v1.2.3 From 057a10fa1f73d745c8e69aa54ab147715f5630ae Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 14 Nov 2020 13:22:53 +0800 Subject: sctp: change to hold/put transport for proto_unreach_timer A call trace was found in Hangbin's Codenomicon testing with debug kernel: [ 2615.981988] ODEBUG: free active (active state 0) object type: timer_list hint: sctp_generate_proto_unreach_event+0x0/0x3a0 [sctp] [ 2615.995050] WARNING: CPU: 17 PID: 0 at lib/debugobjects.c:328 debug_print_object+0x199/0x2b0 [ 2616.095934] RIP: 0010:debug_print_object+0x199/0x2b0 [ 2616.191533] Call Trace: [ 2616.194265] [ 2616.202068] debug_check_no_obj_freed+0x25e/0x3f0 [ 2616.207336] slab_free_freelist_hook+0xeb/0x140 [ 2616.220971] kfree+0xd6/0x2c0 [ 2616.224293] rcu_do_batch+0x3bd/0xc70 [ 2616.243096] rcu_core+0x8b9/0xd00 [ 2616.256065] __do_softirq+0x23d/0xacd [ 2616.260166] irq_exit+0x236/0x2a0 [ 2616.263879] smp_apic_timer_interrupt+0x18d/0x620 [ 2616.269138] apic_timer_interrupt+0xf/0x20 [ 2616.273711] This is because it holds asoc when transport->proto_unreach_timer starts and puts asoc when the timer stops, and without holding transport the transport could be freed when the timer is still running. So fix it by holding/putting transport instead for proto_unreach_timer in transport, just like other timers in transport. v1->v2: - Also use sctp_transport_put() for the "out_unlock:" path in sctp_generate_proto_unreach_event(), as Marcelo noticed. Fixes: 50b5d6ad6382 ("sctp: Fix a race between ICMP protocol unreachable and connect()") Reported-by: Hangbin Liu Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Link: https://lore.kernel.org/r/102788809b554958b13b95d33440f5448113b8d6.1605331373.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski --- net/sctp/input.c | 4 ++-- net/sctp/sm_sideeffect.c | 4 ++-- net/sctp/transport.c | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/net/sctp/input.c b/net/sctp/input.c index 55d4fc6f371d..d508f6f3dd08 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -449,7 +449,7 @@ void sctp_icmp_proto_unreachable(struct sock *sk, else { if (!mod_timer(&t->proto_unreach_timer, jiffies + (HZ/20))) - sctp_association_hold(asoc); + sctp_transport_hold(t); } } else { struct net *net = sock_net(sk); @@ -458,7 +458,7 @@ void sctp_icmp_proto_unreachable(struct sock *sk, "encountered!\n", __func__); if (del_timer(&t->proto_unreach_timer)) - sctp_association_put(asoc); + sctp_transport_put(t); sctp_do_sm(net, SCTP_EVENT_T_OTHER, SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH), diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 813d30767204..0948f14ce221 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -419,7 +419,7 @@ void sctp_generate_proto_unreach_event(struct timer_list *t) /* Try again later. */ if (!mod_timer(&transport->proto_unreach_timer, jiffies + (HZ/20))) - sctp_association_hold(asoc); + sctp_transport_hold(transport); goto out_unlock; } @@ -435,7 +435,7 @@ void sctp_generate_proto_unreach_event(struct timer_list *t) out_unlock: bh_unlock_sock(sk); - sctp_association_put(asoc); + sctp_transport_put(transport); } /* Handle the timeout of the RE-CONFIG timer. */ diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 806af58f4375..60fcf31cdcfb 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -133,7 +133,7 @@ void sctp_transport_free(struct sctp_transport *transport) /* Delete the ICMP proto unreachable timer if it's active. */ if (del_timer(&transport->proto_unreach_timer)) - sctp_association_put(transport->asoc); + sctp_transport_put(transport); sctp_transport_put(transport); } -- cgit v1.2.3 From 1ba86d4366e023d96df3dbe415eea7f1dc08c303 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Fri, 13 Nov 2020 16:30:40 -0500 Subject: netlabel: fix an uninitialized warning in netlbl_unlabel_staticlist() Static checking revealed that a previous fix to netlbl_unlabel_staticlist() leaves a stack variable uninitialized, this patches fixes that. Fixes: 866358ec331f ("netlabel: fix our progress tracking in netlbl_unlabel_staticlist()") Reported-by: Dan Carpenter Signed-off-by: Paul Moore Reviewed-by: James Morris Link: https://lore.kernel.org/r/160530304068.15651.18355773009751195447.stgit@sifl Signed-off-by: Jakub Kicinski --- net/netlabel/netlabel_unlabeled.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index fc55c9116da0..ccb491642811 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1167,7 +1167,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, u32 skip_bkt = cb->args[0]; u32 skip_chain = cb->args[1]; u32 skip_addr4 = cb->args[2]; - u32 iter_bkt, iter_chain, iter_addr4 = 0, iter_addr6 = 0; + u32 iter_bkt, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0; struct netlbl_unlhsh_iface *iface; struct list_head *iter_list; struct netlbl_af4list *addr4; -- cgit v1.2.3 From e35df62e04cc6fc4b9d90d054732f138349ff9b1 Mon Sep 17 00:00:00 2001 From: Sven Van Asbroeck Date: Thu, 12 Nov 2020 13:59:49 -0500 Subject: lan743x: fix issue causing intermittent kernel log warnings When running this chip on arm imx6, we intermittently observe the following kernel warning in the log, especially when the system is under high load: [ 50.119484] ------------[ cut here ]------------ [ 50.124377] WARNING: CPU: 0 PID: 303 at kernel/softirq.c:169 __local_bh_enable_ip+0x100/0x184 [ 50.132925] IRQs not enabled as expected [ 50.159250] CPU: 0 PID: 303 Comm: rngd Not tainted 5.7.8 #1 [ 50.164837] Hardware name: Freescale i.MX6 Quad/DualLite (Device Tree) [ 50.171395] [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [ 50.179162] [] (show_stack) from [] (dump_stack+0xac/0xd8) [ 50.186408] [] (dump_stack) from [] (__warn+0xd0/0x10c) [ 50.193391] [] (__warn) from [] (warn_slowpath_fmt+0x98/0xc4) [ 50.200892] [] (warn_slowpath_fmt) from [] (__local_bh_enable_ip+0x100/0x184) [ 50.209860] [] (__local_bh_enable_ip) from [] (destroy_conntrack+0x48/0xd8 [nf_conntrack]) [ 50.220038] [] (destroy_conntrack [nf_conntrack]) from [] (nf_conntrack_destroy+0x94/0x168) [ 50.230160] [] (nf_conntrack_destroy) from [] (skb_release_head_state+0xa0/0xd0) [ 50.239314] [] (skb_release_head_state) from [] (skb_release_all+0xc/0x24) [ 50.247946] [] (skb_release_all) from [] (consume_skb+0x74/0x17c) [ 50.255796] [] (consume_skb) from [] (lan743x_tx_release_desc+0x120/0x124) [ 50.264428] [] (lan743x_tx_release_desc) from [] (lan743x_tx_napi_poll+0x5c/0x18c) [ 50.273755] [] (lan743x_tx_napi_poll) from [] (net_rx_action+0x118/0x4a4) [ 50.282306] [] (net_rx_action) from [] (__do_softirq+0x13c/0x53c) [ 50.290157] [] (__do_softirq) from [] (irq_exit+0x150/0x17c) [ 50.297575] [] (irq_exit) from [] (__handle_domain_irq+0x60/0xb0) [ 50.305423] [] (__handle_domain_irq) from [] (gic_handle_irq+0x4c/0x90) [ 50.313790] [] (gic_handle_irq) from [] (__irq_usr+0x54/0x80) [ 50.321287] Exception stack(0xecd99fb0 to 0xecd99ff8) [ 50.326355] 9fa0: 1cf1aa74 00000001 00000001 00000000 [ 50.334547] 9fc0: 00000001 00000000 00000000 00000000 00000000 00000000 00004097 b6d17d14 [ 50.342738] 9fe0: 00000001 b6d17c60 00000000 b6e71f94 800b0010 ffffffff [ 50.349364] irq event stamp: 2525027 [ 50.352955] hardirqs last enabled at (2525026): [] net_rx_action+0xb4/0x4a4 [ 50.360892] hardirqs last disabled at (2525027): [] _raw_spin_lock_irqsave+0x1c/0x50 [ 50.369517] softirqs last enabled at (2524660): [] __do_softirq+0x38c/0x53c [ 50.377446] softirqs last disabled at (2524693): [] irq_exit+0x150/0x17c [ 50.385027] ---[ end trace c0b571db4bc8087d ]--- The driver is calling dev_kfree_skb() from code inside a spinlock, where h/w interrupts are disabled. This is forbidden, as documented in include/linux/netdevice.h. The correct function to use dev_kfree_skb_irq(), or dev_kfree_skb_any(). Fix by using the correct dev_kfree_skb_xxx() functions: in lan743x_tx_release_desc(): called by lan743x_tx_release_completed_descriptors() called by in lan743x_tx_napi_poll() which holds a spinlock called by lan743x_tx_release_all_descriptors() called by lan743x_tx_close() which can-sleep conclusion: use dev_kfree_skb_any() in lan743x_tx_xmit_frame(): which holds a spinlock conclusion: use dev_kfree_skb_irq() in lan743x_tx_close(): which can-sleep conclusion: use dev_kfree_skb() in lan743x_rx_release_ring_element(): called by lan743x_rx_close() which can-sleep called by lan743x_rx_open() which can-sleep conclusion: use dev_kfree_skb() Fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver") Signed-off-by: Sven Van Asbroeck Link: https://lore.kernel.org/r/20201112185949.11315-1-TheSven73@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microchip/lan743x_main.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index e2c99d909247..18c053b860ab 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -1307,13 +1307,13 @@ clean_up_data_descriptor: goto clear_active; if (!(buffer_info->flags & TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED)) { - dev_kfree_skb(buffer_info->skb); + dev_kfree_skb_any(buffer_info->skb); goto clear_skb; } if (cleanup) { lan743x_ptp_unrequest_tx_timestamp(tx->adapter); - dev_kfree_skb(buffer_info->skb); + dev_kfree_skb_any(buffer_info->skb); } else { ignore_sync = (buffer_info->flags & TX_BUFFER_INFO_FLAG_IGNORE_SYNC) != 0; @@ -1623,7 +1623,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx, if (required_number_of_descriptors > lan743x_tx_get_avail_desc(tx)) { if (required_number_of_descriptors > (tx->ring_size - 1)) { - dev_kfree_skb(skb); + dev_kfree_skb_irq(skb); } else { /* save to overflow buffer */ tx->overflow_skb = skb; @@ -1656,7 +1656,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx, start_frame_length, do_timestamp, skb->ip_summed == CHECKSUM_PARTIAL)) { - dev_kfree_skb(skb); + dev_kfree_skb_irq(skb); goto unlock; } @@ -1675,7 +1675,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx, * frame assembler clean up was performed inside * lan743x_tx_frame_add_fragment */ - dev_kfree_skb(skb); + dev_kfree_skb_irq(skb); goto unlock; } } -- cgit v1.2.3 From 796a2665ca3e91ebaba7222f76fd9a035714e2d8 Mon Sep 17 00:00:00 2001 From: Sven Van Asbroeck Date: Thu, 12 Nov 2020 15:47:41 -0500 Subject: lan743x: prevent entire kernel HANG on open, for some platforms On arm imx6, when opening the chip's netdev, the whole Linux kernel intermittently hangs/freezes. This is caused by a bug in the driver code which tests if pcie interrupts are working correctly, using the software interrupt: 1. open: enable the software interrupt 2. open: tell the chip to assert the software interrupt 3. open: wait for flag 4. ISR: acknowledge s/w interrupt, set flag 5. open: notice flag, disable the s/w interrupt, continue Unfortunately the ISR only acknowledges the s/w interrupt, but does not disable it. This will re-trigger the ISR in a tight loop. On some (lucky) platforms, open proceeds to disable the s/w interrupt even while the ISR is 'spinning'. On arm imx6, the spinning ISR does not allow open to proceed, resulting in a hung Linux kernel. Fix minimally by disabling the s/w interrupt in the ISR, which will prevent it from spinning. This won't break anything because the s/w interrupt is used as a one-shot interrupt. Note that this is a minimal fix, overlooking many possible cleanups, e.g.: - lan743x_intr_software_isr() is completely redundant and reads INT_STS twice for no apparent reason - disabling the s/w interrupt in lan743x_intr_test_isr() is now redundant, but harmless - waiting on software_isr_flag can be converted from a sleeping poll loop to wait_event_timeout() Fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver") Tested-by: Sven Van Asbroeck # arm imx6 lan7430 Signed-off-by: Sven Van Asbroeck Link: https://lore.kernel.org/r/20201112204741.12375-1-TheSven73@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microchip/lan743x_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 18c053b860ab..b319c22c211c 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -148,7 +148,8 @@ static void lan743x_intr_software_isr(void *context) int_sts = lan743x_csr_read(adapter, INT_STS); if (int_sts & INT_BIT_SW_GP_) { - lan743x_csr_write(adapter, INT_STS, INT_BIT_SW_GP_); + /* disable the interrupt to prevent repeated re-triggering */ + lan743x_csr_write(adapter, INT_EN_CLR, INT_BIT_SW_GP_); intr->software_isr_flag = 1; } } -- cgit v1.2.3 From 56311a315da7ebc668dbcc2f1c99689cc10796c4 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Fri, 13 Nov 2020 09:09:02 +0800 Subject: net: stmmac: dwmac_lib: enlarge dma reset timeout If the phy enables power saving technology, the dwmac's software reset needs more time to complete, enlarge dma reset timeout to 200000us. Signed-off-by: Jisheng Zhang Link: https://lore.kernel.org/r/20201113090902.5c7aab1a@xhacker.debian Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index cb87d31a99df..57a53a600aa5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -23,7 +23,7 @@ int dwmac_dma_reset(void __iomem *ioaddr) return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value, !(value & DMA_BUS_MODE_SFT_RESET), - 10000, 100000); + 10000, 200000); } /* CSR1 enables the transmit DMA to check for new descriptor */ -- cgit v1.2.3 From 849920c703392957f94023f77ec89ca6cf119d43 Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Fri, 13 Nov 2020 19:16:22 +0800 Subject: devlink: Add missing genlmsg_cancel() in devlink_nl_sb_port_pool_fill() If sb_occ_port_pool_get() failed in devlink_nl_sb_port_pool_fill(), msg should be canceled by genlmsg_cancel(). Fixes: df38dafd2559 ("devlink: implement shared buffer occupancy monitoring interface") Reported-by: Hulk Robot Signed-off-by: Wang Hai Link: https://lore.kernel.org/r/20201113111622.11040-1-wanghai38@huawei.com Signed-off-by: Jakub Kicinski --- net/core/devlink.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/core/devlink.c b/net/core/devlink.c index ab4b1368904f..4b0211590aac 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1448,7 +1448,7 @@ static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index, pool_index, &cur, &max); if (err && err != -EOPNOTSUPP) - return err; + goto sb_occ_get_failure; if (!err) { if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur)) goto nla_put_failure; @@ -1461,8 +1461,10 @@ static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, return 0; nla_put_failure: + err = -EMSGSIZE; +sb_occ_get_failure: genlmsg_cancel(msg, hdr); - return -EMSGSIZE; + return err; } static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb, -- cgit v1.2.3 From 14a2e551faea53d45bc11629a9dac88f88950ca7 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Sun, 15 Nov 2020 10:30:04 +0000 Subject: batman-adv: set .owner to THIS_MODULE If THIS_MODULE is not set, the module would be removed while debugfs is being used. It eventually makes kernel panic. Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Signed-off-by: Taehee Yoo Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- net/batman-adv/log.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index a67b2b091447..c0ca5fbe5b08 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -180,6 +180,7 @@ static const struct file_operations batadv_log_fops = { .read = batadv_log_read, .poll = batadv_log_poll, .llseek = no_llseek, + .owner = THIS_MODULE, }; /** -- cgit v1.2.3 From c8c958a58fc67f353289986850a0edf553435702 Mon Sep 17 00:00:00 2001 From: Anant Thazhemadam Date: Wed, 4 Nov 2020 03:09:05 +0530 Subject: can: af_can: prevent potential access of uninitialized member in can_rcv() In can_rcv(), cfd->len is uninitialized when skb->len = 0, and this uninitialized cfd->len is accessed nonetheless by pr_warn_once(). Fix this uninitialized variable access by checking cfd->len's validity condition (cfd->len > CAN_MAX_DLEN) separately after the skb->len's condition is checked, and appropriately modify the log messages that are generated as well. In case either of the required conditions fail, the skb is freed and NET_RX_DROP is returned, same as before. Fixes: 8cb68751c115 ("can: af_can: can_rcv(): replace WARN_ONCE by pr_warn_once") Reported-by: syzbot+9bcb0c9409066696d3aa@syzkaller.appspotmail.com Tested-by: Anant Thazhemadam Signed-off-by: Anant Thazhemadam Link: https://lore.kernel.org/r/20201103213906.24219-2-anant.thazhemadam@gmail.com Signed-off-by: Marc Kleine-Budde --- net/can/af_can.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/net/can/af_can.c b/net/can/af_can.c index 6373ab9c5507..e8d4e3ef5322 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -677,16 +677,25 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU || - cfd->len > CAN_MAX_DLEN)) { - pr_warn_once("PF_CAN: dropped non conform CAN skbuf: dev type %d, len %d, datalen %d\n", + if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU)) { + pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d\n", + dev->type, skb->len); + goto free_skb; + } + + /* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */ + if (unlikely(cfd->len > CAN_MAX_DLEN)) { + pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d, datalen %d\n", dev->type, skb->len, cfd->len); - kfree_skb(skb); - return NET_RX_DROP; + goto free_skb; } can_receive(skb, dev); return NET_RX_SUCCESS; + +free_skb: + kfree_skb(skb); + return NET_RX_DROP; } static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, -- cgit v1.2.3 From 9aa9379d8f868e91719333a7f063ccccc0579acc Mon Sep 17 00:00:00 2001 From: Anant Thazhemadam Date: Wed, 4 Nov 2020 03:09:06 +0530 Subject: can: af_can: prevent potential access of uninitialized member in canfd_rcv() In canfd_rcv(), cfd->len is uninitialized when skb->len = 0, and this uninitialized cfd->len is accessed nonetheless by pr_warn_once(). Fix this uninitialized variable access by checking cfd->len's validity condition (cfd->len > CANFD_MAX_DLEN) separately after the skb->len's condition is checked, and appropriately modify the log messages that are generated as well. In case either of the required conditions fail, the skb is freed and NET_RX_DROP is returned, same as before. Fixes: d4689846881d ("can: af_can: canfd_rcv(): replace WARN_ONCE by pr_warn_once") Reported-by: syzbot+9bcb0c9409066696d3aa@syzkaller.appspotmail.com Tested-by: Anant Thazhemadam Signed-off-by: Anant Thazhemadam Link: https://lore.kernel.org/r/20201103213906.24219-3-anant.thazhemadam@gmail.com Signed-off-by: Marc Kleine-Budde --- net/can/af_can.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/net/can/af_can.c b/net/can/af_can.c index e8d4e3ef5322..5d124c155904 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -703,16 +703,25 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU || - cfd->len > CANFD_MAX_DLEN)) { - pr_warn_once("PF_CAN: dropped non conform CAN FD skbuf: dev type %d, len %d, datalen %d\n", + if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU)) { + pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d\n", + dev->type, skb->len); + goto free_skb; + } + + /* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */ + if (unlikely(cfd->len > CANFD_MAX_DLEN)) { + pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d, datalen %d\n", dev->type, skb->len, cfd->len); - kfree_skb(skb); - return NET_RX_DROP; + goto free_skb; } can_receive(skb, dev); return NET_RX_SUCCESS; + +free_skb: + kfree_skb(skb); + return NET_RX_DROP; } /* af_can protocol functions */ -- cgit v1.2.3 From a1e654070a60d5d4f7cce59c38f4ca790bb79121 Mon Sep 17 00:00:00 2001 From: Alejandro Concepcion Rodriguez Date: Thu, 5 Nov 2020 21:51:47 +0000 Subject: can: dev: can_restart(): post buffer from the right context netif_rx() is meant to be called from interrupt contexts. can_restart() may be called by can_restart_work(), which is called from a worqueue, so it may run in process context. Use netif_rx_ni() instead. Fixes: 39549eef3587 ("can: CAN Network device driver and Netlink interface") Co-developed-by: Loris Fauster Signed-off-by: Loris Fauster Signed-off-by: Alejandro Concepcion Rodriguez Link: https://lore.kernel.org/r/4e84162b-fb31-3a73-fa9a-9438b4bd5234@acoro.eu [mkl: use netif_rx_ni() instead of netif_rx_any_context()] Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 6dee4f8f2024..81e39d7507d8 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -592,7 +592,7 @@ static void can_restart(struct net_device *dev) cf->can_id |= CAN_ERR_RESTARTED; - netif_rx(skb); + netif_rx_ni(skb); stats->rx_packets++; stats->rx_bytes += cf->can_dlc; -- cgit v1.2.3 From 7968c7c79d3be8987feb8021f0c46e6866831408 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Sat, 14 Nov 2020 19:17:08 +0800 Subject: can: ti_hecc: Fix memleak in ti_hecc_probe In the error handling, we should goto the probe_exit_candev to free ndev to prevent memory leak. Fixes: dabf54dd1c63 ("can: ti_hecc: Convert TI HECC driver to DT only driver") Signed-off-by: Zhang Qilong Link: https://lore.kernel.org/r/20201114111708.3465543-1-zhangqilong3@huawei.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/ti_hecc.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index 9913f5458279..2c22f40e12bd 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -881,7 +881,8 @@ static int ti_hecc_probe(struct platform_device *pdev) priv->base = devm_platform_ioremap_resource_byname(pdev, "hecc"); if (IS_ERR(priv->base)) { dev_err(&pdev->dev, "hecc ioremap failed\n"); - return PTR_ERR(priv->base); + err = PTR_ERR(priv->base); + goto probe_exit_candev; } /* handle hecc-ram memory */ @@ -889,20 +890,22 @@ static int ti_hecc_probe(struct platform_device *pdev) "hecc-ram"); if (IS_ERR(priv->hecc_ram)) { dev_err(&pdev->dev, "hecc-ram ioremap failed\n"); - return PTR_ERR(priv->hecc_ram); + err = PTR_ERR(priv->hecc_ram); + goto probe_exit_candev; } /* handle mbx memory */ priv->mbx = devm_platform_ioremap_resource_byname(pdev, "mbx"); if (IS_ERR(priv->mbx)) { dev_err(&pdev->dev, "mbx ioremap failed\n"); - return PTR_ERR(priv->mbx); + err = PTR_ERR(priv->mbx); + goto probe_exit_candev; } irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); if (!irq) { dev_err(&pdev->dev, "No irq resource\n"); - goto probe_exit; + goto probe_exit_candev; } priv->ndev = ndev; @@ -966,7 +969,7 @@ probe_exit_release_clk: clk_put(priv->clk); probe_exit_candev: free_candev(ndev); -probe_exit: + return err; } -- cgit v1.2.3 From 81c9c8e0adef3285336b942f93287c554c89e6c6 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 28 Aug 2019 21:16:55 +0200 Subject: can: mcba_usb: mcba_usb_start_xmit(): first fill skb, then pass to can_put_echo_skb() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver has to first fill the skb with data and then handle it to can_put_echo_skb(). This patch moves the can_put_echo_skb() down, right before sending the skb out via USB. Fixes: 51f3baad7de9 ("can: mcba_usb: Add support for Microchip CAN BUS Analyzer") Cc: Remigiusz Kołłątaj Link: https://lore.kernel.org/r/20201111221204.1639007-1-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/mcba_usb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 5857b37dcd96..e97f2e0da6b0 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -326,8 +326,6 @@ static netdev_tx_t mcba_usb_start_xmit(struct sk_buff *skb, if (!ctx) return NETDEV_TX_BUSY; - can_put_echo_skb(skb, priv->netdev, ctx->ndx); - if (cf->can_id & CAN_EFF_FLAG) { /* SIDH | SIDL | EIDH | EIDL * 28 - 21 | 20 19 18 x x x 17 16 | 15 - 8 | 7 - 0 @@ -357,6 +355,8 @@ static netdev_tx_t mcba_usb_start_xmit(struct sk_buff *skb, if (cf->can_id & CAN_RTR_FLAG) usb_msg.dlc |= MCBA_DLC_RTR_MASK; + can_put_echo_skb(skb, priv->netdev, ctx->ndx); + err = mcba_usb_xmit(priv, (struct mcba_usb_msg *)&usb_msg, ctx); if (err) goto xmit_failed; -- cgit v1.2.3 From 8a68cc0d690c9e5730d676b764c6f059343b842c Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 5 Nov 2020 11:24:27 +0000 Subject: can: peak_usb: fix potential integer overflow on shift of a int The left shift of int 32 bit integer constant 1 is evaluated using 32 bit arithmetic and then assigned to a signed 64 bit variable. In the case where time_ref->adapter->ts_used_bits is 32 or more this can lead to an oveflow. Avoid this by shifting using the BIT_ULL macro instead. Fixes: bb4785551f64 ("can: usb: PEAK-System Technik USB adapters driver core") Signed-off-by: Colin Ian King Link: https://lore.kernel.org/r/20201105112427.40688-1-colin.king@canonical.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/peak_usb/pcan_usb_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index c2764799f9ef..204ccb27d6d9 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -156,7 +156,7 @@ void peak_usb_get_ts_time(struct peak_time_ref *time_ref, u32 ts, ktime_t *time) if (time_ref->ts_dev_1 < time_ref->ts_dev_2) { /* case when event time (tsw) wraps */ if (ts < time_ref->ts_dev_1) - delta_ts = 1 << time_ref->adapter->ts_used_bits; + delta_ts = BIT_ULL(time_ref->adapter->ts_used_bits); /* Otherwise, sync time counter (ts_dev_2) has wrapped: * handle case when event time (tsn) hasn't. @@ -168,7 +168,7 @@ void peak_usb_get_ts_time(struct peak_time_ref *time_ref, u32 ts, ktime_t *time) * tsn ts */ } else if (time_ref->ts_dev_1 < ts) { - delta_ts = -(1 << time_ref->adapter->ts_used_bits); + delta_ts = -BIT_ULL(time_ref->adapter->ts_used_bits); } /* add delay between last sync and event timestamps */ -- cgit v1.2.3 From 499aa923c56769274f81e60414b8de4912864b8d Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 14 Oct 2020 13:41:36 +0200 Subject: can: flexcan: flexcan_setup_stop_mode(): add missing "req_bit" to stop mode property comment In the patch d9b081e3fc4b ("can: flexcan: remove ack_grp and ack_bit handling from driver") the unused ack_grp and ack_bit were removed from the driver. However in the comment, the "req_bit" was accidentally removed, too. This patch adds back the "req_bit" bit. Fixes: d9b081e3fc4b ("can: flexcan: remove ack_grp and ack_bit handling from driver") Reported-by: Joakim Zhang Link: http://lore.kernel.org/r/20201014114810.2911135-1-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- drivers/net/can/flexcan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 881799bd9c5e..4e8fdb6064bd 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -1852,7 +1852,7 @@ static int flexcan_setup_stop_mode(struct platform_device *pdev) return -EINVAL; /* stop mode property format is: - * <&gpr req_gpr>. + * <&gpr req_gpr req_bit>. */ ret = of_property_read_u32_array(np, "fsl,stop-mode", out_val, ARRAY_SIZE(out_val)); -- cgit v1.2.3 From b7ee5bc3e1006433601a058a6a7c24c5272635f4 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Sun, 8 Nov 2020 16:30:00 +0800 Subject: can: flexcan: fix failure handling of pm_runtime_get_sync() pm_runtime_get_sync() will increment pm usage at first and it will resume the device later. If runtime of the device has error or device is in inaccessible state(or other error state), resume operation will fail. If we do not call put operation to decrease the reference, it will result in reference leak in the two functions flexcan_get_berr_counter() and flexcan_open(). Moreover, this device cannot enter the idle state and always stay busy or other non-idle state later. So we should fix it through adding pm_runtime_put_noidle(). Fixes: ca10989632d88 ("can: flexcan: implement can Runtime PM") Signed-off-by: Zhang Qilong Link: https://lore.kernel.org/r/20201108083000.2599705-1-zhangqilong3@huawei.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/flexcan.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 4e8fdb6064bd..d6a9cf0e9b60 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -728,8 +728,10 @@ static int flexcan_get_berr_counter(const struct net_device *dev, int err; err = pm_runtime_get_sync(priv->dev); - if (err < 0) + if (err < 0) { + pm_runtime_put_noidle(priv->dev); return err; + } err = __flexcan_get_berr_counter(dev, bec); @@ -1654,8 +1656,10 @@ static int flexcan_open(struct net_device *dev) } err = pm_runtime_get_sync(priv->dev); - if (err < 0) + if (err < 0) { + pm_runtime_put_noidle(priv->dev); return err; + } err = open_candev(dev); if (err) -- cgit v1.2.3 From 3fcce133f0d9a50d3a23f8e2bc950197b4e03900 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Mon, 13 Apr 2020 16:10:13 +0200 Subject: can: tcan4x5x: replace depends on REGMAP_SPI with depends on SPI regmap is a library function that gets selected by drivers that need it. No driver modules should depend on it. Instead depends on SPI and select REGMAP_SPI. Depending on REGMAP_SPI makes this driver only build if another driver already selected REGMAP_SPI, as the symbol can't be selected through the menu kernel configuration. Signed-off-by: Enric Balletbo i Serra Link: http://lore.kernel.org/r/20200413141013.506613-1-enric.balletbo@collabora.com Reviewed-by: Dan Murphy Fixes: 5443c226ba91 ("can: tcan4x5x: Add tcan4x5x driver to the kernel") Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/can/m_can/Kconfig b/drivers/net/can/m_can/Kconfig index 48be627c85c2..5f9f8192dd0b 100644 --- a/drivers/net/can/m_can/Kconfig +++ b/drivers/net/can/m_can/Kconfig @@ -16,7 +16,8 @@ config CAN_M_CAN_PLATFORM config CAN_M_CAN_TCAN4X5X depends on CAN_M_CAN - depends on REGMAP_SPI + depends on SPI + select REGMAP_SPI tristate "TCAN4X5X M_CAN device" help Say Y here if you want support for Texas Instruments TCAN4x5x -- cgit v1.2.3 From 1ff203badbbf1738027c8395d5b40b0d462b6e4d Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Fri, 3 Jan 2020 11:30:34 +0100 Subject: can: tcan4x5x: tcan4x5x_can_probe(): add missing error checking for devm_regmap_init() This patch adds the missing error checking when initializing the regmap interface fails. Fixes: 5443c226ba91 ("can: tcan4x5x: Add tcan4x5x driver to the kernel") Cc: Dan Murphy Link: http://lore.kernel.org/r/20201019154233.1262589-7-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/tcan4x5x.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c index eacd428e07e9..f058bd9104e9 100644 --- a/drivers/net/can/m_can/tcan4x5x.c +++ b/drivers/net/can/m_can/tcan4x5x.c @@ -487,6 +487,10 @@ static int tcan4x5x_can_probe(struct spi_device *spi) priv->regmap = devm_regmap_init(&spi->dev, &tcan4x5x_bus, &spi->dev, &tcan4x5x_regmap); + if (IS_ERR(priv->regmap)) { + ret = PTR_ERR(priv->regmap); + goto out_clk; + } ret = tcan4x5x_power_enable(priv->power, 1); if (ret) -- cgit v1.2.3 From c81d0b6ca665477c761f227807010762630b089f Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 10 Aug 2020 22:23:49 +0200 Subject: can: tcan4x5x: tcan4x5x_can_remove(): fix order of deregistration Change the order in tcan4x5x_can_remove() to be the exact inverse of tcan4x5x_can_probe(). First m_can_class_unregister(), then power down the device. Fixes: 5443c226ba91 ("can: tcan4x5x: Add tcan4x5x driver to the kernel") Cc: Dan Murphy Link: http://lore.kernel.org/r/20201019154233.1262589-10-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/tcan4x5x.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c index f058bd9104e9..4fdb7121403a 100644 --- a/drivers/net/can/m_can/tcan4x5x.c +++ b/drivers/net/can/m_can/tcan4x5x.c @@ -527,10 +527,10 @@ static int tcan4x5x_can_remove(struct spi_device *spi) { struct tcan4x5x_priv *priv = spi_get_drvdata(spi); - tcan4x5x_power_enable(priv->power, 0); - m_can_class_unregister(priv->mcan_dev); + tcan4x5x_power_enable(priv->power, 0); + return 0; } -- cgit v1.2.3 From cd0d83eab2e0c26fe87a10debfedbb23901853c1 Mon Sep 17 00:00:00 2001 From: Wu Bo Date: Wed, 29 Jan 2020 10:23:30 +0800 Subject: can: m_can: m_can_handle_state_change(): fix state change m_can_handle_state_change() is called with the new_state as an argument. In the switch statements for CAN_STATE_ERROR_ACTIVE, the comment and the following code indicate that a CAN_STATE_ERROR_WARNING is handled. This patch fixes this problem by changing the case to CAN_STATE_ERROR_WARNING. Signed-off-by: Wu Bo Link: http://lore.kernel.org/r/20200129022330.21248-2-wubo.oduw@gmail.com Cc: Dan Murphy Fixes: e0d1f4816f2a ("can: m_can: add Bosch M_CAN controller support") Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/m_can.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 02c5795b7393..63887e23d89c 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -665,7 +665,7 @@ static int m_can_handle_state_change(struct net_device *dev, unsigned int ecr; switch (new_state) { - case CAN_STATE_ERROR_ACTIVE: + case CAN_STATE_ERROR_WARNING: /* error warning state */ cdev->can.can_stats.error_warning++; cdev->can.state = CAN_STATE_ERROR_WARNING; @@ -694,7 +694,7 @@ static int m_can_handle_state_change(struct net_device *dev, __m_can_get_berr_counter(dev, &bec); switch (new_state) { - case CAN_STATE_ERROR_ACTIVE: + case CAN_STATE_ERROR_WARNING: /* error warning state */ cf->can_id |= CAN_ERR_CRTL; cf->data[1] = (bec.txerr > bec.rxerr) ? -- cgit v1.2.3 From a8c22f5b0c689a29f45ef4a110d09fd391debcbc Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Thu, 27 Feb 2020 12:38:29 -0600 Subject: can: m_can: m_can_class_free_dev(): introduce new function This patch creates a common function that peripherials can call to free the netdev device when failures occur. Fixes: f524f829b75a ("can: m_can: Create a m_can platform framework") Reported-by: Marc Kleine-Budde Signed-off-by: Dan Murphy Link: http://lore.kernel.org/r/20200227183829.21854-2-dmurphy@ti.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/m_can.c | 6 ++++++ drivers/net/can/m_can/m_can.h | 1 + 2 files changed, 7 insertions(+) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 63887e23d89c..f2c87b76e569 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1812,6 +1812,12 @@ out: } EXPORT_SYMBOL_GPL(m_can_class_allocate_dev); +void m_can_class_free_dev(struct net_device *net) +{ + free_candev(net); +} +EXPORT_SYMBOL_GPL(m_can_class_free_dev); + int m_can_class_register(struct m_can_classdev *m_can_dev) { int ret; diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index 49f42b50627a..b2699a7c9997 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -99,6 +99,7 @@ struct m_can_classdev { }; struct m_can_classdev *m_can_class_allocate_dev(struct device *dev); +void m_can_class_free_dev(struct net_device *net); int m_can_class_register(struct m_can_classdev *cdev); void m_can_class_unregister(struct m_can_classdev *cdev); int m_can_class_get_clocks(struct m_can_classdev *cdev); -- cgit v1.2.3 From 85816aba460ceebed0047381395615891df68c8f Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Thu, 27 Feb 2020 12:38:29 -0600 Subject: can: m_can: Fix freeing of can device from peripherials Fix leaking netdev device from peripherial devices. The call to allocate the netdev device is made from and managed by the peripherial. Fixes: f524f829b75a ("can: m_can: Create a m_can platform framework") Reported-by: Marc Kleine-Budde Signed-off-by: Dan Murphy Link: http://lore.kernel.org/r/20200227183829.21854-2-dmurphy@ti.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/m_can.c | 3 --- drivers/net/can/m_can/m_can_platform.c | 23 +++++++++++++++-------- drivers/net/can/m_can/tcan4x5x.c | 26 ++++++++++++++++++-------- 3 files changed, 33 insertions(+), 19 deletions(-) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index f2c87b76e569..645101d19989 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1856,7 +1856,6 @@ pm_runtime_fail: if (ret) { if (m_can_dev->pm_clock_support) pm_runtime_disable(m_can_dev->dev); - free_candev(m_can_dev->net); } return ret; @@ -1914,8 +1913,6 @@ void m_can_class_unregister(struct m_can_classdev *m_can_dev) unregister_candev(m_can_dev->net); m_can_clk_stop(m_can_dev); - - free_candev(m_can_dev->net); } EXPORT_SYMBOL_GPL(m_can_class_unregister); diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c index e6d0cb9ee02f..161cb9be018c 100644 --- a/drivers/net/can/m_can/m_can_platform.c +++ b/drivers/net/can/m_can/m_can_platform.c @@ -67,32 +67,36 @@ static int m_can_plat_probe(struct platform_device *pdev) return -ENOMEM; priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; + if (!priv) { + ret = -ENOMEM; + goto probe_fail; + } mcan_class->device_data = priv; - m_can_class_get_clocks(mcan_class); + ret = m_can_class_get_clocks(mcan_class); + if (ret) + goto probe_fail; res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "m_can"); addr = devm_ioremap_resource(&pdev->dev, res); irq = platform_get_irq_byname(pdev, "int0"); if (IS_ERR(addr) || irq < 0) { ret = -EINVAL; - goto failed_ret; + goto probe_fail; } /* message ram could be shared */ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "message_ram"); if (!res) { ret = -ENODEV; - goto failed_ret; + goto probe_fail; } mram_addr = devm_ioremap(&pdev->dev, res->start, resource_size(res)); if (!mram_addr) { ret = -ENOMEM; - goto failed_ret; + goto probe_fail; } priv->base = addr; @@ -111,9 +115,10 @@ static int m_can_plat_probe(struct platform_device *pdev) m_can_init_ram(mcan_class); - ret = m_can_class_register(mcan_class); + return m_can_class_register(mcan_class); -failed_ret: +probe_fail: + m_can_class_free_dev(mcan_class->net); return ret; } @@ -134,6 +139,8 @@ static int m_can_plat_remove(struct platform_device *pdev) m_can_class_unregister(mcan_class); + m_can_class_free_dev(mcan_class->net); + platform_set_drvdata(pdev, NULL); return 0; diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c index 4fdb7121403a..e5d7d85e0b6d 100644 --- a/drivers/net/can/m_can/tcan4x5x.c +++ b/drivers/net/can/m_can/tcan4x5x.c @@ -440,14 +440,18 @@ static int tcan4x5x_can_probe(struct spi_device *spi) return -ENOMEM; priv = devm_kzalloc(&spi->dev, sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; + if (!priv) { + ret = -ENOMEM; + goto out_m_can_class_free_dev; + } priv->power = devm_regulator_get_optional(&spi->dev, "vsup"); - if (PTR_ERR(priv->power) == -EPROBE_DEFER) - return -EPROBE_DEFER; - else + if (PTR_ERR(priv->power) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto out_m_can_class_free_dev; + } else { priv->power = NULL; + } mcan_class->device_data = priv; @@ -460,8 +464,10 @@ static int tcan4x5x_can_probe(struct spi_device *spi) } /* Sanity check */ - if (freq < 20000000 || freq > TCAN4X5X_EXT_CLK_DEF) - return -ERANGE; + if (freq < 20000000 || freq > TCAN4X5X_EXT_CLK_DEF) { + ret = -ERANGE; + goto out_m_can_class_free_dev; + } priv->reg_offset = TCAN4X5X_MCAN_OFFSET; priv->mram_start = TCAN4X5X_MRAM_START; @@ -518,8 +524,10 @@ out_clk: clk_disable_unprepare(mcan_class->cclk); clk_disable_unprepare(mcan_class->hclk); } - + out_m_can_class_free_dev: + m_can_class_free_dev(mcan_class->net); dev_err(&spi->dev, "Probe failed, err=%d\n", ret); + return ret; } @@ -531,6 +539,8 @@ static int tcan4x5x_can_remove(struct spi_device *spi) tcan4x5x_power_enable(priv->power, 0); + m_can_class_free_dev(priv->mcan_dev->net); + return 0; } -- cgit v1.2.3 From a584e9bc1b7e88f24f8504886eafbe6c73d8a97c Mon Sep 17 00:00:00 2001 From: Faiz Abbas Date: Tue, 25 Aug 2020 11:24:42 +0530 Subject: can: m_can: m_can_stop(): set device to software init mode before closing There might be some requests pending in the buffer when the interface close sequence occurs. In some devices, these pending requests might lead to the module not shutting down properly when m_can_clk_stop() is called. Therefore, move the device to init state before potentially powering it down. Fixes: e0d1f4816f2a ("can: m_can: add Bosch M_CAN controller support") Signed-off-by: Faiz Abbas Acked-by: Dan Murphy Link: https://lore.kernel.org/r/20200825055442.16994-1-faiz_abbas@ti.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/m_can.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 645101d19989..e7264043f79a 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1414,6 +1414,9 @@ static void m_can_stop(struct net_device *dev) /* disable all interrupts */ m_can_disable_all_interrupts(cdev); + /* Set init mode to disengage from the network */ + m_can_config_endisable(cdev, true); + /* set the state as STOPPED */ cdev->can.state = CAN_STATE_STOPPED; } -- cgit v1.2.3 From a312db697cb05dfa781848afe8585a1e1f2a5a99 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Fri, 13 Nov 2020 16:57:06 +0100 Subject: vdpasim: fix "mac_pton" undefined error ERROR: modpost: "mac_pton" [drivers/vdpa/vdpa_sim/vdpa_sim.ko] undefined! mac_pton() is defined in lib/net_utils.c and is not built if NET is not set. Select GENERIC_NET_UTILS as vdpasim doesn't depend on NET. Reported-by: kernel test robot Signed-off-by: Laurent Vivier Link: https://lore.kernel.org/r/20201113155706.599434-1-lvivier@redhat.com Signed-off-by: Michael S. Tsirkin Acked-by: Randy Dunlap # build-tested --- drivers/vdpa/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index d7d32b656102..358f6048dd3c 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -13,6 +13,7 @@ config VDPA_SIM depends on RUNTIME_TESTING_MENU && HAS_DMA select DMA_OPS select VHOST_RING + select GENERIC_NET_UTILS default n help vDPA networking device simulator which loop TX traffic back -- cgit v1.2.3 From 6bcf34224ac1e94103797fd68b9836061762f2b2 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 9 Nov 2020 23:33:19 -0600 Subject: vhost: add helper to check if a vq has been setup This adds a helper check if a vq has been setup. The next patches will use this when we move the vhost scsi cmd preallocation from per session to per vq. In the per vq case, we only want to allocate cmds for vqs that have actually been setup and not for all the possible vqs. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/1604986403-4931-2-git-send-email-michael.christie@oracle.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang Acked-by: Stefan Hajnoczi --- drivers/vhost/vhost.c | 6 ++++++ drivers/vhost/vhost.h | 1 + 2 files changed, 7 insertions(+) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 5c835a292783..a262e12c6dc2 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -304,6 +304,12 @@ static void vhost_vring_call_reset(struct vhost_vring_call *call_ctx) memset(&call_ctx->producer, 0x0, sizeof(struct irq_bypass_producer)); } +bool vhost_vq_is_setup(struct vhost_virtqueue *vq) +{ + return vq->avail && vq->desc && vq->used && vhost_vq_access_ok(vq); +} +EXPORT_SYMBOL_GPL(vhost_vq_is_setup); + static void vhost_vq_reset(struct vhost_dev *dev, struct vhost_virtqueue *vq) { diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index e016cd3fa02f..b063324c7669 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -190,6 +190,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *, struct vhost_log *log, unsigned int *log_num); void vhost_discard_vq_desc(struct vhost_virtqueue *, int n); +bool vhost_vq_is_setup(struct vhost_virtqueue *vq); int vhost_vq_init_access(struct vhost_virtqueue *); int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len); int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads, -- cgit v1.2.3 From 25b98b64e28423b0769313dcaf96423836b1f93d Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 9 Nov 2020 23:33:20 -0600 Subject: vhost scsi: alloc cmds per vq instead of session We currently are limited to 256 cmds per session. This leads to problems where if the user has increased virtqueue_size to more than 2 or cmd_per_lun to more than 256 vhost_scsi_get_tag can fail and the guest will get IO errors. This patch moves the cmd allocation to per vq so we can easily match whatever the user has specified for num_queues and virtqueue_size/cmd_per_lun. It also makes it easier to control how much memory we preallocate. For cases, where perf is not as important and we can use the current defaults (1 vq and 128 cmds per vq) memory use from preallocate cmds is cut in half. For cases, where we are willing to use more memory for higher perf, cmd mem use will now increase as the num queues and queue depth increases. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/1604986403-4931-3-git-send-email-michael.christie@oracle.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Maurizio Lombardi Acked-by: Stefan Hajnoczi --- drivers/vhost/scsi.c | 207 +++++++++++++++++++++++++++++++-------------------- 1 file changed, 128 insertions(+), 79 deletions(-) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index b22adf03f584..e31339be7dd7 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -52,7 +52,6 @@ #define VHOST_SCSI_VERSION "v0.1" #define VHOST_SCSI_NAMELEN 256 #define VHOST_SCSI_MAX_CDB_SIZE 32 -#define VHOST_SCSI_DEFAULT_TAGS 256 #define VHOST_SCSI_PREALLOC_SGLS 2048 #define VHOST_SCSI_PREALLOC_UPAGES 2048 #define VHOST_SCSI_PREALLOC_PROT_SGLS 2048 @@ -189,6 +188,9 @@ struct vhost_scsi_virtqueue { * Writers must also take dev mutex and flush under it. */ int inflight_idx; + struct vhost_scsi_cmd *scsi_cmds; + struct sbitmap scsi_tags; + int max_cmds; }; struct vhost_scsi { @@ -324,7 +326,9 @@ static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) { struct vhost_scsi_cmd *tv_cmd = container_of(se_cmd, struct vhost_scsi_cmd, tvc_se_cmd); - struct se_session *se_sess = tv_cmd->tvc_nexus->tvn_se_sess; + struct vhost_scsi_virtqueue *svq = container_of(tv_cmd->tvc_vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_inflight *inflight = tv_cmd->inflight; int i; if (tv_cmd->tvc_sgl_count) { @@ -336,8 +340,8 @@ static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) put_page(sg_page(&tv_cmd->tvc_prot_sgl[i])); } - vhost_scsi_put_inflight(tv_cmd->inflight); - target_free_tag(se_sess, se_cmd); + sbitmap_clear_bit(&svq->scsi_tags, se_cmd->map_tag); + vhost_scsi_put_inflight(inflight); } static u32 vhost_scsi_sess_get_index(struct se_session *se_sess) @@ -566,31 +570,31 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) } static struct vhost_scsi_cmd * -vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, +vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, unsigned char *cdb, u64 scsi_tag, u16 lun, u8 task_attr, u32 exp_data_len, int data_direction) { + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); struct vhost_scsi_cmd *cmd; struct vhost_scsi_nexus *tv_nexus; - struct se_session *se_sess; struct scatterlist *sg, *prot_sg; struct page **pages; - int tag, cpu; + int tag; tv_nexus = tpg->tpg_nexus; if (!tv_nexus) { pr_err("Unable to locate active struct vhost_scsi_nexus\n"); return ERR_PTR(-EIO); } - se_sess = tv_nexus->tvn_se_sess; - tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu); + tag = sbitmap_get(&svq->scsi_tags, 0, false); if (tag < 0) { pr_err("Unable to obtain tag for vhost_scsi_cmd\n"); return ERR_PTR(-ENOMEM); } - cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[tag]; + cmd = &svq->scsi_cmds[tag]; sg = cmd->tvc_sgl; prot_sg = cmd->tvc_prot_sgl; pages = cmd->tvc_upages; @@ -599,7 +603,6 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, cmd->tvc_prot_sgl = prot_sg; cmd->tvc_upages = pages; cmd->tvc_se_cmd.map_tag = tag; - cmd->tvc_se_cmd.map_cpu = cpu; cmd->tvc_tag = scsi_tag; cmd->tvc_lun = lun; cmd->tvc_task_attr = task_attr; @@ -1065,11 +1068,11 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) scsi_command_size(cdb), VHOST_SCSI_MAX_CDB_SIZE); goto err; } - cmd = vhost_scsi_get_tag(vq, tpg, cdb, tag, lun, task_attr, + cmd = vhost_scsi_get_cmd(vq, tpg, cdb, tag, lun, task_attr, exp_data_len + prot_bytes, data_direction); if (IS_ERR(cmd)) { - vq_err(vq, "vhost_scsi_get_tag failed %ld\n", + vq_err(vq, "vhost_scsi_get_cmd failed %ld\n", PTR_ERR(cmd)); goto err; } @@ -1373,6 +1376,83 @@ static void vhost_scsi_flush(struct vhost_scsi *vs) wait_for_completion(&old_inflight[i]->comp); } +static void vhost_scsi_destroy_vq_cmds(struct vhost_virtqueue *vq) +{ + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_cmd *tv_cmd; + unsigned int i; + + if (!svq->scsi_cmds) + return; + + for (i = 0; i < svq->max_cmds; i++) { + tv_cmd = &svq->scsi_cmds[i]; + + kfree(tv_cmd->tvc_sgl); + kfree(tv_cmd->tvc_prot_sgl); + kfree(tv_cmd->tvc_upages); + } + + sbitmap_free(&svq->scsi_tags); + kfree(svq->scsi_cmds); + svq->scsi_cmds = NULL; +} + +static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds) +{ + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_cmd *tv_cmd; + unsigned int i; + + if (svq->scsi_cmds) + return 0; + + if (sbitmap_init_node(&svq->scsi_tags, max_cmds, -1, GFP_KERNEL, + NUMA_NO_NODE)) + return -ENOMEM; + svq->max_cmds = max_cmds; + + svq->scsi_cmds = kcalloc(max_cmds, sizeof(*tv_cmd), GFP_KERNEL); + if (!svq->scsi_cmds) { + sbitmap_free(&svq->scsi_tags); + return -ENOMEM; + } + + for (i = 0; i < max_cmds; i++) { + tv_cmd = &svq->scsi_cmds[i]; + + tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS, + sizeof(struct scatterlist), + GFP_KERNEL); + if (!tv_cmd->tvc_sgl) { + pr_err("Unable to allocate tv_cmd->tvc_sgl\n"); + goto out; + } + + tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES, + sizeof(struct page *), + GFP_KERNEL); + if (!tv_cmd->tvc_upages) { + pr_err("Unable to allocate tv_cmd->tvc_upages\n"); + goto out; + } + + tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS, + sizeof(struct scatterlist), + GFP_KERNEL); + if (!tv_cmd->tvc_prot_sgl) { + pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n"); + goto out; + } + } + return 0; +out: + vhost_scsi_destroy_vq_cmds(vq); + return -ENOMEM; +} + /* * Called from vhost_scsi_ioctl() context to walk the list of available * vhost_scsi_tpg with an active struct vhost_scsi_nexus @@ -1427,10 +1507,9 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) { if (vs->vs_tpg && vs->vs_tpg[tpg->tport_tpgt]) { - kfree(vs_tpg); mutex_unlock(&tpg->tv_tpg_mutex); ret = -EEXIST; - goto out; + goto undepend; } /* * In order to ensure individual vhost-scsi configfs @@ -1442,9 +1521,8 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, ret = target_depend_item(&se_tpg->tpg_group.cg_item); if (ret) { pr_warn("target_depend_item() failed: %d\n", ret); - kfree(vs_tpg); mutex_unlock(&tpg->tv_tpg_mutex); - goto out; + goto undepend; } tpg->tv_tpg_vhost_count++; tpg->vhost_scsi = vs; @@ -1457,6 +1535,16 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (match) { memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn, sizeof(vs->vs_vhost_wwpn)); + + for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) { + vq = &vs->vqs[i].vq; + if (!vhost_vq_is_setup(vq)) + continue; + + if (vhost_scsi_setup_vq_cmds(vq, vq->num)) + goto destroy_vq_cmds; + } + for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) { vq = &vs->vqs[i].vq; mutex_lock(&vq->mutex); @@ -1476,7 +1564,22 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, vhost_scsi_flush(vs); kfree(vs->vs_tpg); vs->vs_tpg = vs_tpg; + goto out; +destroy_vq_cmds: + for (i--; i >= VHOST_SCSI_VQ_IO; i--) { + if (!vhost_vq_get_backend(&vs->vqs[i].vq)) + vhost_scsi_destroy_vq_cmds(&vs->vqs[i].vq); + } +undepend: + for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) { + tpg = vs_tpg[i]; + if (tpg) { + tpg->tv_tpg_vhost_count--; + target_undepend_item(&tpg->se_tpg.tpg_group.cg_item); + } + } + kfree(vs_tpg); out: mutex_unlock(&vs->dev.mutex); mutex_unlock(&vhost_scsi_mutex); @@ -1549,6 +1652,12 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, mutex_lock(&vq->mutex); vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); + /* + * Make sure cmds are not running before tearing them + * down. + */ + vhost_scsi_flush(vs); + vhost_scsi_destroy_vq_cmds(vq); } } /* @@ -1842,23 +1951,6 @@ static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg, mutex_unlock(&vhost_scsi_mutex); } -static void vhost_scsi_free_cmd_map_res(struct se_session *se_sess) -{ - struct vhost_scsi_cmd *tv_cmd; - unsigned int i; - - if (!se_sess->sess_cmd_map) - return; - - for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) { - tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i]; - - kfree(tv_cmd->tvc_sgl); - kfree(tv_cmd->tvc_prot_sgl); - kfree(tv_cmd->tvc_upages); - } -} - static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_store( struct config_item *item, const char *page, size_t count) { @@ -1898,45 +1990,6 @@ static struct configfs_attribute *vhost_scsi_tpg_attrib_attrs[] = { NULL, }; -static int vhost_scsi_nexus_cb(struct se_portal_group *se_tpg, - struct se_session *se_sess, void *p) -{ - struct vhost_scsi_cmd *tv_cmd; - unsigned int i; - - for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) { - tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i]; - - tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS, - sizeof(struct scatterlist), - GFP_KERNEL); - if (!tv_cmd->tvc_sgl) { - pr_err("Unable to allocate tv_cmd->tvc_sgl\n"); - goto out; - } - - tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES, - sizeof(struct page *), - GFP_KERNEL); - if (!tv_cmd->tvc_upages) { - pr_err("Unable to allocate tv_cmd->tvc_upages\n"); - goto out; - } - - tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS, - sizeof(struct scatterlist), - GFP_KERNEL); - if (!tv_cmd->tvc_prot_sgl) { - pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n"); - goto out; - } - } - return 0; -out: - vhost_scsi_free_cmd_map_res(se_sess); - return -ENOMEM; -} - static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg, const char *name) { @@ -1960,12 +2013,9 @@ static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg, * struct se_node_acl for the vhost_scsi struct se_portal_group with * the SCSI Initiator port name of the passed configfs group 'name'. */ - tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, - VHOST_SCSI_DEFAULT_TAGS, - sizeof(struct vhost_scsi_cmd), + tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, 0, 0, TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS, - (unsigned char *)name, tv_nexus, - vhost_scsi_nexus_cb); + (unsigned char *)name, tv_nexus, NULL); if (IS_ERR(tv_nexus->tvn_se_sess)) { mutex_unlock(&tpg->tv_tpg_mutex); kfree(tv_nexus); @@ -2015,7 +2065,6 @@ static int vhost_scsi_drop_nexus(struct vhost_scsi_tpg *tpg) " %s Initiator Port: %s\n", vhost_scsi_dump_proto_id(tpg->tport), tv_nexus->tvn_se_sess->se_node_acl->initiatorname); - vhost_scsi_free_cmd_map_res(se_sess); /* * Release the SCSI I_T Nexus to the emulated vhost Target Port */ -- cgit v1.2.3 From 47a3565e8bb14ec48a75b48daf57aa830e2691f8 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 9 Nov 2020 23:33:21 -0600 Subject: vhost scsi: fix cmd completion race We might not do the final se_cmd put from vhost_scsi_complete_cmd_work. When the last put happens a little later then we could race where vhost_scsi_complete_cmd_work does vhost_signal, the guest runs and sends more IO, and vhost_scsi_handle_vq runs but does not find any free cmds. This patch has us delay completing the cmd until the last lio core ref is dropped. We then know that once we signal to the guest that the cmd is completed that if it queues a new command it will find a free cmd. Signed-off-by: Mike Christie Reviewed-by: Maurizio Lombardi Link: https://lore.kernel.org/r/1604986403-4931-4-git-send-email-michael.christie@oracle.com Signed-off-by: Michael S. Tsirkin Acked-by: Stefan Hajnoczi --- drivers/vhost/scsi.c | 42 +++++++++++++++--------------------------- 1 file changed, 15 insertions(+), 27 deletions(-) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index e31339be7dd7..5d8850f5aef1 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -322,7 +322,7 @@ static u32 vhost_scsi_tpg_get_inst_index(struct se_portal_group *se_tpg) return 1; } -static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) +static void vhost_scsi_release_cmd_res(struct se_cmd *se_cmd) { struct vhost_scsi_cmd *tv_cmd = container_of(se_cmd, struct vhost_scsi_cmd, tvc_se_cmd); @@ -344,6 +344,16 @@ static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) vhost_scsi_put_inflight(inflight); } +static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) +{ + struct vhost_scsi_cmd *cmd = container_of(se_cmd, + struct vhost_scsi_cmd, tvc_se_cmd); + struct vhost_scsi *vs = cmd->tvc_vhost; + + llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list); + vhost_work_queue(&vs->dev, &vs->vs_completion_work); +} + static u32 vhost_scsi_sess_get_index(struct se_session *se_sess) { return 0; @@ -366,28 +376,15 @@ static int vhost_scsi_get_cmd_state(struct se_cmd *se_cmd) return 0; } -static void vhost_scsi_complete_cmd(struct vhost_scsi_cmd *cmd) -{ - struct vhost_scsi *vs = cmd->tvc_vhost; - - llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list); - - vhost_work_queue(&vs->dev, &vs->vs_completion_work); -} - static int vhost_scsi_queue_data_in(struct se_cmd *se_cmd) { - struct vhost_scsi_cmd *cmd = container_of(se_cmd, - struct vhost_scsi_cmd, tvc_se_cmd); - vhost_scsi_complete_cmd(cmd); + transport_generic_free_cmd(se_cmd, 0); return 0; } static int vhost_scsi_queue_status(struct se_cmd *se_cmd) { - struct vhost_scsi_cmd *cmd = container_of(se_cmd, - struct vhost_scsi_cmd, tvc_se_cmd); - vhost_scsi_complete_cmd(cmd); + transport_generic_free_cmd(se_cmd, 0); return 0; } @@ -433,15 +430,6 @@ vhost_scsi_allocate_evt(struct vhost_scsi *vs, return evt; } -static void vhost_scsi_free_cmd(struct vhost_scsi_cmd *cmd) -{ - struct se_cmd *se_cmd = &cmd->tvc_se_cmd; - - /* TODO locking against target/backend threads? */ - transport_generic_free_cmd(se_cmd, 0); - -} - static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd) { return target_put_sess_cmd(se_cmd); @@ -560,7 +548,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) } else pr_err("Faulted on virtio_scsi_cmd_resp\n"); - vhost_scsi_free_cmd(cmd); + vhost_scsi_release_cmd_res(se_cmd); } vq = -1; @@ -1091,7 +1079,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) &prot_iter, exp_data_len, &data_iter))) { vq_err(vq, "Failed to map iov to sgl\n"); - vhost_scsi_release_cmd(&cmd->tvc_se_cmd); + vhost_scsi_release_cmd_res(&cmd->tvc_se_cmd); goto err; } } -- cgit v1.2.3 From 18f1becb6948cd411fd01968a0a54af63732e73c Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 9 Nov 2020 23:33:22 -0600 Subject: vhost scsi: add lun parser helper Move code to parse lun from req's lun_buf to helper, so tmf code can use it in the next patch. Signed-off-by: Mike Christie Reviewed-by: Paolo Bonzini Acked-by: Jason Wang Link: https://lore.kernel.org/r/1604986403-4931-5-git-send-email-michael.christie@oracle.com Signed-off-by: Michael S. Tsirkin Acked-by: Stefan Hajnoczi --- drivers/vhost/scsi.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 5d8850f5aef1..ed7dc6b998f6 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -898,6 +898,11 @@ vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc, return ret; } +static u16 vhost_buf_to_lun(u8 *lun_buf) +{ + return ((lun_buf[2] << 8) | lun_buf[3]) & 0x3FFF; +} + static void vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) { @@ -1036,12 +1041,12 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) tag = vhost64_to_cpu(vq, v_req_pi.tag); task_attr = v_req_pi.task_attr; cdb = &v_req_pi.cdb[0]; - lun = ((v_req_pi.lun[2] << 8) | v_req_pi.lun[3]) & 0x3FFF; + lun = vhost_buf_to_lun(v_req_pi.lun); } else { tag = vhost64_to_cpu(vq, v_req.tag); task_attr = v_req.task_attr; cdb = &v_req.cdb[0]; - lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF; + lun = vhost_buf_to_lun(v_req.lun); } /* * Check that the received CDB size does not exceeded our -- cgit v1.2.3 From efd838fec17bd8756da852a435800a7e6281bfbc Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 9 Nov 2020 23:33:23 -0600 Subject: vhost scsi: Add support for LUN resets. In newer versions of virtio-scsi we just reset the timer when an a command times out, so TMFs are never sent for the cmd time out case. However, in older kernels and for the TMF inject cases, we can still get resets and we end up just failing immediately so the guest might see the device get offlined and IO errors. For the older kernel cases, we want the same end result as the modern virtio-scsi driver where we let the lower levels fire their error handling and handle the problem. And at the upper levels we want to wait. This patch ties the LUN reset handling into the LIO TMF code which will just wait for outstanding commands to complete like we are doing in the modern virtio-scsi case. Note: I did not handle the ABORT case to keep this simple. For ABORTs LIO just waits on the cmd like how it does for the RESET case. If an ABORT fails, the guest OS ends up escalating to LUN RESET, so in the end we get the same behavior where we wait on the outstanding cmds. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/1604986403-4931-6-git-send-email-michael.christie@oracle.com Signed-off-by: Michael S. Tsirkin Acked-by: Stefan Hajnoczi --- drivers/vhost/scsi.c | 147 ++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 134 insertions(+), 13 deletions(-) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index ed7dc6b998f6..f22fce549862 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -139,6 +139,7 @@ struct vhost_scsi_tpg { struct se_portal_group se_tpg; /* Pointer back to vhost_scsi, protected by tv_tpg_mutex */ struct vhost_scsi *vhost_scsi; + struct list_head tmf_queue; }; struct vhost_scsi_tport { @@ -211,6 +212,20 @@ struct vhost_scsi { int vs_events_nr; /* num of pending events, protected by vq->mutex */ }; +struct vhost_scsi_tmf { + struct vhost_work vwork; + struct vhost_scsi_tpg *tpg; + struct vhost_scsi *vhost; + struct vhost_scsi_virtqueue *svq; + struct list_head queue_entry; + + struct se_cmd se_cmd; + struct vhost_scsi_inflight *inflight; + struct iovec resp_iov; + int in_iovs; + int vq_desc; +}; + /* * Context for processing request and control queue operations. */ @@ -344,14 +359,32 @@ static void vhost_scsi_release_cmd_res(struct se_cmd *se_cmd) vhost_scsi_put_inflight(inflight); } +static void vhost_scsi_release_tmf_res(struct vhost_scsi_tmf *tmf) +{ + struct vhost_scsi_tpg *tpg = tmf->tpg; + struct vhost_scsi_inflight *inflight = tmf->inflight; + + mutex_lock(&tpg->tv_tpg_mutex); + list_add_tail(&tpg->tmf_queue, &tmf->queue_entry); + mutex_unlock(&tpg->tv_tpg_mutex); + vhost_scsi_put_inflight(inflight); +} + static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) { - struct vhost_scsi_cmd *cmd = container_of(se_cmd, + if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) { + struct vhost_scsi_tmf *tmf = container_of(se_cmd, + struct vhost_scsi_tmf, se_cmd); + + vhost_work_queue(&tmf->vhost->dev, &tmf->vwork); + } else { + struct vhost_scsi_cmd *cmd = container_of(se_cmd, struct vhost_scsi_cmd, tvc_se_cmd); - struct vhost_scsi *vs = cmd->tvc_vhost; + struct vhost_scsi *vs = cmd->tvc_vhost; - llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list); - vhost_work_queue(&vs->dev, &vs->vs_completion_work); + llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list); + vhost_work_queue(&vs->dev, &vs->vs_completion_work); + } } static u32 vhost_scsi_sess_get_index(struct se_session *se_sess) @@ -390,7 +423,10 @@ static int vhost_scsi_queue_status(struct se_cmd *se_cmd) static void vhost_scsi_queue_tm_rsp(struct se_cmd *se_cmd) { - return; + struct vhost_scsi_tmf *tmf = container_of(se_cmd, struct vhost_scsi_tmf, + se_cmd); + + transport_generic_free_cmd(&tmf->se_cmd, 0); } static void vhost_scsi_aborted_task(struct se_cmd *se_cmd) @@ -1120,9 +1156,9 @@ out: } static void -vhost_scsi_send_tmf_reject(struct vhost_scsi *vs, - struct vhost_virtqueue *vq, - struct vhost_scsi_ctx *vc) +vhost_scsi_send_tmf_resp(struct vhost_scsi *vs, struct vhost_virtqueue *vq, + int in_iovs, int vq_desc, struct iovec *resp_iov, + int tmf_resp_code) { struct virtio_scsi_ctrl_tmf_resp rsp; struct iov_iter iov_iter; @@ -1130,17 +1166,87 @@ vhost_scsi_send_tmf_reject(struct vhost_scsi *vs, pr_debug("%s\n", __func__); memset(&rsp, 0, sizeof(rsp)); - rsp.response = VIRTIO_SCSI_S_FUNCTION_REJECTED; + rsp.response = tmf_resp_code; - iov_iter_init(&iov_iter, READ, &vq->iov[vc->out], vc->in, sizeof(rsp)); + iov_iter_init(&iov_iter, READ, resp_iov, in_iovs, sizeof(rsp)); ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter); if (likely(ret == sizeof(rsp))) - vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0); + vhost_add_used_and_signal(&vs->dev, vq, vq_desc, 0); else pr_err("Faulted on virtio_scsi_ctrl_tmf_resp\n"); } +static void vhost_scsi_tmf_resp_work(struct vhost_work *work) +{ + struct vhost_scsi_tmf *tmf = container_of(work, struct vhost_scsi_tmf, + vwork); + int resp_code; + + if (tmf->se_cmd.se_tmr_req->response == TMR_FUNCTION_COMPLETE) + resp_code = VIRTIO_SCSI_S_FUNCTION_SUCCEEDED; + else + resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED; + + vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs, + tmf->vq_desc, &tmf->resp_iov, resp_code); + vhost_scsi_release_tmf_res(tmf); +} + +static void +vhost_scsi_handle_tmf(struct vhost_scsi *vs, struct vhost_scsi_tpg *tpg, + struct vhost_virtqueue *vq, + struct virtio_scsi_ctrl_tmf_req *vtmf, + struct vhost_scsi_ctx *vc) +{ + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_tmf *tmf; + + if (vhost32_to_cpu(vq, vtmf->subtype) != + VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET) + goto send_reject; + + if (!tpg->tpg_nexus || !tpg->tpg_nexus->tvn_se_sess) { + pr_err("Unable to locate active struct vhost_scsi_nexus for LUN RESET.\n"); + goto send_reject; + } + + mutex_lock(&tpg->tv_tpg_mutex); + if (list_empty(&tpg->tmf_queue)) { + pr_err("Missing reserve TMF. Could not handle LUN RESET.\n"); + mutex_unlock(&tpg->tv_tpg_mutex); + goto send_reject; + } + + tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf, + queue_entry); + list_del_init(&tmf->queue_entry); + mutex_unlock(&tpg->tv_tpg_mutex); + + tmf->tpg = tpg; + tmf->vhost = vs; + tmf->svq = svq; + tmf->resp_iov = vq->iov[vc->out]; + tmf->vq_desc = vc->head; + tmf->in_iovs = vc->in; + tmf->inflight = vhost_scsi_get_inflight(vq); + + if (target_submit_tmr(&tmf->se_cmd, tpg->tpg_nexus->tvn_se_sess, NULL, + vhost_buf_to_lun(vtmf->lun), NULL, + TMR_LUN_RESET, GFP_KERNEL, 0, + TARGET_SCF_ACK_KREF) < 0) { + vhost_scsi_release_tmf_res(tmf); + goto send_reject; + } + + return; + +send_reject: + vhost_scsi_send_tmf_resp(vs, vq, vc->in, vc->head, &vq->iov[vc->out], + VIRTIO_SCSI_S_FUNCTION_REJECTED); +} + static void vhost_scsi_send_an_resp(struct vhost_scsi *vs, struct vhost_virtqueue *vq, @@ -1166,6 +1272,7 @@ vhost_scsi_send_an_resp(struct vhost_scsi *vs, static void vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) { + struct vhost_scsi_tpg *tpg; union { __virtio32 type; struct virtio_scsi_ctrl_an_req an; @@ -1247,12 +1354,12 @@ vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) vc.req += typ_size; vc.req_size -= typ_size; - ret = vhost_scsi_get_req(vq, &vc, NULL); + ret = vhost_scsi_get_req(vq, &vc, &tpg); if (ret) goto err; if (v_req.type == VIRTIO_SCSI_T_TMF) - vhost_scsi_send_tmf_reject(vs, vq, &vc); + vhost_scsi_handle_tmf(vs, tpg, vq, &v_req.tmf, &vc); else vhost_scsi_send_an_resp(vs, vq, &vc); err: @@ -1913,11 +2020,19 @@ static int vhost_scsi_port_link(struct se_portal_group *se_tpg, { struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); + struct vhost_scsi_tmf *tmf; + + tmf = kzalloc(sizeof(*tmf), GFP_KERNEL); + if (!tmf) + return -ENOMEM; + INIT_LIST_HEAD(&tmf->queue_entry); + vhost_work_init(&tmf->vwork, vhost_scsi_tmf_resp_work); mutex_lock(&vhost_scsi_mutex); mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count++; + list_add_tail(&tmf->queue_entry, &tpg->tmf_queue); mutex_unlock(&tpg->tv_tpg_mutex); vhost_scsi_hotplug(tpg, lun); @@ -1932,11 +2047,16 @@ static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg, { struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); + struct vhost_scsi_tmf *tmf; mutex_lock(&vhost_scsi_mutex); mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count--; + tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf, + queue_entry); + list_del(&tmf->queue_entry); + kfree(tmf); mutex_unlock(&tpg->tv_tpg_mutex); vhost_scsi_hotunplug(tpg, lun); @@ -2197,6 +2317,7 @@ vhost_scsi_make_tpg(struct se_wwn *wwn, const char *name) } mutex_init(&tpg->tv_tpg_mutex); INIT_LIST_HEAD(&tpg->tv_tpg_list); + INIT_LIST_HEAD(&tpg->tmf_queue); tpg->tport = tport; tpg->tport_tpgt = tpgt; -- cgit v1.2.3 From 575cba20c421ecb6b563ae352e4e0468e4ca8b3c Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 14 Nov 2020 21:47:43 +1000 Subject: powerpc/64s: Fix KVM system reset handling when CONFIG_PPC_PSERIES=y pseries guest kernels have a FWNMI handler for SRESET and MCE NMIs, which is basically the same as the regular handlers for those interrupts. The system reset FWNMI handler did not have a KVM guest test in it, although it probably should have because the guest can itself run guests. Commit 4f50541f6703b ("powerpc/64s/exception: Move all interrupt handlers to new style code gen macros") convert the handler faithfully to avoid a KVM test with a "clever" trick to modify the IKVM_REAL setting to 0 when the fwnmi handler is to be generated (PPC_PSERIES=y). This worked when the KVM test was generated in the interrupt entry handlers, but a later patch moved the KVM test to the common handler, and the common handler macro is expanded below the fwnmi entry. This prevents the KVM test from being generated even for the 0x100 entry point as well. The result is NMI IPIs in the host kernel when a guest is running will use gest registers. This goes particularly badly when an HPT guest is running and the MMU is set to guest mode. Remove this trickery and just generate the test always. Fixes: 9600f261acaa ("powerpc/64s/exception: Move KVM test to common code") Cc: stable@vger.kernel.org # v5.7+ Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201114114743.3306283-1-npiggin@gmail.com --- arch/powerpc/kernel/exceptions-64s.S | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index f7d748b88705..07d64883c0b5 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1000,8 +1000,6 @@ TRAMP_REAL_BEGIN(system_reset_idle_wake) * Vectors for the FWNMI option. Share common code. */ TRAMP_REAL_BEGIN(system_reset_fwnmi) - /* XXX: fwnmi guest could run a nested/PR guest, so why no test? */ - __IKVM_REAL(system_reset)=0 GEN_INT_ENTRY system_reset, virt=0 #endif /* CONFIG_PPC_PSERIES */ -- cgit v1.2.3 From 4bbf439b09c5ac3f8b3e9584fe080375d8d0ad2d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 12 Nov 2020 14:40:37 -0500 Subject: fix return values of seq_read_iter() Unlike ->read(), ->read_iter() instances *must* return the amount of data they'd left in iterator. For ->read() returning less than it has actually copied is a QoI issue; read(fd, unmapped_page - 5, 8) is allowed to fill all 5 bytes of destination and return 4; it's not nice to caller, but POSIX allows pretty much anything in such situation, up to and including a SIGSEGV. generic_file_splice_read() uses pipe-backed iterator as destination; there a short copy comes from pipe being full, not from running into an un{mapped,writable} page in the middle of destination as we have for iovec-backed iterators read(2) uses. And there we rely upon the ->read_iter() reporting the actual amount it has left in destination. Conversion of a ->read() instance into ->read_iter() has to watch out for that. If you really need an "all or nothing" kind of behaviour somewhere, you need to do iov_iter_revert() to prune the partial copy. In case of seq_read_iter() we can handle short copy just fine; the data is in m->buf and next call will fetch it from there. Fixes: d4d50710a8b4 (seq_file: add seq_read_iter) Tested-by: Nathan Chancellor Signed-off-by: Al Viro --- fs/seq_file.c | 57 +++++++++++++++++++++++++++------------------------------ 1 file changed, 27 insertions(+), 30 deletions(-) diff --git a/fs/seq_file.c b/fs/seq_file.c index 3b20e21604e7..03a369ccd28c 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -168,12 +168,14 @@ EXPORT_SYMBOL(seq_read); ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct seq_file *m = iocb->ki_filp->private_data; - size_t size = iov_iter_count(iter); size_t copied = 0; size_t n; void *p; int err = 0; + if (!iov_iter_count(iter)) + return 0; + mutex_lock(&m->lock); /* @@ -206,36 +208,34 @@ ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter) if (!m->buf) goto Enomem; } - /* if not empty - flush it first */ + // something left in the buffer - copy it out first if (m->count) { - n = min(m->count, size); - if (copy_to_iter(m->buf + m->from, n, iter) != n) - goto Efault; + n = copy_to_iter(m->buf + m->from, m->count, iter); m->count -= n; m->from += n; - size -= n; copied += n; - if (!size) + if (m->count) // hadn't managed to copy everything goto Done; } - /* we need at least one record in buffer */ + // get a non-empty record in the buffer m->from = 0; p = m->op->start(m, &m->index); while (1) { err = PTR_ERR(p); - if (!p || IS_ERR(p)) + if (!p || IS_ERR(p)) // EOF or an error break; err = m->op->show(m, p); - if (err < 0) + if (err < 0) // hard error break; - if (unlikely(err)) + if (unlikely(err)) // ->show() says "skip it" m->count = 0; - if (unlikely(!m->count)) { + if (unlikely(!m->count)) { // empty record p = m->op->next(m, p, &m->index); continue; } - if (m->count < m->size) + if (!seq_has_overflowed(m)) // got it goto Fill; + // need a bigger buffer m->op->stop(m, p); kvfree(m->buf); m->count = 0; @@ -244,11 +244,14 @@ ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter) goto Enomem; p = m->op->start(m, &m->index); } + // EOF or an error m->op->stop(m, p); m->count = 0; goto Done; Fill: - /* they want more? let's try to get some more */ + // one non-empty record is in the buffer; if they want more, + // try to fit more in, but in any case we need to advance + // the iterator once for every record shown. while (1) { size_t offs = m->count; loff_t pos = m->index; @@ -259,30 +262,27 @@ Fill: m->op->next); m->index++; } - if (!p || IS_ERR(p)) { - err = PTR_ERR(p); + if (!p || IS_ERR(p)) // no next record for us break; - } - if (m->count >= size) + if (m->count >= iov_iter_count(iter)) break; err = m->op->show(m, p); - if (seq_has_overflowed(m) || err) { + if (err > 0) { // ->show() says "skip it" m->count = offs; - if (likely(err <= 0)) - break; + } else if (err || seq_has_overflowed(m)) { + m->count = offs; + break; } } m->op->stop(m, p); - n = min(m->count, size); - if (copy_to_iter(m->buf, n, iter) != n) - goto Efault; + n = copy_to_iter(m->buf, m->count, iter); copied += n; m->count -= n; m->from = n; Done: - if (!copied) - copied = err; - else { + if (unlikely(!copied)) { + copied = m->count ? -EFAULT : err; + } else { iocb->ki_pos += copied; m->read_pos += copied; } @@ -291,9 +291,6 @@ Done: Enomem: err = -ENOMEM; goto Done; -Efault: - err = -EFAULT; - goto Done; } EXPORT_SYMBOL(seq_read_iter); -- cgit v1.2.3 From 98128572084c3dd8067f48bb588aa3733d1355b5 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Mon, 9 Nov 2020 17:35:33 +0900 Subject: cifs: fix a memleak with modefromsid kmemleak reported a memory leak allocated in query_info() when cifs is working with modefromsid. backtrace: [<00000000aeef6a1e>] slab_post_alloc_hook+0x58/0x510 [<00000000b2f7a440>] __kmalloc+0x1a0/0x390 [<000000006d470ebc>] query_info+0x5b5/0x700 [cifs] [<00000000bad76ce0>] SMB2_query_acl+0x2b/0x30 [cifs] [<000000001fa09606>] get_smb2_acl_by_path+0x2f3/0x720 [cifs] [<000000001b6ebab7>] get_smb2_acl+0x75/0x90 [cifs] [<00000000abf43904>] cifs_acl_to_fattr+0x13b/0x1d0 [cifs] [<00000000a5372ec3>] cifs_get_inode_info+0x4cd/0x9a0 [cifs] [<00000000388e0a04>] cifs_revalidate_dentry_attr+0x1cd/0x510 [cifs] [<0000000046b6b352>] cifs_getattr+0x8a/0x260 [cifs] [<000000007692c95e>] vfs_getattr_nosec+0xa1/0xc0 [<00000000cbc7d742>] vfs_getattr+0x36/0x40 [<00000000de8acf67>] vfs_statx_fd+0x4a/0x80 [<00000000a58c6adb>] __do_sys_newfstat+0x31/0x70 [<00000000300b3b4e>] __x64_sys_newfstat+0x16/0x20 [<000000006d8e9c48>] do_syscall_64+0x37/0x80 This patch add missing kfree for pntsd when mounting modefromsid option. Cc: Stable # v5.4+ Signed-off-by: Namjae Jeon Reviewed-by: Aurelien Aptel Signed-off-by: Steve French --- fs/cifs/cifsacl.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 23b21e943652..ef4784e72b1d 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1266,6 +1266,7 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc); } else if (mode_from_special_sid) { rc = parse_sec_desc(cifs_sb, pntsd, acllen, fattr, true); + kfree(pntsd); } else { /* get approximated mode from ACL */ rc = parse_sec_desc(cifs_sb, pntsd, acllen, fattr, false); -- cgit v1.2.3 From de9ac0a6e9efdffc8cde18781f48fb56ca4157b7 Mon Sep 17 00:00:00 2001 From: Rohith Surabattula Date: Wed, 28 Oct 2020 13:42:21 +0000 Subject: smb3: Call cifs reconnect from demultiplex thread cifs_reconnect needs to be called only from demultiplex thread. skip cifs_reconnect in offload thread. So, cifs_reconnect will be called by demultiplex thread in subsequent request. These patches address a problem found during decryption offload: CIFS: VFS: trying to dequeue a deleted mid that can cause a refcount use after free: [ 1271.389453] Workqueue: smb3decryptd smb2_decrypt_offload [cifs] [ 1271.389456] RIP: 0010:refcount_warn_saturate+0xae/0xf0 [ 1271.389457] Code: fa 1d 6a 01 01 e8 c7 44 b1 ff 0f 0b 5d c3 80 3d e7 1d 6a 01 00 75 91 48 c7 c7 d8 be 1d a2 c6 05 d7 1d 6a 01 01 e8 a7 44 b1 ff <0f> 0b 5d c3 80 3d c5 1d 6a 01 00 0f 85 6d ff ff ff 48 c7 c7 30 bf [ 1271.389458] RSP: 0018:ffffa4cdc1f87e30 EFLAGS: 00010286 [ 1271.389458] RAX: 0000000000000000 RBX: ffff9974d2809f00 RCX: ffff9974df898cc8 [ 1271.389459] RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffff9974df898cc0 [ 1271.389460] RBP: ffffa4cdc1f87e30 R08: 0000000000000004 R09: 00000000000002c0 [ 1271.389460] R10: 0000000000000000 R11: 0000000000000001 R12: ffff9974b7fdb5c0 [ 1271.389461] R13: ffff9974d2809f00 R14: ffff9974ccea0a80 R15: ffff99748e60db80 [ 1271.389462] FS: 0000000000000000(0000) GS:ffff9974df880000(0000) knlGS:0000000000000000 [ 1271.389462] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1271.389463] CR2: 000055c60f344fe4 CR3: 0000001031a3c002 CR4: 00000000003706e0 [ 1271.389465] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1271.389465] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1271.389466] Call Trace: [ 1271.389483] cifs_mid_q_entry_release+0xce/0x110 [cifs] [ 1271.389499] smb2_decrypt_offload+0xa9/0x1c0 [cifs] [ 1271.389501] process_one_work+0x1e8/0x3b0 [ 1271.389503] worker_thread+0x50/0x370 [ 1271.389504] kthread+0x12f/0x150 [ 1271.389506] ? process_one_work+0x3b0/0x3b0 [ 1271.389507] ? __kthread_bind_mask+0x70/0x70 [ 1271.389509] ret_from_fork+0x22/0x30 Signed-off-by: Rohith Surabattula Reviewed-by: Pavel Shilovsky CC: Stable #5.4+ Signed-off-by: Steve French --- fs/cifs/smb2ops.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 504766cb6c19..efedec2b66c6 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -4356,7 +4356,8 @@ init_read_bvec(struct page **pages, unsigned int npages, unsigned int data_size, static int handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, char *buf, unsigned int buf_len, struct page **pages, - unsigned int npages, unsigned int page_data_size) + unsigned int npages, unsigned int page_data_size, + bool is_offloaded) { unsigned int data_offset; unsigned int data_len; @@ -4378,7 +4379,8 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, if (server->ops->is_session_expired && server->ops->is_session_expired(buf)) { - cifs_reconnect(server); + if (!is_offloaded) + cifs_reconnect(server); return -1; } @@ -4518,7 +4520,8 @@ static void smb2_decrypt_offload(struct work_struct *work) mid->decrypted = true; rc = handle_read_data(dw->server, mid, dw->buf, dw->server->vals->read_rsp_size, - dw->ppages, dw->npages, dw->len); + dw->ppages, dw->npages, dw->len, + true); mid->callback(mid); cifs_mid_q_entry_release(mid); } @@ -4622,7 +4625,7 @@ non_offloaded_decrypt: (*mid)->decrypted = true; rc = handle_read_data(server, *mid, buf, server->vals->read_rsp_size, - pages, npages, len); + pages, npages, len, false); } free_pages: @@ -4765,7 +4768,7 @@ smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid) char *buf = server->large_buf ? server->bigbuf : server->smallbuf; return handle_read_data(server, mid, buf, server->pdu_size, - NULL, 0, 0); + NULL, 0, 0, false); } static int -- cgit v1.2.3 From ac873aa3dc21707c47db5db6608b38981c731afe Mon Sep 17 00:00:00 2001 From: Rohith Surabattula Date: Thu, 29 Oct 2020 05:03:10 +0000 Subject: smb3: Avoid Mid pending list corruption When reconnect happens Mid queue can be corrupted when both demultiplex and offload thread try to dequeue the MID from the pending list. These patches address a problem found during decryption offload: CIFS: VFS: trying to dequeue a deleted mid that could cause a refcount use after free: Workqueue: smb3decryptd smb2_decrypt_offload [cifs] Signed-off-by: Rohith Surabattula Reviewed-by: Pavel Shilovsky CC: Stable #5.4+ Signed-off-by: Steve French --- fs/cifs/smb2ops.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 46 insertions(+), 9 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index efedec2b66c6..b3b2abbb49b9 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -264,7 +264,7 @@ smb2_revert_current_mid(struct TCP_Server_Info *server, const unsigned int val) } static struct mid_q_entry * -smb2_find_mid(struct TCP_Server_Info *server, char *buf) +__smb2_find_mid(struct TCP_Server_Info *server, char *buf, bool dequeue) { struct mid_q_entry *mid; struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf; @@ -281,6 +281,10 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf) (mid->mid_state == MID_REQUEST_SUBMITTED) && (mid->command == shdr->Command)) { kref_get(&mid->refcount); + if (dequeue) { + list_del_init(&mid->qhead); + mid->mid_flags |= MID_DELETED; + } spin_unlock(&GlobalMid_Lock); return mid; } @@ -289,6 +293,18 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf) return NULL; } +static struct mid_q_entry * +smb2_find_mid(struct TCP_Server_Info *server, char *buf) +{ + return __smb2_find_mid(server, buf, false); +} + +static struct mid_q_entry * +smb2_find_dequeue_mid(struct TCP_Server_Info *server, char *buf) +{ + return __smb2_find_mid(server, buf, true); +} + static void smb2_dump_detail(void *buf, struct TCP_Server_Info *server) { @@ -4404,7 +4420,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, cifs_dbg(FYI, "%s: server returned error %d\n", __func__, rdata->result); /* normal error on read response */ - dequeue_mid(mid, false); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_RECEIVED; + else + dequeue_mid(mid, false); return 0; } @@ -4428,7 +4447,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, cifs_dbg(FYI, "%s: data offset (%u) beyond end of smallbuf\n", __func__, data_offset); rdata->result = -EIO; - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } @@ -4444,21 +4466,30 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, cifs_dbg(FYI, "%s: data offset (%u) beyond 1st page of response\n", __func__, data_offset); rdata->result = -EIO; - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } if (data_len > page_data_size - pad_len) { /* data_len is corrupt -- discard frame */ rdata->result = -EIO; - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } rdata->result = init_read_bvec(pages, npages, page_data_size, cur_off, &bvec); if (rdata->result != 0) { - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } @@ -4473,7 +4504,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, /* read response payload cannot be in both buf and pages */ WARN_ONCE(1, "buf can not contain only a part of read data"); rdata->result = -EIO; - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } @@ -4484,7 +4518,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, if (length < 0) return length; - dequeue_mid(mid, false); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_RECEIVED; + else + dequeue_mid(mid, false); return length; } @@ -4513,7 +4550,7 @@ static void smb2_decrypt_offload(struct work_struct *work) } dw->server->lstrp = jiffies; - mid = smb2_find_mid(dw->server, dw->buf); + mid = smb2_find_dequeue_mid(dw->server, dw->buf); if (mid == NULL) cifs_dbg(FYI, "mid not found\n"); else { -- cgit v1.2.3 From 1254100030b3377e8302f9c75090ab191d73ee7c Mon Sep 17 00:00:00 2001 From: Rohith Surabattula Date: Thu, 29 Oct 2020 06:07:56 +0000 Subject: smb3: Handle error case during offload read path Mid callback needs to be called only when valid data is read into pages. These patches address a problem found during decryption offload: CIFS: VFS: trying to dequeue a deleted mid that could cause a refcount use after free: Workqueue: smb3decryptd smb2_decrypt_offload [cifs] Signed-off-by: Rohith Surabattula Reviewed-by: Pavel Shilovsky CC: Stable #5.4+ Signed-off-by: Steve French --- fs/cifs/smb2ops.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index b3b2abbb49b9..dab94f67c988 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -4559,7 +4559,25 @@ static void smb2_decrypt_offload(struct work_struct *work) dw->server->vals->read_rsp_size, dw->ppages, dw->npages, dw->len, true); - mid->callback(mid); + if (rc >= 0) { +#ifdef CONFIG_CIFS_STATS2 + mid->when_received = jiffies; +#endif + mid->callback(mid); + } else { + spin_lock(&GlobalMid_Lock); + if (dw->server->tcpStatus == CifsNeedReconnect) { + mid->mid_state = MID_RETRY_NEEDED; + spin_unlock(&GlobalMid_Lock); + mid->callback(mid); + } else { + mid->mid_state = MID_REQUEST_SUBMITTED; + mid->mid_flags &= ~(MID_DELETED); + list_add_tail(&mid->qhead, + &dw->server->pending_mid_q); + spin_unlock(&GlobalMid_Lock); + } + } cifs_mid_q_entry_release(mid); } -- cgit v1.2.3 From 78e91588510919a0dc9bd48916e760c1ba5797d2 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Tue, 3 Nov 2020 19:23:27 +0800 Subject: usb: cdns3: gadget: initialize link_trb as NULL There is an uninitialized variable "link_trb" usage at function cdns3_ep_run_transfer. Fixed it by initialize "link_trb" as NULL. Fixes: 4e218882eb5a ("usb: cdns3: gadget: improve the dump TRB operation at cdns3_ep_run_transfer") Reported-by: Dan Carpenter Signed-off-by: Peter Chen --- drivers/usb/cdns3/gadget.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c index 66c1e6723eb1..1ee6d3941dd4 100644 --- a/drivers/usb/cdns3/gadget.c +++ b/drivers/usb/cdns3/gadget.c @@ -1114,7 +1114,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, struct cdns3_device *priv_dev = priv_ep->cdns3_dev; struct cdns3_request *priv_req; struct cdns3_trb *trb; - struct cdns3_trb *link_trb; + struct cdns3_trb *link_trb = NULL; dma_addr_t trb_dma; u32 togle_pcs = 1; int sg_iter = 0; -- cgit v1.2.3 From 40252dd7cf7cad81c784c695c36bc475b518f0ea Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Tue, 3 Nov 2020 22:16:00 +0800 Subject: usb: cdns3: gadget: calculate TD_SIZE based on TD The TRB entry TD_SIZE is the packet number for the TD (request) but not the each TRB, so it only needs to be assigned for the first TRB during the TD, and the value of it is for TD too. Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver") Signed-off-by: Peter Chen --- drivers/usb/cdns3/gadget.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c index 1ee6d3941dd4..365f30fb1159 100644 --- a/drivers/usb/cdns3/gadget.c +++ b/drivers/usb/cdns3/gadget.c @@ -1193,10 +1193,20 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, /* set incorrect Cycle Bit for first trb*/ control = priv_ep->pcs ? 0 : TRB_CYCLE; + trb->length = 0; + if (priv_dev->dev_ver >= DEV_VER_V2) { + u16 td_size; + + td_size = DIV_ROUND_UP(request->length, + priv_ep->endpoint.maxpacket); + if (priv_dev->gadget.speed == USB_SPEED_SUPER) + trb->length = TRB_TDL_SS_SIZE(td_size); + else + control |= TRB_TDL_HS_SIZE(td_size); + } do { u32 length; - u16 td_size = 0; /* fill TRB */ control |= TRB_TYPE(TRB_NORMAL); @@ -1208,20 +1218,12 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, length = request->length; } - if (likely(priv_dev->dev_ver >= DEV_VER_V2)) - td_size = DIV_ROUND_UP(length, - priv_ep->endpoint.maxpacket); - else if (priv_ep->flags & EP_TDLCHK_EN) + if (priv_ep->flags & EP_TDLCHK_EN) total_tdl += DIV_ROUND_UP(length, priv_ep->endpoint.maxpacket); - trb->length = cpu_to_le32(TRB_BURST_LEN(priv_ep->trb_burst_size) | + trb->length |= cpu_to_le32(TRB_BURST_LEN(priv_ep->trb_burst_size) | TRB_LEN(length)); - if (priv_dev->gadget.speed == USB_SPEED_SUPER) - trb->length |= cpu_to_le32(TRB_TDL_SS_SIZE(td_size)); - else - control |= TRB_TDL_HS_SIZE(td_size); - pcs = priv_ep->pcs ? TRB_CYCLE : 0; /* -- cgit v1.2.3 From 231655eb55b0f9899054dec9432482dbf986a9c5 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 10 Nov 2020 15:46:00 +0100 Subject: phy: intel: PHY_INTEL_KEEMBAY_EMMC should depend on ARCH_KEEMBAY The Intel Keem Bay eMMC PHY is only present on Intel Keem Bay SoCs. Hence add a dependency on ARCH_KEEMBAY, to prevent asking the user about this driver when configuring a kernel without Intel Keem Bay platform support. Fixes: 885c4f4d6cf448f6 ("phy: intel: Add Keem Bay eMMC PHY support") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20201110144600.3279752-1-geert+renesas@glider.be Signed-off-by: Vinod Koul --- drivers/phy/intel/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/phy/intel/Kconfig b/drivers/phy/intel/Kconfig index 58ec695c92ec..62c24764654b 100644 --- a/drivers/phy/intel/Kconfig +++ b/drivers/phy/intel/Kconfig @@ -4,7 +4,7 @@ # config PHY_INTEL_KEEMBAY_EMMC tristate "Intel Keem Bay EMMC PHY driver" - depends on (OF && ARM64) || COMPILE_TEST + depends on ARCH_KEEMBAY || COMPILE_TEST depends on HAS_IOMEM select GENERIC_PHY select REGMAP_MMIO -- cgit v1.2.3 From 44786a26a7485e12a1d2aaad2adfb3c82f6ad171 Mon Sep 17 00:00:00 2001 From: Bryan O'Donoghue Date: Fri, 13 Nov 2020 15:12:24 +0000 Subject: phy: qualcomm: usb: Fix SuperSpeed PHY OF dependency This Kconfig entry should declare a dependency on OF Fixes: 6076967a500c ("phy: qualcomm: usb: Add SuperSpeed PHY driver") Reported-by: kernel test robot Link: https://lkml.org/lkml/2020/11/13/414 Signed-off-by: Bryan O'Donoghue Link: https://lore.kernel.org/r/20201113151225.1657600-2-bryan.odonoghue@linaro.org Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/phy/qualcomm/Kconfig b/drivers/phy/qualcomm/Kconfig index 928db510b86c..9129c4b8bb9b 100644 --- a/drivers/phy/qualcomm/Kconfig +++ b/drivers/phy/qualcomm/Kconfig @@ -98,7 +98,7 @@ config PHY_QCOM_USB_HS_28NM config PHY_QCOM_USB_SS tristate "Qualcomm USB Super-Speed PHY driver" - depends on ARCH_QCOM || COMPILE_TEST + depends on OF && (ARCH_QCOM || COMPILE_TEST) depends on EXTCON || !EXTCON # if EXTCON=m, this cannot be built-in select GENERIC_PHY help -- cgit v1.2.3 From 14839107b51cc0db19579039b1f72cba7a0c8049 Mon Sep 17 00:00:00 2001 From: Bryan O'Donoghue Date: Fri, 13 Nov 2020 15:12:25 +0000 Subject: phy: qualcomm: Fix 28 nm Hi-Speed USB PHY OF dependency This Kconfig entry should declare a dependency on OF Fixes: 67b27dbeac4d ("phy: qualcomm: Add Synopsys 28nm Hi-Speed USB PHY driver") Signed-off-by: Bryan O'Donoghue Link: https://lore.kernel.org/r/20201113151225.1657600-3-bryan.odonoghue@linaro.org Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/phy/qualcomm/Kconfig b/drivers/phy/qualcomm/Kconfig index 9129c4b8bb9b..7f6fcb8ec5ba 100644 --- a/drivers/phy/qualcomm/Kconfig +++ b/drivers/phy/qualcomm/Kconfig @@ -87,7 +87,7 @@ config PHY_QCOM_USB_HSIC config PHY_QCOM_USB_HS_28NM tristate "Qualcomm 28nm High-Speed PHY" - depends on ARCH_QCOM || COMPILE_TEST + depends on OF && (ARCH_QCOM || COMPILE_TEST) depends on EXTCON || !EXTCON # if EXTCON=m, this cannot be built-in select GENERIC_PHY help -- cgit v1.2.3 From fb89b2544b645527b3a359176999a416e65f5ada Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Sat, 14 Nov 2020 12:05:18 +0000 Subject: phy: mediatek: fix spelling mistake in Kconfig "veriosn" -> "version" There is a spelling mistake in the Kconfig. Fix it. Signed-off-by: Colin Ian King Link: https://lore.kernel.org/r/20201114120518.416120-1-colin.king@canonical.com Signed-off-by: Vinod Koul --- drivers/phy/mediatek/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/phy/mediatek/Kconfig b/drivers/phy/mediatek/Kconfig index 50c5e9306e19..c8126bde9d7c 100644 --- a/drivers/phy/mediatek/Kconfig +++ b/drivers/phy/mediatek/Kconfig @@ -12,7 +12,7 @@ config PHY_MTK_TPHY it supports multiple usb2.0, usb3.0 ports, PCIe and SATA, and meanwhile supports two version T-PHY which have different banks layout, the T-PHY with shared banks between - multi-ports is first version, otherwise is second veriosn, + multi-ports is first version, otherwise is second version, so you can easily distinguish them by banks layout. config PHY_MTK_UFS -- cgit v1.2.3 From e5633b95dce915c2ade5ce1c90d295d555396c60 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Sun, 15 Nov 2020 23:38:42 +0800 Subject: ALSA: usb-audio: Use ALC1220-VB-DT mapping for ASUS ROG Strix TRX40 mobo ASUS ROG Strix also uses ALC1220-VB-DT, so adjust the mapping and add profile name to let userspace pick correct UCM profile. BugLink: https://gitlab.freedesktop.org/pulseaudio/pulseaudio/-/issues/1031 Signed-off-by: Kai-Heng Feng Link: https://lore.kernel.org/r/20201115153843.1109200-1-kai.heng.feng@canonical.com Signed-off-by: Takashi Iwai --- sound/usb/card.c | 4 ++++ sound/usb/mixer_maps.c | 3 ++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/sound/usb/card.c b/sound/usb/card.c index fa764b61fe9c..4457214a3ae6 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -379,6 +379,10 @@ static const struct usb_audio_device_name usb_audio_names[] = { DEVICE_NAME(0x046d, 0x0990, "Logitech, Inc.", "QuickCam Pro 9000"), + /* ASUS ROG Strix */ + PROFILE_NAME(0x0b05, 0x1917, + "Realtek", "ALC1220-VB-DT", "Realtek-ALC1220-VB-Desktop"), + /* Dell WD15 Dock */ PROFILE_NAME(0x0bda, 0x4014, "Dell", "WD15 Dock", "Dell-WD15-Dock"), /* Dell WD19 Dock */ diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index c369c81e74c4..a7212f16660e 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -561,7 +561,8 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { }, { /* ASUS ROG Strix */ .id = USB_ID(0x0b05, 0x1917), - .map = asus_rog_map, + .map = trx40_mobo_map, + .connector_map = trx40_mobo_connector_map, }, { /* MSI TRX40 Creator */ .id = USB_ID(0x0db0, 0x0d64), -- cgit v1.2.3 From 24880a87042b3032a6ac04d79cb51892c5a7901d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 15 Nov 2020 20:06:53 -0800 Subject: usb: typec: qcom-pmic-typec: fix builtin build errors Fix build errors when CONFIG_TYPEC_QCOM_PMIC=y and CONFIG_USB_ROLE_SWITCH=m by limiting the former to =m when USB_ROLE_SWITCH also =m. powerpc64-linux-ld: drivers/usb/typec/qcom-pmic-typec.o: in function `.qcom_pmic_typec_remove': qcom-pmic-typec.c:(.text+0x28): undefined reference to `.usb_role_switch_set_role' powerpc64-linux-ld: qcom-pmic-typec.c:(.text+0x64): undefined reference to `.usb_role_switch_put' powerpc64-linux-ld: drivers/usb/typec/qcom-pmic-typec.o: in function `.qcom_pmic_typec_check_connection': qcom-pmic-typec.c:(.text+0x120): undefined reference to `.usb_role_switch_set_role' powerpc64-linux-ld: drivers/usb/typec/qcom-pmic-typec.o: in function `.qcom_pmic_typec_probe': qcom-pmic-typec.c:(.text+0x360): undefined reference to `.fwnode_usb_role_switch_get' powerpc64-linux-ld: qcom-pmic-typec.c:(.text+0x4e4): undefined reference to `.usb_role_switch_put' Fixes: 6c8cf3695176 ("usb: typec: Add QCOM PMIC typec detection driver") Cc: linux-usb@vger.kernel.org Cc: Wesley Cheng Reported-by: kernel test robot Signed-off-by: Randy Dunlap Link: https://lore.kernel.org/r/20201116040653.7943-1-rdunlap@infradead.org Reviewed-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/typec/Kconfig b/drivers/usb/typec/Kconfig index 6c5908a37ee8..e7f120874c48 100644 --- a/drivers/usb/typec/Kconfig +++ b/drivers/usb/typec/Kconfig @@ -88,6 +88,7 @@ config TYPEC_STUSB160X config TYPEC_QCOM_PMIC tristate "Qualcomm PMIC USB Type-C driver" depends on ARCH_QCOM || COMPILE_TEST + depends on USB_ROLE_SWITCH || !USB_ROLE_SWITCH help Driver for supporting role switch over the Qualcomm PMIC. This will handle the USB Type-C role and orientation detection reported by the -- cgit v1.2.3 From 7bab16a6075b7b94999666355ab532c3dabb94f9 Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Fri, 13 Nov 2020 15:04:06 +0000 Subject: KVM: arm64: Correctly align nVHE percpu data The nVHE percpu data is partially linked but the nVHE linker script did not align the percpu section. The PERCPU_INPUT macro would then align the data to a page boundary: #define PERCPU_INPUT(cacheline) \ __per_cpu_start = .; \ *(.data..percpu..first) \ . = ALIGN(PAGE_SIZE); \ *(.data..percpu..page_aligned) \ . = ALIGN(cacheline); \ *(.data..percpu..read_mostly) \ . = ALIGN(cacheline); \ *(.data..percpu) \ *(.data..percpu..shared_aligned) \ PERCPU_DECRYPTED_SECTION \ __per_cpu_end = .; but then when the final vmlinux linking happens the hypervisor percpu data is included after page alignment and so the offsets potentially don't match. On my build I saw that the .hyp.data..percpu section was at address 0x20 and then the percpu data would begin at 0x1000 (because of the page alignment in PERCPU_INPUT), but when linked into vmlinux, everything would be shifted down by 0x20 bytes. This manifests as one of the CPUs getting lost when running kvm-unit-tests or starting any VM and subsequent soft lockup on a Cortex A72 device. Fixes: 30c953911c43 ("kvm: arm64: Set up hyp percpu data for nVHE") Signed-off-by: Jamie Iles Signed-off-by: Marc Zyngier Acked-by: David Brazdil Cc: David Brazdil Cc: Marc Zyngier Cc: Will Deacon Link: https://lore.kernel.org/r/20201113150406.14314-1-jamie@nuviainc.com --- arch/arm64/kvm/hyp/nvhe/hyp.lds.S | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S index bb2d986ff696..a797abace13f 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S @@ -13,6 +13,11 @@ SECTIONS { HYP_SECTION(.text) + /* + * .hyp..data..percpu needs to be page aligned to maintain the same + * alignment for when linking into vmlinux. + */ + . = ALIGN(PAGE_SIZE); HYP_SECTION_NAME(.data..percpu) : { PERCPU_INPUT(L1_CACHE_BYTES) } -- cgit v1.2.3 From 59024c936561090d766370e839a880dd42232c33 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 10 Nov 2020 21:59:23 +0200 Subject: pinctrl: jasperlake: Unhide SPI group of pins If the group of pins is hidden in the pin list it affects the register offset calculation despite fixed GPIO base. Hence, the offsets of all pins after the hidden group are broken. Instead we have to unhide the group and use a flag to exclude it from GPIO number space. Fixes: e278dcb7048b ("pinctrl: intel: Add Intel Jasper Lake pin controller support") Reported-by: Divagar Mohandass Signed-off-by: Andy Shevchenko Acked-by: Mika Westerberg --- drivers/pinctrl/intel/pinctrl-jasperlake.c | 450 +++++++++++++++-------------- 1 file changed, 230 insertions(+), 220 deletions(-) diff --git a/drivers/pinctrl/intel/pinctrl-jasperlake.c b/drivers/pinctrl/intel/pinctrl-jasperlake.c index 9bd0e8e6310c..c5e204c8da9c 100644 --- a/drivers/pinctrl/intel/pinctrl-jasperlake.c +++ b/drivers/pinctrl/intel/pinctrl-jasperlake.c @@ -65,252 +65,263 @@ static const struct pinctrl_pin_desc jsl_pins[] = { PINCTRL_PIN(17, "EMMC_CLK"), PINCTRL_PIN(18, "EMMC_RESETB"), PINCTRL_PIN(19, "A4WP_PRESENT"), + /* SPI */ + PINCTRL_PIN(20, "SPI0_IO_2"), + PINCTRL_PIN(21, "SPI0_IO_3"), + PINCTRL_PIN(22, "SPI0_MOSI_IO_0"), + PINCTRL_PIN(23, "SPI0_MISO_IO_1"), + PINCTRL_PIN(24, "SPI0_TPM_CSB"), + PINCTRL_PIN(25, "SPI0_FLASH_0_CSB"), + PINCTRL_PIN(26, "SPI0_FLASH_1_CSB"), + PINCTRL_PIN(27, "SPI0_CLK"), + PINCTRL_PIN(28, "SPI0_CLK_LOOPBK"), /* GPP_B */ - PINCTRL_PIN(20, "CORE_VID_0"), - PINCTRL_PIN(21, "CORE_VID_1"), - PINCTRL_PIN(22, "VRALERTB"), - PINCTRL_PIN(23, "CPU_GP_2"), - PINCTRL_PIN(24, "CPU_GP_3"), - PINCTRL_PIN(25, "SRCCLKREQB_0"), - PINCTRL_PIN(26, "SRCCLKREQB_1"), - PINCTRL_PIN(27, "SRCCLKREQB_2"), - PINCTRL_PIN(28, "SRCCLKREQB_3"), - PINCTRL_PIN(29, "SRCCLKREQB_4"), - PINCTRL_PIN(30, "SRCCLKREQB_5"), - PINCTRL_PIN(31, "PMCALERTB"), - PINCTRL_PIN(32, "SLP_S0B"), - PINCTRL_PIN(33, "PLTRSTB"), - PINCTRL_PIN(34, "SPKR"), - PINCTRL_PIN(35, "GSPI0_CS0B"), - PINCTRL_PIN(36, "GSPI0_CLK"), - PINCTRL_PIN(37, "GSPI0_MISO"), - PINCTRL_PIN(38, "GSPI0_MOSI"), - PINCTRL_PIN(39, "GSPI1_CS0B"), - PINCTRL_PIN(40, "GSPI1_CLK"), - PINCTRL_PIN(41, "GSPI1_MISO"), - PINCTRL_PIN(42, "GSPI1_MOSI"), - PINCTRL_PIN(43, "DDSP_HPD_A"), - PINCTRL_PIN(44, "GSPI0_CLK_LOOPBK"), - PINCTRL_PIN(45, "GSPI1_CLK_LOOPBK"), + PINCTRL_PIN(29, "CORE_VID_0"), + PINCTRL_PIN(30, "CORE_VID_1"), + PINCTRL_PIN(31, "VRALERTB"), + PINCTRL_PIN(32, "CPU_GP_2"), + PINCTRL_PIN(33, "CPU_GP_3"), + PINCTRL_PIN(34, "SRCCLKREQB_0"), + PINCTRL_PIN(35, "SRCCLKREQB_1"), + PINCTRL_PIN(36, "SRCCLKREQB_2"), + PINCTRL_PIN(37, "SRCCLKREQB_3"), + PINCTRL_PIN(38, "SRCCLKREQB_4"), + PINCTRL_PIN(39, "SRCCLKREQB_5"), + PINCTRL_PIN(40, "PMCALERTB"), + PINCTRL_PIN(41, "SLP_S0B"), + PINCTRL_PIN(42, "PLTRSTB"), + PINCTRL_PIN(43, "SPKR"), + PINCTRL_PIN(44, "GSPI0_CS0B"), + PINCTRL_PIN(45, "GSPI0_CLK"), + PINCTRL_PIN(46, "GSPI0_MISO"), + PINCTRL_PIN(47, "GSPI0_MOSI"), + PINCTRL_PIN(48, "GSPI1_CS0B"), + PINCTRL_PIN(49, "GSPI1_CLK"), + PINCTRL_PIN(50, "GSPI1_MISO"), + PINCTRL_PIN(51, "GSPI1_MOSI"), + PINCTRL_PIN(52, "DDSP_HPD_A"), + PINCTRL_PIN(53, "GSPI0_CLK_LOOPBK"), + PINCTRL_PIN(54, "GSPI1_CLK_LOOPBK"), /* GPP_A */ - PINCTRL_PIN(46, "ESPI_IO_0"), - PINCTRL_PIN(47, "ESPI_IO_1"), - PINCTRL_PIN(48, "ESPI_IO_2"), - PINCTRL_PIN(49, "ESPI_IO_3"), - PINCTRL_PIN(50, "ESPI_CSB"), - PINCTRL_PIN(51, "ESPI_CLK"), - PINCTRL_PIN(52, "ESPI_RESETB"), - PINCTRL_PIN(53, "SMBCLK"), - PINCTRL_PIN(54, "SMBDATA"), - PINCTRL_PIN(55, "SMBALERTB"), - PINCTRL_PIN(56, "CPU_GP_0"), - PINCTRL_PIN(57, "CPU_GP_1"), - PINCTRL_PIN(58, "USB2_OCB_1"), - PINCTRL_PIN(59, "USB2_OCB_2"), - PINCTRL_PIN(60, "USB2_OCB_3"), - PINCTRL_PIN(61, "DDSP_HPD_A_TIME_SYNC_0"), - PINCTRL_PIN(62, "DDSP_HPD_B"), - PINCTRL_PIN(63, "DDSP_HPD_C"), - PINCTRL_PIN(64, "USB2_OCB_0"), - PINCTRL_PIN(65, "PCHHOTB"), - PINCTRL_PIN(66, "ESPI_CLK_LOOPBK"), + PINCTRL_PIN(55, "ESPI_IO_0"), + PINCTRL_PIN(56, "ESPI_IO_1"), + PINCTRL_PIN(57, "ESPI_IO_2"), + PINCTRL_PIN(58, "ESPI_IO_3"), + PINCTRL_PIN(59, "ESPI_CSB"), + PINCTRL_PIN(60, "ESPI_CLK"), + PINCTRL_PIN(61, "ESPI_RESETB"), + PINCTRL_PIN(62, "SMBCLK"), + PINCTRL_PIN(63, "SMBDATA"), + PINCTRL_PIN(64, "SMBALERTB"), + PINCTRL_PIN(65, "CPU_GP_0"), + PINCTRL_PIN(66, "CPU_GP_1"), + PINCTRL_PIN(67, "USB2_OCB_1"), + PINCTRL_PIN(68, "USB2_OCB_2"), + PINCTRL_PIN(69, "USB2_OCB_3"), + PINCTRL_PIN(70, "DDSP_HPD_A_TIME_SYNC_0"), + PINCTRL_PIN(71, "DDSP_HPD_B"), + PINCTRL_PIN(72, "DDSP_HPD_C"), + PINCTRL_PIN(73, "USB2_OCB_0"), + PINCTRL_PIN(74, "PCHHOTB"), + PINCTRL_PIN(75, "ESPI_CLK_LOOPBK"), /* GPP_S */ - PINCTRL_PIN(67, "SNDW1_CLK"), - PINCTRL_PIN(68, "SNDW1_DATA"), - PINCTRL_PIN(69, "SNDW2_CLK"), - PINCTRL_PIN(70, "SNDW2_DATA"), - PINCTRL_PIN(71, "SNDW1_CLK"), - PINCTRL_PIN(72, "SNDW1_DATA"), - PINCTRL_PIN(73, "SNDW4_CLK_DMIC_CLK_0"), - PINCTRL_PIN(74, "SNDW4_DATA_DMIC_DATA_0"), + PINCTRL_PIN(76, "SNDW1_CLK"), + PINCTRL_PIN(77, "SNDW1_DATA"), + PINCTRL_PIN(78, "SNDW2_CLK"), + PINCTRL_PIN(79, "SNDW2_DATA"), + PINCTRL_PIN(80, "SNDW1_CLK"), + PINCTRL_PIN(81, "SNDW1_DATA"), + PINCTRL_PIN(82, "SNDW4_CLK_DMIC_CLK_0"), + PINCTRL_PIN(83, "SNDW4_DATA_DMIC_DATA_0"), /* GPP_R */ - PINCTRL_PIN(75, "HDA_BCLK"), - PINCTRL_PIN(76, "HDA_SYNC"), - PINCTRL_PIN(77, "HDA_SDO"), - PINCTRL_PIN(78, "HDA_SDI_0"), - PINCTRL_PIN(79, "HDA_RSTB"), - PINCTRL_PIN(80, "HDA_SDI_1"), - PINCTRL_PIN(81, "I2S1_SFRM"), - PINCTRL_PIN(82, "I2S1_TXD"), + PINCTRL_PIN(84, "HDA_BCLK"), + PINCTRL_PIN(85, "HDA_SYNC"), + PINCTRL_PIN(86, "HDA_SDO"), + PINCTRL_PIN(87, "HDA_SDI_0"), + PINCTRL_PIN(88, "HDA_RSTB"), + PINCTRL_PIN(89, "HDA_SDI_1"), + PINCTRL_PIN(90, "I2S1_SFRM"), + PINCTRL_PIN(91, "I2S1_TXD"), /* GPP_H */ - PINCTRL_PIN(83, "GPPC_H_0"), - PINCTRL_PIN(84, "SD_PWR_EN_B"), - PINCTRL_PIN(85, "MODEM_CLKREQ"), - PINCTRL_PIN(86, "SX_EXIT_HOLDOFFB"), - PINCTRL_PIN(87, "I2C2_SDA"), - PINCTRL_PIN(88, "I2C2_SCL"), - PINCTRL_PIN(89, "I2C3_SDA"), - PINCTRL_PIN(90, "I2C3_SCL"), - PINCTRL_PIN(91, "I2C4_SDA"), - PINCTRL_PIN(92, "I2C4_SCL"), - PINCTRL_PIN(93, "CPU_VCCIO_PWR_GATEB"), - PINCTRL_PIN(94, "I2S2_SCLK"), - PINCTRL_PIN(95, "I2S2_SFRM"), - PINCTRL_PIN(96, "I2S2_TXD"), - PINCTRL_PIN(97, "I2S2_RXD"), - PINCTRL_PIN(98, "I2S1_SCLK"), - PINCTRL_PIN(99, "GPPC_H_16"), - PINCTRL_PIN(100, "GPPC_H_17"), - PINCTRL_PIN(101, "GPPC_H_18"), - PINCTRL_PIN(102, "GPPC_H_19"), - PINCTRL_PIN(103, "GPPC_H_20"), - PINCTRL_PIN(104, "GPPC_H_21"), - PINCTRL_PIN(105, "GPPC_H_22"), - PINCTRL_PIN(106, "GPPC_H_23"), + PINCTRL_PIN(92, "GPPC_H_0"), + PINCTRL_PIN(93, "SD_PWR_EN_B"), + PINCTRL_PIN(94, "MODEM_CLKREQ"), + PINCTRL_PIN(95, "SX_EXIT_HOLDOFFB"), + PINCTRL_PIN(96, "I2C2_SDA"), + PINCTRL_PIN(97, "I2C2_SCL"), + PINCTRL_PIN(98, "I2C3_SDA"), + PINCTRL_PIN(99, "I2C3_SCL"), + PINCTRL_PIN(100, "I2C4_SDA"), + PINCTRL_PIN(101, "I2C4_SCL"), + PINCTRL_PIN(102, "CPU_VCCIO_PWR_GATEB"), + PINCTRL_PIN(103, "I2S2_SCLK"), + PINCTRL_PIN(104, "I2S2_SFRM"), + PINCTRL_PIN(105, "I2S2_TXD"), + PINCTRL_PIN(106, "I2S2_RXD"), + PINCTRL_PIN(107, "I2S1_SCLK"), + PINCTRL_PIN(108, "GPPC_H_16"), + PINCTRL_PIN(109, "GPPC_H_17"), + PINCTRL_PIN(110, "GPPC_H_18"), + PINCTRL_PIN(111, "GPPC_H_19"), + PINCTRL_PIN(112, "GPPC_H_20"), + PINCTRL_PIN(113, "GPPC_H_21"), + PINCTRL_PIN(114, "GPPC_H_22"), + PINCTRL_PIN(115, "GPPC_H_23"), /* GPP_D */ - PINCTRL_PIN(107, "SPI1_CSB"), - PINCTRL_PIN(108, "SPI1_CLK"), - PINCTRL_PIN(109, "SPI1_MISO_IO_1"), - PINCTRL_PIN(110, "SPI1_MOSI_IO_0"), - PINCTRL_PIN(111, "ISH_I2C0_SDA"), - PINCTRL_PIN(112, "ISH_I2C0_SCL"), - PINCTRL_PIN(113, "ISH_I2C1_SDA"), - PINCTRL_PIN(114, "ISH_I2C1_SCL"), - PINCTRL_PIN(115, "ISH_SPI_CSB"), - PINCTRL_PIN(116, "ISH_SPI_CLK"), - PINCTRL_PIN(117, "ISH_SPI_MISO"), - PINCTRL_PIN(118, "ISH_SPI_MOSI"), - PINCTRL_PIN(119, "ISH_UART0_RXD"), - PINCTRL_PIN(120, "ISH_UART0_TXD"), - PINCTRL_PIN(121, "ISH_UART0_RTSB"), - PINCTRL_PIN(122, "ISH_UART0_CTSB"), - PINCTRL_PIN(123, "SPI1_IO_2"), - PINCTRL_PIN(124, "SPI1_IO_3"), - PINCTRL_PIN(125, "I2S_MCLK"), - PINCTRL_PIN(126, "CNV_MFUART2_RXD"), - PINCTRL_PIN(127, "CNV_MFUART2_TXD"), - PINCTRL_PIN(128, "CNV_PA_BLANKING"), - PINCTRL_PIN(129, "I2C5_SDA"), - PINCTRL_PIN(130, "I2C5_SCL"), - PINCTRL_PIN(131, "GSPI2_CLK_LOOPBK"), - PINCTRL_PIN(132, "SPI1_CLK_LOOPBK"), + PINCTRL_PIN(116, "SPI1_CSB"), + PINCTRL_PIN(117, "SPI1_CLK"), + PINCTRL_PIN(118, "SPI1_MISO_IO_1"), + PINCTRL_PIN(119, "SPI1_MOSI_IO_0"), + PINCTRL_PIN(120, "ISH_I2C0_SDA"), + PINCTRL_PIN(121, "ISH_I2C0_SCL"), + PINCTRL_PIN(122, "ISH_I2C1_SDA"), + PINCTRL_PIN(123, "ISH_I2C1_SCL"), + PINCTRL_PIN(124, "ISH_SPI_CSB"), + PINCTRL_PIN(125, "ISH_SPI_CLK"), + PINCTRL_PIN(126, "ISH_SPI_MISO"), + PINCTRL_PIN(127, "ISH_SPI_MOSI"), + PINCTRL_PIN(128, "ISH_UART0_RXD"), + PINCTRL_PIN(129, "ISH_UART0_TXD"), + PINCTRL_PIN(130, "ISH_UART0_RTSB"), + PINCTRL_PIN(131, "ISH_UART0_CTSB"), + PINCTRL_PIN(132, "SPI1_IO_2"), + PINCTRL_PIN(133, "SPI1_IO_3"), + PINCTRL_PIN(134, "I2S_MCLK"), + PINCTRL_PIN(135, "CNV_MFUART2_RXD"), + PINCTRL_PIN(136, "CNV_MFUART2_TXD"), + PINCTRL_PIN(137, "CNV_PA_BLANKING"), + PINCTRL_PIN(138, "I2C5_SDA"), + PINCTRL_PIN(139, "I2C5_SCL"), + PINCTRL_PIN(140, "GSPI2_CLK_LOOPBK"), + PINCTRL_PIN(141, "SPI1_CLK_LOOPBK"), /* vGPIO */ - PINCTRL_PIN(133, "CNV_BTEN"), - PINCTRL_PIN(134, "CNV_WCEN"), - PINCTRL_PIN(135, "CNV_BT_HOST_WAKEB"), - PINCTRL_PIN(136, "CNV_BT_IF_SELECT"), - PINCTRL_PIN(137, "vCNV_BT_UART_TXD"), - PINCTRL_PIN(138, "vCNV_BT_UART_RXD"), - PINCTRL_PIN(139, "vCNV_BT_UART_CTS_B"), - PINCTRL_PIN(140, "vCNV_BT_UART_RTS_B"), - PINCTRL_PIN(141, "vCNV_MFUART1_TXD"), - PINCTRL_PIN(142, "vCNV_MFUART1_RXD"), - PINCTRL_PIN(143, "vCNV_MFUART1_CTS_B"), - PINCTRL_PIN(144, "vCNV_MFUART1_RTS_B"), - PINCTRL_PIN(145, "vUART0_TXD"), - PINCTRL_PIN(146, "vUART0_RXD"), - PINCTRL_PIN(147, "vUART0_CTS_B"), - PINCTRL_PIN(148, "vUART0_RTS_B"), - PINCTRL_PIN(149, "vISH_UART0_TXD"), - PINCTRL_PIN(150, "vISH_UART0_RXD"), - PINCTRL_PIN(151, "vISH_UART0_CTS_B"), - PINCTRL_PIN(152, "vISH_UART0_RTS_B"), - PINCTRL_PIN(153, "vCNV_BT_I2S_BCLK"), - PINCTRL_PIN(154, "vCNV_BT_I2S_WS_SYNC"), - PINCTRL_PIN(155, "vCNV_BT_I2S_SDO"), - PINCTRL_PIN(156, "vCNV_BT_I2S_SDI"), - PINCTRL_PIN(157, "vI2S2_SCLK"), - PINCTRL_PIN(158, "vI2S2_SFRM"), - PINCTRL_PIN(159, "vI2S2_TXD"), - PINCTRL_PIN(160, "vI2S2_RXD"), - PINCTRL_PIN(161, "vSD3_CD_B"), + PINCTRL_PIN(142, "CNV_BTEN"), + PINCTRL_PIN(143, "CNV_WCEN"), + PINCTRL_PIN(144, "CNV_BT_HOST_WAKEB"), + PINCTRL_PIN(145, "CNV_BT_IF_SELECT"), + PINCTRL_PIN(146, "vCNV_BT_UART_TXD"), + PINCTRL_PIN(147, "vCNV_BT_UART_RXD"), + PINCTRL_PIN(148, "vCNV_BT_UART_CTS_B"), + PINCTRL_PIN(149, "vCNV_BT_UART_RTS_B"), + PINCTRL_PIN(150, "vCNV_MFUART1_TXD"), + PINCTRL_PIN(151, "vCNV_MFUART1_RXD"), + PINCTRL_PIN(152, "vCNV_MFUART1_CTS_B"), + PINCTRL_PIN(153, "vCNV_MFUART1_RTS_B"), + PINCTRL_PIN(154, "vUART0_TXD"), + PINCTRL_PIN(155, "vUART0_RXD"), + PINCTRL_PIN(156, "vUART0_CTS_B"), + PINCTRL_PIN(157, "vUART0_RTS_B"), + PINCTRL_PIN(158, "vISH_UART0_TXD"), + PINCTRL_PIN(159, "vISH_UART0_RXD"), + PINCTRL_PIN(160, "vISH_UART0_CTS_B"), + PINCTRL_PIN(161, "vISH_UART0_RTS_B"), + PINCTRL_PIN(162, "vCNV_BT_I2S_BCLK"), + PINCTRL_PIN(163, "vCNV_BT_I2S_WS_SYNC"), + PINCTRL_PIN(164, "vCNV_BT_I2S_SDO"), + PINCTRL_PIN(165, "vCNV_BT_I2S_SDI"), + PINCTRL_PIN(166, "vI2S2_SCLK"), + PINCTRL_PIN(167, "vI2S2_SFRM"), + PINCTRL_PIN(168, "vI2S2_TXD"), + PINCTRL_PIN(169, "vI2S2_RXD"), + PINCTRL_PIN(170, "vSD3_CD_B"), /* GPP_C */ - PINCTRL_PIN(162, "GPPC_C_0"), - PINCTRL_PIN(163, "GPPC_C_1"), - PINCTRL_PIN(164, "GPPC_C_2"), - PINCTRL_PIN(165, "GPPC_C_3"), - PINCTRL_PIN(166, "GPPC_C_4"), - PINCTRL_PIN(167, "GPPC_C_5"), - PINCTRL_PIN(168, "SUSWARNB_SUSPWRDNACK"), - PINCTRL_PIN(169, "SUSACKB"), - PINCTRL_PIN(170, "UART0_RXD"), - PINCTRL_PIN(171, "UART0_TXD"), - PINCTRL_PIN(172, "UART0_RTSB"), - PINCTRL_PIN(173, "UART0_CTSB"), - PINCTRL_PIN(174, "UART1_RXD"), - PINCTRL_PIN(175, "UART1_TXD"), - PINCTRL_PIN(176, "UART1_RTSB"), - PINCTRL_PIN(177, "UART1_CTSB"), - PINCTRL_PIN(178, "I2C0_SDA"), - PINCTRL_PIN(179, "I2C0_SCL"), - PINCTRL_PIN(180, "I2C1_SDA"), - PINCTRL_PIN(181, "I2C1_SCL"), - PINCTRL_PIN(182, "UART2_RXD"), - PINCTRL_PIN(183, "UART2_TXD"), - PINCTRL_PIN(184, "UART2_RTSB"), - PINCTRL_PIN(185, "UART2_CTSB"), + PINCTRL_PIN(171, "GPPC_C_0"), + PINCTRL_PIN(172, "GPPC_C_1"), + PINCTRL_PIN(173, "GPPC_C_2"), + PINCTRL_PIN(174, "GPPC_C_3"), + PINCTRL_PIN(175, "GPPC_C_4"), + PINCTRL_PIN(176, "GPPC_C_5"), + PINCTRL_PIN(177, "SUSWARNB_SUSPWRDNACK"), + PINCTRL_PIN(178, "SUSACKB"), + PINCTRL_PIN(179, "UART0_RXD"), + PINCTRL_PIN(180, "UART0_TXD"), + PINCTRL_PIN(181, "UART0_RTSB"), + PINCTRL_PIN(182, "UART0_CTSB"), + PINCTRL_PIN(183, "UART1_RXD"), + PINCTRL_PIN(184, "UART1_TXD"), + PINCTRL_PIN(185, "UART1_RTSB"), + PINCTRL_PIN(186, "UART1_CTSB"), + PINCTRL_PIN(187, "I2C0_SDA"), + PINCTRL_PIN(188, "I2C0_SCL"), + PINCTRL_PIN(189, "I2C1_SDA"), + PINCTRL_PIN(190, "I2C1_SCL"), + PINCTRL_PIN(191, "UART2_RXD"), + PINCTRL_PIN(192, "UART2_TXD"), + PINCTRL_PIN(193, "UART2_RTSB"), + PINCTRL_PIN(194, "UART2_CTSB"), /* HVCMOS */ - PINCTRL_PIN(186, "L_BKLTEN"), - PINCTRL_PIN(187, "L_BKLTCTL"), - PINCTRL_PIN(188, "L_VDDEN"), - PINCTRL_PIN(189, "SYS_PWROK"), - PINCTRL_PIN(190, "SYS_RESETB"), - PINCTRL_PIN(191, "MLK_RSTB"), + PINCTRL_PIN(195, "L_BKLTEN"), + PINCTRL_PIN(196, "L_BKLTCTL"), + PINCTRL_PIN(197, "L_VDDEN"), + PINCTRL_PIN(198, "SYS_PWROK"), + PINCTRL_PIN(199, "SYS_RESETB"), + PINCTRL_PIN(200, "MLK_RSTB"), /* GPP_E */ - PINCTRL_PIN(192, "ISH_GP_0"), - PINCTRL_PIN(193, "ISH_GP_1"), - PINCTRL_PIN(194, "IMGCLKOUT_1"), - PINCTRL_PIN(195, "ISH_GP_2"), - PINCTRL_PIN(196, "IMGCLKOUT_2"), - PINCTRL_PIN(197, "SATA_LEDB"), - PINCTRL_PIN(198, "IMGCLKOUT_3"), - PINCTRL_PIN(199, "ISH_GP_3"), - PINCTRL_PIN(200, "ISH_GP_4"), - PINCTRL_PIN(201, "ISH_GP_5"), - PINCTRL_PIN(202, "ISH_GP_6"), - PINCTRL_PIN(203, "ISH_GP_7"), - PINCTRL_PIN(204, "IMGCLKOUT_4"), - PINCTRL_PIN(205, "DDPA_CTRLCLK"), - PINCTRL_PIN(206, "DDPA_CTRLDATA"), - PINCTRL_PIN(207, "DDPB_CTRLCLK"), - PINCTRL_PIN(208, "DDPB_CTRLDATA"), - PINCTRL_PIN(209, "DDPC_CTRLCLK"), - PINCTRL_PIN(210, "DDPC_CTRLDATA"), - PINCTRL_PIN(211, "IMGCLKOUT_5"), - PINCTRL_PIN(212, "CNV_BRI_DT"), - PINCTRL_PIN(213, "CNV_BRI_RSP"), - PINCTRL_PIN(214, "CNV_RGI_DT"), - PINCTRL_PIN(215, "CNV_RGI_RSP"), + PINCTRL_PIN(201, "ISH_GP_0"), + PINCTRL_PIN(202, "ISH_GP_1"), + PINCTRL_PIN(203, "IMGCLKOUT_1"), + PINCTRL_PIN(204, "ISH_GP_2"), + PINCTRL_PIN(205, "IMGCLKOUT_2"), + PINCTRL_PIN(206, "SATA_LEDB"), + PINCTRL_PIN(207, "IMGCLKOUT_3"), + PINCTRL_PIN(208, "ISH_GP_3"), + PINCTRL_PIN(209, "ISH_GP_4"), + PINCTRL_PIN(210, "ISH_GP_5"), + PINCTRL_PIN(211, "ISH_GP_6"), + PINCTRL_PIN(212, "ISH_GP_7"), + PINCTRL_PIN(213, "IMGCLKOUT_4"), + PINCTRL_PIN(214, "DDPA_CTRLCLK"), + PINCTRL_PIN(215, "DDPA_CTRLDATA"), + PINCTRL_PIN(216, "DDPB_CTRLCLK"), + PINCTRL_PIN(217, "DDPB_CTRLDATA"), + PINCTRL_PIN(218, "DDPC_CTRLCLK"), + PINCTRL_PIN(219, "DDPC_CTRLDATA"), + PINCTRL_PIN(220, "IMGCLKOUT_5"), + PINCTRL_PIN(221, "CNV_BRI_DT"), + PINCTRL_PIN(222, "CNV_BRI_RSP"), + PINCTRL_PIN(223, "CNV_RGI_DT"), + PINCTRL_PIN(224, "CNV_RGI_RSP"), /* GPP_G */ - PINCTRL_PIN(216, "SD3_CMD"), - PINCTRL_PIN(217, "SD3_D0"), - PINCTRL_PIN(218, "SD3_D1"), - PINCTRL_PIN(219, "SD3_D2"), - PINCTRL_PIN(220, "SD3_D3"), - PINCTRL_PIN(221, "SD3_CDB"), - PINCTRL_PIN(222, "SD3_CLK"), - PINCTRL_PIN(223, "SD3_WP"), + PINCTRL_PIN(225, "SD3_CMD"), + PINCTRL_PIN(226, "SD3_D0"), + PINCTRL_PIN(227, "SD3_D1"), + PINCTRL_PIN(228, "SD3_D2"), + PINCTRL_PIN(229, "SD3_D3"), + PINCTRL_PIN(230, "SD3_CDB"), + PINCTRL_PIN(231, "SD3_CLK"), + PINCTRL_PIN(232, "SD3_WP"), }; static const struct intel_padgroup jsl_community0_gpps[] = { JSL_GPP(0, 0, 19, 320), /* GPP_F */ - JSL_GPP(1, 20, 45, 32), /* GPP_B */ - JSL_GPP(2, 46, 66, 64), /* GPP_A */ - JSL_GPP(3, 67, 74, 96), /* GPP_S */ - JSL_GPP(4, 75, 82, 128), /* GPP_R */ + JSL_GPP(1, 20, 28, INTEL_GPIO_BASE_NOMAP), /* SPI */ + JSL_GPP(2, 29, 54, 32), /* GPP_B */ + JSL_GPP(3, 55, 75, 64), /* GPP_A */ + JSL_GPP(4, 76, 83, 96), /* GPP_S */ + JSL_GPP(5, 84, 91, 128), /* GPP_R */ }; static const struct intel_padgroup jsl_community1_gpps[] = { - JSL_GPP(0, 83, 106, 160), /* GPP_H */ - JSL_GPP(1, 107, 132, 192), /* GPP_D */ - JSL_GPP(2, 133, 161, 224), /* vGPIO */ - JSL_GPP(3, 162, 185, 256), /* GPP_C */ + JSL_GPP(0, 92, 115, 160), /* GPP_H */ + JSL_GPP(1, 116, 141, 192), /* GPP_D */ + JSL_GPP(2, 142, 170, 224), /* vGPIO */ + JSL_GPP(3, 171, 194, 256), /* GPP_C */ }; static const struct intel_padgroup jsl_community4_gpps[] = { - JSL_GPP(0, 186, 191, INTEL_GPIO_BASE_NOMAP), /* HVCMOS */ - JSL_GPP(1, 192, 215, 288), /* GPP_E */ + JSL_GPP(0, 195, 200, INTEL_GPIO_BASE_NOMAP), /* HVCMOS */ + JSL_GPP(1, 201, 224, 288), /* GPP_E */ }; static const struct intel_padgroup jsl_community5_gpps[] = { - JSL_GPP(0, 216, 223, INTEL_GPIO_BASE_ZERO), /* GPP_G */ + JSL_GPP(0, 225, 232, INTEL_GPIO_BASE_ZERO), /* GPP_G */ }; static const struct intel_community jsl_communities[] = { - JSL_COMMUNITY(0, 0, 82, jsl_community0_gpps), - JSL_COMMUNITY(1, 83, 185, jsl_community1_gpps), - JSL_COMMUNITY(2, 186, 215, jsl_community4_gpps), - JSL_COMMUNITY(3, 216, 223, jsl_community5_gpps), + JSL_COMMUNITY(0, 0, 91, jsl_community0_gpps), + JSL_COMMUNITY(1, 92, 194, jsl_community1_gpps), + JSL_COMMUNITY(2, 195, 224, jsl_community4_gpps), + JSL_COMMUNITY(3, 225, 232, jsl_community5_gpps), }; static const struct intel_pinctrl_soc_data jsl_soc_data = { @@ -336,7 +347,6 @@ static struct platform_driver jsl_pinctrl_driver = { .pm = &jsl_pinctrl_pm_ops, }, }; - module_platform_driver(jsl_pinctrl_driver); MODULE_AUTHOR("Andy Shevchenko "); -- cgit v1.2.3 From cdd8fc2dd64e3f1b22a6636e242d0eff49c4ba22 Mon Sep 17 00:00:00 2001 From: Evan Green Date: Wed, 11 Nov 2020 15:17:28 -0800 Subject: pinctrl: jasperlake: Fix HOSTSW_OWN offset GPIOs that attempt to use interrupts get thwarted with a message like: "pin 161 cannot be used as IRQ" (for instance with SD_CD). This is because the HOSTSW_OWN offset is incorrect, so every GPIO looks like it's owned by ACPI. Fixes: e278dcb7048b1 ("pinctrl: intel: Add Intel Jasper Lake pin controller support") Cc: stable@vger.kernel.org Signed-off-by: Evan Green Acked-by: Mika Westerberg Signed-off-by: Andy Shevchenko --- drivers/pinctrl/intel/pinctrl-jasperlake.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/intel/pinctrl-jasperlake.c b/drivers/pinctrl/intel/pinctrl-jasperlake.c index c5e204c8da9c..ec435b7ab392 100644 --- a/drivers/pinctrl/intel/pinctrl-jasperlake.c +++ b/drivers/pinctrl/intel/pinctrl-jasperlake.c @@ -16,7 +16,7 @@ #define JSL_PAD_OWN 0x020 #define JSL_PADCFGLOCK 0x080 -#define JSL_HOSTSW_OWN 0x0b0 +#define JSL_HOSTSW_OWN 0x0c0 #define JSL_GPI_IS 0x100 #define JSL_GPI_IE 0x120 -- cgit v1.2.3 From 03a61f11c00213394e3c7ac62ae416d034dc728f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 11 Nov 2020 14:06:05 +0200 Subject: pinctrl: merrifield: Set default bias in case no particular value given When GPIO library asks pin control to set the bias, it doesn't pass any value of it and argument is considered boolean (and this is true for ACPI GpioIo() / GpioInt() resources, by the way). Thus, individual drivers must behave well, when they got the resistance value of 1 Ohm, i.e. transforming it to sane default. In case of Intel Merrifield pin control hardware the 20 kOhm sounds plausible because it gives a good trade off between weakness and minimization of leakage current (will be only 50 uA with the above choice). Fixes: 4e80c8f50574 ("pinctrl: intel: Add Intel Merrifield pin controller support") Depends-on: 2956b5d94a76 ("pinctrl / gpio: Introduce .set_config() callback for GPIO chips") Signed-off-by: Andy Shevchenko Acked-by: Mika Westerberg --- drivers/pinctrl/intel/pinctrl-merrifield.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/pinctrl/intel/pinctrl-merrifield.c b/drivers/pinctrl/intel/pinctrl-merrifield.c index e4ff8da1b894..3ae141e0b421 100644 --- a/drivers/pinctrl/intel/pinctrl-merrifield.c +++ b/drivers/pinctrl/intel/pinctrl-merrifield.c @@ -745,6 +745,10 @@ static int mrfld_config_set_pin(struct mrfld_pinctrl *mp, unsigned int pin, mask |= BUFCFG_Px_EN_MASK | BUFCFG_PUPD_VAL_MASK; bits |= BUFCFG_PU_EN; + /* Set default strength value in case none is given */ + if (arg == 1) + arg = 20000; + switch (arg) { case 50000: bits |= BUFCFG_PUPD_VAL_50K << BUFCFG_PUPD_VAL_SHIFT; @@ -765,6 +769,10 @@ static int mrfld_config_set_pin(struct mrfld_pinctrl *mp, unsigned int pin, mask |= BUFCFG_Px_EN_MASK | BUFCFG_PUPD_VAL_MASK; bits |= BUFCFG_PD_EN; + /* Set default strength value in case none is given */ + if (arg == 1) + arg = 20000; + switch (arg) { case 50000: bits |= BUFCFG_PUPD_VAL_50K << BUFCFG_PUPD_VAL_SHIFT; -- cgit v1.2.3 From 5f714771d01e0e0d410f06d4d192fb27b1ca0edd Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 12 Nov 2020 21:03:01 +0200 Subject: pinctrl: baytrail: Avoid clearing debounce value when turning it off Baytrail pin control has a common register to set up debounce timeout. When a pin configuration requested debounce to be disabled, the rest of the pins may still want to have debounce enabled and thus rely on the common timeout value. Avoid clearing debounce value when turning it off for one pin while others may still use it. Fixes: 658b476c742f ("pinctrl: baytrail: Add debounce configuration") Depends-on: 04ff5a095d66 ("pinctrl: baytrail: Rectify debounce support") Depends-on: 827e1579e1d5 ("pinctrl: baytrail: Rectify debounce support (part 2)") Signed-off-by: Andy Shevchenko Acked-by: Mika Westerberg --- drivers/pinctrl/intel/pinctrl-baytrail.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index d49aab3cfbaa..394a421a19d5 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -1049,7 +1049,6 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev, break; case PIN_CONFIG_INPUT_DEBOUNCE: debounce = readl(db_reg); - debounce &= ~BYT_DEBOUNCE_PULSE_MASK; if (arg) conf |= BYT_DEBOUNCE_EN; @@ -1058,24 +1057,31 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev, switch (arg) { case 375: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_375US; break; case 750: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_750US; break; case 1500: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_1500US; break; case 3000: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_3MS; break; case 6000: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_6MS; break; case 12000: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_12MS; break; case 24000: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_24MS; break; default: -- cgit v1.2.3 From 481535c5b41d191b22775a6873de5ec0e1cdced1 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Mon, 16 Nov 2020 01:25:56 -0800 Subject: xtensa: fix TLBTEMP area placement fast_second_level_miss handler for the TLBTEMP area has an assumption that page table directory entry for the TLBTEMP address range is 0. For it to be true the TLBTEMP area must be aligned to 4MB boundary and not share its 4MB region with anything that may use a page table. This is not true currently: TLBTEMP shares space with vmalloc space which results in the following kinds of runtime errors when fast_second_level_miss loads page table directory entry for the vmalloc space instead of fixing up the TLBTEMP area: Unable to handle kernel paging request at virtual address c7ff0e00 pc = d0009275, ra = 90009478 Oops: sig: 9 [#1] PREEMPT CPU: 1 PID: 61 Comm: kworker/u9:2 Not tainted 5.10.0-rc3-next-20201110-00007-g1fe4962fa983-dirty #58 Workqueue: xprtiod xs_stream_data_receive_workfn a00: 90009478 d11e1dc0 c7ff0e00 00000020 c7ff0000 00000001 7f8b8107 00000000 a08: 900c5992 d11e1d90 d0cc88b8 5506e97c 00000000 5506e97c d06c8074 d11e1d90 pc: d0009275, ps: 00060310, depc: 00000014, excvaddr: c7ff0e00 lbeg: d0009275, lend: d0009287 lcount: 00000003, sar: 00000010 Call Trace: xs_stream_data_receive_workfn+0x43c/0x770 process_one_work+0x1a1/0x324 worker_thread+0x1cc/0x3c0 kthread+0x10d/0x124 ret_from_kernel_thread+0xc/0x18 Cc: stable@vger.kernel.org Signed-off-by: Max Filippov --- Documentation/xtensa/mmu.rst | 9 ++++++--- arch/xtensa/include/asm/pgtable.h | 2 +- 2 files changed, 7 insertions(+), 4 deletions(-) diff --git a/Documentation/xtensa/mmu.rst b/Documentation/xtensa/mmu.rst index e52a12960fdc..450573afa31a 100644 --- a/Documentation/xtensa/mmu.rst +++ b/Documentation/xtensa/mmu.rst @@ -82,7 +82,8 @@ Default MMUv2-compatible layout:: +------------------+ | VMALLOC area | VMALLOC_START 0xc0000000 128MB - 64KB +------------------+ VMALLOC_END - | Cache aliasing | TLBTEMP_BASE_1 0xc7ff0000 DCACHE_WAY_SIZE + +------------------+ + | Cache aliasing | TLBTEMP_BASE_1 0xc8000000 DCACHE_WAY_SIZE | remap area 1 | +------------------+ | Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE @@ -124,7 +125,8 @@ Default MMUv2-compatible layout:: +------------------+ | VMALLOC area | VMALLOC_START 0xa0000000 128MB - 64KB +------------------+ VMALLOC_END - | Cache aliasing | TLBTEMP_BASE_1 0xa7ff0000 DCACHE_WAY_SIZE + +------------------+ + | Cache aliasing | TLBTEMP_BASE_1 0xa8000000 DCACHE_WAY_SIZE | remap area 1 | +------------------+ | Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE @@ -167,7 +169,8 @@ Default MMUv2-compatible layout:: +------------------+ | VMALLOC area | VMALLOC_START 0x90000000 128MB - 64KB +------------------+ VMALLOC_END - | Cache aliasing | TLBTEMP_BASE_1 0x97ff0000 DCACHE_WAY_SIZE + +------------------+ + | Cache aliasing | TLBTEMP_BASE_1 0x98000000 DCACHE_WAY_SIZE | remap area 1 | +------------------+ | Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index fa054a1772e1..4dc04e6c01d7 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -69,7 +69,7 @@ */ #define VMALLOC_START (XCHAL_KSEG_CACHED_VADDR - 0x10000000) #define VMALLOC_END (VMALLOC_START + 0x07FEFFFF) -#define TLBTEMP_BASE_1 (VMALLOC_END + 1) +#define TLBTEMP_BASE_1 (VMALLOC_START + 0x08000000) #define TLBTEMP_BASE_2 (TLBTEMP_BASE_1 + DCACHE_WAY_SIZE) #if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE #define TLBTEMP_SIZE (2 * DCACHE_WAY_SIZE) -- cgit v1.2.3 From 3a860d165eb5f4d7cf0bf81ef6a5b5c5e1754422 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Mon, 16 Nov 2020 01:38:59 -0800 Subject: xtensa: disable preemption around cache alias management calls Although cache alias management calls set up and tear down TLB entries and fast_second_level_miss is able to restore TLB entry should it be evicted they absolutely cannot preempt each other because they use the same TLBTEMP area for different purposes. Disable preemption around all cache alias management calls to enforce that. Cc: stable@vger.kernel.org Signed-off-by: Max Filippov --- arch/xtensa/mm/cache.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index 5835406b3cec..085b8c77b9d9 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -70,8 +70,10 @@ static inline void kmap_invalidate_coherent(struct page *page, kvaddr = TLBTEMP_BASE_1 + (page_to_phys(page) & DCACHE_ALIAS_MASK); + preempt_disable(); __invalidate_dcache_page_alias(kvaddr, page_to_phys(page)); + preempt_enable(); } } } @@ -156,6 +158,7 @@ void flush_dcache_page(struct page *page) if (!alias && !mapping) return; + preempt_disable(); virt = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(virt, phys); @@ -166,6 +169,7 @@ void flush_dcache_page(struct page *page) if (mapping) __invalidate_icache_page_alias(virt, phys); + preempt_enable(); } /* There shouldn't be an entry in the cache for this page anymore. */ @@ -199,8 +203,10 @@ void local_flush_cache_page(struct vm_area_struct *vma, unsigned long address, unsigned long phys = page_to_phys(pfn_to_page(pfn)); unsigned long virt = TLBTEMP_BASE_1 + (address & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(virt, phys); __invalidate_icache_page_alias(virt, phys); + preempt_enable(); } EXPORT_SYMBOL(local_flush_cache_page); @@ -227,11 +233,13 @@ update_mmu_cache(struct vm_area_struct * vma, unsigned long addr, pte_t *ptep) unsigned long phys = page_to_phys(page); unsigned long tmp; + preempt_disable(); tmp = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(tmp, phys); tmp = TLBTEMP_BASE_1 + (addr & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(tmp, phys); __invalidate_icache_page_alias(tmp, phys); + preempt_enable(); clear_bit(PG_arch_1, &page->flags); } @@ -265,7 +273,9 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(t, phys); + preempt_enable(); } /* Copy data */ @@ -280,9 +290,11 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_range((unsigned long) dst, len); if ((vma->vm_flags & VM_EXEC) != 0) __invalidate_icache_page_alias(t, phys); + preempt_enable(); } else if ((vma->vm_flags & VM_EXEC) != 0) { __flush_dcache_range((unsigned long)dst,len); @@ -304,7 +316,9 @@ extern void copy_from_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(t, phys); + preempt_enable(); } memcpy(dst, src, len); -- cgit v1.2.3 From c39de538a06e76d89b7e598a71e16688009cd56c Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 4 Nov 2020 16:21:26 +0300 Subject: cpuidle: tegra: Annotate tegra_pm_set_cpu_in_lp2() with RCU_NONIDLE Annotate tegra_pm_set[clear]_cpu_in_lp2() with RCU_NONIDLE in order to fix lockdep warning about suspicious RCU usage of a spinlock during late idling phase. WARNING: suspicious RCU usage ... include/trace/events/lock.h:13 suspicious rcu_dereference_check() usage! ... (dump_stack) from (lock_acquire) (lock_acquire) from (_raw_spin_lock) (_raw_spin_lock) from (tegra_pm_set_cpu_in_lp2) (tegra_pm_set_cpu_in_lp2) from (tegra_cpuidle_enter) (tegra_cpuidle_enter) from (cpuidle_enter_state) (cpuidle_enter_state) from (cpuidle_enter_state_coupled) (cpuidle_enter_state_coupled) from (cpuidle_enter) (cpuidle_enter) from (do_idle) ... Tested-by: Peter Geis Reported-by: Peter Geis Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/cpuidle-tegra.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/cpuidle/cpuidle-tegra.c b/drivers/cpuidle/cpuidle-tegra.c index e8956706a291..191966dc8d02 100644 --- a/drivers/cpuidle/cpuidle-tegra.c +++ b/drivers/cpuidle/cpuidle-tegra.c @@ -189,7 +189,7 @@ static int tegra_cpuidle_state_enter(struct cpuidle_device *dev, } local_fiq_disable(); - tegra_pm_set_cpu_in_lp2(); + RCU_NONIDLE(tegra_pm_set_cpu_in_lp2()); cpu_pm_enter(); switch (index) { @@ -207,7 +207,7 @@ static int tegra_cpuidle_state_enter(struct cpuidle_device *dev, } cpu_pm_exit(); - tegra_pm_clear_cpu_in_lp2(); + RCU_NONIDLE(tegra_pm_clear_cpu_in_lp2()); local_fiq_enable(); return err ?: index; -- cgit v1.2.3 From 75b49620267c700f0a07fec7f27f69852db70e46 Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Thu, 5 Nov 2020 14:47:13 +0100 Subject: KVM: PPC: Book3S HV: XIVE: Fix possible oops when accessing ESB page MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When accessing the ESB page of a source interrupt, the fault handler will retrieve the page address from the XIVE interrupt 'xive_irq_data' structure. If the associated KVM XIVE interrupt is not valid, that is not allocated at the HW level for some reason, the fault handler will dereference a NULL pointer leading to the oops below : WARNING: CPU: 40 PID: 59101 at arch/powerpc/kvm/book3s_xive_native.c:259 xive_native_esb_fault+0xe4/0x240 [kvm] CPU: 40 PID: 59101 Comm: qemu-system-ppc Kdump: loaded Tainted: G W --------- - - 4.18.0-240.el8.ppc64le #1 NIP: c00800000e949fac LR: c00000000044b164 CTR: c00800000e949ec8 REGS: c000001f69617840 TRAP: 0700 Tainted: G W --------- - - (4.18.0-240.el8.ppc64le) MSR: 9000000000029033 CR: 44044282 XER: 00000000 CFAR: c00000000044b160 IRQMASK: 0 GPR00: c00000000044b164 c000001f69617ac0 c00800000e96e000 c000001f69617c10 GPR04: 05faa2b21e000080 0000000000000000 0000000000000005 ffffffffffffffff GPR08: 0000000000000000 0000000000000001 0000000000000000 0000000000000001 GPR12: c00800000e949ec8 c000001ffffd3400 0000000000000000 0000000000000000 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000000000000 0000000000000000 c000001f5c065160 c000000001c76f90 GPR24: c000001f06f20000 c000001f5c065100 0000000000000008 c000001f0eb98c78 GPR28: c000001dcab40000 c000001dcab403d8 c000001f69617c10 0000000000000011 NIP [c00800000e949fac] xive_native_esb_fault+0xe4/0x240 [kvm] LR [c00000000044b164] __do_fault+0x64/0x220 Call Trace: [c000001f69617ac0] [0000000137a5dc20] 0x137a5dc20 (unreliable) [c000001f69617b50] [c00000000044b164] __do_fault+0x64/0x220 [c000001f69617b90] [c000000000453838] do_fault+0x218/0x930 [c000001f69617bf0] [c000000000456f50] __handle_mm_fault+0x350/0xdf0 [c000001f69617cd0] [c000000000457b1c] handle_mm_fault+0x12c/0x310 [c000001f69617d10] [c00000000007ef44] __do_page_fault+0x264/0xbb0 [c000001f69617df0] [c00000000007f8c8] do_page_fault+0x38/0xd0 [c000001f69617e30] [c00000000000a714] handle_page_fault+0x18/0x38 Instruction dump: 40c2fff0 7c2004ac 2fa90000 409e0118 73e90001 41820080 e8bd0008 7c2004ac 7ca90074 39400000 915c0000 7929d182 <0b090000> 2fa50000 419e0080 e89e0018 ---[ end trace 66c6ff034c53f64f ]--- xive-kvm: xive_native_esb_fault: accessing invalid ESB page for source 8 ! Fix that by checking the validity of the KVM XIVE interrupt structure. Fixes: 6520ca64cde7 ("KVM: PPC: Book3S HV: XIVE: Add a mapping for the source ESB pages") Cc: stable@vger.kernel.org # v5.2+ Reported-by: Greg Kurz Signed-off-by: Cédric Le Goater Tested-by: Greg Kurz Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201105134713.656160-1-clg@kaod.org --- arch/powerpc/kvm/book3s_xive_native.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index d0c2db0e07fa..a59a94f02733 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -251,6 +251,13 @@ static vm_fault_t xive_native_esb_fault(struct vm_fault *vmf) } state = &sb->irq_state[src]; + + /* Some sanity checking */ + if (!state->valid) { + pr_devel("%s: source %lx invalid !\n", __func__, irq); + return VM_FAULT_SIGBUS; + } + kvmppc_xive_select_irq(state, &hw_num, &xd); arch_spin_lock(&sb->lock); -- cgit v1.2.3 From 8986f223bd777a73119f5d593c15b4d630ff49bb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 16 Nov 2020 13:52:47 +0100 Subject: iommu/vt-d: Take CONFIG_PCI_ATS into account pci_dev::physfn is only available when CONFIG_PCI_ATS is set. The recent fix for the irqdomain rework missed that dependency which makes the build fail when CONFIG_PCI_ATS=n. Add the necessary #ifdeffery. Reported-by: Geert Uytterhoeven Fixes: ff828729be44 ("iommu/vt-d: Cure VF irqdomain hickup") Signed-off-by: Thomas Gleixner Cc: Joerg Roedel --- drivers/iommu/intel/dmar.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index b2e804473209..bc9f4cf72240 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -335,7 +335,9 @@ static void dmar_pci_bus_del_dev(struct dmar_pci_notify_info *info) static inline void vf_inherit_msi_domain(struct pci_dev *pdev) { +#ifdef CONFIG_PCI_ATS dev_set_msi_domain(&pdev->dev, dev_get_msi_domain(&pdev->physfn->dev)); +#endif } static int dmar_pci_bus_notifier(struct notifier_block *nb, -- cgit v1.2.3 From 7dc7a8b04f3da8aa3c3be514e155e2fa094e976f Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 10 Nov 2020 15:52:01 -0800 Subject: ACPI: fan: Initialize performance state sysfs attribute The following warning is reported if lock debugging is enabled. DEBUG_LOCKS_WARN_ON(1) WARNING: CPU: 1 PID: 1 at kernel/locking/lockdep.c:4617 lockdep_init_map_waits+0x141/0x222 ... Call Trace: __kernfs_create_file+0x7a/0xd8 sysfs_add_file_mode_ns+0x135/0x189 sysfs_create_file_ns+0x70/0xa0 acpi_fan_probe+0x547/0x621 platform_drv_probe+0x67/0x8b ... Dynamically allocated sysfs attributes need to be initialized to avoid the warning. Fixes: d19e470b6605 ("ACPI: fan: Expose fan performance state information") Signed-off-by: Guenter Roeck Cc: 5.6+ # 5.6+ Signed-off-by: Rafael J. Wysocki --- drivers/acpi/fan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c index 48354f82fba6..66c3983f0ccc 100644 --- a/drivers/acpi/fan.c +++ b/drivers/acpi/fan.c @@ -352,6 +352,7 @@ static int acpi_fan_get_fps(struct acpi_device *device) struct acpi_fan_fps *fps = &fan->fps[i]; snprintf(fps->name, ACPI_FPS_NAME_LEN, "state%d", i); + sysfs_attr_init(&fps->dev_attr.attr); fps->dev_attr.show = show_state; fps->dev_attr.store = NULL; fps->dev_attr.attr.name = fps->name; -- cgit v1.2.3 From d78359b25f7c6759a23189145be8141b6fdfe385 Mon Sep 17 00:00:00 2001 From: Kai Vehmanen Date: Mon, 16 Nov 2020 16:19:55 +0200 Subject: ALSA: hda: Add Alderlake-S PCI ID and HDMI codec vid Add HD Audio PCI ID and HDMI codec vendor ID for Intel Alder Lake. Signed-off-by: Kai Vehmanen Reviewed-by: Pierre-Louis Bossart Reviewed-by: Guennadi Liakhovetski Link: https://lore.kernel.org/r/20201116141955.2091240-1-kai.vehmanen@linux.intel.com Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_intel.c | 3 +++ sound/pci/hda/patch_hdmi.c | 1 + 2 files changed, 4 insertions(+) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index d539f52009a1..6852668f1bcb 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2506,6 +2506,9 @@ static const struct pci_device_id azx_ids[] = { /* DG1 */ { PCI_DEVICE(0x8086, 0x490d), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* Alderlake-S */ + { PCI_DEVICE(0x8086, 0x7ad0), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Elkhart Lake */ { PCI_DEVICE(0x8086, 0x4b55), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index ccd1df059654..b0068f8ca46d 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4274,6 +4274,7 @@ HDA_CODEC_ENTRY(0x8086280d, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862814, "DG1 HDMI", patch_i915_tgl_hdmi), +HDA_CODEC_ENTRY(0x80862815, "Alderlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862816, "Rocketlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI", patch_i915_icl_hdmi), -- cgit v1.2.3 From 6f117cb854a44a79898d844e6ae3fd23bd94e786 Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Mon, 16 Nov 2020 16:23:47 +0100 Subject: s390/dasd: fix null pointer dereference for ERP requests When requeueing all requests on the device request queue to the blocklayer we might get to an ERP (error recovery) request that is a copy of an original CQR. Those requests do not have blocklayer request information or a pointer to the dasd_queue set. When trying to access those data it will lead to a null pointer dereference in dasd_requeue_all_requests(). Fix by checking if the request is an ERP request that can simply be ignored. The blocklayer request will be requeued by the original CQR that is on the device queue right behind the ERP request. Fixes: 9487cfd3430d ("s390/dasd: fix handling of internal requests") Cc: #4.16 Signed-off-by: Stefan Haberland Reviewed-by: Jan Hoeppner Signed-off-by: Jens Axboe --- drivers/s390/block/dasd.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index eb17fea8075c..217a7b84abdf 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2980,6 +2980,12 @@ static int _dasd_requeue_request(struct dasd_ccw_req *cqr) if (!block) return -EINVAL; + /* + * If the request is an ERP request there is nothing to requeue. + * This will be done with the remaining original request. + */ + if (cqr->refers) + return 0; spin_lock_irq(&cqr->dq->lock); req = (struct request *) cqr->callback_data; blk_mq_requeue_request(req, false); -- cgit v1.2.3 From cef397038167ac15d085914493d6c86385773709 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 11 Nov 2020 17:52:58 +0100 Subject: arch: pgtable: define MAX_POSSIBLE_PHYSMEM_BITS where needed Stefan Agner reported a bug when using zsram on 32-bit Arm machines with RAM above the 4GB address boundary: Unable to handle kernel NULL pointer dereference at virtual address 00000000 pgd = a27bd01c [00000000] *pgd=236a0003, *pmd=1ffa64003 Internal error: Oops: 207 [#1] SMP ARM Modules linked in: mdio_bcm_unimac(+) brcmfmac cfg80211 brcmutil raspberrypi_hwmon hci_uart crc32_arm_ce bcm2711_thermal phy_generic genet CPU: 0 PID: 123 Comm: mkfs.ext4 Not tainted 5.9.6 #1 Hardware name: BCM2711 PC is at zs_map_object+0x94/0x338 LR is at zram_bvec_rw.constprop.0+0x330/0xa64 pc : [] lr : [] psr: 60000013 sp : e376bbe0 ip : 00000000 fp : c1e2921c r10: 00000002 r9 : c1dda730 r8 : 00000000 r7 : e8ff7a00 r6 : 00000000 r5 : 02f9ffa0 r4 : e3710000 r3 : 000fdffe r2 : c1e0ce80 r1 : ebf979a0 r0 : 00000000 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user Control: 30c5383d Table: 235c2a80 DAC: fffffffd Process mkfs.ext4 (pid: 123, stack limit = 0x495a22e6) Stack: (0xe376bbe0 to 0xe376c000) As it turns out, zsram needs to know the maximum memory size, which is defined in MAX_PHYSMEM_BITS when CONFIG_SPARSEMEM is set, or in MAX_POSSIBLE_PHYSMEM_BITS on the x86 architecture. The same problem will be hit on all 32-bit architectures that have a physical address space larger than 4GB and happen to not enable sparsemem and include asm/sparsemem.h from asm/pgtable.h. After the initial discussion, I suggested just always defining MAX_POSSIBLE_PHYSMEM_BITS whenever CONFIG_PHYS_ADDR_T_64BIT is set, or provoking a build error otherwise. This addresses all configurations that can currently have this runtime bug, but leaves all other configurations unchanged. I looked up the possible number of bits in source code and datasheets, here is what I found: - on ARC, CONFIG_ARC_HAS_PAE40 controls whether 32 or 40 bits are used - on ARM, CONFIG_LPAE enables 40 bit addressing, without it we never support more than 32 bits, even though supersections in theory allow up to 40 bits as well. - on MIPS, some MIPS32r1 or later chips support 36 bits, and MIPS32r5 XPA supports up to 60 bits in theory, but 40 bits are more than anyone will ever ship - On PowerPC, there are three different implementations of 36 bit addressing, but 32-bit is used without CONFIG_PTE_64BIT - On RISC-V, the normal page table format can support 34 bit addressing. There is no highmem support on RISC-V, so anything above 2GB is unused, but it might be useful to eventually support CONFIG_ZRAM for high pages. Fixes: 61989a80fb3a ("staging: zsmalloc: zsmalloc memory allocation library") Fixes: 02390b87a945 ("mm/zsmalloc: Prepare to variable MAX_PHYSMEM_BITS") Acked-by: Thomas Bogendoerfer Reviewed-by: Stefan Agner Tested-by: Stefan Agner Acked-by: Mike Rapoport Link: https://lore.kernel.org/linux-mm/bdfa44bf1c570b05d6c70898e2bbb0acf234ecdf.1604762181.git.stefan@agner.ch/ Signed-off-by: Arnd Bergmann --- arch/arc/include/asm/pgtable.h | 2 ++ arch/arm/include/asm/pgtable-2level.h | 2 ++ arch/arm/include/asm/pgtable-3level.h | 2 ++ arch/mips/include/asm/pgtable-32.h | 3 +++ arch/powerpc/include/asm/book3s/32/pgtable.h | 2 ++ arch/powerpc/include/asm/nohash/32/pgtable.h | 2 ++ arch/riscv/include/asm/pgtable-32.h | 2 ++ include/linux/pgtable.h | 13 +++++++++++++ 8 files changed, 28 insertions(+) diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index f1ed17edb085..163641726a2b 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -134,8 +134,10 @@ #ifdef CONFIG_ARC_HAS_PAE40 #define PTE_BITS_NON_RWX_IN_PD1 (0xff00000000 | PAGE_MASK | _PAGE_CACHEABLE) +#define MAX_POSSIBLE_PHYSMEM_BITS 40 #else #define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /************************************************************************** diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index 3502c2f746ca..baf7d0204eb5 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -75,6 +75,8 @@ #define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t)) #define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 + /* * PMD_SHIFT determines the size of the area a second-level page table can map * PGDIR_SHIFT determines what a third-level page table entry can map diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index fbb6693c3352..2b85d175e999 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -25,6 +25,8 @@ #define PTE_HWTABLE_OFF (0) #define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u64)) +#define MAX_POSSIBLE_PHYSMEM_BITS 40 + /* * PGDIR_SHIFT determines the size a top-level page table entry can map. */ diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index a950fc1ddb4d..6c0532d7b211 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -154,6 +154,7 @@ static inline void pmd_clear(pmd_t *pmdp) #if defined(CONFIG_XPA) +#define MAX_POSSIBLE_PHYSMEM_BITS 40 #define pte_pfn(x) (((unsigned long)((x).pte_high >> _PFN_SHIFT)) | (unsigned long)((x).pte_low << _PAGE_PRESENT_SHIFT)) static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) @@ -169,6 +170,7 @@ pfn_pte(unsigned long pfn, pgprot_t prot) #elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #define pte_pfn(x) ((unsigned long)((x).pte_high >> 6)) static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) @@ -183,6 +185,7 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) #else +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #ifdef CONFIG_CPU_VR41XX #define pte_pfn(x) ((unsigned long)((x).pte >> (PAGE_SHIFT + 2))) #define pfn_pte(pfn, prot) __pte(((pfn) << (PAGE_SHIFT + 2)) | pgprot_val(prot)) diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 36443cda8dcf..1376be95e975 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -36,8 +36,10 @@ static inline bool pte_user(pte_t pte) */ #ifdef CONFIG_PTE_64BIT #define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #else #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /* diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index ee2243ba96cf..96522f7f0618 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -153,8 +153,10 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); */ #if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) #define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #else #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /* diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h index b0ab66e5fdb1..5b2e79e5bfa5 100644 --- a/arch/riscv/include/asm/pgtable-32.h +++ b/arch/riscv/include/asm/pgtable-32.h @@ -14,4 +14,6 @@ #define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 34 + #endif /* _ASM_RISCV_PGTABLE_32_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 71125a4676c4..e237004d498d 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1427,6 +1427,19 @@ typedef unsigned int pgtbl_mod_mask; #endif /* !__ASSEMBLY__ */ +#if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT) +#ifdef CONFIG_PHYS_ADDR_T_64BIT +/* + * ZSMALLOC needs to know the highest PFN on 32-bit architectures + * with physical address space extension, but falls back to + * BITS_PER_LONG otherwise. + */ +#error Missing MAX_POSSIBLE_PHYSMEM_BITS definition +#else +#define MAX_POSSIBLE_PHYSMEM_BITS 32 +#endif +#endif + #ifndef has_transparent_hugepage #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define has_transparent_hugepage() 1 -- cgit v1.2.3 From 1c756cd429d8f3da33d31f2a970284b9d5260534 Mon Sep 17 00:00:00 2001 From: Al Grant Date: Fri, 13 Nov 2020 20:38:26 +0000 Subject: perf inject: Fix file corruption due to event deletion "perf inject" can create corrupt files when synthesizing sample events from AUX data. This happens when in the input file, the first event (for the AUX data) has a different sample_type from the second event (generally dummy). Specifically, they differ in the bits that indicate the standard fields appended to perf records in the mmap buffer. "perf inject" deletes the first event and moves up the second event to first position. The problem is with the synthetic PERF_RECORD_MMAP (etc.) events created by "perf record". Since these are synthetic versions of events which are normally produced by the kernel, they have to have the standard fields appended as described by sample_type. "perf record" fills these in with zeroes, including the IDENTIFIER field; perf readers interpret records with zero IDENTIFIER using the descriptor for the first event in the file. Since "perf inject" changes the first event, these synthetic records are then processed with the wrong value of sample_type, and the perf reader reads bad data, reports on incorrect length records etc. Mismatching sample_types are seen with "perf record -e cs_etm//", where the AUX event has TID|TIME|CPU|IDENTIFIER and the dummy event has TID|TIME|IDENTIFIER. Perhaps they could be the same, but it isn't normally a problem if they aren't - perf has no problems reading the file. The sample_types have to agree on the position of IDENTIFIER, because that's how perf finds the right event descriptor in the first place, but they don't normally have to agree on other fields, and perf doesn't check that they do. The problem is specific to the way "perf inject" reorganizes the events and the way synthetic MMAP events are recorded with a zero identifier. A simple solution is to stop "perf inject" deleting the tracing event. Committer testing Removed the now unused 'evsel' variable, update the comment about the evsel removal not being performed anymore, and apply the patch manually as it failed with this warning: warning: Patch sent with format=flowed; space at the end of lines might be lost. Testing it with: $ perf bench internals inject-build-id # Running 'internals/inject-build-id' benchmark: Average build-id injection took: 8.543 msec (+- 0.130 msec) Average time per event: 0.838 usec (+- 0.013 usec) Average memory usage: 12717 KB (+- 9 KB) Average build-id-all injection took: 5.710 msec (+- 0.058 msec) Average time per event: 0.560 usec (+- 0.006 usec) Average memory usage: 12079 KB (+- 7 KB) $ Signed-off-by: Al Grant Acked-by: Adrian Hunter Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra LPU-Reference: b9cf5611-daae-2390-3439-6617f8f0a34b@foss.arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 452a75fe68e5..0462dc8db2e3 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -779,25 +779,15 @@ static int __cmd_inject(struct perf_inject *inject) dsos__hit_all(session); /* * The AUX areas have been removed and replaced with - * synthesized hardware events, so clear the feature flag and - * remove the evsel. + * synthesized hardware events, so clear the feature flag. */ if (inject->itrace_synth_opts.set) { - struct evsel *evsel; - perf_header__clear_feat(&session->header, HEADER_AUXTRACE); if (inject->itrace_synth_opts.last_branch || inject->itrace_synth_opts.add_last_branch) perf_header__set_feat(&session->header, HEADER_BRANCH_STACK); - evsel = perf_evlist__id2evsel_strict(session->evlist, - inject->aux_id); - if (evsel) { - pr_debug("Deleting %s\n", evsel__name(evsel)); - evlist__remove(session->evlist, evsel); - evsel__delete(evsel); - } } session->header.data_offset = output_data_offset; session->header.data_size = inject->bytes_written; -- cgit v1.2.3 From 8326be9f1c0bb498baf134878a8deb8a952e0135 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 11 Nov 2020 15:23:46 -0700 Subject: dmaengine: idxd: fix mapping of portal size Portal size is 4k. Current code is mapping all 4 portals in a single chunk. Restrict the mapped portal size to a single portal to ensure that submission only goes to the intended portal address. Fixes: c52ca478233c ("dmaengine: idxd: add configuration component of driver") Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/160513342642.510187.16450549281618747065.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/device.c | 2 +- drivers/dma/idxd/registers.h | 2 +- drivers/dma/idxd/submit.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 506ac85c4a7f..663344987e3f 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -271,7 +271,7 @@ int idxd_wq_map_portal(struct idxd_wq *wq) resource_size_t start; start = pci_resource_start(pdev, IDXD_WQ_BAR); - start = start + wq->id * IDXD_PORTAL_SIZE; + start += idxd_get_wq_portal_full_offset(wq->id, IDXD_PORTAL_LIMITED); wq->dportal = devm_ioremap(dev, start, IDXD_PORTAL_SIZE); if (!wq->dportal) diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index aef5a902829e..54390334c243 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -8,7 +8,7 @@ #define IDXD_MMIO_BAR 0 #define IDXD_WQ_BAR 2 -#define IDXD_PORTAL_SIZE 0x4000 +#define IDXD_PORTAL_SIZE PAGE_SIZE /* MMIO Device BAR0 Registers */ #define IDXD_VER_OFFSET 0x00 diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index 156a1ee233aa..417048e3c42a 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -74,7 +74,7 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) if (idxd->state != IDXD_DEV_ENABLED) return -EIO; - portal = wq->dportal + idxd_get_wq_portal_offset(IDXD_PORTAL_UNLIMITED); + portal = wq->dportal; /* * The wmb() flushes writes to coherent DMA data before possibly * triggering a DMA read. The wmb() is necessary even on UP because -- cgit v1.2.3 From 568beb27959b0515d325ea1c6cf211eed2d66740 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 13 Nov 2020 10:20:53 -0800 Subject: perf test: Avoid an msan warning in a copied stack. This fix is for a failure that occurred in the DWARF unwind perf test. Stack unwinders may probe memory when looking for frames. Memory sanitizer will poison and track uninitialized memory on the stack, and on the heap if the value is copied to the heap. This can lead to false memory sanitizer failures for the use of an uninitialized value. Avoid this problem by removing the poison on the copied stack. The full msan failure with track origins looks like: ==2168==WARNING: MemorySanitizer: use-of-uninitialized-value #0 0x559ceb10755b in handle_cfi elfutils/libdwfl/frame_unwind.c:648:8 #1 0x559ceb105448 in __libdwfl_frame_unwind elfutils/libdwfl/frame_unwind.c:741:4 #2 0x559ceb0ece90 in dwfl_thread_getframes elfutils/libdwfl/dwfl_frame.c:435:7 #3 0x559ceb0ec6b7 in get_one_thread_frames_cb elfutils/libdwfl/dwfl_frame.c:379:10 #4 0x559ceb0ec6b7 in get_one_thread_cb elfutils/libdwfl/dwfl_frame.c:308:17 #5 0x559ceb0ec6b7 in dwfl_getthreads elfutils/libdwfl/dwfl_frame.c:283:17 #6 0x559ceb0ec6b7 in getthread elfutils/libdwfl/dwfl_frame.c:354:14 #7 0x559ceb0ec6b7 in dwfl_getthread_frames elfutils/libdwfl/dwfl_frame.c:388:10 #8 0x559ceaff6ae6 in unwind__get_entries tools/perf/util/unwind-libdw.c:236:8 #9 0x559ceabc9dbc in test_dwarf_unwind__thread tools/perf/tests/dwarf-unwind.c:111:8 #10 0x559ceabca5cf in test_dwarf_unwind__compare tools/perf/tests/dwarf-unwind.c:138:26 #11 0x7f812a6865b0 in bsearch (libc.so.6+0x4e5b0) #12 0x559ceabca871 in test_dwarf_unwind__krava_3 tools/perf/tests/dwarf-unwind.c:162:2 #13 0x559ceabca926 in test_dwarf_unwind__krava_2 tools/perf/tests/dwarf-unwind.c:169:9 #14 0x559ceabca946 in test_dwarf_unwind__krava_1 tools/perf/tests/dwarf-unwind.c:174:9 #15 0x559ceabcae12 in test__dwarf_unwind tools/perf/tests/dwarf-unwind.c:211:8 #16 0x559ceabbc4ab in run_test tools/perf/tests/builtin-test.c:418:9 #17 0x559ceabbc4ab in test_and_print tools/perf/tests/builtin-test.c:448:9 #18 0x559ceabbac70 in __cmd_test tools/perf/tests/builtin-test.c:669:4 #19 0x559ceabbac70 in cmd_test tools/perf/tests/builtin-test.c:815:9 #20 0x559cea960e30 in run_builtin tools/perf/perf.c:313:11 #21 0x559cea95fbce in handle_internal_command tools/perf/perf.c:365:8 #22 0x559cea95fbce in run_argv tools/perf/perf.c:409:2 #23 0x559cea95fbce in main tools/perf/perf.c:539:3 Uninitialized value was stored to memory at #0 0x559ceb106acf in __libdwfl_frame_reg_set elfutils/libdwfl/frame_unwind.c:77:22 #1 0x559ceb106acf in handle_cfi elfutils/libdwfl/frame_unwind.c:627:13 #2 0x559ceb105448 in __libdwfl_frame_unwind elfutils/libdwfl/frame_unwind.c:741:4 #3 0x559ceb0ece90 in dwfl_thread_getframes elfutils/libdwfl/dwfl_frame.c:435:7 #4 0x559ceb0ec6b7 in get_one_thread_frames_cb elfutils/libdwfl/dwfl_frame.c:379:10 #5 0x559ceb0ec6b7 in get_one_thread_cb elfutils/libdwfl/dwfl_frame.c:308:17 #6 0x559ceb0ec6b7 in dwfl_getthreads elfutils/libdwfl/dwfl_frame.c:283:17 #7 0x559ceb0ec6b7 in getthread elfutils/libdwfl/dwfl_frame.c:354:14 #8 0x559ceb0ec6b7 in dwfl_getthread_frames elfutils/libdwfl/dwfl_frame.c:388:10 #9 0x559ceaff6ae6 in unwind__get_entries tools/perf/util/unwind-libdw.c:236:8 #10 0x559ceabc9dbc in test_dwarf_unwind__thread tools/perf/tests/dwarf-unwind.c:111:8 #11 0x559ceabca5cf in test_dwarf_unwind__compare tools/perf/tests/dwarf-unwind.c:138:26 #12 0x7f812a6865b0 in bsearch (libc.so.6+0x4e5b0) #13 0x559ceabca871 in test_dwarf_unwind__krava_3 tools/perf/tests/dwarf-unwind.c:162:2 #14 0x559ceabca926 in test_dwarf_unwind__krava_2 tools/perf/tests/dwarf-unwind.c:169:9 #15 0x559ceabca946 in test_dwarf_unwind__krava_1 tools/perf/tests/dwarf-unwind.c:174:9 #16 0x559ceabcae12 in test__dwarf_unwind tools/perf/tests/dwarf-unwind.c:211:8 #17 0x559ceabbc4ab in run_test tools/perf/tests/builtin-test.c:418:9 #18 0x559ceabbc4ab in test_and_print tools/perf/tests/builtin-test.c:448:9 #19 0x559ceabbac70 in __cmd_test tools/perf/tests/builtin-test.c:669:4 #20 0x559ceabbac70 in cmd_test tools/perf/tests/builtin-test.c:815:9 #21 0x559cea960e30 in run_builtin tools/perf/perf.c:313:11 #22 0x559cea95fbce in handle_internal_command tools/perf/perf.c:365:8 #23 0x559cea95fbce in run_argv tools/perf/perf.c:409:2 #24 0x559cea95fbce in main tools/perf/perf.c:539:3 Uninitialized value was stored to memory at #0 0x559ceb106a54 in handle_cfi elfutils/libdwfl/frame_unwind.c:613:9 #1 0x559ceb105448 in __libdwfl_frame_unwind elfutils/libdwfl/frame_unwind.c:741:4 #2 0x559ceb0ece90 in dwfl_thread_getframes elfutils/libdwfl/dwfl_frame.c:435:7 #3 0x559ceb0ec6b7 in get_one_thread_frames_cb elfutils/libdwfl/dwfl_frame.c:379:10 #4 0x559ceb0ec6b7 in get_one_thread_cb elfutils/libdwfl/dwfl_frame.c:308:17 #5 0x559ceb0ec6b7 in dwfl_getthreads elfutils/libdwfl/dwfl_frame.c:283:17 #6 0x559ceb0ec6b7 in getthread elfutils/libdwfl/dwfl_frame.c:354:14 #7 0x559ceb0ec6b7 in dwfl_getthread_frames elfutils/libdwfl/dwfl_frame.c:388:10 #8 0x559ceaff6ae6 in unwind__get_entries tools/perf/util/unwind-libdw.c:236:8 #9 0x559ceabc9dbc in test_dwarf_unwind__thread tools/perf/tests/dwarf-unwind.c:111:8 #10 0x559ceabca5cf in test_dwarf_unwind__compare tools/perf/tests/dwarf-unwind.c:138:26 #11 0x7f812a6865b0 in bsearch (libc.so.6+0x4e5b0) #12 0x559ceabca871 in test_dwarf_unwind__krava_3 tools/perf/tests/dwarf-unwind.c:162:2 #13 0x559ceabca926 in test_dwarf_unwind__krava_2 tools/perf/tests/dwarf-unwind.c:169:9 #14 0x559ceabca946 in test_dwarf_unwind__krava_1 tools/perf/tests/dwarf-unwind.c:174:9 #15 0x559ceabcae12 in test__dwarf_unwind tools/perf/tests/dwarf-unwind.c:211:8 #16 0x559ceabbc4ab in run_test tools/perf/tests/builtin-test.c:418:9 #17 0x559ceabbc4ab in test_and_print tools/perf/tests/builtin-test.c:448:9 #18 0x559ceabbac70 in __cmd_test tools/perf/tests/builtin-test.c:669:4 #19 0x559ceabbac70 in cmd_test tools/perf/tests/builtin-test.c:815:9 #20 0x559cea960e30 in run_builtin tools/perf/perf.c:313:11 #21 0x559cea95fbce in handle_internal_command tools/perf/perf.c:365:8 #22 0x559cea95fbce in run_argv tools/perf/perf.c:409:2 #23 0x559cea95fbce in main tools/perf/perf.c:539:3 Uninitialized value was stored to memory at #0 0x559ceaff8800 in memory_read tools/perf/util/unwind-libdw.c:156:10 #1 0x559ceb10f053 in expr_eval elfutils/libdwfl/frame_unwind.c:501:13 #2 0x559ceb1060cc in handle_cfi elfutils/libdwfl/frame_unwind.c:603:18 #3 0x559ceb105448 in __libdwfl_frame_unwind elfutils/libdwfl/frame_unwind.c:741:4 #4 0x559ceb0ece90 in dwfl_thread_getframes elfutils/libdwfl/dwfl_frame.c:435:7 #5 0x559ceb0ec6b7 in get_one_thread_frames_cb elfutils/libdwfl/dwfl_frame.c:379:10 #6 0x559ceb0ec6b7 in get_one_thread_cb elfutils/libdwfl/dwfl_frame.c:308:17 #7 0x559ceb0ec6b7 in dwfl_getthreads elfutils/libdwfl/dwfl_frame.c:283:17 #8 0x559ceb0ec6b7 in getthread elfutils/libdwfl/dwfl_frame.c:354:14 #9 0x559ceb0ec6b7 in dwfl_getthread_frames elfutils/libdwfl/dwfl_frame.c:388:10 #10 0x559ceaff6ae6 in unwind__get_entries tools/perf/util/unwind-libdw.c:236:8 #11 0x559ceabc9dbc in test_dwarf_unwind__thread tools/perf/tests/dwarf-unwind.c:111:8 #12 0x559ceabca5cf in test_dwarf_unwind__compare tools/perf/tests/dwarf-unwind.c:138:26 #13 0x7f812a6865b0 in bsearch (libc.so.6+0x4e5b0) #14 0x559ceabca871 in test_dwarf_unwind__krava_3 tools/perf/tests/dwarf-unwind.c:162:2 #15 0x559ceabca926 in test_dwarf_unwind__krava_2 tools/perf/tests/dwarf-unwind.c:169:9 #16 0x559ceabca946 in test_dwarf_unwind__krava_1 tools/perf/tests/dwarf-unwind.c:174:9 #17 0x559ceabcae12 in test__dwarf_unwind tools/perf/tests/dwarf-unwind.c:211:8 #18 0x559ceabbc4ab in run_test tools/perf/tests/builtin-test.c:418:9 #19 0x559ceabbc4ab in test_and_print tools/perf/tests/builtin-test.c:448:9 #20 0x559ceabbac70 in __cmd_test tools/perf/tests/builtin-test.c:669:4 #21 0x559ceabbac70 in cmd_test tools/perf/tests/builtin-test.c:815:9 #22 0x559cea960e30 in run_builtin tools/perf/perf.c:313:11 #23 0x559cea95fbce in handle_internal_command tools/perf/perf.c:365:8 #24 0x559cea95fbce in run_argv tools/perf/perf.c:409:2 #25 0x559cea95fbce in main tools/perf/perf.c:539:3 Uninitialized value was stored to memory at #0 0x559cea9027d9 in __msan_memcpy llvm/llvm-project/compiler-rt/lib/msan/msan_interceptors.cpp:1558:3 #1 0x559cea9d2185 in sample_ustack tools/perf/arch/x86/tests/dwarf-unwind.c:41:2 #2 0x559cea9d202c in test__arch_unwind_sample tools/perf/arch/x86/tests/dwarf-unwind.c:72:9 #3 0x559ceabc9cbd in test_dwarf_unwind__thread tools/perf/tests/dwarf-unwind.c:106:6 #4 0x559ceabca5cf in test_dwarf_unwind__compare tools/perf/tests/dwarf-unwind.c:138:26 #5 0x7f812a6865b0 in bsearch (libc.so.6+0x4e5b0) #6 0x559ceabca871 in test_dwarf_unwind__krava_3 tools/perf/tests/dwarf-unwind.c:162:2 #7 0x559ceabca926 in test_dwarf_unwind__krava_2 tools/perf/tests/dwarf-unwind.c:169:9 #8 0x559ceabca946 in test_dwarf_unwind__krava_1 tools/perf/tests/dwarf-unwind.c:174:9 #9 0x559ceabcae12 in test__dwarf_unwind tools/perf/tests/dwarf-unwind.c:211:8 #10 0x559ceabbc4ab in run_test tools/perf/tests/builtin-test.c:418:9 #11 0x559ceabbc4ab in test_and_print tools/perf/tests/builtin-test.c:448:9 #12 0x559ceabbac70 in __cmd_test tools/perf/tests/builtin-test.c:669:4 #13 0x559ceabbac70 in cmd_test tools/perf/tests/builtin-test.c:815:9 #14 0x559cea960e30 in run_builtin tools/perf/perf.c:313:11 #15 0x559cea95fbce in handle_internal_command tools/perf/perf.c:365:8 #16 0x559cea95fbce in run_argv tools/perf/perf.c:409:2 #17 0x559cea95fbce in main tools/perf/perf.c:539:3 Uninitialized value was created by an allocation of 'bf' in the stack frame of function 'perf_event__synthesize_mmap_events' #0 0x559ceafc5f60 in perf_event__synthesize_mmap_events tools/perf/util/synthetic-events.c:445 SUMMARY: MemorySanitizer: use-of-uninitialized-value elfutils/libdwfl/frame_unwind.c:648:8 in handle_cfi Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: clang-built-linux@googlegroups.com Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Sandeep Dasgupta Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20201113182053.754625-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/tests/dwarf-unwind.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index 4e40402a4f81..478078fb0f22 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -38,6 +38,13 @@ static int sample_ustack(struct perf_sample *sample, stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; memcpy(buf, (void *) sp, stack_size); +#ifdef MEMORY_SANITIZER + /* + * Copying the stack may copy msan poison, avoid false positives in the + * unwinder by removing the poison here. + */ + __msan_unpoison(buf, stack_size); +#endif stack->data = (char *) buf; stack->size = stack_size; return 0; -- cgit v1.2.3 From 4e7d4f295dee1feed96b2b0a31d80d673b5465e8 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Fri, 13 Nov 2020 09:12:48 +0100 Subject: dmaengine: ioatdma: remove unused function missed during dma_v2 removal Commit 7f832645d0e5 ("dmaengine: ioatdma: remove ioatdma v2 registration") missed to remove dca2_tag_map_valid() during its removal. Hence, since then, dca2_tag_map_valid() is unused and make CC=clang W=1 warns: drivers/dma/ioat/dca.c:44:19: warning: unused function 'dca2_tag_map_valid' [-Wunused-function] So, remove this unused function and get rid of a -Wused-function warning. Signed-off-by: Lukas Bulwahn Reviewed-by: Nathan Chancellor Link: https://lore.kernel.org/r/20201113081248.26416-1-lukas.bulwahn@gmail.com Signed-off-by: Vinod Koul --- drivers/dma/ioat/dca.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/drivers/dma/ioat/dca.c b/drivers/dma/ioat/dca.c index 0be385587c4c..289c59ed74b9 100644 --- a/drivers/dma/ioat/dca.c +++ b/drivers/dma/ioat/dca.c @@ -40,16 +40,6 @@ #define DCA2_TAG_MAP_BYTE3 0x82 #define DCA2_TAG_MAP_BYTE4 0x82 -/* verify if tag map matches expected values */ -static inline int dca2_tag_map_valid(u8 *tag_map) -{ - return ((tag_map[0] == DCA2_TAG_MAP_BYTE0) && - (tag_map[1] == DCA2_TAG_MAP_BYTE1) && - (tag_map[2] == DCA2_TAG_MAP_BYTE2) && - (tag_map[3] == DCA2_TAG_MAP_BYTE3) && - (tag_map[4] == DCA2_TAG_MAP_BYTE4)); -} - /* * "Legacy" DCA systems do not implement the DCA register set in the * I/OAT device. Software needs direct support for their tag mappings. -- cgit v1.2.3 From e773ca7da8beeca7f17fe4c9d1284a2b66839cc1 Mon Sep 17 00:00:00 2001 From: Sugar Zhang Date: Sat, 14 Nov 2020 11:55:06 +0800 Subject: dmaengine: pl330: _prep_dma_memcpy: Fix wrong burst size Actually, burst size is equal to '1 << desc->rqcfg.brst_size'. we should use burst size, not desc->rqcfg.brst_size. dma memcpy performance on Rockchip RV1126 @ 1512MHz A7, 1056MHz LPDDR3, 200MHz DMA: dmatest: /# echo dma0chan0 > /sys/module/dmatest/parameters/channel /# echo 4194304 > /sys/module/dmatest/parameters/test_buf_size /# echo 8 > /sys/module/dmatest/parameters/iterations /# echo y > /sys/module/dmatest/parameters/norandom /# echo y > /sys/module/dmatest/parameters/verbose /# echo 1 > /sys/module/dmatest/parameters/run dmatest: dma0chan0-copy0: result #1: 'test passed' with src_off=0x0 dst_off=0x0 len=0x400000 dmatest: dma0chan0-copy0: result #2: 'test passed' with src_off=0x0 dst_off=0x0 len=0x400000 dmatest: dma0chan0-copy0: result #3: 'test passed' with src_off=0x0 dst_off=0x0 len=0x400000 dmatest: dma0chan0-copy0: result #4: 'test passed' with src_off=0x0 dst_off=0x0 len=0x400000 dmatest: dma0chan0-copy0: result #5: 'test passed' with src_off=0x0 dst_off=0x0 len=0x400000 dmatest: dma0chan0-copy0: result #6: 'test passed' with src_off=0x0 dst_off=0x0 len=0x400000 dmatest: dma0chan0-copy0: result #7: 'test passed' with src_off=0x0 dst_off=0x0 len=0x400000 dmatest: dma0chan0-copy0: result #8: 'test passed' with src_off=0x0 dst_off=0x0 len=0x400000 Before: dmatest: dma0chan0-copy0: summary 8 tests, 0 failures 48 iops 200338 KB/s (0) After this patch: dmatest: dma0chan0-copy0: summary 8 tests, 0 failures 179 iops 734873 KB/s (0) After this patch and increase dma clk to 400MHz: dmatest: dma0chan0-copy0: summary 8 tests, 0 failures 259 iops 1062929 KB/s (0) Signed-off-by: Sugar Zhang Link: https://lore.kernel.org/r/1605326106-55681-1-git-send-email-sugar.zhang@rock-chips.com Signed-off-by: Vinod Koul --- drivers/dma/pl330.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index e9f0101d92fa..0f5c19370f6d 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -2799,7 +2799,7 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst, * If burst size is smaller than bus width then make sure we only * transfer one at a time to avoid a burst stradling an MFIFO entry. */ - if (desc->rqcfg.brst_size * 8 < pl330->pcfg.data_bus_width) + if (burst * 8 < pl330->pcfg.data_bus_width) desc->rqcfg.brst_len = 1; desc->bytes_requested = len; -- cgit v1.2.3 From dd8088d5a8969dc2b42f71d7bc01c25c61a78066 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Tue, 10 Nov 2020 17:29:32 +0800 Subject: PM: runtime: Add pm_runtime_resume_and_get to deal with usage counter In many case, we need to check return value of pm_runtime_get_sync, but it brings a trouble to the usage counter processing. Many callers forget to decrease the usage counter when it failed, which could resulted in reference leak. It has been discussed a lot[0][1]. So we add a function to deal with the usage counter for better coding. [0]https://lkml.org/lkml/2020/6/14/88 [1]https://patchwork.ozlabs.org/project/linux-tegra/list/?series=178139 Signed-off-by: Zhang Qilong Acked-by: Rafael J. Wysocki Signed-off-by: Jakub Kicinski --- include/linux/pm_runtime.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 4b708f4e8eed..b492ae00cc90 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -386,6 +386,27 @@ static inline int pm_runtime_get_sync(struct device *dev) return __pm_runtime_resume(dev, RPM_GET_PUT); } +/** + * pm_runtime_resume_and_get - Bump up usage counter of a device and resume it. + * @dev: Target device. + * + * Resume @dev synchronously and if that is successful, increment its runtime + * PM usage counter. Return 0 if the runtime PM usage counter of @dev has been + * incremented or a negative error code otherwise. + */ +static inline int pm_runtime_resume_and_get(struct device *dev) +{ + int ret; + + ret = __pm_runtime_resume(dev, RPM_GET_PUT); + if (ret < 0) { + pm_runtime_put_noidle(dev); + return ret; + } + + return 0; +} + /** * pm_runtime_put - Drop device usage counter and queue up "idle check" if 0. * @dev: Target device. -- cgit v1.2.3 From da875fa5040b0f951cb4bf7efbf59f6dcff44d3c Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Tue, 10 Nov 2020 17:29:33 +0800 Subject: net: fec: Fix reference count leak in fec series ops pm_runtime_get_sync() will increment pm usage at first and it will resume the device later. If runtime of the device has error or device is in inaccessible state(or other error state), resume operation will fail. If we do not call put operation to decrease the reference, it will result in reference count leak. Moreover, this device cannot enter the idle state and always stay busy or other non-idle state later. So we fixed it by replacing it with pm_runtime_resume_and_get. Fixes: 8fff755e9f8d0 ("net: fec: Ensure clocks are enabled while using mdio bus") Signed-off-by: Zhang Qilong Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/fec_main.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index d7919555250d..04f24c66cf36 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1808,7 +1808,7 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) int ret = 0, frame_start, frame_addr, frame_op; bool is_c45 = !!(regnum & MII_ADDR_C45); - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret; @@ -1867,11 +1867,9 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, int ret, frame_start, frame_addr; bool is_c45 = !!(regnum & MII_ADDR_C45); - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret; - else - ret = 0; if (is_c45) { frame_start = FEC_MMFR_ST_C45; @@ -2275,7 +2273,7 @@ static void fec_enet_get_regs(struct net_device *ndev, u32 i, off; int ret; - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return; @@ -2976,7 +2974,7 @@ fec_enet_open(struct net_device *ndev) int ret; bool reset_again; - ret = pm_runtime_get_sync(&fep->pdev->dev); + ret = pm_runtime_resume_and_get(&fep->pdev->dev); if (ret < 0) return ret; @@ -3770,7 +3768,7 @@ fec_drv_remove(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; int ret; - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) return ret; -- cgit v1.2.3 From a7a20f721e812a52a62a00de20dcd0779fbb587f Mon Sep 17 00:00:00 2001 From: Stanimir Varbanov Date: Tue, 27 Oct 2020 10:19:36 +0100 Subject: media: venus: venc: Fix setting of profile and level The profile and level in op_set_ctrl was recently changed but during v4l2_ctrl_handler_setup profile and level control values are mangled. Fixes: 435c53c3698f ("media: venus: venc: Use helper to set profile and level") Signed-off-by: Stanimir Varbanov Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/qcom/venus/core.h | 15 +++++++++++-- drivers/media/platform/qcom/venus/venc.c | 31 +++++++++++++++++++++++++- drivers/media/platform/qcom/venus/venc_ctrls.c | 14 ++++++++++-- 3 files changed, 55 insertions(+), 5 deletions(-) diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h index 7b79a33dc9d6..05c9fbd51f0c 100644 --- a/drivers/media/platform/qcom/venus/core.h +++ b/drivers/media/platform/qcom/venus/core.h @@ -243,8 +243,19 @@ struct venc_controls { u32 header_mode; - u32 profile; - u32 level; + struct { + u32 h264; + u32 mpeg4; + u32 hevc; + u32 vp8; + u32 vp9; + } profile; + struct { + u32 h264; + u32 mpeg4; + u32 hevc; + u32 vp9; + } level; }; struct venus_buffer { diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c index f8b1484e7dcd..47246528ac7e 100644 --- a/drivers/media/platform/qcom/venus/venc.c +++ b/drivers/media/platform/qcom/venus/venc.c @@ -537,6 +537,7 @@ static int venc_set_properties(struct venus_inst *inst) struct hfi_quantization quant; struct hfi_quantization_range quant_range; u32 ptype, rate_control, bitrate; + u32 profile, level; int ret; ret = venus_helper_set_work_mode(inst, VIDC_WORK_MODE_2); @@ -684,7 +685,35 @@ static int venc_set_properties(struct venus_inst *inst) if (ret) return ret; - ret = venus_helper_set_profile_level(inst, ctr->profile, ctr->level); + switch (inst->hfi_codec) { + case HFI_VIDEO_CODEC_H264: + profile = ctr->profile.h264; + level = ctr->level.h264; + break; + case HFI_VIDEO_CODEC_MPEG4: + profile = ctr->profile.mpeg4; + level = ctr->level.mpeg4; + break; + case HFI_VIDEO_CODEC_VP8: + profile = ctr->profile.vp8; + level = 0; + break; + case HFI_VIDEO_CODEC_VP9: + profile = ctr->profile.vp9; + level = ctr->level.vp9; + break; + case HFI_VIDEO_CODEC_HEVC: + profile = ctr->profile.hevc; + level = ctr->level.hevc; + break; + case HFI_VIDEO_CODEC_MPEG2: + default: + profile = 0; + level = 0; + break; + } + + ret = venus_helper_set_profile_level(inst, profile, level); if (ret) return ret; diff --git a/drivers/media/platform/qcom/venus/venc_ctrls.c b/drivers/media/platform/qcom/venus/venc_ctrls.c index 0708b3b89d0c..cf860e6446c0 100644 --- a/drivers/media/platform/qcom/venus/venc_ctrls.c +++ b/drivers/media/platform/qcom/venus/venc_ctrls.c @@ -103,15 +103,25 @@ static int venc_op_s_ctrl(struct v4l2_ctrl *ctrl) ctr->h264_entropy_mode = ctrl->val; break; case V4L2_CID_MPEG_VIDEO_MPEG4_PROFILE: + ctr->profile.mpeg4 = ctrl->val; + break; case V4L2_CID_MPEG_VIDEO_H264_PROFILE: + ctr->profile.h264 = ctrl->val; + break; case V4L2_CID_MPEG_VIDEO_HEVC_PROFILE: + ctr->profile.hevc = ctrl->val; + break; case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: - ctr->profile = ctrl->val; + ctr->profile.vp8 = ctrl->val; break; case V4L2_CID_MPEG_VIDEO_MPEG4_LEVEL: + ctr->level.mpeg4 = ctrl->val; + break; case V4L2_CID_MPEG_VIDEO_H264_LEVEL: + ctr->level.h264 = ctrl->val; + break; case V4L2_CID_MPEG_VIDEO_HEVC_LEVEL: - ctr->level = ctrl->val; + ctr->level.hevc = ctrl->val; break; case V4L2_CID_MPEG_VIDEO_H264_I_FRAME_QP: ctr->h264_i_qp = ctrl->val; -- cgit v1.2.3 From 9215f6bb4705ffe205885411394732bfc439dee0 Mon Sep 17 00:00:00 2001 From: Stanimir Varbanov Date: Sun, 1 Nov 2020 13:35:52 +0100 Subject: media: venus: pm_helpers: Fix kernel module reload After initial kernel module load during kernel boot and removing the module and try to load it again an Unable to handle kernel paging request is observed: Unable to handle kernel paging request at virtual address ffffa44f7416eae0 Mem abort info: ESR = 0x96000047 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000047 CM = 0, WnR = 1 swapper pgtable: 4k pages, 48-bit VAs, pgdp=000000008147c000 [ffffa44f7416eae0] pgd=000000017df9f003, p4d=000000017df9f003, pud=000000017df9e003, pmd=000000017df9b003, pte=0000000000000000 Internal error: Oops: 96000047 [#1] PREEMPT SMP Modules linked in: venus_core(+) snd_soc_wsa881x regmap_sdw af_alg snd_soc_wcd934x soundwire_qcom gpio_wcd934x q6asm_dai q6routing q6adm q6afe_dai snd_soc_hdmi_codec q6afe q6asm q6dsp_common q6cor display_connector rmtfs_mem drm ip_tables x_tables ipv6 [last unloaded: venus_core] CPU: 6 PID: 889 Comm: modprobe Tainted: G W 5.10.0-rc1+ #8 Hardware name: Thundercomm Dragonboard 845c (DT) pstate: 80400085 (Nzcv daIf +PAN -UAO -TCO BTYPE=--) pc : queued_spin_lock_slowpath+0x1dc/0x3c8 lr : do_raw_spin_lock+0xc0/0x118 sp : ffff8000142cb7b0 x29: ffff8000142cb7b0 x28: 0000000000000013 x27: ffffa44f72de5690 x26: 0000000000000003 x25: ffff17c2d00f8080 x24: ffff17c2c0d78010 x23: ffff17c2c0d4f700 x22: ffff17c2d00f8080 x21: 0000000000000000 x20: ffffa44f74148000 x19: ffff17c2c0d4f8f8 x18: 0000000000000000 x17: 0000000000000000 x16: ffffa44f7342f158 x15: 0000000000000040 x14: ffffa44f746e8320 x13: 0000000000000228 x12: 0000000000000020 x11: 0000000000000000 x10: 00000000001c0000 x9 : 0000000000000000 x8 : ffff17c33d746ac0 x7 : ffff17c2c109b000 x6 : ffffa44f7416eac0 x5 : ffff17c33d746ac0 x4 : 0000000000000000 x3 : ffff17c2c0d4f8f8 x2 : ffffa44f7416eae0 x1 : ffffa44f7416eae0 x0 : ffff17c33d746ac8 Call trace: queued_spin_lock_slowpath+0x1dc/0x3c8 do_raw_spin_lock+0xc0/0x118 _raw_spin_lock_irqsave+0x80/0x14c __pm_runtime_resume+0x38/0xb8 device_link_add+0x3b8/0x5d0 core_get_v4+0x268/0x2d8 [venus_core] venus_probe+0x108/0x458 [venus_core] platform_drv_probe+0x54/0xa8 really_probe+0xe4/0x3b0 driver_probe_device+0x58/0xb8 device_driver_attach+0x74/0x80 __driver_attach+0x58/0xe8 bus_for_each_dev+0x70/0xc0 driver_attach+0x24/0x30 bus_add_driver+0x150/0x1f8 driver_register+0x64/0x120 __platform_driver_register+0x48/0x58 qcom_venus_driver_init+0x20/0x1000 [venus_core] do_one_initcall+0x84/0x458 do_init_module+0x58/0x208 load_module+0x1ec0/0x26a8 __do_sys_finit_module+0xb8/0xf8 __arm64_sys_finit_module+0x20/0x30 el0_svc_common.constprop.0+0x7c/0x1c0 do_el0_svc+0x24/0x90 el0_sync_handler+0x180/0x188 el0_sync+0x174/0x180 Code: 91002100 8b0200c2 f861d884 aa0203e1 (f8246828) ---[ end trace f1f687c15fd6b2ca ]--- note: modprobe[889] exited with preempt_count 1 After revisit the OPP part of the code I found that OPP pmdomain is detached with direct call to dev_pm_domain_detach instead of OPP wraper for detaching pmdomains with OPP table. Correct this by calling the OPP dev_pm_opp_detach_genpd. Fixes: 9a538b83612c ('media: venus: core: Add support for opp tables/perf voting') Signed-off-by: Stanimir Varbanov Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/qcom/venus/pm_helpers.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/qcom/venus/pm_helpers.c b/drivers/media/platform/qcom/venus/pm_helpers.c index 57877eacecf0..a9538c2cc3c9 100644 --- a/drivers/media/platform/qcom/venus/pm_helpers.c +++ b/drivers/media/platform/qcom/venus/pm_helpers.c @@ -794,7 +794,7 @@ skip_pmdomains: return 0; opp_dl_add_err: - dev_pm_domain_detach(core->opp_pmdomain, true); + dev_pm_opp_detach_genpd(core->opp_table); opp_attach_err: if (core->pd_dl_venus) { device_link_del(core->pd_dl_venus); @@ -832,7 +832,7 @@ skip_pmdomains: if (core->opp_dl_venus) device_link_del(core->opp_dl_venus); - dev_pm_domain_detach(core->opp_pmdomain, true); + dev_pm_opp_detach_genpd(core->opp_table); } static int core_get_v4(struct device *dev) -- cgit v1.2.3 From 9d9e937b1c8be97b424e3e11938e183fcde905c0 Mon Sep 17 00:00:00 2001 From: Georg Kohmann Date: Wed, 11 Nov 2020 12:50:25 +0100 Subject: ipv6/netfilter: Discard first fragment not including all headers Packets are processed even though the first fragment don't include all headers through the upper layer header. This breaks TAHI IPv6 Core Conformance Test v6LC.1.3.6. Referring to RFC8200 SECTION 4.5: "If the first fragment does not include all headers through an Upper-Layer header, then that fragment should be discarded and an ICMP Parameter Problem, Code 3, message should be sent to the source of the fragment, with the Pointer field set to zero." The fragment needs to be validated the same way it is done in commit 2efdaaaf883a ("IPv6: reply ICMP error if the first fragment don't include all headers") for ipv6. Wrap the validation into a common function, ipv6_frag_thdr_truncated() to check for truncation in the upper layer header. This validation does not fullfill all aspects of RFC 8200, section 4.5, but is at the moment sufficient to pass mentioned TAHI test. In netfilter, utilize the fragment offset returned by find_prev_fhdr() to let ipv6_frag_thdr_truncated() start it's traverse from the fragment header. Return 0 to drop the fragment in the netfilter. This is the same behaviour as used on other protocol errors in this function, e.g. when nf_ct_frag6_queue() returns -EPROTO. The Fragment will later be picked up by ipv6_frag_rcv() in reassembly.c. ipv6_frag_rcv() will then send an appropriate ICMP Parameter Problem message back to the source. References commit 2efdaaaf883a ("IPv6: reply ICMP error if the first fragment don't include all headers") Signed-off-by: Georg Kohmann Acked-by: Pablo Neira Ayuso Link: https://lore.kernel.org/r/20201111115025.28879-1-geokohma@cisco.com Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 2 ++ net/ipv6/netfilter/nf_conntrack_reasm.c | 9 ++++++ net/ipv6/reassembly.c | 55 +++++++++++++++++++++------------ 3 files changed, 46 insertions(+), 20 deletions(-) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index bd1f396cc9c7..637cc6dd12b7 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1064,6 +1064,8 @@ int ipv6_skip_exthdr(const struct sk_buff *, int start, u8 *nexthdrp, bool ipv6_ext_hdr(u8 nexthdr); +bool ipv6_frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp); + enum { IP6_FH_F_FRAG = (1 << 0), IP6_FH_F_AUTH = (1 << 1), diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 054d287eb13d..b9cc0b330dbe 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -440,6 +440,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { u16 savethdr = skb->transport_header; + u8 nexthdr = NEXTHDR_FRAGMENT; int fhoff, nhoff, ret; struct frag_hdr *fhdr; struct frag_queue *fq; @@ -455,6 +456,14 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) return 0; + /* Discard the first fragment if it does not include all headers + * RFC 8200, Section 4.5 + */ + if (ipv6_frag_thdr_truncated(skb, fhoff, &nexthdr)) { + pr_debug("Drop incomplete fragment\n"); + return 0; + } + if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr))) return -ENOMEM; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index c8cf1bbad74a..e3869bac9c88 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -318,15 +318,43 @@ out_fail: return -1; } +/* Check if the upper layer header is truncated in the first fragment. */ +bool ipv6_frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp) +{ + u8 nexthdr = *nexthdrp; + __be16 frag_off; + int offset; + + offset = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off); + if (offset < 0 || (frag_off & htons(IP6_OFFSET))) + return false; + switch (nexthdr) { + case NEXTHDR_TCP: + offset += sizeof(struct tcphdr); + break; + case NEXTHDR_UDP: + offset += sizeof(struct udphdr); + break; + case NEXTHDR_ICMP: + offset += sizeof(struct icmp6hdr); + break; + default: + offset += 1; + } + if (offset > skb->len) + return true; + return false; +} +EXPORT_SYMBOL(ipv6_frag_thdr_truncated); + static int ipv6_frag_rcv(struct sk_buff *skb) { struct frag_hdr *fhdr; struct frag_queue *fq; const struct ipv6hdr *hdr = ipv6_hdr(skb); struct net *net = dev_net(skb_dst(skb)->dev); - __be16 frag_off; - int iif, offset; u8 nexthdr; + int iif; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED) goto fail_hdr; @@ -362,24 +390,11 @@ static int ipv6_frag_rcv(struct sk_buff *skb) * the source of the fragment, with the Pointer field set to zero. */ nexthdr = hdr->nexthdr; - offset = ipv6_skip_exthdr(skb, skb_transport_offset(skb), &nexthdr, &frag_off); - if (offset >= 0) { - /* Check some common protocols' header */ - if (nexthdr == IPPROTO_TCP) - offset += sizeof(struct tcphdr); - else if (nexthdr == IPPROTO_UDP) - offset += sizeof(struct udphdr); - else if (nexthdr == IPPROTO_ICMPV6) - offset += sizeof(struct icmp6hdr); - else - offset += 1; - - if (!(frag_off & htons(IP6_OFFSET)) && offset > skb->len) { - __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), - IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0); - return -1; - } + if (ipv6_frag_thdr_truncated(skb, skb_transport_offset(skb), &nexthdr)) { + __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), + IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0); + return -1; } iif = skb->dev ? skb->dev->ifindex : 0; -- cgit v1.2.3 From 857524564eae8aefc3006a3d35139bb69ca53210 Mon Sep 17 00:00:00 2001 From: Xie He Date: Sat, 14 Nov 2020 03:10:29 -0800 Subject: MAINTAINERS: Add Martin Schiller as a maintainer for the X.25 stack Martin Schiller is an active developer and reviewer for the X.25 code. His company is providing products based on the Linux X.25 stack. So he is a good candidate for maintainers of the X.25 code. The original maintainer of the X.25 network layer (Andrew Hendry) has not sent any email to the netdev mail list since 2013. So he is probably inactive now. Cc: Andrew Hendry Signed-off-by: Xie He Acked-by: Martin Schiller Link: https://lore.kernel.org/r/20201114111029.326972-1-xie.he.0141@gmail.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 4a34b25ecc1f..e0144f396462 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9843,13 +9843,6 @@ S: Maintained F: arch/mips/lantiq F: drivers/soc/lantiq -LAPB module -L: linux-x25@vger.kernel.org -S: Orphan -F: Documentation/networking/lapb-module.rst -F: include/*/lapb.h -F: net/lapb/ - LASI 53c700 driver for PARISC M: "James E.J. Bottomley" L: linux-scsi@vger.kernel.org @@ -18998,12 +18991,18 @@ L: linux-kernel@vger.kernel.org S: Maintained N: axp[128] -X.25 NETWORK LAYER -M: Andrew Hendry +X.25 STACK +M: Martin Schiller L: linux-x25@vger.kernel.org -S: Odd Fixes +S: Maintained +F: Documentation/networking/lapb-module.rst F: Documentation/networking/x25* +F: drivers/net/wan/hdlc_x25.c +F: drivers/net/wan/lapbether.c +F: include/*/lapb.h F: include/net/x25* +F: include/uapi/linux/x25.h +F: net/lapb/ F: net/x25/ X86 ARCHITECTURE (32-BIT AND 64-BIT) -- cgit v1.2.3 From 4fba15fbb8106e8db17f486d653484e64969eb87 Mon Sep 17 00:00:00 2001 From: Aili Yao Date: Tue, 10 Nov 2020 00:33:34 -0800 Subject: ACPI, APEI, Fix error return value in apei_map_generic_address() From commit 6915564dc5a8 ("ACPI: OSL: Change the type of acpi_os_map_generic_address() return value"), acpi_os_map_generic_address() will return logical address or NULL for error, but for ACPI_ADR_SPACE_SYSTEM_IO case, it should be also return 0 as it's a normal case, but now it will return -ENXIO. So check it out for such case to avoid einj module initialization fail. Fixes: 6915564dc5a8 ("ACPI: OSL: Change the type of acpi_os_map_generic_address() return value") Cc: Reviewed-by: James Morse Tested-by: Tony Luck Signed-off-by: Aili Yao Signed-off-by: Rafael J. Wysocki --- drivers/acpi/apei/apei-base.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index 552fd9ffaca4..3294cc8dc073 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -633,6 +633,10 @@ int apei_map_generic_address(struct acpi_generic_address *reg) if (rc) return rc; + /* IO space doesn't need mapping */ + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) + return 0; + if (!acpi_os_map_generic_address(reg)) return -ENXIO; -- cgit v1.2.3 From 728321e53045d2668bf2b8627a8d61bc2c480d3b Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 13 Nov 2020 02:21:19 -0500 Subject: drm/amd/display: Add missing pflip irq for dcn2.0 If we have more than 4 displays we will run into dummy irq calls or flip timout issues. Reviewed-by: Nicholas Kazlauskas Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c index 2a1fea501f8c..3f1e7a196a23 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c @@ -299,8 +299,8 @@ irq_source_info_dcn20[DAL_IRQ_SOURCES_NUMBER] = { pflip_int_entry(1), pflip_int_entry(2), pflip_int_entry(3), - [DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(), - [DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(), + pflip_int_entry(4), + pflip_int_entry(5), [DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(), gpio_pad_int_entry(0), gpio_pad_int_entry(1), -- cgit v1.2.3 From 854c57f02bc718b0653bc467073b4541b8155a36 Mon Sep 17 00:00:00 2001 From: Ashish Kalra Date: Tue, 10 Nov 2020 22:42:05 +0000 Subject: KVM: SVM: Fix offset computation bug in __sev_dbg_decrypt(). Fix offset computation in __sev_dbg_decrypt() to include the source paddr before it is rounded down to be aligned to 16 bytes as required by SEV API. This fixes incorrect guest memory dumps observed when using qemu monitor. Signed-off-by: Ashish Kalra Message-Id: <20201110224205.29444-1-Ashish.Kalra@amd.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index c0b14106258a..566f4d18185b 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -642,8 +642,8 @@ static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, * Its safe to read more than we are asked, caller should ensure that * destination has enough space. */ - src_paddr = round_down(src_paddr, 16); offset = src_paddr & 15; + src_paddr = round_down(src_paddr, 16); sz = round_up(sz + offset, 16); return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false); -- cgit v1.2.3 From 1bd7b0fc0165694897b7d2fb39751a07b98f6bf1 Mon Sep 17 00:00:00 2001 From: Michael Sit Wei Hong Date: Mon, 16 Nov 2020 14:19:01 +0800 Subject: ASoC: Intel: KMB: Fix S24_LE configuration S24_LE is 24 bit audio in 32 bit container configuration Fixing the configuration to match the data arrangement of this audio format. Fixes: c5477e966728 ("ASoC: Intel: Add KeemBay platform driver") Signed-off-by: Michael Sit Wei Hong Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20201116061905.32431-2-michael.wei.hong.sit@intel.com Signed-off-by: Mark Brown --- sound/soc/intel/keembay/kmb_platform.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/sound/soc/intel/keembay/kmb_platform.c b/sound/soc/intel/keembay/kmb_platform.c index f54b710ee1c2..291a686568c2 100644 --- a/sound/soc/intel/keembay/kmb_platform.c +++ b/sound/soc/intel/keembay/kmb_platform.c @@ -487,9 +487,9 @@ static int kmb_dai_hw_params(struct snd_pcm_substream *substream, kmb_i2s->xfer_resolution = 0x02; break; case SNDRV_PCM_FORMAT_S24_LE: - config->data_width = 24; - kmb_i2s->ccr = 0x08; - kmb_i2s->xfer_resolution = 0x04; + config->data_width = 32; + kmb_i2s->ccr = 0x14; + kmb_i2s->xfer_resolution = 0x05; break; case SNDRV_PCM_FORMAT_S32_LE: config->data_width = 32; -- cgit v1.2.3 From bd6327fda2f3ded85b69b3c3125c99aaa51c7881 Mon Sep 17 00:00:00 2001 From: Srinivasa Rao Mandadapu Date: Sun, 15 Nov 2020 10:26:50 +0530 Subject: ASoC: qcom: lpass-platform: Fix memory leak lpass_pcm_data is not freed in error paths. Free it in error paths to avoid memory leak. Fixes: 022d00ee0b55 ("ASoC: lpass-platform: Fix broken pcm data usage") Signed-off-by: Pavel Machek Signed-off-by: V Sujith Kumar Reddy Signed-off-by: Srinivasa Rao Mandadapu Link: https://lore.kernel.org/r/1605416210-14530-1-git-send-email-srivasam@codeaurora.org Signed-off-by: Mark Brown --- sound/soc/qcom/lpass-platform.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c index 36d1512ffd1f..7a3fdf89968a 100644 --- a/sound/soc/qcom/lpass-platform.c +++ b/sound/soc/qcom/lpass-platform.c @@ -122,8 +122,10 @@ static int lpass_platform_pcmops_open(struct snd_soc_component *component, else dma_ch = 0; - if (dma_ch < 0) + if (dma_ch < 0) { + kfree(data); return dma_ch; + } if (cpu_dai->driver->id == LPASS_DP_RX) { map = drvdata->hdmiif_map; @@ -147,6 +149,7 @@ static int lpass_platform_pcmops_open(struct snd_soc_component *component, ret = snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); if (ret < 0) { + kfree(data); dev_err(soc_runtime->dev, "setting constraints failed: %d\n", ret); return -EINVAL; -- cgit v1.2.3 From ac9978fcad3c5abc43cdd225441ce9459c36e16b Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Mon, 16 Nov 2020 22:18:36 +0800 Subject: spi: cadence-quadspi: Fix error return code in cqspi_probe Fix to return the error code from devm_reset_control_get_optional_exclusive() instaed of 0 in cqspi_probe(). Fixes: 31fb632b5d43ca ("spi: Move cadence-quadspi driver to drivers/spi/") Reported-by: Hulk Robot Signed-off-by: Zhihao Cheng Reviewed-by: Philipp Zabel Link: https://lore.kernel.org/r/20201116141836.2970579-1-chengzhihao1@huawei.com Signed-off-by: Mark Brown --- drivers/spi/spi-cadence-quadspi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 40938cf3806d..ba7d40c2922f 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1260,12 +1260,14 @@ static int cqspi_probe(struct platform_device *pdev) /* Obtain QSPI reset control */ rstc = devm_reset_control_get_optional_exclusive(dev, "qspi"); if (IS_ERR(rstc)) { + ret = PTR_ERR(rstc); dev_err(dev, "Cannot get QSPI reset.\n"); goto probe_reset_failed; } rstc_ocp = devm_reset_control_get_optional_exclusive(dev, "qspi-ocp"); if (IS_ERR(rstc_ocp)) { + ret = PTR_ERR(rstc_ocp); dev_err(dev, "Cannot get QSPI OCP reset.\n"); goto probe_reset_failed; } -- cgit v1.2.3 From aa9e3fa4992d83acb7311fc86d11d0d53e7ffb8e Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Mon, 16 Nov 2020 14:33:28 +0100 Subject: ASoC: Intel: catpt: Skip position update for unprepared streams Playing with very low period sizes may lead to timeouts when awaiting RESET_STREAM reply for offload streams. This is caused by NOTIFY_POSITION appearing in the middle of trigger(stop). Stream is unprepared during trigger(stop) where PAUSE_STREAM IPC gets invoked. However, all data that is already mixed in DSP firmware's mixer stream will still be played regardless of the pause. For offload streams, this means possibility for another NOTIFY_POSITION to process. Keep these notifications in check by only handling them when stream is in prepared state. Fixes: a126750fc865 ("ASoC: Intel: catpt: PCM operations") Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20201116133332.8530-2-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- sound/soc/intel/catpt/pcm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/intel/catpt/pcm.c b/sound/soc/intel/catpt/pcm.c index f78018c857b8..174a786cd776 100644 --- a/sound/soc/intel/catpt/pcm.c +++ b/sound/soc/intel/catpt/pcm.c @@ -534,6 +534,8 @@ void catpt_stream_update_position(struct catpt_dev *cdev, dsppos = bytes_to_frames(r, pos->stream_position); + if (!stream->prepared) + goto exit; /* only offload is set_write_pos driven */ if (stream->template->type != CATPT_STRM_TYPE_RENDER) goto exit; -- cgit v1.2.3 From 1072460a1aabacf6ececda98acd3b5ecaad23fd2 Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Mon, 16 Nov 2020 14:33:29 +0100 Subject: ASoC: Intel: catpt: Correct clock selection for dai trigger During stream start DSP firmware requires LPCS disabled as that moment in time is resource heavy. Currently high-clock is selected on start of second stream onwards while low-clock is re-selected before stream actually leaves RESUME state i.e. PAUSE_STREAM call. Fix this by always updating clock before RESUME_STREAM and directly after PAUSE_STREAM. Fixes: a126750fc865 ("ASoC: Intel: catpt: PCM operations") Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20201116133332.8530-3-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- sound/soc/intel/catpt/pcm.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/sound/soc/intel/catpt/pcm.c b/sound/soc/intel/catpt/pcm.c index 174a786cd776..2061978b6cb9 100644 --- a/sound/soc/intel/catpt/pcm.c +++ b/sound/soc/intel/catpt/pcm.c @@ -458,10 +458,6 @@ static int catpt_dai_prepare(struct snd_pcm_substream *substream, if (ret) return CATPT_IPC_ERROR(ret); - ret = catpt_dsp_update_lpclock(cdev); - if (ret) - return ret; - ret = catpt_dai_apply_usettings(dai, stream); if (ret) return ret; @@ -500,6 +496,7 @@ static int catpt_dai_trigger(struct snd_pcm_substream *substream, int cmd, case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: resume_stream: + catpt_dsp_update_lpclock(cdev); ret = catpt_ipc_resume_stream(cdev, stream->info.stream_hw_id); if (ret) return CATPT_IPC_ERROR(ret); @@ -507,11 +504,11 @@ static int catpt_dai_trigger(struct snd_pcm_substream *substream, int cmd, case SNDRV_PCM_TRIGGER_STOP: stream->prepared = false; - catpt_dsp_update_lpclock(cdev); fallthrough; case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: ret = catpt_ipc_pause_stream(cdev, stream->info.stream_hw_id); + catpt_dsp_update_lpclock(cdev); if (ret) return CATPT_IPC_ERROR(ret); break; -- cgit v1.2.3 From 0abed7c69b956d135cb6d320c350b2adb213e7d8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 16 Nov 2020 13:36:24 -0700 Subject: mm: never attempt async page lock if we've transferred data already We catch the case where we enter generic_file_buffered_read() with data already transferred, but we also need to be careful not to allow an async page lock if we're looping transferring data. If not, we could be returning -EIOCBQUEUED instead of the transferred amount, and it could result in double waitqueue additions as well. Cc: stable@vger.kernel.org # v5.9 Fixes: 1a0a7853b901 ("mm: support async buffered reads in generic_file_buffered_read()") Signed-off-by: Jens Axboe --- mm/filemap.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/mm/filemap.c b/mm/filemap.c index d5e7c2029d16..3ebbe64a0106 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2347,10 +2347,15 @@ page_ok: page_not_up_to_date: /* Get exclusive access to the page ... */ - if (iocb->ki_flags & IOCB_WAITQ) + if (iocb->ki_flags & IOCB_WAITQ) { + if (written) { + put_page(page); + goto out; + } error = lock_page_async(page, iocb->ki_waitq); - else + } else { error = lock_page_killable(page); + } if (unlikely(error)) goto readpage_error; @@ -2393,10 +2398,15 @@ readpage: } if (!PageUptodate(page)) { - if (iocb->ki_flags & IOCB_WAITQ) + if (iocb->ki_flags & IOCB_WAITQ) { + if (written) { + put_page(page); + goto out; + } error = lock_page_async(page, iocb->ki_waitq); - else + } else { error = lock_page_killable(page); + } if (unlikely(error)) goto readpage_error; -- cgit v1.2.3 From 2acc3c1bc8e98bc66b1badec42e9ea205b4fcdaa Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Mon, 16 Nov 2020 18:16:33 +0800 Subject: selftests/bpf: Fix error return code in run_getsockopt_test() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 65b4414a05eb ("selftests/bpf: add sockopt test that exercises BPF_F_ALLOW_MULTI") Reported-by: Hulk Robot Signed-off-by: Wang Hai Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20201116101633.64627-1-wanghai38@huawei.com --- tools/testing/selftests/bpf/prog_tests/sockopt_multi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index 29188d6f5c8d..51fac975b316 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -138,7 +138,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, */ buf = 0x40; - if (setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1) < 0) { + err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1); + if (err < 0) { log_err("Failed to call setsockopt(IP_TOS)"); goto detach; } -- cgit v1.2.3 From 2a1828e378c1b5ba1ff283ed8f8c5cc37bb391dc Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sun, 15 Nov 2020 17:57:57 +0100 Subject: net: lantiq: Wait for the GPHY firmware to be ready A user reports (slightly shortened from the original message): libphy: lantiq,xrx200-mdio: probed mdio_bus 1e108000.switch-mii: MDIO device at address 17 is missing. gswip 1e108000.switch lan: no phy at 2 gswip 1e108000.switch lan: failed to connect to port 2: -19 lantiq,xrx200-net 1e10b308.eth eth0: error -19 setting up slave phy This is a single-port board using the internal Fast Ethernet PHY. The user reports that switching to PHY scanning instead of configuring the PHY within device-tree works around this issue. The documentation for the standalone variant of the PHY11G (which is probably very similar to what is used inside the xRX200 SoCs but having the firmware burnt onto that standalone chip in the factory) states that the PHY needs 300ms to be ready for MDIO communication after releasing the reset. Add a 300ms delay after initializing all GPHYs to ensure that the GPHY firmware had enough time to initialize and to appear on the MDIO bus. Unfortunately there is no (known) documentation on what the minimum time to wait after releasing the reset on an internal PHY so play safe and take the one for the external variant. Only wait after the last GPHY firmware is loaded to not slow down the initialization too much ( xRX200 has two GPHYs but newer SoCs have at least three GPHYs). Fixes: 14fceff4771e51 ("net: dsa: Add Lantiq / Intel DSA driver for vrx200") Reviewed-by: Andrew Lunn Signed-off-by: Martin Blumenstingl Acked-by: Hauke Mehrtens Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20201115165757.552641-1-martin.blumenstingl@googlemail.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/lantiq_gswip.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 74db81dafee3..09701c17f3f6 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -26,6 +26,7 @@ */ #include +#include #include #include #include @@ -1837,6 +1838,16 @@ static int gswip_gphy_fw_list(struct gswip_priv *priv, i++; } + /* The standalone PHY11G requires 300ms to be fully + * initialized and ready for any MDIO communication after being + * taken out of reset. For the SoC-internal GPHY variant there + * is no (known) documentation for the minimum time after a + * reset. Use the same value as for the standalone variant as + * some users have reported internal PHYs not being detected + * without any delay. + */ + msleep(300); + return 0; remove_gphy: -- cgit v1.2.3 From c1609f0e2882095408708a80693e298a90f17904 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 16 Nov 2020 10:10:52 -0500 Subject: drm/amdgpu: remove experimental flag from arcturus This has been stable for a while. Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 42d9748921f5..8e988f07f085 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1055,10 +1055,10 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU}, {0x1002, 0x15d8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU}, /* Arcturus */ - {0x1002, 0x738C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7388, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x738E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7390, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x738C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, + {0x1002, 0x7388, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, + {0x1002, 0x738E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, + {0x1002, 0x7390, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, /* Navi10 */ {0x1002, 0x7310, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, {0x1002, 0x7312, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, -- cgit v1.2.3 From 794e442ca39e6c8d46003c430559bdb67a73690c Mon Sep 17 00:00:00 2001 From: Raju Rangoju Date: Mon, 16 Nov 2020 16:13:22 +0530 Subject: MAINTAINERS: update cxgb4 and cxgb3 maintainer Update cxgb4 and cxgb3 driver maintainer Signed-off-by: Raju Rangoju Link: https://lore.kernel.org/r/20201116104322.3959-1-rajur@chelsio.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index e0144f396462..8cb1aae96bdf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4710,7 +4710,7 @@ T: git git://linuxtv.org/anttip/media_tree.git F: drivers/media/dvb-frontends/cxd2820r* CXGB3 ETHERNET DRIVER (CXGB3) -M: Vishal Kulkarni +M: Raju Rangoju L: netdev@vger.kernel.org S: Supported W: http://www.chelsio.com @@ -4742,7 +4742,7 @@ W: http://www.chelsio.com F: drivers/net/ethernet/chelsio/inline_crypto/ CXGB4 ETHERNET DRIVER (CXGB4) -M: Vishal Kulkarni +M: Raju Rangoju L: netdev@vger.kernel.org S: Supported W: http://www.chelsio.com @@ -4764,7 +4764,7 @@ F: drivers/infiniband/hw/cxgb4/ F: include/uapi/rdma/cxgb4-abi.h CXGB4VF ETHERNET DRIVER (CXGB4VF) -M: Vishal Kulkarni +M: Raju Rangoju L: netdev@vger.kernel.org S: Supported W: http://www.chelsio.com -- cgit v1.2.3 From 85a12d7eb8fe449cf38f1aa9ead5ca744729a98f Mon Sep 17 00:00:00 2001 From: Rodrigo Vivi Date: Wed, 11 Nov 2020 09:09:36 -0500 Subject: drm/i915/tgl: Fix Media power gate sequence. Some media power gates are disabled by default. commit 5d86923060fc ("drm/i915/tgl: Enable VD HCP/MFX sub-pipe power gating") tried to enable it, but it duplicated an existent register. So, the main PG setup sequences ended up overwriting it. So, let's now merge this to the main PG setup sequence. v2: (Chris): s/BIT/REG_BIT, remove useless comment, remove useless =0, use the right gt, remove rc6 sequence doubt from commit message. Fixes: 5d86923060fc ("drm/i915/tgl: Enable VD HCP/MFX sub-pipe power gating") Cc: Lucas De Marchi Cc: stable@vger.kernel.org#v5.5+ Cc: Dale B Stimson Signed-off-by: Rodrigo Vivi Cc: Chris Wilson Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20201111072859.1186070-1-rodrigo.vivi@intel.com (cherry picked from commit 695dc55b573985569259e18f8e6261a77924342b) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_rc6.c | 22 +++++++++++++++++----- drivers/gpu/drm/i915/i915_reg.h | 12 +++++------- drivers/gpu/drm/i915/intel_pm.c | 13 ------------- 3 files changed, 22 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index ab675d35030d..d7b8e4457fc2 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -56,9 +56,12 @@ static inline void set(struct intel_uncore *uncore, i915_reg_t reg, u32 val) static void gen11_rc6_enable(struct intel_rc6 *rc6) { - struct intel_uncore *uncore = rc6_to_uncore(rc6); + struct intel_gt *gt = rc6_to_gt(rc6); + struct intel_uncore *uncore = gt->uncore; struct intel_engine_cs *engine; enum intel_engine_id id; + u32 pg_enable; + int i; /* 2b: Program RC6 thresholds.*/ set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85); @@ -102,10 +105,19 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6) GEN6_RC_CTL_RC6_ENABLE | GEN6_RC_CTL_EI_MODE(1); - set(uncore, GEN9_PG_ENABLE, - GEN9_RENDER_PG_ENABLE | - GEN9_MEDIA_PG_ENABLE | - GEN11_MEDIA_SAMPLER_PG_ENABLE); + pg_enable = + GEN9_RENDER_PG_ENABLE | + GEN9_MEDIA_PG_ENABLE | + GEN11_MEDIA_SAMPLER_PG_ENABLE; + + if (INTEL_GEN(gt->i915) >= 12) { + for (i = 0; i < I915_MAX_VCS; i++) + if (HAS_ENGINE(gt, _VCS(i))) + pg_enable |= (VDN_HCP_POWERGATE_ENABLE(i) | + VDN_MFX_POWERGATE_ENABLE(i)); + } + + set(uncore, GEN9_PG_ENABLE, pg_enable); } static void gen9_rc6_enable(struct intel_rc6 *rc6) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index d805d4da6181..664f3bf9af03 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -8971,10 +8971,6 @@ enum { #define GEN9_PWRGT_MEDIA_STATUS_MASK (1 << 0) #define GEN9_PWRGT_RENDER_STATUS_MASK (1 << 1) -#define POWERGATE_ENABLE _MMIO(0xa210) -#define VDN_HCP_POWERGATE_ENABLE(n) BIT(((n) * 2) + 3) -#define VDN_MFX_POWERGATE_ENABLE(n) BIT(((n) * 2) + 4) - #define GTFIFODBG _MMIO(0x120000) #define GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV (0x1f << 20) #define GT_FIFO_FREE_ENTRIES_CHV (0x7f << 13) @@ -9114,9 +9110,11 @@ enum { #define GEN9_MEDIA_PG_IDLE_HYSTERESIS _MMIO(0xA0C4) #define GEN9_RENDER_PG_IDLE_HYSTERESIS _MMIO(0xA0C8) #define GEN9_PG_ENABLE _MMIO(0xA210) -#define GEN9_RENDER_PG_ENABLE REG_BIT(0) -#define GEN9_MEDIA_PG_ENABLE REG_BIT(1) -#define GEN11_MEDIA_SAMPLER_PG_ENABLE REG_BIT(2) +#define GEN9_RENDER_PG_ENABLE REG_BIT(0) +#define GEN9_MEDIA_PG_ENABLE REG_BIT(1) +#define GEN11_MEDIA_SAMPLER_PG_ENABLE REG_BIT(2) +#define VDN_HCP_POWERGATE_ENABLE(n) REG_BIT(3 + 2 * (n)) +#define VDN_MFX_POWERGATE_ENABLE(n) REG_BIT(4 + 2 * (n)) #define GEN8_PUSHBUS_CONTROL _MMIO(0xA248) #define GEN8_PUSHBUS_ENABLE _MMIO(0xA250) #define GEN8_PUSHBUS_SHIFT _MMIO(0xA25C) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 34e0d22d456b..cfb806767fc5 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -7118,23 +7118,10 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv) static void tgl_init_clock_gating(struct drm_i915_private *dev_priv) { - u32 vd_pg_enable = 0; - unsigned int i; - /* Wa_1409120013:tgl */ I915_WRITE(ILK_DPFC_CHICKEN, ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL); - /* This is not a WA. Enable VD HCP & MFX_ENC powergate */ - for (i = 0; i < I915_MAX_VCS; i++) { - if (HAS_ENGINE(&dev_priv->gt, _VCS(i))) - vd_pg_enable |= VDN_HCP_POWERGATE_ENABLE(i) | - VDN_MFX_POWERGATE_ENABLE(i); - } - - I915_WRITE(POWERGATE_ENABLE, - I915_READ(POWERGATE_ENABLE) | vd_pg_enable); - /* Wa_1409825376:tgl (pre-prod)*/ if (IS_TGL_DISP_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_B1)) I915_WRITE(GEN9_CLKGATE_DIS_3, I915_READ(GEN9_CLKGATE_DIS_3) | -- cgit v1.2.3 From 973dd87fa56ac943ce1060fd07244d7652115164 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Fri, 13 Nov 2020 13:25:10 +0000 Subject: drm/i915: Avoid memory leak with more than 16 workarounds on a list I forgot to free the old list when growing past 16 entries. Luckily, as much as I checked, none of the current platforms has more than 16 workarounds on a single list. Signed-off-by: Tvrtko Ursulin Fixes: 452420d22d5b ("drm/i915: Fuse per-context workaround handling with the common framework") Reported-by: Chris Wilson Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20201113132510.2298483-1-tvrtko.ursulin@linux.intel.com (cherry picked from commit 77c296966e866a795742a46fc52a218771894867) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 6c580d0d9ea8..4a3bde7c9f21 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -131,8 +131,10 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) return; } - if (wal->list) + if (wal->list) { memcpy(list, wal->list, sizeof(*wa) * wal->count); + kfree(wal->list); + } wal->list = list; } -- cgit v1.2.3 From 2106edbdfd15e37afa6c5225421b8036bf0e38ec Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Mon, 16 Nov 2020 09:41:12 -0500 Subject: drm/i915/selftests: Fix wrong return value of perf_series_engines() If intel context create failed, the perf_series_engines() will return 0 rather than error, because we doesn't initialize the return value. Fixes: cbfd3a0c5a55 ("drm/i915/selftests: Add request throughput measurement to perf") Reported-by: Hulk Robot Signed-off-by: Zhang Xiaoxu Reviewed-by: Mika Kuoppala Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20201116144112.3673011-1-zhangxiaoxu5@huawei.com (cherry picked from commit 01d708840c26c9532579677eaca942363a009fd5) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/selftests/i915_request.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index 64bbb8288249..480b3da4d8a6 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -2467,8 +2467,10 @@ static int perf_series_engines(void *arg) struct intel_context *ce; ce = intel_context_create(engine); - if (IS_ERR(ce)) + if (IS_ERR(ce)) { + err = PTR_ERR(ce); goto out; + } err = intel_context_pin(ce); if (err) { -- cgit v1.2.3 From b5462cc377748181af2b05729c69f5faecec3717 Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Mon, 16 Nov 2020 09:35:40 -0500 Subject: drm/i915/selftests: Fix wrong return value of perf_request_latency() If intel context create failed, the perf_request_latency() will return 0 rather than error, because we doesn't initialize the return value. Fixes: 25c26f18ea79 ("drm/i915/selftests: Measure dispatch latency") Reported-by: Hulk Robot Signed-off-by: Zhang Xiaoxu Reviewed-by: Mika Kuoppala Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20201116143540.3648870-1-zhangxiaoxu5@huawei.com (cherry picked from commit 19384452052a1e0525e663bfbdd62ac1399bb647) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/selftests/i915_request.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index 480b3da4d8a6..e424a6d1a68c 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -2293,8 +2293,10 @@ static int perf_request_latency(void *arg) struct intel_context *ce; ce = intel_context_create(engine); - if (IS_ERR(ce)) + if (IS_ERR(ce)) { + err = PTR_ERR(ce); goto out; + } err = intel_context_pin(ce); if (err) { -- cgit v1.2.3 From cfbaa8b33e022aca62a3f2815ffbc02874d4cb8b Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Fri, 13 Nov 2020 14:07:07 +0800 Subject: cx82310_eth: fix error return code in cx82310_bind() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: ca139d76b0d9 ("cx82310_eth: re-enable ethernet mode after router reboot") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Link: https://lore.kernel.org/r/1605247627-15385-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/usb/cx82310_eth.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c index ca89d8258dd3..c4568a491dc4 100644 --- a/drivers/net/usb/cx82310_eth.c +++ b/drivers/net/usb/cx82310_eth.c @@ -197,7 +197,8 @@ static int cx82310_bind(struct usbnet *dev, struct usb_interface *intf) } /* enable ethernet mode (?) */ - if (cx82310_enable_ethernet(dev)) + ret = cx82310_enable_ethernet(dev); + if (ret) goto err; /* get the MAC address */ -- cgit v1.2.3 From 3beb9be165083c2964eba1923601c3bfac0b02d4 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Fri, 13 Nov 2020 14:16:26 +0800 Subject: qlcnic: fix error return code in qlcnic_83xx_restart_hw() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 3ced0a88cd4c ("qlcnic: Add support to run firmware POST") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Link: https://lore.kernel.org/r/1605248186-16013-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index b8af59fc1aa4..d2c190732d3e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -2231,7 +2231,8 @@ static int qlcnic_83xx_restart_hw(struct qlcnic_adapter *adapter) /* Boot either flash image or firmware image from host file system */ if (qlcnic_load_fw_file == 1) { - if (qlcnic_83xx_load_fw_image_from_host(adapter)) + err = qlcnic_83xx_load_fw_image_from_host(adapter); + if (err) return err; } else { QLC_SHARED_REG_WR32(adapter, QLCNIC_FW_IMG_VALID, -- cgit v1.2.3 From 661710bfd5039267f911e42675ab743760b6449d Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Fri, 13 Nov 2020 14:34:03 +0800 Subject: net: stmmac: dwmac-intel-plat: fix error return code in intel_eth_plat_probe() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 9efc9b2b04c7 ("net: stmmac: Add dwmac-intel-plat for GBE driver") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Link: https://lore.kernel.org/r/1605249243-17262-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c index f61cb997a8f6..82b1c7a5a7a9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c @@ -113,8 +113,10 @@ static int intel_eth_plat_probe(struct platform_device *pdev) /* Enable TX clock */ if (dwmac->data->tx_clk_en) { dwmac->tx_clk = devm_clk_get(&pdev->dev, "tx_clk"); - if (IS_ERR(dwmac->tx_clk)) + if (IS_ERR(dwmac->tx_clk)) { + ret = PTR_ERR(dwmac->tx_clk); goto err_remove_config_dt; + } clk_prepare_enable(dwmac->tx_clk); -- cgit v1.2.3 From 35f735c665114840dcd3142f41148d07870f51f7 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Fri, 13 Nov 2020 14:49:33 +0800 Subject: net: ethernet: ti: cpsw: fix error return code in cpsw_probe() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 83a8471ba255 ("net: ethernet: ti: cpsw: refactor probe to group common hw initialization") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Link: https://lore.kernel.org/r/1605250173-18438-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/cpsw.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index fa2d1025cbb2..b0f00b4edd94 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1634,6 +1634,7 @@ static int cpsw_probe(struct platform_device *pdev) CPSW_MAX_QUEUES, CPSW_MAX_QUEUES); if (!ndev) { dev_err(dev, "error allocating net_device\n"); + ret = -ENOMEM; goto clean_cpts; } -- cgit v1.2.3 From 7a30ecc9237681bb125cbd30eee92bef7e86293d Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 13 Nov 2020 10:27:27 +0100 Subject: net: bridge: add missing counters to ndo_get_stats64 callback In br_forward.c and br_input.c fields dev->stats.tx_dropped and dev->stats.multicast are populated, but they are ignored in ndo_get_stats64. Fixes: 28172739f0a2 ("net: fix 64 bit counters on 32 bit arches") Signed-off-by: Heiner Kallweit Link: https://lore.kernel.org/r/58ea9963-77ad-a7cf-8dfd-fc95ab95f606@gmail.com Signed-off-by: Jakub Kicinski --- net/bridge/br_device.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 6f742fee874a..7730c8f3cb53 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -207,6 +207,7 @@ static void br_get_stats64(struct net_device *dev, { struct net_bridge *br = netdev_priv(dev); + netdev_stats_to_stats64(stats, &dev->stats); dev_fetch_sw_netstats(stats, br->stats); } -- cgit v1.2.3 From 8e5debed39017836a850c6c7bfacc93299d19bad Mon Sep 17 00:00:00 2001 From: Wong Vee Khee Date: Sun, 15 Nov 2020 15:42:10 +0800 Subject: net: stmmac: Use rtnl_lock/unlock on netif_set_real_num_rx_queues() call Fix an issue where dump stack is printed on suspend resume flow due to netif_set_real_num_rx_queues() is not called with rtnl_lock held(). Fixes: 686cff3d7022 ("net: stmmac: Fix incorrect location to set real_num_rx|tx_queues") Reported-by: Christophe ROULLIER Tested-by: Christophe ROULLIER Cc: Alexandre TORGUE Reviewed-by: Ong Boon Leong Signed-off-by: Wong Vee Khee Link: https://lore.kernel.org/r/20201115074210.23605-1-vee.khee.wong@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d833908b660a..ba45fe237512 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5247,6 +5247,7 @@ int stmmac_resume(struct device *dev) return ret; } + rtnl_lock(); mutex_lock(&priv->lock); stmmac_reset_queues_param(priv); @@ -5262,6 +5263,7 @@ int stmmac_resume(struct device *dev) stmmac_enable_all_queues(priv); mutex_unlock(&priv->lock); + rtnl_unlock(); if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { rtnl_lock(); -- cgit v1.2.3 From 9c79a8ab5f124db01eb1d7287454a702f0d4252f Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 13 Nov 2020 19:16:57 +0100 Subject: net: mvneta: fix possible memory leak in mvneta_swbm_add_rx_fragment Recycle the page running page_pool_put_full_page() in mvneta_swbm_add_rx_fragment routine when the last descriptor contains just the FCS or if the received packet contains more than MAX_SKB_FRAGS fragments Fixes: ca0e014609f0 ("net: mvneta: move skb build after descriptors processing") Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/df6a2bad70323ee58d3901491ada31c1ca2a40b9.1605291228.git.lorenzo@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/mvneta.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 54b0bf574c05..4a9041ee1b39 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2287,6 +2287,7 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, dma_sync_single_for_cpu(dev->dev.parent, rx_desc->buf_phys_addr, len, dma_dir); + rx_desc->buf_phys_addr = 0; if (data_len > 0 && sinfo->nr_frags < MAX_SKB_FRAGS) { skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags]; @@ -2295,8 +2296,8 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, skb_frag_size_set(frag, data_len); __skb_frag_set_page(frag, page); sinfo->nr_frags++; - - rx_desc->buf_phys_addr = 0; + } else { + page_pool_put_full_page(rxq->page_pool, page, true); } *size -= len; } -- cgit v1.2.3 From fc70f5bf5e525dde81565f0a30d5e39168062eba Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Fri, 13 Nov 2020 13:12:05 -0700 Subject: net: qualcomm: rmnet: Fix incorrect receive packet handling during cleanup During rmnet unregistration, the real device rx_handler is first cleared followed by the removal of rx_handler_data after the rcu synchronization. Any packets in the receive path may observe that the rx_handler is NULL. However, there is no check when dereferencing this value to use the rmnet_port information. This fixes following splat by adding the NULL check. Unable to handle kernel NULL pointer dereference at virtual address 000000000000000d pc : rmnet_rx_handler+0x124/0x284 lr : rmnet_rx_handler+0x124/0x284 rmnet_rx_handler+0x124/0x284 __netif_receive_skb_core+0x758/0xd74 __netif_receive_skb+0x50/0x17c process_backlog+0x15c/0x1b8 napi_poll+0x88/0x284 net_rx_action+0xbc/0x23c __do_softirq+0x20c/0x48c Fixes: ceed73a2cf4a ("drivers: net: ethernet: qualcomm: rmnet: Initial implementation") Signed-off-by: Sean Tranchetti Signed-off-by: Subash Abhinov Kasiviswanathan Link: https://lore.kernel.org/r/1605298325-3705-1-git-send-email-subashab@codeaurora.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 29a7bfa2584d..3d7d3ab383f8 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -188,6 +188,11 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) dev = skb->dev; port = rmnet_get_port_rcu(dev); + if (unlikely(!port)) { + atomic_long_inc(&skb->dev->rx_nohandler); + kfree_skb(skb); + goto done; + } switch (port->rmnet_mode) { case RMNET_EPMODE_VND: -- cgit v1.2.3 From 3fe16edf6767decd640fa2654308bc64f8d656dc Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Sun, 15 Nov 2020 07:16:00 +0300 Subject: net/tls: fix corrupted data in recvmsg If tcp socket has more data than Encrypted Handshake Message then tls_sw_recvmsg will try to decrypt next record instead of returning full control message to userspace as mentioned in comment. The next message - usually Application Data - gets corrupted because it uses zero copy for decryption that's why the data is not stored in skb for next iteration. Revert check to not decrypt next record if current is not Application Data. Fixes: 692d7b5d1f91 ("tls: Fix recvmsg() to be able to peek across multiple records") Signed-off-by: Vadim Fedorenko Link: https://lore.kernel.org/r/1605413760-21153-1-git-send-email-vfedorenko@novek.ru Signed-off-by: Jakub Kicinski --- net/tls/tls_sw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 95ab5545a931..2fe9e2cf8659 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1913,7 +1913,7 @@ pick_next_record: * another message type */ msg->msg_flags |= MSG_EOR; - if (ctx->control != TLS_RECORD_TYPE_DATA) + if (control != TLS_RECORD_TYPE_DATA) goto recv_end; } else { break; -- cgit v1.2.3 From 064c9c32b17ca9b36f95eba32ee790dbbebd9a5f Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Sat, 14 Nov 2020 12:20:17 -0600 Subject: net: ipa: lock when freeing transaction Transactions sit on one of several lists, depending on their state (allocated, pending, complete, or polled). A spinlock protects against concurrent access when transactions are moved between these lists. Transactions are also reference counted. A newly-allocated transaction has an initial count of 1; a transaction is released in gsi_trans_free() only if its decremented reference count reaches 0. Releasing a transaction includes removing it from the polled (or if unused, allocated) list, so the spinlock is acquired when we release a transaction. The reference count is used to allow a caller to synchronously wait for a committed transaction to complete. In this case, the waiter takes an extra reference to the transaction *before* committing it (so it won't be freed), and releases its reference (calls gsi_trans_free()) when it is done with it. Similarly, gsi_channel_update() takes an extra reference to ensure a transaction isn't released before the function is done operating on it. Until the transaction is moved to the completed list (by this function) it won't be freed, so this reference is taken "safely." But in the quiesce path, we want to wait for the "last" transaction, which we find in the completed or polled list. Transactions on these lists can be freed at any time, so we (try to) prevent that by taking the reference while holding the spinlock. Currently gsi_trans_free() decrements a transaction's reference count unconditionally, acquiring the lock to remove the transaction from its list *only* when the count reaches 0. This does not protect the quiesce path, which depends on the lock to ensure its extra reference prevents release of the transaction. Fix this by only dropping the last reference to a transaction in gsi_trans_free() while holding the spinlock. Fixes: 9dd441e4ed575 ("soc: qcom: ipa: GSI transactions") Reported-by: Stephen Boyd Signed-off-by: Alex Elder Link: https://lore.kernel.org/r/20201114182017.28270-1-elder@linaro.org Signed-off-by: Jakub Kicinski --- drivers/net/ipa/gsi_trans.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index 92642030e735..e8599bb948c0 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -362,22 +362,31 @@ struct gsi_trans *gsi_channel_trans_alloc(struct gsi *gsi, u32 channel_id, return trans; } -/* Free a previously-allocated transaction (used only in case of error) */ +/* Free a previously-allocated transaction */ void gsi_trans_free(struct gsi_trans *trans) { + refcount_t *refcount = &trans->refcount; struct gsi_trans_info *trans_info; + bool last; - if (!refcount_dec_and_test(&trans->refcount)) + /* We must hold the lock to release the last reference */ + if (refcount_dec_not_one(refcount)) return; trans_info = &trans->gsi->channel[trans->channel_id].trans_info; spin_lock_bh(&trans_info->spinlock); - list_del(&trans->links); + /* Reference might have been added before we got the lock */ + last = refcount_dec_and_test(refcount); + if (last) + list_del(&trans->links); spin_unlock_bh(&trans_info->spinlock); + if (!last) + return; + ipa_gsi_trans_release(trans); /* Releasing the reserved TREs implicitly frees the sgl[] and -- cgit v1.2.3 From 4260330b32b14330cfe427d568ac5f5b29b5be3d Mon Sep 17 00:00:00 2001 From: Edwin Peer Date: Sun, 15 Nov 2020 19:27:49 -0500 Subject: bnxt_en: read EEPROM A2h address using page 0 The module eeprom address range returned by bnxt_get_module_eeprom() should be 256 bytes of A0h address space, the lower half of the A2h address space, and page 0 for the upper half of the A2h address space. Fix the firmware call by passing page_number 0 for the A2h slave address space. Fixes: 42ee18fe4ca2 ("bnxt_en: Add Support for ETHTOOL_GMODULEINFO and ETHTOOL_GMODULEEEPRO") Signed-off-by: Edwin Peer Signed-off-by: Michael Chan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 53687bc7fcf5..f133ea5674cb 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -2997,7 +2997,7 @@ static int bnxt_get_module_eeprom(struct net_device *dev, /* Read A2 portion of the EEPROM */ if (length) { start -= ETH_MODULE_SFF_8436_LEN; - rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 1, + rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 0, start, length, data); } return rc; -- cgit v1.2.3 From eba93de6d31c1734dee59909020a162de612e41e Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 15 Nov 2020 19:27:50 -0500 Subject: bnxt_en: Free port stats during firmware reset. Firmware is unable to retain the port counters during any kind of fatal or non-fatal resets, so we must clear the port counters to avoid false detection of port counter overflow. Fixes: fea6b3335527 ("bnxt_en: Accumulate all counters.") Reviewed-by: Edwin Peer Reviewed-by: Vasundhara Volam Signed-off-by: Michael Chan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 7975f59735d6..448e1ba762ee 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4099,7 +4099,8 @@ static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init) bnxt_free_ntp_fltrs(bp, irq_re_init); if (irq_re_init) { bnxt_free_ring_stats(bp); - if (!(bp->fw_cap & BNXT_FW_CAP_PORT_STATS_NO_RESET)) + if (!(bp->fw_cap & BNXT_FW_CAP_PORT_STATS_NO_RESET) || + test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) bnxt_free_port_stats(bp); bnxt_free_ring_grps(bp); bnxt_free_vnics(bp); -- cgit v1.2.3 From fa97f303fa4cf8469fd3d1ef29da69c0a3f6ddc8 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 15 Nov 2020 19:27:51 -0500 Subject: bnxt_en: Fix counter overflow logic. bnxt_add_one_ctr() adds a hardware counter to a software counter and adjusts for the hardware counter wraparound against the mask. The logic assumes that the hardware counter is always smaller than or equal to the mask. This assumption is mostly correct. But in some cases if the firmware is older and does not provide the accurate mask, the driver can use a mask that is smaller than the actual hardware mask. This can cause some extra carry bits to be added to the software counter, resulting in counters that far exceed the actual value. Fix it by masking the hardware counter with the mask passed into bnxt_add_one_ctr(). Fixes: fea6b3335527 ("bnxt_en: Accumulate all counters.") Reviewed-by: Vasundhara Volam Reviewed-by: Pavan Chebbi Reviewed-by: Edwin Peer Signed-off-by: Michael Chan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 448e1ba762ee..7c21aaa8b9af 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7758,6 +7758,7 @@ static void bnxt_add_one_ctr(u64 hw, u64 *sw, u64 mask) { u64 sw_tmp; + hw &= mask; sw_tmp = (*sw & ~mask) | hw; if (hw < (*sw & mask)) sw_tmp += mask + 1; -- cgit v1.2.3 From 0ae0a779efb8840a0cdb2d6bd9a5d07663ac3ee2 Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Sun, 15 Nov 2020 19:27:52 -0500 Subject: bnxt_en: Avoid unnecessary NVM_GET_DEV_INFO cmd error log on VFs. VFs do not have access permissions to issue NVM_GET_DEV_INFO firmware command. Fixes: 4933f6753b50 ("bnxt_en: Add bnxt_hwrm_nvm_get_dev_info() to query NVM info.") Signed-off-by: Vasundhara Volam Signed-off-by: Michael Chan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index f133ea5674cb..1471c9a36238 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -2079,6 +2079,9 @@ int bnxt_hwrm_nvm_get_dev_info(struct bnxt *bp, struct hwrm_nvm_get_dev_info_input req = {0}; int rc; + if (BNXT_VF(bp)) + return -EOPNOTSUPP; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_DEV_INFO, -1, -1); mutex_lock(&bp->hwrm_cmd_lock); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); -- cgit v1.2.3 From fe0a8a95e7134d0b44cd407bc0085b9ba8d8fe31 Mon Sep 17 00:00:00 2001 From: Lee Duncan Date: Fri, 6 Nov 2020 11:33:17 -0800 Subject: scsi: libiscsi: Fix NOP race condition iSCSI NOPs are sometimes "lost", mistakenly sent to the user-land iscsid daemon instead of handled in the kernel, as they should be, resulting in a message from the daemon like: iscsid: Got nop in, but kernel supports nop handling. This can occur because of the new forward- and back-locks, and the fact that an iSCSI NOP response can occur before processing of the NOP send is complete. This can result in "conn->ping_task" being NULL in iscsi_nop_out_rsp(), when the pointer is actually in the process of being set. To work around this, we add a new state to the "ping_task" pointer. In addition to NULL (not assigned) and a pointer (assigned), we add the state "being set", which is signaled with an INVALID pointer (using "-1"). Link: https://lore.kernel.org/r/20201106193317.16993-1-leeman.duncan@gmail.com Reviewed-by: Mike Christie Signed-off-by: Lee Duncan Signed-off-by: Martin K. Petersen --- drivers/scsi/libiscsi.c | 23 +++++++++++++++-------- include/scsi/libiscsi.h | 3 +++ 2 files changed, 18 insertions(+), 8 deletions(-) diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 1e9c3171fa9f..f9314f1393fb 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -533,8 +533,8 @@ static void iscsi_complete_task(struct iscsi_task *task, int state) if (conn->task == task) conn->task = NULL; - if (conn->ping_task == task) - conn->ping_task = NULL; + if (READ_ONCE(conn->ping_task) == task) + WRITE_ONCE(conn->ping_task, NULL); /* release get from queueing */ __iscsi_put_task(task); @@ -738,6 +738,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, task->conn->session->age); } + if (unlikely(READ_ONCE(conn->ping_task) == INVALID_SCSI_TASK)) + WRITE_ONCE(conn->ping_task, task); + if (!ihost->workq) { if (iscsi_prep_mgmt_task(conn, task)) goto free_task; @@ -941,8 +944,11 @@ static int iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr) struct iscsi_nopout hdr; struct iscsi_task *task; - if (!rhdr && conn->ping_task) - return -EINVAL; + if (!rhdr) { + if (READ_ONCE(conn->ping_task)) + return -EINVAL; + WRITE_ONCE(conn->ping_task, INVALID_SCSI_TASK); + } memset(&hdr, 0, sizeof(struct iscsi_nopout)); hdr.opcode = ISCSI_OP_NOOP_OUT | ISCSI_OP_IMMEDIATE; @@ -957,11 +963,12 @@ static int iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr) task = __iscsi_conn_send_pdu(conn, (struct iscsi_hdr *)&hdr, NULL, 0); if (!task) { + if (!rhdr) + WRITE_ONCE(conn->ping_task, NULL); iscsi_conn_printk(KERN_ERR, conn, "Could not send nopout\n"); return -EIO; } else if (!rhdr) { /* only track our nops */ - conn->ping_task = task; conn->last_ping = jiffies; } @@ -984,7 +991,7 @@ static int iscsi_nop_out_rsp(struct iscsi_task *task, struct iscsi_conn *conn = task->conn; int rc = 0; - if (conn->ping_task != task) { + if (READ_ONCE(conn->ping_task) != task) { /* * If this is not in response to one of our * nops then it must be from userspace. @@ -1923,7 +1930,7 @@ static void iscsi_start_tx(struct iscsi_conn *conn) */ static int iscsi_has_ping_timed_out(struct iscsi_conn *conn) { - if (conn->ping_task && + if (READ_ONCE(conn->ping_task) && time_before_eq(conn->last_recv + (conn->recv_timeout * HZ) + (conn->ping_timeout * HZ), jiffies)) return 1; @@ -2058,7 +2065,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc) * Checking the transport already or nop from a cmd timeout still * running */ - if (conn->ping_task) { + if (READ_ONCE(conn->ping_task)) { task->have_checked_conn = true; rc = BLK_EH_RESET_TIMER; goto done; diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index c25fb86ffae9..b3bbd10eb3f0 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -132,6 +132,9 @@ struct iscsi_task { void *dd_data; /* driver/transport data */ }; +/* invalid scsi_task pointer */ +#define INVALID_SCSI_TASK (struct iscsi_task *)-1l + static inline int iscsi_task_has_unsol_data(struct iscsi_task *task) { return task->unsol_r2t.data_length > task->unsol_r2t.sent; -- cgit v1.2.3 From f36199355c64a39fe82cfddc7623d827c7e050da Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 13 Nov 2020 19:46:18 -0600 Subject: scsi: target: iscsi: Fix cmd abort fabric stop race Maurizio found a race where the abort and cmd stop paths can race as follows: 1. thread1 runs iscsit_release_commands_from_conn and sets CMD_T_FABRIC_STOP. 2. thread2 runs iscsit_aborted_task and then does __iscsit_free_cmd. It then returns from the aborted_task callout and we finish target_handle_abort and do: target_handle_abort -> transport_cmd_check_stop_to_fabric -> lio_check_stop_free -> target_put_sess_cmd The cmd is now freed. 3. thread1 now finishes iscsit_release_commands_from_conn and runs iscsit_free_cmd while accessing a command we just released. In __target_check_io_state we check for CMD_T_FABRIC_STOP and set the CMD_T_ABORTED if the driver is not cleaning up the cmd because of a session shutdown. However, iscsit_release_commands_from_conn only sets the CMD_T_FABRIC_STOP and does not check to see if the abort path has claimed completion ownership of the command. This adds a check in iscsit_release_commands_from_conn so only the abort or fabric stop path cleanup the command. Link: https://lore.kernel.org/r/1605318378-9269-1-git-send-email-michael.christie@oracle.com Reported-by: Maurizio Lombardi Reviewed-by: Maurizio Lombardi Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- drivers/target/iscsi/iscsi_target.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index f77e5eee6b80..518fac4864cf 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -483,8 +483,7 @@ EXPORT_SYMBOL(iscsit_queue_rsp); void iscsit_aborted_task(struct iscsi_conn *conn, struct iscsi_cmd *cmd) { spin_lock_bh(&conn->cmd_lock); - if (!list_empty(&cmd->i_conn_node) && - !(cmd->se_cmd.transport_state & CMD_T_FABRIC_STOP)) + if (!list_empty(&cmd->i_conn_node)) list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); @@ -4083,12 +4082,22 @@ static void iscsit_release_commands_from_conn(struct iscsi_conn *conn) spin_lock_bh(&conn->cmd_lock); list_splice_init(&conn->conn_cmd_list, &tmp_list); - list_for_each_entry(cmd, &tmp_list, i_conn_node) { + list_for_each_entry_safe(cmd, cmd_tmp, &tmp_list, i_conn_node) { struct se_cmd *se_cmd = &cmd->se_cmd; if (se_cmd->se_tfo != NULL) { spin_lock_irq(&se_cmd->t_state_lock); - se_cmd->transport_state |= CMD_T_FABRIC_STOP; + if (se_cmd->transport_state & CMD_T_ABORTED) { + /* + * LIO's abort path owns the cleanup for this, + * so put it back on the list and let + * aborted_task handle it. + */ + list_move_tail(&cmd->i_conn_node, + &conn->conn_cmd_list); + } else { + se_cmd->transport_state |= CMD_T_FABRIC_STOP; + } spin_unlock_irq(&se_cmd->t_state_lock); } } -- cgit v1.2.3 From e010d1d25e47642fb91023479a4965000cf934a8 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Tue, 3 Nov 2020 11:55:14 +0000 Subject: cpufreq: tegra186: Fix get frequency callback Commit b89c01c96051 ("cpufreq: tegra186: Fix initial frequency") implemented the CPUFREQ 'get' callback to determine the current operating frequency for each CPU. This implementation used a simple looked up to determine the current operating frequency. The problem with this is that frequency table for different Tegra186 devices may vary and so the default boot frequency for Tegra186 device may or may not be present in the frequency table. If the default boot frequency is not present in the frequency table, this causes the function tegra186_cpufreq_get() to return 0 and in turn causes cpufreq_online() to fail which prevents CPUFREQ from working. Fix this by always calculating the CPU frequency based upon the current 'ndiv' setting for the CPU. Note that the CPU frequency for Tegra186 is calculated by reading the current 'ndiv' setting, multiplying by the CPU reference clock and dividing by a constant divisor. Fixes: b89c01c96051 ("cpufreq: tegra186: Fix initial frequency") Signed-off-by: Jon Hunter Signed-off-by: Viresh Kumar --- drivers/cpufreq/tegra186-cpufreq.c | 33 +++++++++++++++++++++------------ 1 file changed, 21 insertions(+), 12 deletions(-) diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index 4b4079f51559..7eb2c56c65de 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -42,6 +42,8 @@ static const struct tegra186_cpufreq_cluster_info tegra186_clusters[] = { struct tegra186_cpufreq_cluster { const struct tegra186_cpufreq_cluster_info *info; struct cpufreq_frequency_table *table; + u32 ref_clk_khz; + u32 div; }; struct tegra186_cpufreq_data { @@ -94,7 +96,7 @@ static int tegra186_cpufreq_set_target(struct cpufreq_policy *policy, static unsigned int tegra186_cpufreq_get(unsigned int cpu) { - struct cpufreq_frequency_table *tbl; + struct tegra186_cpufreq_data *data = cpufreq_get_driver_data(); struct cpufreq_policy *policy; void __iomem *edvd_reg; unsigned int i, freq = 0; @@ -104,17 +106,23 @@ static unsigned int tegra186_cpufreq_get(unsigned int cpu) if (!policy) return 0; - tbl = policy->freq_table; edvd_reg = policy->driver_data; ndiv = readl(edvd_reg) & EDVD_CORE_VOLT_FREQ_F_MASK; - for (i = 0; tbl[i].frequency != CPUFREQ_TABLE_END; i++) { - if ((tbl[i].driver_data & EDVD_CORE_VOLT_FREQ_F_MASK) == ndiv) { - freq = tbl[i].frequency; - break; + for (i = 0; i < data->num_clusters; i++) { + struct tegra186_cpufreq_cluster *cluster = &data->clusters[i]; + int core; + + for (core = 0; core < ARRAY_SIZE(cluster->info->cpus); core++) { + if (cluster->info->cpus[core] != policy->cpu) + continue; + + freq = (cluster->ref_clk_khz * ndiv) / cluster->div; + goto out; } } +out: cpufreq_cpu_put(policy); return freq; @@ -133,7 +141,7 @@ static struct cpufreq_driver tegra186_cpufreq_driver = { static struct cpufreq_frequency_table *init_vhint_table( struct platform_device *pdev, struct tegra_bpmp *bpmp, - unsigned int cluster_id) + struct tegra186_cpufreq_cluster *cluster) { struct cpufreq_frequency_table *table; struct mrq_cpu_vhint_request req; @@ -152,7 +160,7 @@ static struct cpufreq_frequency_table *init_vhint_table( memset(&req, 0, sizeof(req)); req.addr = phys; - req.cluster_id = cluster_id; + req.cluster_id = cluster->info->bpmp_cluster_id; memset(&msg, 0, sizeof(msg)); msg.mrq = MRQ_CPU_VHINT; @@ -185,6 +193,9 @@ static struct cpufreq_frequency_table *init_vhint_table( goto free; } + cluster->ref_clk_khz = data->ref_clk_hz / 1000; + cluster->div = data->pdiv * data->mdiv; + for (i = data->vfloor, j = 0; i <= data->vceil; i++) { struct cpufreq_frequency_table *point; u16 ndiv = data->ndiv[i]; @@ -202,8 +213,7 @@ static struct cpufreq_frequency_table *init_vhint_table( point = &table[j++]; point->driver_data = edvd_val; - point->frequency = data->ref_clk_hz * ndiv / data->pdiv / - data->mdiv / 1000; + point->frequency = (cluster->ref_clk_khz * ndiv) / cluster->div; } table[j].frequency = CPUFREQ_TABLE_END; @@ -245,8 +255,7 @@ static int tegra186_cpufreq_probe(struct platform_device *pdev) struct tegra186_cpufreq_cluster *cluster = &data->clusters[i]; cluster->info = &tegra186_clusters[i]; - cluster->table = init_vhint_table( - pdev, bpmp, cluster->info->bpmp_cluster_id); + cluster->table = init_vhint_table(pdev, bpmp, cluster); if (IS_ERR(cluster->table)) { err = PTR_ERR(cluster->table); goto put_bpmp; -- cgit v1.2.3 From 8410e7f3b31e53bfa7a34c282b4313e79ed7ff8d Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 10 Nov 2020 11:10:40 +0000 Subject: cpufreq: scmi: Fix OPP addition failure with a dummy clock provider Commit dd461cd9183f ("opp: Allow dev_pm_opp_get_opp_table() to return -EPROBE_DEFER") handles -EPROBE_DEFER for the clock/interconnects within _allocate_opp_table() which is called from dev_pm_opp_add and it now propagates the error back to the caller. SCMI performance domain re-used clock bindings to keep it simple. However with the above mentioned change, if clock property is present in a device node, opps fails to get added with below errors until clk_get succeeds. cpu0: failed to add opp 450000000Hz cpu0: failed to add opps to the device ....(errors on cpu1-cpu4) cpu5: failed to add opp 450000000Hz cpu5: failed to add opps to the device So, in order to fix the issue, we need to register dummy clock provider. With the dummy clock provider, clk_get returns NULL(no errors!), then opp core proceeds to add OPPs for the CPUs. Cc: Rafael J. Wysocki Fixes: dd461cd9183f ("opp: Allow dev_pm_opp_get_opp_table() to return -EPROBE_DEFER") Signed-off-by: Sudeep Holla Signed-off-by: Viresh Kumar --- drivers/cpufreq/scmi-cpufreq.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index e855e8612a67..78318508a6d6 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -8,6 +8,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -228,12 +229,17 @@ static struct cpufreq_driver scmi_cpufreq_driver = { static int scmi_cpufreq_probe(struct scmi_device *sdev) { int ret; + struct device *dev = &sdev->dev; handle = sdev->handle; if (!handle || !handle->perf_ops) return -ENODEV; + /* dummy clock provider as needed by OPP if clocks property is used */ + if (of_find_property(dev->of_node, "#clock-cells", NULL)) + devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL); + ret = cpufreq_register_driver(&scmi_cpufreq_driver); if (ret) { dev_err(&sdev->dev, "%s: registering cpufreq failed, err: %d\n", -- cgit v1.2.3 From 054409ab253d9f31bec5760105144166b4b71e22 Mon Sep 17 00:00:00 2001 From: Chen Zhou Date: Tue, 17 Nov 2020 10:54:26 +0800 Subject: KVM: SVM: fix error return code in svm_create_vcpu() Fix to return a negative error code from the error handling case instead of 0 in function svm_create_vcpu(), as done elsewhere in this function. Fixes: f4c847a95654 ("KVM: SVM: refactor msr permission bitmap allocation") Reported-by: Hulk Robot Signed-off-by: Chen Zhou Message-Id: <20201117025426.167824-1-chenzhou10@huawei.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 1e81cfebd491..79b3a564f1c9 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1309,8 +1309,10 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm->avic_is_running = true; svm->msrpm = svm_vcpu_alloc_msrpm(); - if (!svm->msrpm) + if (!svm->msrpm) { + err = -ENOMEM; goto error_free_vmcb_page; + } svm_vcpu_init_msrpm(vcpu, svm->msrpm); -- cgit v1.2.3 From 61a2f1aecf6052f7bcf900829ca2b9d74437ec07 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 16 Nov 2020 18:45:15 +0100 Subject: MIPS: kernel: Fix for_each_memblock conversion The loop over all memblocks works with PFNs and not physical addresses, so we need for_each_mem_pfn_range(). Fixes: b10d6bca8720 ("arch, drivers: replace for_each_membock() with for_each_mem_range()") Signed-off-by: Thomas Bogendoerfer Reviewed-by: Mike Rapoport Reviewed-by: Serge Semin --- arch/mips/kernel/setup.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 0d4253208bde..ca579deef939 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -262,8 +262,8 @@ static void __init bootmem_init(void) static void __init bootmem_init(void) { phys_addr_t ramstart, ramend; - phys_addr_t start, end; - u64 i; + unsigned long start, end; + int i; ramstart = memblock_start_of_DRAM(); ramend = memblock_end_of_DRAM(); @@ -300,7 +300,7 @@ static void __init bootmem_init(void) min_low_pfn = ARCH_PFN_OFFSET; max_pfn = PFN_DOWN(ramend); - for_each_mem_range(i, &start, &end) { + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) { /* * Skip highmem here so we get an accurate max_low_pfn if low * memory stops short of high memory. -- cgit v1.2.3 From 1a371e67dc77125736cc56d3a0893f06b75855b6 Mon Sep 17 00:00:00 2001 From: Chen Yu Date: Fri, 13 Nov 2020 09:59:23 +0800 Subject: x86/microcode/intel: Check patch signature before saving microcode for early loading Currently, scan_microcode() leverages microcode_matches() to check if the microcode matches the CPU by comparing the family and model. However, the processor stepping and flags of the microcode signature should also be considered when saving a microcode patch for early update. Use find_matching_signature() in scan_microcode() and get rid of the now-unused microcode_matches() which is a good cleanup in itself. Complete the verification of the patch being saved for early loading in save_microcode_patch() directly. This needs to be done there too because save_mc_for_early() will call save_microcode_patch() too. The second reason why this needs to be done is because the loader still tries to support, at least hypothetically, mixed-steppings systems and thus adds all patches to the cache that belong to the same CPU model albeit with different steppings. For example: microcode: CPU: sig=0x906ec, pf=0x2, rev=0xd6 microcode: mc_saved[0]: sig=0x906e9, pf=0x2a, rev=0xd6, total size=0x19400, date = 2020-04-23 microcode: mc_saved[1]: sig=0x906ea, pf=0x22, rev=0xd6, total size=0x19000, date = 2020-04-27 microcode: mc_saved[2]: sig=0x906eb, pf=0x2, rev=0xd6, total size=0x19400, date = 2020-04-23 microcode: mc_saved[3]: sig=0x906ec, pf=0x22, rev=0xd6, total size=0x19000, date = 2020-04-27 microcode: mc_saved[4]: sig=0x906ed, pf=0x22, rev=0xd6, total size=0x19400, date = 2020-04-23 The patch which is being saved for early loading, however, can only be the one which fits the CPU this runs on so do the signature verification before saving. [ bp: Do signature verification in save_microcode_patch() and rewrite commit message. ] Fixes: ec400ddeff20 ("x86/microcode_intel_early.c: Early update ucode on Intel's CPU") Signed-off-by: Chen Yu Signed-off-by: Borislav Petkov Cc: stable@vger.kernel.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=208535 Link: https://lkml.kernel.org/r/20201113015923.13960-1-yu.c.chen@intel.com --- arch/x86/kernel/cpu/microcode/intel.c | 63 ++++++----------------------------- 1 file changed, 10 insertions(+), 53 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 6a99535d7f37..7e8e07bddd5f 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -100,53 +100,6 @@ static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev return find_matching_signature(mc, csig, cpf); } -/* - * Given CPU signature and a microcode patch, this function finds if the - * microcode patch has matching family and model with the CPU. - * - * %true - if there's a match - * %false - otherwise - */ -static bool microcode_matches(struct microcode_header_intel *mc_header, - unsigned long sig) -{ - unsigned long total_size = get_totalsize(mc_header); - unsigned long data_size = get_datasize(mc_header); - struct extended_sigtable *ext_header; - unsigned int fam_ucode, model_ucode; - struct extended_signature *ext_sig; - unsigned int fam, model; - int ext_sigcount, i; - - fam = x86_family(sig); - model = x86_model(sig); - - fam_ucode = x86_family(mc_header->sig); - model_ucode = x86_model(mc_header->sig); - - if (fam == fam_ucode && model == model_ucode) - return true; - - /* Look for ext. headers: */ - if (total_size <= data_size + MC_HEADER_SIZE) - return false; - - ext_header = (void *) mc_header + data_size + MC_HEADER_SIZE; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; - ext_sigcount = ext_header->count; - - for (i = 0; i < ext_sigcount; i++) { - fam_ucode = x86_family(ext_sig->sig); - model_ucode = x86_model(ext_sig->sig); - - if (fam == fam_ucode && model == model_ucode) - return true; - - ext_sig++; - } - return false; -} - static struct ucode_patch *memdup_patch(void *data, unsigned int size) { struct ucode_patch *p; @@ -164,7 +117,7 @@ static struct ucode_patch *memdup_patch(void *data, unsigned int size) return p; } -static void save_microcode_patch(void *data, unsigned int size) +static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigned int size) { struct microcode_header_intel *mc_hdr, *mc_saved_hdr; struct ucode_patch *iter, *tmp, *p = NULL; @@ -210,6 +163,9 @@ static void save_microcode_patch(void *data, unsigned int size) if (!p) return; + if (!find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf)) + return; + /* * Save for early loading. On 32-bit, that needs to be a physical * address as the APs are running from physical addresses, before @@ -344,13 +300,14 @@ scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save) size -= mc_size; - if (!microcode_matches(mc_header, uci->cpu_sig.sig)) { + if (!find_matching_signature(data, uci->cpu_sig.sig, + uci->cpu_sig.pf)) { data += mc_size; continue; } if (save) { - save_microcode_patch(data, mc_size); + save_microcode_patch(uci, data, mc_size); goto next; } @@ -483,14 +440,14 @@ static void show_saved_mc(void) * Save this microcode patch. It will be loaded early when a CPU is * hot-added or resumes. */ -static void save_mc_for_early(u8 *mc, unsigned int size) +static void save_mc_for_early(struct ucode_cpu_info *uci, u8 *mc, unsigned int size) { /* Synchronization during CPU hotplug. */ static DEFINE_MUTEX(x86_cpu_microcode_mutex); mutex_lock(&x86_cpu_microcode_mutex); - save_microcode_patch(mc, size); + save_microcode_patch(uci, mc, size); show_saved_mc(); mutex_unlock(&x86_cpu_microcode_mutex); @@ -935,7 +892,7 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter) * permanent memory. So it will be loaded early when a CPU is hot added * or resumes. */ - save_mc_for_early(new_mc, new_mc_size); + save_mc_for_early(uci, new_mc, new_mc_size); pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); -- cgit v1.2.3 From e02152ba2810f7c88cb54e71cda096268dfa9241 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 16 Nov 2020 23:09:13 +1100 Subject: powerpc: Drop -me200 addition to build flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently a build with CONFIG_E200=y will fail with: Error: invalid switch -me200 Error: unrecognized option -me200 Upstream binutils has never supported an -me200 option. Presumably it was supported at some point by either a fork or Freescale internal binutils. We can't support code that we can't even build test, so drop the addition of -me200 to the build flags, so we can at least build with CONFIG_E200=y. Reported-by: Németh Márton Reported-by: kernel test robot Signed-off-by: Michael Ellerman Reviewed-by: Nick Desaulniers Acked-by: Scott Wood Link: https://lore.kernel.org/r/20201116120913.165317-1-mpe@ellerman.id.au --- arch/powerpc/Makefile | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index a4d56f0a41d9..16b8336f91dd 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -248,7 +248,6 @@ KBUILD_CFLAGS += $(call cc-option,-mno-string) cpu-as-$(CONFIG_40x) += -Wa,-m405 cpu-as-$(CONFIG_44x) += -Wa,-m440 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) -cpu-as-$(CONFIG_E200) += -Wa,-me200 cpu-as-$(CONFIG_E500) += -Wa,-me500 # When using '-many -mpower4' gas will first try and find a matching power4 -- cgit v1.2.3 From 60d53566100abde4acc5504b524bc97f89015690 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 12 Nov 2020 15:36:56 +0200 Subject: mmc: sdhci-pci: Prefer SDR25 timing for High Speed mode for BYT-based Intel controllers A UHS setting of SDR25 can give better results for High Speed mode. This is because there is no setting corresponding to high speed. Currently SDHCI sets no value, which means zero which is also the setting for SDR12. There was an attempt to change this in sdhci.c but it caused problems for some drivers, so it was reverted and the change was made to sdhci-brcmstb in commit 2fefc7c5f7d16e ("mmc: sdhci-brcmstb: Fix incorrect switch to HS mode"). Several other drivers also do this. Signed-off-by: Adrian Hunter Cc: stable@vger.kernel.org # v5.4+ Link: https://lore.kernel.org/r/20201112133656.20317-1-adrian.hunter@intel.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-pci-core.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index 23da7f7fe093..9552708846ca 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -665,6 +665,15 @@ static void sdhci_intel_set_power(struct sdhci_host *host, unsigned char mode, } } +static void sdhci_intel_set_uhs_signaling(struct sdhci_host *host, + unsigned int timing) +{ + /* Set UHS timing to SDR25 for High Speed mode */ + if (timing == MMC_TIMING_MMC_HS || timing == MMC_TIMING_SD_HS) + timing = MMC_TIMING_UHS_SDR25; + sdhci_set_uhs_signaling(host, timing); +} + #define INTEL_HS400_ES_REG 0x78 #define INTEL_HS400_ES_BIT BIT(0) @@ -721,7 +730,7 @@ static const struct sdhci_ops sdhci_intel_byt_ops = { .enable_dma = sdhci_pci_enable_dma, .set_bus_width = sdhci_set_bus_width, .reset = sdhci_reset, - .set_uhs_signaling = sdhci_set_uhs_signaling, + .set_uhs_signaling = sdhci_intel_set_uhs_signaling, .hw_reset = sdhci_pci_hw_reset, }; @@ -731,7 +740,7 @@ static const struct sdhci_ops sdhci_intel_glk_ops = { .enable_dma = sdhci_pci_enable_dma, .set_bus_width = sdhci_set_bus_width, .reset = sdhci_cqhci_reset, - .set_uhs_signaling = sdhci_set_uhs_signaling, + .set_uhs_signaling = sdhci_intel_set_uhs_signaling, .hw_reset = sdhci_pci_hw_reset, .irq = sdhci_cqhci_irq, }; -- cgit v1.2.3 From 9e9534329306fcd7ea1b84f14860a3c04ebe7f1a Mon Sep 17 00:00:00 2001 From: Manish Narani Date: Mon, 16 Nov 2020 14:02:43 +0530 Subject: mmc: sdhci-of-arasan: Allow configuring zero tap values Allow configuring the Output and Input tap values with zero to avoid failures in some cases (one of them is SD boot mode) where the output and input tap values may be already set to non-zero. Fixes: a5c8b2ae2e51 ("mmc: sdhci-of-arasan: Add support for ZynqMP Platform Tap Delays Setup") Signed-off-by: Sai Krishna Potthuri Signed-off-by: Manish Narani Acked-by: Michal Simek Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/1605515565-117562-2-git-send-email-manish.narani@xilinx.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-of-arasan.c | 40 ++++++++------------------------------ 1 file changed, 8 insertions(+), 32 deletions(-) diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c index 829ccef87426..100621e55427 100644 --- a/drivers/mmc/host/sdhci-of-arasan.c +++ b/drivers/mmc/host/sdhci-of-arasan.c @@ -600,14 +600,8 @@ static int sdhci_zynqmp_sdcardclk_set_phase(struct clk_hw *hw, int degrees) u8 tap_delay, tap_max = 0; int ret; - /* - * This is applicable for SDHCI_SPEC_300 and above - * ZynqMP does not set phase for <=25MHz clock. - * If degrees is zero, no need to do anything. - */ - if (host->version < SDHCI_SPEC_300 || - host->timing == MMC_TIMING_LEGACY || - host->timing == MMC_TIMING_UHS_SDR12 || !degrees) + /* This is applicable for SDHCI_SPEC_300 and above */ + if (host->version < SDHCI_SPEC_300) return 0; switch (host->timing) { @@ -668,14 +662,8 @@ static int sdhci_zynqmp_sampleclk_set_phase(struct clk_hw *hw, int degrees) u8 tap_delay, tap_max = 0; int ret; - /* - * This is applicable for SDHCI_SPEC_300 and above - * ZynqMP does not set phase for <=25MHz clock. - * If degrees is zero, no need to do anything. - */ - if (host->version < SDHCI_SPEC_300 || - host->timing == MMC_TIMING_LEGACY || - host->timing == MMC_TIMING_UHS_SDR12 || !degrees) + /* This is applicable for SDHCI_SPEC_300 and above */ + if (host->version < SDHCI_SPEC_300) return 0; switch (host->timing) { @@ -733,14 +721,8 @@ static int sdhci_versal_sdcardclk_set_phase(struct clk_hw *hw, int degrees) struct sdhci_host *host = sdhci_arasan->host; u8 tap_delay, tap_max = 0; - /* - * This is applicable for SDHCI_SPEC_300 and above - * Versal does not set phase for <=25MHz clock. - * If degrees is zero, no need to do anything. - */ - if (host->version < SDHCI_SPEC_300 || - host->timing == MMC_TIMING_LEGACY || - host->timing == MMC_TIMING_UHS_SDR12 || !degrees) + /* This is applicable for SDHCI_SPEC_300 and above */ + if (host->version < SDHCI_SPEC_300) return 0; switch (host->timing) { @@ -804,14 +786,8 @@ static int sdhci_versal_sampleclk_set_phase(struct clk_hw *hw, int degrees) struct sdhci_host *host = sdhci_arasan->host; u8 tap_delay, tap_max = 0; - /* - * This is applicable for SDHCI_SPEC_300 and above - * Versal does not set phase for <=25MHz clock. - * If degrees is zero, no need to do anything. - */ - if (host->version < SDHCI_SPEC_300 || - host->timing == MMC_TIMING_LEGACY || - host->timing == MMC_TIMING_UHS_SDR12 || !degrees) + /* This is applicable for SDHCI_SPEC_300 and above */ + if (host->version < SDHCI_SPEC_300) return 0; switch (host->timing) { -- cgit v1.2.3 From d338c6d01dc614cad253d6c042501fa0eb242d5c Mon Sep 17 00:00:00 2001 From: Manish Narani Date: Mon, 16 Nov 2020 14:02:44 +0530 Subject: mmc: sdhci-of-arasan: Use Mask writes for Tap delays Mask the ITAP and OTAP delay bits before updating with the new tap value for Versal platform. Fixes: 1a470721c8f5 ("sdhci: arasan: Add support for Versal Tap Delays") Signed-off-by: Sai Krishna Potthuri Signed-off-by: Manish Narani Acked-by: Michal Simek Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/1605515565-117562-3-git-send-email-manish.narani@xilinx.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-of-arasan.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c index 100621e55427..3ec5ecad637c 100644 --- a/drivers/mmc/host/sdhci-of-arasan.c +++ b/drivers/mmc/host/sdhci-of-arasan.c @@ -30,7 +30,10 @@ #define SDHCI_ARASAN_VENDOR_REGISTER 0x78 #define SDHCI_ARASAN_ITAPDLY_REGISTER 0xF0F8 +#define SDHCI_ARASAN_ITAPDLY_SEL_MASK 0xFF + #define SDHCI_ARASAN_OTAPDLY_REGISTER 0xF0FC +#define SDHCI_ARASAN_OTAPDLY_SEL_MASK 0x3F #define SDHCI_ARASAN_CQE_BASE_ADDR 0x200 #define VENDOR_ENHANCED_STROBE BIT(0) @@ -755,6 +758,7 @@ static int sdhci_versal_sdcardclk_set_phase(struct clk_hw *hw, int degrees) regval = sdhci_readl(host, SDHCI_ARASAN_OTAPDLY_REGISTER); regval |= SDHCI_OTAPDLY_ENABLE; sdhci_writel(host, regval, SDHCI_ARASAN_OTAPDLY_REGISTER); + regval &= ~SDHCI_ARASAN_OTAPDLY_SEL_MASK; regval |= tap_delay; sdhci_writel(host, regval, SDHCI_ARASAN_OTAPDLY_REGISTER); } @@ -822,6 +826,7 @@ static int sdhci_versal_sampleclk_set_phase(struct clk_hw *hw, int degrees) sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER); regval |= SDHCI_ITAPDLY_ENABLE; sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER); + regval &= ~SDHCI_ARASAN_ITAPDLY_SEL_MASK; regval |= tap_delay; sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER); regval &= ~SDHCI_ITAPDLY_CHGWIN; -- cgit v1.2.3 From d06d60d52ec0b0eef702dd3e7b4699f0b589ad0f Mon Sep 17 00:00:00 2001 From: Manish Narani Date: Mon, 16 Nov 2020 14:02:45 +0530 Subject: mmc: sdhci-of-arasan: Issue DLL reset explicitly In the current implementation DLL reset will be issued for each ITAP and OTAP setting inside ATF, this is creating issues in some scenarios and this sequence is not inline with the TRM. To fix the issue, DLL reset should be removed from the ATF and host driver will request it explicitly. This patch update host driver to explicitly request for DLL reset before ITAP (assert DLL) and after OTAP (release DLL) settings. Fixes: a5c8b2ae2e51 ("mmc: sdhci-of-arasan: Add support for ZynqMP Platform Tap Delays Setup") Signed-off-by: Sai Krishna Potthuri Signed-off-by: Manish Narani Acked-by: Michal Simek Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/1605515565-117562-4-git-send-email-manish.narani@xilinx.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-of-arasan.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c index 3ec5ecad637c..d25a4b50c2f3 100644 --- a/drivers/mmc/host/sdhci-of-arasan.c +++ b/drivers/mmc/host/sdhci-of-arasan.c @@ -635,6 +635,9 @@ static int sdhci_zynqmp_sdcardclk_set_phase(struct clk_hw *hw, int degrees) if (ret) pr_err("Error setting Output Tap Delay\n"); + /* Release DLL Reset */ + zynqmp_pm_sd_dll_reset(node_id, PM_DLL_RESET_RELEASE); + return ret; } @@ -669,6 +672,9 @@ static int sdhci_zynqmp_sampleclk_set_phase(struct clk_hw *hw, int degrees) if (host->version < SDHCI_SPEC_300) return 0; + /* Assert DLL Reset */ + zynqmp_pm_sd_dll_reset(node_id, PM_DLL_RESET_ASSERT); + switch (host->timing) { case MMC_TIMING_MMC_HS: case MMC_TIMING_SD_HS: -- cgit v1.2.3 From ac3b57adf87ad9bac7e33ca26bbbb13fae1ed62b Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Fri, 13 Nov 2020 21:18:56 +0800 Subject: MIPS: Alchemy: Fix memleak in alchemy_clk_setup_cpu If the clk_register fails, we should free h before function returns to prevent memleak. Fixes: 474402291a0ad ("MIPS: Alchemy: clock framework integration of onchip clocks") Reported-by: Hulk Robot Signed-off-by: Zhang Qilong Signed-off-by: Thomas Bogendoerfer --- arch/mips/alchemy/common/clock.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/mips/alchemy/common/clock.c b/arch/mips/alchemy/common/clock.c index a95a894aceaf..f0c830337104 100644 --- a/arch/mips/alchemy/common/clock.c +++ b/arch/mips/alchemy/common/clock.c @@ -152,6 +152,7 @@ static struct clk __init *alchemy_clk_setup_cpu(const char *parent_name, { struct clk_init_data id; struct clk_hw *h; + struct clk *clk; h = kzalloc(sizeof(*h), GFP_KERNEL); if (!h) @@ -164,7 +165,13 @@ static struct clk __init *alchemy_clk_setup_cpu(const char *parent_name, id.ops = &alchemy_clkops_cpu; h->init = &id; - return clk_register(NULL, h); + clk = clk_register(NULL, h); + if (IS_ERR(clk)) { + pr_err("failed to register clock\n"); + kfree(h); + } + + return clk; } /* AUXPLLs ************************************************************/ -- cgit v1.2.3 From 8e1ac4299a6e8726de42310d9c1379f188140c71 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Thu, 12 Nov 2020 11:12:01 +0000 Subject: sched/fair: Fix overutilized update in enqueue_task_fair() enqueue_task_fair() attempts to skip the overutilized update for new tasks as their util_avg is not accurate yet. However, the flag we check to do so is overwritten earlier on in the function, which makes the condition pretty much a nop. Fix this by saving the flag early on. Fixes: 2802bf3cd936 ("sched/fair: Add over-utilization/tipping point indicator") Reported-by: Rick Yiu Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Vincent Guittot Reviewed-by: Valentin Schneider Link: https://lkml.kernel.org/r/20201112111201.2081902-1-qperret@google.com --- kernel/sched/fair.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8e563cf2b5e7..56a8ca93a971 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5477,6 +5477,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; int idle_h_nr_running = task_has_idle_policy(p); + int task_new = !(flags & ENQUEUE_WAKEUP); /* * The code below (indirectly) updates schedutil which looks at @@ -5549,7 +5550,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) * into account, but that is not straightforward to implement, * and the following generally works well enough in practice. */ - if (flags & ENQUEUE_WAKEUP) + if (!task_new) update_overutilized_status(rq); enqueue_throttle: -- cgit v1.2.3 From f97bb5272d9e95d400d6c8643ebb146b3e3e7842 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 17 Nov 2020 09:08:41 +0100 Subject: sched: Fix data-race in wakeup Mel reported that on some ARM64 platforms loadavg goes bananas and Will tracked it down to the following race: CPU0 CPU1 schedule() prev->sched_contributes_to_load = X; deactivate_task(prev); try_to_wake_up() if (p->on_rq &&) // false if (smp_load_acquire(&p->on_cpu) && // true ttwu_queue_wakelist()) p->sched_remote_wakeup = Y; smp_store_release(prev->on_cpu, 0); where both p->sched_contributes_to_load and p->sched_remote_wakeup are in the same word, and thus the stores X and Y race (and can clobber one another's data). Whereas prior to commit c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu") the p->on_cpu handoff serialized access to p->sched_remote_wakeup (just as it still does with p->sched_contributes_to_load) that commit broke that by calling ttwu_queue_wakelist() with p->on_cpu != 0. However, due to p->XXX = X ttwu() schedule() if (p->on_rq && ...) // false smp_mb__after_spinlock() if (smp_load_acquire(&p->on_cpu) && deactivate_task() ttwu_queue_wakelist()) p->on_rq = 0; p->sched_remote_wakeup = Y; We can be sure any 'current' store is complete and 'current' is guaranteed asleep. Therefore we can move p->sched_remote_wakeup into the current flags word. Note: while the observed failure was loadavg accounting gone wrong due to ttwu() cobbering p->sched_contributes_to_load, the reverse problem is also possible where schedule() clobbers p->sched_remote_wakeup, this could result in enqueue_entity() wrecking ->vruntime and causing scheduling artifacts. Fixes: c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu") Reported-by: Mel Gorman Debugged-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20201117083016.GK3121392@hirez.programming.kicks-ass.net --- include/linux/sched.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index d383cf09e78f..0e91b451d2a2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -769,7 +769,6 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; - unsigned sched_remote_wakeup:1; #ifdef CONFIG_PSI unsigned sched_psi_wake_requeue:1; #endif @@ -779,6 +778,21 @@ struct task_struct { /* Unserialized, strictly 'current' */ + /* + * This field must not be in the scheduler word above due to wakelist + * queueing no longer being serialized by p->on_cpu. However: + * + * p->XXX = X; ttwu() + * schedule() if (p->on_rq && ..) // false + * smp_mb__after_spinlock(); if (smp_load_acquire(&p->on_cpu) && //true + * deactivate_task() ttwu_queue_wakelist()) + * p->on_rq = 0; p->sched_remote_wakeup = Y; + * + * guarantees all stores of 'current' are visible before + * ->sched_remote_wakeup gets used, so it can be in this word. + */ + unsigned sched_remote_wakeup:1; + /* Bit to tell LSMs we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; -- cgit v1.2.3 From ec618b84f6e15281cc3660664d34cd0dd2f2579e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 24 Sep 2020 13:50:42 +0200 Subject: sched: Fix rq->nr_iowait ordering schedule() ttwu() deactivate_task(); if (p->on_rq && ...) // false atomic_dec(&task_rq(p)->nr_iowait); if (prev->in_iowait) atomic_inc(&rq->nr_iowait); Allows nr_iowait to be decremented before it gets incremented, resulting in more dodgy IO-wait numbers than usual. Note that because we can now do ttwu_queue_wakelist() before p->on_cpu==0, we lose the natural ordering and have to further delay the decrement. Fixes: c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu") Reported-by: Tejun Heo Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mel Gorman Link: https://lkml.kernel.org/r/20201117093829.GD3121429@hirez.programming.kicks-ass.net --- kernel/sched/core.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d2003a7d5ab5..9f0ebfb0d17b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2501,7 +2501,12 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, #ifdef CONFIG_SMP if (wake_flags & WF_MIGRATED) en_flags |= ENQUEUE_MIGRATED; + else #endif + if (p->in_iowait) { + delayacct_blkio_end(p); + atomic_dec(&task_rq(p)->nr_iowait); + } activate_task(rq, p, en_flags); ttwu_do_wakeup(rq, p, wake_flags, rf); @@ -2888,11 +2893,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags)) goto unlock; - if (p->in_iowait) { - delayacct_blkio_end(p); - atomic_dec(&task_rq(p)->nr_iowait); - } - #ifdef CONFIG_SMP /* * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be @@ -2963,6 +2963,11 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); if (task_cpu(p) != cpu) { + if (p->in_iowait) { + delayacct_blkio_end(p); + atomic_dec(&task_rq(p)->nr_iowait); + } + wake_flags |= WF_MIGRATED; psi_ttwu_dequeue(p); set_task_cpu(p, cpu); -- cgit v1.2.3 From 2279f540ea7d05f22d2f0c4224319330228586bc Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Tue, 17 Nov 2020 07:14:32 +0100 Subject: sched/deadline: Fix priority inheritance with multiple scheduling classes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Glenn reported that "an application [he developed produces] a BUG in deadline.c when a SCHED_DEADLINE task contends with CFS tasks on nested PTHREAD_PRIO_INHERIT mutexes. I believe the bug is triggered when a CFS task that was boosted by a SCHED_DEADLINE task boosts another CFS task (nested priority inheritance). ------------[ cut here ]------------ kernel BUG at kernel/sched/deadline.c:1462! invalid opcode: 0000 [#1] PREEMPT SMP CPU: 12 PID: 19171 Comm: dl_boost_bug Tainted: ... Hardware name: ... RIP: 0010:enqueue_task_dl+0x335/0x910 Code: ... RSP: 0018:ffffc9000c2bbc68 EFLAGS: 00010002 RAX: 0000000000000009 RBX: ffff888c0af94c00 RCX: ffffffff81e12500 RDX: 000000000000002e RSI: ffff888c0af94c00 RDI: ffff888c10b22600 RBP: ffffc9000c2bbd08 R08: 0000000000000009 R09: 0000000000000078 R10: ffffffff81e12440 R11: ffffffff81e1236c R12: ffff888bc8932600 R13: ffff888c0af94eb8 R14: ffff888c10b22600 R15: ffff888bc8932600 FS: 00007fa58ac55700(0000) GS:ffff888c10b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fa58b523230 CR3: 0000000bf44ab003 CR4: 00000000007606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: ? intel_pstate_update_util_hwp+0x13/0x170 rt_mutex_setprio+0x1cc/0x4b0 task_blocks_on_rt_mutex+0x225/0x260 rt_spin_lock_slowlock_locked+0xab/0x2d0 rt_spin_lock_slowlock+0x50/0x80 hrtimer_grab_expiry_lock+0x20/0x30 hrtimer_cancel+0x13/0x30 do_nanosleep+0xa0/0x150 hrtimer_nanosleep+0xe1/0x230 ? __hrtimer_init_sleeper+0x60/0x60 __x64_sys_nanosleep+0x8d/0xa0 do_syscall_64+0x4a/0x100 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fa58b52330d ... ---[ end trace 0000000000000002 ]— He also provided a simple reproducer creating the situation below: So the execution order of locking steps are the following (N1 and N2 are non-deadline tasks. D1 is a deadline task. M1 and M2 are mutexes that are enabled * with priority inheritance.) Time moves forward as this timeline goes down: N1 N2 D1 | | | | | | Lock(M1) | | | | | | Lock(M2) | | | | | | Lock(M2) | | | | Lock(M1) | | (!!bug triggered!) | Daniel reported a similar situation as well, by just letting ksoftirqd run with DEADLINE (and eventually block on a mutex). Problem is that boosted entities (Priority Inheritance) use static DEADLINE parameters of the top priority waiter. However, there might be cases where top waiter could be a non-DEADLINE entity that is currently boosted by a DEADLINE entity from a different lock chain (i.e., nested priority chains involving entities of non-DEADLINE classes). In this case, top waiter static DEADLINE parameters could be null (initialized to 0 at fork()) and replenish_dl_entity() would hit a BUG(). Fix this by keeping track of the original donor and using its parameters when a task is boosted. Reported-by: Glenn Elliott Reported-by: Daniel Bristot de Oliveira Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra (Intel) Tested-by: Daniel Bristot de Oliveira Link: https://lkml.kernel.org/r/20201117061432.517340-1-juri.lelli@redhat.com --- include/linux/sched.h | 10 ++++- kernel/sched/core.c | 11 +++--- kernel/sched/deadline.c | 97 +++++++++++++++++++++++++++---------------------- 3 files changed, 68 insertions(+), 50 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 0e91b451d2a2..095fdec07b38 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -551,7 +551,6 @@ struct sched_dl_entity { * overruns. */ unsigned int dl_throttled : 1; - unsigned int dl_boosted : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; @@ -570,6 +569,15 @@ struct sched_dl_entity { * time. */ struct hrtimer inactive_timer; + +#ifdef CONFIG_RT_MUTEXES + /* + * Priority Inheritance. When a DEADLINE scheduling entity is boosted + * pi_se points to the donor, otherwise points to the dl_se it belongs + * to (the original one/itself). + */ + struct sched_dl_entity *pi_se; +#endif }; #ifdef CONFIG_UCLAMP_TASK diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9f0ebfb0d17b..e7e453492cff 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4912,20 +4912,21 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) if (!dl_prio(p->normal_prio) || (pi_task && dl_prio(pi_task->prio) && dl_entity_preempt(&pi_task->dl, &p->dl))) { - p->dl.dl_boosted = 1; + p->dl.pi_se = pi_task->dl.pi_se; queue_flag |= ENQUEUE_REPLENISH; - } else - p->dl.dl_boosted = 0; + } else { + p->dl.pi_se = &p->dl; + } p->sched_class = &dl_sched_class; } else if (rt_prio(prio)) { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + p->dl.pi_se = &p->dl; if (oldprio < prio) queue_flag |= ENQUEUE_HEAD; p->sched_class = &rt_sched_class; } else { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + p->dl.pi_se = &p->dl; if (rt_prio(oldprio)) p->rt.timeout = 0; p->sched_class = &fair_sched_class; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 6d93f4518734..949bc5c083c1 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -43,6 +43,28 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se) return !RB_EMPTY_NODE(&dl_se->rb_node); } +#ifdef CONFIG_RT_MUTEXES +static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se) +{ + return dl_se->pi_se; +} + +static inline bool is_dl_boosted(struct sched_dl_entity *dl_se) +{ + return pi_of(dl_se) != dl_se; +} +#else +static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se) +{ + return dl_se; +} + +static inline bool is_dl_boosted(struct sched_dl_entity *dl_se) +{ + return false; +} +#endif + #ifdef CONFIG_SMP static inline struct dl_bw *dl_bw_of(int i) { @@ -698,7 +720,7 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - WARN_ON(dl_se->dl_boosted); + WARN_ON(is_dl_boosted(dl_se)); WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline)); /* @@ -736,21 +758,20 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) * could happen are, typically, a entity voluntarily trying to overcome its * runtime, or it just underestimated it during sched_setattr(). */ -static void replenish_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se) +static void replenish_dl_entity(struct sched_dl_entity *dl_se) { struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - BUG_ON(pi_se->dl_runtime <= 0); + BUG_ON(pi_of(dl_se)->dl_runtime <= 0); /* * This could be the case for a !-dl task that is boosted. * Just go with full inherited parameters. */ if (dl_se->dl_deadline == 0) { - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } if (dl_se->dl_yielded && dl_se->runtime > 0) @@ -763,8 +784,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * arbitrary large. */ while (dl_se->runtime <= 0) { - dl_se->deadline += pi_se->dl_period; - dl_se->runtime += pi_se->dl_runtime; + dl_se->deadline += pi_of(dl_se)->dl_period; + dl_se->runtime += pi_of(dl_se)->dl_runtime; } /* @@ -778,8 +799,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, */ if (dl_time_before(dl_se->deadline, rq_clock(rq))) { printk_deferred_once("sched: DL replenish lagged too much\n"); - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } if (dl_se->dl_yielded) @@ -812,8 +833,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * task with deadline equal to period this is the same of using * dl_period instead of dl_deadline in the equation above. */ -static bool dl_entity_overflow(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se, u64 t) +static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t) { u64 left, right; @@ -835,9 +855,9 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, * of anything below microseconds resolution is actually fiction * (but still we want to give the user that illusion >;). */ - left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); + left = (pi_of(dl_se)->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); right = ((dl_se->deadline - t) >> DL_SCALE) * - (pi_se->dl_runtime >> DL_SCALE); + (pi_of(dl_se)->dl_runtime >> DL_SCALE); return dl_time_before(right, left); } @@ -922,24 +942,23 @@ static inline bool dl_is_implicit(struct sched_dl_entity *dl_se) * Please refer to the comments update_dl_revised_wakeup() function to find * more about the Revised CBS rule. */ -static void update_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se) +static void update_dl_entity(struct sched_dl_entity *dl_se) { struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); if (dl_time_before(dl_se->deadline, rq_clock(rq)) || - dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { + dl_entity_overflow(dl_se, rq_clock(rq))) { if (unlikely(!dl_is_implicit(dl_se) && !dl_time_before(dl_se->deadline, rq_clock(rq)) && - !dl_se->dl_boosted)){ + !is_dl_boosted(dl_se))) { update_dl_revised_wakeup(dl_se, rq); return; } - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } } @@ -1038,7 +1057,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * The task might have been boosted by someone else and might be in the * boosting/deboosting path, its not throttled. */ - if (dl_se->dl_boosted) + if (is_dl_boosted(dl_se)) goto unlock; /* @@ -1066,7 +1085,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * but do not enqueue -- wait for our wakeup to do that. */ if (!task_on_rq_queued(p)) { - replenish_dl_entity(dl_se, dl_se); + replenish_dl_entity(dl_se); goto unlock; } @@ -1156,7 +1175,7 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) if (dl_time_before(dl_se->deadline, rq_clock(rq)) && dl_time_before(rq_clock(rq), dl_next_period(dl_se))) { - if (unlikely(dl_se->dl_boosted || !start_dl_timer(p))) + if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p))) return; dl_se->dl_throttled = 1; if (dl_se->runtime > 0) @@ -1287,7 +1306,7 @@ throttle: dl_se->dl_overrun = 1; __dequeue_task_dl(rq, curr, 0); - if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr))) + if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr))) enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH); if (!is_leftmost(curr, &rq->dl)) @@ -1481,8 +1500,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se) } static void -enqueue_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se, int flags) +enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags) { BUG_ON(on_dl_rq(dl_se)); @@ -1493,9 +1511,9 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, */ if (flags & ENQUEUE_WAKEUP) { task_contending(dl_se, flags); - update_dl_entity(dl_se, pi_se); + update_dl_entity(dl_se); } else if (flags & ENQUEUE_REPLENISH) { - replenish_dl_entity(dl_se, pi_se); + replenish_dl_entity(dl_se); } else if ((flags & ENQUEUE_RESTORE) && dl_time_before(dl_se->deadline, rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) { @@ -1512,19 +1530,7 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se) static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) { - struct task_struct *pi_task = rt_mutex_get_top_task(p); - struct sched_dl_entity *pi_se = &p->dl; - - /* - * Use the scheduling parameters of the top pi-waiter task if: - * - we have a top pi-waiter which is a SCHED_DEADLINE task AND - * - our dl_boosted is set (i.e. the pi-waiter's (absolute) deadline is - * smaller than our deadline OR we are a !SCHED_DEADLINE task getting - * boosted due to a SCHED_DEADLINE pi-waiter). - * Otherwise we keep our runtime and deadline. - */ - if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) { - pi_se = &pi_task->dl; + if (is_dl_boosted(&p->dl)) { /* * Because of delays in the detection of the overrun of a * thread's runtime, it might be the case that a thread @@ -1557,7 +1563,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) * the throttle. */ p->dl.dl_throttled = 0; - BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH); + BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH); return; } @@ -1594,7 +1600,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) return; } - enqueue_dl_entity(&p->dl, pi_se, flags); + enqueue_dl_entity(&p->dl, flags); if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); @@ -2787,11 +2793,14 @@ void __dl_clear_params(struct task_struct *p) dl_se->dl_bw = 0; dl_se->dl_density = 0; - dl_se->dl_boosted = 0; dl_se->dl_throttled = 0; dl_se->dl_yielded = 0; dl_se->dl_non_contending = 0; dl_se->dl_overrun = 0; + +#ifdef CONFIG_RT_MUTEXES + dl_se->pi_se = dl_se; +#endif } bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) -- cgit v1.2.3 From 43be4388e94b915799a24f0eaf664bf95b85231f Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Fri, 13 Nov 2020 19:05:03 +0800 Subject: lockdep: Put graph lock/unlock under lock_recursion protection A warning was hit when running xfstests/generic/068 in a Hyper-V guest: [...] ------------[ cut here ]------------ [...] DEBUG_LOCKS_WARN_ON(lockdep_hardirqs_enabled()) [...] WARNING: CPU: 2 PID: 1350 at kernel/locking/lockdep.c:5280 check_flags.part.0+0x165/0x170 [...] ... [...] Workqueue: events pwq_unbound_release_workfn [...] RIP: 0010:check_flags.part.0+0x165/0x170 [...] ... [...] Call Trace: [...] lock_is_held_type+0x72/0x150 [...] ? lock_acquire+0x16e/0x4a0 [...] rcu_read_lock_sched_held+0x3f/0x80 [...] __send_ipi_one+0x14d/0x1b0 [...] hv_send_ipi+0x12/0x30 [...] __pv_queued_spin_unlock_slowpath+0xd1/0x110 [...] __raw_callee_save___pv_queued_spin_unlock_slowpath+0x11/0x20 [...] .slowpath+0x9/0xe [...] lockdep_unregister_key+0x128/0x180 [...] pwq_unbound_release_workfn+0xbb/0xf0 [...] process_one_work+0x227/0x5c0 [...] worker_thread+0x55/0x3c0 [...] ? process_one_work+0x5c0/0x5c0 [...] kthread+0x153/0x170 [...] ? __kthread_bind_mask+0x60/0x60 [...] ret_from_fork+0x1f/0x30 The cause of the problem is we have call chain lockdep_unregister_key() -> lockdep_unlock() -> arch_spin_unlock() -> __pv_queued_spin_unlock_slowpath() -> pv_kick() -> __send_ipi_one() -> trace_hyperv_send_ipi_one(). Although this particular warning is triggered because Hyper-V has a trace point in ipi sending, but in general arch_spin_unlock() may call another function having a trace point in it, so put the arch_spin_lock() and arch_spin_unlock() after lock_recursion protection to fix this problem and avoid similiar problems. Signed-off-by: Boqun Feng Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20201113110512.1056501-1-boqun.feng@gmail.com --- kernel/locking/lockdep.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index d9fb9e19d2ed..c1418b47f625 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -108,19 +108,21 @@ static inline void lockdep_lock(void) { DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + __this_cpu_inc(lockdep_recursion); arch_spin_lock(&__lock); __owner = current; - __this_cpu_inc(lockdep_recursion); } static inline void lockdep_unlock(void) { + DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + if (debug_locks && DEBUG_LOCKS_WARN_ON(__owner != current)) return; - __this_cpu_dec(lockdep_recursion); __owner = NULL; arch_spin_unlock(&__lock); + __this_cpu_dec(lockdep_recursion); } static inline bool lockdep_assert_locked(void) -- cgit v1.2.3 From ebd19fc372e3e78bf165f230e7c084e304441c08 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 13 Nov 2020 10:31:26 -0800 Subject: perf/x86: fix sysfs type mismatches This change switches rapl to use PMU_FORMAT_ATTR, and fixes two other macros to use device_attribute instead of kobj_attribute to avoid callback type mismatches that trip indirect call checking with Clang's Control-Flow Integrity (CFI). Reported-by: Sedat Dilek Signed-off-by: Sami Tolvanen Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20201113183126.1239404-1-samitolvanen@google.com --- arch/x86/events/intel/cstate.c | 6 +++--- arch/x86/events/intel/uncore.c | 4 ++-- arch/x86/events/intel/uncore.h | 12 ++++++------ arch/x86/events/rapl.c | 14 +------------- 4 files changed, 12 insertions(+), 24 deletions(-) diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 442e1ed4acd4..4eb7ee5fed72 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -107,14 +107,14 @@ MODULE_LICENSE("GPL"); #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __cstate_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ +static ssize_t __cstate_##_var##_show(struct device *dev, \ + struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ -static struct kobj_attribute format_attr_##_var = \ +static struct device_attribute format_attr_##_var = \ __ATTR(_name, 0444, __cstate_##_var##_show, NULL) static ssize_t cstate_get_attr_cpumask(struct device *dev, diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 86d012b3e0b4..80d52cbe2fde 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -94,8 +94,8 @@ end: return map; } -ssize_t uncore_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) +ssize_t uncore_event_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct uncore_event_desc *event = container_of(attr, struct uncore_event_desc, attr); diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 83d2a7d490e0..9efea154349d 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -157,7 +157,7 @@ struct intel_uncore_box { #define UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS 2 struct uncore_event_desc { - struct kobj_attribute attr; + struct device_attribute attr; const char *config; }; @@ -179,8 +179,8 @@ struct pci2phy_map { struct pci2phy_map *__find_pci2phy_map(int segment); int uncore_pcibus_to_physid(struct pci_bus *bus); -ssize_t uncore_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf); +ssize_t uncore_event_show(struct device *dev, + struct device_attribute *attr, char *buf); static inline struct intel_uncore_pmu *dev_to_uncore_pmu(struct device *dev) { @@ -201,14 +201,14 @@ extern int __uncore_max_dies; } #define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __uncore_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ +static ssize_t __uncore_##_var##_show(struct device *dev, \ + struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ -static struct kobj_attribute format_attr_##_var = \ +static struct device_attribute format_attr_##_var = \ __ATTR(_name, 0444, __uncore_##_var##_show, NULL) static inline bool uncore_pmc_fixed(int idx) diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 7c0120e2e957..7dbbeaacd995 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -93,18 +93,6 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { * any other bit is reserved */ #define RAPL_EVENT_MASK 0xFFULL - -#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __rapl_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ - char *page) \ -{ \ - BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ - return sprintf(page, _format "\n"); \ -} \ -static struct kobj_attribute format_attr_##_var = \ - __ATTR(_name, 0444, __rapl_##_var##_show, NULL) - #define RAPL_CNTR_WIDTH 32 #define RAPL_EVENT_ATTR_STR(_name, v, str) \ @@ -441,7 +429,7 @@ static struct attribute_group rapl_pmu_events_group = { .attrs = attrs_empty, }; -DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7"); +PMU_FORMAT_ATTR(event, "config:0-7"); static struct attribute *rapl_formats_attr[] = { &format_attr_event.attr, NULL, -- cgit v1.2.3 From 54a2a3898f469a915510038fe84ef4f083131d3e Mon Sep 17 00:00:00 2001 From: Joakim Tjernlund Date: Tue, 17 Nov 2020 13:28:03 +0100 Subject: ALSA: usb-audio: Add delay quirk for all Logitech USB devices Found one more Logitech device, BCC950 ConferenceCam, which needs the same delay here. This makes 3 out of 3 devices I have tried. Therefore, add a delay for all Logitech devices as it does not hurt. Signed-off-by: Joakim Tjernlund Cc: # 4.19.y, 5.4.y Link: https://lore.kernel.org/r/20201117122803.24310-1-joakim.tjernlund@infinera.com Signed-off-by: Takashi Iwai --- sound/usb/quirks.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index c989ad8052ae..c50be2f75f70 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1672,13 +1672,13 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) msleep(20); - /* Zoom R16/24, Logitech H650e/H570e, Jabra 550a, Kingston HyperX - * needs a tiny delay here, otherwise requests like get/set - * frequency return as failed despite actually succeeding. + /* Zoom R16/24, many Logitech(at least H650e/H570e/BCC950), + * Jabra 550a, Kingston HyperX needs a tiny delay here, + * otherwise requests like get/set frequency return + * as failed despite actually succeeding. */ if ((chip->usb_id == USB_ID(0x1686, 0x00dd) || - chip->usb_id == USB_ID(0x046d, 0x0a46) || - chip->usb_id == USB_ID(0x046d, 0x0a56) || + USB_ID_VENDOR(chip->usb_id) == 0x046d || /* Logitech */ chip->usb_id == USB_ID(0x0b0e, 0x0349) || chip->usb_id == USB_ID(0x0951, 0x16ad)) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) -- cgit v1.2.3 From dc293f2106903ab9c24e9cea18c276e32c394c33 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Tue, 1 Sep 2020 00:09:37 +0300 Subject: xtensa: uaccess: Add missing __user to strncpy_from_user() prototype When adding __user annotations in commit 2adf5352a34a, the strncpy_from_user() function declaration for the CONFIG_GENERIC_STRNCPY_FROM_USER case was missed. Fix it. Reported-by: kernel test robot Signed-off-by: Laurent Pinchart Message-Id: <20200831210937.17938-1-laurent.pinchart@ideasonboard.com> Signed-off-by: Max Filippov --- arch/xtensa/include/asm/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h index b9758119feca..5c9fb8005aa8 100644 --- a/arch/xtensa/include/asm/uaccess.h +++ b/arch/xtensa/include/asm/uaccess.h @@ -302,7 +302,7 @@ strncpy_from_user(char *dst, const char __user *src, long count) return -EFAULT; } #else -long strncpy_from_user(char *dst, const char *src, long count); +long strncpy_from_user(char *dst, const char __user *src, long count); #endif /* -- cgit v1.2.3 From 2013a4b684b6eb614ee5c9a3c07b0ae6f5ca96d9 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Fri, 16 Oct 2020 17:08:32 +0800 Subject: arm64: dts: broadcom: clear the warnings caused by empty dma-ranges The scripts/dtc/checks.c requires that the node have empty "dma-ranges" property must have the same "#address-cells" and "#size-cells" values as the parent node. Otherwise, the following warnings is reported: arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi:7.3-14: Warning \ (dma_ranges_format): /usb:dma-ranges: empty "dma-ranges" property but \ its #address-cells (1) differs from / (2) arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi:7.3-14: Warning \ (dma_ranges_format): /usb:dma-ranges: empty "dma-ranges" property but \ its #size-cells (1) differs from / (2) Arnd Bergmann figured out why it's necessary: Also note that the #address-cells=<1> means that any device under this bus is assumed to only support 32-bit addressing, and DMA will have to go through a slow swiotlb in the absence of an IOMMU. Suggested-by: Arnd Bergmann Signed-off-by: Zhen Lei Link: https://lore.kernel.org/r/20201016090833.1892-2-thunder.leizhen@huawei.com' Acked-by: Florian Fainelli Signed-off-by: Arnd Bergmann --- .../boot/dts/broadcom/stingray/stingray-usb.dtsi | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi index 55259f973b5a..aef8f2b00778 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi @@ -5,20 +5,20 @@ usb { compatible = "simple-bus"; dma-ranges; - #address-cells = <1>; - #size-cells = <1>; - ranges = <0x0 0x0 0x68500000 0x00400000>; + #address-cells = <2>; + #size-cells = <2>; + ranges = <0x0 0x0 0x0 0x68500000 0x0 0x00400000>; usbphy0: usb-phy@0 { compatible = "brcm,sr-usb-combo-phy"; - reg = <0x00000000 0x100>; + reg = <0x0 0x00000000 0x0 0x100>; #phy-cells = <1>; status = "disabled"; }; xhci0: usb@1000 { compatible = "generic-xhci"; - reg = <0x00001000 0x1000>; + reg = <0x0 0x00001000 0x0 0x1000>; interrupts = ; phys = <&usbphy0 1>, <&usbphy0 0>; phy-names = "phy0", "phy1"; @@ -28,7 +28,7 @@ bdc0: usb@2000 { compatible = "brcm,bdc-v0.16"; - reg = <0x00002000 0x1000>; + reg = <0x0 0x00002000 0x0 0x1000>; interrupts = ; phys = <&usbphy0 0>, <&usbphy0 1>; phy-names = "phy0", "phy1"; @@ -38,21 +38,21 @@ usbphy1: usb-phy@10000 { compatible = "brcm,sr-usb-combo-phy"; - reg = <0x00010000 0x100>; + reg = <0x0 0x00010000 0x0 0x100>; #phy-cells = <1>; status = "disabled"; }; usbphy2: usb-phy@20000 { compatible = "brcm,sr-usb-hs-phy"; - reg = <0x00020000 0x100>; + reg = <0x0 0x00020000 0x0 0x100>; #phy-cells = <0>; status = "disabled"; }; xhci1: usb@11000 { compatible = "generic-xhci"; - reg = <0x00011000 0x1000>; + reg = <0x0 0x00011000 0x0 0x1000>; interrupts = ; phys = <&usbphy1 1>, <&usbphy2>, <&usbphy1 0>; phy-names = "phy0", "phy1", "phy2"; @@ -62,7 +62,7 @@ bdc1: usb@21000 { compatible = "brcm,bdc-v0.16"; - reg = <0x00021000 0x1000>; + reg = <0x0 0x00021000 0x0 0x1000>; interrupts = ; phys = <&usbphy2>; phy-names = "phy0"; -- cgit v1.2.3 From e3389b0a14952aac7f2998bb98f633afb21eaa92 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Fri, 16 Oct 2020 17:08:33 +0800 Subject: arm64: dts: qcom: clear the warnings caused by empty dma-ranges The scripts/dtc/checks.c requires that the node have empty "dma-ranges" property must have the same "#address-cells" and "#size-cells" values as the parent node. Otherwise, the following warnings is reported: arch/arm64/boot/dts/qcom/ipq6018.dtsi:185.3-14: Warning \ (dma_ranges_format): /soc:dma-ranges: empty "dma-ranges" property but \ its #address-cells (1) differs from / (2) arch/arm64/boot/dts/qcom/ipq6018.dtsi:185.3-14: Warning \ (dma_ranges_format): /soc:dma-ranges: empty "dma-ranges" property but \ its #size-cells (1) differs from / (2) Arnd Bergmann figured out why it's necessary: Also note that the #address-cells=<1> means that any device under this bus is assumed to only support 32-bit addressing, and DMA will have to go through a slow swiotlb in the absence of an IOMMU. Suggested-by: Arnd Bergmann Signed-off-by: Zhen Lei Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20201016090833.1892-3-thunder.leizhen@huawei.com' Signed-off-by: Arnd Bergmann --- arch/arm64/boot/dts/qcom/ipq6018.dtsi | 72 +++++++++++++++++------------------ 1 file changed, 36 insertions(+), 36 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi index a94dac76bf3f..59e0cbfa2214 100644 --- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi @@ -179,22 +179,22 @@ }; soc: soc { - #address-cells = <1>; - #size-cells = <1>; - ranges = <0 0 0 0xffffffff>; + #address-cells = <2>; + #size-cells = <2>; + ranges = <0 0 0 0 0x0 0xffffffff>; dma-ranges; compatible = "simple-bus"; prng: qrng@e1000 { compatible = "qcom,prng-ee"; - reg = <0xe3000 0x1000>; + reg = <0x0 0xe3000 0x0 0x1000>; clocks = <&gcc GCC_PRNG_AHB_CLK>; clock-names = "core"; }; cryptobam: dma@704000 { compatible = "qcom,bam-v1.7.0"; - reg = <0x00704000 0x20000>; + reg = <0x0 0x00704000 0x0 0x20000>; interrupts = ; clocks = <&gcc GCC_CRYPTO_AHB_CLK>; clock-names = "bam_clk"; @@ -206,7 +206,7 @@ crypto: crypto@73a000 { compatible = "qcom,crypto-v5.1"; - reg = <0x0073a000 0x6000>; + reg = <0x0 0x0073a000 0x0 0x6000>; clocks = <&gcc GCC_CRYPTO_AHB_CLK>, <&gcc GCC_CRYPTO_AXI_CLK>, <&gcc GCC_CRYPTO_CLK>; @@ -217,7 +217,7 @@ tlmm: pinctrl@1000000 { compatible = "qcom,ipq6018-pinctrl"; - reg = <0x01000000 0x300000>; + reg = <0x0 0x01000000 0x0 0x300000>; interrupts = ; gpio-controller; #gpio-cells = <2>; @@ -235,7 +235,7 @@ gcc: gcc@1800000 { compatible = "qcom,gcc-ipq6018"; - reg = <0x01800000 0x80000>; + reg = <0x0 0x01800000 0x0 0x80000>; clocks = <&xo>, <&sleep_clk>; clock-names = "xo", "sleep_clk"; #clock-cells = <1>; @@ -244,17 +244,17 @@ tcsr_mutex_regs: syscon@1905000 { compatible = "syscon"; - reg = <0x01905000 0x8000>; + reg = <0x0 0x01905000 0x0 0x8000>; }; tcsr_q6: syscon@1945000 { compatible = "syscon"; - reg = <0x01945000 0xe000>; + reg = <0x0 0x01945000 0x0 0xe000>; }; blsp_dma: dma@7884000 { compatible = "qcom,bam-v1.7.0"; - reg = <0x07884000 0x2b000>; + reg = <0x0 0x07884000 0x0 0x2b000>; interrupts = ; clocks = <&gcc GCC_BLSP1_AHB_CLK>; clock-names = "bam_clk"; @@ -264,7 +264,7 @@ blsp1_uart3: serial@78b1000 { compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm"; - reg = <0x078b1000 0x200>; + reg = <0x0 0x078b1000 0x0 0x200>; interrupts = ; clocks = <&gcc GCC_BLSP1_UART3_APPS_CLK>, <&gcc GCC_BLSP1_AHB_CLK>; @@ -276,7 +276,7 @@ compatible = "qcom,spi-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b5000 0x600>; + reg = <0x0 0x078b5000 0x0 0x600>; interrupts = ; spi-max-frequency = <50000000>; clocks = <&gcc GCC_BLSP1_QUP1_SPI_APPS_CLK>, @@ -291,7 +291,7 @@ compatible = "qcom,spi-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b6000 0x600>; + reg = <0x0 0x078b6000 0x0 0x600>; interrupts = ; spi-max-frequency = <50000000>; clocks = <&gcc GCC_BLSP1_QUP2_SPI_APPS_CLK>, @@ -306,7 +306,7 @@ compatible = "qcom,i2c-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b6000 0x600>; + reg = <0x0 0x078b6000 0x0 0x600>; interrupts = ; clocks = <&gcc GCC_BLSP1_AHB_CLK>, <&gcc GCC_BLSP1_QUP2_I2C_APPS_CLK>; @@ -321,7 +321,7 @@ compatible = "qcom,i2c-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b7000 0x600>; + reg = <0x0 0x078b7000 0x0 0x600>; interrupts = ; clocks = <&gcc GCC_BLSP1_AHB_CLK>, <&gcc GCC_BLSP1_QUP3_I2C_APPS_CLK>; @@ -336,24 +336,24 @@ compatible = "qcom,msm-qgic2"; interrupt-controller; #interrupt-cells = <0x3>; - reg = <0x0b000000 0x1000>, /*GICD*/ - <0x0b002000 0x1000>, /*GICC*/ - <0x0b001000 0x1000>, /*GICH*/ - <0x0b004000 0x1000>; /*GICV*/ + reg = <0x0 0x0b000000 0x0 0x1000>, /*GICD*/ + <0x0 0x0b002000 0x0 0x1000>, /*GICC*/ + <0x0 0x0b001000 0x0 0x1000>, /*GICH*/ + <0x0 0x0b004000 0x0 0x1000>; /*GICV*/ interrupts = ; }; watchdog@b017000 { compatible = "qcom,kpss-wdt"; interrupts = ; - reg = <0x0b017000 0x40>; + reg = <0x0 0x0b017000 0x0 0x40>; clocks = <&sleep_clk>; timeout-sec = <10>; }; apcs_glb: mailbox@b111000 { compatible = "qcom,ipq6018-apcs-apps-global"; - reg = <0x0b111000 0x1000>; + reg = <0x0 0x0b111000 0x0 0x1000>; #clock-cells = <1>; clocks = <&a53pll>, <&xo>; clock-names = "pll", "xo"; @@ -362,7 +362,7 @@ a53pll: clock@b116000 { compatible = "qcom,ipq6018-a53pll"; - reg = <0x0b116000 0x40>; + reg = <0x0 0x0b116000 0x0 0x40>; #clock-cells = <0>; clocks = <&xo>; clock-names = "xo"; @@ -377,68 +377,68 @@ }; timer@b120000 { - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; ranges; compatible = "arm,armv7-timer-mem"; - reg = <0x0b120000 0x1000>; + reg = <0x0 0x0b120000 0x0 0x1000>; clock-frequency = <19200000>; frame@b120000 { frame-number = <0>; interrupts = , ; - reg = <0x0b121000 0x1000>, - <0x0b122000 0x1000>; + reg = <0x0 0x0b121000 0x0 0x1000>, + <0x0 0x0b122000 0x0 0x1000>; }; frame@b123000 { frame-number = <1>; interrupts = ; - reg = <0xb123000 0x1000>; + reg = <0x0 0xb123000 0x0 0x1000>; status = "disabled"; }; frame@b124000 { frame-number = <2>; interrupts = ; - reg = <0x0b124000 0x1000>; + reg = <0x0 0x0b124000 0x0 0x1000>; status = "disabled"; }; frame@b125000 { frame-number = <3>; interrupts = ; - reg = <0x0b125000 0x1000>; + reg = <0x0 0x0b125000 0x0 0x1000>; status = "disabled"; }; frame@b126000 { frame-number = <4>; interrupts = ; - reg = <0x0b126000 0x1000>; + reg = <0x0 0x0b126000 0x0 0x1000>; status = "disabled"; }; frame@b127000 { frame-number = <5>; interrupts = ; - reg = <0x0b127000 0x1000>; + reg = <0x0 0x0b127000 0x0 0x1000>; status = "disabled"; }; frame@b128000 { frame-number = <6>; interrupts = ; - reg = <0x0b128000 0x1000>; + reg = <0x0 0x0b128000 0x0 0x1000>; status = "disabled"; }; }; q6v5_wcss: remoteproc@cd00000 { compatible = "qcom,ipq8074-wcss-pil"; - reg = <0x0cd00000 0x4040>, - <0x004ab000 0x20>; + reg = <0x0 0x0cd00000 0x0 0x4040>, + <0x0 0x004ab000 0x0 0x20>; reg-names = "qdsp6", "rmb"; interrupts-extended = <&intc GIC_SPI 325 IRQ_TYPE_EDGE_RISING>, -- cgit v1.2.3 From a7a10bce8a04f48238a8306ec97d430b77917015 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Thu, 15 Oct 2020 13:21:44 -0400 Subject: dm integrity: don't use drivers that have CRYPTO_ALG_ALLOCATES_MEMORY Don't use crypto drivers that have the flag CRYPTO_ALG_ALLOCATES_MEMORY set. These drivers allocate memory and thus they are not suitable for block I/O processing. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- drivers/md/dm-integrity.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 3fc3757def55..5a7a1b90e671 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -3462,7 +3462,7 @@ static int get_mac(struct crypto_shash **hash, struct alg_spec *a, char **error, int r; if (a->alg_string) { - *hash = crypto_alloc_shash(a->alg_string, 0, 0); + *hash = crypto_alloc_shash(a->alg_string, 0, CRYPTO_ALG_ALLOCATES_MEMORY); if (IS_ERR(*hash)) { *error = error_alg; r = PTR_ERR(*hash); @@ -3519,7 +3519,7 @@ static int create_journal(struct dm_integrity_c *ic, char **error) struct journal_completion comp; comp.ic = ic; - ic->journal_crypt = crypto_alloc_skcipher(ic->journal_crypt_alg.alg_string, 0, 0); + ic->journal_crypt = crypto_alloc_skcipher(ic->journal_crypt_alg.alg_string, 0, CRYPTO_ALG_ALLOCATES_MEMORY); if (IS_ERR(ic->journal_crypt)) { *error = "Invalid journal cipher"; r = PTR_ERR(ic->journal_crypt); -- cgit v1.2.3 From e5d41cbca1b2036362c9e29d705d3a175a01eff8 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 10 Nov 2020 07:44:01 -0500 Subject: dm writecache: advance the number of arguments when reporting max_age When reporting the "max_age" value the number of arguments must advance by two. Signed-off-by: Mikulas Patocka Fixes: 3923d4854e18 ("dm writecache: implement gradual cleanup") Cc: stable@vger.kernel.org # v5.7+ Signed-off-by: Mike Snitzer --- drivers/md/dm-writecache.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 9ae4ce7df95c..1ea923af47c6 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -2479,6 +2479,8 @@ static void writecache_status(struct dm_target *ti, status_type_t type, extra_args += 2; if (wc->autocommit_time_set) extra_args += 2; + if (wc->max_age != MAX_AGE_UNSPECIFIED) + extra_args += 2; if (wc->cleaner) extra_args++; if (wc->writeback_fua_set) -- cgit v1.2.3 From 67aa3ec3dbc43d6e34401d9b2a40040ff7bb57af Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 10 Nov 2020 07:45:13 -0500 Subject: dm writecache: fix the maximum number of arguments Advance the maximum number of arguments to 16. This fixes issue where certain operations, combined with table configured args, exceed 10 arguments. Signed-off-by: Mikulas Patocka Fixes: 48debafe4f2f ("dm: add writecache target") Cc: stable@vger.kernel.org # v4.18+ Signed-off-by: Mike Snitzer --- drivers/md/dm-writecache.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 1ea923af47c6..7d277de26b3a 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -2041,7 +2041,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) struct wc_memory_superblock s; static struct dm_arg _args[] = { - {0, 10, "Invalid number of feature args"}, + {0, 16, "Invalid number of feature args"}, }; as.argc = argc; -- cgit v1.2.3 From a41b0ad07bfa081584218431cb0cd7e7ecc71210 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Tue, 17 Nov 2020 12:40:54 +0300 Subject: spi: dw: Set transfer handler before unmasking the IRQs It turns out the IRQs most like can be unmasked before the controller is enabled with no problematic consequences. The manual doesn't explicitly state that, but the examples perform the controller initialization procedure in that order. So the commit da8f58909e7e ("spi: dw: Unmask IRQs after enabling the chip") hasn't been that required as I thought. But anyway setting the IRQs up after the chip enabling still worth adding since it has simplified the code a bit. The problem is that it has introduced a potential bug. The transfer handler pointer is now initialized after the IRQs are enabled. That may and eventually will cause an invalid or uninitialized callback invocation. Fix that just by performing the callback initialization before the IRQ unmask procedure. Fixes: da8f58909e7e ("spi: dw: Unmask IRQs after enabling the chip") Signed-off-by: Serge Semin Link: https://lore.kernel.org/r/20201117094054.4696-1-Sergey.Semin@baikalelectronics.ru Signed-off-by: Mark Brown --- drivers/spi/spi-dw-core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-dw-core.c b/drivers/spi/spi-dw-core.c index 2e50cc0a9291..0b2236ade412 100644 --- a/drivers/spi/spi-dw-core.c +++ b/drivers/spi/spi-dw-core.c @@ -357,11 +357,11 @@ static void dw_spi_irq_setup(struct dw_spi *dws) dw_writel(dws, DW_SPI_TXFTLR, level); dw_writel(dws, DW_SPI_RXFTLR, level - 1); + dws->transfer_handler = dw_spi_transfer_handler; + imask = SPI_INT_TXEI | SPI_INT_TXOI | SPI_INT_RXUI | SPI_INT_RXOI | SPI_INT_RXFI; spi_umask_intr(dws, imask); - - dws->transfer_handler = dw_spi_transfer_handler; } /* -- cgit v1.2.3 From 04a9cd51d3f3308a98cbc6adc07acb12fbade011 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Mon, 16 Nov 2020 09:23:10 +0100 Subject: spi: npcm-fiu: Don't leak SPI master in probe error path If the calls to of_match_device(), of_alias_get_id(), devm_ioremap_resource(), devm_regmap_init_mmio() or devm_clk_get() fail on probe of the NPCM FIU SPI driver, the spi_controller struct is erroneously not freed. Fix by switching over to the new devm_spi_alloc_master() helper. Fixes: ace55c411b11 ("spi: npcm-fiu: add NPCM FIU controller driver") Signed-off-by: Lukas Wunner Cc: # v5.4+: 5e844cc37a5c: spi: Introduce device-managed SPI controller allocation Cc: # v5.4+ Cc: Tomer Maimon Link: https://lore.kernel.org/r/a420c23a363a3bc9aa684c6e790c32a8af106d17.1605512876.git.lukas@wunner.de Signed-off-by: Mark Brown --- drivers/spi/spi-npcm-fiu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi-npcm-fiu.c b/drivers/spi/spi-npcm-fiu.c index 341f7cffeaac..1cb9329de945 100644 --- a/drivers/spi/spi-npcm-fiu.c +++ b/drivers/spi/spi-npcm-fiu.c @@ -679,7 +679,7 @@ static int npcm_fiu_probe(struct platform_device *pdev) struct resource *res; int id; - ctrl = spi_alloc_master(dev, sizeof(*fiu)); + ctrl = devm_spi_alloc_master(dev, sizeof(*fiu)); if (!ctrl) return -ENOMEM; -- cgit v1.2.3 From 6654b57866b98230a270953dd34f67de17ab1708 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Mon, 16 Nov 2020 09:09:29 +0800 Subject: drm/sun4i: dw-hdmi: fix error return code in sun8i_dw_hdmi_bind() Fix to return a negative error code from the error handling case instead of 0 in function sun8i_dw_hdmi_bind(). Fixes: b7c7436a5ff0 ("drm/sun4i: Implement A83T HDMI driver") Reported-by: Hulk Robot Signed-off-by: Xiongfeng Wang Reviewed-by: Jernej Skrabec Signed-off-by: Jernej Skrabec Link: https://patchwork.freedesktop.org/patch/msgid/1605488969-5211-1-git-send-email-wangxiongfeng2@huawei.com --- drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c index d4c08043dd81..92add2cef2e7 100644 --- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c +++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c @@ -208,6 +208,7 @@ static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master, phy_node = of_parse_phandle(dev->of_node, "phys", 0); if (!phy_node) { dev_err(dev, "Can't found PHY phandle\n"); + ret = -EINVAL; goto err_disable_clk_tmds; } -- cgit v1.2.3 From cb47d16ea21045c66eebbf5ed792e74a8537e27a Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Mon, 16 Nov 2020 21:07:13 +0800 Subject: qed: fix error return code in qed_iwarp_ll2_start() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 469981b17a4f ("qed: Add unaligned and packed packet processing") Fixes: fcb39f6c10b2 ("qed: Add mpa buffer descriptors for storing and processing mpa fpdus") Fixes: 1e28eaad07ea ("qed: Add iWARP support for fpdu spanned over more than two tcp packets") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Acked-by: Michal Kalderon  Link: https://lore.kernel.org/r/1605532033-27373-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index 512cbef24097..a99861124630 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -2754,14 +2754,18 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, iwarp_info->partial_fpdus = kcalloc((u16)p_hwfn->p_rdma_info->num_qps, sizeof(*iwarp_info->partial_fpdus), GFP_KERNEL); - if (!iwarp_info->partial_fpdus) + if (!iwarp_info->partial_fpdus) { + rc = -ENOMEM; goto err; + } iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps; iwarp_info->mpa_intermediate_buf = kzalloc(buff_size, GFP_KERNEL); - if (!iwarp_info->mpa_intermediate_buf) + if (!iwarp_info->mpa_intermediate_buf) { + rc = -ENOMEM; goto err; + } /* The mpa_bufs array serves for pending RX packets received on the * mpa ll2 that don't have place on the tx ring and require later @@ -2771,8 +2775,10 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, iwarp_info->mpa_bufs = kcalloc(data.input.rx_num_desc, sizeof(*iwarp_info->mpa_bufs), GFP_KERNEL); - if (!iwarp_info->mpa_bufs) + if (!iwarp_info->mpa_bufs) { + rc = -ENOMEM; goto err; + } INIT_LIST_HEAD(&iwarp_info->mpa_buf_pending_list); INIT_LIST_HEAD(&iwarp_info->mpa_buf_list); -- cgit v1.2.3 From 7b027c249da54f492699c43e26cba486cfd48035 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Tue, 17 Nov 2020 11:02:11 +0800 Subject: net: b44: fix error return code in b44_init_one() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 39a6f4bce6b4 ("b44: replace the ssb_dma API with the generic DMA API") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Reviewed-by: Michael Chan Link: https://lore.kernel.org/r/1605582131-36735-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/b44.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 74c1778d841e..b455b60a5434 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -2383,7 +2383,8 @@ static int b44_init_one(struct ssb_device *sdev, goto err_out_free_dev; } - if (dma_set_mask_and_coherent(sdev->dma_dev, DMA_BIT_MASK(30))) { + err = dma_set_mask_and_coherent(sdev->dma_dev, DMA_BIT_MASK(30)); + if (err) { dev_err(sdev->dev, "Required 30BIT DMA mask unsupported by the system\n"); goto err_out_powerdown; -- cgit v1.2.3 From 23bde34771f1ea92fb5e6682c0d8c04304d34b3b Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Tue, 17 Nov 2020 23:16:29 +0800 Subject: KVM: arm64: vgic-v3: Drop the reporting of GICR_TYPER.Last for userspace It was recently reported that if GICR_TYPER is accessed before the RD base address is set, we'll suffer from the unset @rdreg dereferencing. Oops... gpa_t last_rdist_typer = rdreg->base + GICR_TYPER + (rdreg->free_index - 1) * KVM_VGIC_V3_REDIST_SIZE; It's "expected" that users will access registers in the redistributor if the RD has been properly configured (e.g., the RD base address is set). But it hasn't yet been covered by the existing documentation. Per discussion on the list [1], the reporting of the GICR_TYPER.Last bit for userspace never actually worked. And it's difficult for us to emulate it correctly given that userspace has the flexibility to access it any time. Let's just drop the reporting of the Last bit for userspace for now (userspace should have full knowledge about it anyway) and it at least prevents kernel from panic ;-) [1] https://lore.kernel.org/kvmarm/c20865a267e44d1e2c0d52ce4e012263@kernel.org/ Fixes: ba7b3f1275fd ("KVM: arm/arm64: Revisit Redistributor TYPER last bit computation") Reported-by: Keqian Zhu Signed-off-by: Zenghui Yu Signed-off-by: Marc Zyngier Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20201117151629.1738-1-yuzenghui@huawei.com Cc: stable@vger.kernel.org --- arch/arm64/kvm/vgic/vgic-mmio-v3.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 52d6f24f65dc..15a6c98ee92f 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -273,6 +273,23 @@ static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu, return extract_bytes(value, addr & 7, len); } +static unsigned long vgic_uaccess_read_v3r_typer(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu); + int target_vcpu_id = vcpu->vcpu_id; + u64 value; + + value = (u64)(mpidr & GENMASK(23, 0)) << 32; + value |= ((target_vcpu_id & 0xffff) << 8); + + if (vgic_has_its(vcpu->kvm)) + value |= GICR_TYPER_PLPIS; + + /* reporting of the Last bit is not supported for userspace */ + return extract_bytes(value, addr & 7, len); +} + static unsigned long vgic_mmio_read_v3r_iidr(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { @@ -593,8 +610,9 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { REGISTER_DESC_WITH_LENGTH(GICR_IIDR, vgic_mmio_read_v3r_iidr, vgic_mmio_write_wi, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_TYPER, - vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, 8, + REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_TYPER, + vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, + vgic_uaccess_read_v3r_typer, vgic_mmio_uaccess_write_wi, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_WAKER, vgic_mmio_read_raz, vgic_mmio_write_wi, 4, -- cgit v1.2.3 From 3d5179458d22dc0b4fdc724e4bed4231a655112a Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Tue, 17 Nov 2020 13:14:48 +1030 Subject: net: ftgmac100: Fix crash when removing driver When removing the driver we would hit BUG_ON(!list_empty(&dev->ptype_specific)) in net/core/dev.c due to still having the NC-SI packet handler registered. # echo 1e660000.ethernet > /sys/bus/platform/drivers/ftgmac100/unbind ------------[ cut here ]------------ kernel BUG at net/core/dev.c:10254! Internal error: Oops - BUG: 0 [#1] SMP ARM CPU: 0 PID: 115 Comm: sh Not tainted 5.10.0-rc3-next-20201111-00007-g02e0365710c4 #46 Hardware name: Generic DT based system PC is at netdev_run_todo+0x314/0x394 LR is at cpumask_next+0x20/0x24 pc : [<806f5830>] lr : [<80863cb0>] psr: 80000153 sp : 855bbd58 ip : 00000001 fp : 855bbdac r10: 80c03d00 r9 : 80c06228 r8 : 81158c54 r7 : 00000000 r6 : 80c05dec r5 : 80c05d18 r4 : 813b9280 r3 : 813b9054 r2 : 8122c470 r1 : 00000002 r0 : 00000002 Flags: Nzcv IRQs on FIQs off Mode SVC_32 ISA ARM Segment none Control: 00c5387d Table: 85514008 DAC: 00000051 Process sh (pid: 115, stack limit = 0x7cb5703d) ... Backtrace: [<806f551c>] (netdev_run_todo) from [<80707eec>] (rtnl_unlock+0x18/0x1c) r10:00000051 r9:854ed710 r8:81158c54 r7:80c76bb0 r6:81158c10 r5:8115b410 r4:813b9000 [<80707ed4>] (rtnl_unlock) from [<806f5db8>] (unregister_netdev+0x2c/0x30) [<806f5d8c>] (unregister_netdev) from [<805a8180>] (ftgmac100_remove+0x20/0xa8) r5:8115b410 r4:813b9000 [<805a8160>] (ftgmac100_remove) from [<805355e4>] (platform_drv_remove+0x34/0x4c) Fixes: bd466c3fb5a4 ("net/faraday: Support NCSI mode") Signed-off-by: Joel Stanley Link: https://lore.kernel.org/r/20201117024448.1170761-1-joel@jms.id.au Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/faraday/ftgmac100.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 00024dd41147..80fb1f537bb3 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1907,6 +1907,8 @@ err_register_netdev: clk_disable_unprepare(priv->rclk); clk_disable_unprepare(priv->clk); err_ncsi_dev: + if (priv->ndev) + ncsi_unregister_dev(priv->ndev); ftgmac100_destroy_mdio(netdev); err_setup_mdio: iounmap(priv->base); @@ -1926,6 +1928,8 @@ static int ftgmac100_remove(struct platform_device *pdev) netdev = platform_get_drvdata(pdev); priv = netdev_priv(netdev); + if (priv->ndev) + ncsi_unregister_dev(priv->ndev); unregister_netdev(netdev); clk_disable_unprepare(priv->rclk); -- cgit v1.2.3 From 1b9e2a8c99a5c021041bfb2d512dc3ed92a94ffd Mon Sep 17 00:00:00 2001 From: Ryan Sharpelletti Date: Mon, 16 Nov 2020 17:44:13 +0000 Subject: tcp: only postpone PROBE_RTT if RTT is < current min_rtt estimate During loss recovery, retransmitted packets are forced to use TCP timestamps to calculate the RTT samples, which have a millisecond granularity. BBR is designed using a microsecond granularity. As a result, multiple RTT samples could be truncated to the same RTT value during loss recovery. This is problematic, as BBR will not enter PROBE_RTT if the RTT sample is <= the current min_rtt sample, meaning that if there are persistent losses, PROBE_RTT will constantly be pushed off and potentially never re-entered. This patch makes sure that BBR enters PROBE_RTT by checking if RTT sample is < the current min_rtt sample, rather than <=. The Netflix transport/TCP team discovered this bug in the Linux TCP BBR code during lab tests. Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control") Signed-off-by: Ryan Sharpelletti Signed-off-by: Neal Cardwell Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Yuchung Cheng Link: https://lore.kernel.org/r/20201116174412.1433277-1-sharpelletti.kdev@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_bbr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 6c4d79baff26..6ea3dc2e4219 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -945,7 +945,7 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) filter_expired = after(tcp_jiffies32, bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ); if (rs->rtt_us >= 0 && - (rs->rtt_us <= bbr->min_rtt_us || + (rs->rtt_us < bbr->min_rtt_us || (filter_expired && !rs->is_ack_delayed))) { bbr->min_rtt_us = rs->rtt_us; bbr->min_rtt_stamp = tcp_jiffies32; -- cgit v1.2.3 From ea63609857321c38fd4ad096388b413b66001c6c Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Thu, 8 Oct 2020 12:34:10 +0300 Subject: net/mlx5e: Fix refcount leak on kTLS RX resync On resync, the driver calls inet_lookup_established (__inet6_lookup_established) that increases sk_refcnt of the socket. To decrease it, the driver set skb->destructor to sock_edemux. However, it didn't work well, because the TCP stack also sets this destructor for early demux, and the refcount gets decreased only once, while increased two times (in mlx5e and in the TCP stack). It leads to a socket leak, a TLS context leak, which in the end leads to calling tls_dev_del twice: on socket close and on driver unload, which in turn leads to a crash. This commit fixes the refcount leak by calling sock_gen_put right away after using the socket, thus fixing all the subsequent issues. Fixes: 0419d8c9d8f8 ("net/mlx5e: kTLS, Add kTLS RX resync support") Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index 7f6221b8b1f7..6a1d82503ef8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -476,19 +476,22 @@ static void resync_update_sn(struct mlx5e_rq *rq, struct sk_buff *skb) depth += sizeof(struct tcphdr); - if (unlikely(!sk || sk->sk_state == TCP_TIME_WAIT)) + if (unlikely(!sk)) return; - if (unlikely(!resync_queue_get_psv(sk))) - return; + if (unlikely(sk->sk_state == TCP_TIME_WAIT)) + goto unref; - skb->sk = sk; - skb->destructor = sock_edemux; + if (unlikely(!resync_queue_get_psv(sk))) + goto unref; seq = th->seq; datalen = skb->len - depth; tls_offload_rx_resync_async_request_start(sk, seq, datalen); rq->stats->tls_resync_req_start++; + +unref: + sock_gen_put(sk); } void mlx5e_ktls_rx_resync(struct net_device *netdev, struct sock *sk, -- cgit v1.2.3 From 5cfb540ef27b5b763a3b181d142847ef0411728e Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Thu, 22 Oct 2020 11:22:56 -0500 Subject: net/mlx5e: Set IPsec WAs only in IP's non checksum partial case. The IP's checksum partial still requires L4 csum flag on Ethernet WQE. Make the IPsec WAs only for the IP's non checksum partial case (for example icmd packet) Fixes: 5be019040cb7 ("net/mlx5e: IPsec: Add Connect-X IPsec Tx data path offload") Signed-off-by: Huy Nguyen Reviewed-by: Raed Salem Reviewed-by: Alaa Hleihel Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 82b4419af9d4..6dd3ea3cbbed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -144,7 +144,9 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs) memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz); } -/* RM 2311217: no L4 inner checksum for IPsec tunnel type packet */ +/* If packet is not IP's CHECKSUM_PARTIAL (e.g. icmd packet), + * need to set L3 checksum flag for IPsec + */ static void ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) @@ -154,7 +156,6 @@ ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM; sq->stats->csum_partial_inner++; } else { - eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial++; } } @@ -162,11 +163,6 @@ ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, static inline void mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) { - if (unlikely(eseg->flow_table_metadata & cpu_to_be32(MLX5_ETH_WQE_FT_META_IPSEC))) { - ipsec_txwqe_build_eseg_csum(sq, skb, eseg); - return; - } - if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; if (skb->encapsulation) { @@ -177,6 +173,9 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial++; } + } else if (unlikely(eseg->flow_table_metadata & cpu_to_be32(MLX5_ETH_WQE_FT_META_IPSEC))) { + ipsec_txwqe_build_eseg_csum(sq, skb, eseg); + } else sq->stats->csum_none++; } -- cgit v1.2.3 From 6248ce991f8eed4f2f0fdec694f5749156105629 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Tue, 3 Nov 2020 12:56:18 -0600 Subject: net/mlx5e: Fix IPsec packet drop by mlx5e_tc_update_skb Both TC and IPsec crypto offload use metadata_regB to store private information. Since TC does not use bit 31 of regB, IPsec will use bit 31 as the IPsec packet marker. The IPsec's regB usage is changed to: Bit31: IPsec marker Bit30-24: IPsec syndrome Bit23-0: IPsec obj id Fixes: b2ac7541e377 ("net/mlx5e: IPsec: Add Connect-X IPsec Rx data path offload") Signed-off-by: Huy Nguyen Reviewed-by: Raed Salem Reviewed-by: Ariel Levkovich Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c | 14 +++++++------- .../net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c | 3 +-- .../net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h | 9 +++++---- drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 3 +++ 4 files changed, 16 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 0e45590662a8..381a9c8c9da9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -64,13 +64,13 @@ static int rx_err_add_rule(struct mlx5e_priv *priv, if (!spec) return -ENOMEM; - /* Action to copy 7 bit ipsec_syndrome to regB[0:6] */ + /* Action to copy 7 bit ipsec_syndrome to regB[24:30] */ MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY); MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME); MLX5_SET(copy_action_in, action, src_offset, 0); MLX5_SET(copy_action_in, action, length, 7); MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); - MLX5_SET(copy_action_in, action, dst_offset, 0); + MLX5_SET(copy_action_in, action, dst_offset, 24); modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL, 1, action); @@ -488,13 +488,13 @@ static int rx_add_rule(struct mlx5e_priv *priv, setup_fte_common(attrs, ipsec_obj_id, spec, &flow_act); - /* Set 1 bit ipsec marker */ - /* Set 24 bit ipsec_obj_id */ + /* Set bit[31] ipsec marker */ + /* Set bit[23-0] ipsec_obj_id */ MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); - MLX5_SET(set_action_in, action, data, (ipsec_obj_id << 1) | 0x1); - MLX5_SET(set_action_in, action, offset, 7); - MLX5_SET(set_action_in, action, length, 25); + MLX5_SET(set_action_in, action, data, (ipsec_obj_id | BIT(31))); + MLX5_SET(set_action_in, action, offset, 0); + MLX5_SET(set_action_in, action, length, 32); modify_hdr = mlx5_modify_header_alloc(priv->mdev, MLX5_FLOW_NAMESPACE_KERNEL, 1, action); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 11e31a3db2be..a9b45606dbdb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -453,7 +453,6 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev, struct mlx5_cqe64 *cqe) { u32 ipsec_meta_data = be32_to_cpu(cqe->ft_metadata); - u8 ipsec_syndrome = ipsec_meta_data & 0xFF; struct mlx5e_priv *priv; struct xfrm_offload *xo; struct xfrm_state *xs; @@ -481,7 +480,7 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev, xo = xfrm_offload(skb); xo->flags = CRYPTO_DONE; - switch (ipsec_syndrome & MLX5_IPSEC_METADATA_SYNDROM_MASK) { + switch (MLX5_IPSEC_METADATA_SYNDROM(ipsec_meta_data)) { case MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED: xo->status = CRYPTO_SUCCESS; if (WARN_ON_ONCE(priv->ipsec->no_trailer)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index 056dacb612b0..9df9b9a8e09b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -39,9 +39,10 @@ #include "en.h" #include "en/txrx.h" -#define MLX5_IPSEC_METADATA_MARKER_MASK (0x80) -#define MLX5_IPSEC_METADATA_SYNDROM_MASK (0x7F) -#define MLX5_IPSEC_METADATA_HANDLE(metadata) (((metadata) >> 8) & 0xFF) +/* Bit31: IPsec marker, Bit30-24: IPsec syndrome, Bit23-0: IPsec obj id */ +#define MLX5_IPSEC_METADATA_MARKER(metadata) (((metadata) >> 31) & 0x1) +#define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(6, 0)) +#define MLX5_IPSEC_METADATA_HANDLE(metadata) ((metadata) & GENMASK(23, 0)) struct mlx5e_accel_tx_ipsec_state { struct xfrm_offload *xo; @@ -78,7 +79,7 @@ static inline unsigned int mlx5e_ipsec_tx_ids_len(struct mlx5e_accel_tx_ipsec_st static inline bool mlx5_ipsec_is_rx_flow(struct mlx5_cqe64 *cqe) { - return !!(MLX5_IPSEC_METADATA_MARKER_MASK & be32_to_cpu(cqe->ft_metadata)); + return MLX5_IPSEC_METADATA_MARKER(be32_to_cpu(cqe->ft_metadata)); } static inline bool mlx5e_ipsec_is_tx_flow(struct mlx5e_accel_tx_ipsec_state *ipsec_st) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 3b979008143d..4a2ce241522e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -283,6 +283,9 @@ static inline bool mlx5e_cqe_regb_chain(struct mlx5_cqe64 *cqe) reg_b = be32_to_cpu(cqe->ft_metadata); + if (reg_b >> (MLX5E_TC_TABLE_CHAIN_TAG_BITS + ZONE_RESTORE_BITS)) + return false; + chain = reg_b & MLX5E_TC_TABLE_CHAIN_TAG_MASK; if (chain) return true; -- cgit v1.2.3 From 219b3267ca102a35092f5998921a9e6f99074af2 Mon Sep 17 00:00:00 2001 From: Maor Dickman Date: Wed, 4 Nov 2020 14:10:30 +0200 Subject: net/mlx5e: Fix check if netdev is bond slave Bond events handler uses bond_slave_get_rtnl to check if net device is bond slave. bond_slave_get_rtnl return the rcu rx_handler pointer from the netdev which exists for bond slaves but also exists for devices that are attached to linux bridge so using it as indication for bond slave is wrong. Fix by using netif_is_lag_port instead. Fixes: 7e51891a237f ("net/mlx5e: Use netdev events to set/del egress acl forward-to-vport rule") Signed-off-by: Maor Dickman Reviewed-by: Raed Salem Reviewed-by: Ariel Levkovich Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c index 3e44e4d820c5..95f2b26a3ee3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c @@ -187,7 +187,7 @@ static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev) struct mlx5e_priv *priv; /* A given netdev is not a representor or not a slave of LAG configuration */ - if (!mlx5e_eswitch_rep(netdev) || !bond_slave_get_rtnl(netdev)) + if (!mlx5e_eswitch_rep(netdev) || !netif_is_lag_port(netdev)) return false; priv = netdev_priv(netdev); -- cgit v1.2.3 From 8cbcc5ef2a281f6bb10099f4572a08cb765ffbf4 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Mon, 2 Nov 2020 17:34:44 +0200 Subject: net/mlx5: Add handling of port type in rule deletion Handle destruction of rules with port destination type to enable full destruction of flow. Without this handling of TX rules the deletion of these rules fails. Dmesg of flow destruction failure: [ 203.714146] mlx5_core 0000:00:0b.0: mlx5_cmd_check:753:(pid 342): SET_FLOW_TABLE_ENTRY(0x936) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x144b7a) [ 210.547387] ------------[ cut here ]------------ [ 210.548663] refcount_t: decrement hit 0; leaking memory. [ 210.550651] WARNING: CPU: 4 PID: 342 at lib/refcount.c:31 refcount_warn_saturate+0x5c/0x110 [ 210.550654] Modules linked in: mlx5_ib mlx5_core ib_ipoib rdma_ucm rdma_cm iw_cm ib_cm ib_umad ib_uverbs ib_core [ 210.550675] CPU: 4 PID: 342 Comm: test Not tainted 5.8.0-rc2+ #116 [ 210.550678] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 [ 210.550680] RIP: 0010:refcount_warn_saturate+0x5c/0x110 [ 210.550685] Code: c6 d1 1b 01 00 0f 84 ad 00 00 00 5b 5d c3 80 3d b5 d1 1b 01 00 75 f4 48 c7 c7 20 d1 15 82 c6 05 a5 d1 1b 01 01 e8 a7 eb af ff <0f> 0b eb dd 80 3d 99 d1 1b 01 00 75 d4 48 c7 c7 c0 cf 15 82 c6 05 [ 210.550687] RSP: 0018:ffff8881642e77e8 EFLAGS: 00010282 [ 210.550691] RAX: 0000000000000000 RBX: 0000000000000004 RCX: 0000000000000000 [ 210.550694] RDX: 0000000000000027 RSI: 0000000000000004 RDI: ffffed102c85ceef [ 210.550696] RBP: ffff888161720428 R08: ffffffff8124c10e R09: ffffed103243beae [ 210.550698] R10: ffff8881921df56b R11: ffffed103243bead R12: ffff8881841b4180 [ 210.550701] R13: ffff888161720428 R14: ffff8881616d0000 R15: ffff888161720380 [ 210.550704] FS: 00007fc27f025740(0000) GS:ffff888192000000(0000) knlGS:0000000000000000 [ 210.550706] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 210.550708] CR2: 0000557e4b41a6a0 CR3: 0000000002415004 CR4: 0000000000360ea0 [ 210.550711] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 210.550713] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 210.550715] Call Trace: [ 210.550717] mlx5_del_flow_rules+0x484/0x490 [mlx5_core] [ 210.550720] ? mlx5_cmd_set_fte+0xa80/0xa80 [mlx5_core] [ 210.550722] mlx5_ib_destroy_flow+0x17f/0x280 [mlx5_ib] [ 210.550724] uverbs_free_flow+0x4c/0x90 [ib_uverbs] [ 210.550726] destroy_hw_idr_uobject+0x41/0xb0 [ib_uverbs] [ 210.550728] uverbs_destroy_uobject+0xaa/0x390 [ib_uverbs] [ 210.550731] __uverbs_cleanup_ufile+0x129/0x1b0 [ib_uverbs] [ 210.550733] ? uverbs_destroy_uobject+0x390/0x390 [ib_uverbs] [ 210.550735] uverbs_destroy_ufile_hw+0x78/0x190 [ib_uverbs] [ 210.550737] ib_uverbs_close+0x36/0x140 [ib_uverbs] [ 210.550739] __fput+0x181/0x380 [ 210.550741] task_work_run+0x88/0xd0 [ 210.550743] do_exit+0x5f6/0x13b0 [ 210.550745] ? sched_clock_cpu+0x30/0x140 [ 210.550747] ? is_current_pgrp_orphaned+0x70/0x70 [ 210.550750] ? lock_downgrade+0x360/0x360 [ 210.550752] ? mark_held_locks+0x1d/0x90 [ 210.550754] do_group_exit+0x8a/0x140 [ 210.550756] get_signal+0x20a/0xf50 [ 210.550758] do_signal+0x8c/0xbe0 [ 210.550760] ? hrtimer_nanosleep+0x1d8/0x200 [ 210.550762] ? nanosleep_copyout+0x50/0x50 [ 210.550764] ? restore_sigcontext+0x320/0x320 [ 210.550766] ? __hrtimer_init+0xf0/0xf0 [ 210.550768] ? timespec64_add_safe+0x150/0x150 [ 210.550770] ? mark_held_locks+0x1d/0x90 [ 210.550772] ? lockdep_hardirqs_on_prepare+0x14c/0x240 [ 210.550774] __prepare_exit_to_usermode+0x119/0x170 [ 210.550776] do_syscall_64+0x65/0x300 [ 210.550778] ? trace_hardirqs_off+0x10/0x120 [ 210.550781] ? mark_held_locks+0x1d/0x90 [ 210.550783] ? asm_sysvec_apic_timer_interrupt+0xa/0x20 [ 210.550785] ? lockdep_hardirqs_on+0x112/0x190 [ 210.550787] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 210.550789] RIP: 0033:0x7fc27f1cd157 [ 210.550791] Code: Bad RIP value. [ 210.550793] RSP: 002b:00007ffd4db27ea8 EFLAGS: 00000246 ORIG_RAX: 0000000000000023 [ 210.550798] RAX: fffffffffffffdfc RBX: ffffffffffffff80 RCX: 00007fc27f1cd157 [ 210.550800] RDX: 00007fc27f025740 RSI: 00007ffd4db27eb0 RDI: 00007ffd4db27eb0 [ 210.550803] RBP: 0000000000000016 R08: 0000000000000000 R09: 000000000000000e [ 210.550805] R10: 00007ffd4db27dc7 R11: 0000000000000246 R12: 0000000000400c00 [ 210.550808] R13: 00007ffd4db285f0 R14: 0000000000000000 R15: 0000000000000000 [ 210.550809] irq event stamp: 49399 [ 210.550812] hardirqs last enabled at (49399): [] console_unlock+0x556/0x6f0 [ 210.550815] hardirqs last disabled at (49398): [] console_unlock+0xb7/0x6f0 [ 210.550818] softirqs last enabled at (48706): [] __do_softirq+0x37b/0x60c [ 210.550820] softirqs last disabled at (48697): [] asm_call_on_stack+0xf/0x20 [ 210.550822] ---[ end trace ad18c0e6fa846454 ]--- [ 210.581862] mlx5_core 0000:00:0c.0: mlx5_destroy_flow_table:2132:(pid 342): Flow table 262150 wasn't destroyed, refcount > 1 Fixes: a7ee18bdee83 ("RDMA/mlx5: Allow creating a matcher for a NIC TX flow table") Signed-off-by: Michael Guralnik Reviewed-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 325a5b0d6829..9fdd99272e31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -534,6 +534,13 @@ static void del_sw_hw_rule(struct fs_node *node) goto out; } + if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_PORT && + --fte->dests_size) { + fte->modify_mask |= BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION); + fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_ALLOW; + goto out; + } + if ((fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) && --fte->dests_size) { fte->modify_mask |= -- cgit v1.2.3 From 1ce5fc724a26e0b476e42c5d588bdb80caea003b Mon Sep 17 00:00:00 2001 From: Vladyslav Tarasiuk Date: Mon, 2 Nov 2020 13:45:24 +0200 Subject: net/mlx5: Clear bw_share upon VF disable Currently, if user disables VFs with some min and max rates configured, they are cleared. But QoS data is not cleared and restored upon next VF enable placing limits on minimal rate for given VF, when user expects none. To match cleared vport->info struct with QoS-related min and max rates upon VF disable, clear vport->qos struct too. Fixes: 556b9d16d3f5 ("net/mlx5: Clear VF's configuration on disabling SRIOV") Signed-off-by: Vladyslav Tarasiuk Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index e8e6294c7cca..6562f4d484e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1408,6 +1408,7 @@ static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw) int i; mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) { + memset(&vport->qos, 0, sizeof(vport->qos)); memset(&vport->info, 0, sizeof(vport->info)); vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; } -- cgit v1.2.3 From 470b74758260e4abc2508cf1614573c00a00465c Mon Sep 17 00:00:00 2001 From: Vladyslav Tarasiuk Date: Wed, 21 Oct 2020 11:05:41 +0300 Subject: net/mlx5: Disable QoS when min_rates on all VFs are zero MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently when QoS is enabled for VF and any min_rate is configured, the driver sets bw_share value to at least 1 and doesn’t allow to set it to 0 to make minimal rate unlimited. It means there is always a minimal rate configured for every VF, even if user tries to remove it. In order to make QoS disable possible, check whether all vports have configured min_rate = 0. If this is true, set their bw_share to 0 to disable min_rate limitations. Fixes: c9497c98901c ("net/mlx5: Add support for setting VF min rate") Signed-off-by: Vladyslav Tarasiuk Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 6562f4d484e6..5ad2308a2a6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2222,12 +2222,15 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw) max_guarantee = evport->info.min_rate; } - return max_t(u32, max_guarantee / fw_max_bw_share, 1); + if (max_guarantee) + return max_t(u32, max_guarantee / fw_max_bw_share, 1); + return 0; } -static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) +static int normalize_vports_min_rate(struct mlx5_eswitch *esw) { u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share); + u32 divider = calculate_vports_min_rate_divider(esw); struct mlx5_vport *evport; u32 vport_max_rate; u32 vport_min_rate; @@ -2240,9 +2243,9 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) continue; vport_min_rate = evport->info.min_rate; vport_max_rate = evport->info.max_rate; - bw_share = MLX5_MIN_BW_SHARE; + bw_share = 0; - if (vport_min_rate) + if (divider) bw_share = MLX5_RATE_TO_BW_SHARE(vport_min_rate, divider, fw_max_bw_share); @@ -2267,7 +2270,6 @@ int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport, struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); u32 fw_max_bw_share; u32 previous_min_rate; - u32 divider; bool min_rate_supported; bool max_rate_supported; int err = 0; @@ -2292,8 +2294,7 @@ int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport, previous_min_rate = evport->info.min_rate; evport->info.min_rate = min_rate; - divider = calculate_vports_min_rate_divider(esw); - err = normalize_vports_min_rate(esw, divider); + err = normalize_vports_min_rate(esw); if (err) { evport->info.min_rate = previous_min_rate; goto unlock; -- cgit v1.2.3 From 5b8631c7b21ca8bc039f0bc030048973b039e0d2 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Mon, 9 Nov 2020 11:35:52 +0200 Subject: net/mlx5: E-Switch, Fail mlx5_esw_modify_vport_rate if qos disabled Avoid calling mlx5_esw_modify_vport_rate() if qos is not enabled and avoid unnecessary syndrome messages from firmware. Fixes: fcb64c0f5640 ("net/mlx5: E-Switch, add ingress rate support") Signed-off-by: Eli Cohen Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 5ad2308a2a6b..d4ee0a9c03db 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1142,6 +1142,10 @@ int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, struct mlx5_vport *vport; vport = mlx5_eswitch_get_vport(esw, vport_num); + + if (!vport->qos.enabled) + return -EOPNOTSUPP; + MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps); return mlx5_modify_scheduling_element_cmd(esw->dev, -- cgit v1.2.3 From 68ec32daf7d50a9f7425f8607a7402c13aa0c587 Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Sat, 14 Nov 2020 19:52:23 +0800 Subject: net/mlx5: fix error return code in mlx5e_tc_nic_init() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: aedd133d17bc ("net/mlx5e: Support CT offload for tc nic flows") Reported-by: Hulk Robot Signed-off-by: Wang Hai Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 2e2fa0440032..ce710f22b1ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -5229,8 +5229,10 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) tc->ct = mlx5_tc_ct_init(priv, tc->chains, &priv->fs.tc.mod_hdr, MLX5_FLOW_NAMESPACE_KERNEL); - if (IS_ERR(tc->ct)) + if (IS_ERR(tc->ct)) { + err = PTR_ERR(tc->ct); goto err_ct; + } tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event; err = register_netdevice_notifier_dev_net(priv->netdev, -- cgit v1.2.3 From c464e26f2375a5529ec7bad7b38914e1b87df1e2 Mon Sep 17 00:00:00 2001 From: Sylvain Lemieux Date: Fri, 18 Sep 2020 10:15:27 -0400 Subject: MAINTAINERS: Remove myself as LPC32xx maintainers I appreciate my time as a kernel maintainer for the last few years. I am no longer working on the LPC32xx platform and cannot commit time for support and discussions. Signed-off-by: Sylvain Lemieux Acked-by: Vladimir Zapolskiy Signed-off-by: Arnd Bergmann --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 3da6d8c154e4..30c7e3910d66 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1994,7 +1994,6 @@ N: lpc18xx ARM/LPC32XX SOC SUPPORT M: Vladimir Zapolskiy -M: Sylvain Lemieux L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://github.com/vzapolskiy/linux-lpc32xx.git -- cgit v1.2.3 From fd5736bf9f235d26c83cac8a16c70bbdafa55abe Mon Sep 17 00:00:00 2001 From: Alex Marginean Date: Thu, 12 Nov 2020 20:26:08 +0200 Subject: enetc: Workaround for MDIO register access issue Due to a hardware issue, an access to MDIO registers that is concurrent with other ENETC register accesses may lead to the MDIO access being dropped or corrupted. The workaround introduces locking for all register accesses to the ENETC register space. To reduce performance impact, a readers-writers locking scheme has been implemented. The writer in this case is the MDIO access code (irrelevant whether that MDIO access is a register read or write), and the reader is any access code to non-MDIO ENETC registers. Also, the datapath functions acquire the read lock fewer times and use _hot accessors. All the rest of the code uses the _wa accessors which lock every register access. The commit introducing MDIO support is - commit ebfcb23d62ab ("enetc: Add ENETC PF level external MDIO support") but due to subsequent refactoring this patch is applicable on top of a later commit. Fixes: 6517798dd343 ("enetc: Make MDIO accessors more generic and export to include/linux/fsl") Signed-off-by: Alex Marginean Signed-off-by: Vladimir Oltean Signed-off-by: Claudiu Manoil Link: https://lore.kernel.org/r/20201112182608.26177-1-claudiu.manoil@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/Kconfig | 1 + drivers/net/ethernet/freescale/enetc/enetc.c | 62 ++++++++---- drivers/net/ethernet/freescale/enetc/enetc_hw.h | 115 ++++++++++++++++++++-- drivers/net/ethernet/freescale/enetc/enetc_mdio.c | 8 +- 4 files changed, 161 insertions(+), 25 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig index 0fa18b00c49b..d99ea0f4e4a6 100644 --- a/drivers/net/ethernet/freescale/enetc/Kconfig +++ b/drivers/net/ethernet/freescale/enetc/Kconfig @@ -16,6 +16,7 @@ config FSL_ENETC config FSL_ENETC_VF tristate "ENETC VF driver" depends on PCI && PCI_MSI + select FSL_ENETC_MDIO select PHYLINK select DIMLIB help diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 52be6e315752..fc2075ea57fe 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -33,7 +33,10 @@ netdev_tx_t enetc_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_BUSY; } + enetc_lock_mdio(); count = enetc_map_tx_buffs(tx_ring, skb, priv->active_offloads); + enetc_unlock_mdio(); + if (unlikely(!count)) goto drop_packet_err; @@ -239,7 +242,7 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb, skb_tx_timestamp(skb); /* let H/W know BD ring has been updated */ - enetc_wr_reg(tx_ring->tpir, i); /* includes wmb() */ + enetc_wr_reg_hot(tx_ring->tpir, i); /* includes wmb() */ return count; @@ -262,12 +265,16 @@ static irqreturn_t enetc_msix(int irq, void *data) struct enetc_int_vector *v = data; int i; + enetc_lock_mdio(); + /* disable interrupts */ - enetc_wr_reg(v->rbier, 0); - enetc_wr_reg(v->ricr1, v->rx_ictt); + enetc_wr_reg_hot(v->rbier, 0); + enetc_wr_reg_hot(v->ricr1, v->rx_ictt); for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS) - enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), 0); + enetc_wr_reg_hot(v->tbier_base + ENETC_BDR_OFF(i), 0); + + enetc_unlock_mdio(); napi_schedule(&v->napi); @@ -334,19 +341,23 @@ static int enetc_poll(struct napi_struct *napi, int budget) v->rx_napi_work = false; + enetc_lock_mdio(); + /* enable interrupts */ - enetc_wr_reg(v->rbier, ENETC_RBIER_RXTIE); + enetc_wr_reg_hot(v->rbier, ENETC_RBIER_RXTIE); for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS) - enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), - ENETC_TBIER_TXTIE); + enetc_wr_reg_hot(v->tbier_base + ENETC_BDR_OFF(i), + ENETC_TBIER_TXTIE); + + enetc_unlock_mdio(); return work_done; } static int enetc_bd_ready_count(struct enetc_bdr *tx_ring, int ci) { - int pi = enetc_rd_reg(tx_ring->tcir) & ENETC_TBCIR_IDX_MASK; + int pi = enetc_rd_reg_hot(tx_ring->tcir) & ENETC_TBCIR_IDX_MASK; return pi >= ci ? pi - ci : tx_ring->bd_count - ci + pi; } @@ -386,7 +397,10 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) i = tx_ring->next_to_clean; tx_swbd = &tx_ring->tx_swbd[i]; + + enetc_lock_mdio(); bds_to_clean = enetc_bd_ready_count(tx_ring, i); + enetc_unlock_mdio(); do_tstamp = false; @@ -429,16 +443,20 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) tx_swbd = tx_ring->tx_swbd; } + enetc_lock_mdio(); + /* BD iteration loop end */ if (is_eof) { tx_frm_cnt++; /* re-arm interrupt source */ - enetc_wr_reg(tx_ring->idr, BIT(tx_ring->index) | - BIT(16 + tx_ring->index)); + enetc_wr_reg_hot(tx_ring->idr, BIT(tx_ring->index) | + BIT(16 + tx_ring->index)); } if (unlikely(!bds_to_clean)) bds_to_clean = enetc_bd_ready_count(tx_ring, i); + + enetc_unlock_mdio(); } tx_ring->next_to_clean = i; @@ -515,8 +533,6 @@ static int enetc_refill_rx_ring(struct enetc_bdr *rx_ring, const int buff_cnt) if (likely(j)) { rx_ring->next_to_alloc = i; /* keep track from page reuse */ rx_ring->next_to_use = i; - /* update ENETC's consumer index */ - enetc_wr_reg(rx_ring->rcir, i); } return j; @@ -534,8 +550,8 @@ static void enetc_get_rx_tstamp(struct net_device *ndev, u64 tstamp; if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_TSTMP) { - lo = enetc_rd(hw, ENETC_SICTR0); - hi = enetc_rd(hw, ENETC_SICTR1); + lo = enetc_rd_reg_hot(hw->reg + ENETC_SICTR0); + hi = enetc_rd_reg_hot(hw->reg + ENETC_SICTR1); rxbd = enetc_rxbd_ext(rxbd); tstamp_lo = le32_to_cpu(rxbd->ext.tstamp); if (lo <= tstamp_lo) @@ -684,23 +700,31 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, u32 bd_status; u16 size; + enetc_lock_mdio(); + if (cleaned_cnt >= ENETC_RXBD_BUNDLE) { int count = enetc_refill_rx_ring(rx_ring, cleaned_cnt); + /* update ENETC's consumer index */ + enetc_wr_reg_hot(rx_ring->rcir, rx_ring->next_to_use); cleaned_cnt -= count; } rxbd = enetc_rxbd(rx_ring, i); bd_status = le32_to_cpu(rxbd->r.lstatus); - if (!bd_status) + if (!bd_status) { + enetc_unlock_mdio(); break; + } - enetc_wr_reg(rx_ring->idr, BIT(rx_ring->index)); + enetc_wr_reg_hot(rx_ring->idr, BIT(rx_ring->index)); dma_rmb(); /* for reading other rxbd fields */ size = le16_to_cpu(rxbd->r.buf_len); skb = enetc_map_rx_buff_to_skb(rx_ring, i, size); - if (!skb) + if (!skb) { + enetc_unlock_mdio(); break; + } enetc_get_offloads(rx_ring, rxbd, skb); @@ -712,6 +736,7 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, if (unlikely(bd_status & ENETC_RXBD_LSTATUS(ENETC_RXBD_ERR_MASK))) { + enetc_unlock_mdio(); dev_kfree_skb(skb); while (!(bd_status & ENETC_RXBD_LSTATUS_F)) { dma_rmb(); @@ -751,6 +776,8 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, enetc_process_skb(rx_ring, skb); + enetc_unlock_mdio(); + napi_gro_receive(napi, skb); rx_frm_cnt++; @@ -1225,6 +1252,7 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) rx_ring->idr = hw->reg + ENETC_SIRXIDR; enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring)); + enetc_wr(hw, ENETC_SIRXIDR, rx_ring->next_to_use); /* enable ring */ enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 17cf7c94fdb5..eb6bbf1113c7 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -324,14 +324,100 @@ struct enetc_hw { void __iomem *global; }; -/* general register accessors */ -#define enetc_rd_reg(reg) ioread32((reg)) -#define enetc_wr_reg(reg, val) iowrite32((val), (reg)) +/* ENETC register accessors */ + +/* MDIO issue workaround (on LS1028A) - + * Due to a hardware issue, an access to MDIO registers + * that is concurrent with other ENETC register accesses + * may lead to the MDIO access being dropped or corrupted. + * To protect the MDIO accesses a readers-writers locking + * scheme is used, where the MDIO register accesses are + * protected by write locks to insure exclusivity, while + * the remaining ENETC registers are accessed under read + * locks since they only compete with MDIO accesses. + */ +extern rwlock_t enetc_mdio_lock; + +/* use this locking primitive only on the fast datapath to + * group together multiple non-MDIO register accesses to + * minimize the overhead of the lock + */ +static inline void enetc_lock_mdio(void) +{ + read_lock(&enetc_mdio_lock); +} + +static inline void enetc_unlock_mdio(void) +{ + read_unlock(&enetc_mdio_lock); +} + +/* use these accessors only on the fast datapath under + * the enetc_lock_mdio() locking primitive to minimize + * the overhead of the lock + */ +static inline u32 enetc_rd_reg_hot(void __iomem *reg) +{ + lockdep_assert_held(&enetc_mdio_lock); + + return ioread32(reg); +} + +static inline void enetc_wr_reg_hot(void __iomem *reg, u32 val) +{ + lockdep_assert_held(&enetc_mdio_lock); + + iowrite32(val, reg); +} + +/* internal helpers for the MDIO w/a */ +static inline u32 _enetc_rd_reg_wa(void __iomem *reg) +{ + u32 val; + + enetc_lock_mdio(); + val = ioread32(reg); + enetc_unlock_mdio(); + + return val; +} + +static inline void _enetc_wr_reg_wa(void __iomem *reg, u32 val) +{ + enetc_lock_mdio(); + iowrite32(val, reg); + enetc_unlock_mdio(); +} + +static inline u32 _enetc_rd_mdio_reg_wa(void __iomem *reg) +{ + unsigned long flags; + u32 val; + + write_lock_irqsave(&enetc_mdio_lock, flags); + val = ioread32(reg); + write_unlock_irqrestore(&enetc_mdio_lock, flags); + + return val; +} + +static inline void _enetc_wr_mdio_reg_wa(void __iomem *reg, u32 val) +{ + unsigned long flags; + + write_lock_irqsave(&enetc_mdio_lock, flags); + iowrite32(val, reg); + write_unlock_irqrestore(&enetc_mdio_lock, flags); +} + #ifdef ioread64 -#define enetc_rd_reg64(reg) ioread64((reg)) +static inline u64 _enetc_rd_reg64(void __iomem *reg) +{ + return ioread64(reg); +} #else /* using this to read out stats on 32b systems */ -static inline u64 enetc_rd_reg64(void __iomem *reg) +static inline u64 _enetc_rd_reg64(void __iomem *reg) { u32 low, high, tmp; @@ -345,12 +431,29 @@ static inline u64 enetc_rd_reg64(void __iomem *reg) } #endif +static inline u64 _enetc_rd_reg64_wa(void __iomem *reg) +{ + u64 val; + + enetc_lock_mdio(); + val = _enetc_rd_reg64(reg); + enetc_unlock_mdio(); + + return val; +} + +/* general register accessors */ +#define enetc_rd_reg(reg) _enetc_rd_reg_wa((reg)) +#define enetc_wr_reg(reg, val) _enetc_wr_reg_wa((reg), (val)) #define enetc_rd(hw, off) enetc_rd_reg((hw)->reg + (off)) #define enetc_wr(hw, off, val) enetc_wr_reg((hw)->reg + (off), val) -#define enetc_rd64(hw, off) enetc_rd_reg64((hw)->reg + (off)) +#define enetc_rd64(hw, off) _enetc_rd_reg64_wa((hw)->reg + (off)) /* port register accessors - PF only */ #define enetc_port_rd(hw, off) enetc_rd_reg((hw)->port + (off)) #define enetc_port_wr(hw, off, val) enetc_wr_reg((hw)->port + (off), val) +#define enetc_port_rd_mdio(hw, off) _enetc_rd_mdio_reg_wa((hw)->port + (off)) +#define enetc_port_wr_mdio(hw, off, val) _enetc_wr_mdio_reg_wa(\ + (hw)->port + (off), val) /* global register accessors - PF only */ #define enetc_global_rd(hw, off) enetc_rd_reg((hw)->global + (off)) #define enetc_global_wr(hw, off, val) enetc_wr_reg((hw)->global + (off), val) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c index 48c32a171afa..ee0116ed4738 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c @@ -16,13 +16,13 @@ static inline u32 _enetc_mdio_rd(struct enetc_mdio_priv *mdio_priv, int off) { - return enetc_port_rd(mdio_priv->hw, mdio_priv->mdio_base + off); + return enetc_port_rd_mdio(mdio_priv->hw, mdio_priv->mdio_base + off); } static inline void _enetc_mdio_wr(struct enetc_mdio_priv *mdio_priv, int off, u32 val) { - enetc_port_wr(mdio_priv->hw, mdio_priv->mdio_base + off, val); + enetc_port_wr_mdio(mdio_priv->hw, mdio_priv->mdio_base + off, val); } #define enetc_mdio_rd(mdio_priv, off) \ @@ -174,3 +174,7 @@ struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs) return hw; } EXPORT_SYMBOL_GPL(enetc_hw_alloc); + +/* Lock for MDIO access errata on LS1028A */ +DEFINE_RWLOCK(enetc_mdio_lock); +EXPORT_SYMBOL_GPL(enetc_mdio_lock); -- cgit v1.2.3 From cf23705244c947151179f929774fabf71e239eee Mon Sep 17 00:00:00 2001 From: Mickaël Salaün Date: Fri, 30 Oct 2020 13:38:48 +0100 Subject: ptrace: Set PF_SUPERPRIV when checking capability MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 69f594a38967 ("ptrace: do not audit capability check when outputing /proc/pid/stat") replaced the use of ns_capable() with has_ns_capability{,_noaudit}() which doesn't set PF_SUPERPRIV. Commit 6b3ad6649a4c ("ptrace: reintroduce usage of subjective credentials in ptrace_has_cap()") replaced has_ns_capability{,_noaudit}() with security_capable(), which doesn't set PF_SUPERPRIV neither. Since commit 98f368e9e263 ("kernel: Add noaudit variant of ns_capable()"), a new ns_capable_noaudit() helper is available. Let's use it! As a result, the signature of ptrace_has_cap() is restored to its original one. Cc: Christian Brauner Cc: Eric Paris Cc: Jann Horn Cc: Kees Cook Cc: Oleg Nesterov Cc: Serge E. Hallyn Cc: Tyler Hicks Cc: stable@vger.kernel.org Fixes: 6b3ad6649a4c ("ptrace: reintroduce usage of subjective credentials in ptrace_has_cap()") Fixes: 69f594a38967 ("ptrace: do not audit capability check when outputing /proc/pid/stat") Signed-off-by: Mickaël Salaün Reviewed-by: Jann Horn Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201030123849.770769-2-mic@digikod.net --- kernel/ptrace.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 43d6179508d6..79de1294f8eb 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -264,17 +264,11 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) return ret; } -static bool ptrace_has_cap(const struct cred *cred, struct user_namespace *ns, - unsigned int mode) +static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { - int ret; - if (mode & PTRACE_MODE_NOAUDIT) - ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT); - else - ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NONE); - - return ret == 0; + return ns_capable_noaudit(ns, CAP_SYS_PTRACE); + return ns_capable(ns, CAP_SYS_PTRACE); } /* Returns 0 on success, -errno on denial. */ @@ -326,7 +320,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; - if (ptrace_has_cap(cred, tcred->user_ns, mode)) + if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; @@ -345,7 +339,7 @@ ok: mm = task->mm; if (mm && ((get_dumpable(mm) != SUID_DUMP_USER) && - !ptrace_has_cap(cred, mm->user_ns, mode))) + !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; return security_ptrace_access_check(task, mode); -- cgit v1.2.3 From fb14528e443646dd3fd02df4437fcf5265b66baa Mon Sep 17 00:00:00 2001 From: Mickaël Salaün Date: Fri, 30 Oct 2020 13:38:49 +0100 Subject: seccomp: Set PF_SUPERPRIV when checking capability MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace the use of security_capable(current_cred(), ...) with ns_capable_noaudit() which set PF_SUPERPRIV. Since commit 98f368e9e263 ("kernel: Add noaudit variant of ns_capable()"), a new ns_capable_noaudit() helper is available. Let's use it! Cc: Jann Horn Cc: Kees Cook Cc: Tyler Hicks Cc: Will Drewry Cc: stable@vger.kernel.org Fixes: e2cfabdfd075 ("seccomp: add system call filtering using BPF") Signed-off-by: Mickaël Salaün Reviewed-by: Jann Horn Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201030123849.770769-3-mic@digikod.net --- kernel/seccomp.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 8ad7a293255a..53a7d1512dd7 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -38,7 +38,7 @@ #include #include #include -#include +#include #include #include #include @@ -558,8 +558,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) * behavior of privileged children. */ if (!task_no_new_privs(current) && - security_capable(current_cred(), current_user_ns(), - CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) != 0) + !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)) return ERR_PTR(-EACCES); /* Allocate a new seccomp_filter */ -- cgit v1.2.3 From a5bbcbf29089a1252c201b1a7fd38151de355db9 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Sun, 15 Nov 2020 10:30:41 +0000 Subject: netdevsim: set .owner to THIS_MODULE If THIS_MODULE is not set, the module would be removed while debugfs is being used. It eventually makes kernel panic. Fixes: 82c93a87bf8b ("netdevsim: implement couple of testing devlink health reporters") Fixes: 424be63ad831 ("netdevsim: add UDP tunnel port offload support") Fixes: 4418f862d675 ("netdevsim: implement support for devlink region and snapshots") Fixes: d3cbb907ae57 ("netdevsim: add ACL trap reporting cookie as a metadata") Signed-off-by: Taehee Yoo Link: https://lore.kernel.org/r/20201115103041.30701-1-ap420073@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/netdevsim/dev.c | 2 ++ drivers/net/netdevsim/health.c | 1 + drivers/net/netdevsim/udp_tunnels.c | 1 + 3 files changed, 4 insertions(+) diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index d07061417675..e7972e88ffe0 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -96,6 +96,7 @@ static const struct file_operations nsim_dev_take_snapshot_fops = { .open = simple_open, .write = nsim_dev_take_snapshot_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, }; static ssize_t nsim_dev_trap_fa_cookie_read(struct file *file, @@ -188,6 +189,7 @@ static const struct file_operations nsim_dev_trap_fa_cookie_fops = { .read = nsim_dev_trap_fa_cookie_read, .write = nsim_dev_trap_fa_cookie_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, }; static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c index 62958b238d50..21e2974660e7 100644 --- a/drivers/net/netdevsim/health.c +++ b/drivers/net/netdevsim/health.c @@ -261,6 +261,7 @@ static const struct file_operations nsim_dev_health_break_fops = { .open = simple_open, .write = nsim_dev_health_break_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, }; int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink) diff --git a/drivers/net/netdevsim/udp_tunnels.c b/drivers/net/netdevsim/udp_tunnels.c index 6ab023acefd6..02dc3123eb6c 100644 --- a/drivers/net/netdevsim/udp_tunnels.c +++ b/drivers/net/netdevsim/udp_tunnels.c @@ -124,6 +124,7 @@ static const struct file_operations nsim_udp_tunnels_info_reset_fops = { .open = simple_open, .write = nsim_udp_tunnels_info_reset_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, }; int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, -- cgit v1.2.3 From c993df5a688975bf9ce899706ca13d2bc8d6be25 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 17 Nov 2020 07:59:16 -0700 Subject: io_uring: don't double complete failed reissue request Zorro reports that an xfstest test case is failing, and it turns out that for the reissue path we can potentially issue a double completion on the request for the failure path. There's an issue around the retry as well, but for now, at least just make sure that we handle the error path correctly. Cc: stable@vger.kernel.org Fixes: b63534c41e20 ("io_uring: re-issue block requests that failed because of resources") Reported-by: Zorro Lang Signed-off-by: Jens Axboe --- fs/io_uring.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index f05978a74ce1..b205c1df3f74 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2578,7 +2578,6 @@ static bool io_resubmit_prep(struct io_kiocb *req, int error) } end_req: req_set_fail_links(req); - io_req_complete(req, ret); return false; } #endif -- cgit v1.2.3 From 7381e27b1e563aa8a1c6bcf74a8cadb6901c283a Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Fri, 6 Nov 2020 16:48:47 +0200 Subject: interconnect: qcom: msm8974: Prevent integer overflow in rate When sync_state support got introduced recently, by default we try to set the NoCs to run initially at maximum rate. But as these values are aggregated, we may end with a really big clock rate value, which is then converted from "u64" to "long" during the clock rate rounding. But on 32bit platforms this may result an overflow. Fix it by making sure that the rate is within range. Reported-by: Luca Weiss Reviewed-by: Brian Masney Link: https://lore.kernel.org/r/20201106144847.7726-1-georgi.djakov@linaro.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/msm8974.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/interconnect/qcom/msm8974.c b/drivers/interconnect/qcom/msm8974.c index 3a313e11e73d..b6b639dad691 100644 --- a/drivers/interconnect/qcom/msm8974.c +++ b/drivers/interconnect/qcom/msm8974.c @@ -618,6 +618,8 @@ static int msm8974_icc_set(struct icc_node *src, struct icc_node *dst) do_div(rate, src_qn->buswidth); + rate = min_t(u32, rate, INT_MAX); + if (src_qn->rate == rate) return 0; @@ -758,6 +760,7 @@ static struct platform_driver msm8974_noc_driver = { .driver = { .name = "qnoc-msm8974", .of_match_table = msm8974_noc_of_match, + .sync_state = icc_sync_state, }, }; module_platform_driver(msm8974_noc_driver); -- cgit v1.2.3 From 9caf2d956cfa254c6d89c5f4d7b3f8235d75b28f Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Mon, 9 Nov 2020 14:45:12 +0200 Subject: interconnect: qcom: msm8974: Don't boost the NoC rate during boot It has been reported that on Fairphone 2 (msm8974-based), increasing the clock rate for some of the NoCs during boot may lead to hangs. Let's restore the original behavior and not touch the clock rate of any of the NoCs to fix the regression. Reported-by: Luca Weiss Tested-by: Luca Weiss Fixes: b1d681d8d324 ("interconnect: Add sync state support") Link: https://lore.kernel.org/r/20201109124512.10776-1-georgi.djakov@linaro.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/msm8974.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/interconnect/qcom/msm8974.c b/drivers/interconnect/qcom/msm8974.c index b6b639dad691..da68ce375a89 100644 --- a/drivers/interconnect/qcom/msm8974.c +++ b/drivers/interconnect/qcom/msm8974.c @@ -637,6 +637,14 @@ static int msm8974_icc_set(struct icc_node *src, struct icc_node *dst) return 0; } +static int msm8974_get_bw(struct icc_node *node, u32 *avg, u32 *peak) +{ + *avg = 0; + *peak = 0; + + return 0; +} + static int msm8974_icc_probe(struct platform_device *pdev) { const struct msm8974_icc_desc *desc; @@ -690,6 +698,7 @@ static int msm8974_icc_probe(struct platform_device *pdev) provider->aggregate = icc_std_aggregate; provider->xlate = of_icc_xlate_onecell; provider->data = data; + provider->get_bw = msm8974_get_bw; ret = icc_provider_add(provider); if (ret) { -- cgit v1.2.3 From 138559b9f99d3b6b1d5e75c78facc067a23871c6 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Sun, 15 Nov 2020 15:14:48 +0200 Subject: net/tls: Fix wrong record sn in async mode of device resync In async_resync mode, we log the TCP seq of records until the async request is completed. Later, in case one of the logged seqs matches the resync request, we return it, together with its record serial number. Before this fix, we mistakenly returned the serial number of the current record instead. Fixes: ed9b7646b06a ("net/tls: Add asynchronous resync") Signed-off-by: Tariq Toukan Reviewed-by: Boris Pismenny Link: https://lore.kernel.org/r/20201115131448.2702-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- include/net/tls.h | 16 +++++++++++++++- net/tls/tls_device.c | 37 +++++++++++++++++++++++++++---------- 2 files changed, 42 insertions(+), 11 deletions(-) diff --git a/include/net/tls.h b/include/net/tls.h index baf1e99d8193..cf1473099453 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -300,7 +300,8 @@ enum tls_offload_sync_type { #define TLS_DEVICE_RESYNC_ASYNC_LOGMAX 13 struct tls_offload_resync_async { atomic64_t req; - u32 loglen; + u16 loglen; + u16 rcd_delta; u32 log[TLS_DEVICE_RESYNC_ASYNC_LOGMAX]; }; @@ -471,6 +472,18 @@ static inline bool tls_bigint_increment(unsigned char *seq, int len) return (i == -1); } +static inline void tls_bigint_subtract(unsigned char *seq, int n) +{ + u64 rcd_sn; + __be64 *p; + + BUILD_BUG_ON(TLS_MAX_REC_SEQ_SIZE != 8); + + p = (__be64 *)seq; + rcd_sn = be64_to_cpu(*p); + *p = cpu_to_be64(rcd_sn - n); +} + static inline struct tls_context *tls_get_ctx(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -639,6 +652,7 @@ tls_offload_rx_resync_async_request_start(struct sock *sk, __be32 seq, u16 len) atomic64_set(&rx_ctx->resync_async->req, ((u64)ntohl(seq) << 32) | ((u64)len << 16) | RESYNC_REQ | RESYNC_REQ_ASYNC); rx_ctx->resync_async->loglen = 0; + rx_ctx->resync_async->rcd_delta = 0; } static inline void diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index cec86229a6a0..54d3e161d198 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -694,36 +694,51 @@ static void tls_device_resync_rx(struct tls_context *tls_ctx, static bool tls_device_rx_resync_async(struct tls_offload_resync_async *resync_async, - s64 resync_req, u32 *seq) + s64 resync_req, u32 *seq, u16 *rcd_delta) { u32 is_async = resync_req & RESYNC_REQ_ASYNC; u32 req_seq = resync_req >> 32; u32 req_end = req_seq + ((resync_req >> 16) & 0xffff); + u16 i; + + *rcd_delta = 0; if (is_async) { + /* shouldn't get to wraparound: + * too long in async stage, something bad happened + */ + if (WARN_ON_ONCE(resync_async->rcd_delta == USHRT_MAX)) + return false; + /* asynchronous stage: log all headers seq such that * req_seq <= seq <= end_seq, and wait for real resync request */ - if (between(*seq, req_seq, req_end) && + if (before(*seq, req_seq)) + return false; + if (!after(*seq, req_end) && resync_async->loglen < TLS_DEVICE_RESYNC_ASYNC_LOGMAX) resync_async->log[resync_async->loglen++] = *seq; + resync_async->rcd_delta++; + return false; } /* synchronous stage: check against the logged entries and * proceed to check the next entries if no match was found */ - while (resync_async->loglen) { - if (req_seq == resync_async->log[resync_async->loglen - 1] && - atomic64_try_cmpxchg(&resync_async->req, - &resync_req, 0)) { - resync_async->loglen = 0; + for (i = 0; i < resync_async->loglen; i++) + if (req_seq == resync_async->log[i] && + atomic64_try_cmpxchg(&resync_async->req, &resync_req, 0)) { + *rcd_delta = resync_async->rcd_delta - i; *seq = req_seq; + resync_async->loglen = 0; + resync_async->rcd_delta = 0; return true; } - resync_async->loglen--; - } + + resync_async->loglen = 0; + resync_async->rcd_delta = 0; if (req_seq == *seq && atomic64_try_cmpxchg(&resync_async->req, @@ -741,6 +756,7 @@ void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) u32 sock_data, is_req_pending; struct tls_prot_info *prot; s64 resync_req; + u16 rcd_delta; u32 req_seq; if (tls_ctx->rx_conf != TLS_HW) @@ -786,8 +802,9 @@ void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) return; if (!tls_device_rx_resync_async(rx_ctx->resync_async, - resync_req, &seq)) + resync_req, &seq, &rcd_delta)) return; + tls_bigint_subtract(rcd_sn, rcd_delta); break; } -- cgit v1.2.3 From c9c89dcd872ea33327673fcb97398993a1f22736 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 16 Nov 2020 14:27:46 -0800 Subject: bpf, sockmap: Fix partial copy_page_to_iter so progress can still be made If copy_page_to_iter() fails or even partially completes, but with fewer bytes copied than expected we currently reset sg.start and return EFAULT. This proves problematic if we already copied data into the user buffer before we return an error. Because we leave the copied data in the user buffer and fail to unwind the scatterlist so kernel side believes data has been copied and user side believes data has _not_ been received. Expected behavior should be to return number of bytes copied and then on the next read we need to return the error assuming its still there. This can happen if we have a copy length spanning multiple scatterlist elements and one or more complete before the error is hit. The error is rare enough though that my normal testing with server side programs, such as nginx, httpd, envoy, etc., I have never seen this. The only reliable way to reproduce that I've found is to stream movies over my browser for a day or so and wait for it to hang. Not very scientific, but with a few extra WARN_ON()s in the code the bug was obvious. When we review the errors from copy_page_to_iter() it seems we are hitting a page fault from copy_page_to_iter_iovec() where the code checks fault_in_pages_writeable(buf, copy) where buf is the user buffer. It also seems typical server applications don't hit this case. The other way to try and reproduce this is run the sockmap selftest tool test_sockmap with data verification enabled, but it doesn't reproduce the fault. Perhaps we can trigger this case artificially somehow from the test tools. I haven't sorted out a way to do that yet though. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/160556566659.73229.15694973114605301063.stgit@john-XPS-13-9370 --- net/ipv4/tcp_bpf.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 37f4cb2bba5c..8e950b0bfabc 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -15,8 +15,8 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, { struct iov_iter *iter = &msg->msg_iter; int peek = flags & MSG_PEEK; - int i, ret, copied = 0; struct sk_msg *msg_rx; + int i, copied = 0; msg_rx = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list); @@ -37,11 +37,9 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, page = sg_page(sge); if (copied + copy > len) copy = len - copied; - ret = copy_page_to_iter(page, sge->offset, copy, iter); - if (ret != copy) { - msg_rx->sg.start = i; - return -EFAULT; - } + copy = copy_page_to_iter(page, sge->offset, copy, iter); + if (!copy) + return copied ? copied : -EFAULT; copied += copy; if (likely(!peek)) { @@ -56,6 +54,11 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, put_page(page); } } else { + /* Lets not optimize peek case if copy_page_to_iter + * didn't copy the entire length lets just break. + */ + if (copy != sge->length) + return copied; sk_msg_iter_var_next(i); } -- cgit v1.2.3 From 36cd0e696a832a00247fca522034703566ac8885 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 16 Nov 2020 14:28:06 -0800 Subject: bpf, sockmap: Ensure SO_RCVBUF memory is observed on ingress redirect Fix sockmap sk_skb programs so that they observe sk_rcvbuf limits. This allows users to tune SO_RCVBUF and sockmap will honor them. We can refactor the if(charge) case out in later patches. But, keep this fix to the point. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Suggested-by: Jakub Sitnicki Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/160556568657.73229.8404601585878439060.stgit@john-XPS-13-9370 --- net/core/skmsg.c | 20 ++++++++++++++++---- net/ipv4/tcp_bpf.c | 3 ++- 2 files changed, 18 insertions(+), 5 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 654182ecf87b..fe44280c033e 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -170,10 +170,12 @@ static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i, struct scatterlist *sge = sk_msg_elem(msg, i); u32 len = sge->length; - if (charge) - sk_mem_uncharge(sk, len); - if (!msg->skb) + /* When the skb owns the memory we free it from consume_skb path. */ + if (!msg->skb) { + if (charge) + sk_mem_uncharge(sk, len); put_page(sg_page(sge)); + } memset(sge, 0, sizeof(*sge)); return len; } @@ -403,6 +405,9 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) int copied = 0, num_sge; struct sk_msg *msg; + if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) + return -EAGAIN; + msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); if (unlikely(!msg)) return -EAGAIN; @@ -418,7 +423,14 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) return num_sge; } - sk_mem_charge(sk, skb->len); + /* This will transition ownership of the data from the socket where + * the BPF program was run initiating the redirect to the socket + * we will eventually receive this data on. The data will be released + * from skb_consume found in __tcp_bpf_recvmsg() after its been copied + * into user buffers. + */ + skb_set_owner_r(skb, sk); + copied = skb->len; msg->sg.start = 0; msg->sg.size = copied; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 8e950b0bfabc..bc7d2a586e18 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -45,7 +45,8 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, if (likely(!peek)) { sge->offset += copy; sge->length -= copy; - sk_mem_uncharge(sk, copy); + if (!msg_rx->skb) + sk_mem_uncharge(sk, copy); msg_rx->sg.size -= copy; if (!sge->length) { -- cgit v1.2.3 From 70796fb751f1d34cc650e640572a174faf009cd4 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 16 Nov 2020 14:28:26 -0800 Subject: bpf, sockmap: Use truesize with sk_rmem_schedule() We use skb->size with sk_rmem_scheduled() which is not correct. Instead use truesize to align with socket and tcp stack usage of sk_rmem_schedule. Suggested-by: Daniel Borkman Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/160556570616.73229.17003722112077507863.stgit@john-XPS-13-9370 --- net/core/skmsg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index fe44280c033e..d09426ce4af3 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -411,7 +411,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); if (unlikely(!msg)) return -EAGAIN; - if (!sk_rmem_schedule(sk, skb, skb->len)) { + if (!sk_rmem_schedule(sk, skb, skb->truesize)) { kfree(msg); return -EAGAIN; } -- cgit v1.2.3 From 6fa9201a898983da731fca068bb4b5c941537588 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 16 Nov 2020 14:28:46 -0800 Subject: bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self If a socket redirects to itself and it is under memory pressure it is possible to get a socket stuck so that recv() returns EAGAIN and the socket can not advance for some time. This happens because when redirecting a skb to the same socket we received the skb on we first check if it is OK to enqueue the skb on the receiving socket by checking memory limits. But, if the skb is itself the object holding the memory needed to enqueue the skb we will keep retrying from kernel side and always fail with EAGAIN. Then userspace will get a recv() EAGAIN error if there are no skbs in the psock ingress queue. This will continue until either some skbs get kfree'd causing the memory pressure to reduce far enough that we can enqueue the pending packet or the socket is destroyed. In some cases its possible to get a socket stuck for a noticeable amount of time if the socket is only receiving skbs from sk_skb verdict programs. To reproduce I make the socket memory limits ridiculously low so sockets are always under memory pressure. More often though if under memory pressure it looks like a spurious EAGAIN error on user space side causing userspace to retry and typically enough has moved on the memory side that it works. To fix skip memory checks and skb_orphan if receiving on the same sock as already assigned. For SK_PASS cases this is easy, its always the same socket so we can just omit the orphan/set_owner pair. For backlog cases we need to check skb->sk and decide if the orphan and set_owner pair are needed. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370 --- net/core/skmsg.c | 72 +++++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 53 insertions(+), 19 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index d09426ce4af3..9aed5a2c7c5b 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -399,38 +399,38 @@ out: } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); -static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, + struct sk_buff *skb) { - struct sock *sk = psock->sk; - int copied = 0, num_sge; struct sk_msg *msg; if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) - return -EAGAIN; + return NULL; + + if (!sk_rmem_schedule(sk, skb, skb->truesize)) + return NULL; msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); if (unlikely(!msg)) - return -EAGAIN; - if (!sk_rmem_schedule(sk, skb, skb->truesize)) { - kfree(msg); - return -EAGAIN; - } + return NULL; sk_msg_init(msg); - num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); + return msg; +} + +static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, + struct sk_psock *psock, + struct sock *sk, + struct sk_msg *msg) +{ + int num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); + int copied; + if (unlikely(num_sge < 0)) { kfree(msg); return num_sge; } - /* This will transition ownership of the data from the socket where - * the BPF program was run initiating the redirect to the socket - * we will eventually receive this data on. The data will be released - * from skb_consume found in __tcp_bpf_recvmsg() after its been copied - * into user buffers. - */ - skb_set_owner_r(skb, sk); - copied = skb->len; msg->sg.start = 0; msg->sg.size = copied; @@ -442,6 +442,40 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) return copied; } +static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +{ + struct sock *sk = psock->sk; + struct sk_msg *msg; + + msg = sk_psock_create_ingress_msg(sk, skb); + if (!msg) + return -EAGAIN; + + /* This will transition ownership of the data from the socket where + * the BPF program was run initiating the redirect to the socket + * we will eventually receive this data on. The data will be released + * from skb_consume found in __tcp_bpf_recvmsg() after its been copied + * into user buffers. + */ + skb_set_owner_r(skb, sk); + return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); +} + +/* Puts an skb on the ingress queue of the socket already assigned to the + * skb. In this case we do not need to check memory limits or skb_set_owner_r + * because the skb is already accounted for here. + */ +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb) +{ + struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); + struct sock *sk = psock->sk; + + if (unlikely(!msg)) + return -EAGAIN; + sk_msg_init(msg); + return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); +} + static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len, bool ingress) { @@ -801,7 +835,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, * retrying later from workqueue. */ if (skb_queue_empty(&psock->ingress_skb)) { - err = sk_psock_skb_ingress(psock, skb); + err = sk_psock_skb_ingress_self(psock, skb); } if (err < 0) { skb_queue_tail(&psock->ingress_skb, skb); -- cgit v1.2.3 From 2443ca66676d50a4eb3305c236bccd84a9828ce2 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 16 Nov 2020 14:29:08 -0800 Subject: bpf, sockmap: Handle memory acct if skb_verdict prog redirects to self If the skb_verdict_prog redirects an skb knowingly to itself, fix your BPF program this is not optimal and an abuse of the API please use SK_PASS. That said there may be cases, such as socket load balancing, where picking the socket is hashed based or otherwise picks the same socket it was received on in some rare cases. If this happens we don't want to confuse userspace giving them an EAGAIN error if we can avoid it. To avoid double accounting in these cases. At the moment even if the skb has already been charged against the sockets rcvbuf and forward alloc we check it again and do set_owner_r() causing it to be orphaned and recharged. For one this is useless work, but more importantly we can have a case where the skb could be put on the ingress queue, but because we are under memory pressure we return EAGAIN. The trouble here is the skb has already been accounted for so any rcvbuf checks include the memory associated with the packet already. This rolls up and can result in unnecessary EAGAIN errors in userspace read() calls. Fix by doing an unlikely check and skipping checks if skb->sk == sk. Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/160556574804.73229.11328201020039674147.stgit@john-XPS-13-9370 --- net/core/skmsg.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 9aed5a2c7c5b..514bc9f6f8ae 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -442,11 +442,19 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, return copied; } +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb); + static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) { struct sock *sk = psock->sk; struct sk_msg *msg; + /* If we are receiving on the same sock skb->sk is already assigned, + * skip memory accounting and owner transition seeing it already set + * correctly. + */ + if (unlikely(skb->sk == sk)) + return sk_psock_skb_ingress_self(psock, skb); msg = sk_psock_create_ingress_msg(sk, skb); if (!msg) return -EAGAIN; -- cgit v1.2.3 From 4363023d2668e621b0743db351a9555d6e6ea57e Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 16 Nov 2020 14:29:28 -0800 Subject: bpf, sockmap: Avoid failures from skb_to_sgvec when skb has frag_list When skb has a frag_list its possible for skb_to_sgvec() to fail. This happens when the scatterlist has fewer elements to store pages than would be needed for the initial skb plus any of its frags. This case appears rare, but is possible when running an RX parser/verdict programs exposed to the internet. Currently, when this happens we throw an error, break the pipe, and kfree the msg. This effectively breaks the application or forces it to do a retry. Lets catch this case and handle it by doing an skb_linearize() on any skb we receive with frags. At this point skb_to_sgvec should not fail because the failing conditions would require frags to be in place. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/160556576837.73229.14800682790808797635.stgit@john-XPS-13-9370 --- net/core/skmsg.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 514bc9f6f8ae..25cdbb20f3a0 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -423,9 +423,16 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, struct sock *sk, struct sk_msg *msg) { - int num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); - int copied; + int num_sge, copied; + /* skb linearize may fail with ENOMEM, but lets simply try again + * later if this happens. Under memory pressure we don't want to + * drop the skb. We need to linearize the skb so that the mapping + * in skb_to_sgvec can not error. + */ + if (skb_linearize(skb)) + return -EAGAIN; + num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); if (unlikely(num_sge < 0)) { kfree(msg); return num_sge; -- cgit v1.2.3 From ee415d73dcc24caef7f6bbf292dcc365613d2188 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Sun, 15 Nov 2020 14:06:23 +0200 Subject: tools/testing/scatterlist: Fix test to compile and run Add missing define of ALIGN_DOWN to make the test build and run. In addition, __sg_alloc_table_from_pages now support unaligned maximum segment, so adapt the test result accordingly. Fixes: 07da1223ec93 ("lib/scatterlist: Add support in dynamic allocation of SG table from pages") Link: https://lore.kernel.org/r/20201115120623.139113-1-leon@kernel.org Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- tools/testing/scatterlist/linux/mm.h | 1 + tools/testing/scatterlist/main.c | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h index 6ae907f375d2..f9a12005fcea 100644 --- a/tools/testing/scatterlist/linux/mm.h +++ b/tools/testing/scatterlist/linux/mm.h @@ -33,6 +33,7 @@ typedef unsigned long dma_addr_t; #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) +#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c index b2c7e9f7b8d3..f561aed7c657 100644 --- a/tools/testing/scatterlist/main.c +++ b/tools/testing/scatterlist/main.c @@ -52,9 +52,9 @@ int main(void) { const unsigned int sgmax = SCATTERLIST_MAX_SEGMENT; struct test *test, tests[] = { - { -EINVAL, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 }, { -EINVAL, 1, pfn(0), PAGE_SIZE, 0, 1 }, - { -EINVAL, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 }, + { 0, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 }, + { 0, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 }, { 0, 1, pfn(0), PAGE_SIZE, sgmax, 1 }, { 0, 1, pfn(0), 1, sgmax, 1 }, { 0, 2, pfn(0, 1), 2 * PAGE_SIZE, sgmax, 1 }, -- cgit v1.2.3 From e33de7c5317e2827b2ba6fd120a505e9eb727b05 Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Mon, 16 Nov 2020 16:20:18 +0800 Subject: inet_diag: Fix error path to cancel the meseage in inet_req_diag_fill() nlmsg_cancel() needs to be called in the error path of inet_req_diag_fill to cancel the message. Fixes: d545caca827b ("net: inet: diag: expose the socket mark to privileged processes.") Reported-by: Hulk Robot Signed-off-by: Wang Hai Link: https://lore.kernel.org/r/20201116082018.16496-1-wanghai38@huawei.com Signed-off-by: Jakub Kicinski --- net/ipv4/inet_diag.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 366a4507b5a3..93474b1bea4e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -479,8 +479,10 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, r->idiag_inode = 0; if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, - inet_rsk(reqsk)->ir_mark)) + inet_rsk(reqsk)->ir_mark)) { + nlmsg_cancel(skb, nlh); return -EMSGSIZE; + } nlmsg_end(skb, nlh); return 0; -- cgit v1.2.3 From 93be52612431e71ee8cb980ef11468997857e4c4 Mon Sep 17 00:00:00 2001 From: Dmitry Bogdanov Date: Mon, 16 Nov 2020 16:29:44 +0300 Subject: qed: fix ILT configuration of SRC block The code refactoring of ILT configuration was not complete, the old unused variables were used for the SRC block. That could lead to the memory corruption by HW when rx filters are configured. This patch completes that refactoring. Fixes: 8a52bbab39c9 (qed: Debug feature: ilt and mdump) Signed-off-by: Igor Russkikh Signed-off-by: Ariel Elior Signed-off-by: Dmitry Bogdanov Link: https://lore.kernel.org/r/20201116132944.2055-1-dbogdanov@marvell.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/qlogic/qed/qed_cxt.c | 4 ++-- drivers/net/ethernet/qlogic/qed/qed_cxt.h | 3 --- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 0e4cd8890cff..0a22f8ce9a2c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -1647,9 +1647,9 @@ static void qed_src_init_pf(struct qed_hwfn *p_hwfn) ilog2(rounded_conn_num)); STORE_RT_REG_AGG(p_hwfn, SRC_REG_FIRSTFREE_RT_OFFSET, - p_hwfn->p_cxt_mngr->first_free); + p_hwfn->p_cxt_mngr->src_t2.first_free); STORE_RT_REG_AGG(p_hwfn, SRC_REG_LASTFREE_RT_OFFSET, - p_hwfn->p_cxt_mngr->last_free); + p_hwfn->p_cxt_mngr->src_t2.last_free); } /* Timers PF */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h index 8b64495f8745..056e79620a0e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h @@ -326,9 +326,6 @@ struct qed_cxt_mngr { /* SRC T2 */ struct qed_src_t2 src_t2; - u32 t2_num_pages; - u64 first_free; - u64 last_free; /* total number of SRQ's for this hwfn */ u32 srq_count; -- cgit v1.2.3 From c09c8a27b9baa417864b9adc3228b10ae5eeec93 Mon Sep 17 00:00:00 2001 From: Florian Klink Date: Sun, 15 Nov 2020 23:45:09 +0100 Subject: ipv4: use IS_ENABLED instead of ifdef Checking for ifdef CONFIG_x fails if CONFIG_x=m. Use IS_ENABLED instead, which is true for both built-ins and modules. Otherwise, a > ip -4 route add 1.2.3.4/32 via inet6 fe80::2 dev eth1 fails with the message "Error: IPv6 support not enabled in kernel." if CONFIG_IPV6 is `m`. In the spirit of b8127113d01e53adba15b41aefd37b90ed83d631. Fixes: d15662682db2 ("ipv4: Allow ipv6 gateway with ipv4 routes") Cc: Kim Phillips Signed-off-by: Florian Klink Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20201115224509.2020651-1-flokli@flokli.de Signed-off-by: Jakub Kicinski --- net/ipv4/fib_frontend.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 86a23e4a6a50..b87140a1fa28 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -696,7 +696,7 @@ int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, cfg->fc_gw4 = *((__be32 *)via->rtvia_addr); break; case AF_INET6: -#ifdef CONFIG_IPV6 +#if IS_ENABLED(CONFIG_IPV6) if (alen != sizeof(struct in6_addr)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA"); return -EINVAL; -- cgit v1.2.3 From cd81acc600a9684ea4b4d25a47900d38a3890eab Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 17 Nov 2020 23:56:17 +1000 Subject: powerpc/64s/exception: KVM Fix for host DSI being taken in HPT guest MMU context Commit 2284ffea8f0c ("powerpc/64s/exception: Only test KVM in SRR interrupts when PR KVM is supported") removed KVM guest tests from interrupts that do not set HV=1, when PR-KVM is not configured. This is wrong for HV-KVM HPT guest MMIO emulation case which attempts to load the faulting instruction word with MSR[DR]=1 and MSR[HV]=1 with the guest MMU context loaded. This can cause host DSI, DSLB interrupts which must test for KVM guest. Restore this and add a comment. Fixes: 2284ffea8f0c ("powerpc/64s/exception: Only test KVM in SRR interrupts when PR KVM is supported") Cc: stable@vger.kernel.org # v5.7+ Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201117135617.3521127-1-npiggin@gmail.com --- arch/powerpc/kernel/exceptions-64s.S | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 07d64883c0b5..8e6b2cc8db67 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1410,6 +1410,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) * If none is found, do a Linux page fault. Linux page faults can happen in * kernel mode due to user copy operations of course. * + * KVM: The KVM HDSI handler may perform a load with MSR[DR]=1 in guest + * MMU context, which may cause a DSI in the host, which must go to the + * KVM handler. MSR[IR] is not enabled, so the real-mode handler will + * always be used regardless of AIL setting. + * * - Radix MMU * The hardware loads from the Linux page table directly, so a fault goes * immediately to Linux page fault. @@ -1420,10 +1425,8 @@ INT_DEFINE_BEGIN(data_access) IVEC=0x300 IDAR=1 IDSISR=1 -#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE IKVM_SKIP=1 IKVM_REAL=1 -#endif INT_DEFINE_END(data_access) EXC_REAL_BEGIN(data_access, 0x300, 0x80) @@ -1462,6 +1465,8 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) * ppc64_bolted_size (first segment). The kernel handler must avoid stomping * on user-handler data structures. * + * KVM: Same as 0x300, DSLB must test for KVM guest. + * * A dedicated save area EXSLB is used (XXX: but it actually need not be * these days, we could use EXGEN). */ @@ -1470,10 +1475,8 @@ INT_DEFINE_BEGIN(data_access_slb) IAREA=PACA_EXSLB IRECONCILE=0 IDAR=1 -#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE IKVM_SKIP=1 IKVM_REAL=1 -#endif INT_DEFINE_END(data_access_slb) EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80) -- cgit v1.2.3 From 78aec9bb1f3c79e4570eb50260d6320063f823a2 Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Wed, 21 Oct 2020 23:12:20 +0200 Subject: ARC: bitops: Remove unecessary operation and value The 1-bit shift rotation to the left on x variable located on 4 last if statement can be removed because the computed value is will not be used afront. Signed-off-by: Gustavo Pimentel Signed-off-by: Vineet Gupta --- arch/arc/include/asm/bitops.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h index c6606f4d20d6..fb98440c0bd4 100644 --- a/arch/arc/include/asm/bitops.h +++ b/arch/arc/include/asm/bitops.h @@ -243,10 +243,8 @@ static inline int constant_fls(unsigned int x) x <<= 2; r -= 2; } - if (!(x & 0x80000000u)) { - x <<= 1; + if (!(x & 0x80000000u)) r -= 1; - } return r; } -- cgit v1.2.3 From 5f840df591a9554e4e1355ef1f8946bc2120ca9f Mon Sep 17 00:00:00 2001 From: Flavio Suligoi Date: Mon, 9 Nov 2020 14:21:30 +0100 Subject: ARC: mm: fix spelling mistakes Signed-off-by: Flavio Suligoi Signed-off-by: Vineet Gupta --- arch/arc/mm/tlb.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index c340acd989a0..9bb3c24f3677 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -30,14 +30,14 @@ * -Changes related to MMU v2 (Rel 4.8) * * Vineetg: Aug 29th 2008 - * -In TLB Flush operations (Metal Fix MMU) there is a explict command to + * -In TLB Flush operations (Metal Fix MMU) there is a explicit command to * flush Micro-TLBS. If TLB Index Reg is invalid prior to TLBIVUTLB cmd, * it fails. Thus need to load it with ANY valid value before invoking * TLBIVUTLB cmd * * Vineetg: Aug 21th 2008: * -Reduced the duration of IRQ lockouts in TLB Flush routines - * -Multiple copies of TLB erase code seperated into a "single" function + * -Multiple copies of TLB erase code separated into a "single" function * -In TLB Flush routines, interrupt disabling moved UP to retrieve ASID * in interrupt-safe region. * @@ -66,7 +66,7 @@ * * Although J-TLB is 2 way set assoc, ARC700 caches J-TLB into uTLBS which has * much higher associativity. u-D-TLB is 8 ways, u-I-TLB is 4 ways. - * Given this, the thrasing problem should never happen because once the 3 + * Given this, the thrashing problem should never happen because once the 3 * J-TLB entries are created (even though 3rd will knock out one of the prev * two), the u-D-TLB and u-I-TLB will have what is required to accomplish memcpy * @@ -127,7 +127,7 @@ static void utlb_invalidate(void) * There was however an obscure hardware bug, where uTLB flush would * fail when a prior probe for J-TLB (both totally unrelated) would * return lkup err - because the entry didn't exist in MMU. - * The Workround was to set Index reg with some valid value, prior to + * The Workaround was to set Index reg with some valid value, prior to * flush. This was fixed in MMU v3 */ unsigned int idx; @@ -272,7 +272,7 @@ noinline void local_flush_tlb_all(void) } /* - * Flush the entrie MM for userland. The fastest way is to move to Next ASID + * Flush the entire MM for userland. The fastest way is to move to Next ASID */ noinline void local_flush_tlb_mm(struct mm_struct *mm) { @@ -303,7 +303,7 @@ noinline void local_flush_tlb_mm(struct mm_struct *mm) * Difference between this and Kernel Range Flush is * -Here the fastest way (if range is too large) is to move to next ASID * without doing any explicit Shootdown - * -In case of kernel Flush, entry has to be shot down explictly + * -In case of kernel Flush, entry has to be shot down explicitly */ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) @@ -620,7 +620,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, * Super Page size is configurable in hardware (4K to 16M), but fixed once * RTL builds. * - * The exact THP size a Linx configuration will support is a function of: + * The exact THP size a Linux configuration will support is a function of: * - MMU page size (typical 8K, RTL fixed) * - software page walker address split between PGD:PTE:PFN (typical * 11:8:13, but can be changed with 1 line) @@ -698,7 +698,7 @@ void local_flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, #endif -/* Read the Cache Build Confuration Registers, Decode them and save into +/* Read the Cache Build Configuration Registers, Decode them and save into * the cpuinfo structure for later use. * No Validation is done here, simply read/convert the BCRs */ @@ -803,13 +803,13 @@ void arc_mmu_init(void) pr_info("%s", arc_mmu_mumbojumbo(0, str, sizeof(str))); /* - * Can't be done in processor.h due to header include depenedencies + * Can't be done in processor.h due to header include dependencies */ BUILD_BUG_ON(!IS_ALIGNED((CONFIG_ARC_KVADDR_SIZE << 20), PMD_SIZE)); /* * stack top size sanity check, - * Can't be done in processor.h due to header include depenedencies + * Can't be done in processor.h due to header include dependencies */ BUILD_BUG_ON(!IS_ALIGNED(STACK_TOP, PMD_SIZE)); @@ -881,7 +881,7 @@ void arc_mmu_init(void) * the duplicate one. * -Knob to be verbose abt it.(TODO: hook them up to debugfs) */ -volatile int dup_pd_silent; /* Be slient abt it or complain (default) */ +volatile int dup_pd_silent; /* Be silent abt it or complain (default) */ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, struct pt_regs *regs) @@ -948,7 +948,7 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, /*********************************************************************** * Diagnostic Routines - * -Called from Low Level TLB Hanlders if things don;t look good + * -Called from Low Level TLB Handlers if things don;t look good **********************************************************************/ #ifdef CONFIG_ARC_DBG_TLB_PARANOIA -- cgit v1.2.3 From e42404fa10fd11fe72d0a0e149a321d10e577715 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 6 Nov 2020 16:59:27 -0800 Subject: ARC: stack unwinding: don't assume non-current task is sleeping To start stack unwinding (SP, PC and BLINK) are needed. When the explicit execution context (pt_regs etc) is not available, unwinder assumes the task is sleeping (in __switch_to()) and fetches SP and BLINK from kernel mode stack. But this assumption is not true, specially in a SMP system, when top runs on 1 core, there may be active running processes on all cores. So when unwinding non courrent tasks, ensure they are NOT running. And while at it, handle the self unwinding case explicitly. This came out of investigation of a customer reported hang with rcutorture+top Link: https://github.com/foss-for-synopsys-dwc-arc-processors/linux/issues/31 Signed-off-by: Vineet Gupta --- arch/arc/kernel/stacktrace.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index b23986f98450..b2557f581ea8 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -38,15 +38,15 @@ #ifdef CONFIG_ARC_DW2_UNWIND -static void seed_unwind_frame_info(struct task_struct *tsk, - struct pt_regs *regs, - struct unwind_frame_info *frame_info) +static int +seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs, + struct unwind_frame_info *frame_info) { /* * synchronous unwinding (e.g. dump_stack) * - uses current values of SP and friends */ - if (tsk == NULL && regs == NULL) { + if (regs == NULL && (tsk == NULL || tsk == current)) { unsigned long fp, sp, blink, ret; frame_info->task = current; @@ -65,11 +65,15 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->call_frame = 0; } else if (regs == NULL) { /* - * Asynchronous unwinding of sleeping task - * - Gets SP etc from task's pt_regs (saved bottom of kernel - * mode stack of task) + * Asynchronous unwinding of a likely sleeping task + * - first ensure it is actually sleeping + * - if so, it will be in __switch_to, kernel mode SP of task + * is safe-kept and BLINK at a well known location in there */ + if (tsk->state == TASK_RUNNING) + return -1; + frame_info->task = tsk; frame_info->regs.r27 = TSK_K_FP(tsk); @@ -103,6 +107,8 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->regs.r63 = regs->ret; frame_info->call_frame = 0; } + + return 0; } #endif @@ -116,7 +122,8 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, unsigned int address; struct unwind_frame_info frame_info; - seed_unwind_frame_info(tsk, regs, &frame_info); + if (seed_unwind_frame_info(tsk, regs, &frame_info)) + return 0; while (1) { address = UNW_PC(&frame_info); -- cgit v1.2.3 From f737561c709667013d832316dd3198a7fe3d1260 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 6 Nov 2020 17:37:34 -0800 Subject: ARC: stack unwinding: reorganize how initial register state setup This is a non-functional change, if anything a better fall-back handling. Signed-off-by: Vineet Gupta --- arch/arc/kernel/stacktrace.c | 37 ++++++++++++++++++------------------- 1 file changed, 18 insertions(+), 19 deletions(-) diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index b2557f581ea8..f73da203b170 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -42,11 +42,23 @@ static int seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs, struct unwind_frame_info *frame_info) { - /* - * synchronous unwinding (e.g. dump_stack) - * - uses current values of SP and friends - */ - if (regs == NULL && (tsk == NULL || tsk == current)) { + if (regs) { + /* + * Asynchronous unwinding of intr/exception + * - Just uses the pt_regs passed + */ + frame_info->task = tsk; + + frame_info->regs.r27 = regs->fp; + frame_info->regs.r28 = regs->sp; + frame_info->regs.r31 = regs->blink; + frame_info->regs.r63 = regs->ret; + frame_info->call_frame = 0; + } else if (tsk == NULL || tsk == current) { + /* + * synchronous unwinding (e.g. dump_stack) + * - uses current values of SP and friends + */ unsigned long fp, sp, blink, ret; frame_info->task = current; @@ -63,7 +75,7 @@ seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs, frame_info->regs.r31 = blink; frame_info->regs.r63 = ret; frame_info->call_frame = 0; - } else if (regs == NULL) { + } else { /* * Asynchronous unwinding of a likely sleeping task * - first ensure it is actually sleeping @@ -94,20 +106,7 @@ seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs, frame_info->regs.r28 += 60; frame_info->call_frame = 0; - } else { - /* - * Asynchronous unwinding of intr/exception - * - Just uses the pt_regs passed - */ - frame_info->task = tsk; - - frame_info->regs.r27 = regs->fp; - frame_info->regs.r28 = regs->sp; - frame_info->regs.r31 = regs->blink; - frame_info->regs.r63 = regs->ret; - frame_info->call_frame = 0; } - return 0; } -- cgit v1.2.3 From 957a1ea3599210e9996777a734ea5284eaef75c7 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Fri, 6 Nov 2020 15:22:31 +0100 Subject: drm/sun4i: backend: Fix probe failure with multiple backends Commit e0d072782c73 ("dma-mapping: introduce DMA range map, supplanting dma_pfn_offset") introduced a regression in our code since the second backed to probe will now get -EINVAL back from dma_direct_set_offset and will prevent the entire DRM device from probing. Ignore -EINVAL as a temporary measure to get it back working, before removing that call entirely. Fixes: e0d072782c73 ("dma-mapping: introduce DMA range map, supplanting dma_pfn_offset") Signed-off-by: Maxime Ripard Reviewed-by: Chen-Yu Tsai Reviewed-by: Christoph Hellwig Acked-by: Daniel Vetter --- drivers/gpu/drm/sun4i/sun4i_backend.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c index 77497b45f9a2..55960cbb1019 100644 --- a/drivers/gpu/drm/sun4i/sun4i_backend.c +++ b/drivers/gpu/drm/sun4i/sun4i_backend.c @@ -814,9 +814,15 @@ static int sun4i_backend_bind(struct device *dev, struct device *master, * * XXX(hch): this has no business in a driver and needs to move * to the device tree. + * + * If we have two subsequent calls to dma_direct_set_offset + * returns -EINVAL. Unfortunately, this happens when we have two + * backends in the system, and will result in the driver + * reporting an error while it has been setup properly before. + * Ignore EINVAL, but it should really be removed eventually. */ ret = dma_direct_set_offset(drm->dev, PHYS_OFFSET, 0, SZ_4G); - if (ret) + if (ret && ret != -EINVAL) return ret; } -- cgit v1.2.3 From 470e14c00c63752466ac44de392f584dfdddd82e Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Sun, 15 Nov 2020 17:30:22 +0100 Subject: can: kvaser_pciefd: Fix KCAN bittiming limits Use correct bittiming limits for the KCAN CAN controller. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20201115163027.16851-1-jimmyassarsson@gmail.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 6f766918211a..72acd1ba162d 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -287,12 +287,12 @@ struct kvaser_pciefd_tx_packet { static const struct can_bittiming_const kvaser_pciefd_bittiming_const = { .name = KVASER_PCIEFD_DRV_NAME, .tseg1_min = 1, - .tseg1_max = 255, + .tseg1_max = 512, .tseg2_min = 1, .tseg2_max = 32, .sjw_max = 16, .brp_min = 1, - .brp_max = 4096, + .brp_max = 8192, .brp_inc = 1, }; -- cgit v1.2.3 From d003868d7f8579838ed58b6429af91844039b6f8 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Sun, 15 Nov 2020 17:30:23 +0100 Subject: can: kvaser_usb: kvaser_usb_hydra: Fix KCAN bittiming limits Use correct bittiming limits for the KCAN CAN controller. Fixes: aec5fb2268b7 ("can: kvaser_usb: Add support for Kvaser USB hydra family") Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20201115163027.16851-2-jimmyassarsson@gmail.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 7ab87a758754..218fadc91155 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -367,7 +367,7 @@ static const struct can_bittiming_const kvaser_usb_hydra_kcan_bittiming_c = { .tseg2_max = 32, .sjw_max = 16, .brp_min = 1, - .brp_max = 4096, + .brp_max = 8192, .brp_inc = 1, }; -- cgit v1.2.3 From 860aaabac8235cfde10fe556aa82abbbe3117888 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 17 Nov 2020 21:23:34 +0100 Subject: x86/dumpstack: Do not try to access user space code of other tasks sysrq-t ends up invoking show_opcodes() for each task which tries to access the user space code of other processes, which is obviously bogus. It either manages to dump where the foreign task's regs->ip points to in a valid mapping of the current task or triggers a pagefault and prints "Code: Bad RIP value.". Both is just wrong. Add a safeguard in copy_code() and check whether the @regs pointer matches currents pt_regs. If not, do not even try to access it. While at it, add commentary why using copy_from_user_nmi() is safe in copy_code() even if the function name suggests otherwise. Reported-by: Oleg Nesterov Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Acked-by: Oleg Nesterov Tested-by: Borislav Petkov Link: https://lkml.kernel.org/r/20201117202753.667274723@linutronix.de --- arch/x86/kernel/dumpstack.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 25c06b67e7e0..97aa900386cb 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -78,6 +78,9 @@ static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, if (!user_mode(regs)) return copy_from_kernel_nofault(buf, (u8 *)src, nbytes); + /* The user space code from other tasks cannot be accessed. */ + if (regs != task_pt_regs(current)) + return -EPERM; /* * Make sure userspace isn't trying to trick us into dumping kernel * memory by pointing the userspace instruction pointer at it. @@ -85,6 +88,12 @@ static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX)) return -EINVAL; + /* + * Even if named copy_from_user_nmi() this can be invoked from + * other contexts and will not try to resolve a pagefault, which is + * the correct thing to do here as this code can be called from any + * context. + */ return copy_from_user_nmi(buf, (void __user *)src, nbytes); } @@ -115,13 +124,19 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) u8 opcodes[OPCODE_BUFSIZE]; unsigned long prologue = regs->ip - PROLOGUE_SIZE; - if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { - printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", - loglvl, prologue); - } else { + switch (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { + case 0: printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes, opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1); + break; + case -EPERM: + /* No access to the user space stack of other tasks. Ignore. */ + break; + default: + printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", + loglvl, prologue); + break; } } -- cgit v1.2.3 From 4c80d05714d347405865802b7098f1c97362cbef Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 17 Nov 2020 20:00:33 +0100 Subject: s390/uv: handle destroy page legacy interface Older firmware can return rc=0x107 rrc=0xd for destroy page if the page is already non-secure. This should be handled like a success as already done by newer firmware. Signed-off-by: Christian Borntraeger Fixes: 1a80b54d1ce1 ("s390/uv: add destroy page call") Reviewed-by: David Hildenbrand Acked-by: Cornelia Huck Reviewed-by: Janosch Frank --- arch/s390/kernel/uv.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 14bd9d58edc9..883bfed9f5c2 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -129,8 +129,15 @@ int uv_destroy_page(unsigned long paddr) .paddr = paddr }; - if (uv_call(0, (u64)&uvcb)) + if (uv_call(0, (u64)&uvcb)) { + /* + * Older firmware uses 107/d as an indication of a non secure + * page. Let us emulate the newer variant (no-op). + */ + if (uvcb.header.rc == 0x107 && uvcb.header.rrc == 0xd) + return 0; return -EINVAL; + } return 0; } -- cgit v1.2.3 From 735931f9a51ab09cf795721b37696b420484625f Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 18 Nov 2020 08:44:12 +0100 Subject: MAINTAINERS: add uv.c also to KVM/s390 Most changes in uv.c are related to KVM. Involve also the KVM team regarding changes to uv.c. Signed-off-by: Christian Borntraeger Reviewed-by: David Hildenbrand Acked-by: Cornelia Huck Acked-by: Heiko Carstens --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index e73636b75f29..06116d892a4b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9674,6 +9674,7 @@ F: Documentation/virt/kvm/s390* F: arch/s390/include/asm/gmap.h F: arch/s390/include/asm/kvm* F: arch/s390/include/uapi/asm/kvm* +F: arch/s390/kernel/uv.c F: arch/s390/kvm/ F: arch/s390/mm/gmap.c F: tools/testing/selftests/kvm/*/s390x/ -- cgit v1.2.3 From 7e4be1290a38b3dd4a77cdf4565c9ffe7e620013 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 13 Nov 2020 13:16:31 +0300 Subject: dmaengine: fix error codes in channel_register() The error codes were not set on some of these error paths. Also the error handling was more confusing than it needed to be so I cleaned it up and shuffled it around a bit. Fixes: d2fb0a043838 ("dmaengine: break out channel registration") Signed-off-by: Dan Carpenter Reviewed-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20201113101631.GE168908@mwanda Signed-off-by: Vinod Koul --- drivers/dma/dmaengine.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 7974fa0400d8..962cbb5e5f7f 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -1039,16 +1039,15 @@ static int get_dma_id(struct dma_device *device) static int __dma_async_device_channel_register(struct dma_device *device, struct dma_chan *chan) { - int rc = 0; + int rc; chan->local = alloc_percpu(typeof(*chan->local)); if (!chan->local) - goto err_out; + return -ENOMEM; chan->dev = kzalloc(sizeof(*chan->dev), GFP_KERNEL); if (!chan->dev) { - free_percpu(chan->local); - chan->local = NULL; - goto err_out; + rc = -ENOMEM; + goto err_free_local; } /* @@ -1061,7 +1060,8 @@ static int __dma_async_device_channel_register(struct dma_device *device, if (chan->chan_id < 0) { pr_err("%s: unable to alloc ida for chan: %d\n", __func__, chan->chan_id); - goto err_out; + rc = chan->chan_id; + goto err_free_dev; } chan->dev->device.class = &dma_devclass; @@ -1082,9 +1082,10 @@ static int __dma_async_device_channel_register(struct dma_device *device, mutex_lock(&device->chan_mutex); ida_free(&device->chan_ida, chan->chan_id); mutex_unlock(&device->chan_mutex); - err_out: - free_percpu(chan->local); + err_free_dev: kfree(chan->dev); + err_free_local: + free_percpu(chan->local); return rc; } -- cgit v1.2.3 From 4d213e76a359e540ca786ee937da7f35faa8e5f8 Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Tue, 10 Nov 2020 15:19:08 +0800 Subject: iommu/vt-d: Avoid panic if iommu init fails in tboot system "intel_iommu=off" command line is used to disable iommu but iommu is force enabled in a tboot system for security reason. However for better performance on high speed network device, a new option "intel_iommu=tboot_noforce" is introduced to disable the force on. By default kernel should panic if iommu init fail in tboot for security reason, but it's unnecessory if we use "intel_iommu=tboot_noforce,off". Fix the code setting force_on and move intel_iommu_tboot_noforce from tboot code to intel iommu code. Fixes: 7304e8f28bb2 ("iommu/vt-d: Correctly disable Intel IOMMU force on") Signed-off-by: Zhenzhong Duan Tested-by: Lukasz Hawrylko Acked-by: Lu Baolu Link: https://lore.kernel.org/r/20201110071908.3133-1-zhenzhong.duan@gmail.com Signed-off-by: Will Deacon --- arch/x86/kernel/tboot.c | 3 --- drivers/iommu/intel/iommu.c | 5 +++-- include/linux/intel-iommu.h | 1 - 3 files changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 992fb1415c0f..420be871d9d4 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -514,9 +514,6 @@ int tboot_force_iommu(void) if (!tboot_enabled()) return 0; - if (intel_iommu_tboot_noforce) - return 1; - if (no_iommu || swiotlb || dmar_disabled) pr_warn("Forcing Intel-IOMMU to enabled\n"); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 1b1ca63e6bbe..4d9b298002f0 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -179,7 +179,7 @@ static int rwbf_quirk; * (used when kernel is launched w/ TXT) */ static int force_on = 0; -int intel_iommu_tboot_noforce; +static int intel_iommu_tboot_noforce; static int no_platform_optin; #define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry)) @@ -4885,7 +4885,8 @@ int __init intel_iommu_init(void) * Intel IOMMU is required for a TXT/tboot launch or platform * opt in, so enforce that. */ - force_on = tboot_force_iommu() || platform_optin_force_iommu(); + force_on = (!intel_iommu_tboot_noforce && tboot_force_iommu()) || + platform_optin_force_iommu(); if (iommu_init_mempool()) { if (force_on) diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index fbf5b3e7707e..d956987ed032 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -798,7 +798,6 @@ extern int iommu_calculate_agaw(struct intel_iommu *iommu); extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); extern int dmar_disabled; extern int intel_iommu_enabled; -extern int intel_iommu_tboot_noforce; extern int intel_iommu_gfx_mapped; #else static inline int iommu_calculate_agaw(struct intel_iommu *iommu) -- cgit v1.2.3 From 1e5d770bb8a23dd01e28e92f4fb0b1093c8bdbe6 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 18 Nov 2020 14:56:25 +0000 Subject: io_uring: get an active ref_node from files_data An active ref_node always can be found in ctx->files_data, it's much safer to get it this way instead of poking into files_data->ref_list. Signed-off-by: Pavel Begunkov Cc: stable@vger.kernel.org # v5.7+ Signed-off-by: Jens Axboe --- fs/io_uring.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index b205c1df3f74..5cb194ca4fce 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6974,9 +6974,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) return -ENXIO; spin_lock(&data->lock); - if (!list_empty(&data->ref_list)) - ref_node = list_first_entry(&data->ref_list, - struct fixed_file_ref_node, node); + ref_node = data->node; spin_unlock(&data->lock); if (ref_node) percpu_ref_kill(&ref_node->refs); -- cgit v1.2.3 From e297822b20e7fe683e107aea46e6402adcf99c70 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 18 Nov 2020 14:56:26 +0000 Subject: io_uring: order refnode recycling Don't recycle a refnode until we're done with all requests of nodes ejected before. Signed-off-by: Pavel Begunkov Cc: stable@vger.kernel.org # v5.7+ Signed-off-by: Jens Axboe --- fs/io_uring.c | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 5cb194ca4fce..7d4b755ab451 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -205,6 +205,7 @@ struct fixed_file_ref_node { struct list_head file_list; struct fixed_file_data *file_data; struct llist_node llist; + bool done; }; struct fixed_file_data { @@ -7323,10 +7324,6 @@ static void __io_file_put_work(struct fixed_file_ref_node *ref_node) kfree(pfile); } - spin_lock(&file_data->lock); - list_del(&ref_node->node); - spin_unlock(&file_data->lock); - percpu_ref_exit(&ref_node->refs); kfree(ref_node); percpu_ref_put(&file_data->refs); @@ -7353,17 +7350,32 @@ static void io_file_put_work(struct work_struct *work) static void io_file_data_ref_zero(struct percpu_ref *ref) { struct fixed_file_ref_node *ref_node; + struct fixed_file_data *data; struct io_ring_ctx *ctx; - bool first_add; + bool first_add = false; int delay = HZ; ref_node = container_of(ref, struct fixed_file_ref_node, refs); - ctx = ref_node->file_data->ctx; + data = ref_node->file_data; + ctx = data->ctx; + + spin_lock(&data->lock); + ref_node->done = true; + + while (!list_empty(&data->ref_list)) { + ref_node = list_first_entry(&data->ref_list, + struct fixed_file_ref_node, node); + /* recycle ref nodes in order */ + if (!ref_node->done) + break; + list_del(&ref_node->node); + first_add |= llist_add(&ref_node->llist, &ctx->file_put_llist); + } + spin_unlock(&data->lock); - if (percpu_ref_is_dying(&ctx->file_data->refs)) + if (percpu_ref_is_dying(&data->refs)) delay = 0; - first_add = llist_add(&ref_node->llist, &ctx->file_put_llist); if (!delay) mod_delayed_work(system_wq, &ctx->file_put_work, 0); else if (first_add) @@ -7387,6 +7399,7 @@ static struct fixed_file_ref_node *alloc_fixed_file_ref_node( INIT_LIST_HEAD(&ref_node->node); INIT_LIST_HEAD(&ref_node->file_list); ref_node->file_data = ctx->file_data; + ref_node->done = false; return ref_node; } @@ -7482,7 +7495,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, file_data->node = ref_node; spin_lock(&file_data->lock); - list_add(&ref_node->node, &file_data->ref_list); + list_add_tail(&ref_node->node, &file_data->ref_list); spin_unlock(&file_data->lock); percpu_ref_get(&file_data->refs); return ret; @@ -7641,7 +7654,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (needs_switch) { percpu_ref_kill(&data->node->refs); spin_lock(&data->lock); - list_add(&ref_node->node, &data->ref_list); + list_add_tail(&ref_node->node, &data->ref_list); data->node = ref_node; spin_unlock(&data->lock); percpu_ref_get(&ctx->file_data->refs); -- cgit v1.2.3 From cd9f13c59461351d7a5fd07924264fb49b287359 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 18 Nov 2020 16:01:48 +0100 Subject: can: flexcan: flexcan_chip_start(): fix erroneous flexcan_transceiver_enable() during bus-off recovery If the CAN controller goes into bus off, the do_set_mode() callback with CAN_MODE_START can be used to recover the controller, which then calls flexcan_chip_start(). If configured, this is done automatically by the framework or manually by the user. In flexcan_chip_start() there is an explicit call to flexcan_transceiver_enable(), which does a regulator_enable() on the transceiver regulator. This results in a net usage counter increase, as there is no corresponding flexcan_transceiver_disable() in the bus off code path. This further leads to the transceiver stuck enabled, even if the CAN interface is shut down. To fix this problem the flexcan_transceiver_enable()/flexcan_transceiver_disable() are moved out of flexcan_chip_start()/flexcan_chip_stop() into flexcan_open()/flexcan_close(). Fixes: e955cead0311 ("CAN: Add Flexcan CAN controller driver") Link: https://lore.kernel.org/r/20201118150148.2664024-1-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- drivers/net/can/flexcan.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index d6a9cf0e9b60..99e5f272205d 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -1567,14 +1567,10 @@ static int flexcan_chip_start(struct net_device *dev) priv->write(reg_ctrl2, ®s->ctrl2); } - err = flexcan_transceiver_enable(priv); - if (err) - goto out_chip_disable; - /* synchronize with the can bus */ err = flexcan_chip_unfreeze(priv); if (err) - goto out_transceiver_disable; + goto out_chip_disable; priv->can.state = CAN_STATE_ERROR_ACTIVE; @@ -1592,8 +1588,6 @@ static int flexcan_chip_start(struct net_device *dev) return 0; - out_transceiver_disable: - flexcan_transceiver_disable(priv); out_chip_disable: flexcan_chip_disable(priv); return err; @@ -1623,7 +1617,6 @@ static int __flexcan_chip_stop(struct net_device *dev, bool disable_on_error) priv->write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL, ®s->ctrl); - flexcan_transceiver_disable(priv); priv->can.state = CAN_STATE_STOPPED; return 0; @@ -1665,10 +1658,14 @@ static int flexcan_open(struct net_device *dev) if (err) goto out_runtime_put; - err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev); + err = flexcan_transceiver_enable(priv); if (err) goto out_close; + err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev); + if (err) + goto out_transceiver_disable; + if (priv->can.ctrlmode & CAN_CTRLMODE_FD) priv->mb_size = sizeof(struct flexcan_mb) + CANFD_MAX_DLEN; else @@ -1720,6 +1717,8 @@ static int flexcan_open(struct net_device *dev) can_rx_offload_del(&priv->offload); out_free_irq: free_irq(dev->irq, dev); + out_transceiver_disable: + flexcan_transceiver_disable(priv); out_close: close_candev(dev); out_runtime_put: @@ -1738,6 +1737,7 @@ static int flexcan_close(struct net_device *dev) can_rx_offload_del(&priv->offload); free_irq(dev->irq, dev); + flexcan_transceiver_disable(priv); close_candev(dev); pm_runtime_put(priv->dev); -- cgit v1.2.3 From 20b329129009caf1c646152abe09b697227e1c37 Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Wed, 18 Nov 2020 08:54:31 -0500 Subject: gfs2: Fix regression in freeze_go_sync Patch 541656d3a513 ("gfs2: freeze should work on read-only mounts") changed the check for glock state in function freeze_go_sync() from "gl->gl_state == LM_ST_SHARED" to "gl->gl_req == LM_ST_EXCLUSIVE". That's wrong and it regressed gfs2's freeze/thaw mechanism because it caused only the freezing node (which requests the glock in EX) to queue freeze work. All nodes go through this go_sync code path during the freeze to drop their SHared hold on the freeze glock, allowing the freezing node to acquire it in EXclusive mode. But all the nodes must freeze access to the file system locally, so they ALL must queue freeze work. The freeze_work calls freeze_func, which makes a request to reacquire the freeze glock in SH, effectively blocking until the thaw from the EX holder. Once thawed, the freezing node drops its EX hold on the freeze glock, then the (blocked) freeze_func reacquires the freeze glock in SH again (on all nodes, including the freezer) so all nodes go back to a thawed state. This patch changes the check back to gl_state == LM_ST_SHARED like it was prior to 541656d3a513. Fixes: 541656d3a513 ("gfs2: freeze should work on read-only mounts") Cc: stable@vger.kernel.org # v5.8+ Signed-off-by: Bob Peterson Signed-off-by: Andreas Gruenbacher --- fs/gfs2/glops.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 6c1432d78dce..67f2921ae8d4 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -571,7 +571,18 @@ static int freeze_go_sync(struct gfs2_glock *gl) int error = 0; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - if (gl->gl_req == LM_ST_EXCLUSIVE && !gfs2_withdrawn(sdp)) { + /* + * We need to check gl_state == LM_ST_SHARED here and not gl_req == + * LM_ST_EXCLUSIVE. That's because when any node does a freeze, + * all the nodes should have the freeze glock in SH mode and they all + * call do_xmote: One for EX and the others for UN. They ALL must + * freeze locally, and they ALL must queue freeze work. The freeze_work + * calls freeze_func, which tries to reacquire the freeze glock in SH, + * effectively waiting for the thaw on the node who holds it in EX. + * Once thawed, the work func acquires the freeze glock in + * SH and everybody goes back to thawed. + */ + if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp)) { atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE); error = freeze_super(sdp->sd_vfs); if (error) { -- cgit v1.2.3 From a1f634463aaf2c94dfa13001dbdea011303124cc Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Tue, 15 Sep 2020 16:47:15 +0300 Subject: can: m_can: process interrupt only when not runtime suspended Avoid processing bogus interrupt statuses when the HW is runtime suspended and the M_CAN_IR register read may get all bits 1's. Handler can be called if the interrupt request is shared with other peripherals or at the end of free_irq(). Therefore check the runtime suspended status before processing. Fixes: cdf8259d6573 ("can: m_can: Add PM Support") Signed-off-by: Jarkko Nikula Link: https://lore.kernel.org/r/20200915134715.696303-1-jarkko.nikula@linux.intel.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/m_can.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index e7264043f79a..f3fc37e96b08 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -956,6 +956,8 @@ static irqreturn_t m_can_isr(int irq, void *dev_id) struct net_device_stats *stats = &dev->stats; u32 ir; + if (pm_runtime_suspended(cdev->dev)) + return IRQ_NONE; ir = m_can_read(cdev, M_CAN_IR); if (!ir) return IRQ_NONE; -- cgit v1.2.3 From e95b6c3ef1311dd7b20467d932a24b6d0fd88395 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sun, 8 Nov 2020 16:32:41 -0800 Subject: xfs: fix the minrecs logic when dealing with inode root child blocks The comment and logic in xchk_btree_check_minrecs for dealing with inode-rooted btrees isn't quite correct. While the direct children of the inode root are allowed to have fewer records than what would normally be allowed for a regular ondisk btree block, this is only true if there is only one child block and the number of records don't fit in the inode root. Fixes: 08a3a692ef58 ("xfs: btree scrub should check minrecs") Signed-off-by: Darrick J. Wong Reviewed-by: Chandan Babu R Reviewed-by: Christoph Hellwig --- fs/xfs/scrub/btree.c | 45 +++++++++++++++++++++++++++------------------ 1 file changed, 27 insertions(+), 18 deletions(-) diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index f52a7b8256f9..debf392e0515 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -452,32 +452,41 @@ xchk_btree_check_minrecs( int level, struct xfs_btree_block *block) { - unsigned int numrecs; - int ok_level; - - numrecs = be16_to_cpu(block->bb_numrecs); + struct xfs_btree_cur *cur = bs->cur; + unsigned int root_level = cur->bc_nlevels - 1; + unsigned int numrecs = be16_to_cpu(block->bb_numrecs); /* More records than minrecs means the block is ok. */ - if (numrecs >= bs->cur->bc_ops->get_minrecs(bs->cur, level)) + if (numrecs >= cur->bc_ops->get_minrecs(cur, level)) return; /* - * Certain btree blocks /can/ have fewer than minrecs records. Any - * level greater than or equal to the level of the highest dedicated - * btree block are allowed to violate this constraint. - * - * For a btree rooted in a block, the btree root can have fewer than - * minrecs records. If the btree is rooted in an inode and does not - * store records in the root, the direct children of the root and the - * root itself can have fewer than minrecs records. + * For btrees rooted in the inode, it's possible that the root block + * contents spilled into a regular ondisk block because there wasn't + * enough space in the inode root. The number of records in that + * child block might be less than the standard minrecs, but that's ok + * provided that there's only one direct child of the root. */ - ok_level = bs->cur->bc_nlevels - 1; - if (bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) - ok_level--; - if (level >= ok_level) + if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && + level == cur->bc_nlevels - 2) { + struct xfs_btree_block *root_block; + struct xfs_buf *root_bp; + int root_maxrecs; + + root_block = xfs_btree_get_block(cur, root_level, &root_bp); + root_maxrecs = cur->bc_ops->get_dmaxrecs(cur, root_level); + if (be16_to_cpu(root_block->bb_numrecs) != 1 || + numrecs <= root_maxrecs) + xchk_btree_set_corrupt(bs->sc, cur, level); return; + } - xchk_btree_set_corrupt(bs->sc, bs->cur, level); + /* + * Otherwise, only the root level is allowed to have fewer than minrecs + * records or keyptrs. + */ + if (level < root_level) + xchk_btree_set_corrupt(bs->sc, cur, level); } /* -- cgit v1.2.3 From 498fe261f0d6d5189f8e11d283705dd97b474b54 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sun, 8 Nov 2020 16:32:41 -0800 Subject: xfs: strengthen rmap record flags checking We always know the correct state of the rmap record flags (attr, bmbt, unwritten) so check them by direct comparison. Fixes: d852657ccfc0 ("xfs: cross-reference reverse-mapping btree") Signed-off-by: Darrick J. Wong Reviewed-by: Chandan Babu R Reviewed-by: Christoph Hellwig --- fs/xfs/scrub/bmap.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 412e2ec55e38..fed56d213a3f 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -218,13 +218,13 @@ xchk_bmap_xref_rmap( * which doesn't track unwritten state. */ if (owner != XFS_RMAP_OWN_COW && - irec->br_state == XFS_EXT_UNWRITTEN && - !(rmap.rm_flags & XFS_RMAP_UNWRITTEN)) + !!(irec->br_state == XFS_EXT_UNWRITTEN) != + !!(rmap.rm_flags & XFS_RMAP_UNWRITTEN)) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); - if (info->whichfork == XFS_ATTR_FORK && - !(rmap.rm_flags & XFS_RMAP_ATTR_FORK)) + if (!!(info->whichfork == XFS_ATTR_FORK) != + !!(rmap.rm_flags & XFS_RMAP_ATTR_FORK)) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); if (rmap.rm_flags & XFS_RMAP_BMBT_BLOCK) -- cgit v1.2.3 From 6b48e5b8a20f653b7d64ccf99a498f2523bff752 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sun, 8 Nov 2020 16:32:42 -0800 Subject: xfs: directory scrub should check the null bestfree entries too Teach the directory scrubber to check all the bestfree entries, including the null ones. We want to be able to detect the case where the entry is null but there actually /is/ a directory data block. Found by fuzzing lbests[0] = ones in xfs/391. Fixes: df481968f33b ("xfs: scrub directory freespace") Signed-off-by: Darrick J. Wong Reviewed-by: Chandan Babu R Reviewed-by: Christoph Hellwig --- fs/xfs/scrub/dir.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index 7c432997edad..b045e95c2ea7 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -558,14 +558,27 @@ xchk_directory_leaf1_bestfree( /* Check all the bestfree entries. */ for (i = 0; i < bestcount; i++, bestp++) { best = be16_to_cpu(*bestp); - if (best == NULLDATAOFF) - continue; error = xfs_dir3_data_read(sc->tp, sc->ip, - i * args->geo->fsbcount, 0, &dbp); + xfs_dir2_db_to_da(args->geo, i), + XFS_DABUF_MAP_HOLE_OK, + &dbp); if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error)) break; - xchk_directory_check_freesp(sc, lblk, dbp, best); + + if (!dbp) { + if (best != NULLDATAOFF) { + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, + lblk); + break; + } + continue; + } + + if (best == NULLDATAOFF) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk); + else + xchk_directory_check_freesp(sc, lblk, dbp, best); xfs_trans_brelse(sc->tp, dbp); if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) break; -- cgit v1.2.3 From ada49d64fb3538144192181db05de17e2ffc3551 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Sat, 14 Nov 2020 11:06:01 -0800 Subject: xfs: fix forkoff miscalculation related to XFS_LITINO(mp) Currently, commit e9e2eae89ddb dropped a (int) decoration from XFS_LITINO(mp), and since sizeof() expression is also involved, the result of XFS_LITINO(mp) is simply as the size_t type (commonly unsigned long). Considering the expression in xfs_attr_shortform_bytesfit(): offset = (XFS_LITINO(mp) - bytes) >> 3; let "bytes" be (int)340, and "XFS_LITINO(mp)" be (unsigned long)336. on 64-bit platform, the expression is offset = ((unsigned long)336 - (int)340) >> 3 = (int)(0xfffffffffffffffcUL >> 3) = -1 but on 32-bit platform, the expression is offset = ((unsigned long)336 - (int)340) >> 3 = (int)(0xfffffffcUL >> 3) = 0x1fffffff instead. so offset becomes a large positive number on 32-bit platform, and cause xfs_attr_shortform_bytesfit() returns maxforkoff rather than 0. Therefore, one result is "ASSERT(new_size <= XFS_IFORK_SIZE(ip, whichfork));" assertion failure in xfs_idata_realloc(), which was also the root cause of the original bugreport from Dennis, see: https://bugzilla.redhat.com/show_bug.cgi?id=1894177 And it can also be manually triggered with the following commands: $ touch a; $ setfattr -n user.0 -v "`seq 0 80`" a; $ setfattr -n user.1 -v "`seq 0 80`" a on 32-bit platform. Fix the case in xfs_attr_shortform_bytesfit() by bailing out "XFS_LITINO(mp) < bytes" in advance suggested by Eric and a misleading comment together with this bugfix suggested by Darrick. It seems the other users of XFS_LITINO(mp) are not impacted. Fixes: e9e2eae89ddb ("xfs: only check the superblock version for dinode size calculation") Cc: # 5.7+ Reported-and-tested-by: Dennis Gilmore Reviewed-by: Christoph Hellwig Signed-off-by: Gao Xiang Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_attr_leaf.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index bb128db220ac..d6ef69ab1c67 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -515,7 +515,7 @@ xfs_attr_copy_value( *========================================================================*/ /* - * Query whether the requested number of additional bytes of extended + * Query whether the total requested number of attr fork bytes of extended * attribute space will be able to fit inline. * * Returns zero if not, else the di_forkoff fork offset to be used in the @@ -535,6 +535,12 @@ xfs_attr_shortform_bytesfit( int maxforkoff; int offset; + /* + * Check if the new size could fit at all first: + */ + if (bytes > XFS_LITINO(mp)) + return 0; + /* rounded down */ offset = (XFS_LITINO(mp) - bytes) >> 3; -- cgit v1.2.3 From 27c14b5daa82861220d6fa6e27b51f05f21ffaa7 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sat, 14 Nov 2020 09:59:22 -0800 Subject: xfs: ensure inobt record walks always make forward progress The aim of the inode btree record iterator function is to call a callback on every record in the btree. To avoid having to tear down and recreate the inode btree cursor around every callback, it caches a certain number of records in a memory buffer. After each batch of callback invocations, we have to perform a btree lookup to find the next record after where we left off. However, if the keys of the inode btree are corrupt, the lookup might put us in the wrong part of the inode btree, causing the walk function to loop forever. Therefore, we add extra cursor tracking to make sure that we never go backwards neither when performing the lookup nor when jumping to the next inobt record. This also fixes an off by one error where upon resume the lookup should have been for the inode /after/ the point at which we stopped. Found by fuzzing xfs/460 with keys[2].startino = ones causing bulkstat and quotacheck to hang. Fixes: a211432c27ff ("xfs: create simplified inode walk function") Signed-off-by: Darrick J. Wong Reviewed-by: Chandan Babu R --- fs/xfs/xfs_iwalk.c | 27 ++++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c index 233dcc8784db..2a45138831e3 100644 --- a/fs/xfs/xfs_iwalk.c +++ b/fs/xfs/xfs_iwalk.c @@ -55,6 +55,9 @@ struct xfs_iwalk_ag { /* Where do we start the traversal? */ xfs_ino_t startino; + /* What was the last inode number we saw when iterating the inobt? */ + xfs_ino_t lastino; + /* Array of inobt records we cache. */ struct xfs_inobt_rec_incore *recs; @@ -301,6 +304,9 @@ xfs_iwalk_ag_start( if (XFS_IS_CORRUPT(mp, *has_more != 1)) return -EFSCORRUPTED; + iwag->lastino = XFS_AGINO_TO_INO(mp, agno, + irec->ir_startino + XFS_INODES_PER_CHUNK - 1); + /* * If the LE lookup yielded an inobt record before the cursor position, * skip it and see if there's another one after it. @@ -347,15 +353,17 @@ xfs_iwalk_run_callbacks( struct xfs_mount *mp = iwag->mp; struct xfs_trans *tp = iwag->tp; struct xfs_inobt_rec_incore *irec; - xfs_agino_t restart; + xfs_agino_t next_agino; int error; + next_agino = XFS_INO_TO_AGINO(mp, iwag->lastino) + 1; + ASSERT(iwag->nr_recs > 0); /* Delete cursor but remember the last record we cached... */ xfs_iwalk_del_inobt(tp, curpp, agi_bpp, 0); irec = &iwag->recs[iwag->nr_recs - 1]; - restart = irec->ir_startino + XFS_INODES_PER_CHUNK - 1; + ASSERT(next_agino == irec->ir_startino + XFS_INODES_PER_CHUNK); error = xfs_iwalk_ag_recs(iwag); if (error) @@ -372,7 +380,7 @@ xfs_iwalk_run_callbacks( if (error) return error; - return xfs_inobt_lookup(*curpp, restart, XFS_LOOKUP_GE, has_more); + return xfs_inobt_lookup(*curpp, next_agino, XFS_LOOKUP_GE, has_more); } /* Walk all inodes in a single AG, from @iwag->startino to the end of the AG. */ @@ -396,6 +404,7 @@ xfs_iwalk_ag( while (!error && has_more) { struct xfs_inobt_rec_incore *irec; + xfs_ino_t rec_fsino; cond_resched(); if (xfs_pwork_want_abort(&iwag->pwork)) @@ -407,6 +416,15 @@ xfs_iwalk_ag( if (error || !has_more) break; + /* Make sure that we always move forward. */ + rec_fsino = XFS_AGINO_TO_INO(mp, agno, irec->ir_startino); + if (iwag->lastino != NULLFSINO && + XFS_IS_CORRUPT(mp, iwag->lastino >= rec_fsino)) { + error = -EFSCORRUPTED; + goto out; + } + iwag->lastino = rec_fsino + XFS_INODES_PER_CHUNK - 1; + /* No allocated inodes in this chunk; skip it. */ if (iwag->skip_empty && irec->ir_freecount == irec->ir_count) { error = xfs_btree_increment(cur, 0, &has_more); @@ -535,6 +553,7 @@ xfs_iwalk( .trim_start = 1, .skip_empty = 1, .pwork = XFS_PWORK_SINGLE_THREADED, + .lastino = NULLFSINO, }; xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); int error; @@ -623,6 +642,7 @@ xfs_iwalk_threaded( iwag->data = data; iwag->startino = startino; iwag->sz_recs = xfs_iwalk_prefetch(inode_records); + iwag->lastino = NULLFSINO; xfs_pwork_queue(&pctl, &iwag->pwork); startino = XFS_AGINO_TO_INO(mp, agno + 1, 0); if (flags & XFS_INOBT_WALK_SAME_AG) @@ -696,6 +716,7 @@ xfs_inobt_walk( .startino = startino, .sz_recs = xfs_inobt_walk_prefetch(inobt_records), .pwork = XFS_PWORK_SINGLE_THREADED, + .lastino = NULLFSINO, }; xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); int error; -- cgit v1.2.3 From 595189c25c28a55523354336bf24453242c81c15 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Wed, 18 Nov 2020 09:21:26 -0800 Subject: xfs: return corresponding errcode if xfs_initialize_perag() fail In xfs_initialize_perag(), if kmem_zalloc(), xfs_buf_hash_init(), or radix_tree_preload() failed, the returned value 'error' is not set accordingly. Reported-as-fixing: 8b26c5825e02 ("xfs: handle ENOMEM correctly during initialisation of perag structures") Fixes: 9b2471797942 ("xfs: cache unlinked pointers in an rhashtable") Reported-by: Hulk Robot Signed-off-by: Yu Kuai Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_mount.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 150ee5cb8645..7110507a2b6b 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -194,20 +194,25 @@ xfs_initialize_perag( } pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL); - if (!pag) + if (!pag) { + error = -ENOMEM; goto out_unwind_new_pags; + } pag->pag_agno = index; pag->pag_mount = mp; spin_lock_init(&pag->pag_ici_lock); INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); - if (xfs_buf_hash_init(pag)) + + error = xfs_buf_hash_init(pag); + if (error) goto out_free_pag; init_waitqueue_head(&pag->pagb_wait); spin_lock_init(&pag->pagb_lock); pag->pagb_count = 0; pag->pagb_tree = RB_ROOT; - if (radix_tree_preload(GFP_NOFS)) + error = radix_tree_preload(GFP_NOFS); + if (error) goto out_hash_destroy; spin_lock(&mp->m_perag_lock); -- cgit v1.2.3 From 879ee8b6f2bae0cc4a25536f8841db1dbc969523 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 11 Nov 2020 12:54:34 -0800 Subject: ASOC: Intel: kbl_rt5663_rt5514_max98927: Do not try to disable disabled clock In kabylake_set_bias_level(), enabling mclk may fail if the clock has already been enabled by the firmware. Attempts to disable that clock later will fail with a warning backtrace. mclk already disabled WARNING: CPU: 2 PID: 108 at drivers/clk/clk.c:952 clk_core_disable+0x1b6/0x1cf ... Call Trace: clk_disable+0x2d/0x3a kabylake_set_bias_level+0x72/0xfd [snd_soc_kbl_rt5663_rt5514_max98927] snd_soc_card_set_bias_level+0x2b/0x6f snd_soc_dapm_set_bias_level+0xe1/0x209 dapm_pre_sequence_async+0x63/0x96 async_run_entry_fn+0x3d/0xd1 process_one_work+0x2a9/0x526 ... Only disable the clock if it has been enabled. Fixes: 15747a802075 ("ASoC: eve: implement set_bias_level function for rt5514") Cc: Brent Lu Cc: Curtis Malainey Signed-off-by: Guenter Roeck Link: https://lore.kernel.org/r/20201111205434.207610-1-linux@roeck-us.net Signed-off-by: Mark Brown --- sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c index 922cd0176e1f..f95546c184aa 100644 --- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c +++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c @@ -700,6 +700,8 @@ static int kabylake_set_bias_level(struct snd_soc_card *card, switch (level) { case SND_SOC_BIAS_PREPARE: if (dapm->bias_level == SND_SOC_BIAS_ON) { + if (!__clk_is_enabled(priv->mclk)) + return 0; dev_dbg(card->dev, "Disable mclk"); clk_disable_unprepare(priv->mclk); } else { -- cgit v1.2.3 From 2ba546ebe0ce2af47833d8912ced9b4a579f13cb Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Wed, 18 Nov 2020 08:50:09 -0600 Subject: regulator: ti-abb: Fix array out of bound read access on the first transition At the start of driver initialization, we do not know what bias setting the bootloader has configured the system for and we only know for certain the very first time we do a transition. However, since the initial value of the comparison index is -EINVAL, this negative value results in an array out of bound access on the very first transition. Since we don't know what the setting is, we just set the bias configuration as there is nothing to compare against. This prevents the array out of bound access. NOTE: Even though we could use a more relaxed check of "< 0" the only valid values(ignoring cosmic ray induced bitflips) are -EINVAL, 0+. Fixes: 40b1936efebd ("regulator: Introduce TI Adaptive Body Bias(ABB) on-chip LDO driver") Link: https://lore.kernel.org/linux-mm/CA+G9fYuk4imvhyCN7D7T6PMDH6oNp6HDCRiTUKMQ6QXXjBa4ag@mail.gmail.com/ Reported-by: Naresh Kamboju Reviewed-by: Arnd Bergmann Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20201118145009.10492-1-nm@ti.com Signed-off-by: Mark Brown --- drivers/regulator/ti-abb-regulator.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c index 3e60bff76194..9f0a4d50cead 100644 --- a/drivers/regulator/ti-abb-regulator.c +++ b/drivers/regulator/ti-abb-regulator.c @@ -342,8 +342,17 @@ static int ti_abb_set_voltage_sel(struct regulator_dev *rdev, unsigned sel) return ret; } - /* If data is exactly the same, then just update index, no change */ info = &abb->info[sel]; + /* + * When Linux kernel is starting up, we are'nt sure of the + * Bias configuration that bootloader has configured. + * So, we get to know the actual setting the first time + * we are asked to transition. + */ + if (abb->current_info_idx == -EINVAL) + goto just_set_abb; + + /* If data is exactly the same, then just update index, no change */ oinfo = &abb->info[abb->current_info_idx]; if (!memcmp(info, oinfo, sizeof(*info))) { dev_dbg(dev, "%s: Same data new idx=%d, old idx=%d\n", __func__, @@ -351,6 +360,7 @@ static int ti_abb_set_voltage_sel(struct regulator_dev *rdev, unsigned sel) goto out; } +just_set_abb: ret = ti_abb_set_opp(rdev, abb, info); out: -- cgit v1.2.3 From df8d85d8c69d6837817e54dcb73c84a8b5a13877 Mon Sep 17 00:00:00 2001 From: Filip Moc Date: Tue, 17 Nov 2020 18:36:31 +0100 Subject: net: usb: qmi_wwan: Set DTR quirk for MR400 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit LTE module MR400 embedded in TL-MR6400 v4 requires DTR to be set. Signed-off-by: Filip Moc Acked-by: Bjørn Mork Link: https://lore.kernel.org/r/20201117173631.GA550981@moc6.cz Signed-off-by: Jakub Kicinski --- drivers/net/usb/qmi_wwan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 581ed51abb53..fc378ff56775 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1070,7 +1070,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x05c6, 0x9011, 4)}, {QMI_FIXED_INTF(0x05c6, 0x9021, 1)}, {QMI_FIXED_INTF(0x05c6, 0x9022, 2)}, - {QMI_FIXED_INTF(0x05c6, 0x9025, 4)}, /* Alcatel-sbell ASB TL131 TDD LTE (China Mobile) */ + {QMI_QUIRK_SET_DTR(0x05c6, 0x9025, 4)}, /* Alcatel-sbell ASB TL131 TDD LTE (China Mobile) */ {QMI_FIXED_INTF(0x05c6, 0x9026, 3)}, {QMI_FIXED_INTF(0x05c6, 0x902e, 5)}, {QMI_FIXED_INTF(0x05c6, 0x9031, 5)}, -- cgit v1.2.3 From a5ebcbdf34b65fcc07f38eaf2d60563b42619a59 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Tue, 17 Nov 2020 10:45:05 +0800 Subject: ah6: fix error return code in ah6_input() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Link: https://lore.kernel.org/r/1605581105-35295-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- net/ipv6/ah6.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index d88d97617f7e..440080da805b 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -588,7 +588,8 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); memset(ah->auth_data, 0, ahp->icv_trunc_len); - if (ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN)) + err = ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN); + if (err) goto out_free; ip6h->priority = 0; -- cgit v1.2.3 From 537a14726582c4e7bfe4dff9cb7fca19dc912cf6 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Tue, 17 Nov 2020 10:55:21 +0800 Subject: atl1c: fix error return code in atl1c_probe() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 43250ddd75a3 ("atl1c: Atheros L1C Gigabit Ethernet driver") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Link: https://lore.kernel.org/r/1605581721-36028-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 0c12cf7bda50..3f65f2b370c5 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -2543,8 +2543,8 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * various kernel subsystems to support the mechanics required by a * fixed-high-32-bit system. */ - if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) || - (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { dev_err(&pdev->dev, "No usable DMA configuration,aborting\n"); goto err_dma; } -- cgit v1.2.3 From 3a36060bf294e7b7e33c5dddcc4f5d2c1c834e56 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Tue, 17 Nov 2020 10:57:55 +0800 Subject: atl1e: fix error return code in atl1e_probe() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: a6a5325239c2 ("atl1e: Atheros L1E Gigabit Ethernet driver") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Link: https://lore.kernel.org/r/1605581875-36281-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/atheros/atl1e/atl1e_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 098b0328e3cb..ff9f96de74b8 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -2312,8 +2312,8 @@ static int atl1e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * various kernel subsystems to support the mechanics required by a * fixed-high-32-bit system. */ - if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) || - (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { dev_err(&pdev->dev, "No usable DMA configuration,aborting\n"); goto err_dma; } -- cgit v1.2.3 From 1532b9778478577152201adbafa7738b1e844868 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 16 Nov 2020 19:52:34 -0800 Subject: net: Have netpoll bring-up DSA management interface DSA network devices rely on having their DSA management interface up and running otherwise their ndo_open() will return -ENETDOWN. Without doing this it would not be possible to use DSA devices as netconsole when configured on the command line. These devices also do not utilize the upper/lower linking so the check about the netpoll device having upper is not going to be a problem. The solution adopted here is identical to the one done for net/ipv4/ipconfig.c with 728c02089a0e ("net: ipv4: handle DSA enabled master network devices"), with the network namespace scope being restricted to that of the process configuring netpoll. Fixes: 04ff53f96a93 ("net: dsa: Add netconsole support") Tested-by: Vladimir Oltean Signed-off-by: Florian Fainelli Link: https://lore.kernel.org/r/20201117035236.22658-1-f.fainelli@gmail.com Signed-off-by: Jakub Kicinski --- net/core/netpoll.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index c310c7c1cef7..960948290001 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -657,15 +658,15 @@ EXPORT_SYMBOL_GPL(__netpoll_setup); int netpoll_setup(struct netpoll *np) { - struct net_device *ndev = NULL; + struct net_device *ndev = NULL, *dev = NULL; + struct net *net = current->nsproxy->net_ns; struct in_device *in_dev; int err; rtnl_lock(); - if (np->dev_name[0]) { - struct net *net = current->nsproxy->net_ns; + if (np->dev_name[0]) ndev = __dev_get_by_name(net, np->dev_name); - } + if (!ndev) { np_err(np, "%s doesn't exist, aborting\n", np->dev_name); err = -ENODEV; @@ -673,6 +674,19 @@ int netpoll_setup(struct netpoll *np) } dev_hold(ndev); + /* bring up DSA management network devices up first */ + for_each_netdev(net, dev) { + if (!netdev_uses_dsa(dev)) + continue; + + err = dev_change_flags(dev, dev->flags | IFF_UP, NULL); + if (err < 0) { + np_err(np, "%s failed to open %s\n", + np->dev_name, dev->name); + goto put; + } + } + if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); err = -EBUSY; -- cgit v1.2.3 From fb738b99ef229bd3d25f1b3e5503925dba9b1a7c Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 17 Nov 2020 19:33:51 +0200 Subject: mlxsw: Fix firmware flashing The commit cited below moved firmware flashing functionality from mlxsw_spectrum to mlxsw_core, but did not adjust the Kconfig dependencies. This makes it possible to have mlxsw_core as built-in and mlxfw as a module. The mlxfw code is therefore not reachable from mlxsw_core and firmware flashing fails: # devlink dev flash pci/0000:01:00.0 file mellanox/mlxsw_spectrum-13.2008.1310.mfa2 devlink answers: Operation not supported Fix by having mlxsw_core select mlxfw. Fixes: b79cb787ac70 ("mlxsw: Move fw flashing code into core.c") Signed-off-by: Ido Schimmel Reported-by: Vadim Pasternak Tested-by: Vadim Pasternak Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlxsw/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index 872e9910bb7c..a619d90559f7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -6,6 +6,7 @@ config MLXSW_CORE tristate "Mellanox Technologies Switch ASICs support" select NET_DEVLINK + select MLXFW help This driver supports Mellanox Technologies Switch ASICs family. @@ -82,7 +83,6 @@ config MLXSW_SPECTRUM select GENERIC_ALLOCATOR select PARMAN select OBJAGG - select MLXFW imply PTP_1588_CLOCK select NET_PTP_CLASSIFY if PTP_1588_CLOCK default m -- cgit v1.2.3 From 1f492eab67bced119a0ac7db75ef2047e29a30c6 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 17 Nov 2020 19:33:52 +0200 Subject: mlxsw: core: Use variable timeout for EMAD retries The driver sends Ethernet Management Datagram (EMAD) packets to the device for configuration purposes and waits for up to 200ms for a reply. A request is retried up to 5 times. When the system is under heavy load, replies are not always processed in time and EMAD transactions fail. Make the process more robust to such delays by using exponential backoff. First wait for up to 200ms, then retransmit and wait for up to 400ms and so on. Fixes: caf7297e7ab5 ("mlxsw: core: Introduce support for asynchronous EMAD register access") Reported-by: Denis Yulevich Tested-by: Denis Yulevich Signed-off-by: Ido Schimmel Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlxsw/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 937b8e46f8c7..1a86535c4968 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -571,7 +571,8 @@ static void mlxsw_emad_trans_timeout_schedule(struct mlxsw_reg_trans *trans) if (trans->core->fw_flash_in_progress) timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS); - queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, timeout); + queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, + timeout << trans->retries); } static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core, -- cgit v1.2.3 From a3dcb3e7e70c72a68a79b30fc3a3adad5612731c Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 16 Nov 2020 08:43:01 -0800 Subject: net: dsa: mv88e6xxx: Wait for EEPROM done after HW reset When the switch is hardware reset, it reads the contents of the EEPROM. This can contain instructions for programming values into registers and to perform waits between such programming. Reading the EEPROM can take longer than the 100ms mv88e6xxx_hardware_reset() waits after deasserting the reset GPIO. So poll the EEPROM done bit to ensure it is complete. Signed-off-by: Andrew Lunn Signed-off-by: Ruslan Sushko Link: https://lore.kernel.org/r/20201116164301.977661-1-rus@sushko.dev Signed-off-by: Jakub Kicinski --- drivers/net/dsa/mv88e6xxx/chip.c | 2 ++ drivers/net/dsa/mv88e6xxx/global1.c | 31 +++++++++++++++++++++++++++++++ drivers/net/dsa/mv88e6xxx/global1.h | 1 + 3 files changed, 34 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index bd297ae7cf9e..34cca0a4b31c 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2297,6 +2297,8 @@ static void mv88e6xxx_hardware_reset(struct mv88e6xxx_chip *chip) usleep_range(10000, 20000); gpiod_set_value_cansleep(gpiod, 0); usleep_range(10000, 20000); + + mv88e6xxx_g1_wait_eeprom_done(chip); } } diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index f62aa83ca08d..33d443a37efc 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -75,6 +75,37 @@ static int mv88e6xxx_g1_wait_init_ready(struct mv88e6xxx_chip *chip) return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STS, bit, 1); } +void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip) +{ + const unsigned long timeout = jiffies + 1 * HZ; + u16 val; + int err; + + /* Wait up to 1 second for the switch to finish reading the + * EEPROM. + */ + while (time_before(jiffies, timeout)) { + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &val); + if (err) { + dev_err(chip->dev, "Error reading status"); + return; + } + + /* If the switch is still resetting, it may not + * respond on the bus, and so MDIO read returns + * 0xffff. Differentiate between that, and waiting for + * the EEPROM to be done by bit 0 being set. + */ + if (val != 0xffff && + val & BIT(MV88E6XXX_G1_STS_IRQ_EEPROM_DONE)) + return; + + usleep_range(1000, 2000); + } + + dev_err(chip->dev, "Timeout waiting for EEPROM done"); +} + /* Offset 0x01: Switch MAC Address Register Bytes 0 & 1 * Offset 0x02: Switch MAC Address Register Bytes 2 & 3 * Offset 0x03: Switch MAC Address Register Bytes 4 & 5 diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 1e3546f8b072..e05abe61fa11 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -278,6 +278,7 @@ int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr); int mv88e6185_g1_reset(struct mv88e6xxx_chip *chip); int mv88e6352_g1_reset(struct mv88e6xxx_chip *chip); int mv88e6250_g1_reset(struct mv88e6xxx_chip *chip); +void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip); int mv88e6185_g1_ppu_enable(struct mv88e6xxx_chip *chip); int mv88e6185_g1_ppu_disable(struct mv88e6xxx_chip *chip); -- cgit v1.2.3 From 2b3af2705645c87eee0f386e075871886fd429b3 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Tue, 17 Nov 2020 09:33:51 -0500 Subject: drm/amd/display: Always get CRTC updated constant values inside commit tail We recently improved our display atomic commit and tail sequence to avoid some issues related to concurrency. One of the major changes consisted of moving the interrupt disable and the stream release from our atomic commit to our atomic tail (commit 6d90a208cfff ("drm/amd/display: Move disable interrupt into commit tail")) . However, the new code introduced inside our commit tail function was inserted right after the function drm_atomic_helper_update_legacy_modeset_state(), which has routines for updating internal data structs related to timestamps. As a result, in certain conditions, the display module can reach a situation where we update our constants and, after that, clean it. This situation generates the following warning: amdgpu 0000:03:00.0: drm_WARN_ON_ONCE(drm_drv_uses_atomic_modeset(dev)) WARNING: CPU: 6 PID: 1269 at drivers/gpu/drm/drm_vblank.c:722 drm_crtc_vblank_helper_get_vblank_timestamp_internal+0x32b/0x340 [drm] ... RIP: 0010:drm_crtc_vblank_helper_get_vblank_timestamp_internal+0x32b/0x340 [drm] ... Call Trace: ? dc_stream_get_vblank_counter+0x57/0x60 [amdgpu] drm_crtc_vblank_helper_get_vblank_timestamp+0x1c/0x20 [drm] drm_get_last_vbltimestamp+0xad/0xc0 [drm] drm_reset_vblank_timestamp+0x63/0xd0 [drm] drm_crtc_vblank_on+0x85/0x150 [drm] amdgpu_dm_atomic_commit_tail+0xaf1/0x2330 [amdgpu] commit_tail+0x99/0x130 [drm_kms_helper] drm_atomic_helper_commit+0x123/0x150 [drm_kms_helper] amdgpu_dm_atomic_commit+0x11/0x20 [amdgpu] drm_atomic_commit+0x4a/0x50 [drm] drm_atomic_helper_set_config+0x7c/0xc0 [drm_kms_helper] drm_mode_setcrtc+0x20b/0x7e0 [drm] ? tomoyo_path_number_perm+0x6f/0x200 ? drm_mode_getcrtc+0x190/0x190 [drm] drm_ioctl_kernel+0xae/0xf0 [drm] drm_ioctl+0x245/0x400 [drm] ? drm_mode_getcrtc+0x190/0x190 [drm] amdgpu_drm_ioctl+0x4e/0x80 [amdgpu] __x64_sys_ioctl+0x91/0xc0 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ... For fixing this issue we rely upon a refactor introduced on drm_atomic_helper_update_legacy_modeset_state ("Remove the timestamping constant update from drm_atomic_helper_update_legacy_modeset_state()") which decouples constant values update from drm_atomic_helper_update_legacy_modeset_state to a new helper. Basically, this commit uses this new helper and place it right after our release module to avoid a situation where our CRTC struct gets wrong values. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1373 Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1349 Reviewed-by: Harry Wentland Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index e93e18c06c0e..0e7118000919 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7506,7 +7506,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) bool mode_set_reset_required = false; drm_atomic_helper_update_legacy_modeset_state(dev, state); - drm_atomic_helper_calc_timestamping_constants(state); dm_state = dm_atomic_get_new_state(state); if (dm_state && dm_state->context) { @@ -7533,6 +7532,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) } } + drm_atomic_helper_calc_timestamping_constants(state); + /* update changed items */ for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); -- cgit v1.2.3 From d8c19014bba8f565d8a2f1f46b4e38d1d97bf1a7 Mon Sep 17 00:00:00 2001 From: Dongli Zhang Date: Sun, 15 Nov 2020 12:10:29 -0800 Subject: page_frag: Recover from memory pressure The ethernet driver may allocate skb (and skb->data) via napi_alloc_skb(). This ends up to page_frag_alloc() to allocate skb->data from page_frag_cache->va. During the memory pressure, page_frag_cache->va may be allocated as pfmemalloc page. As a result, the skb->pfmemalloc is always true as skb->data is from page_frag_cache->va. The skb will be dropped if the sock (receiver) does not have SOCK_MEMALLOC. This is expected behaviour under memory pressure. However, once kernel is not under memory pressure any longer (suppose large amount of memory pages are just reclaimed), the page_frag_alloc() may still re-use the prior pfmemalloc page_frag_cache->va to allocate skb->data. As a result, the skb->pfmemalloc is always true unless page_frag_cache->va is re-allocated, even if the kernel is not under memory pressure any longer. Here is how kernel runs into issue. 1. The kernel is under memory pressure and allocation of PAGE_FRAG_CACHE_MAX_ORDER in __page_frag_cache_refill() will fail. Instead, the pfmemalloc page is allocated for page_frag_cache->va. 2: All skb->data from page_frag_cache->va (pfmemalloc) will have skb->pfmemalloc=true. The skb will always be dropped by sock without SOCK_MEMALLOC. This is an expected behaviour. 3. Suppose a large amount of pages are reclaimed and kernel is not under memory pressure any longer. We expect skb->pfmemalloc drop will not happen. 4. Unfortunately, page_frag_alloc() does not proactively re-allocate page_frag_alloc->va and will always re-use the prior pfmemalloc page. The skb->pfmemalloc is always true even kernel is not under memory pressure any longer. Fix this by freeing and re-allocating the page instead of recycling it. References: https://lore.kernel.org/lkml/20201103193239.1807-1-dongli.zhang@oracle.com/ References: https://lore.kernel.org/linux-mm/20201105042140.5253-1-willy@infradead.org/ Suggested-by: Matthew Wilcox (Oracle) Cc: Aruna Ramakrishna Cc: Bert Barbe Cc: Rama Nichanamatlu Cc: Venkat Venkatsubra Cc: Manjunath Patil Cc: Joe Jin Cc: SRINIVAS Fixes: 79930f5892e1 ("net: do not deplete pfmemalloc reserve") Signed-off-by: Dongli Zhang Acked-by: Vlastimil Babka Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20201115201029.11903-1-dongli.zhang@oracle.com Signed-off-by: Jakub Kicinski --- mm/page_alloc.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 23f5066bd4a5..eaa227a479e4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5103,6 +5103,11 @@ refill: if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) goto refill; + if (unlikely(nc->pfmemalloc)) { + free_the_page(page, compound_order(page)); + goto refill; + } + #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) /* if size can vary use size else just use PAGE_SIZE */ size = nc->size; -- cgit v1.2.3 From 6dceaa9f56e22d0f9b4c4ad2ed9e04e315ce7fe5 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 16 Nov 2020 17:21:14 +0100 Subject: atm: nicstar: Unmap DMA on send error The `skb' is mapped for DMA in ns_send() but does not unmap DMA in case push_scqe() fails to submit the `skb'. The memory of the `skb' is released so only the DMA mapping is leaking. Unmap the DMA mapping in case push_scqe() failed. Fixes: 864a3ff635fa7 ("atm: [nicstar] remove virt_to_bus() and support 64-bit platforms") Cc: Chas Williams <3chas3@gmail.com> Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Jakub Kicinski --- drivers/atm/nicstar.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c index 7af74fb450a0..09ad73361879 100644 --- a/drivers/atm/nicstar.c +++ b/drivers/atm/nicstar.c @@ -1706,6 +1706,8 @@ static int ns_send(struct atm_vcc *vcc, struct sk_buff *skb) if (push_scqe(card, vc, scq, &scqe, skb) != 0) { atomic_inc(&vcc->stats->tx_err); + dma_unmap_single(&card->pcidev->dev, NS_PRV_DMA(skb), skb->len, + DMA_TO_DEVICE); dev_kfree_skb_any(skb); return -EIO; } -- cgit v1.2.3 From 6d9c8d15af0ef20a66a0b432cac0d08319920602 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Wed, 18 Nov 2020 10:19:22 +0200 Subject: net/mlx4_core: Fix init_hca fields offset Slave function read the following capabilities from the wrong offset: 1. log_mc_entry_sz 2. fs_log_entry_sz 3. log_mc_hash_sz Fix that by adjusting these capabilities offset to match firmware layout. Due to the wrong offset read, the following issues might occur: 1+2. Negative value reported at max_mcast_qp_attach. 3. Driver to init FW with multicast hash size of zero. Fixes: a40ded604365 ("net/mlx4_core: Add masking for a few queries on HCA caps") Signed-off-by: Aya Levin Reviewed-by: Moshe Shemesh Reviewed-by: Eran Ben Elisha Signed-off-by: Tariq Toukan Link: https://lore.kernel.org/r/20201118081922.553-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx4/fw.c | 6 +++--- drivers/net/ethernet/mellanox/mlx4/fw.h | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index f6ff9620a137..f6cfec81ccc3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -1864,8 +1864,8 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) #define INIT_HCA_LOG_RD_OFFSET (INIT_HCA_QPC_OFFSET + 0x77) #define INIT_HCA_MCAST_OFFSET 0x0c0 #define INIT_HCA_MC_BASE_OFFSET (INIT_HCA_MCAST_OFFSET + 0x00) -#define INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x12) -#define INIT_HCA_LOG_MC_HASH_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x16) +#define INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x13) +#define INIT_HCA_LOG_MC_HASH_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x17) #define INIT_HCA_UC_STEERING_OFFSET (INIT_HCA_MCAST_OFFSET + 0x18) #define INIT_HCA_LOG_MC_TABLE_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x1b) #define INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN 0x6 @@ -1873,7 +1873,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) #define INIT_HCA_DRIVER_VERSION_SZ 0x40 #define INIT_HCA_FS_PARAM_OFFSET 0x1d0 #define INIT_HCA_FS_BASE_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x00) -#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x12) +#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x13) #define INIT_HCA_FS_A0_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x18) #define INIT_HCA_FS_LOG_TABLE_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x1b) #define INIT_HCA_FS_ETH_BITS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x21) diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index 650ae08c71de..8f020f26ebf5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -182,8 +182,8 @@ struct mlx4_init_hca_param { u64 cmpt_base; u64 mtt_base; u64 global_caps; - u16 log_mc_entry_sz; - u16 log_mc_hash_sz; + u8 log_mc_entry_sz; + u8 log_mc_hash_sz; u16 hca_core_clock; /* Internal Clock Frequency (in MHz) */ u8 log_num_qps; u8 log_num_srqs; -- cgit v1.2.3 From 1699f980d87fb678a669490462cf0b9517c1fb47 Mon Sep 17 00:00:00 2001 From: Can Guo Date: Wed, 21 Oct 2020 22:59:00 -0700 Subject: scsi: ufs: Fix unexpected values from ufshcd_read_desc_param() WB-related sysfs entries can be accessed even when an UFS device does not support the feature. The descriptors which are not supported by the UFS device may be wrongly reported when they are accessed from their corrsponding sysfs entries. Fix it by adding a sanity check of parameter offset against the actual decriptor length. Link: https://lore.kernel.org/r/1603346348-14149-1-git-send-email-cang@codeaurora.org Reviewed-by: Asutosh Das Acked-by: Daejun Park Signed-off-by: Can Guo Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 7a160b86adc6..180e64dc6f2d 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -3192,13 +3192,19 @@ int ufshcd_read_desc_param(struct ufs_hba *hba, /* Get the length of descriptor */ ufshcd_map_desc_id_to_length(hba, desc_id, &buff_len); if (!buff_len) { - dev_err(hba->dev, "%s: Failed to get desc length", __func__); + dev_err(hba->dev, "%s: Failed to get desc length\n", __func__); + return -EINVAL; + } + + if (param_offset >= buff_len) { + dev_err(hba->dev, "%s: Invalid offset 0x%x in descriptor IDN 0x%x, length 0x%x\n", + __func__, param_offset, desc_id, buff_len); return -EINVAL; } /* Check whether we need temp memory */ if (param_offset != 0 || param_size < buff_len) { - desc_buf = kmalloc(buff_len, GFP_KERNEL); + desc_buf = kzalloc(buff_len, GFP_KERNEL); if (!desc_buf) return -ENOMEM; } else { @@ -3212,14 +3218,14 @@ int ufshcd_read_desc_param(struct ufs_hba *hba, desc_buf, &buff_len); if (ret) { - dev_err(hba->dev, "%s: Failed reading descriptor. desc_id %d, desc_index %d, param_offset %d, ret %d", + dev_err(hba->dev, "%s: Failed reading descriptor. desc_id %d, desc_index %d, param_offset %d, ret %d\n", __func__, desc_id, desc_index, param_offset, ret); goto out; } /* Sanity check */ if (desc_buf[QUERY_DESC_DESC_TYPE_OFFSET] != desc_id) { - dev_err(hba->dev, "%s: invalid desc_id %d in descriptor header", + dev_err(hba->dev, "%s: invalid desc_id %d in descriptor header\n", __func__, desc_buf[QUERY_DESC_DESC_TYPE_OFFSET]); ret = -EINVAL; goto out; @@ -3229,12 +3235,12 @@ int ufshcd_read_desc_param(struct ufs_hba *hba, buff_len = desc_buf[QUERY_DESC_LENGTH_OFFSET]; ufshcd_update_desc_length(hba, desc_id, desc_index, buff_len); - /* Check wherher we will not copy more data, than available */ - if (is_kmalloc && (param_offset + param_size) > buff_len) - param_size = buff_len - param_offset; - - if (is_kmalloc) + if (is_kmalloc) { + /* Make sure we don't copy more data than available */ + if (param_offset + param_size > buff_len) + param_size = buff_len - param_offset; memcpy(param_read_buf, &desc_buf[param_offset], param_size); + } out: if (is_kmalloc) kfree(desc_buf); -- cgit v1.2.3 From 73cc291c270248567245f084dcdf5078069af6b5 Mon Sep 17 00:00:00 2001 From: Can Guo Date: Tue, 22 Sep 2020 00:09:04 -0700 Subject: scsi: ufs: Make sure clk scaling happens only when HBA is runtime ACTIVE If someone plays with the UFS clk scaling devfreq governor through sysfs, ufshcd_devfreq_scale may be called even when HBA is not runtime ACTIVE. This can lead to unexpected error. We cannot just protect it by calling pm_runtime_get_sync() because that may cause a race condition since HBA runtime suspend ops need to suspend clk scaling. To fix this call pm_runtime_get_noresume() and check HBA's runtime status. Only proceed if HBA is runtime ACTIVE, otherwise just bail. governor_store devfreq_performance_handler update_devfreq devfreq_set_target ufshcd_devfreq_target ufshcd_devfreq_scale Link: https://lore.kernel.org/r/1600758548-28576-1-git-send-email-cang@codeaurora.org Reviewed-by: Stanley Chu Signed-off-by: Can Guo Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 180e64dc6f2d..20b16de4c5e2 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -1294,8 +1294,15 @@ static int ufshcd_devfreq_target(struct device *dev, } spin_unlock_irqrestore(hba->host->host_lock, irq_flags); + pm_runtime_get_noresume(hba->dev); + if (!pm_runtime_active(hba->dev)) { + pm_runtime_put_noidle(hba->dev); + ret = -EAGAIN; + goto out; + } start = ktime_get(); ret = ufshcd_devfreq_scale(hba, scale_up); + pm_runtime_put(hba->dev); trace_ufshcd_profile_clk_scaling(dev_name(hba->dev), (scale_up ? "up" : "down"), -- cgit v1.2.3 From d2e3fce9ddafe689c6f7cb355f23560637e30b9d Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Tue, 10 Nov 2020 23:04:47 +0200 Subject: drm/i915: Handle max_bpc==16 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit EDID can declare the maximum supported bpc up to 16, and apparently there are displays that do so. Currently we assume 12 bpc is tha max. Fix the assumption and toss in a MISSING_CASE() for any other value we don't expect to see. This fixes modesets with a display with EDID max bpc > 12. Previously any modeset would just silently fail on platforms that didn't otherwise limit this via the max_bpc property. In particular we don't add the max_bpc property to HDMI ports on gmch platforms, and thus we would see the raw max_bpc coming from the EDID. I suppose we could already adjust this to also allow 16bpc, but seeing as no current platform supports that there is little point. Cc: stable@vger.kernel.org Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2632 Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20201110210447.27454-1-ville.syrjala@linux.intel.com Reviewed-by: José Roberto de Souza (cherry picked from commit 2ca5a7b85b0c2b97ef08afbd7799b022e29f192e) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/display/intel_display.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 31337d2a2cde..99e682563d47 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -12878,10 +12878,11 @@ compute_sink_pipe_bpp(const struct drm_connector_state *conn_state, case 10 ... 11: bpp = 10 * 3; break; - case 12: + case 12 ... 16: bpp = 12 * 3; break; default: + MISSING_CASE(conn_state->max_bpc); return -EINVAL; } -- cgit v1.2.3 From b4ca4354b42e59f13365a6901bdc5e729cf4adb4 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 18 Nov 2020 13:38:39 +0000 Subject: drm/i915/gt: Remember to free the virtual breadcrumbs Since we allocate some breadcrumbs for the virtual engine, and the virtual engine has a custom destructor, we also need to free the breadcrumbs after use. Fixes: b3786b29379c ("drm/i915/gt: Distinguish the virtual breadcrumbs from the irq breadcrumbs") Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20201118133839.1783-1-chris@chris-wilson.co.uk (cherry picked from commit 45e50f48b7907e650cfbbc7879abfe3a0c419c73) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_lrc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index f82c6dd1de18..9bb16bdf93cf 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -5457,6 +5457,7 @@ static void virtual_context_destroy(struct kref *kref) __execlists_context_fini(&ve->context); intel_context_fini(&ve->context); + intel_breadcrumbs_free(ve->base.breadcrumbs); intel_engine_free_request_pool(&ve->base); kfree(ve->bonds); -- cgit v1.2.3 From 65fb73676112f6fd107c5e542b2cbcfb206fe881 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Wed, 18 Nov 2020 16:19:00 +0200 Subject: bus: ti-sysc: suppress err msg for timers used as clockevent/source GP Timers used as clockevent/source are not available for ti-sysc bus and handled by Kernel timekeeping core. Now ti-sysc produces error message every time such timer is detected: "ti-sysc: probe of 48040000.target-module failed with error -16" Such messages are not necessary, so suppress them by returning -ENXIO instead of -EBUSY. Fixes: 6cfcd5563b4f ("clocksource/drivers/timer-ti-dm: Fix suspend and resume for am3 and am4") Signed-off-by: Grygorii Strashko Signed-off-by: Tony Lindgren --- drivers/bus/ti-sysc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 16132e6e91f8..92ecf1a78ec7 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -2889,7 +2889,7 @@ static int sysc_check_active_timer(struct sysc *ddata) if ((ddata->cfg.quirks & SYSC_QUIRK_NO_RESET_ON_INIT) && (ddata->cfg.quirks & SYSC_QUIRK_NO_IDLE)) - return -EBUSY; + return -ENXIO; return 0; } -- cgit v1.2.3 From 05d5de6ba7dbe490dd413b5ca11d0875bd2bc006 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 11 Nov 2020 15:12:11 +0100 Subject: ARM: dts: dra76x: m_can: fix order of clocks According to the bosch,m_can.yaml bindings the first clock shall be the "hclk", while the second clock "cclk". This patch fixes the order accordingly. Fixes: 0adbe832f21a ("ARM: dts: dra76x: Add MCAN node") Cc: Faiz Abbas Cc: Tony Lindgren Cc: linux-omap@vger.kernel.org Signed-off-by: Marc Kleine-Budde Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/dra76x.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/dra76x.dtsi b/arch/arm/boot/dts/dra76x.dtsi index b69c7d40f5d8..2f326151116b 100644 --- a/arch/arm/boot/dts/dra76x.dtsi +++ b/arch/arm/boot/dts/dra76x.dtsi @@ -32,8 +32,8 @@ interrupts = , ; interrupt-names = "int0", "int1"; - clocks = <&mcan_clk>, <&l3_iclk_div>; - clock-names = "cclk", "hclk"; + clocks = <&l3_iclk_div>, <&mcan_clk>; + clock-names = "hclk", "cclk"; bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>; }; }; -- cgit v1.2.3 From 3645a34f5b962aeedeb02f30cdf048eaae9b5f5c Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 19 Nov 2020 13:51:19 +0800 Subject: iommu/vt-d: Fix compile error with CONFIG_PCI_ATS not set MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the compile error below (CONFIG_PCI_ATS not set): drivers/iommu/intel/dmar.c: In function ‘vf_inherit_msi_domain’: drivers/iommu/intel/dmar.c:338:59: error: ‘struct pci_dev’ has no member named ‘physfn’; did you mean ‘is_physfn’? 338 | dev_set_msi_domain(&pdev->dev, dev_get_msi_domain(&pdev->physfn->dev)); | ^~~~~~ | is_physfn Fixes: ff828729be44 ("iommu/vt-d: Cure VF irqdomain hickup") Reported-by: Geert Uytterhoeven Signed-off-by: Lu Baolu Cc: Thomas Gleixner Link: https://lore.kernel.org/linux-iommu/CAMuHMdXA7wfJovmfSH2nbAhN0cPyCiFHodTvg4a8Hm9rx5Dj-w@mail.gmail.com/ Link: https://lore.kernel.org/r/20201119055119.2862701-1-baolu.lu@linux.intel.com Signed-off-by: Will Deacon --- drivers/iommu/intel/dmar.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index b2e804473209..11319e4dce4a 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -335,7 +335,9 @@ static void dmar_pci_bus_del_dev(struct dmar_pci_notify_info *info) static inline void vf_inherit_msi_domain(struct pci_dev *pdev) { - dev_set_msi_domain(&pdev->dev, dev_get_msi_domain(&pdev->physfn->dev)); + struct pci_dev *physfn = pci_physfn(pdev); + + dev_set_msi_domain(&pdev->dev, dev_get_msi_domain(&physfn->dev)); } static int dmar_pci_bus_notifier(struct notifier_block *nb, -- cgit v1.2.3 From 91c2c28d8de34815ea9bb4d16e9db7308ad33d3e Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 19 Nov 2020 11:12:17 +0000 Subject: MAINTAINERS: Temporarily add myself to the IOMMU entry Joerg is recovering from an injury, so temporarily add myself to the IOMMU MAINTAINERS entry so that I'm more likely to get CC'd on patches while I help to look after the tree for him. Suggested-by: Joerg Roedel Link: https://lore.kernel.org/r/20201117100953.GR22888@8bytes.org Signed-off-by: Will Deacon --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 3da6d8c154e4..9f60b7a25136 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9171,6 +9171,7 @@ F: include/linux/iomap.h IOMMU DRIVERS M: Joerg Roedel +M: Will Deacon L: iommu@lists.linux-foundation.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git -- cgit v1.2.3 From 551310e7356cb8af4eb4c618961ad1e7b2f89e19 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 19 Nov 2020 13:04:04 +0100 Subject: ALSA: hda/ca0132: Fix compile warning without PCI CONFIG_PCI=n leads to a compile warning like: sound/pci/hda/patch_ca0132.c:8214:10: warning: no case matching constant switch condition '0' due to the missed handling of QUIRK_NONE in ca0132_mmio_init(). Fix it. Fixes: bf2aa9ccc8e5 ("ALSA: hda/ca0132 - Cleanup ca0132_mmio_init function.") Reported-by: kernel test robot Link: https://lore.kernel.org/r/20201119120404.16833-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_ca0132.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index e0c38f2735c6..d8370a417e3d 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -9183,6 +9183,8 @@ static void ca0132_mmio_init(struct hda_codec *codec) case QUIRK_AE5: ca0132_mmio_init_ae5(codec); break; + default: + break; } } -- cgit v1.2.3 From fcb48454c23c5679d1a2e252f127642e91b05cbe Mon Sep 17 00:00:00 2001 From: Russell Currey Date: Tue, 17 Nov 2020 16:59:11 +1100 Subject: selftests/powerpc: rfi_flush: disable entry flush if present We are about to add an entry flush. The rfi (exit) flush test measures the number of L1D flushes over a syscall with the RFI flush enabled and disabled. But if the entry flush is also enabled, the effect of enabling and disabling the RFI flush is masked. If there is a debugfs entry for the entry flush, disable it during the RFI flush and restore it later. Reported-by: Spoorthy S Signed-off-by: Russell Currey Signed-off-by: Daniel Axtens Signed-off-by: Michael Ellerman --- .../testing/selftests/powerpc/security/rfi_flush.c | 35 ++++++++++++++++++---- 1 file changed, 29 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c index 93a65bd1f231..4e7b2776c367 100644 --- a/tools/testing/selftests/powerpc/security/rfi_flush.c +++ b/tools/testing/selftests/powerpc/security/rfi_flush.c @@ -85,19 +85,33 @@ int rfi_flush_test(void) __u64 l1d_misses_total = 0; unsigned long iterations = 100000, zero_size = 24 * 1024; unsigned long l1d_misses_expected; - int rfi_flush_org, rfi_flush; + int rfi_flush_orig, rfi_flush; + int have_entry_flush, entry_flush_orig; SKIP_IF(geteuid() != 0); // The PMU event we use only works on Power7 or later SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); - if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_org)) { + if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { perror("Unable to read powerpc/rfi_flush debugfs file"); SKIP_IF(1); } - rfi_flush = rfi_flush_org; + if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + have_entry_flush = 0; + } else { + have_entry_flush = 1; + + if (entry_flush_orig != 0) { + if (write_debugfs_file("powerpc/entry_flush", 0) < 0) { + perror("error writing to powerpc/entry_flush debugfs file"); + return 1; + } + } + } + + rfi_flush = rfi_flush_orig; fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1); FAIL_IF(fd < 0); @@ -106,6 +120,7 @@ int rfi_flush_test(void) FAIL_IF(perf_event_enable(fd)); + // disable L1 prefetching set_dscr(1); iter = repetitions; @@ -147,8 +162,8 @@ again: repetitions * l1d_misses_expected / 2, passes, repetitions); - if (rfi_flush == rfi_flush_org) { - rfi_flush = !rfi_flush_org; + if (rfi_flush == rfi_flush_orig) { + rfi_flush = !rfi_flush_orig; if (write_debugfs_file("powerpc/rfi_flush", rfi_flush) < 0) { perror("error writing to powerpc/rfi_flush debugfs file"); return 1; @@ -164,11 +179,19 @@ again: set_dscr(0); - if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_org) < 0) { + if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { perror("unable to restore original value of powerpc/rfi_flush debugfs file"); return 1; } + if (have_entry_flush) { + if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + perror("unable to restore original value of powerpc/entry_flush " + "debugfs file"); + return 1; + } + } + return rc; } -- cgit v1.2.3 From f79643787e0a0762d2409b7b8334e83f22d85695 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 17 Nov 2020 16:59:12 +1100 Subject: powerpc/64s: flush L1D on kernel entry IBM Power9 processors can speculatively operate on data in the L1 cache before it has been completely validated, via a way-prediction mechanism. It is not possible for an attacker to determine the contents of impermissible memory using this method, since these systems implement a combination of hardware and software security measures to prevent scenarios where protected data could be leaked. However these measures don't address the scenario where an attacker induces the operating system to speculatively execute instructions using data that the attacker controls. This can be used for example to speculatively bypass "kernel user access prevention" techniques, as discovered by Anthony Steinhauser of Google's Safeside Project. This is not an attack by itself, but there is a possibility it could be used in conjunction with side-channels or other weaknesses in the privileged code to construct an attack. This issue can be mitigated by flushing the L1 cache between privilege boundaries of concern. This patch flushes the L1 cache on kernel entry. This is part of the fix for CVE-2020-4788. Signed-off-by: Nicholas Piggin Signed-off-by: Daniel Axtens Signed-off-by: Michael Ellerman --- Documentation/admin-guide/kernel-parameters.txt | 3 ++ arch/powerpc/include/asm/exception-64s.h | 9 +++- arch/powerpc/include/asm/feature-fixups.h | 10 +++++ arch/powerpc/include/asm/security_features.h | 4 ++ arch/powerpc/include/asm/setup.h | 3 ++ arch/powerpc/kernel/exceptions-64s.S | 37 +++++++++++++++ arch/powerpc/kernel/setup_64.c | 60 ++++++++++++++++++++++++- arch/powerpc/kernel/vmlinux.lds.S | 7 +++ arch/powerpc/lib/feature-fixups.c | 54 ++++++++++++++++++++++ arch/powerpc/platforms/powernv/setup.c | 11 +++++ arch/powerpc/platforms/pseries/setup.c | 4 ++ 11 files changed, 200 insertions(+), 2 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 526d65d8573a..383889fe771f 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2858,6 +2858,7 @@ mds=off [X86] tsx_async_abort=off [X86] kvm.nx_huge_pages=off [X86] + no_entry_flush [PPC] Exceptions: This does not have any effect on @@ -3186,6 +3187,8 @@ noefi Disable EFI runtime services support. + no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel. + noexec [IA-64] noexec [X86] diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index ebe95aa04d53..83fa88bc9935 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -57,11 +57,18 @@ nop; \ nop +#define ENTRY_FLUSH_SLOT \ + ENTRY_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop; + /* * r10 must be free to use, r13 must be paca */ #define INTERRUPT_TO_KERNEL \ - STF_ENTRY_BARRIER_SLOT + STF_ENTRY_BARRIER_SLOT; \ + ENTRY_FLUSH_SLOT /* * Macros for annotating the expected destination of (h)rfid diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index b0af97add751..06a48219bbf2 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -205,6 +205,14 @@ label##3: \ FTR_ENTRY_OFFSET 955b-956b; \ .popsection; +#define ENTRY_FLUSH_FIXUP_SECTION \ +957: \ + .pushsection __entry_flush_fixup,"a"; \ + .align 2; \ +958: \ + FTR_ENTRY_OFFSET 957b-958b; \ + .popsection; + #define RFI_FLUSH_FIXUP_SECTION \ 951: \ .pushsection __rfi_flush_fixup,"a"; \ @@ -237,8 +245,10 @@ label##3: \ #include extern long stf_barrier_fallback; +extern long entry_flush_fallback; extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; +extern long __start___entry_flush_fixup, __stop___entry_flush_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index fbb8fa32150f..9e7459d2edca 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -86,12 +86,16 @@ static inline bool security_ftr_enabled(u64 feature) // Software required to flush link stack on context switch #define SEC_FTR_FLUSH_LINK_STACK 0x0000000000001000ull +// The L1-D cache should be flushed when entering the kernel +#define SEC_FTR_L1D_FLUSH_ENTRY 0x0000000000004000ull + // Features enabled by default #define SEC_FTR_DEFAULT \ (SEC_FTR_L1D_FLUSH_HV | \ SEC_FTR_L1D_FLUSH_PR | \ SEC_FTR_BNDS_CHK_SPEC_BAR | \ + SEC_FTR_L1D_FLUSH_ENTRY | \ SEC_FTR_FAVOUR_SECURITY) #endif /* _ASM_POWERPC_SECURITY_FEATURES_H */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 9efbddee2bca..e2fcd3e874f8 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -52,12 +52,15 @@ enum l1d_flush_type { }; void setup_rfi_flush(enum l1d_flush_type, bool enable); +void setup_entry_flush(bool enable); +void setup_uaccess_flush(bool enable); void do_rfi_flush_fixups(enum l1d_flush_type types); #ifdef CONFIG_PPC_BARRIER_NOSPEC void setup_barrier_nospec(void); #else static inline void setup_barrier_nospec(void) { }; #endif +void do_entry_flush_fixups(enum l1d_flush_type types); void do_barrier_nospec_fixups(bool enable); extern bool barrier_nospec_enabled; diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index f7d748b88705..5577dd887d37 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2951,6 +2951,43 @@ TRAMP_REAL_BEGIN(stf_barrier_fallback) .endr blr +TRAMP_REAL_BEGIN(entry_flush_fallback) + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) + ld r11,PACA_L1D_FLUSH_SIZE(r13) + srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ + mtctr r11 + DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ + + /* order ld/st prior to dcbt stop all streams with flushing */ + sync + + /* + * The load addresses are at staggered offsets within cachelines, + * which suits some pipelines better (on others it should not + * hurt). + */ +1: + ld r11,(0x80 + 8)*0(r10) + ld r11,(0x80 + 8)*1(r10) + ld r11,(0x80 + 8)*2(r10) + ld r11,(0x80 + 8)*3(r10) + ld r11,(0x80 + 8)*4(r10) + ld r11,(0x80 + 8)*5(r10) + ld r11,(0x80 + 8)*6(r10) + ld r11,(0x80 + 8)*7(r10) + addi r10,r10,0x80*8 + bdnz 1b + + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + blr + TRAMP_REAL_BEGIN(rfi_flush_fallback) SET_SCRATCH0(r13); GET_PACA(r13); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index bb9cab3641d7..7d447b43ad13 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -945,7 +945,9 @@ early_initcall(disable_hardlockup_detector); static enum l1d_flush_type enabled_flush_types; static void *l1d_flush_fallback_area; static bool no_rfi_flush; +static bool no_entry_flush; bool rfi_flush; +bool entry_flush; static int __init handle_no_rfi_flush(char *p) { @@ -955,6 +957,14 @@ static int __init handle_no_rfi_flush(char *p) } early_param("no_rfi_flush", handle_no_rfi_flush); +static int __init handle_no_entry_flush(char *p) +{ + pr_info("entry-flush: disabled on command line."); + no_entry_flush = true; + return 0; +} +early_param("no_entry_flush", handle_no_entry_flush); + /* * The RFI flush is not KPTI, but because users will see doco that says to use * nopti we hijack that option here to also disable the RFI flush. @@ -986,6 +996,18 @@ void rfi_flush_enable(bool enable) rfi_flush = enable; } +void entry_flush_enable(bool enable) +{ + if (enable) { + do_entry_flush_fixups(enabled_flush_types); + on_each_cpu(do_nothing, NULL, 1); + } else { + do_entry_flush_fixups(L1D_FLUSH_NONE); + } + + entry_flush = enable; +} + static void __ref init_fallback_flush(void) { u64 l1d_size, limit; @@ -1044,10 +1066,19 @@ void setup_rfi_flush(enum l1d_flush_type types, bool enable) enabled_flush_types = types; - if (!no_rfi_flush && !cpu_mitigations_off()) + if (!cpu_mitigations_off() && !no_rfi_flush) rfi_flush_enable(enable); } +void setup_entry_flush(bool enable) +{ + if (cpu_mitigations_off()) + return; + + if (!no_entry_flush) + entry_flush_enable(enable); +} + #ifdef CONFIG_DEBUG_FS static int rfi_flush_set(void *data, u64 val) { @@ -1075,9 +1106,36 @@ static int rfi_flush_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n"); +static int entry_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + /* Only do anything if we're changing state */ + if (enable != entry_flush) + entry_flush_enable(enable); + + return 0; +} + +static int entry_flush_get(void *data, u64 *val) +{ + *val = entry_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n"); + static __init int rfi_flush_debugfs_init(void) { debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush); + debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush); return 0; } device_initcall(rfi_flush_debugfs_init); diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index e0548b4950de..715ec4d4614a 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -131,6 +131,13 @@ SECTIONS __stop___stf_entry_barrier_fixup = .; } + . = ALIGN(8); + __entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) { + __start___entry_flush_fixup = .; + *(__entry_flush_fixup) + __stop___entry_flush_fixup = .; + } + . = ALIGN(8); __stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) { __start___stf_exit_barrier_fixup = .; diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 4c0a7ee9fa00..70e83cfd74aa 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -234,6 +234,60 @@ void do_stf_barrier_fixups(enum stf_barrier_type types) do_stf_exit_barrier_fixups(types); } +void do_entry_flush_fixups(enum l1d_flush_type types) +{ + unsigned int instrs[3], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___entry_flush_fixup); + end = PTRRELOC(&__stop___entry_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + + i = 0; + if (types == L1D_FLUSH_FALLBACK) { + instrs[i++] = 0x7d4802a6; /* mflr r10 */ + instrs[i++] = 0x60000000; /* branch patched below */ + instrs[i++] = 0x7d4803a6; /* mtlr r10 */ + } + + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + + if (types == L1D_FLUSH_FALLBACK) + patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&entry_flush_fallback, + BRANCH_SET_LINK); + else + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + } + + printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i, + (types == L1D_FLUSH_NONE) ? "no" : + (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : + (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG) + ? "ori+mttrig type" + : "ori type" : + (types & L1D_FLUSH_MTTRIG) ? "mttrig type" + : "unknown"); +} + void do_rfi_flush_fixups(enum l1d_flush_type types) { unsigned int instrs[3], *dest; diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 9acaa0f131b9..d04a085c423d 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -122,12 +122,23 @@ static void pnv_setup_rfi_flush(void) type = L1D_FLUSH_ORI; } + /* + * If we are non-Power9 bare metal, we don't need to flush on kernel + * entry: it fixes a P9 specific vulnerability. + */ + if (!pvr_version_is(PVR_POWER9)) + security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY); + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \ (security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR) || \ security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV)); setup_rfi_flush(type, enable); setup_count_cache_flush(); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY); + setup_entry_flush(enable); } static void __init pnv_check_guarded_cores(void) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 633c45ec406d..8136c5368ee4 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -579,6 +579,10 @@ void pseries_setup_rfi_flush(void) setup_rfi_flush(types, enable); setup_count_cache_flush(); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY); + setup_entry_flush(enable); } #ifdef CONFIG_PCI_IOV -- cgit v1.2.3 From 9a32a7e78bd0cd9a9b6332cbdc345ee5ffd0c5de Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 17 Nov 2020 16:59:13 +1100 Subject: powerpc/64s: flush L1D after user accesses IBM Power9 processors can speculatively operate on data in the L1 cache before it has been completely validated, via a way-prediction mechanism. It is not possible for an attacker to determine the contents of impermissible memory using this method, since these systems implement a combination of hardware and software security measures to prevent scenarios where protected data could be leaked. However these measures don't address the scenario where an attacker induces the operating system to speculatively execute instructions using data that the attacker controls. This can be used for example to speculatively bypass "kernel user access prevention" techniques, as discovered by Anthony Steinhauser of Google's Safeside Project. This is not an attack by itself, but there is a possibility it could be used in conjunction with side-channels or other weaknesses in the privileged code to construct an attack. This issue can be mitigated by flushing the L1 cache between privilege boundaries of concern. This patch flushes the L1 cache after user accesses. This is part of the fix for CVE-2020-4788. Signed-off-by: Nicholas Piggin Signed-off-by: Daniel Axtens Signed-off-by: Michael Ellerman --- Documentation/admin-guide/kernel-parameters.txt | 4 ++ arch/powerpc/include/asm/book3s/64/kup-radix.h | 66 ++++++++++++------- arch/powerpc/include/asm/exception-64s.h | 3 + arch/powerpc/include/asm/feature-fixups.h | 9 +++ arch/powerpc/include/asm/kup.h | 19 ++++-- arch/powerpc/include/asm/security_features.h | 3 + arch/powerpc/include/asm/setup.h | 1 + arch/powerpc/kernel/exceptions-64s.S | 85 ++++++++----------------- arch/powerpc/kernel/setup_64.c | 62 ++++++++++++++++++ arch/powerpc/kernel/vmlinux.lds.S | 7 ++ arch/powerpc/lib/feature-fixups.c | 50 +++++++++++++++ arch/powerpc/platforms/powernv/setup.c | 10 ++- arch/powerpc/platforms/pseries/setup.c | 4 ++ 13 files changed, 233 insertions(+), 90 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 383889fe771f..44fde25bb221 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2859,6 +2859,7 @@ tsx_async_abort=off [X86] kvm.nx_huge_pages=off [X86] no_entry_flush [PPC] + no_uaccess_flush [PPC] Exceptions: This does not have any effect on @@ -3238,6 +3239,9 @@ nospec_store_bypass_disable [HW] Disable all mitigations for the Speculative Store Bypass vulnerability + no_uaccess_flush + [PPC] Don't flush the L1-D cache after accessing user data. + noxsave [BUGS=X86] Disables x86 extended register state save and restore using xsave. The kernel will fallback to enabling legacy floating-point and sse state. diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h index 3ee1ec60be84..97c2394e7dea 100644 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -61,6 +61,8 @@ #else /* !__ASSEMBLY__ */ +DECLARE_STATIC_KEY_FALSE(uaccess_flush_key); + #ifdef CONFIG_PPC_KUAP #include @@ -103,8 +105,16 @@ static inline void kuap_check_amr(void) static inline unsigned long get_kuap(void) { + /* + * We return AMR_KUAP_BLOCKED when we don't support KUAP because + * prevent_user_access_return needs to return AMR_KUAP_BLOCKED to + * cause restore_user_access to do a flush. + * + * This has no effect in terms of actually blocking things on hash, + * so it doesn't break anything. + */ if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP)) - return 0; + return AMR_KUAP_BLOCKED; return mfspr(SPRN_AMR); } @@ -123,6 +133,31 @@ static inline void set_kuap(unsigned long value) isync(); } +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) && + (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)), + "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read"); +} +#else /* CONFIG_PPC_KUAP */ +static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr) { } + +static inline unsigned long kuap_get_and_check_amr(void) +{ + return 0UL; +} + +static inline void kuap_check_amr(void) { } + +static inline unsigned long get_kuap(void) +{ + return AMR_KUAP_BLOCKED; +} + +static inline void set_kuap(unsigned long value) { } +#endif /* !CONFIG_PPC_KUAP */ + static __always_inline void allow_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { @@ -142,6 +177,8 @@ static inline void prevent_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { set_kuap(AMR_KUAP_BLOCKED); + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); } static inline unsigned long prevent_user_access_return(void) @@ -149,6 +186,8 @@ static inline unsigned long prevent_user_access_return(void) unsigned long flags = get_kuap(); set_kuap(AMR_KUAP_BLOCKED); + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); return flags; } @@ -156,30 +195,9 @@ static inline unsigned long prevent_user_access_return(void) static inline void restore_user_access(unsigned long flags) { set_kuap(flags); + if (static_branch_unlikely(&uaccess_flush_key) && flags == AMR_KUAP_BLOCKED) + do_uaccess_flush(); } - -static inline bool -bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) -{ - return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) && - (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)), - "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read"); -} -#else /* CONFIG_PPC_KUAP */ -static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr) -{ -} - -static inline void kuap_check_amr(void) -{ -} - -static inline unsigned long kuap_get_and_check_amr(void) -{ - return 0; -} -#endif /* CONFIG_PPC_KUAP */ - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */ diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 83fa88bc9935..1d32b174ab6a 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -144,6 +144,9 @@ RFSCV; \ b rfscv_flush_fallback +#else /* __ASSEMBLY__ */ +/* Prototype for function defined in exceptions-64s.S */ +void do_uaccess_flush(void); #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_EXCEPTION_H */ diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index 06a48219bbf2..fbd406cd6916 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -205,6 +205,14 @@ label##3: \ FTR_ENTRY_OFFSET 955b-956b; \ .popsection; +#define UACCESS_FLUSH_FIXUP_SECTION \ +959: \ + .pushsection __uaccess_flush_fixup,"a"; \ + .align 2; \ +960: \ + FTR_ENTRY_OFFSET 959b-960b; \ + .popsection; + #define ENTRY_FLUSH_FIXUP_SECTION \ 957: \ .pushsection __entry_flush_fixup,"a"; \ @@ -248,6 +256,7 @@ extern long stf_barrier_fallback; extern long entry_flush_fallback; extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; +extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup; extern long __start___entry_flush_fixup, __stop___entry_flush_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h index 1d0f7d838b2e..0f5c606ae057 100644 --- a/arch/powerpc/include/asm/kup.h +++ b/arch/powerpc/include/asm/kup.h @@ -53,17 +53,26 @@ static inline void setup_kuep(bool disabled) { } void setup_kuap(bool disabled); #else static inline void setup_kuap(bool disabled) { } + +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + return false; +} + +/* + * book3s/64/kup-radix.h defines these functions for the !KUAP case to flush + * the L1D cache after user accesses. Only include the empty stubs for other + * platforms. + */ +#ifndef CONFIG_PPC64 static inline void allow_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { } static inline void prevent_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { } static inline unsigned long prevent_user_access_return(void) { return 0UL; } static inline void restore_user_access(unsigned long flags) { } -static inline bool -bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) -{ - return false; -} +#endif /* CONFIG_PPC64 */ #endif /* CONFIG_PPC_KUAP */ static inline void allow_read_from_user(const void __user *from, unsigned long size) diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index 9e7459d2edca..b774a4477d5f 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -89,6 +89,8 @@ static inline bool security_ftr_enabled(u64 feature) // The L1-D cache should be flushed when entering the kernel #define SEC_FTR_L1D_FLUSH_ENTRY 0x0000000000004000ull +// The L1-D cache should be flushed after user accesses from the kernel +#define SEC_FTR_L1D_FLUSH_UACCESS 0x0000000000008000ull // Features enabled by default #define SEC_FTR_DEFAULT \ @@ -96,6 +98,7 @@ static inline bool security_ftr_enabled(u64 feature) SEC_FTR_L1D_FLUSH_PR | \ SEC_FTR_BNDS_CHK_SPEC_BAR | \ SEC_FTR_L1D_FLUSH_ENTRY | \ + SEC_FTR_L1D_FLUSH_UACCESS | \ SEC_FTR_FAVOUR_SECURITY) #endif /* _ASM_POWERPC_SECURITY_FEATURES_H */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index e2fcd3e874f8..a466749703f1 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -60,6 +60,7 @@ void setup_barrier_nospec(void); #else static inline void setup_barrier_nospec(void) { }; #endif +void do_uaccess_flush_fixups(enum l1d_flush_type types); void do_entry_flush_fixups(enum l1d_flush_type types); void do_barrier_nospec_fixups(bool enable); extern bool barrier_nospec_enabled; diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 5577dd887d37..f63a3d3bca3d 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2951,11 +2951,8 @@ TRAMP_REAL_BEGIN(stf_barrier_fallback) .endr blr -TRAMP_REAL_BEGIN(entry_flush_fallback) - std r9,PACA_EXRFI+EX_R9(r13) - std r10,PACA_EXRFI+EX_R10(r13) - std r11,PACA_EXRFI+EX_R11(r13) - mfctr r9 +/* Clobbers r10, r11, ctr */ +.macro L1D_DISPLACEMENT_FLUSH ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) ld r11,PACA_L1D_FLUSH_SIZE(r13) srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ @@ -2981,7 +2978,14 @@ TRAMP_REAL_BEGIN(entry_flush_fallback) ld r11,(0x80 + 8)*7(r10) addi r10,r10,0x80*8 bdnz 1b +.endm +TRAMP_REAL_BEGIN(entry_flush_fallback) + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + L1D_DISPLACEMENT_FLUSH mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) @@ -2997,32 +3001,7 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) std r10,PACA_EXRFI+EX_R10(r13) std r11,PACA_EXRFI+EX_R11(r13) mfctr r9 - ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) - ld r11,PACA_L1D_FLUSH_SIZE(r13) - srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ - mtctr r11 - DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ - - /* order ld/st prior to dcbt stop all streams with flushing */ - sync - - /* - * The load adresses are at staggered offsets within cachelines, - * which suits some pipelines better (on others it should not - * hurt). - */ -1: - ld r11,(0x80 + 8)*0(r10) - ld r11,(0x80 + 8)*1(r10) - ld r11,(0x80 + 8)*2(r10) - ld r11,(0x80 + 8)*3(r10) - ld r11,(0x80 + 8)*4(r10) - ld r11,(0x80 + 8)*5(r10) - ld r11,(0x80 + 8)*6(r10) - ld r11,(0x80 + 8)*7(r10) - addi r10,r10,0x80*8 - bdnz 1b - + L1D_DISPLACEMENT_FLUSH mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) @@ -3040,32 +3019,7 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) std r10,PACA_EXRFI+EX_R10(r13) std r11,PACA_EXRFI+EX_R11(r13) mfctr r9 - ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) - ld r11,PACA_L1D_FLUSH_SIZE(r13) - srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ - mtctr r11 - DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ - - /* order ld/st prior to dcbt stop all streams with flushing */ - sync - - /* - * The load adresses are at staggered offsets within cachelines, - * which suits some pipelines better (on others it should not - * hurt). - */ -1: - ld r11,(0x80 + 8)*0(r10) - ld r11,(0x80 + 8)*1(r10) - ld r11,(0x80 + 8)*2(r10) - ld r11,(0x80 + 8)*3(r10) - ld r11,(0x80 + 8)*4(r10) - ld r11,(0x80 + 8)*5(r10) - ld r11,(0x80 + 8)*6(r10) - ld r11,(0x80 + 8)*7(r10) - addi r10,r10,0x80*8 - bdnz 1b - + L1D_DISPLACEMENT_FLUSH mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) @@ -3116,8 +3070,21 @@ TRAMP_REAL_BEGIN(rfscv_flush_fallback) RFSCV USE_TEXT_SECTION() - MASKED_INTERRUPT - MASKED_INTERRUPT hsrr=1 + +_GLOBAL(do_uaccess_flush) + UACCESS_FLUSH_FIXUP_SECTION + nop + nop + nop + blr + L1D_DISPLACEMENT_FLUSH + blr +_ASM_NOKPROBE_SYMBOL(do_uaccess_flush) +EXPORT_SYMBOL(do_uaccess_flush) + + +MASKED_INTERRUPT +MASKED_INTERRUPT hsrr=1 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER kvmppc_skip_interrupt: diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 7d447b43ad13..74fd47f46fa5 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -946,8 +946,12 @@ static enum l1d_flush_type enabled_flush_types; static void *l1d_flush_fallback_area; static bool no_rfi_flush; static bool no_entry_flush; +static bool no_uaccess_flush; bool rfi_flush; bool entry_flush; +bool uaccess_flush; +DEFINE_STATIC_KEY_FALSE(uaccess_flush_key); +EXPORT_SYMBOL(uaccess_flush_key); static int __init handle_no_rfi_flush(char *p) { @@ -965,6 +969,14 @@ static int __init handle_no_entry_flush(char *p) } early_param("no_entry_flush", handle_no_entry_flush); +static int __init handle_no_uaccess_flush(char *p) +{ + pr_info("uaccess-flush: disabled on command line."); + no_uaccess_flush = true; + return 0; +} +early_param("no_uaccess_flush", handle_no_uaccess_flush); + /* * The RFI flush is not KPTI, but because users will see doco that says to use * nopti we hijack that option here to also disable the RFI flush. @@ -1008,6 +1020,20 @@ void entry_flush_enable(bool enable) entry_flush = enable; } +void uaccess_flush_enable(bool enable) +{ + if (enable) { + do_uaccess_flush_fixups(enabled_flush_types); + static_branch_enable(&uaccess_flush_key); + on_each_cpu(do_nothing, NULL, 1); + } else { + static_branch_disable(&uaccess_flush_key); + do_uaccess_flush_fixups(L1D_FLUSH_NONE); + } + + uaccess_flush = enable; +} + static void __ref init_fallback_flush(void) { u64 l1d_size, limit; @@ -1079,6 +1105,15 @@ void setup_entry_flush(bool enable) entry_flush_enable(enable); } +void setup_uaccess_flush(bool enable) +{ + if (cpu_mitigations_off()) + return; + + if (!no_uaccess_flush) + uaccess_flush_enable(enable); +} + #ifdef CONFIG_DEBUG_FS static int rfi_flush_set(void *data, u64 val) { @@ -1132,10 +1167,37 @@ static int entry_flush_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n"); +static int uaccess_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + /* Only do anything if we're changing state */ + if (enable != uaccess_flush) + uaccess_flush_enable(enable); + + return 0; +} + +static int uaccess_flush_get(void *data, u64 *val) +{ + *val = uaccess_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set, "%llu\n"); + static __init int rfi_flush_debugfs_init(void) { debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush); debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush); + debugfs_create_file("uaccess_flush", 0600, powerpc_debugfs_root, NULL, &fops_uaccess_flush); return 0; } device_initcall(rfi_flush_debugfs_init); diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 715ec4d4614a..6db90cdf11da 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -131,6 +131,13 @@ SECTIONS __stop___stf_entry_barrier_fixup = .; } + . = ALIGN(8); + __uaccess_flush_fixup : AT(ADDR(__uaccess_flush_fixup) - LOAD_OFFSET) { + __start___uaccess_flush_fixup = .; + *(__uaccess_flush_fixup) + __stop___uaccess_flush_fixup = .; + } + . = ALIGN(8); __entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) { __start___entry_flush_fixup = .; diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 70e83cfd74aa..321c12a9ef6b 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -234,6 +234,56 @@ void do_stf_barrier_fixups(enum stf_barrier_type types) do_stf_exit_barrier_fixups(types); } +void do_uaccess_flush_fixups(enum l1d_flush_type types) +{ + unsigned int instrs[4], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___uaccess_flush_fixup); + end = PTRRELOC(&__stop___uaccess_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + instrs[3] = 0x4e800020; /* blr */ + + i = 0; + if (types == L1D_FLUSH_FALLBACK) { + instrs[3] = 0x60000000; /* nop */ + /* fallthrough to fallback flush */ + } + + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)(dest + 3), ppc_inst(instrs[3])); + } + + printk(KERN_DEBUG "uaccess-flush: patched %d locations (%s flush)\n", i, + (types == L1D_FLUSH_NONE) ? "no" : + (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : + (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG) + ? "ori+mttrig type" + : "ori type" : + (types & L1D_FLUSH_MTTRIG) ? "mttrig type" + : "unknown"); +} + void do_entry_flush_fixups(enum l1d_flush_type types) { unsigned int instrs[3], *dest; diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index d04a085c423d..087ec92acfc4 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -124,10 +124,12 @@ static void pnv_setup_rfi_flush(void) /* * If we are non-Power9 bare metal, we don't need to flush on kernel - * entry: it fixes a P9 specific vulnerability. + * entry or after user access: they fix a P9 specific vulnerability. */ - if (!pvr_version_is(PVR_POWER9)) + if (!pvr_version_is(PVR_POWER9)) { security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY); + security_ftr_clear(SEC_FTR_L1D_FLUSH_UACCESS); + } enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \ (security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR) || \ @@ -139,6 +141,10 @@ static void pnv_setup_rfi_flush(void) enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY); setup_entry_flush(enable); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS); + setup_uaccess_flush(enable); } static void __init pnv_check_guarded_cores(void) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 8136c5368ee4..3617cdb079f6 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -583,6 +583,10 @@ void pseries_setup_rfi_flush(void) enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY); setup_entry_flush(enable); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS); + setup_uaccess_flush(enable); } #ifdef CONFIG_PCI_IOV -- cgit v1.2.3 From 178d52c6e89c38d0553b0ac8b99927b11eb995b0 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 19 Nov 2020 23:43:53 +1100 Subject: powerpc: Only include kup-radix.h for 64-bit Book3S In kup.h we currently include kup-radix.h for all 64-bit builds, which includes Book3S and Book3E. The latter doesn't make sense, Book3E never uses the Radix MMU. This has worked up until now, but almost by accident, and the recent uaccess flush changes introduced a build breakage on Book3E because of the bad structure of the code. So disentangle things so that we only use kup-radix.h for Book3S. This requires some more stubs in kup.h and fixing an include in syscall_64.c. Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/kup-radix.h | 4 ++-- arch/powerpc/include/asm/kup.h | 11 ++++++++--- arch/powerpc/kernel/syscall_64.c | 2 +- 3 files changed, 11 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h index 97c2394e7dea..28716e2f13e3 100644 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -27,6 +27,7 @@ #endif .endm +#ifdef CONFIG_PPC_KUAP .macro kuap_check_amr gpr1, gpr2 #ifdef CONFIG_PPC_KUAP_DEBUG BEGIN_MMU_FTR_SECTION_NESTED(67) @@ -38,6 +39,7 @@ END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67) #endif .endm +#endif .macro kuap_save_amr_and_lock gpr1, gpr2, use_cr, msr_pr_cr #ifdef CONFIG_PPC_KUAP @@ -148,8 +150,6 @@ static inline unsigned long kuap_get_and_check_amr(void) return 0UL; } -static inline void kuap_check_amr(void) { } - static inline unsigned long get_kuap(void) { return AMR_KUAP_BLOCKED; diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h index 0f5c606ae057..0d93331d0fab 100644 --- a/arch/powerpc/include/asm/kup.h +++ b/arch/powerpc/include/asm/kup.h @@ -14,7 +14,7 @@ #define KUAP_CURRENT_WRITE 8 #define KUAP_CURRENT (KUAP_CURRENT_READ | KUAP_CURRENT_WRITE) -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S_64 #include #endif #ifdef CONFIG_PPC_8xx @@ -35,6 +35,9 @@ .macro kuap_check current, gpr .endm +.macro kuap_check_amr gpr1, gpr2 +.endm + #endif #else /* !__ASSEMBLY__ */ @@ -60,19 +63,21 @@ bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) return false; } +static inline void kuap_check_amr(void) { } + /* * book3s/64/kup-radix.h defines these functions for the !KUAP case to flush * the L1D cache after user accesses. Only include the empty stubs for other * platforms. */ -#ifndef CONFIG_PPC64 +#ifndef CONFIG_PPC_BOOK3S_64 static inline void allow_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { } static inline void prevent_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { } static inline unsigned long prevent_user_access_return(void) { return 0UL; } static inline void restore_user_access(unsigned long flags) { } -#endif /* CONFIG_PPC64 */ +#endif /* CONFIG_PPC_BOOK3S_64 */ #endif /* CONFIG_PPC_KUAP */ static inline void allow_read_from_user(const void __user *from, unsigned long size) diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c index 8e50818aa50b..310bcd768cd5 100644 --- a/arch/powerpc/kernel/syscall_64.c +++ b/arch/powerpc/kernel/syscall_64.c @@ -2,7 +2,7 @@ #include #include -#include +#include #include #include #include -- cgit v1.2.3 From 89a83a0c69c81a25ce91002b90ca27ed86132a0a Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Tue, 17 Nov 2020 16:59:14 +1100 Subject: selftests/powerpc: entry flush test Add a test modelled on the RFI flush test which counts the number of L1D misses doing a simple syscall with the entry flush on and off. For simplicity of backporting, this test duplicates a lot of code from rfi_flush. We clean that up in the next patch. Signed-off-by: Daniel Axtens Signed-off-by: Michael Ellerman --- .../testing/selftests/powerpc/security/.gitignore | 1 + tools/testing/selftests/powerpc/security/Makefile | 2 +- .../selftests/powerpc/security/entry_flush.c | 198 +++++++++++++++++++++ 3 files changed, 200 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/powerpc/security/entry_flush.c diff --git a/tools/testing/selftests/powerpc/security/.gitignore b/tools/testing/selftests/powerpc/security/.gitignore index f795e06f5ae3..4257a1f156bb 100644 --- a/tools/testing/selftests/powerpc/security/.gitignore +++ b/tools/testing/selftests/powerpc/security/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only rfi_flush +entry_flush diff --git a/tools/testing/selftests/powerpc/security/Makefile b/tools/testing/selftests/powerpc/security/Makefile index eadbbff50be6..921152caf1dc 100644 --- a/tools/testing/selftests/powerpc/security/Makefile +++ b/tools/testing/selftests/powerpc/security/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0+ -TEST_GEN_PROGS := rfi_flush spectre_v2 +TEST_GEN_PROGS := rfi_flush entry_flush spectre_v2 top_srcdir = ../../../../.. CFLAGS += -I../../../../../usr/include diff --git a/tools/testing/selftests/powerpc/security/entry_flush.c b/tools/testing/selftests/powerpc/security/entry_flush.c new file mode 100644 index 000000000000..7ae7e37204c5 --- /dev/null +++ b/tools/testing/selftests/powerpc/security/entry_flush.c @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Copyright 2018 IBM Corporation. + */ + +#define __SANE_USERSPACE_TYPES__ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "utils.h" + +#define CACHELINE_SIZE 128 + +struct perf_event_read { + __u64 nr; + __u64 l1d_misses; +}; + +static inline __u64 load(void *addr) +{ + __u64 tmp; + + asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr)); + + return tmp; +} + +static void syscall_loop(char *p, unsigned long iterations, + unsigned long zero_size) +{ + for (unsigned long i = 0; i < iterations; i++) { + for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE) + load(p + j); + getppid(); + } +} + +static void sigill_handler(int signr, siginfo_t *info, void *unused) +{ + static int warned; + ucontext_t *ctx = (ucontext_t *)unused; + unsigned long *pc = &UCONTEXT_NIA(ctx); + + /* mtspr 3,RS to check for move to DSCR below */ + if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) { + if (!warned++) + printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n"); + *pc += 4; + } else { + printf("SIGILL at %p\n", pc); + abort(); + } +} + +static void set_dscr(unsigned long val) +{ + static int init; + struct sigaction sa; + + if (!init) { + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = sigill_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGILL, &sa, NULL)) + perror("sigill_handler"); + init = 1; + } + + asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); +} + +int entry_flush_test(void) +{ + char *p; + int repetitions = 10; + int fd, passes = 0, iter, rc = 0; + struct perf_event_read v; + __u64 l1d_misses_total = 0; + unsigned long iterations = 100000, zero_size = 24 * 1024; + unsigned long l1d_misses_expected; + int rfi_flush_orig; + int entry_flush, entry_flush_orig; + + SKIP_IF(geteuid() != 0); + + // The PMU event we use only works on Power7 or later + SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); + + if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { + perror("Unable to read powerpc/rfi_flush debugfs file"); + SKIP_IF(1); + } + + if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + perror("Unable to read powerpc/entry_flush debugfs file"); + SKIP_IF(1); + } + + if (rfi_flush_orig != 0) { + if (write_debugfs_file("powerpc/rfi_flush", 0) < 0) { + perror("error writing to powerpc/rfi_flush debugfs file"); + FAIL_IF(1); + } + } + + entry_flush = entry_flush_orig; + + fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1); + FAIL_IF(fd < 0); + + p = (char *)memalign(zero_size, CACHELINE_SIZE); + + FAIL_IF(perf_event_enable(fd)); + + // disable L1 prefetching + set_dscr(1); + + iter = repetitions; + + /* + * We expect to see l1d miss for each cacheline access when entry_flush + * is set. Allow a small variation on this. + */ + l1d_misses_expected = iterations * (zero_size / CACHELINE_SIZE - 2); + +again: + FAIL_IF(perf_event_reset(fd)); + + syscall_loop(p, iterations, zero_size); + + FAIL_IF(read(fd, &v, sizeof(v)) != sizeof(v)); + + if (entry_flush && v.l1d_misses >= l1d_misses_expected) + passes++; + else if (!entry_flush && v.l1d_misses < (l1d_misses_expected / 2)) + passes++; + + l1d_misses_total += v.l1d_misses; + + while (--iter) + goto again; + + if (passes < repetitions) { + printf("FAIL (L1D misses with entry_flush=%d: %llu %c %lu) [%d/%d failures]\n", + entry_flush, l1d_misses_total, entry_flush ? '<' : '>', + entry_flush ? repetitions * l1d_misses_expected : + repetitions * l1d_misses_expected / 2, + repetitions - passes, repetitions); + rc = 1; + } else { + printf("PASS (L1D misses with entry_flush=%d: %llu %c %lu) [%d/%d pass]\n", + entry_flush, l1d_misses_total, entry_flush ? '>' : '<', + entry_flush ? repetitions * l1d_misses_expected : + repetitions * l1d_misses_expected / 2, + passes, repetitions); + } + + if (entry_flush == entry_flush_orig) { + entry_flush = !entry_flush_orig; + if (write_debugfs_file("powerpc/entry_flush", entry_flush) < 0) { + perror("error writing to powerpc/entry_flush debugfs file"); + return 1; + } + iter = repetitions; + l1d_misses_total = 0; + passes = 0; + goto again; + } + + perf_event_disable(fd); + close(fd); + + set_dscr(0); + + if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { + perror("unable to restore original value of powerpc/rfi_flush debugfs file"); + return 1; + } + + if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + perror("unable to restore original value of powerpc/entry_flush debugfs file"); + return 1; + } + + return rc; +} + +int main(int argc, char *argv[]) +{ + return test_harness(entry_flush_test, "entry_flush_test"); +} -- cgit v1.2.3 From 0d239f3b03efc78fb5b290aff6c747fecd3b98cb Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Tue, 17 Nov 2020 16:59:15 +1100 Subject: selftests/powerpc: refactor entry and rfi_flush tests For simplicity in backporting, the original entry_flush test contained a lot of duplicated code from the rfi_flush test. De-duplicate that code. Signed-off-by: Daniel Axtens Signed-off-by: Michael Ellerman --- tools/testing/selftests/powerpc/include/utils.h | 5 ++ tools/testing/selftests/powerpc/security/Makefile | 2 + .../selftests/powerpc/security/entry_flush.c | 61 +------------------ .../selftests/powerpc/security/flush_utils.c | 70 ++++++++++++++++++++++ .../selftests/powerpc/security/flush_utils.h | 17 ++++++ .../testing/selftests/powerpc/security/rfi_flush.c | 61 +------------------ 6 files changed, 96 insertions(+), 120 deletions(-) create mode 100644 tools/testing/selftests/powerpc/security/flush_utils.c create mode 100644 tools/testing/selftests/powerpc/security/flush_utils.h diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index 052b5a775dc2..b7d188fc87c7 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -42,6 +42,11 @@ int perf_event_enable(int fd); int perf_event_disable(int fd); int perf_event_reset(int fd); +struct perf_event_read { + __u64 nr; + __u64 l1d_misses; +}; + #if !defined(__GLIBC_PREREQ) || !__GLIBC_PREREQ(2, 30) #include #include diff --git a/tools/testing/selftests/powerpc/security/Makefile b/tools/testing/selftests/powerpc/security/Makefile index 921152caf1dc..f25e854fe370 100644 --- a/tools/testing/selftests/powerpc/security/Makefile +++ b/tools/testing/selftests/powerpc/security/Makefile @@ -11,3 +11,5 @@ $(TEST_GEN_PROGS): ../harness.c ../utils.c $(OUTPUT)/spectre_v2: CFLAGS += -m64 $(OUTPUT)/spectre_v2: ../pmu/event.c branch_loops.S +$(OUTPUT)/rfi_flush: flush_utils.c +$(OUTPUT)/entry_flush: flush_utils.c diff --git a/tools/testing/selftests/powerpc/security/entry_flush.c b/tools/testing/selftests/powerpc/security/entry_flush.c index 7ae7e37204c5..78cf914fa321 100644 --- a/tools/testing/selftests/powerpc/security/entry_flush.c +++ b/tools/testing/selftests/powerpc/security/entry_flush.c @@ -15,66 +15,7 @@ #include #include #include "utils.h" - -#define CACHELINE_SIZE 128 - -struct perf_event_read { - __u64 nr; - __u64 l1d_misses; -}; - -static inline __u64 load(void *addr) -{ - __u64 tmp; - - asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr)); - - return tmp; -} - -static void syscall_loop(char *p, unsigned long iterations, - unsigned long zero_size) -{ - for (unsigned long i = 0; i < iterations; i++) { - for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE) - load(p + j); - getppid(); - } -} - -static void sigill_handler(int signr, siginfo_t *info, void *unused) -{ - static int warned; - ucontext_t *ctx = (ucontext_t *)unused; - unsigned long *pc = &UCONTEXT_NIA(ctx); - - /* mtspr 3,RS to check for move to DSCR below */ - if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) { - if (!warned++) - printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n"); - *pc += 4; - } else { - printf("SIGILL at %p\n", pc); - abort(); - } -} - -static void set_dscr(unsigned long val) -{ - static int init; - struct sigaction sa; - - if (!init) { - memset(&sa, 0, sizeof(sa)); - sa.sa_sigaction = sigill_handler; - sa.sa_flags = SA_SIGINFO; - if (sigaction(SIGILL, &sa, NULL)) - perror("sigill_handler"); - init = 1; - } - - asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); -} +#include "flush_utils.h" int entry_flush_test(void) { diff --git a/tools/testing/selftests/powerpc/security/flush_utils.c b/tools/testing/selftests/powerpc/security/flush_utils.c new file mode 100644 index 000000000000..0c3c4c40c7fb --- /dev/null +++ b/tools/testing/selftests/powerpc/security/flush_utils.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Copyright 2018 IBM Corporation. + */ + +#define __SANE_USERSPACE_TYPES__ + +#include +#include +#include +#include +#include +#include +#include +#include "utils.h" +#include "flush_utils.h" + +static inline __u64 load(void *addr) +{ + __u64 tmp; + + asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr)); + + return tmp; +} + +void syscall_loop(char *p, unsigned long iterations, + unsigned long zero_size) +{ + for (unsigned long i = 0; i < iterations; i++) { + for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE) + load(p + j); + getppid(); + } +} + +static void sigill_handler(int signr, siginfo_t *info, void *unused) +{ + static int warned; + ucontext_t *ctx = (ucontext_t *)unused; + unsigned long *pc = &UCONTEXT_NIA(ctx); + + /* mtspr 3,RS to check for move to DSCR below */ + if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) { + if (!warned++) + printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n"); + *pc += 4; + } else { + printf("SIGILL at %p\n", pc); + abort(); + } +} + +void set_dscr(unsigned long val) +{ + static int init; + struct sigaction sa; + + if (!init) { + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = sigill_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGILL, &sa, NULL)) + perror("sigill_handler"); + init = 1; + } + + asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); +} diff --git a/tools/testing/selftests/powerpc/security/flush_utils.h b/tools/testing/selftests/powerpc/security/flush_utils.h new file mode 100644 index 000000000000..07a5eb301466 --- /dev/null +++ b/tools/testing/selftests/powerpc/security/flush_utils.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +/* + * Copyright 2018 IBM Corporation. + */ + +#ifndef _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H +#define _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H + +#define CACHELINE_SIZE 128 + +void syscall_loop(char *p, unsigned long iterations, + unsigned long zero_size); + +void set_dscr(unsigned long val); + +#endif /* _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H */ diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c index 4e7b2776c367..7565fd786640 100644 --- a/tools/testing/selftests/powerpc/security/rfi_flush.c +++ b/tools/testing/selftests/powerpc/security/rfi_flush.c @@ -10,71 +10,12 @@ #include #include #include -#include #include #include #include #include "utils.h" +#include "flush_utils.h" -#define CACHELINE_SIZE 128 - -struct perf_event_read { - __u64 nr; - __u64 l1d_misses; -}; - -static inline __u64 load(void *addr) -{ - __u64 tmp; - - asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr)); - - return tmp; -} - -static void syscall_loop(char *p, unsigned long iterations, - unsigned long zero_size) -{ - for (unsigned long i = 0; i < iterations; i++) { - for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE) - load(p + j); - getppid(); - } -} - -static void sigill_handler(int signr, siginfo_t *info, void *unused) -{ - static int warned = 0; - ucontext_t *ctx = (ucontext_t *)unused; - unsigned long *pc = &UCONTEXT_NIA(ctx); - - /* mtspr 3,RS to check for move to DSCR below */ - if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) { - if (!warned++) - printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n"); - *pc += 4; - } else { - printf("SIGILL at %p\n", pc); - abort(); - } -} - -static void set_dscr(unsigned long val) -{ - static int init = 0; - struct sigaction sa; - - if (!init) { - memset(&sa, 0, sizeof(sa)); - sa.sa_sigaction = sigill_handler; - sa.sa_flags = SA_SIGINFO; - if (sigaction(SIGILL, &sa, NULL)) - perror("sigill_handler"); - init = 1; - } - - asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); -} int rfi_flush_test(void) { -- cgit v1.2.3 From da631f7fd623b6c180c8d93a93040d1e0d61291f Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Tue, 17 Nov 2020 16:59:16 +1100 Subject: powerpc/64s: rename pnv|pseries_setup_rfi_flush to _setup_security_mitigations pseries|pnv_setup_rfi_flush already does the count cache flush setup, and we just added entry and uaccess flushes. So the name is not very accurate any more. In both platforms we then also immediately setup the STF flush. Rename them to _setup_security_mitigations and fold the STF flush in. Signed-off-by: Daniel Axtens Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/powernv/setup.c | 7 ++++--- arch/powerpc/platforms/pseries/mobility.c | 4 ++-- arch/powerpc/platforms/pseries/pseries.h | 2 +- arch/powerpc/platforms/pseries/setup.c | 7 ++++--- 4 files changed, 11 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 087ec92acfc4..46115231a3b2 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -98,7 +98,7 @@ static void init_fw_feat_flags(struct device_node *np) security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR); } -static void pnv_setup_rfi_flush(void) +static void pnv_setup_security_mitigations(void) { struct device_node *np, *fw_features; enum l1d_flush_type type; @@ -145,6 +145,8 @@ static void pnv_setup_rfi_flush(void) enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS); setup_uaccess_flush(enable); + + setup_stf_barrier(); } static void __init pnv_check_guarded_cores(void) @@ -173,8 +175,7 @@ static void __init pnv_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); - pnv_setup_rfi_flush(); - setup_stf_barrier(); + pnv_setup_security_mitigations(); /* Initialize SMP */ pnv_smp_init(); diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index d6f4162478a5..2f73cb5bf12d 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -349,8 +349,8 @@ void post_mobility_fixup(void) cpus_read_unlock(); - /* Possibly switch to a new RFI flush type */ - pseries_setup_rfi_flush(); + /* Possibly switch to a new L1 flush type */ + pseries_setup_security_mitigations(); /* Reinitialise system information for hv-24x7 */ read_24x7_sys_info(); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 13fa370a87e4..593840847cd3 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -111,7 +111,7 @@ static inline unsigned long cmo_get_page_size(void) int dlpar_workqueue_init(void); -void pseries_setup_rfi_flush(void); +void pseries_setup_security_mitigations(void); void pseries_lpar_read_hblkrm_characteristics(void); #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 3617cdb079f6..090c13f6c881 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -542,7 +542,7 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result) security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR); } -void pseries_setup_rfi_flush(void) +void pseries_setup_security_mitigations(void) { struct h_cpu_char_result result; enum l1d_flush_type types; @@ -587,6 +587,8 @@ void pseries_setup_rfi_flush(void) enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS); setup_uaccess_flush(enable); + + setup_stf_barrier(); } #ifdef CONFIG_PCI_IOV @@ -776,8 +778,7 @@ static void __init pSeries_setup_arch(void) fwnmi_init(); - pseries_setup_rfi_flush(); - setup_stf_barrier(); + pseries_setup_security_mitigations(); pseries_lpar_read_hblkrm_characteristics(); /* By default, only probe PCI (can be overridden by rtas_pci) */ -- cgit v1.2.3 From fbdae7d6d04d2db36c687723920f612e93b2cbda Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 18 Nov 2020 13:15:15 +0100 Subject: ASoC: Intel: bytcr_rt5640: Fix HP Pavilion x2 Detachable quirks The HP Pavilion x2 Detachable line comes in many variants: 1. Bay Trail SoC + AXP288 PMIC, Micro-USB charging (10-k010nz, ...) DMI_SYS_VENDOR: "Hewlett-Packard" DMI_PRODUCT_NAME: "HP Pavilion x2 Detachable PC 10" DMI_BOARD_NAME: "8021" 2. Bay Trail SoC + AXP288 PMIC, Type-C charging (10-n000nd, 10-n010nl, ...) DMI_SYS_VENDOR: "Hewlett-Packard" DMI_PRODUCT_NAME: "HP Pavilion x2 Detachable" DMI_BOARD_NAME: "815D" 3. Cherry Trail SoC + AXP288 PMIC, Type-C charging (10-n101ng, ...) DMI_SYS_VENDOR: "HP" DMI_PRODUCT_NAME: "HP Pavilion x2 Detachable" DMI_BOARD_NAME: "813E" 4. Cherry Trail SoC + TI PMIC, Type-C charging (10-p002nd, 10-p018wm, ...) DMI_SYS_VENDOR: "HP" DMI_PRODUCT_NAME: "HP x2 Detachable 10-p0XX" DMI_BOARD_NAME: "827C" 5. Cherry Trail SoC + TI PMIC, Type-C charging (x2-210-g2, ...) DMI_SYS_VENDOR: "HP" DMI_PRODUCT_NAME: "HP x2 210 G2" DMI_BOARD_NAME: "82F4" Variant 1 needs the exact same quirk as variant 2, so relax the DMI check for the existing quirk a bit so that it matches both variant 1 and 2 (note the other variants will still not match). Variant 2 already has an existing quirk (which now also matches variant 1) Variant 3 uses a cx2072x codec, so is not applicable here. Variant 4 almost works with the defaults, but it also needs a quirk to fix jack-detection, add a new quirk for this. Variant 5 does use a RT5640 codec (based on old dmesg output), but was otherwise not tested, keep using the defaults for this variant. Fixes: ec8e8418ff7d ("ASoC: Intel: bytcr_rt5640: Add quirks for various devices") Signed-off-by: Hans de Goede Acked-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20201118121515.11441-1-hdegoede@redhat.com Signed-off-by: Mark Brown --- sound/soc/intel/boards/bytcr_rt5640.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 9dadf6561444..f790514a147d 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -520,10 +520,10 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { .driver_data = (void *)(BYT_RT5640_IN1_MAP | BYT_RT5640_MCLK_EN), }, - { /* HP Pavilion x2 10-n000nd */ + { /* HP Pavilion x2 10-k0XX, 10-n0XX */ .matches = { - DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HP Pavilion x2 Detachable"), + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion x2 Detachable"), }, .driver_data = (void *)(BYT_RT5640_DMIC1_MAP | BYT_RT5640_JD_SRC_JD2_IN4N | @@ -532,6 +532,17 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { /* HP Pavilion x2 10-p0XX */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP x2 Detachable 10-p0XX"), + }, + .driver_data = (void *)(BYT_RT5640_DMIC1_MAP | + BYT_RT5640_JD_SRC_JD1_IN4P | + BYT_RT5640_OVCD_TH_1500UA | + BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_MCLK_EN), + }, { /* HP Stream 7 */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), -- cgit v1.2.3 From 63495f6b4aede26e6f8fe3da69e5cfdd8a4ccc3b Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 29 Oct 2020 13:25:21 +0100 Subject: drm/vc4: hdmi: Make sure our clock rate is within limits The HDMI controller cannot go above a certain pixel rate limit depending on the generations, but that limit is only enforced in mode_valid at the moment, which means that we won't advertise modes that exceed that limit, but the userspace is still free to try to setup a mode that would. Implement atomic_check to make sure we check it in that scenario too. Signed-off-by: Maxime Ripard Reviewed-by: Dave Stevenson Link: https://patchwork.freedesktop.org/patch/msgid/20201029122522.1917579-1-maxime@cerno.tech --- drivers/gpu/drm/vc4/vc4_hdmi.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 95779d50cca0..600dd6d40309 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -760,6 +760,20 @@ static void vc4_hdmi_encoder_enable(struct drm_encoder *encoder) { } +static int vc4_hdmi_encoder_atomic_check(struct drm_encoder *encoder, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) +{ + struct drm_display_mode *mode = &crtc_state->adjusted_mode; + struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); + unsigned long long pixel_rate = mode->clock * 1000; + + if (pixel_rate > vc4_hdmi->variant->max_pixel_clock) + return -EINVAL; + + return 0; +} + static enum drm_mode_status vc4_hdmi_encoder_mode_valid(struct drm_encoder *encoder, const struct drm_display_mode *mode) @@ -773,6 +787,7 @@ vc4_hdmi_encoder_mode_valid(struct drm_encoder *encoder, } static const struct drm_encoder_helper_funcs vc4_hdmi_encoder_helper_funcs = { + .atomic_check = vc4_hdmi_encoder_atomic_check, .mode_valid = vc4_hdmi_encoder_mode_valid, .disable = vc4_hdmi_encoder_disable, .enable = vc4_hdmi_encoder_enable, -- cgit v1.2.3 From 57fb32e632be4d406b4594829e3befdae1100c12 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 29 Oct 2020 13:25:22 +0100 Subject: drm/vc4: hdmi: Block odd horizontal timings The FIFO between the pixelvalve and the HDMI controller runs at 2 pixels per clock cycle, and cannot deal with odd timings. Let's reject any mode with such timings. Signed-off-by: Maxime Ripard Reviewed-by: Dave Stevenson Link: https://patchwork.freedesktop.org/patch/msgid/20201029122522.1917579-2-maxime@cerno.tech --- drivers/gpu/drm/vc4/vc4_hdmi.c | 12 ++++++++++++ drivers/gpu/drm/vc4/vc4_hdmi.h | 3 +++ 2 files changed, 15 insertions(+) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 600dd6d40309..4689a7338ac5 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -768,6 +768,11 @@ static int vc4_hdmi_encoder_atomic_check(struct drm_encoder *encoder, struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); unsigned long long pixel_rate = mode->clock * 1000; + if (vc4_hdmi->variant->unsupported_odd_h_timings && + ((mode->hdisplay % 2) || (mode->hsync_start % 2) || + (mode->hsync_end % 2) || (mode->htotal % 2))) + return -EINVAL; + if (pixel_rate > vc4_hdmi->variant->max_pixel_clock) return -EINVAL; @@ -780,6 +785,11 @@ vc4_hdmi_encoder_mode_valid(struct drm_encoder *encoder, { struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); + if (vc4_hdmi->variant->unsupported_odd_h_timings && + ((mode->hdisplay % 2) || (mode->hsync_start % 2) || + (mode->hsync_end % 2) || (mode->htotal % 2))) + return MODE_H_ILLEGAL; + if ((mode->clock * 1000) > vc4_hdmi->variant->max_pixel_clock) return MODE_CLOCK_HIGH; @@ -1832,6 +1842,7 @@ static const struct vc4_hdmi_variant bcm2711_hdmi0_variant = { PHY_LANE_2, PHY_LANE_CK, }, + .unsupported_odd_h_timings = true, .init_resources = vc5_hdmi_init_resources, .csc_setup = vc5_hdmi_csc_setup, @@ -1857,6 +1868,7 @@ static const struct vc4_hdmi_variant bcm2711_hdmi1_variant = { PHY_LANE_CK, PHY_LANE_2, }, + .unsupported_odd_h_timings = true, .init_resources = vc5_hdmi_init_resources, .csc_setup = vc5_hdmi_csc_setup, diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h index 63c6f8bddf1d..6815e93b1a48 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.h +++ b/drivers/gpu/drm/vc4/vc4_hdmi.h @@ -62,6 +62,9 @@ struct vc4_hdmi_variant { */ enum vc4_hdmi_phy_channel phy_lane_mapping[4]; + /* The BCM2711 cannot deal with odd horizontal pixel timings */ + bool unsupported_odd_h_timings; + /* Callback to get the resources (memory region, interrupts, * clocks, etc) for that variant. */ -- cgit v1.2.3 From 3c354ed1c43dabbdaae8569f982cdcccfdecd6a8 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 5 Nov 2020 14:56:50 +0100 Subject: drm/vc4: kms: Switch to drmm_add_action_or_reset Even though it was pointed in the review by Daniel, and I thought to have fixed it while applying the patches, but it turns out I forgot to commit the fixes in the process. Properly fix it this time. Fixes: dcda7c28bff2 ("drm/vc4: kms: Add functions to create the state objects") Signed-off-by: Maxime Ripard Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20201105135656.383350-2-maxime@cerno.tech --- drivers/gpu/drm/vc4/vc4_kms.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index 2b951cae04ad..44db31e16e91 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -113,7 +113,7 @@ static int vc4_ctm_obj_init(struct vc4_dev *vc4) drm_atomic_private_obj_init(&vc4->base, &vc4->ctm_manager, &ctm_state->base, &vc4_ctm_state_funcs); - return drmm_add_action(&vc4->base, vc4_ctm_obj_fini, NULL); + return drmm_add_action_or_reset(&vc4->base, vc4_ctm_obj_fini, NULL); } /* Converts a DRM S31.32 value to the HW S0.9 format. */ @@ -657,7 +657,7 @@ static int vc4_load_tracker_obj_init(struct vc4_dev *vc4) &load_state->base, &vc4_load_tracker_state_funcs); - return drmm_add_action(&vc4->base, vc4_load_tracker_obj_fini, NULL); + return drmm_add_action_or_reset(&vc4->base, vc4_load_tracker_obj_fini, NULL); } #define NUM_OUTPUTS 6 -- cgit v1.2.3 From 213189dbe7a1d7b1032aca4eacb0348a3ed67823 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 5 Nov 2020 14:56:51 +0100 Subject: drm/vc4: kms: Remove useless define NUM_OUTPUTS isn't used anymore, let's remove it. Signed-off-by: Maxime Ripard Tested-by: Hoegeun Kwon Reviewed-by: Hoegeun Kwon Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20201105135656.383350-3-maxime@cerno.tech --- drivers/gpu/drm/vc4/vc4_kms.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index 44db31e16e91..4b558ccb18fe 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -660,7 +660,6 @@ static int vc4_load_tracker_obj_init(struct vc4_dev *vc4) return drmm_add_action_or_reset(&vc4->base, vc4_load_tracker_obj_fini, NULL); } -#define NUM_OUTPUTS 6 #define NUM_CHANNELS 3 static int -- cgit v1.2.3 From a9661f27dc6bfbb6869b07cf68f9c2fd05167746 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 5 Nov 2020 14:56:52 +0100 Subject: drm/vc4: kms: Rename NUM_CHANNELS The NUM_CHANNELS define has a pretty generic name and was right before the function using it. Let's move to something that makes the hardware-specific nature more obvious, and to a more appropriate place. Signed-off-by: Maxime Ripard Tested-by: Hoegeun Kwon Reviewed-by: Hoegeun Kwon Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20201105135656.383350-4-maxime@cerno.tech --- drivers/gpu/drm/vc4/vc4_kms.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index 4b558ccb18fe..ad69c70f66a2 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -24,6 +24,8 @@ #include "vc4_drv.h" #include "vc4_regs.h" +#define HVS_NUM_CHANNELS 3 + struct vc4_ctm_state { struct drm_private_state base; struct drm_color_ctm *ctm; @@ -660,12 +662,10 @@ static int vc4_load_tracker_obj_init(struct vc4_dev *vc4) return drmm_add_action_or_reset(&vc4->base, vc4_load_tracker_obj_fini, NULL); } -#define NUM_CHANNELS 3 - static int vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) { - unsigned long unassigned_channels = GENMASK(NUM_CHANNELS - 1, 0); + unsigned long unassigned_channels = GENMASK(HVS_NUM_CHANNELS - 1, 0); struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct drm_crtc *crtc; int i, ret; -- cgit v1.2.3 From a72b0458cd5123b40dd5084f6e536af63aeacda1 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 5 Nov 2020 14:56:53 +0100 Subject: drm/vc4: kms: Split the HVS muxing check in a separate function The code that assigns HVS channels during atomic_check is starting to grow a bit big, let's move it into a separate function. Signed-off-by: Maxime Ripard Tested-by: Hoegeun Kwon Reviewed-by: Hoegeun Kwon Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20201105135656.383350-5-maxime@cerno.tech --- drivers/gpu/drm/vc4/vc4_kms.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index ad69c70f66a2..bb2efc5d2d01 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -662,13 +662,13 @@ static int vc4_load_tracker_obj_init(struct vc4_dev *vc4) return drmm_add_action_or_reset(&vc4->base, vc4_load_tracker_obj_fini, NULL); } -static int -vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) +static int vc4_pv_muxing_atomic_check(struct drm_device *dev, + struct drm_atomic_state *state) { unsigned long unassigned_channels = GENMASK(HVS_NUM_CHANNELS - 1, 0); struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct drm_crtc *crtc; - int i, ret; + unsigned int i; /* * Since the HVS FIFOs are shared across all the pixelvalves and @@ -741,6 +741,18 @@ vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) } } + return 0; +} + +static int +vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) +{ + int ret; + + ret = vc4_pv_muxing_atomic_check(dev, state); + if (ret) + return ret; + ret = vc4_ctm_atomic_check(dev, state); if (ret < 0) return ret; -- cgit v1.2.3 From b5dbc4d36885bef6257054a737a76101d293b185 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 5 Nov 2020 14:56:54 +0100 Subject: drm/vc4: kms: Document the muxing corner cases We've had a number of muxing corner-cases with specific ways to reproduce them, so let's document them to make sure they aren't lost and introduce regressions later on. Signed-off-by: Maxime Ripard Tested-by: Hoegeun Kwon Reviewed-by: Hoegeun Kwon Acked-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20201105135656.383350-6-maxime@cerno.tech --- drivers/gpu/drm/vc4/vc4_kms.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index bb2efc5d2d01..0f44fc526fd2 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -662,6 +662,28 @@ static int vc4_load_tracker_obj_init(struct vc4_dev *vc4) return drmm_add_action_or_reset(&vc4->base, vc4_load_tracker_obj_fini, NULL); } +/* + * The BCM2711 HVS has up to 7 outputs connected to the pixelvalves and + * the TXP (and therefore all the CRTCs found on that platform). + * + * The naive (and our initial) implementation would just iterate over + * all the active CRTCs, try to find a suitable FIFO, and then remove it + * from the pool of available FIFOs. However, there are a few corner + * cases that need to be considered: + * + * - When running in a dual-display setup (so with two CRTCs involved), + * we can update the state of a single CRTC (for example by changing + * its mode using xrandr under X11) without affecting the other. In + * this case, the other CRTC wouldn't be in the state at all, so we + * need to consider all the running CRTCs in the DRM device to assign + * a FIFO, not just the one in the state. + * + * - Since we need the pixelvalve to be disabled and enabled back when + * the FIFO is changed, we should keep the FIFO assigned for as long + * as the CRTC is enabled, only considering it free again once that + * CRTC has been disabled. This can be tested by booting X11 on a + * single display, and changing the resolution down and then back up. + */ static int vc4_pv_muxing_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) { -- cgit v1.2.3 From a61ea6379ae9dbb63fbf022d1456733520db6be7 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 19 Nov 2020 14:53:22 +0900 Subject: tools/bootconfig: Fix errno reference after printf() Fix not to refer the errno variable as the result of previous libc functions after printf() because printf() can change the errno. Link: https://lkml.kernel.org/r/160576520243.320071.51093664672431249.stgit@devnote2 Fixes: 85c46b78da58 ("bootconfig: Add bootconfig magic word for indicating bootconfig explicitly") Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- tools/bootconfig/main.c | 52 +++++++++++++++++++++++++++---------------------- 1 file changed, 29 insertions(+), 23 deletions(-) diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index eb92027817a7..52eb2bbe8966 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -147,6 +147,12 @@ static int load_xbc_file(const char *path, char **buf) return ret; } +static int pr_errno(const char *msg, int err) +{ + pr_err("%s: %d\n", msg, err); + return err; +} + static int load_xbc_from_initrd(int fd, char **buf) { struct stat stat; @@ -162,26 +168,24 @@ static int load_xbc_from_initrd(int fd, char **buf) if (stat.st_size < 8 + BOOTCONFIG_MAGIC_LEN) return 0; - if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) { - pr_err("Failed to lseek: %d\n", -errno); - return -errno; - } + if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) + return pr_errno("Failed to lseek for magic", -errno); + if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0) - return -errno; + return pr_errno("Failed to read", -errno); + /* Check the bootconfig magic bytes */ if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0) return 0; - if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) { - pr_err("Failed to lseek: %d\n", -errno); - return -errno; - } + if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) + return pr_errno("Failed to lseek for size", -errno); if (read(fd, &size, sizeof(u32)) < 0) - return -errno; + return pr_errno("Failed to read size", -errno); if (read(fd, &csum, sizeof(u32)) < 0) - return -errno; + return pr_errno("Failed to read checksum", -errno); /* Wrong size error */ if (stat.st_size < size + 8 + BOOTCONFIG_MAGIC_LEN) { @@ -190,10 +194,8 @@ static int load_xbc_from_initrd(int fd, char **buf) } if (lseek(fd, stat.st_size - (size + 8 + BOOTCONFIG_MAGIC_LEN), - SEEK_SET) < 0) { - pr_err("Failed to lseek: %d\n", -errno); - return -errno; - } + SEEK_SET) < 0) + return pr_errno("Failed to lseek", -errno); ret = load_xbc_fd(fd, buf, size); if (ret < 0) @@ -262,14 +264,16 @@ static int show_xbc(const char *path, bool list) ret = stat(path, &st); if (ret < 0) { - pr_err("Failed to stat %s: %d\n", path, -errno); - return -errno; + ret = -errno; + pr_err("Failed to stat %s: %d\n", path, ret); + return ret; } fd = open(path, O_RDONLY); if (fd < 0) { - pr_err("Failed to open initrd %s: %d\n", path, fd); - return -errno; + ret = -errno; + pr_err("Failed to open initrd %s: %d\n", path, ret); + return ret; } ret = load_xbc_from_initrd(fd, &buf); @@ -307,8 +311,9 @@ static int delete_xbc(const char *path) fd = open(path, O_RDWR); if (fd < 0) { - pr_err("Failed to open initrd %s: %d\n", path, fd); - return -errno; + ret = -errno; + pr_err("Failed to open initrd %s: %d\n", path, ret); + return ret; } size = load_xbc_from_initrd(fd, &buf); @@ -383,9 +388,10 @@ static int apply_xbc(const char *path, const char *xbc_path) /* Apply new one */ fd = open(path, O_RDWR | O_APPEND); if (fd < 0) { - pr_err("Failed to open %s: %d\n", path, fd); + ret = -errno; + pr_err("Failed to open %s: %d\n", path, ret); free(data); - return fd; + return ret; } /* TODO: Ensure the @path is initramfs/initrd image */ ret = write(fd, data, size + 8); -- cgit v1.2.3 From a995e6bc0524450adfd6181dfdcd9d0520cfaba5 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 19 Nov 2020 14:53:31 +0900 Subject: tools/bootconfig: Fix to check the write failure correctly Fix to check the write(2) failure including partial write correctly and try to rollback the partial write, because if there is no BOOTCONFIG_MAGIC string, we can not remove it. Link: https://lkml.kernel.org/r/160576521135.320071.3883101436675969998.stgit@devnote2 Fixes: 85c46b78da58 ("bootconfig: Add bootconfig magic word for indicating bootconfig explicitly") Suggested-by: Linus Torvalds Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- tools/bootconfig/main.c | 30 ++++++++++++++++++++++++++---- 1 file changed, 26 insertions(+), 4 deletions(-) diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 52eb2bbe8966..a0733cbb3c49 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -337,6 +337,7 @@ static int delete_xbc(const char *path) static int apply_xbc(const char *path, const char *xbc_path) { + struct stat stat; u32 size, csum; char *buf, *data; int ret, fd; @@ -394,16 +395,26 @@ static int apply_xbc(const char *path, const char *xbc_path) return ret; } /* TODO: Ensure the @path is initramfs/initrd image */ + if (fstat(fd, &stat) < 0) { + pr_err("Failed to get the size of %s\n", path); + goto out; + } ret = write(fd, data, size + 8); - if (ret < 0) { + if (ret < size + 8) { + if (ret < 0) + ret = -errno; pr_err("Failed to apply a boot config: %d\n", ret); - goto out; + if (ret < 0) + goto out; + goto out_rollback; } /* Write a magic word of the bootconfig */ ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); - if (ret < 0) { + if (ret < BOOTCONFIG_MAGIC_LEN) { + if (ret < 0) + ret = -errno; pr_err("Failed to apply a boot config magic: %d\n", ret); - goto out; + goto out_rollback; } ret = 0; out: @@ -411,6 +422,17 @@ out: free(data); return ret; + +out_rollback: + /* Map the partial write to -ENOSPC */ + if (ret >= 0) + ret = -ENOSPC; + if (ftruncate(fd, stat.st_size) < 0) { + ret = -errno; + pr_err("Failed to rollback the write error: %d\n", ret); + pr_err("The initrd %s may be corrupted. Recommend to rebuild.\n", path); + } + goto out; } static int usage(void) -- cgit v1.2.3 From e1cef2d4c379b2aab43a7dc9601f645048209090 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 19 Nov 2020 14:53:40 +0900 Subject: tools/bootconfig: Align the bootconfig applied initrd image size to 4 Align the bootconfig applied initrd image size to 4. To fill the gap, the bootconfig command uses null characters in between the bootconfig data and the footer. This will expands the footer size but don't change the checksum. Thus the block image of the initrd file with bootconfig is as follows. [initrd][bootconfig][(pad)][size][csum]["#BOOTCONFIG\n"] Link: https://lkml.kernel.org/r/160576522046.320071.8550680670010950634.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/bootconfig.h | 3 ++ tools/bootconfig/main.c | 57 ++++++++++++++++++++++--------------- tools/bootconfig/test-bootconfig.sh | 6 +++- 3 files changed, 42 insertions(+), 24 deletions(-) diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 9903088891fa..2696eb0fc149 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -12,6 +12,9 @@ #define BOOTCONFIG_MAGIC "#BOOTCONFIG\n" #define BOOTCONFIG_MAGIC_LEN 12 +#define BOOTCONFIG_ALIGN_SHIFT 2 +#define BOOTCONFIG_ALIGN (1 << BOOTCONFIG_ALIGN_SHIFT) +#define BOOTCONFIG_ALIGN_MASK (BOOTCONFIG_ALIGN - 1) /* XBC tree node */ struct xbc_node { diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index a0733cbb3c49..4a445b6304bb 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -337,12 +337,13 @@ static int delete_xbc(const char *path) static int apply_xbc(const char *path, const char *xbc_path) { + char *buf, *data, *p; + size_t total_size; struct stat stat; + const char *msg; u32 size, csum; - char *buf, *data; + int pos, pad; int ret, fd; - const char *msg; - int pos; ret = load_xbc_file(xbc_path, &buf); if (ret < 0) { @@ -352,13 +353,12 @@ static int apply_xbc(const char *path, const char *xbc_path) size = strlen(buf) + 1; csum = checksum((unsigned char *)buf, size); - /* Prepare xbc_path data */ - data = malloc(size + 8); + /* Backup the bootconfig data */ + data = calloc(size + BOOTCONFIG_ALIGN + + sizeof(u32) + sizeof(u32) + BOOTCONFIG_MAGIC_LEN, 1); if (!data) return -ENOMEM; - strcpy(data, buf); - *(u32 *)(data + size) = size; - *(u32 *)(data + size + 4) = csum; + memcpy(data, buf, size); /* Check the data format */ ret = xbc_init(buf, &msg, &pos); @@ -399,24 +399,35 @@ static int apply_xbc(const char *path, const char *xbc_path) pr_err("Failed to get the size of %s\n", path); goto out; } - ret = write(fd, data, size + 8); - if (ret < size + 8) { + + /* To align up the total size to BOOTCONFIG_ALIGN, get padding size */ + total_size = stat.st_size + size + sizeof(u32) * 2 + BOOTCONFIG_MAGIC_LEN; + pad = ((total_size + BOOTCONFIG_ALIGN - 1) & (~BOOTCONFIG_ALIGN_MASK)) - total_size; + size += pad; + + /* Add a footer */ + p = data + size; + *(u32 *)p = size; + p += sizeof(u32); + + *(u32 *)p = csum; + p += sizeof(u32); + + memcpy(p, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); + p += BOOTCONFIG_MAGIC_LEN; + + total_size = p - data; + + ret = write(fd, data, total_size); + if (ret < total_size) { if (ret < 0) ret = -errno; pr_err("Failed to apply a boot config: %d\n", ret); - if (ret < 0) - goto out; - goto out_rollback; - } - /* Write a magic word of the bootconfig */ - ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); - if (ret < BOOTCONFIG_MAGIC_LEN) { - if (ret < 0) - ret = -errno; - pr_err("Failed to apply a boot config magic: %d\n", ret); - goto out_rollback; - } - ret = 0; + if (ret >= 0) + goto out_rollback; + } else + ret = 0; + out: close(fd); free(data); diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh index d295e406a756..baed891d0ba4 100755 --- a/tools/bootconfig/test-bootconfig.sh +++ b/tools/bootconfig/test-bootconfig.sh @@ -9,6 +9,7 @@ else TESTDIR=. fi BOOTCONF=${TESTDIR}/bootconfig +ALIGN=4 INITRD=`mktemp ${TESTDIR}/initrd-XXXX` TEMPCONF=`mktemp ${TESTDIR}/temp-XXXX.bconf` @@ -59,7 +60,10 @@ echo "Show command test" xpass $BOOTCONF $INITRD echo "File size check" -xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9 + 12) +total_size=$(expr $bconf_size + $initrd_size + 9 + 12 + $ALIGN - 1 ) +total_size=$(expr $total_size / $ALIGN) +total_size=$(expr $total_size \* $ALIGN) +xpass test $new_size -eq $total_size echo "Apply command repeat test" xpass $BOOTCONF -a $TEMPCONF $INITRD -- cgit v1.2.3 From fbc6e1c6e0a4b5ef402f9eb8d00880a5e1d98df3 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 19 Nov 2020 14:53:49 +0900 Subject: docs: bootconfig: Update file format on initrd image To align the total file size, add padding null character when appending the bootconfig to initrd image. Link: https://lkml.kernel.org/r/160576522916.320071.4145530996151028855.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- Documentation/admin-guide/bootconfig.rst | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst index a22024f9175e..363599683784 100644 --- a/Documentation/admin-guide/bootconfig.rst +++ b/Documentation/admin-guide/bootconfig.rst @@ -137,15 +137,22 @@ Boot Kernel With a Boot Config ============================== Since the boot configuration file is loaded with initrd, it will be added -to the end of the initrd (initramfs) image file with size, checksum and -12-byte magic word as below. +to the end of the initrd (initramfs) image file with padding, size, +checksum and 12-byte magic word as below. -[initrd][bootconfig][size(u32)][checksum(u32)][#BOOTCONFIG\n] +[initrd][bootconfig][padding][size(u32)][checksum(u32)][#BOOTCONFIG\n] + +When the boot configuration is added to the initrd image, the total +file size is aligned to 4 bytes. To fill the gap, null characters +(``\0``) will be added. Thus the ``size`` is the length of the bootconfig +file + padding bytes. The Linux kernel decodes the last part of the initrd image in memory to get the boot configuration data. Because of this "piggyback" method, there is no need to change or -update the boot loader and the kernel image itself. +update the boot loader and the kernel image itself as long as the boot +loader passes the correct initrd file size. If by any chance, the boot +loader passes a longer size, the kernel feils to find the bootconfig data. To do this operation, Linux kernel provides "bootconfig" command under tools/bootconfig, which allows admin to apply or delete the config file @@ -176,7 +183,8 @@ up to 512 key-value pairs. If keys contains 3 words in average, it can contain 256 key-value pairs. In most cases, the number of config items will be under 100 entries and smaller than 8KB, so it would be enough. If the node number exceeds 1024, parser returns an error even if the file -size is smaller than 32KB. +size is smaller than 32KB. (Note that this maximum size is not including +the padding null characters.) Anyway, since bootconfig command verifies it when appending a boot config to initrd image, user can notice it before boot. -- cgit v1.2.3 From 01cf158e48d2b5ce947430de5896c10f4f7c1822 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 19 Nov 2020 15:07:19 +0100 Subject: Revert "iommu/vt-d: Take CONFIG_PCI_ATS into account" This reverts commit 8986f223bd777a73119f5d593c15b4d630ff49bb. The proper fix is queued in Will's tree now Signed-off-by: Thomas Gleixner --- drivers/iommu/intel/dmar.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index bc9f4cf72240..b2e804473209 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -335,9 +335,7 @@ static void dmar_pci_bus_del_dev(struct dmar_pci_notify_info *info) static inline void vf_inherit_msi_domain(struct pci_dev *pdev) { -#ifdef CONFIG_PCI_ATS dev_set_msi_domain(&pdev->dev, dev_get_msi_domain(&pdev->physfn->dev)); -#endif } static int dmar_pci_bus_notifier(struct notifier_block *nb, -- cgit v1.2.3 From 600c0849cf86b75d86352f59745226273290986a Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 18 Nov 2020 13:08:21 +0200 Subject: thunderbolt: Fix use-after-free in remove_unplugged_switch() Paulian reported a crash that happens when a dock is unplugged during hibernation: [78436.228217] thunderbolt 0-1: device disconnected [78436.228365] BUG: kernel NULL pointer dereference, address: 00000000000001e0 ... [78436.228397] RIP: 0010:icm_free_unplugged_children+0x109/0x1a0 ... [78436.228432] Call Trace: [78436.228439] icm_rescan_work+0x24/0x30 [78436.228444] process_one_work+0x1a3/0x3a0 [78436.228449] worker_thread+0x30/0x370 [78436.228454] ? process_one_work+0x3a0/0x3a0 [78436.228457] kthread+0x13d/0x160 [78436.228461] ? kthread_park+0x90/0x90 [78436.228465] ret_from_fork+0x1f/0x30 This happens because remove_unplugged_switch() calls tb_switch_remove() that releases the memory pointed by sw so the following lines reference to a memory that might be released already. Fix this by saving pointer to the parent device before calling tb_switch_remove(). Reported-by: Paulian Bogdan Marinca Fixes: 4f7c2e0d8765 ("thunderbolt: Make sure device runtime resume completes before taking domain lock") Cc: stable@vger.kernel.org Signed-off-by: Mika Westerberg Reviewed-by: Greg Kroah-Hartman --- drivers/thunderbolt/icm.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index 977ba91f4d0e..82c46b200c34 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -1976,7 +1976,9 @@ static int complete_rpm(struct device *dev, void *data) static void remove_unplugged_switch(struct tb_switch *sw) { - pm_runtime_get_sync(sw->dev.parent); + struct device *parent = get_device(sw->dev.parent); + + pm_runtime_get_sync(parent); /* * Signal this and switches below for rpm_complete because @@ -1987,8 +1989,10 @@ static void remove_unplugged_switch(struct tb_switch *sw) bus_for_each_dev(&tb_bus_type, &sw->dev, NULL, complete_rpm); tb_switch_remove(sw); - pm_runtime_mark_last_busy(sw->dev.parent); - pm_runtime_put_autosuspend(sw->dev.parent); + pm_runtime_mark_last_busy(parent); + pm_runtime_put_autosuspend(parent); + + put_device(parent); } static void icm_free_unplugged_children(struct tb_switch *sw) -- cgit v1.2.3 From 8d15aa4ed02bed2f5b0720480ab8eb032dc0887e Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 29 Oct 2020 14:40:16 +0100 Subject: dt-bindings: display: Add a property to deal with WiFi coexistence The RaspberryPi4 has both a WiFi chip and HDMI outputs capable of doing 4k. Unfortunately, the 1440p resolution at 60Hz has a TMDS rate on the HDMI cable right in the middle of the first Wifi channel. Add a property to our HDMI controller, that could be reused by other similar HDMI controllers, to allow the OS to take whatever measure is necessary to avoid that crosstalk. Signed-off-by: Maxime Ripard Reviewed-by: Nicolas Saenz Julienne Reviewed-by: Rob Herring Link: https://patchwork.freedesktop.org/patch/msgid/20201029134018.1948636-1-maxime@cerno.tech --- Documentation/devicetree/bindings/display/brcm,bcm2711-hdmi.yaml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/Documentation/devicetree/bindings/display/brcm,bcm2711-hdmi.yaml b/Documentation/devicetree/bindings/display/brcm,bcm2711-hdmi.yaml index 03a76729d26c..7ce06f9f9f8e 100644 --- a/Documentation/devicetree/bindings/display/brcm,bcm2711-hdmi.yaml +++ b/Documentation/devicetree/bindings/display/brcm,bcm2711-hdmi.yaml @@ -76,6 +76,12 @@ properties: resets: maxItems: 1 + wifi-2.4ghz-coexistence: + type: boolean + description: > + Should the pixel frequencies in the WiFi frequencies range be + avoided? + required: - compatible - reg -- cgit v1.2.3 From 9fa1d7e60ad5ad2f7859ea8912d7b0b57821a5b7 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 29 Oct 2020 14:40:17 +0100 Subject: drm/vc4: hdmi: Disable Wifi Frequencies There's cross-talk on the RPi4 between the 2.4GHz channels used by the WiFi chip and some resolutions, most notably 1440p at 60Hz. In such a case, we can either reject entirely the mode, or lower slightly the pixel frequency to remove the overlap. Let's go for the latter. Signed-off-by: Maxime Ripard Acked-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20201029134018.1948636-2-maxime@cerno.tech --- drivers/gpu/drm/vc4/vc4_hdmi.c | 21 +++++++++++++++++++++ drivers/gpu/drm/vc4/vc4_hdmi.h | 8 ++++++++ 2 files changed, 29 insertions(+) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 4689a7338ac5..afc178b0d89f 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -760,6 +760,9 @@ static void vc4_hdmi_encoder_enable(struct drm_encoder *encoder) { } +#define WIFI_2_4GHz_CH1_MIN_FREQ 2400000000ULL +#define WIFI_2_4GHz_CH1_MAX_FREQ 2422000000ULL + static int vc4_hdmi_encoder_atomic_check(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state, struct drm_connector_state *conn_state) @@ -767,12 +770,27 @@ static int vc4_hdmi_encoder_atomic_check(struct drm_encoder *encoder, struct drm_display_mode *mode = &crtc_state->adjusted_mode; struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); unsigned long long pixel_rate = mode->clock * 1000; + unsigned long long tmds_rate; if (vc4_hdmi->variant->unsupported_odd_h_timings && ((mode->hdisplay % 2) || (mode->hsync_start % 2) || (mode->hsync_end % 2) || (mode->htotal % 2))) return -EINVAL; + /* + * The 1440p@60 pixel rate is in the same range than the first + * WiFi channel (between 2.4GHz and 2.422GHz with 22MHz + * bandwidth). Slightly lower the frequency to bring it out of + * the WiFi range. + */ + tmds_rate = pixel_rate * 10; + if (vc4_hdmi->disable_wifi_frequencies && + (tmds_rate >= WIFI_2_4GHz_CH1_MIN_FREQ && + tmds_rate <= WIFI_2_4GHz_CH1_MAX_FREQ)) { + mode->clock = 238560; + pixel_rate = mode->clock * 1000; + } + if (pixel_rate > vc4_hdmi->variant->max_pixel_clock) return -EINVAL; @@ -1719,6 +1737,9 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) vc4_hdmi->hpd_active_low = hpd_gpio_flags & OF_GPIO_ACTIVE_LOW; } + vc4_hdmi->disable_wifi_frequencies = + of_property_read_bool(dev->of_node, "wifi-2.4ghz-coexistence"); + pm_runtime_enable(dev); drm_simple_encoder_init(drm, encoder, DRM_MODE_ENCODER_TMDS); diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h index 6815e93b1a48..0526a9cf608a 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.h +++ b/drivers/gpu/drm/vc4/vc4_hdmi.h @@ -142,6 +142,14 @@ struct vc4_hdmi { int hpd_gpio; bool hpd_active_low; + /* + * On some systems (like the RPi4), some modes are in the same + * frequency range than the WiFi channels (1440p@60Hz for + * example). Should we take evasive actions because that system + * has a wifi adapter? + */ + bool disable_wifi_frequencies; + struct cec_adapter *cec_adap; struct cec_msg cec_rx_msg; bool cec_tx_ok; -- cgit v1.2.3 From eec231e060fb79923c349f6e89f022b286f32c1e Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 14 Nov 2020 10:45:31 +0100 Subject: HID: logitech-dj: Fix an error in mse_bluetooth_descriptor Fix an error in the mouse / INPUT(2) descriptor used for quad/bt2.0 combo receivers. Replace INPUT with INPUT (Data,Var,Abs) for the field for the 4 extra buttons which share their report-byte with the low-res hwheel. This is likely a copy and paste error. I've verified that the new 0x81, 0x02 value matches both the mouse descriptor for the currently supported MX5000 / MX5500 receivers, as well as the INPUT(2) mouse descriptors for the Dinovo receivers for which support is being worked on. Cc: stable@vger.kernel.org Fixes: f2113c3020ef ("HID: logitech-dj: add support for Logitech Bluetooth Mini-Receiver") Signed-off-by: Hans de Goede Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-logitech-dj.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 1cafb65428b0..19b9bca0f40a 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -328,7 +328,7 @@ static const char mse_bluetooth_descriptor[] = { 0x25, 0x01, /* LOGICAL_MAX (1) */ 0x75, 0x01, /* REPORT_SIZE (1) */ 0x95, 0x04, /* REPORT_COUNT (4) */ - 0x81, 0x06, /* INPUT */ + 0x81, 0x02, /* INPUT (Data,Var,Abs) */ 0xC0, /* END_COLLECTION */ 0xC0, /* END_COLLECTION */ }; -- cgit v1.2.3 From b4c00e7976636f33a4f67eab436a11666c8afd60 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 14 Nov 2020 22:20:56 +0100 Subject: HID: logitech-dj: Fix Dinovo Mini when paired with a MX5x00 receiver Some users are pairing the Dinovo keyboards with the MX5000 or MX5500 receivers, instead of with the Dinovo receivers. The receivers are mostly the same (and the air protocol obviously is compatible) but currently the Dinovo receivers are handled by hid-lg.c while the MX5x00 receivers are handled by logitech-dj.c. When using a Dinovo keyboard, with its builtin touchpad, through logitech-dj.c then the touchpad stops working because when asking the receiver for paired devices, we get only 1 paired device with a device_type of REPORT_TYPE_KEYBOARD. And since we don't see a paired mouse, we have nowhere to send mouse-events to, so we drop them. Extend the existing fix for the Dinovo Edge for this to also cover the Dinovo Mini keyboard and also add a mapping to logitech-hidpp for the Media key on the Dinovo Mini, so that that keeps working too. BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1811424 Fixes: f2113c3020ef ("HID: logitech-dj: add support for Logitech Bluetooth Mini-Receiver") Signed-off-by: Hans de Goede Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-logitech-dj.c | 1 + drivers/hid/hid-logitech-hidpp.c | 25 +++++++++++++++++++++++++ 2 files changed, 26 insertions(+) diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 19b9bca0f40a..1cbbcf607ee9 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -875,6 +875,7 @@ static void logi_dj_recv_queue_notification(struct dj_receiver_dev *djrcv_dev, */ static const u16 kbd_builtin_touchpad_ids[] = { 0xb309, /* Dinovo Edge */ + 0xb30c, /* Dinovo Mini */ }; static void logi_hidpp_dev_conn_notif_equad(struct hid_device *hdev, diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 40b7c75b3384..0ca723119547 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -93,6 +93,8 @@ MODULE_PARM_DESC(disable_tap_to_click, #define HIDPP_CAPABILITY_BATTERY_LEVEL_STATUS BIT(3) #define HIDPP_CAPABILITY_BATTERY_VOLTAGE BIT(4) +#define lg_map_key_clear(c) hid_map_usage_clear(hi, usage, bit, max, EV_KEY, (c)) + /* * There are two hidpp protocols in use, the first version hidpp10 is known * as register access protocol or RAP, the second version hidpp20 is known as @@ -2950,6 +2952,26 @@ static int g920_get_config(struct hidpp_device *hidpp, return g920_ff_set_autocenter(hidpp, data); } +/* -------------------------------------------------------------------------- */ +/* Logitech Dinovo Mini keyboard with builtin touchpad */ +/* -------------------------------------------------------------------------- */ +#define DINOVO_MINI_PRODUCT_ID 0xb30c + +static int lg_dinovo_input_mapping(struct hid_device *hdev, struct hid_input *hi, + struct hid_field *field, struct hid_usage *usage, + unsigned long **bit, int *max) +{ + if ((usage->hid & HID_USAGE_PAGE) != HID_UP_LOGIVENDOR) + return 0; + + switch (usage->hid & HID_USAGE) { + case 0x00d: lg_map_key_clear(KEY_MEDIA); break; + default: + return 0; + } + return 1; +} + /* -------------------------------------------------------------------------- */ /* HID++1.0 devices which use HID++ reports for their wheels */ /* -------------------------------------------------------------------------- */ @@ -3185,6 +3207,9 @@ static int hidpp_input_mapping(struct hid_device *hdev, struct hid_input *hi, field->application != HID_GD_MOUSE) return m560_input_mapping(hdev, hi, field, usage, bit, max); + if (hdev->product == DINOVO_MINI_PRODUCT_ID) + return lg_dinovo_input_mapping(hdev, hi, field, usage, bit, max); + return 0; } -- cgit v1.2.3 From 1fd6cee127e2ddff36d648573d7566aafb0d0b77 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 18 Nov 2020 22:13:50 +0100 Subject: libbpf: Fix VERSIONED_SYM_COUNT number parsing We remove "other info" from "readelf -s --wide" output when parsing GLOBAL_SYM_COUNT variable, which was added in [1]. But we don't do that for VERSIONED_SYM_COUNT and it's failing the check_abi target on powerpc Fedora 33. The extra "other info" wasn't problem for VERSIONED_SYM_COUNT parsing until commit [2] added awk in the pipe, which assumes that the last column is symbol, but it can be "other info". Adding "other info" removal for VERSIONED_SYM_COUNT the same way as we did for GLOBAL_SYM_COUNT parsing. [1] aa915931ac3e ("libbpf: Fix readelf output parsing for Fedora") [2] 746f534a4809 ("tools/libbpf: Avoid counting local symbols in ABI check") Fixes: 746f534a4809 ("tools/libbpf: Avoid counting local symbols in ABI check") Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20201118211350.1493421-1-jolsa@kernel.org --- tools/lib/bpf/Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 5f9abed3e226..55bd78b3496f 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -146,6 +146,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) @@ -214,6 +215,7 @@ check_abi: $(OUTPUT)libbpf.so awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \ -- cgit v1.2.3 From 883a790a84401f6f55992887fd7263d808d4d05d Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 19 Nov 2020 08:59:11 -0800 Subject: xfs: don't allow NOWAIT DIO across extent boundaries Jens has reported a situation where partial direct IOs can be issued and completed yet still return -EAGAIN. We don't want this to report a short IO as we want XFS to complete user DIO entirely or not at all. This partial IO situation can occur on a write IO that is split across an allocated extent and a hole, and the second mapping is returning EAGAIN because allocation would be required. The trivial reproducer: $ sudo xfs_io -fdt -c "pwrite 0 4k" -c "pwrite -V 1 -b 8k -N 0 8k" /mnt/scr/foo wrote 4096/4096 bytes at offset 0 4 KiB, 1 ops; 0.0001 sec (27.509 MiB/sec and 7042.2535 ops/sec) pwrite: Resource temporarily unavailable $ The pwritev2(0, 8kB, RWF_NOWAIT) call returns EAGAIN having done the first 4kB write: xfs_file_direct_write: dev 259:1 ino 0x83 size 0x1000 offset 0x0 count 0x2000 iomap_apply: dev 259:1 ino 0x83 pos 0 length 8192 flags WRITE|DIRECT|NOWAIT (0x31) ops xfs_direct_write_iomap_ops caller iomap_dio_rw actor iomap_dio_actor xfs_ilock_nowait: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_ilock_for_iomap xfs_iunlock: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_direct_write_iomap_begin xfs_iomap_found: dev 259:1 ino 0x83 size 0x1000 offset 0x0 count 8192 fork data startoff 0x0 startblock 24 blockcount 0x1 iomap_apply_dstmap: dev 259:1 ino 0x83 bdev 259:1 addr 102400 offset 0 length 4096 type MAPPED flags DIRTY Here the first iomap loop has mapped the first 4kB of the file and issued the IO, and we enter the second iomap_apply loop: iomap_apply: dev 259:1 ino 0x83 pos 4096 length 4096 flags WRITE|DIRECT|NOWAIT (0x31) ops xfs_direct_write_iomap_ops caller iomap_dio_rw actor iomap_dio_actor xfs_ilock_nowait: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_ilock_for_iomap xfs_iunlock: dev 259:1 ino 0x83 flags ILOCK_SHARED caller xfs_direct_write_iomap_begin And we exit with -EAGAIN out because we hit the allocate case trying to make the second 4kB block. Then IO completes on the first 4kB and the original IO context completes and unlocks the inode, returning -EAGAIN to userspace: xfs_end_io_direct_write: dev 259:1 ino 0x83 isize 0x1000 disize 0x1000 offset 0x0 count 4096 xfs_iunlock: dev 259:1 ino 0x83 flags IOLOCK_SHARED caller xfs_file_dio_aio_write There are other vectors to the same problem when we re-enter the mapping code if we have to make multiple mappinfs under NOWAIT conditions. e.g. failing trylocks, COW extents being found, allocation being required, and so on. Avoid all these potential problems by only allowing IOMAP_NOWAIT IO to go ahead if the mapping we retrieve for the IO spans an entire allocated extent. This avoids the possibility of subsequent mappings to complete the IO from triggering NOWAIT semantics by any means as NOWAIT IO will now only enter the mapping code once per NOWAIT IO. Reported-and-tested-by: Jens Axboe Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_iomap.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 3abb8b9d6f4c..7b9ff824e82d 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -706,6 +706,23 @@ relock: return 0; } +/* + * Check that the imap we are going to return to the caller spans the entire + * range that the caller requested for the IO. + */ +static bool +imap_spans_range( + struct xfs_bmbt_irec *imap, + xfs_fileoff_t offset_fsb, + xfs_fileoff_t end_fsb) +{ + if (imap->br_startoff > offset_fsb) + return false; + if (imap->br_startoff + imap->br_blockcount < end_fsb) + return false; + return true; +} + static int xfs_direct_write_iomap_begin( struct inode *inode, @@ -766,6 +783,18 @@ xfs_direct_write_iomap_begin( if (imap_needs_alloc(inode, flags, &imap, nimaps)) goto allocate_blocks; + /* + * NOWAIT IO needs to span the entire requested IO with a single map so + * that we avoid partial IO failures due to the rest of the IO range not + * covered by this map triggering an EAGAIN condition when it is + * subsequently mapped and aborting the IO. + */ + if ((flags & IOMAP_NOWAIT) && + !imap_spans_range(&imap, offset_fsb, end_fsb)) { + error = -EAGAIN; + goto out_unlock; + } + xfs_iunlock(ip, lockmode); trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap); return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags); -- cgit v1.2.3 From d21b96c8ed2aea7e6b7bf4735e1d2503cfbf4072 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 19 Nov 2020 13:14:40 +0100 Subject: ALSA: mixart: Fix mutex deadlock The code change for switching to non-atomic mode brought the unexpected mutex deadlock in get_msg(). It converted the spinlock with the existing mutex, but there were calls with the already holding the mutex. Since the only place that needs the extra lock is the code path from snd_mixart_send_msg(), remove the mutex lock in get_msg() and apply in the caller side for fixing the mutex deadlock. Fixes: 8d3a8b5cb57d ("ALSA: mixart: Use nonatomic PCM ops") Reported-by: Dan Carpenter Cc: Link: https://lore.kernel.org/r/20201119121440.18945-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/pci/mixart/mixart_core.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/sound/pci/mixart/mixart_core.c b/sound/pci/mixart/mixart_core.c index 0bdd33b0af65..fb8895af0363 100644 --- a/sound/pci/mixart/mixart_core.c +++ b/sound/pci/mixart/mixart_core.c @@ -70,7 +70,6 @@ static int get_msg(struct mixart_mgr *mgr, struct mixart_msg *resp, unsigned int i; #endif - mutex_lock(&mgr->msg_lock); err = 0; /* copy message descriptor from miXart to driver */ @@ -119,8 +118,6 @@ static int get_msg(struct mixart_mgr *mgr, struct mixart_msg *resp, writel_be(headptr, MIXART_MEM(mgr, MSG_OUTBOUND_FREE_HEAD)); _clean_exit: - mutex_unlock(&mgr->msg_lock); - return err; } @@ -258,7 +255,9 @@ int snd_mixart_send_msg(struct mixart_mgr *mgr, struct mixart_msg *request, int resp.data = resp_data; resp.size = max_resp_size; + mutex_lock(&mgr->msg_lock); err = get_msg(mgr, &resp, msg_frame); + mutex_unlock(&mgr->msg_lock); if( request->message_id != resp.message_id ) dev_err(&mgr->pci->dev, "RESPONSE ERROR!\n"); -- cgit v1.2.3 From 2d8f6481c17db9fa5238b277cdbc392084060b09 Mon Sep 17 00:00:00 2001 From: Georg Kohmann Date: Thu, 19 Nov 2020 10:58:33 +0100 Subject: ipv6: Remove dependency of ipv6_frag_thdr_truncated on ipv6 module IPV6=m NF_DEFRAG_IPV6=y ld: net/ipv6/netfilter/nf_conntrack_reasm.o: in function `nf_ct_frag6_gather': net/ipv6/netfilter/nf_conntrack_reasm.c:462: undefined reference to `ipv6_frag_thdr_truncated' Netfilter is depending on ipv6 symbol ipv6_frag_thdr_truncated. This dependency is forcing IPV6=y. Remove this dependency by moving ipv6_frag_thdr_truncated out of ipv6. This is the same solution as used with a similar issues: Referring to commit 70b095c843266 ("ipv6: remove dependency of nf_defrag_ipv6 on ipv6 module") Fixes: 9d9e937b1c8b ("ipv6/netfilter: Discard first fragment not including all headers") Reported-by: Randy Dunlap Reported-by: kernel test robot Signed-off-by: Georg Kohmann Acked-by: Pablo Neira Ayuso Acked-by: Randy Dunlap # build-tested Link: https://lore.kernel.org/r/20201119095833.8409-1-geokohma@cisco.com Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 2 -- include/net/ipv6_frag.h | 30 ++++++++++++++++++++++++++++++ net/ipv6/netfilter/nf_conntrack_reasm.c | 2 +- net/ipv6/reassembly.c | 31 +------------------------------ 4 files changed, 32 insertions(+), 33 deletions(-) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 637cc6dd12b7..bd1f396cc9c7 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1064,8 +1064,6 @@ int ipv6_skip_exthdr(const struct sk_buff *, int start, u8 *nexthdrp, bool ipv6_ext_hdr(u8 nexthdr); -bool ipv6_frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp); - enum { IP6_FH_F_FRAG = (1 << 0), IP6_FH_F_AUTH = (1 << 1), diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index a21e8b1381a1..851029ecff13 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -108,5 +108,35 @@ out_rcu_unlock: rcu_read_unlock(); inet_frag_put(&fq->q); } + +/* Check if the upper layer header is truncated in the first fragment. */ +static inline bool +ipv6frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp) +{ + u8 nexthdr = *nexthdrp; + __be16 frag_off; + int offset; + + offset = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off); + if (offset < 0 || (frag_off & htons(IP6_OFFSET))) + return false; + switch (nexthdr) { + case NEXTHDR_TCP: + offset += sizeof(struct tcphdr); + break; + case NEXTHDR_UDP: + offset += sizeof(struct udphdr); + break; + case NEXTHDR_ICMP: + offset += sizeof(struct icmp6hdr); + break; + default: + offset += 1; + } + if (offset > skb->len) + return true; + return false; +} + #endif #endif diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index b9cc0b330dbe..c129ad334eb3 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -459,7 +459,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) /* Discard the first fragment if it does not include all headers * RFC 8200, Section 4.5 */ - if (ipv6_frag_thdr_truncated(skb, fhoff, &nexthdr)) { + if (ipv6frag_thdr_truncated(skb, fhoff, &nexthdr)) { pr_debug("Drop incomplete fragment\n"); return 0; } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index e3869bac9c88..47a0dc46cbdb 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -318,35 +318,6 @@ out_fail: return -1; } -/* Check if the upper layer header is truncated in the first fragment. */ -bool ipv6_frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp) -{ - u8 nexthdr = *nexthdrp; - __be16 frag_off; - int offset; - - offset = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off); - if (offset < 0 || (frag_off & htons(IP6_OFFSET))) - return false; - switch (nexthdr) { - case NEXTHDR_TCP: - offset += sizeof(struct tcphdr); - break; - case NEXTHDR_UDP: - offset += sizeof(struct udphdr); - break; - case NEXTHDR_ICMP: - offset += sizeof(struct icmp6hdr); - break; - default: - offset += 1; - } - if (offset > skb->len) - return true; - return false; -} -EXPORT_SYMBOL(ipv6_frag_thdr_truncated); - static int ipv6_frag_rcv(struct sk_buff *skb) { struct frag_hdr *fhdr; @@ -390,7 +361,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) * the source of the fragment, with the Pointer field set to zero. */ nexthdr = hdr->nexthdr; - if (ipv6_frag_thdr_truncated(skb, skb_transport_offset(skb), &nexthdr)) { + if (ipv6frag_thdr_truncated(skb, skb_transport_offset(skb), &nexthdr)) { __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0); -- cgit v1.2.3 From 0530bd6e6a3d5a0292a1a5f33ea980ae7e8b56ca Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 18 Nov 2020 22:40:37 +0100 Subject: net/smc: fix matching of existing link groups With the multi-subnet support of SMC-Dv2 the match for existing link groups should not include the vlanid of the network device. Set ini->smcd_version accordingly before the call to smc_conn_create() and use this value in smc_conn_create() to skip the vlanid check. Fixes: 5c21c4ccafe8 ("net/smc: determine accepted ISM devices") Signed-off-by: Karsten Graul Signed-off-by: Jakub Kicinski --- net/smc/af_smc.c | 3 ++- net/smc/smc_core.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index e9f487c8c6d5..5dd4faaf7d6e 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -979,7 +979,8 @@ static int __smc_connect(struct smc_sock *smc) /* check if smc modes and versions of CLC proposal and accept match */ rc = smc_connect_check_aclc(ini, aclc); - version = aclc->hdr.version == SMC_V1 ? SMC_V1 : version; + version = aclc->hdr.version == SMC_V1 ? SMC_V1 : SMC_V2; + ini->smcd_version = version; if (rc) goto vlan_cleanup; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2b19863f7171..af96f813c075 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1309,7 +1309,8 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) ini->ism_peer_gid[ini->ism_selected]) : smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) && !lgr->sync_err && - lgr->vlan_id == ini->vlan_id && + (ini->smcd_version == SMC_V2 || + lgr->vlan_id == ini->vlan_id) && (role == SMC_CLNT || ini->is_smcd || lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) { /* link group found */ -- cgit v1.2.3 From 41a0be3f8f6be893860b991eb10c47fc3ee09d7f Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 18 Nov 2020 22:40:38 +0100 Subject: net/smc: fix direct access to ib_gid_addr->ndev in smc_ib_determine_gid() Sparse complaints 3 times about: net/smc/smc_ib.c:203:52: warning: incorrect type in argument 1 (different address spaces) net/smc/smc_ib.c:203:52: expected struct net_device const *dev net/smc/smc_ib.c:203:52: got struct net_device [noderef] __rcu *const ndev Fix that by using the existing and validated ndev variable instead of accessing attr->ndev directly. Fixes: 5102eca9039b ("net/smc: Use rdma_read_gid_l2_fields to L2 fields") Signed-off-by: Karsten Graul Signed-off-by: Jakub Kicinski --- net/smc/smc_ib.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 1c314dbdc7fa..fc766b537ac7 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -198,9 +198,9 @@ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, rcu_read_lock(); ndev = rdma_read_gid_attr_ndev_rcu(attr); if (!IS_ERR(ndev) && - ((!vlan_id && !is_vlan_dev(attr->ndev)) || - (vlan_id && is_vlan_dev(attr->ndev) && - vlan_dev_vlan_id(attr->ndev) == vlan_id)) && + ((!vlan_id && !is_vlan_dev(ndev)) || + (vlan_id && is_vlan_dev(ndev) && + vlan_dev_vlan_id(ndev) == vlan_id)) && attr->gid_type == IB_GID_TYPE_ROCE) { rcu_read_unlock(); if (gid) -- cgit v1.2.3 From 01822dd1bacfce25418cd4662c14240e6eb17ad6 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Mon, 21 Sep 2020 16:25:36 +0200 Subject: drm/vram-helper: Fix use of top-down placement MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 7053e0eab473 ("drm/vram-helper: stop using TTM placement flags") cleared the BO placement flags if top-down placement had been selected. Hence, BOs that were supposed to go into VRAM are now placed in a default location in system memory. Trying to scanout the incorrectly pinned BO results in displayed garbage and an error message. [ 146.108127] ------------[ cut here ]------------ [ 146.1V08180] WARNING: CPU: 0 PID: 152 at drivers/gpu/drm/drm_gem_vram_helper.c:284 drm_gem_vram_offset+0x59/0x60 [drm_vram_helper] ... [ 146.108591] ast_cursor_page_flip+0x3e/0x150 [ast] [ 146.108622] ast_cursor_plane_helper_atomic_update+0x8a/0xc0 [ast] [ 146.108654] drm_atomic_helper_commit_planes+0x197/0x4c0 [ 146.108699] drm_atomic_helper_commit_tail_rpm+0x59/0xa0 [ 146.108718] commit_tail+0x103/0x1c0 ... [ 146.109302] ---[ end trace d901a1ba1d949036 ]--- Fix the bug by keeping the placement flags. The top-down placement flag is stored in a separate variable. Signed-off-by: Thomas Zimmermann Reviewed-by: Christian König Fixes: 7053e0eab473 ("drm/vram-helper: stop using TTM placement flags") Reported-by: Pu Wen [for 5.10-rc1] Tested-by: Pu Wen Cc: Christian König Cc: Dave Airlie Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: David Airlie Cc: Daniel Vetter Cc: dri-devel@lists.freedesktop.org Link: https://patchwork.freedesktop.org/patch/msgid/20200921142536.4392-1-tzimmermann@suse.de (cherry picked from commit b8f8dbf6495850b0babc551377bde754b7bc0eea) [pulled into fixes from drm-next] Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_gem_vram_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 50cad0e4a92e..375c79e23ca5 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -140,7 +140,7 @@ static void drm_gem_vram_placement(struct drm_gem_vram_object *gbo, unsigned int c = 0; if (pl_flag & DRM_GEM_VRAM_PL_FLAG_TOPDOWN) - pl_flag = TTM_PL_FLAG_TOPDOWN; + invariant_flags = TTM_PL_FLAG_TOPDOWN; gbo->placement.placement = gbo->placements; gbo->placement.busy_placement = gbo->placements; -- cgit v1.2.3 From 6fa6d28051e9fcaa1570e69648ea13a353a5d218 Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Tue, 17 Nov 2020 12:05:45 -0800 Subject: lib/strncpy_from_user.c: Mask out bytes after NUL terminator. do_strncpy_from_user() may copy some extra bytes after the NUL terminator into the destination buffer. This usually does not matter for normal string operations. However, when BPF programs key BPF maps with strings, this matters a lot. A BPF program may read strings from user memory by calling the bpf_probe_read_user_str() helper which eventually calls do_strncpy_from_user(). The program can then key a map with the destination buffer. BPF map keys are fixed-width and string-agnostic, meaning that map keys are treated as a set of bytes. The issue is when do_strncpy_from_user() overcopies bytes after the NUL terminator, it can result in seemingly identical strings occupying multiple slots in a BPF map. This behavior is subtle and totally unexpected by the user. This commit masks out the bytes following the NUL while preserving long-sized stride in the fast path. Fixes: 6ae08ae3dea2 ("bpf: Add probe_read_{user, kernel} and probe_read_{user, kernel}_str helpers") Signed-off-by: Daniel Xu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/21efc982b3e9f2f7b0379eed642294caaa0c27a7.1605642949.git.dxu@dxuuu.xyz --- kernel/trace/bpf_trace.c | 10 ++++++++++ lib/strncpy_from_user.c | 19 +++++++++++++++++-- 2 files changed, 27 insertions(+), 2 deletions(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 5113fd423cdf..048c655315f1 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -181,6 +181,16 @@ bpf_probe_read_user_str_common(void *dst, u32 size, { int ret; + /* + * NB: We rely on strncpy_from_user() not copying junk past the NUL + * terminator into `dst`. + * + * strncpy_from_user() does long-sized strides in the fast path. If the + * strncpy does not mask out the bytes after the NUL in `unsafe_ptr`, + * then there could be junk after the NUL in `dst`. If user takes `dst` + * and keys a hash map with it, then semantically identical strings can + * occupy multiple entries in the map. + */ ret = strncpy_from_user_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index e6d5fcc2cdf3..122d8d0e253c 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -35,17 +35,32 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src, goto byte_at_a_time; while (max >= sizeof(unsigned long)) { - unsigned long c, data; + unsigned long c, data, mask; /* Fall back to byte-at-a-time if we get a page fault */ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); - *(unsigned long *)(dst+res) = c; + /* + * Note that we mask out the bytes following the NUL. This is + * important to do because string oblivious code may read past + * the NUL. For those routines, we don't want to give them + * potentially random bytes after the NUL in `src`. + * + * One example of such code is BPF map keys. BPF treats map keys + * as an opaque set of bytes. Without the post-NUL mask, any BPF + * maps keyed by strings returned from strncpy_from_user() may + * have multiple entries for semantically identical strings. + */ if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); + mask = zero_bytemask(data); + *(unsigned long *)(dst+res) = c & mask; return res + find_zero(data); } + + *(unsigned long *)(dst+res) = c; + res += sizeof(unsigned long); max -= sizeof(unsigned long); } -- cgit v1.2.3 From c8a36aedf3e24768e94d87fdcdd37684bd241c44 Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Tue, 17 Nov 2020 12:05:46 -0800 Subject: selftest/bpf: Test bpf_probe_read_user_str() strips trailing bytes after NUL Previously, bpf_probe_read_user_str() could potentially overcopy the trailing bytes after the NUL due to how do_strncpy_from_user() does the copy in long-sized strides. The issue has been fixed in the previous commit. This commit adds a selftest that ensures we don't regress bpf_probe_read_user_str() again. Signed-off-by: Daniel Xu Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/4d977508fab4ec5b7b574b85bdf8b398868b6ee9.1605642949.git.dxu@dxuuu.xyz --- .../selftests/bpf/prog_tests/probe_read_user_str.c | 71 ++++++++++++++++++++++ .../selftests/bpf/progs/test_probe_read_user_str.c | 25 ++++++++ 2 files changed, 96 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c create mode 100644 tools/testing/selftests/bpf/progs/test_probe_read_user_str.c diff --git a/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c b/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c new file mode 100644 index 000000000000..e419298132b5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include "test_probe_read_user_str.skel.h" + +static const char str1[] = "mestring"; +static const char str2[] = "mestringalittlebigger"; +static const char str3[] = "mestringblubblubblubblubblub"; + +static int test_one_str(struct test_probe_read_user_str *skel, const char *str, + size_t len) +{ + int err, duration = 0; + char buf[256]; + + /* Ensure bytes after string are ones */ + memset(buf, 1, sizeof(buf)); + memcpy(buf, str, len); + + /* Give prog our userspace pointer */ + skel->bss->user_ptr = buf; + + /* Trigger tracepoint */ + usleep(1); + + /* Did helper fail? */ + if (CHECK(skel->bss->ret < 0, "prog_ret", "prog returned: %ld\n", + skel->bss->ret)) + return 1; + + /* Check that string was copied correctly */ + err = memcmp(skel->bss->buf, str, len); + if (CHECK(err, "memcmp", "prog copied wrong string")) + return 1; + + /* Now check that no extra trailing bytes were copied */ + memset(buf, 0, sizeof(buf)); + err = memcmp(skel->bss->buf + len, buf, sizeof(buf) - len); + if (CHECK(err, "memcmp", "trailing bytes were not stripped")) + return 1; + + return 0; +} + +void test_probe_read_user_str(void) +{ + struct test_probe_read_user_str *skel; + int err, duration = 0; + + skel = test_probe_read_user_str__open_and_load(); + if (CHECK(!skel, "test_probe_read_user_str__open_and_load", + "skeleton open and load failed\n")) + return; + + /* Give pid to bpf prog so it doesn't read from anyone else */ + skel->bss->pid = getpid(); + + err = test_probe_read_user_str__attach(skel); + if (CHECK(err, "test_probe_read_user_str__attach", + "skeleton attach failed: %d\n", err)) + goto out; + + if (test_one_str(skel, str1, sizeof(str1))) + goto out; + if (test_one_str(skel, str2, sizeof(str2))) + goto out; + if (test_one_str(skel, str3, sizeof(str3))) + goto out; + +out: + test_probe_read_user_str__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c new file mode 100644 index 000000000000..3ae398b75dcd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include + +#include + +pid_t pid = 0; +long ret = 0; +void *user_ptr = 0; +char buf[256] = {}; + +SEC("tracepoint/syscalls/sys_enter_nanosleep") +int on_write(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + ret = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr); + + return 0; +} + +char _license[] SEC("license") = "GPL"; -- cgit v1.2.3 From 2801a5da5b25b7af9dd2addd19b2315c02d17b64 Mon Sep 17 00:00:00 2001 From: Luo Meng Date: Wed, 18 Nov 2020 22:49:31 +0900 Subject: fail_function: Remove a redundant mutex unlock Fix a mutex_unlock() issue where before copy_from_user() is not called mutex_locked. Fixes: 4b1a29a7f542 ("error-injection: Support fault injection framework") Reported-by: Hulk Robot Signed-off-by: Luo Meng Signed-off-by: Masami Hiramatsu Signed-off-by: Alexei Starovoitov Acked-by: Masami Hiramatsu Link: https://lore.kernel.org/bpf/160570737118.263807.8358435412898356284.stgit@devnote2 --- kernel/fail_function.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/kernel/fail_function.c b/kernel/fail_function.c index 63b349168da7..b0b1ad93fa95 100644 --- a/kernel/fail_function.c +++ b/kernel/fail_function.c @@ -253,7 +253,7 @@ static ssize_t fei_write(struct file *file, const char __user *buffer, if (copy_from_user(buf, buffer, count)) { ret = -EFAULT; - goto out; + goto out_free; } buf[count] = '\0'; sym = strstrip(buf); @@ -307,8 +307,9 @@ static ssize_t fei_write(struct file *file, const char __user *buffer, ret = count; } out: - kfree(buf); mutex_unlock(&fei_lock); +out_free: + kfree(buf); return ret; } -- cgit v1.2.3 From be33805c65297611971003d72e7f9235e23ec84d Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 15 Oct 2020 13:21:38 +0100 Subject: drm/i915/gt: Fixup tgl mocs for PTE tracking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Forcing mocs:1 [used for our winsys follows-pte mode] to be cached caused display glitches. Though it is documented as deprecated (and so likely behaves as uncached) use the follow-pte bit and force it out of L3 cache. Testcase: igt/kms_frontbuffer_tracking Testcase: igt/kms_big_fb Signed-off-by: Chris Wilson Cc: Ayaz A Siddiqui Cc: Lucas De Marchi Cc: Matt Roper Cc: Ville Syrjälä Cc: Joonas Lahtinen Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20201015122138.30161-4-chris@chris-wilson.co.uk (cherry picked from commit a04ac827366594c7244f60e9be79fcb404af69f0) Fixes: 849c0fe9e831 ("drm/i915/gt: Initialize reserved and unspecified MOCS indices") Signed-off-by: Rodrigo Vivi [Rodrigo: Updated Fixes tag] --- drivers/gpu/drm/i915/gt/intel_mocs.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index b8f56e62158e..313e51e7d4f7 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -243,8 +243,9 @@ static const struct drm_i915_mocs_entry tgl_mocs_table[] = { * only, __init_mocs_table() take care to program unused index with * this entry. */ - MOCS_ENTRY(1, LE_3_WB | LE_TC_1_LLC | LE_LRUM(3), - L3_3_WB), + MOCS_ENTRY(I915_MOCS_PTE, + LE_0_PAGETABLE | LE_TC_0_PAGETABLE, + L3_1_UC), GEN11_MOCS_ENTRIES, /* Implicitly enable L1 - HDC:L1 + L3 + LLC */ -- cgit v1.2.3 From f6341f6448e04c9a0ab22fabe38d0c6b43aab848 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:06 +0100 Subject: mtd: rawnand: gpio: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(), a NAND controller hook. Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Reported-by: Christophe Leroy Signed-off-by: Miquel Raynal Tested-by: Christophe Leroy Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-2-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/gpio.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/raw/gpio.c b/drivers/mtd/nand/raw/gpio.c index 4ec0a1e10867..eb03b8cea1cb 100644 --- a/drivers/mtd/nand/raw/gpio.c +++ b/drivers/mtd/nand/raw/gpio.c @@ -161,8 +161,17 @@ static int gpio_nand_exec_op(struct nand_chip *chip, return ret; } +static int gpio_nand_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + static const struct nand_controller_ops gpio_nand_ops = { .exec_op = gpio_nand_exec_op, + .attach_chip = gpio_nand_attach_chip, }; #ifdef CONFIG_OF @@ -342,8 +351,6 @@ static int gpio_nand_probe(struct platform_device *pdev) gpiomtd->base.ops = &gpio_nand_ops; nand_set_flash_node(chip, pdev->dev.of_node); - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; chip->options = gpiomtd->plat.options; chip->controller = &gpiomtd->base; -- cgit v1.2.3 From d525914b5bd8d71f7e92a30a170c108c485814ad Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:07 +0100 Subject: mtd: rawnand: xway: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(), a NAND controller hook. Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-3-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/xway_nand.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/raw/xway_nand.c b/drivers/mtd/nand/raw/xway_nand.c index f2dbd63a5c1f..efc5bf5434e0 100644 --- a/drivers/mtd/nand/raw/xway_nand.c +++ b/drivers/mtd/nand/raw/xway_nand.c @@ -62,6 +62,7 @@ #define NAND_CON_NANDM 1 struct xway_nand_data { + struct nand_controller controller; struct nand_chip chip; unsigned long csflags; void __iomem *nandaddr; @@ -145,6 +146,18 @@ static void xway_write_buf(struct nand_chip *chip, const u_char *buf, int len) xway_writeb(nand_to_mtd(chip), NAND_WRITE_DATA, buf[i]); } +static int xway_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + +static const struct nand_controller_ops xway_nand_ops = { + .attach_chip = xway_attach_chip, +}; + /* * Probe for the NAND device. */ @@ -180,8 +193,9 @@ static int xway_nand_probe(struct platform_device *pdev) data->chip.legacy.read_byte = xway_read_byte; data->chip.legacy.chip_delay = 30; - data->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - data->chip.ecc.algo = NAND_ECC_ALGO_HAMMING; + nand_controller_init(&data->controller); + data->controller.ops = &xway_nand_ops; + data->chip.controller = &data->controller; platform_set_drvdata(pdev, data); nand_set_controller_data(&data->chip, data); -- cgit v1.2.3 From 59d93473323ab104c733778831c459f4cdbe95b2 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:08 +0100 Subject: mtd: rawnand: ams-delta: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-4-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/ams-delta.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index d3c5cc513c8f..0c352b39ad4b 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -215,8 +215,17 @@ static int gpio_nand_setup_interface(struct nand_chip *this, int csline, return 0; } +static int gpio_nand_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + static const struct nand_controller_ops gpio_nand_ops = { .exec_op = gpio_nand_exec_op, + .attach_chip = gpio_nand_attach_chip, .setup_interface = gpio_nand_setup_interface, }; @@ -260,9 +269,6 @@ static int gpio_nand_probe(struct platform_device *pdev) return err; } - this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - this->ecc.algo = NAND_ECC_ALGO_HAMMING; - platform_set_drvdata(pdev, priv); /* Set chip enabled but write protected */ -- cgit v1.2.3 From dbffc8ccdf3a1d0c93bc923cb2dce3272d5fd4e8 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:09 +0100 Subject: mtd: rawnand: au1550: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-5-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/au1550nd.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/raw/au1550nd.c b/drivers/mtd/nand/raw/au1550nd.c index 79b057400fe9..7892022bd6dd 100644 --- a/drivers/mtd/nand/raw/au1550nd.c +++ b/drivers/mtd/nand/raw/au1550nd.c @@ -236,8 +236,17 @@ static int au1550nd_exec_op(struct nand_chip *this, return ret; } +static int au1550nd_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + static const struct nand_controller_ops au1550nd_ops = { .exec_op = au1550nd_exec_op, + .attach_chip = au1550nd_attach_chip, }; static int au1550nd_probe(struct platform_device *pdev) @@ -294,8 +303,6 @@ static int au1550nd_probe(struct platform_device *pdev) nand_controller_init(&ctx->controller); ctx->controller.ops = &au1550nd_ops; this->controller = &ctx->controller; - this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - this->ecc.algo = NAND_ECC_ALGO_HAMMING; if (pd->devwidth) this->options |= NAND_BUSWIDTH_16; -- cgit v1.2.3 From 704c2317cab5571da0e5763cd47ad07f8900aa76 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 19 Nov 2020 15:36:25 -0500 Subject: ext4: drop fast_commit from /proc/mounts The options in /proc/mounts must be valid mount options --- and fast_commit is not a mount option. Otherwise, command sequences like this will fail: # mount /dev/vdc /vdc # mkdir -p /vdc/phoronix_test_suite /pts # mount --bind /vdc/phoronix_test_suite /pts # mount -o remount,nodioread_nolock /pts mount: /pts: mount point not mounted or bad option. And in the system logs, you'll find: EXT4-fs (vdc): Unrecognized mount option "fast_commit" or missing value Fixes: 995a3ed67fc8 ("ext4: add fast_commit feature and handling for extended mount options") Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6633b20224d5..94472044f4c1 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2638,10 +2638,6 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, } else if (test_opt2(sb, DAX_INODE)) { SEQ_OPTS_PUTS("dax=inode"); } - - if (test_opt2(sb, JOURNAL_FAST_COMMIT)) - SEQ_OPTS_PUTS("fast_commit"); - ext4_show_quota_options(seq, sb); return 0; } -- cgit v1.2.3 From 58e111002887ad5f0b665685aac3d4c3bc3768db Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:10 +0100 Subject: mtd: rawnand: cs553x: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/cs553x_nand.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c index b7f3f6347761..282203debd0c 100644 --- a/drivers/mtd/nand/raw/cs553x_nand.c +++ b/drivers/mtd/nand/raw/cs553x_nand.c @@ -243,8 +243,24 @@ static int cs_calculate_ecc(struct nand_chip *this, const u_char *dat, static struct cs553x_nand_controller *controllers[4]; +static int cs553x_attach_chip(struct nand_chip *chip) +{ + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + + chip->ecc.size = 256; + chip->ecc.bytes = 3; + chip->ecc.hwctl = cs_enable_hwecc; + chip->ecc.calculate = cs_calculate_ecc; + chip->ecc.correct = nand_correct_data; + chip->ecc.strength = 1; + + return 0; +} + static const struct nand_controller_ops cs553x_nand_controller_ops = { .exec_op = cs553x_exec_op, + .attach_chip = cs553x_attach_chip, }; static int __init cs553x_init_one(int cs, int mmio, unsigned long adr) @@ -286,14 +302,6 @@ static int __init cs553x_init_one(int cs, int mmio, unsigned long adr) goto out_mtd; } - this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - this->ecc.size = 256; - this->ecc.bytes = 3; - this->ecc.hwctl = cs_enable_hwecc; - this->ecc.calculate = cs_calculate_ecc; - this->ecc.correct = nand_correct_data; - this->ecc.strength = 1; - /* Enable the following for a flash based bad block table */ this->bbt_options = NAND_BBT_USE_FLASH; -- cgit v1.2.3 From 3500bd7035ee6df2a465f37439d3cb9e00d2f66a Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:11 +0100 Subject: mtd: rawnand: davinci: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Cc: Bartosz Golaszewski Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-7-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/davinci_nand.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c index 427f320fb79b..f8c36d19ab47 100644 --- a/drivers/mtd/nand/raw/davinci_nand.c +++ b/drivers/mtd/nand/raw/davinci_nand.c @@ -585,6 +585,10 @@ static int davinci_nand_attach_chip(struct nand_chip *chip) if (IS_ERR(pdata)) return PTR_ERR(pdata); + /* Use board-specific ECC config */ + info->chip.ecc.engine_type = pdata->engine_type; + info->chip.ecc.placement = pdata->ecc_placement; + switch (info->chip.ecc.engine_type) { case NAND_ECC_ENGINE_TYPE_NONE: pdata->ecc_bits = 0; @@ -850,10 +854,6 @@ static int nand_davinci_probe(struct platform_device *pdev) info->mask_ale = pdata->mask_ale ? : MASK_ALE; info->mask_cle = pdata->mask_cle ? : MASK_CLE; - /* Use board-specific ECC config */ - info->chip.ecc.engine_type = pdata->engine_type; - info->chip.ecc.placement = pdata->ecc_placement; - spin_lock_irq(&davinci_nand_lock); /* put CSxNAND into NAND mode */ -- cgit v1.2.3 From 7f4ea0340ed4fa5cdfff6b1dd9f51f293d3f5ee7 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:12 +0100 Subject: mtd: rawnand: diskonchip: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-8-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/diskonchip.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c index 94432a453e5e..26b265e4384a 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -1269,12 +1269,31 @@ static inline int __init doc2001plus_init(struct mtd_info *mtd) return 1; } +static int doc200x_attach_chip(struct nand_chip *chip) +{ + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + + chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED; + chip->ecc.size = 512; + chip->ecc.bytes = 6; + chip->ecc.strength = 2; + chip->ecc.options = NAND_ECC_GENERIC_ERASED_CHECK; + chip->ecc.hwctl = doc200x_enable_hwecc; + chip->ecc.calculate = doc200x_calculate_ecc; + chip->ecc.correct = doc200x_correct_data; + + return 0; +} + static const struct nand_controller_ops doc200x_ops = { .exec_op = doc200x_exec_op, + .attach_chip = doc200x_attach_chip, }; static const struct nand_controller_ops doc2001plus_ops = { .exec_op = doc2001plus_exec_op, + .attach_chip = doc200x_attach_chip, }; static int __init doc_probe(unsigned long physadr) @@ -1452,16 +1471,6 @@ static int __init doc_probe(unsigned long physadr) nand->controller = &doc->base; nand_set_controller_data(nand, doc); - nand->ecc.hwctl = doc200x_enable_hwecc; - nand->ecc.calculate = doc200x_calculate_ecc; - nand->ecc.correct = doc200x_correct_data; - - nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - nand->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED; - nand->ecc.size = 512; - nand->ecc.bytes = 6; - nand->ecc.strength = 2; - nand->ecc.options = NAND_ECC_GENERIC_ERASED_CHECK; nand->bbt_options = NAND_BBT_USE_FLASH; /* Skip the automatic BBT scan so we can run it manually */ nand->options |= NAND_SKIP_BBTSCAN | NAND_NO_BBM_QUIRK; -- cgit v1.2.3 From 98591a68736f3d2431384b5284713fb98da488a6 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:13 +0100 Subject: mtd: rawnand: fsmc: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/fsmc_nand.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index 4191831df182..c88421a1c078 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -880,6 +880,20 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand) struct mtd_info *mtd = nand_to_mtd(nand); struct fsmc_nand_data *host = nand_to_fsmc(nand); + if (nand->ecc.engine_type == NAND_ECC_ENGINE_TYPE_INVALID) + nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; + + if (!nand->ecc.size) + nand->ecc.size = 512; + + if (AMBA_REV_BITS(host->pid) >= 8) { + nand->ecc.read_page = fsmc_read_page_hwecc; + nand->ecc.calculate = fsmc_read_hwecc_ecc4; + nand->ecc.correct = fsmc_bch8_correct_data; + nand->ecc.bytes = 13; + nand->ecc.strength = 8; + } + if (AMBA_REV_BITS(host->pid) >= 8) { switch (mtd->oobsize) { case 16: @@ -905,6 +919,7 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand) dev_info(host->dev, "Using 1-bit HW ECC scheme\n"); nand->ecc.calculate = fsmc_read_hwecc_ecc1; nand->ecc.correct = nand_correct_data; + nand->ecc.hwctl = fsmc_enable_hwecc; nand->ecc.bytes = 3; nand->ecc.strength = 1; nand->ecc.options |= NAND_ECC_SOFT_HAMMING_SM_ORDER; @@ -1055,13 +1070,6 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) mtd->dev.parent = &pdev->dev; - /* - * Setup default ECC mode. nand_dt_init() called from nand_scan_ident() - * can overwrite this value if the DT provides a different value. - */ - nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - nand->ecc.hwctl = fsmc_enable_hwecc; - nand->ecc.size = 512; nand->badblockbits = 7; if (host->mode == USE_DMA_ACCESS) { @@ -1084,14 +1092,6 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) nand->options |= NAND_KEEP_TIMINGS; } - if (AMBA_REV_BITS(host->pid) >= 8) { - nand->ecc.read_page = fsmc_read_page_hwecc; - nand->ecc.calculate = fsmc_read_hwecc_ecc4; - nand->ecc.correct = fsmc_bch8_correct_data; - nand->ecc.bytes = 13; - nand->ecc.strength = 8; - } - nand_controller_init(&host->base); host->base.ops = &fsmc_nand_controller_ops; nand->controller = &host->base; -- cgit v1.2.3 From 2dbd8382a2e1a9b167712dc3764616bfdb189818 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:14 +0100 Subject: mtd: rawnand: lpc32xx_mlc: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Cc: Vladimir Zapolskiy Cc: Sylvain Lemieux Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-10-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/lpc32xx_mlc.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c index 4940bb2e3c07..9e728c731795 100644 --- a/drivers/mtd/nand/raw/lpc32xx_mlc.c +++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c @@ -648,6 +648,9 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip) struct lpc32xx_nand_host *host = nand_get_controller_data(chip); struct device *dev = &host->pdev->dev; + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + host->dma_buf = devm_kzalloc(dev, mtd->writesize, GFP_KERNEL); if (!host->dma_buf) return -ENOMEM; @@ -656,8 +659,17 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip) if (!host->dummy_buf) return -ENOMEM; - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; chip->ecc.size = 512; + chip->ecc.hwctl = lpc32xx_ecc_enable; + chip->ecc.read_page_raw = lpc32xx_read_page; + chip->ecc.read_page = lpc32xx_read_page; + chip->ecc.write_page_raw = lpc32xx_write_page_lowlevel; + chip->ecc.write_page = lpc32xx_write_page_lowlevel; + chip->ecc.write_oob = lpc32xx_write_oob; + chip->ecc.read_oob = lpc32xx_read_oob; + chip->ecc.strength = 4; + chip->ecc.bytes = 10; + mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops); host->mlcsubpages = mtd->writesize / 512; @@ -741,15 +753,6 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) platform_set_drvdata(pdev, host); /* Initialize function pointers */ - nand_chip->ecc.hwctl = lpc32xx_ecc_enable; - nand_chip->ecc.read_page_raw = lpc32xx_read_page; - nand_chip->ecc.read_page = lpc32xx_read_page; - nand_chip->ecc.write_page_raw = lpc32xx_write_page_lowlevel; - nand_chip->ecc.write_page = lpc32xx_write_page_lowlevel; - nand_chip->ecc.write_oob = lpc32xx_write_oob; - nand_chip->ecc.read_oob = lpc32xx_read_oob; - nand_chip->ecc.strength = 4; - nand_chip->ecc.bytes = 10; nand_chip->legacy.waitfunc = lpc32xx_waitfunc; nand_chip->options = NAND_NO_SUBPAGE_WRITE; -- cgit v1.2.3 From e044b8b72151637738b0d2880d62ee5e21f6be5d Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:15 +0100 Subject: mtd: rawnand: lpc32xx_slc: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Cc: Vladimir Zapolskiy Cc: Sylvain Lemieux --- drivers/mtd/nand/raw/lpc32xx_slc.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c index 6db9d2ed6881..dc7785e30d2f 100644 --- a/drivers/mtd/nand/raw/lpc32xx_slc.c +++ b/drivers/mtd/nand/raw/lpc32xx_slc.c @@ -775,6 +775,9 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip) struct mtd_info *mtd = nand_to_mtd(chip); struct lpc32xx_nand_host *host = nand_get_controller_data(chip); + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + /* OOB and ECC CPU and DMA work areas */ host->ecc_buf = (uint32_t *)(host->data_buf + LPC32XX_DMA_DATA_SIZE); @@ -786,11 +789,22 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip) if (mtd->writesize <= 512) mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops); + chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED; /* These sizes remain the same regardless of page size */ chip->ecc.size = 256; + chip->ecc.strength = 1; chip->ecc.bytes = LPC32XX_SLC_DEV_ECC_BYTES; chip->ecc.prepad = 0; chip->ecc.postpad = 0; + chip->ecc.read_page_raw = lpc32xx_nand_read_page_raw_syndrome; + chip->ecc.read_page = lpc32xx_nand_read_page_syndrome; + chip->ecc.write_page_raw = lpc32xx_nand_write_page_raw_syndrome; + chip->ecc.write_page = lpc32xx_nand_write_page_syndrome; + chip->ecc.write_oob = lpc32xx_nand_write_oob_syndrome; + chip->ecc.read_oob = lpc32xx_nand_read_oob_syndrome; + chip->ecc.calculate = lpc32xx_nand_ecc_calculate; + chip->ecc.correct = nand_correct_data; + chip->ecc.hwctl = lpc32xx_nand_ecc_enable; /* * Use a custom BBT marker setup for small page FLASH that @@ -881,21 +895,9 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) platform_set_drvdata(pdev, host); /* NAND callbacks for LPC32xx SLC hardware */ - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED; chip->legacy.read_byte = lpc32xx_nand_read_byte; chip->legacy.read_buf = lpc32xx_nand_read_buf; chip->legacy.write_buf = lpc32xx_nand_write_buf; - chip->ecc.read_page_raw = lpc32xx_nand_read_page_raw_syndrome; - chip->ecc.read_page = lpc32xx_nand_read_page_syndrome; - chip->ecc.write_page_raw = lpc32xx_nand_write_page_raw_syndrome; - chip->ecc.write_page = lpc32xx_nand_write_page_syndrome; - chip->ecc.write_oob = lpc32xx_nand_write_oob_syndrome; - chip->ecc.read_oob = lpc32xx_nand_read_oob_syndrome; - chip->ecc.calculate = lpc32xx_nand_ecc_calculate; - chip->ecc.correct = nand_correct_data; - chip->ecc.strength = 1; - chip->ecc.hwctl = lpc32xx_nand_ecc_enable; /* * Allocate a large enough buffer for a single huge page plus -- cgit v1.2.3 From 6dd09f775b729478e180eed295ddfa50569e61be Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:16 +0100 Subject: mtd: rawnand: mpc5121: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-12-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/mpc5121_nfc.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/raw/mpc5121_nfc.c b/drivers/mtd/nand/raw/mpc5121_nfc.c index dfd0d3ed5ed0..fb4c0b11689f 100644 --- a/drivers/mtd/nand/raw/mpc5121_nfc.c +++ b/drivers/mtd/nand/raw/mpc5121_nfc.c @@ -104,6 +104,7 @@ #define NFC_TIMEOUT (HZ / 10) /* 1/10 s */ struct mpc5121_nfc_prv { + struct nand_controller controller; struct nand_chip chip; int irq; void __iomem *regs; @@ -602,6 +603,18 @@ static void mpc5121_nfc_free(struct device *dev, struct mtd_info *mtd) iounmap(prv->csreg); } +static int mpc5121_nfc_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + +static const struct nand_controller_ops mpc5121_nfc_ops = { + .attach_chip = mpc5121_nfc_attach_chip, +}; + static int mpc5121_nfc_probe(struct platform_device *op) { struct device_node *dn = op->dev.of_node; @@ -634,6 +647,10 @@ static int mpc5121_nfc_probe(struct platform_device *op) chip = &prv->chip; mtd = nand_to_mtd(chip); + nand_controller_init(&prv->controller); + prv->controller.ops = &mpc5121_nfc_ops; + chip->controller = &prv->controller; + mtd->dev.parent = dev; nand_set_controller_data(chip, prv); nand_set_flash_node(chip, dn); @@ -688,8 +705,6 @@ static int mpc5121_nfc_probe(struct platform_device *op) chip->legacy.set_features = nand_get_set_features_notsupp; chip->legacy.get_features = nand_get_set_features_notsupp; chip->bbt_options = NAND_BBT_USE_FLASH; - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; /* Support external chip-select logic on ADS5121 board */ if (of_machine_is_compatible("fsl,mpc5121ads")) { -- cgit v1.2.3 From 553508cec2e8138ec50f284bc8ec10e7ef0d44b1 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:17 +0100 Subject: mtd: rawnand: orion: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-13-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/orion_nand.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c index df9c0f8e4b4e..e3bb65fd3ab2 100644 --- a/drivers/mtd/nand/raw/orion_nand.c +++ b/drivers/mtd/nand/raw/orion_nand.c @@ -22,6 +22,7 @@ #include struct orion_nand_info { + struct nand_controller controller; struct nand_chip chip; struct clk *clk; }; @@ -82,6 +83,18 @@ static void orion_nand_read_buf(struct nand_chip *chip, uint8_t *buf, int len) buf[i++] = readb(io_base); } +static int orion_nand_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + +static const struct nand_controller_ops orion_nand_ops = { + .attach_chip = orion_nand_attach_chip, +}; + static int __init orion_nand_probe(struct platform_device *pdev) { struct orion_nand_info *info; @@ -101,6 +114,10 @@ static int __init orion_nand_probe(struct platform_device *pdev) nc = &info->chip; mtd = nand_to_mtd(nc); + nand_controller_init(&info->controller); + info->controller.ops = &orion_nand_ops; + nc->controller = &info->controller; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); io_base = devm_ioremap_resource(&pdev->dev, res); @@ -139,8 +156,6 @@ static int __init orion_nand_probe(struct platform_device *pdev) nc->legacy.IO_ADDR_R = nc->legacy.IO_ADDR_W = io_base; nc->legacy.cmd_ctrl = orion_nand_cmd_ctrl; nc->legacy.read_buf = orion_nand_read_buf; - nc->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - nc->ecc.algo = NAND_ECC_ALGO_HAMMING; if (board->chip_delay) nc->legacy.chip_delay = board->chip_delay; -- cgit v1.2.3 From 3c3bbf014ab3bc9793a51d550a048873e832f2fa Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:18 +0100 Subject: mtd: rawnand: txx9ndfmc: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-14-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/txx9ndfmc.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c index ef81dce6b5c4..fe8ed2441588 100644 --- a/drivers/mtd/nand/raw/txx9ndfmc.c +++ b/drivers/mtd/nand/raw/txx9ndfmc.c @@ -253,6 +253,11 @@ static int txx9ndfmc_attach_chip(struct nand_chip *chip) { struct mtd_info *mtd = nand_to_mtd(chip); + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + + chip->ecc.strength = 1; + if (mtd->writesize >= 512) { chip->ecc.size = 512; chip->ecc.bytes = 6; @@ -261,6 +266,10 @@ static int txx9ndfmc_attach_chip(struct nand_chip *chip) chip->ecc.bytes = 3; } + chip->ecc.calculate = txx9ndfmc_calculate_ecc; + chip->ecc.correct = txx9ndfmc_correct_data; + chip->ecc.hwctl = txx9ndfmc_enable_hwecc; + return 0; } @@ -326,11 +335,6 @@ static int __init txx9ndfmc_probe(struct platform_device *dev) chip->legacy.write_buf = txx9ndfmc_write_buf; chip->legacy.cmd_ctrl = txx9ndfmc_cmd_ctrl; chip->legacy.dev_ready = txx9ndfmc_dev_ready; - chip->ecc.calculate = txx9ndfmc_calculate_ecc; - chip->ecc.correct = txx9ndfmc_correct_data; - chip->ecc.hwctl = txx9ndfmc_enable_hwecc; - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - chip->ecc.strength = 1; chip->legacy.chip_delay = 100; chip->controller = &drvdata->controller; -- cgit v1.2.3 From 1f65976b55865adf84340d6e07c4c773cb8a728b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:19 +0100 Subject: mtd: rawnand: tmio: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-15-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/tmio_nand.c | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-) diff --git a/drivers/mtd/nand/raw/tmio_nand.c b/drivers/mtd/nand/raw/tmio_nand.c index 235a2f7b1bad..aa6c7e7bbf1b 100644 --- a/drivers/mtd/nand/raw/tmio_nand.c +++ b/drivers/mtd/nand/raw/tmio_nand.c @@ -103,6 +103,7 @@ /*--------------------------------------------------------------------------*/ struct tmio_nand { + struct nand_controller controller; struct nand_chip chip; struct completion comp; @@ -355,6 +356,25 @@ static void tmio_hw_stop(struct platform_device *dev, struct tmio_nand *tmio) cell->disable(dev); } +static int tmio_attach_chip(struct nand_chip *chip) +{ + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + + chip->ecc.size = 512; + chip->ecc.bytes = 6; + chip->ecc.strength = 2; + chip->ecc.hwctl = tmio_nand_enable_hwecc; + chip->ecc.calculate = tmio_nand_calculate_ecc; + chip->ecc.correct = tmio_nand_correct_data; + + return 0; +} + +static const struct nand_controller_ops tmio_ops = { + .attach_chip = tmio_attach_chip, +}; + static int tmio_probe(struct platform_device *dev) { struct tmio_nand_data *data = dev_get_platdata(&dev->dev); @@ -385,6 +405,10 @@ static int tmio_probe(struct platform_device *dev) mtd->name = "tmio-nand"; mtd->dev.parent = &dev->dev; + nand_controller_init(&tmio->controller); + tmio->controller.ops = &tmio_ops; + nand_chip->controller = &tmio->controller; + tmio->ccr = devm_ioremap(&dev->dev, ccr->start, resource_size(ccr)); if (!tmio->ccr) return -EIO; @@ -409,15 +433,6 @@ static int tmio_probe(struct platform_device *dev) nand_chip->legacy.write_buf = tmio_nand_write_buf; nand_chip->legacy.read_buf = tmio_nand_read_buf; - /* set eccmode using hardware ECC */ - nand_chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - nand_chip->ecc.size = 512; - nand_chip->ecc.bytes = 6; - nand_chip->ecc.strength = 2; - nand_chip->ecc.hwctl = tmio_nand_enable_hwecc; - nand_chip->ecc.calculate = tmio_nand_calculate_ecc; - nand_chip->ecc.correct = tmio_nand_correct_data; - if (data) nand_chip->badblock_pattern = data->badblock_pattern; -- cgit v1.2.3 From 8fc6f1f042b2d383f57110ab808b788592550b25 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:20 +0100 Subject: mtd: rawnand: pasemi: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-16-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/pasemi_nand.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/raw/pasemi_nand.c b/drivers/mtd/nand/raw/pasemi_nand.c index 2b8f155cc0c5..4dfff34800f4 100644 --- a/drivers/mtd/nand/raw/pasemi_nand.c +++ b/drivers/mtd/nand/raw/pasemi_nand.c @@ -29,6 +29,7 @@ static unsigned int lpcctl; static struct mtd_info *pasemi_nand_mtd; +static struct nand_controller controller; static const char driver_name[] = "pasemi-nand"; static void pasemi_read_buf(struct nand_chip *chip, u_char *buf, int len) @@ -73,6 +74,18 @@ static int pasemi_device_ready(struct nand_chip *chip) return !!(inl(lpcctl) & LBICTRL_LPCCTL_NR); } +static int pasemi_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + +static const struct nand_controller_ops pasemi_ops = { + .attach_chip = pasemi_attach_chip, +}; + static int pasemi_nand_probe(struct platform_device *ofdev) { struct device *dev = &ofdev->dev; @@ -100,6 +113,10 @@ static int pasemi_nand_probe(struct platform_device *ofdev) goto out; } + controller.ops = &pasemi_ops; + nand_controller_init(&controller); + chip->controller = &controller; + pasemi_nand_mtd = nand_to_mtd(chip); /* Link the private data with the MTD structure */ @@ -132,8 +149,6 @@ static int pasemi_nand_probe(struct platform_device *ofdev) chip->legacy.read_buf = pasemi_read_buf; chip->legacy.write_buf = pasemi_write_buf; chip->legacy.chip_delay = 0; - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; /* Enable the following for a flash based bad block table */ chip->bbt_options = NAND_BBT_USE_FLASH; -- cgit v1.2.3 From 612e048e6aabbc5d042140c0ec494753f36bdfe6 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:21 +0100 Subject: mtd: rawnand: plat_nand: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-17-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/plat_nand.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c index b98c0d5c413f..93d9f1694dc1 100644 --- a/drivers/mtd/nand/raw/plat_nand.c +++ b/drivers/mtd/nand/raw/plat_nand.c @@ -14,10 +14,23 @@ #include struct plat_nand_data { + struct nand_controller controller; struct nand_chip chip; void __iomem *io_base; }; +static int plat_nand_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + +static const struct nand_controller_ops plat_nand_ops = { + .attach_chip = plat_nand_attach_chip, +}; + /* * Probe for the NAND device. */ @@ -46,6 +59,10 @@ static int plat_nand_probe(struct platform_device *pdev) if (!data) return -ENOMEM; + data->controller.ops = &plat_nand_ops; + nand_controller_init(&data->controller); + data->chip.controller = &data->controller; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); data->io_base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(data->io_base)) @@ -66,9 +83,6 @@ static int plat_nand_probe(struct platform_device *pdev) data->chip.options |= pdata->chip.options; data->chip.bbt_options |= pdata->chip.bbt_options; - data->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - data->chip.ecc.algo = NAND_ECC_ALGO_HAMMING; - platform_set_drvdata(pdev, data); /* Handle any platform specific setup */ -- cgit v1.2.3 From eb8409071a1d47e3593cfe077107ac46853182ab Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 19 Nov 2020 15:17:50 -0800 Subject: xfs: revert "xfs: fix rmap key and record comparison functions" This reverts commit 6ff646b2ceb0eec916101877f38da0b73e3a5b7f. Your maintainer committed a major braino in the rmap code by adding the attr fork, bmbt, and unwritten extent usage bits into rmap record key comparisons. While XFS uses the usage bits *in the rmap records* for cross-referencing metadata in xfs_scrub and xfs_repair, it only needs the owner and offset information to distinguish between reverse mappings of the same physical extent into the data fork of a file at multiple offsets. The other bits are not important for key comparisons for index lookups, and never have been. Eric Sandeen reports that this causes regressions in generic/299, so undo this patch before it does more damage. Reported-by: Eric Sandeen Fixes: 6ff646b2ceb0 ("xfs: fix rmap key and record comparison functions") Signed-off-by: Darrick J. Wong Reviewed-by: Eric Sandeen --- fs/xfs/libxfs/xfs_rmap_btree.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index 577a66381327..beb81c84a937 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -243,8 +243,8 @@ xfs_rmapbt_key_diff( else if (y > x) return -1; - x = be64_to_cpu(kp->rm_offset); - y = xfs_rmap_irec_offset_pack(rec); + x = XFS_RMAP_OFF(be64_to_cpu(kp->rm_offset)); + y = rec->rm_offset; if (x > y) return 1; else if (y > x) @@ -275,8 +275,8 @@ xfs_rmapbt_diff_two_keys( else if (y > x) return -1; - x = be64_to_cpu(kp1->rm_offset); - y = be64_to_cpu(kp2->rm_offset); + x = XFS_RMAP_OFF(be64_to_cpu(kp1->rm_offset)); + y = XFS_RMAP_OFF(be64_to_cpu(kp2->rm_offset)); if (x > y) return 1; else if (y > x) @@ -390,8 +390,8 @@ xfs_rmapbt_keys_inorder( return 1; else if (a > b) return 0; - a = be64_to_cpu(k1->rmap.rm_offset); - b = be64_to_cpu(k2->rmap.rm_offset); + a = XFS_RMAP_OFF(be64_to_cpu(k1->rmap.rm_offset)); + b = XFS_RMAP_OFF(be64_to_cpu(k2->rmap.rm_offset)); if (a <= b) return 1; return 0; @@ -420,8 +420,8 @@ xfs_rmapbt_recs_inorder( return 1; else if (a > b) return 0; - a = be64_to_cpu(r1->rmap.rm_offset); - b = be64_to_cpu(r2->rmap.rm_offset); + a = XFS_RMAP_OFF(be64_to_cpu(r1->rmap.rm_offset)); + b = XFS_RMAP_OFF(be64_to_cpu(r2->rmap.rm_offset)); if (a <= b) return 1; return 0; -- cgit v1.2.3 From e92643db514803c2c87d72caf5950b4c0a8faf4a Mon Sep 17 00:00:00 2001 From: Stanley Chu Date: Thu, 19 Nov 2020 14:29:16 +0800 Subject: scsi: ufs: Fix race between shutdown and runtime resume flow If UFS host device is in runtime-suspended state while UFS shutdown callback is invoked, UFS device shall be resumed for register accesses. Currently only UFS local runtime resume function will be invoked to wake up the host. This is not enough because if someone triggers runtime resume from block layer, then race may happen between shutdown and runtime resume flow, and finally lead to unlocked register access. To fix this, in ufshcd_shutdown(), use pm_runtime_get_sync() instead of resuming UFS device by ufshcd_runtime_resume() "internally" to let runtime PM framework manage the whole resume flow. Link: https://lore.kernel.org/r/20201119062916.12931-1-stanley.chu@mediatek.com Fixes: 57d104c153d3 ("ufs: add UFS power management support") Reviewed-by: Can Guo Signed-off-by: Stanley Chu Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 20b16de4c5e2..0c148fcd24de 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -8913,11 +8913,7 @@ int ufshcd_shutdown(struct ufs_hba *hba) if (ufshcd_is_ufs_dev_poweroff(hba) && ufshcd_is_link_off(hba)) goto out; - if (pm_runtime_suspended(hba->dev)) { - ret = ufshcd_runtime_resume(hba); - if (ret) - goto out; - } + pm_runtime_get_sync(hba->dev); ret = ufshcd_suspend(hba, UFS_SHUTDOWN_PM); out: -- cgit v1.2.3 From 2bf31d94423c8ae3ff58e38a115b177df6940399 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 16 Nov 2020 11:18:08 +0100 Subject: jbd2: fix kernel-doc markups Kernel-doc markup should use this format: identifier - description They should not have any type before that, as otherwise the parser won't do the right thing. Also, some identifiers have different names between their prototypes and the kernel-doc markup. Reviewed-by: Jan Kara Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/72f5c6628f5f278d67625f60893ffbc2ca28d46e.1605521731.git.mchehab+huawei@kernel.org Signed-off-by: Theodore Ts'o --- fs/jbd2/journal.c | 34 ++++++++++++++++++---------------- fs/jbd2/transaction.c | 31 ++++++++++++++++--------------- include/linux/jbd2.h | 2 +- 3 files changed, 35 insertions(+), 32 deletions(-) diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 0c3d5e3b24b2..188f79d76988 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -566,12 +566,14 @@ static int __jbd2_journal_force_commit(journal_t *journal) } /** - * Force and wait upon a commit if the calling process is not within - * transaction. This is used for forcing out undo-protected data which contains - * bitmaps, when the fs is running out of space. + * jbd2_journal_force_commit_nested - Force and wait upon a commit if the + * calling process is not within transaction. * * @journal: journal to force * Returns true if progress was made. + * + * This is used for forcing out undo-protected data which contains + * bitmaps, when the fs is running out of space. */ int jbd2_journal_force_commit_nested(journal_t *journal) { @@ -582,7 +584,7 @@ int jbd2_journal_force_commit_nested(journal_t *journal) } /** - * int journal_force_commit() - force any uncommitted transactions + * jbd2_journal_force_commit() - force any uncommitted transactions * @journal: journal to force * * Caller want unconditional commit. We can only force the running transaction @@ -1881,7 +1883,7 @@ static int load_superblock(journal_t *journal) /** - * int jbd2_journal_load() - Read journal from disk. + * jbd2_journal_load() - Read journal from disk. * @journal: Journal to act on. * * Given a journal_t structure which tells us which disk blocks contain @@ -1951,7 +1953,7 @@ recovery_error: } /** - * void jbd2_journal_destroy() - Release a journal_t structure. + * jbd2_journal_destroy() - Release a journal_t structure. * @journal: Journal to act on. * * Release a journal_t structure once it is no longer in use by the @@ -2028,7 +2030,7 @@ int jbd2_journal_destroy(journal_t *journal) /** - *int jbd2_journal_check_used_features() - Check if features specified are used. + * jbd2_journal_check_used_features() - Check if features specified are used. * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -2063,7 +2065,7 @@ int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat, } /** - * int jbd2_journal_check_available_features() - Check feature set in journalling layer + * jbd2_journal_check_available_features() - Check feature set in journalling layer * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -2126,7 +2128,7 @@ jbd2_journal_initialize_fast_commit(journal_t *journal) } /** - * int jbd2_journal_set_features() - Mark a given journal feature in the superblock + * jbd2_journal_set_features() - Mark a given journal feature in the superblock * @journal: Journal to act on. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -2217,7 +2219,7 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, } /* - * jbd2_journal_clear_features () - Clear a given journal feature in the + * jbd2_journal_clear_features() - Clear a given journal feature in the * superblock * @journal: Journal to act on. * @compat: bitmask of compatible features @@ -2246,7 +2248,7 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat, EXPORT_SYMBOL(jbd2_journal_clear_features); /** - * int jbd2_journal_flush () - Flush journal + * jbd2_journal_flush() - Flush journal * @journal: Journal to act on. * * Flush all data for a given journal to disk and empty the journal. @@ -2321,7 +2323,7 @@ out: } /** - * int jbd2_journal_wipe() - Wipe journal contents + * jbd2_journal_wipe() - Wipe journal contents * @journal: Journal to act on. * @write: flag (see below) * @@ -2362,7 +2364,7 @@ int jbd2_journal_wipe(journal_t *journal, int write) } /** - * void jbd2_journal_abort () - Shutdown the journal immediately. + * jbd2_journal_abort () - Shutdown the journal immediately. * @journal: the journal to shutdown. * @errno: an error number to record in the journal indicating * the reason for the shutdown. @@ -2453,7 +2455,7 @@ void jbd2_journal_abort(journal_t *journal, int errno) } /** - * int jbd2_journal_errno () - returns the journal's error state. + * jbd2_journal_errno() - returns the journal's error state. * @journal: journal to examine. * * This is the errno number set with jbd2_journal_abort(), the last @@ -2477,7 +2479,7 @@ int jbd2_journal_errno(journal_t *journal) } /** - * int jbd2_journal_clear_err () - clears the journal's error state + * jbd2_journal_clear_err() - clears the journal's error state * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly @@ -2497,7 +2499,7 @@ int jbd2_journal_clear_err(journal_t *journal) } /** - * void jbd2_journal_ack_err() - Ack journal err. + * jbd2_journal_ack_err() - Ack journal err. * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index d54f04674e8e..9396666b7314 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -519,7 +519,7 @@ EXPORT_SYMBOL(jbd2__journal_start); /** - * handle_t *jbd2_journal_start() - Obtain a new handle. + * jbd2_journal_start() - Obtain a new handle. * @journal: Journal to start transaction on. * @nblocks: number of block buffer we might modify * @@ -566,7 +566,7 @@ void jbd2_journal_free_reserved(handle_t *handle) EXPORT_SYMBOL(jbd2_journal_free_reserved); /** - * int jbd2_journal_start_reserved() - start reserved handle + * jbd2_journal_start_reserved() - start reserved handle * @handle: handle to start * @type: for handle statistics * @line_no: for handle statistics @@ -620,7 +620,7 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, EXPORT_SYMBOL(jbd2_journal_start_reserved); /** - * int jbd2_journal_extend() - extend buffer credits. + * jbd2_journal_extend() - extend buffer credits. * @handle: handle to 'extend' * @nblocks: nr blocks to try to extend by. * @revoke_records: number of revoke records to try to extend by. @@ -745,7 +745,7 @@ static void stop_this_handle(handle_t *handle) } /** - * int jbd2_journal_restart() - restart a handle . + * jbd2__journal_restart() - restart a handle . * @handle: handle to restart * @nblocks: nr credits requested * @revoke_records: number of revoke record credits requested @@ -815,7 +815,7 @@ int jbd2_journal_restart(handle_t *handle, int nblocks) EXPORT_SYMBOL(jbd2_journal_restart); /** - * void jbd2_journal_lock_updates () - establish a transaction barrier. + * jbd2_journal_lock_updates () - establish a transaction barrier. * @journal: Journal to establish a barrier on. * * This locks out any further updates from being started, and blocks @@ -874,7 +874,7 @@ void jbd2_journal_lock_updates(journal_t *journal) } /** - * void jbd2_journal_unlock_updates (journal_t* journal) - release barrier + * jbd2_journal_unlock_updates () - release barrier * @journal: Journal to release the barrier on. * * Release a transaction barrier obtained with jbd2_journal_lock_updates(). @@ -1182,7 +1182,8 @@ out: } /** - * int jbd2_journal_get_write_access() - notify intent to modify a buffer for metadata (not data) update. + * jbd2_journal_get_write_access() - notify intent to modify a buffer + * for metadata (not data) update. * @handle: transaction to add buffer modifications to * @bh: bh to be used for metadata writes * @@ -1226,7 +1227,7 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) * unlocked buffer beforehand. */ /** - * int jbd2_journal_get_create_access () - notify intent to use newly created bh + * jbd2_journal_get_create_access () - notify intent to use newly created bh * @handle: transaction to new buffer to * @bh: new buffer. * @@ -1306,7 +1307,7 @@ out: } /** - * int jbd2_journal_get_undo_access() - Notify intent to modify metadata with + * jbd2_journal_get_undo_access() - Notify intent to modify metadata with * non-rewindable consequences * @handle: transaction * @bh: buffer to undo @@ -1383,7 +1384,7 @@ out: } /** - * void jbd2_journal_set_triggers() - Add triggers for commit writeout + * jbd2_journal_set_triggers() - Add triggers for commit writeout * @bh: buffer to trigger on * @type: struct jbd2_buffer_trigger_type containing the trigger(s). * @@ -1425,7 +1426,7 @@ void jbd2_buffer_abort_trigger(struct journal_head *jh, } /** - * int jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata + * jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata * @handle: transaction to add buffer to. * @bh: buffer to mark * @@ -1593,7 +1594,7 @@ out: } /** - * void jbd2_journal_forget() - bforget() for potentially-journaled buffers. + * jbd2_journal_forget() - bforget() for potentially-journaled buffers. * @handle: transaction handle * @bh: bh to 'forget' * @@ -1762,7 +1763,7 @@ drop: } /** - * int jbd2_journal_stop() - complete a transaction + * jbd2_journal_stop() - complete a transaction * @handle: transaction to complete. * * All done for a particular handle. @@ -2080,7 +2081,7 @@ out: } /** - * int jbd2_journal_try_to_free_buffers() - try to free page buffers. + * jbd2_journal_try_to_free_buffers() - try to free page buffers. * @journal: journal for operation * @page: to try and free * @@ -2411,7 +2412,7 @@ zap_buffer_unlocked: } /** - * void jbd2_journal_invalidatepage() + * jbd2_journal_invalidatepage() * @journal: journal to use for flush... * @page: page to flush * @offset: start of the range to invalidate diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 1c49fd62ff2e..578ff196b3ce 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -401,7 +401,7 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) #define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** - * struct jbd_inode - The jbd_inode type is the structure linking inodes in + * struct jbd2_inode - The jbd_inode type is the structure linking inodes in * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { -- cgit v1.2.3 From f902b216501094495ff75834035656e8119c537f Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 18 Nov 2020 16:30:32 +0100 Subject: ext4: fix bogus warning in ext4_update_dx_flag() The idea of the warning in ext4_update_dx_flag() is that we should warn when we are clearing EXT4_INODE_INDEX on a filesystem with metadata checksums enabled since after clearing the flag, checksums for internal htree nodes will become invalid. So there's no need to warn (or actually do anything) when EXT4_INODE_INDEX is not set. Link: https://lore.kernel.org/r/20201118153032.17281-1-jack@suse.cz Fixes: 48a34311953d ("ext4: fix checksum errors with indexed dirs") Reported-by: Eric Biggers Reviewed-by: Eric Biggers Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o Cc: stable@kernel.org --- fs/ext4/ext4.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index bf9429484462..65ecaf96d0a4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2695,7 +2695,8 @@ void ext4_insert_dentry(struct inode *inode, struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { - if (!ext4_has_feature_dir_index(inode->i_sb)) { + if (!ext4_has_feature_dir_index(inode->i_sb) && + ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { /* ext4_iget() should have caught this... */ WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb)); ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); -- cgit v1.2.3 From b5f796b62c98cd8c219c4b788ecb6e1218e648cb Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Wed, 18 Nov 2020 20:17:31 +0800 Subject: bnxt_en: fix error return code in bnxt_init_one() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: c213eae8d3cd ("bnxt_en: Improve VF/PF link change logic.") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Reviewed-by: Edwin Peer Link: https://lore.kernel.org/r/1605701851-20270-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 7c21aaa8b9af..092775e396c7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12674,6 +12674,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) create_singlethread_workqueue("bnxt_pf_wq"); if (!bnxt_pf_wq) { dev_err(&pdev->dev, "Unable to create workqueue.\n"); + rc = -ENOMEM; goto init_err_pci_clean; } } -- cgit v1.2.3 From 3383176efc0fb0c0900a191026468a58668b4214 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Thu, 19 Nov 2020 21:30:21 +0800 Subject: bnxt_en: fix error return code in bnxt_init_board() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Reviewed-by: Edwin Peer Link: https://lore.kernel.org/r/1605792621-6268-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 092775e396c7..6e8329534cde 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11590,6 +11590,7 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev) if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) != 0 && dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)) != 0) { dev_err(&pdev->dev, "System does not support DMA, aborting\n"); + rc = -EIO; goto init_err_disable; } -- cgit v1.2.3 From 5e4d659b10fde14403adb2e215df4a3168fe8465 Mon Sep 17 00:00:00 2001 From: Vincent Palatin Date: Fri, 20 Nov 2020 10:28:28 +0100 Subject: USB: serial: option: add Fibocom NL668 variants Update the USB serial option driver support for the Fibocom NL668 Cat.4 LTE modules as there are actually several different variants. Got clarifications from Fibocom, there are distinct products: - VID:PID 1508:1001, NL668 for IOT (no MBIM interface) - VID:PID 2cb7:01a0, NL668-AM and NL652-EU are laptop M.2 cards (with MBIM interfaces for Windows/Linux/Chrome OS), respectively for Americas and Europe. usb-devices output for the laptop M.2 cards: T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 4 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=2cb7 ProdID=01a0 Rev=03.18 S: Manufacturer=Fibocom Wireless Inc. S: Product=Fibocom NL652-EU Modem S: SerialNumber=0123456789ABCDEF C: #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim I: If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I: If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) I: If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) I: If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) Signed-off-by: Vincent Palatin Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 54ca85cc920d..2aa31173997f 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -2046,12 +2046,13 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE(0x0489, 0xe0b5), /* Foxconn T77W968 ESIM */ .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, - { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 */ + { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 (IOT version) */ .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, { USB_DEVICE(0x2cb7, 0x0104), /* Fibocom NL678 series */ .driver_info = RSVD(4) | RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0105, 0xff), /* Fibocom NL678 series */ .driver_info = RSVD(6) }, + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) }, /* GosunCn GM500 ECM/NCM */ -- cgit v1.2.3 From 7ef969a042281bdcdba31f1b69daeea4f0789ed1 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:22 +0100 Subject: mtd: rawnand: r852: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Cc: Maxim Levitsky Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-18-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/r852.c | 40 +++++++++++++++++++++++++++------------- drivers/mtd/nand/raw/r852.h | 1 + 2 files changed, 28 insertions(+), 13 deletions(-) diff --git a/drivers/mtd/nand/raw/r852.c b/drivers/mtd/nand/raw/r852.c index 6b7addd2c420..c742354c1b0b 100644 --- a/drivers/mtd/nand/raw/r852.c +++ b/drivers/mtd/nand/raw/r852.c @@ -817,6 +817,29 @@ out: return ret; } +static int r852_attach_chip(struct nand_chip *chip) +{ + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + + chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED; + chip->ecc.size = R852_DMA_LEN; + chip->ecc.bytes = SM_OOB_SIZE; + chip->ecc.strength = 2; + chip->ecc.hwctl = r852_ecc_hwctl; + chip->ecc.calculate = r852_ecc_calculate; + chip->ecc.correct = r852_ecc_correct; + + /* TODO: hack */ + chip->ecc.read_oob = r852_read_oob; + + return 0; +} + +static const struct nand_controller_ops r852_ops = { + .attach_chip = r852_attach_chip, +}; + static int r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) { int error; @@ -858,19 +881,6 @@ static int r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) chip->legacy.read_buf = r852_read_buf; chip->legacy.write_buf = r852_write_buf; - /* ecc */ - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED; - chip->ecc.size = R852_DMA_LEN; - chip->ecc.bytes = SM_OOB_SIZE; - chip->ecc.strength = 2; - chip->ecc.hwctl = r852_ecc_hwctl; - chip->ecc.calculate = r852_ecc_calculate; - chip->ecc.correct = r852_ecc_correct; - - /* TODO: hack */ - chip->ecc.read_oob = r852_read_oob; - /* init our device structure */ dev = kzalloc(sizeof(struct r852_device), GFP_KERNEL); @@ -882,6 +892,10 @@ static int r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) dev->pci_dev = pci_dev; pci_set_drvdata(pci_dev, dev); + nand_controller_init(&dev->controller); + dev->controller.ops = &r852_ops; + chip->controller = &dev->controller; + dev->bounce_buffer = dma_alloc_coherent(&pci_dev->dev, R852_DMA_LEN, &dev->phys_bounce_buffer, GFP_KERNEL); diff --git a/drivers/mtd/nand/raw/r852.h b/drivers/mtd/nand/raw/r852.h index e9ce299c499d..96fe301d15da 100644 --- a/drivers/mtd/nand/raw/r852.h +++ b/drivers/mtd/nand/raw/r852.h @@ -104,6 +104,7 @@ #define DMA_MEMORY 1 struct r852_device { + struct nand_controller controller; void __iomem *mmio; /* mmio */ struct nand_chip *chip; /* nand chip backpointer */ struct pci_dev *pci_dev; /* pci backpointer */ -- cgit v1.2.3 From 1ac6870991939c9351d4c5c49c38b52c97ee7e19 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:23 +0100 Subject: mtd: rawnand: sharpsl: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/sharpsl.c | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c index 1327bfb3d5d3..af98bcc9d689 100644 --- a/drivers/mtd/nand/raw/sharpsl.c +++ b/drivers/mtd/nand/raw/sharpsl.c @@ -20,6 +20,7 @@ #include struct sharpsl_nand { + struct nand_controller controller; struct nand_chip chip; void __iomem *io; @@ -96,6 +97,25 @@ static int sharpsl_nand_calculate_ecc(struct nand_chip *chip, return readb(sharpsl->io + ECCCNTR) != 0; } +static int sharpsl_attach_chip(struct nand_chip *chip) +{ + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + + chip->ecc.size = 256; + chip->ecc.bytes = 3; + chip->ecc.strength = 1; + chip->ecc.hwctl = sharpsl_nand_enable_hwecc; + chip->ecc.calculate = sharpsl_nand_calculate_ecc; + chip->ecc.correct = nand_correct_data; + + return 0; +} + +static const struct nand_controller_ops sharpsl_ops = { + .attach_chip = sharpsl_attach_chip, +}; + /* * Main initialization routine */ @@ -136,6 +156,10 @@ static int sharpsl_nand_probe(struct platform_device *pdev) /* Get pointer to private data */ this = (struct nand_chip *)(&sharpsl->chip); + nand_controller_init(&sharpsl->controller); + sharpsl->controller.ops = &sharpsl_ops; + this->controller = &sharpsl->controller; + /* Link the private data with the MTD structure */ mtd = nand_to_mtd(this); mtd->dev.parent = &pdev->dev; @@ -156,15 +180,7 @@ static int sharpsl_nand_probe(struct platform_device *pdev) this->legacy.dev_ready = sharpsl_nand_dev_ready; /* 15 us command delay time */ this->legacy.chip_delay = 15; - /* set eccmode using hardware ECC */ - this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - this->ecc.size = 256; - this->ecc.bytes = 3; - this->ecc.strength = 1; this->badblock_pattern = data->badblock_pattern; - this->ecc.hwctl = sharpsl_nand_enable_hwecc; - this->ecc.calculate = sharpsl_nand_calculate_ecc; - this->ecc.correct = nand_correct_data; /* Scan to find existence of the device */ err = nand_scan(this, 1); -- cgit v1.2.3 From b36bf0a0fe5d18561dd98eb774ef61dd396edc42 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 13 Nov 2020 13:34:24 +0100 Subject: mtd: rawnand: socrates: Move the ECC initialization to ->attach_chip() The probe function is only supposed to initialize the controller hardware but not the ECC engine. Indeed, we don't know anything about the NAND chip(s) at this stage. Let's move the logic initializing the ECC engine, even pretty simple, to the ->attach_chip() hook which gets called during nand_scan() routine, after the NAND chip discovery. As the previously mentioned logic is supposed to parse the DT for us, it is likely that the chip->ecc.* entries be overwritten. So let's avoid this by moving these lines to ->attach_chip(). Fixes: d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201113123424.32233-20-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/socrates_nand.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/nand/raw/socrates_nand.c b/drivers/mtd/nand/raw/socrates_nand.c index 0f63ff6f7fe7..107208311987 100644 --- a/drivers/mtd/nand/raw/socrates_nand.c +++ b/drivers/mtd/nand/raw/socrates_nand.c @@ -22,6 +22,7 @@ #define FPGA_NAND_DATA_SHIFT 16 struct socrates_nand_host { + struct nand_controller controller; struct nand_chip nand_chip; void __iomem *io_base; struct device *dev; @@ -116,6 +117,18 @@ static int socrates_nand_device_ready(struct nand_chip *nand_chip) return 1; } +static int socrates_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + +static const struct nand_controller_ops socrates_ops = { + .attach_chip = socrates_attach_chip, +}; + /* * Probe for the NAND device. */ @@ -141,6 +154,10 @@ static int socrates_nand_probe(struct platform_device *ofdev) mtd = nand_to_mtd(nand_chip); host->dev = &ofdev->dev; + nand_controller_init(&host->controller); + host->controller.ops = &socrates_ops; + nand_chip->controller = &host->controller; + /* link the private data structures */ nand_set_controller_data(nand_chip, host); nand_set_flash_node(nand_chip, ofdev->dev.of_node); @@ -153,10 +170,6 @@ static int socrates_nand_probe(struct platform_device *ofdev) nand_chip->legacy.read_buf = socrates_nand_read_buf; nand_chip->legacy.dev_ready = socrates_nand_device_ready; - /* enable ECC */ - nand_chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - nand_chip->ecc.algo = NAND_ECC_ALGO_HAMMING; - /* TODO: I have no idea what real delay is. */ nand_chip->legacy.chip_delay = 20; /* 20us command delay time */ -- cgit v1.2.3 From 5f1251a48c17b54939d7477305e39679a565382c Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Tue, 17 Nov 2020 16:03:05 -0800 Subject: video: hyperv_fb: Fix the cache type when mapping the VRAM x86 Hyper-V used to essentially always overwrite the effective cache type of guest memory accesses to WB. This was problematic in cases where there is a physical device assigned to the VM, since that often requires that the VM should have control over cache types. Thus, on newer Hyper-V since 2018, Hyper-V always honors the VM's cache type, but unexpectedly Linux VM users start to complain that Linux VM's VRAM becomes very slow, and it turns out that Linux VM should not map the VRAM uncacheable by ioremap(). Fix this slowness issue by using ioremap_cache(). On ARM64, ioremap_cache() is also required as the host also maps the VRAM cacheable, otherwise VM Connect can't display properly with ioremap() or ioremap_wc(). With this change, the VRAM on new Hyper-V is as fast as regular RAM, so it's no longer necessary to use the hacks we added to mitigate the slowness, i.e. we no longer need to allocate physical memory and use it to back up the VRAM in Generation-1 VM, and we also no longer need to allocate physical memory to back up the framebuffer in a Generation-2 VM and copy the framebuffer to the real VRAM. A further big change will address these for v5.11. Fixes: 68a2d20b79b1 ("drivers/video: add Hyper-V Synthetic Video Frame Buffer Driver") Tested-by: Boqun Feng Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Reviewed-by: Haiyang Zhang Link: https://lore.kernel.org/r/20201118000305.24797-1-decui@microsoft.com Signed-off-by: Wei Liu --- drivers/video/fbdev/hyperv_fb.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index 02411d89cb46..58c74d2356ba 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -1092,7 +1092,12 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) goto err1; } - fb_virt = ioremap(par->mem->start, screen_fb_size); + /* + * Map the VRAM cacheable for performance. This is also required for + * VM Connect to display properly for ARM64 Linux VM, as the host also + * maps the VRAM cacheable. + */ + fb_virt = ioremap_cache(par->mem->start, screen_fb_size); if (!fb_virt) goto err2; -- cgit v1.2.3 From c497f9322af947204c28292be6f20dd2d97483dd Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Thu, 12 Nov 2020 12:51:40 +0200 Subject: interconnect: qcom: msm8916: Remove rpm-ids from non-RPM nodes Some nodes are incorrectly marked as RPM-controlled (they have RPM master and slave ids assigned), but are actually controlled by the application CPU instead. The RPM complains when we send requests for resources that it can't control. Let's fix this by replacing the IDs, with the default "-1" in which case no requests are sent. Reviewed-by: Mike Tipton Link: https://lore.kernel.org/r/20201112105140.10092-1-georgi.djakov@linaro.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/msm8916.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/interconnect/qcom/msm8916.c b/drivers/interconnect/qcom/msm8916.c index 42c6c5581662..e8371d40ab8d 100644 --- a/drivers/interconnect/qcom/msm8916.c +++ b/drivers/interconnect/qcom/msm8916.c @@ -182,7 +182,7 @@ DEFINE_QNODE(mas_pcnoc_sdcc_1, MSM8916_MASTER_SDCC_1, 8, -1, -1, MSM8916_PNOC_IN DEFINE_QNODE(mas_pcnoc_sdcc_2, MSM8916_MASTER_SDCC_2, 8, -1, -1, MSM8916_PNOC_INT_1); DEFINE_QNODE(mas_qdss_bam, MSM8916_MASTER_QDSS_BAM, 8, -1, -1, MSM8916_SNOC_QDSS_INT); DEFINE_QNODE(mas_qdss_etr, MSM8916_MASTER_QDSS_ETR, 8, -1, -1, MSM8916_SNOC_QDSS_INT); -DEFINE_QNODE(mas_snoc_cfg, MSM8916_MASTER_SNOC_CFG, 4, 20, -1, MSM8916_SNOC_QDSS_INT); +DEFINE_QNODE(mas_snoc_cfg, MSM8916_MASTER_SNOC_CFG, 4, -1, -1, MSM8916_SNOC_QDSS_INT); DEFINE_QNODE(mas_spdm, MSM8916_MASTER_SPDM, 4, -1, -1, MSM8916_PNOC_MAS_0); DEFINE_QNODE(mas_tcu0, MSM8916_MASTER_TCU0, 8, -1, -1, MSM8916_SLAVE_EBI_CH0, MSM8916_BIMC_SNOC_MAS, MSM8916_SLAVE_AMPSS_L2); DEFINE_QNODE(mas_tcu1, MSM8916_MASTER_TCU1, 8, -1, -1, MSM8916_SLAVE_EBI_CH0, MSM8916_BIMC_SNOC_MAS, MSM8916_SLAVE_AMPSS_L2); @@ -208,14 +208,14 @@ DEFINE_QNODE(pcnoc_snoc_mas, MSM8916_PNOC_SNOC_MAS, 8, 29, -1, MSM8916_PNOC_SNOC DEFINE_QNODE(pcnoc_snoc_slv, MSM8916_PNOC_SNOC_SLV, 8, -1, 45, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC, MSM8916_SNOC_INT_1); DEFINE_QNODE(qdss_int, MSM8916_SNOC_QDSS_INT, 8, -1, -1, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC); DEFINE_QNODE(slv_apps_l2, MSM8916_SLAVE_AMPSS_L2, 8, -1, -1, 0); -DEFINE_QNODE(slv_apss, MSM8916_SLAVE_APSS, 4, -1, 20, 0); +DEFINE_QNODE(slv_apss, MSM8916_SLAVE_APSS, 4, -1, -1, 0); DEFINE_QNODE(slv_audio, MSM8916_SLAVE_LPASS, 4, -1, -1, 0); DEFINE_QNODE(slv_bimc_cfg, MSM8916_SLAVE_BIMC_CFG, 4, -1, -1, 0); DEFINE_QNODE(slv_blsp_1, MSM8916_SLAVE_BLSP_1, 4, -1, -1, 0); DEFINE_QNODE(slv_boot_rom, MSM8916_SLAVE_BOOT_ROM, 4, -1, -1, 0); DEFINE_QNODE(slv_camera_cfg, MSM8916_SLAVE_CAMERA_CFG, 4, -1, -1, 0); -DEFINE_QNODE(slv_cats_0, MSM8916_SLAVE_CATS_128, 16, -1, 106, 0); -DEFINE_QNODE(slv_cats_1, MSM8916_SLAVE_OCMEM_64, 8, -1, 107, 0); +DEFINE_QNODE(slv_cats_0, MSM8916_SLAVE_CATS_128, 16, -1, -1, 0); +DEFINE_QNODE(slv_cats_1, MSM8916_SLAVE_OCMEM_64, 8, -1, -1, 0); DEFINE_QNODE(slv_clk_ctl, MSM8916_SLAVE_CLK_CTL, 4, -1, -1, 0); DEFINE_QNODE(slv_crypto_0_cfg, MSM8916_SLAVE_CRYPTO_0_CFG, 4, -1, -1, 0); DEFINE_QNODE(slv_dehr_cfg, MSM8916_SLAVE_DEHR_CFG, 4, -1, -1, 0); @@ -239,7 +239,7 @@ DEFINE_QNODE(slv_sdcc_2, MSM8916_SLAVE_SDCC_2, 4, -1, -1, 0); DEFINE_QNODE(slv_security, MSM8916_SLAVE_SECURITY, 4, -1, -1, 0); DEFINE_QNODE(slv_snoc_cfg, MSM8916_SLAVE_SNOC_CFG, 4, -1, -1, 0); DEFINE_QNODE(slv_spdm, MSM8916_SLAVE_SPDM, 4, -1, -1, 0); -DEFINE_QNODE(slv_srvc_snoc, MSM8916_SLAVE_SRVC_SNOC, 8, -1, 29, 0); +DEFINE_QNODE(slv_srvc_snoc, MSM8916_SLAVE_SRVC_SNOC, 8, -1, -1, 0); DEFINE_QNODE(slv_tcsr, MSM8916_SLAVE_TCSR, 4, -1, -1, 0); DEFINE_QNODE(slv_tlmm, MSM8916_SLAVE_TLMM, 4, -1, -1, 0); DEFINE_QNODE(slv_usb_hs, MSM8916_SLAVE_USB_HS, 4, -1, -1, 0); @@ -249,7 +249,7 @@ DEFINE_QNODE(snoc_bimc_0_slv, MSM8916_SNOC_BIMC_0_SLV, 8, -1, 24, MSM8916_SLAVE_ DEFINE_QNODE(snoc_bimc_1_mas, MSM8916_SNOC_BIMC_1_MAS, 16, -1, -1, MSM8916_SNOC_BIMC_1_SLV); DEFINE_QNODE(snoc_bimc_1_slv, MSM8916_SNOC_BIMC_1_SLV, 8, -1, -1, MSM8916_SLAVE_EBI_CH0); DEFINE_QNODE(snoc_int_0, MSM8916_SNOC_INT_0, 8, 99, 130, MSM8916_SLAVE_QDSS_STM, MSM8916_SLAVE_IMEM, MSM8916_SNOC_PNOC_MAS); -DEFINE_QNODE(snoc_int_1, MSM8916_SNOC_INT_1, 8, 100, 131, MSM8916_SLAVE_APSS, MSM8916_SLAVE_CATS_128, MSM8916_SLAVE_OCMEM_64); +DEFINE_QNODE(snoc_int_1, MSM8916_SNOC_INT_1, 8, -1, -1, MSM8916_SLAVE_APSS, MSM8916_SLAVE_CATS_128, MSM8916_SLAVE_OCMEM_64); DEFINE_QNODE(snoc_int_bimc, MSM8916_SNOC_INT_BIMC, 8, 101, 132, MSM8916_SNOC_BIMC_0_MAS); DEFINE_QNODE(snoc_pcnoc_mas, MSM8916_SNOC_PNOC_MAS, 8, -1, -1, MSM8916_SNOC_PNOC_SLV); DEFINE_QNODE(snoc_pcnoc_slv, MSM8916_SNOC_PNOC_SLV, 8, -1, -1, MSM8916_PNOC_INT_0); -- cgit v1.2.3 From 7ab1e9117607485df977bb6e271be5c5ad649a4c Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Wed, 18 Nov 2020 13:10:44 +0200 Subject: interconnect: qcom: qcs404: Remove GPU and display RPM IDs The following errors are noticed during boot on a QCS404 board: [ 2.926647] qcom_icc_rpm_smd_send mas 6 error -6 [ 2.934573] qcom_icc_rpm_smd_send mas 8 error -6 These errors show when we try to configure the GPU and display nodes. Since these particular nodes aren't supported on RPM and are purely local, we should just change their mas_rpm_id to -1 to avoid any requests being sent for these master IDs. Reviewed-by: Mike Tipton Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20201118111044.26056-1-georgi.djakov@linaro.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/qcs404.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/interconnect/qcom/qcs404.c b/drivers/interconnect/qcom/qcs404.c index d4769a5ea182..9820709b43db 100644 --- a/drivers/interconnect/qcom/qcs404.c +++ b/drivers/interconnect/qcom/qcs404.c @@ -157,8 +157,8 @@ struct qcom_icc_desc { } DEFINE_QNODE(mas_apps_proc, QCS404_MASTER_AMPSS_M0, 8, 0, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV); -DEFINE_QNODE(mas_oxili, QCS404_MASTER_GRAPHICS_3D, 8, 6, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV); -DEFINE_QNODE(mas_mdp, QCS404_MASTER_MDP_PORT0, 8, 8, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV); +DEFINE_QNODE(mas_oxili, QCS404_MASTER_GRAPHICS_3D, 8, -1, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV); +DEFINE_QNODE(mas_mdp, QCS404_MASTER_MDP_PORT0, 8, -1, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV); DEFINE_QNODE(mas_snoc_bimc_1, QCS404_SNOC_BIMC_1_MAS, 8, 76, -1, QCS404_SLAVE_EBI_CH0); DEFINE_QNODE(mas_tcu_0, QCS404_MASTER_TCU_0, 8, -1, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV); DEFINE_QNODE(mas_spdm, QCS404_MASTER_SPDM, 4, -1, -1, QCS404_PNOC_INT_3); -- cgit v1.2.3 From 92666d45adcfd4a4a70580ff9f732309e16131f9 Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Thu, 19 Nov 2020 17:04:21 +0800 Subject: ALSA: hda/realtek - Fixed Dell AIO wrong sound tone This platform only had one audio jack. If it plugged speaker then replug with speaker or headset, the sound tone will change to abnormal. Headset Mic also can't record when this issue was happen. [ Added a short comment about the COEF by tiwai ] Signed-off-by: Kailang Yang Cc: Link: https://lore.kernel.org/r/593c777dcfef4546aa050e105b8e53b5@realtek.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 739dbaf54517..b90cd4c65b58 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -119,6 +119,7 @@ struct alc_spec { unsigned int no_shutup_pins:1; unsigned int ultra_low_power:1; unsigned int has_hs_key:1; + unsigned int no_internal_mic_pin:1; /* for PLL fix */ hda_nid_t pll_nid; @@ -4523,6 +4524,7 @@ static const struct coef_fw alc225_pre_hsmode[] = { static void alc_headset_mode_unplugged(struct hda_codec *codec) { + struct alc_spec *spec = codec->spec; static const struct coef_fw coef0255[] = { WRITE_COEF(0x1b, 0x0c0b), /* LDO and MISC control */ WRITE_COEF(0x45, 0xd089), /* UAJ function set to menual mode */ @@ -4597,6 +4599,11 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec) {} }; + if (spec->no_internal_mic_pin) { + alc_update_coef_idx(codec, 0x45, 0xf<<12 | 1<<10, 5<<12); + return; + } + switch (codec->core.vendor_id) { case 0x10ec0255: alc_process_coef_fw(codec, coef0255); @@ -5163,6 +5170,11 @@ static void alc_determine_headset_type(struct hda_codec *codec) {} }; + if (spec->no_internal_mic_pin) { + alc_update_coef_idx(codec, 0x45, 0xf<<12 | 1<<10, 5<<12); + return; + } + switch (codec->core.vendor_id) { case 0x10ec0255: alc_process_coef_fw(codec, coef0255); @@ -6121,6 +6133,23 @@ static void alc274_fixup_hp_headset_mic(struct hda_codec *codec, } } +static void alc_fixup_no_int_mic(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + /* Mic RING SLEEVE swap for combo jack */ + alc_update_coef_idx(codec, 0x45, 0xf<<12 | 1<<10, 5<<12); + spec->no_internal_mic_pin = true; + break; + case HDA_FIXUP_ACT_INIT: + alc_combo_jack_hp_jd_restart(codec); + break; + } +} + /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" @@ -6320,6 +6349,7 @@ enum { ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, ALC287_FIXUP_HP_GPIO_LED, ALC256_FIXUP_HP_HEADSET_MIC, + ALC236_FIXUP_DELL_AIO_HEADSET_MIC, }; static const struct hda_fixup alc269_fixups[] = { @@ -7738,6 +7768,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc274_fixup_hp_headset_mic, }, + [ALC236_FIXUP_DELL_AIO_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_no_int_mic, + .chained = true, + .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7815,6 +7851,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x097d, "Dell Precision", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x098d, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x09bf, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x0a2e, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC), + SND_PCI_QUIRK(0x1028, 0x0a30, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -8353,6 +8391,8 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x19, 0x02a11020}, {0x1a, 0x02a11030}, {0x21, 0x0221101f}), + SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC, + {0x21, 0x02211010}), SND_HDA_PIN_QUIRK(0x10ec0236, 0x103c, "HP", ALC256_FIXUP_HP_HEADSET_MIC, {0x14, 0x90170110}, {0x19, 0x02a11020}, -- cgit v1.2.3 From 017496af28e2589c2c2cb396baba0507179d2748 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Thu, 19 Nov 2020 11:37:46 +0100 Subject: interconnect: fix memory trashing in of_count_icc_providers() of_count_icc_providers() function uses for_each_available_child_of_node() helper to recursively check all the available nodes. This helper already properly handles child nodes' reference count, so there is no need to do it explicitly. Remove the excessive call to of_node_put(). This fixes memory trashing when CONFIG_OF_DYNAMIC is enabled (for example arm/multi_v7_defconfig). Fixes: b1d681d8d324 ("interconnect: Add sync state support") Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20201119103746.32564-1-m.szyprowski@samsung.com Signed-off-by: Georgi Djakov --- drivers/interconnect/core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 974a66725d09..5ad519c9f239 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -1083,7 +1083,6 @@ static int of_count_icc_providers(struct device_node *np) count++; count += of_count_icc_providers(child); } - of_node_put(np); return count; } -- cgit v1.2.3 From 6200d5c3831370cd0ab4b6455933d12e82ea9956 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Fri, 20 Nov 2020 09:53:09 +0100 Subject: MAINTAINERS: Update XDP and AF_XDP entries MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Getting too many false positive matches with current use of the content regex K: and file regex N: patterns. This patch drops file match N: and makes K: more restricted. Some more normal F: file wildcards are added. Notice that AF_XDP forgot to some F: files that is also updated in this patch. Suggested-by: Jakub Kicinski Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/160586238944.2808432.4401269290440394008.stgit@firesoul --- MAINTAINERS | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index c7f6924d34c7..15355c055a1a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19109,12 +19109,17 @@ L: netdev@vger.kernel.org L: bpf@vger.kernel.org S: Supported F: include/net/xdp.h +F: include/net/xdp_priv.h F: include/trace/events/xdp.h F: kernel/bpf/cpumap.c F: kernel/bpf/devmap.c F: net/core/xdp.c -N: xdp -K: xdp +F: samples/bpf/xdp* +F: tools/testing/selftests/bpf/*xdp* +F: tools/testing/selftests/bpf/*/*xdp* +F: drivers/net/ethernet/*/*/*/*/*xdp* +F: drivers/net/ethernet/*/*/*xdp* +K: (?:\b|_)xdp(?:\b|_) XDP SOCKETS (AF_XDP) M: Björn Töpel @@ -19123,9 +19128,12 @@ R: Jonathan Lemon L: netdev@vger.kernel.org L: bpf@vger.kernel.org S: Maintained +F: Documentation/networking/af_xdp.rst F: include/net/xdp_sock* F: include/net/xsk_buff_pool.h F: include/uapi/linux/if_xdp.h +F: include/uapi/linux/xdp_diag.h +F: include/net/netns/xdp.h F: net/xdp/ F: samples/bpf/xdpsock* F: tools/lib/bpf/xsk* -- cgit v1.2.3 From 537cf4e3cc2f6cc9088dcd6162de573f603adc29 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 20 Nov 2020 12:53:39 +0100 Subject: xsk: Fix umem cleanup bug at socket destruct Fix a bug that is triggered when a partially setup socket is destroyed. For a fully setup socket, a socket that has been bound to a device, the cleanup of the umem is performed at the end of the buffer pool's cleanup work queue item. This has to be performed in a work queue, and not in RCU cleanup, as it is doing a vunmap that cannot execute in interrupt context. However, when a socket has only been partially set up so that a umem has been created but the buffer pool has not, the code erroneously directly calls the umem cleanup function instead of using a work queue, and this leads to a BUG_ON() in vunmap(). As there in this case is no buffer pool, we cannot use its work queue, so we need to introduce a work queue for the umem and schedule this for the cleanup. So in the case there is no pool, we are going to use the umem's own work queue to schedule the cleanup. But if there is a pool, the cleanup of the umem is still being performed by the pool's work queue, as it is important that the umem is cleaned up after the pool. Fixes: e5e1a4bc916d ("xsk: Fix possible memory leak at socket close") Reported-by: Marek Majtyka Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Tested-by: Marek Majtyka Link: https://lore.kernel.org/bpf/1605873219-21629-1-git-send-email-magnus.karlsson@gmail.com --- include/net/xdp_sock.h | 1 + net/xdp/xdp_umem.c | 19 ++++++++++++++++--- net/xdp/xdp_umem.h | 2 +- net/xdp/xsk.c | 2 +- net/xdp/xsk_buff_pool.c | 2 +- 5 files changed, 20 insertions(+), 6 deletions(-) diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 1a9559c0cbdd..4f4e93bf814c 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -31,6 +31,7 @@ struct xdp_umem { struct page **pgs; int id; struct list_head xsk_dma_list; + struct work_struct work; }; struct xsk_map { diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 56d052bc65cb..56a28a686988 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -66,18 +66,31 @@ static void xdp_umem_release(struct xdp_umem *umem) kfree(umem); } +static void xdp_umem_release_deferred(struct work_struct *work) +{ + struct xdp_umem *umem = container_of(work, struct xdp_umem, work); + + xdp_umem_release(umem); +} + void xdp_get_umem(struct xdp_umem *umem) { refcount_inc(&umem->users); } -void xdp_put_umem(struct xdp_umem *umem) +void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup) { if (!umem) return; - if (refcount_dec_and_test(&umem->users)) - xdp_umem_release(umem); + if (refcount_dec_and_test(&umem->users)) { + if (defer_cleanup) { + INIT_WORK(&umem->work, xdp_umem_release_deferred); + schedule_work(&umem->work); + } else { + xdp_umem_release(umem); + } + } } static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h index 181fdda2f2a8..aa9fe2780410 100644 --- a/net/xdp/xdp_umem.h +++ b/net/xdp/xdp_umem.h @@ -9,7 +9,7 @@ #include void xdp_get_umem(struct xdp_umem *umem); -void xdp_put_umem(struct xdp_umem *umem); +void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup); struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr); #endif /* XDP_UMEM_H_ */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index cfbec3989a76..5a6cdf7b320d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -1147,7 +1147,7 @@ static void xsk_destruct(struct sock *sk) return; if (!xp_put_pool(xs->pool)) - xdp_put_umem(xs->umem); + xdp_put_umem(xs->umem, !xs->pool); sk_refcnt_debug_dec(sk); } diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 8a3bf4e1318e..3c5a1423d922 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -242,7 +242,7 @@ static void xp_release_deferred(struct work_struct *work) pool->cq = NULL; } - xdp_put_umem(pool->umem); + xdp_put_umem(pool->umem, false); xp_destroy(pool); } -- cgit v1.2.3 From 9ca57518361418ad5ae7dc38a2128fbf4855e1a2 Mon Sep 17 00:00:00 2001 From: penghao Date: Wed, 18 Nov 2020 20:30:39 +0800 Subject: USB: quirks: Add USB_QUIRK_DISCONNECT_SUSPEND quirk for Lenovo A630Z TIO built-in usb-audio card Add a USB_QUIRK_DISCONNECT_SUSPEND quirk for the Lenovo TIO built-in usb-audio. when A630Z going into S3,the system immediately wakeup 7-8 seconds later by usb-audio disconnect interrupt to avoids the issue. eg dmesg: .... [ 626.974091 ] usb 7-1.1: USB disconnect, device number 3 .... .... [ 1774.486691] usb 7-1.1: new full-speed USB device number 5 using xhci_hcd [ 1774.947742] usb 7-1.1: New USB device found, idVendor=17ef, idProduct=a012, bcdDevice= 0.55 [ 1774.956588] usb 7-1.1: New USB device strings: Mfr=1, Product=2, SerialNumber=3 [ 1774.964339] usb 7-1.1: Product: Thinkcentre TIO24Gen3 for USB-audio [ 1774.970999] usb 7-1.1: Manufacturer: Lenovo [ 1774.975447] usb 7-1.1: SerialNumber: 000000000000 [ 1775.048590] usb 7-1.1: 2:1: cannot get freq at ep 0x1 ....... Seeking a better fix, we've tried a lot of things, including: - Check that the device's power/wakeup is disabled - Check that remote wakeup is off at the USB level - All the quirks in drivers/usb/core/quirks.c e.g. USB_QUIRK_RESET_RESUME, USB_QUIRK_RESET, USB_QUIRK_IGNORE_REMOTE_WAKEUP, USB_QUIRK_NO_LPM. but none of that makes any difference. There are no errors in the logs showing any suspend/resume-related issues. When the system wakes up due to the modem, log-wise it appears to be a normal resume. Introduce a quirk to disable the port during suspend when the modem is detected. Signed-off-by: penghao Link: https://lore.kernel.org/r/20201118123039.11696-1-penghao@uniontech.com Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/quirks.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index a1e3a037a289..f536ea9fe945 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -421,6 +421,10 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x1532, 0x0116), .driver_info = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL }, + /* Lenovo ThinkCenter A630Z TI024Gen3 usb-audio */ + { USB_DEVICE(0x17ef, 0xa012), .driver_info = + USB_QUIRK_DISCONNECT_SUSPEND }, + /* BUILDWIN Photo Frame */ { USB_DEVICE(0x1908, 0x1315), .driver_info = USB_QUIRK_HONOR_BNUMINTERFACES }, -- cgit v1.2.3 From e7694cb6998379341fd9bf3bd62b48c4e6a79385 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Tue, 17 Nov 2020 10:16:28 +0800 Subject: usb: gadget: f_midi: Fix memleak in f_midi_alloc In the error path, if midi is not null, we should free the midi->id if necessary to prevent memleak. Fixes: b85e9de9e818d ("usb: gadget: f_midi: convert to new function interface with backward compatibility") Reported-by: Hulk Robot Signed-off-by: Zhang Qilong Link: https://lore.kernel.org/r/20201117021629.1470544-2-zhangqilong3@huawei.com Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_midi.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c index 85cb15734aa8..19d97940eeb9 100644 --- a/drivers/usb/gadget/function/f_midi.c +++ b/drivers/usb/gadget/function/f_midi.c @@ -1315,7 +1315,7 @@ static struct usb_function *f_midi_alloc(struct usb_function_instance *fi) midi->id = kstrdup(opts->id, GFP_KERNEL); if (opts->id && !midi->id) { status = -ENOMEM; - goto setup_fail; + goto midi_free; } midi->in_ports = opts->in_ports; midi->out_ports = opts->out_ports; @@ -1327,7 +1327,7 @@ static struct usb_function *f_midi_alloc(struct usb_function_instance *fi) status = kfifo_alloc(&midi->in_req_fifo, midi->qlen, GFP_KERNEL); if (status) - goto setup_fail; + goto midi_free; spin_lock_init(&midi->transmit_lock); @@ -1343,9 +1343,13 @@ static struct usb_function *f_midi_alloc(struct usb_function_instance *fi) return &midi->func; +midi_free: + if (midi) + kfree(midi->id); + kfree(midi); setup_fail: mutex_unlock(&opts->lock); - kfree(midi); + return ERR_PTR(status); } -- cgit v1.2.3 From 87bed3d7d26c974948a3d6e7176f304b2d41272b Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Tue, 17 Nov 2020 10:16:29 +0800 Subject: usb: gadget: Fix memleak in gadgetfs_fill_super usb_get_gadget_udc_name will alloc memory for CHIP in "Enomem" branch. we should free it before error returns to prevent memleak. Fixes: 175f712119c57 ("usb: gadget: provide interface for legacy gadgets to get UDC name") Reported-by: Hulk Robot Acked-by: Alan Stern Signed-off-by: Zhang Qilong Link: https://lore.kernel.org/r/20201117021629.1470544-3-zhangqilong3@huawei.com Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/legacy/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 1b430b36d0a6..71e7d10dd76b 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -2039,6 +2039,9 @@ gadgetfs_fill_super (struct super_block *sb, struct fs_context *fc) return 0; Enomem: + kfree(CHIP); + CHIP = NULL; + return -ENOMEM; } -- cgit v1.2.3 From 184eead057cc7e803558269babc1f2cfb9113ad1 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Thu, 19 Nov 2020 12:00:40 -0500 Subject: USB: core: Fix regression in Hercules audio card Commit 3e4f8e21c4f2 ("USB: core: fix check for duplicate endpoints") aimed to make the USB stack more reliable by detecting and skipping over endpoints that are duplicated between interfaces. This caused a regression for a Hercules audio card (reported as Bugzilla #208357), which contains such non-compliant duplications. Although the duplications are harmless, skipping the valid endpoints prevented the device from working. This patch fixes the regression by adding ENDPOINT_IGNORE quirks for the Hercules card, telling the kernel to ignore the invalid duplicate endpoints and thereby allowing the valid endpoints to be used as intended. Fixes: 3e4f8e21c4f2 ("USB: core: fix check for duplicate endpoints") CC: Reported-by: Alexander Chalikiopoulos Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/20201119170040.GA576844@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/quirks.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index f536ea9fe945..fad31ccd1fa8 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -348,6 +348,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* Guillemot Webcam Hercules Dualpix Exchange*/ { USB_DEVICE(0x06f8, 0x3005), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Guillemot Hercules DJ Console audio card (BZ 208357) */ + { USB_DEVICE(0x06f8, 0xb000), .driver_info = + USB_QUIRK_ENDPOINT_IGNORE }, + /* Midiman M-Audio Keystation 88es */ { USB_DEVICE(0x0763, 0x0192), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -525,6 +529,8 @@ static const struct usb_device_id usb_amd_resume_quirk_list[] = { * Matched for devices with USB_QUIRK_ENDPOINT_IGNORE. */ static const struct usb_device_id usb_endpoint_ignore[] = { + { USB_DEVICE_INTERFACE_NUMBER(0x06f8, 0xb000, 5), .driver_info = 0x01 }, + { USB_DEVICE_INTERFACE_NUMBER(0x06f8, 0xb000, 5), .driver_info = 0x81 }, { USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0202, 1), .driver_info = 0x85 }, { USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0208, 1), .driver_info = 0x85 }, { } -- cgit v1.2.3 From c2b1209d852fef65dbe13c1eed2c6d7a8cd0d1f8 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 19 Nov 2020 10:37:07 -0800 Subject: MAINTAINERS: Update email address for Sean Christopherson Update my email address to one provided by my new benefactor. Cc: Thomas Gleixner Cc: Borislav Petkov Cc: Jarkko Sakkinen Cc: Dave Hansen Cc: Andy Lutomirski Cc: Vitaly Kuznetsov Cc: Wanpeng Li Cc: Jim Mattson Cc: Joerg Roedel Cc: kvm@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20201119183707.291864-1-sean.kvm@gmail.com> Signed-off-by: Paolo Bonzini --- .mailmap | 1 + 1 file changed, 1 insertion(+) diff --git a/.mailmap b/.mailmap index 1e14566a3d56..a0d1685a165a 100644 --- a/.mailmap +++ b/.mailmap @@ -287,6 +287,7 @@ Santosh Shilimkar Sarangdhar Joshi Sascha Hauer S.Çağlar Onur +Sean Christopherson Sean Nyekjaer Sebastian Reichel Sebastian Reichel -- cgit v1.2.3 From f3bc432aa8a7a2bfe9ebb432502be5c5d979d7fe Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Thu, 19 Nov 2020 12:02:28 -0500 Subject: USB: core: Change %pK for __user pointers to %px Commit 2f964780c03b ("USB: core: replace %p with %pK") used the %pK format specifier for a bunch of __user pointers. But as the 'K' in the specifier indicates, it is meant for kernel pointers. The reason for the %pK specifier is to avoid leaks of kernel addresses, but when the pointer is to an address in userspace the security implications are minimal. In particular, no kernel information is leaked. This patch changes the __user %pK specifiers (used in a bunch of debugging output lines) to %px, which will always print the actual address with no mangling. (Notably, there is no printk format specifier particularly intended for __user pointers.) Fixes: 2f964780c03b ("USB: core: replace %p with %pK") CC: Vamsi Krishna Samavedam CC: Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/20201119170228.GB576844@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/devio.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index e96a858a1218..533236366a03 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -482,11 +482,11 @@ static void snoop_urb(struct usb_device *udev, if (userurb) { /* Async */ if (when == SUBMIT) - dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, " + dev_info(&udev->dev, "userurb %px, ep%d %s-%s, " "length %u\n", userurb, ep, t, d, length); else - dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, " + dev_info(&udev->dev, "userurb %px, ep%d %s-%s, " "actual_length %u status %d\n", userurb, ep, t, d, length, timeout_or_status); @@ -1997,7 +1997,7 @@ static int proc_reapurb(struct usb_dev_state *ps, void __user *arg) if (as) { int retval; - snoop(&ps->dev->dev, "reap %pK\n", as->userurb); + snoop(&ps->dev->dev, "reap %px\n", as->userurb); retval = processcompl(as, (void __user * __user *)arg); free_async(as); return retval; @@ -2014,7 +2014,7 @@ static int proc_reapurbnonblock(struct usb_dev_state *ps, void __user *arg) as = async_getcompleted(ps); if (as) { - snoop(&ps->dev->dev, "reap %pK\n", as->userurb); + snoop(&ps->dev->dev, "reap %px\n", as->userurb); retval = processcompl(as, (void __user * __user *)arg); free_async(as); } else { @@ -2142,7 +2142,7 @@ static int proc_reapurb_compat(struct usb_dev_state *ps, void __user *arg) if (as) { int retval; - snoop(&ps->dev->dev, "reap %pK\n", as->userurb); + snoop(&ps->dev->dev, "reap %px\n", as->userurb); retval = processcompl_compat(as, (void __user * __user *)arg); free_async(as); return retval; @@ -2159,7 +2159,7 @@ static int proc_reapurbnonblock_compat(struct usb_dev_state *ps, void __user *ar as = async_getcompleted(ps); if (as) { - snoop(&ps->dev->dev, "reap %pK\n", as->userurb); + snoop(&ps->dev->dev, "reap %px\n", as->userurb); retval = processcompl_compat(as, (void __user * __user *)arg); free_async(as); } else { @@ -2624,7 +2624,7 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd, #endif case USBDEVFS_DISCARDURB: - snoop(&dev->dev, "%s: DISCARDURB %pK\n", __func__, p); + snoop(&dev->dev, "%s: DISCARDURB %px\n", __func__, p); ret = proc_unlinkurb(ps, p); break; -- cgit v1.2.3 From a98fd117a2553ab1a6d2fe3c7acae88c1eca4372 Mon Sep 17 00:00:00 2001 From: Icenowy Zheng Date: Fri, 20 Nov 2020 13:08:51 +0800 Subject: ARM: dts: sun8i: v3s: fix GIC node memory range Currently the GIC node in V3s DTSI follows some old DT examples, and being broken. This leads a warning at boot. Fix this. Fixes: f989086ccbc6 ("ARM: dts: sunxi: add dtsi file for V3s SoC") Signed-off-by: Icenowy Zheng Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20201120050851.4123759-1-icenowy@aosc.io --- arch/arm/boot/dts/sun8i-v3s.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sun8i-v3s.dtsi b/arch/arm/boot/dts/sun8i-v3s.dtsi index 0c7341676921..89abd4cc7e23 100644 --- a/arch/arm/boot/dts/sun8i-v3s.dtsi +++ b/arch/arm/boot/dts/sun8i-v3s.dtsi @@ -539,7 +539,7 @@ gic: interrupt-controller@1c81000 { compatible = "arm,gic-400"; reg = <0x01c81000 0x1000>, - <0x01c82000 0x1000>, + <0x01c82000 0x2000>, <0x01c84000 0x2000>, <0x01c86000 0x2000>; interrupt-controller; -- cgit v1.2.3 From 4fae3a58ab59d8a286864d61fe1846283a0316f2 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Tue, 17 Nov 2020 12:45:17 +0300 Subject: spi: Take the SPI IO-mutex in the spi_setup() method I've discovered that due to the recent commit 49d7d695ca4b ("spi: dw: Explicitly de-assert CS on SPI transfer completion") a concurrent usage of the spidev devices with different chip-selects causes the "SPI transfer timed out" error. The root cause of the problem has turned to be in a race condition of the SPI-transfer execution procedure and the spi_setup() method being called at the same time. In particular in calling the spi_set_cs(false) while there is an SPI-transfer being executed. In my case due to the commit cited above all CSs get to be switched off by calling the spi_setup() for /dev/spidev0.1 while there is an concurrent SPI-transfer execution performed on /dev/spidev0.0. Of course a situation of the spi_setup() being called while there is an SPI-transfer being executed for two different SPI peripheral devices of the same controller may happen not only for the spidev driver, but for instance for MMC SPI + some another device, or spi_setup() being called from an SPI-peripheral probe method while some other device has already been probed and is being used by a corresponding driver... Of course I could have provided a fix affecting the DW APB SSI driver only, for instance, by creating a mutual exclusive access to the set_cs callback and setting/clearing only the bit responsible for the corresponding chip-select. But after a short research I've discovered that the problem most likely affects a lot of the other drivers: - drivers/spi/spi-sun4i.c - RMW the chip-select register; - drivers/spi/spi-rockchip.c - RMW the chip-select register; - drivers/spi/spi-qup.c - RMW a generic force-CS flag in a CSR. - drivers/spi/spi-sifive.c - set a generic CS-mode flag in a CSR. - drivers/spi/spi-bcm63xx-hsspi.c - uses an internal mutex to serialize the bus config changes, but still isn't protected from the race condition described above; - drivers/spi/spi-geni-qcom.c - RMW a chip-select internal flag and set the CS state in HW; - drivers/spi/spi-orion.c - RMW a chip-select register; - drivers/spi/spi-cadence.c - RMW a chip-select register; - drivers/spi/spi-armada-3700.c - RMW a chip-select register; - drivers/spi/spi-lantiq-ssc.c - overwrites the chip-select register; - drivers/spi/spi-sun6i.c - RMW a chip-select register; - drivers/spi/spi-synquacer.c - RMW a chip-select register; - drivers/spi/spi-altera.c - directly sets the chip-select state; - drivers/spi/spi-omap2-mcspi.c - RMW an internally cached CS state and writes it to HW; - drivers/spi/spi-mt65xx.c - RMW some CSR; - drivers/spi/spi-jcore.c - directly sets the chip-selects state; - drivers/spi/spi-mt7621.c - RMW a chip-select register; I could have missed some drivers, but a scale of the problem is obvious. As you can see most of the drivers perform an unprotected Read-modify-write chip-select register modification in the set_cs callback. Seeing the spi_setup() function is calling the spi_set_cs() and it can be executed concurrently with SPI-transfers exec procedure, which also calls spi_set_cs() in the SPI core spi_transfer_one_message() method, the race condition of the register modification turns to be obvious. To sum up the problem denoted above affects each driver for a controller having more than one chip-select lane and which: 1) performs the RMW to some CS-related register with no serialization; 2) directly disables any CS on spi_set_cs(dev, false). * the later is the case of the DW APB SSI driver. The controllers which equipped with a single CS theoretically can also experience the problem, but in practice will not since normally the spi_setup() isn't called concurrently with the SPI-transfers executed on the same SPI peripheral device. In order to generically fix the denoted bug I'd suggest to serialize an access to the controller IO by taking the IO mutex in the spi_setup() callback. The mutex is held while there is an SPI communication going on on the SPI-bus of the corresponding SPI-controller. So calling the spi_setup() method and disabling/updating the CS state within it would be safe while there is no any SPI-transfers being executed. Also note I suppose it would be safer to protect the spi_controller->setup() callback invocation too, seeing some of the SPI-controller drivers update a HW state in there. Fixes: 49d7d695ca4b ("spi: dw: Explicitly de-assert CS on SPI transfer completion") Signed-off-by: Serge Semin Link: https://lore.kernel.org/r/20201117094517.5654-1-Sergey.Semin@baikalelectronics.ru Signed-off-by: Mark Brown --- drivers/spi/spi.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 05c75f890ace..fc9a59788d2e 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -3372,12 +3372,15 @@ int spi_setup(struct spi_device *spi) if (!spi->max_speed_hz) spi->max_speed_hz = spi->controller->max_speed_hz; + mutex_lock(&spi->controller->io_mutex); + if (spi->controller->setup) status = spi->controller->setup(spi); if (spi->controller->auto_runtime_pm && spi->controller->set_cs) { status = pm_runtime_get_sync(spi->controller->dev.parent); if (status < 0) { + mutex_unlock(&spi->controller->io_mutex); pm_runtime_put_noidle(spi->controller->dev.parent); dev_err(&spi->controller->dev, "Failed to power device: %d\n", status); @@ -3399,6 +3402,8 @@ int spi_setup(struct spi_device *spi) spi_set_cs(spi, false); } + mutex_unlock(&spi->controller->io_mutex); + if (spi->rt && !spi->controller->rt) { spi->controller->rt = true; spi_set_thread_rt(spi->controller); -- cgit v1.2.3 From f46e79aa1a2bea7de2885fa8d79a68d11545a5fd Mon Sep 17 00:00:00 2001 From: Martin Habets Date: Fri, 20 Nov 2020 11:32:07 +0000 Subject: MAINTAINERS: Change Solarflare maintainers Email from solarflare.com will stop working. Update the maintainers. A replacement for linux-net-drivers@solarflare.com is not working yet, for now remove it. Signed-off-by: Martin Habets Signed-off-by: Edward Cree Link: https://lore.kernel.org/r/20201120113207.GA1605547@mh-desktop Signed-off-by: Jakub Kicinski --- MAINTAINERS | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index c7f6924d34c7..aaf3b023e044 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15775,9 +15775,8 @@ F: drivers/slimbus/ F: include/linux/slimbus.h SFC NETWORK DRIVER -M: Solarflare linux maintainers -M: Edward Cree -M: Martin Habets +M: Edward Cree +M: Martin Habets L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/sfc/ -- cgit v1.2.3 From 3b3fd068c56e3fbea30090859216a368398e39bf Mon Sep 17 00:00:00 2001 From: Anmol Karn Date: Fri, 20 Nov 2020 00:40:43 +0530 Subject: rose: Fix Null pointer dereference in rose_send_frame() rose_send_frame() dereferences `neigh->dev` when called from rose_transmit_clear_request(), and the first occurrence of the `neigh` is in rose_loopback_timer() as `rose_loopback_neigh`, and it is initialized in rose_add_loopback_neigh() as NULL. i.e when `rose_loopback_neigh` used in rose_loopback_timer() its `->dev` was still NULL and rose_loopback_timer() was calling rose_rx_call_request() without checking for NULL. - net/rose/rose_link.c This bug seems to get triggered in this line: rose_call = (ax25_address *)neigh->dev->dev_addr; Fix it by adding NULL checking for `rose_loopback_neigh->dev` in rose_loopback_timer(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Suggested-by: Jakub Kicinski Reported-by: syzbot+a1c743815982d9496393@syzkaller.appspotmail.com Tested-by: syzbot+a1c743815982d9496393@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=9d2a7ca8c7f2e4b682c97578dfa3f236258300b3 Signed-off-by: Anmol Karn Link: https://lore.kernel.org/r/20201119191043.28813-1-anmol.karan123@gmail.com Signed-off-by: Jakub Kicinski --- net/rose/rose_loopback.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 7b094275ea8b..11c45c8c6c16 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -96,10 +96,19 @@ static void rose_loopback_timer(struct timer_list *unused) } if (frametype == ROSE_CALL_REQUEST) { - if ((dev = rose_dev_get(dest)) != NULL) { - if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0) - kfree_skb(skb); - } else { + if (!rose_loopback_neigh->dev) { + kfree_skb(skb); + continue; + } + + dev = rose_dev_get(dest); + if (!dev) { + kfree_skb(skb); + continue; + } + + if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0) { + dev_put(dev); kfree_skb(skb); } } else { -- cgit v1.2.3 From c54bc3ced5106663c2f2b44071800621f505b00e Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 20 Nov 2020 02:44:31 -0500 Subject: bnxt_en: Release PCI regions when DMA mask setup fails during probe. Jump to init_err_release to cleanup. bnxt_unmap_bars() will also be called but it will do nothing if the BARs are not mapped yet. Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.") Reported-by: Jakub Kicinski Signed-off-by: Michael Chan Link: https://lore.kernel.org/r/1605858271-8209-1-git-send-email-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6e8329534cde..0af0af2b70fe 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11591,7 +11591,7 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev) dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)) != 0) { dev_err(&pdev->dev, "System does not support DMA, aborting\n"); rc = -EIO; - goto init_err_disable; + goto init_err_release; } pci_set_master(pdev); -- cgit v1.2.3 From 20ffc7adf53a5fd3d19751fbff7895bcca66686e Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Thu, 19 Nov 2020 18:59:48 +0300 Subject: net/tls: missing received data after fast remote close In case when tcp socket received FIN after some data and the parser haven't started before reading data caller will receive an empty buffer. This behavior differs from plain TCP socket and leads to special treating in user-space. The flow that triggers the race is simple. Server sends small amount of data right after the connection is configured to use TLS and closes the connection. In this case receiver sees TLS Handshake data, configures TLS socket right after Change Cipher Spec record. While the configuration is in process, TCP socket receives small Application Data record, Encrypted Alert record and FIN packet. So the TCP socket changes sk_shutdown to RCV_SHUTDOWN and sk_flag with SK_DONE bit set. The received data is not parsed upon arrival and is never sent to user-space. Patch unpauses parser directly if we have unparsed data in tcp receive queue. Fixes: fcf4793e278e ("tls: check RCV_SHUTDOWN in tls_wait_data") Signed-off-by: Vadim Fedorenko Link: https://lore.kernel.org/r/1605801588-12236-1-git-send-email-vfedorenko@novek.ru Signed-off-by: Jakub Kicinski --- net/tls/tls_sw.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 2fe9e2cf8659..845c628ac1b2 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1295,6 +1295,12 @@ static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock, return NULL; } + if (!skb_queue_empty(&sk->sk_receive_queue)) { + __strp_unpause(&ctx->strp); + if (ctx->recv_pkt) + return ctx->recv_pkt; + } + if (sk->sk_shutdown & RCV_SHUTDOWN) return NULL; -- cgit v1.2.3 From 47a846536e1bf62626f1c0d8488f3718ce5f8296 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 11 Nov 2020 13:48:55 -0800 Subject: block/keyslot-manager: prevent crash when num_slots=1 If there is only one keyslot, then blk_ksm_init() computes slot_hashtable_size=1 and log_slot_ht_size=0. This causes blk_ksm_find_keyslot() to crash later because it uses hash_ptr(key, log_slot_ht_size) to find the hash bucket containing the key, and hash_ptr() doesn't support the bits == 0 case. Fix this by making the hash table always have at least 2 buckets. Tested by running: kvm-xfstests -c ext4 -g encrypt -m inlinecrypt \ -o blk-crypto-fallback.num_keyslots=1 Fixes: 1b2628397058 ("block: Keyslot Manager for Inline Encryption") Signed-off-by: Eric Biggers Signed-off-by: Jens Axboe --- block/keyslot-manager.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c index 35abcb1ec051..86f8195d8039 100644 --- a/block/keyslot-manager.c +++ b/block/keyslot-manager.c @@ -103,6 +103,13 @@ int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots) spin_lock_init(&ksm->idle_slots_lock); slot_hashtable_size = roundup_pow_of_two(num_slots); + /* + * hash_ptr() assumes bits != 0, so ensure the hash table has at least 2 + * buckets. This only makes a difference when there is only 1 keyslot. + */ + if (slot_hashtable_size < 2) + slot_hashtable_size = 2; + ksm->log_slot_ht_size = ilog2(slot_hashtable_size); ksm->slot_hashtable = kvmalloc_array(slot_hashtable_size, sizeof(ksm->slot_hashtable[0]), -- cgit v1.2.3 From f5098e34dd4c774c3040e417960f1637e5daade8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 17 Nov 2020 11:33:02 -0800 Subject: selftests/seccomp: powerpc: Fix typo in macro variable name A typo sneaked into the powerpc selftest. Fix the name so it builds again. Fixes: 46138329faea ("selftests/seccomp: powerpc: Fix seccomp return value testing") Acked-by: Michael Ellerman Link: https://lore.kernel.org/lkml/87y2ix2895.fsf@mpe.ellerman.id.au Signed-off-by: Kees Cook --- tools/testing/selftests/seccomp/seccomp_bpf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 4a180439ee9e..7f7ecfcd66db 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1758,10 +1758,10 @@ TEST_F(TRACE_poke, getpid_runs_normally) * and the code is stored as a positive value. \ */ \ if (_result < 0) { \ - SYSCALL_RET(_regs) = -result; \ + SYSCALL_RET(_regs) = -_result; \ (_regs).ccr |= 0x10000000; \ } else { \ - SYSCALL_RET(_regs) = result; \ + SYSCALL_RET(_regs) = _result; \ (_regs).ccr &= ~0x10000000; \ } \ } while (0) -- cgit v1.2.3 From 4c222f31fb1db4d590503a181a6268ced9252379 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 17 Nov 2020 11:54:43 -0800 Subject: selftests/seccomp: sh: Fix register names It looks like the seccomp selftests was never actually built for sh. This fixes it, though I don't have an environment to do a runtime test of it yet. Fixes: 0bb605c2c7f2b4b3 ("sh: Add SECCOMP_FILTER") Tested-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/lkml/a36d7b48-6598-1642-e403-0c77a86f416d@physik.fu-berlin.de Signed-off-by: Kees Cook --- tools/testing/selftests/seccomp/seccomp_bpf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 7f7ecfcd66db..26c72f2b61b1 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1804,8 +1804,8 @@ TEST_F(TRACE_poke, getpid_runs_normally) #define SYSCALL_RET(_regs) (_regs).a[(_regs).windowbase * 4 + 2] #elif defined(__sh__) # define ARCH_REGS struct pt_regs -# define SYSCALL_NUM(_regs) (_regs).gpr[3] -# define SYSCALL_RET(_regs) (_regs).gpr[0] +# define SYSCALL_NUM(_regs) (_regs).regs[3] +# define SYSCALL_RET(_regs) (_regs).regs[0] #else # error "Do not know how to find your architecture's registers and syscalls" #endif -- cgit v1.2.3 From bff453921ae105a8dbbad0ed7dd5f5ce424536e7 Mon Sep 17 00:00:00 2001 From: Raju Rangoju Date: Wed, 18 Nov 2020 20:02:13 +0530 Subject: cxgb4: fix the panic caused by non smac rewrite SMT entry is allocated only when loopback Source MAC rewriting is requested. Accessing SMT entry for non smac rewrite cases results in kernel panic. Fix the panic caused by non smac rewrite Fixes: 937d84205884 ("cxgb4: set up filter action after rewrites") Signed-off-by: Raju Rangoju Link: https://lore.kernel.org/r/20201118143213.13319-1-rajur@chelsio.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 4e55f7081644..83b46440408b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -880,7 +880,8 @@ int set_filter_wr(struct adapter *adapter, int fidx) FW_FILTER_WR_OVLAN_VLD_V(f->fs.val.ovlan_vld) | FW_FILTER_WR_IVLAN_VLDM_V(f->fs.mask.ivlan_vld) | FW_FILTER_WR_OVLAN_VLDM_V(f->fs.mask.ovlan_vld)); - fwr->smac_sel = f->smt->idx; + if (f->fs.newsmac) + fwr->smac_sel = f->smt->idx; fwr->rx_chan_rx_rpl_iq = htons(FW_FILTER_WR_RX_CHAN_V(0) | FW_FILTER_WR_RX_RPL_IQ_V(adapter->sge.fw_evtq.abs_id)); -- cgit v1.2.3 From d2624e70a2f53b6f402fdaeabe7db798148618c5 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 19 Nov 2020 16:51:06 +0200 Subject: dpaa2-eth: select XGMAC_MDIO for MDIO bus support Explicitly enable the FSL_XGMAC_MDIO Kconfig option in order to have MDIO access to internal and external PHYs. Fixes: 719479230893 ("dpaa2-eth: add MAC/PHY support through phylink") Signed-off-by: Ioana Ciornei Link: https://lore.kernel.org/r/20201119145106.712761-1-ciorneiioana@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/dpaa2/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/freescale/dpaa2/Kconfig b/drivers/net/ethernet/freescale/dpaa2/Kconfig index cfd369cf4c8c..c0e05f71826d 100644 --- a/drivers/net/ethernet/freescale/dpaa2/Kconfig +++ b/drivers/net/ethernet/freescale/dpaa2/Kconfig @@ -4,6 +4,7 @@ config FSL_DPAA2_ETH depends on FSL_MC_BUS && FSL_MC_DPIO select PHYLINK select PCS_LYNX + select FSL_XGMAC_MDIO help This is the DPAA2 Ethernet driver supporting Freescale SoCs with DPAA2 (DataPath Acceleration Architecture v2). -- cgit v1.2.3 From 861602b57730a5c6d3e0b1e4ca7133ca9a8b8538 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 19 Nov 2020 13:23:51 -0800 Subject: tcp: Allow full IP tos/IPv6 tclass to be reflected in L3 header An issue was recently found where DCTCP SYN/ACK packets did not have the ECT bit set in the L3 header. A bit of code review found that the recent change referenced below had gone though and added a mask that prevented the ECN bits from being populated in the L3 header. This patch addresses that by rolling back the mask so that it is only applied to the flags coming from the incoming TCP request instead of applying it to the socket tos/tclass field. Doing this the ECT bits were restored in the SYN/ACK packets in my testing. One thing that is not addressed by this patch set is the fact that tcp_reflect_tos appears to be incompatible with ECN based congestion avoidance algorithms. At a minimum the feature should likely be documented which it currently isn't. Fixes: ac8f1710c12b ("tcp: reflect tos value received in SYN to the socket") Signed-off-by: Alexander Duyck Acked-by: Wei Wang Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_ipv4.c | 5 +++-- net/ipv6/tcp_ipv6.c | 6 +++--- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7352c097ae48..25d35a56ceba 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -981,7 +981,8 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos : inet_sk(sk)->tos; + tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : + inet_sk(sk)->tos; if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); @@ -990,7 +991,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, rcu_dereference(ireq->ireq_opt), - tos & ~INET_ECN_MASK); + tos); rcu_read_unlock(); err = net_xmit_eval(err); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8db59f4e5f13..3d49e8d0afee 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -530,12 +530,12 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_lock(); opt = ireq->ipv6_opt; tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos : np->tclass; + tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : + np->tclass; if (!opt) opt = rcu_dereference(np->opt); err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, - tclass & ~INET_ECN_MASK, - sk->sk_priority); + tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } -- cgit v1.2.3 From 55472017a4219ca965a957584affdb17549ae4a4 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 19 Nov 2020 13:23:58 -0800 Subject: tcp: Set INET_ECN_xmit configuration in tcp_reinit_congestion_control When setting congestion control via a BPF program it is seen that the SYN/ACK for packets within a given flow will not include the ECT0 flag. A bit of simple printk debugging shows that when this is configured without BPF we will see the value INET_ECN_xmit value initialized in tcp_assign_congestion_control however when we configure this via BPF the socket is in the closed state and as such it isn't configured, and I do not see it being initialized when we transition the socket into the listen state. The result of this is that the ECT0 bit is configured based on whatever the default state is for the socket. Any easy way to reproduce this is to monitor the following with tcpdump: tools/testing/selftests/bpf/test_progs -t bpf_tcp_ca Without this patch the SYN/ACK will follow whatever the default is. If dctcp all SYN/ACK packets will have the ECT0 bit set, and if it is not then ECT0 will be cleared on all SYN/ACK packets. With this patch applied the SYN/ACK bit matches the value seen on the other packets in the given stream. Fixes: 91b5b21c7c16 ("bpf: Add support for changing congestion control") Signed-off-by: Alexander Duyck Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_cong.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index db47ac24d057..563d016e7478 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -198,6 +198,11 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); + if (ca->flags & TCP_CONG_NEEDS_ECN) + INET_ECN_xmit(sk); + else + INET_ECN_dontxmit(sk); + if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) tcp_init_congestion_control(sk); } -- cgit v1.2.3 From 0d0e2b538c13f4f698ba58485a573ce824036567 Mon Sep 17 00:00:00 2001 From: Alexandra Winter Date: Fri, 20 Nov 2020 10:09:36 +0100 Subject: s390/qeth: Remove pnso workaround Remove workaround that supported early hardware implementations of PNSO OC3. Rely on the 'enarf' feature bit instead. Fixes: fa115adff2c1 ("s390/qeth: Detect PNSO OC3 capability") Signed-off-by: Alexandra Winter Reviewed-by: Julian Wiedmann [jwi: use logical instead of bit-wise AND] Signed-off-by: Julian Wiedmann Signed-off-by: Jakub Kicinski --- drivers/s390/net/qeth_l2_main.c | 18 ++---------------- 1 file changed, 2 insertions(+), 16 deletions(-) diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 28f6dda95736..79939ba5d523 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -985,32 +985,19 @@ static void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) * change notification' and thus can support the learning_sync bridgeport * attribute * @card: qeth_card structure pointer - * - * This is a destructive test and must be called before dev2br or - * bridgeport address notification is enabled! */ static void qeth_l2_detect_dev2br_support(struct qeth_card *card) { struct qeth_priv *priv = netdev_priv(card->dev); bool dev2br_supported; - int rc; QETH_CARD_TEXT(card, 2, "d2brsup"); if (!IS_IQD(card)) return; /* dev2br requires valid cssid,iid,chid */ - if (!card->info.ids_valid) { - dev2br_supported = false; - } else if (css_general_characteristics.enarf) { - dev2br_supported = true; - } else { - /* Old machines don't have the feature bit: - * Probe by testing whether a disable succeeds - */ - rc = qeth_l2_pnso(card, PNSO_OC_NET_ADDR_INFO, 0, NULL, NULL); - dev2br_supported = !rc; - } + dev2br_supported = card->info.ids_valid && + css_general_characteristics.enarf; QETH_CARD_TEXT_(card, 2, "D2Bsup%02x", dev2br_supported); if (dev2br_supported) @@ -2233,7 +2220,6 @@ static int qeth_l2_set_online(struct qeth_card *card, bool carrier_ok) struct net_device *dev = card->dev; int rc = 0; - /* query before bridgeport_notification may be enabled */ qeth_l2_detect_dev2br_support(card); mutex_lock(&card->sbp_lock); -- cgit v1.2.3 From 34c7f50f7d0d36fa663c74aee39e25e912505320 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 20 Nov 2020 10:09:37 +0100 Subject: s390/qeth: make af_iucv TX notification call more robust Calling into socket code is ugly already, at least check whether we are dealing with the expected sk_family. Only looking at skb->protocol is bound to cause troubles (consider eg. af_packet). Fixes: b333293058aa ("qeth: add support for af_iucv HiperSockets transport") Signed-off-by: Julian Wiedmann Signed-off-by: Jakub Kicinski --- drivers/s390/net/qeth_core_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 93c9b30ab17a..715f440bdc7c 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -33,6 +33,7 @@ #include #include +#include #include #include @@ -1405,7 +1406,7 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *q, skb_queue_walk(&buf->skb_list, skb) { QETH_CARD_TEXT_(q->card, 5, "skbn%d", notification); QETH_CARD_TEXT_(q->card, 5, "%lx", (long) skb); - if (skb->protocol == htons(ETH_P_AF_IUCV) && skb->sk) + if (skb->sk && skb->sk->sk_family == PF_IUCV) iucv_sk(skb->sk)->sk_txnotify(skb, notification); } } -- cgit v1.2.3 From 8908f36d20d8ba610d3a7d110b3049b5853b9bb1 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 20 Nov 2020 10:09:38 +0100 Subject: s390/qeth: fix af_iucv notification race The two expected notification sequences are 1. TX_NOTIFY_PENDING with a subsequent TX_NOTIFY_DELAYED_*, when our TX completion code first observed the pending TX and the QAOB then completes at a later time; or 2. TX_NOTIFY_OK, when qeth_qdio_handle_aob() picked up the QAOB completion before our TX completion code even noticed that the TX was pending. But as qeth_iqd_tx_complete() and qeth_qdio_handle_aob() can run concurrently, we may end up with a race that results in a sequence of TX_NOTIFY_DELAYED_* followed by TX_NOTIFY_PENDING. Which would confuse the af_iucv code in its tracking of pending transmits. Rework the notification code, so that qeth_qdio_handle_aob() defers its notification if the TX completion code is still active. Fixes: b333293058aa ("qeth: add support for af_iucv HiperSockets transport") Signed-off-by: Julian Wiedmann Signed-off-by: Jakub Kicinski --- drivers/s390/net/qeth_core.h | 9 +++-- drivers/s390/net/qeth_core_main.c | 73 ++++++++++++++++++++++++++++----------- 2 files changed, 58 insertions(+), 24 deletions(-) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index f73b4756ed5e..b235393e091c 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -417,10 +417,13 @@ enum qeth_qdio_out_buffer_state { QETH_QDIO_BUF_EMPTY, /* Filled by driver; owned by hardware in order to be sent. */ QETH_QDIO_BUF_PRIMED, - /* Identified to be pending in TPQ. */ + /* Discovered by the TX completion code: */ QETH_QDIO_BUF_PENDING, - /* Found in completion queue. */ - QETH_QDIO_BUF_IN_CQ, + /* Finished by the TX completion code: */ + QETH_QDIO_BUF_NEED_QAOB, + /* Received QAOB notification on CQ: */ + QETH_QDIO_BUF_QAOB_OK, + QETH_QDIO_BUF_QAOB_ERROR, /* Handled via transfer pending / completion queue. */ QETH_QDIO_BUF_HANDLED_DELAYED, }; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 715f440bdc7c..48f9e4a027bf 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -511,6 +511,7 @@ static void qeth_cleanup_handled_pending(struct qeth_qdio_out_q *q, int bidx, static void qeth_qdio_handle_aob(struct qeth_card *card, unsigned long phys_aob_addr) { + enum qeth_qdio_out_buffer_state new_state = QETH_QDIO_BUF_QAOB_OK; struct qaob *aob; struct qeth_qdio_out_buffer *buffer; enum iucv_tx_notify notification; @@ -522,22 +523,6 @@ static void qeth_qdio_handle_aob(struct qeth_card *card, buffer = (struct qeth_qdio_out_buffer *) aob->user1; QETH_CARD_TEXT_(card, 5, "%lx", aob->user1); - if (atomic_cmpxchg(&buffer->state, QETH_QDIO_BUF_PRIMED, - QETH_QDIO_BUF_IN_CQ) == QETH_QDIO_BUF_PRIMED) { - notification = TX_NOTIFY_OK; - } else { - WARN_ON_ONCE(atomic_read(&buffer->state) != - QETH_QDIO_BUF_PENDING); - atomic_set(&buffer->state, QETH_QDIO_BUF_IN_CQ); - notification = TX_NOTIFY_DELAYED_OK; - } - - if (aob->aorc != 0) { - QETH_CARD_TEXT_(card, 2, "aorc%02X", aob->aorc); - notification = qeth_compute_cq_notification(aob->aorc, 1); - } - qeth_notify_skbs(buffer->q, buffer, notification); - /* Free dangling allocations. The attached skbs are handled by * qeth_cleanup_handled_pending(). */ @@ -549,7 +534,33 @@ static void qeth_qdio_handle_aob(struct qeth_card *card, if (data && buffer->is_header[i]) kmem_cache_free(qeth_core_header_cache, data); } - atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED); + + if (aob->aorc) { + QETH_CARD_TEXT_(card, 2, "aorc%02X", aob->aorc); + new_state = QETH_QDIO_BUF_QAOB_ERROR; + } + + switch (atomic_xchg(&buffer->state, new_state)) { + case QETH_QDIO_BUF_PRIMED: + /* Faster than TX completion code. */ + notification = qeth_compute_cq_notification(aob->aorc, 0); + qeth_notify_skbs(buffer->q, buffer, notification); + atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED); + break; + case QETH_QDIO_BUF_PENDING: + /* TX completion code is active and will handle the async + * completion for us. + */ + break; + case QETH_QDIO_BUF_NEED_QAOB: + /* TX completion code is already finished. */ + notification = qeth_compute_cq_notification(aob->aorc, 1); + qeth_notify_skbs(buffer->q, buffer, notification); + atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED); + break; + default: + WARN_ON_ONCE(1); + } qdio_release_aob(aob); } @@ -1417,9 +1428,6 @@ static void qeth_tx_complete_buf(struct qeth_qdio_out_buffer *buf, bool error, struct qeth_qdio_out_q *queue = buf->q; struct sk_buff *skb; - /* release may never happen from within CQ tasklet scope */ - WARN_ON_ONCE(atomic_read(&buf->state) == QETH_QDIO_BUF_IN_CQ); - if (atomic_read(&buf->state) == QETH_QDIO_BUF_PENDING) qeth_notify_skbs(queue, buf, TX_NOTIFY_GENERALERROR); @@ -5870,9 +5878,32 @@ static void qeth_iqd_tx_complete(struct qeth_qdio_out_q *queue, if (atomic_cmpxchg(&buffer->state, QETH_QDIO_BUF_PRIMED, QETH_QDIO_BUF_PENDING) == - QETH_QDIO_BUF_PRIMED) + QETH_QDIO_BUF_PRIMED) { qeth_notify_skbs(queue, buffer, TX_NOTIFY_PENDING); + /* Handle race with qeth_qdio_handle_aob(): */ + switch (atomic_xchg(&buffer->state, + QETH_QDIO_BUF_NEED_QAOB)) { + case QETH_QDIO_BUF_PENDING: + /* No concurrent QAOB notification. */ + break; + case QETH_QDIO_BUF_QAOB_OK: + qeth_notify_skbs(queue, buffer, + TX_NOTIFY_DELAYED_OK); + atomic_set(&buffer->state, + QETH_QDIO_BUF_HANDLED_DELAYED); + break; + case QETH_QDIO_BUF_QAOB_ERROR: + qeth_notify_skbs(queue, buffer, + TX_NOTIFY_DELAYED_GENERALERROR); + atomic_set(&buffer->state, + QETH_QDIO_BUF_HANDLED_DELAYED); + break; + default: + WARN_ON_ONCE(1); + } + } + QETH_CARD_TEXT_(card, 5, "pel%u", bidx); /* prepare the queue slot for re-use: */ -- cgit v1.2.3 From 7ed10e16e50daf74460f54bc922e27c6863c8d61 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 20 Nov 2020 10:09:39 +0100 Subject: s390/qeth: fix tear down of async TX buffers When qeth_iqd_tx_complete() detects that a TX buffer requires additional async completion via QAOB, it might fail to replace the queue entry's metadata (and ends up triggering recovery). Assume now that the device gets torn down, overruling the recovery. If the QAOB notification then arrives before the tear down has sufficiently progressed, the buffer state is changed to QETH_QDIO_BUF_HANDLED_DELAYED by qeth_qdio_handle_aob(). The tear down code calls qeth_drain_output_queue(), where qeth_cleanup_handled_pending() will then attempt to replace such a buffer _again_. If it succeeds this time, the buffer ends up dangling in its replacement's ->next_pending list ... where it will never be freed, since there's no further call to qeth_cleanup_handled_pending(). But the second attempt isn't actually needed, we can simply leave the buffer on the queue and re-use it after a potential recovery has completed. The qeth_clear_output_buffer() in qeth_drain_output_queue() will ensure that it's in a clean state again. Fixes: 72861ae792c2 ("qeth: recovery through asynchronous delivery") Signed-off-by: Julian Wiedmann Signed-off-by: Jakub Kicinski --- drivers/s390/net/qeth_core_main.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 48f9e4a027bf..e27319de7b00 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -500,12 +500,6 @@ static void qeth_cleanup_handled_pending(struct qeth_qdio_out_q *q, int bidx, } } - if (forced_cleanup && (atomic_read(&(q->bufs[bidx]->state)) == - QETH_QDIO_BUF_HANDLED_DELAYED)) { - /* for recovery situations */ - qeth_init_qdio_out_buf(q, bidx); - QETH_CARD_TEXT(q->card, 2, "clprecov"); - } } static void qeth_qdio_handle_aob(struct qeth_card *card, -- cgit v1.2.3 From 487778f8d22fcdebb6436f0a5f96484ffa237b0b Mon Sep 17 00:00:00 2001 From: CK Hu Date: Fri, 13 Nov 2020 11:49:07 +0800 Subject: drm/mediatek: dsi: Modify horizontal front/back porch byte formula In the patch to be fixed, horizontal_backporch_byte become too large for some panel, so roll back that patch. For small hfp or hbp panel, using vm->hfront_porch + vm->hback_porch to calculate horizontal_backporch_byte would make it negtive, so use horizontal_backporch_byte itself to make it positive. Fixes: 35bf948f1edb ("drm/mediatek: dsi: Fix scrolling of panel with small hfp or hbp") Signed-off-by: CK Hu Signed-off-by: Chun-Kuang Hu Tested-by: Bilal Wasim --- drivers/gpu/drm/mediatek/mtk_dsi.c | 61 ++++++++++++++------------------------ 1 file changed, 22 insertions(+), 39 deletions(-) diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 4a188a942c38..65fd99c528af 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -444,7 +444,10 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi) u32 horizontal_sync_active_byte; u32 horizontal_backporch_byte; u32 horizontal_frontporch_byte; + u32 horizontal_front_back_byte; + u32 data_phy_cycles_byte; u32 dsi_tmp_buf_bpp, data_phy_cycles; + u32 delta; struct mtk_phy_timing *timing = &dsi->phy_timing; struct videomode *vm = &dsi->vm; @@ -466,50 +469,30 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi) horizontal_sync_active_byte = (vm->hsync_len * dsi_tmp_buf_bpp - 10); if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) - horizontal_backporch_byte = vm->hback_porch * dsi_tmp_buf_bpp; + horizontal_backporch_byte = vm->hback_porch * dsi_tmp_buf_bpp - 10; else horizontal_backporch_byte = (vm->hback_porch + vm->hsync_len) * - dsi_tmp_buf_bpp; + dsi_tmp_buf_bpp - 10; data_phy_cycles = timing->lpx + timing->da_hs_prepare + - timing->da_hs_zero + timing->da_hs_exit; - - if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) { - if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp > - data_phy_cycles * dsi->lanes + 18) { - horizontal_frontporch_byte = - vm->hfront_porch * dsi_tmp_buf_bpp - - (data_phy_cycles * dsi->lanes + 18) * - vm->hfront_porch / - (vm->hfront_porch + vm->hback_porch); - - horizontal_backporch_byte = - horizontal_backporch_byte - - (data_phy_cycles * dsi->lanes + 18) * - vm->hback_porch / - (vm->hfront_porch + vm->hback_porch); - } else { - DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n"); - horizontal_frontporch_byte = vm->hfront_porch * - dsi_tmp_buf_bpp; - } + timing->da_hs_zero + timing->da_hs_exit + 3; + + delta = dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST ? 18 : 12; + + horizontal_frontporch_byte = vm->hfront_porch * dsi_tmp_buf_bpp; + horizontal_front_back_byte = horizontal_frontporch_byte + horizontal_backporch_byte; + data_phy_cycles_byte = data_phy_cycles * dsi->lanes + delta; + + if (horizontal_front_back_byte > data_phy_cycles_byte) { + horizontal_frontporch_byte -= data_phy_cycles_byte * + horizontal_frontporch_byte / + horizontal_front_back_byte; + + horizontal_backporch_byte -= data_phy_cycles_byte * + horizontal_backporch_byte / + horizontal_front_back_byte; } else { - if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp > - data_phy_cycles * dsi->lanes + 12) { - horizontal_frontporch_byte = - vm->hfront_porch * dsi_tmp_buf_bpp - - (data_phy_cycles * dsi->lanes + 12) * - vm->hfront_porch / - (vm->hfront_porch + vm->hback_porch); - horizontal_backporch_byte = horizontal_backporch_byte - - (data_phy_cycles * dsi->lanes + 12) * - vm->hback_porch / - (vm->hfront_porch + vm->hback_porch); - } else { - DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n"); - horizontal_frontporch_byte = vm->hfront_porch * - dsi_tmp_buf_bpp; - } + DRM_WARN("HFP + HBP less than d-phy, FPS will under 60Hz\n"); } writel(horizontal_sync_active_byte, dsi->regs + DSI_HSA_WC); -- cgit v1.2.3 From b9ad3e9f5a7a760ab068e33e1f18d240ba32ce92 Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Fri, 20 Nov 2020 14:28:27 +0000 Subject: bonding: wait for sysfs kobject destruction before freeing struct slave syzkaller found that with CONFIG_DEBUG_KOBJECT_RELEASE=y, releasing a struct slave device could result in the following splat: kobject: 'bonding_slave' (00000000cecdd4fe): kobject_release, parent 0000000074ceb2b2 (delayed 1000) bond0 (unregistering): (slave bond_slave_1): Releasing backup interface ------------[ cut here ]------------ ODEBUG: free active (active state 0) object type: timer_list hint: workqueue_select_cpu_near kernel/workqueue.c:1549 [inline] ODEBUG: free active (active state 0) object type: timer_list hint: delayed_work_timer_fn+0x0/0x98 kernel/workqueue.c:1600 WARNING: CPU: 1 PID: 842 at lib/debugobjects.c:485 debug_print_object+0x180/0x240 lib/debugobjects.c:485 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 842 Comm: kworker/u4:4 Tainted: G S 5.9.0-rc8+ #96 Hardware name: linux,dummy-virt (DT) Workqueue: netns cleanup_net Call trace: dump_backtrace+0x0/0x4d8 include/linux/bitmap.h:239 show_stack+0x34/0x48 arch/arm64/kernel/traps.c:142 __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x174/0x1f8 lib/dump_stack.c:118 panic+0x360/0x7a0 kernel/panic.c:231 __warn+0x244/0x2ec kernel/panic.c:600 report_bug+0x240/0x398 lib/bug.c:198 bug_handler+0x50/0xc0 arch/arm64/kernel/traps.c:974 call_break_hook+0x160/0x1d8 arch/arm64/kernel/debug-monitors.c:322 brk_handler+0x30/0xc0 arch/arm64/kernel/debug-monitors.c:329 do_debug_exception+0x184/0x340 arch/arm64/mm/fault.c:864 el1_dbg+0x48/0xb0 arch/arm64/kernel/entry-common.c:65 el1_sync_handler+0x170/0x1c8 arch/arm64/kernel/entry-common.c:93 el1_sync+0x80/0x100 arch/arm64/kernel/entry.S:594 debug_print_object+0x180/0x240 lib/debugobjects.c:485 __debug_check_no_obj_freed lib/debugobjects.c:967 [inline] debug_check_no_obj_freed+0x200/0x430 lib/debugobjects.c:998 slab_free_hook mm/slub.c:1536 [inline] slab_free_freelist_hook+0x190/0x210 mm/slub.c:1577 slab_free mm/slub.c:3138 [inline] kfree+0x13c/0x460 mm/slub.c:4119 bond_free_slave+0x8c/0xf8 drivers/net/bonding/bond_main.c:1492 __bond_release_one+0xe0c/0xec8 drivers/net/bonding/bond_main.c:2190 bond_slave_netdev_event drivers/net/bonding/bond_main.c:3309 [inline] bond_netdev_event+0x8f0/0xa70 drivers/net/bonding/bond_main.c:3420 notifier_call_chain+0xf0/0x200 kernel/notifier.c:83 __raw_notifier_call_chain kernel/notifier.c:361 [inline] raw_notifier_call_chain+0x44/0x58 kernel/notifier.c:368 call_netdevice_notifiers_info+0xbc/0x150 net/core/dev.c:2033 call_netdevice_notifiers_extack net/core/dev.c:2045 [inline] call_netdevice_notifiers net/core/dev.c:2059 [inline] rollback_registered_many+0x6a4/0xec0 net/core/dev.c:9347 unregister_netdevice_many.part.0+0x2c/0x1c0 net/core/dev.c:10509 unregister_netdevice_many net/core/dev.c:10508 [inline] default_device_exit_batch+0x294/0x338 net/core/dev.c:10992 ops_exit_list.isra.0+0xec/0x150 net/core/net_namespace.c:189 cleanup_net+0x44c/0x888 net/core/net_namespace.c:603 process_one_work+0x96c/0x18c0 kernel/workqueue.c:2269 worker_thread+0x3f0/0xc30 kernel/workqueue.c:2415 kthread+0x390/0x498 kernel/kthread.c:292 ret_from_fork+0x10/0x18 arch/arm64/kernel/entry.S:925 This is a potential use-after-free if the sysfs nodes are being accessed whilst removing the struct slave, so wait for the object destruction to complete before freeing the struct slave itself. Fixes: 07699f9a7c8d ("bonding: add sysfs /slave dir for bond slave devices.") Fixes: a068aab42258 ("bonding: Fix reference count leak in bond_sysfs_slave_add.") Cc: Qiushi Wu Cc: Jay Vosburgh Cc: Veaceslav Falico Cc: Andy Gospodarek Signed-off-by: Jamie Iles Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20201120142827.879226-1-jamie@nuviainc.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_main.c | 61 ++++++++++++++++++++++++---------- drivers/net/bonding/bond_sysfs_slave.c | 18 +--------- include/net/bonding.h | 8 +++++ 3 files changed, 52 insertions(+), 35 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 84ecbc6fa0ff..47afc5938c26 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1460,7 +1460,39 @@ static void bond_upper_dev_unlink(struct bonding *bond, struct slave *slave) slave->dev->flags &= ~IFF_SLAVE; } -static struct slave *bond_alloc_slave(struct bonding *bond) +static void slave_kobj_release(struct kobject *kobj) +{ + struct slave *slave = to_slave(kobj); + struct bonding *bond = bond_get_bond_by_slave(slave); + + cancel_delayed_work_sync(&slave->notify_work); + if (BOND_MODE(bond) == BOND_MODE_8023AD) + kfree(SLAVE_AD_INFO(slave)); + + kfree(slave); +} + +static struct kobj_type slave_ktype = { + .release = slave_kobj_release, +#ifdef CONFIG_SYSFS + .sysfs_ops = &slave_sysfs_ops, +#endif +}; + +static int bond_kobj_init(struct slave *slave) +{ + int err; + + err = kobject_init_and_add(&slave->kobj, &slave_ktype, + &(slave->dev->dev.kobj), "bonding_slave"); + if (err) + kobject_put(&slave->kobj); + + return err; +} + +static struct slave *bond_alloc_slave(struct bonding *bond, + struct net_device *slave_dev) { struct slave *slave = NULL; @@ -1468,11 +1500,17 @@ static struct slave *bond_alloc_slave(struct bonding *bond) if (!slave) return NULL; + slave->bond = bond; + slave->dev = slave_dev; + + if (bond_kobj_init(slave)) + return NULL; + if (BOND_MODE(bond) == BOND_MODE_8023AD) { SLAVE_AD_INFO(slave) = kzalloc(sizeof(struct ad_slave_info), GFP_KERNEL); if (!SLAVE_AD_INFO(slave)) { - kfree(slave); + kobject_put(&slave->kobj); return NULL; } } @@ -1481,17 +1519,6 @@ static struct slave *bond_alloc_slave(struct bonding *bond) return slave; } -static void bond_free_slave(struct slave *slave) -{ - struct bonding *bond = bond_get_bond_by_slave(slave); - - cancel_delayed_work_sync(&slave->notify_work); - if (BOND_MODE(bond) == BOND_MODE_8023AD) - kfree(SLAVE_AD_INFO(slave)); - - kfree(slave); -} - static void bond_fill_ifbond(struct bonding *bond, struct ifbond *info) { info->bond_mode = BOND_MODE(bond); @@ -1678,14 +1705,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, goto err_undo_flags; } - new_slave = bond_alloc_slave(bond); + new_slave = bond_alloc_slave(bond, slave_dev); if (!new_slave) { res = -ENOMEM; goto err_undo_flags; } - new_slave->bond = bond; - new_slave->dev = slave_dev; /* Set the new_slave's queue_id to be zero. Queue ID mapping * is set via sysfs or module option if desired. */ @@ -2007,7 +2032,7 @@ err_restore_mtu: dev_set_mtu(slave_dev, new_slave->original_mtu); err_free: - bond_free_slave(new_slave); + kobject_put(&new_slave->kobj); err_undo_flags: /* Enslave of first slave has failed and we need to fix master's mac */ @@ -2187,7 +2212,7 @@ static int __bond_release_one(struct net_device *bond_dev, if (!netif_is_bond_master(slave_dev)) slave_dev->priv_flags &= ~IFF_BONDING; - bond_free_slave(slave); + kobject_put(&slave->kobj); return 0; } diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c index 9b8346638f69..fd07561da034 100644 --- a/drivers/net/bonding/bond_sysfs_slave.c +++ b/drivers/net/bonding/bond_sysfs_slave.c @@ -121,7 +121,6 @@ static const struct slave_attribute *slave_attrs[] = { }; #define to_slave_attr(_at) container_of(_at, struct slave_attribute, attr) -#define to_slave(obj) container_of(obj, struct slave, kobj) static ssize_t slave_show(struct kobject *kobj, struct attribute *attr, char *buf) @@ -132,28 +131,15 @@ static ssize_t slave_show(struct kobject *kobj, return slave_attr->show(slave, buf); } -static const struct sysfs_ops slave_sysfs_ops = { +const struct sysfs_ops slave_sysfs_ops = { .show = slave_show, }; -static struct kobj_type slave_ktype = { -#ifdef CONFIG_SYSFS - .sysfs_ops = &slave_sysfs_ops, -#endif -}; - int bond_sysfs_slave_add(struct slave *slave) { const struct slave_attribute **a; int err; - err = kobject_init_and_add(&slave->kobj, &slave_ktype, - &(slave->dev->dev.kobj), "bonding_slave"); - if (err) { - kobject_put(&slave->kobj); - return err; - } - for (a = slave_attrs; *a; ++a) { err = sysfs_create_file(&slave->kobj, &((*a)->attr)); if (err) { @@ -171,6 +157,4 @@ void bond_sysfs_slave_del(struct slave *slave) for (a = slave_attrs; *a; ++a) sysfs_remove_file(&slave->kobj, &((*a)->attr)); - - kobject_put(&slave->kobj); } diff --git a/include/net/bonding.h b/include/net/bonding.h index 7d132cc1e584..d9d0ff3b0ad3 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -185,6 +185,11 @@ struct slave { struct rtnl_link_stats64 slave_stats; }; +static inline struct slave *to_slave(struct kobject *kobj) +{ + return container_of(kobj, struct slave, kobj); +} + struct bond_up_slave { unsigned int count; struct rcu_head rcu; @@ -750,6 +755,9 @@ extern struct bond_parm_tbl ad_select_tbl[]; /* exported from bond_netlink.c */ extern struct rtnl_link_ops bond_link_ops; +/* exported from bond_sysfs_slave.c */ +extern const struct sysfs_ops slave_sysfs_ops; + static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb) { atomic_long_inc(&dev->tx_dropped); -- cgit v1.2.3 From 659fbdcf2f147010a7624f7eac04f4282814b013 Mon Sep 17 00:00:00 2001 From: Tom Seewald Date: Fri, 20 Nov 2020 13:25:28 -0600 Subject: cxgb4: Fix build failure when CONFIG_TLS=m After commit 9d2e5e9eeb59 ("cxgb4/ch_ktls: decrypted bit is not enough") whenever CONFIG_TLS=m and CONFIG_CHELSIO_T4=y, the following build failure occurs: ld: drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.o: in function `cxgb_select_queue': cxgb4_main.c:(.text+0x2dac): undefined reference to `tls_validate_xmit_skb' Fix this by ensuring that if TLS is set to be a module, CHELSIO_T4 will also be compiled as a module. As otherwise the cxgb4 driver will not be able to access TLS' symbols. Fixes: 9d2e5e9eeb59 ("cxgb4/ch_ktls: decrypted bit is not enough") Signed-off-by: Tom Seewald Link: https://lore.kernel.org/r/20201120192528.615-1-tseewald@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/chelsio/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig index 87cc0ef68b31..8ba0e08e5e64 100644 --- a/drivers/net/ethernet/chelsio/Kconfig +++ b/drivers/net/ethernet/chelsio/Kconfig @@ -68,7 +68,7 @@ config CHELSIO_T3 config CHELSIO_T4 tristate "Chelsio Communications T4/T5/T6 Ethernet support" - depends on PCI && (IPV6 || IPV6=n) + depends on PCI && (IPV6 || IPV6=n) && (TLS || TLS=n) select FW_LOADER select MDIO select ZLIB_DEFLATE -- cgit v1.2.3 From f33d9e2b48a34e1558b67a473a1fc1d6e793f93c Mon Sep 17 00:00:00 2001 From: Yves-Alexis Perez Date: Thu, 19 Nov 2020 18:24:39 +0100 Subject: usbnet: ipheth: fix connectivity with iOS 14 Starting with iOS 14 released in September 2020, connectivity using the personal hotspot USB tethering function of iOS devices is broken. Communication between the host and the device (for example ICMP traffic or DNS resolution using the DNS service running in the device itself) works fine, but communication to endpoints further away doesn't work. Investigation on the matter shows that no UDP and ICMP traffic from the tethered host is reaching the Internet at all. For TCP traffic there are exchanges between tethered host and server but packets are modified in transit leading to impossible communication. After some trials Matti Vuorela discovered that reducing the URB buffer size by two bytes restored the previous behavior. While a better solution might exist to fix the issue, since the protocol is not publicly documented and considering the small size of the fix, let's do that. Tested-by: Matti Vuorela Signed-off-by: Yves-Alexis Perez Link: https://lore.kernel.org/linux-usb/CAAn0qaXmysJ9vx3ZEMkViv_B19ju-_ExN8Yn_uSefxpjS6g4Lw@mail.gmail.com/ Link: https://github.com/libimobiledevice/libimobiledevice/issues/1038 Link: https://lore.kernel.org/r/20201119172439.94988-1-corsac@corsac.net Signed-off-by: Jakub Kicinski --- drivers/net/usb/ipheth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index b09b45382faf..207e59e74935 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -59,7 +59,7 @@ #define IPHETH_USBINTF_SUBCLASS 253 #define IPHETH_USBINTF_PROTO 1 -#define IPHETH_BUF_SIZE 1516 +#define IPHETH_BUF_SIZE 1514 #define IPHETH_IP_ALIGN 2 /* padding at front of URB */ #define IPHETH_TX_TIMEOUT (5 * HZ) -- cgit v1.2.3 From c5dab0941fcdc9664eb0ec0d4d51433216d91336 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 20 Nov 2020 11:06:57 +0100 Subject: net/af_iucv: set correct sk_protocol for child sockets Child sockets erroneously inherit their parent's sk_type (ie. SOCK_*), instead of the PF_IUCV protocol that the parent was created with in iucv_sock_create(). We're currently not using sk->sk_protocol ourselves, so this shouldn't have much impact (except eg. getting the output in skb_dump() right). Fixes: eac3731bd04c ("[S390]: Add AF_IUCV socket support") Signed-off-by: Julian Wiedmann Link: https://lore.kernel.org/r/20201120100657.34407-1-jwi@linux.ibm.com Signed-off-by: Jakub Kicinski --- net/iucv/af_iucv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 047238f01ba6..db7d888914fa 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1645,7 +1645,7 @@ static int iucv_callback_connreq(struct iucv_path *path, } /* Create the new socket */ - nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0); + nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0); if (!nsk) { err = pr_iucv->path_sever(path, user_data); iucv_path_free(path); @@ -1851,7 +1851,7 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb) goto out; } - nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0); + nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0); bh_lock_sock(sk); if ((sk->sk_state != IUCV_LISTEN) || sk_acceptq_is_full(sk) || -- cgit v1.2.3 From 5aac0390a63b8718237a61dd0d24a29201d1c94a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Nov 2020 07:59:54 -0700 Subject: tun: honor IOCB_NOWAIT flag tun only checks the file O_NONBLOCK flag, but it should also be checking the iocb IOCB_NOWAIT flag. Any fops using ->read/write_iter() should check both, otherwise it breaks users that correctly expect O_NONBLOCK semantics if IOCB_NOWAIT is set. Signed-off-by: Jens Axboe Link: https://lore.kernel.org/r/e9451860-96cc-c7c7-47b8-fe42cadd5f4c@kernel.dk Signed-off-by: Jakub Kicinski --- drivers/net/tun.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index be69d272052f..cd06cae76035 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1961,12 +1961,15 @@ static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t result; + int noblock = 0; if (!tun) return -EBADFD; - result = tun_get_user(tun, tfile, NULL, from, - file->f_flags & O_NONBLOCK, false); + if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) + noblock = 1; + + result = tun_get_user(tun, tfile, NULL, from, noblock, false); tun_put(tun); return result; @@ -2185,10 +2188,15 @@ static ssize_t tun_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t len = iov_iter_count(to), ret; + int noblock = 0; if (!tun) return -EBADFD; - ret = tun_do_read(tun, tfile, to, file->f_flags & O_NONBLOCK, NULL); + + if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) + noblock = 1; + + ret = tun_do_read(tun, tfile, to, noblock, NULL); ret = min_t(ssize_t, ret, len); if (ret > 0) iocb->ki_pos = ret; -- cgit v1.2.3 From 8393597579f5250636f1cff157ea73f402b6501e Mon Sep 17 00:00:00 2001 From: Lijun Pan Date: Fri, 20 Nov 2020 16:40:11 -0600 Subject: ibmvnic: fix call_netdevice_notifiers in do_reset When netdev_notify_peers was substituted in commit 986103e7920c ("net/ibmvnic: Fix RTNL deadlock during device reset"), call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev) was missed. Fix it now. Fixes: 986103e7920c ("net/ibmvnic: Fix RTNL deadlock during device reset") Signed-off-by: Lijun Pan Reviewed-by: Dany Madden Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index da15913879f8..eface3543b2c 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2074,8 +2074,10 @@ static int do_reset(struct ibmvnic_adapter *adapter, for (i = 0; i < adapter->req_rx_queues; i++) napi_schedule(&adapter->napi[i]); - if (adapter->reset_reason != VNIC_RESET_FAILOVER) + if (adapter->reset_reason != VNIC_RESET_FAILOVER) { call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev); + call_netdevice_notifiers(NETDEV_RESEND_IGMP, netdev); + } rc = 0; -- cgit v1.2.3 From 98025bce3a6200a0c4637272a33b5913928ba5b8 Mon Sep 17 00:00:00 2001 From: Lijun Pan Date: Fri, 20 Nov 2020 16:40:12 -0600 Subject: ibmvnic: notify peers when failover and migration happen Commit 61d3e1d9bc2a ("ibmvnic: Remove netdev notify for failover resets") excluded the failover case for notify call because it said netdev_notify_peers() can cause network traffic to stall or halt. Current testing does not show network traffic stall or halt because of the notify call for failover event. netdev_notify_peers may be used when a device wants to inform the rest of the network about some sort of a reconfiguration such as failover or migration. It is unnecessary to call that in other events like FATAL, NON_FATAL, CHANGE_PARAM, and TIMEOUT resets since in those scenarios the hardware does not change. If the driver must do a hard reset, it is necessary to notify peers. Fixes: 61d3e1d9bc2a ("ibmvnic: Remove netdev notify for failover resets") Suggested-by: Brian King Suggested-by: Pradeep Satyanarayana Signed-off-by: Dany Madden Signed-off-by: Lijun Pan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index eface3543b2c..9665532a9ed2 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2074,7 +2074,8 @@ static int do_reset(struct ibmvnic_adapter *adapter, for (i = 0; i < adapter->req_rx_queues; i++) napi_schedule(&adapter->napi[i]); - if (adapter->reset_reason != VNIC_RESET_FAILOVER) { + if (adapter->reset_reason == VNIC_RESET_FAILOVER || + adapter->reset_reason == VNIC_RESET_MOBILITY) { call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev); call_netdevice_notifiers(NETDEV_RESEND_IGMP, netdev); } @@ -2147,6 +2148,9 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter, if (rc) return IBMVNIC_OPEN_FAILED; + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev); + call_netdevice_notifiers(NETDEV_RESEND_IGMP, netdev); + return 0; } -- cgit v1.2.3 From 855a631a4c11458a9cef1ab79c1530436aa95fae Mon Sep 17 00:00:00 2001 From: Lijun Pan Date: Fri, 20 Nov 2020 16:40:13 -0600 Subject: ibmvnic: skip tx timeout reset while in resetting Sometimes it takes longer than 5 seconds (watchdog timeout) to complete failover, migration, and other resets. In stead of scheduling another timeout reset, we wait for the current one to complete. Suggested-by: Brian King Signed-off-by: Lijun Pan Reviewed-by: Dany Madden Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 9665532a9ed2..2aa40b2f225c 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2356,6 +2356,12 @@ static void ibmvnic_tx_timeout(struct net_device *dev, unsigned int txqueue) { struct ibmvnic_adapter *adapter = netdev_priv(dev); + if (test_bit(0, &adapter->resetting)) { + netdev_err(adapter->netdev, + "Adapter is resetting, skip timeout reset\n"); + return; + } + ibmvnic_reset(adapter, VNIC_RESET_TIMEOUT); } -- cgit v1.2.3 From d001e41e1b15716e9b759df5ef00510699f85282 Mon Sep 17 00:00:00 2001 From: Chen Baozi Date: Tue, 17 Nov 2020 11:20:15 +0800 Subject: irqchip/exiu: Fix the index of fwspec for IRQ type Since fwspec->param_count of ACPI node is two, the index of IRQ type in fwspec->param[] should be 1 rather than 2. Fixes: 3d090a36c8c8 ("irqchip/exiu: Implement ACPI support") Signed-off-by: Chen Baozi Signed-off-by: Marc Zyngier Acked-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20201117032015.11805-1-cbz@baozis.org Cc: stable@vger.kernel.org --- drivers/irqchip/irq-sni-exiu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-sni-exiu.c b/drivers/irqchip/irq-sni-exiu.c index 1d027623c776..abd011fcecf4 100644 --- a/drivers/irqchip/irq-sni-exiu.c +++ b/drivers/irqchip/irq-sni-exiu.c @@ -136,7 +136,7 @@ static int exiu_domain_translate(struct irq_domain *domain, if (fwspec->param_count != 2) return -EINVAL; *hwirq = fwspec->param[0]; - *type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK; + *type = fwspec->param[1] & IRQ_TYPE_SENSE_MASK; } return 0; } -- cgit v1.2.3 From 74cde1a53368aed4f2b4b54bf7030437f64a534b Mon Sep 17 00:00:00 2001 From: Xu Qiang Date: Sat, 7 Nov 2020 10:42:26 +0000 Subject: irqchip/gic-v3-its: Unconditionally save/restore the ITS state on suspend On systems without HW-based collections (i.e. anything except GIC-500), we rely on firmware to perform the ITS save/restore. This doesn't really work, as although FW can properly save everything, it cannot fully restore the state of the command queue (the read-side is reset to the head of the queue). This results in the ITS consuming previously processed commands, potentially corrupting the state. Instead, let's always save the ITS state on suspend, disabling it in the process, and restore the full state on resume. This saves us from broken FW as long as it doesn't enable the ITS by itself (for which we can't do anything). This amounts to simply dropping the ITS_FLAGS_SAVE_SUSPEND_STATE. Signed-off-by: Xu Qiang [maz: added warning on resume, rewrote commit message] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20201107104226.14282-1-xuqiang36@huawei.com --- drivers/irqchip/irq-gic-v3-its.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 0418071a3724..0598c5caff5c 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -42,7 +42,6 @@ #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING (1ULL << 0) #define ITS_FLAGS_WORKAROUND_CAVIUM_22375 (1ULL << 1) #define ITS_FLAGS_WORKAROUND_CAVIUM_23144 (1ULL << 2) -#define ITS_FLAGS_SAVE_SUSPEND_STATE (1ULL << 3) #define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING (1 << 0) #define RDIST_FLAGS_RD_TABLES_PREALLOCATED (1 << 1) @@ -4741,9 +4740,6 @@ static int its_save_disable(void) list_for_each_entry(its, &its_nodes, entry) { void __iomem *base; - if (!(its->flags & ITS_FLAGS_SAVE_SUSPEND_STATE)) - continue; - base = its->base; its->ctlr_save = readl_relaxed(base + GITS_CTLR); err = its_force_quiescent(base); @@ -4762,9 +4758,6 @@ err: list_for_each_entry_continue_reverse(its, &its_nodes, entry) { void __iomem *base; - if (!(its->flags & ITS_FLAGS_SAVE_SUSPEND_STATE)) - continue; - base = its->base; writel_relaxed(its->ctlr_save, base + GITS_CTLR); } @@ -4784,9 +4777,6 @@ static void its_restore_enable(void) void __iomem *base; int i; - if (!(its->flags & ITS_FLAGS_SAVE_SUSPEND_STATE)) - continue; - base = its->base; /* @@ -4794,7 +4784,10 @@ static void its_restore_enable(void) * don't restore it since writing to CBASER or BASER * registers is undefined according to the GIC v3 ITS * Specification. + * + * Firmware resuming with the ITS enabled is terminally broken. */ + WARN_ON(readl_relaxed(base + GITS_CTLR) & GITS_CTLR_ENABLE); ret = its_force_quiescent(base); if (ret) { pr_err("ITS@%pa: failed to quiesce on resume: %d\n", @@ -5074,9 +5067,6 @@ static int __init its_probe_one(struct resource *res, ctlr |= GITS_CTLR_ImDe; writel_relaxed(ctlr, its->base + GITS_CTLR); - if (GITS_TYPER_HCC(typer)) - its->flags |= ITS_FLAGS_SAVE_SUSPEND_STATE; - err = its_init_domain(handle, its); if (err) goto out_free_tables; -- cgit v1.2.3 From 450677dcb0cce5cb751538360b7196c28b733f3e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 21 Nov 2020 22:16:58 -0800 Subject: mm/madvise: fix memory leak from process_madvise The early return in process_madvise() will produce a memory leak. Fix it. Fixes: ecb8ac8b1f14 ("mm/madvise: introduce process_madvise() syscall: an external memory hinting API") Signed-off-by: Eric Dumazet Signed-off-by: Minchan Kim Signed-off-by: Andrew Morton Link: https://lkml.kernel.org/r/20201116155132.GA3805951@google.com Signed-off-by: Linus Torvalds --- mm/madvise.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/mm/madvise.c b/mm/madvise.c index 416a56b8e757..7e773f949ef9 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -1231,8 +1231,6 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, ret = total_len - iov_iter_count(&iter); mmput(mm); - return ret; - release_task: put_task_struct(task); put_pid: -- cgit v1.2.3 From bc2dc4406c463174613047d8b7946e12c8808cda Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Sat, 21 Nov 2020 22:17:01 -0800 Subject: compiler-clang: remove version check for BPF Tracing bpftrace parses the kernel headers and uses Clang under the hood. Remove the version check when __BPF_TRACING__ is defined (as bpftrace does) so that this tool can continue to parse kernel headers, even with older clang sources. Fixes: commit 1f7a44f63e6c ("compiler-clang: add build check for clang 10.0.1") Reported-by: Chen Yu Reported-by: Jarkko Sakkinen Signed-off-by: Nick Desaulniers Signed-off-by: Andrew Morton Tested-by: Jarkko Sakkinen Acked-by: Jarkko Sakkinen Acked-by: Song Liu Acked-by: Nathan Chancellor Acked-by: Miguel Ojeda Link: https://lkml.kernel.org/r/20201104191052.390657-1-ndesaulniers@google.com Signed-off-by: Linus Torvalds --- include/linux/compiler-clang.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index dd7233c48bf3..98cff1b4b088 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -8,8 +8,10 @@ + __clang_patchlevel__) #if CLANG_VERSION < 100001 +#ifndef __BPF_TRACING__ # error Sorry, your version of Clang is too old - please use 10.0.1 or newer. #endif +#endif /* Compiler specific definitions for Clang compiler */ -- cgit v1.2.3 From a927bd6ba952d13c52b8b385030943032f659a3e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 21 Nov 2020 22:17:05 -0800 Subject: mm: fix phys_to_target_node() and memory_add_physaddr_to_nid() exports The core-mm has a default __weak implementation of phys_to_target_node() to mirror the weak definition of memory_add_physaddr_to_nid(). That symbol is exported for modules. However, while the export in mm/memory_hotplug.c exported the symbol in the configuration cases of: CONFIG_NUMA_KEEP_MEMINFO=y CONFIG_MEMORY_HOTPLUG=y ...and: CONFIG_NUMA_KEEP_MEMINFO=n CONFIG_MEMORY_HOTPLUG=y ...it failed to export the symbol in the case of: CONFIG_NUMA_KEEP_MEMINFO=y CONFIG_MEMORY_HOTPLUG=n Not only is that broken, but Christoph points out that the kernel should not be exporting any __weak symbol, which means that memory_add_physaddr_to_nid() example that phys_to_target_node() copied is broken too. Rework the definition of phys_to_target_node() and memory_add_physaddr_to_nid() to not require weak symbols. Move to the common arch override design-pattern of an asm header defining a symbol to replace the default implementation. The only common header that all memory_add_physaddr_to_nid() producing architectures implement is asm/sparsemem.h. In fact, powerpc already defines its memory_add_physaddr_to_nid() helper in sparsemem.h. Double-down on that observation and define phys_to_target_node() where necessary in asm/sparsemem.h. An alternate consideration that was discarded was to put this override in asm/numa.h, but that entangles with the definition of MAX_NUMNODES relative to the inclusion of linux/nodemask.h, and requires powerpc to grow a new header. The dependency on NUMA_KEEP_MEMINFO for DEV_DAX_HMEM_DEVICES is invalid now that the symbol is properly exported / stubbed in all combinations of CONFIG_NUMA_KEEP_MEMINFO and CONFIG_MEMORY_HOTPLUG. [dan.j.williams@intel.com: v4] Link: https://lkml.kernel.org/r/160461461867.1505359.5301571728749534585.stgit@dwillia2-desk3.amr.corp.intel.com [dan.j.williams@intel.com: powerpc: fix create_section_mapping compile warning] Link: https://lkml.kernel.org/r/160558386174.2948926.2740149041249041764.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: a035b6bf863e ("mm/memory_hotplug: introduce default phys_to_target_node() implementation") Reported-by: Randy Dunlap Reported-by: Thomas Gleixner Reported-by: kernel test robot Reported-by: Christoph Hellwig Signed-off-by: Dan Williams Signed-off-by: Andrew Morton Tested-by: Randy Dunlap Tested-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Reviewed-by: Christoph Hellwig Cc: Joao Martins Cc: Tony Luck Cc: Fenghua Yu Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Vishal Verma Cc: Stephen Rothwell Link: https://lkml.kernel.org/r/160447639846.1133764.7044090803980177548.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/sparsemem.h | 6 ++++++ arch/powerpc/include/asm/mmzone.h | 5 +++++ arch/powerpc/include/asm/sparsemem.h | 5 ++--- arch/powerpc/mm/mem.c | 1 + arch/x86/include/asm/sparsemem.h | 10 ++++++++++ arch/x86/mm/numa.c | 2 ++ drivers/dax/Kconfig | 1 - include/linux/memory_hotplug.h | 14 -------------- include/linux/numa.h | 30 +++++++++++++++++++++++++++++- mm/memory_hotplug.c | 18 ------------------ 10 files changed, 55 insertions(+), 37 deletions(-) diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h index 336d0570e1fa..dd8c166ffd7b 100644 --- a/arch/ia64/include/asm/sparsemem.h +++ b/arch/ia64/include/asm/sparsemem.h @@ -18,4 +18,10 @@ #endif #endif /* CONFIG_SPARSEMEM */ + +#ifdef CONFIG_MEMORY_HOTPLUG +int memory_add_physaddr_to_nid(u64 addr); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif + #endif /* _ASM_IA64_SPARSEMEM_H */ diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 91c69ff53a8a..6cda76b57c5d 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -46,5 +46,10 @@ u64 memory_hotplug_max(void); #define __HAVE_ARCH_RESERVED_KERNEL_PAGES #endif +#ifdef CONFIG_MEMORY_HOTPLUG +extern int create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot); +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_MMZONE_H_ */ diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index 1e6fa371cc38..d072866842e4 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -13,9 +13,9 @@ #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_MEMORY_HOTPLUG -extern int create_section_mapping(unsigned long start, unsigned long end, - int nid, pgprot_t prot); extern int remove_section_mapping(unsigned long start, unsigned long end); +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid #ifdef CONFIG_NUMA extern int hot_add_scn_to_nid(unsigned long scn_addr); @@ -26,6 +26,5 @@ static inline int hot_add_scn_to_nid(unsigned long scn_addr) } #endif /* CONFIG_NUMA */ #endif /* CONFIG_MEMORY_HOTPLUG */ - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_SPARSEMEM_H */ diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 01ec2a252f09..3fc325bebe4d 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -50,6 +50,7 @@ #include #include #include +#include #include diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 6bfc878f6771..6a9ccc1b2be5 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -28,4 +28,14 @@ #endif #endif /* CONFIG_SPARSEMEM */ + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_NUMA_KEEP_MEMINFO +extern int phys_to_target_node(phys_addr_t start); +#define phys_to_target_node phys_to_target_node +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif +#endif /* __ASSEMBLY__ */ + #endif /* _ASM_X86_SPARSEMEM_H */ diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 44148691d78b..5eb4dc2b97da 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -938,6 +938,7 @@ int phys_to_target_node(phys_addr_t start) return meminfo_to_nid(&numa_reserved_meminfo, start); } +EXPORT_SYMBOL_GPL(phys_to_target_node); int memory_add_physaddr_to_nid(u64 start) { @@ -947,4 +948,5 @@ int memory_add_physaddr_to_nid(u64 start) nid = numa_meminfo.blk[0].nid; return nid; } +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig index 567428e10b7b..d2834c2cfa10 100644 --- a/drivers/dax/Kconfig +++ b/drivers/dax/Kconfig @@ -50,7 +50,6 @@ config DEV_DAX_HMEM Say M if unsure. config DEV_DAX_HMEM_DEVICES - depends on NUMA_KEEP_MEMINFO # for phys_to_target_node() depends on DEV_DAX_HMEM && DAX=y def_bool y diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index d65c6fdc5cfc..551093b74596 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -281,20 +281,6 @@ static inline bool movable_node_is_enabled(void) } #endif /* ! CONFIG_MEMORY_HOTPLUG */ -#ifdef CONFIG_NUMA -extern int memory_add_physaddr_to_nid(u64 start); -extern int phys_to_target_node(u64 start); -#else -static inline int memory_add_physaddr_to_nid(u64 start) -{ - return 0; -} -static inline int phys_to_target_node(u64 start) -{ - return 0; -} -#endif - #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * pgdat resizing functions diff --git a/include/linux/numa.h b/include/linux/numa.h index 8cb33ccfb671..cb44cfe2b725 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -21,13 +21,41 @@ #endif #ifdef CONFIG_NUMA +#include +#include + /* Generic implementation available */ int numa_map_to_online_node(int node); -#else + +#ifndef memory_add_physaddr_to_nid +static inline int memory_add_physaddr_to_nid(u64 start) +{ + pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +#endif +#ifndef phys_to_target_node +static inline int phys_to_target_node(u64 start) +{ + pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +#endif +#else /* !CONFIG_NUMA */ static inline int numa_map_to_online_node(int node) { return NUMA_NO_NODE; } +static inline int memory_add_physaddr_to_nid(u64 start) +{ + return 0; +} +static inline int phys_to_target_node(u64 start) +{ + return 0; +} #endif #endif /* _LINUX_NUMA_H */ diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b44d4c7ba73b..63b2e46b6555 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -350,24 +350,6 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, return err; } -#ifdef CONFIG_NUMA -int __weak memory_add_physaddr_to_nid(u64 start) -{ - pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); - -int __weak phys_to_target_node(u64 start) -{ - pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} -EXPORT_SYMBOL_GPL(phys_to_target_node); -#endif - /* find the smallest valid pfn in the range [start_pfn, end_pfn) */ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, -- cgit v1.2.3 From 4349a83a3190c1d4414371161b0f4a4c3ccd3f9d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 21 Nov 2020 22:17:08 -0800 Subject: mm: fix readahead_page_batch for retry entries Both btrfs and fuse have reported faults caused by seeing a retry entry instead of the page they were looking for. This was caused by a missing check in the iterator. As can be seen in the below panic log, the accessing 0x402 causes a panic. In the xarray.h, 0x402 means RETRY_ENTRY. BUG: kernel NULL pointer dereference, address: 0000000000000402 CPU: 14 PID: 306003 Comm: as Not tainted 5.9.0-1-amd64 #1 Debian 5.9.1-1 Hardware name: Lenovo ThinkSystem SR665/7D2VCTO1WW, BIOS D8E106Q-1.01 05/30/2020 RIP: 0010:fuse_readahead+0x152/0x470 [fuse] Code: 41 8b 57 18 4c 8d 54 10 ff 4c 89 d6 48 8d 7c 24 10 e8 d2 e3 28 f9 48 85 c0 0f 84 fe 00 00 00 44 89 f2 49 89 04 d4 44 8d 72 01 <48> 8b 10 41 8b 4f 1c 48 c1 ea 10 83 e2 01 80 fa 01 19 d2 81 e2 01 RSP: 0018:ffffad99ceaebc50 EFLAGS: 00010246 RAX: 0000000000000402 RBX: 0000000000000001 RCX: 0000000000000002 RDX: 0000000000000000 RSI: ffff94c5af90bd98 RDI: ffffad99ceaebc60 RBP: ffff94ddc1749a00 R08: 0000000000000402 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000100 R12: ffff94de6c429ce0 R13: ffff94de6c4d3700 R14: 0000000000000001 R15: ffffad99ceaebd68 FS: 00007f228c5c7040(0000) GS:ffff94de8ed80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000402 CR3: 0000001dbd9b4000 CR4: 0000000000350ee0 Call Trace: read_pages+0x83/0x270 page_cache_readahead_unbounded+0x197/0x230 generic_file_buffered_read+0x57a/0xa20 new_sync_read+0x112/0x1a0 vfs_read+0xf8/0x180 ksys_read+0x5f/0xe0 do_syscall_64+0x33/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 042124cc64c3 ("mm: add new readahead_control API") Reported-by: David Sterba Reported-by: Wonhyuk Yang Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Cc: Link: https://lkml.kernel.org/r/20201103142852.8543-1-willy@infradead.org Link: https://lkml.kernel.org/r/20201103124349.16722-1-vvghjk1234@gmail.com Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index e1e19c1f9ec9..d5570deff400 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -906,6 +906,8 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, xas_set(&xas, rac->_index); rcu_read_lock(); xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) { + if (xas_retry(&xas, page)) + continue; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; -- cgit v1.2.3 From 8faeb1ffd79593c9cd8a2a80ecdda371e3b826cb Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Sat, 21 Nov 2020 22:17:12 -0800 Subject: mm: memcg/slab: fix root memcg vmstats If we reparent the slab objects to the root memcg, when we free the slab object, we need to update the per-memcg vmstats to keep it correct for the root memcg. Now this at least affects the vmstat of NR_KERNEL_STACK_KB for !CONFIG_VMAP_STACK when the thread stack size is smaller than the PAGE_SIZE. David said: "I assume that without this fix that the root memcg's vmstat would always be inflated if we reparented" Fixes: ec9f02384f60 ("mm: workingset: fix vmstat counters for shadow nodes") Signed-off-by: Muchun Song Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Roman Gushchin Acked-by: Johannes Weiner Acked-by: David Rientjes Cc: Michal Hocko Cc: Vladimir Davydov Cc: Christopher Lameter Cc: Pekka Enberg Cc: Joonsoo Kim Cc: Roman Gushchin Cc: Vlastimil Babka Cc: Yafang Shao Cc: Chris Down Cc: [5.3+] Link: https://lkml.kernel.org/r/20201110031015.15715-1-songmuchun@bytedance.com Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3dcbf24d2227..29459a6ce1c7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -867,8 +867,13 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) rcu_read_lock(); memcg = mem_cgroup_from_obj(p); - /* Untracked pages have no memcg, no lruvec. Update only the node */ - if (!memcg || memcg == root_mem_cgroup) { + /* + * Untracked pages have no memcg, no lruvec. Update only the + * node. If we reparent the slab objects to the root memcg, + * when we free the slab object, we need to update the per-memcg + * vmstats to keep it correct for the root memcg. + */ + if (!memcg) { __mod_node_page_state(pgdat, idx, val); } else { lruvec = mem_cgroup_lruvec(memcg, pgdat); -- cgit v1.2.3 From bfe8cc1db02ab243c62780f17fc57f65bde0afe1 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Sat, 21 Nov 2020 22:17:15 -0800 Subject: mm/userfaultfd: do not access vma->vm_mm after calling handle_userfault() Alexander reported a syzkaller / KASAN finding on s390, see below for complete output. In do_huge_pmd_anonymous_page(), the pre-allocated pagetable will be freed in some cases. In the case of userfaultfd_missing(), this will happen after calling handle_userfault(), which might have released the mmap_lock. Therefore, the following pte_free(vma->vm_mm, pgtable) will access an unstable vma->vm_mm, which could have been freed or re-used already. For all architectures other than s390 this will go w/o any negative impact, because pte_free() simply frees the page and ignores the passed-in mm. The implementation for SPARC32 would also access mm->page_table_lock for pte_free(), but there is no THP support in SPARC32, so the buggy code path will not be used there. For s390, the mm->context.pgtable_list is being used to maintain the 2K pagetable fragments, and operating on an already freed or even re-used mm could result in various more or less subtle bugs due to list / pagetable corruption. Fix this by calling pte_free() before handle_userfault(), similar to how it is already done in __do_huge_pmd_anonymous_page() for the WRITE / non-huge_zero_page case. Commit 6b251fc96cf2c ("userfaultfd: call handle_userfault() for userfaultfd_missing() faults") actually introduced both, the do_huge_pmd_anonymous_page() and also __do_huge_pmd_anonymous_page() changes wrt to calling handle_userfault(), but only in the latter case it put the pte_free() before calling handle_userfault(). BUG: KASAN: use-after-free in do_huge_pmd_anonymous_page+0xcda/0xd90 mm/huge_memory.c:744 Read of size 8 at addr 00000000962d6988 by task syz-executor.0/9334 CPU: 1 PID: 9334 Comm: syz-executor.0 Not tainted 5.10.0-rc1-syzkaller-07083-g4c9720875573 #0 Hardware name: IBM 3906 M04 701 (KVM/Linux) Call Trace: do_huge_pmd_anonymous_page+0xcda/0xd90 mm/huge_memory.c:744 create_huge_pmd mm/memory.c:4256 [inline] __handle_mm_fault+0xe6e/0x1068 mm/memory.c:4480 handle_mm_fault+0x288/0x748 mm/memory.c:4607 do_exception+0x394/0xae0 arch/s390/mm/fault.c:479 do_dat_exception+0x34/0x80 arch/s390/mm/fault.c:567 pgm_check_handler+0x1da/0x22c arch/s390/kernel/entry.S:706 copy_from_user_mvcos arch/s390/lib/uaccess.c:111 [inline] raw_copy_from_user+0x3a/0x88 arch/s390/lib/uaccess.c:174 _copy_from_user+0x48/0xa8 lib/usercopy.c:16 copy_from_user include/linux/uaccess.h:192 [inline] __do_sys_sigaltstack kernel/signal.c:4064 [inline] __s390x_sys_sigaltstack+0xc8/0x240 kernel/signal.c:4060 system_call+0xe0/0x28c arch/s390/kernel/entry.S:415 Allocated by task 9334: slab_alloc_node mm/slub.c:2891 [inline] slab_alloc mm/slub.c:2899 [inline] kmem_cache_alloc+0x118/0x348 mm/slub.c:2904 vm_area_dup+0x9c/0x2b8 kernel/fork.c:356 __split_vma+0xba/0x560 mm/mmap.c:2742 split_vma+0xca/0x108 mm/mmap.c:2800 mlock_fixup+0x4ae/0x600 mm/mlock.c:550 apply_vma_lock_flags+0x2c6/0x398 mm/mlock.c:619 do_mlock+0x1aa/0x718 mm/mlock.c:711 __do_sys_mlock2 mm/mlock.c:738 [inline] __s390x_sys_mlock2+0x86/0xa8 mm/mlock.c:728 system_call+0xe0/0x28c arch/s390/kernel/entry.S:415 Freed by task 9333: slab_free mm/slub.c:3142 [inline] kmem_cache_free+0x7c/0x4b8 mm/slub.c:3158 __vma_adjust+0x7b2/0x2508 mm/mmap.c:960 vma_merge+0x87e/0xce0 mm/mmap.c:1209 userfaultfd_release+0x412/0x6b8 fs/userfaultfd.c:868 __fput+0x22c/0x7a8 fs/file_table.c:281 task_work_run+0x200/0x320 kernel/task_work.c:151 tracehook_notify_resume include/linux/tracehook.h:188 [inline] do_notify_resume+0x100/0x148 arch/s390/kernel/signal.c:538 system_call+0xe6/0x28c arch/s390/kernel/entry.S:416 The buggy address belongs to the object at 00000000962d6948 which belongs to the cache vm_area_struct of size 200 The buggy address is located 64 bytes inside of 200-byte region [00000000962d6948, 00000000962d6a10) The buggy address belongs to the page: page:00000000313a09fe refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x962d6 flags: 0x3ffff00000000200(slab) raw: 3ffff00000000200 000040000257e080 0000000c0000000c 000000008020ba00 raw: 0000000000000000 000f001e00000000 ffffffff00000001 0000000096959501 page dumped because: kasan: bad access detected page->mem_cgroup:0000000096959501 Memory state around the buggy address: 00000000962d6880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00000000962d6900: 00 fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb >00000000962d6980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ 00000000962d6a00: fb fb fc fc fc fc fc fc fc fc 00 00 00 00 00 00 00000000962d6a80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ================================================================== Fixes: 6b251fc96cf2c ("userfaultfd: call handle_userfault() for userfaultfd_missing() faults") Reported-by: Alexander Egorenkov Signed-off-by: Gerald Schaefer Signed-off-by: Andrew Morton Cc: Andrea Arcangeli Cc: Heiko Carstens Cc: [4.3+] Link: https://lkml.kernel.org/r/20201110190329.11920-1-gerald.schaefer@linux.ibm.com Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9474dbc150ed..ec2bb93f7431 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -710,7 +710,6 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) transparent_hugepage_use_zero_page()) { pgtable_t pgtable; struct page *zero_page; - bool set; vm_fault_t ret; pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) @@ -723,25 +722,25 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); ret = 0; - set = false; if (pmd_none(*vmf->pmd)) { ret = check_stable_address_space(vma->vm_mm); if (ret) { spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); } else if (userfaultfd_missing(vma)) { spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); } else { set_huge_zero_page(pgtable, vma->vm_mm, vma, haddr, vmf->pmd, zero_page); spin_unlock(vmf->ptl); - set = true; } - } else + } else { spin_unlock(vmf->ptl); - if (!set) pte_free(vma->vm_mm, pgtable); + } return ret; } gfp = alloc_hugepage_direct_gfpmask(vma); -- cgit v1.2.3 From 488dac0c9237647e9b8f788b6a342595bfa40bda Mon Sep 17 00:00:00 2001 From: Yicong Yang Date: Sat, 21 Nov 2020 22:17:19 -0800 Subject: libfs: fix error cast of negative value in simple_attr_write() The attr->set() receive a value of u64, but simple_strtoll() is used for doing the conversion. It will lead to the error cast if user inputs a negative value. Use kstrtoull() instead of simple_strtoll() to convert a string got from the user to an unsigned value. The former will return '-EINVAL' if it gets a negetive value, but the latter can't handle the situation correctly. Make 'val' unsigned long long as what kstrtoull() takes, this will eliminate the compile warning on no 64-bit architectures. Fixes: f7b88631a897 ("fs/libfs.c: fix simple_attr_write() on 32bit machines") Signed-off-by: Yicong Yang Signed-off-by: Andrew Morton Cc: Al Viro Link: https://lkml.kernel.org/r/1605341356-11872-1-git-send-email-yangyicong@hisilicon.com Signed-off-by: Linus Torvalds --- fs/libfs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/libfs.c b/fs/libfs.c index fc34361c1489..7124c2e8df2f 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -959,7 +959,7 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { struct simple_attr *attr; - u64 val; + unsigned long long val; size_t size; ssize_t ret; @@ -977,7 +977,9 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, goto out; attr->set_buf[size] = '\0'; - val = simple_strtoll(attr->set_buf, NULL, 0); + ret = kstrtoull(attr->set_buf, 0, &val); + if (ret) + goto out; ret = attr->set(attr->data, val); if (ret == 0) ret = len; /* on success, claim we got the whole input */ -- cgit v1.2.3 From 66383800df9cbdbf3b0c34d5a51bf35bcdb72fd2 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 21 Nov 2020 22:17:22 -0800 Subject: mm: fix madvise WILLNEED performance problem The calculation of the end page index was incorrect, leading to a regression of 70% when running stress-ng. With this fix, we instead see a performance improvement of 3%. Fixes: e6e88712e43b ("mm: optimise madvise WILLNEED") Reported-by: kernel test robot Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Tested-by: Xing Zhengjun Acked-by: Johannes Weiner Cc: William Kucharski Cc: Feng Tang Cc: "Chen, Rong A" Link: https://lkml.kernel.org/r/20201109134851.29692-1-willy@infradead.org Signed-off-by: Linus Torvalds --- mm/madvise.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/madvise.c b/mm/madvise.c index 7e773f949ef9..a8d8d48a57fe 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -226,7 +226,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, struct address_space *mapping) { XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start)); - pgoff_t end_index = end / PAGE_SIZE; + pgoff_t end_index = linear_page_index(vma, end + PAGE_SIZE - 1); struct page *page; rcu_read_lock(); -- cgit v1.2.3 From a9e5c87ca7443d09fb530fffa4d96ce1c76dbe4d Mon Sep 17 00:00:00 2001 From: David Howells Date: Sun, 22 Nov 2020 13:13:45 +0000 Subject: afs: Fix speculative status fetch going out of order wrt to modifications When doing a lookup in a directory, the afs filesystem uses a bulk status fetch to speculatively retrieve the statuses of up to 48 other vnodes found in the same directory and it will then either update extant inodes or create new ones - effectively doing 'lookup ahead'. To avoid the possibility of deadlocking itself, however, the filesystem doesn't lock all of those inodes; rather just the directory inode is locked (by the VFS). When the operation completes, afs_inode_init_from_status() or afs_apply_status() is called, depending on whether the inode already exists, to commit the new status. A case exists, however, where the speculative status fetch operation may straddle a modification operation on one of those vnodes. What can then happen is that the speculative bulk status RPC retrieves the old status, and whilst that is happening, the modification happens - which returns an updated status, then the modification status is committed, then we attempt to commit the speculative status. This results in something like the following being seen in dmesg: kAFS: vnode modified {100058:861} 8->9 YFS.InlineBulkStatus showing that for vnode 861 on volume 100058, we saw YFS.InlineBulkStatus say that the vnode had data version 8 when we'd already recorded version 9 due to a local modification. This was causing the cache to be invalidated for that vnode when it shouldn't have been. If it happens on a data file, this might lead to local changes being lost. Fix this by ignoring speculative status updates if the data version doesn't match the expected value. Note that it is possible to get a DV regression if a volume gets restored from a backup - but we should get a callback break in such a case that should trigger a recheck anyway. It might be worth checking the volume creation time in the volsync info and, if a change is observed in that (as would happen on a restore), invalidate all caches associated with the volume. Fixes: 5cf9dd55a0ec ("afs: Prospectively look up extra files when doing a single lookup") Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- fs/afs/dir.c | 1 + fs/afs/inode.c | 8 ++++++++ fs/afs/internal.h | 1 + 3 files changed, 10 insertions(+) diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 1bb5b9d7f0a2..9068d5578a26 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -823,6 +823,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, vp->cb_break_before = afs_calc_vnode_cb_break(vnode); vp->vnode = vnode; vp->put_vnode = true; + vp->speculative = true; /* vnode not locked */ } } } diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 0fe8844b4bee..b0d7b892090d 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -294,6 +294,13 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v op->flags &= ~AFS_OPERATION_DIR_CONFLICT; } } else if (vp->scb.have_status) { + if (vp->dv_before + vp->dv_delta != vp->scb.status.data_version && + vp->speculative) + /* Ignore the result of a speculative bulk status fetch + * if it splits around a modification op, thereby + * appearing to regress the data version. + */ + goto out; afs_apply_status(op, vp); if (vp->scb.have_cb) afs_apply_callback(op, vp); @@ -305,6 +312,7 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v } } +out: write_sequnlock(&vnode->cb_lock); if (vp->scb.have_status) diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 14d5d75f4b6e..0d150a29e39e 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -755,6 +755,7 @@ struct afs_vnode_param { bool update_ctime:1; /* Need to update the ctime */ bool set_size:1; /* Must update i_size */ bool op_unlinked:1; /* True if file was unlinked by op */ + bool speculative:1; /* T if speculative status fetch (no vnode lock) */ }; /* -- cgit v1.2.3 From 418baf2c28f3473039f2f7377760bd8f6897ae18 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 22 Nov 2020 15:36:08 -0800 Subject: Linux 5.10-rc5 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index e2c3f65c4721..ed081e3eb800 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Kleptomaniac Octopus # *DOCUMENTATION* -- cgit v1.2.3 From e2d3d2e904ad3d381753798dcd5cae03e3c47242 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 16 Nov 2020 18:53:00 +0100 Subject: drm/exynos: depend on COMMON_CLK to fix compile tests The Exynos DRM uses Common Clock Framework thus it cannot be built on platforms without it (e.g. compile test on MIPS with RALINK and SOC_RT305X): /usr/bin/mips-linux-gnu-ld: drivers/gpu/drm/exynos/exynos_mixer.o: in function `mixer_bind': exynos_mixer.c:(.text+0x958): undefined reference to `clk_set_parent' Reported-by: kernel test robot Signed-off-by: Krzysztof Kozlowski Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig index 6417f374b923..951d5f708e92 100644 --- a/drivers/gpu/drm/exynos/Kconfig +++ b/drivers/gpu/drm/exynos/Kconfig @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only config DRM_EXYNOS tristate "DRM Support for Samsung SoC Exynos Series" - depends on OF && DRM && (ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM || COMPILE_TEST) + depends on OF && DRM && COMMON_CLK + depends on ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM || COMPILE_TEST depends on MMU select DRM_KMS_HELPER select VIDEOMODE_HELPERS -- cgit v1.2.3 From f943849f720689214abb3930623c31ff91990be9 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 20 Nov 2020 10:12:52 +0000 Subject: cpufreq: scmi: Fix build for !CONFIG_COMMON_CLK Commit 8410e7f3b31e ("cpufreq: scmi: Fix OPP addition failure with a dummy clock provider") registers a dummy clock provider using devm_of_clk_add_hw_provider. These *_hw_provider functions are defined only when CONFIG_COMMON_CLK=y. One possible fix is to add the Kconfig dependency, but since we plan to move away from the clock dependency for scmi cpufreq, it is preferrable to avoid that. Let us just conditionally compile out the offending call to devm_of_clk_add_hw_provider. It also uses the variable 'dev' outside of the #ifdef block to avoid build warning. Fixes: 8410e7f3b31e ("cpufreq: scmi: Fix OPP addition failure with a dummy clock provider") Cc: Rafael J. Wysocki Cc: Viresh Kumar Signed-off-by: Sudeep Holla Signed-off-by: Viresh Kumar --- drivers/cpufreq/scmi-cpufreq.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 78318508a6d6..8286205c7165 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -236,13 +236,15 @@ static int scmi_cpufreq_probe(struct scmi_device *sdev) if (!handle || !handle->perf_ops) return -ENODEV; +#ifdef CONFIG_COMMON_CLK /* dummy clock provider as needed by OPP if clocks property is used */ if (of_find_property(dev->of_node, "#clock-cells", NULL)) devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL); +#endif ret = cpufreq_register_driver(&scmi_cpufreq_driver); if (ret) { - dev_err(&sdev->dev, "%s: registering cpufreq failed, err: %d\n", + dev_err(dev, "%s: registering cpufreq failed, err: %d\n", __func__, ret); } -- cgit v1.2.3 From b6b79dd53082db11070b4368d85dd6699ff0b063 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Mon, 23 Nov 2020 18:40:16 +1100 Subject: powerpc/64s: Fix allnoconfig build since uaccess flush Using DECLARE_STATIC_KEY_FALSE needs linux/jump_table.h. Otherwise the build fails with eg: arch/powerpc/include/asm/book3s/64/kup-radix.h:66:1: warning: data definition has no type or storage class 66 | DECLARE_STATIC_KEY_FALSE(uaccess_flush_key); Fixes: 9a32a7e78bd0 ("powerpc/64s: flush L1D after user accesses") Signed-off-by: Stephen Rothwell [mpe: Massage change log] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201123184016.693fe464@canb.auug.org.au --- arch/powerpc/include/asm/book3s/64/kup-radix.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h index 28716e2f13e3..a39e2d193fdc 100644 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -63,6 +63,8 @@ #else /* !__ASSEMBLY__ */ +#include + DECLARE_STATIC_KEY_FALSE(uaccess_flush_key); #ifdef CONFIG_PPC_KUAP -- cgit v1.2.3 From 1179f170b6f0af7bb0b3b7628136eaac450ddf31 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Fri, 20 Nov 2020 14:17:52 +0100 Subject: s390: fix fpu restore in entry.S We need to disable interrupts in load_fpu_regs(). Otherwise an interrupt might come in after the registers are loaded, but before CIF_FPU is cleared in load_fpu_regs(). When the interrupt returns, CIF_FPU will be cleared and the registers will never be restored. The entry.S code usually saves the interrupt state in __SF_EMPTY on the stack when disabling/restoring interrupts. sie64a however saves the pointer to the sie control block in __SF_SIE_CONTROL, which references the same location. This is non-obvious to the reader. To avoid thrashing the sie control block pointer in load_fpu_regs(), move the __SIE_* offsets eight bytes after __SF_EMPTY on the stack. Cc: # 5.8 Fixes: 0b0ed657fe00 ("s390: remove critical section cleanup from entry.S") Reported-by: Pierre Morel Signed-off-by: Sven Schnelle Acked-by: Christian Borntraeger Reviewed-by: Heiko Carstens Signed-off-by: Heiko Carstens --- arch/s390/kernel/asm-offsets.c | 10 +++++----- arch/s390/kernel/entry.S | 2 ++ 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 2012c1cf0853..483051e10db3 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -53,11 +53,11 @@ int main(void) /* stack_frame offsets */ OFFSET(__SF_BACKCHAIN, stack_frame, back_chain); OFFSET(__SF_GPRS, stack_frame, gprs); - OFFSET(__SF_EMPTY, stack_frame, empty1); - OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[0]); - OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[1]); - OFFSET(__SF_SIE_REASON, stack_frame, empty1[2]); - OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[3]); + OFFSET(__SF_EMPTY, stack_frame, empty1[0]); + OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[1]); + OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[2]); + OFFSET(__SF_SIE_REASON, stack_frame, empty1[3]); + OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[4]); BLANK(); OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val); BLANK(); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 5346545b9860..26bb0603c5a1 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -1068,6 +1068,7 @@ EXPORT_SYMBOL(save_fpu_regs) * %r4 */ load_fpu_regs: + stnsm __SF_EMPTY(%r15),0xfc lg %r4,__LC_CURRENT aghi %r4,__TASK_thread TSTMSK __LC_CPU_FLAGS,_CIF_FPU @@ -1099,6 +1100,7 @@ load_fpu_regs: .Lload_fpu_regs_done: ni __LC_CPU_FLAGS+7,255-_CIF_FPU .Lload_fpu_regs_exit: + ssm __SF_EMPTY(%r15) BR_EX %r14 .Lload_fpu_regs_end: ENDPROC(load_fpu_regs) -- cgit v1.2.3 From 03659efe4287230b1d65b31c993708f335c8de82 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 22 Nov 2020 20:45:10 -0800 Subject: arm64/fpsimd: add to to fix fpsimd build Adding brought in which uses , which uses 'pstate_check_t' so the latter needs to #include for this typedef. Fixes this build error: In file included from arch/arm64/include/asm/kprobes.h:24, from arch/arm64/include/asm/exception.h:11, from arch/arm64/kernel/fpsimd.c:35: arch/arm64/include/asm/probes.h:16:2: error: unknown type name 'pstate_check_t' 16 | pstate_check_t *pstate_cc; Fixes: c6b90d5cf637 ("arm64/fpsimd: Fix missing-prototypes in fpsimd.c") Reported-by: kernel test robot Signed-off-by: Randy Dunlap Cc: Will Deacon Cc: Tian Tao Link: https://lore.kernel.org/r/20201123044510.9942-1-rdunlap@infradead.org Signed-off-by: Will Deacon --- arch/arm64/include/asm/probes.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/probes.h b/arch/arm64/include/asm/probes.h index 4266262101fe..006946745352 100644 --- a/arch/arm64/include/asm/probes.h +++ b/arch/arm64/include/asm/probes.h @@ -7,6 +7,8 @@ #ifndef _ARM_PROBES_H #define _ARM_PROBES_H +#include + typedef u32 probe_opcode_t; typedef void (probes_handler_t) (u32 opcode, long addr, struct pt_regs *); -- cgit v1.2.3 From 774c4a3b5e5fd897909e24c0f7dd4c6579da833f Mon Sep 17 00:00:00 2001 From: Shiju Jose Date: Wed, 14 Oct 2020 10:31:39 +0100 Subject: ACPI/IORT: Fix doc warnings in iort.c Fix following warnings caused by mismatch between function parameters and function comments. drivers/acpi/arm64/iort.c:55: warning: Function parameter or member 'iort_node' not described in 'iort_set_fwnode' drivers/acpi/arm64/iort.c:55: warning: Excess function parameter 'node' description in 'iort_set_fwnode' drivers/acpi/arm64/iort.c:682: warning: Function parameter or member 'id' not described in 'iort_get_device_domain' drivers/acpi/arm64/iort.c:682: warning: Function parameter or member 'bus_token' not described in 'iort_get_device_domain' drivers/acpi/arm64/iort.c:682: warning: Excess function parameter 'req_id' description in 'iort_get_device_domain' drivers/acpi/arm64/iort.c:1142: warning: Function parameter or member 'dma_size' not described in 'iort_dma_setup' drivers/acpi/arm64/iort.c:1142: warning: Excess function parameter 'size' description in 'iort_dma_setup' drivers/acpi/arm64/iort.c:1534: warning: Function parameter or member 'ops' not described in 'iort_add_platform_device' Signed-off-by: Shiju Jose Acked-by: Hanjun Guo Acked-by: Lorenzo Pieralisi Link: https://lore.kernel.org/r/20201014093139.1580-1-shiju.jose@huawei.com Signed-off-by: Will Deacon --- drivers/acpi/arm64/iort.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 9929ff50c0c0..770d84071a32 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -44,7 +44,7 @@ static DEFINE_SPINLOCK(iort_fwnode_lock); * iort_set_fwnode() - Create iort_fwnode and use it to register * iommu data in the iort_fwnode_list * - * @node: IORT table node associated with the IOMMU + * @iort_node: IORT table node associated with the IOMMU * @fwnode: fwnode associated with the IORT node * * Returns: 0 on success @@ -673,7 +673,8 @@ static int iort_dev_find_its_id(struct device *dev, u32 id, /** * iort_get_device_domain() - Find MSI domain related to a device * @dev: The device. - * @req_id: Requester ID for the device. + * @id: Requester ID for the device. + * @bus_token: irq domain bus token. * * Returns: the MSI domain for this device, NULL otherwise */ @@ -1136,7 +1137,7 @@ static int rc_dma_get_range(struct device *dev, u64 *size) * * @dev: device to configure * @dma_addr: device DMA address result pointer - * @size: DMA range size result pointer + * @dma_size: DMA range size result pointer */ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size) { @@ -1526,6 +1527,7 @@ static __init const struct iort_dev_config *iort_get_dev_cfg( /** * iort_add_platform_device() - Allocate a platform device for IORT node * @node: Pointer to device ACPI IORT node + * @ops: Pointer to IORT device config struct * * Returns: 0 on success, <0 failure */ -- cgit v1.2.3 From 178648916e73e00de83150eb0c90c0d3a977a46a Mon Sep 17 00:00:00 2001 From: Marek Majtyka Date: Fri, 20 Nov 2020 16:14:43 +0100 Subject: xsk: Fix incorrect netdev reference count Fix incorrect netdev reference count in xsk_bind operation. Incorrect reference count of the device appears when a user calls bind with the XDP_ZEROCOPY flag on an interface which does not support zero-copy. In such a case, an error is returned but the reference count is not decreased. This change fixes the fault, by decreasing the reference count in case of such an error. The problem being corrected appeared in '162c820ed896' for the first time, and the code was moved to new file location over the time with commit 'c2d3d6a47462'. This specific patch applies to all version starting from 'c2d3d6a47462'. The same solution should be applied but on different file (net/xdp/xdp_umem.c) and function (xdp_umem_assign_dev) for versions from '162c820ed896' to 'c2d3d6a47462' excluded. Fixes: 162c820ed896 ("xdp: hold device for umem regardless of zero-copy mode") Signed-off-by: Marek Majtyka Signed-off-by: Daniel Borkmann Acked-by: Magnus Karlsson Link: https://lore.kernel.org/bpf/20201120151443.105903-1-marekx.majtyka@intel.com --- net/xdp/xsk_buff_pool.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 3c5a1423d922..9287eddec52c 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -185,8 +185,10 @@ err_unreg_xsk: err_unreg_pool: if (!force_zc) err = 0; /* fallback to copy mode */ - if (err) + if (err) { xsk_clear_pool_at_qid(netdev, queue_id); + dev_put(netdev); + } return err; } -- cgit v1.2.3 From 6d39bdee238f9799718653a9d4d61ebf2922e23d Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 5 Nov 2020 14:58:32 +0000 Subject: iommu/amd: Enforce 4k mapping for certain IOMMU data structures AMD IOMMU requires 4k-aligned pages for the event log, the PPR log, and the completion wait write-back regions. However, when allocating the pages, they could be part of large mapping (e.g. 2M) page. This causes #PF due to the SNP RMP hardware enforces the check based on the page level for these data structures. So, fix by calling set_memory_4k() on the allocated pages. Fixes: c69d89aff393 ("iommu/amd: Use 4K page for completion wait write-back semaphore") Signed-off-by: Suravee Suthikulpanit Cc: Brijesh Singh Link: https://lore.kernel.org/r/20201105145832.3065-1-suravee.suthikulpanit@amd.com Signed-off-by: Will Deacon --- drivers/iommu/amd/init.c | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 82e4af8f09bb..23a790f8f550 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -29,6 +29,7 @@ #include #include #include +#include #include @@ -672,11 +673,27 @@ static void __init free_command_buffer(struct amd_iommu *iommu) free_pages((unsigned long)iommu->cmd_buf, get_order(CMD_BUFFER_SIZE)); } +static void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu, + gfp_t gfp, size_t size) +{ + int order = get_order(size); + void *buf = (void *)__get_free_pages(gfp, order); + + if (buf && + iommu_feature(iommu, FEATURE_SNP) && + set_memory_4k((unsigned long)buf, (1 << order))) { + free_pages((unsigned long)buf, order); + buf = NULL; + } + + return buf; +} + /* allocates the memory where the IOMMU will log its events to */ static int __init alloc_event_buffer(struct amd_iommu *iommu) { - iommu->evt_buf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - get_order(EVT_BUFFER_SIZE)); + iommu->evt_buf = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, + EVT_BUFFER_SIZE); return iommu->evt_buf ? 0 : -ENOMEM; } @@ -715,8 +732,8 @@ static void __init free_event_buffer(struct amd_iommu *iommu) /* allocates the memory where the IOMMU will log its events to */ static int __init alloc_ppr_log(struct amd_iommu *iommu) { - iommu->ppr_log = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - get_order(PPR_LOG_SIZE)); + iommu->ppr_log = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, + PPR_LOG_SIZE); return iommu->ppr_log ? 0 : -ENOMEM; } @@ -838,7 +855,7 @@ static int iommu_init_ga(struct amd_iommu *iommu) static int __init alloc_cwwb_sem(struct amd_iommu *iommu) { - iommu->cmd_sem = (void *)get_zeroed_page(GFP_KERNEL); + iommu->cmd_sem = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, 1); return iommu->cmd_sem ? 0 : -ENOMEM; } -- cgit v1.2.3 From c0a2074ac575fff2848c8ef804bdc8590466c36c Mon Sep 17 00:00:00 2001 From: Wenbin Mei Date: Wed, 18 Nov 2020 14:34:05 +0800 Subject: mmc: mediatek: Fix system suspend/resume support for CQHCI Before we got these errors on MT8192 platform: [ 59.153891] Restarting tasks ... [ 59.154540] done. [ 59.159175] PM: suspend exit [ 59.218724] mtk-msdc 11f60000.mmc: phase: [map:fffffffe] [maxlen:31] [final:16] [ 119.776083] mmc0: cqhci: timeout for tag 9 [ 119.780196] mmc0: cqhci: ============ CQHCI REGISTER DUMP =========== [ 119.786709] mmc0: cqhci: Caps: 0x100020b6 | Version: 0x00000510 [ 119.793225] mmc0: cqhci: Config: 0x00000101 | Control: 0x00000000 [ 119.799706] mmc0: cqhci: Int stat: 0x00000000 | Int enab: 0x00000000 [ 119.806177] mmc0: cqhci: Int sig: 0x00000000 | Int Coal: 0x00000000 [ 119.812670] mmc0: cqhci: TDL base: 0x00000000 | TDL up32: 0x00000000 [ 119.819149] mmc0: cqhci: Doorbell: 0x003ffc00 | TCN: 0x00000200 [ 119.825656] mmc0: cqhci: Dev queue: 0x00000000 | Dev Pend: 0x00000000 [ 119.832155] mmc0: cqhci: Task clr: 0x00000000 | SSC1: 0x00001000 [ 119.838627] mmc0: cqhci: SSC2: 0x00000000 | DCMD rsp: 0x00000000 [ 119.845174] mmc0: cqhci: RED mask: 0xfdf9a080 | TERRI: 0x0000891c [ 119.851654] mmc0: cqhci: Resp idx: 0x00000000 | Resp arg: 0x00000000 [ 119.865773] mmc0: cqhci: : =========================================== [ 119.872358] mmc0: running CQE recovery From these logs, we found TDL base was back to the default value. After suspend, the mmc host is powered off by HW, and bring CQE register to the default value, so we add system suspend/resume interface, then bring CQE to deactivated state before suspend, it will be enabled by CQE first request after resume. Signed-off-by: Wenbin Mei Link: https://lore.kernel.org/r/20201118063405.24906-1-wenbin.mei@mediatek.com Fixes: 88bd652b3c74 ("mmc: mediatek: command queue support") Cc: stable@vger.kernel.org [Ulf: Renamed functions] Signed-off-by: Ulf Hansson --- drivers/mmc/host/mtk-sd.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index a704745e5882..b40ec966288e 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -2681,11 +2681,29 @@ static int msdc_runtime_resume(struct device *dev) msdc_restore_reg(host); return 0; } + +static int msdc_suspend(struct device *dev) +{ + struct mmc_host *mmc = dev_get_drvdata(dev); + int ret; + + if (mmc->caps2 & MMC_CAP2_CQE) { + ret = cqhci_suspend(mmc); + if (ret) + return ret; + } + + return pm_runtime_force_suspend(dev); +} + +static int msdc_resume(struct device *dev) +{ + return pm_runtime_force_resume(dev); +} #endif static const struct dev_pm_ops msdc_dev_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, - pm_runtime_force_resume) + SET_SYSTEM_SLEEP_PM_OPS(msdc_suspend, msdc_resume) SET_RUNTIME_PM_OPS(msdc_runtime_suspend, msdc_runtime_resume, NULL) }; -- cgit v1.2.3 From 71d80563b0760a411cd90a3680536f5d887fff6b Mon Sep 17 00:00:00 2001 From: Ran Wang Date: Mon, 23 Nov 2020 10:57:15 +0800 Subject: spi: spi-nxp-fspi: fix fspi panic by unexpected interrupts Given the case that bootloader(such as UEFI)'s FSPI driver might not handle all interrupts before loading kernel, those legacy interrupts would assert immidiately once kernel's FSPI driver enable them. Further, if it was FSPI_INTR_IPCMDDONE, the irq handler nxp_fspi_irq_handler() would call complete(&f->c) to notify others. However, f->c might not be initialized yet at that time, then cause kernel panic. Of cause, we should fix this issue within bootloader. But it would be better to have this pacth to make dirver more robust (by clearing all interrupt status bits before enabling interrupts). Suggested-by: Han Xu Signed-off-by: Ran Wang Link: https://lore.kernel.org/r/20201123025715.14635-1-ran.wang_1@nxp.com Signed-off-by: Mark Brown --- drivers/spi/spi-nxp-fspi.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c index 0d41406c036d..ab9035662717 100644 --- a/drivers/spi/spi-nxp-fspi.c +++ b/drivers/spi/spi-nxp-fspi.c @@ -1001,6 +1001,7 @@ static int nxp_fspi_probe(struct platform_device *pdev) struct resource *res; struct nxp_fspi *f; int ret; + u32 reg; ctlr = spi_alloc_master(&pdev->dev, sizeof(*f)); if (!ctlr) @@ -1032,6 +1033,12 @@ static int nxp_fspi_probe(struct platform_device *pdev) goto err_put_ctrl; } + /* Clear potential interrupts */ + reg = fspi_readl(f, f->iobase + FSPI_INTR); + if (reg) + fspi_writel(f, reg, f->iobase + FSPI_INTR); + + /* find the resources - controller memory mapped space */ if (is_acpi_node(f->dev->fwnode)) res = platform_get_resource(pdev, IORESOURCE_MEM, 1); -- cgit v1.2.3 From 72b55c96f3a5ae6e486c20b5dacf5114060ed042 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 12 Nov 2020 22:05:19 +0000 Subject: arm-smmu-qcom: Ensure the qcom_scm driver has finished probing Robin Murphy pointed out that if the arm-smmu driver probes before the qcom_scm driver, we may call qcom_scm_qsmmu500_wait_safe_toggle() before the __scm is initialized. Now, getting this to happen is a bit contrived, as in my efforts it required enabling asynchronous probing for both drivers, moving the firmware dts node to the end of the dtsi file, as well as forcing a long delay in the qcom_scm_probe function. With those tweaks we ran into the following crash: [ 2.631040] arm-smmu 15000000.iommu: Stage-1: 48-bit VA -> 48-bit IPA [ 2.633372] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 ... [ 2.633402] [0000000000000000] user address but active_mm is swapper [ 2.633409] Internal error: Oops: 96000005 [#1] PREEMPT SMP [ 2.633415] Modules linked in: [ 2.633427] CPU: 5 PID: 117 Comm: kworker/u16:2 Tainted: G W 5.10.0-rc1-mainline-00025-g272a618fc36-dirty #3971 [ 2.633430] Hardware name: Thundercomm Dragonboard 845c (DT) [ 2.633448] Workqueue: events_unbound async_run_entry_fn [ 2.633456] pstate: 80c00005 (Nzcv daif +PAN +UAO -TCO BTYPE=--) [ 2.633465] pc : qcom_scm_qsmmu500_wait_safe_toggle+0x78/0xb0 [ 2.633473] lr : qcom_smmu500_reset+0x58/0x78 [ 2.633476] sp : ffffffc0105a3b60 ... [ 2.633567] Call trace: [ 2.633572] qcom_scm_qsmmu500_wait_safe_toggle+0x78/0xb0 [ 2.633576] qcom_smmu500_reset+0x58/0x78 [ 2.633581] arm_smmu_device_reset+0x194/0x270 [ 2.633585] arm_smmu_device_probe+0xc94/0xeb8 [ 2.633592] platform_drv_probe+0x58/0xa8 [ 2.633597] really_probe+0xec/0x398 [ 2.633601] driver_probe_device+0x5c/0xb8 [ 2.633606] __driver_attach_async_helper+0x64/0x88 [ 2.633610] async_run_entry_fn+0x4c/0x118 [ 2.633617] process_one_work+0x20c/0x4b0 [ 2.633621] worker_thread+0x48/0x460 [ 2.633628] kthread+0x14c/0x158 [ 2.633634] ret_from_fork+0x10/0x18 [ 2.633642] Code: a9034fa0 d0007f73 29107fa0 91342273 (f9400020) To avoid this, this patch adds a check on qcom_scm_is_available() in the qcom_smmu_impl_init() function, returning -EPROBE_DEFER if its not ready. This allows the driver to try to probe again later after qcom_scm has finished probing. Reported-by: Robin Murphy Signed-off-by: John Stultz Reviewed-by: Robin Murphy Cc: Robin Murphy Cc: Will Deacon Cc: Andy Gross Cc: Maulik Shah Cc: Bjorn Andersson Cc: Saravana Kannan Cc: Marc Zyngier Cc: Lina Iyer Cc: iommu@lists.linux-foundation.org Cc: linux-arm-msm Link: https://lore.kernel.org/r/20201112220520.48159-1-john.stultz@linaro.org Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index be4318044f96..702fbaa6c9ad 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -69,6 +69,10 @@ struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu) { struct qcom_smmu *qsmmu; + /* Check to make sure qcom_scm has finished probing */ + if (!qcom_scm_is_available()) + return ERR_PTR(-EPROBE_DEFER); + qsmmu = devm_kzalloc(smmu->dev, sizeof(*qsmmu), GFP_KERNEL); if (!qsmmu) return ERR_PTR(-ENOMEM); -- cgit v1.2.3 From 77c38c8cf52ef715bfc5cab3d14222d4f3e776e2 Mon Sep 17 00:00:00 2001 From: Shameer Kolothum Date: Thu, 19 Nov 2020 16:58:46 +0000 Subject: iommu: Check return of __iommu_attach_device() Currently iommu_create_device_direct_mappings() is called without checking the return of __iommu_attach_device(). This may result in failures in iommu driver if dev attach returns error. Fixes: ce574c27ae27 ("iommu: Move iommu_group_create_direct_mappings() out of iommu_group_add_device()") Signed-off-by: Shameer Kolothum Link: https://lore.kernel.org/r/20201119165846.34180-1-shameerali.kolothum.thodi@huawei.com Signed-off-by: Will Deacon --- drivers/iommu/iommu.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index b53446bb8c6b..0f4dc25d46c9 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -264,16 +264,18 @@ int iommu_probe_device(struct device *dev) */ iommu_alloc_default_domain(group, dev); - if (group->default_domain) + if (group->default_domain) { ret = __iommu_attach_device(group->default_domain, dev); + if (ret) { + iommu_group_put(group); + goto err_release; + } + } iommu_create_device_direct_mappings(group, dev); iommu_group_put(group); - if (ret) - goto err_release; - if (ops->probe_finalize) ops->probe_finalize(dev); -- cgit v1.2.3 From 07509e10dcc77627f8b6a57381e878fe269958d3 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 20 Nov 2020 13:28:01 +0000 Subject: arm64: pgtable: Fix pte_accessible() pte_accessible() is used by ptep_clear_flush() to figure out whether TLB invalidation is necessary when unmapping pages for reclaim. Although our implementation is correct according to the architecture, returning true only for valid, young ptes in the absence of racing page-table modifications, this is in fact flawed due to lazy invalidation of old ptes in ptep_clear_flush_young() where we elide the expensive DSB instruction for completing the TLB invalidation. Rather than penalise the aging path, adjust pte_accessible() to return true for any valid pte, even if the access flag is cleared. Cc: Fixes: 76c714be0e5e ("arm64: pgtable: implement pte_accessible()") Reported-by: Yu Zhao Acked-by: Yu Zhao Reviewed-by: Minchan Kim Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20201120143557.6715-2-will@kernel.org Signed-off-by: Will Deacon --- arch/arm64/include/asm/pgtable.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 4ff12a7adcfd..326c34677e86 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -115,8 +115,6 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) -#define pte_valid_young(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) #define pte_valid_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) @@ -124,9 +122,12 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; * Could the pte be present in the TLB? We must check mm_tlb_flush_pending * so that we don't erroneously return false for pages that have been * remapped as PROT_NONE but are yet to be flushed from the TLB. + * Note that we can't make any assumptions based on the state of the access + * flag, since ptep_clear_flush_young() elides a DSB when invalidating the + * TLB. */ #define pte_accessible(mm, pte) \ - (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte)) + (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) /* * p??_access_permitted() is true for valid user mappings (subject to the -- cgit v1.2.3 From ff1712f953e27f0b0718762ec17d0adb15c9fd0b Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 20 Nov 2020 13:57:48 +0000 Subject: arm64: pgtable: Ensure dirty bit is preserved across pte_wrprotect() With hardware dirty bit management, calling pte_wrprotect() on a writable, dirty PTE will lose the dirty state and return a read-only, clean entry. Move the logic from ptep_set_wrprotect() into pte_wrprotect() to ensure that the dirty bit is preserved for writable entries, as this is required for soft-dirty bit management if we enable it in the future. Cc: Fixes: 2f4b829c625e ("arm64: Add support for hardware updates of the access and dirty pte bits") Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20201120143557.6715-3-will@kernel.org Signed-off-by: Will Deacon --- arch/arm64/include/asm/pgtable.h | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 326c34677e86..5628289b9d5e 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -165,13 +165,6 @@ static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot) return pmd; } -static inline pte_t pte_wrprotect(pte_t pte) -{ - pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); - pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); - return pte; -} - static inline pte_t pte_mkwrite(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); @@ -197,6 +190,20 @@ static inline pte_t pte_mkdirty(pte_t pte) return pte; } +static inline pte_t pte_wrprotect(pte_t pte) +{ + /* + * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY + * clear), set the PTE_DIRTY bit. + */ + if (pte_hw_dirty(pte)) + pte = pte_mkdirty(pte); + + pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); + pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); + return pte; +} + static inline pte_t pte_mkold(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_AF)); @@ -846,12 +853,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres pte = READ_ONCE(*ptep); do { old_pte = pte; - /* - * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY - * clear), set the PTE_DIRTY bit. - */ - if (pte_hw_dirty(pte)) - pte = pte_mkdirty(pte); pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); -- cgit v1.2.3 From f2df84e096a8254ddb18c531b185fc2a45879077 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Fri, 20 Nov 2020 15:42:44 +0100 Subject: drm/vc4: kms: Store the unassigned channel list in the state If a CRTC is enabled but not active, and that we're then doing a page flip on another CRTC, drm_atomic_get_crtc_state will bring the first CRTC state into the global state, and will make us wait for its vblank as well, even though that might never occur. Instead of creating the list of the free channels each time atomic_check is called, and calling drm_atomic_get_crtc_state to retrieve the allocated channels, let's create a private state object in the main atomic state, and use it to store the available channels. Since vc4 has a semaphore (with a value of 1, so a lock) in its commit implementation to serialize all the commits, even the nonblocking ones, we are free from the use-after-free race if two subsequent commits are not ran in their submission order. Fixes: 87ebcd42fb7b ("drm/vc4: crtc: Assign output to channel automatically") Signed-off-by: Maxime Ripard Tested-by: Hoegeun Kwon Reviewed-by: Hoegeun Kwon Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20201120144245.398711-2-maxime@cerno.tech --- drivers/gpu/drm/vc4/vc4_drv.h | 1 + drivers/gpu/drm/vc4/vc4_kms.c | 126 +++++++++++++++++++++++++++++++++--------- 2 files changed, 102 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h index 19b75bebd35f..fcfeef0949af 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.h +++ b/drivers/gpu/drm/vc4/vc4_drv.h @@ -219,6 +219,7 @@ struct vc4_dev { struct drm_modeset_lock ctm_state_lock; struct drm_private_obj ctm_manager; + struct drm_private_obj hvs_channels; struct drm_private_obj load_tracker; /* List of vc4_debugfs_info_entry for adding to debugfs once diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index 0f44fc526fd2..0bbd7b554275 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -37,6 +37,17 @@ static struct vc4_ctm_state *to_vc4_ctm_state(struct drm_private_state *priv) return container_of(priv, struct vc4_ctm_state, base); } +struct vc4_hvs_state { + struct drm_private_state base; + unsigned int unassigned_channels; +}; + +static struct vc4_hvs_state * +to_vc4_hvs_state(struct drm_private_state *priv) +{ + return container_of(priv, struct vc4_hvs_state, base); +} + struct vc4_load_tracker_state { struct drm_private_state base; u64 hvs_load; @@ -171,6 +182,19 @@ vc4_ctm_commit(struct vc4_dev *vc4, struct drm_atomic_state *state) VC4_SET_FIELD(ctm_state->fifo, SCALER_OLEDOFFS_DISPFIFO)); } +static struct vc4_hvs_state * +vc4_hvs_get_global_state(struct drm_atomic_state *state) +{ + struct vc4_dev *vc4 = to_vc4_dev(state->dev); + struct drm_private_state *priv_state; + + priv_state = drm_atomic_get_private_obj_state(state, &vc4->hvs_channels); + if (IS_ERR(priv_state)) + return ERR_CAST(priv_state); + + return to_vc4_hvs_state(priv_state); +} + static void vc4_hvs_pv_muxing_commit(struct vc4_dev *vc4, struct drm_atomic_state *state) { @@ -662,6 +686,59 @@ static int vc4_load_tracker_obj_init(struct vc4_dev *vc4) return drmm_add_action_or_reset(&vc4->base, vc4_load_tracker_obj_fini, NULL); } +static struct drm_private_state * +vc4_hvs_channels_duplicate_state(struct drm_private_obj *obj) +{ + struct vc4_hvs_state *old_state = to_vc4_hvs_state(obj->state); + struct vc4_hvs_state *state; + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (!state) + return NULL; + + __drm_atomic_helper_private_obj_duplicate_state(obj, &state->base); + + state->unassigned_channels = old_state->unassigned_channels; + + return &state->base; +} + +static void vc4_hvs_channels_destroy_state(struct drm_private_obj *obj, + struct drm_private_state *state) +{ + struct vc4_hvs_state *hvs_state = to_vc4_hvs_state(state); + + kfree(hvs_state); +} + +static const struct drm_private_state_funcs vc4_hvs_state_funcs = { + .atomic_duplicate_state = vc4_hvs_channels_duplicate_state, + .atomic_destroy_state = vc4_hvs_channels_destroy_state, +}; + +static void vc4_hvs_channels_obj_fini(struct drm_device *dev, void *unused) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + + drm_atomic_private_obj_fini(&vc4->hvs_channels); +} + +static int vc4_hvs_channels_obj_init(struct vc4_dev *vc4) +{ + struct vc4_hvs_state *state; + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (!state) + return -ENOMEM; + + state->unassigned_channels = GENMASK(HVS_NUM_CHANNELS - 1, 0); + drm_atomic_private_obj_init(&vc4->base, &vc4->hvs_channels, + &state->base, + &vc4_hvs_state_funcs); + + return drmm_add_action_or_reset(&vc4->base, vc4_hvs_channels_obj_fini, NULL); +} + /* * The BCM2711 HVS has up to 7 outputs connected to the pixelvalves and * the TXP (and therefore all the CRTCs found on that platform). @@ -678,6 +755,14 @@ static int vc4_load_tracker_obj_init(struct vc4_dev *vc4) * need to consider all the running CRTCs in the DRM device to assign * a FIFO, not just the one in the state. * + * - To fix the above, we can't use drm_atomic_get_crtc_state on all + * enabled CRTCs to pull their CRTC state into the global state, since + * a page flip would start considering their vblank to complete. Since + * we don't have a guarantee that they are actually active, that + * vblank might never happen, and shouldn't even be considered if we + * want to do a page flip on a single CRTC. That can be tested by + * doing a modetest -v first on HDMI1 and then on HDMI0. + * * - Since we need the pixelvalve to be disabled and enabled back when * the FIFO is changed, we should keep the FIFO assigned for as long * as the CRTC is enabled, only considering it free again once that @@ -687,46 +772,33 @@ static int vc4_load_tracker_obj_init(struct vc4_dev *vc4) static int vc4_pv_muxing_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) { - unsigned long unassigned_channels = GENMASK(HVS_NUM_CHANNELS - 1, 0); + struct vc4_hvs_state *hvs_new_state; struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct drm_crtc *crtc; unsigned int i; - /* - * Since the HVS FIFOs are shared across all the pixelvalves and - * the TXP (and thus all the CRTCs), we need to pull the current - * state of all the enabled CRTCs so that an update to a single - * CRTC still keeps the previous FIFOs enabled and assigned to - * the same CRTCs, instead of evaluating only the CRTC being - * modified. - */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - struct drm_crtc_state *crtc_state; - - if (!crtc->state->enable) - continue; - - crtc_state = drm_atomic_get_crtc_state(state, crtc); - if (IS_ERR(crtc_state)) - return PTR_ERR(crtc_state); - } + hvs_new_state = vc4_hvs_get_global_state(state); + if (!hvs_new_state) + return -EINVAL; for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { + struct vc4_crtc_state *old_vc4_crtc_state = + to_vc4_crtc_state(old_crtc_state); struct vc4_crtc_state *new_vc4_crtc_state = to_vc4_crtc_state(new_crtc_state); struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); unsigned int matching_channels; - if (old_crtc_state->enable && !new_crtc_state->enable) + if (old_crtc_state->enable && !new_crtc_state->enable) { + hvs_new_state->unassigned_channels |= BIT(old_vc4_crtc_state->assigned_channel); new_vc4_crtc_state->assigned_channel = VC4_HVS_CHANNEL_DISABLED; + } if (!new_crtc_state->enable) continue; - if (new_vc4_crtc_state->assigned_channel != VC4_HVS_CHANNEL_DISABLED) { - unassigned_channels &= ~BIT(new_vc4_crtc_state->assigned_channel); + if (new_vc4_crtc_state->assigned_channel != VC4_HVS_CHANNEL_DISABLED) continue; - } /* * The problem we have to solve here is that we have @@ -752,12 +824,12 @@ static int vc4_pv_muxing_atomic_check(struct drm_device *dev, * the future, we will need to have something smarter, * but it works so far. */ - matching_channels = unassigned_channels & vc4_crtc->data->hvs_available_channels; + matching_channels = hvs_new_state->unassigned_channels & vc4_crtc->data->hvs_available_channels; if (matching_channels) { unsigned int channel = ffs(matching_channels) - 1; new_vc4_crtc_state->assigned_channel = channel; - unassigned_channels &= ~BIT(channel); + hvs_new_state->unassigned_channels &= ~BIT(channel); } else { return -EINVAL; } @@ -841,6 +913,10 @@ int vc4_kms_load(struct drm_device *dev) if (ret) return ret; + ret = vc4_hvs_channels_obj_init(vc4); + if (ret) + return ret; + drm_mode_config_reset(dev); drm_kms_helper_poll_init(dev); -- cgit v1.2.3 From 2820526dd5c27326d9c0d2c831a34b8f14e7c404 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Fri, 20 Nov 2020 15:42:45 +0100 Subject: drm/vc4: kms: Don't disable the muxing of an active CRTC The current HVS muxing code will consider the CRTCs in a given state to setup their muxing in the HVS, and disable the other CRTCs muxes. However, it's valid to only update a single CRTC with a state, and in this situation we would mux out a CRTC that was enabled but left untouched by the new state. Fix this by setting a flag on the CRTC state when the muxing has been changed, and only change the muxing configuration when that flag is there. Fixes: 87ebcd42fb7b ("drm/vc4: crtc: Assign output to channel automatically") Signed-off-by: Maxime Ripard Tested-by: Hoegeun Kwon Reviewed-by: Hoegeun Kwon Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20201120144245.398711-3-maxime@cerno.tech --- drivers/gpu/drm/vc4/vc4_drv.h | 3 ++ drivers/gpu/drm/vc4/vc4_kms.c | 81 ++++++++++++++++++++++++------------------- 2 files changed, 48 insertions(+), 36 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h index fcfeef0949af..c5f2944d5bc6 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.h +++ b/drivers/gpu/drm/vc4/vc4_drv.h @@ -532,6 +532,9 @@ struct vc4_crtc_state { unsigned int top; unsigned int bottom; } margins; + + /* Transitional state below, only valid during atomic commits */ + bool update_muxing; }; #define VC4_HVS_CHANNEL_DISABLED ((unsigned int)-1) diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index 0bbd7b554275..ba310c0ab5f6 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -239,10 +239,7 @@ static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4, { struct drm_crtc_state *crtc_state; struct drm_crtc *crtc; - unsigned char dsp2_mux = 0; - unsigned char dsp3_mux = 3; - unsigned char dsp4_mux = 3; - unsigned char dsp5_mux = 3; + unsigned char mux; unsigned int i; u32 reg; @@ -250,50 +247,59 @@ static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4, struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc_state); struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); - if (!crtc_state->active) + if (!vc4_state->update_muxing) continue; switch (vc4_crtc->data->hvs_output) { case 2: - dsp2_mux = (vc4_state->assigned_channel == 2) ? 0 : 1; + mux = (vc4_state->assigned_channel == 2) ? 0 : 1; + reg = HVS_READ(SCALER_DISPECTRL); + HVS_WRITE(SCALER_DISPECTRL, + (reg & ~SCALER_DISPECTRL_DSP2_MUX_MASK) | + VC4_SET_FIELD(mux, SCALER_DISPECTRL_DSP2_MUX)); break; case 3: - dsp3_mux = vc4_state->assigned_channel; + if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED) + mux = 3; + else + mux = vc4_state->assigned_channel; + + reg = HVS_READ(SCALER_DISPCTRL); + HVS_WRITE(SCALER_DISPCTRL, + (reg & ~SCALER_DISPCTRL_DSP3_MUX_MASK) | + VC4_SET_FIELD(mux, SCALER_DISPCTRL_DSP3_MUX)); break; case 4: - dsp4_mux = vc4_state->assigned_channel; + if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED) + mux = 3; + else + mux = vc4_state->assigned_channel; + + reg = HVS_READ(SCALER_DISPEOLN); + HVS_WRITE(SCALER_DISPEOLN, + (reg & ~SCALER_DISPEOLN_DSP4_MUX_MASK) | + VC4_SET_FIELD(mux, SCALER_DISPEOLN_DSP4_MUX)); + break; case 5: - dsp5_mux = vc4_state->assigned_channel; + if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED) + mux = 3; + else + mux = vc4_state->assigned_channel; + + reg = HVS_READ(SCALER_DISPDITHER); + HVS_WRITE(SCALER_DISPDITHER, + (reg & ~SCALER_DISPDITHER_DSP5_MUX_MASK) | + VC4_SET_FIELD(mux, SCALER_DISPDITHER_DSP5_MUX)); break; default: break; } } - - reg = HVS_READ(SCALER_DISPECTRL); - HVS_WRITE(SCALER_DISPECTRL, - (reg & ~SCALER_DISPECTRL_DSP2_MUX_MASK) | - VC4_SET_FIELD(dsp2_mux, SCALER_DISPECTRL_DSP2_MUX)); - - reg = HVS_READ(SCALER_DISPCTRL); - HVS_WRITE(SCALER_DISPCTRL, - (reg & ~SCALER_DISPCTRL_DSP3_MUX_MASK) | - VC4_SET_FIELD(dsp3_mux, SCALER_DISPCTRL_DSP3_MUX)); - - reg = HVS_READ(SCALER_DISPEOLN); - HVS_WRITE(SCALER_DISPEOLN, - (reg & ~SCALER_DISPEOLN_DSP4_MUX_MASK) | - VC4_SET_FIELD(dsp4_mux, SCALER_DISPEOLN_DSP4_MUX)); - - reg = HVS_READ(SCALER_DISPDITHER); - HVS_WRITE(SCALER_DISPDITHER, - (reg & ~SCALER_DISPDITHER_DSP5_MUX_MASK) | - VC4_SET_FIELD(dsp5_mux, SCALER_DISPDITHER_DSP5_MUX)); } static void @@ -789,16 +795,19 @@ static int vc4_pv_muxing_atomic_check(struct drm_device *dev, struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); unsigned int matching_channels; - if (old_crtc_state->enable && !new_crtc_state->enable) { - hvs_new_state->unassigned_channels |= BIT(old_vc4_crtc_state->assigned_channel); - new_vc4_crtc_state->assigned_channel = VC4_HVS_CHANNEL_DISABLED; - } - - if (!new_crtc_state->enable) + /* Nothing to do here, let's skip it */ + if (old_crtc_state->enable == new_crtc_state->enable) continue; - if (new_vc4_crtc_state->assigned_channel != VC4_HVS_CHANNEL_DISABLED) + /* Muxing will need to be modified, mark it as such */ + new_vc4_crtc_state->update_muxing = true; + + /* If we're disabling our CRTC, we put back our channel */ + if (!new_crtc_state->enable) { + hvs_new_state->unassigned_channels |= BIT(old_vc4_crtc_state->assigned_channel); + new_vc4_crtc_state->assigned_channel = VC4_HVS_CHANNEL_DISABLED; continue; + } /* * The problem we have to solve here is that we have -- cgit v1.2.3 From 652b44453ea953d3157f02a7f17e18e329952649 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sat, 21 Nov 2020 14:35:35 +0200 Subject: habanalabs/gaudi: fix missing code in ECC handling There is missing statement and missing "break;" in the ECC handling code in gaudi.c This will cause a wrong behavior upon certain ECC interrupts. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/gaudi/gaudi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 2519a34e25b7..7ea6b4368a91 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -5436,6 +5436,8 @@ static void gaudi_handle_ecc_event(struct hl_device *hdev, u16 event_type, params.num_memories = 33; params.derr = true; params.disable_clock_gating = true; + extract_info_from_fw = false; + break; default: return; } -- cgit v1.2.3 From b1824968221ccc498625750d8c49cf0d7d39a4de Mon Sep 17 00:00:00 2001 From: Srinivasa Rao Mandadapu Date: Mon, 23 Nov 2020 21:47:53 +0530 Subject: ASoC: qcom: Fix enabling BCLK and LRCLK in LPAIF invalid state Fix enabling BCLK and LRCLK only when LPAIF is invalid state and bit clock in enable state. In device suspend/resume scenario LPAIF is going to reset state. which is causing LRCLK disable and BCLK enable. Avoid such inconsitency by removing unnecessary cpu dai prepare API, which is doing LRCLK enable, and by maintaining BLCK state information. Fixes: 7e6799d8f87d ("ASoC: qcom: lpass-cpu: Enable MI2S BCLK and LRCLK together") Signed-off-by: V Sujith Kumar Reddy Signed-off-by: Srinivasa Rao Mandadapu Link: https://lore.kernel.org/r/1606148273-17325-1-git-send-email-srivasam@codeaurora.org Signed-off-by: Mark Brown --- sound/soc/qcom/lpass-cpu.c | 62 ++++++++++++++++++++-------------------- sound/soc/qcom/lpass-lpaif-reg.h | 7 +++++ sound/soc/qcom/lpass-platform.c | 20 +++++++++++-- sound/soc/qcom/lpass.h | 1 + 4 files changed, 57 insertions(+), 33 deletions(-) diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index 9d17c87445a9..426235a217ec 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -263,28 +263,6 @@ static int lpass_cpu_daiops_hw_params(struct snd_pcm_substream *substream, return 0; } -static int lpass_cpu_daiops_prepare(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai); - struct lpaif_i2sctl *i2sctl = drvdata->i2sctl; - unsigned int id = dai->driver->id; - int ret; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { - ret = regmap_fields_write(i2sctl->spken, id, - LPAIF_I2SCTL_SPKEN_ENABLE); - } else { - ret = regmap_fields_write(i2sctl->micen, id, - LPAIF_I2SCTL_MICEN_ENABLE); - } - - if (ret) - dev_err(dai->dev, "error writing to i2sctl enable: %d\n", ret); - - return ret; -} - static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, int cmd, struct snd_soc_dai *dai) { @@ -292,6 +270,18 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, struct lpaif_i2sctl *i2sctl = drvdata->i2sctl; unsigned int id = dai->driver->id; int ret = -EINVAL; + unsigned int val = 0; + + ret = regmap_read(drvdata->lpaif_map, + LPAIF_I2SCTL_REG(drvdata->variant, dai->driver->id), &val); + if (ret) { + dev_err(dai->dev, "error reading from i2sctl reg: %d\n", ret); + return ret; + } + if (val == LPAIF_I2SCTL_RESET_STATE) { + dev_err(dai->dev, "error in i2sctl register state\n"); + return -ENOTRECOVERABLE; + } switch (cmd) { case SNDRV_PCM_TRIGGER_START: @@ -308,11 +298,14 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, dev_err(dai->dev, "error writing to i2sctl reg: %d\n", ret); - ret = clk_enable(drvdata->mi2s_bit_clk[id]); - if (ret) { - dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret); - clk_disable(drvdata->mi2s_osr_clk[id]); - return ret; + if (drvdata->bit_clk_state[id] == LPAIF_BIT_CLK_DISABLE) { + ret = clk_enable(drvdata->mi2s_bit_clk[id]); + if (ret) { + dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret); + clk_disable(drvdata->mi2s_osr_clk[id]); + return ret; + } + drvdata->bit_clk_state[id] = LPAIF_BIT_CLK_ENABLE; } break; @@ -329,7 +322,10 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, if (ret) dev_err(dai->dev, "error writing to i2sctl reg: %d\n", ret); - clk_disable(drvdata->mi2s_bit_clk[dai->driver->id]); + if (drvdata->bit_clk_state[id] == LPAIF_BIT_CLK_ENABLE) { + clk_disable(drvdata->mi2s_bit_clk[dai->driver->id]); + drvdata->bit_clk_state[id] = LPAIF_BIT_CLK_DISABLE; + } break; } @@ -341,7 +337,6 @@ const struct snd_soc_dai_ops asoc_qcom_lpass_cpu_dai_ops = { .startup = lpass_cpu_daiops_startup, .shutdown = lpass_cpu_daiops_shutdown, .hw_params = lpass_cpu_daiops_hw_params, - .prepare = lpass_cpu_daiops_prepare, .trigger = lpass_cpu_daiops_trigger, }; EXPORT_SYMBOL_GPL(asoc_qcom_lpass_cpu_dai_ops); @@ -459,16 +454,20 @@ static bool lpass_cpu_regmap_volatile(struct device *dev, unsigned int reg) struct lpass_variant *v = drvdata->variant; int i; + for (i = 0; i < v->i2s_ports; ++i) + if (reg == LPAIF_I2SCTL_REG(v, i)) + return true; for (i = 0; i < v->irq_ports; ++i) if (reg == LPAIF_IRQSTAT_REG(v, i)) return true; for (i = 0; i < v->rdma_channels; ++i) - if (reg == LPAIF_RDMACURR_REG(v, i)) + if (reg == LPAIF_RDMACURR_REG(v, i) || reg == LPAIF_RDMACTL_REG(v, i)) return true; for (i = 0; i < v->wrdma_channels; ++i) - if (reg == LPAIF_WRDMACURR_REG(v, i + v->wrdma_channel_start)) + if (reg == LPAIF_WRDMACURR_REG(v, i + v->wrdma_channel_start) || + reg == LPAIF_WRDMACTL_REG(v, i + v->wrdma_channel_start)) return true; return false; @@ -861,6 +860,7 @@ int asoc_qcom_lpass_cpu_platform_probe(struct platform_device *pdev) PTR_ERR(drvdata->mi2s_bit_clk[dai_id])); return PTR_ERR(drvdata->mi2s_bit_clk[dai_id]); } + drvdata->bit_clk_state[dai_id] = LPAIF_BIT_CLK_DISABLE; } /* Allocation for i2sctl regmap fields */ diff --git a/sound/soc/qcom/lpass-lpaif-reg.h b/sound/soc/qcom/lpass-lpaif-reg.h index 08f3fe508b85..405542832e99 100644 --- a/sound/soc/qcom/lpass-lpaif-reg.h +++ b/sound/soc/qcom/lpass-lpaif-reg.h @@ -60,6 +60,13 @@ #define LPAIF_I2SCTL_BITWIDTH_24 1 #define LPAIF_I2SCTL_BITWIDTH_32 2 +#define LPAIF_BIT_CLK_DISABLE 0 +#define LPAIF_BIT_CLK_ENABLE 1 + +#define LPAIF_I2SCTL_RESET_STATE 0x003C0004 +#define LPAIF_DMACTL_RESET_STATE 0x00200000 + + /* LPAIF IRQ */ #define LPAIF_IRQ_REG_ADDR(v, addr, port) \ (v->irq_reg_base + (addr) + v->irq_reg_stride * (port)) diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c index 7a3fdf89968a..80b09dede5f9 100644 --- a/sound/soc/qcom/lpass-platform.c +++ b/sound/soc/qcom/lpass-platform.c @@ -110,6 +110,7 @@ static int lpass_platform_pcmops_open(struct snd_soc_component *component, struct regmap *map; unsigned int dai_id = cpu_dai->driver->id; + component->id = dai_id; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; @@ -451,19 +452,34 @@ static int lpass_platform_pcmops_trigger(struct snd_soc_component *component, unsigned int reg_irqclr = 0, val_irqclr = 0; unsigned int reg_irqen = 0, val_irqen = 0, val_mask = 0; unsigned int dai_id = cpu_dai->driver->id; + unsigned int dma_ctrl_reg = 0; ch = pcm_data->dma_ch; if (dir == SNDRV_PCM_STREAM_PLAYBACK) { id = pcm_data->dma_ch; - if (dai_id == LPASS_DP_RX) + if (dai_id == LPASS_DP_RX) { dmactl = drvdata->hdmi_rd_dmactl; - else + map = drvdata->hdmiif_map; + } else { dmactl = drvdata->rd_dmactl; + map = drvdata->lpaif_map; + } } else { dmactl = drvdata->wr_dmactl; id = pcm_data->dma_ch - v->wrdma_channel_start; + map = drvdata->lpaif_map; + } + ret = regmap_read(map, LPAIF_DMACTL_REG(v, ch, dir, dai_id), &dma_ctrl_reg); + if (ret) { + dev_err(soc_runtime->dev, "error reading from rdmactl reg: %d\n", ret); + return ret; } + if (dma_ctrl_reg == LPAIF_DMACTL_RESET_STATE || + dma_ctrl_reg == LPAIF_DMACTL_RESET_STATE + 1) { + dev_err(soc_runtime->dev, "error in rdmactl register state\n"); + return -ENOTRECOVERABLE; + } switch (cmd) { case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: diff --git a/sound/soc/qcom/lpass.h b/sound/soc/qcom/lpass.h index b4830f353796..bccd1a05d771 100644 --- a/sound/soc/qcom/lpass.h +++ b/sound/soc/qcom/lpass.h @@ -68,6 +68,7 @@ struct lpass_data { unsigned int mi2s_playback_sd_mode[LPASS_MAX_MI2S_PORTS]; unsigned int mi2s_capture_sd_mode[LPASS_MAX_MI2S_PORTS]; int hdmi_port_enable; + int bit_clk_state[LPASS_MAX_MI2S_PORTS]; /* low-power audio interface (LPAIF) registers */ void __iomem *lpaif; -- cgit v1.2.3 From 0697d9a610998b8bdee6b2390836cb2391d8fd1a Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 18 Nov 2020 18:03:26 +0900 Subject: btrfs: don't access possibly stale fs_info data for printing duplicate device Syzbot reported a possible use-after-free when printing a duplicate device warning device_list_add(). At this point it can happen that a btrfs_device::fs_info is not correctly setup yet, so we're accessing stale data, when printing the warning message using the btrfs_printk() wrappers. ================================================================== BUG: KASAN: use-after-free in btrfs_printk+0x3eb/0x435 fs/btrfs/super.c:245 Read of size 8 at addr ffff8880878e06a8 by task syz-executor225/7068 CPU: 1 PID: 7068 Comm: syz-executor225 Not tainted 5.9.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1d6/0x29e lib/dump_stack.c:118 print_address_description+0x66/0x620 mm/kasan/report.c:383 __kasan_report mm/kasan/report.c:513 [inline] kasan_report+0x132/0x1d0 mm/kasan/report.c:530 btrfs_printk+0x3eb/0x435 fs/btrfs/super.c:245 device_list_add+0x1a88/0x1d60 fs/btrfs/volumes.c:943 btrfs_scan_one_device+0x196/0x490 fs/btrfs/volumes.c:1359 btrfs_mount_root+0x48f/0xb60 fs/btrfs/super.c:1634 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x88/0x270 fs/super.c:1547 fc_mount fs/namespace.c:978 [inline] vfs_kern_mount+0xc9/0x160 fs/namespace.c:1008 btrfs_mount+0x33c/0xae0 fs/btrfs/super.c:1732 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x88/0x270 fs/super.c:1547 do_new_mount fs/namespace.c:2875 [inline] path_mount+0x179d/0x29e0 fs/namespace.c:3192 do_mount fs/namespace.c:3205 [inline] __do_sys_mount fs/namespace.c:3413 [inline] __se_sys_mount+0x126/0x180 fs/namespace.c:3390 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x44840a RSP: 002b:00007ffedfffd608 EFLAGS: 00000293 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00007ffedfffd670 RCX: 000000000044840a RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007ffedfffd630 RBP: 00007ffedfffd630 R08: 00007ffedfffd670 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000293 R12: 000000000000001a R13: 0000000000000004 R14: 0000000000000003 R15: 0000000000000003 Allocated by task 6945: kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track mm/kasan/common.c:56 [inline] __kasan_kmalloc+0x100/0x130 mm/kasan/common.c:461 kmalloc_node include/linux/slab.h:577 [inline] kvmalloc_node+0x81/0x110 mm/util.c:574 kvmalloc include/linux/mm.h:757 [inline] kvzalloc include/linux/mm.h:765 [inline] btrfs_mount_root+0xd0/0xb60 fs/btrfs/super.c:1613 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x88/0x270 fs/super.c:1547 fc_mount fs/namespace.c:978 [inline] vfs_kern_mount+0xc9/0x160 fs/namespace.c:1008 btrfs_mount+0x33c/0xae0 fs/btrfs/super.c:1732 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x88/0x270 fs/super.c:1547 do_new_mount fs/namespace.c:2875 [inline] path_mount+0x179d/0x29e0 fs/namespace.c:3192 do_mount fs/namespace.c:3205 [inline] __do_sys_mount fs/namespace.c:3413 [inline] __se_sys_mount+0x126/0x180 fs/namespace.c:3390 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 6945: kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track+0x3d/0x70 mm/kasan/common.c:56 kasan_set_free_info+0x17/0x30 mm/kasan/generic.c:355 __kasan_slab_free+0xdd/0x110 mm/kasan/common.c:422 __cache_free mm/slab.c:3418 [inline] kfree+0x113/0x200 mm/slab.c:3756 deactivate_locked_super+0xa7/0xf0 fs/super.c:335 btrfs_mount_root+0x72b/0xb60 fs/btrfs/super.c:1678 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x88/0x270 fs/super.c:1547 fc_mount fs/namespace.c:978 [inline] vfs_kern_mount+0xc9/0x160 fs/namespace.c:1008 btrfs_mount+0x33c/0xae0 fs/btrfs/super.c:1732 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x88/0x270 fs/super.c:1547 do_new_mount fs/namespace.c:2875 [inline] path_mount+0x179d/0x29e0 fs/namespace.c:3192 do_mount fs/namespace.c:3205 [inline] __do_sys_mount fs/namespace.c:3413 [inline] __se_sys_mount+0x126/0x180 fs/namespace.c:3390 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The buggy address belongs to the object at ffff8880878e0000 which belongs to the cache kmalloc-16k of size 16384 The buggy address is located 1704 bytes inside of 16384-byte region [ffff8880878e0000, ffff8880878e4000) The buggy address belongs to the page: page:0000000060704f30 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x878e0 head:0000000060704f30 order:3 compound_mapcount:0 compound_pincount:0 flags: 0xfffe0000010200(slab|head) raw: 00fffe0000010200 ffffea00028e9a08 ffffea00021e3608 ffff8880aa440b00 raw: 0000000000000000 ffff8880878e0000 0000000100000001 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8880878e0580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880878e0600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8880878e0680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8880878e0700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880878e0780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== The syzkaller reproducer for this use-after-free crafts a filesystem image and loop mounts it twice in a loop. The mount will fail as the crafted image has an invalid chunk tree. When this happens btrfs_mount_root() will call deactivate_locked_super(), which then cleans up fs_info and fs_info::sb. If a second thread now adds the same block-device to the filesystem, it will get detected as a duplicate device and device_list_add() will reject the duplicate and print a warning. But as the fs_info pointer passed in is non-NULL this will result in a use-after-free. Instead of printing possibly uninitialized or already freed memory in btrfs_printk(), explicitly pass in a NULL fs_info so the printing of the device name will be skipped altogether. There was a slightly different approach discussed in https://lore.kernel.org/linux-btrfs/20200114060920.4527-1-anand.jain@oracle.com/t/#u Link: https://lore.kernel.org/linux-btrfs/000000000000c9e14b05afcc41ba@google.com Reported-by: syzbot+582e66e5edf36a22c7b0@syzkaller.appspotmail.com CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Nikolay Borisov Reviewed-by: Anand Jain Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a6406b3b8c2b..78637665166e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -940,7 +940,13 @@ static noinline struct btrfs_device *device_list_add(const char *path, if (device->bdev != path_bdev) { bdput(path_bdev); mutex_unlock(&fs_devices->device_list_mutex); - btrfs_warn_in_rcu(device->fs_info, + /* + * device->fs_info may not be reliable here, so + * pass in a NULL instead. This avoids a + * possible use-after-free when the fs_info and + * fs_info->sb are already torn down. + */ + btrfs_warn_in_rcu(NULL, "duplicate device %s devid %llu generation %llu scanned by %s (%d)", path, devid, found_transid, current->comm, -- cgit v1.2.3 From 6d06b0ad94d3dd7e3503d8ad39c39c4634884611 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 16 Nov 2020 19:53:52 +0100 Subject: btrfs: tree-checker: add missing returns after data_ref alignment checks There are sectorsize alignment checks that are reported but then check_extent_data_ref continues. This was not intended, wrong alignment is not a minor problem and we should return with error. CC: stable@vger.kernel.org # 5.4+ Fixes: 0785a9aacf9d ("btrfs: tree-checker: Add EXTENT_DATA_REF check") Reviewed-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/tree-checker.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 6cefabd27209..ea2bb4cb5890 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1424,6 +1424,7 @@ static int check_extent_data_ref(struct extent_buffer *leaf, "invalid item size, have %u expect aligned to %zu for key type %u", btrfs_item_size_nr(leaf, slot), sizeof(*dref), key->type); + return -EUCLEAN; } if (!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize)) { generic_err(leaf, slot, @@ -1452,6 +1453,7 @@ static int check_extent_data_ref(struct extent_buffer *leaf, extent_err(leaf, slot, "invalid extent data backref offset, have %llu expect aligned to %u", offset, leaf->fs_info->sectorsize); + return -EUCLEAN; } } return 0; -- cgit v1.2.3 From 3d05cad3c357a2b749912914356072b38435edfa Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 23 Nov 2020 14:28:44 +0000 Subject: btrfs: fix lockdep splat when reading qgroup config on mount Lockdep reported the following splat when running test btrfs/190 from fstests: [ 9482.126098] ====================================================== [ 9482.126184] WARNING: possible circular locking dependency detected [ 9482.126281] 5.10.0-rc4-btrfs-next-73 #1 Not tainted [ 9482.126365] ------------------------------------------------------ [ 9482.126456] mount/24187 is trying to acquire lock: [ 9482.126534] ffffa0c869a7dac0 (&fs_info->qgroup_rescan_lock){+.+.}-{3:3}, at: qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.126647] but task is already holding lock: [ 9482.126777] ffffa0c892ebd3a0 (btrfs-quota-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x27/0x120 [btrfs] [ 9482.126886] which lock already depends on the new lock. [ 9482.127078] the existing dependency chain (in reverse order) is: [ 9482.127213] -> #1 (btrfs-quota-00){++++}-{3:3}: [ 9482.127366] lock_acquire+0xd8/0x490 [ 9482.127436] down_read_nested+0x45/0x220 [ 9482.127528] __btrfs_tree_read_lock+0x27/0x120 [btrfs] [ 9482.127613] btrfs_read_lock_root_node+0x41/0x130 [btrfs] [ 9482.127702] btrfs_search_slot+0x514/0xc30 [btrfs] [ 9482.127788] update_qgroup_status_item+0x72/0x140 [btrfs] [ 9482.127877] btrfs_qgroup_rescan_worker+0xde/0x680 [btrfs] [ 9482.127964] btrfs_work_helper+0xf1/0x600 [btrfs] [ 9482.128039] process_one_work+0x24e/0x5e0 [ 9482.128110] worker_thread+0x50/0x3b0 [ 9482.128181] kthread+0x153/0x170 [ 9482.128256] ret_from_fork+0x22/0x30 [ 9482.128327] -> #0 (&fs_info->qgroup_rescan_lock){+.+.}-{3:3}: [ 9482.128464] check_prev_add+0x91/0xc60 [ 9482.128551] __lock_acquire+0x1740/0x3110 [ 9482.128623] lock_acquire+0xd8/0x490 [ 9482.130029] __mutex_lock+0xa3/0xb30 [ 9482.130590] qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.131577] btrfs_read_qgroup_config+0x43a/0x550 [btrfs] [ 9482.132175] open_ctree+0x1228/0x18a0 [btrfs] [ 9482.132756] btrfs_mount_root.cold+0x13/0xed [btrfs] [ 9482.133325] legacy_get_tree+0x30/0x60 [ 9482.133866] vfs_get_tree+0x28/0xe0 [ 9482.134392] fc_mount+0xe/0x40 [ 9482.134908] vfs_kern_mount.part.0+0x71/0x90 [ 9482.135428] btrfs_mount+0x13b/0x3e0 [btrfs] [ 9482.135942] legacy_get_tree+0x30/0x60 [ 9482.136444] vfs_get_tree+0x28/0xe0 [ 9482.136949] path_mount+0x2d7/0xa70 [ 9482.137438] do_mount+0x75/0x90 [ 9482.137923] __x64_sys_mount+0x8e/0xd0 [ 9482.138400] do_syscall_64+0x33/0x80 [ 9482.138873] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 9482.139346] other info that might help us debug this: [ 9482.140735] Possible unsafe locking scenario: [ 9482.141594] CPU0 CPU1 [ 9482.142011] ---- ---- [ 9482.142411] lock(btrfs-quota-00); [ 9482.142806] lock(&fs_info->qgroup_rescan_lock); [ 9482.143216] lock(btrfs-quota-00); [ 9482.143629] lock(&fs_info->qgroup_rescan_lock); [ 9482.144056] *** DEADLOCK *** [ 9482.145242] 2 locks held by mount/24187: [ 9482.145637] #0: ffffa0c8411c40e8 (&type->s_umount_key#44/1){+.+.}-{3:3}, at: alloc_super+0xb9/0x400 [ 9482.146061] #1: ffffa0c892ebd3a0 (btrfs-quota-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x27/0x120 [btrfs] [ 9482.146509] stack backtrace: [ 9482.147350] CPU: 1 PID: 24187 Comm: mount Not tainted 5.10.0-rc4-btrfs-next-73 #1 [ 9482.147788] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 9482.148709] Call Trace: [ 9482.149169] dump_stack+0x8d/0xb5 [ 9482.149628] check_noncircular+0xff/0x110 [ 9482.150090] check_prev_add+0x91/0xc60 [ 9482.150561] ? kvm_clock_read+0x14/0x30 [ 9482.151017] ? kvm_sched_clock_read+0x5/0x10 [ 9482.151470] __lock_acquire+0x1740/0x3110 [ 9482.151941] ? __btrfs_tree_read_lock+0x27/0x120 [btrfs] [ 9482.152402] lock_acquire+0xd8/0x490 [ 9482.152887] ? qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.153354] __mutex_lock+0xa3/0xb30 [ 9482.153826] ? qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.154301] ? qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.154768] ? qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.155226] qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.155690] btrfs_read_qgroup_config+0x43a/0x550 [btrfs] [ 9482.156160] open_ctree+0x1228/0x18a0 [btrfs] [ 9482.156643] btrfs_mount_root.cold+0x13/0xed [btrfs] [ 9482.157108] ? rcu_read_lock_sched_held+0x5d/0x90 [ 9482.157567] ? kfree+0x31f/0x3e0 [ 9482.158030] legacy_get_tree+0x30/0x60 [ 9482.158489] vfs_get_tree+0x28/0xe0 [ 9482.158947] fc_mount+0xe/0x40 [ 9482.159403] vfs_kern_mount.part.0+0x71/0x90 [ 9482.159875] btrfs_mount+0x13b/0x3e0 [btrfs] [ 9482.160335] ? rcu_read_lock_sched_held+0x5d/0x90 [ 9482.160805] ? kfree+0x31f/0x3e0 [ 9482.161260] ? legacy_get_tree+0x30/0x60 [ 9482.161714] legacy_get_tree+0x30/0x60 [ 9482.162166] vfs_get_tree+0x28/0xe0 [ 9482.162616] path_mount+0x2d7/0xa70 [ 9482.163070] do_mount+0x75/0x90 [ 9482.163525] __x64_sys_mount+0x8e/0xd0 [ 9482.163986] do_syscall_64+0x33/0x80 [ 9482.164437] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 9482.164902] RIP: 0033:0x7f51e907caaa This happens because at btrfs_read_qgroup_config() we can call qgroup_rescan_init() while holding a read lock on a quota btree leaf, acquired by the previous call to btrfs_search_slot_for_read(), and qgroup_rescan_init() acquires the mutex qgroup_rescan_lock. A qgroup rescan worker does the opposite: it acquires the mutex qgroup_rescan_lock, at btrfs_qgroup_rescan_worker(), and then tries to update the qgroup status item in the quota btree through the call to update_qgroup_status_item(). This inversion of locking order between the qgroup_rescan_lock mutex and quota btree locks causes the splat. Fix this simply by releasing and freeing the path before calling qgroup_rescan_init() at btrfs_read_qgroup_config(). CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/qgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 4621b8043021..a3f0d209fce5 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -497,13 +497,13 @@ next2: break; } out: + btrfs_free_path(path); fs_info->qgroup_flags |= flags; if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); else if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN && ret >= 0) ret = qgroup_rescan_init(fs_info, rescan_progress, 0); - btrfs_free_path(path); if (ret < 0) { ulist_free(fs_info->qgroup_ulist); -- cgit v1.2.3 From 7aa6d359845a9dbf7ad90b0b1b6347ef4764621f Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 23 Nov 2020 18:30:54 +0000 Subject: btrfs: do nofs allocations when adding and removing qgroup relations When adding or removing a qgroup relation we are doing a GFP_KERNEL allocation which is not safe because we are holding a transaction handle open and that can make us deadlock if the allocator needs to recurse into the filesystem. So just surround those calls with a nofs context. Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/qgroup.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a3f0d209fce5..d690ef702522 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "ctree.h" #include "transaction.h" @@ -1324,13 +1325,17 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, struct btrfs_qgroup *member; struct btrfs_qgroup_list *list; struct ulist *tmp; + unsigned int nofs_flag; int ret = 0; /* Check the level of src and dst first */ if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) return -EINVAL; + /* We hold a transaction handle open, must do a NOFS allocation. */ + nofs_flag = memalloc_nofs_save(); tmp = ulist_alloc(GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!tmp) return -ENOMEM; @@ -1387,10 +1392,14 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, struct btrfs_qgroup_list *list; struct ulist *tmp; bool found = false; + unsigned int nofs_flag; int ret = 0; int ret2; + /* We hold a transaction handle open, must do a NOFS allocation. */ + nofs_flag = memalloc_nofs_save(); tmp = ulist_alloc(GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!tmp) return -ENOMEM; -- cgit v1.2.3 From a855fbe69229078cd8aecd8974fb996a5ca651e6 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 23 Nov 2020 18:31:02 +0000 Subject: btrfs: fix lockdep splat when enabling and disabling qgroups When running test case btrfs/017 from fstests, lockdep reported the following splat: [ 1297.067385] ====================================================== [ 1297.067708] WARNING: possible circular locking dependency detected [ 1297.068022] 5.10.0-rc4-btrfs-next-73 #1 Not tainted [ 1297.068322] ------------------------------------------------------ [ 1297.068629] btrfs/189080 is trying to acquire lock: [ 1297.068929] ffff9f2725731690 (sb_internal#2){.+.+}-{0:0}, at: btrfs_quota_enable+0xaf/0xa70 [btrfs] [ 1297.069274] but task is already holding lock: [ 1297.069868] ffff9f2702b61a08 (&fs_info->qgroup_ioctl_lock){+.+.}-{3:3}, at: btrfs_quota_enable+0x3b/0xa70 [btrfs] [ 1297.070219] which lock already depends on the new lock. [ 1297.071131] the existing dependency chain (in reverse order) is: [ 1297.071721] -> #1 (&fs_info->qgroup_ioctl_lock){+.+.}-{3:3}: [ 1297.072375] lock_acquire+0xd8/0x490 [ 1297.072710] __mutex_lock+0xa3/0xb30 [ 1297.073061] btrfs_qgroup_inherit+0x59/0x6a0 [btrfs] [ 1297.073421] create_subvol+0x194/0x990 [btrfs] [ 1297.073780] btrfs_mksubvol+0x3fb/0x4a0 [btrfs] [ 1297.074133] __btrfs_ioctl_snap_create+0x119/0x1a0 [btrfs] [ 1297.074498] btrfs_ioctl_snap_create+0x58/0x80 [btrfs] [ 1297.074872] btrfs_ioctl+0x1a90/0x36f0 [btrfs] [ 1297.075245] __x64_sys_ioctl+0x83/0xb0 [ 1297.075617] do_syscall_64+0x33/0x80 [ 1297.075993] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 1297.076380] -> #0 (sb_internal#2){.+.+}-{0:0}: [ 1297.077166] check_prev_add+0x91/0xc60 [ 1297.077572] __lock_acquire+0x1740/0x3110 [ 1297.077984] lock_acquire+0xd8/0x490 [ 1297.078411] start_transaction+0x3c5/0x760 [btrfs] [ 1297.078853] btrfs_quota_enable+0xaf/0xa70 [btrfs] [ 1297.079323] btrfs_ioctl+0x2c60/0x36f0 [btrfs] [ 1297.079789] __x64_sys_ioctl+0x83/0xb0 [ 1297.080232] do_syscall_64+0x33/0x80 [ 1297.080680] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 1297.081139] other info that might help us debug this: [ 1297.082536] Possible unsafe locking scenario: [ 1297.083510] CPU0 CPU1 [ 1297.084005] ---- ---- [ 1297.084500] lock(&fs_info->qgroup_ioctl_lock); [ 1297.084994] lock(sb_internal#2); [ 1297.085485] lock(&fs_info->qgroup_ioctl_lock); [ 1297.085974] lock(sb_internal#2); [ 1297.086454] *** DEADLOCK *** [ 1297.087880] 3 locks held by btrfs/189080: [ 1297.088324] #0: ffff9f2725731470 (sb_writers#14){.+.+}-{0:0}, at: btrfs_ioctl+0xa73/0x36f0 [btrfs] [ 1297.088799] #1: ffff9f2702b60cc0 (&fs_info->subvol_sem){++++}-{3:3}, at: btrfs_ioctl+0x1f4d/0x36f0 [btrfs] [ 1297.089284] #2: ffff9f2702b61a08 (&fs_info->qgroup_ioctl_lock){+.+.}-{3:3}, at: btrfs_quota_enable+0x3b/0xa70 [btrfs] [ 1297.089771] stack backtrace: [ 1297.090662] CPU: 5 PID: 189080 Comm: btrfs Not tainted 5.10.0-rc4-btrfs-next-73 #1 [ 1297.091132] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 1297.092123] Call Trace: [ 1297.092629] dump_stack+0x8d/0xb5 [ 1297.093115] check_noncircular+0xff/0x110 [ 1297.093596] check_prev_add+0x91/0xc60 [ 1297.094076] ? kvm_clock_read+0x14/0x30 [ 1297.094553] ? kvm_sched_clock_read+0x5/0x10 [ 1297.095029] __lock_acquire+0x1740/0x3110 [ 1297.095510] lock_acquire+0xd8/0x490 [ 1297.095993] ? btrfs_quota_enable+0xaf/0xa70 [btrfs] [ 1297.096476] start_transaction+0x3c5/0x760 [btrfs] [ 1297.096962] ? btrfs_quota_enable+0xaf/0xa70 [btrfs] [ 1297.097451] btrfs_quota_enable+0xaf/0xa70 [btrfs] [ 1297.097941] ? btrfs_ioctl+0x1f4d/0x36f0 [btrfs] [ 1297.098429] btrfs_ioctl+0x2c60/0x36f0 [btrfs] [ 1297.098904] ? do_user_addr_fault+0x20c/0x430 [ 1297.099382] ? kvm_clock_read+0x14/0x30 [ 1297.099854] ? kvm_sched_clock_read+0x5/0x10 [ 1297.100328] ? sched_clock+0x5/0x10 [ 1297.100801] ? sched_clock_cpu+0x12/0x180 [ 1297.101272] ? __x64_sys_ioctl+0x83/0xb0 [ 1297.101739] __x64_sys_ioctl+0x83/0xb0 [ 1297.102207] do_syscall_64+0x33/0x80 [ 1297.102673] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 1297.103148] RIP: 0033:0x7f773ff65d87 This is because during the quota enable ioctl we lock first the mutex qgroup_ioctl_lock and then start a transaction, and starting a transaction acquires a fs freeze semaphore (at the VFS level). However, every other code path, except for the quota disable ioctl path, we do the opposite: we start a transaction and then lock the mutex. So fix this by making the quota enable and disable paths to start the transaction without having the mutex locked, and then, after starting the transaction, lock the mutex and check if some other task already enabled or disabled the quotas, bailing with success if that was the case. Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 5 ++++- fs/btrfs/qgroup.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 53 insertions(+), 9 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0378933d163c..0b29bdb25105 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -878,7 +878,10 @@ struct btrfs_fs_info { */ struct ulist *qgroup_ulist; - /* protect user change for quota operations */ + /* + * Protect user change for quota operations. If a transaction is needed, + * it must be started before locking this lock. + */ struct mutex qgroup_ioctl_lock; /* list of dirty qgroups to be written at next commit */ diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index d690ef702522..87bd37b70738 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -937,6 +937,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) struct btrfs_key found_key; struct btrfs_qgroup *qgroup = NULL; struct btrfs_trans_handle *trans = NULL; + struct ulist *ulist = NULL; int ret = 0; int slot; @@ -944,8 +945,8 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) if (fs_info->quota_root) goto out; - fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL); - if (!fs_info->qgroup_ulist) { + ulist = ulist_alloc(GFP_KERNEL); + if (!ulist) { ret = -ENOMEM; goto out; } @@ -953,6 +954,22 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) ret = btrfs_sysfs_add_qgroups(fs_info); if (ret < 0) goto out; + + /* + * Unlock qgroup_ioctl_lock before starting the transaction. This is to + * avoid lock acquisition inversion problems (reported by lockdep) between + * qgroup_ioctl_lock and the vfs freeze semaphores, acquired when we + * start a transaction. + * After we started the transaction lock qgroup_ioctl_lock again and + * check if someone else created the quota root in the meanwhile. If so, + * just return success and release the transaction handle. + * + * Also we don't need to worry about someone else calling + * btrfs_sysfs_add_qgroups() after we unlock and getting an error because + * that function returns 0 (success) when the sysfs entries already exist. + */ + mutex_unlock(&fs_info->qgroup_ioctl_lock); + /* * 1 for quota root item * 1 for BTRFS_QGROUP_STATUS item @@ -962,12 +979,20 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) * would be a lot of overkill. */ trans = btrfs_start_transaction(tree_root, 2); + + mutex_lock(&fs_info->qgroup_ioctl_lock); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; goto out; } + if (fs_info->quota_root) + goto out; + + fs_info->qgroup_ulist = ulist; + ulist = NULL; + /* * initially create the quota tree */ @@ -1125,11 +1150,14 @@ out: if (ret) { ulist_free(fs_info->qgroup_ulist); fs_info->qgroup_ulist = NULL; - if (trans) - btrfs_end_transaction(trans); btrfs_sysfs_del_qgroups(fs_info); } mutex_unlock(&fs_info->qgroup_ioctl_lock); + if (ret && trans) + btrfs_end_transaction(trans); + else if (trans) + ret = btrfs_end_transaction(trans); + ulist_free(ulist); return ret; } @@ -1142,19 +1170,29 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) goto out; + mutex_unlock(&fs_info->qgroup_ioctl_lock); /* * 1 For the root item * * We should also reserve enough items for the quota tree deletion in * btrfs_clean_quota_tree but this is not done. + * + * Also, we must always start a transaction without holding the mutex + * qgroup_ioctl_lock, see btrfs_quota_enable(). */ trans = btrfs_start_transaction(fs_info->tree_root, 1); + + mutex_lock(&fs_info->qgroup_ioctl_lock); if (IS_ERR(trans)) { ret = PTR_ERR(trans); + trans = NULL; goto out; } + if (!fs_info->quota_root) + goto out; + clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); @@ -1168,13 +1206,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) ret = btrfs_clean_quota_tree(trans, quota_root); if (ret) { btrfs_abort_transaction(trans, ret); - goto end_trans; + goto out; } ret = btrfs_del_root(trans, "a_root->root_key); if (ret) { btrfs_abort_transaction(trans, ret); - goto end_trans; + goto out; } list_del("a_root->dirty_list); @@ -1186,10 +1224,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) btrfs_put_root(quota_root); -end_trans: - ret = btrfs_end_transaction(trans); out: mutex_unlock(&fs_info->qgroup_ioctl_lock); + if (ret && trans) + btrfs_end_transaction(trans); + else if (trans) + ret = btrfs_end_transaction(trans); + return ret; } -- cgit v1.2.3 From 6830ff853a5764c75e56750d59d0bbb6b26f1835 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Fri, 20 Nov 2020 09:57:02 +0800 Subject: IB/mthca: fix return value of error branch in mthca_init_cq() We return 'err' in the error branch, but this variable may be set as zero by the above code. Fix it by setting 'err' as a negative value before we goto the error label. Fixes: 74c2174e7be5 ("IB uverbs: add mthca user CQ support") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://lore.kernel.org/r/1605837422-42724-1-git-send-email-wangxiongfeng2@huawei.com Reported-by: Hulk Robot Signed-off-by: Xiongfeng Wang Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mthca/mthca_cq.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/mthca/mthca_cq.c b/drivers/infiniband/hw/mthca/mthca_cq.c index c3cfea243af8..119b2573c9a0 100644 --- a/drivers/infiniband/hw/mthca/mthca_cq.c +++ b/drivers/infiniband/hw/mthca/mthca_cq.c @@ -803,8 +803,10 @@ int mthca_init_cq(struct mthca_dev *dev, int nent, } mailbox = mthca_alloc_mailbox(dev, GFP_KERNEL); - if (IS_ERR(mailbox)) + if (IS_ERR(mailbox)) { + err = PTR_ERR(mailbox); goto err_out_arm; + } cq_context = mailbox->buf; @@ -846,9 +848,9 @@ int mthca_init_cq(struct mthca_dev *dev, int nent, } spin_lock_irq(&dev->cq_table.lock); - if (mthca_array_set(&dev->cq_table.cq, - cq->cqn & (dev->limits.num_cqs - 1), - cq)) { + err = mthca_array_set(&dev->cq_table.cq, + cq->cqn & (dev->limits.num_cqs - 1), cq); + if (err) { spin_unlock_irq(&dev->cq_table.lock); goto err_out_free_mr; } -- cgit v1.2.3 From 01770a166165738a6e05c3d911fb4609cc4eb416 Mon Sep 17 00:00:00 2001 From: Ricardo Dias Date: Fri, 20 Nov 2020 11:11:33 +0000 Subject: tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski --- include/net/inet_hashtables.h | 5 +-- net/dccp/ipv4.c | 2 +- net/dccp/ipv6.c | 2 +- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/inet_hashtables.c | 68 ++++++++++++++++++++++++++++++++++++----- net/ipv4/tcp_ipv4.c | 15 +++++++-- net/ipv6/tcp_ipv6.c | 13 +++++++- 7 files changed, 91 insertions(+), 16 deletions(-) diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 92560974ea67..ca6a3ea9057e 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -247,8 +247,9 @@ void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, unsigned long high_limit); int inet_hashinfo2_init_mod(struct inet_hashinfo *h); -bool inet_ehash_insert(struct sock *sk, struct sock *osk); -bool inet_ehash_nolisten(struct sock *sk, struct sock *osk); +bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk); +bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, + bool *found_dup_sk); int __inet_hash(struct sock *sk, struct sock *osk); int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index bb3d70664dde..b0b6e6a4784e 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -427,7 +427,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); if (*own_req) ireq->ireq_opt = NULL; else diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index ef4ab28cfde0..78ee1b5acf1f 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -533,7 +533,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, dccp_done(newsk); goto out; } - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); /* Clone pktoptions received with SYN, if we own the req */ if (*own_req && ireq->pktopts) { newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 4148f5f78f31..f60869acbef0 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -787,7 +787,7 @@ static void reqsk_queue_hash_req(struct request_sock *req, timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); - inet_ehash_insert(req_to_sk(req), NULL); + inet_ehash_insert(req_to_sk(req), NULL, NULL); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 8cbe74313f38..45fb450b4522 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -20,6 +20,9 @@ #include #include #include +#if IS_ENABLED(CONFIG_IPV6) +#include +#endif #include #include #include @@ -508,10 +511,52 @@ static u32 inet_sk_port_offset(const struct sock *sk) inet->inet_dport); } -/* insert a socket into ehash, and eventually remove another one - * (The another one can be a SYN_RECV or TIMEWAIT +/* Searches for an exsiting socket in the ehash bucket list. + * Returns true if found, false otherwise. */ -bool inet_ehash_insert(struct sock *sk, struct sock *osk) +static bool inet_ehash_lookup_by_sk(struct sock *sk, + struct hlist_nulls_head *list) +{ + const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport, sk->sk_num); + const int sdif = sk->sk_bound_dev_if; + const int dif = sk->sk_bound_dev_if; + const struct hlist_nulls_node *node; + struct net *net = sock_net(sk); + struct sock *esk; + + INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr); + + sk_nulls_for_each_rcu(esk, node, list) { + if (esk->sk_hash != sk->sk_hash) + continue; + if (sk->sk_family == AF_INET) { + if (unlikely(INET_MATCH(esk, net, acookie, + sk->sk_daddr, + sk->sk_rcv_saddr, + ports, dif, sdif))) { + return true; + } + } +#if IS_ENABLED(CONFIG_IPV6) + else if (sk->sk_family == AF_INET6) { + if (unlikely(INET6_MATCH(esk, net, + &sk->sk_v6_daddr, + &sk->sk_v6_rcv_saddr, + ports, dif, sdif))) { + return true; + } + } +#endif + } + return false; +} + +/* Insert a socket into ehash, and eventually remove another one + * (The another one can be a SYN_RECV or TIMEWAIT) + * If an existing socket already exists, socket sk is not inserted, + * and sets found_dup_sk parameter to true. + */ +bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct hlist_nulls_head *list; @@ -530,16 +575,23 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk) if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); ret = sk_nulls_del_node_init_rcu(osk); + } else if (found_dup_sk) { + *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); + if (*found_dup_sk) + ret = false; } + if (ret) __sk_nulls_add_node_rcu(sk, list); + spin_unlock(lock); + return ret; } -bool inet_ehash_nolisten(struct sock *sk, struct sock *osk) +bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk) { - bool ok = inet_ehash_insert(sk, osk); + bool ok = inet_ehash_insert(sk, osk, found_dup_sk); if (ok) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -583,7 +635,7 @@ int __inet_hash(struct sock *sk, struct sock *osk) int err = 0; if (sk->sk_state != TCP_LISTEN) { - inet_ehash_nolisten(sk, osk); + inet_ehash_nolisten(sk, osk, NULL); return 0; } WARN_ON(!sk_unhashed(sk)); @@ -679,7 +731,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, tb = inet_csk(sk)->icsk_bind_hash; spin_lock_bh(&head->lock); if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) { - inet_ehash_nolisten(sk, NULL); + inet_ehash_nolisten(sk, NULL, NULL); spin_unlock_bh(&head->lock); return 0; } @@ -758,7 +810,7 @@ ok: inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); - inet_ehash_nolisten(sk, (struct sock *)tw); + inet_ehash_nolisten(sk, (struct sock *)tw, NULL); } if (tw) inet_twsk_bind_unhash(tw, hinfo); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 25d35a56ceba..c95fcdfeed42 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1499,6 +1499,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, bool *own_req) { struct inet_request_sock *ireq; + bool found_dup_sk = false; struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; @@ -1576,12 +1577,22 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), + &found_dup_sk); if (likely(*own_req)) { tcp_move_syn(newtp, req); ireq->ireq_opt = NULL; } else { - newinet->inet_opt = NULL; + if (!req_unhash && found_dup_sk) { + /* This code path should only be executed in the + * syncookie case only + */ + bh_unlock_sock(newsk); + sock_put(newsk); + newsk = NULL; + } else { + newinet->inet_opt = NULL; + } } return newsk; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 3d49e8d0afee..d2502911b7fa 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1193,6 +1193,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * const struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct ipv6_txoptions *opt; struct inet_sock *newinet; + bool found_dup_sk = false; struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG @@ -1368,7 +1369,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * tcp_done(newsk); goto out; } - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), + &found_dup_sk); if (*own_req) { tcp_move_syn(newtp, req); @@ -1383,6 +1385,15 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * skb_set_owner_r(newnp->pktoptions, newsk); } } + } else { + if (!req_unhash && found_dup_sk) { + /* This code path should only be executed in the + * syncookie case only + */ + bh_unlock_sock(newsk); + sock_put(newsk); + newsk = NULL; + } } return newsk; -- cgit v1.2.3 From 3fe356d58efae54dade9ec94ea7c919ed20cf4db Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 20 Nov 2020 11:47:36 +0100 Subject: vsock/virtio: discard packets only when socket is really closed Starting from commit 8692cefc433f ("virtio_vsock: Fix race condition in virtio_transport_recv_pkt"), we discard packets in virtio_transport_recv_pkt() if the socket has been released. When the socket is connected, we schedule a delayed work to wait the RST packet from the other peer, also if SHUTDOWN_MASK is set in sk->sk_shutdown. This is done to complete the virtio-vsock shutdown algorithm, releasing the port assigned to the socket definitively only when the other peer has consumed all the packets. If we discard the RST packet received, the socket will be closed only when the VSOCK_CLOSE_TIMEOUT is reached. Sergio discovered the issue while running ab(1) HTTP benchmark using libkrun [1] and observing a latency increase with that commit. To avoid this issue, we discard packet only if the socket is really closed (SOCK_DONE flag is set). We also set SOCK_DONE in virtio_transport_release() when we don't need to wait any packets from the other peer (we didn't schedule the delayed work). In this case we remove the socket from the vsock lists, releasing the port assigned. [1] https://github.com/containers/libkrun Fixes: 8692cefc433f ("virtio_vsock: Fix race condition in virtio_transport_recv_pkt") Cc: justin.he@arm.com Reported-by: Sergio Lopez Tested-by: Sergio Lopez Signed-off-by: Stefano Garzarella Acked-by: Jia He Link: https://lore.kernel.org/r/20201120104736.73749-1-sgarzare@redhat.com Signed-off-by: Jakub Kicinski --- net/vmw_vsock/virtio_transport_common.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 0edda1edf988..5956939eebb7 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -841,8 +841,10 @@ void virtio_transport_release(struct vsock_sock *vsk) virtio_transport_free_pkt(pkt); } - if (remove_sock) + if (remove_sock) { + sock_set_flag(sk, SOCK_DONE); vsock_remove_sock(vsk); + } } EXPORT_SYMBOL_GPL(virtio_transport_release); @@ -1132,8 +1134,8 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, lock_sock(sk); - /* Check if sk has been released before lock_sock */ - if (sk->sk_shutdown == SHUTDOWN_MASK) { + /* Check if sk has been closed before lock_sock */ + if (sock_flag(sk, SOCK_DONE)) { (void)virtio_transport_reset_no_sock(t, pkt); release_sock(sk); sock_put(sk); -- cgit v1.2.3 From 2980cbd4dce7b1e9bf57df3ced43a7b184986f50 Mon Sep 17 00:00:00 2001 From: Sylwester Dziedziuch Date: Fri, 20 Nov 2020 10:06:40 -0800 Subject: i40e: Fix removing driver while bare-metal VFs pass traffic Prevent VFs from resetting when PF driver is being unloaded: - introduce new pf state: __I40E_VF_RESETS_DISABLED; - check if pf state has __I40E_VF_RESETS_DISABLED state set, if so, disable any further VFLR event notifications; - when i40e_remove (rmmod i40e) is called, disable any resets on the VFs; Previously if there were bare-metal VFs passing traffic and PF driver was removed, there was a possibility of VFs triggering a Tx timeout right before iavf_remove. This was causing iavf_close to not be called because there is a check in the beginning of iavf_remove that bails out early if adapter->state < IAVF_DOWN_PENDING. This makes it so some resources do not get cleaned up. Fixes: 6a9ddb36eeb8 ("i40e: disable IOV before freeing resources") Signed-off-by: Slawomir Laba Signed-off-by: Brett Creeley Signed-off-by: Sylwester Dziedziuch Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen Link: https://lore.kernel.org/r/20201120180640.3654474-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/i40e/i40e.h | 1 + drivers/net/ethernet/intel/i40e/i40e_main.c | 22 ++++++++++++------ drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 26 +++++++++++++--------- 3 files changed, 31 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 537300e762f0..d231a2cdd98f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -140,6 +140,7 @@ enum i40e_state_t { __I40E_CLIENT_RESET, __I40E_VIRTCHNL_OP_PENDING, __I40E_RECOVERY_MODE, + __I40E_VF_RESETS_DISABLED, /* disable resets during i40e_remove */ /* This must be last as it determines the size of the BITMAP */ __I40E_STATE_SIZE__, }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 4f8a2154b93f..1337686bd099 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4010,8 +4010,16 @@ static irqreturn_t i40e_intr(int irq, void *data) } if (icr0 & I40E_PFINT_ICR0_VFLR_MASK) { - ena_mask &= ~I40E_PFINT_ICR0_ENA_VFLR_MASK; - set_bit(__I40E_VFLR_EVENT_PENDING, pf->state); + /* disable any further VFLR event notifications */ + if (test_bit(__I40E_VF_RESETS_DISABLED, pf->state)) { + u32 reg = rd32(hw, I40E_PFINT_ICR0_ENA); + + reg &= ~I40E_PFINT_ICR0_VFLR_MASK; + wr32(hw, I40E_PFINT_ICR0_ENA, reg); + } else { + ena_mask &= ~I40E_PFINT_ICR0_ENA_VFLR_MASK; + set_bit(__I40E_VFLR_EVENT_PENDING, pf->state); + } } if (icr0 & I40E_PFINT_ICR0_GRST_MASK) { @@ -15311,6 +15319,11 @@ static void i40e_remove(struct pci_dev *pdev) while (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) usleep_range(1000, 2000); + if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { + set_bit(__I40E_VF_RESETS_DISABLED, pf->state); + i40e_free_vfs(pf); + pf->flags &= ~I40E_FLAG_SRIOV_ENABLED; + } /* no more scheduling of any task */ set_bit(__I40E_SUSPENDED, pf->state); set_bit(__I40E_DOWN, pf->state); @@ -15337,11 +15350,6 @@ static void i40e_remove(struct pci_dev *pdev) */ i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false); - if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { - i40e_free_vfs(pf); - pf->flags &= ~I40E_FLAG_SRIOV_ENABLED; - } - i40e_fdir_teardown(pf); /* If there is a switch structure or any orphans, remove them. diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 4919d22d7b6b..1b5390ec3d78 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1403,7 +1403,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf) * @vf: pointer to the VF structure * @flr: VFLR was issued or not * - * Returns true if the VF is reset, false otherwise. + * Returns true if the VF is in reset, resets successfully, or resets + * are disabled and false otherwise. **/ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) { @@ -1413,11 +1414,14 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) u32 reg; int i; + if (test_bit(__I40E_VF_RESETS_DISABLED, pf->state)) + return true; + /* If the VFs have been disabled, this means something else is * resetting the VF, so we shouldn't continue. */ if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) - return false; + return true; i40e_trigger_vf_reset(vf, flr); @@ -1581,6 +1585,15 @@ void i40e_free_vfs(struct i40e_pf *pf) i40e_notify_client_of_vf_enable(pf, 0); + /* Disable IOV before freeing resources. This lets any VF drivers + * running in the host get themselves cleaned up before we yank + * the carpet out from underneath their feet. + */ + if (!pci_vfs_assigned(pf->pdev)) + pci_disable_sriov(pf->pdev); + else + dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n"); + /* Amortize wait time by stopping all VFs at the same time */ for (i = 0; i < pf->num_alloc_vfs; i++) { if (test_bit(I40E_VF_STATE_INIT, &pf->vf[i].vf_states)) @@ -1596,15 +1609,6 @@ void i40e_free_vfs(struct i40e_pf *pf) i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[i].lan_vsi_idx]); } - /* Disable IOV before freeing resources. This lets any VF drivers - * running in the host get themselves cleaned up before we yank - * the carpet out from underneath their feet. - */ - if (!pci_vfs_assigned(pf->pdev)) - pci_disable_sriov(pf->pdev); - else - dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n"); - /* free up VF resources */ tmp = pf->num_alloc_vfs; pf->num_alloc_vfs = 0; -- cgit v1.2.3 From 2663b3388551230cbc4606a40fabf3331ceb59e4 Mon Sep 17 00:00:00 2001 From: Hao Si Date: Tue, 20 Oct 2020 10:18:32 +0800 Subject: soc: fsl: dpio: Get the cpumask through cpumask_of(cpu) The local variable 'cpumask_t mask' is in the stack memory, and its address is assigned to 'desc->affinity' in 'irq_set_affinity_hint()'. But the memory area where this variable is located is at risk of being modified. During LTP testing, the following error was generated: Unable to handle kernel paging request at virtual address ffff000012e9b790 Mem abort info: ESR = 0x96000007 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000007 CM = 0, WnR = 0 swapper pgtable: 4k pages, 48-bit VAs, pgdp = 0000000075ac5e07 [ffff000012e9b790] pgd=00000027dbffe003, pud=00000027dbffd003, pmd=00000027b6d61003, pte=0000000000000000 Internal error: Oops: 96000007 [#1] PREEMPT SMP Modules linked in: xt_conntrack Process read_all (pid: 20171, stack limit = 0x0000000044ea4095) CPU: 14 PID: 20171 Comm: read_all Tainted: G B W Hardware name: NXP Layerscape LX2160ARDB (DT) pstate: 80000085 (Nzcv daIf -PAN -UAO) pc : irq_affinity_hint_proc_show+0x54/0xb0 lr : irq_affinity_hint_proc_show+0x4c/0xb0 sp : ffff00001138bc10 x29: ffff00001138bc10 x28: 0000ffffd131d1e0 x27: 00000000007000c0 x26: ffff8025b9480dc0 x25: ffff8025b9480da8 x24: 00000000000003ff x23: ffff8027334f8300 x22: ffff80272e97d000 x21: ffff80272e97d0b0 x20: ffff8025b9480d80 x19: ffff000009a49000 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000040 x11: 0000000000000000 x10: ffff802735b79b88 x9 : 0000000000000000 x8 : 0000000000000000 x7 : ffff000009a49848 x6 : 0000000000000003 x5 : 0000000000000000 x4 : ffff000008157d6c x3 : ffff00001138bc10 x2 : ffff000012e9b790 x1 : 0000000000000000 x0 : 0000000000000000 Call trace: irq_affinity_hint_proc_show+0x54/0xb0 seq_read+0x1b0/0x440 proc_reg_read+0x80/0xd8 __vfs_read+0x60/0x178 vfs_read+0x94/0x150 ksys_read+0x74/0xf0 __arm64_sys_read+0x24/0x30 el0_svc_common.constprop.0+0xd8/0x1a0 el0_svc_handler+0x34/0x88 el0_svc+0x10/0x14 Code: f9001bbf 943e0732 f94066c2 b4000062 (f9400041) ---[ end trace b495bdcb0b3b732b ]--- Kernel panic - not syncing: Fatal exception SMP: stopping secondary CPUs SMP: failed to stop secondary CPUs 0,2-4,6,8,11,13-15 Kernel Offset: disabled CPU features: 0x0,21006008 Memory Limit: none ---[ end Kernel panic - not syncing: Fatal exception ]--- Fix it by using 'cpumask_of(cpu)' to get the cpumask. Signed-off-by: Hao Si Signed-off-by: Lin Chen Signed-off-by: Yi Wang Signed-off-by: Li Yang --- drivers/soc/fsl/dpio/dpio-driver.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/soc/fsl/dpio/dpio-driver.c b/drivers/soc/fsl/dpio/dpio-driver.c index 7b642c330977..7f397b4ad878 100644 --- a/drivers/soc/fsl/dpio/dpio-driver.c +++ b/drivers/soc/fsl/dpio/dpio-driver.c @@ -95,7 +95,6 @@ static int register_dpio_irq_handlers(struct fsl_mc_device *dpio_dev, int cpu) { int error; struct fsl_mc_device_irq *irq; - cpumask_t mask; irq = dpio_dev->irqs[0]; error = devm_request_irq(&dpio_dev->dev, @@ -112,9 +111,7 @@ static int register_dpio_irq_handlers(struct fsl_mc_device *dpio_dev, int cpu) } /* set the affinity hint */ - cpumask_clear(&mask); - cpumask_set_cpu(cpu, &mask); - if (irq_set_affinity_hint(irq->msi_desc->irq, &mask)) + if (irq_set_affinity_hint(irq->msi_desc->irq, cpumask_of(cpu))) dev_err(&dpio_dev->dev, "irq_set_affinity failed irq %d cpu %d\n", irq->msi_desc->irq, cpu); -- cgit v1.2.3 From d549699048b4b5c22dd710455bcdb76966e55aa3 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Sat, 21 Nov 2020 08:28:17 +0200 Subject: net/packet: fix packet receive on L3 devices without visible hard header In the patchset merged by commit b9fcf0a0d826 ("Merge branch 'support-AF_PACKET-for-layer-3-devices'") L3 devices which did not have header_ops were given one for the purpose of protocol parsing on af_packet transmit path. That change made af_packet receive path regard these devices as having a visible L3 header and therefore aligned incoming skb->data to point to the skb's mac_header. Some devices, such as ipip, xfrmi, and others, do not reset their mac_header prior to ingress and therefore their incoming packets became malformed. Ideally these devices would reset their mac headers, or af_packet would be able to rely on dev->hard_header_len being 0 for such cases, but it seems this is not the case. Fix by changing af_packet RX ll visibility criteria to include the existence of a '.create()' header operation, which is used when creating a device hard header - via dev_hard_header() - by upper layers, and does not exist in these L3 devices. As this predicate may be useful in other situations, add it as a common dev_has_header() helper in netdevice.h. Fixes: b9fcf0a0d826 ("Merge branch 'support-AF_PACKET-for-layer-3-devices'") Signed-off-by: Eyal Birger Acked-by: Jason A. Donenfeld Acked-by: Willem de Bruijn Link: https://lore.kernel.org/r/20201121062817.3178900-1-eyal.birger@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 5 +++++ net/packet/af_packet.c | 18 +++++++++--------- 2 files changed, 14 insertions(+), 9 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 964b494b0e8d..fa275a054f46 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3137,6 +3137,11 @@ static inline bool dev_validate_header(const struct net_device *dev, return false; } +static inline bool dev_has_header(const struct net_device *dev) +{ + return dev->header_ops && dev->header_ops->create; +} + typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len, int size); int register_gifconf(unsigned int family, gifconf_func_t *gifconf); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index cefbd50c1090..7a18ffff8551 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -93,8 +93,8 @@ /* Assumptions: - - If the device has no dev->header_ops, there is no LL header visible - above the device. In this case, its hard_header_len should be 0. + - If the device has no dev->header_ops->create, there is no LL header + visible above the device. In this case, its hard_header_len should be 0. The device may prepend its own header internally. In this case, its needed_headroom should be set to the space needed for it to add its internal header. @@ -108,26 +108,26 @@ On receive: ----------- -Incoming, dev->header_ops != NULL +Incoming, dev_has_header(dev) == true mac_header -> ll header data -> data -Outgoing, dev->header_ops != NULL +Outgoing, dev_has_header(dev) == true mac_header -> ll header data -> ll header -Incoming, dev->header_ops == NULL +Incoming, dev_has_header(dev) == false mac_header -> data However drivers often make it point to the ll header. This is incorrect because the ll header should be invisible to us. data -> data -Outgoing, dev->header_ops == NULL +Outgoing, dev_has_header(dev) == false mac_header -> data. ll header is invisible to us. data -> data Resume - If dev->header_ops == NULL we are unable to restore the ll header, + If dev_has_header(dev) == false we are unable to restore the ll header, because it is invisible to us. @@ -2069,7 +2069,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, skb->dev = dev; - if (dev->header_ops) { + if (dev_has_header(dev)) { /* The device has an explicit notion of ll header, * exported to higher levels. * @@ -2198,7 +2198,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; - if (dev->header_ops) { + if (dev_has_header(dev)) { if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { -- cgit v1.2.3 From 903a72eca4abf241293dcc1385896fd428e15fe9 Mon Sep 17 00:00:00 2001 From: yong mao Date: Thu, 19 Nov 2020 11:02:37 +0800 Subject: mmc: mediatek: Extend recheck_sdio_irq fix to more variants The SDIO recheck fix is required for more of the supported variants. Let's add it to those that needs it. Reported-by: Fabien Parent Reported-by: Mattijs Korpershoek Signed-off-by: Yong Mao Link: https://lore.kernel.org/r/20201119030237.9414-1-yong.mao@mediatek.com Fixes: 9e2582e57407 ("mmc: mediatek: fix SDIO irq issue") Cc: stable@vger.kernel.org [Ulf: Clarified commitmsg ] Signed-off-by: Ulf Hansson --- drivers/mmc/host/mtk-sd.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index b40ec966288e..7eb99255ae3d 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -446,7 +446,7 @@ struct msdc_host { static const struct mtk_mmc_compatible mt8135_compat = { .clk_div_bits = 8, - .recheck_sdio_irq = false, + .recheck_sdio_irq = true, .hs400_tune = false, .pad_tune_reg = MSDC_PAD_TUNE, .async_fifo = false, @@ -485,7 +485,7 @@ static const struct mtk_mmc_compatible mt8183_compat = { static const struct mtk_mmc_compatible mt2701_compat = { .clk_div_bits = 12, - .recheck_sdio_irq = false, + .recheck_sdio_irq = true, .hs400_tune = false, .pad_tune_reg = MSDC_PAD_TUNE0, .async_fifo = true, @@ -511,7 +511,7 @@ static const struct mtk_mmc_compatible mt2712_compat = { static const struct mtk_mmc_compatible mt7622_compat = { .clk_div_bits = 12, - .recheck_sdio_irq = false, + .recheck_sdio_irq = true, .hs400_tune = false, .pad_tune_reg = MSDC_PAD_TUNE0, .async_fifo = true, @@ -524,7 +524,7 @@ static const struct mtk_mmc_compatible mt7622_compat = { static const struct mtk_mmc_compatible mt8516_compat = { .clk_div_bits = 12, - .recheck_sdio_irq = false, + .recheck_sdio_irq = true, .hs400_tune = false, .pad_tune_reg = MSDC_PAD_TUNE0, .async_fifo = true, @@ -535,7 +535,7 @@ static const struct mtk_mmc_compatible mt8516_compat = { static const struct mtk_mmc_compatible mt7620_compat = { .clk_div_bits = 8, - .recheck_sdio_irq = false, + .recheck_sdio_irq = true, .hs400_tune = false, .pad_tune_reg = MSDC_PAD_TUNE, .async_fifo = false, @@ -548,6 +548,7 @@ static const struct mtk_mmc_compatible mt7620_compat = { static const struct mtk_mmc_compatible mt6779_compat = { .clk_div_bits = 12, + .recheck_sdio_irq = false, .hs400_tune = false, .pad_tune_reg = MSDC_PAD_TUNE0, .async_fifo = true, -- cgit v1.2.3 From a42a7ec9bb99a17869c3b9f3d365aaf2bdb1a554 Mon Sep 17 00:00:00 2001 From: Muhammad Husaini Zulkifli Date: Wed, 18 Nov 2020 20:01:20 +0800 Subject: mmc: sdhci-of-arasan: Fix clock registration error for Keem Bay SOC The commit 16ada730a759 ("mmc: sdhci-of-arasan: Modify clock operations handling") introduced support for platform specific clock operations. Around the same point in time the commit 36c6aadaae86 ("mmc: sdhci-of-arasan: Add support for Intel Keem Bay") was also merged. Unfortunate it was not really tested on top of the previously mentioned commit, which causes clock registration failures for Keem Bay SOC devices. Let's fix this, by properly declaring the clock operation for Keem Bay SOC devices. Fixes: 36c6aadaae86 ("mmc: sdhci-of-arasan: Add support for Intel Keem Bay") Signed-off-by: Muhammad Husaini Zulkifli Reviewed-by: Adrian Hunter Link: https://lore.kernel.org/r/20201118120120.24908-2-muhammad.husaini.zulkifli@intel.com Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-of-arasan.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c index d25a4b50c2f3..3b8d456e857d 100644 --- a/drivers/mmc/host/sdhci-of-arasan.c +++ b/drivers/mmc/host/sdhci-of-arasan.c @@ -1186,16 +1186,19 @@ static struct sdhci_arasan_of_data sdhci_arasan_versal_data = { static struct sdhci_arasan_of_data intel_keembay_emmc_data = { .soc_ctl_map = &intel_keembay_soc_ctl_map, .pdata = &sdhci_keembay_emmc_pdata, + .clk_ops = &arasan_clk_ops, }; static struct sdhci_arasan_of_data intel_keembay_sd_data = { .soc_ctl_map = &intel_keembay_soc_ctl_map, .pdata = &sdhci_keembay_sd_pdata, + .clk_ops = &arasan_clk_ops, }; static struct sdhci_arasan_of_data intel_keembay_sdio_data = { .soc_ctl_map = &intel_keembay_soc_ctl_map, .pdata = &sdhci_keembay_sdio_pdata, + .clk_ops = &arasan_clk_ops, }; static const struct of_device_id sdhci_arasan_of_match[] = { -- cgit v1.2.3 From fd8d9db3559a29fd737bcdb7c4fcbe1940caae34 Mon Sep 17 00:00:00 2001 From: Xiaochen Shen Date: Sat, 31 Oct 2020 03:10:53 +0800 Subject: x86/resctrl: Remove superfluous kernfs_get() calls to prevent refcount leak Willem reported growing of kernfs_node_cache entries in slabtop when repeatedly creating and removing resctrl subdirectories as well as when repeatedly mounting and unmounting the resctrl filesystem. On resource group (control as well as monitoring) creation via a mkdir an extra kernfs_node reference is obtained to ensure that the rdtgroup structure remains accessible for the rdtgroup_kn_unlock() calls where it is removed on deletion. The kernfs_node reference count is dropped by kernfs_put() in rdtgroup_kn_unlock(). With the above explaining the need for one kernfs_get()/kernfs_put() pair in resctrl there are more places where a kernfs_node reference is obtained without a corresponding release. The excessive amount of reference count on kernfs nodes will never be dropped to 0 and the kernfs nodes will never be freed in the call paths of rmdir and umount. It leads to reference count leak and kernfs_node_cache memory leak. Remove the superfluous kernfs_get() calls and expand the existing comments surrounding the remaining kernfs_get()/kernfs_put() pair that remains in use. Superfluous kernfs_get() calls are removed from two areas: (1) In call paths of mount and mkdir, when kernfs nodes for "info", "mon_groups" and "mon_data" directories and sub-directories are created, the reference count of newly created kernfs node is set to 1. But after kernfs_create_dir() returns, superfluous kernfs_get() are called to take an additional reference. (2) kernfs_get() calls in rmdir call paths. Fixes: 17eafd076291 ("x86/intel_rdt: Split resource group removal in two") Fixes: 4af4a88e0c92 ("x86/intel_rdt/cqm: Add mount,umount support") Fixes: f3cbeacaa06e ("x86/intel_rdt/cqm: Add rmdir support") Fixes: d89b7379015f ("x86/intel_rdt/cqm: Add mon_data") Fixes: c7d9aac61311 ("x86/intel_rdt/cqm: Add mkdir support for RDT monitoring") Fixes: 5dc1d5c6bac2 ("x86/intel_rdt: Simplify info and base file lists") Fixes: 60cf5e101fd4 ("x86/intel_rdt: Add mkdir to resctrl file system") Fixes: 4e978d06dedb ("x86/intel_rdt: Add "info" files to resctrl file system") Reported-by: Willem de Bruijn Signed-off-by: Xiaochen Shen Signed-off-by: Borislav Petkov Reviewed-by: Reinette Chatre Tested-by: Willem de Bruijn Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1604085053-31639-1-git-send-email-xiaochen.shen@intel.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 35 ++-------------------------------- 1 file changed, 2 insertions(+), 33 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index af323e2e3100..2ab1266a5f14 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1769,7 +1769,6 @@ static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, if (IS_ERR(kn_subdir)) return PTR_ERR(kn_subdir); - kernfs_get(kn_subdir); ret = rdtgroup_kn_set_ugid(kn_subdir); if (ret) return ret; @@ -1792,7 +1791,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); if (IS_ERR(kn_info)) return PTR_ERR(kn_info); - kernfs_get(kn_info); ret = rdtgroup_add_files(kn_info, RF_TOP_INFO); if (ret) @@ -1813,12 +1811,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) goto out_destroy; } - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that @rdtgrp->kn is always accessible. - */ - kernfs_get(kn_info); - ret = rdtgroup_kn_set_ugid(kn_info); if (ret) goto out_destroy; @@ -1847,12 +1839,6 @@ mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, if (dest_kn) *dest_kn = kn; - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that @rdtgrp->kn is always accessible. - */ - kernfs_get(kn); - ret = rdtgroup_kn_set_ugid(kn); if (ret) goto out_destroy; @@ -2139,13 +2125,11 @@ static int rdt_get_tree(struct fs_context *fc) &kn_mongrp); if (ret < 0) goto out_info; - kernfs_get(kn_mongrp); ret = mkdir_mondata_all(rdtgroup_default.kn, &rdtgroup_default, &kn_mondata); if (ret < 0) goto out_mongrp; - kernfs_get(kn_mondata); rdtgroup_default.mon.mon_data_kn = kn_mondata; } @@ -2499,11 +2483,6 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, if (IS_ERR(kn)) return PTR_ERR(kn); - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that kn is always accessible. - */ - kernfs_get(kn); ret = rdtgroup_kn_set_ugid(kn); if (ret) goto out_destroy; @@ -2838,8 +2817,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, /* * kernfs_remove() will drop the reference count on "kn" which * will free it. But we still need it to stick around for the - * rdtgroup_kn_unlock(kn} call below. Take one extra reference - * here, which will be dropped inside rdtgroup_kn_unlock(). + * rdtgroup_kn_unlock(kn) call. Take one extra reference here, + * which will be dropped inside rdtgroup_kn_unlock(). */ kernfs_get(kn); @@ -3049,11 +3028,6 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); list_del(&rdtgrp->mon.crdtgrp_list); - /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); kernfs_remove(rdtgrp->kn); return 0; @@ -3065,11 +3039,6 @@ static int rdtgroup_ctrl_remove(struct kernfs_node *kn, rdtgrp->flags = RDT_DELETED; list_del(&rdtgrp->rdtgroup_list); - /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); kernfs_remove(rdtgrp->kn); return 0; } -- cgit v1.2.3 From 758999246965eeb8b253d47e72f7bfe508804b16 Mon Sep 17 00:00:00 2001 From: Xiaochen Shen Date: Sat, 31 Oct 2020 03:11:28 +0800 Subject: x86/resctrl: Add necessary kernfs_put() calls to prevent refcount leak On resource group creation via a mkdir an extra kernfs_node reference is obtained by kernfs_get() to ensure that the rdtgroup structure remains accessible for the rdtgroup_kn_unlock() calls where it is removed on deletion. Currently the extra kernfs_node reference count is only dropped by kernfs_put() in rdtgroup_kn_unlock() while the rdtgroup structure is removed in a few other locations that lack the matching reference drop. In call paths of rmdir and umount, when a control group is removed, kernfs_remove() is called to remove the whole kernfs nodes tree of the control group (including the kernfs nodes trees of all child monitoring groups), and then rdtgroup structure is freed by kfree(). The rdtgroup structures of all child monitoring groups under the control group are freed by kfree() in free_all_child_rdtgrp(). Before calling kfree() to free the rdtgroup structures, the kernfs node of the control group itself as well as the kernfs nodes of all child monitoring groups still take the extra references which will never be dropped to 0 and the kernfs nodes will never be freed. It leads to reference count leak and kernfs_node_cache memory leak. For example, reference count leak is observed in these two cases: (1) mount -t resctrl resctrl /sys/fs/resctrl mkdir /sys/fs/resctrl/c1 mkdir /sys/fs/resctrl/c1/mon_groups/m1 umount /sys/fs/resctrl (2) mkdir /sys/fs/resctrl/c1 mkdir /sys/fs/resctrl/c1/mon_groups/m1 rmdir /sys/fs/resctrl/c1 The same reference count leak issue also exists in the error exit paths of mkdir in mkdir_rdt_prepare() and rdtgroup_mkdir_ctrl_mon(). Fix this issue by following changes to make sure the extra kernfs_node reference on rdtgroup is dropped before freeing the rdtgroup structure. (1) Introduce rdtgroup removal helper rdtgroup_remove() to wrap up kernfs_put() and kfree(). (2) Call rdtgroup_remove() in rdtgroup removal path where the rdtgroup structure is about to be freed by kfree(). (3) Call rdtgroup_remove() or kernfs_put() as appropriate in the error exit paths of mkdir where an extra reference is taken by kernfs_get(). Fixes: f3cbeacaa06e ("x86/intel_rdt/cqm: Add rmdir support") Fixes: e02737d5b826 ("x86/intel_rdt: Add tasks files") Fixes: 60cf5e101fd4 ("x86/intel_rdt: Add mkdir to resctrl file system") Reported-by: Willem de Bruijn Signed-off-by: Xiaochen Shen Signed-off-by: Borislav Petkov Reviewed-by: Reinette Chatre Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1604085088-31707-1-git-send-email-xiaochen.shen@intel.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 32 +++++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 2ab1266a5f14..6f4ca4bea625 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -507,6 +507,24 @@ unlock: return ret ?: nbytes; } +/** + * rdtgroup_remove - the helper to remove resource group safely + * @rdtgrp: resource group to remove + * + * On resource group creation via a mkdir, an extra kernfs_node reference is + * taken to ensure that the rdtgroup structure remains accessible for the + * rdtgroup_kn_unlock() calls where it is removed. + * + * Drop the extra reference here, then free the rdtgroup structure. + * + * Return: void + */ +static void rdtgroup_remove(struct rdtgroup *rdtgrp) +{ + kernfs_put(rdtgrp->kn); + kfree(rdtgrp); +} + struct task_move_callback { struct callback_head work; struct rdtgroup *rdtgrp; @@ -529,7 +547,7 @@ static void move_myself(struct callback_head *head) (rdtgrp->flags & RDT_DELETED)) { current->closid = 0; current->rmid = 0; - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } if (unlikely(current->flags & PF_EXITING)) @@ -2065,8 +2083,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) rdtgroup_pseudo_lock_remove(rdtgrp); kernfs_unbreak_active_protection(kn); - kernfs_put(rdtgrp->kn); - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } else { kernfs_unbreak_active_protection(kn); } @@ -2341,7 +2358,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) if (atomic_read(&sentry->waitcount) != 0) sentry->flags = RDT_DELETED; else - kfree(sentry); + rdtgroup_remove(sentry); } } @@ -2383,7 +2400,7 @@ static void rmdir_all_sub(void) if (atomic_read(&rdtgrp->waitcount) != 0) rdtgrp->flags = RDT_DELETED; else - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ update_closid_rmid(cpu_online_mask, &rdtgroup_default); @@ -2818,7 +2835,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, * kernfs_remove() will drop the reference count on "kn" which * will free it. But we still need it to stick around for the * rdtgroup_kn_unlock(kn) call. Take one extra reference here, - * which will be dropped inside rdtgroup_kn_unlock(). + * which will be dropped by kernfs_put() in rdtgroup_remove(). */ kernfs_get(kn); @@ -2859,6 +2876,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, out_idfree: free_rmid(rdtgrp->mon.rmid); out_destroy: + kernfs_put(rdtgrp->kn); kernfs_remove(rdtgrp->kn); out_free_rgrp: kfree(rdtgrp); @@ -2871,7 +2889,7 @@ static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) { kernfs_remove(rgrp->kn); free_rmid(rgrp->mon.rmid); - kfree(rgrp); + rdtgroup_remove(rgrp); } /* -- cgit v1.2.3 From eeacd80fcb29b769ea915cd06b7dd35e0bf0bc25 Mon Sep 17 00:00:00 2001 From: Jian-Hong Pan Date: Tue, 24 Nov 2020 17:20:25 +0800 Subject: ALSA: hda/realtek: Enable headset of ASUS UX482EG & B9400CEA with ALC294 Some laptops like ASUS UX482EG & B9400CEA's headset audio does not work until the quirk ALC294_FIXUP_ASUS_HPE is applied. Signed-off-by: Jian-Hong Pan Cc: Link: https://lore.kernel.org/r/20201124092024.179540-1-jhp@endlessos.org Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b90cd4c65b58..34ad24d2c970 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8625,6 +8625,9 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE, ALC292_STANDARD_PINS, {0x13, 0x90a60140}), + SND_HDA_PIN_QUIRK(0x10ec0294, 0x1043, "ASUS", ALC294_FIXUP_ASUS_HPE, + {0x17, 0x90170110}, + {0x21, 0x04211020}), SND_HDA_PIN_QUIRK(0x10ec0294, 0x1043, "ASUS", ALC294_FIXUP_ASUS_MIC, {0x14, 0x90170110}, {0x1b, 0x90a70130}, -- cgit v1.2.3 From f4426311f927b01776edf8a45f6fad90feae4e72 Mon Sep 17 00:00:00 2001 From: Manish Narani Date: Mon, 16 Nov 2020 19:22:24 +0530 Subject: firmware: xilinx: Fix SD DLL node reset issue Fix the SD DLL node reset issue where incorrect node is being referenced instead of SD DLL node. Fixes: 426c8d85df7a ("firmware: xilinx: Use APIs instead of IOCTLs") Signed-off-by: Manish Narani Link: https://lore.kernel.org/r/1605534744-15649-1-git-send-email-manish.narani@xilinx.com Signed-off-by: Michal Simek --- drivers/firmware/xilinx/zynqmp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index efb8a66efc68..5828302c7c5c 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -615,7 +615,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_tapdelay); */ int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type) { - return zynqmp_pm_invoke_fn(PM_IOCTL, node_id, IOCTL_SET_SD_TAPDELAY, + return zynqmp_pm_invoke_fn(PM_IOCTL, node_id, IOCTL_SD_DLL_RESET, type, 0, NULL); } EXPORT_SYMBOL_GPL(zynqmp_pm_sd_dll_reset); -- cgit v1.2.3 From acfdd18591eaac25446e976a0c0d190f8b3dbfb1 Mon Sep 17 00:00:00 2001 From: Amit Sunil Dhamne Date: Mon, 23 Nov 2020 21:52:41 -0800 Subject: firmware: xilinx: Use hash-table for api feature check MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently array of fix length PM_API_MAX is used to cache the pm_api version (valid or invalid). However ATF based PM APIs values are much higher then PM_API_MAX. So to include ATF based PM APIs also, use hash-table to store the pm_api version status. Signed-off-by: Amit Sunil Dhamne Reported-by: Arnd Bergmann  Signed-off-by: Ravi Patel Signed-off-by: Rajan Vaja Reviewed-by: Arnd Bergmann Tested-by: Michal Simek Fixes: f3217d6f2f7a ("firmware: xilinx: fix out-of-bounds access") Cc: stable Link: https://lore.kernel.org/r/1606197161-25976-1-git-send-email-rajan.vaja@xilinx.com Signed-off-by: Michal Simek --- drivers/firmware/xilinx/zynqmp.c | 63 ++++++++++++++++++++++++++++-------- include/linux/firmware/xlnx-zynqmp.h | 4 --- 2 files changed, 49 insertions(+), 18 deletions(-) diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 5828302c7c5c..d08ac824c993 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -20,12 +20,28 @@ #include #include #include +#include #include #include "zynqmp-debug.h" +/* Max HashMap Order for PM API feature check (1<<7 = 128) */ +#define PM_API_FEATURE_CHECK_MAX_ORDER 7 + static bool feature_check_enabled; -static u32 zynqmp_pm_features[PM_API_MAX]; +DEFINE_HASHTABLE(pm_api_features_map, PM_API_FEATURE_CHECK_MAX_ORDER); + +/** + * struct pm_api_feature_data - PM API Feature data + * @pm_api_id: PM API Id, used as key to index into hashmap + * @feature_status: status of PM API feature: valid, invalid + * @hentry: hlist_node that hooks this entry into hashtable + */ +struct pm_api_feature_data { + u32 pm_api_id; + int feature_status; + struct hlist_node hentry; +}; static const struct mfd_cell firmware_devs[] = { { @@ -142,29 +158,37 @@ static int zynqmp_pm_feature(u32 api_id) int ret; u32 ret_payload[PAYLOAD_ARG_CNT]; u64 smc_arg[2]; + struct pm_api_feature_data *feature_data; if (!feature_check_enabled) return 0; - /* Return value if feature is already checked */ - if (api_id > ARRAY_SIZE(zynqmp_pm_features)) - return PM_FEATURE_INVALID; + /* Check for existing entry in hash table for given api */ + hash_for_each_possible(pm_api_features_map, feature_data, hentry, + api_id) { + if (feature_data->pm_api_id == api_id) + return feature_data->feature_status; + } - if (zynqmp_pm_features[api_id] != PM_FEATURE_UNCHECKED) - return zynqmp_pm_features[api_id]; + /* Add new entry if not present */ + feature_data = kmalloc(sizeof(*feature_data), GFP_KERNEL); + if (!feature_data) + return -ENOMEM; + feature_data->pm_api_id = api_id; smc_arg[0] = PM_SIP_SVC | PM_FEATURE_CHECK; smc_arg[1] = api_id; ret = do_fw_call(smc_arg[0], smc_arg[1], 0, ret_payload); - if (ret) { - zynqmp_pm_features[api_id] = PM_FEATURE_INVALID; - return PM_FEATURE_INVALID; - } + if (ret) + ret = -EOPNOTSUPP; + else + ret = ret_payload[1]; - zynqmp_pm_features[api_id] = ret_payload[1]; + feature_data->feature_status = ret; + hash_add(pm_api_features_map, &feature_data->hentry, api_id); - return zynqmp_pm_features[api_id]; + return ret; } /** @@ -200,9 +224,12 @@ int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1, * Make sure to stay in x0 register */ u64 smc_arg[4]; + int ret; - if (zynqmp_pm_feature(pm_api_id) == PM_FEATURE_INVALID) - return -ENOTSUPP; + /* Check if feature is supported or not */ + ret = zynqmp_pm_feature(pm_api_id); + if (ret < 0) + return ret; smc_arg[0] = PM_SIP_SVC | pm_api_id; smc_arg[1] = ((u64)arg1 << 32) | arg0; @@ -1252,9 +1279,17 @@ static int zynqmp_firmware_probe(struct platform_device *pdev) static int zynqmp_firmware_remove(struct platform_device *pdev) { + struct pm_api_feature_data *feature_data; + int i; + mfd_remove_devices(&pdev->dev); zynqmp_pm_api_debugfs_exit(); + hash_for_each(pm_api_features_map, i, feature_data, hentry) { + hash_del(&feature_data->hentry); + kfree(feature_data); + } + return 0; } diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 5968df82b991..41a1bab98b7e 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -50,10 +50,6 @@ #define ZYNQMP_PM_CAPABILITY_WAKEUP 0x4U #define ZYNQMP_PM_CAPABILITY_UNUSABLE 0x8U -/* Feature check status */ -#define PM_FEATURE_INVALID -1 -#define PM_FEATURE_UNCHECKED 0 - /* * Firmware FPGA Manager flags * XILINX_ZYNQMP_PM_FPGA_FULL: FPGA full reconfiguration -- cgit v1.2.3 From 7cd71202961090d8f2d2b863ec66b25ae43e1d39 Mon Sep 17 00:00:00 2001 From: Clark Wang Date: Tue, 24 Nov 2020 16:52:47 +0800 Subject: spi: imx: fix the unbalanced spi runtime pm management If set active without increase the usage count of pm, the dont use autosuspend function will call the suspend callback to close the two clocks of spi because the usage count is reduced to -1. This will cause the warning dump below when the defer-probe occurs. [ 129.379701] ecspi2_root_clk already disabled [ 129.384005] WARNING: CPU: 1 PID: 33 at drivers/clk/clk.c:952 clk_core_disable+0xa4/0xb0 So add the get noresume function before set active. Fixes: 43b6bf406cd0 spi: imx: fix runtime pm support for !CONFIG_PM Signed-off-by: Clark Wang Link: https://lore.kernel.org/r/20201124085247.18025-1-xiaoning.wang@nxp.com Signed-off-by: Mark Brown --- drivers/spi/spi-imx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 4b80e27ecdbf..0b597905ee72 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -1686,6 +1686,7 @@ static int spi_imx_probe(struct platform_device *pdev) pm_runtime_set_autosuspend_delay(spi_imx->dev, MXC_RPM_TIMEOUT); pm_runtime_use_autosuspend(spi_imx->dev); + pm_runtime_get_noresume(spi_imx->dev); pm_runtime_set_active(spi_imx->dev); pm_runtime_enable(spi_imx->dev); -- cgit v1.2.3 From a7361b9c4615951f52ffd2b1afa09a1384c7b4e4 Mon Sep 17 00:00:00 2001 From: Adam Sampson Date: Mon, 23 Nov 2020 17:47:39 +0000 Subject: ARM: dts: sun7i: pcduino3-nano: enable RGMII RX/TX delay on PHY The RX/TX delays for the Ethernet PHY on the Linksprite pcDuino 3 Nano are configured in hardware, using resistors that are populated to pull the RTL8211E's RXDLY/TXDLY pins low or high as needed. phy-mode should be set to rgmii-id to reflect this. Previously it was set to rgmii, which used to work but now results in the delays being disabled again as a result of the bugfix in commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config"). Tested on two pcDuino 3 Nano boards purchased in 2015. Without this fix, Ethernet works unreliably on one board and doesn't work at all on the other. Fixes: 061035d456c9 ("ARM: dts: sun7i: Add dts file for pcDuino 3 Nano board") Signed-off-by: Adam Sampson Signed-off-by: Maxime Ripard Reviewed-by: Andrew Lunn Acked-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20201123174739.6809-1-ats@offog.org --- arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts b/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts index fce2f7fcd084..bf38c66c1815 100644 --- a/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts +++ b/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts @@ -1,5 +1,5 @@ /* - * Copyright 2015 Adam Sampson + * Copyright 2015-2020 Adam Sampson * * This file is dual-licensed: you can use it either under the terms * of the GPL or the X11 license, at your option. Note that this dual @@ -115,7 +115,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; -- cgit v1.2.3 From eb2667b343361863da7b79be26de641e22844ba0 Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Tue, 24 Nov 2020 15:03:03 +0800 Subject: io_uring: fix shift-out-of-bounds when round up cq size Abaci Fuzz reported a shift-out-of-bounds BUG in io_uring_create(): [ 59.598207] UBSAN: shift-out-of-bounds in ./include/linux/log2.h:57:13 [ 59.599665] shift exponent 64 is too large for 64-bit type 'long unsigned int' [ 59.601230] CPU: 0 PID: 963 Comm: a.out Not tainted 5.10.0-rc4+ #3 [ 59.602502] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 [ 59.603673] Call Trace: [ 59.604286] dump_stack+0x107/0x163 [ 59.605237] ubsan_epilogue+0xb/0x5a [ 59.606094] __ubsan_handle_shift_out_of_bounds.cold+0xb2/0x20e [ 59.607335] ? lock_downgrade+0x6c0/0x6c0 [ 59.608182] ? rcu_read_lock_sched_held+0xaf/0xe0 [ 59.609166] io_uring_create.cold+0x99/0x149 [ 59.610114] io_uring_setup+0xd6/0x140 [ 59.610975] ? io_uring_create+0x2510/0x2510 [ 59.611945] ? lockdep_hardirqs_on_prepare+0x286/0x400 [ 59.613007] ? syscall_enter_from_user_mode+0x27/0x80 [ 59.614038] ? trace_hardirqs_on+0x5b/0x180 [ 59.615056] do_syscall_64+0x2d/0x40 [ 59.615940] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 59.617007] RIP: 0033:0x7f2bb8a0b239 This is caused by roundup_pow_of_two() if the input entries larger enough, e.g. 2^32-1. For sq_entries, it will check first and we allow at most IORING_MAX_ENTRIES, so it is okay. But for cq_entries, we do round up first, that may overflow and truncate it to 0, which is not the expected behavior. So check the cq size first and then do round up. Fixes: 88ec3211e463 ("io_uring: round-up cq size before comparing with rounded sq size") Reported-by: Abaci Fuzz Signed-off-by: Joseph Qi Reviewed-by: Stefano Garzarella Signed-off-by: Jens Axboe --- fs/io_uring.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index a8c136a1cf4e..f971589878bc 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -9252,14 +9252,16 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, * to a power-of-two, if it isn't already. We do NOT impose * any cq vs sq ring sizing. */ - p->cq_entries = roundup_pow_of_two(p->cq_entries); - if (p->cq_entries < p->sq_entries) + if (!p->cq_entries) return -EINVAL; if (p->cq_entries > IORING_MAX_CQ_ENTRIES) { if (!(p->flags & IORING_SETUP_CLAMP)) return -EINVAL; p->cq_entries = IORING_MAX_CQ_ENTRIES; } + p->cq_entries = roundup_pow_of_two(p->cq_entries); + if (p->cq_entries < p->sq_entries) + return -EINVAL; } else { p->cq_entries = 2 * p->sq_entries; } -- cgit v1.2.3 From 9c3a205c5ffa36e96903c2e37eb5f41c0f03c43e Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 23 Nov 2020 23:20:27 +0000 Subject: io_uring: fix ITER_BVEC check iov_iter::type is a bitmask that also keeps direction etc., so it shouldn't be directly compared against ITER_*. Use proper helper. Fixes: ff6165b2d7f6 ("io_uring: retain iov_iter state over io_read/io_write calls") Reported-by: David Howells Signed-off-by: Pavel Begunkov Cc: # 5.9 Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index f971589878bc..ff6deffe5aa9 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3193,7 +3193,7 @@ static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec, rw->free_iovec = iovec; rw->bytes_done = 0; /* can only be fixed buffers, no need to do anything */ - if (iter->type == ITER_BVEC) + if (iov_iter_is_bvec(iter)) return; if (!iovec) { unsigned iov_off = 0; -- cgit v1.2.3 From 58c644ba512cfbc2e39b758dd979edd1d6d00e27 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 20 Nov 2020 11:50:35 +0100 Subject: sched/idle: Fix arch_cpu_idle() vs tracing We call arch_cpu_idle() with RCU disabled, but then use local_irq_{en,dis}able(), which invokes tracing, which relies on RCU. Switch all arch_cpu_idle() implementations to use raw_local_irq_{en,dis}able() and carefully manage the lockdep,rcu,tracing state like we do in entry. (XXX: we really should change arch_cpu_idle() to not return with interrupts enabled) Reported-by: Sven Schnelle Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Mark Rutland Tested-by: Mark Rutland Link: https://lkml.kernel.org/r/20201120114925.594122626@infradead.org --- arch/alpha/kernel/process.c | 2 +- arch/arm/kernel/process.c | 2 +- arch/arm64/kernel/process.c | 2 +- arch/csky/kernel/process.c | 2 +- arch/h8300/kernel/process.c | 2 +- arch/hexagon/kernel/process.c | 2 +- arch/ia64/kernel/process.c | 2 +- arch/microblaze/kernel/process.c | 2 +- arch/mips/kernel/idle.c | 12 ++++++------ arch/nios2/kernel/process.c | 2 +- arch/openrisc/kernel/process.c | 2 +- arch/parisc/kernel/process.c | 2 +- arch/powerpc/kernel/idle.c | 4 ++-- arch/riscv/kernel/process.c | 2 +- arch/s390/kernel/idle.c | 6 +++--- arch/sh/kernel/idle.c | 2 +- arch/sparc/kernel/leon_pmc.c | 4 ++-- arch/sparc/kernel/process_32.c | 2 +- arch/sparc/kernel/process_64.c | 4 ++-- arch/um/kernel/process.c | 2 +- arch/x86/include/asm/mwait.h | 2 -- arch/x86/kernel/process.c | 12 +++++++----- kernel/sched/idle.c | 28 +++++++++++++++++++++++++++- 23 files changed, 64 insertions(+), 38 deletions(-) diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 7462a7911002..4c7b0414a3ff 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -57,7 +57,7 @@ EXPORT_SYMBOL(pm_power_off); void arch_cpu_idle(void) { wtint(0); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_dead(void) diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 8e6ace03e960..9f199b1e8383 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -71,7 +71,7 @@ void arch_cpu_idle(void) arm_pm_idle(); else cpu_do_idle(); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_prepare(void) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 4784011cecac..9ebe02574127 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -126,7 +126,7 @@ void arch_cpu_idle(void) * tricks */ cpu_do_idle(); - local_irq_enable(); + raw_local_irq_enable(); } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index f730869e21ee..69af6bc87e64 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -102,6 +102,6 @@ void arch_cpu_idle(void) #ifdef CONFIG_CPU_PM_STOP asm volatile("stop\n"); #endif - local_irq_enable(); + raw_local_irq_enable(); } #endif diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index aea0a40b77a9..bc1364db58fe 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -57,7 +57,7 @@ asmlinkage void ret_from_kernel_thread(void); */ void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); __asm__("sleep"); } diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index 5a0a95d93ddb..67767c5ed98c 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -44,7 +44,7 @@ void arch_cpu_idle(void) { __vmwait(); /* interrupts wake us up, but irqs are still disabled */ - local_irq_enable(); + raw_local_irq_enable(); } /* diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 6b61a703bcf5..c9ff8796b509 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -239,7 +239,7 @@ void arch_cpu_idle(void) if (mark_idle) (*mark_idle)(1); - safe_halt(); + raw_safe_halt(); if (mark_idle) (*mark_idle)(0); diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index a9e46e525cd0..f99860771ff4 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -149,5 +149,5 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpregs) void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); } diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c index 5bc3b04693c7..18e69ebf5691 100644 --- a/arch/mips/kernel/idle.c +++ b/arch/mips/kernel/idle.c @@ -33,19 +33,19 @@ static void __cpuidle r3081_wait(void) { unsigned long cfg = read_c0_conf(); write_c0_conf(cfg | R30XX_CONF_HALT); - local_irq_enable(); + raw_local_irq_enable(); } static void __cpuidle r39xx_wait(void) { if (!need_resched()) write_c0_conf(read_c0_conf() | TX39_CONF_HALT); - local_irq_enable(); + raw_local_irq_enable(); } void __cpuidle r4k_wait(void) { - local_irq_enable(); + raw_local_irq_enable(); __r4k_wait(); } @@ -64,7 +64,7 @@ void __cpuidle r4k_wait_irqoff(void) " .set arch=r4000 \n" " wait \n" " .set pop \n"); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -84,7 +84,7 @@ static void __cpuidle rm7k_wait_irqoff(void) " wait \n" " mtc0 $1, $12 # stalls until W stage \n" " .set pop \n"); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -257,7 +257,7 @@ void arch_cpu_idle(void) if (cpu_wait) cpu_wait(); else - local_irq_enable(); + raw_local_irq_enable(); } #ifdef CONFIG_CPU_IDLE diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c index 4ffe857e6ada..50b4eb19a6cc 100644 --- a/arch/nios2/kernel/process.c +++ b/arch/nios2/kernel/process.c @@ -33,7 +33,7 @@ EXPORT_SYMBOL(pm_power_off); void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); } /* diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 0ff391f00334..3c98728cce24 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -79,7 +79,7 @@ void machine_power_off(void) */ void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); if (mfspr(SPR_UPR) & SPR_UPR_PMP) mtspr(SPR_PMR, mfspr(SPR_PMR) | SPR_PMR_DME); } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index f196d96e2f9f..a92a23d6acd9 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -169,7 +169,7 @@ void __cpuidle arch_cpu_idle_dead(void) void __cpuidle arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); /* nop on real hardware, qemu will idle sleep. */ asm volatile("or %%r10,%%r10,%%r10\n":::); diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index ae0e2632393d..1f835539fda4 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -52,9 +52,9 @@ void arch_cpu_idle(void) * interrupts enabled, some don't. */ if (irqs_disabled()) - local_irq_enable(); + raw_local_irq_enable(); } else { - local_irq_enable(); + raw_local_irq_enable(); /* * Go into low thread priority and possibly * low power mode. diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 19225ec65db6..dd5f985b1f40 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -36,7 +36,7 @@ extern asmlinkage void ret_from_kernel_thread(void); void arch_cpu_idle(void) { wait_for_interrupt(); - local_irq_enable(); + raw_local_irq_enable(); } void show_regs(struct pt_regs *regs) diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index f7f1e64e0d98..2b85096964f8 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -33,10 +33,10 @@ void enabled_wait(void) PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; clear_cpu_flag(CIF_NOHZ_DELAY); - local_irq_save(flags); + raw_local_irq_save(flags); /* Call the assembler magic in entry.S */ psw_idle(idle, psw_mask); - local_irq_restore(flags); + raw_local_irq_restore(flags); /* Account time spent with enabled wait psw loaded as idle time. */ raw_write_seqcount_begin(&idle->seqcount); @@ -123,7 +123,7 @@ void arch_cpu_idle_enter(void) void arch_cpu_idle(void) { enabled_wait(); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_exit(void) diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 0dc0f52f9bb8..f59814983bd5 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -22,7 +22,7 @@ static void (*sh_idle)(void); void default_idle(void) { set_bl_bit(); - local_irq_enable(); + raw_local_irq_enable(); /* Isn't this racy ? */ cpu_sleep(); clear_bl_bit(); diff --git a/arch/sparc/kernel/leon_pmc.c b/arch/sparc/kernel/leon_pmc.c index 065e2d4b7290..396f46bca52e 100644 --- a/arch/sparc/kernel/leon_pmc.c +++ b/arch/sparc/kernel/leon_pmc.c @@ -50,7 +50,7 @@ static void pmc_leon_idle_fixup(void) register unsigned int address = (unsigned int)leon3_irqctrl_regs; /* Interrupts need to be enabled to not hang the CPU */ - local_irq_enable(); + raw_local_irq_enable(); __asm__ __volatile__ ( "wr %%g0, %%asr19\n" @@ -66,7 +66,7 @@ static void pmc_leon_idle_fixup(void) static void pmc_leon_idle(void) { /* Interrupts need to be enabled to not hang the CPU */ - local_irq_enable(); + raw_local_irq_enable(); /* For systems without power-down, this will be no-op */ __asm__ __volatile__ ("wr %g0, %asr19\n\t"); diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index adfcaeab3ddc..a02363735915 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -74,7 +74,7 @@ void arch_cpu_idle(void) { if (sparc_idle) (*sparc_idle)(); - local_irq_enable(); + raw_local_irq_enable(); } /* XXX cli/sti -> local_irq_xxx here, check this works once SMP is fixed. */ diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index a75093b993f9..6f8c7822fc06 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -62,11 +62,11 @@ void arch_cpu_idle(void) { if (tlb_type != hypervisor) { touch_nmi_watchdog(); - local_irq_enable(); + raw_local_irq_enable(); } else { unsigned long pstate; - local_irq_enable(); + raw_local_irq_enable(); /* The sun4v sleeping code requires that we have PSTATE.IE cleared over * the cpu sleep hypervisor call. diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 3bed09538dd9..9505a7e87396 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -217,7 +217,7 @@ void arch_cpu_idle(void) { cpu_tasks[current_thread_info()->cpu].pid = os_getpid(); um_idle_sleep(); - local_irq_enable(); + raw_local_irq_enable(); } int __cant_sleep(void) { diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index e039a933aca3..29dd27b5a339 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -88,8 +88,6 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx, static inline void __sti_mwait(unsigned long eax, unsigned long ecx) { - trace_hardirqs_on(); - mds_idle_clear_cpu_buffers(); /* "mwait %eax, %ecx;" */ asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ba4593a913fa..145a7ac0c19a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -685,7 +685,7 @@ void arch_cpu_idle(void) */ void __cpuidle default_idle(void) { - safe_halt(); + raw_safe_halt(); } #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) EXPORT_SYMBOL(default_idle); @@ -736,6 +736,8 @@ void stop_this_cpu(void *dummy) /* * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power * states (local apic timer and TSC stop). + * + * XXX this function is completely buggered vs RCU and tracing. */ static void amd_e400_idle(void) { @@ -757,9 +759,9 @@ static void amd_e400_idle(void) * The switch back from broadcast mode needs to be called with * interrupts disabled. */ - local_irq_disable(); + raw_local_irq_disable(); tick_broadcast_exit(); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -801,9 +803,9 @@ static __cpuidle void mwait_idle(void) if (!need_resched()) __sti_mwait(0, 0); else - local_irq_enable(); + raw_local_irq_enable(); } else { - local_irq_enable(); + raw_local_irq_enable(); } __current_clr_polling(); } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 24d0ee26377d..c6932b8f4467 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -78,7 +78,7 @@ void __weak arch_cpu_idle_dead(void) { } void __weak arch_cpu_idle(void) { cpu_idle_force_poll = 1; - local_irq_enable(); + raw_local_irq_enable(); } /** @@ -94,9 +94,35 @@ void __cpuidle default_idle_call(void) trace_cpu_idle(1, smp_processor_id()); stop_critical_timings(); + + /* + * arch_cpu_idle() is supposed to enable IRQs, however + * we can't do that because of RCU and tracing. + * + * Trace IRQs enable here, then switch off RCU, and have + * arch_cpu_idle() use raw_local_irq_enable(). Note that + * rcu_idle_enter() relies on lockdep IRQ state, so switch that + * last -- this is very similar to the entry code. + */ + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(_THIS_IP_); rcu_idle_enter(); + lockdep_hardirqs_on(_THIS_IP_); + arch_cpu_idle(); + + /* + * OK, so IRQs are enabled here, but RCU needs them disabled to + * turn itself back on.. funny thing is that disabling IRQs + * will cause tracing, which needs RCU. Jump through hoops to + * make it 'work'. + */ + raw_local_irq_disable(); + lockdep_hardirqs_off(_THIS_IP_); rcu_idle_exit(); + lockdep_hardirqs_on(_THIS_IP_); + raw_local_irq_enable(); + start_critical_timings(); trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } -- cgit v1.2.3 From 6e1d2bc675bd57640f5658a4a657ae488db4c204 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 20 Nov 2020 11:28:35 +0100 Subject: intel_idle: Fix intel_idle() vs tracing cpuidle->enter() callbacks should not call into tracing because RCU has already been disabled. Instead of doing the broadcast thing itself, simply advertise to the cpuidle core that those states stop the timer. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Rafael J. Wysocki Link: https://lkml.kernel.org/r/20201123143510.GR3021@hirez.programming.kicks-ass.net --- drivers/idle/intel_idle.c | 37 ++++++++++++++++++++----------------- 1 file changed, 20 insertions(+), 17 deletions(-) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 01bace49a962..7ee7ffe22ae3 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -126,26 +126,9 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state = &drv->states[index]; unsigned long eax = flg2MWAIT(state->flags); unsigned long ecx = 1; /* break on interrupt flag */ - bool tick; - - if (!static_cpu_has(X86_FEATURE_ARAT)) { - /* - * Switch over to one-shot tick broadcast if the target C-state - * is deeper than C1. - */ - if ((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) { - tick = true; - tick_broadcast_enter(); - } else { - tick = false; - } - } mwait_idle_with_hints(eax, ecx); - if (!static_cpu_has(X86_FEATURE_ARAT) && tick) - tick_broadcast_exit(); - return index; } @@ -1227,6 +1210,20 @@ static bool __init intel_idle_acpi_cst_extract(void) return false; } +static bool __init intel_idle_state_needs_timer_stop(struct cpuidle_state *state) +{ + unsigned long eax = flg2MWAIT(state->flags); + + if (boot_cpu_has(X86_FEATURE_ARAT)) + return false; + + /* + * Switch over to one-shot tick broadcast if the target C-state + * is deeper than C1. + */ + return !!((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK); +} + static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv) { int cstate, limit = min_t(int, CPUIDLE_STATE_MAX, acpi_state_table.count); @@ -1269,6 +1266,9 @@ static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv) if (disabled_states_mask & BIT(cstate)) state->flags |= CPUIDLE_FLAG_OFF; + if (intel_idle_state_needs_timer_stop(state)) + state->flags |= CPUIDLE_FLAG_TIMER_STOP; + state->enter = intel_idle; state->enter_s2idle = intel_idle_s2idle; } @@ -1507,6 +1507,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) !(cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_ALWAYS_ENABLE))) drv->states[drv->state_count].flags |= CPUIDLE_FLAG_OFF; + if (intel_idle_state_needs_timer_stop(&drv->states[drv->state_count])) + drv->states[drv->state_count].flags |= CPUIDLE_FLAG_TIMER_STOP; + drv->state_count++; } -- cgit v1.2.3 From 0305613dbcf42b6b27ddf516fea2738dfbfdb7c0 Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Tue, 17 Nov 2020 15:01:24 +0200 Subject: drm/i915/perf: workaround register corruption in OATAILPTR After having written the entire OA buffer with reports, the HW will write again at the beginning of the OA buffer. It'll indicate it by setting the WRAP bits in the OASTATUS register. When a wrap happens and that at the end of the read vfunc we write the OASTATUS register back to clear the REPORT_LOST bit, we sometimes see that the OATAILPTR register is reset to a previous position on Gen8/9 (apparently not the case on Gen11+). This leads the next call to the read vfunc to process reports we've already read. Because we've marked those as read by clearing the reason & timestamp dwords, they're discarded and a "Skipping spurious, invalid OA report" message is emitted. The workaround to avoid this OATAILPTR value reset seems to be to set the wrap bits when writing back OASTATUS. This change has no impact on userspace, it only avoids a bunch of DRM_NOTE("Skipping spurious, invalid OA report\n") messages. Signed-off-by: Lionel Landwerlin Fixes: 19f81df2859eb1 ("drm/i915/perf: Add OA unit support for Gen 8+") Reviewed-by: Umesh Nerlige Ramappa Link: https://patchwork.freedesktop.org/patch/msgid/20201117130124.829979-1-lionel.g.landwerlin@intel.com (cherry picked from commit 059a0beb486344a577ff476acce75e69eab704be) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/i915_perf.c | 9 +++++++-- drivers/gpu/drm/i915/i915_reg.h | 2 ++ 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index e94976976571..3640d0e229d2 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -909,8 +909,13 @@ static int gen8_oa_read(struct i915_perf_stream *stream, DRM_I915_PERF_RECORD_OA_REPORT_LOST); if (ret) return ret; - intel_uncore_write(uncore, oastatus_reg, - oastatus & ~GEN8_OASTATUS_REPORT_LOST); + + intel_uncore_rmw(uncore, oastatus_reg, + GEN8_OASTATUS_COUNTER_OVERFLOW | + GEN8_OASTATUS_REPORT_LOST, + IS_GEN_RANGE(uncore->i915, 8, 10) ? + (GEN8_OASTATUS_HEAD_POINTER_WRAP | + GEN8_OASTATUS_TAIL_POINTER_WRAP) : 0); } return gen8_append_oa_reports(stream, buf, count, offset); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 664f3bf9af03..5cd83eac940c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -676,6 +676,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN7_OASTATUS2_MEM_SELECT_GGTT (1 << 0) /* 0: PPGTT, 1: GGTT */ #define GEN8_OASTATUS _MMIO(0x2b08) +#define GEN8_OASTATUS_TAIL_POINTER_WRAP (1 << 17) +#define GEN8_OASTATUS_HEAD_POINTER_WRAP (1 << 16) #define GEN8_OASTATUS_OVERRUN_STATUS (1 << 3) #define GEN8_OASTATUS_COUNTER_OVERFLOW (1 << 2) #define GEN8_OASTATUS_OABUFFER_OVERFLOW (1 << 1) -- cgit v1.2.3 From b5e420f4595003c8c4669b2274bc5fa3856fc1be Mon Sep 17 00:00:00 2001 From: Yan Zhao Date: Thu, 10 Sep 2020 11:54:05 +0800 Subject: drm/i915/gvt: correct a false comment of flag F_UNALIGN Correct falsely removed comment of flag F_UNALIGN. Fixes: a6c5817a38cf ("drm/i915/gvt: remove flag F_CMD_ACCESSED") Reviewed-by: Zhenyu Wang Signed-off-by: Yan Zhao Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20200910035405.20273-1-yan.y.zhao@intel.com (cherry picked from commit 6594094f819e0020e926e137e47e2edb97ba500b) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gvt/gvt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 9831361f181e..a81cf0f01e78 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -255,7 +255,7 @@ struct intel_gvt_mmio { #define F_CMD_ACCESS (1 << 3) /* This reg has been accessed by a VM */ #define F_ACCESSED (1 << 4) -/* This reg has been accessed through GPU commands */ +/* This reg could be accessed by unaligned address */ #define F_UNALIGN (1 << 6) /* This reg is in GVT's mmio save-restor list and in hardware * logical context image -- cgit v1.2.3 From 08b49e14ec4f88f87a3a8443fca944dc2768066b Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 23 Nov 2020 11:37:14 +0000 Subject: drm/i915/gt: Defer enabling the breadcrumb interrupt to after submission Move the register slow register write and readback from out of the critical path for execlists submission and delay it until the following worker, shaving off around 200us. Note that the same signal_irq_work() is allowed to run concurrently on each CPU (but it will only be queued once, once running though it can be requeued and reexecuted) so we have to remember to lock the global interactions as we cannot rely on the signal_irq_work() itself providing the serialisation (in constrast to a tasklet). By pushing the arm/disarm into the central signaling worker we can close the race for disarming the interrupt (and dropping its associated GT wakeref) on parking the engine. If we loose the race, that GT wakeref may be held indefinitely, preventing the machine from sleeping while the GPU is ostensibly idle. v2: Move the self-arming parking of the signal_irq_work to a flush of the irq-work from intel_breadcrumbs_park(). Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2271 Fixes: e23005604b2f ("drm/i915/gt: Hold context/request reference while breadcrumbs are active") Signed-off-by: Chris Wilson Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20201123113717.20500-1-chris@chris-wilson.co.uk (cherry picked from commit 9d5612ca165a58aacc160465532e7998b9aab270) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 109 ++++++++++++++++++---------- 1 file changed, 70 insertions(+), 39 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index d8b206e53660..8d85683314e1 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -30,18 +30,21 @@ #include "i915_trace.h" #include "intel_breadcrumbs.h" #include "intel_context.h" +#include "intel_engine_pm.h" #include "intel_gt_pm.h" #include "intel_gt_requests.h" -static void irq_enable(struct intel_engine_cs *engine) +static bool irq_enable(struct intel_engine_cs *engine) { if (!engine->irq_enable) - return; + return false; /* Caller disables interrupts */ spin_lock(&engine->gt->irq_lock); engine->irq_enable(engine); spin_unlock(&engine->gt->irq_lock); + + return true; } static void irq_disable(struct intel_engine_cs *engine) @@ -57,12 +60,11 @@ static void irq_disable(struct intel_engine_cs *engine) static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b) { - lockdep_assert_held(&b->irq_lock); - - if (!b->irq_engine || b->irq_armed) - return; - - if (!intel_gt_pm_get_if_awake(b->irq_engine->gt)) + /* + * Since we are waiting on a request, the GPU should be busy + * and should have its own rpm reference. + */ + if (GEM_WARN_ON(!intel_gt_pm_get_if_awake(b->irq_engine->gt))) return; /* @@ -73,25 +75,24 @@ static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b) */ WRITE_ONCE(b->irq_armed, true); - /* - * Since we are waiting on a request, the GPU should be busy - * and should have its own rpm reference. This is tracked - * by i915->gt.awake, we can forgo holding our own wakref - * for the interrupt as before i915->gt.awake is released (when - * the driver is idle) we disarm the breadcrumbs. - */ - - if (!b->irq_enabled++) - irq_enable(b->irq_engine); + /* Requests may have completed before we could enable the interrupt. */ + if (!b->irq_enabled++ && irq_enable(b->irq_engine)) + irq_work_queue(&b->irq_work); } -static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) +static void intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b) { - lockdep_assert_held(&b->irq_lock); - - if (!b->irq_engine || !b->irq_armed) + if (!b->irq_engine) return; + spin_lock(&b->irq_lock); + if (!b->irq_armed) + __intel_breadcrumbs_arm_irq(b); + spin_unlock(&b->irq_lock); +} + +static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) +{ GEM_BUG_ON(!b->irq_enabled); if (!--b->irq_enabled) irq_disable(b->irq_engine); @@ -105,8 +106,6 @@ static void add_signaling_context(struct intel_breadcrumbs *b, { intel_context_get(ce); list_add_tail(&ce->signal_link, &b->signalers); - if (list_is_first(&ce->signal_link, &b->signalers)) - __intel_breadcrumbs_arm_irq(b); } static void remove_signaling_context(struct intel_breadcrumbs *b, @@ -197,7 +196,32 @@ static void signal_irq_work(struct irq_work *work) spin_lock(&b->irq_lock); - if (list_empty(&b->signalers)) + /* + * Keep the irq armed until the interrupt after all listeners are gone. + * + * Enabling/disabling the interrupt is rather costly, roughly a couple + * of hundred microseconds. If we are proactive and enable/disable + * the interrupt around every request that wants a breadcrumb, we + * quickly drown in the extra orders of magnitude of latency imposed + * on request submission. + * + * So we try to be lazy, and keep the interrupts enabled until no + * more listeners appear within a breadcrumb interrupt interval (that + * is until a request completes that no one cares about). The + * observation is that listeners come in batches, and will often + * listen to a bunch of requests in succession. Though note on icl+, + * interrupts are always enabled due to concerns with rc6 being + * dysfunctional with per-engine interrupt masking. + * + * We also try to avoid raising too many interrupts, as they may + * be generated by userspace batches and it is unfortunately rather + * too easy to drown the CPU under a flood of GPU interrupts. Thus + * whenever no one appears to be listening, we turn off the interrupts. + * Fewer interrupts should conserve power -- at the very least, fewer + * interrupt draw less ire from other users of the system and tools + * like powertop. + */ + if (b->irq_armed && list_empty(&b->signalers)) __intel_breadcrumbs_disarm_irq(b); list_splice_init(&b->signaled_requests, &signal); @@ -251,6 +275,9 @@ static void signal_irq_work(struct irq_work *work) i915_request_put(rq); } + + if (!READ_ONCE(b->irq_armed) && !list_empty(&b->signalers)) + intel_breadcrumbs_arm_irq(b); } struct intel_breadcrumbs * @@ -292,21 +319,22 @@ void intel_breadcrumbs_reset(struct intel_breadcrumbs *b) void intel_breadcrumbs_park(struct intel_breadcrumbs *b) { - unsigned long flags; - - if (!READ_ONCE(b->irq_armed)) - return; - - spin_lock_irqsave(&b->irq_lock, flags); - __intel_breadcrumbs_disarm_irq(b); - spin_unlock_irqrestore(&b->irq_lock, flags); - - if (!list_empty(&b->signalers)) - irq_work_queue(&b->irq_work); + /* Kick the work once more to drain the signalers */ + irq_work_sync(&b->irq_work); + while (unlikely(READ_ONCE(b->irq_armed))) { + local_irq_disable(); + signal_irq_work(&b->irq_work); + local_irq_enable(); + cond_resched(); + } + GEM_BUG_ON(!list_empty(&b->signalers)); } void intel_breadcrumbs_free(struct intel_breadcrumbs *b) { + irq_work_sync(&b->irq_work); + GEM_BUG_ON(!list_empty(&b->signalers)); + GEM_BUG_ON(b->irq_armed); kfree(b); } @@ -362,9 +390,12 @@ static void insert_breadcrumb(struct i915_request *rq, GEM_BUG_ON(!check_signal_order(ce, rq)); set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); - /* Check after attaching to irq, interrupt may have already fired. */ - if (__request_completed(rq)) - irq_work_queue(&b->irq_work); + /* + * Defer enabling the interrupt to after HW submission and recheck + * the request as it may have completed and raised the interrupt as + * we were attaching it into the lists. + */ + irq_work_queue(&b->irq_work); } bool i915_request_enable_breadcrumb(struct i915_request *rq) -- cgit v1.2.3 From 7acc79eb5f78d3d1aa5dd21fc0a0329f1b7f2be5 Mon Sep 17 00:00:00 2001 From: Kenneth Feng Date: Tue, 17 Nov 2020 21:10:59 +0800 Subject: drm/amd/amdgpu: fix null pointer in runtime pm fix the null pointer issue when runtime pm is triggered. Signed-off-by: Kenneth Feng Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index e3783f5a459d..026789b466db 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4852,7 +4852,7 @@ int amdgpu_device_baco_enter(struct drm_device *dev) if (!amdgpu_device_supports_baco(adev_to_drm(adev))) return -ENOTSUPP; - if (ras && ras->supported) + if (ras && ras->supported && adev->nbio.funcs->enable_doorbell_interrupt) adev->nbio.funcs->enable_doorbell_interrupt(adev, false); return amdgpu_dpm_baco_enter(adev); @@ -4871,7 +4871,7 @@ int amdgpu_device_baco_exit(struct drm_device *dev) if (ret) return ret; - if (ras && ras->supported) + if (ras && ras->supported && adev->nbio.funcs->enable_doorbell_interrupt) adev->nbio.funcs->enable_doorbell_interrupt(adev, true); return 0; -- cgit v1.2.3 From 4d6a95366117b241bb3298e1c318a36ebb7544d0 Mon Sep 17 00:00:00 2001 From: Sonny Jiang Date: Fri, 6 Nov 2020 16:42:47 -0500 Subject: drm/amdgpu: fix SI UVD firmware validate resume fail The SI UVD firmware validate key is stored at the end of firmware, which is changed during resume while playing video. So get the key at sw_init and store it for fw validate using. Signed-off-by: Sonny Jiang Reviewed-by: Leo Liu Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h | 1 + drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c | 20 +++++++++++--------- 2 files changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h index 5eb63288d157..edbb8194ee81 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h @@ -67,6 +67,7 @@ struct amdgpu_uvd { unsigned harvest_config; /* store image width to adjust nb memory state */ unsigned decode_image_width; + uint32_t keyselect; }; int amdgpu_uvd_sw_init(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c index 7cf4b11a65c5..3a5dce634cda 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c @@ -277,15 +277,8 @@ static void uvd_v3_1_mc_resume(struct amdgpu_device *adev) */ static int uvd_v3_1_fw_validate(struct amdgpu_device *adev) { - void *ptr; - uint32_t ucode_len, i; - uint32_t keysel; - - ptr = adev->uvd.inst[0].cpu_addr; - ptr += 192 + 16; - memcpy(&ucode_len, ptr, 4); - ptr += ucode_len; - memcpy(&keysel, ptr, 4); + int i; + uint32_t keysel = adev->uvd.keyselect; WREG32(mmUVD_FW_START, keysel); @@ -550,6 +543,8 @@ static int uvd_v3_1_sw_init(void *handle) struct amdgpu_ring *ring; struct amdgpu_device *adev = (struct amdgpu_device *)handle; int r; + void *ptr; + uint32_t ucode_len; /* UVD TRAP */ r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq); @@ -560,6 +555,13 @@ static int uvd_v3_1_sw_init(void *handle) if (r) return r; + /* Retrieval firmware validate key */ + ptr = adev->uvd.inst[0].cpu_addr; + ptr += 192 + 16; + memcpy(&ucode_len, ptr, 4); + ptr += ucode_len; + memcpy(&adev->uvd.keyselect, ptr, 4); + ring = &adev->uvd.inst->ring; sprintf(ring->name, "uvd"); r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0, -- cgit v1.2.3 From dbbf2728d50343b7947001a81f4c8cc98e4b44e5 Mon Sep 17 00:00:00 2001 From: Sonny Jiang Date: Fri, 20 Nov 2020 02:38:09 -0500 Subject: drm/amdgpu: fix a page fault The UVD firmware is copied to cpu addr in uvd_resume, so it should be used after that. This is to fix a bug introduced by patch drm/amdgpu: fix SI UVD firmware validate resume fail. Signed-off-by: Sonny Jiang Reviewed-by: Leo Liu Signed-off-by: Alex Deucher CC: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c index 3a5dce634cda..41800fcad410 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c @@ -555,13 +555,6 @@ static int uvd_v3_1_sw_init(void *handle) if (r) return r; - /* Retrieval firmware validate key */ - ptr = adev->uvd.inst[0].cpu_addr; - ptr += 192 + 16; - memcpy(&ucode_len, ptr, 4); - ptr += ucode_len; - memcpy(&adev->uvd.keyselect, ptr, 4); - ring = &adev->uvd.inst->ring; sprintf(ring->name, "uvd"); r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0, @@ -573,6 +566,13 @@ static int uvd_v3_1_sw_init(void *handle) if (r) return r; + /* Retrieval firmware validate key */ + ptr = adev->uvd.inst[0].cpu_addr; + ptr += 192 + 16; + memcpy(&ucode_len, ptr, 4); + ptr += ucode_len; + memcpy(&adev->uvd.keyselect, ptr, 4); + r = amdgpu_uvd_entity_init(adev); return r; -- cgit v1.2.3 From eb0104ee498d7f83ff98b8783181613685b8df6e Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 23 Nov 2020 11:37:15 +0000 Subject: drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock Make b->signaled_requests a lockless-list so that we can manipulate it outside of the b->irq_lock. Signed-off-by: Chris Wilson Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20201123113717.20500-2-chris@chris-wilson.co.uk (cherry picked from commit 6cfe66eb71b638968350b5f0fff051fd25eb75fb) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 34 +++++++++++++++-------- drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h | 2 +- drivers/gpu/drm/i915/i915_request.h | 6 +++- 3 files changed, 28 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index 8d85683314e1..43cfabb102ea 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -173,26 +173,34 @@ static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl) intel_engine_add_retire(b->irq_engine, tl); } -static bool __signal_request(struct i915_request *rq, struct list_head *signals) +static bool __signal_request(struct i915_request *rq) { - clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); - if (!__dma_fence_signal(&rq->fence)) { i915_request_put(rq); return false; } - list_add_tail(&rq->signal_link, signals); return true; } +static struct llist_node * +slist_add(struct llist_node *node, struct llist_node *head) +{ + node->next = head; + return node; +} + static void signal_irq_work(struct irq_work *work) { struct intel_breadcrumbs *b = container_of(work, typeof(*b), irq_work); const ktime_t timestamp = ktime_get(); + struct llist_node *signal, *sn; struct intel_context *ce, *cn; struct list_head *pos, *next; - LIST_HEAD(signal); + + signal = NULL; + if (unlikely(!llist_empty(&b->signaled_requests))) + signal = llist_del_all(&b->signaled_requests); spin_lock(&b->irq_lock); @@ -224,8 +232,6 @@ static void signal_irq_work(struct irq_work *work) if (b->irq_armed && list_empty(&b->signalers)) __intel_breadcrumbs_disarm_irq(b); - list_splice_init(&b->signaled_requests, &signal); - list_for_each_entry_safe(ce, cn, &b->signalers, signal_link) { GEM_BUG_ON(list_empty(&ce->signals)); @@ -242,7 +248,10 @@ static void signal_irq_work(struct irq_work *work) * spinlock as the callback chain may end up adding * more signalers to the same context or engine. */ - __signal_request(rq, &signal); + clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); + if (__signal_request(rq)) + /* We own signal_node now, xfer to local list */ + signal = slist_add(&rq->signal_node, signal); } /* @@ -262,9 +271,9 @@ static void signal_irq_work(struct irq_work *work) spin_unlock(&b->irq_lock); - list_for_each_safe(pos, next, &signal) { + llist_for_each_safe(signal, sn, signal) { struct i915_request *rq = - list_entry(pos, typeof(*rq), signal_link); + llist_entry(signal, typeof(*rq), signal_node); struct list_head cb_list; spin_lock(&rq->lock); @@ -291,7 +300,7 @@ intel_breadcrumbs_create(struct intel_engine_cs *irq_engine) spin_lock_init(&b->irq_lock); INIT_LIST_HEAD(&b->signalers); - INIT_LIST_HEAD(&b->signaled_requests); + init_llist_head(&b->signaled_requests); init_irq_work(&b->irq_work, signal_irq_work); @@ -355,7 +364,8 @@ static void insert_breadcrumb(struct i915_request *rq, * its signal completion. */ if (__request_completed(rq)) { - if (__signal_request(rq, &b->signaled_requests)) + if (__signal_request(rq) && + llist_add(&rq->signal_node, &b->signaled_requests)) irq_work_queue(&b->irq_work); return; } diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h index 8e53b9942695..3fa19820b37a 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h @@ -35,7 +35,7 @@ struct intel_breadcrumbs { struct intel_engine_cs *irq_engine; struct list_head signalers; - struct list_head signaled_requests; + struct llist_head signaled_requests; struct irq_work irq_work; /* for use from inside irq_lock */ diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 16b721080195..874af6db6103 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -176,7 +176,11 @@ struct i915_request { struct intel_context *context; struct intel_ring *ring; struct intel_timeline __rcu *timeline; - struct list_head signal_link; + + union { + struct list_head signal_link; + struct llist_node signal_node; + }; /* * The rcu epoch of when this request was allocated. Used to judiciously -- cgit v1.2.3 From 2e6ce8313a53b757b28b288bf4bb930df786e899 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 23 Nov 2020 11:37:16 +0000 Subject: drm/i915/gt: Don't cancel the interrupt shadow too early We currently want to keep the interrupt enabled until the interrupt after which we have no more work to do. This heuristic was broken by us kicking the irq-work on adding a completed request without attaching a signaler -- hence it appearing to the irq-worker that an interrupt had fired when we were idle. Fixes: 2854d866327a ("drm/i915/gt: Replace intel_engine_transfer_stale_breadcrumbs") Signed-off-by: Chris Wilson Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20201123113717.20500-3-chris@chris-wilson.co.uk (cherry picked from commit 3aef910d26ef48b8a79d48b006dc04383b86dd31) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index 43cfabb102ea..cf6e05ea4d8f 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -229,7 +229,7 @@ static void signal_irq_work(struct irq_work *work) * interrupt draw less ire from other users of the system and tools * like powertop. */ - if (b->irq_armed && list_empty(&b->signalers)) + if (!signal && b->irq_armed && list_empty(&b->signalers)) __intel_breadcrumbs_disarm_irq(b); list_for_each_entry_safe(ce, cn, &b->signalers, signal_link) { -- cgit v1.2.3 From 280ffdb6ddb5de85eddd476a3bcdc19c9a80f089 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 23 Nov 2020 11:37:17 +0000 Subject: drm/i915/gt: Free stale request on destroying the virtual engine Since preempt-to-busy, we may unsubmit a request while it is still on the HW and completes asynchronously. That means it may be retired and in the process destroy the virtual engine (as the user has closed their context), but that engine may still be holding onto the unsubmitted compelted request. Therefore we need to potentially cleanup the old request on destroying the virtual engine. We also have to keep the virtual_engine alive until after the sibling's execlists_dequeue() have finished peeking into the virtual engines, for which we serialise with RCU. v2: Be paranoid and flush the tasklet as well. v3: And flush the tasklet before the engines, as the tasklet may re-attach an rb_node after our removal from the siblings. Fixes: 6d06779e8672 ("drm/i915: Load balancing across a virtual engine") Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20201123113717.20500-4-chris@chris-wilson.co.uk (cherry picked from commit 46eecfccb4c2b0f258adbafb2e53ca3b822cd663) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_lrc.c | 60 ++++++++++++++++++++++++++++++++----- 1 file changed, 53 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 9bb16bdf93cf..0952bf157234 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -182,6 +182,7 @@ struct virtual_engine { struct intel_engine_cs base; struct intel_context context; + struct rcu_work rcu; /* * We allow only a single request through the virtual engine at a time @@ -5425,33 +5426,57 @@ static struct list_head *virtual_queue(struct virtual_engine *ve) return &ve->base.execlists.default_priolist.requests[0]; } -static void virtual_context_destroy(struct kref *kref) +static void rcu_virtual_context_destroy(struct work_struct *wrk) { struct virtual_engine *ve = - container_of(kref, typeof(*ve), context.ref); + container_of(wrk, typeof(*ve), rcu.work); unsigned int n; - GEM_BUG_ON(!list_empty(virtual_queue(ve))); - GEM_BUG_ON(ve->request); GEM_BUG_ON(ve->context.inflight); + /* Preempt-to-busy may leave a stale request behind. */ + if (unlikely(ve->request)) { + struct i915_request *old; + + spin_lock_irq(&ve->base.active.lock); + + old = fetch_and_zero(&ve->request); + if (old) { + GEM_BUG_ON(!i915_request_completed(old)); + __i915_request_submit(old); + i915_request_put(old); + } + + spin_unlock_irq(&ve->base.active.lock); + } + + /* + * Flush the tasklet in case it is still running on another core. + * + * This needs to be done before we remove ourselves from the siblings' + * rbtrees as in the case it is running in parallel, it may reinsert + * the rb_node into a sibling. + */ + tasklet_kill(&ve->base.execlists.tasklet); + + /* Decouple ourselves from the siblings, no more access allowed. */ for (n = 0; n < ve->num_siblings; n++) { struct intel_engine_cs *sibling = ve->siblings[n]; struct rb_node *node = &ve->nodes[sibling->id].rb; - unsigned long flags; if (RB_EMPTY_NODE(node)) continue; - spin_lock_irqsave(&sibling->active.lock, flags); + spin_lock_irq(&sibling->active.lock); /* Detachment is lazily performed in the execlists tasklet */ if (!RB_EMPTY_NODE(node)) rb_erase_cached(node, &sibling->execlists.virtual); - spin_unlock_irqrestore(&sibling->active.lock, flags); + spin_unlock_irq(&sibling->active.lock); } GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.execlists.tasklet)); + GEM_BUG_ON(!list_empty(virtual_queue(ve))); if (ve->context.state) __execlists_context_fini(&ve->context); @@ -5464,6 +5489,27 @@ static void virtual_context_destroy(struct kref *kref) kfree(ve); } +static void virtual_context_destroy(struct kref *kref) +{ + struct virtual_engine *ve = + container_of(kref, typeof(*ve), context.ref); + + GEM_BUG_ON(!list_empty(&ve->context.signals)); + + /* + * When destroying the virtual engine, we have to be aware that + * it may still be in use from an hardirq/softirq context causing + * the resubmission of a completed request (background completion + * due to preempt-to-busy). Before we can free the engine, we need + * to flush the submission code and tasklets that are still potentially + * accessing the engine. Flushing the tasklets requires process context, + * and since we can guard the resubmit onto the engine with an RCU read + * lock, we can delegate the free of the engine to an RCU worker. + */ + INIT_RCU_WORK(&ve->rcu, rcu_virtual_context_destroy); + queue_rcu_work(system_wq, &ve->rcu); +} + static void virtual_engine_initial_hint(struct virtual_engine *ve) { int swp; -- cgit v1.2.3 From d661155bfca329851a27bb5120fab027db43bd23 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Tue, 17 Nov 2020 15:25:48 -0500 Subject: drm/amd/display: Avoid HDCP initialization in devices without output The HDCP feature requires at least one connector attached to the device; however, some GPUs do not have a physical output, making the HDCP initialization irrelevant. This patch disables HDCP initialization when the graphic card does not have output. Acked-by: Alex Deucher Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 0e7118000919..9b6809f309f4 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1041,7 +1041,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) amdgpu_dm_init_color_mod(); #ifdef CONFIG_DRM_AMD_DC_HDCP - if (adev->asic_type >= CHIP_RAVEN) { + if (adev->dm.dc->caps.max_links > 0 && adev->asic_type >= CHIP_RAVEN) { adev->dm.hdcp_workqueue = hdcp_create_workqueue(adev, &init_params.cp_psp, adev->dm.dc); if (!adev->dm.hdcp_workqueue) -- cgit v1.2.3 From 60734bd54679d7998a24a257b0403f7644005572 Mon Sep 17 00:00:00 2001 From: Likun Gao Date: Mon, 23 Nov 2020 10:28:46 +0800 Subject: drm/amdgpu: update golden setting for sienna_cichlid Update golden setting for sienna_cichlid. Signed-off-by: Likun Gao Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 5.9.x --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 3579565e0eab..55f4b8c3b933 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3105,6 +3105,8 @@ static const struct soc15_reg_golden golden_settings_gc_10_3[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_EXCEPTION_CONTROL, 0x7fff0f1f, 0x00b80000), + SOC15_REG_GOLDEN_VALUE(GC, 0 ,mmGCEA_SDP_TAG_RESERVE0, 0xffffffff, 0x10100100), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCEA_SDP_TAG_RESERVE1, 0xffffffff, 0x17000088), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Sienna_Cichlid, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGE_PC_CNTL, 0x003fffff, 0x00280400), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf), -- cgit v1.2.3 From 095fbca0a94930b58f977284ef1b759b98700f8b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 26 Oct 2020 23:03:13 +0100 Subject: Makefile.extrawarn: move -Wcast-align to W=3 This warning behaves differently depending on the architecture and compiler. Using x86 gcc, we get no output at all because gcc knows the architecture can handle unaligned accesses. Using x86 clang, or gcc on an architecture that needs to manually deal with unaligned accesses, the build log is completely flooded with these warnings, as they are commonly invoked by inline functions of networking headers, e.g. include/linux/skbuff.h:1426:26: warning: cast increases required alignment of target type [-Wcast-align] The compiler is correct to point this out, as we are dealing with undefined behavior that does cause problems in practice, but there is also no good way to rewrite the code in commonly included headers to a safer method. Signed-off-by: Arnd Bergmann Reviewed-by: Nathan Chancellor Signed-off-by: Masahiro Yamada --- scripts/Makefile.extrawarn | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 95e4cdb94fe9..6baee1200615 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -60,7 +60,6 @@ endif # ifneq ($(findstring 2, $(KBUILD_EXTRA_WARN)),) -KBUILD_CFLAGS += -Wcast-align KBUILD_CFLAGS += -Wdisabled-optimization KBUILD_CFLAGS += -Wnested-externs KBUILD_CFLAGS += -Wshadow @@ -80,6 +79,7 @@ endif ifneq ($(findstring 3, $(KBUILD_EXTRA_WARN)),) KBUILD_CFLAGS += -Wbad-function-cast +KBUILD_CFLAGS += -Wcast-align KBUILD_CFLAGS += -Wcast-qual KBUILD_CFLAGS += -Wconversion KBUILD_CFLAGS += -Wpacked -- cgit v1.2.3 From a716bd7432106aed82a751409d7be851a23022ac Mon Sep 17 00:00:00 2001 From: Denys Zagorui Date: Mon, 2 Nov 2020 04:08:53 -0800 Subject: kbuild: use -fmacro-prefix-map for .S sources Follow-up to commit a73619a845d5 ("kbuild: use -fmacro-prefix-map to make __FILE__ a relative path"). Assembler sources also use __FILE__ macro so this flag should be also applied to those sources. Signed-off-by: Denys Zagorui Signed-off-by: Masahiro Yamada --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index ed081e3eb800..87d659d3c8de 100644 --- a/Makefile +++ b/Makefile @@ -946,7 +946,7 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=incompatible-pointer-types) KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init) # change __FILE__ to the relative path from the srctree -KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) +KBUILD_CPPFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) # ensure -fcf-protection is disabled when using retpoline as it is # incompatible with -mindirect-branch=thunk-extern -- cgit v1.2.3 From b8a9092330da2030496ff357272f342eb970d51b Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Mon, 9 Nov 2020 10:35:28 -0800 Subject: Kbuild: do not emit debug info for assembly with LLVM_IAS=1 Clang's integrated assembler produces the warning for assembly files: warning: DWARF2 only supports one section per compilation unit If -Wa,-gdwarf-* is unspecified, then debug info is not emitted for assembly sources (it is still emitted for C sources). This will be re-enabled for newer DWARF versions in a follow up patch. Enables defconfig+CONFIG_DEBUG_INFO to build cleanly with LLVM=1 LLVM_IAS=1 for x86_64 and arm64. Cc: Link: https://github.com/ClangBuiltLinux/linux/issues/716 Reported-by: Dmitry Golovin Reported-by: Nathan Chancellor Suggested-by: Dmitry Golovin Suggested-by: Nathan Chancellor Suggested-by: Sedat Dilek Reviewed-by: Fangrui Song Reviewed-by: Nathan Chancellor Signed-off-by: Nick Desaulniers Signed-off-by: Masahiro Yamada --- Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Makefile b/Makefile index 87d659d3c8de..ae1592c1f5d6 100644 --- a/Makefile +++ b/Makefile @@ -828,7 +828,9 @@ else DEBUG_CFLAGS += -g endif +ifneq ($(LLVM_IAS),1) KBUILD_AFLAGS += -Wa,-gdwarf-2 +endif ifdef CONFIG_DEBUG_INFO_DWARF4 DEBUG_CFLAGS += -gdwarf-4 -- cgit v1.2.3 From 9bd2702d292cb7b565b09e949d30288ab7a26d51 Mon Sep 17 00:00:00 2001 From: Lincoln Ramsay Date: Mon, 23 Nov 2020 21:40:43 +0000 Subject: aquantia: Remove the build_skb path When performing IPv6 forwarding, there is an expectation that SKBs will have some headroom. When forwarding a packet from the aquantia driver, this does not always happen, triggering a kernel warning. aq_ring.c has this code (edited slightly for brevity): if (buff->is_eop && buff->len <= AQ_CFG_RX_FRAME_MAX - AQ_SKB_ALIGN) { skb = build_skb(aq_buf_vaddr(&buff->rxdata), AQ_CFG_RX_FRAME_MAX); } else { skb = napi_alloc_skb(napi, AQ_CFG_RX_HDR_SIZE); There is a significant difference between the SKB produced by these 2 code paths. When napi_alloc_skb creates an SKB, there is a certain amount of headroom reserved. However, this is not done in the build_skb codepath. As the hardware buffer that build_skb is built around does not handle the presence of the SKB header, this code path is being removed and the napi_alloc_skb path will always be used. This code path does have to copy the packet header into the SKB, but it adds the packet data as a frag. Fixes: 018423e90bee ("net: ethernet: aquantia: Add ring support code") Signed-off-by: Lincoln Ramsay Link: https://lore.kernel.org/r/MWHPR1001MB23184F3EAFA413E0D1910EC9E8FC0@MWHPR1001MB2318.namprd10.prod.outlook.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 126 ++++++++++------------- 1 file changed, 52 insertions(+), 74 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 4f913658eea4..24122ccda614 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -413,85 +413,63 @@ int aq_ring_rx_clean(struct aq_ring_s *self, buff->rxdata.pg_off, buff->len, DMA_FROM_DEVICE); - /* for single fragment packets use build_skb() */ - if (buff->is_eop && - buff->len <= AQ_CFG_RX_FRAME_MAX - AQ_SKB_ALIGN) { - skb = build_skb(aq_buf_vaddr(&buff->rxdata), + skb = napi_alloc_skb(napi, AQ_CFG_RX_HDR_SIZE); + if (unlikely(!skb)) { + u64_stats_update_begin(&self->stats.rx.syncp); + self->stats.rx.skb_alloc_fails++; + u64_stats_update_end(&self->stats.rx.syncp); + err = -ENOMEM; + goto err_exit; + } + if (is_ptp_ring) + buff->len -= + aq_ptp_extract_ts(self->aq_nic, skb, + aq_buf_vaddr(&buff->rxdata), + buff->len); + + hdr_len = buff->len; + if (hdr_len > AQ_CFG_RX_HDR_SIZE) + hdr_len = eth_get_headlen(skb->dev, + aq_buf_vaddr(&buff->rxdata), + AQ_CFG_RX_HDR_SIZE); + + memcpy(__skb_put(skb, hdr_len), aq_buf_vaddr(&buff->rxdata), + ALIGN(hdr_len, sizeof(long))); + + if (buff->len - hdr_len > 0) { + skb_add_rx_frag(skb, 0, buff->rxdata.page, + buff->rxdata.pg_off + hdr_len, + buff->len - hdr_len, AQ_CFG_RX_FRAME_MAX); - if (unlikely(!skb)) { - u64_stats_update_begin(&self->stats.rx.syncp); - self->stats.rx.skb_alloc_fails++; - u64_stats_update_end(&self->stats.rx.syncp); - err = -ENOMEM; - goto err_exit; - } - if (is_ptp_ring) - buff->len -= - aq_ptp_extract_ts(self->aq_nic, skb, - aq_buf_vaddr(&buff->rxdata), - buff->len); - skb_put(skb, buff->len); page_ref_inc(buff->rxdata.page); - } else { - skb = napi_alloc_skb(napi, AQ_CFG_RX_HDR_SIZE); - if (unlikely(!skb)) { - u64_stats_update_begin(&self->stats.rx.syncp); - self->stats.rx.skb_alloc_fails++; - u64_stats_update_end(&self->stats.rx.syncp); - err = -ENOMEM; - goto err_exit; - } - if (is_ptp_ring) - buff->len -= - aq_ptp_extract_ts(self->aq_nic, skb, - aq_buf_vaddr(&buff->rxdata), - buff->len); - - hdr_len = buff->len; - if (hdr_len > AQ_CFG_RX_HDR_SIZE) - hdr_len = eth_get_headlen(skb->dev, - aq_buf_vaddr(&buff->rxdata), - AQ_CFG_RX_HDR_SIZE); - - memcpy(__skb_put(skb, hdr_len), aq_buf_vaddr(&buff->rxdata), - ALIGN(hdr_len, sizeof(long))); - - if (buff->len - hdr_len > 0) { - skb_add_rx_frag(skb, 0, buff->rxdata.page, - buff->rxdata.pg_off + hdr_len, - buff->len - hdr_len, - AQ_CFG_RX_FRAME_MAX); - page_ref_inc(buff->rxdata.page); - } + } - if (!buff->is_eop) { - buff_ = buff; - i = 1U; - do { - next_ = buff_->next, - buff_ = &self->buff_ring[next_]; + if (!buff->is_eop) { + buff_ = buff; + i = 1U; + do { + next_ = buff_->next; + buff_ = &self->buff_ring[next_]; - dma_sync_single_range_for_cpu( - aq_nic_get_dev(self->aq_nic), - buff_->rxdata.daddr, - buff_->rxdata.pg_off, - buff_->len, - DMA_FROM_DEVICE); - skb_add_rx_frag(skb, i++, - buff_->rxdata.page, - buff_->rxdata.pg_off, - buff_->len, - AQ_CFG_RX_FRAME_MAX); - page_ref_inc(buff_->rxdata.page); - buff_->is_cleaned = 1; - - buff->is_ip_cso &= buff_->is_ip_cso; - buff->is_udp_cso &= buff_->is_udp_cso; - buff->is_tcp_cso &= buff_->is_tcp_cso; - buff->is_cso_err |= buff_->is_cso_err; + dma_sync_single_range_for_cpu(aq_nic_get_dev(self->aq_nic), + buff_->rxdata.daddr, + buff_->rxdata.pg_off, + buff_->len, + DMA_FROM_DEVICE); + skb_add_rx_frag(skb, i++, + buff_->rxdata.page, + buff_->rxdata.pg_off, + buff_->len, + AQ_CFG_RX_FRAME_MAX); + page_ref_inc(buff_->rxdata.page); + buff_->is_cleaned = 1; - } while (!buff_->is_eop); - } + buff->is_ip_cso &= buff_->is_ip_cso; + buff->is_udp_cso &= buff_->is_udp_cso; + buff->is_tcp_cso &= buff_->is_tcp_cso; + buff->is_cso_err |= buff_->is_cso_err; + + } while (!buff_->is_eop); } if (buff->is_vlan) -- cgit v1.2.3 From 5204bb683c1633e550c2124ccc2358dd645a80db Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Mon, 23 Nov 2020 07:36:25 +0200 Subject: devlink: Fix reload stats structure Fix reload stats structure exposed to the user. Change stats structure hierarchy to have the reload action as a parent of the stat entry and then stat entry includes value per limit. This will also help to avoid string concatenation on iproute2 output. Reload stats structure before this fix: "stats": { "reload": { "driver_reinit": 2, "fw_activate": 1, "fw_activate_no_reset": 0 } } After this fix: "stats": { "reload": { "driver_reinit": { "unspecified": 2 }, "fw_activate": { "unspecified": 1, "no_reset": 0 } } Fixes: a254c264267e ("devlink: Add reload stats") Signed-off-by: Moshe Shemesh Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/1606109785-25197-1-git-send-email-moshe@mellanox.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/devlink.h | 2 ++ net/core/devlink.c | 49 +++++++++++++++++++++++++++++--------------- 2 files changed, 35 insertions(+), 16 deletions(-) diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 0113bc4db9f5..5203f54a2be1 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -526,6 +526,8 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_STATS_LIMIT, /* u8 */ DEVLINK_ATTR_RELOAD_STATS_VALUE, /* u32 */ DEVLINK_ATTR_REMOTE_RELOAD_STATS, /* nested */ + DEVLINK_ATTR_RELOAD_ACTION_INFO, /* nested */ + DEVLINK_ATTR_RELOAD_ACTION_STATS, /* nested */ /* add new attributes above here, update the policy in devlink.c */ diff --git a/net/core/devlink.c b/net/core/devlink.c index 4b0211590aac..c91e15b7a2bd 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -517,7 +517,7 @@ devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_l return test_bit(limit, &devlink->ops->reload_limits); } -static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_action action, +static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_limit limit, u32 value) { struct nlattr *reload_stats_entry; @@ -526,8 +526,7 @@ static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_acti if (!reload_stats_entry) return -EMSGSIZE; - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, action) || - nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) goto nla_put_failure; nla_nest_end(msg, reload_stats_entry); @@ -540,7 +539,7 @@ nla_put_failure: static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) { - struct nlattr *reload_stats_attr; + struct nlattr *reload_stats_attr, *act_info, *act_stats; int i, j, stat_idx; u32 value; @@ -552,17 +551,29 @@ static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink if (!reload_stats_attr) return -EMSGSIZE; - for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { - /* Remote stats are shown even if not locally supported. Stats - * of actions with unspecified limit are shown though drivers - * don't need to register unspecified limit. - */ - if (!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && - !devlink_reload_limit_is_supported(devlink, j)) + for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { + if ((!is_remote && + !devlink_reload_action_is_supported(devlink, i)) || + i == DEVLINK_RELOAD_ACTION_UNSPEC) continue; - for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { - if ((!is_remote && !devlink_reload_action_is_supported(devlink, i)) || - i == DEVLINK_RELOAD_ACTION_UNSPEC || + act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO); + if (!act_info) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i)) + goto action_info_nest_cancel; + act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS); + if (!act_stats) + goto action_info_nest_cancel; + + for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { + /* Remote stats are shown even if not locally supported. + * Stats of actions with unspecified limit are shown + * though drivers don't need to register unspecified + * limit. + */ + if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && + !devlink_reload_limit_is_supported(devlink, j)) || devlink_reload_combination_is_invalid(i, j)) continue; @@ -571,13 +582,19 @@ static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink value = devlink->stats.reload_stats[stat_idx]; else value = devlink->stats.remote_reload_stats[stat_idx]; - if (devlink_reload_stat_put(msg, i, j, value)) - goto nla_put_failure; + if (devlink_reload_stat_put(msg, j, value)) + goto action_stats_nest_cancel; } + nla_nest_end(msg, act_stats); + nla_nest_end(msg, act_info); } nla_nest_end(msg, reload_stats_attr); return 0; +action_stats_nest_cancel: + nla_nest_cancel(msg, act_stats); +action_info_nest_cancel: + nla_nest_cancel(msg, act_info); nla_put_failure: nla_nest_cancel(msg, reload_stats_attr); return -EMSGSIZE; -- cgit v1.2.3 From 36ccdf85829a7dd6936dba5d02fa50138471f0d3 Mon Sep 17 00:00:00 2001 From: Björn Töpel Date: Mon, 23 Nov 2020 18:56:00 +0100 Subject: net, xsk: Avoid taking multiple skbuff references MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 642e450b6b59 ("xsk: Do not discard packet when NETDEV_TX_BUSY") addressed the problem that packets were discarded from the Tx AF_XDP ring, when the driver returned NETDEV_TX_BUSY. Part of the fix was bumping the skbuff reference count, so that the buffer would not be freed by dev_direct_xmit(). A reference count larger than one means that the skbuff is "shared", which is not the case. If the "shared" skbuff is sent to the generic XDP receive path, netif_receive_generic_xdp(), and pskb_expand_head() is entered the BUG_ON(skb_shared(skb)) will trigger. This patch adds a variant to dev_direct_xmit(), __dev_direct_xmit(), where a user can select the skbuff free policy. This allows AF_XDP to avoid bumping the reference count, but still keep the NETDEV_TX_BUSY behavior. Fixes: 642e450b6b59 ("xsk: Do not discard packet when NETDEV_TX_BUSY") Reported-by: Yonghong Song Signed-off-by: Björn Töpel Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20201123175600.146255-1-bjorn.topel@gmail.com --- include/linux/netdevice.h | 14 +++++++++++++- net/core/dev.c | 8 ++------ net/xdp/xsk.c | 8 +------- 3 files changed, 16 insertions(+), 14 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 964b494b0e8d..76775abf259d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2813,9 +2813,21 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); + int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); -int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); +int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id); + +static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) +{ + int ret; + + ret = __dev_direct_xmit(skb, queue_id); + if (!dev_xmit_complete(ret)) + kfree_skb(skb); + return ret; +} + int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head); diff --git a/net/core/dev.c b/net/core/dev.c index 82dc6b48e45f..8588ade790cb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4180,7 +4180,7 @@ int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev) } EXPORT_SYMBOL(dev_queue_xmit_accel); -int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) +int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { struct net_device *dev = skb->dev; struct sk_buff *orig_skb = skb; @@ -4210,17 +4210,13 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) dev_xmit_recursion_dec(); local_bh_enable(); - - if (!dev_xmit_complete(ret)) - kfree_skb(skb); - return ret; drop: atomic_long_inc(&dev->tx_dropped); kfree_skb_list(skb); return NET_XMIT_DROP; } -EXPORT_SYMBOL(dev_direct_xmit); +EXPORT_SYMBOL(__dev_direct_xmit); /************************************************************************* * Receiver routines diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 5a6cdf7b320d..b7b039bd9d03 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -411,11 +411,7 @@ static int xsk_generic_xmit(struct sock *sk) skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr; skb->destructor = xsk_destruct_skb; - /* Hinder dev_direct_xmit from freeing the packet and - * therefore completing it in the destructor - */ - refcount_inc(&skb->users); - err = dev_direct_xmit(skb, xs->queue_id); + err = __dev_direct_xmit(skb, xs->queue_id); if (err == NETDEV_TX_BUSY) { /* Tell user-space to retry the send */ skb->destructor = sock_wfree; @@ -429,12 +425,10 @@ static int xsk_generic_xmit(struct sock *sk) /* Ignore NET_XMIT_CN as packet might have been sent */ if (err == NET_XMIT_DROP) { /* SKB completed but not sent */ - kfree_skb(skb); err = -EBUSY; goto out; } - consume_skb(skb); sent_frame = true; } -- cgit v1.2.3 From 407c85c7ddd6b84d3cbdd2275616f70c27c17913 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Nov 2020 19:47:44 -0800 Subject: tcp: Set ECT0 bit in tos/tclass for synack when BPF needs ECN When a BPF program is used to select between a type of TCP congestion control algorithm that uses either ECN or not there is a case where the synack for the frame was coming up without the ECT0 bit set. A bit of research found that this was due to the final socket being configured to dctcp while the listener socket was staying in cubic. To reproduce it all that is needed is to monitor TCP traffic while running the sample bpf program "samples/bpf/tcp_cong_kern.c". What is observed, assuming tcp_dctcp module is loaded or compiled in and the traffic matches the rules in the sample file, is that for all frames with the exception of the synack the ECT0 bit is set. To address that it is necessary to make one additional call to tcp_bpf_ca_needs_ecn using the request socket and then use the output of that to set the ECT0 bit for the tos/tclass of the packet. Fixes: 91b5b21c7c16 ("bpf: Add support for changing congestion control") Signed-off-by: Alexander Duyck Link: https://lore.kernel.org/r/160593039663.2604.1374502006916871573.stgit@localhost.localdomain Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_ipv4.c | 12 ++++++++---- net/ipv6/tcp_ipv6.c | 9 +++++++-- 2 files changed, 15 insertions(+), 6 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c95fcdfeed42..8391aa29e7a4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -980,13 +980,17 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); - tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : - inet_sk(sk)->tos; - if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); + tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? + tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : + inet_sk(sk)->tos; + + if (!INET_ECN_is_capable(tos) && + tcp_bpf_ca_needs_ecn((struct sock *)req)) + tos |= INET_ECN_ECT_0; + rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d2502911b7fa..992cbf3eb9e3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -527,11 +527,16 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, if (np->repflow && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); - rcu_read_lock(); - opt = ireq->ipv6_opt; tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : np->tclass; + + if (!INET_ECN_is_capable(tclass) && + tcp_bpf_ca_needs_ecn((struct sock *)req)) + tclass |= INET_ECN_ECT_0; + + rcu_read_lock(); + opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, -- cgit v1.2.3 From 68878a5c5b852d17f5827ce8a0f6fbd8b4cdfada Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Tue, 24 Nov 2020 18:41:00 +0800 Subject: bpftool: Fix error return value in build_btf_type_table An appropriate return value should be set on the failed path. Fixes: 4d374ba0bf30 ("tools: bpftool: implement "bpftool btf show|list"") Reported-by: Hulk Robot Signed-off-by: Zhen Lei Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20201124104100.491-1-thunder.leizhen@huawei.com --- tools/bpf/bpftool/btf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 8ab142ff5eac..2afb7d5b1aca 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -693,6 +693,7 @@ build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type, obj_node = calloc(1, sizeof(*obj_node)); if (!obj_node) { p_err("failed to allocate memory: %s", strerror(errno)); + err = -ENOMEM; goto err_free; } -- cgit v1.2.3 From bc40a3691f15c0728209cd0e2dc9e8e18854187f Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 23 Nov 2020 14:42:26 +0100 Subject: MAINTAINERS: Update page pool entry Add some file F: matches that is related to page_pool. Acked-by: Ilias Apalodimas Signed-off-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/160613894639.2826716.14635284017814375894.stgit@firesoul Signed-off-by: Jakub Kicinski --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index ac84b34ef2ad..d0d974f44655 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13161,7 +13161,9 @@ M: Jesper Dangaard Brouer M: Ilias Apalodimas L: netdev@vger.kernel.org S: Supported +F: Documentation/networking/page_pool.rst F: include/net/page_pool.h +F: include/trace/events/page_pool.h F: net/core/page_pool.c PANASONIC LAPTOP ACPI EXTRAS DRIVER -- cgit v1.2.3 From 16e6281b6b22b0178eab95c6a82502d7b10f67b8 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Sun, 22 Nov 2020 18:10:24 -0500 Subject: gfs2: Fix deadlock dumping resource group glocks Commit 0e539ca1bbbe ("gfs2: Fix NULL pointer dereference in gfs2_rgrp_dump") introduced additional locking in gfs2_rgrp_go_dump, which is also used for dumping resource group glocks via debugfs. However, on that code path, the glock spin lock is already taken in dump_glock, and taking it again in gfs2_glock2rgrp leads to deadlock. This can be reproduced with: $ mkfs.gfs2 -O -p lock_nolock /dev/FOO $ mount /dev/FOO /mnt/foo $ touch /mnt/foo/bar $ cat /sys/kernel/debug/gfs2/FOO/glocks Fix that by not taking the glock spin lock inside the go_dump callback. Fixes: 0e539ca1bbbe ("gfs2: Fix NULL pointer dereference in gfs2_rgrp_dump") Signed-off-by: Alexander Aring Signed-off-by: Andreas Gruenbacher --- fs/gfs2/glops.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 67f2921ae8d4..6cedeefb7b3f 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -245,7 +245,7 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags) static void gfs2_rgrp_go_dump(struct seq_file *seq, struct gfs2_glock *gl, const char *fs_id_buf) { - struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); + struct gfs2_rgrpd *rgd = gl->gl_object; if (rgd) gfs2_rgrp_dump(seq, rgd, fs_id_buf); -- cgit v1.2.3 From 515b269d5bd29a986d5e1c0a0cba87fa865a48b4 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 23 Nov 2020 10:53:35 -0500 Subject: gfs2: set lockdep subclass for iopen glocks This patch introduce a new globs attribute to define the subclass of the glock lockref spinlock. This avoid the following lockdep warning, which occurs when we lock an inode lock while an iopen lock is held: ============================================ WARNING: possible recursive locking detected 5.10.0-rc3+ #4990 Not tainted -------------------------------------------- kworker/0:1/12 is trying to acquire lock: ffff9067d45672d8 (&gl->gl_lockref.lock){+.+.}-{3:3}, at: lockref_get+0x9/0x20 but task is already holding lock: ffff9067da308588 (&gl->gl_lockref.lock){+.+.}-{3:3}, at: delete_work_func+0x164/0x260 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&gl->gl_lockref.lock); lock(&gl->gl_lockref.lock); *** DEADLOCK *** May be due to missing lock nesting notation 3 locks held by kworker/0:1/12: #0: ffff9067c1bfdd38 ((wq_completion)delete_workqueue){+.+.}-{0:0}, at: process_one_work+0x1b7/0x540 #1: ffffac594006be70 ((work_completion)(&(&gl->gl_delete)->work)){+.+.}-{0:0}, at: process_one_work+0x1b7/0x540 #2: ffff9067da308588 (&gl->gl_lockref.lock){+.+.}-{3:3}, at: delete_work_func+0x164/0x260 stack backtrace: CPU: 0 PID: 12 Comm: kworker/0:1 Not tainted 5.10.0-rc3+ #4990 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 Workqueue: delete_workqueue delete_work_func Call Trace: dump_stack+0x8b/0xb0 __lock_acquire.cold+0x19e/0x2e3 lock_acquire+0x150/0x410 ? lockref_get+0x9/0x20 _raw_spin_lock+0x27/0x40 ? lockref_get+0x9/0x20 lockref_get+0x9/0x20 delete_work_func+0x188/0x260 process_one_work+0x237/0x540 worker_thread+0x4d/0x3b0 ? process_one_work+0x540/0x540 kthread+0x127/0x140 ? __kthread_bind_mask+0x60/0x60 ret_from_fork+0x22/0x30 Suggested-by: Andreas Gruenbacher Signed-off-by: Alexander Aring Signed-off-by: Andreas Gruenbacher --- fs/gfs2/glock.c | 1 + fs/gfs2/glops.c | 1 + fs/gfs2/incore.h | 1 + 3 files changed, 3 insertions(+) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index d98a2e5dab9f..35a6fd103761 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1035,6 +1035,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, gl->gl_node.next = NULL; gl->gl_flags = 0; gl->gl_name = name; + lockdep_set_subclass(&gl->gl_lockref.lock, glops->go_subclass); gl->gl_lockref.count = 1; gl->gl_state = LM_ST_UNLOCKED; gl->gl_target = LM_ST_UNLOCKED; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 6cedeefb7b3f..e2cfc00ab936 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -781,6 +781,7 @@ const struct gfs2_glock_operations gfs2_iopen_glops = { .go_callback = iopen_go_callback, .go_demote_ok = iopen_go_demote_ok, .go_flags = GLOF_LRU | GLOF_NONDISK, + .go_subclass = 1, }; const struct gfs2_glock_operations gfs2_flock_glops = { diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index d7707307f4b1..f8858d995b24 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -247,6 +247,7 @@ struct gfs2_glock_operations { const char *fs_id_buf); void (*go_callback)(struct gfs2_glock *gl, bool remote); void (*go_free)(struct gfs2_glock *gl); + const int go_subclass; const int go_type; const unsigned long go_flags; #define GLOF_ASPACE 1 /* address space attached */ -- cgit v1.2.3 From 078eb55cdf25e0a621d406c233cc1b4acc31c82f Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Mon, 23 Nov 2020 18:35:53 +0200 Subject: dpaa2-eth: Fix compile error due to missing devlink support The dpaa2 driver depends on devlink, so it should select NET_DEVLINK in order to fix compile errors, such as: drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.o: in function `dpaa2_eth_rx_err': dpaa2-eth.c:(.text+0x3cec): undefined reference to `devlink_trap_report' drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.o: in function `dpaa2_eth_dl_info_get': dpaa2-eth-devlink.c:(.text+0x160): undefined reference to `devlink_info_driver_name_put' Fixes: ceeb03ad8e22 ("dpaa2-eth: add basic devlink support") Signed-off-by: Ezequiel Garcia Signed-off-by: Ioana Ciornei Link: https://lore.kernel.org/r/20201123163553.1666476-1-ciorneiioana@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/dpaa2/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/freescale/dpaa2/Kconfig b/drivers/net/ethernet/freescale/dpaa2/Kconfig index c0e05f71826d..ee7a906e30b3 100644 --- a/drivers/net/ethernet/freescale/dpaa2/Kconfig +++ b/drivers/net/ethernet/freescale/dpaa2/Kconfig @@ -5,6 +5,7 @@ config FSL_DPAA2_ETH select PHYLINK select PCS_LYNX select FSL_XGMAC_MDIO + select NET_DEVLINK help This is the DPAA2 Ethernet driver supporting Freescale SoCs with DPAA2 (DataPath Acceleration Architecture v2). -- cgit v1.2.3 From d8f0a86795c69f5b697f7d9e5274c124da93c92d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 23 Nov 2020 17:23:51 +0100 Subject: nfc: s3fwrn5: use signed integer for parsing GPIO numbers GPIOs - as returned by of_get_named_gpio() and used by the gpiolib - are signed integers, where negative number indicates error. The return value of of_get_named_gpio() should not be assigned to an unsigned int because in case of !CONFIG_GPIOLIB such number would be a valid GPIO. Fixes: c04c674fadeb ("nfc: s3fwrn5: Add driver for Samsung S3FWRN5 NFC Chip") Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20201123162351.209100-1-krzk@kernel.org Signed-off-by: Jakub Kicinski --- drivers/nfc/s3fwrn5/i2c.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nfc/s3fwrn5/i2c.c b/drivers/nfc/s3fwrn5/i2c.c index dc995286be84..d0a3bd9ff3c3 100644 --- a/drivers/nfc/s3fwrn5/i2c.c +++ b/drivers/nfc/s3fwrn5/i2c.c @@ -26,8 +26,8 @@ struct s3fwrn5_i2c_phy { struct i2c_client *i2c_dev; struct nci_dev *ndev; - unsigned int gpio_en; - unsigned int gpio_fw_wake; + int gpio_en; + int gpio_fw_wake; struct mutex mutex; -- cgit v1.2.3 From 073861ed77b6b957c3c8d54a11dc503f7d986ceb Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 24 Nov 2020 08:46:43 -0800 Subject: mm: fix VM_BUG_ON(PageTail) and BUG_ON(PageWriteback) Twice now, when exercising ext4 looped on shmem huge pages, I have crashed on the PF_ONLY_HEAD check inside PageWaiters(): ext4_finish_bio() calling end_page_writeback() calling wake_up_page() on tail of a shmem huge page, no longer an ext4 page at all. The problem is that PageWriteback is not accompanied by a page reference (as the NOTE at the end of test_clear_page_writeback() acknowledges): as soon as TestClearPageWriteback has been done, that page could be removed from page cache, freed, and reused for something else by the time that wake_up_page() is reached. https://lore.kernel.org/linux-mm/20200827122019.GC14765@casper.infradead.org/ Matthew Wilcox suggested avoiding or weakening the PageWaiters() tail check; but I'm paranoid about even looking at an unreferenced struct page, lest its memory might itself have already been reused or hotremoved (and wake_up_page_bit() may modify that memory with its ClearPageWaiters()). Then on crashing a second time, realized there's a stronger reason against that approach. If my testing just occasionally crashes on that check, when the page is reused for part of a compound page, wouldn't it be much more common for the page to get reused as an order-0 page before reaching wake_up_page()? And on rare occasions, might that reused page already be marked PageWriteback by its new user, and already be waited upon? What would that look like? It would look like BUG_ON(PageWriteback) after wait_on_page_writeback() in write_cache_pages() (though I have never seen that crash myself). Matthew Wilcox explaining this to himself: "page is allocated, added to page cache, dirtied, writeback starts, --- thread A --- filesystem calls end_page_writeback() test_clear_page_writeback() --- context switch to thread B --- truncate_inode_pages_range() finds the page, it doesn't have writeback set, we delete it from the page cache. Page gets reallocated, dirtied, writeback starts again. Then we call write_cache_pages(), see PageWriteback() set, call wait_on_page_writeback() --- context switch back to thread A --- wake_up_page(page, PG_writeback); ... thread B is woken, but because the wakeup was for the old use of the page, PageWriteback is still set. Devious" And prior to 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") this would have been much less likely: before that, wake_page_function()'s non-exclusive case would stop walking and not wake if it found Writeback already set again; whereas now the non-exclusive case proceeds to wake. I have not thought of a fix that does not add a little overhead: the simplest fix is for end_page_writeback() to get_page() before calling test_clear_page_writeback(), then put_page() after wake_up_page(). Was there a chance of missed wakeups before, since a page freed before reaching wake_up_page() would have PageWaiters cleared? I think not, because each waiter does hold a reference on the page. This bug comes when the old use of the page, the one we do TestClearPageWriteback on, had *no* waiters, so no additional page reference beyond the page cache (and whoever racily freed it). The reuse of the page has a waiter holding a reference, and its own PageWriteback set; but the belated wake_up_page() has woken the reuse to hit that BUG_ON(PageWriteback). Reported-by: syzbot+3622cea378100f45d59f@syzkaller.appspotmail.com Reported-by: Qian Cai Fixes: 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") Signed-off-by: Hugh Dickins Cc: stable@vger.kernel.org # v5.8+ Signed-off-by: Linus Torvalds --- mm/filemap.c | 8 ++++++++ mm/page-writeback.c | 6 ------ 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/mm/filemap.c b/mm/filemap.c index 3ebbe64a0106..0b2067b3c328 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1484,11 +1484,19 @@ void end_page_writeback(struct page *page) rotate_reclaimable_page(page); } + /* + * Writeback does not hold a page reference of its own, relying + * on truncation to wait for the clearing of PG_writeback. + * But here we must make sure that the page is not freed and + * reused before the wake_up_page(). + */ + get_page(page); if (!test_clear_page_writeback(page)) BUG(); smp_mb__after_atomic(); wake_up_page(page, PG_writeback); + put_page(page); } EXPORT_SYMBOL(end_page_writeback); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 7709f0e223f5..586042472ac9 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2754,12 +2754,6 @@ int test_clear_page_writeback(struct page *page) } else { ret = TestClearPageWriteback(page); } - /* - * NOTE: Page might be free now! Writeback doesn't hold a page - * reference on its own, it relies on truncation to wait for - * the clearing of PG_writeback. The below can only access - * page state that is static across allocation cycles. - */ if (ret) { dec_lruvec_state(lruvec, NR_WRITEBACK); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); -- cgit v1.2.3 From 5b7022cf1dc0d721bd4b5f3bada05bd8ced82fe0 Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Mon, 23 Nov 2020 21:08:57 +0200 Subject: net: ena: handle bad request id in ena_netdev After request id is checked in validate_rx_req_id() its value is still used in the line rx_ring->free_ids[next_to_clean] = rx_ring->ena_bufs[i].req_id; even if it was found to be out-of-bound for the array free_ids. The patch moves the request id to an earlier stage in the napi routine and makes sure its value isn't used if it's found out-of-bounds. Fixes: 30623e1ed116 ("net: ena: avoid memory access violation by validating req_id properly") Signed-off-by: Ido Segev Signed-off-by: Shay Agroskin Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amazon/ena/ena_eth_com.c | 3 ++ drivers/net/ethernet/amazon/ena/ena_netdev.c | 43 +++++++-------------------- 2 files changed, 14 insertions(+), 32 deletions(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c index ad30cacc1622..032ab9f20438 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c @@ -516,6 +516,7 @@ int ena_com_rx_pkt(struct ena_com_io_cq *io_cq, { struct ena_com_rx_buf_info *ena_buf = &ena_rx_ctx->ena_bufs[0]; struct ena_eth_io_rx_cdesc_base *cdesc = NULL; + u16 q_depth = io_cq->q_depth; u16 cdesc_idx = 0; u16 nb_hw_desc; u16 i = 0; @@ -543,6 +544,8 @@ int ena_com_rx_pkt(struct ena_com_io_cq *io_cq, do { ena_buf[i].len = cdesc->length; ena_buf[i].req_id = cdesc->req_id; + if (unlikely(ena_buf[i].req_id >= q_depth)) + return -EIO; if (++i >= nb_hw_desc) break; diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index e8131dadc22c..574c2b5ba21e 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -789,24 +789,6 @@ static void ena_free_all_io_tx_resources(struct ena_adapter *adapter) adapter->num_io_queues); } -static int validate_rx_req_id(struct ena_ring *rx_ring, u16 req_id) -{ - if (likely(req_id < rx_ring->ring_size)) - return 0; - - netif_err(rx_ring->adapter, rx_err, rx_ring->netdev, - "Invalid rx req_id: %hu\n", req_id); - - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.bad_req_id++; - u64_stats_update_end(&rx_ring->syncp); - - /* Trigger device reset */ - rx_ring->adapter->reset_reason = ENA_REGS_RESET_INV_RX_REQ_ID; - set_bit(ENA_FLAG_TRIGGER_RESET, &rx_ring->adapter->flags); - return -EFAULT; -} - /* ena_setup_rx_resources - allocate I/O Rx resources (Descriptors) * @adapter: network interface device structure * @qid: queue index @@ -1356,15 +1338,10 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, struct ena_rx_buffer *rx_info; u16 len, req_id, buf = 0; void *va; - int rc; len = ena_bufs[buf].len; req_id = ena_bufs[buf].req_id; - rc = validate_rx_req_id(rx_ring, req_id); - if (unlikely(rc < 0)) - return NULL; - rx_info = &rx_ring->rx_buffer_info[req_id]; if (unlikely(!rx_info->page)) { @@ -1440,10 +1417,6 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, len = ena_bufs[buf].len; req_id = ena_bufs[buf].req_id; - rc = validate_rx_req_id(rx_ring, req_id); - if (unlikely(rc < 0)) - return NULL; - rx_info = &rx_ring->rx_buffer_info[req_id]; } while (1); @@ -1697,12 +1670,18 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, error: adapter = netdev_priv(rx_ring->netdev); - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.bad_desc_num++; - u64_stats_update_end(&rx_ring->syncp); + if (rc == -ENOSPC) { + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->rx_stats.bad_desc_num++; + u64_stats_update_end(&rx_ring->syncp); + adapter->reset_reason = ENA_REGS_RESET_TOO_MANY_RX_DESCS; + } else { + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->rx_stats.bad_req_id++; + u64_stats_update_end(&rx_ring->syncp); + adapter->reset_reason = ENA_REGS_RESET_INV_RX_REQ_ID; + } - /* Too many desc from the device. Trigger reset */ - adapter->reset_reason = ENA_REGS_RESET_TOO_MANY_RX_DESCS; set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); return 0; -- cgit v1.2.3 From 09323b3bca95181c0da79daebc8b0603e500f573 Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Mon, 23 Nov 2020 21:08:58 +0200 Subject: net: ena: set initial DMA width to avoid intel iommu issue The ENA driver uses the readless mechanism, which uses DMA, to find out what the DMA mask is supposed to be. If DMA is used without setting the dma_mask first, it causes the Intel IOMMU driver to think that ENA is a 32-bit device and therefore disables IOMMU passthrough permanently. This patch sets the dma_mask to be ENA_MAX_PHYS_ADDR_SIZE_BITS=48 before readless initialization in ena_device_init()->ena_com_mmio_reg_read_request_init(), which is large enough to workaround the intel_iommu issue. DMA mask is set again to the correct value after it's received from the device after readless is initialized. The patch also changes the driver to use dma_set_mask_and_coherent() function instead of the two pci_set_dma_mask() and pci_set_consistent_dma_mask() ones. Both methods achieve the same effect. Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)") Signed-off-by: Mike Cui Signed-off-by: Arthur Kiyanovski Signed-off-by: Shay Agroskin Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 574c2b5ba21e..ec0008ba7751 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -3367,16 +3367,9 @@ static int ena_device_init(struct ena_com_dev *ena_dev, struct pci_dev *pdev, goto err_mmio_read_less; } - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(dma_width)); + rc = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(dma_width)); if (rc) { - dev_err(dev, "pci_set_dma_mask failed 0x%x\n", rc); - goto err_mmio_read_less; - } - - rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(dma_width)); - if (rc) { - dev_err(dev, "err_pci_set_consistent_dma_mask failed 0x%x\n", - rc); + dev_err(dev, "dma_set_mask_and_coherent failed %d\n", rc); goto err_mmio_read_less; } @@ -4146,6 +4139,12 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return rc; } + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(ENA_MAX_PHYS_ADDR_SIZE_BITS)); + if (rc) { + dev_err(&pdev->dev, "dma_set_mask_and_coherent failed %d\n", rc); + goto err_disable_device; + } + pci_set_master(pdev); ena_dev = vzalloc(sizeof(*ena_dev)); -- cgit v1.2.3 From 1396d3148bd250db880573f9ed0abe5d6fba1fce Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Mon, 23 Nov 2020 21:08:59 +0200 Subject: net: ena: fix packet's addresses for rx_offset feature This patch fixes two lines in which the rx_offset received by the device wasn't taken into account: - prefetch function: In our driver the copied data would reside in rx_info->page + rx_headroom + rx_offset so the prefetch function is changed accordingly. - setting page_offset to zero for descriptors > 1: for every descriptor but the first, the rx_offset is zero. Hence the page_offset value should be set to rx_headroom. The previous implementation changed the value of rx_info after the descriptor was added to the SKB (essentially providing wrong page offset). Fixes: 68f236df93a9 ("net: ena: add support for the rx offset feature") Signed-off-by: Shay Agroskin Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index ec0008ba7751..df1884d57d1a 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -908,10 +908,14 @@ static void ena_free_all_io_rx_resources(struct ena_adapter *adapter) static int ena_alloc_rx_page(struct ena_ring *rx_ring, struct ena_rx_buffer *rx_info, gfp_t gfp) { + int headroom = rx_ring->rx_headroom; struct ena_com_buf *ena_buf; struct page *page; dma_addr_t dma; + /* restore page offset value in case it has been changed by device */ + rx_info->page_offset = headroom; + /* if previous allocated page is not used */ if (unlikely(rx_info->page)) return 0; @@ -941,10 +945,9 @@ static int ena_alloc_rx_page(struct ena_ring *rx_ring, "Allocate page %p, rx_info %p\n", page, rx_info); rx_info->page = page; - rx_info->page_offset = 0; ena_buf = &rx_info->ena_buf; - ena_buf->paddr = dma + rx_ring->rx_headroom; - ena_buf->len = ENA_PAGE_SIZE - rx_ring->rx_headroom; + ena_buf->paddr = dma + headroom; + ena_buf->len = ENA_PAGE_SIZE - headroom; return 0; } @@ -1356,7 +1359,8 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, /* save virt address of first buffer */ va = page_address(rx_info->page) + rx_info->page_offset; - prefetch(va + NET_IP_ALIGN); + + prefetch(va); if (len <= rx_ring->rx_copybreak) { skb = ena_alloc_skb(rx_ring, false); @@ -1397,8 +1401,6 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page, rx_info->page_offset, len, ENA_PAGE_SIZE); - /* The offset is non zero only for the first buffer */ - rx_info->page_offset = 0; netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "RX skb updated. len %d. data_len %d\n", @@ -1517,8 +1519,7 @@ static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp) int ret; rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]; - xdp->data = page_address(rx_info->page) + - rx_info->page_offset + rx_ring->rx_headroom; + xdp->data = page_address(rx_info->page) + rx_info->page_offset; xdp_set_data_meta_invalid(xdp); xdp->data_hard_start = page_address(rx_info->page); xdp->data_end = xdp->data + rx_ring->ena_bufs[0].len; @@ -1585,8 +1586,9 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, if (unlikely(ena_rx_ctx.descs == 0)) break; + /* First descriptor might have an offset set by the device */ rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]; - rx_info->page_offset = ena_rx_ctx.pkt_offset; + rx_info->page_offset += ena_rx_ctx.pkt_offset; netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "rx_poll: q %d got packet from ena. descs #: %d l3 proto %d l4 proto %d hash: %x\n", -- cgit v1.2.3 From a0faaa27c71608799e0dd765c5af38a089091802 Mon Sep 17 00:00:00 2001 From: Lijun Pan Date: Mon, 23 Nov 2020 13:35:45 -0600 Subject: ibmvnic: fix NULL pointer dereference in reset_sub_crq_queues adapter->tx_scrq and adapter->rx_scrq could be NULL if the previous reset did not complete after freeing sub crqs. Check for NULL before dereferencing them. Snippet of call trace: ibmvnic 30000006 env6: Releasing sub-CRQ ibmvnic 30000006 env6: Releasing CRQ ... ibmvnic 30000006 env6: Got Control IP offload Response ibmvnic 30000006 env6: Re-setting tx_scrq[0] BUG: Kernel NULL pointer dereference on read at 0x00000000 Faulting instruction address: 0xc008000003dea7cc Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: rpadlpar_io rpaphp xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 nft_compat nft_counter nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables xsk_diag tcp_diag udp_diag raw_diag inet_diag unix_diag af_packet_diag netlink_diag tun bridge stp llc rfkill sunrpc pseries_rng xts vmx_crypto uio_pdrv_genirq uio binfmt_misc ip_tables xfs libcrc32c sd_mod t10_pi sg ibmvscsi ibmvnic ibmveth scsi_transport_srp dm_mirror dm_region_hash dm_log dm_mod CPU: 80 PID: 1856 Comm: kworker/80:2 Tainted: G W 5.8.0+ #4 Workqueue: events __ibmvnic_reset [ibmvnic] NIP: c008000003dea7cc LR: c008000003dea7bc CTR: 0000000000000000 REGS: c0000007ef7db860 TRAP: 0380 Tainted: G W (5.8.0+) MSR: 800000000280b033 CR: 28002422 XER: 0000000d CFAR: c000000000bd9520 IRQMASK: 0 GPR00: c008000003dea7bc c0000007ef7dbaf0 c008000003df7400 c0000007fa26ec00 GPR04: c0000007fcd0d008 c0000007fcd96350 0000000000000027 c0000007fcd0d010 GPR08: 0000000000000023 0000000000000000 0000000000000000 0000000000000000 GPR12: 0000000000002000 c00000001ec18e00 c0000000001982f8 c0000007bad6e840 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000000000000 0000000000000000 0000000000000000 fffffffffffffef7 GPR24: 0000000000000402 c0000007fa26f3a8 0000000000000003 c00000016f8ec048 GPR28: 0000000000000000 0000000000000000 0000000000000000 c0000007fa26ec00 NIP [c008000003dea7cc] ibmvnic_reset_init+0x15c/0x258 [ibmvnic] LR [c008000003dea7bc] ibmvnic_reset_init+0x14c/0x258 [ibmvnic] Call Trace: [c0000007ef7dbaf0] [c008000003dea7bc] ibmvnic_reset_init+0x14c/0x258 [ibmvnic] (unreliable) [c0000007ef7dbb80] [c008000003de8860] __ibmvnic_reset+0x408/0x970 [ibmvnic] [c0000007ef7dbc50] [c00000000018b7cc] process_one_work+0x2cc/0x800 [c0000007ef7dbd20] [c00000000018bd78] worker_thread+0x78/0x520 [c0000007ef7dbdb0] [c0000000001984c4] kthread+0x1d4/0x1e0 [c0000007ef7dbe20] [c00000000000cea8] ret_from_kernel_thread+0x5c/0x74 Fixes: 57a49436f4e8 ("ibmvnic: Reset sub-crqs during driver reset") Signed-off-by: Lijun Pan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 2aa40b2f225c..db4a8e17477c 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2880,6 +2880,9 @@ static int reset_sub_crq_queues(struct ibmvnic_adapter *adapter) { int i, rc; + if (!adapter->tx_scrq || !adapter->rx_scrq) + return -EINVAL; + for (i = 0; i < adapter->req_tx_queues; i++) { netdev_dbg(adapter->netdev, "Re-setting tx_scrq[%d]\n", i); rc = reset_one_sub_crq_queue(adapter, adapter->tx_scrq[i]); -- cgit v1.2.3 From 0e435befaea45f7ea58682eecab5e37e05b2ce65 Mon Sep 17 00:00:00 2001 From: Lijun Pan Date: Mon, 23 Nov 2020 13:35:46 -0600 Subject: ibmvnic: fix NULL pointer dereference in ibmvic_reset_crq crq->msgs could be NULL if the previous reset did not complete after freeing crq->msgs. Check for NULL before dereferencing them. Snippet of call trace: ... ibmvnic 30000003 env3 (unregistering): Releasing sub-CRQ ibmvnic 30000003 env3 (unregistering): Releasing CRQ BUG: Kernel NULL pointer dereference on read at 0x00000000 Faulting instruction address: 0xc0000000000c1a30 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: ibmvnic(E-) rpadlpar_io rpaphp xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 nft_compat nft_counter nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables xsk_diag tcp_diag udp_diag tun raw_diag inet_diag unix_diag bridge af_packet_diag netlink_diag stp llc rfkill sunrpc pseries_rng xts vmx_crypto uio_pdrv_genirq uio binfmt_misc ip_tables xfs libcrc32c sd_mod t10_pi sg ibmvscsi ibmveth scsi_transport_srp dm_mirror dm_region_hash dm_log dm_mod [last unloaded: ibmvnic] CPU: 20 PID: 8426 Comm: kworker/20:0 Tainted: G E 5.10.0-rc1+ #12 Workqueue: events __ibmvnic_reset [ibmvnic] NIP: c0000000000c1a30 LR: c008000001b00c18 CTR: 0000000000000400 REGS: c00000000d05b7a0 TRAP: 0380 Tainted: G E (5.10.0-rc1+) MSR: 800000000280b033 CR: 44002480 XER: 20040000 CFAR: c0000000000c19ec IRQMASK: 0 GPR00: 0000000000000400 c00000000d05ba30 c008000001b17c00 0000000000000000 GPR04: 0000000000000000 0000000000000000 0000000000000000 00000000000001e2 GPR08: 000000000001f400 ffffffffffffd950 0000000000000000 c008000001b0b280 GPR12: c0000000000c19c8 c00000001ec72e00 c00000000019a778 c00000002647b440 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000000000006 0000000000000001 0000000000000003 0000000000000002 GPR24: 0000000000001000 c008000001b0d570 0000000000000005 c00000007ab5d550 GPR28: c00000007ab5c000 c000000032fcf848 c00000007ab5cc00 c000000032fcf800 NIP [c0000000000c1a30] memset+0x68/0x104 LR [c008000001b00c18] ibmvnic_reset_crq+0x70/0x110 [ibmvnic] Call Trace: [c00000000d05ba30] [0000000000000800] 0x800 (unreliable) [c00000000d05bab0] [c008000001b0a930] do_reset.isra.40+0x224/0x634 [ibmvnic] [c00000000d05bb80] [c008000001b08574] __ibmvnic_reset+0x17c/0x3c0 [ibmvnic] [c00000000d05bc50] [c00000000018d9ac] process_one_work+0x2cc/0x800 [c00000000d05bd20] [c00000000018df58] worker_thread+0x78/0x520 [c00000000d05bdb0] [c00000000019a934] kthread+0x1c4/0x1d0 [c00000000d05be20] [c00000000000d5d0] ret_from_kernel_thread+0x5c/0x6c Fixes: 032c5e82847a ("Driver for IBM System i/p VNIC protocol") Signed-off-by: Lijun Pan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index db4a8e17477c..26ba07df404e 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -4973,6 +4973,9 @@ static int ibmvnic_reset_crq(struct ibmvnic_adapter *adapter) } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); /* Clean out the queue */ + if (!crq->msgs) + return -EINVAL; + memset(crq->msgs, 0, PAGE_SIZE); crq->cur = 0; crq->active = false; -- cgit v1.2.3 From 3ada288150fb17ab3fcce2cf5fce20461f86b2ee Mon Sep 17 00:00:00 2001 From: Lijun Pan Date: Mon, 23 Nov 2020 13:35:47 -0600 Subject: ibmvnic: enhance resetting status check during module exit Based on the discussion with Sukadev Bhattiprolu and Dany Madden, we believe that checking adapter->resetting bit is preferred since RESETTING state flag is not as strict as resetting bit. RESETTING state flag is removed since it is verbose now. Fixes: 7d7195a026ba ("ibmvnic: Do not process device remove during device reset") Signed-off-by: Lijun Pan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 3 +-- drivers/net/ethernet/ibm/ibmvnic.h | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 26ba07df404e..2491ebc97871 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2215,7 +2215,6 @@ static void __ibmvnic_reset(struct work_struct *work) if (!saved_state) { reset_state = adapter->state; - adapter->state = VNIC_RESETTING; saved_state = true; } spin_unlock_irqrestore(&adapter->state_lock, flags); @@ -5280,7 +5279,7 @@ static int ibmvnic_remove(struct vio_dev *dev) unsigned long flags; spin_lock_irqsave(&adapter->state_lock, flags); - if (adapter->state == VNIC_RESETTING) { + if (test_bit(0, &adapter->resetting)) { spin_unlock_irqrestore(&adapter->state_lock, flags); return -EBUSY; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 217dcc7ded70..47a3fd71c96f 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -942,8 +942,7 @@ enum vnic_state {VNIC_PROBING = 1, VNIC_CLOSING, VNIC_CLOSED, VNIC_REMOVING, - VNIC_REMOVED, - VNIC_RESETTING}; + VNIC_REMOVED}; enum ibmvnic_reset_reason {VNIC_RESET_FAILOVER = 1, VNIC_RESET_MOBILITY, -- cgit v1.2.3 From fa248db082270200863d254e0f39bbb29923d6b1 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 24 Nov 2020 17:42:57 -0800 Subject: Input: soc_button_array - add missing include This fixes the following build errors: CC [M] drivers/input/misc/soc_button_array.o drivers/input/misc/soc_button_array.c:156:4: error: implicit declaration of function 'irq_set_irq_type' [-Werror,-Wimplicit-function-declaration] irq_set_irq_type(irq, IRQ_TYPE_LEVEL_LOW); ^ drivers/input/misc/soc_button_array.c:156:26: error: use of undeclared identifier 'IRQ_TYPE_LEVEL_LOW' irq_set_irq_type(irq, IRQ_TYPE_LEVEL_LOW); ^ 2 errors generated. Fixes: 78a5b53e9fb4 ("Input: soc_button_array - work around DSDTs which modify the irqflags") Reported-by: kernel test robot Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20201123061508.GA1009828@dtor-ws Signed-off-by: Dmitry Torokhov --- drivers/input/misc/soc_button_array.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index cae1a3fae83a..d14a65683c5e 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 855b69857830f8d918d715014f05e59a3f7491a0 Mon Sep 17 00:00:00 2001 From: Luo Meng Date: Tue, 24 Nov 2020 17:45:23 -0800 Subject: Input: i8042 - fix error return code in i8042_setup_aux() Fix to return a negative error code from the error handling case instead of 0 in function i8042_setup_aux(), as done elsewhere in this function. Fixes: f81134163fc7 ("Input: i8042 - use platform_driver_probe") Reported-by: Hulk Robot Signed-off-by: Luo Meng Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20201123133420.4071187-1-luomeng12@huawei.com Signed-off-by: Dmitry Torokhov --- drivers/input/serio/i8042.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index 944cbb519c6d..abae23af0791 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -1471,7 +1471,8 @@ static int __init i8042_setup_aux(void) if (error) goto err_free_ports; - if (aux_enable()) + error = aux_enable(); + if (error) goto err_free_irq; i8042_aux_irq_registered = true; -- cgit v1.2.3 From 6f7a1f9c1af30f1eadc0ad9e77ec8ee95c48b2c9 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 24 Nov 2020 20:15:24 -0800 Subject: Documentation: netdev-FAQ: suggest how to post co-dependent series Make an explicit suggestion how to post user space side of kernel patches to avoid reposts when patchwork groups the wrong patches. v2: mention the cases unlike iproute2 explicitly Signed-off-by: Jakub Kicinski Reviewed-by: Florian Fainelli Reviewed-by: David Ahern Signed-off-by: David S. Miller --- Documentation/networking/netdev-FAQ.rst | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst index 21537766be4d..4b9ed5874d5a 100644 --- a/Documentation/networking/netdev-FAQ.rst +++ b/Documentation/networking/netdev-FAQ.rst @@ -254,6 +254,32 @@ you will have done run-time testing specific to your change, but at a minimum, your changes should survive an ``allyesconfig`` and an ``allmodconfig`` build without new warnings or failures. +Q: How do I post corresponding changes to user space components? +---------------------------------------------------------------- +A: User space code exercising kernel features should be posted +alongside kernel patches. This gives reviewers a chance to see +how any new interface is used and how well it works. + +When user space tools reside in the kernel repo itself all changes +should generally come as one series. If series becomes too large +or the user space project is not reviewed on netdev include a link +to a public repo where user space patches can be seen. + +In case user space tooling lives in a separate repository but is +reviewed on netdev (e.g. patches to `iproute2` tools) kernel and +user space patches should form separate series (threads) when posted +to the mailing list, e.g.:: + + [PATCH net-next 0/3] net: some feature cover letter + └─ [PATCH net-next 1/3] net: some feature prep + └─ [PATCH net-next 2/3] net: some feature do it + └─ [PATCH net-next 3/3] selftest: net: some feature + + [PATCH iproute2-next] ip: add support for some feature + +Posting as one thread is discouraged because it confuses patchwork +(as of patchwork 2.2.2). + Q: Any other tips to help ensure my net/net-next patch gets OK'd? ----------------------------------------------------------------- A: Attention to detail. Re-read your own work as if you were the -- cgit v1.2.3 From 030c5b52d4c1225030891d25abfe376b6e239712 Mon Sep 17 00:00:00 2001 From: xinhui pan Date: Fri, 23 Oct 2020 13:41:12 +0800 Subject: drm/amdgpu: Fix size calculation when init onchip memory MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Size is page count here. Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/1372 Reviewed-by: Christian König Signed-off-by: xinhui pan Signed-off-by: Alex Deucher (cherry picked from commit d836917da7e5ca9b33ef4d499972f1feeb519e00) [airlied: from drm-next] Signed-off-by: Dave Airlie --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 8039d2399584..a0248d78190f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -69,10 +69,10 @@ static int amdgpu_ttm_backend_bind(struct ttm_bo_device *bdev, static int amdgpu_ttm_init_on_chip(struct amdgpu_device *adev, unsigned int type, - uint64_t size) + uint64_t size_in_page) { return ttm_range_man_init(&adev->mman.bdev, type, - false, size >> PAGE_SHIFT); + false, size_in_page); } /** -- cgit v1.2.3 From 10e26e749fd0ba78a913548e2efeca1a157772da Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 22 Sep 2020 16:46:55 +0200 Subject: drm/ast: Reload gamma LUT after changing primary plane's color format The gamma LUT has to be reloaded after changing the primary plane's color format. This used to be done implicitly by the CRTC atomic_enable() helper after updating the primary plane. With the recent reordering of the steps, the primary plane's setup was moved last and invalidated the gamma LUT. Fix this by setting the LUT from within atomic_flush(). Signed-off-by: Thomas Zimmermann Reviewed-by: Daniel Vetter Fixes: 2f0ddd89fe32 ("drm/ast: Enable CRTC before planes") Cc: Thomas Zimmermann Cc: Daniel Vetter Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Link: https://patchwork.freedesktop.org/patch/msgid/20200922144655.23624-1-tzimmermann@suse.de (cherry-picked from 8e3784dfef8a03143b13e7e4011f276a954f1bc6) --- drivers/gpu/drm/ast/ast_mode.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 834a156e3a75..0a1e1cf57e19 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -742,7 +742,6 @@ static void ast_crtc_dpms(struct drm_crtc *crtc, int mode) case DRM_MODE_DPMS_SUSPEND: if (ast->tx_chip_type == AST_TX_DP501) ast_set_dp501_video_output(crtc->dev, 1); - ast_crtc_load_lut(ast, crtc); break; case DRM_MODE_DPMS_OFF: if (ast->tx_chip_type == AST_TX_DP501) @@ -777,6 +776,21 @@ static int ast_crtc_helper_atomic_check(struct drm_crtc *crtc, return 0; } +static void +ast_crtc_helper_atomic_flush(struct drm_crtc *crtc, struct drm_crtc_state *old_crtc_state) +{ + struct ast_private *ast = to_ast_private(crtc->dev); + struct ast_crtc_state *ast_crtc_state = to_ast_crtc_state(crtc->state); + struct ast_crtc_state *old_ast_crtc_state = to_ast_crtc_state(old_crtc_state); + + /* + * The gamma LUT has to be reloaded after changing the primary + * plane's color format. + */ + if (old_ast_crtc_state->format != ast_crtc_state->format) + ast_crtc_load_lut(ast, crtc); +} + static void ast_crtc_helper_atomic_enable(struct drm_crtc *crtc, struct drm_crtc_state *old_crtc_state) @@ -830,6 +844,7 @@ ast_crtc_helper_atomic_disable(struct drm_crtc *crtc, static const struct drm_crtc_helper_funcs ast_crtc_helper_funcs = { .atomic_check = ast_crtc_helper_atomic_check, + .atomic_flush = ast_crtc_helper_atomic_flush, .atomic_enable = ast_crtc_helper_atomic_enable, .atomic_disable = ast_crtc_helper_atomic_disable, }; -- cgit v1.2.3 From b4fffc177fad3c99ee049611a508ca9561bb6871 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 20 Nov 2020 09:50:59 -0600 Subject: vhost scsi: fix lun reset completion handling vhost scsi owns the scsi se_cmd but lio frees the se_cmd->se_tmr before calling release_cmd, so while with normal cmd completion we can access the se_cmd from the vhost work, we can't do the same with se_cmd->se_tmr. This has us copy the tmf response in vhost_scsi_queue_tm_rsp to our internal vhost-scsi tmf struct for when it gets sent to the guest from our worker thread. Fixes: efd838fec17b ("vhost scsi: Add support for LUN resets.") Signed-off-by: Mike Christie Acked-by: Stefan Hajnoczi Link: https://lore.kernel.org/r/1605887459-3864-1-git-send-email-michael.christie@oracle.com Signed-off-by: Michael S. Tsirkin --- drivers/vhost/scsi.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index f22fce549862..6ff8a5096691 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -220,6 +220,7 @@ struct vhost_scsi_tmf { struct list_head queue_entry; struct se_cmd se_cmd; + u8 scsi_resp; struct vhost_scsi_inflight *inflight; struct iovec resp_iov; int in_iovs; @@ -426,6 +427,7 @@ static void vhost_scsi_queue_tm_rsp(struct se_cmd *se_cmd) struct vhost_scsi_tmf *tmf = container_of(se_cmd, struct vhost_scsi_tmf, se_cmd); + tmf->scsi_resp = se_cmd->se_tmr_req->response; transport_generic_free_cmd(&tmf->se_cmd, 0); } @@ -1183,7 +1185,7 @@ static void vhost_scsi_tmf_resp_work(struct vhost_work *work) vwork); int resp_code; - if (tmf->se_cmd.se_tmr_req->response == TMR_FUNCTION_COMPLETE) + if (tmf->scsi_resp == TMR_FUNCTION_COMPLETE) resp_code = VIRTIO_SCSI_S_FUNCTION_SUCCEEDED; else resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED; -- cgit v1.2.3 From 8009b0f4ab3151f3b8c1675ceb0f9151f09dddaa Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Mon, 16 Nov 2020 17:16:53 +0100 Subject: vringh: fix vringh_iov_push_*() documentation vringh_iov_push_*() functions don't have 'dst' parameter, but have the 'src' parameter. Replace 'dst' description with 'src' description. Signed-off-by: Stefano Garzarella Link: https://lore.kernel.org/r/20201116161653.102904-1-sgarzare@redhat.com Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vringh.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 8bd8b403f087..b7403ba8e7f7 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -730,7 +730,7 @@ EXPORT_SYMBOL(vringh_iov_pull_user); /** * vringh_iov_push_user - copy bytes into vring_iov. * @wiov: the wiov as passed to vringh_getdesc_user() (updated as we consume) - * @dst: the place to copy. + * @src: the place to copy from. * @len: the maximum length to copy. * * Returns the bytes copied <= len or a negative errno. @@ -976,7 +976,7 @@ EXPORT_SYMBOL(vringh_iov_pull_kern); /** * vringh_iov_push_kern - copy bytes into vring_iov. * @wiov: the wiov as passed to vringh_getdesc_kern() (updated as we consume) - * @dst: the place to copy. + * @src: the place to copy from. * @len: the maximum length to copy. * * Returns the bytes copied <= len or a negative errno. @@ -1333,7 +1333,7 @@ EXPORT_SYMBOL(vringh_iov_pull_iotlb); * vringh_iov_push_iotlb - copy bytes into vring_iov. * @vrh: the vring. * @wiov: the wiov as passed to vringh_getdesc_iotlb() (updated as we consume) - * @dst: the place to copy. + * @src: the place to copy from. * @len: the maximum length to copy. * * Returns the bytes copied <= len or a negative errno. -- cgit v1.2.3 From ad89653f79f1882d55d9df76c9b2b94f008c4e27 Mon Sep 17 00:00:00 2001 From: Si-Wei Liu Date: Thu, 5 Nov 2020 18:26:33 -0500 Subject: vhost-vdpa: fix page pinning leakage in error path (rework) Pinned pages are not properly accounted particularly when mapping error occurs on IOTLB update. Clean up dangling pinned pages for the error path. The memory usage for bookkeeping pinned pages is reverted to what it was before: only one single free page is needed. This helps reduce the host memory demand for VM with a large amount of memory, or in the situation where host is running short of free memory. Fixes: 4c8cf31885f6 ("vhost: introduce vDPA-based backend") Signed-off-by: Si-Wei Liu Link: https://lore.kernel.org/r/1604618793-4681-1-git-send-email-si-wei.liu@oracle.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vhost/vdpa.c | 80 ++++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 62 insertions(+), 18 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 2754f3069738..f2db99031e2f 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -577,6 +577,8 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, if (r) vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1); + else + atomic64_add(size >> PAGE_SHIFT, &dev->mm->pinned_vm); return r; } @@ -608,8 +610,9 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, unsigned long list_size = PAGE_SIZE / sizeof(struct page *); unsigned int gup_flags = FOLL_LONGTERM; unsigned long npages, cur_base, map_pfn, last_pfn = 0; - unsigned long locked, lock_limit, pinned, i; + unsigned long lock_limit, sz2pin, nchunks, i; u64 iova = msg->iova; + long pinned; int ret = 0; if (msg->iova < v->range.first || @@ -620,6 +623,7 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, msg->iova + msg->size - 1)) return -EEXIST; + /* Limit the use of memory for bookkeeping */ page_list = (struct page **) __get_free_page(GFP_KERNEL); if (!page_list) return -ENOMEM; @@ -628,52 +632,75 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, gup_flags |= FOLL_WRITE; npages = PAGE_ALIGN(msg->size + (iova & ~PAGE_MASK)) >> PAGE_SHIFT; - if (!npages) - return -EINVAL; + if (!npages) { + ret = -EINVAL; + goto free; + } mmap_read_lock(dev->mm); - locked = atomic64_add_return(npages, &dev->mm->pinned_vm); lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - - if (locked > lock_limit) { + if (npages + atomic64_read(&dev->mm->pinned_vm) > lock_limit) { ret = -ENOMEM; - goto out; + goto unlock; } cur_base = msg->uaddr & PAGE_MASK; iova &= PAGE_MASK; + nchunks = 0; while (npages) { - pinned = min_t(unsigned long, npages, list_size); - ret = pin_user_pages(cur_base, pinned, - gup_flags, page_list, NULL); - if (ret != pinned) + sz2pin = min_t(unsigned long, npages, list_size); + pinned = pin_user_pages(cur_base, sz2pin, + gup_flags, page_list, NULL); + if (sz2pin != pinned) { + if (pinned < 0) { + ret = pinned; + } else { + unpin_user_pages(page_list, pinned); + ret = -ENOMEM; + } goto out; + } + nchunks++; if (!last_pfn) map_pfn = page_to_pfn(page_list[0]); - for (i = 0; i < ret; i++) { + for (i = 0; i < pinned; i++) { unsigned long this_pfn = page_to_pfn(page_list[i]); u64 csize; if (last_pfn && (this_pfn != last_pfn + 1)) { /* Pin a contiguous chunk of memory */ csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT; - if (vhost_vdpa_map(v, iova, csize, - map_pfn << PAGE_SHIFT, - msg->perm)) + ret = vhost_vdpa_map(v, iova, csize, + map_pfn << PAGE_SHIFT, + msg->perm); + if (ret) { + /* + * Unpin the pages that are left unmapped + * from this point on in the current + * page_list. The remaining outstanding + * ones which may stride across several + * chunks will be covered in the common + * error path subsequently. + */ + unpin_user_pages(&page_list[i], + pinned - i); goto out; + } + map_pfn = this_pfn; iova += csize; + nchunks = 0; } last_pfn = this_pfn; } - cur_base += ret << PAGE_SHIFT; - npages -= ret; + cur_base += pinned << PAGE_SHIFT; + npages -= pinned; } /* Pin the rest chunk */ @@ -681,10 +708,27 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, map_pfn << PAGE_SHIFT, msg->perm); out: if (ret) { + if (nchunks) { + unsigned long pfn; + + /* + * Unpin the outstanding pages which are yet to be + * mapped but haven't due to vdpa_map() or + * pin_user_pages() failure. + * + * Mapped pages are accounted in vdpa_map(), hence + * the corresponding unpinning will be handled by + * vdpa_unmap(). + */ + WARN_ON(!last_pfn); + for (pfn = map_pfn; pfn <= last_pfn; pfn++) + unpin_user_page(pfn_to_page(pfn)); + } vhost_vdpa_unmap(v, msg->iova, msg->size); - atomic64_sub(npages, &dev->mm->pinned_vm); } +unlock: mmap_read_unlock(dev->mm); +free: free_page((unsigned long)page_list); return ret; } -- cgit v1.2.3 From 853735e404244f5496cdb6188c5ed9a0f9627ee6 Mon Sep 17 00:00:00 2001 From: Rui Miguel Silva Date: Fri, 13 Nov 2020 15:06:04 +0000 Subject: optee: add writeback to valid memory type Only in smp systems the cache policy is setup as write alloc, in single cpu systems the cache policy is set as writeback and it is normal memory, so, it should pass the is_normal_memory check in the share memory registration. Add the right condition to make it work in no smp systems. Fixes: cdbcf83d29c1 ("tee: optee: check type of registered shared memory") Signed-off-by: Rui Miguel Silva Signed-off-by: Jens Wiklander --- drivers/tee/optee/call.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c index 20b6fd7383c5..c981757ba0d4 100644 --- a/drivers/tee/optee/call.c +++ b/drivers/tee/optee/call.c @@ -534,7 +534,8 @@ void optee_free_pages_list(void *list, size_t num_entries) static bool is_normal_memory(pgprot_t p) { #if defined(CONFIG_ARM) - return (pgprot_val(p) & L_PTE_MT_MASK) == L_PTE_MT_WRITEALLOC; + return (((pgprot_val(p) & L_PTE_MT_MASK) == L_PTE_MT_WRITEALLOC) || + ((pgprot_val(p) & L_PTE_MT_MASK) == L_PTE_MT_WRITEBACK)); #elif defined(CONFIG_ARM64) return (pgprot_val(p) & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL); #else -- cgit v1.2.3 From fdeb17c70c9ecae655378761accf5a26a55a33cf Mon Sep 17 00:00:00 2001 From: Hui Su Date: Wed, 25 Nov 2020 00:52:05 +0800 Subject: trace: fix potenial dangerous pointer The bdi_dev_name() returns a char [64], and the __entry->name is a char [32]. It maybe dangerous to TP_printk("%s", __entry->name) after the strncpy(). CC: stable@vger.kernel.org Link: https://lore.kernel.org/r/20201124165205.GA23937@rlk Acked-by: Steven Rostedt (VMware) Acked-by: Tejun Heo Signed-off-by: Hui Su Signed-off-by: Jan Kara --- include/trace/events/writeback.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index e7cbccc7c14c..57d795365987 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -190,7 +190,7 @@ TRACE_EVENT(inode_foreign_history, ), TP_fast_assign( - strncpy(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); + strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); __entry->history = history; @@ -219,7 +219,7 @@ TRACE_EVENT(inode_switch_wbs, ), TP_fast_assign( - strncpy(__entry->name, bdi_dev_name(old_wb->bdi), 32); + strscpy_pad(__entry->name, bdi_dev_name(old_wb->bdi), 32); __entry->ino = inode->i_ino; __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb); __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb); @@ -252,7 +252,7 @@ TRACE_EVENT(track_foreign_dirty, struct address_space *mapping = page_mapping(page); struct inode *inode = mapping ? mapping->host : NULL; - strncpy(__entry->name, bdi_dev_name(wb->bdi), 32); + strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->bdi_id = wb->bdi->id; __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; @@ -285,7 +285,7 @@ TRACE_EVENT(flush_foreign, ), TP_fast_assign( - strncpy(__entry->name, bdi_dev_name(wb->bdi), 32); + strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->frn_bdi_id = frn_bdi_id; __entry->frn_memcg_id = frn_memcg_id; -- cgit v1.2.3 From e2be2a833ab5338fa5b8b99ba622b911d96f1795 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 25 Nov 2020 09:41:24 +0800 Subject: x86/tboot: Don't disable swiotlb when iommu is forced on After commit 327d5b2fee91c ("iommu/vt-d: Allow 32bit devices to uses DMA domain"), swiotlb could also be used for direct memory access if IOMMU is enabled but a device is configured to pass through the DMA translation. Keep swiotlb when IOMMU is forced on, otherwise, some devices won't work if "iommu=pt" kernel parameter is used. Fixes: 327d5b2fee91 ("iommu/vt-d: Allow 32bit devices to uses DMA domain") Reported-and-tested-by: Adrian Huang Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20201125014124.4070776-1-baolu.lu@linux.intel.com Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=210237 Signed-off-by: Will Deacon --- arch/x86/kernel/tboot.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 420be871d9d4..ae64f98ec2ab 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -514,13 +514,10 @@ int tboot_force_iommu(void) if (!tboot_enabled()) return 0; - if (no_iommu || swiotlb || dmar_disabled) + if (no_iommu || dmar_disabled) pr_warn("Forcing Intel-IOMMU to enabled\n"); dmar_disabled = 0; -#ifdef CONFIG_SWIOTLB - swiotlb = 0; -#endif no_iommu = 0; return 1; -- cgit v1.2.3 From 3fba05a2832f93b4d0cd4204f771fdae0d823114 Mon Sep 17 00:00:00 2001 From: Luo Meng Date: Mon, 23 Nov 2020 21:38:39 +0800 Subject: ASoC: wm_adsp: fix error return code in wm_adsp_load() Fix to return a negative error code from the error handling case instead of 0 in function wm_adsp_load(), as done elsewhere in this function. Fixes: 170b1e123f38 ("ASoC: wm_adsp: Add support for new Halo core DSPs") Reported-by: Hulk Robot Signed-off-by: Luo Meng Acked-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20201123133839.4073787-1-luomeng12@huawei.com Signed-off-by: Mark Brown --- sound/soc/codecs/wm_adsp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index bcf18bf15a02..e61d00486c65 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -1937,6 +1937,7 @@ static int wm_adsp_load(struct wm_adsp *dsp) mem = wm_adsp_find_region(dsp, type); if (!mem) { adsp_err(dsp, "No region of type: %x\n", type); + ret = -EINVAL; goto out_fw; } -- cgit v1.2.3 From 0abdb0fba07322ce960d32a92a64847b3009b2e2 Mon Sep 17 00:00:00 2001 From: Lars Povlsen Date: Fri, 20 Nov 2020 22:34:14 +0100 Subject: spi: dw: Fix spi registration for controllers overriding CS When SPI DW memory ops support was introduced, there was a check for excluding controllers which supplied their own CS function. Even so, the mem_ops pointer is *always* presented to the SPI core. This causes the SPI core sanity check in spi_controller_check_ops() to refuse registration, since a mem_ops pointer is being supplied without an exec_op member function. The end result is failure of the SPI DW driver on sparx5 and similar platforms. The fix in the core SPI DW driver is to avoid presenting the mem_ops pointer if the exec_op function is not set. Fixes: 6423207e57ea (spi: dw: Add memory operations support) Signed-off-by: Lars Povlsen Acked-by: Serge Semin Link: https://lore.kernel.org/r/20201120213414.339701-1-lars.povlsen@microchip.com Signed-off-by: Mark Brown --- drivers/spi/spi-dw-core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-dw-core.c b/drivers/spi/spi-dw-core.c index 0b2236ade412..c33866f747db 100644 --- a/drivers/spi/spi-dw-core.c +++ b/drivers/spi/spi-dw-core.c @@ -875,7 +875,8 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws) master->set_cs = dw_spi_set_cs; master->transfer_one = dw_spi_transfer_one; master->handle_err = dw_spi_handle_err; - master->mem_ops = &dws->mem_ops; + if (dws->mem_ops.exec_op) + master->mem_ops = &dws->mem_ops; master->max_speed_hz = dws->max_freq; master->dev.of_node = dev->of_node; master->dev.fwnode = dev->fwnode; -- cgit v1.2.3 From fb319496935b7475a863a00c76895e8bb3216704 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Mon, 16 Nov 2020 16:20:26 +0000 Subject: arm64: tegra: Disable the ACONNECT for Jetson TX2 Commit ff4c371d2bc0 ("arm64: defconfig: Build ADMA and ACONNECT driver") enable the Tegra ADMA and ACONNECT drivers and this is causing resume from system suspend to fail on Jetson TX2. Resume is failing because the ACONNECT driver is being resumed before the BPMP driver, and the ACONNECT driver is attempting to power on a power-domain that is provided by the BPMP. While a proper fix for the resume sequencing problem is identified, disable the ACONNECT for Jetson TX2 temporarily to avoid breaking system suspend. Please note that ACONNECT driver is used by the Audio Processing Engine (APE) on Tegra, but because there is no mainline support for APE on Jetson TX2 currently, disabling the ACONNECT does not disable any useful feature at the moment. Signed-off-by: Jon Hunter Signed-off-by: Thierry Reding --- arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts b/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts index 381a84912ba8..c28d51cc5797 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts @@ -10,18 +10,6 @@ model = "NVIDIA Jetson TX2 Developer Kit"; compatible = "nvidia,p2771-0000", "nvidia,tegra186"; - aconnect { - status = "okay"; - - dma-controller@2930000 { - status = "okay"; - }; - - interrupt-controller@2a40000 { - status = "okay"; - }; - }; - i2c@3160000 { power-monitor@42 { compatible = "ti,ina3221"; -- cgit v1.2.3 From 476e23f4c540949ac5ea4fad4f6f6fa0e2d41f42 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Wed, 11 Nov 2020 10:41:17 +0000 Subject: arm64: tegra: Correct the UART for Jetson Xavier NX The Jetson Xavier NX board routes UARTA to the 40-pin header and UARTC to a 12-pin debug header. The UARTs can be used by either the Tegra Combined UART (TCU) driver or the Tegra 8250 driver. By default, the TCU will use UARTC on Jetson Xavier NX. Currently, device-tree for Xavier NX enables the TCU and the Tegra 8250 node for UARTC. Fix this by disabling the Tegra 8250 node for UARTC and enabling the Tegra 8250 node for UARTA. Fixes: 3f9efbbe57bc ("arm64: tegra: Add support for Jetson Xavier NX") Cc: stable@vger.kernel.org Signed-off-by: Jon Hunter Signed-off-by: Thierry Reding --- arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi index a2893be80507..0dc8304a2edd 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi @@ -54,7 +54,7 @@ status = "okay"; }; - serial@c280000 { + serial@3100000 { status = "okay"; }; -- cgit v1.2.3 From f24a2acc15bcc7bbd295f9759efc873b88fbe429 Mon Sep 17 00:00:00 2001 From: JC Kuo Date: Thu, 19 Nov 2020 15:23:45 +0800 Subject: arm64: tegra: Fix USB_VBUS_EN0 regulator on Jetson TX1 USB host mode is broken on the OTG port of Jetson TX1 platform because the USB_VBUS_EN0 regulator (regulator@11) is being overwritten by the vdd-cam-1v2 regulator. This commit rearranges USB_VBUS_EN0 to be regulator@14. Fixes: 257c8047be44 ("arm64: tegra: jetson-tx1: Add camera supplies") Cc: stable@vger.kernel.org Signed-off-by: JC Kuo Reviewed-by: Jon Hunter Signed-off-by: Thierry Reding --- arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi index e18e1a9a3011..a9caaf7c0d67 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi @@ -1663,16 +1663,6 @@ vin-supply = <&vdd_5v0_sys>; }; - vdd_usb_vbus_otg: regulator@11 { - compatible = "regulator-fixed"; - regulator-name = "USB_VBUS_EN0"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - gpio = <&gpio TEGRA_GPIO(CC, 4) GPIO_ACTIVE_HIGH>; - enable-active-high; - vin-supply = <&vdd_5v0_sys>; - }; - vdd_hdmi: regulator@10 { compatible = "regulator-fixed"; regulator-name = "VDD_HDMI_5V0"; @@ -1712,4 +1702,14 @@ enable-active-high; vin-supply = <&vdd_3v3_sys>; }; + + vdd_usb_vbus_otg: regulator@14 { + compatible = "regulator-fixed"; + regulator-name = "USB_VBUS_EN0"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + gpio = <&gpio TEGRA_GPIO(CC, 4) GPIO_ACTIVE_HIGH>; + enable-active-high; + vin-supply = <&vdd_5v0_sys>; + }; }; -- cgit v1.2.3 From 1741e18737948c140ccc4cc643e8126d95ee6e79 Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Fri, 11 Sep 2020 19:26:45 -0700 Subject: arm64: tegra: Wrong AON HSP reg property size The AON HSP node's "reg" property size 0xa0000 will overlap with other resources. This patch fixes that wrong value with correct size 0x90000. Reviewed-by: Mikko Perttunen Signed-off-by: Dipen Patel Fixes: a38570c22e9d ("arm64: tegra: Add nodes for TCU on Tegra194") Signed-off-by: Thierry Reding --- arch/arm64/boot/dts/nvidia/tegra194.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index e9c90f0f44ff..93438d2b9469 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -1161,7 +1161,7 @@ hsp_aon: hsp@c150000 { compatible = "nvidia,tegra194-hsp", "nvidia,tegra186-hsp"; - reg = <0x0c150000 0xa0000>; + reg = <0x0c150000 0x90000>; interrupts = , , , -- cgit v1.2.3 From d98bccf10dd0f36cabee71a425381fce0908de3b Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Wed, 18 Nov 2020 16:04:58 +0000 Subject: arm64: tegra: Fix Tegra234 VDK node names When the device-tree board file was added for the Tegra234 VDK simulator it incorrectly used the names 'cbb' and 'sdhci' instead of 'bus' and 'mmc', respectively. The names 'bus' and 'mmc' are required by the device-tree json-schema validation tools. Therefore, fix this by renaming these nodes accordingly. Fixes: 639448912ba1 ("arm64: tegra: Initial Tegra234 VDK support") Reported-by: Ashish Singhal Signed-off-by: Jon Hunter Signed-off-by: Thierry Reding --- arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts b/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts index f6e6a24829af..b5d9a5526272 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts +++ b/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts @@ -8,7 +8,7 @@ compatible = "nvidia,tegra234-vdk", "nvidia,tegra234"; aliases { - sdhci3 = "/cbb@0/sdhci@3460000"; + mmc3 = "/bus@0/mmc@3460000"; serial0 = &uarta; }; @@ -17,12 +17,12 @@ stdout-path = "serial0:115200n8"; }; - cbb@0 { + bus@0 { serial@3100000 { status = "okay"; }; - sdhci@3460000 { + mmc@3460000 { status = "okay"; bus-width = <8>; non-removable; -- cgit v1.2.3 From 2ed381439e89fa6d1a0839ef45ccd45d99d8e915 Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Tue, 24 Nov 2020 18:56:16 -0600 Subject: RDMA/i40iw: Address an mmap handler exploit in i40iw i40iw_mmap manipulates the vma->vm_pgoff to differentiate a push page mmap vs a doorbell mmap, and uses it to compute the pfn in remap_pfn_range without any validation. This is vulnerable to an mmap exploit as described in: https://lore.kernel.org/r/20201119093523.7588-1-zhudi21@huawei.com The push feature is disabled in the driver currently and therefore no push mmaps are issued from user-space. The feature does not work as expected in the x722 product. Remove the push module parameter and all VMA attribute manipulations for this feature in i40iw_mmap. Update i40iw_mmap to only allow DB user mmapings at offset = 0. Check vm_pgoff for zero and if the mmaps are bound to a single page. Cc: Fixes: d37498417947 ("i40iw: add files for iwarp interface") Link: https://lore.kernel.org/r/20201125005616.1800-2-shiraz.saleem@intel.com Reported-by: Di Zhu Signed-off-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/i40iw/i40iw_main.c | 5 ----- drivers/infiniband/hw/i40iw/i40iw_verbs.c | 37 ++++++------------------------- 2 files changed, 7 insertions(+), 35 deletions(-) diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index 2408b279e4c2..584932d3cc44 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -54,10 +54,6 @@ #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." __stringify(DRV_VERSION_BUILD) -static int push_mode; -module_param(push_mode, int, 0644); -MODULE_PARM_DESC(push_mode, "Low latency mode: 0=disabled (default), 1=enabled)"); - static int debug; module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "debug flags: 0=disabled (default), 0x7fffffff=all"); @@ -1580,7 +1576,6 @@ static enum i40iw_status_code i40iw_setup_init_state(struct i40iw_handler *hdl, if (status) goto exit; iwdev->obj_next = iwdev->obj_mem; - iwdev->push_mode = push_mode; init_waitqueue_head(&iwdev->vchnl_waitq); init_waitqueue_head(&dev->vf_reqs); diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 581ecbadf586..533f3caecb7a 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -167,39 +167,16 @@ static void i40iw_dealloc_ucontext(struct ib_ucontext *context) */ static int i40iw_mmap(struct ib_ucontext *context, struct vm_area_struct *vma) { - struct i40iw_ucontext *ucontext; - u64 db_addr_offset, push_offset, pfn; - - ucontext = to_ucontext(context); - if (ucontext->iwdev->sc_dev.is_pf) { - db_addr_offset = I40IW_DB_ADDR_OFFSET; - push_offset = I40IW_PUSH_OFFSET; - if (vma->vm_pgoff) - vma->vm_pgoff += I40IW_PF_FIRST_PUSH_PAGE_INDEX - 1; - } else { - db_addr_offset = I40IW_VF_DB_ADDR_OFFSET; - push_offset = I40IW_VF_PUSH_OFFSET; - if (vma->vm_pgoff) - vma->vm_pgoff += I40IW_VF_FIRST_PUSH_PAGE_INDEX - 1; - } + struct i40iw_ucontext *ucontext = to_ucontext(context); + u64 dbaddr; - vma->vm_pgoff += db_addr_offset >> PAGE_SHIFT; - - if (vma->vm_pgoff == (db_addr_offset >> PAGE_SHIFT)) { - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - } else { - if ((vma->vm_pgoff - (push_offset >> PAGE_SHIFT)) % 2) - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - else - vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); - } + if (vma->vm_pgoff || vma->vm_end - vma->vm_start != PAGE_SIZE) + return -EINVAL; - pfn = vma->vm_pgoff + - (pci_resource_start(ucontext->iwdev->ldev->pcidev, 0) >> - PAGE_SHIFT); + dbaddr = I40IW_DB_ADDR_OFFSET + pci_resource_start(ucontext->iwdev->ldev->pcidev, 0); - return rdma_user_mmap_io(context, vma, pfn, PAGE_SIZE, - vma->vm_page_prot, NULL); + return rdma_user_mmap_io(context, vma, dbaddr >> PAGE_SHIFT, PAGE_SIZE, + pgprot_noncached(vma->vm_page_prot), NULL); } /** -- cgit v1.2.3 From 50bdcf047503e30126327d0be4f0ad7337106d68 Mon Sep 17 00:00:00 2001 From: Amadeusz Sławiński Date: Mon, 23 Nov 2020 12:28:17 -0500 Subject: efi/efivars: Set generic ops before loading SSDT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Efivars allows for overriding of SSDT tables, however starting with commit bf67fad19e493b ("efi: Use more granular check for availability for variable services") this use case is broken. When loading SSDT generic ops should be set first, however mentioned commit reversed order of operations. Fix this by restoring original order of operations. Fixes: bf67fad19e493b ("efi: Use more granular check for availability for variable services") Signed-off-by: Amadeusz Sławiński Link: https://lore.kernel.org/r/20201123172817.124146-1-amadeuszx.slawinski@linux.intel.com Tested-by: Cezary Rojewski Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/efi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 5e5480a0a32d..6c6eec044a97 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -390,10 +390,10 @@ static int __init efisubsys_init(void) if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE | EFI_RT_SUPPORTED_GET_NEXT_VARIABLE_NAME)) { - efivar_ssdt_load(); error = generic_ops_register(); if (error) goto err_put; + efivar_ssdt_load(); platform_device_register_simple("efivars", 0, NULL, 0); } -- cgit v1.2.3 From ff04f3b6f2e27f8ae28a498416af2a8dd5072b43 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 25 Nov 2020 08:45:55 +0100 Subject: efivarfs: revert "fix memory leak in efivarfs_create()" The memory leak addressed by commit fe5186cf12e3 is a false positive: all allocations are recorded in a linked list, and freed when the filesystem is unmounted. This leads to double frees, and as reported by David, leads to crashes if SLUB is configured to self destruct when double frees occur. So drop the redundant kfree() again, and instead, mark the offending pointer variable so the allocation is ignored by kmemleak. Cc: Vamshi K Sthambamkadi Fixes: fe5186cf12e3 ("efivarfs: fix memory leak in efivarfs_create()") Reported-by: David Laight Signed-off-by: Ard Biesheuvel --- fs/efivarfs/inode.c | 2 ++ fs/efivarfs/super.c | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 96c0c86f3fff..0297ad95eb5c 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -103,6 +104,7 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, var->var.VariableName[i] = '\0'; inode->i_private = var; + kmemleak_ignore(var); err = efivar_entry_add(var, &efivarfs_list); if (err) diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index f943fd0b0699..15880a68faad 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -21,7 +21,6 @@ LIST_HEAD(efivarfs_list); static void efivarfs_evict_inode(struct inode *inode) { clear_inode(inode); - kfree(inode->i_private); } static const struct super_operations efivarfs_ops = { -- cgit v1.2.3 From 36a237526cd81ff4b6829e6ebd60921c6f976e3b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 24 Nov 2020 20:16:46 +0100 Subject: efi: EFI_EARLYCON should depend on EFI CONFIG_EFI_EARLYCON defaults to yes, and thus is enabled on systems that do not support EFI, or do not have EFI support enabled, but do satisfy the symbol's other dependencies. While drivers/firmware/efi/ won't be entered during the build phase if CONFIG_EFI=n, and drivers/firmware/efi/earlycon.c itself thus won't be built, enabling EFI_EARLYCON does force-enable CONFIG_FONT_SUPPORT and CONFIG_ARCH_USE_MEMREMAP_PROT, and CONFIG_FONT_8x16, which is undesirable. Fix this by making CONFIG_EFI_EARLYCON depend on CONFIG_EFI. This reduces kernel size on headless systems by more than 4 KiB. Fixes: 69c1f396f25b805a ("efi/x86: Convert x86 EFI earlyprintk into generic earlycon implementation") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20201124191646.3559757-1-geert@linux-m68k.org Reviewed-by: Damien Le Moal Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index 36ec1f718893..d9895491ff34 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -270,7 +270,7 @@ config EFI_DEV_PATH_PARSER config EFI_EARLYCON def_bool y - depends on SERIAL_EARLYCON && !ARM && !IA64 + depends on EFI && SERIAL_EARLYCON && !ARM && !IA64 select FONT_SUPPORT select ARCH_USE_MEMREMAP_PROT -- cgit v1.2.3 From 778721510e84209f78e31e2ccb296ae36d623f5e Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Tue, 24 Nov 2020 10:44:36 -0500 Subject: gfs2: check for empty rgrp tree in gfs2_ri_update If gfs2 tries to mount a (corrupt) file system that has no resource groups it still tries to set preferences on the first one, which causes a kernel null pointer dereference. This patch adds a check to function gfs2_ri_update so this condition is detected and reported back as an error. Reported-by: syzbot+e3f23ce40269a4c9053a@syzkaller.appspotmail.com Signed-off-by: Bob Peterson Signed-off-by: Andreas Gruenbacher --- fs/gfs2/rgrp.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index f7addc6197ed..5e8eef9990e3 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -985,6 +985,10 @@ static int gfs2_ri_update(struct gfs2_inode *ip) if (error < 0) return error; + if (RB_EMPTY_ROOT(&sdp->sd_rindex_tree)) { + fs_err(sdp, "no resource groups found in the file system.\n"); + return -ENOENT; + } set_rgrp_preferences(sdp); sdp->sd_rindex_uptodate = 1; -- cgit v1.2.3 From f39e7d3aae2934b1cfdd209b54c508e2552e9531 Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Tue, 24 Nov 2020 10:41:40 -0600 Subject: gfs2: Don't freeze the file system during unmount GFS2's freeze/thaw mechanism uses a special freeze glock to control its operation. It does this with a sync glock operation (glops.c) called freeze_go_sync. When the freeze glock is demoted (glock's do_xmote) the glops function causes the file system to be frozen. This is intended. However, GFS2's mount and unmount processes also hold the freeze glock to prevent other processes, perhaps on different cluster nodes, from mounting the frozen file system in read-write mode. Before this patch, there was no check in freeze_go_sync for whether a freeze in intended or whether the glock demote was caused by a normal unmount. So it was trying to freeze the file system it's trying to unmount, which ends up in a deadlock. This patch adds an additional check to freeze_go_sync so that demotes of the freeze glock are ignored if they come from the unmount process. Fixes: 20b329129009 ("gfs2: Fix regression in freeze_go_sync") Signed-off-by: Bob Peterson Signed-off-by: Andreas Gruenbacher --- fs/gfs2/glops.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index e2cfc00ab936..3faa421568b0 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -582,7 +582,8 @@ static int freeze_go_sync(struct gfs2_glock *gl) * Once thawed, the work func acquires the freeze glock in * SH and everybody goes back to thawed. */ - if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp)) { + if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp) && + !test_bit(SDF_NORECOVERY, &sdp->sd_flags)) { atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE); error = freeze_super(sdp->sd_vfs); if (error) { -- cgit v1.2.3 From e553fdc8105ac2ef3f321739da3908bb6673f7de Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Sun, 8 Nov 2020 13:37:37 -0700 Subject: riscv: Explicitly specify the build id style in vDSO Makefile again Commit a96843372331 ("kbuild: explicitly specify the build id style") explicitly set the build ID style to SHA1. Commit c2c81bb2f691 ("RISC-V: Fix the VDSO symbol generaton for binutils-2.35+") undid this change, likely unintentionally. Restore it so that the build ID style stays consistent across the tree regardless of linker. Fixes: c2c81bb2f691 ("RISC-V: Fix the VDSO symbol generaton for binutils-2.35+") Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Reviewed-by: Bill Wendling Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/vdso/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index cb8f9e4cfcbf..0cfd6da784f8 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -44,7 +44,7 @@ SYSCFLAGS_vdso.so.dbg = $(c_flags) $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold) SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ - -Wl,--build-id -Wl,--hash-style=both + -Wl,--build-id=sha1 -Wl,--hash-style=both # We also create a special relocatable object that should mirror the symbol # table and layout of the linked DSO. With ld --just-symbols we can then -- cgit v1.2.3 From 6134b110f97178d6919441a82dc91a7f3664b4e0 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Fri, 6 Nov 2020 13:23:59 +0530 Subject: RISC-V: Add missing jump label initialization The jump_label_init() should be called from setup_arch() very early for proper functioning of jump label support. Fixes: ebc00dde8a97 ("riscv: Add jump-label implementation") Signed-off-by: Anup Patel Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/setup.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index c424cc6dd833..117f3212a8e4 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -75,6 +75,7 @@ void __init setup_arch(char **cmdline_p) *cmdline_p = boot_command_line; early_ioremap_setup(); + jump_label_init(); parse_early_param(); efi_init(); -- cgit v1.2.3 From 30aca1bacb398dec6c1ed5eeca33f355bd7b6203 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 16 Nov 2020 17:39:51 -0800 Subject: RISC-V: fix barrier() use in riscv's uses barrier() so it should include Fixes this build error: CC [M] drivers/net/ethernet/emulex/benet/be_main.o In file included from ./include/vdso/processor.h:10, from ./arch/riscv/include/asm/processor.h:11, from ./include/linux/prefetch.h:15, from drivers/net/ethernet/emulex/benet/be_main.c:14: ./arch/riscv/include/asm/vdso/processor.h: In function 'cpu_relax': ./arch/riscv/include/asm/vdso/processor.h:14:2: error: implicit declaration of function 'barrier' [-Werror=implicit-function-declaration] 14 | barrier(); This happens with a total of 5 networking drivers -- they all use . rv64 allmodconfig now builds cleanly after this patch. Fixes fallout from: 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Fixes: ad5d1122b82f ("riscv: use vDSO common flow to reduce the latency of the time-related functions") Reported-by: Andreas Schwab Signed-off-by: Randy Dunlap Acked-by: Arvind Sankar Signed-off-by: Palmer Dabbelt Reviewed-by: Nick Desaulniers Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/vdso/processor.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h index 82a5693b1861..134388cbaaa1 100644 --- a/arch/riscv/include/asm/vdso/processor.h +++ b/arch/riscv/include/asm/vdso/processor.h @@ -4,6 +4,8 @@ #ifndef __ASSEMBLY__ +#include + static inline void cpu_relax(void) { #ifdef __riscv_muldiv -- cgit v1.2.3 From 33fc379df76b4991e5ae312f07bcd6820811971e Mon Sep 17 00:00:00 2001 From: Anand K Mistry Date: Tue, 10 Nov 2020 12:33:53 +1100 Subject: x86/speculation: Fix prctl() when spectre_v2_user={seccomp,prctl},ibpb When spectre_v2_user={seccomp,prctl},ibpb is specified on the command line, IBPB is force-enabled and STIPB is conditionally-enabled (or not available). However, since 21998a351512 ("x86/speculation: Avoid force-disabling IBPB based on STIBP and enhanced IBRS.") the spectre_v2_user_ibpb variable is set to SPECTRE_V2_USER_{PRCTL,SECCOMP} instead of SPECTRE_V2_USER_STRICT, which is the actual behaviour. Because the issuing of IBPB relies on the switch_mm_*_ibpb static branches, the mitigations behave as expected. Since 1978b3a53a74 ("x86/speculation: Allow IBPB to be conditionally enabled on CPUs with always-on STIBP") this discrepency caused the misreporting of IB speculation via prctl(). On CPUs with STIBP always-on and spectre_v2_user=seccomp,ibpb, prctl(PR_GET_SPECULATION_CTRL) would return PR_SPEC_PRCTL | PR_SPEC_ENABLE instead of PR_SPEC_DISABLE since both IBPB and STIPB are always on. It also allowed prctl(PR_SET_SPECULATION_CTRL) to set the IB speculation mode, even though the flag is ignored. Similarly, for CPUs without SMT, prctl(PR_GET_SPECULATION_CTRL) should also return PR_SPEC_DISABLE since IBPB is always on and STIBP is not available. [ bp: Massage commit message. ] Fixes: 21998a351512 ("x86/speculation: Avoid force-disabling IBPB based on STIBP and enhanced IBRS.") Fixes: 1978b3a53a74 ("x86/speculation: Allow IBPB to be conditionally enabled on CPUs with always-on STIBP") Signed-off-by: Anand K Mistry Signed-off-by: Borislav Petkov Cc: Link: https://lkml.kernel.org/r/20201110123349.1.Id0cbf996d2151f4c143c90f9028651a5b49a5908@changeid --- arch/x86/kernel/cpu/bugs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 581fb7223ad0..d41b70fe4918 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -739,11 +739,13 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + spectre_v2_user_ibpb = mode; switch (cmd) { case SPECTRE_V2_USER_CMD_FORCE: case SPECTRE_V2_USER_CMD_PRCTL_IBPB: case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: static_branch_enable(&switch_mm_always_ibpb); + spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT; break; case SPECTRE_V2_USER_CMD_PRCTL: case SPECTRE_V2_USER_CMD_AUTO: @@ -757,8 +759,6 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n", static_key_enabled(&switch_mm_always_ibpb) ? "always-on" : "conditional"); - - spectre_v2_user_ibpb = mode; } /* -- cgit v1.2.3 From e255e11e66da8281e337e4e352956e8a4999fca4 Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Tue, 24 Nov 2020 15:17:28 +0800 Subject: ipv6: addrlabel: fix possible memory leak in ip6addrlbl_net_init kmemleak report a memory leak as follows: unreferenced object 0xffff8880059c6a00 (size 64): comm "ip", pid 23696, jiffies 4296590183 (age 1755.384s) hex dump (first 32 bytes): 20 01 00 10 00 00 00 00 00 00 00 00 00 00 00 00 ............... 1c 00 00 00 00 00 00 00 00 00 00 00 07 00 00 00 ................ backtrace: [<00000000aa4e7a87>] ip6addrlbl_add+0x90/0xbb0 [<0000000070b8d7f1>] ip6addrlbl_net_init+0x109/0x170 [<000000006a9ca9d4>] ops_init+0xa8/0x3c0 [<000000002da57bf2>] setup_net+0x2de/0x7e0 [<000000004e52d573>] copy_net_ns+0x27d/0x530 [<00000000b07ae2b4>] create_new_namespaces+0x382/0xa30 [<000000003b76d36f>] unshare_nsproxy_namespaces+0xa1/0x1d0 [<0000000030653721>] ksys_unshare+0x3a4/0x780 [<0000000007e82e40>] __x64_sys_unshare+0x2d/0x40 [<0000000031a10c08>] do_syscall_64+0x33/0x40 [<0000000099df30e7>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 We should free all rules when we catch an error in ip6addrlbl_net_init(). otherwise a memory leak will occur. Fixes: 2a8cc6c89039 ("[IPV6] ADDRCONF: Support RFC3484 configurable address selection policy table.") Reported-by: Hulk Robot Signed-off-by: Wang Hai Link: https://lore.kernel.org/r/20201124071728.8385-1-wanghai38@huawei.com Signed-off-by: Jakub Kicinski --- net/ipv6/addrlabel.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 642fc6ac13d2..8a22486cf270 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -306,7 +306,9 @@ static int ip6addrlbl_del(struct net *net, /* add default label */ static int __net_init ip6addrlbl_net_init(struct net *net) { - int err = 0; + struct ip6addrlbl_entry *p = NULL; + struct hlist_node *n; + int err; int i; ADDRLABEL(KERN_DEBUG "%s\n", __func__); @@ -315,14 +317,20 @@ static int __net_init ip6addrlbl_net_init(struct net *net) INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head); for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) { - int ret = ip6addrlbl_add(net, - ip6addrlbl_init_table[i].prefix, - ip6addrlbl_init_table[i].prefixlen, - 0, - ip6addrlbl_init_table[i].label, 0); - /* XXX: should we free all rules when we catch an error? */ - if (ret && (!err || err != -ENOMEM)) - err = ret; + err = ip6addrlbl_add(net, + ip6addrlbl_init_table[i].prefix, + ip6addrlbl_init_table[i].prefixlen, + 0, + ip6addrlbl_init_table[i].label, 0); + if (err) + goto err_ip6addrlbl_add; + } + return 0; + +err_ip6addrlbl_add: + hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { + hlist_del_rcu(&p->list); + kfree_rcu(p, rcu); } return err; } -- cgit v1.2.3 From 12a8fe56c0f06eaab1f9d89d246c3591bcc7a966 Mon Sep 17 00:00:00 2001 From: Antonio Borneo Date: Tue, 24 Nov 2020 23:37:29 +0100 Subject: net: stmmac: fix incorrect merge of patch upstream Commit 757926247836 ("net: stmmac: add flexible PPS to dwmac 4.10a") was intended to modify the struct dwmac410_ops, but it got somehow badly merged and modified the struct dwmac4_ops. Revert the modification in struct dwmac4_ops and re-apply it properly in struct dwmac410_ops. Fixes: 757926247836 ("net: stmmac: add flexible PPS to dwmac 4.10a") Signed-off-by: Antonio Borneo Reported-by: Ahmad Fatoum Link: https://lore.kernel.org/r/20201124223729.886992-1-antonio.borneo@st.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 002791b77356..ced6d76a0d85 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -1171,7 +1171,6 @@ const struct stmmac_ops dwmac4_ops = { .pcs_get_adv_lp = dwmac4_get_adv_lp, .debug = dwmac4_debug, .set_filter = dwmac4_set_filter, - .flex_pps_config = dwmac5_flex_pps_config, .set_mac_loopback = dwmac4_set_mac_loopback, .update_vlan_hash = dwmac4_update_vlan_hash, .sarc_configure = dwmac4_sarc_configure, @@ -1213,6 +1212,7 @@ const struct stmmac_ops dwmac410_ops = { .pcs_get_adv_lp = dwmac4_get_adv_lp, .debug = dwmac4_debug, .set_filter = dwmac4_set_filter, + .flex_pps_config = dwmac5_flex_pps_config, .set_mac_loopback = dwmac4_set_mac_loopback, .update_vlan_hash = dwmac4_update_vlan_hash, .sarc_configure = dwmac4_sarc_configure, -- cgit v1.2.3 From 2543a6000e593a213fba5b504f52c07e09f39835 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 24 Nov 2020 12:38:22 -0800 Subject: gro_cells: reduce number of synchronize_net() calls After cited commit, gro_cells_destroy() became damn slow on hosts with a lot of cores. This is because we have one additional synchronize_net() per cpu as stated in the changelog. gro_cells_init() is setting NAPI_STATE_NO_BUSY_POLL, and this was enough to not have one synchronize_net() call per netif_napi_del() We can factorize all the synchronize_net() to a single one, right before freeing per-cpu memory. Fixes: 5198d545dba8 ("net: remove napi_hash_del() from driver-facing API") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20201124203822.1360107-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- net/core/gro_cells.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index e095fb871d91..6eb2e5ec2c50 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -99,9 +99,14 @@ void gro_cells_destroy(struct gro_cells *gcells) struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); napi_disable(&cell->napi); - netif_napi_del(&cell->napi); + __netif_napi_del(&cell->napi); __skb_queue_purge(&cell->napi_skbs); } + /* This barrier is needed because netpoll could access dev->napi_list + * under rcu protection. + */ + synchronize_net(); + free_percpu(gcells->cells); gcells->cells = NULL; } -- cgit v1.2.3 From 90cf87d16bd566cff40c2bc8e32e6d4cd3af23f0 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 25 Nov 2020 00:02:59 +0200 Subject: enetc: Let the hardware auto-advance the taprio base-time of 0 The tc-taprio base time indicates the beginning of the tc-taprio schedule, which is cyclic by definition (where the length of the cycle in nanoseconds is called the cycle time). The base time is a 64-bit PTP time in the TAI domain. Logically, the base-time should be a future time. But that imposes some restrictions to user space, which has to retrieve the current PTP time from the NIC first, then calculate a base time that will still be larger than the base time by the time the kernel driver programs this value into the hardware. Actually ensuring that the programmed base time is in the future is still a problem even if the kernel alone deals with this. Luckily, the enetc hardware already advances a base-time that is in the past into a congruent time in the immediate future, according to the same formula that can be found in the software implementation of taprio (in taprio_get_start_time): /* Schedule the start time for the beginning of the next * cycle. */ n = div64_s64(ktime_sub_ns(now, base), cycle); *start = ktime_add_ns(base, (n + 1) * cycle); There's only one problem: the driver doesn't let the hardware do that. It interferes with the base-time passed from user space, by special-casing the situation when the base-time is zero, and replaces that with the current PTP time. This changes the intended effective base-time of the schedule, which will in the end have a different phase offset than if the base-time of 0.000000000 was to be advanced by an integer multiple of the cycle-time. Fixes: 34c6adf1977b ("enetc: Configure the Time-Aware Scheduler via tc-taprio offload") Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20201124220259.3027991-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc_qos.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 827f74e86d34..dbceb99c4441 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -92,18 +92,8 @@ static int enetc_setup_taprio(struct net_device *ndev, gcl_config->atc = 0xff; gcl_config->acl_len = cpu_to_le16(gcl_len); - if (!admin_conf->base_time) { - gcl_data->btl = - cpu_to_le32(enetc_rd(&priv->si->hw, ENETC_SICTR0)); - gcl_data->bth = - cpu_to_le32(enetc_rd(&priv->si->hw, ENETC_SICTR1)); - } else { - gcl_data->btl = - cpu_to_le32(lower_32_bits(admin_conf->base_time)); - gcl_data->bth = - cpu_to_le32(upper_32_bits(admin_conf->base_time)); - } - + gcl_data->btl = cpu_to_le32(lower_32_bits(admin_conf->base_time)); + gcl_data->bth = cpu_to_le32(upper_32_bits(admin_conf->base_time)); gcl_data->ct = cpu_to_le32(admin_conf->cycle_time); gcl_data->cte = cpu_to_le32(admin_conf->cycle_time_extension); -- cgit v1.2.3 From 9a44bc9449cfe7e39dbadf537ff669fb007a9e63 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Wed, 25 Nov 2020 20:24:04 +0000 Subject: bpf: Add MAINTAINERS entry for BPF LSM Similar to XDP and some JITs, also add Brendan and Florent who have been reviewing all my patches internally as reviewers. The patches are expected as usual to go via the BPF tree(s) / list / merge workflows. Signed-off-by: KP Singh Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20201125202404.1419509-1-kpsingh@chromium.org --- MAINTAINERS | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 15355c055a1a..3004f0abfe7d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3356,6 +3356,17 @@ S: Supported F: arch/x86/net/ X: arch/x86/net/bpf_jit_comp32.c +BPF LSM (Security Audit and Enforcement using BPF) +M: KP Singh +R: Florent Revest +R: Brendan Jackman +L: bpf@vger.kernel.org +S: Maintained +F: Documentation/bpf/bpf_lsm.rst +F: include/linux/bpf_lsm.h +F: kernel/bpf/bpf_lsm.c +F: security/bpf/ + BROADCOM B44 10/100 ETHERNET DRIVER M: Michael Chan L: netdev@vger.kernel.org -- cgit v1.2.3 From 68ad89de918e1c5a79c9c56127e5e31741fd517e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 19 Nov 2020 01:59:32 -0800 Subject: netfilter: ipset: prevent uninit-value in hash_ip6_add syzbot found that we are not validating user input properly before copying 16 bytes [1]. Using NLA_BINARY in ipaddr_policy[] for IPv6 address is not correct, since it ensures at most 16 bytes were provided. We should instead make sure user provided exactly 16 bytes. In old kernels (before v4.20), fix would be to remove the NLA_BINARY, since NLA_POLICY_EXACT_LEN() was not yet available. [1] BUG: KMSAN: uninit-value in hash_ip6_add+0x1cba/0x3a50 net/netfilter/ipset/ip_set_hash_gen.h:892 CPU: 1 PID: 11611 Comm: syz-executor.0 Not tainted 5.10.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x21c/0x280 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118 __msan_warning+0x5f/0xa0 mm/kmsan/kmsan_instr.c:197 hash_ip6_add+0x1cba/0x3a50 net/netfilter/ipset/ip_set_hash_gen.h:892 hash_ip6_uadt+0x976/0xbd0 net/netfilter/ipset/ip_set_hash_ip.c:267 call_ad+0x329/0xd00 net/netfilter/ipset/ip_set_core.c:1720 ip_set_ad+0x111f/0x1440 net/netfilter/ipset/ip_set_core.c:1808 ip_set_uadd+0xf6/0x110 net/netfilter/ipset/ip_set_core.c:1833 nfnetlink_rcv_msg+0xc7d/0xdf0 net/netfilter/nfnetlink.c:252 netlink_rcv_skb+0x70a/0x820 net/netlink/af_netlink.c:2494 nfnetlink_rcv+0x4f0/0x4380 net/netfilter/nfnetlink.c:600 netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline] netlink_unicast+0x11da/0x14b0 net/netlink/af_netlink.c:1330 netlink_sendmsg+0x173c/0x1840 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc7a/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d5/0x830 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x45deb9 Code: 0d b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 db b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fe2e503fc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000029ec0 RCX: 000000000045deb9 RDX: 0000000000000000 RSI: 0000000020000140 RDI: 0000000000000003 RBP: 000000000118bf60 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000118bf2c R13: 000000000169fb7f R14: 00007fe2e50409c0 R15: 000000000118bf2c Uninit was stored to memory at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:121 [inline] kmsan_internal_chain_origin+0xad/0x130 mm/kmsan/kmsan.c:289 __msan_chain_origin+0x57/0xa0 mm/kmsan/kmsan_instr.c:147 ip6_netmask include/linux/netfilter/ipset/pfxlen.h:49 [inline] hash_ip6_netmask net/netfilter/ipset/ip_set_hash_ip.c:185 [inline] hash_ip6_uadt+0xb1c/0xbd0 net/netfilter/ipset/ip_set_hash_ip.c:263 call_ad+0x329/0xd00 net/netfilter/ipset/ip_set_core.c:1720 ip_set_ad+0x111f/0x1440 net/netfilter/ipset/ip_set_core.c:1808 ip_set_uadd+0xf6/0x110 net/netfilter/ipset/ip_set_core.c:1833 nfnetlink_rcv_msg+0xc7d/0xdf0 net/netfilter/nfnetlink.c:252 netlink_rcv_skb+0x70a/0x820 net/netlink/af_netlink.c:2494 nfnetlink_rcv+0x4f0/0x4380 net/netfilter/nfnetlink.c:600 netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline] netlink_unicast+0x11da/0x14b0 net/netlink/af_netlink.c:1330 netlink_sendmsg+0x173c/0x1840 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc7a/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d5/0x830 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Uninit was stored to memory at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:121 [inline] kmsan_internal_chain_origin+0xad/0x130 mm/kmsan/kmsan.c:289 kmsan_memcpy_memmove_metadata+0x25e/0x2d0 mm/kmsan/kmsan.c:226 kmsan_memcpy_metadata+0xb/0x10 mm/kmsan/kmsan.c:246 __msan_memcpy+0x46/0x60 mm/kmsan/kmsan_instr.c:110 ip_set_get_ipaddr6+0x2cb/0x370 net/netfilter/ipset/ip_set_core.c:310 hash_ip6_uadt+0x439/0xbd0 net/netfilter/ipset/ip_set_hash_ip.c:255 call_ad+0x329/0xd00 net/netfilter/ipset/ip_set_core.c:1720 ip_set_ad+0x111f/0x1440 net/netfilter/ipset/ip_set_core.c:1808 ip_set_uadd+0xf6/0x110 net/netfilter/ipset/ip_set_core.c:1833 nfnetlink_rcv_msg+0xc7d/0xdf0 net/netfilter/nfnetlink.c:252 netlink_rcv_skb+0x70a/0x820 net/netlink/af_netlink.c:2494 nfnetlink_rcv+0x4f0/0x4380 net/netfilter/nfnetlink.c:600 netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline] netlink_unicast+0x11da/0x14b0 net/netlink/af_netlink.c:1330 netlink_sendmsg+0x173c/0x1840 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc7a/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d5/0x830 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:121 [inline] kmsan_internal_poison_shadow+0x5c/0xf0 mm/kmsan/kmsan.c:104 kmsan_slab_alloc+0x8d/0xe0 mm/kmsan/kmsan_hooks.c:76 slab_alloc_node mm/slub.c:2906 [inline] __kmalloc_node_track_caller+0xc61/0x15f0 mm/slub.c:4512 __kmalloc_reserve net/core/skbuff.c:142 [inline] __alloc_skb+0x309/0xae0 net/core/skbuff.c:210 alloc_skb include/linux/skbuff.h:1094 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1176 [inline] netlink_sendmsg+0xdb8/0x1840 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc7a/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d5/0x830 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: a7b4f989a629 ("netfilter: ipset: IP set core support") Signed-off-by: Eric Dumazet Reported-by: syzbot Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 7cff6e5e7445..2b19189a930f 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -271,8 +271,7 @@ flag_nested(const struct nlattr *nla) static const struct nla_policy ipaddr_policy[IPSET_ATTR_IPADDR_MAX + 1] = { [IPSET_ATTR_IPADDR_IPV4] = { .type = NLA_U32 }, - [IPSET_ATTR_IPADDR_IPV6] = { .type = NLA_BINARY, - .len = sizeof(struct in6_addr) }, + [IPSET_ATTR_IPADDR_IPV6] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), }; int -- cgit v1.2.3 From c0700dfa2cae44c033ed97dade8a2679c7d22a9d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 19 Nov 2020 16:34:54 +0100 Subject: netfilter: nf_tables: avoid false-postive lockdep splat There are reports wrt lockdep splat in nftables, e.g.: ------------[ cut here ]------------ WARNING: CPU: 2 PID: 31416 at net/netfilter/nf_tables_api.c:622 lockdep_nfnl_nft_mutex_not_held+0x28/0x38 [nf_tables] ... These are caused by an earlier, unrelated bug such as a n ABBA deadlock in a different subsystem. In such an event, lockdep is disabled and lockdep_is_held returns true unconditionally. This then causes the WARN() in nf_tables. Make the WARN conditional on lockdep still active to avoid this. Fixes: f102d66b335a417 ("netfilter: nf_tables: use dedicated mutex to guard transactions") Reported-by: Naresh Kamboju Link: https://lore.kernel.org/linux-kselftest/CA+G9fYvFUpODs+NkSYcnwKnXm62tmP=ksLeBPmB+KFrB2rvCtQ@mail.gmail.com/ Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0f58e98542be..23abf1578594 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -619,7 +619,8 @@ static int nft_request_module(struct net *net, const char *fmt, ...) static void lockdep_nfnl_nft_mutex_not_held(void) { #ifdef CONFIG_PROVE_LOCKING - WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); + if (debug_locks) + WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); #endif } -- cgit v1.2.3 From 3d2a9d642512c21a12d19b9250e7a835dcb41a79 Mon Sep 17 00:00:00 2001 From: Dennis Dalessandro Date: Wed, 25 Nov 2020 16:01:12 -0500 Subject: IB/hfi1: Ensure correct mm is used at all times Two earlier bug fixes have created a security problem in the hfi1 driver. One fix aimed to solve an issue where current->mm was not valid when closing the hfi1 cdev. It attempted to do this by saving a cached value of the current->mm pointer at file open time. This is a problem if another process with access to the FD calls in via write() or ioctl() to pin pages via the hfi driver. The other fix tried to solve a use after free by taking a reference on the mm. To fix this correctly we use the existing cached value of the mm in the mmu notifier. Now we can check in the insert, evict, etc. routines that current->mm matched what the notifier was registered for. If not, then don't allow access. The register of the mmu notifier will save the mm pointer. Since in do_exit() the exit_mm() is called before exit_files(), which would call our close routine a reference is needed on the mm. We rely on the mmgrab done by the registration of the notifier, whereas before it was explicit. The mmu notifier deregistration happens when the user context is torn down, the creation of which triggered the registration. Also of note is we do not do any explicit work to protect the interval tree notifier. It doesn't seem that this is going to be needed since we aren't actually doing anything with current->mm. The interval tree notifier stuff still has a FIXME noted from a previous commit that will be addressed in a follow on patch. Cc: Fixes: e0cf75deab81 ("IB/hfi1: Fix mm_struct use after free") Fixes: 3faa3d9a308e ("IB/hfi1: Make use of mm consistent") Link: https://lore.kernel.org/r/20201125210112.104301.51331.stgit@awfm-01.aw.intel.com Suggested-by: Jann Horn Reported-by: Jason Gunthorpe Reviewed-by: Ira Weiny Reviewed-by: Mike Marciniszyn Signed-off-by: Dennis Dalessandro Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hfi1/file_ops.c | 4 +- drivers/infiniband/hw/hfi1/hfi.h | 2 +- drivers/infiniband/hw/hfi1/mmu_rb.c | 68 ++++++++++++++++--------------- drivers/infiniband/hw/hfi1/mmu_rb.h | 16 +++++++- drivers/infiniband/hw/hfi1/user_exp_rcv.c | 12 ++++-- drivers/infiniband/hw/hfi1/user_exp_rcv.h | 6 +++ drivers/infiniband/hw/hfi1/user_sdma.c | 13 +++--- drivers/infiniband/hw/hfi1/user_sdma.h | 7 +++- 8 files changed, 79 insertions(+), 49 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 8ca51e43cf53..329ee4f48d95 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -1,4 +1,5 @@ /* + * Copyright(c) 2020 Cornelis Networks, Inc. * Copyright(c) 2015-2020 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -206,8 +207,6 @@ static int hfi1_file_open(struct inode *inode, struct file *fp) spin_lock_init(&fd->tid_lock); spin_lock_init(&fd->invalid_lock); fd->rec_cpu_num = -1; /* no cpu affinity by default */ - fd->mm = current->mm; - mmgrab(fd->mm); fd->dd = dd; fp->private_data = fd; return 0; @@ -711,7 +710,6 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) deallocate_ctxt(uctxt); done: - mmdrop(fdata->mm); if (atomic_dec_and_test(&dd->user_refcount)) complete(&dd->user_comp); diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index b4c6bff60a4e..e09e8244a94c 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -1,6 +1,7 @@ #ifndef _HFI1_KERNEL_H #define _HFI1_KERNEL_H /* + * Copyright(c) 2020 Cornelis Networks, Inc. * Copyright(c) 2015-2020 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -1451,7 +1452,6 @@ struct hfi1_filedata { u32 invalid_tid_idx; /* protect invalid_tids array and invalid_tid_idx */ spinlock_t invalid_lock; - struct mm_struct *mm; }; extern struct xarray hfi1_dev_table; diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index 24ca17b77b72..f3fb28e3d5d7 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -1,4 +1,5 @@ /* + * Copyright(c) 2020 Cornelis Networks, Inc. * Copyright(c) 2016 - 2017 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -48,23 +49,11 @@ #include #include #include +#include #include "mmu_rb.h" #include "trace.h" -struct mmu_rb_handler { - struct mmu_notifier mn; - struct rb_root_cached root; - void *ops_arg; - spinlock_t lock; /* protect the RB tree */ - struct mmu_rb_ops *ops; - struct mm_struct *mm; - struct list_head lru_list; - struct work_struct del_work; - struct list_head del_list; - struct workqueue_struct *wq; -}; - static unsigned long mmu_node_start(struct mmu_rb_node *); static unsigned long mmu_node_last(struct mmu_rb_node *); static int mmu_notifier_range_start(struct mmu_notifier *, @@ -92,37 +81,36 @@ static unsigned long mmu_node_last(struct mmu_rb_node *node) return PAGE_ALIGN(node->addr + node->len) - 1; } -int hfi1_mmu_rb_register(void *ops_arg, struct mm_struct *mm, +int hfi1_mmu_rb_register(void *ops_arg, struct mmu_rb_ops *ops, struct workqueue_struct *wq, struct mmu_rb_handler **handler) { - struct mmu_rb_handler *handlr; + struct mmu_rb_handler *h; int ret; - handlr = kmalloc(sizeof(*handlr), GFP_KERNEL); - if (!handlr) + h = kmalloc(sizeof(*h), GFP_KERNEL); + if (!h) return -ENOMEM; - handlr->root = RB_ROOT_CACHED; - handlr->ops = ops; - handlr->ops_arg = ops_arg; - INIT_HLIST_NODE(&handlr->mn.hlist); - spin_lock_init(&handlr->lock); - handlr->mn.ops = &mn_opts; - handlr->mm = mm; - INIT_WORK(&handlr->del_work, handle_remove); - INIT_LIST_HEAD(&handlr->del_list); - INIT_LIST_HEAD(&handlr->lru_list); - handlr->wq = wq; - - ret = mmu_notifier_register(&handlr->mn, handlr->mm); + h->root = RB_ROOT_CACHED; + h->ops = ops; + h->ops_arg = ops_arg; + INIT_HLIST_NODE(&h->mn.hlist); + spin_lock_init(&h->lock); + h->mn.ops = &mn_opts; + INIT_WORK(&h->del_work, handle_remove); + INIT_LIST_HEAD(&h->del_list); + INIT_LIST_HEAD(&h->lru_list); + h->wq = wq; + + ret = mmu_notifier_register(&h->mn, current->mm); if (ret) { - kfree(handlr); + kfree(h); return ret; } - *handler = handlr; + *handler = h; return 0; } @@ -134,7 +122,7 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) struct list_head del_list; /* Unregister first so we don't get any more notifications. */ - mmu_notifier_unregister(&handler->mn, handler->mm); + mmu_notifier_unregister(&handler->mn, handler->mn.mm); /* * Make sure the wq delete handler is finished running. It will not @@ -166,6 +154,10 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, int ret = 0; trace_hfi1_mmu_rb_insert(mnode->addr, mnode->len); + + if (current->mm != handler->mn.mm) + return -EPERM; + spin_lock_irqsave(&handler->lock, flags); node = __mmu_rb_search(handler, mnode->addr, mnode->len); if (node) { @@ -180,6 +172,7 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, __mmu_int_rb_remove(mnode, &handler->root); list_del(&mnode->list); /* remove from LRU list */ } + mnode->handler = handler; unlock: spin_unlock_irqrestore(&handler->lock, flags); return ret; @@ -217,6 +210,9 @@ bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler, unsigned long flags; bool ret = false; + if (current->mm != handler->mn.mm) + return ret; + spin_lock_irqsave(&handler->lock, flags); node = __mmu_rb_search(handler, addr, len); if (node) { @@ -239,6 +235,9 @@ void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) unsigned long flags; bool stop = false; + if (current->mm != handler->mn.mm) + return; + INIT_LIST_HEAD(&del_list); spin_lock_irqsave(&handler->lock, flags); @@ -272,6 +271,9 @@ void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler, { unsigned long flags; + if (current->mm != handler->mn.mm) + return; + /* Validity of handler and node pointers has been checked by caller. */ trace_hfi1_mmu_rb_remove(node->addr, node->len); spin_lock_irqsave(&handler->lock, flags); diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.h b/drivers/infiniband/hw/hfi1/mmu_rb.h index f04cec1e99d1..423aacc67e94 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.h +++ b/drivers/infiniband/hw/hfi1/mmu_rb.h @@ -1,4 +1,5 @@ /* + * Copyright(c) 2020 Cornelis Networks, Inc. * Copyright(c) 2016 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -54,6 +55,7 @@ struct mmu_rb_node { unsigned long len; unsigned long __last; struct rb_node node; + struct mmu_rb_handler *handler; struct list_head list; }; @@ -71,7 +73,19 @@ struct mmu_rb_ops { void *evict_arg, bool *stop); }; -int hfi1_mmu_rb_register(void *ops_arg, struct mm_struct *mm, +struct mmu_rb_handler { + struct mmu_notifier mn; + struct rb_root_cached root; + void *ops_arg; + spinlock_t lock; /* protect the RB tree */ + struct mmu_rb_ops *ops; + struct list_head lru_list; + struct work_struct del_work; + struct list_head del_list; + struct workqueue_struct *wq; +}; + +int hfi1_mmu_rb_register(void *ops_arg, struct mmu_rb_ops *ops, struct workqueue_struct *wq, struct mmu_rb_handler **handler); diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index f81ca20f4b69..b94fc7fd75a9 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -1,4 +1,5 @@ /* + * Copyright(c) 2020 Cornelis Networks, Inc. * Copyright(c) 2015-2018 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -173,15 +174,18 @@ static void unpin_rcv_pages(struct hfi1_filedata *fd, { struct page **pages; struct hfi1_devdata *dd = fd->uctxt->dd; + struct mm_struct *mm; if (mapped) { pci_unmap_single(dd->pcidev, node->dma_addr, node->npages * PAGE_SIZE, PCI_DMA_FROMDEVICE); pages = &node->pages[idx]; + mm = mm_from_tid_node(node); } else { pages = &tidbuf->pages[idx]; + mm = current->mm; } - hfi1_release_user_pages(fd->mm, pages, npages, mapped); + hfi1_release_user_pages(mm, pages, npages, mapped); fd->tid_n_pinned -= npages; } @@ -216,12 +220,12 @@ static int pin_rcv_pages(struct hfi1_filedata *fd, struct tid_user_buf *tidbuf) * pages, accept the amount pinned so far and program only that. * User space knows how to deal with partially programmed buffers. */ - if (!hfi1_can_pin_pages(dd, fd->mm, fd->tid_n_pinned, npages)) { + if (!hfi1_can_pin_pages(dd, current->mm, fd->tid_n_pinned, npages)) { kfree(pages); return -ENOMEM; } - pinned = hfi1_acquire_user_pages(fd->mm, vaddr, npages, true, pages); + pinned = hfi1_acquire_user_pages(current->mm, vaddr, npages, true, pages); if (pinned <= 0) { kfree(pages); return pinned; @@ -756,7 +760,7 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd, if (fd->use_mn) { ret = mmu_interval_notifier_insert( - &node->notifier, fd->mm, + &node->notifier, current->mm, tbuf->vaddr + (pageidx * PAGE_SIZE), npages * PAGE_SIZE, &tid_mn_ops); if (ret) diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.h b/drivers/infiniband/hw/hfi1/user_exp_rcv.h index 332abb446861..d45c7b6988d4 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.h +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.h @@ -1,6 +1,7 @@ #ifndef _HFI1_USER_EXP_RCV_H #define _HFI1_USER_EXP_RCV_H /* + * Copyright(c) 2020 - Cornelis Networks, Inc. * Copyright(c) 2015 - 2017 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -95,4 +96,9 @@ int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd, int hfi1_user_exp_rcv_invalid(struct hfi1_filedata *fd, struct hfi1_tid_info *tinfo); +static inline struct mm_struct *mm_from_tid_node(struct tid_rb_node *node) +{ + return node->notifier.mm; +} + #endif /* _HFI1_USER_EXP_RCV_H */ diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index a92346e88628..4a4956f96a7e 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -1,4 +1,5 @@ /* + * Copyright(c) 2020 - Cornelis Networks, Inc. * Copyright(c) 2015 - 2018 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -188,7 +189,6 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt, atomic_set(&pq->n_reqs, 0); init_waitqueue_head(&pq->wait); atomic_set(&pq->n_locked, 0); - pq->mm = fd->mm; iowait_init(&pq->busy, 0, NULL, NULL, defer_packet_queue, activate_packet_queue, NULL, NULL); @@ -230,7 +230,7 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt, cq->nentries = hfi1_sdma_comp_ring_size; - ret = hfi1_mmu_rb_register(pq, pq->mm, &sdma_rb_ops, dd->pport->hfi1_wq, + ret = hfi1_mmu_rb_register(pq, &sdma_rb_ops, dd->pport->hfi1_wq, &pq->handler); if (ret) { dd_dev_err(dd, "Failed to register with MMU %d", ret); @@ -980,13 +980,13 @@ static int pin_sdma_pages(struct user_sdma_request *req, npages -= node->npages; retry: - if (!hfi1_can_pin_pages(pq->dd, pq->mm, + if (!hfi1_can_pin_pages(pq->dd, current->mm, atomic_read(&pq->n_locked), npages)) { cleared = sdma_cache_evict(pq, npages); if (cleared >= npages) goto retry; } - pinned = hfi1_acquire_user_pages(pq->mm, + pinned = hfi1_acquire_user_pages(current->mm, ((unsigned long)iovec->iov.iov_base + (node->npages * PAGE_SIZE)), npages, 0, pages + node->npages); @@ -995,7 +995,7 @@ retry: return pinned; } if (pinned != npages) { - unpin_vector_pages(pq->mm, pages, node->npages, pinned); + unpin_vector_pages(current->mm, pages, node->npages, pinned); return -EFAULT; } kfree(node->pages); @@ -1008,7 +1008,8 @@ retry: static void unpin_sdma_pages(struct sdma_mmu_node *node) { if (node->npages) { - unpin_vector_pages(node->pq->mm, node->pages, 0, node->npages); + unpin_vector_pages(mm_from_sdma_node(node), node->pages, 0, + node->npages); atomic_sub(node->npages, &node->pq->n_locked); } } diff --git a/drivers/infiniband/hw/hfi1/user_sdma.h b/drivers/infiniband/hw/hfi1/user_sdma.h index 9972e0e6545e..1e8c02fe8ad1 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.h +++ b/drivers/infiniband/hw/hfi1/user_sdma.h @@ -1,6 +1,7 @@ #ifndef _HFI1_USER_SDMA_H #define _HFI1_USER_SDMA_H /* + * Copyright(c) 2020 - Cornelis Networks, Inc. * Copyright(c) 2015 - 2018 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -133,7 +134,6 @@ struct hfi1_user_sdma_pkt_q { unsigned long unpinned; struct mmu_rb_handler *handler; atomic_t n_locked; - struct mm_struct *mm; }; struct hfi1_user_sdma_comp_q { @@ -250,4 +250,9 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, struct iovec *iovec, unsigned long dim, unsigned long *count); +static inline struct mm_struct *mm_from_sdma_node(struct sdma_mmu_node *node) +{ + return node->rb.handler->mn.mm; +} + #endif /* _HFI1_USER_SDMA_H */ -- cgit v1.2.3 From 3cb2e6d92be637b79d6ba0746d610a8dfcc0400b Mon Sep 17 00:00:00 2001 From: Min Li Date: Tue, 24 Nov 2020 21:58:35 -0500 Subject: ptp: clockmatrix: bug fix for idtcm_strverscmp Feed kstrtou8 with NULL terminated string. Changes since v1: -Use sscanf to get rid of adhoc string parse. Changes since v2: -Check if sscanf returns 3. Fixes: 7ea5fda2b132 ("ptp: ptp_clockmatrix: update to support 4.8.7 firmware") Signed-off-by: Min Li Link: https://lore.kernel.org/r/1606273115-25792-1-git-send-email-min.li.xe@renesas.com Signed-off-by: Jakub Kicinski --- drivers/ptp/ptp_clockmatrix.c | 49 ++++++++++++++----------------------------- 1 file changed, 16 insertions(+), 33 deletions(-) diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c index e020faff7da5..663255774c0b 100644 --- a/drivers/ptp/ptp_clockmatrix.c +++ b/drivers/ptp/ptp_clockmatrix.c @@ -103,43 +103,26 @@ static int timespec_to_char_array(struct timespec64 const *ts, return 0; } -static int idtcm_strverscmp(const char *ver1, const char *ver2) +static int idtcm_strverscmp(const char *version1, const char *version2) { - u8 num1; - u8 num2; - int result = 0; - - /* loop through each level of the version string */ - while (result == 0) { - /* extract leading version numbers */ - if (kstrtou8(ver1, 10, &num1) < 0) - return -1; + u8 ver1[3], ver2[3]; + int i; - if (kstrtou8(ver2, 10, &num2) < 0) - return -1; + if (sscanf(version1, "%hhu.%hhu.%hhu", + &ver1[0], &ver1[1], &ver1[2]) != 3) + return -1; + if (sscanf(version2, "%hhu.%hhu.%hhu", + &ver2[0], &ver2[1], &ver2[2]) != 3) + return -1; - /* if numbers differ, then set the result */ - if (num1 < num2) - result = -1; - else if (num1 > num2) - result = 1; - else { - /* if numbers are the same, go to next level */ - ver1 = strchr(ver1, '.'); - ver2 = strchr(ver2, '.'); - if (!ver1 && !ver2) - break; - else if (!ver1) - result = -1; - else if (!ver2) - result = 1; - else { - ver1++; - ver2++; - } - } + for (i = 0; i < 3; i++) { + if (ver1[i] > ver2[i]) + return 1; + if (ver1[i] < ver2[i]) + return -1; } - return result; + + return 0; } static int idtcm_xfer_read(struct idtcm *idtcm, -- cgit v1.2.3 From b187c9b4178b87954dbc94e78a7094715794714f Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 25 Nov 2020 11:16:19 +0200 Subject: devlink: Hold rtnl lock while reading netdev attributes A netdevice of a devlink port can be moved to different net namespace than its parent devlink instance. This scenario occurs when devlink reload is not used. When netdevice is undergoing migration to net namespace, its ifindex and name may change. In such use case, devlink port query may read stale netdev attributes. Fix it by reading them under rtnl lock. Fixes: bfcd3a466172 ("Introduce devlink infrastructure") Signed-off-by: Parav Pandit Signed-off-by: Jakub Kicinski --- net/core/devlink.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/core/devlink.c b/net/core/devlink.c index c91e15b7a2bd..79b8df41bea3 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -772,6 +772,8 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; + /* Hold rtnl lock while accessing port's netdev attributes. */ + rtnl_lock(); spin_lock_bh(&devlink_port->type_lock); if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure_type_locked; @@ -798,6 +800,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, goto nla_put_failure_type_locked; } spin_unlock_bh(&devlink_port->type_lock); + rtnl_unlock(); if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure; if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack)) @@ -808,6 +811,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, nla_put_failure_type_locked: spin_unlock_bh(&devlink_port->type_lock); + rtnl_unlock(); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; -- cgit v1.2.3 From a7b43649507dae4e55ff0087cad4e4dd1c6d5b99 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 25 Nov 2020 11:16:20 +0200 Subject: devlink: Make sure devlink instance and port are in same net namespace When devlink reload operation is not used, netdev of an Ethernet port may be present in different net namespace than the net namespace of the devlink instance. Ensure that both the devlink instance and devlink port netdev are located in same net namespace. Fixes: 070c63f20f6c ("net: devlink: allow to change namespaces during reload") Signed-off-by: Parav Pandit Signed-off-by: Jakub Kicinski --- net/core/devlink.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/core/devlink.c b/net/core/devlink.c index 79b8df41bea3..8c5ddffd707d 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -782,9 +782,10 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, devlink_port->desired_type)) goto nla_put_failure_type_locked; if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { + struct net *net = devlink_net(devlink_port->devlink); struct net_device *netdev = devlink_port->type_dev; - if (netdev && + if (netdev && net_eq(net, dev_net(netdev)) && (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, netdev->ifindex) || nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, -- cgit v1.2.3 From 025cc2fb6a4e84e9a0552c0017dcd1c24b7ac7da Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 25 Nov 2020 14:18:10 -0800 Subject: net/tls: Protect from calling tls_dev_del for TLS RX twice tls_device_offload_cleanup_rx doesn't clear tls_ctx->netdev after calling tls_dev_del if TLX TX offload is also enabled. Clearing tls_ctx->netdev gets postponed until tls_device_gc_task. It leaves a time frame when tls_device_down may get called and call tls_dev_del for RX one extra time, confusing the driver, which may lead to a crash. This patch corrects this racy behavior by adding a flag to prevent tls_device_down from calling tls_dev_del the second time. Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure") Signed-off-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed Link: https://lore.kernel.org/r/20201125221810.69870-1-saeedm@nvidia.com Signed-off-by: Jakub Kicinski --- include/net/tls.h | 6 ++++++ net/tls/tls_device.c | 5 ++++- 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/include/net/tls.h b/include/net/tls.h index cf1473099453..2bdd802212fe 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -199,6 +199,12 @@ enum tls_context_flags { * to be atomic. */ TLS_TX_SYNC_SCHED = 1, + /* tls_dev_del was called for the RX side, device state was released, + * but tls_ctx->netdev might still be kept, because TX-side driver + * resources might not be released yet. Used to prevent the second + * tls_dev_del call in tls_device_down if it happens simultaneously. + */ + TLS_RX_DEV_CLOSED = 2, }; struct cipher_context { diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 54d3e161d198..a3ab2d3d4e4e 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1262,6 +1262,8 @@ void tls_device_offload_cleanup_rx(struct sock *sk) if (tls_ctx->tx_conf != TLS_HW) { dev_put(netdev); tls_ctx->netdev = NULL; + } else { + set_bit(TLS_RX_DEV_CLOSED, &tls_ctx->flags); } out: up_read(&device_offload_lock); @@ -1291,7 +1293,8 @@ static int tls_device_down(struct net_device *netdev) if (ctx->tx_conf == TLS_HW) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); - if (ctx->rx_conf == TLS_HW) + if (ctx->rx_conf == TLS_HW && + !test_bit(TLS_RX_DEV_CLOSED, &ctx->flags)) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_RX); WRITE_ONCE(ctx->netdev, NULL); -- cgit v1.2.3 From cbf3d60329c4e11edcecac0c8fc6767b0f05e3a7 Mon Sep 17 00:00:00 2001 From: Rohit Maheshwari Date: Wed, 25 Nov 2020 12:56:26 +0530 Subject: ch_ktls: lock is not freed Currently lock gets freed only if timeout expires, but missed a case when HW returns failure and goes for cleanup. Fixes: efca3878a5fb ("ch_ktls: Issue if connection offload fails") Signed-off-by: Rohit Maheshwari Link: https://lore.kernel.org/r/20201125072626.10861-1-rohitm@chelsio.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c index c24485c0d512..7f90b828d159 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c @@ -544,7 +544,9 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk, /* need to wait for hw response, can't free tx_info yet. */ if (tx_info->open_state == CH_KTLS_OPEN_PENDING) tx_info->pending_close = true; - /* free the lock after the cleanup */ + else + spin_unlock_bh(&tx_info->lock); + /* if in pending close, free the lock after the cleanup */ goto put_module; } spin_unlock_bh(&tx_info->lock); -- cgit v1.2.3 From dd6dbe8d7e312238cc0ad0b907042a96b0505d44 Mon Sep 17 00:00:00 2001 From: "Daniel W. S. Almeida" Date: Sat, 31 Oct 2020 16:05:47 +0100 Subject: media: vidtv: extract the initial CRC value to into a #define The same constant (0xffffffff) is used in three different functions. Extract it into a #define to avoid repetition. Signed-off-by: Daniel W. S. Almeida Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_psi.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index 82cf67dd27c0..f2e25e68c085 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -31,6 +31,7 @@ #define CRC_SIZE_IN_BYTES 4 #define MAX_VERSION_NUM 32 +#define INITIAL_CRC 0xffffffff static const u32 CRC_LUT[256] = { /* from libdvbv5 */ @@ -784,7 +785,7 @@ u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args args) /* the number of bytes written by this function */ u32 nbytes = 0; const u16 pat_pid = VIDTV_PAT_PID; - u32 crc = 0xffffffff; + u32 crc = INITIAL_CRC; struct vidtv_psi_table_pat_program *p = args.pat->program; @@ -974,7 +975,7 @@ u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) { /* the number of bytes written by this function */ u32 nbytes = 0; - u32 crc = 0xffffffff; + u32 crc = INITIAL_CRC; struct vidtv_psi_desc *table_descriptor = args.pmt->descriptor; struct vidtv_psi_table_pmt_stream *stream = args.pmt->stream; @@ -1124,7 +1125,7 @@ u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) u32 nbytes = 0; u16 sdt_pid = VIDTV_SDT_PID; /* see ETSI EN 300 468 v1.15.1 p. 11 */ - u32 crc = 0xffffffff; + u32 crc = INITIAL_CRC; struct vidtv_psi_table_sdt_service *service = args.sdt->service; struct vidtv_psi_desc *service_desc = (args.sdt->service) ? -- cgit v1.2.3 From c2f78f0cb294aa6f009d3a170f4ee8ad199ba5da Mon Sep 17 00:00:00 2001 From: "Daniel W. S. Almeida" Date: Sat, 31 Oct 2020 16:05:48 +0100 Subject: media: vidtv: psi: add a Network Information Table (NIT) Add a Network Information Table (NIT) as specified in ETSI EN 300 468. This table conveys information relating to the physical organization of the multiplexes carried via a given network and the characteristics of the network itself. It is conveyed in the output of vidtv as packets with TS PID of 0x0010 [mchehab+huawei@kernel.org: removed an extra blank line] Signed-off-by: Daniel W. S. Almeida Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Mauro Carvalho Chehab --- Documentation/driver-api/media/drivers/vidtv.rst | 6 +- drivers/media/test-drivers/vidtv/vidtv_bridge.c | 4 + drivers/media/test-drivers/vidtv/vidtv_channel.c | 59 ++++ drivers/media/test-drivers/vidtv/vidtv_mux.c | 16 ++ drivers/media/test-drivers/vidtv/vidtv_mux.h | 9 + drivers/media/test-drivers/vidtv/vidtv_psi.c | 345 ++++++++++++++++++++++- drivers/media/test-drivers/vidtv/vidtv_psi.h | 118 +++++++- 7 files changed, 545 insertions(+), 12 deletions(-) diff --git a/Documentation/driver-api/media/drivers/vidtv.rst b/Documentation/driver-api/media/drivers/vidtv.rst index 65115448c52d..2d7ddf676b13 100644 --- a/Documentation/driver-api/media/drivers/vidtv.rst +++ b/Documentation/driver-api/media/drivers/vidtv.rst @@ -149,11 +149,11 @@ vidtv_psi.[ch] Because the generator is implemented in a separate file, it can be reused elsewhere in the media subsystem. - Currently vidtv supports working with 3 PSI tables: PAT, PMT and - SDT. + Currently vidtv supports working with 4 PSI tables: PAT, PMT, + SDT and NIT. The specification for PAT and PMT can be found in *ISO 13818-1: - Systems*, while the specification for the SDT can be found in *ETSI + Systems*, while the specification for the SDT, NIT can be found in *ETSI EN 300 468: Specification for Service Information (SI) in DVB systems*. diff --git a/drivers/media/test-drivers/vidtv/vidtv_bridge.c b/drivers/media/test-drivers/vidtv/vidtv_bridge.c index 74b054947bbe..2f97ecf423ed 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_bridge.c +++ b/drivers/media/test-drivers/vidtv/vidtv_bridge.c @@ -28,6 +28,8 @@ //#define MUX_BUF_MIN_SZ #define TUNER_DEFAULT_ADDR 0x68 #define DEMOD_DEFAULT_ADDR 0x60 +#define VIDTV_DEFAULT_NETWORK_ID 0x744 +#define VIDTV_DEFAULT_NETWORK_NAME "LinuxTV.org" /* LNBf fake parameters: ranges used by an Universal (extended) European LNBf */ #define LNB_CUT_FREQUENCY 11700000 @@ -177,6 +179,8 @@ static int vidtv_start_streaming(struct vidtv_dvb *dvb) mux_args.si_period_usecs = si_period_msec * 1000; mux_args.pcr_pid = pcr_pid; mux_args.transport_stream_id = VIDTV_DEFAULT_TS_ID; + mux_args.network_id = VIDTV_DEFAULT_NETWORK_ID, + mux_args.network_name = VIDTV_DEFAULT_NETWORK_NAME, mux_args.priv = dvb; dvb->streaming = true; diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index f2b97cf08e87..a246b49123d9 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -246,10 +246,57 @@ vidtv_channel_pmt_match_sections(struct vidtv_channel *channels, } } +static struct vidtv_psi_desc_service_list_entry +*vidtv_channel_build_service_list(struct vidtv_psi_table_sdt_service *s) +{ + struct vidtv_psi_desc_service_list_entry *curr_e = NULL; + struct vidtv_psi_desc_service_list_entry *head_e = NULL; + struct vidtv_psi_desc_service_list_entry *prev_e = NULL; + struct vidtv_psi_desc *desc = s->descriptor; + struct vidtv_psi_desc_service *s_desc; + + while (s) { + while (desc) { + if (s->descriptor->type != SERVICE_DESCRIPTOR) + goto next_desc; + + s_desc = (struct vidtv_psi_desc_service *)desc; + + curr_e = kzalloc(sizeof(*curr_e), GFP_KERNEL); + curr_e->service_id = s->service_id; + curr_e->service_type = s_desc->service_type; + + if (!head_e) + head_e = curr_e; + if (prev_e) + prev_e->next = curr_e; + + prev_e = curr_e; + +next_desc: + desc = desc->next; + } + s = s->next; + } + return head_e; +} + +static void vidtv_channel_destroy_service_list(struct vidtv_psi_desc_service_list_entry *e) +{ + struct vidtv_psi_desc_service_list_entry *tmp; + + while (e) { + tmp = e; + e = e->next; + kfree(tmp); + } +} + void vidtv_channel_si_init(struct vidtv_mux *m) { struct vidtv_psi_table_pat_program *programs = NULL; struct vidtv_psi_table_sdt_service *services = NULL; + struct vidtv_psi_desc_service_list_entry *service_list = NULL; m->si.pat = vidtv_psi_pat_table_init(m->transport_stream_id); @@ -258,6 +305,15 @@ void vidtv_channel_si_init(struct vidtv_mux *m) programs = vidtv_channel_pat_prog_cat_into_new(m); services = vidtv_channel_sdt_serv_cat_into_new(m); + /* look for a service descriptor for every service */ + service_list = vidtv_channel_build_service_list(services); + + /* use these descriptors to build the NIT */ + m->si.nit = vidtv_psi_nit_table_init(m->network_id, + m->transport_stream_id, + m->network_name, + service_list); + /* assemble all programs and assign to PAT */ vidtv_psi_pat_program_assign(m->si.pat, programs); @@ -269,6 +325,8 @@ void vidtv_channel_si_init(struct vidtv_mux *m) vidtv_channel_pmt_match_sections(m->channels, m->si.pmt_secs, m->si.pat->programs); + + vidtv_channel_destroy_service_list(service_list); } void vidtv_channel_si_destroy(struct vidtv_mux *m) @@ -283,6 +341,7 @@ void vidtv_channel_si_destroy(struct vidtv_mux *m) kfree(m->si.pmt_secs); vidtv_psi_sdt_table_destroy(m->si.sdt); + vidtv_psi_nit_table_destroy(m->si.nit); } void vidtv_channels_init(struct vidtv_mux *m) diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index 082740ae9d44..2a960e87c39c 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -74,6 +74,8 @@ static void vidtv_mux_pid_ctx_init(struct vidtv_mux *m) vidtv_mux_create_pid_ctx_once(m, VIDTV_PAT_PID); /* push the SDT pid ctx */ vidtv_mux_create_pid_ctx_once(m, VIDTV_SDT_PID); + /* push the NIT pid ctx */ + vidtv_mux_create_pid_ctx_once(m, VIDTV_NIT_PID); /* add a ctx for all PMT sections */ while (p) { @@ -117,10 +119,12 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) struct vidtv_mux_pid_ctx *pat_ctx; struct vidtv_mux_pid_ctx *pmt_ctx; struct vidtv_mux_pid_ctx *sdt_ctx; + struct vidtv_mux_pid_ctx *nit_ctx; struct vidtv_psi_pat_write_args pat_args = {}; struct vidtv_psi_pmt_write_args pmt_args = {}; struct vidtv_psi_sdt_write_args sdt_args = {}; + struct vidtv_psi_nit_write_args nit_args = {}; u32 nbytes; /* the number of bytes written by this function */ u16 pmt_pid; @@ -128,6 +132,7 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) pat_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_PAT_PID); sdt_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_SDT_PID); + nit_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_NIT_PID); pat_args.buf = m->mux_buf; pat_args.offset = m->mux_buf_offset; @@ -169,6 +174,14 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) m->mux_buf_offset += vidtv_psi_sdt_write_into(sdt_args); + nit_args.buf = m->mux_buf; + nit_args.offset = m->mux_buf_offset; + nit_args.nit = m->si.nit; + nit_args.buf_sz = m->mux_buf_sz; + nit_args.continuity_counter = &nit_ctx->cc; + + m->mux_buf_offset += vidtv_psi_nit_write_into(nit_args); + nbytes = m->mux_buf_offset - initial_offset; m->num_streamed_si++; @@ -446,6 +459,8 @@ struct vidtv_mux *vidtv_mux_init(struct dvb_frontend *fe, m->pcr_pid = args.pcr_pid; m->transport_stream_id = args.transport_stream_id; m->priv = args.priv; + m->network_id = args.network_id; + m->network_name = kstrdup(args.network_name, GFP_KERNEL); m->timing.current_jiffies = get_jiffies_64(); if (args.channels) @@ -469,6 +484,7 @@ void vidtv_mux_destroy(struct vidtv_mux *m) vidtv_mux_pid_ctx_destroy(m); vidtv_channel_si_destroy(m); vidtv_channels_destroy(m); + kfree(m->network_name); vfree(m->mux_buf); kfree(m); } diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.h b/drivers/media/test-drivers/vidtv/vidtv_mux.h index 2caa60623e97..5dfbe30c2ac8 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.h +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.h @@ -64,6 +64,7 @@ struct vidtv_mux_si { struct vidtv_psi_table_pat *pat; struct vidtv_psi_table_pmt **pmt_secs; /* the PMT sections */ struct vidtv_psi_table_sdt *sdt; + struct vidtv_psi_table_nit *nit; }; /** @@ -99,6 +100,8 @@ struct vidtv_mux_pid_ctx { * @pcr_pid: The TS PID used for the PSI packets. All channels will share the * same PCR. * @transport_stream_id: The transport stream ID + * @network_id: The network ID + * @network_name: The network name * @priv: Private data. */ struct vidtv_mux { @@ -128,6 +131,8 @@ struct vidtv_mux { u16 pcr_pid; u16 transport_stream_id; + u16 network_id; + char *network_name; void *priv; }; @@ -142,6 +147,8 @@ struct vidtv_mux { * same PCR. * @transport_stream_id: The transport stream ID * @channels: an optional list of channels to use + * @network_id: The network ID + * @network_name: The network name * @priv: Private data. */ struct vidtv_mux_init_args { @@ -153,6 +160,8 @@ struct vidtv_mux_init_args { u16 pcr_pid; u16 transport_stream_id; struct vidtv_channel *channels; + u16 network_id; + char *network_name; void *priv; }; diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index f2e25e68c085..0de6d646a483 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -6,10 +6,6 @@ * technically be broken into one or more sections, we do not do this here, * hence 'table' and 'section' are interchangeable for vidtv. * - * This code currently supports three tables: PAT, PMT and SDT. These are the - * bare minimum to get userspace to recognize our MPEG transport stream. It can - * be extended to support more PSI tables in the future. - * * Copyright (C) 2020 Daniel W. S. Almeida */ @@ -389,6 +385,75 @@ struct vidtv_psi_desc_registration return desc; } +struct vidtv_psi_desc_network_name +*vidtv_psi_network_name_desc_init(struct vidtv_psi_desc *head, char *network_name) +{ + struct vidtv_psi_desc_network_name *desc; + u32 network_name_len = network_name ? strlen(network_name) : 0; + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + + desc->type = NETWORK_NAME_DESCRIPTOR; + + desc->length = network_name_len; + + if (network_name && network_name_len) + desc->network_name = kstrdup(network_name, GFP_KERNEL); + + if (head) { + while (head->next) + head = head->next; + + head->next = (struct vidtv_psi_desc *)desc; + } + + return desc; +} + +struct vidtv_psi_desc_service_list +*vidtv_psi_service_list_desc_init(struct vidtv_psi_desc *head, + struct vidtv_psi_desc_service_list_entry *entry) +{ + struct vidtv_psi_desc_service_list *desc; + struct vidtv_psi_desc_service_list_entry *curr_e = NULL; + struct vidtv_psi_desc_service_list_entry *head_e = NULL; + struct vidtv_psi_desc_service_list_entry *prev_e = NULL; + u16 length = 0; + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + + desc->type = SERVICE_LIST_DESCRIPTOR; + + while (entry) { + curr_e = kzalloc(sizeof(*curr_e), GFP_KERNEL); + curr_e->service_id = entry->service_id; + curr_e->service_type = entry->service_type; + + length += sizeof(struct vidtv_psi_desc_service_list_entry) - + sizeof(struct vidtv_psi_desc_service_list_entry *); + + if (!head_e) + head_e = curr_e; + if (prev_e) + prev_e->next = curr_e; + + prev_e = curr_e; + entry = entry->next; + } + + desc->length = length; + desc->service_list = head_e; + + if (head) { + while (head->next) + head = head->next; + + head->next = (struct vidtv_psi_desc *)desc; + } + + return desc; +} + struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc) { struct vidtv_psi_desc *head = NULL; @@ -396,6 +461,8 @@ struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc) struct vidtv_psi_desc *curr = NULL; struct vidtv_psi_desc_service *service; + struct vidtv_psi_desc_network_name *desc_network_name; + struct vidtv_psi_desc_service_list *desc_service_list; while (desc) { switch (desc->type) { @@ -408,6 +475,20 @@ struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc) service->provider_name); break; + case NETWORK_NAME_DESCRIPTOR: + desc_network_name = (struct vidtv_psi_desc_network_name *)desc; + curr = (struct vidtv_psi_desc *) + vidtv_psi_network_name_desc_init(head, + desc_network_name->network_name); + break; + + case SERVICE_LIST_DESCRIPTOR: + desc_service_list = (struct vidtv_psi_desc_service_list *)desc; + curr = (struct vidtv_psi_desc *) + vidtv_psi_service_list_desc_init(head, + desc_service_list->service_list); + break; + case REGISTRATION_DESCRIPTOR: default: curr = kzalloc(sizeof(*desc) + desc->length, GFP_KERNEL); @@ -433,6 +514,8 @@ void vidtv_psi_desc_destroy(struct vidtv_psi_desc *desc) { struct vidtv_psi_desc *curr = desc; struct vidtv_psi_desc *tmp = NULL; + struct vidtv_psi_desc_service_list_entry *sl_entry = NULL; + struct vidtv_psi_desc_service_list_entry *sl_entry_tmp = NULL; while (curr) { tmp = curr; @@ -448,6 +531,19 @@ void vidtv_psi_desc_destroy(struct vidtv_psi_desc *desc) /* nothing to do */ break; + case NETWORK_NAME_DESCRIPTOR: + kfree(((struct vidtv_psi_desc_network_name *)tmp)->network_name); + break; + + case SERVICE_LIST_DESCRIPTOR: + sl_entry = ((struct vidtv_psi_desc_service_list *)tmp)->service_list; + while (sl_entry) { + sl_entry_tmp = sl_entry; + sl_entry = sl_entry->next; + kfree(sl_entry_tmp); + } + break; + default: pr_warn_ratelimited("Possible leak: not handling descriptor type %d\n", tmp->type); @@ -519,6 +615,7 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args args) /* the number of bytes written by this function */ u32 nbytes = 0; struct psi_write_args psi_args = {}; + struct vidtv_psi_desc_service_list_entry *serv_list_entry = NULL; psi_args.dest_buf = args.dest_buf; psi_args.from = &args.desc->type; @@ -564,6 +661,28 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args args) nbytes += vidtv_psi_ts_psi_write_into(psi_args); break; + case NETWORK_NAME_DESCRIPTOR: + psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.len = args.desc->length; + psi_args.from = ((struct vidtv_psi_desc_network_name *)args.desc)->network_name; + + nbytes += vidtv_psi_ts_psi_write_into(psi_args); + break; + + case SERVICE_LIST_DESCRIPTOR: + serv_list_entry = ((struct vidtv_psi_desc_service_list *)args.desc)->service_list; + while (serv_list_entry) { + psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.len = sizeof(struct vidtv_psi_desc_service_list_entry) - + sizeof(struct vidtv_psi_desc_service_list_entry *); + psi_args.from = serv_list_entry; + + nbytes += vidtv_psi_ts_psi_write_into(psi_args); + + serv_list_entry = serv_list_entry->next; + } + break; + case REGISTRATION_DESCRIPTOR: default: psi_args.dest_offset = args.dest_offset + nbytes; @@ -682,7 +801,6 @@ void vidtv_psi_sdt_table_update_sec_len(struct vidtv_psi_table_sdt *sdt) } length += CRC_SIZE_IN_BYTES; - vidtv_psi_set_sec_len(&sdt->header, length); } @@ -1321,3 +1439,220 @@ struct vidtv_psi_table_pmt return NULL; /* not found */ } + +static void vidtv_psi_nit_table_update_sec_len(struct vidtv_psi_table_nit *nit) +{ + u16 length = 0; + struct vidtv_psi_table_transport *t = nit->transport; + u16 desc_loop_len; + u16 transport_loop_len = 0; + + /* + * from immediately after 'section_length' until + * 'network_descriptor_length' + */ + length += NIT_LEN_UNTIL_NETWORK_DESCRIPTOR_LEN; + + desc_loop_len = vidtv_psi_desc_comp_loop_len(nit->descriptor); + vidtv_psi_set_desc_loop_len(&nit->bitfield, desc_loop_len, 12); + + length += desc_loop_len; + + length += sizeof_field(struct vidtv_psi_table_nit, bitfield2); + + while (t) { + /* skip both pointers at the end */ + transport_loop_len += sizeof(struct vidtv_psi_table_transport) - + sizeof(struct vidtv_psi_desc *) - + sizeof(struct vidtv_psi_table_transport *); + + length += transport_loop_len; + + desc_loop_len = vidtv_psi_desc_comp_loop_len(t->descriptor); + vidtv_psi_set_desc_loop_len(&t->bitfield, desc_loop_len, 12); + + length += desc_loop_len; + + t = t->next; + } + + // Actually sets the transport stream loop len, maybe rename this function later + vidtv_psi_set_desc_loop_len(&nit->bitfield2, transport_loop_len, 12); + length += CRC_SIZE_IN_BYTES; + + vidtv_psi_set_sec_len(&nit->header, length); +} + +struct vidtv_psi_table_nit +*vidtv_psi_nit_table_init(u16 network_id, + u16 transport_stream_id, + char *network_name, + struct vidtv_psi_desc_service_list_entry *service_list) +{ + struct vidtv_psi_table_nit *nit = kzalloc(sizeof(*nit), GFP_KERNEL); + struct vidtv_psi_table_transport *transport = kzalloc(sizeof(*transport), GFP_KERNEL); + + const u16 SYNTAX = 0x1; + const u16 ONE = 0x1; + const u16 ONES = 0x03; + + nit->header.table_id = 0x40; // ACTUAL_NETWORK + + nit->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ONE << 14) | (ONES << 12)); + + nit->header.id = cpu_to_be16(network_id); + nit->header.current_next = ONE; + + nit->header.version = 0x1f; + + nit->header.one2 = ONES; + nit->header.section_id = 0; + nit->header.last_section = 0; + + nit->bitfield = cpu_to_be16(0xf); + nit->bitfield2 = cpu_to_be16(0xf); + + nit->descriptor = (struct vidtv_psi_desc *) + vidtv_psi_network_name_desc_init(NULL, network_name); + + transport->transport_id = cpu_to_be16(transport_stream_id); + transport->network_id = cpu_to_be16(network_id); + transport->bitfield = cpu_to_be16(0xf); + transport->descriptor = (struct vidtv_psi_desc *) + vidtv_psi_service_list_desc_init(NULL, service_list); + + nit->transport = transport; + + vidtv_psi_nit_table_update_sec_len(nit); + + return nit; +} + +u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) +{ + /* the number of bytes written by this function */ + u32 nbytes = 0; + u32 crc = INITIAL_CRC; + + struct vidtv_psi_desc *table_descriptor = args.nit->descriptor; + struct vidtv_psi_table_transport *transport = args.nit->transport; + struct vidtv_psi_desc *transport_descriptor = (transport) ? + args.nit->transport->descriptor : + NULL; + + struct header_write_args h_args = {}; + struct psi_write_args psi_args = {}; + struct desc_write_args d_args = {}; + struct crc32_write_args c_args = {}; + + vidtv_psi_nit_table_update_sec_len(args.nit); + + h_args.dest_buf = args.buf; + h_args.dest_offset = args.offset; + h_args.h = &args.nit->header; + h_args.pid = VIDTV_NIT_PID; + h_args.continuity_counter = args.continuity_counter; + h_args.dest_buf_sz = args.buf_sz; + h_args.crc = &crc; + + nbytes += vidtv_psi_table_header_write_into(h_args); + + /* write the bitfield */ + psi_args.dest_buf = args.buf; + psi_args.from = &args.nit->bitfield; + psi_args.len = sizeof_field(struct vidtv_psi_table_nit, bitfield); + + psi_args.dest_offset = args.offset + nbytes; + psi_args.pid = VIDTV_NIT_PID; + psi_args.new_psi_section = false; + psi_args.continuity_counter = args.continuity_counter; + psi_args.is_crc = false; + psi_args.dest_buf_sz = args.buf_sz; + psi_args.crc = &crc; + + nbytes += vidtv_psi_ts_psi_write_into(psi_args); + + while (table_descriptor) { + /* write the descriptors, if any */ + d_args.dest_buf = args.buf; + d_args.dest_offset = args.offset + nbytes; + d_args.desc = table_descriptor; + d_args.pid = VIDTV_NIT_PID; + d_args.continuity_counter = args.continuity_counter; + d_args.dest_buf_sz = args.buf_sz; + d_args.crc = &crc; + + nbytes += vidtv_psi_desc_write_into(d_args); + + table_descriptor = table_descriptor->next; + } + + /* write the second bitfield */ + psi_args.dest_buf = args.buf; + psi_args.from = &args.nit->bitfield2; + psi_args.len = sizeof_field(struct vidtv_psi_table_nit, bitfield2); + psi_args.dest_offset = args.offset + nbytes; + psi_args.pid = VIDTV_NIT_PID; + + nbytes += vidtv_psi_ts_psi_write_into(psi_args); + + while (transport) { + /* write the transport sections, if any */ + psi_args.from = transport; + psi_args.len = sizeof_field(struct vidtv_psi_table_transport, transport_id) + + sizeof_field(struct vidtv_psi_table_transport, network_id) + + sizeof_field(struct vidtv_psi_table_transport, bitfield); + psi_args.dest_offset = args.offset + nbytes; + + nbytes += vidtv_psi_ts_psi_write_into(psi_args); + + while (transport_descriptor) { + /* write the transport descriptors, if any */ + d_args.dest_buf = args.buf; + d_args.dest_offset = args.offset + nbytes; + d_args.desc = transport_descriptor; + d_args.pid = VIDTV_NIT_PID; + d_args.continuity_counter = args.continuity_counter; + d_args.dest_buf_sz = args.buf_sz; + d_args.crc = &crc; + + nbytes += vidtv_psi_desc_write_into(d_args); + + transport_descriptor = transport_descriptor->next; + } + + transport = transport->next; + } + + c_args.dest_buf = args.buf; + c_args.dest_offset = args.offset + nbytes; + c_args.crc = cpu_to_be32(crc); + c_args.pid = VIDTV_NIT_PID; + c_args.continuity_counter = args.continuity_counter; + c_args.dest_buf_sz = args.buf_sz; + + /* Write the CRC32 at the end */ + nbytes += table_section_crc32_write_into(c_args); + + return nbytes; +} + +static void vidtv_psi_transport_destroy(struct vidtv_psi_table_transport *t) +{ + struct vidtv_psi_table_transport *curr_t = t; + struct vidtv_psi_table_transport *tmp_t = NULL; + + while (curr_t) { + tmp_t = curr_t; + curr_t = curr_t->next; + vidtv_psi_desc_destroy(tmp_t->descriptor); + kfree(tmp_t); + } +} + +void vidtv_psi_nit_table_destroy(struct vidtv_psi_table_nit *nit) +{ + vidtv_psi_desc_destroy(nit->descriptor); + vidtv_psi_transport_destroy(nit->transport); + kfree(nit); +} diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index 3f962cc78278..b5f2e6d7d1e8 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -6,10 +6,6 @@ * technically be broken into one or more sections, we do not do this here, * hence 'table' and 'section' are interchangeable for vidtv. * - * This code currently supports three tables: PAT, PMT and SDT. These are the - * bare minimum to get userspace to recognize our MPEG transport stream. It can - * be extended to support more PSI tables in the future. - * * Copyright (C) 2020 Daniel W. S. Almeida */ @@ -27,12 +23,16 @@ #define PAT_LEN_UNTIL_LAST_SECTION_NUMBER 5 #define PMT_LEN_UNTIL_PROGRAM_INFO_LENGTH 9 #define SDT_LEN_UNTIL_RESERVED_FOR_FUTURE_USE 8 +#define NIT_LEN_UNTIL_NETWORK_DESCRIPTOR_LEN 7 #define MAX_SECTION_LEN 1021 #define VIDTV_PAT_PID 0 /* mandated by the specs */ #define VIDTV_SDT_PID 0x0011 /* mandated by the specs */ +#define VIDTV_NIT_PID 0x0010 /* mandated by the specs */ enum vidtv_psi_descriptors { REGISTRATION_DESCRIPTOR = 0x05, /* See ISO/IEC 13818-1 section 2.6.8 */ + NETWORK_NAME_DESCRIPTOR = 0x40, /* See ETSI EN 300 468 section 6.2.27 */ + SERVICE_LIST_DESCRIPTOR = 0x41, /* See ETSI EN 300 468 section 6.2.35 */ SERVICE_DESCRIPTOR = 0x48, /* See ETSI EN 300 468 section 6.2.33 */ }; @@ -90,6 +90,34 @@ struct vidtv_psi_desc_registration { u8 additional_identification_info[]; } __packed; +/** + * struct vidtv_psi_desc_network_name - A network name descriptor + * see ETSI EN 300 468 v1.15.1 section 6.2.27 + */ +struct vidtv_psi_desc_network_name { + struct vidtv_psi_desc *next; + u8 type; + u8 length; + char *network_name; +} __packed; + +struct vidtv_psi_desc_service_list_entry { + __be16 service_id; + u8 service_type; + struct vidtv_psi_desc_service_list_entry *next; +} __packed; + +/** + * struct vidtv_psi_desc_service_list - A service list descriptor + * see ETSI EN 300 468 v1.15.1 section 6.2.35 + */ +struct vidtv_psi_desc_service_list { + struct vidtv_psi_desc *next; + u8 type; + u8 length; + struct vidtv_psi_desc_service_list_entry *service_list; +} __packed; + /** * struct vidtv_psi_table_header - A header that is present for all PSI tables. */ @@ -290,6 +318,13 @@ struct vidtv_psi_desc_registration u8 *additional_ident_info, u32 additional_info_len); +struct vidtv_psi_desc_network_name +*vidtv_psi_network_name_desc_init(struct vidtv_psi_desc *head, char *network_name); + +struct vidtv_psi_desc_service_list +*vidtv_psi_service_list_desc_init(struct vidtv_psi_desc *head, + struct vidtv_psi_desc_service_list_entry *entry); + struct vidtv_psi_table_pat_program *vidtv_psi_pat_program_init(struct vidtv_psi_table_pat_program *head, u16 service_id, @@ -574,4 +609,79 @@ struct vidtv_psi_table_pmt *vidtv_psi_find_pmt_sec(struct vidtv_psi_table_pmt ** u16 vidtv_psi_get_pat_program_pid(struct vidtv_psi_table_pat_program *p); u16 vidtv_psi_pmt_stream_get_elem_pid(struct vidtv_psi_table_pmt_stream *s); +/** + * struct vidtv_psi_table_transport - A entry in the TS loop for the NIT and/or other tables. + * See ETSI 300 468 section 5.2.1 + * @transport_id: The TS ID being described + * @network_id: The network_id that contains the TS ID + * @bitfield: Contains the descriptor loop length + * @descriptor: A descriptor loop + * @next: Pointer to the next entry + * + */ +struct vidtv_psi_table_transport { + __be16 transport_id; + __be16 network_id; + __be16 bitfield; /* desc_len: 12, reserved: 4 */ + struct vidtv_psi_desc *descriptor; + struct vidtv_psi_table_transport *next; +} __packed; + +/** + * struct vidtv_psi_table_nit - A Network Information Table (NIT). See ETSI 300 + * 468 section 5.2.1 + * @header: A PSI table header + * @bitfield: Contains the network descriptor length + * @descriptor: A descriptor loop describing the network + * @bitfield2: Contains the transport stream loop length + * @transport: The transport stream loop + * + */ +struct vidtv_psi_table_nit { + struct vidtv_psi_table_header header; + __be16 bitfield; /* network_desc_len: 12, reserved:4 */ + struct vidtv_psi_desc *descriptor; + __be16 bitfield2; /* ts_loop_len: 12, reserved: 4 */ + struct vidtv_psi_table_transport *transport; +} __packed; + +struct vidtv_psi_table_nit +*vidtv_psi_nit_table_init(u16 network_id, + u16 transport_stream_id, + char *network_name, + struct vidtv_psi_desc_service_list_entry *service_list); + +/** + * struct vidtv_psi_nit_write_args - Arguments for writing a NIT section + * @buf: The destination buffer. + * @offset: The offset into the destination buffer. + * @nit: A pointer to the NIT + * @buf_sz: The size of the destination buffer. + * @continuity_counter: A pointer to the CC. Incremented on every new packet. + * + */ +struct vidtv_psi_nit_write_args { + char *buf; + u32 offset; + struct vidtv_psi_table_nit *nit; + u32 buf_sz; + u8 *continuity_counter; +}; + +/** + * vidtv_psi_nit_write_into - Write NIT as MPEG-TS packets into a buffer. + * @args: an instance of struct vidtv_psi_nit_write_args + * + * This function writes the MPEG TS packets for a NIT table into a buffer. + * Calling code will usually generate the NIT via a call to its init function + * and thus is responsible for freeing it. + * + * Return: The number of bytes written into the buffer. This is NOT + * equal to the size of the NIT, since more space is needed for TS headers during TS + * encapsulation. + */ +u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args); + +void vidtv_psi_nit_table_destroy(struct vidtv_psi_table_nit *nit); + #endif // VIDTV_PSI_H -- cgit v1.2.3 From 7a7899f6f58e3270ccfd200ee63ebced5ddba3c9 Mon Sep 17 00:00:00 2001 From: "Daniel W. S. Almeida" Date: Sat, 31 Oct 2020 16:05:49 +0100 Subject: media: vidtv: psi: Implement an Event Information Table (EIT) Implement an Event Information Table (EIT) as per EN 300 468 5.2.4. The EIT provides information in chronological order regarding the events contained within each service. For now only present event information is supported. [mchehab+huawei@kernel.org: removed an extra blank line] Signed-off-by: Daniel W. S. Almeida Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Mauro Carvalho Chehab --- Documentation/driver-api/media/drivers/vidtv.rst | 8 +- drivers/media/test-drivers/vidtv/vidtv_channel.c | 71 ++++- drivers/media/test-drivers/vidtv/vidtv_channel.h | 3 + drivers/media/test-drivers/vidtv/vidtv_mux.c | 13 + drivers/media/test-drivers/vidtv/vidtv_mux.h | 2 + drivers/media/test-drivers/vidtv/vidtv_psi.c | 315 ++++++++++++++++++++++- drivers/media/test-drivers/vidtv/vidtv_psi.h | 120 ++++++++- 7 files changed, 523 insertions(+), 9 deletions(-) diff --git a/Documentation/driver-api/media/drivers/vidtv.rst b/Documentation/driver-api/media/drivers/vidtv.rst index 2d7ddf676b13..edaceef2808c 100644 --- a/Documentation/driver-api/media/drivers/vidtv.rst +++ b/Documentation/driver-api/media/drivers/vidtv.rst @@ -149,11 +149,11 @@ vidtv_psi.[ch] Because the generator is implemented in a separate file, it can be reused elsewhere in the media subsystem. - Currently vidtv supports working with 4 PSI tables: PAT, PMT, - SDT and NIT. + Currently vidtv supports working with 5 PSI tables: PAT, PMT, + SDT, NIT and EIT. The specification for PAT and PMT can be found in *ISO 13818-1: - Systems*, while the specification for the SDT, NIT can be found in *ETSI + Systems*, while the specification for the SDT, NIT, EIT can be found in *ETSI EN 300 468: Specification for Service Information (SI) in DVB systems*. @@ -197,6 +197,8 @@ vidtv_channel.[ch] #. Their programs will be concatenated to populate the PAT + #. Their events will be concatenated to populate the EIT + #. For each program in the PAT, a PMT section will be created #. The PMT section for a channel will be assigned its streams. diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index a246b49123d9..13e56544bb1e 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -9,6 +9,7 @@ * When vidtv boots, it will create some hardcoded channels. * Their services will be concatenated to populate the SDT. * Their programs will be concatenated to populate the PAT + * Their events will be concatenated to populate the EIT * For each program in the PAT, a PMT section will be created * The PMT section for a channel will be assigned its streams. * Every stream will have its corresponding encoder polled to produce TS packets @@ -59,13 +60,17 @@ struct vidtv_channel char *name = ENCODING_ISO8859_15 "Beethoven"; char *provider = ENCODING_ISO8859_15 "LinuxTV.org"; + char *iso_language_code = ENCODING_ISO8859_15 "eng"; + char *event_name = ENCODING_ISO8859_15 "Beethoven Music"; + char *event_text = ENCODING_ISO8859_15 "Beethoven's 5th Symphony"; + const u16 s302m_beethoven_event_id = 1; struct vidtv_channel *s302m = kzalloc(sizeof(*s302m), GFP_KERNEL); struct vidtv_s302m_encoder_init_args encoder_args = {}; s302m->name = kstrdup(name, GFP_KERNEL); - s302m->service = vidtv_psi_sdt_service_init(NULL, s302m_service_id); + s302m->service = vidtv_psi_sdt_service_init(NULL, s302m_service_id, false, true); s302m->service->descriptor = (struct vidtv_psi_desc *) vidtv_psi_service_desc_init(NULL, @@ -94,6 +99,13 @@ struct vidtv_channel s302m->encoders = vidtv_s302m_encoder_init(encoder_args); + s302m->events = vidtv_psi_eit_event_init(NULL, s302m_beethoven_event_id); + s302m->events->descriptor = (struct vidtv_psi_desc *) + vidtv_psi_short_event_desc_init(NULL, + iso_language_code, + event_name, + event_text); + if (head) { while (head->next) head = head->next; @@ -104,6 +116,48 @@ struct vidtv_channel return s302m; } +static struct vidtv_psi_table_eit_event +*vidtv_channel_eit_event_cat_into_new(struct vidtv_mux *m) +{ + /* Concatenate the events */ + const struct vidtv_channel *cur_chnl = m->channels; + + struct vidtv_psi_table_eit_event *curr = NULL; + struct vidtv_psi_table_eit_event *head = NULL; + struct vidtv_psi_table_eit_event *tail = NULL; + + struct vidtv_psi_desc *desc = NULL; + u16 event_id; + + if (!cur_chnl) + return NULL; + + while (cur_chnl) { + curr = cur_chnl->events; + + if (!curr) + dev_warn_ratelimited(m->dev, + "No events found for channel %s\n", cur_chnl->name); + + while (curr) { + event_id = be16_to_cpu(curr->event_id); + tail = vidtv_psi_eit_event_init(tail, event_id); + + desc = vidtv_psi_desc_clone(curr->descriptor); + vidtv_psi_desc_assign(&tail->descriptor, desc); + + if (!head) + head = tail; + + curr = curr->next; + } + + cur_chnl = cur_chnl->next; + } + + return head; +} + static struct vidtv_psi_table_sdt_service *vidtv_channel_sdt_serv_cat_into_new(struct vidtv_mux *m) { @@ -129,7 +183,10 @@ static struct vidtv_psi_table_sdt_service while (curr) { service_id = be16_to_cpu(curr->service_id); - tail = vidtv_psi_sdt_service_init(tail, service_id); + tail = vidtv_psi_sdt_service_init(tail, + service_id, + curr->EIT_schedule, + curr->EIT_present_following); desc = vidtv_psi_desc_clone(curr->descriptor); vidtv_psi_desc_assign(&tail->descriptor, desc); @@ -297,6 +354,7 @@ void vidtv_channel_si_init(struct vidtv_mux *m) struct vidtv_psi_table_pat_program *programs = NULL; struct vidtv_psi_table_sdt_service *services = NULL; struct vidtv_psi_desc_service_list_entry *service_list = NULL; + struct vidtv_psi_table_eit_event *events = NULL; m->si.pat = vidtv_psi_pat_table_init(m->transport_stream_id); @@ -305,6 +363,8 @@ void vidtv_channel_si_init(struct vidtv_mux *m) programs = vidtv_channel_pat_prog_cat_into_new(m); services = vidtv_channel_sdt_serv_cat_into_new(m); + events = vidtv_channel_eit_event_cat_into_new(m); + /* look for a service descriptor for every service */ service_list = vidtv_channel_build_service_list(services); @@ -314,12 +374,17 @@ void vidtv_channel_si_init(struct vidtv_mux *m) m->network_name, service_list); + m->si.eit = vidtv_psi_eit_table_init(m->network_id, m->transport_stream_id); + /* assemble all programs and assign to PAT */ vidtv_psi_pat_program_assign(m->si.pat, programs); /* assemble all services and assign to SDT */ vidtv_psi_sdt_service_assign(m->si.sdt, services); + /* assemble all events and assign to EIT */ + vidtv_psi_eit_event_assign(m->si.eit, events); + m->si.pmt_secs = vidtv_psi_pmt_create_sec_for_each_pat_entry(m->si.pat, m->pcr_pid); vidtv_channel_pmt_match_sections(m->channels, @@ -342,6 +407,7 @@ void vidtv_channel_si_destroy(struct vidtv_mux *m) kfree(m->si.pmt_secs); vidtv_psi_sdt_table_destroy(m->si.sdt); vidtv_psi_nit_table_destroy(m->si.nit); + vidtv_psi_eit_table_destroy(m->si.eit); } void vidtv_channels_init(struct vidtv_mux *m) @@ -361,6 +427,7 @@ void vidtv_channels_destroy(struct vidtv_mux *m) vidtv_psi_pat_program_destroy(curr->program); vidtv_psi_pmt_stream_destroy(curr->streams); vidtv_channel_encoder_destroy(curr->encoders); + vidtv_psi_eit_event_destroy(curr->events); tmp = curr; curr = curr->next; diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.h b/drivers/media/test-drivers/vidtv/vidtv_channel.h index 2c3cba4313b0..40ed7fcdc5a1 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.h +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.h @@ -9,6 +9,7 @@ * When vidtv boots, it will create some hardcoded channels. * Their services will be concatenated to populate the SDT. * Their programs will be concatenated to populate the PAT + * Their events will be concatenated to populate the EIT * For each program in the PAT, a PMT section will be created * The PMT section for a channel will be assigned its streams. * Every stream will have its corresponding encoder polled to produce TS packets @@ -44,6 +45,7 @@ * Will be concatenated into the PAT. * @streams: A stream loop used to populate the PMT section for 'program' * @encoders: A encoder loop. There must be one encoder for each stream. + * @events: Optional event information. This will feed into the EIT. * @next: Optionally chain this channel. */ struct vidtv_channel { @@ -54,6 +56,7 @@ struct vidtv_channel { struct vidtv_psi_table_pat_program *program; struct vidtv_psi_table_pmt_stream *streams; struct vidtv_encoder *encoders; + struct vidtv_psi_table_eit_event *events; struct vidtv_channel *next; }; diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index 2a960e87c39c..c3646dd269dd 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -76,6 +76,8 @@ static void vidtv_mux_pid_ctx_init(struct vidtv_mux *m) vidtv_mux_create_pid_ctx_once(m, VIDTV_SDT_PID); /* push the NIT pid ctx */ vidtv_mux_create_pid_ctx_once(m, VIDTV_NIT_PID); + /* push the EIT pid ctx */ + vidtv_mux_create_pid_ctx_once(m, VIDTV_EIT_PID); /* add a ctx for all PMT sections */ while (p) { @@ -120,11 +122,13 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) struct vidtv_mux_pid_ctx *pmt_ctx; struct vidtv_mux_pid_ctx *sdt_ctx; struct vidtv_mux_pid_ctx *nit_ctx; + struct vidtv_mux_pid_ctx *eit_ctx; struct vidtv_psi_pat_write_args pat_args = {}; struct vidtv_psi_pmt_write_args pmt_args = {}; struct vidtv_psi_sdt_write_args sdt_args = {}; struct vidtv_psi_nit_write_args nit_args = {}; + struct vidtv_psi_eit_write_args eit_args = {}; u32 nbytes; /* the number of bytes written by this function */ u16 pmt_pid; @@ -133,6 +137,7 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) pat_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_PAT_PID); sdt_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_SDT_PID); nit_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_NIT_PID); + eit_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_EIT_PID); pat_args.buf = m->mux_buf; pat_args.offset = m->mux_buf_offset; @@ -182,6 +187,14 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) m->mux_buf_offset += vidtv_psi_nit_write_into(nit_args); + eit_args.buf = m->mux_buf; + eit_args.offset = m->mux_buf_offset; + eit_args.eit = m->si.eit; + eit_args.buf_sz = m->mux_buf_sz; + eit_args.continuity_counter = &eit_ctx->cc; + + m->mux_buf_offset += vidtv_psi_eit_write_into(eit_args); + nbytes = m->mux_buf_offset - initial_offset; m->num_streamed_si++; diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.h b/drivers/media/test-drivers/vidtv/vidtv_mux.h index 5dfbe30c2ac8..6eeb09fbfe4d 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.h +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.h @@ -58,6 +58,7 @@ struct vidtv_mux_timing { * @pat: The PAT in use by the muxer. * @pmt_secs: The PMT sections in use by the muxer. One for each program in the PAT. * @sdt: The SDT in use by the muxer. + * @eit: the EIT in use by the muxer. */ struct vidtv_mux_si { /* the SI tables */ @@ -65,6 +66,7 @@ struct vidtv_mux_si { struct vidtv_psi_table_pmt **pmt_secs; /* the PMT sections */ struct vidtv_psi_table_sdt *sdt; struct vidtv_psi_table_nit *nit; + struct vidtv_psi_table_eit *eit; }; /** diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index 0de6d646a483..b0b476545d65 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -28,6 +28,7 @@ #define CRC_SIZE_IN_BYTES 4 #define MAX_VERSION_NUM 32 #define INITIAL_CRC 0xffffffff +#define ISO_LANGUAGE_CODE_LEN 3 static const u32 CRC_LUT[256] = { /* from libdvbv5 */ @@ -454,6 +455,51 @@ struct vidtv_psi_desc_service_list return desc; } +struct vidtv_psi_desc_short_event +*vidtv_psi_short_event_desc_init(struct vidtv_psi_desc *head, + char *iso_language_code, + char *event_name, + char *text) +{ + struct vidtv_psi_desc_short_event *desc; + u32 event_name_len = event_name ? strlen(event_name) : 0; + u32 text_len = text ? strlen(text) : 0; + u32 iso_len = iso_language_code ? strlen(iso_language_code) : 0; + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + + desc->type = SHORT_EVENT_DESCRIPTOR; + + desc->length = ISO_LANGUAGE_CODE_LEN + + sizeof_field(struct vidtv_psi_desc_short_event, event_name_len) + + event_name_len + + sizeof_field(struct vidtv_psi_desc_short_event, text_len) + + text_len; + + desc->event_name_len = event_name_len; + desc->text_len = text_len; + + if (iso_len != ISO_LANGUAGE_CODE_LEN) + iso_language_code = "eng"; + + desc->iso_language_code = kstrdup(iso_language_code, GFP_KERNEL); + + if (event_name && event_name_len) + desc->event_name = kstrdup(event_name, GFP_KERNEL); + + if (text && text_len) + desc->text = kstrdup(text, GFP_KERNEL); + + if (head) { + while (head->next) + head = head->next; + + head->next = (struct vidtv_psi_desc *)desc; + } + + return desc; +} + struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc) { struct vidtv_psi_desc *head = NULL; @@ -463,6 +509,7 @@ struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc) struct vidtv_psi_desc_service *service; struct vidtv_psi_desc_network_name *desc_network_name; struct vidtv_psi_desc_service_list *desc_service_list; + struct vidtv_psi_desc_short_event *desc_short_event; while (desc) { switch (desc->type) { @@ -489,6 +536,15 @@ struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc) desc_service_list->service_list); break; + case SHORT_EVENT_DESCRIPTOR: + desc_short_event = (struct vidtv_psi_desc_short_event *)desc; + curr = (struct vidtv_psi_desc *) + vidtv_psi_short_event_desc_init(head, + desc_short_event->iso_language_code, + desc_short_event->event_name, + desc_short_event->text); + break; + case REGISTRATION_DESCRIPTOR: default: curr = kzalloc(sizeof(*desc) + desc->length, GFP_KERNEL); @@ -544,6 +600,12 @@ void vidtv_psi_desc_destroy(struct vidtv_psi_desc *desc) } break; + case SHORT_EVENT_DESCRIPTOR: + kfree(((struct vidtv_psi_desc_short_event *)tmp)->iso_language_code); + kfree(((struct vidtv_psi_desc_short_event *)tmp)->event_name); + kfree(((struct vidtv_psi_desc_short_event *)tmp)->text); + break; + default: pr_warn_ratelimited("Possible leak: not handling descriptor type %d\n", tmp->type); @@ -683,6 +745,41 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args args) } break; + case SHORT_EVENT_DESCRIPTOR: + psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.len = ISO_LANGUAGE_CODE_LEN; + psi_args.from = ((struct vidtv_psi_desc_short_event *) + args.desc)->iso_language_code; + + nbytes += vidtv_psi_ts_psi_write_into(psi_args); + + psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.len = sizeof_field(struct vidtv_psi_desc_short_event, event_name_len); + psi_args.from = &((struct vidtv_psi_desc_short_event *) + args.desc)->event_name_len; + + nbytes += vidtv_psi_ts_psi_write_into(psi_args); + + psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.len = ((struct vidtv_psi_desc_short_event *)args.desc)->event_name_len; + psi_args.from = ((struct vidtv_psi_desc_short_event *)args.desc)->event_name; + + nbytes += vidtv_psi_ts_psi_write_into(psi_args); + + psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.len = sizeof_field(struct vidtv_psi_desc_short_event, text_len); + psi_args.from = &((struct vidtv_psi_desc_short_event *)args.desc)->text_len; + + nbytes += vidtv_psi_ts_psi_write_into(psi_args); + + psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.len = ((struct vidtv_psi_desc_short_event *)args.desc)->text_len; + psi_args.from = ((struct vidtv_psi_desc_short_event *)args.desc)->text; + + nbytes += vidtv_psi_ts_psi_write_into(psi_args); + + break; + case REGISTRATION_DESCRIPTOR: default: psi_args.dest_offset = args.dest_offset + nbytes; @@ -1334,7 +1431,9 @@ void vidtv_psi_sdt_table_destroy(struct vidtv_psi_table_sdt *sdt) struct vidtv_psi_table_sdt_service *vidtv_psi_sdt_service_init(struct vidtv_psi_table_sdt_service *head, - u16 service_id) + u16 service_id, + bool eit_schedule, + bool eit_present_following) { struct vidtv_psi_table_sdt_service *service; @@ -1347,8 +1446,8 @@ struct vidtv_psi_table_sdt_service * corresponding program_map_section */ service->service_id = cpu_to_be16(service_id); - service->EIT_schedule = 0x0; - service->EIT_present_following = 0x0; + service->EIT_schedule = eit_schedule; + service->EIT_present_following = eit_present_following; service->reserved = 0x3f; service->bitfield = cpu_to_be16(RUNNING << 13); @@ -1656,3 +1755,213 @@ void vidtv_psi_nit_table_destroy(struct vidtv_psi_table_nit *nit) vidtv_psi_transport_destroy(nit->transport); kfree(nit); } + +void vidtv_psi_eit_table_update_sec_len(struct vidtv_psi_table_eit *eit) +{ + u16 length = 0; + struct vidtv_psi_table_eit_event *e = eit->event; + u16 desc_loop_len; + + /* + * from immediately after 'section_length' until + * 'last_table_id' + */ + length += EIT_LEN_UNTIL_LAST_TABLE_ID; + + while (e) { + /* skip both pointers at the end */ + length += sizeof(struct vidtv_psi_table_eit_event) - + sizeof(struct vidtv_psi_desc *) - + sizeof(struct vidtv_psi_table_eit_event *); + + desc_loop_len = vidtv_psi_desc_comp_loop_len(e->descriptor); + vidtv_psi_set_desc_loop_len(&e->bitfield, desc_loop_len, 12); + + length += desc_loop_len; + + e = e->next; + } + + length += CRC_SIZE_IN_BYTES; + + vidtv_psi_set_sec_len(&eit->header, length); +} + +void vidtv_psi_eit_event_assign(struct vidtv_psi_table_eit *eit, + struct vidtv_psi_table_eit_event *e) +{ + if (e == eit->event) + return; + + eit->event = e; + vidtv_psi_eit_table_update_sec_len(eit); + + if (vidtv_psi_get_sec_len(&eit->header) > EIT_MAX_SECTION_LEN) + vidtv_psi_eit_event_assign(eit, NULL); + + vidtv_psi_update_version_num(&eit->header); +} + +struct vidtv_psi_table_eit +*vidtv_psi_eit_table_init(u16 network_id, + u16 transport_stream_id) +{ + struct vidtv_psi_table_eit *eit = kzalloc(sizeof(*eit), GFP_KERNEL); + + const u16 SYNTAX = 0x1; + const u16 ONE = 0x1; + const u16 ONES = 0x03; + + eit->header.table_id = 0x4e; //actual_transport_stream: present/following + + eit->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ONE << 14) | (ONES << 12)); + + eit->header.id = cpu_to_be16(network_id); + eit->header.current_next = ONE; + + eit->header.version = 0x1f; + + eit->header.one2 = ONES; + eit->header.section_id = 0; + eit->header.last_section = 0; + + eit->transport_id = cpu_to_be16(transport_stream_id); + eit->network_id = cpu_to_be16(network_id); + + eit->last_segment = eit->header.last_section; /* not implemented */ + eit->last_table_id = eit->header.table_id; /* not implemented */ + + vidtv_psi_eit_table_update_sec_len(eit); + + return eit; +} + +u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) +{ + u32 nbytes = 0; + u32 crc = INITIAL_CRC; + + struct vidtv_psi_table_eit_event *event = args.eit->event; + struct vidtv_psi_desc *event_descriptor = (args.eit->event) ? + args.eit->event->descriptor : + NULL; + + struct header_write_args h_args = {}; + struct psi_write_args psi_args = {}; + struct desc_write_args d_args = {}; + struct crc32_write_args c_args = {}; + + vidtv_psi_eit_table_update_sec_len(args.eit); + + h_args.dest_buf = args.buf; + h_args.dest_offset = args.offset; + h_args.h = &args.eit->header; + h_args.pid = VIDTV_EIT_PID; + h_args.continuity_counter = args.continuity_counter; + h_args.dest_buf_sz = args.buf_sz; + h_args.crc = &crc; + + nbytes += vidtv_psi_table_header_write_into(h_args); + + psi_args.dest_buf = args.buf; + psi_args.from = &args.eit->transport_id; + + psi_args.len = sizeof_field(struct vidtv_psi_table_eit, transport_id) + + sizeof_field(struct vidtv_psi_table_eit, network_id) + + sizeof_field(struct vidtv_psi_table_eit, last_segment) + + sizeof_field(struct vidtv_psi_table_eit, last_table_id); + + psi_args.dest_offset = args.offset + nbytes; + psi_args.pid = VIDTV_EIT_PID; + psi_args.new_psi_section = false; + psi_args.continuity_counter = args.continuity_counter; + psi_args.is_crc = false; + psi_args.dest_buf_sz = args.buf_sz; + psi_args.crc = &crc; + + nbytes += vidtv_psi_ts_psi_write_into(psi_args); + + while (event) { + /* copy the events, if any */ + psi_args.from = event; + /* skip both pointers at the end */ + psi_args.len = sizeof(struct vidtv_psi_table_eit_event) - + sizeof(struct vidtv_psi_desc *) - + sizeof(struct vidtv_psi_table_eit_event *); + psi_args.dest_offset = args.offset + nbytes; + + nbytes += vidtv_psi_ts_psi_write_into(psi_args); + + event_descriptor = event->descriptor; + + while (event_descriptor) { + /* copy the event descriptors, if any */ + d_args.dest_buf = args.buf; + d_args.dest_offset = args.offset + nbytes; + d_args.desc = event_descriptor; + d_args.pid = VIDTV_EIT_PID; + d_args.continuity_counter = args.continuity_counter; + d_args.dest_buf_sz = args.buf_sz; + d_args.crc = &crc; + + nbytes += vidtv_psi_desc_write_into(d_args); + + event_descriptor = event_descriptor->next; + } + + event = event->next; + } + + c_args.dest_buf = args.buf; + c_args.dest_offset = args.offset + nbytes; + c_args.crc = cpu_to_be32(crc); + c_args.pid = VIDTV_EIT_PID; + c_args.continuity_counter = args.continuity_counter; + c_args.dest_buf_sz = args.buf_sz; + + /* Write the CRC at the end */ + nbytes += table_section_crc32_write_into(c_args); + + return nbytes; +} + +struct vidtv_psi_table_eit_event +*vidtv_psi_eit_event_init(struct vidtv_psi_table_eit_event *head, u16 event_id) +{ + struct vidtv_psi_table_eit_event *e = kzalloc(sizeof(*e), GFP_KERNEL); + const u8 DURATION_ONE_HOUR[] = {1, 0, 0}; + + e->event_id = cpu_to_be16(event_id); + memset(e->start_time, 0xff, sizeof(e->start_time)); //todo: 0xff means 'unspecified' + memcpy(e->duration, DURATION_ONE_HOUR, sizeof(e->duration)); //todo, default to this for now + + e->bitfield = cpu_to_be16(RUNNING << 13); + + if (head) { + while (head->next) + head = head->next; + + head->next = e; + } + + return e; +} + +void vidtv_psi_eit_event_destroy(struct vidtv_psi_table_eit_event *e) +{ + struct vidtv_psi_table_eit_event *curr_e = e; + struct vidtv_psi_table_eit_event *tmp_e = NULL; + + while (curr_e) { + tmp_e = curr_e; + curr_e = curr_e->next; + vidtv_psi_desc_destroy(tmp_e->descriptor); + kfree(tmp_e); + } +} + +void vidtv_psi_eit_table_destroy(struct vidtv_psi_table_eit *eit) +{ + vidtv_psi_eit_event_destroy(eit->event); + kfree(eit); +} diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index b5f2e6d7d1e8..58efe54f7a5a 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -24,16 +24,20 @@ #define PMT_LEN_UNTIL_PROGRAM_INFO_LENGTH 9 #define SDT_LEN_UNTIL_RESERVED_FOR_FUTURE_USE 8 #define NIT_LEN_UNTIL_NETWORK_DESCRIPTOR_LEN 7 +#define EIT_LEN_UNTIL_LAST_TABLE_ID 11 #define MAX_SECTION_LEN 1021 +#define EIT_MAX_SECTION_LEN 4093 /* see ETSI 300 468 v.1.10.1 p. 26 */ #define VIDTV_PAT_PID 0 /* mandated by the specs */ #define VIDTV_SDT_PID 0x0011 /* mandated by the specs */ #define VIDTV_NIT_PID 0x0010 /* mandated by the specs */ +#define VIDTV_EIT_PID 0x0012 /*mandated by the specs */ enum vidtv_psi_descriptors { REGISTRATION_DESCRIPTOR = 0x05, /* See ISO/IEC 13818-1 section 2.6.8 */ NETWORK_NAME_DESCRIPTOR = 0x40, /* See ETSI EN 300 468 section 6.2.27 */ SERVICE_LIST_DESCRIPTOR = 0x41, /* See ETSI EN 300 468 section 6.2.35 */ SERVICE_DESCRIPTOR = 0x48, /* See ETSI EN 300 468 section 6.2.33 */ + SHORT_EVENT_DESCRIPTOR = 0x4d, /* See ETSI EN 300 468 section 6.2.37 */ }; enum vidtv_psi_stream_types { @@ -118,6 +122,27 @@ struct vidtv_psi_desc_service_list { struct vidtv_psi_desc_service_list_entry *service_list; } __packed; +/** + * struct vidtv_psi_desc_short_event - A short event descriptor + * see ETSI EN 300 468 v1.15.1 section 6.2.37 + */ +struct vidtv_psi_desc_short_event { + struct vidtv_psi_desc *next; + u8 type; + u8 length; + char *iso_language_code; + u8 event_name_len; + char *event_name; + u8 text_len; + char *text; +} __packed; + +struct vidtv_psi_desc_short_event +*vidtv_psi_short_event_desc_init(struct vidtv_psi_desc *head, + char *iso_language_code, + char *event_name, + char *text); + /** * struct vidtv_psi_table_header - A header that is present for all PSI tables. */ @@ -344,7 +369,9 @@ struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 transport_stream_id); struct vidtv_psi_table_sdt_service* vidtv_psi_sdt_service_init(struct vidtv_psi_table_sdt_service *head, - u16 service_id); + u16 service_id, + bool eit_schedule, + bool eit_present_following); void vidtv_psi_desc_destroy(struct vidtv_psi_desc *desc); @@ -684,4 +711,95 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args); void vidtv_psi_nit_table_destroy(struct vidtv_psi_table_nit *nit); +/** + * struct vidtv_psi_desc_short_event - A short event descriptor + * see ETSI EN 300 468 v1.15.1 section 6.2.37 + */ +struct vidtv_psi_table_eit_event { + __be16 event_id; + u8 start_time[5]; + u8 duration[3]; + __be16 bitfield; /* desc_length: 12, free_CA_mode: 1, running_status: 1 */ + struct vidtv_psi_desc *descriptor; + struct vidtv_psi_table_eit_event *next; +} __packed; + +/* + * struct vidtv_psi_table_eit - A Event Information Table (EIT) + * See ETSI 300 468 section 5.2.4 + */ +struct vidtv_psi_table_eit { + struct vidtv_psi_table_header header; + __be16 transport_id; + __be16 network_id; + u8 last_segment; + u8 last_table_id; + struct vidtv_psi_table_eit_event *event; +} __packed; + +struct vidtv_psi_table_eit +*vidtv_psi_eit_table_init(u16 network_id, + u16 transport_stream_id); + +/** + * struct vidtv_psi_eit_write_args - Arguments for writing an EIT section + * @buf: The destination buffer. + * @offset: The offset into the destination buffer. + * @nit: A pointer to the NIT + * @buf_sz: The size of the destination buffer. + * @continuity_counter: A pointer to the CC. Incremented on every new packet. + * + */ +struct vidtv_psi_eit_write_args { + char *buf; + u32 offset; + struct vidtv_psi_table_eit *eit; + u32 buf_sz; + u8 *continuity_counter; +}; + +/** + * vidtv_psi_eit_write_into - Write EIT as MPEG-TS packets into a buffer. + * @args: an instance of struct vidtv_psi_nit_write_args + * + * This function writes the MPEG TS packets for a EIT table into a buffer. + * Calling code will usually generate the EIT via a call to its init function + * and thus is responsible for freeing it. + * + * Return: The number of bytes written into the buffer. This is NOT + * equal to the size of the EIT, since more space is needed for TS headers during TS + * encapsulation. + */ +u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args); + +void vidtv_psi_eit_table_destroy(struct vidtv_psi_table_eit *eit); + +/** + * vidtv_psi_eit_table_update_sec_len - Recompute and update the EIT section length. + * @eit: The EIT whose length is to be updated. + * + * This will traverse the table and accumulate the length of its components, + * which is then used to replace the 'section_length' field. + * + * If section_length > EIT_MAX_SECTION_LEN, the operation fails. + */ +void vidtv_psi_eit_table_update_sec_len(struct vidtv_psi_table_eit *eit); + +/** + * vidtv_psi_eit_event_assign - Assigns the event loop to the EIT. + * @eit: The EIT to assign to. + * @e: The event loop + * + * This will free the previous event loop in the table. + * This will assign ownership of the stream loop to the table, i.e. the table + * will free this stream loop when a call to its destroy function is made. + */ +void vidtv_psi_eit_event_assign(struct vidtv_psi_table_eit *eit, + struct vidtv_psi_table_eit_event *e); + +struct vidtv_psi_table_eit_event +*vidtv_psi_eit_event_init(struct vidtv_psi_table_eit_event *head, u16 event_id); + +void vidtv_psi_eit_event_destroy(struct vidtv_psi_table_eit_event *e); + #endif // VIDTV_PSI_H -- cgit v1.2.3 From 84306c96b1c249d5eab6af9f86110a2d80b56010 Mon Sep 17 00:00:00 2001 From: "Daniel W. S. Almeida" Date: Sat, 31 Oct 2020 16:05:50 +0100 Subject: media: vidtv: psi: extract descriptor chaining code into a helper The code to append a descriptor to the end of a chain is repeated throughout the psi generator code. Extract it into its own helper function to avoid cluttering. Signed-off-by: Daniel W. S. Almeida Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_psi.c | 49 +++++++++------------------- 1 file changed, 15 insertions(+), 34 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index b0b476545d65..ad2957efa483 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -314,6 +314,16 @@ static u32 table_section_crc32_write_into(struct crc32_write_args args) return nbytes; } +static void vidtv_psi_desc_chain(struct vidtv_psi_desc *head, struct vidtv_psi_desc *desc) +{ + if (head) { + while (head->next) + head = head->next; + + head->next = desc; + } +} + struct vidtv_psi_desc_service *vidtv_psi_service_desc_init(struct vidtv_psi_desc *head, enum service_type service_type, char *service_name, @@ -345,12 +355,7 @@ struct vidtv_psi_desc_service *vidtv_psi_service_desc_init(struct vidtv_psi_desc if (provider_name && provider_name_len) desc->provider_name = kstrdup(provider_name, GFP_KERNEL); - if (head) { - while (head->next) - head = head->next; - - head->next = (struct vidtv_psi_desc *)desc; - } + vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc); return desc; } @@ -376,13 +381,7 @@ struct vidtv_psi_desc_registration additional_ident_info, additional_info_len); - if (head) { - while (head->next) - head = head->next; - - head->next = (struct vidtv_psi_desc *)desc; - } - + vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc); return desc; } @@ -401,13 +400,7 @@ struct vidtv_psi_desc_network_name if (network_name && network_name_len) desc->network_name = kstrdup(network_name, GFP_KERNEL); - if (head) { - while (head->next) - head = head->next; - - head->next = (struct vidtv_psi_desc *)desc; - } - + vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc); return desc; } @@ -445,13 +438,7 @@ struct vidtv_psi_desc_service_list desc->length = length; desc->service_list = head_e; - if (head) { - while (head->next) - head = head->next; - - head->next = (struct vidtv_psi_desc *)desc; - } - + vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc); return desc; } @@ -490,13 +477,7 @@ struct vidtv_psi_desc_short_event if (text && text_len) desc->text = kstrdup(text, GFP_KERNEL); - if (head) { - while (head->next) - head = head->next; - - head->next = (struct vidtv_psi_desc *)desc; - } - + vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc); return desc; } -- cgit v1.2.3 From 99b99d135ee3fd3a073556b5b646a69b1793f3a2 Mon Sep 17 00:00:00 2001 From: "Daniel W. S. Almeida" Date: Sat, 31 Oct 2020 16:05:51 +0100 Subject: media: vidtv: Move s302m specific fields into encoder context A few fields used only by the tone generator in the s302m encoder are stored in struct vidtv_encoder. Move them into struct vidtv_s302m_ctx instead. While we are at it: fix a checkpatch warning for long lines. Signed-off-by: Daniel W. S. Almeida Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_encoder.h | 3 --- drivers/media/test-drivers/vidtv/vidtv_s302m.c | 25 +++++++++++++----------- drivers/media/test-drivers/vidtv/vidtv_s302m.h | 3 +++ 3 files changed, 17 insertions(+), 14 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_encoder.h b/drivers/media/test-drivers/vidtv/vidtv_encoder.h index 65d81daef4c3..f742d566fbcb 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_encoder.h +++ b/drivers/media/test-drivers/vidtv/vidtv_encoder.h @@ -131,9 +131,6 @@ struct vidtv_encoder { u32 encoder_buf_offset; u64 sample_count; - int last_duration; - int note_offset; - enum musical_notes last_tone; struct vidtv_access_unit *access_units; diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.c b/drivers/media/test-drivers/vidtv/vidtv_s302m.c index a447ccbd68d5..aacf8110d874 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.c +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.c @@ -230,36 +230,38 @@ static u16 vidtv_s302m_get_sample(struct vidtv_encoder *e) { u16 sample; int pos; + struct vidtv_s302m_ctx *ctx = e->ctx; if (!e->src_buf) { /* * Simple tone generator: play the tones at the * beethoven_5th_symphony array. */ - if (e->last_duration <= 0) { + if (ctx->last_duration <= 0) { if (e->src_buf_offset >= ARRAY_SIZE(beethoven_5th_symphony)) e->src_buf_offset = 0; - e->last_tone = beethoven_5th_symphony[e->src_buf_offset].note; - e->last_duration = beethoven_5th_symphony[e->src_buf_offset].duration * S302M_SAMPLING_RATE_HZ / COMPASS / 5; + ctx->last_tone = beethoven_5th_symphony[e->src_buf_offset].note; + ctx->last_duration = beethoven_5th_symphony[e->src_buf_offset].duration * + S302M_SAMPLING_RATE_HZ / COMPASS / 5; e->src_buf_offset++; - e->note_offset = 0; + ctx->note_offset = 0; } else { - e->last_duration--; + ctx->last_duration--; } /* Handle silent */ - if (!e->last_tone) { + if (!ctx->last_tone) { e->src_buf_offset = 0; return 0x8000; } - pos = (2 * PI * e->note_offset * e->last_tone / S302M_SAMPLING_RATE_HZ); + pos = (2 * PI * ctx->note_offset * ctx->last_tone / S302M_SAMPLING_RATE_HZ); if (pos == 360) - e->note_offset = 0; + ctx->note_offset = 0; else - e->note_offset++; + ctx->note_offset++; return (fixp_sin32(pos % (2 * PI)) >> 16) + 0x8000; } @@ -442,6 +444,7 @@ struct vidtv_encoder { struct vidtv_encoder *e = kzalloc(sizeof(*e), GFP_KERNEL); u32 priv_sz = sizeof(struct vidtv_s302m_ctx); + struct vidtv_s302m_ctx *ctx = kzalloc(priv_sz, GFP_KERNEL); e->id = S302M; @@ -453,14 +456,14 @@ struct vidtv_encoder e->encoder_buf_offset = 0; e->sample_count = 0; - e->last_duration = 0; e->src_buf = (args.src_buf) ? args.src_buf : NULL; e->src_buf_sz = (args.src_buf) ? args.src_buf_sz : 0; e->src_buf_offset = 0; e->is_video_encoder = false; - e->ctx = kzalloc(priv_sz, GFP_KERNEL); + e->ctx = ctx; + ctx->last_duration = 0; e->encode = vidtv_s302m_encode; e->clear = vidtv_s302m_clear; diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.h b/drivers/media/test-drivers/vidtv/vidtv_s302m.h index eca5e3150ede..b1bbe521e766 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.h +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.h @@ -39,6 +39,9 @@ struct vidtv_s302m_ctx { struct vidtv_encoder *enc; u32 frame_index; u32 au_count; + int last_duration; + int note_offset; + enum musical_notes last_tone; }; /** -- cgit v1.2.3 From c2b6ca661ae209ea3eeb71ea38ef3fa7dca9c3c1 Mon Sep 17 00:00:00 2001 From: "Daniel W. S. Almeida" Date: Sat, 31 Oct 2020 16:05:52 +0100 Subject: media: vidtv: psi: fix missing assignments in while loops Some variables were only assigned once but were used in while loops as if they had been updated at every iteration. Fix this. Signed-off-by: Daniel W. S. Almeida Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_psi.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index ad2957efa483..4dda5b0004a3 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -1175,9 +1175,7 @@ u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) struct vidtv_psi_desc *table_descriptor = args.pmt->descriptor; struct vidtv_psi_table_pmt_stream *stream = args.pmt->stream; - struct vidtv_psi_desc *stream_descriptor = (stream) ? - args.pmt->stream->descriptor : - NULL; + struct vidtv_psi_desc *stream_descriptor; struct header_write_args h_args = {}; struct psi_write_args psi_args = {}; @@ -1237,6 +1235,8 @@ u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) nbytes += vidtv_psi_ts_psi_write_into(psi_args); + stream_descriptor = stream->descriptor; + while (stream_descriptor) { /* write the stream descriptors, if any */ d_args.dest_buf = args.buf; @@ -1324,9 +1324,7 @@ u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) u32 crc = INITIAL_CRC; struct vidtv_psi_table_sdt_service *service = args.sdt->service; - struct vidtv_psi_desc *service_desc = (args.sdt->service) ? - args.sdt->service->descriptor : - NULL; + struct vidtv_psi_desc *service_desc; struct header_write_args h_args = {}; struct psi_write_args psi_args = {}; @@ -1373,6 +1371,8 @@ u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) nbytes += vidtv_psi_ts_psi_write_into(psi_args); + service_desc = service->descriptor; + while (service_desc) { /* copy the service descriptors, if any */ d_args.dest_buf = args.buf; @@ -1616,9 +1616,7 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) struct vidtv_psi_desc *table_descriptor = args.nit->descriptor; struct vidtv_psi_table_transport *transport = args.nit->transport; - struct vidtv_psi_desc *transport_descriptor = (transport) ? - args.nit->transport->descriptor : - NULL; + struct vidtv_psi_desc *transport_descriptor; struct header_write_args h_args = {}; struct psi_write_args psi_args = {}; @@ -1686,6 +1684,8 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) nbytes += vidtv_psi_ts_psi_write_into(psi_args); + transport_descriptor = transport->descriptor; + while (transport_descriptor) { /* write the transport descriptors, if any */ d_args.dest_buf = args.buf; @@ -1823,9 +1823,7 @@ u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) u32 crc = INITIAL_CRC; struct vidtv_psi_table_eit_event *event = args.eit->event; - struct vidtv_psi_desc *event_descriptor = (args.eit->event) ? - args.eit->event->descriptor : - NULL; + struct vidtv_psi_desc *event_descriptor; struct header_write_args h_args = {}; struct psi_write_args psi_args = {}; -- cgit v1.2.3 From 8922e3931dd79055bb3f851bed33f069fc67a2fc Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 21 Sep 2020 14:19:08 +0200 Subject: media: vidtv: reorganize includes - Place the includes on alphabetical order; - get rid of asm/byteorder.h; - add bug.h at vidtv_s302m.c, as it is needed by inux/fixp-arith.h Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_bridge.c | 8 ++++---- drivers/media/test-drivers/vidtv/vidtv_bridge.h | 2 ++ drivers/media/test-drivers/vidtv/vidtv_channel.c | 8 ++++---- drivers/media/test-drivers/vidtv/vidtv_channel.h | 3 ++- drivers/media/test-drivers/vidtv/vidtv_demod.c | 1 + drivers/media/test-drivers/vidtv/vidtv_demod.h | 1 + drivers/media/test-drivers/vidtv/vidtv_mux.c | 18 +++++++++--------- drivers/media/test-drivers/vidtv/vidtv_mux.h | 3 ++- drivers/media/test-drivers/vidtv/vidtv_pes.c | 1 - drivers/media/test-drivers/vidtv/vidtv_pes.h | 1 - drivers/media/test-drivers/vidtv/vidtv_psi.c | 11 +++++------ drivers/media/test-drivers/vidtv/vidtv_psi.h | 1 - drivers/media/test-drivers/vidtv/vidtv_s302m.c | 21 ++++++++++----------- drivers/media/test-drivers/vidtv/vidtv_s302m.h | 1 - drivers/media/test-drivers/vidtv/vidtv_ts.c | 5 ++--- drivers/media/test-drivers/vidtv/vidtv_ts.h | 1 - drivers/media/test-drivers/vidtv/vidtv_tuner.c | 5 +++-- drivers/media/test-drivers/vidtv/vidtv_tuner.h | 1 + 18 files changed, 46 insertions(+), 46 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_bridge.c b/drivers/media/test-drivers/vidtv/vidtv_bridge.c index 2f97ecf423ed..068fb4e9fafe 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_bridge.c +++ b/drivers/media/test-drivers/vidtv/vidtv_bridge.c @@ -9,20 +9,20 @@ * Copyright (C) 2020 Daniel W. S. Almeida */ +#include #include #include #include -#include #include #include #include #include "vidtv_bridge.h" +#include "vidtv_common.h" #include "vidtv_demod.h" -#include "vidtv_tuner.h" -#include "vidtv_ts.h" #include "vidtv_mux.h" -#include "vidtv_common.h" +#include "vidtv_ts.h" +#include "vidtv_tuner.h" //#define MUX_BUF_MAX_SZ //#define MUX_BUF_MIN_SZ diff --git a/drivers/media/test-drivers/vidtv/vidtv_bridge.h b/drivers/media/test-drivers/vidtv/vidtv_bridge.h index 78fe8472fa37..a85068bffd0f 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_bridge.h +++ b/drivers/media/test-drivers/vidtv/vidtv_bridge.h @@ -20,9 +20,11 @@ #include #include #include + #include #include #include + #include "vidtv_mux.h" /** diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index 13e56544bb1e..683da9014064 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -19,16 +19,16 @@ * Copyright (C) 2020 Daniel W. S. Almeida */ -#include -#include #include #include +#include +#include #include "vidtv_channel.h" -#include "vidtv_psi.h" +#include "vidtv_common.h" #include "vidtv_encoder.h" #include "vidtv_mux.h" -#include "vidtv_common.h" +#include "vidtv_psi.h" #include "vidtv_s302m.h" static void vidtv_channel_encoder_destroy(struct vidtv_encoder *e) diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.h b/drivers/media/test-drivers/vidtv/vidtv_channel.h index 40ed7fcdc5a1..e1ba638ab77f 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.h +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.h @@ -23,9 +23,10 @@ #define VIDTV_CHANNEL_H #include -#include "vidtv_psi.h" + #include "vidtv_encoder.h" #include "vidtv_mux.h" +#include "vidtv_psi.h" /** * struct vidtv_channel - A 'channel' abstraction diff --git a/drivers/media/test-drivers/vidtv/vidtv_demod.c b/drivers/media/test-drivers/vidtv/vidtv_demod.c index eba7fe1a1b48..63ac55b81f39 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_demod.c +++ b/drivers/media/test-drivers/vidtv/vidtv_demod.c @@ -19,6 +19,7 @@ #include #include #include + #include #include "vidtv_demod.h" diff --git a/drivers/media/test-drivers/vidtv/vidtv_demod.h b/drivers/media/test-drivers/vidtv/vidtv_demod.h index 87651b0193e6..ab84044f33ba 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_demod.h +++ b/drivers/media/test-drivers/vidtv/vidtv_demod.h @@ -12,6 +12,7 @@ #define VIDTV_DEMOD_H #include + #include /** diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index c3646dd269dd..465c5a6a3bc8 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -12,23 +12,23 @@ * Copyright (C) 2020 Daniel W. S. Almeida */ -#include -#include +#include +#include #include #include -#include +#include #include -#include +#include +#include #include -#include -#include "vidtv_mux.h" -#include "vidtv_ts.h" -#include "vidtv_pes.h" -#include "vidtv_encoder.h" #include "vidtv_channel.h" #include "vidtv_common.h" +#include "vidtv_encoder.h" +#include "vidtv_mux.h" +#include "vidtv_pes.h" #include "vidtv_psi.h" +#include "vidtv_ts.h" static struct vidtv_mux_pid_ctx *vidtv_mux_get_pid_ctx(struct vidtv_mux *m, u16 pid) diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.h b/drivers/media/test-drivers/vidtv/vidtv_mux.h index 6eeb09fbfe4d..005b707f1445 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.h +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.h @@ -15,9 +15,10 @@ #ifndef VIDTV_MUX_H #define VIDTV_MUX_H -#include #include +#include #include + #include #include "vidtv_psi.h" diff --git a/drivers/media/test-drivers/vidtv/vidtv_pes.c b/drivers/media/test-drivers/vidtv/vidtv_pes.c index 1c75f88070e9..102352d398ed 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_pes.c +++ b/drivers/media/test-drivers/vidtv/vidtv_pes.c @@ -16,7 +16,6 @@ #include #include #include -#include #include "vidtv_pes.h" #include "vidtv_common.h" diff --git a/drivers/media/test-drivers/vidtv/vidtv_pes.h b/drivers/media/test-drivers/vidtv/vidtv_pes.h index 0ea9e863024d..a152693233a9 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_pes.h +++ b/drivers/media/test-drivers/vidtv/vidtv_pes.h @@ -14,7 +14,6 @@ #ifndef VIDTV_PES_H #define VIDTV_PES_H -#include #include #include "vidtv_common.h" diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index 4dda5b0004a3..f4f6b90633db 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -11,18 +11,17 @@ #define pr_fmt(fmt) KBUILD_MODNAME ":%s, %d: " fmt, __func__, __LINE__ -#include -#include -#include #include -#include +#include #include #include +#include +#include #include -#include +#include -#include "vidtv_psi.h" #include "vidtv_common.h" +#include "vidtv_psi.h" #include "vidtv_ts.h" #define CRC_SIZE_IN_BYTES 4 diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index 58efe54f7a5a..4fcb2c0615bb 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -13,7 +13,6 @@ #define VIDTV_PSI_H #include -#include /* * all section lengths start immediately after the 'section_length' field diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.c b/drivers/media/test-drivers/vidtv/vidtv_s302m.c index aacf8110d874..ec88af63a74e 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.c +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.c @@ -17,23 +17,22 @@ #define pr_fmt(fmt) KBUILD_MODNAME ":%s, %d: " fmt, __func__, __LINE__ -#include -#include +#include #include -#include -#include -#include +#include #include +#include +#include #include #include -#include - -#include -#include +#include +#include +#include +#include -#include "vidtv_s302m.h" -#include "vidtv_encoder.h" #include "vidtv_common.h" +#include "vidtv_encoder.h" +#include "vidtv_s302m.h" #define S302M_SAMPLING_RATE_HZ 48000 #define PES_PRIVATE_STREAM_1 0xbd /* PES: private_stream_1 */ diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.h b/drivers/media/test-drivers/vidtv/vidtv_s302m.h index b1bbe521e766..a0101734e758 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.h +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.h @@ -19,7 +19,6 @@ #define VIDTV_S302M_H #include -#include #include "vidtv_encoder.h" diff --git a/drivers/media/test-drivers/vidtv/vidtv_ts.c b/drivers/media/test-drivers/vidtv/vidtv_ts.c index 190b9e4438dc..ca4bb9c40b78 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_ts.c +++ b/drivers/media/test-drivers/vidtv/vidtv_ts.c @@ -9,14 +9,13 @@ #define pr_fmt(fmt) KBUILD_MODNAME ":%s, %d: " fmt, __func__, __LINE__ +#include #include #include #include -#include -#include -#include "vidtv_ts.h" #include "vidtv_common.h" +#include "vidtv_ts.h" static u32 vidtv_ts_write_pcr_bits(u8 *to, u32 to_offset, u64 pcr) { diff --git a/drivers/media/test-drivers/vidtv/vidtv_ts.h b/drivers/media/test-drivers/vidtv/vidtv_ts.h index 83dcc9183b45..6b989a2c1433 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_ts.h +++ b/drivers/media/test-drivers/vidtv/vidtv_ts.h @@ -11,7 +11,6 @@ #define VIDTV_TS_H #include -#include #define TS_SYNC_BYTE 0x47 #define TS_PACKET_LEN 188 diff --git a/drivers/media/test-drivers/vidtv/vidtv_tuner.c b/drivers/media/test-drivers/vidtv/vidtv_tuner.c index 9bc49e099f65..14b6bc902ee1 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_tuner.c +++ b/drivers/media/test-drivers/vidtv/vidtv_tuner.c @@ -13,11 +13,12 @@ #include #include #include +#include +#include #include #include + #include -#include -#include #include "vidtv_tuner.h" diff --git a/drivers/media/test-drivers/vidtv/vidtv_tuner.h b/drivers/media/test-drivers/vidtv/vidtv_tuner.h index 8455b2d564b3..fd55346a5c87 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_tuner.h +++ b/drivers/media/test-drivers/vidtv/vidtv_tuner.h @@ -11,6 +11,7 @@ #define VIDTV_TUNER_H #include + #include #define NUM_VALID_TUNER_FREQS 8 -- cgit v1.2.3 From 3be8037960bccd13052cfdeba8805ad785041d70 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 21 Sep 2020 15:11:50 +0200 Subject: media: vidtv: add error checks Currently, there are not checks if something gets bad during memory allocation: it will simply use NULL pointers and crash. Add error path at the logic which allocates memory for the MPEG-TS generator code, propagating the errors up to the vidtv_bridge. Now, if something wents bad, start_streaming will return an error that userspace can detect: ERROR DMX_SET_PES_FILTER failed (PID = 0x2000): 12 Cannot allocate memory and the driver doesn't crash. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_bridge.c | 2 + drivers/media/test-drivers/vidtv/vidtv_channel.c | 137 ++++++++++++++++++++--- drivers/media/test-drivers/vidtv/vidtv_channel.h | 4 +- drivers/media/test-drivers/vidtv/vidtv_mux.c | 85 +++++++++----- drivers/media/test-drivers/vidtv/vidtv_psi.c | 109 ++++++++++++++---- drivers/media/test-drivers/vidtv/vidtv_s302m.c | 19 +++- 6 files changed, 289 insertions(+), 67 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_bridge.c b/drivers/media/test-drivers/vidtv/vidtv_bridge.c index 068fb4e9fafe..e846aaab2c44 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_bridge.c +++ b/drivers/media/test-drivers/vidtv/vidtv_bridge.c @@ -185,6 +185,8 @@ static int vidtv_start_streaming(struct vidtv_dvb *dvb) dvb->streaming = true; dvb->mux = vidtv_mux_init(dvb->fe[0], dev, mux_args); + if (!dvb->mux) + return -ENOMEM; vidtv_mux_start_thread(dvb->mux); dev_dbg_ratelimited(dev, "Started streaming\n"); diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index 683da9014064..ddfeecd381e6 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -57,54 +57,75 @@ struct vidtv_channel const u16 s302m_program_pid = 0x101; /* packet id for PMT*/ const u16 s302m_es_pid = 0x111; /* packet id for the ES */ const __be32 s302m_fid = cpu_to_be32(VIDTV_S302M_FORMAT_IDENTIFIER); - char *name = ENCODING_ISO8859_15 "Beethoven"; char *provider = ENCODING_ISO8859_15 "LinuxTV.org"; char *iso_language_code = ENCODING_ISO8859_15 "eng"; char *event_name = ENCODING_ISO8859_15 "Beethoven Music"; char *event_text = ENCODING_ISO8859_15 "Beethoven's 5th Symphony"; const u16 s302m_beethoven_event_id = 1; - - struct vidtv_channel *s302m = kzalloc(sizeof(*s302m), GFP_KERNEL); + struct vidtv_channel *s302m; struct vidtv_s302m_encoder_init_args encoder_args = {}; + s302m = kzalloc(sizeof(*s302m), GFP_KERNEL); + if (!s302m) + return NULL; + s302m->name = kstrdup(name, GFP_KERNEL); + if (!s302m->name) + goto free_s302m; s302m->service = vidtv_psi_sdt_service_init(NULL, s302m_service_id, false, true); + if (!s302m->service) + goto free_name; s302m->service->descriptor = (struct vidtv_psi_desc *) vidtv_psi_service_desc_init(NULL, DIGITAL_TELEVISION_SERVICE, name, provider); + if (!s302m->service->descriptor) + goto free_service; s302m->transport_stream_id = transport_stream_id; s302m->program = vidtv_psi_pat_program_init(NULL, s302m_service_id, s302m_program_pid); + if (!s302m->program) + goto free_service; s302m->program_num = s302m_program_num; s302m->streams = vidtv_psi_pmt_stream_init(NULL, STREAM_PRIVATE_DATA, s302m_es_pid); + if (!s302m->streams) + goto free_program; s302m->streams->descriptor = (struct vidtv_psi_desc *) vidtv_psi_registration_desc_init(NULL, s302m_fid, NULL, 0); + if (!s302m->streams->descriptor) + goto free_streams; + encoder_args.es_pid = s302m_es_pid; s302m->encoders = vidtv_s302m_encoder_init(encoder_args); + if (!s302m->encoders) + goto free_streams; s302m->events = vidtv_psi_eit_event_init(NULL, s302m_beethoven_event_id); + if (!s302m->events) + goto free_encoders; s302m->events->descriptor = (struct vidtv_psi_desc *) vidtv_psi_short_event_desc_init(NULL, iso_language_code, event_name, event_text); + if (!s302m->events->descriptor) + goto free_events; if (head) { while (head->next) @@ -114,6 +135,23 @@ struct vidtv_channel } return s302m; + +free_events: + vidtv_psi_eit_event_destroy(s302m->events); +free_encoders: + vidtv_s302m_encoder_destroy(s302m->encoders); +free_streams: + vidtv_psi_pmt_stream_destroy(s302m->streams); +free_program: + vidtv_psi_pat_program_destroy(s302m->program); +free_service: + vidtv_psi_sdt_service_destroy(s302m->service); +free_name: + kfree(s302m->name); +free_s302m: + kfree(s302m); + + return NULL; } static struct vidtv_psi_table_eit_event @@ -142,6 +180,10 @@ static struct vidtv_psi_table_eit_event while (curr) { event_id = be16_to_cpu(curr->event_id); tail = vidtv_psi_eit_event_init(tail, event_id); + if (!tail) { + vidtv_psi_eit_event_destroy(head); + return NULL; + } desc = vidtv_psi_desc_clone(curr->descriptor); vidtv_psi_desc_assign(&tail->descriptor, desc); @@ -187,8 +229,12 @@ static struct vidtv_psi_table_sdt_service service_id, curr->EIT_schedule, curr->EIT_present_following); + if (!tail) + goto free; desc = vidtv_psi_desc_clone(curr->descriptor); + if (!desc) + goto free_tail; vidtv_psi_desc_assign(&tail->descriptor, desc); if (!head) @@ -201,6 +247,12 @@ static struct vidtv_psi_table_sdt_service } return head; + +free_tail: + vidtv_psi_sdt_service_destroy(tail); +free: + vidtv_psi_sdt_service_destroy(head); + return NULL; } static struct vidtv_psi_table_pat_program* @@ -231,6 +283,10 @@ vidtv_channel_pat_prog_cat_into_new(struct vidtv_mux *m) tail = vidtv_psi_pat_program_init(tail, serv_id, pid); + if (!tail) { + vidtv_psi_pat_program_destroy(head); + return NULL; + } if (!head) head = tail; @@ -303,6 +359,17 @@ vidtv_channel_pmt_match_sections(struct vidtv_channel *channels, } } +static void vidtv_channel_destroy_service_list(struct vidtv_psi_desc_service_list_entry *e) +{ + struct vidtv_psi_desc_service_list_entry *tmp; + + while (e) { + tmp = e; + e = e->next; + kfree(tmp); + } +} + static struct vidtv_psi_desc_service_list_entry *vidtv_channel_build_service_list(struct vidtv_psi_table_sdt_service *s) { @@ -320,6 +387,11 @@ static struct vidtv_psi_desc_service_list_entry s_desc = (struct vidtv_psi_desc_service *)desc; curr_e = kzalloc(sizeof(*curr_e), GFP_KERNEL); + if (!curr_e) { + vidtv_channel_destroy_service_list(head_e); + return NULL; + } + curr_e->service_id = s->service_id; curr_e->service_type = s_desc->service_type; @@ -338,18 +410,7 @@ next_desc: return head_e; } -static void vidtv_channel_destroy_service_list(struct vidtv_psi_desc_service_list_entry *e) -{ - struct vidtv_psi_desc_service_list_entry *tmp; - - while (e) { - tmp = e; - e = e->next; - kfree(tmp); - } -} - -void vidtv_channel_si_init(struct vidtv_mux *m) +int vidtv_channel_si_init(struct vidtv_mux *m) { struct vidtv_psi_table_pat_program *programs = NULL; struct vidtv_psi_table_sdt_service *services = NULL; @@ -357,24 +418,41 @@ void vidtv_channel_si_init(struct vidtv_mux *m) struct vidtv_psi_table_eit_event *events = NULL; m->si.pat = vidtv_psi_pat_table_init(m->transport_stream_id); + if (!m->si.pat) + return -ENOMEM; m->si.sdt = vidtv_psi_sdt_table_init(m->transport_stream_id); + if (!m->si.sdt) + goto free_pat; programs = vidtv_channel_pat_prog_cat_into_new(m); + if (!programs) + goto free_sdt; services = vidtv_channel_sdt_serv_cat_into_new(m); + if (!services) + goto free_programs; events = vidtv_channel_eit_event_cat_into_new(m); + if (!events) + goto free_services; /* look for a service descriptor for every service */ service_list = vidtv_channel_build_service_list(services); + if (!service_list) + goto free_events; /* use these descriptors to build the NIT */ m->si.nit = vidtv_psi_nit_table_init(m->network_id, m->transport_stream_id, m->network_name, service_list); + if (!m->si.nit) + goto free_service_list; m->si.eit = vidtv_psi_eit_table_init(m->network_id, m->transport_stream_id); + if (!m->si.eit) + goto free_nit; + /* assemble all programs and assign to PAT */ vidtv_psi_pat_program_assign(m->si.pat, programs); @@ -386,12 +464,34 @@ void vidtv_channel_si_init(struct vidtv_mux *m) vidtv_psi_eit_event_assign(m->si.eit, events); m->si.pmt_secs = vidtv_psi_pmt_create_sec_for_each_pat_entry(m->si.pat, m->pcr_pid); + if (!m->si.pmt_secs) + goto free_eit; vidtv_channel_pmt_match_sections(m->channels, m->si.pmt_secs, m->si.pat->programs); vidtv_channel_destroy_service_list(service_list); + + return 0; + +free_eit: + vidtv_psi_eit_table_destroy(m->si.eit); +free_nit: + vidtv_psi_nit_table_destroy(m->si.nit); +free_service_list: + vidtv_channel_destroy_service_list(service_list); +free_events: + vidtv_psi_eit_event_destroy(events); +free_services: + vidtv_psi_sdt_service_destroy(services); +free_programs: + vidtv_psi_pat_program_destroy(programs); +free_sdt: + vidtv_psi_sdt_table_destroy(m->si.sdt); +free_pat: + vidtv_psi_pat_table_destroy(m->si.pat); + return 0; } void vidtv_channel_si_destroy(struct vidtv_mux *m) @@ -410,10 +510,15 @@ void vidtv_channel_si_destroy(struct vidtv_mux *m) vidtv_psi_eit_table_destroy(m->si.eit); } -void vidtv_channels_init(struct vidtv_mux *m) +int vidtv_channels_init(struct vidtv_mux *m) { /* this is the place to add new 'channels' for vidtv */ m->channels = vidtv_channel_s302m_init(NULL, m->transport_stream_id); + + if (!m->channels) + return -ENOMEM; + + return 0; } void vidtv_channels_destroy(struct vidtv_mux *m) diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.h b/drivers/media/test-drivers/vidtv/vidtv_channel.h index e1ba638ab77f..4bc2a4c0980d 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.h +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.h @@ -65,14 +65,14 @@ struct vidtv_channel { * vidtv_channel_si_init - Init the PSI tables from the channels in the mux * @m: The mux containing the channels. */ -void vidtv_channel_si_init(struct vidtv_mux *m); +int vidtv_channel_si_init(struct vidtv_mux *m); void vidtv_channel_si_destroy(struct vidtv_mux *m); /** * vidtv_channels_init - Init hardcoded, fake 'channels'. * @m: The mux to store the channels into. */ -void vidtv_channels_init(struct vidtv_mux *m); +int vidtv_channels_init(struct vidtv_mux *m); struct vidtv_channel *vidtv_channel_s302m_init(struct vidtv_channel *head, u16 transport_stream_id); void vidtv_channels_destroy(struct vidtv_mux *m); diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index 465c5a6a3bc8..bba3f2315531 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -47,37 +47,56 @@ static struct vidtv_mux_pid_ctx struct vidtv_mux_pid_ctx *ctx; ctx = vidtv_mux_get_pid_ctx(m, pid); - if (ctx) - goto end; + return ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return NULL; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); ctx->pid = pid; ctx->cc = 0; hash_add(m->pid_ctx, &ctx->h, pid); -end: return ctx; } -static void vidtv_mux_pid_ctx_init(struct vidtv_mux *m) +static void vidtv_mux_pid_ctx_destroy(struct vidtv_mux *m) +{ + int bkt; + struct vidtv_mux_pid_ctx *ctx; + struct hlist_node *tmp; + + hash_for_each_safe(m->pid_ctx, bkt, tmp, ctx, h) { + hash_del(&ctx->h); + kfree(ctx); + } +} + +static int vidtv_mux_pid_ctx_init(struct vidtv_mux *m) { struct vidtv_psi_table_pat_program *p = m->si.pat->program; u16 pid; hash_init(m->pid_ctx); /* push the pcr pid ctx */ - vidtv_mux_create_pid_ctx_once(m, m->pcr_pid); - /* push the null packet pid ctx */ - vidtv_mux_create_pid_ctx_once(m, TS_NULL_PACKET_PID); + if (!vidtv_mux_create_pid_ctx_once(m, m->pcr_pid)) + return -ENOMEM; + /* push the NULL packet pid ctx */ + if (!vidtv_mux_create_pid_ctx_once(m, TS_NULL_PACKET_PID)) + goto free; /* push the PAT pid ctx */ - vidtv_mux_create_pid_ctx_once(m, VIDTV_PAT_PID); + if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_PAT_PID)) + goto free; /* push the SDT pid ctx */ - vidtv_mux_create_pid_ctx_once(m, VIDTV_SDT_PID); + if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_SDT_PID)) + goto free; /* push the NIT pid ctx */ - vidtv_mux_create_pid_ctx_once(m, VIDTV_NIT_PID); + if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_NIT_PID)) + goto free; /* push the EIT pid ctx */ - vidtv_mux_create_pid_ctx_once(m, VIDTV_EIT_PID); + if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_EIT_PID)) + goto free; /* add a ctx for all PMT sections */ while (p) { @@ -85,18 +104,12 @@ static void vidtv_mux_pid_ctx_init(struct vidtv_mux *m) vidtv_mux_create_pid_ctx_once(m, pid); p = p->next; } -} -static void vidtv_mux_pid_ctx_destroy(struct vidtv_mux *m) -{ - int bkt; - struct vidtv_mux_pid_ctx *ctx; - struct hlist_node *tmp; + return 0; - hash_for_each_safe(m->pid_ctx, bkt, tmp, ctx, h) { - hash_del(&ctx->h); - kfree(ctx); - } +free: + vidtv_mux_pid_ctx_destroy(m); + return -ENOMEM; } static void vidtv_mux_update_clk(struct vidtv_mux *m) @@ -455,7 +468,11 @@ struct vidtv_mux *vidtv_mux_init(struct dvb_frontend *fe, struct device *dev, struct vidtv_mux_init_args args) { - struct vidtv_mux *m = kzalloc(sizeof(*m), GFP_KERNEL); + struct vidtv_mux *m; + + m = kzalloc(sizeof(*m), GFP_KERNEL); + if (!m) + return NULL; m->dev = dev; m->fe = fe; @@ -467,6 +484,9 @@ struct vidtv_mux *vidtv_mux_init(struct dvb_frontend *fe, m->on_new_packets_available_cb = args.on_new_packets_available_cb; m->mux_buf = vzalloc(args.mux_buf_sz); + if (!m->mux_buf) + goto free_mux; + m->mux_buf_sz = args.mux_buf_sz; m->pcr_pid = args.pcr_pid; @@ -479,16 +499,29 @@ struct vidtv_mux *vidtv_mux_init(struct dvb_frontend *fe, if (args.channels) m->channels = args.channels; else - vidtv_channels_init(m); + if (vidtv_channels_init(m) < 0) + goto free_mux_buf; /* will alloc data for pmt_sections after initializing pat */ - vidtv_channel_si_init(m); + if (vidtv_channel_si_init(m) < 0) + goto free_channels; INIT_WORK(&m->mpeg_thread, vidtv_mux_tick); - vidtv_mux_pid_ctx_init(m); + if (vidtv_mux_pid_ctx_init(m) < 0) + goto free_channel_si; return m; + +free_channel_si: + vidtv_channel_si_destroy(m); +free_channels: + vidtv_channels_destroy(m); +free_mux_buf: + vfree(m->mux_buf); +free_mux: + kfree(m); + return NULL; } void vidtv_mux_destroy(struct vidtv_mux *m) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index f4f6b90633db..f7caa96c0ee8 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -333,6 +333,8 @@ struct vidtv_psi_desc_service *vidtv_psi_service_desc_init(struct vidtv_psi_desc u32 provider_name_len = provider_name ? strlen(provider_name) : 0; desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + return NULL; desc->type = SERVICE_DESCRIPTOR; @@ -367,6 +369,8 @@ struct vidtv_psi_desc_registration struct vidtv_psi_desc_registration *desc; desc = kzalloc(sizeof(*desc) + sizeof(format_id) + additional_info_len, GFP_KERNEL); + if (!desc) + return NULL; desc->type = REGISTRATION_DESCRIPTOR; @@ -391,6 +395,8 @@ struct vidtv_psi_desc_network_name u32 network_name_len = network_name ? strlen(network_name) : 0; desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + return NULL; desc->type = NETWORK_NAME_DESCRIPTOR; @@ -414,11 +420,23 @@ struct vidtv_psi_desc_service_list u16 length = 0; desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + return NULL; desc->type = SERVICE_LIST_DESCRIPTOR; while (entry) { curr_e = kzalloc(sizeof(*curr_e), GFP_KERNEL); + if (!curr_e) { + while (head_e) { + curr_e = head_e; + head_e = head_e->next; + kfree(curr_e); + } + kfree(desc); + return NULL; + } + curr_e->service_id = entry->service_id; curr_e->service_type = entry->service_type; @@ -453,6 +471,8 @@ struct vidtv_psi_desc_short_event u32 iso_len = iso_language_code ? strlen(iso_language_code) : 0; desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + return NULL; desc->type = SHORT_EVENT_DESCRIPTOR; @@ -496,10 +516,10 @@ struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc) case SERVICE_DESCRIPTOR: service = (struct vidtv_psi_desc_service *)desc; curr = (struct vidtv_psi_desc *) - vidtv_psi_service_desc_init(head, - service->service_type, - service->service_name, - service->provider_name); + vidtv_psi_service_desc_init(head, + service->service_type, + service->service_name, + service->provider_name); break; case NETWORK_NAME_DESCRIPTOR: @@ -512,8 +532,8 @@ struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc) case SERVICE_LIST_DESCRIPTOR: desc_service_list = (struct vidtv_psi_desc_service_list *)desc; curr = (struct vidtv_psi_desc *) - vidtv_psi_service_list_desc_init(head, - desc_service_list->service_list); + vidtv_psi_service_list_desc_init(head, + desc_service_list->service_list); break; case SHORT_EVENT_DESCRIPTOR: @@ -528,12 +548,15 @@ struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc) case REGISTRATION_DESCRIPTOR: default: curr = kzalloc(sizeof(*desc) + desc->length, GFP_KERNEL); + if (!curr) + return NULL; memcpy(curr, desc, sizeof(*desc) + desc->length); - break; - } + } + + if (!curr) + return NULL; - if (curr) - curr->next = NULL; + curr->next = NULL; if (!head) head = curr; if (prev) @@ -890,6 +913,8 @@ vidtv_psi_pat_program_init(struct vidtv_psi_table_pat_program *head, const u16 RESERVED = 0x07; program = kzalloc(sizeof(*program), GFP_KERNEL); + if (!program) + return NULL; program->service_id = cpu_to_be16(service_id); @@ -951,11 +976,15 @@ vidtv_psi_pat_program_assign(struct vidtv_psi_table_pat *pat, struct vidtv_psi_table_pat *vidtv_psi_pat_table_init(u16 transport_stream_id) { - struct vidtv_psi_table_pat *pat = kzalloc(sizeof(*pat), GFP_KERNEL); + struct vidtv_psi_table_pat *pat; const u16 SYNTAX = 0x1; const u16 ZERO = 0x0; const u16 ONES = 0x03; + pat = kzalloc(sizeof(*pat), GFP_KERNEL); + if (!pat) + return NULL; + pat->header.table_id = 0x0; pat->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ZERO << 14) | (ONES << 12)); @@ -1055,6 +1084,8 @@ vidtv_psi_pmt_stream_init(struct vidtv_psi_table_pmt_stream *head, u16 desc_loop_len; stream = kzalloc(sizeof(*stream), GFP_KERNEL); + if (!stream) + return NULL; stream->type = stream_type; @@ -1129,7 +1160,7 @@ u16 vidtv_psi_pmt_get_pid(struct vidtv_psi_table_pmt *section, struct vidtv_psi_table_pmt *vidtv_psi_pmt_table_init(u16 program_number, u16 pcr_pid) { - struct vidtv_psi_table_pmt *pmt = kzalloc(sizeof(*pmt), GFP_KERNEL); + struct vidtv_psi_table_pmt *pmt; const u16 SYNTAX = 0x1; const u16 ZERO = 0x0; const u16 ONES = 0x03; @@ -1137,6 +1168,10 @@ struct vidtv_psi_table_pmt *vidtv_psi_pmt_table_init(u16 program_number, const u16 RESERVED2 = 0x0f; u16 desc_loop_len; + pmt = kzalloc(sizeof(*pmt), GFP_KERNEL); + if (!pmt) + return NULL; + if (!pcr_pid) pcr_pid = 0x1fff; @@ -1276,14 +1311,17 @@ void vidtv_psi_pmt_table_destroy(struct vidtv_psi_table_pmt *pmt) struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 transport_stream_id) { - struct vidtv_psi_table_sdt *sdt = kzalloc(sizeof(*sdt), GFP_KERNEL); + struct vidtv_psi_table_sdt *sdt; const u16 SYNTAX = 0x1; const u16 ONE = 0x1; const u16 ONES = 0x03; const u16 RESERVED = 0xff; - sdt->header.table_id = 0x42; + sdt = kzalloc(sizeof(*sdt), GFP_KERNEL); + if (!sdt) + return NULL; + sdt->header.table_id = 0x42; sdt->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ONE << 14) | (ONES << 12)); /* @@ -1418,6 +1456,8 @@ struct vidtv_psi_table_sdt_service struct vidtv_psi_table_sdt_service *service; service = kzalloc(sizeof(*service), GFP_KERNEL); + if (!service) + return NULL; /* * ETSI 300 468: this is a 16bit field which serves as a label to @@ -1491,6 +1531,8 @@ vidtv_psi_pmt_create_sec_for_each_pat_entry(struct vidtv_psi_table_pat *pat, u16 pmt_secs = kcalloc(pat->programs, sizeof(struct vidtv_psi_table_pmt *), GFP_KERNEL); + if (!pmt_secs) + return NULL; while (program) { pmt_secs[i] = vidtv_psi_pmt_table_init(be16_to_cpu(program->service_id), pcr_pid); @@ -1568,13 +1610,20 @@ struct vidtv_psi_table_nit char *network_name, struct vidtv_psi_desc_service_list_entry *service_list) { - struct vidtv_psi_table_nit *nit = kzalloc(sizeof(*nit), GFP_KERNEL); - struct vidtv_psi_table_transport *transport = kzalloc(sizeof(*transport), GFP_KERNEL); - + struct vidtv_psi_table_nit *nit; + struct vidtv_psi_table_transport *transport; const u16 SYNTAX = 0x1; const u16 ONE = 0x1; const u16 ONES = 0x03; + nit = kzalloc(sizeof(*nit), GFP_KERNEL); + if (!nit) + return NULL; + + transport = kzalloc(sizeof(*transport), GFP_KERNEL); + if (!transport) + goto free_nit; + nit->header.table_id = 0x40; // ACTUAL_NETWORK nit->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ONE << 14) | (ONES << 12)); @@ -1593,18 +1642,31 @@ struct vidtv_psi_table_nit nit->descriptor = (struct vidtv_psi_desc *) vidtv_psi_network_name_desc_init(NULL, network_name); + if (!nit->descriptor) + goto free_transport; transport->transport_id = cpu_to_be16(transport_stream_id); transport->network_id = cpu_to_be16(network_id); transport->bitfield = cpu_to_be16(0xf); transport->descriptor = (struct vidtv_psi_desc *) vidtv_psi_service_list_desc_init(NULL, service_list); + if (!transport->descriptor) + goto free_nit_desc; nit->transport = transport; vidtv_psi_nit_table_update_sec_len(nit); return nit; + +free_nit_desc: + vidtv_psi_desc_destroy((struct vidtv_psi_desc *)nit->descriptor); + +free_transport: + kfree(transport); +free_nit: + kfree(nit); + return NULL; } u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) @@ -1786,12 +1848,15 @@ struct vidtv_psi_table_eit *vidtv_psi_eit_table_init(u16 network_id, u16 transport_stream_id) { - struct vidtv_psi_table_eit *eit = kzalloc(sizeof(*eit), GFP_KERNEL); - + struct vidtv_psi_table_eit *eit; const u16 SYNTAX = 0x1; const u16 ONE = 0x1; const u16 ONES = 0x03; + eit = kzalloc(sizeof(*eit), GFP_KERNEL); + if (!eit) + return NULL; + eit->header.table_id = 0x4e; //actual_transport_stream: present/following eit->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ONE << 14) | (ONES << 12)); @@ -1906,9 +1971,13 @@ u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) struct vidtv_psi_table_eit_event *vidtv_psi_eit_event_init(struct vidtv_psi_table_eit_event *head, u16 event_id) { - struct vidtv_psi_table_eit_event *e = kzalloc(sizeof(*e), GFP_KERNEL); + struct vidtv_psi_table_eit_event *e; const u8 DURATION_ONE_HOUR[] = {1, 0, 0}; + e = kzalloc(sizeof(*e), GFP_KERNEL); + if (!e) + return NULL; + e->event_id = cpu_to_be16(event_id); memset(e->start_time, 0xff, sizeof(e->start_time)); //todo: 0xff means 'unspecified' memcpy(e->duration, DURATION_ONE_HOUR, sizeof(e->duration)); //todo, default to this for now diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.c b/drivers/media/test-drivers/vidtv/vidtv_s302m.c index ec88af63a74e..146e4e9d361b 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.c +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.c @@ -144,7 +144,11 @@ static const struct tone_duration beethoven_5th_symphony[] = { static struct vidtv_access_unit *vidtv_s302m_access_unit_init(struct vidtv_access_unit *head) { - struct vidtv_access_unit *au = kzalloc(sizeof(*au), GFP_KERNEL); + struct vidtv_access_unit *au; + + au = kzalloc(sizeof(*au), GFP_KERNEL); + if (!au) + return NULL; if (head) { while (head->next) @@ -441,9 +445,13 @@ static u32 vidtv_s302m_clear(struct vidtv_encoder *e) struct vidtv_encoder *vidtv_s302m_encoder_init(struct vidtv_s302m_encoder_init_args args) { - struct vidtv_encoder *e = kzalloc(sizeof(*e), GFP_KERNEL); + struct vidtv_encoder *e; u32 priv_sz = sizeof(struct vidtv_s302m_ctx); - struct vidtv_s302m_ctx *ctx = kzalloc(priv_sz, GFP_KERNEL); + struct vidtv_s302m_ctx *ctx; + + e = kzalloc(sizeof(*e), GFP_KERNEL); + if (!e) + return NULL; e->id = S302M; @@ -461,6 +469,11 @@ struct vidtv_encoder e->src_buf_offset = 0; e->is_video_encoder = false; + + ctx = kzalloc(priv_sz, GFP_KERNEL); + if (!ctx) + return NULL; + e->ctx = ctx; ctx->last_duration = 0; -- cgit v1.2.3 From 31e82355a14ede525b96e1f300acebb29052915f Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 17 Nov 2020 17:38:36 +0100 Subject: media: vidtv: don't use recursive functions The Linux stack is too short. So, using recursive functions is a very bad idea. Convert those into non-recursive ones. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_psi.c | 75 +++++++++++++++------------- 1 file changed, 41 insertions(+), 34 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index f7caa96c0ee8..b31a29f46bde 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -951,25 +951,29 @@ vidtv_psi_pat_program_assign(struct vidtv_psi_table_pat *pat, { /* This function transfers ownership of p to the table */ - u16 program_count = 0; - struct vidtv_psi_table_pat_program *program = p; + u16 program_count; + struct vidtv_psi_table_pat_program *program; - if (p == pat->program) - return; + do { + program_count = 0; + program = p; - while (program) { - ++program_count; - program = program->next; - } + if (p == pat->program) + return; + + while (program) { + ++program_count; + program = program->next; + } - pat->programs = program_count; - pat->program = p; + pat->programs = program_count; + pat->program = p; - /* Recompute section length */ - vidtv_psi_pat_table_update_sec_len(pat); + /* Recompute section length */ + vidtv_psi_pat_table_update_sec_len(pat); - if (vidtv_psi_get_sec_len(&pat->header) > MAX_SECTION_LEN) - vidtv_psi_pat_program_assign(pat, NULL); + p = NULL; + } while (vidtv_psi_get_sec_len(&pat->header) > MAX_SECTION_LEN); vidtv_psi_update_version_num(&pat->header); } @@ -1124,15 +1128,16 @@ void vidtv_psi_pmt_stream_destroy(struct vidtv_psi_table_pmt_stream *s) void vidtv_psi_pmt_stream_assign(struct vidtv_psi_table_pmt *pmt, struct vidtv_psi_table_pmt_stream *s) { - /* This function transfers ownership of s to the table */ - if (s == pmt->stream) - return; + do { + /* This function transfers ownership of s to the table */ + if (s == pmt->stream) + return; - pmt->stream = s; - vidtv_psi_pmt_table_update_sec_len(pmt); + pmt->stream = s; + vidtv_psi_pmt_table_update_sec_len(pmt); - if (vidtv_psi_get_sec_len(&pmt->header) > MAX_SECTION_LEN) - vidtv_psi_pmt_stream_assign(pmt, NULL); + s = NULL; + } while (vidtv_psi_get_sec_len(&pmt->header) > MAX_SECTION_LEN); vidtv_psi_update_version_num(&pmt->header); } @@ -1500,16 +1505,17 @@ void vidtv_psi_sdt_service_assign(struct vidtv_psi_table_sdt *sdt, struct vidtv_psi_table_sdt_service *service) { - if (service == sdt->service) - return; + do { + if (service == sdt->service) + return; - sdt->service = service; + sdt->service = service; - /* recompute section length */ - vidtv_psi_sdt_table_update_sec_len(sdt); + /* recompute section length */ + vidtv_psi_sdt_table_update_sec_len(sdt); - if (vidtv_psi_get_sec_len(&sdt->header) > MAX_SECTION_LEN) - vidtv_psi_sdt_service_assign(sdt, NULL); + service = NULL; + } while (vidtv_psi_get_sec_len(&sdt->header) > MAX_SECTION_LEN); vidtv_psi_update_version_num(&sdt->header); } @@ -1832,14 +1838,15 @@ void vidtv_psi_eit_table_update_sec_len(struct vidtv_psi_table_eit *eit) void vidtv_psi_eit_event_assign(struct vidtv_psi_table_eit *eit, struct vidtv_psi_table_eit_event *e) { - if (e == eit->event) - return; + do { + if (e == eit->event) + return; - eit->event = e; - vidtv_psi_eit_table_update_sec_len(eit); + eit->event = e; + vidtv_psi_eit_table_update_sec_len(eit); - if (vidtv_psi_get_sec_len(&eit->header) > EIT_MAX_SECTION_LEN) - vidtv_psi_eit_event_assign(eit, NULL); + e = NULL; + } while (vidtv_psi_get_sec_len(&eit->header) > EIT_MAX_SECTION_LEN); vidtv_psi_update_version_num(&eit->header); } -- cgit v1.2.3 From af66e03edd4d46c7c37f6360dab3ed5953f36943 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 19 Nov 2020 09:41:22 +0100 Subject: media: vidtv: fix the name of the program MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While the original plan was to use the first movement of the 5th Symphony, it was opted to use the Für Elise song, instead. Fix it. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_channel.c | 2 +- drivers/media/test-drivers/vidtv/vidtv_s302m.c | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index ddfeecd381e6..f64a68dea234 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -61,7 +61,7 @@ struct vidtv_channel char *provider = ENCODING_ISO8859_15 "LinuxTV.org"; char *iso_language_code = ENCODING_ISO8859_15 "eng"; char *event_name = ENCODING_ISO8859_15 "Beethoven Music"; - char *event_text = ENCODING_ISO8859_15 "Beethoven's 5th Symphony"; + char *event_text = ENCODING_ISO8859_15 "Beethoven's Für Elise"; const u16 s302m_beethoven_event_id = 1; struct vidtv_channel *s302m; struct vidtv_s302m_encoder_init_args encoder_args = {}; diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.c b/drivers/media/test-drivers/vidtv/vidtv_s302m.c index 146e4e9d361b..cbf89530aafe 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.c +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.c @@ -79,7 +79,7 @@ struct tone_duration { }; #define COMPASS 120 /* beats per minute (Allegro) */ -static const struct tone_duration beethoven_5th_symphony[] = { +static const struct tone_duration beethoven_fur_elise[] = { { NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_B_5, 128}, { NOTE_D_6, 128}, { NOTE_C_6, 128}, { NOTE_A_3, 128}, @@ -238,14 +238,14 @@ static u16 vidtv_s302m_get_sample(struct vidtv_encoder *e) if (!e->src_buf) { /* * Simple tone generator: play the tones at the - * beethoven_5th_symphony array. + * beethoven_fur_elise array. */ if (ctx->last_duration <= 0) { - if (e->src_buf_offset >= ARRAY_SIZE(beethoven_5th_symphony)) + if (e->src_buf_offset >= ARRAY_SIZE(beethoven_fur_elise)) e->src_buf_offset = 0; - ctx->last_tone = beethoven_5th_symphony[e->src_buf_offset].note; - ctx->last_duration = beethoven_5th_symphony[e->src_buf_offset].duration * + ctx->last_tone = beethoven_fur_elise[e->src_buf_offset].note; + ctx->last_duration = beethoven_fur_elise[e->src_buf_offset].duration * S302M_SAMPLING_RATE_HZ / COMPASS / 5; e->src_buf_offset++; ctx->note_offset = 0; -- cgit v1.2.3 From ab6bad0a4db69009fb7b2a50b8929b2bcaf7824d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 19 Nov 2020 11:20:46 +0100 Subject: media: vidtv: fix the tone generator logic The tone generator logic were repeating the song after the first silent. There's also a wrong logic at the note offset calculus, which may create some noise. Fix it. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_s302m.c | 14 ++++---------- drivers/media/test-drivers/vidtv/vidtv_s302m.h | 2 +- 2 files changed, 5 insertions(+), 11 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.c b/drivers/media/test-drivers/vidtv/vidtv_s302m.c index cbf89530aafe..fdb3d649c516 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.c +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.c @@ -253,18 +253,12 @@ static u16 vidtv_s302m_get_sample(struct vidtv_encoder *e) ctx->last_duration--; } - /* Handle silent */ - if (!ctx->last_tone) { - e->src_buf_offset = 0; + /* Handle pause notes */ + if (!ctx->last_tone) return 0x8000; - } - - pos = (2 * PI * ctx->note_offset * ctx->last_tone / S302M_SAMPLING_RATE_HZ); - if (pos == 360) - ctx->note_offset = 0; - else - ctx->note_offset++; + pos = (2 * PI * ctx->note_offset * ctx->last_tone) / S302M_SAMPLING_RATE_HZ; + ctx->note_offset++; return (fixp_sin32(pos % (2 * PI)) >> 16) + 0x8000; } diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.h b/drivers/media/test-drivers/vidtv/vidtv_s302m.h index a0101734e758..e990b755bb20 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.h +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.h @@ -39,7 +39,7 @@ struct vidtv_s302m_ctx { u32 frame_index; u32 au_count; int last_duration; - int note_offset; + unsigned int note_offset; enum musical_notes last_tone; }; -- cgit v1.2.3 From 0d271a79c702d4b986809cb3acfbe8911bba892e Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 19 Nov 2020 11:20:38 +0100 Subject: media: vidtv: fix some notes at the tone generator The sheet music used to generate the tones had a few polyphonic notes. Due to that, its conversion to a tones sequence had a few errors. Also, due to a bug at the tone generator, it was missing the pause at the initial compass. Fix them. While here, reduce the compass to 100bpm. The music was converted from a Music XML file using this small script: my $count = 0; my $silent = 0; my $note; my $octave; print "\t"; while (<>) { $note = $1 if (m,\(.*)\,); $octave = "_$1" if (m,\(.*)\,); if (m,\1\,) { $note .= "S"; $sharp = 1; } if (m,\,) { $note = "SILENT"; $silent = 1; } if (m,\(.*)\,) { printf "{ NOTE_${note}${octave}, %d},", $1 * 128 / 480; $count++; if ($silent || $count >= 3) { print "\n\t"; $count = 0; $silent = 0; } else { print " "; print " " if (!$sharp); } $sharp = 0; $note = ""; $octave = ""; }; }; print "\n"; Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_s302m.c | 38 ++++++++++++++------------ 1 file changed, 20 insertions(+), 18 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.c b/drivers/media/test-drivers/vidtv/vidtv_s302m.c index fdb3d649c516..569e7a50129f 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.c +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.c @@ -78,8 +78,9 @@ struct tone_duration { int duration; }; -#define COMPASS 120 /* beats per minute (Allegro) */ +#define COMPASS 100 /* beats per minute */ static const struct tone_duration beethoven_fur_elise[] = { + { NOTE_SILENT, 512}, { NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_B_5, 128}, { NOTE_D_6, 128}, { NOTE_C_6, 128}, { NOTE_A_3, 128}, @@ -120,26 +121,27 @@ static const struct tone_duration beethoven_fur_elise[] = { { NOTE_E_5, 128}, { NOTE_D_5, 128}, { NOTE_A_3, 128}, { NOTE_E_4, 128}, { NOTE_A_4, 128}, { NOTE_E_4, 128}, { NOTE_D_5, 128}, { NOTE_C_5, 128}, { NOTE_E_3, 128}, - { NOTE_E_4, 128}, { NOTE_E_5, 255}, { NOTE_E_6, 128}, - { NOTE_E_5, 128}, { NOTE_E_6, 128}, { NOTE_E_5, 255}, + { NOTE_E_4, 128}, { NOTE_E_5, 128}, { NOTE_E_5, 128}, + { NOTE_E_6, 128}, { NOTE_E_5, 128}, { NOTE_E_6, 128}, + { NOTE_E_5, 128}, { NOTE_E_5, 128}, { NOTE_DS_5, 128}, + { NOTE_E_5, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_DS_5, 128}, { NOTE_E_5, 128}, { NOTE_DS_6, 128}, - { NOTE_E_6, 128}, { NOTE_DS_5, 128}, { NOTE_E_5, 128}, - { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, - { NOTE_B_5, 128}, { NOTE_D_6, 128}, { NOTE_C_6, 128}, - { NOTE_A_3, 128}, { NOTE_E_4, 128}, { NOTE_A_4, 128}, - { NOTE_C_5, 128}, { NOTE_E_5, 128}, { NOTE_A_5, 128}, - { NOTE_E_3, 128}, { NOTE_E_4, 128}, { NOTE_GS_4, 128}, - { NOTE_E_5, 128}, { NOTE_GS_5, 128}, { NOTE_B_5, 128}, - { NOTE_A_3, 128}, { NOTE_E_4, 128}, { NOTE_A_4, 128}, - { NOTE_E_5, 128}, { NOTE_E_6, 128}, { NOTE_DS_6, 128}, + { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_B_5, 128}, + { NOTE_D_6, 128}, { NOTE_C_6, 128}, { NOTE_A_3, 128}, + { NOTE_E_4, 128}, { NOTE_A_4, 128}, { NOTE_C_5, 128}, + { NOTE_E_5, 128}, { NOTE_A_5, 128}, { NOTE_E_3, 128}, + { NOTE_E_4, 128}, { NOTE_GS_4, 128}, { NOTE_E_5, 128}, + { NOTE_GS_5, 128}, { NOTE_B_5, 128}, { NOTE_A_3, 128}, + { NOTE_E_4, 128}, { NOTE_A_4, 128}, { NOTE_E_5, 128}, { NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, - { NOTE_B_5, 128}, { NOTE_D_6, 128}, { NOTE_C_6, 128}, - { NOTE_A_3, 128}, { NOTE_E_4, 128}, { NOTE_A_4, 128}, - { NOTE_C_5, 128}, { NOTE_E_5, 128}, { NOTE_A_5, 128}, - { NOTE_E_3, 128}, { NOTE_E_4, 128}, { NOTE_GS_4, 128}, - { NOTE_E_5, 128}, { NOTE_C_6, 128}, { NOTE_B_5, 128}, - { NOTE_C_5, 255}, { NOTE_C_5, 255}, { NOTE_SILENT, 512}, + { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_B_5, 128}, + { NOTE_D_6, 128}, { NOTE_C_6, 128}, { NOTE_A_3, 128}, + { NOTE_E_4, 128}, { NOTE_A_4, 128}, { NOTE_C_5, 128}, + { NOTE_E_5, 128}, { NOTE_A_5, 128}, { NOTE_E_3, 128}, + { NOTE_E_4, 128}, { NOTE_GS_4, 128}, { NOTE_E_5, 128}, + { NOTE_C_6, 128}, { NOTE_B_5, 128}, { NOTE_A_5, 512}, + { NOTE_SILENT, 256}, }; static struct vidtv_access_unit *vidtv_s302m_access_unit_init(struct vidtv_access_unit *head) -- cgit v1.2.3 From 0a33ab1682b44ac0b4128ada7ace9f7a0ef6b59c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 22 Sep 2020 10:28:12 +0200 Subject: media: vidtv: avoid data copy when initializing the multiplexer Initialize the fields of the arguments directly when declaring it, and pass the args as a pointer, instead of copying them. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_bridge.c | 28 +++++++++++++------------ drivers/media/test-drivers/vidtv/vidtv_mux.c | 28 ++++++++++++------------- drivers/media/test-drivers/vidtv/vidtv_mux.h | 2 +- 3 files changed, 30 insertions(+), 28 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_bridge.c b/drivers/media/test-drivers/vidtv/vidtv_bridge.c index e846aaab2c44..3fc7bf00a3e5 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_bridge.c +++ b/drivers/media/test-drivers/vidtv/vidtv_bridge.c @@ -161,7 +161,17 @@ vidtv_bridge_on_new_pkts_avail(void *priv, u8 *buf, u32 npkts) static int vidtv_start_streaming(struct vidtv_dvb *dvb) { - struct vidtv_mux_init_args mux_args = {0}; + struct vidtv_mux_init_args mux_args = { + .mux_rate_kbytes_sec = mux_rate_kbytes_sec, + .on_new_packets_available_cb = vidtv_bridge_on_new_pkts_avail, + .pcr_period_usecs = pcr_period_msec * USEC_PER_MSEC, + .si_period_usecs = si_period_msec * USEC_PER_MSEC, + .pcr_pid = pcr_pid, + .transport_stream_id = VIDTV_DEFAULT_TS_ID, + .network_id = VIDTV_DEFAULT_NETWORK_ID, + .network_name = VIDTV_DEFAULT_NETWORK_NAME, + .priv = dvb, + }; struct device *dev = &dvb->pdev->dev; u32 mux_buf_sz; @@ -170,21 +180,13 @@ static int vidtv_start_streaming(struct vidtv_dvb *dvb) return 0; } - mux_buf_sz = (mux_buf_sz_pkts) ? mux_buf_sz_pkts : vidtv_bridge_mux_buf_sz_for_mux_rate(); + mux_buf_sz = (mux_buf_sz_pkts) ? mux_buf_sz_pkts : + vidtv_bridge_mux_buf_sz_for_mux_rate(); - mux_args.mux_rate_kbytes_sec = mux_rate_kbytes_sec; - mux_args.on_new_packets_available_cb = vidtv_bridge_on_new_pkts_avail; - mux_args.mux_buf_sz = mux_buf_sz; - mux_args.pcr_period_usecs = pcr_period_msec * 1000; - mux_args.si_period_usecs = si_period_msec * 1000; - mux_args.pcr_pid = pcr_pid; - mux_args.transport_stream_id = VIDTV_DEFAULT_TS_ID; - mux_args.network_id = VIDTV_DEFAULT_NETWORK_ID, - mux_args.network_name = VIDTV_DEFAULT_NETWORK_NAME, - mux_args.priv = dvb; + mux_args.mux_buf_sz = mux_buf_sz; dvb->streaming = true; - dvb->mux = vidtv_mux_init(dvb->fe[0], dev, mux_args); + dvb->mux = vidtv_mux_init(dvb->fe[0], dev, &mux_args); if (!dvb->mux) return -ENOMEM; vidtv_mux_start_thread(dvb->mux); diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index bba3f2315531..89b19f0844b8 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -466,7 +466,7 @@ void vidtv_mux_stop_thread(struct vidtv_mux *m) struct vidtv_mux *vidtv_mux_init(struct dvb_frontend *fe, struct device *dev, - struct vidtv_mux_init_args args) + struct vidtv_mux_init_args *args) { struct vidtv_mux *m; @@ -476,28 +476,28 @@ struct vidtv_mux *vidtv_mux_init(struct dvb_frontend *fe, m->dev = dev; m->fe = fe; - m->timing.pcr_period_usecs = args.pcr_period_usecs; - m->timing.si_period_usecs = args.si_period_usecs; + m->timing.pcr_period_usecs = args->pcr_period_usecs; + m->timing.si_period_usecs = args->si_period_usecs; - m->mux_rate_kbytes_sec = args.mux_rate_kbytes_sec; + m->mux_rate_kbytes_sec = args->mux_rate_kbytes_sec; - m->on_new_packets_available_cb = args.on_new_packets_available_cb; + m->on_new_packets_available_cb = args->on_new_packets_available_cb; - m->mux_buf = vzalloc(args.mux_buf_sz); + m->mux_buf = vzalloc(args->mux_buf_sz); if (!m->mux_buf) goto free_mux; - m->mux_buf_sz = args.mux_buf_sz; + m->mux_buf_sz = args->mux_buf_sz; - m->pcr_pid = args.pcr_pid; - m->transport_stream_id = args.transport_stream_id; - m->priv = args.priv; - m->network_id = args.network_id; - m->network_name = kstrdup(args.network_name, GFP_KERNEL); + m->pcr_pid = args->pcr_pid; + m->transport_stream_id = args->transport_stream_id; + m->priv = args->priv; + m->network_id = args->network_id; + m->network_name = kstrdup(args->network_name, GFP_KERNEL); m->timing.current_jiffies = get_jiffies_64(); - if (args.channels) - m->channels = args.channels; + if (args->channels) + m->channels = args->channels; else if (vidtv_channels_init(m) < 0) goto free_mux_buf; diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.h b/drivers/media/test-drivers/vidtv/vidtv_mux.h index 005b707f1445..e186094c4fb7 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.h +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.h @@ -170,7 +170,7 @@ struct vidtv_mux_init_args { struct vidtv_mux *vidtv_mux_init(struct dvb_frontend *fe, struct device *dev, - struct vidtv_mux_init_args args); + struct vidtv_mux_init_args *args); void vidtv_mux_destroy(struct vidtv_mux *m); void vidtv_mux_start_thread(struct vidtv_mux *m); -- cgit v1.2.3 From 163d72a2d3ec7e0bc41b943fed7667f7cbfc760f Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 22 Sep 2020 11:01:17 +0200 Subject: media: vidtv: avoid copying data for PES structs Minimize the number of data copies and initialization at the code, passing them as pointers instead of duplicating the data. The only case where we're keeping the data copy is at vidtv_pes_write_h(), as it needs a copy of the passed arguments. On such case, we're being more explicit. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_mux.c | 30 +++-- drivers/media/test-drivers/vidtv/vidtv_pes.c | 178 +++++++++++++-------------- drivers/media/test-drivers/vidtv/vidtv_pes.h | 2 +- 3 files changed, 102 insertions(+), 108 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index 89b19f0844b8..eb24e27b7f5f 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -270,22 +270,28 @@ static u32 vidtv_mux_packetize_access_units(struct vidtv_mux *m, struct vidtv_encoder *e) { u32 nbytes = 0; - - struct pes_write_args args = {}; + struct pes_write_args args = { + .dest_buf = m->mux_buf, + .dest_buf_sz = m->mux_buf_sz, + .pid = be16_to_cpu(e->es_pid), + .encoder_id = e->id, + .stream_id = be16_to_cpu(e->stream_id), + .send_pts = true, /* forbidden value '01'... */ + .send_dts = false, /* ...for PTS_DTS flags */ + }; u32 initial_offset = m->mux_buf_offset; struct vidtv_access_unit *au = e->access_units; - u8 *buf = NULL; - struct vidtv_mux_pid_ctx *pid_ctx = vidtv_mux_create_pid_ctx_once(m, - be16_to_cpu(e->es_pid)); + struct vidtv_mux_pid_ctx *pid_ctx; - args.dest_buf = m->mux_buf; - args.dest_buf_sz = m->mux_buf_sz; - args.pid = be16_to_cpu(e->es_pid); - args.encoder_id = e->id; + /* see SMPTE 302M clause 6.4 */ + if (args.encoder_id == S302M) { + args.send_dts = false; + args.send_pts = true; + } + + pid_ctx = vidtv_mux_create_pid_ctx_once(m, be16_to_cpu(e->es_pid)); args.continuity_counter = &pid_ctx->cc; - args.stream_id = be16_to_cpu(e->stream_id); - args.send_pts = true; while (au) { buf = e->encoder_buf + au->offset; @@ -295,7 +301,7 @@ static u32 vidtv_mux_packetize_access_units(struct vidtv_mux *m, args.pts = au->pts; args.pcr = m->timing.clk; - m->mux_buf_offset += vidtv_pes_write_into(args); + m->mux_buf_offset += vidtv_pes_write_into(&args); au = au->next; } diff --git a/drivers/media/test-drivers/vidtv/vidtv_pes.c b/drivers/media/test-drivers/vidtv/vidtv_pes.c index 102352d398ed..782e5e7fbb02 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_pes.c +++ b/drivers/media/test-drivers/vidtv/vidtv_pes.c @@ -56,7 +56,7 @@ static u32 vidtv_pes_h_get_len(bool send_pts, bool send_dts) return len; } -static u32 vidtv_pes_write_header_stuffing(struct pes_header_write_args args) +static u32 vidtv_pes_write_header_stuffing(struct pes_header_write_args *args) { /* * This is a fixed 8-bit value equal to '0xFF' that can be inserted @@ -64,20 +64,20 @@ static u32 vidtv_pes_write_header_stuffing(struct pes_header_write_args args) * It is discarded by the decoder. No more than 32 stuffing bytes shall * be present in one PES packet header. */ - if (args.n_pes_h_s_bytes > PES_HEADER_MAX_STUFFING_BYTES) { + if (args->n_pes_h_s_bytes > PES_HEADER_MAX_STUFFING_BYTES) { pr_warn_ratelimited("More than %d stuffing bytes in PES packet header\n", PES_HEADER_MAX_STUFFING_BYTES); - args.n_pes_h_s_bytes = PES_HEADER_MAX_STUFFING_BYTES; + args->n_pes_h_s_bytes = PES_HEADER_MAX_STUFFING_BYTES; } - return vidtv_memset(args.dest_buf, - args.dest_offset, - args.dest_buf_sz, + return vidtv_memset(args->dest_buf, + args->dest_offset, + args->dest_buf_sz, TS_FILL_BYTE, - args.n_pes_h_s_bytes); + args->n_pes_h_s_bytes); } -static u32 vidtv_pes_write_pts_dts(struct pes_header_write_args args) +static u32 vidtv_pes_write_pts_dts(struct pes_header_write_args *args) { u32 nbytes = 0; /* the number of bytes written by this function */ @@ -89,7 +89,7 @@ static u32 vidtv_pes_write_pts_dts(struct pes_header_write_args args) u64 mask2; u64 mask3; - if (!args.send_pts && args.send_dts) + if (!args->send_pts && args->send_dts) return 0; mask1 = GENMASK_ULL(32, 30); @@ -97,80 +97,81 @@ static u32 vidtv_pes_write_pts_dts(struct pes_header_write_args args) mask3 = GENMASK_ULL(14, 0); /* see ISO/IEC 13818-1 : 2000 p. 32 */ - if (args.send_pts && args.send_dts) { - pts_dts.pts1 = (0x3 << 4) | ((args.pts & mask1) >> 29) | 0x1; - pts_dts.pts2 = cpu_to_be16(((args.pts & mask2) >> 14) | 0x1); - pts_dts.pts3 = cpu_to_be16(((args.pts & mask3) << 1) | 0x1); + if (args->send_pts && args->send_dts) { + pts_dts.pts1 = (0x3 << 4) | ((args->pts & mask1) >> 29) | 0x1; + pts_dts.pts2 = cpu_to_be16(((args->pts & mask2) >> 14) | 0x1); + pts_dts.pts3 = cpu_to_be16(((args->pts & mask3) << 1) | 0x1); - pts_dts.dts1 = (0x1 << 4) | ((args.dts & mask1) >> 29) | 0x1; - pts_dts.dts2 = cpu_to_be16(((args.dts & mask2) >> 14) | 0x1); - pts_dts.dts3 = cpu_to_be16(((args.dts & mask3) << 1) | 0x1); + pts_dts.dts1 = (0x1 << 4) | ((args->dts & mask1) >> 29) | 0x1; + pts_dts.dts2 = cpu_to_be16(((args->dts & mask2) >> 14) | 0x1); + pts_dts.dts3 = cpu_to_be16(((args->dts & mask3) << 1) | 0x1); op = &pts_dts; op_sz = sizeof(pts_dts); - } else if (args.send_pts) { - pts.pts1 = (0x1 << 5) | ((args.pts & mask1) >> 29) | 0x1; - pts.pts2 = cpu_to_be16(((args.pts & mask2) >> 14) | 0x1); - pts.pts3 = cpu_to_be16(((args.pts & mask3) << 1) | 0x1); + } else if (args->send_pts) { + pts.pts1 = (0x1 << 5) | ((args->pts & mask1) >> 29) | 0x1; + pts.pts2 = cpu_to_be16(((args->pts & mask2) >> 14) | 0x1); + pts.pts3 = cpu_to_be16(((args->pts & mask3) << 1) | 0x1); op = &pts; op_sz = sizeof(pts); } /* copy PTS/DTS optional */ - nbytes += vidtv_memcpy(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + nbytes += vidtv_memcpy(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, op, op_sz); return nbytes; } -static u32 vidtv_pes_write_h(struct pes_header_write_args args) +static u32 vidtv_pes_write_h(struct pes_header_write_args *args) { u32 nbytes = 0; /* the number of bytes written by this function */ struct vidtv_mpeg_pes pes_header = {}; struct vidtv_pes_optional pes_optional = {}; - struct pes_header_write_args pts_dts_args = args; - u32 stream_id = (args.encoder_id == S302M) ? PRIVATE_STREAM_1_ID : args.stream_id; + struct pes_header_write_args pts_dts_args; + u32 stream_id = (args->encoder_id == S302M) ? PRIVATE_STREAM_1_ID : args->stream_id; u16 pes_opt_bitfield = 0x01 << 15; pes_header.bitfield = cpu_to_be32((PES_START_CODE_PREFIX << 8) | stream_id); - pes_header.length = cpu_to_be16(vidtv_pes_op_get_len(args.send_pts, - args.send_dts) + - args.access_unit_len); + pes_header.length = cpu_to_be16(vidtv_pes_op_get_len(args->send_pts, + args->send_dts) + + args->access_unit_len); - if (args.send_pts && args.send_dts) + if (args->send_pts && args->send_dts) pes_opt_bitfield |= (0x3 << 6); - else if (args.send_pts) + else if (args->send_pts) pes_opt_bitfield |= (0x1 << 7); pes_optional.bitfield = cpu_to_be16(pes_opt_bitfield); - pes_optional.length = vidtv_pes_op_get_len(args.send_pts, args.send_dts) + - args.n_pes_h_s_bytes - + pes_optional.length = vidtv_pes_op_get_len(args->send_pts, args->send_dts) + + args->n_pes_h_s_bytes - sizeof(struct vidtv_pes_optional); /* copy header */ - nbytes += vidtv_memcpy(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + nbytes += vidtv_memcpy(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, &pes_header, sizeof(pes_header)); /* copy optional header bits */ - nbytes += vidtv_memcpy(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + nbytes += vidtv_memcpy(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, &pes_optional, sizeof(pes_optional)); /* copy the timing information */ - pts_dts_args.dest_offset = args.dest_offset + nbytes; - nbytes += vidtv_pes_write_pts_dts(pts_dts_args); + pts_dts_args = *args; + pts_dts_args.dest_offset = args->dest_offset + nbytes; + nbytes += vidtv_pes_write_pts_dts(&pts_dts_args); /* write any PES header stuffing */ nbytes += vidtv_pes_write_header_stuffing(args); @@ -299,14 +300,31 @@ static u32 vidtv_pes_write_ts_h(struct pes_ts_header_write_args args, return nbytes; } -u32 vidtv_pes_write_into(struct pes_write_args args) +u32 vidtv_pes_write_into(struct pes_write_args *args) { - u32 unaligned_bytes = (args.dest_offset % TS_PACKET_LEN); - struct pes_ts_header_write_args ts_header_args = {}; - struct pes_header_write_args pes_header_args = {}; - u32 remaining_len = args.access_unit_len; + u32 unaligned_bytes = (args->dest_offset % TS_PACKET_LEN); + struct pes_ts_header_write_args ts_header_args = { + .dest_buf = args->dest_buf, + .dest_buf_sz = args->dest_buf_sz, + .pid = args->pid, + .pcr = args->pcr, + .continuity_counter = args->continuity_counter, + }; + struct pes_header_write_args pes_header_args = { + .dest_buf = args->dest_buf, + .dest_buf_sz = args->dest_buf_sz, + .encoder_id = args->encoder_id, + .send_pts = args->send_pts, + .pts = args->pts, + .send_dts = args->send_dts, + .dts = args->dts, + .stream_id = args->stream_id, + .n_pes_h_s_bytes = args->n_pes_h_s_bytes, + .access_unit_len = args->access_unit_len, + }; + u32 remaining_len = args->access_unit_len; bool wrote_pes_header = false; - u64 last_pcr = args.pcr; + u64 last_pcr = args->pcr; bool need_pcr = true; u32 available_space; u32 payload_size; @@ -317,25 +335,13 @@ u32 vidtv_pes_write_into(struct pes_write_args args) pr_warn_ratelimited("buffer is misaligned, while starting PES\n"); /* forcibly align and hope for the best */ - nbytes += vidtv_memset(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + nbytes += vidtv_memset(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, TS_FILL_BYTE, TS_PACKET_LEN - unaligned_bytes); } - if (args.send_dts && !args.send_pts) { - pr_warn_ratelimited("forbidden value '01' for PTS_DTS flags\n"); - args.send_pts = true; - args.pts = args.dts; - } - - /* see SMPTE 302M clause 6.4 */ - if (args.encoder_id == S302M) { - args.send_dts = false; - args.send_pts = true; - } - while (remaining_len) { available_space = TS_PAYLOAD_LEN; /* @@ -344,14 +350,14 @@ u32 vidtv_pes_write_into(struct pes_write_args args) * the space needed for the TS header _and_ for the PES header */ if (!wrote_pes_header) - available_space -= vidtv_pes_h_get_len(args.send_pts, - args.send_dts); + available_space -= vidtv_pes_h_get_len(args->send_pts, + args->send_dts); /* * if the encoder has inserted stuffing bytes in the PES * header, account for them. */ - available_space -= args.n_pes_h_s_bytes; + available_space -= args->n_pes_h_s_bytes; /* Take the extra adaptation into account if need to send PCR */ if (need_pcr) { @@ -386,14 +392,9 @@ u32 vidtv_pes_write_into(struct pes_write_args args) } /* write ts header */ - ts_header_args.dest_buf = args.dest_buf; - ts_header_args.dest_offset = args.dest_offset + nbytes; - ts_header_args.dest_buf_sz = args.dest_buf_sz; - ts_header_args.pid = args.pid; - ts_header_args.pcr = args.pcr; - ts_header_args.continuity_counter = args.continuity_counter; - ts_header_args.wrote_pes_header = wrote_pes_header; - ts_header_args.n_stuffing_bytes = stuff_bytes; + ts_header_args.dest_offset = args->dest_offset + nbytes; + ts_header_args.wrote_pes_header = wrote_pes_header; + ts_header_args.n_stuffing_bytes = stuff_bytes; nbytes += vidtv_pes_write_ts_h(ts_header_args, need_pcr, &last_pcr); @@ -402,33 +403,20 @@ u32 vidtv_pes_write_into(struct pes_write_args args) if (!wrote_pes_header) { /* write the PES header only once */ - pes_header_args.dest_buf = args.dest_buf; - - pes_header_args.dest_offset = args.dest_offset + - nbytes; - - pes_header_args.dest_buf_sz = args.dest_buf_sz; - pes_header_args.encoder_id = args.encoder_id; - pes_header_args.send_pts = args.send_pts; - pes_header_args.pts = args.pts; - pes_header_args.send_dts = args.send_dts; - pes_header_args.dts = args.dts; - pes_header_args.stream_id = args.stream_id; - pes_header_args.n_pes_h_s_bytes = args.n_pes_h_s_bytes; - pes_header_args.access_unit_len = args.access_unit_len; - - nbytes += vidtv_pes_write_h(pes_header_args); - wrote_pes_header = true; + pes_header_args.dest_offset = args->dest_offset + + nbytes; + nbytes += vidtv_pes_write_h(&pes_header_args); + wrote_pes_header = true; } /* write as much of the payload as we possibly can */ - nbytes += vidtv_memcpy(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, - args.from, + nbytes += vidtv_memcpy(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, + args->from, payload_size); - args.from += payload_size; + args->from += payload_size; remaining_len -= payload_size; } diff --git a/drivers/media/test-drivers/vidtv/vidtv_pes.h b/drivers/media/test-drivers/vidtv/vidtv_pes.h index a152693233a9..99f45056adc2 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_pes.h +++ b/drivers/media/test-drivers/vidtv/vidtv_pes.h @@ -185,6 +185,6 @@ struct pes_write_args { * equal to the size of the access unit, since we need space for PES headers, TS headers * and padding bytes, if any. */ -u32 vidtv_pes_write_into(struct pes_write_args args); +u32 vidtv_pes_write_into(struct pes_write_args *args); #endif // VIDTV_PES_H -- cgit v1.2.3 From 2be65641642ef423f82162c3a5f28c754d1637d2 Mon Sep 17 00:00:00 2001 From: Matti Hamalainen Date: Fri, 20 Nov 2020 17:23:38 +0200 Subject: drm/nouveau: fix relocations applying logic and a double-free Commit 03e0d26fcf79 ("drm/nouveau: slowpath for pushbuf ioctl") included a logic-bug which results in the relocations not actually getting applied at all as the call to nouveau_gem_pushbuf_reloc_apply() is never reached. This causes a regression with graphical corruption, triggered when relocations need to be done (for example after a suspend/resume cycle.) Fix by setting *apply_relocs value only if there were more than 0 relocations. Additionally, the never reached code had a leftover u_free() call, which, after fixing the logic, now got called and resulted in a double-free. Fix by removing one u_free(), moving the other and adding check for errors. Cc: Daniel Vetter Cc: Ben Skeggs Cc: nouveau@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org Signed-off-by: Matti Hamalainen Fixes: 03e0d26fcf79 ("drm/nouveau: slowpath for pushbuf ioctl") References: https://gitlab.freedesktop.org/drm/nouveau/-/issues/11 Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20201120152338.1203257-1-ccr@tnsp.org --- drivers/gpu/drm/nouveau/nouveau_gem.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 549bc67feabb..c2051380d18c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -558,8 +558,10 @@ nouveau_gem_pushbuf_validate(struct nouveau_channel *chan, NV_PRINTK(err, cli, "validating bo list\n"); validate_fini(op, chan, NULL, NULL); return ret; + } else if (ret > 0) { + *apply_relocs = true; } - *apply_relocs = ret; + return 0; } @@ -662,7 +664,6 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli, nouveau_bo_wr32(nvbo, r->reloc_bo_offset >> 2, data); } - u_free(reloc); return ret; } @@ -872,9 +873,10 @@ out: break; } } - u_free(reloc); } out_prevalid: + if (!IS_ERR(reloc)) + u_free(reloc); u_free(bo); u_free(push); -- cgit v1.2.3 From a8bd461ca3b32468777d054d9a0e050be5a418e9 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 22 Sep 2020 16:43:56 +0200 Subject: media: vidtv: do some cleanups at the driver Do some cleanups at the coding style of the driver: - remove "inline" declarations; - use reverse xmas-tree for local var declarations; - Adjust some indent to avoid breaking 80-cols; - Cleanup some comments. No functional changes. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_bridge.c | 81 ++++++----- drivers/media/test-drivers/vidtv/vidtv_channel.c | 69 ++++----- drivers/media/test-drivers/vidtv/vidtv_demod.c | 1 - drivers/media/test-drivers/vidtv/vidtv_encoder.h | 2 +- drivers/media/test-drivers/vidtv/vidtv_mux.c | 33 ++--- drivers/media/test-drivers/vidtv/vidtv_psi.c | 173 +++++++++++------------ drivers/media/test-drivers/vidtv/vidtv_s302m.c | 14 +- 7 files changed, 182 insertions(+), 191 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_bridge.c b/drivers/media/test-drivers/vidtv/vidtv_bridge.c index 3fc7bf00a3e5..d428bdb47ae4 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_bridge.c +++ b/drivers/media/test-drivers/vidtv/vidtv_bridge.c @@ -4,7 +4,8 @@ * validate the existing APIs in the media subsystem. It can also aid * developers working on userspace applications. * - * When this module is loaded, it will attempt to modprobe 'dvb_vidtv_tuner' and 'dvb_vidtv_demod'. + * When this module is loaded, it will attempt to modprobe 'dvb_vidtv_tuner' + * and 'dvb_vidtv_demod'. * * Copyright (C) 2020 Daniel W. S. Almeida */ @@ -24,18 +25,21 @@ #include "vidtv_ts.h" #include "vidtv_tuner.h" -//#define MUX_BUF_MAX_SZ -//#define MUX_BUF_MIN_SZ +#define MUX_BUF_MIN_SZ 90164 +#define MUX_BUF_MAX_SZ (MUX_BUF_MIN_SZ * 10) #define TUNER_DEFAULT_ADDR 0x68 #define DEMOD_DEFAULT_ADDR 0x60 #define VIDTV_DEFAULT_NETWORK_ID 0x744 #define VIDTV_DEFAULT_NETWORK_NAME "LinuxTV.org" -/* LNBf fake parameters: ranges used by an Universal (extended) European LNBf */ -#define LNB_CUT_FREQUENCY 11700000 -#define LNB_LOW_FREQ 9750000 -#define LNB_HIGH_FREQ 10600000 - +/* + * The LNBf fake parameters here are the ranges used by an + * Universal (extended) European LNBf, which is likely the most common LNBf + * found on Satellite digital TV system nowadays. + */ +#define LNB_CUT_FREQUENCY 11700000 /* high IF frequency */ +#define LNB_LOW_FREQ 9750000 /* low IF frequency */ +#define LNB_HIGH_FREQ 10600000 /* transition frequency */ static unsigned int drop_tslock_prob_on_low_snr; module_param(drop_tslock_prob_on_low_snr, uint, 0); @@ -94,7 +98,8 @@ MODULE_PARM_DESC(si_period_msec, "How often to send SI packets. Default: 40ms"); static unsigned int pcr_period_msec = 40; module_param(pcr_period_msec, uint, 0); -MODULE_PARM_DESC(pcr_period_msec, "How often to send PCR packets. Default: 40ms"); +MODULE_PARM_DESC(pcr_period_msec, + "How often to send PCR packets. Default: 40ms"); static unsigned int mux_rate_kbytes_sec = 4096; module_param(mux_rate_kbytes_sec, uint, 0); @@ -106,16 +111,14 @@ MODULE_PARM_DESC(pcr_pid, "PCR PID for all channels: defaults to 0x200"); static unsigned int mux_buf_sz_pkts; module_param(mux_buf_sz_pkts, uint, 0); -MODULE_PARM_DESC(mux_buf_sz_pkts, "Size for the internal mux buffer in multiples of 188 bytes"); - -#define MUX_BUF_MIN_SZ 90164 -#define MUX_BUF_MAX_SZ (MUX_BUF_MIN_SZ * 10) +MODULE_PARM_DESC(mux_buf_sz_pkts, + "Size for the internal mux buffer in multiples of 188 bytes"); static u32 vidtv_bridge_mux_buf_sz_for_mux_rate(void) { u32 max_elapsed_time_msecs = VIDTV_MAX_SLEEP_USECS / USEC_PER_MSEC; - u32 nbytes_expected; u32 mux_buf_sz = mux_buf_sz_pkts * TS_PACKET_LEN; + u32 nbytes_expected; nbytes_expected = mux_rate_kbytes_sec; nbytes_expected *= max_elapsed_time_msecs; @@ -145,14 +148,12 @@ static bool vidtv_bridge_check_demod_lock(struct vidtv_dvb *dvb, u32 n) FE_HAS_LOCK); } -static void -vidtv_bridge_on_new_pkts_avail(void *priv, u8 *buf, u32 npkts) +/* + * called on a separate thread by the mux when new packets become available + */ +static void vidtv_bridge_on_new_pkts_avail(void *priv, u8 *buf, u32 npkts) { - /* - * called on a separate thread by the mux when new packets become - * available - */ - struct vidtv_dvb *dvb = (struct vidtv_dvb *)priv; + struct vidtv_dvb *dvb = priv; /* drop packets if we lose the lock */ if (vidtv_bridge_check_demod_lock(dvb, 0)) @@ -180,8 +181,10 @@ static int vidtv_start_streaming(struct vidtv_dvb *dvb) return 0; } - mux_buf_sz = (mux_buf_sz_pkts) ? mux_buf_sz_pkts : - vidtv_bridge_mux_buf_sz_for_mux_rate(); + if (mux_buf_sz_pkts) + mux_buf_sz = mux_buf_sz_pkts; + else + mux_buf_sz = vidtv_bridge_mux_buf_sz_for_mux_rate(); mux_args.mux_buf_sz = mux_buf_sz; @@ -212,8 +215,8 @@ static int vidtv_start_feed(struct dvb_demux_feed *feed) { struct dvb_demux *demux = feed->demux; struct vidtv_dvb *dvb = demux->priv; - int rc; int ret; + int rc; if (!demux->dmx.frontend) return -EINVAL; @@ -251,9 +254,9 @@ static int vidtv_stop_feed(struct dvb_demux_feed *feed) static struct dvb_frontend *vidtv_get_frontend_ptr(struct i2c_client *c) { - /* the demod will set this when its probe function runs */ struct vidtv_demod_state *state = i2c_get_clientdata(c); + /* the demod will set this when its probe function runs */ return &state->frontend; } @@ -261,6 +264,11 @@ static int vidtv_master_xfer(struct i2c_adapter *i2c_adap, struct i2c_msg msgs[], int num) { + /* + * Right now, this virtual driver doesn't really send or receive + * messages from I2C. A real driver will require an implementation + * here. + */ return 0; } @@ -328,11 +336,10 @@ static int vidtv_bridge_dmxdev_init(struct vidtv_dvb *dvb) static int vidtv_bridge_probe_demod(struct vidtv_dvb *dvb, u32 n) { - struct vidtv_demod_config cfg = {}; - - cfg.drop_tslock_prob_on_low_snr = drop_tslock_prob_on_low_snr; - cfg.recover_tslock_prob_on_good_snr = recover_tslock_prob_on_good_snr; - + struct vidtv_demod_config cfg = { + .drop_tslock_prob_on_low_snr = drop_tslock_prob_on_low_snr, + .recover_tslock_prob_on_good_snr = recover_tslock_prob_on_good_snr, + }; dvb->i2c_client_demod[n] = dvb_module_probe("dvb_vidtv_demod", NULL, &dvb->i2c_adapter, @@ -351,14 +358,14 @@ static int vidtv_bridge_probe_demod(struct vidtv_dvb *dvb, u32 n) static int vidtv_bridge_probe_tuner(struct vidtv_dvb *dvb, u32 n) { - struct vidtv_tuner_config cfg = {}; + struct vidtv_tuner_config cfg = { + .fe = dvb->fe[n], + .mock_power_up_delay_msec = mock_power_up_delay_msec, + .mock_tune_delay_msec = mock_tune_delay_msec, + }; u32 freq; int i; - cfg.fe = dvb->fe[n]; - cfg.mock_power_up_delay_msec = mock_power_up_delay_msec; - cfg.mock_tune_delay_msec = mock_tune_delay_msec; - /* TODO: check if the frequencies are at a valid range */ memcpy(cfg.vidtv_valid_dvb_t_freqs, @@ -397,9 +404,7 @@ static int vidtv_bridge_probe_tuner(struct vidtv_dvb *dvb, u32 n) static int vidtv_bridge_dvb_init(struct vidtv_dvb *dvb) { - int ret; - int i; - int j; + int ret, i, j; ret = vidtv_bridge_i2c_register_adap(dvb); if (ret < 0) diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index f64a68dea234..8206bcefd7c7 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -33,8 +33,8 @@ static void vidtv_channel_encoder_destroy(struct vidtv_encoder *e) { - struct vidtv_encoder *curr = e; struct vidtv_encoder *tmp = NULL; + struct vidtv_encoder *curr = e; while (curr) { /* forward the call to the derived type */ @@ -46,25 +46,25 @@ static void vidtv_channel_encoder_destroy(struct vidtv_encoder *e) #define ENCODING_ISO8859_15 "\x0b" +/* + * init an audio only channel with a s302m encoder + */ struct vidtv_channel *vidtv_channel_s302m_init(struct vidtv_channel *head, u16 transport_stream_id) { - /* - * init an audio only channel with a s302m encoder - */ - const u16 s302m_service_id = 0x880; - const u16 s302m_program_num = 0x880; - const u16 s302m_program_pid = 0x101; /* packet id for PMT*/ - const u16 s302m_es_pid = 0x111; /* packet id for the ES */ const __be32 s302m_fid = cpu_to_be32(VIDTV_S302M_FORMAT_IDENTIFIER); - char *name = ENCODING_ISO8859_15 "Beethoven"; - char *provider = ENCODING_ISO8859_15 "LinuxTV.org"; - char *iso_language_code = ENCODING_ISO8859_15 "eng"; - char *event_name = ENCODING_ISO8859_15 "Beethoven Music"; char *event_text = ENCODING_ISO8859_15 "Beethoven's Für Elise"; + char *event_name = ENCODING_ISO8859_15 "Beethoven Music"; + struct vidtv_s302m_encoder_init_args encoder_args = {}; + char *iso_language_code = ENCODING_ISO8859_15 "eng"; + char *provider = ENCODING_ISO8859_15 "LinuxTV.org"; + char *name = ENCODING_ISO8859_15 "Beethoven"; + const u16 s302m_es_pid = 0x111; /* packet id for the ES */ + const u16 s302m_program_pid = 0x101; /* packet id for PMT*/ + const u16 s302m_service_id = 0x880; + const u16 s302m_program_num = 0x880; const u16 s302m_beethoven_event_id = 1; struct vidtv_channel *s302m; - struct vidtv_s302m_encoder_init_args encoder_args = {}; s302m = kzalloc(sizeof(*s302m), GFP_KERNEL); if (!s302m) @@ -159,11 +159,9 @@ static struct vidtv_psi_table_eit_event { /* Concatenate the events */ const struct vidtv_channel *cur_chnl = m->channels; - struct vidtv_psi_table_eit_event *curr = NULL; struct vidtv_psi_table_eit_event *head = NULL; struct vidtv_psi_table_eit_event *tail = NULL; - struct vidtv_psi_desc *desc = NULL; u16 event_id; @@ -175,7 +173,8 @@ static struct vidtv_psi_table_eit_event if (!curr) dev_warn_ratelimited(m->dev, - "No events found for channel %s\n", cur_chnl->name); + "No events found for channel %s\n", + cur_chnl->name); while (curr) { event_id = be16_to_cpu(curr->event_id); @@ -221,7 +220,8 @@ static struct vidtv_psi_table_sdt_service if (!curr) dev_warn_ratelimited(m->dev, - "No services found for channel %s\n", cur_chnl->name); + "No services found for channel %s\n", + cur_chnl->name); while (curr) { service_id = be16_to_cpu(curr->service_id); @@ -300,26 +300,24 @@ vidtv_channel_pat_prog_cat_into_new(struct vidtv_mux *m) return head; } +/* + * Match channels to their respective PMT sections, then assign the + * streams + */ static void vidtv_channel_pmt_match_sections(struct vidtv_channel *channels, struct vidtv_psi_table_pmt **sections, u32 nsections) { - /* - * Match channels to their respective PMT sections, then assign the - * streams - */ struct vidtv_psi_table_pmt *curr_section = NULL; - struct vidtv_channel *cur_chnl = channels; - - struct vidtv_psi_table_pmt_stream *s = NULL; struct vidtv_psi_table_pmt_stream *head = NULL; struct vidtv_psi_table_pmt_stream *tail = NULL; - + struct vidtv_psi_table_pmt_stream *s = NULL; + struct vidtv_channel *cur_chnl = channels; struct vidtv_psi_desc *desc = NULL; - u32 j; - u16 curr_id; u16 e_pid; /* elementary stream pid */ + u16 curr_id; + u32 j; while (cur_chnl) { for (j = 0; j < nsections; ++j) { @@ -345,7 +343,8 @@ vidtv_channel_pmt_match_sections(struct vidtv_channel *channels, head = tail; desc = vidtv_psi_desc_clone(s->descriptor); - vidtv_psi_desc_assign(&tail->descriptor, desc); + vidtv_psi_desc_assign(&tail->descriptor, + desc); s = s->next; } @@ -359,7 +358,8 @@ vidtv_channel_pmt_match_sections(struct vidtv_channel *channels, } } -static void vidtv_channel_destroy_service_list(struct vidtv_psi_desc_service_list_entry *e) +static void +vidtv_channel_destroy_service_list(struct vidtv_psi_desc_service_list_entry *e) { struct vidtv_psi_desc_service_list_entry *tmp; @@ -412,9 +412,9 @@ next_desc: int vidtv_channel_si_init(struct vidtv_mux *m) { + struct vidtv_psi_desc_service_list_entry *service_list = NULL; struct vidtv_psi_table_pat_program *programs = NULL; struct vidtv_psi_table_sdt_service *services = NULL; - struct vidtv_psi_desc_service_list_entry *service_list = NULL; struct vidtv_psi_table_eit_event *events = NULL; m->si.pat = vidtv_psi_pat_table_init(m->transport_stream_id); @@ -449,11 +449,11 @@ int vidtv_channel_si_init(struct vidtv_mux *m) if (!m->si.nit) goto free_service_list; - m->si.eit = vidtv_psi_eit_table_init(m->network_id, m->transport_stream_id); + m->si.eit = vidtv_psi_eit_table_init(m->network_id, + m->transport_stream_id); if (!m->si.eit) goto free_nit; - /* assemble all programs and assign to PAT */ vidtv_psi_pat_program_assign(m->si.pat, programs); @@ -463,7 +463,8 @@ int vidtv_channel_si_init(struct vidtv_mux *m) /* assemble all events and assign to EIT */ vidtv_psi_eit_event_assign(m->si.eit, events); - m->si.pmt_secs = vidtv_psi_pmt_create_sec_for_each_pat_entry(m->si.pat, m->pcr_pid); + m->si.pmt_secs = vidtv_psi_pmt_create_sec_for_each_pat_entry(m->si.pat, + m->pcr_pid); if (!m->si.pmt_secs) goto free_eit; @@ -496,8 +497,8 @@ free_pat: void vidtv_channel_si_destroy(struct vidtv_mux *m) { - u32 i; u16 num_programs = m->si.pat->programs; + u32 i; vidtv_psi_pat_table_destroy(m->si.pat); diff --git a/drivers/media/test-drivers/vidtv/vidtv_demod.c b/drivers/media/test-drivers/vidtv/vidtv_demod.c index 63ac55b81f39..b7823d97b30d 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_demod.c +++ b/drivers/media/test-drivers/vidtv/vidtv_demod.c @@ -193,7 +193,6 @@ static void vidtv_demod_update_stats(struct dvb_frontend *fe) c->cnr.stat[0].svalue = state->tuner_cnr; c->cnr.stat[0].svalue -= prandom_u32_max(state->tuner_cnr / 50); - } static int vidtv_demod_read_status(struct dvb_frontend *fe, diff --git a/drivers/media/test-drivers/vidtv/vidtv_encoder.h b/drivers/media/test-drivers/vidtv/vidtv_encoder.h index f742d566fbcb..0ac5b1e3f666 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_encoder.h +++ b/drivers/media/test-drivers/vidtv/vidtv_encoder.h @@ -28,7 +28,7 @@ struct vidtv_access_unit { struct vidtv_access_unit *next; }; -/* Some musical notes, used by a tone generator */ +/* Some musical notes, used by a tone generator. Values are in Hz */ enum musical_notes { NOTE_SILENT = 0, diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index eb24e27b7f5f..6df9cfd7f33b 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -63,9 +63,9 @@ static struct vidtv_mux_pid_ctx static void vidtv_mux_pid_ctx_destroy(struct vidtv_mux *m) { - int bkt; struct vidtv_mux_pid_ctx *ctx; struct hlist_node *tmp; + int bkt; hash_for_each_safe(m->pid_ctx, bkt, tmp, ctx, h) { hash_del(&ctx->h); @@ -129,21 +129,18 @@ static void vidtv_mux_update_clk(struct vidtv_mux *m) static u32 vidtv_mux_push_si(struct vidtv_mux *m) { + struct vidtv_psi_pat_write_args pat_args = {}; + struct vidtv_psi_pmt_write_args pmt_args = {}; + struct vidtv_psi_sdt_write_args sdt_args = {}; + struct vidtv_psi_nit_write_args nit_args = {}; + struct vidtv_psi_eit_write_args eit_args = {}; u32 initial_offset = m->mux_buf_offset; - struct vidtv_mux_pid_ctx *pat_ctx; struct vidtv_mux_pid_ctx *pmt_ctx; struct vidtv_mux_pid_ctx *sdt_ctx; struct vidtv_mux_pid_ctx *nit_ctx; struct vidtv_mux_pid_ctx *eit_ctx; - - struct vidtv_psi_pat_write_args pat_args = {}; - struct vidtv_psi_pmt_write_args pmt_args = {}; - struct vidtv_psi_sdt_write_args sdt_args = {}; - struct vidtv_psi_nit_write_args nit_args = {}; - struct vidtv_psi_eit_write_args eit_args = {}; - - u32 nbytes; /* the number of bytes written by this function */ + u32 nbytes; u16 pmt_pid; u32 i; @@ -269,7 +266,6 @@ static bool vidtv_mux_should_push_si(struct vidtv_mux *m) static u32 vidtv_mux_packetize_access_units(struct vidtv_mux *m, struct vidtv_encoder *e) { - u32 nbytes = 0; struct pes_write_args args = { .dest_buf = m->mux_buf, .dest_buf_sz = m->mux_buf_sz, @@ -279,10 +275,11 @@ static u32 vidtv_mux_packetize_access_units(struct vidtv_mux *m, .send_pts = true, /* forbidden value '01'... */ .send_dts = false, /* ...for PTS_DTS flags */ }; - u32 initial_offset = m->mux_buf_offset; struct vidtv_access_unit *au = e->access_units; - u8 *buf = NULL; + u32 initial_offset = m->mux_buf_offset; struct vidtv_mux_pid_ctx *pid_ctx; + u32 nbytes = 0; + u8 *buf = NULL; /* see SMPTE 302M clause 6.4 */ if (args.encoder_id == S302M) { @@ -318,10 +315,10 @@ static u32 vidtv_mux_packetize_access_units(struct vidtv_mux *m, static u32 vidtv_mux_poll_encoders(struct vidtv_mux *m) { - u32 nbytes = 0; - u32 au_nbytes; struct vidtv_channel *cur_chnl = m->channels; struct vidtv_encoder *e = NULL; + u32 nbytes = 0; + u32 au_nbytes; while (cur_chnl) { e = cur_chnl->encoders; @@ -347,9 +344,9 @@ static u32 vidtv_mux_pad_with_nulls(struct vidtv_mux *m, u32 npkts) { struct null_packet_write_args args = {}; u32 initial_offset = m->mux_buf_offset; - u32 nbytes; /* the number of bytes written by this function */ - u32 i; struct vidtv_mux_pid_ctx *ctx; + u32 nbytes; + u32 i; ctx = vidtv_mux_get_pid_ctx(m, TS_NULL_PACKET_PID); @@ -388,9 +385,9 @@ static void vidtv_mux_tick(struct work_struct *work) struct vidtv_mux, mpeg_thread); struct dtv_frontend_properties *c = &m->fe->dtv_property_cache; + u32 tot_bits = 0; u32 nbytes; u32 npkts; - u32 tot_bits = 0; while (m->streaming) { nbytes = 0; diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index b31a29f46bde..375e01480d3d 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -76,7 +76,7 @@ static const u32 CRC_LUT[256] = { 0xbcb4666d, 0xb8757bda, 0xb5365d03, 0xb1f740b4 }; -static inline u32 dvb_crc32(u32 crc, u8 *data, u32 len) +static u32 dvb_crc32(u32 crc, u8 *data, u32 len) { /* from libdvbv5 */ while (len--) @@ -89,7 +89,8 @@ static void vidtv_psi_update_version_num(struct vidtv_psi_table_header *h) h->version++; } -static inline u16 vidtv_psi_sdt_serv_get_desc_loop_len(struct vidtv_psi_table_sdt_service *s) +static u16 +vidtv_psi_sdt_serv_get_desc_loop_len(struct vidtv_psi_table_sdt_service *s) { u16 mask; u16 ret; @@ -100,7 +101,8 @@ static inline u16 vidtv_psi_sdt_serv_get_desc_loop_len(struct vidtv_psi_table_sd return ret; } -static inline u16 vidtv_psi_pmt_stream_get_desc_loop_len(struct vidtv_psi_table_pmt_stream *s) +static u16 +vidtv_psi_pmt_stream_get_desc_loop_len(struct vidtv_psi_table_pmt_stream *s) { u16 mask; u16 ret; @@ -111,7 +113,7 @@ static inline u16 vidtv_psi_pmt_stream_get_desc_loop_len(struct vidtv_psi_table_ return ret; } -static inline u16 vidtv_psi_pmt_get_desc_loop_len(struct vidtv_psi_table_pmt *p) +static u16 vidtv_psi_pmt_get_desc_loop_len(struct vidtv_psi_table_pmt *p) { u16 mask; u16 ret; @@ -122,7 +124,7 @@ static inline u16 vidtv_psi_pmt_get_desc_loop_len(struct vidtv_psi_table_pmt *p) return ret; } -static inline u16 vidtv_psi_get_sec_len(struct vidtv_psi_table_header *h) +static u16 vidtv_psi_get_sec_len(struct vidtv_psi_table_header *h) { u16 mask; u16 ret; @@ -133,7 +135,7 @@ static inline u16 vidtv_psi_get_sec_len(struct vidtv_psi_table_header *h) return ret; } -inline u16 vidtv_psi_get_pat_program_pid(struct vidtv_psi_table_pat_program *p) +u16 vidtv_psi_get_pat_program_pid(struct vidtv_psi_table_pat_program *p) { u16 mask; u16 ret; @@ -144,7 +146,7 @@ inline u16 vidtv_psi_get_pat_program_pid(struct vidtv_psi_table_pat_program *p) return ret; } -inline u16 vidtv_psi_pmt_stream_get_elem_pid(struct vidtv_psi_table_pmt_stream *s) +u16 vidtv_psi_pmt_stream_get_elem_pid(struct vidtv_psi_table_pmt_stream *s) { u16 mask; u16 ret; @@ -155,10 +157,11 @@ inline u16 vidtv_psi_pmt_stream_get_elem_pid(struct vidtv_psi_table_pmt_stream * return ret; } -static inline void vidtv_psi_set_desc_loop_len(__be16 *bitfield, u16 new_len, u8 desc_len_nbits) +static void vidtv_psi_set_desc_loop_len(__be16 *bitfield, u16 new_len, + u8 desc_len_nbits) { - u16 mask; __be16 new; + u16 mask; mask = GENMASK(15, desc_len_nbits); @@ -185,27 +188,22 @@ static void vidtv_psi_set_sec_len(struct vidtv_psi_table_header *h, u16 new_len) h->bitfield = new; } +/* + * Packetize PSI sections into TS packets: + * push a TS header (4bytes) every 184 bytes + * manage the continuity_counter + * add stuffing (i.e. padding bytes) after the CRC + */ static u32 vidtv_psi_ts_psi_write_into(struct psi_write_args args) { - /* - * Packetize PSI sections into TS packets: - * push a TS header (4bytes) every 184 bytes - * manage the continuity_counter - * add stuffing (i.e. padding bytes) after the CRC - */ u32 nbytes_past_boundary = (args.dest_offset % TS_PACKET_LEN); bool aligned = (nbytes_past_boundary == 0); struct vidtv_mpeg_ts ts_header = {}; - - /* number of bytes written by this function */ - u32 nbytes = 0; - /* how much there is left to write */ u32 remaining_len = args.len; - /* how much we can be written in this packet */ u32 payload_write_len = 0; - /* where we are in the source */ u32 payload_offset = 0; + u32 nbytes = 0; const u16 PAYLOAD_START = args.new_psi_section; @@ -294,9 +292,10 @@ static u32 vidtv_psi_ts_psi_write_into(struct psi_write_args args) static u32 table_section_crc32_write_into(struct crc32_write_args args) { - /* the CRC is the last entry in the section */ - u32 nbytes = 0; struct psi_write_args psi_args = {}; + u32 nbytes = 0; + + /* the CRC is the last entry in the section */ psi_args.dest_buf = args.dest_buf; psi_args.from = &args.crc; @@ -391,8 +390,8 @@ struct vidtv_psi_desc_registration struct vidtv_psi_desc_network_name *vidtv_psi_network_name_desc_init(struct vidtv_psi_desc *head, char *network_name) { - struct vidtv_psi_desc_network_name *desc; u32 network_name_len = network_name ? strlen(network_name) : 0; + struct vidtv_psi_desc_network_name *desc; desc = kzalloc(sizeof(*desc), GFP_KERNEL); if (!desc) @@ -413,10 +412,10 @@ struct vidtv_psi_desc_service_list *vidtv_psi_service_list_desc_init(struct vidtv_psi_desc *head, struct vidtv_psi_desc_service_list_entry *entry) { - struct vidtv_psi_desc_service_list *desc; struct vidtv_psi_desc_service_list_entry *curr_e = NULL; struct vidtv_psi_desc_service_list_entry *head_e = NULL; struct vidtv_psi_desc_service_list_entry *prev_e = NULL; + struct vidtv_psi_desc_service_list *desc; u16 length = 0; desc = kzalloc(sizeof(*desc), GFP_KERNEL); @@ -465,10 +464,10 @@ struct vidtv_psi_desc_short_event char *event_name, char *text) { - struct vidtv_psi_desc_short_event *desc; + u32 iso_len = iso_language_code ? strlen(iso_language_code) : 0; u32 event_name_len = event_name ? strlen(event_name) : 0; + struct vidtv_psi_desc_short_event *desc; u32 text_len = text ? strlen(text) : 0; - u32 iso_len = iso_language_code ? strlen(iso_language_code) : 0; desc = kzalloc(sizeof(*desc), GFP_KERNEL); if (!desc) @@ -502,14 +501,13 @@ struct vidtv_psi_desc_short_event struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc) { - struct vidtv_psi_desc *head = NULL; - struct vidtv_psi_desc *prev = NULL; - struct vidtv_psi_desc *curr = NULL; - - struct vidtv_psi_desc_service *service; struct vidtv_psi_desc_network_name *desc_network_name; struct vidtv_psi_desc_service_list *desc_service_list; struct vidtv_psi_desc_short_event *desc_short_event; + struct vidtv_psi_desc_service *service; + struct vidtv_psi_desc *head = NULL; + struct vidtv_psi_desc *prev = NULL; + struct vidtv_psi_desc *curr = NULL; while (desc) { switch (desc->type) { @@ -571,10 +569,10 @@ struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc) void vidtv_psi_desc_destroy(struct vidtv_psi_desc *desc) { + struct vidtv_psi_desc_service_list_entry *sl_entry_tmp = NULL; + struct vidtv_psi_desc_service_list_entry *sl_entry = NULL; struct vidtv_psi_desc *curr = desc; struct vidtv_psi_desc *tmp = NULL; - struct vidtv_psi_desc_service_list_entry *sl_entry = NULL; - struct vidtv_psi_desc_service_list_entry *sl_entry_tmp = NULL; while (curr) { tmp = curr; @@ -677,10 +675,10 @@ void vidtv_sdt_desc_assign(struct vidtv_psi_table_sdt *sdt, static u32 vidtv_psi_desc_write_into(struct desc_write_args args) { + struct vidtv_psi_desc_service_list_entry *serv_list_entry = NULL; + struct psi_write_args psi_args = {}; /* the number of bytes written by this function */ u32 nbytes = 0; - struct psi_write_args psi_args = {}; - struct vidtv_psi_desc_service_list_entry *serv_list_entry = NULL; psi_args.dest_buf = args.dest_buf; psi_args.from = &args.desc->type; @@ -799,9 +797,9 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args args) static u32 vidtv_psi_table_header_write_into(struct header_write_args args) { + struct psi_write_args psi_args = {}; /* the number of bytes written by this function */ u32 nbytes = 0; - struct psi_write_args psi_args = {}; psi_args.dest_buf = args.dest_buf; psi_args.from = args.h; @@ -822,10 +820,11 @@ vidtv_psi_table_header_write_into(struct header_write_args args) void vidtv_psi_pat_table_update_sec_len(struct vidtv_psi_table_pat *pat) { - /* see ISO/IEC 13818-1 : 2000 p.43 */ u16 length = 0; u32 i; + /* see ISO/IEC 13818-1 : 2000 p.43 */ + /* from immediately after 'section_length' until 'last_section_number'*/ length += PAT_LEN_UNTIL_LAST_SECTION_NUMBER; @@ -841,10 +840,11 @@ vidtv_psi_pat_table_update_sec_len(struct vidtv_psi_table_pat *pat) void vidtv_psi_pmt_table_update_sec_len(struct vidtv_psi_table_pmt *pmt) { - /* see ISO/IEC 13818-1 : 2000 p.46 */ - u16 length = 0; struct vidtv_psi_table_pmt_stream *s = pmt->stream; u16 desc_loop_len; + u16 length = 0; + + /* see ISO/IEC 13818-1 : 2000 p.46 */ /* from immediately after 'section_length' until 'program_info_length'*/ length += PMT_LEN_UNTIL_PROGRAM_INFO_LENGTH; @@ -875,10 +875,11 @@ void vidtv_psi_pmt_table_update_sec_len(struct vidtv_psi_table_pmt *pmt) void vidtv_psi_sdt_table_update_sec_len(struct vidtv_psi_table_sdt *sdt) { - /* see ETSI EN 300 468 V 1.10.1 p.24 */ - u16 length = 0; struct vidtv_psi_table_sdt_service *s = sdt->service; u16 desc_loop_len; + u16 length = 0; + + /* see ETSI EN 300 468 V 1.10.1 p.24 */ /* * from immediately after 'section_length' until @@ -935,8 +936,8 @@ vidtv_psi_pat_program_init(struct vidtv_psi_table_pat_program *head, void vidtv_psi_pat_program_destroy(struct vidtv_psi_table_pat_program *p) { - struct vidtv_psi_table_pat_program *curr = p; struct vidtv_psi_table_pat_program *tmp = NULL; + struct vidtv_psi_table_pat_program *curr = p; while (curr) { tmp = curr; @@ -945,14 +946,13 @@ vidtv_psi_pat_program_destroy(struct vidtv_psi_table_pat_program *p) } } +/* This function transfers ownership of p to the table */ void vidtv_psi_pat_program_assign(struct vidtv_psi_table_pat *pat, struct vidtv_psi_table_pat_program *p) { - /* This function transfers ownership of p to the table */ - - u16 program_count; struct vidtv_psi_table_pat_program *program; + u16 program_count; do { program_count = 0; @@ -1010,16 +1010,13 @@ struct vidtv_psi_table_pat *vidtv_psi_pat_table_init(u16 transport_stream_id) u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args args) { - /* the number of bytes written by this function */ - u32 nbytes = 0; - const u16 pat_pid = VIDTV_PAT_PID; - u32 crc = INITIAL_CRC; - struct vidtv_psi_table_pat_program *p = args.pat->program; - struct header_write_args h_args = {}; - struct psi_write_args psi_args = {}; + struct psi_write_args psi_args = {}; struct crc32_write_args c_args = {}; + const u16 pat_pid = VIDTV_PAT_PID; + u32 crc = INITIAL_CRC; + u32 nbytes = 0; vidtv_psi_pat_table_update_sec_len(args.pat); @@ -1114,8 +1111,8 @@ vidtv_psi_pmt_stream_init(struct vidtv_psi_table_pmt_stream *head, void vidtv_psi_pmt_stream_destroy(struct vidtv_psi_table_pmt_stream *s) { - struct vidtv_psi_table_pmt_stream *curr_stream = s; struct vidtv_psi_table_pmt_stream *tmp_stream = NULL; + struct vidtv_psi_table_pmt_stream *curr_stream = s; while (curr_stream) { tmp_stream = curr_stream; @@ -1166,11 +1163,11 @@ struct vidtv_psi_table_pmt *vidtv_psi_pmt_table_init(u16 program_number, u16 pcr_pid) { struct vidtv_psi_table_pmt *pmt; - const u16 SYNTAX = 0x1; - const u16 ZERO = 0x0; - const u16 ONES = 0x03; const u16 RESERVED1 = 0x07; const u16 RESERVED2 = 0x0f; + const u16 SYNTAX = 0x1; + const u16 ONES = 0x03; + const u16 ZERO = 0x0; u16 desc_loop_len; pmt = kzalloc(sizeof(*pmt), GFP_KERNEL); @@ -1208,18 +1205,15 @@ struct vidtv_psi_table_pmt *vidtv_psi_pmt_table_init(u16 program_number, u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) { - /* the number of bytes written by this function */ - u32 nbytes = 0; - u32 crc = INITIAL_CRC; - struct vidtv_psi_desc *table_descriptor = args.pmt->descriptor; struct vidtv_psi_table_pmt_stream *stream = args.pmt->stream; struct vidtv_psi_desc *stream_descriptor; - struct header_write_args h_args = {}; struct psi_write_args psi_args = {}; struct desc_write_args d_args = {}; struct crc32_write_args c_args = {}; + u32 crc = INITIAL_CRC; + u32 nbytes = 0; vidtv_psi_pmt_table_update_sec_len(args.pmt); @@ -1317,10 +1311,10 @@ void vidtv_psi_pmt_table_destroy(struct vidtv_psi_table_pmt *pmt) struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 transport_stream_id) { struct vidtv_psi_table_sdt *sdt; + const u16 RESERVED = 0xff; const u16 SYNTAX = 0x1; - const u16 ONE = 0x1; const u16 ONES = 0x03; - const u16 RESERVED = 0xff; + const u16 ONE = 0x1; sdt = kzalloc(sizeof(*sdt), GFP_KERNEL); if (!sdt) @@ -1360,18 +1354,17 @@ struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 transport_stream_id) u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) { - u32 nbytes = 0; - u16 sdt_pid = VIDTV_SDT_PID; /* see ETSI EN 300 468 v1.15.1 p. 11 */ - - u32 crc = INITIAL_CRC; - struct vidtv_psi_table_sdt_service *service = args.sdt->service; struct vidtv_psi_desc *service_desc; - struct header_write_args h_args = {}; struct psi_write_args psi_args = {}; struct desc_write_args d_args = {}; struct crc32_write_args c_args = {}; + u16 sdt_pid = VIDTV_SDT_PID; + u32 nbytes = 0; + u32 crc = INITIAL_CRC; + + /* see ETSI EN 300 468 v1.15.1 p. 11 */ vidtv_psi_sdt_table_update_sec_len(args.sdt); @@ -1520,15 +1513,16 @@ vidtv_psi_sdt_service_assign(struct vidtv_psi_table_sdt *sdt, vidtv_psi_update_version_num(&sdt->header); } +/* + * PMTs contain information about programs. For each program, + * there is one PMT section. This function will create a section + * for each program found in the PAT + */ struct vidtv_psi_table_pmt** -vidtv_psi_pmt_create_sec_for_each_pat_entry(struct vidtv_psi_table_pat *pat, u16 pcr_pid) +vidtv_psi_pmt_create_sec_for_each_pat_entry(struct vidtv_psi_table_pat *pat, + u16 pcr_pid) { - /* - * PMTs contain information about programs. For each program, - * there is one PMT section. This function will create a section - * for each program found in the PAT - */ struct vidtv_psi_table_pat_program *program = pat->program; struct vidtv_psi_table_pmt **pmt_secs; u32 i = 0; @@ -1549,12 +1543,12 @@ vidtv_psi_pmt_create_sec_for_each_pat_entry(struct vidtv_psi_table_pat *pat, u16 return pmt_secs; } +/* find the PMT section associated with 'program_num' */ struct vidtv_psi_table_pmt *vidtv_psi_find_pmt_sec(struct vidtv_psi_table_pmt **pmt_sections, u16 nsections, u16 program_num) { - /* find the PMT section associated with 'program_num' */ struct vidtv_psi_table_pmt *sec = NULL; u32 i; @@ -1616,11 +1610,11 @@ struct vidtv_psi_table_nit char *network_name, struct vidtv_psi_desc_service_list_entry *service_list) { - struct vidtv_psi_table_nit *nit; struct vidtv_psi_table_transport *transport; + struct vidtv_psi_table_nit *nit; const u16 SYNTAX = 0x1; - const u16 ONE = 0x1; const u16 ONES = 0x03; + const u16 ONE = 0x1; nit = kzalloc(sizeof(*nit), GFP_KERNEL); if (!nit) @@ -1677,18 +1671,15 @@ free_nit: u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) { - /* the number of bytes written by this function */ - u32 nbytes = 0; - u32 crc = INITIAL_CRC; - struct vidtv_psi_desc *table_descriptor = args.nit->descriptor; struct vidtv_psi_table_transport *transport = args.nit->transport; struct vidtv_psi_desc *transport_descriptor; - struct header_write_args h_args = {}; struct psi_write_args psi_args = {}; struct desc_write_args d_args = {}; struct crc32_write_args c_args = {}; + u32 crc = INITIAL_CRC; + u32 nbytes = 0; vidtv_psi_nit_table_update_sec_len(args.nit); @@ -1786,8 +1777,8 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) static void vidtv_psi_transport_destroy(struct vidtv_psi_table_transport *t) { - struct vidtv_psi_table_transport *curr_t = t; struct vidtv_psi_table_transport *tmp_t = NULL; + struct vidtv_psi_table_transport *curr_t = t; while (curr_t) { tmp_t = curr_t; @@ -1806,9 +1797,9 @@ void vidtv_psi_nit_table_destroy(struct vidtv_psi_table_nit *nit) void vidtv_psi_eit_table_update_sec_len(struct vidtv_psi_table_eit *eit) { - u16 length = 0; struct vidtv_psi_table_eit_event *e = eit->event; u16 desc_loop_len; + u16 length = 0; /* * from immediately after 'section_length' until @@ -1890,16 +1881,14 @@ struct vidtv_psi_table_eit u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) { - u32 nbytes = 0; - u32 crc = INITIAL_CRC; - struct vidtv_psi_table_eit_event *event = args.eit->event; struct vidtv_psi_desc *event_descriptor; - struct header_write_args h_args = {}; struct psi_write_args psi_args = {}; struct desc_write_args d_args = {}; struct crc32_write_args c_args = {}; + u32 crc = INITIAL_CRC; + u32 nbytes = 0; vidtv_psi_eit_table_update_sec_len(args.eit); @@ -1978,8 +1967,8 @@ u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) struct vidtv_psi_table_eit_event *vidtv_psi_eit_event_init(struct vidtv_psi_table_eit_event *head, u16 event_id) { - struct vidtv_psi_table_eit_event *e; const u8 DURATION_ONE_HOUR[] = {1, 0, 0}; + struct vidtv_psi_table_eit_event *e; e = kzalloc(sizeof(*e), GFP_KERNEL); if (!e) @@ -2003,8 +1992,8 @@ struct vidtv_psi_table_eit_event void vidtv_psi_eit_event_destroy(struct vidtv_psi_table_eit_event *e) { - struct vidtv_psi_table_eit_event *curr_e = e; struct vidtv_psi_table_eit_event *tmp_e = NULL; + struct vidtv_psi_table_eit_event *curr_e = e; while (curr_e) { tmp_e = curr_e; diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.c b/drivers/media/test-drivers/vidtv/vidtv_s302m.c index 569e7a50129f..ce7dd6cafc8b 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.c +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.c @@ -201,10 +201,10 @@ static void vidtv_s302m_alloc_au(struct vidtv_encoder *e) static void vidtv_s302m_compute_sample_count_from_video(struct vidtv_encoder *e) { - struct vidtv_access_unit *au = e->access_units; struct vidtv_access_unit *sync_au = e->sync->access_units; - u32 vau_duration_usecs; + struct vidtv_access_unit *au = e->access_units; u32 sample_duration_usecs; + u32 vau_duration_usecs; u32 s; vau_duration_usecs = USEC_PER_SEC / e->sync->sampling_rate_hz; @@ -290,9 +290,9 @@ static u16 vidtv_s302m_get_sample(struct vidtv_encoder *e) static u32 vidtv_s302m_write_frame(struct vidtv_encoder *e, u16 sample) { - u32 nbytes = 0; - struct vidtv_s302m_frame_16 f = {}; struct vidtv_s302m_ctx *ctx = e->ctx; + struct vidtv_s302m_frame_16 f = {}; + u32 nbytes = 0; /* from ffmpeg: see s302enc.c */ @@ -389,6 +389,8 @@ static void vidtv_s302m_write_frames(struct vidtv_encoder *e) static void *vidtv_s302m_encode(struct vidtv_encoder *e) { + struct vidtv_s302m_ctx *ctx = e->ctx; + /* * According to SMPTE 302M, an audio access unit is specified as those * AES3 words that are associated with a corresponding video frame. @@ -402,8 +404,6 @@ static void *vidtv_s302m_encode(struct vidtv_encoder *e) * ffmpeg */ - struct vidtv_s302m_ctx *ctx = e->ctx; - vidtv_s302m_access_unit_destroy(e); vidtv_s302m_alloc_au(e); @@ -441,9 +441,9 @@ static u32 vidtv_s302m_clear(struct vidtv_encoder *e) struct vidtv_encoder *vidtv_s302m_encoder_init(struct vidtv_s302m_encoder_init_args args) { - struct vidtv_encoder *e; u32 priv_sz = sizeof(struct vidtv_s302m_ctx); struct vidtv_s302m_ctx *ctx; + struct vidtv_encoder *e; e = kzalloc(sizeof(*e), GFP_KERNEL); if (!e) -- cgit v1.2.3 From 330d135679e55659448953c80753c33ef16383aa Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 20 Nov 2020 09:39:03 +0100 Subject: media: vidtv: remove some unused functions Right now, there's no need to access the length of some tables. So, drop the unused functions. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_psi.c | 35 ---------------------------- 1 file changed, 35 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index 375e01480d3d..341af312ad56 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -89,41 +89,6 @@ static void vidtv_psi_update_version_num(struct vidtv_psi_table_header *h) h->version++; } -static u16 -vidtv_psi_sdt_serv_get_desc_loop_len(struct vidtv_psi_table_sdt_service *s) -{ - u16 mask; - u16 ret; - - mask = GENMASK(11, 0); - - ret = be16_to_cpu(s->bitfield) & mask; - return ret; -} - -static u16 -vidtv_psi_pmt_stream_get_desc_loop_len(struct vidtv_psi_table_pmt_stream *s) -{ - u16 mask; - u16 ret; - - mask = GENMASK(9, 0); - - ret = be16_to_cpu(s->bitfield2) & mask; - return ret; -} - -static u16 vidtv_psi_pmt_get_desc_loop_len(struct vidtv_psi_table_pmt *p) -{ - u16 mask; - u16 ret; - - mask = GENMASK(9, 0); - - ret = be16_to_cpu(p->bitfield2) & mask; - return ret; -} - static u16 vidtv_psi_get_sec_len(struct vidtv_psi_table_header *h) { u16 mask; -- cgit v1.2.3 From c857b065abf9bd8f2064cbf82c03aba7277fe2e1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 20 Nov 2020 10:51:50 +0100 Subject: media: vidtv: pre-initialize mux arrays Instead of first zeroing all fields at the mux structs and then filling, do some initialization for the const data when they're created. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_mux.c | 46 ++++++++++++++++------------ 1 file changed, 26 insertions(+), 20 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index 6df9cfd7f33b..728ae7c78827 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -129,11 +129,32 @@ static void vidtv_mux_update_clk(struct vidtv_mux *m) static u32 vidtv_mux_push_si(struct vidtv_mux *m) { - struct vidtv_psi_pat_write_args pat_args = {}; - struct vidtv_psi_pmt_write_args pmt_args = {}; - struct vidtv_psi_sdt_write_args sdt_args = {}; - struct vidtv_psi_nit_write_args nit_args = {}; - struct vidtv_psi_eit_write_args eit_args = {}; + struct vidtv_psi_pat_write_args pat_args = { + .buf = m->mux_buf, + .buf_sz = m->mux_buf_sz, + .pat = m->si.pat, + }; + struct vidtv_psi_pmt_write_args pmt_args = { + .buf = m->mux_buf, + .buf_sz = m->mux_buf_sz, + .pcr_pid = m->pcr_pid, + }; + struct vidtv_psi_sdt_write_args sdt_args = { + .buf = m->mux_buf, + .buf_sz = m->mux_buf_sz, + .sdt = m->si.sdt, + }; + struct vidtv_psi_nit_write_args nit_args = { + .buf = m->mux_buf, + .buf_sz = m->mux_buf_sz, + .nit = m->si.nit, + + }; + struct vidtv_psi_eit_write_args eit_args = { + .buf = m->mux_buf, + .buf_sz = m->mux_buf_sz, + .eit = m->si.eit, + }; u32 initial_offset = m->mux_buf_offset; struct vidtv_mux_pid_ctx *pat_ctx; struct vidtv_mux_pid_ctx *pmt_ctx; @@ -149,10 +170,7 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) nit_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_NIT_PID); eit_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_EIT_PID); - pat_args.buf = m->mux_buf; pat_args.offset = m->mux_buf_offset; - pat_args.pat = m->si.pat; - pat_args.buf_sz = m->mux_buf_sz; pat_args.continuity_counter = &pat_ctx->cc; m->mux_buf_offset += vidtv_psi_pat_write_into(pat_args); @@ -169,38 +187,26 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) pmt_ctx = vidtv_mux_get_pid_ctx(m, pmt_pid); - pmt_args.buf = m->mux_buf; pmt_args.offset = m->mux_buf_offset; pmt_args.pmt = m->si.pmt_secs[i]; pmt_args.pid = pmt_pid; - pmt_args.buf_sz = m->mux_buf_sz; pmt_args.continuity_counter = &pmt_ctx->cc; - pmt_args.pcr_pid = m->pcr_pid; /* write each section into buffer */ m->mux_buf_offset += vidtv_psi_pmt_write_into(pmt_args); } - sdt_args.buf = m->mux_buf; sdt_args.offset = m->mux_buf_offset; - sdt_args.sdt = m->si.sdt; - sdt_args.buf_sz = m->mux_buf_sz; sdt_args.continuity_counter = &sdt_ctx->cc; m->mux_buf_offset += vidtv_psi_sdt_write_into(sdt_args); - nit_args.buf = m->mux_buf; nit_args.offset = m->mux_buf_offset; - nit_args.nit = m->si.nit; - nit_args.buf_sz = m->mux_buf_sz; nit_args.continuity_counter = &nit_ctx->cc; m->mux_buf_offset += vidtv_psi_nit_write_into(nit_args); - eit_args.buf = m->mux_buf; eit_args.offset = m->mux_buf_offset; - eit_args.eit = m->si.eit; - eit_args.buf_sz = m->mux_buf_sz; eit_args.continuity_counter = &eit_ctx->cc; m->mux_buf_offset += vidtv_psi_eit_write_into(eit_args); -- cgit v1.2.3 From ec3eda53f4aec2e1a9cd0df27c12c95e02f8aec0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 20 Nov 2020 11:15:24 +0100 Subject: media: vidtv: cleanup null packet initialization logic Initialize the destination buffer/size and the initial offset when creating the local var. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_mux.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index 728ae7c78827..e0cc74e98632 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -348,7 +348,11 @@ static u32 vidtv_mux_poll_encoders(struct vidtv_mux *m) static u32 vidtv_mux_pad_with_nulls(struct vidtv_mux *m, u32 npkts) { - struct null_packet_write_args args = {}; + struct null_packet_write_args args = { + .dest_buf = m->mux_buf, + .buf_sz = m->mux_buf_sz, + .dest_offset = m->mux_buf_offset, + }; u32 initial_offset = m->mux_buf_offset; struct vidtv_mux_pid_ctx *ctx; u32 nbytes; @@ -356,10 +360,7 @@ static u32 vidtv_mux_pad_with_nulls(struct vidtv_mux *m, u32 npkts) ctx = vidtv_mux_get_pid_ctx(m, TS_NULL_PACKET_PID); - args.dest_buf = m->mux_buf; - args.buf_sz = m->mux_buf_sz; args.continuity_counter = &ctx->cc; - args.dest_offset = m->mux_buf_offset; for (i = 0; i < npkts; ++i) { m->mux_buf_offset += vidtv_ts_null_write_into(args); -- cgit v1.2.3 From b9e09e06e32e61269342e34f41321499da50d428 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 23 Nov 2020 11:24:11 +0100 Subject: media: vidtv: improve EIT data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Place some text at EIT data, and use ISO 8859-15 encoding for the German letter "ü" (u mit umlat) letter. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_channel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index 8206bcefd7c7..b49fb61847e1 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -53,8 +53,8 @@ struct vidtv_channel *vidtv_channel_s302m_init(struct vidtv_channel *head, u16 transport_stream_id) { const __be32 s302m_fid = cpu_to_be32(VIDTV_S302M_FORMAT_IDENTIFIER); - char *event_text = ENCODING_ISO8859_15 "Beethoven's Für Elise"; - char *event_name = ENCODING_ISO8859_15 "Beethoven Music"; + char *event_text = ENCODING_ISO8859_15 "Bagatelle No. 25 in A minor for solo piano, also known as F\xfcr Elise, composed by Ludwig van Beethoven"; + char *event_name = ENCODING_ISO8859_15 "Ludwig van Beethoven: F\xfcr Elise"; struct vidtv_s302m_encoder_init_args encoder_args = {}; char *iso_language_code = ENCODING_ISO8859_15 "eng"; char *provider = ENCODING_ISO8859_15 "LinuxTV.org"; -- cgit v1.2.3 From 1d2b2a6d8c599be2cbb1e984eeb970186694ef38 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 23 Nov 2020 12:20:45 +0100 Subject: media: vidtv: fix the network ID range As defined at ETSI TS 101 162, original network IDs up to 0xfebf are reserved for registration at dvb.org. Let's use, instead, an original network ID at the range 0xff00-0xffff, as this is for private temporary usage. As the same value is also used for the network ID, the range 0xff01-0xffff also fits better, as values lower than that depend if the network is used for satellite, terrestrial, cable of CI. While here, move the TS ID to the bridge code, where it is used, and change its value, as it was identical to the value previously used by network ID. While we could keep the same value, let's change it, just to make easier to check for the new code while reading it with DVB tools like dvbinspector. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_bridge.c | 3 ++- drivers/media/test-drivers/vidtv/vidtv_common.h | 1 - 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_bridge.c b/drivers/media/test-drivers/vidtv/vidtv_bridge.c index d428bdb47ae4..fc64d0c8492a 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_bridge.c +++ b/drivers/media/test-drivers/vidtv/vidtv_bridge.c @@ -29,8 +29,9 @@ #define MUX_BUF_MAX_SZ (MUX_BUF_MIN_SZ * 10) #define TUNER_DEFAULT_ADDR 0x68 #define DEMOD_DEFAULT_ADDR 0x60 -#define VIDTV_DEFAULT_NETWORK_ID 0x744 +#define VIDTV_DEFAULT_NETWORK_ID 0xff44 #define VIDTV_DEFAULT_NETWORK_NAME "LinuxTV.org" +#define VIDTV_DEFAULT_TS_ID 0x4081 /* * The LNBf fake parameters here are the ranges used by an diff --git a/drivers/media/test-drivers/vidtv/vidtv_common.h b/drivers/media/test-drivers/vidtv/vidtv_common.h index 818e7f2b9ec5..42f63fdee681 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_common.h +++ b/drivers/media/test-drivers/vidtv/vidtv_common.h @@ -16,7 +16,6 @@ #define CLOCK_UNIT_27MHZ 27000000 #define VIDTV_SLEEP_USECS 10000 #define VIDTV_MAX_SLEEP_USECS (2 * VIDTV_SLEEP_USECS) -#define VIDTV_DEFAULT_TS_ID 0x744 u32 vidtv_memcpy(void *to, size_t to_offset, -- cgit v1.2.3 From 91a8a240e2806c37eaf730347831f4a7de1535ac Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 23 Nov 2020 13:51:31 +0100 Subject: media: vidtv: properly fill EIT service_id The EIT header ID field should not contain the network ID, but, instead, the service_id of the program described at EIT. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_channel.c | 3 ++- drivers/media/test-drivers/vidtv/vidtv_psi.c | 5 +++-- drivers/media/test-drivers/vidtv/vidtv_psi.h | 3 ++- 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index b49fb61847e1..77e33f33afee 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -450,7 +450,8 @@ int vidtv_channel_si_init(struct vidtv_mux *m) goto free_service_list; m->si.eit = vidtv_psi_eit_table_init(m->network_id, - m->transport_stream_id); + m->transport_stream_id, + programs->service_id); if (!m->si.eit) goto free_nit; diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index 341af312ad56..02dd217bdbf6 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -1809,7 +1809,8 @@ void vidtv_psi_eit_event_assign(struct vidtv_psi_table_eit *eit, struct vidtv_psi_table_eit *vidtv_psi_eit_table_init(u16 network_id, - u16 transport_stream_id) + u16 transport_stream_id, + __be16 service_id) { struct vidtv_psi_table_eit *eit; const u16 SYNTAX = 0x1; @@ -1824,7 +1825,7 @@ struct vidtv_psi_table_eit eit->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ONE << 14) | (ONES << 12)); - eit->header.id = cpu_to_be16(network_id); + eit->header.id = service_id; eit->header.current_next = ONE; eit->header.version = 0x1f; diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index 4fcb2c0615bb..d8645d75c3f1 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -738,7 +738,8 @@ struct vidtv_psi_table_eit { struct vidtv_psi_table_eit *vidtv_psi_eit_table_init(u16 network_id, - u16 transport_stream_id); + u16 transport_stream_id, + u16 service_id); /** * struct vidtv_psi_eit_write_args - Arguments for writing an EIT section -- cgit v1.2.3 From 039b7caed173667eccd8725509f3995c661aae82 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 23 Nov 2020 14:16:40 +0100 Subject: media: vidtv: add a PID entry for the NIT table On normal TS streams, the NIT table has its own entry at PAT, but not at PMT. While here, properly handle alloc problems when creating PMT entries. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_channel.c | 8 +++-- drivers/media/test-drivers/vidtv/vidtv_mux.c | 2 +- drivers/media/test-drivers/vidtv/vidtv_psi.c | 43 +++++++++++++++++------- drivers/media/test-drivers/vidtv/vidtv_psi.h | 3 +- 4 files changed, 39 insertions(+), 17 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index 77e33f33afee..c3261494120e 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -45,6 +45,7 @@ static void vidtv_channel_encoder_destroy(struct vidtv_encoder *e) } #define ENCODING_ISO8859_15 "\x0b" +#define TS_NIT_PID 0x10 /* * init an audio only channel with a s302m encoder @@ -296,6 +297,8 @@ vidtv_channel_pat_prog_cat_into_new(struct vidtv_mux *m) cur_chnl = cur_chnl->next; } + /* Add the NIT table */ + vidtv_psi_pat_program_init(tail, 0, TS_NIT_PID); return head; } @@ -471,7 +474,7 @@ int vidtv_channel_si_init(struct vidtv_mux *m) vidtv_channel_pmt_match_sections(m->channels, m->si.pmt_secs, - m->si.pat->programs); + m->si.pat->num_pmt); vidtv_channel_destroy_service_list(service_list); @@ -498,12 +501,11 @@ free_pat: void vidtv_channel_si_destroy(struct vidtv_mux *m) { - u16 num_programs = m->si.pat->programs; u32 i; vidtv_psi_pat_table_destroy(m->si.pat); - for (i = 0; i < num_programs; ++i) + for (i = 0; i < m->si.pat->num_pmt; ++i) vidtv_psi_pmt_table_destroy(m->si.pmt_secs[i]); kfree(m->si.pmt_secs); diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index e0cc74e98632..0cf784c09024 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -175,7 +175,7 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) m->mux_buf_offset += vidtv_psi_pat_write_into(pat_args); - for (i = 0; i < m->si.pat->programs; ++i) { + for (i = 0; i < m->si.pat->num_pmt; ++i) { pmt_pid = vidtv_psi_pmt_get_pid(m->si.pmt_secs[i], m->si.pat); diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index 02dd217bdbf6..5c887639b676 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -794,7 +794,7 @@ vidtv_psi_pat_table_update_sec_len(struct vidtv_psi_table_pat *pat) length += PAT_LEN_UNTIL_LAST_SECTION_NUMBER; /* do not count the pointer */ - for (i = 0; i < pat->programs; ++i) + for (i = 0; i < pat->num_pat; ++i) length += sizeof(struct vidtv_psi_table_pat_program) - sizeof(struct vidtv_psi_table_pat_program *); @@ -931,7 +931,7 @@ vidtv_psi_pat_program_assign(struct vidtv_psi_table_pat *pat, program = program->next; } - pat->programs = program_count; + pat->num_pat = program_count; pat->program = p; /* Recompute section length */ @@ -966,8 +966,6 @@ struct vidtv_psi_table_pat *vidtv_psi_pat_table_init(u16 transport_stream_id) pat->header.section_id = 0x0; pat->header.last_section = 0x0; - pat->programs = 0; - vidtv_psi_pat_table_update_sec_len(pat); return pat; @@ -1488,22 +1486,43 @@ vidtv_psi_pmt_create_sec_for_each_pat_entry(struct vidtv_psi_table_pat *pat, u16 pcr_pid) { - struct vidtv_psi_table_pat_program *program = pat->program; + struct vidtv_psi_table_pat_program *program; struct vidtv_psi_table_pmt **pmt_secs; - u32 i = 0; + u32 i = 0, num_pmt = 0; - /* a section for each program_id */ - pmt_secs = kcalloc(pat->programs, + /* + * The number of PMT entries is the number of PAT entries + * that contain service_id. That exclude special tables, like NIT + */ + program = pat->program; + while (program) { + if (program->service_id) + num_pmt++; + program = program->next; + } + + pmt_secs = kcalloc(num_pmt, sizeof(struct vidtv_psi_table_pmt *), GFP_KERNEL); if (!pmt_secs) return NULL; - while (program) { - pmt_secs[i] = vidtv_psi_pmt_table_init(be16_to_cpu(program->service_id), pcr_pid); - ++i; - program = program->next; + for (program = pat->program; program; program = program->next) { + if (!program->service_id) + continue; + pmt_secs[i] = vidtv_psi_pmt_table_init(be16_to_cpu(program->service_id), + pcr_pid); + + if (!pmt_secs[i]) { + while (i > 0) { + i--; + vidtv_psi_pmt_table_destroy(pmt_secs[i]); + } + return NULL; + } + i++; } + pat->num_pmt = num_pmt; return pmt_secs; } diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index d8645d75c3f1..c3bd440e1320 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -174,7 +174,8 @@ struct vidtv_psi_table_pat_program { */ struct vidtv_psi_table_pat { struct vidtv_psi_table_header header; - u16 programs; /* Included by libdvbv5, not part of the table and not actually serialized */ + u16 num_pat; + u16 num_pmt; struct vidtv_psi_table_pat_program *program; } __packed; -- cgit v1.2.3 From 11f4933f7bc955c16a54bf402383c5d7e4cfa8dc Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 23 Nov 2020 18:04:14 +0100 Subject: media: vidtv: fix service type As the service currently broadcasts just audio, change the service type to reflect that. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_channel.c | 2 +- drivers/media/test-drivers/vidtv/vidtv_psi.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index c3261494120e..4aab3bb67001 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -81,7 +81,7 @@ struct vidtv_channel s302m->service->descriptor = (struct vidtv_psi_desc *) vidtv_psi_service_desc_init(NULL, - DIGITAL_TELEVISION_SERVICE, + DIGITAL_RADIO_SOUND_SERVICE, name, provider); if (!s302m->service->descriptor) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index c3bd440e1320..4b64715d5759 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -220,6 +220,7 @@ enum service_running_status { enum service_type { /* see ETSI EN 300 468 v1.15.1 p. 77 */ DIGITAL_TELEVISION_SERVICE = 0x1, + DIGITAL_RADIO_SOUND_SERVICE = 0X2, }; /** -- cgit v1.2.3 From bfa4aaebe8c097439feee65f8d39a3bb541b0aea Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 23 Nov 2020 18:40:29 +0100 Subject: media: vidtv: fix service_id at SDT table The service_id there should be equal to the one used on other tables, otherwise, EIT entries won't be valid. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_channel.c | 3 ++- drivers/media/test-drivers/vidtv/vidtv_psi.c | 5 +++-- drivers/media/test-drivers/vidtv/vidtv_psi.h | 3 ++- 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index 4aab3bb67001..8ad6c0744d36 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -424,7 +424,8 @@ int vidtv_channel_si_init(struct vidtv_mux *m) if (!m->si.pat) return -ENOMEM; - m->si.sdt = vidtv_psi_sdt_table_init(m->transport_stream_id); + m->si.sdt = vidtv_psi_sdt_table_init(m->network_id, + m->transport_stream_id); if (!m->si.sdt) goto free_pat; diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index 5c887639b676..77bb560342a6 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -1271,7 +1271,8 @@ void vidtv_psi_pmt_table_destroy(struct vidtv_psi_table_pmt *pmt) kfree(pmt); } -struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 transport_stream_id) +struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 network_id, + u16 transport_stream_id) { struct vidtv_psi_table_sdt *sdt; const u16 RESERVED = 0xff; @@ -1307,7 +1308,7 @@ struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 transport_stream_id) * This can be changed to something more useful, when support for * NIT gets added */ - sdt->network_id = cpu_to_be16(0xff01); + sdt->network_id = cpu_to_be16(network_id); sdt->reserved = RESERVED; vidtv_psi_sdt_table_update_sec_len(sdt); diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index 4b64715d5759..d30c8dd53d11 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -366,7 +366,8 @@ struct vidtv_psi_table_pat *vidtv_psi_pat_table_init(u16 transport_stream_id); struct vidtv_psi_table_pmt *vidtv_psi_pmt_table_init(u16 program_number, u16 pcr_pid); -struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 transport_stream_id); +struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 network_id, + u16 transport_stream_id); struct vidtv_psi_table_sdt_service* vidtv_psi_sdt_service_init(struct vidtv_psi_table_sdt_service *head, -- cgit v1.2.3 From 160028542bb15868c2da0b88bda6335dce221c1c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 23 Nov 2020 16:57:49 +0100 Subject: media: vidtv: add date to the current event The current event is using an undefined date. Instead, it should be the timestamp when the EIT table was generated. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_psi.c | 44 ++++++++++++++++++++++++++-- 1 file changed, 41 insertions(+), 3 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index 77bb560342a6..fcdd61744ab4 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -11,13 +11,16 @@ #define pr_fmt(fmt) KBUILD_MODNAME ":%s, %d: " fmt, __func__, __LINE__ +#include #include #include +#include #include #include #include #include #include +#include #include #include "vidtv_common.h" @@ -1953,16 +1956,51 @@ u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) struct vidtv_psi_table_eit_event *vidtv_psi_eit_event_init(struct vidtv_psi_table_eit_event *head, u16 event_id) { - const u8 DURATION_ONE_HOUR[] = {1, 0, 0}; + const u8 DURATION[] = {0x23, 0x59, 0x59}; /* BCD encoded */ struct vidtv_psi_table_eit_event *e; + struct timespec64 ts; + struct tm time; + int mjd, l; + __be16 mjd_be; e = kzalloc(sizeof(*e), GFP_KERNEL); if (!e) return NULL; e->event_id = cpu_to_be16(event_id); - memset(e->start_time, 0xff, sizeof(e->start_time)); //todo: 0xff means 'unspecified' - memcpy(e->duration, DURATION_ONE_HOUR, sizeof(e->duration)); //todo, default to this for now + + ts = ktime_to_timespec64(ktime_get_real()); + time64_to_tm(ts.tv_sec, 0, &time); + + /* Convert date to Modified Julian Date - per EN 300 468 Annex C */ + if (time.tm_mon < 2) + l = 1; + else + l = 0; + + mjd = 14956 + time.tm_mday; + mjd += (time.tm_year - l) * 36525 / 100; + mjd += (time.tm_mon + 2 + l * 12) * 306001 / 10000; + mjd_be = cpu_to_be16(mjd); + + /* + * Store MJD and hour/min/sec to the event. + * + * Let's make the event to start on a full hour + */ + memcpy(e->start_time, &mjd_be, sizeof(mjd_be)); + e->start_time[2] = bin2bcd(time.tm_hour); + e->start_time[3] = 0; + e->start_time[4] = 0; + + /* + * TODO: for now, the event will last for a day. Should be + * enough for testing purposes, but if one runs the driver + * for more than that, the current event will become invalid. + * So, we need a better code here in order to change the start + * time once the event expires. + */ + memcpy(e->duration, DURATION, sizeof(e->duration)); e->bitfield = cpu_to_be16(RUNNING << 13); -- cgit v1.2.3 From 5edbd330e3a06557642ffb509cc2be39964e26a6 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 24 Nov 2020 08:42:20 +0100 Subject: media: vidtv: simplify PSI write function The function vidtv_psi_ts_psi_write_into() initializes the ts_header fields several times, and receives a struct as argument, instead of using a pointer to struct. Cleanup the function, in order to reduce its stack usage and to avoid initializing the ts_header multiple times. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_psi.c | 130 +++++++++++++-------------- 1 file changed, 63 insertions(+), 67 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index fcdd61744ab4..2b56c642246e 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -162,79 +162,75 @@ static void vidtv_psi_set_sec_len(struct vidtv_psi_table_header *h, u16 new_len) * manage the continuity_counter * add stuffing (i.e. padding bytes) after the CRC */ -static u32 vidtv_psi_ts_psi_write_into(struct psi_write_args args) +static u32 vidtv_psi_ts_psi_write_into(struct psi_write_args *args) { - - u32 nbytes_past_boundary = (args.dest_offset % TS_PACKET_LEN); + struct vidtv_mpeg_ts ts_header = { + .sync_byte = TS_SYNC_BYTE, + .bitfield = cpu_to_be16((args->new_psi_section << 14) | args->pid), + .scrambling = 0, + .payload = 1, + .adaptation_field = 0, /* no adaptation field */ + }; + u32 nbytes_past_boundary = (args->dest_offset % TS_PACKET_LEN); bool aligned = (nbytes_past_boundary == 0); - struct vidtv_mpeg_ts ts_header = {}; - u32 remaining_len = args.len; + u32 remaining_len = args->len; u32 payload_write_len = 0; u32 payload_offset = 0; u32 nbytes = 0; - const u16 PAYLOAD_START = args.new_psi_section; - - if (!args.crc && !args.is_crc) + if (!args->crc && !args->is_crc) pr_warn_ratelimited("Missing CRC for chunk\n"); - if (args.crc) - *args.crc = dvb_crc32(*args.crc, args.from, args.len); + if (args->crc) + *args->crc = dvb_crc32(*args->crc, args->from, args->len); - if (args.new_psi_section && !aligned) { + if (args->new_psi_section && !aligned) { pr_warn_ratelimited("Cannot write a new PSI section in a misaligned buffer\n"); /* forcibly align and hope for the best */ - nbytes += vidtv_memset(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + nbytes += vidtv_memset(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, TS_FILL_BYTE, TS_PACKET_LEN - nbytes_past_boundary); } while (remaining_len) { - nbytes_past_boundary = (args.dest_offset + nbytes) % TS_PACKET_LEN; + nbytes_past_boundary = (args->dest_offset + nbytes) % TS_PACKET_LEN; aligned = (nbytes_past_boundary == 0); if (aligned) { /* if at a packet boundary, write a new TS header */ - ts_header.sync_byte = TS_SYNC_BYTE; - ts_header.bitfield = cpu_to_be16((PAYLOAD_START << 14) | args.pid); - ts_header.scrambling = 0; - ts_header.continuity_counter = *args.continuity_counter; - ts_header.payload = 1; - /* no adaptation field */ - ts_header.adaptation_field = 0; - - /* copy the header */ - nbytes += vidtv_memcpy(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + ts_header.continuity_counter = *args->continuity_counter; + + nbytes += vidtv_memcpy(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, &ts_header, sizeof(ts_header)); /* * This will trigger a discontinuity if the buffer is full, * effectively dropping the packet. */ - vidtv_ts_inc_cc(args.continuity_counter); + vidtv_ts_inc_cc(args->continuity_counter); } /* write the pointer_field in the first byte of the payload */ - if (args.new_psi_section) - nbytes += vidtv_memset(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + if (args->new_psi_section) + nbytes += vidtv_memset(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, 0x0, 1); /* write as much of the payload as possible */ - nbytes_past_boundary = (args.dest_offset + nbytes) % TS_PACKET_LEN; + nbytes_past_boundary = (args->dest_offset + nbytes) % TS_PACKET_LEN; payload_write_len = min(TS_PACKET_LEN - nbytes_past_boundary, remaining_len); - nbytes += vidtv_memcpy(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, - args.from + payload_offset, + nbytes += vidtv_memcpy(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, + args->from + payload_offset, payload_write_len); /* 'payload_write_len' written from a total of 'len' requested*/ @@ -246,12 +242,12 @@ static u32 vidtv_psi_ts_psi_write_into(struct psi_write_args args) * fill the rest of the packet if there is any remaining space unused */ - nbytes_past_boundary = (args.dest_offset + nbytes) % TS_PACKET_LEN; + nbytes_past_boundary = (args->dest_offset + nbytes) % TS_PACKET_LEN; - if (args.is_crc) - nbytes += vidtv_memset(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + if (args->is_crc) + nbytes += vidtv_memset(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, TS_FILL_BYTE, TS_PACKET_LEN - nbytes_past_boundary); @@ -275,7 +271,7 @@ static u32 table_section_crc32_write_into(struct crc32_write_args args) psi_args.is_crc = true; psi_args.dest_buf_sz = args.dest_buf_sz; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); return nbytes; } @@ -662,7 +658,7 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args args) psi_args.dest_buf_sz = args.dest_buf_sz; psi_args.crc = args.crc; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); switch (args.desc->type) { case SERVICE_DESCRIPTOR: @@ -671,25 +667,25 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args args) sizeof_field(struct vidtv_psi_desc_service, provider_name_len); psi_args.from = &((struct vidtv_psi_desc_service *)args.desc)->service_type; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); psi_args.dest_offset = args.dest_offset + nbytes; psi_args.len = ((struct vidtv_psi_desc_service *)args.desc)->provider_name_len; psi_args.from = ((struct vidtv_psi_desc_service *)args.desc)->provider_name; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); psi_args.dest_offset = args.dest_offset + nbytes; psi_args.len = sizeof_field(struct vidtv_psi_desc_service, service_name_len); psi_args.from = &((struct vidtv_psi_desc_service *)args.desc)->service_name_len; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); psi_args.dest_offset = args.dest_offset + nbytes; psi_args.len = ((struct vidtv_psi_desc_service *)args.desc)->service_name_len; psi_args.from = ((struct vidtv_psi_desc_service *)args.desc)->service_name; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); break; case NETWORK_NAME_DESCRIPTOR: @@ -697,7 +693,7 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args args) psi_args.len = args.desc->length; psi_args.from = ((struct vidtv_psi_desc_network_name *)args.desc)->network_name; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); break; case SERVICE_LIST_DESCRIPTOR: @@ -708,7 +704,7 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args args) sizeof(struct vidtv_psi_desc_service_list_entry *); psi_args.from = serv_list_entry; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); serv_list_entry = serv_list_entry->next; } @@ -720,32 +716,32 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args args) psi_args.from = ((struct vidtv_psi_desc_short_event *) args.desc)->iso_language_code; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); psi_args.dest_offset = args.dest_offset + nbytes; psi_args.len = sizeof_field(struct vidtv_psi_desc_short_event, event_name_len); psi_args.from = &((struct vidtv_psi_desc_short_event *) args.desc)->event_name_len; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); psi_args.dest_offset = args.dest_offset + nbytes; psi_args.len = ((struct vidtv_psi_desc_short_event *)args.desc)->event_name_len; psi_args.from = ((struct vidtv_psi_desc_short_event *)args.desc)->event_name; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); psi_args.dest_offset = args.dest_offset + nbytes; psi_args.len = sizeof_field(struct vidtv_psi_desc_short_event, text_len); psi_args.from = &((struct vidtv_psi_desc_short_event *)args.desc)->text_len; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); psi_args.dest_offset = args.dest_offset + nbytes; psi_args.len = ((struct vidtv_psi_desc_short_event *)args.desc)->text_len; psi_args.from = ((struct vidtv_psi_desc_short_event *)args.desc)->text; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); break; @@ -755,7 +751,7 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args args) psi_args.len = args.desc->length; psi_args.from = &args.desc->data; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); break; } @@ -780,7 +776,7 @@ vidtv_psi_table_header_write_into(struct header_write_args args) psi_args.dest_buf_sz = args.dest_buf_sz; psi_args.crc = args.crc; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); return nbytes; } @@ -1014,7 +1010,7 @@ u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args args) sizeof(struct vidtv_psi_table_pat_program *); psi_args.dest_offset = args.offset + nbytes; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); p = p->next; } @@ -1207,7 +1203,7 @@ u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) psi_args.dest_buf_sz = args.buf_sz; psi_args.crc = &crc; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); while (table_descriptor) { /* write the descriptors, if any */ @@ -1232,7 +1228,7 @@ u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) sizeof_field(struct vidtv_psi_table_pmt_stream, bitfield2); psi_args.dest_offset = args.offset + nbytes; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); stream_descriptor = stream->descriptor; @@ -1360,7 +1356,7 @@ u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) psi_args.crc = &crc; /* copy u16 network_id + u8 reserved)*/ - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); while (service) { /* copy the services, if any */ @@ -1371,7 +1367,7 @@ u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) sizeof(struct vidtv_psi_table_sdt_service *); psi_args.dest_offset = args.offset + nbytes; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); service_desc = service->descriptor; @@ -1694,7 +1690,7 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) psi_args.dest_buf_sz = args.buf_sz; psi_args.crc = &crc; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); while (table_descriptor) { /* write the descriptors, if any */ @@ -1718,7 +1714,7 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) psi_args.dest_offset = args.offset + nbytes; psi_args.pid = VIDTV_NIT_PID; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); while (transport) { /* write the transport sections, if any */ @@ -1728,7 +1724,7 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) sizeof_field(struct vidtv_psi_table_transport, bitfield); psi_args.dest_offset = args.offset + nbytes; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); transport_descriptor = transport->descriptor; @@ -1907,7 +1903,7 @@ u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) psi_args.dest_buf_sz = args.buf_sz; psi_args.crc = &crc; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); while (event) { /* copy the events, if any */ @@ -1918,7 +1914,7 @@ u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) sizeof(struct vidtv_psi_table_eit_event *); psi_args.dest_offset = args.offset + nbytes; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); event_descriptor = event->descriptor; -- cgit v1.2.3 From 9e0067417b26f3d9a6e3292323a160f20620a468 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 24 Nov 2020 08:54:58 +0100 Subject: media: vidtv: simplify the crc writing logic Cleanup the table_section_crc32_write_into() function by initializing struct psi_write_args only once and by passing the args as a pointer. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_psi.c | 39 +++++++++++++--------------- 1 file changed, 18 insertions(+), 21 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index 2b56c642246e..f02ee4c9a0f7 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -254,26 +254,23 @@ static u32 vidtv_psi_ts_psi_write_into(struct psi_write_args *args) return nbytes; } -static u32 table_section_crc32_write_into(struct crc32_write_args args) +static u32 table_section_crc32_write_into(struct crc32_write_args *args) { - struct psi_write_args psi_args = {}; - u32 nbytes = 0; + struct psi_write_args psi_args = { + .dest_buf = args->dest_buf, + .from = &args->crc, + .len = CRC_SIZE_IN_BYTES, + .dest_offset = args->dest_offset, + .pid = args->pid, + .new_psi_section = false, + .continuity_counter = args->continuity_counter, + .is_crc = true, + .dest_buf_sz = args->dest_buf_sz, + }; /* the CRC is the last entry in the section */ - psi_args.dest_buf = args.dest_buf; - psi_args.from = &args.crc; - psi_args.len = CRC_SIZE_IN_BYTES; - psi_args.dest_offset = args.dest_offset; - psi_args.pid = args.pid; - psi_args.new_psi_section = false; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = true; - psi_args.dest_buf_sz = args.dest_buf_sz; - - nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - - return nbytes; + return vidtv_psi_ts_psi_write_into(&psi_args); } static void vidtv_psi_desc_chain(struct vidtv_psi_desc *head, struct vidtv_psi_desc *desc) @@ -1023,7 +1020,7 @@ u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args args) c_args.dest_buf_sz = args.buf_sz; /* Write the CRC32 at the end */ - nbytes += table_section_crc32_write_into(c_args); + nbytes += table_section_crc32_write_into(&c_args); return nbytes; } @@ -1258,7 +1255,7 @@ u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) c_args.dest_buf_sz = args.buf_sz; /* Write the CRC32 at the end */ - nbytes += table_section_crc32_write_into(c_args); + nbytes += table_section_crc32_write_into(&c_args); return nbytes; } @@ -1397,7 +1394,7 @@ u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) c_args.dest_buf_sz = args.buf_sz; /* Write the CRC at the end */ - nbytes += table_section_crc32_write_into(c_args); + nbytes += table_section_crc32_write_into(&c_args); return nbytes; } @@ -1754,7 +1751,7 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) c_args.dest_buf_sz = args.buf_sz; /* Write the CRC32 at the end */ - nbytes += table_section_crc32_write_into(c_args); + nbytes += table_section_crc32_write_into(&c_args); return nbytes; } @@ -1944,7 +1941,7 @@ u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) c_args.dest_buf_sz = args.buf_sz; /* Write the CRC at the end */ - nbytes += table_section_crc32_write_into(c_args); + nbytes += table_section_crc32_write_into(&c_args); return nbytes; } -- cgit v1.2.3 From 974ea17692b59e09c5d0af1a3bc09f45d1892ea4 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 24 Nov 2020 09:25:00 +0100 Subject: media: vidtv: cleanup PSI descriptor write function This function initializes the psi_args twice, and receives a struct, instead of a pointer to a struct. Clean it up. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_psi.c | 104 +++++++++++++-------------- 1 file changed, 51 insertions(+), 53 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index f02ee4c9a0f7..decb9b31c86d 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -634,69 +634,67 @@ void vidtv_sdt_desc_assign(struct vidtv_psi_table_sdt *sdt, vidtv_psi_update_version_num(&sdt->header); } -static u32 vidtv_psi_desc_write_into(struct desc_write_args args) +static u32 vidtv_psi_desc_write_into(struct desc_write_args *args) { + struct psi_write_args psi_args = { + .dest_buf = args->dest_buf, + .from = &args->desc->type, + .pid = args->pid, + .new_psi_section = false, + .continuity_counter = args->continuity_counter, + .is_crc = false, + .dest_buf_sz = args->dest_buf_sz, + .crc = args->crc, + .len = sizeof_field(struct vidtv_psi_desc, type) + + sizeof_field(struct vidtv_psi_desc, length), + }; struct vidtv_psi_desc_service_list_entry *serv_list_entry = NULL; - struct psi_write_args psi_args = {}; - /* the number of bytes written by this function */ u32 nbytes = 0; - psi_args.dest_buf = args.dest_buf; - psi_args.from = &args.desc->type; - - psi_args.len = sizeof_field(struct vidtv_psi_desc, type) + - sizeof_field(struct vidtv_psi_desc, length); - - psi_args.dest_offset = args.dest_offset + nbytes; - psi_args.pid = args.pid; - psi_args.new_psi_section = false; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = false; - psi_args.dest_buf_sz = args.dest_buf_sz; - psi_args.crc = args.crc; + psi_args.dest_offset = args->dest_offset + nbytes; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - switch (args.desc->type) { + switch (args->desc->type) { case SERVICE_DESCRIPTOR: - psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.dest_offset = args->dest_offset + nbytes; psi_args.len = sizeof_field(struct vidtv_psi_desc_service, service_type) + sizeof_field(struct vidtv_psi_desc_service, provider_name_len); - psi_args.from = &((struct vidtv_psi_desc_service *)args.desc)->service_type; + psi_args.from = &((struct vidtv_psi_desc_service *)args->desc)->service_type; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - psi_args.dest_offset = args.dest_offset + nbytes; - psi_args.len = ((struct vidtv_psi_desc_service *)args.desc)->provider_name_len; - psi_args.from = ((struct vidtv_psi_desc_service *)args.desc)->provider_name; + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = ((struct vidtv_psi_desc_service *)args->desc)->provider_name_len; + psi_args.from = ((struct vidtv_psi_desc_service *)args->desc)->provider_name; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.dest_offset = args->dest_offset + nbytes; psi_args.len = sizeof_field(struct vidtv_psi_desc_service, service_name_len); - psi_args.from = &((struct vidtv_psi_desc_service *)args.desc)->service_name_len; + psi_args.from = &((struct vidtv_psi_desc_service *)args->desc)->service_name_len; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - psi_args.dest_offset = args.dest_offset + nbytes; - psi_args.len = ((struct vidtv_psi_desc_service *)args.desc)->service_name_len; - psi_args.from = ((struct vidtv_psi_desc_service *)args.desc)->service_name; + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = ((struct vidtv_psi_desc_service *)args->desc)->service_name_len; + psi_args.from = ((struct vidtv_psi_desc_service *)args->desc)->service_name; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); break; case NETWORK_NAME_DESCRIPTOR: - psi_args.dest_offset = args.dest_offset + nbytes; - psi_args.len = args.desc->length; - psi_args.from = ((struct vidtv_psi_desc_network_name *)args.desc)->network_name; + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = args->desc->length; + psi_args.from = ((struct vidtv_psi_desc_network_name *)args->desc)->network_name; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); break; case SERVICE_LIST_DESCRIPTOR: - serv_list_entry = ((struct vidtv_psi_desc_service_list *)args.desc)->service_list; + serv_list_entry = ((struct vidtv_psi_desc_service_list *)args->desc)->service_list; while (serv_list_entry) { - psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.dest_offset = args->dest_offset + nbytes; psi_args.len = sizeof(struct vidtv_psi_desc_service_list_entry) - sizeof(struct vidtv_psi_desc_service_list_entry *); psi_args.from = serv_list_entry; @@ -708,35 +706,35 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args args) break; case SHORT_EVENT_DESCRIPTOR: - psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.dest_offset = args->dest_offset + nbytes; psi_args.len = ISO_LANGUAGE_CODE_LEN; psi_args.from = ((struct vidtv_psi_desc_short_event *) - args.desc)->iso_language_code; + args->desc)->iso_language_code; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.dest_offset = args->dest_offset + nbytes; psi_args.len = sizeof_field(struct vidtv_psi_desc_short_event, event_name_len); psi_args.from = &((struct vidtv_psi_desc_short_event *) - args.desc)->event_name_len; + args->desc)->event_name_len; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - psi_args.dest_offset = args.dest_offset + nbytes; - psi_args.len = ((struct vidtv_psi_desc_short_event *)args.desc)->event_name_len; - psi_args.from = ((struct vidtv_psi_desc_short_event *)args.desc)->event_name; + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = ((struct vidtv_psi_desc_short_event *)args->desc)->event_name_len; + psi_args.from = ((struct vidtv_psi_desc_short_event *)args->desc)->event_name; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.dest_offset = args->dest_offset + nbytes; psi_args.len = sizeof_field(struct vidtv_psi_desc_short_event, text_len); - psi_args.from = &((struct vidtv_psi_desc_short_event *)args.desc)->text_len; + psi_args.from = &((struct vidtv_psi_desc_short_event *)args->desc)->text_len; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - psi_args.dest_offset = args.dest_offset + nbytes; - psi_args.len = ((struct vidtv_psi_desc_short_event *)args.desc)->text_len; - psi_args.from = ((struct vidtv_psi_desc_short_event *)args.desc)->text; + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = ((struct vidtv_psi_desc_short_event *)args->desc)->text_len; + psi_args.from = ((struct vidtv_psi_desc_short_event *)args->desc)->text; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); @@ -744,9 +742,9 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args args) case REGISTRATION_DESCRIPTOR: default: - psi_args.dest_offset = args.dest_offset + nbytes; - psi_args.len = args.desc->length; - psi_args.from = &args.desc->data; + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = args->desc->length; + psi_args.from = &args->desc->data; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); break; @@ -1212,7 +1210,7 @@ u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) d_args.dest_buf_sz = args.buf_sz; d_args.crc = &crc; - nbytes += vidtv_psi_desc_write_into(d_args); + nbytes += vidtv_psi_desc_write_into(&d_args); table_descriptor = table_descriptor->next; } @@ -1239,7 +1237,7 @@ u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) d_args.dest_buf_sz = args.buf_sz; d_args.crc = &crc; - nbytes += vidtv_psi_desc_write_into(d_args); + nbytes += vidtv_psi_desc_write_into(&d_args); stream_descriptor = stream_descriptor->next; } @@ -1378,7 +1376,7 @@ u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) d_args.dest_buf_sz = args.buf_sz; d_args.crc = &crc; - nbytes += vidtv_psi_desc_write_into(d_args); + nbytes += vidtv_psi_desc_write_into(&d_args); service_desc = service_desc->next; } @@ -1699,7 +1697,7 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) d_args.dest_buf_sz = args.buf_sz; d_args.crc = &crc; - nbytes += vidtv_psi_desc_write_into(d_args); + nbytes += vidtv_psi_desc_write_into(&d_args); table_descriptor = table_descriptor->next; } @@ -1735,7 +1733,7 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) d_args.dest_buf_sz = args.buf_sz; d_args.crc = &crc; - nbytes += vidtv_psi_desc_write_into(d_args); + nbytes += vidtv_psi_desc_write_into(&d_args); transport_descriptor = transport_descriptor->next; } @@ -1925,7 +1923,7 @@ u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) d_args.dest_buf_sz = args.buf_sz; d_args.crc = &crc; - nbytes += vidtv_psi_desc_write_into(d_args); + nbytes += vidtv_psi_desc_write_into(&d_args); event_descriptor = event_descriptor->next; } -- cgit v1.2.3 From c570fb9ffc056124fe6dc7ea2c69ca3af3093116 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 24 Nov 2020 09:33:44 +0100 Subject: media: vidtv: cleanup PSI table header function - Pass struct header_write_args as a pointer, instead of passing as a var; - Initialize the psi_args struct only once. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_psi.c | 42 +++++++++++++--------------- 1 file changed, 19 insertions(+), 23 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index decb9b31c86d..c769c7757ef8 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -754,26 +754,22 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args *args) } static u32 -vidtv_psi_table_header_write_into(struct header_write_args args) +vidtv_psi_table_header_write_into(struct header_write_args *args) { - struct psi_write_args psi_args = {}; - /* the number of bytes written by this function */ - u32 nbytes = 0; - - psi_args.dest_buf = args.dest_buf; - psi_args.from = args.h; - psi_args.len = sizeof(struct vidtv_psi_table_header); - psi_args.dest_offset = args.dest_offset; - psi_args.pid = args.pid; - psi_args.new_psi_section = true; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = false; - psi_args.dest_buf_sz = args.dest_buf_sz; - psi_args.crc = args.crc; - - nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + struct psi_write_args psi_args = { + .dest_buf = args->dest_buf, + .from = args->h, + .len = sizeof(struct vidtv_psi_table_header), + .dest_offset = args->dest_offset, + .pid = args->pid, + .new_psi_section = true, + .continuity_counter = args->continuity_counter, + .is_crc = false, + .dest_buf_sz = args->dest_buf_sz, + .crc = args->crc, + }; - return nbytes; + return vidtv_psi_ts_psi_write_into(&psi_args); } void @@ -985,7 +981,7 @@ u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args args) h_args.dest_buf_sz = args.buf_sz; h_args.crc = &crc; - nbytes += vidtv_psi_table_header_write_into(h_args); + nbytes += vidtv_psi_table_header_write_into(&h_args); /* note that the field 'u16 programs' is not really part of the PAT */ @@ -1182,7 +1178,7 @@ u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) h_args.dest_buf_sz = args.buf_sz; h_args.crc = &crc; - nbytes += vidtv_psi_table_header_write_into(h_args); + nbytes += vidtv_psi_table_header_write_into(&h_args); /* write the two bitfields */ psi_args.dest_buf = args.buf; @@ -1334,7 +1330,7 @@ u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) h_args.dest_buf_sz = args.buf_sz; h_args.crc = &crc; - nbytes += vidtv_psi_table_header_write_into(h_args); + nbytes += vidtv_psi_table_header_write_into(&h_args); psi_args.dest_buf = args.buf; psi_args.from = &args.sdt->network_id; @@ -1670,7 +1666,7 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) h_args.dest_buf_sz = args.buf_sz; h_args.crc = &crc; - nbytes += vidtv_psi_table_header_write_into(h_args); + nbytes += vidtv_psi_table_header_write_into(&h_args); /* write the bitfield */ psi_args.dest_buf = args.buf; @@ -1880,7 +1876,7 @@ u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) h_args.dest_buf_sz = args.buf_sz; h_args.crc = &crc; - nbytes += vidtv_psi_table_header_write_into(h_args); + nbytes += vidtv_psi_table_header_write_into(&h_args); psi_args.dest_buf = args.buf; psi_args.from = &args.eit->transport_id; -- cgit v1.2.3 From 7f957515191af5ad78f9905afad5fae584988986 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 24 Nov 2020 09:45:49 +0100 Subject: media: vidtv: cleanup PAT write function Avoid initializing the structs multiple times and pass the PAT struct as a pointer, instead of a var. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_mux.c | 2 +- drivers/media/test-drivers/vidtv/vidtv_psi.c | 57 +++++++++++++++------------- drivers/media/test-drivers/vidtv/vidtv_psi.h | 2 +- 3 files changed, 32 insertions(+), 29 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index 0cf784c09024..200a8000603f 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -173,7 +173,7 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) pat_args.offset = m->mux_buf_offset; pat_args.continuity_counter = &pat_ctx->cc; - m->mux_buf_offset += vidtv_psi_pat_write_into(pat_args); + m->mux_buf_offset += vidtv_psi_pat_write_into(&pat_args); for (i = 0; i < m->si.pat->num_pmt; ++i) { pmt_pid = vidtv_psi_pmt_get_pid(m->si.pmt_secs[i], diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index c769c7757ef8..722be777ff01 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -961,57 +961,60 @@ struct vidtv_psi_table_pat *vidtv_psi_pat_table_init(u16 transport_stream_id) return pat; } -u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args args) +u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args *args) { - struct vidtv_psi_table_pat_program *p = args.pat->program; - struct header_write_args h_args = {}; - struct psi_write_args psi_args = {}; - struct crc32_write_args c_args = {}; - const u16 pat_pid = VIDTV_PAT_PID; + struct vidtv_psi_table_pat_program *p = args->pat->program; + struct header_write_args h_args = { + .dest_buf = args->buf, + .dest_offset = args->offset, + .pid = VIDTV_PAT_PID, + .h = &args->pat->header, + .continuity_counter = args->continuity_counter, + .dest_buf_sz = args->buf_sz, + }; + struct psi_write_args psi_args = { + .dest_buf = args->buf, + .pid = VIDTV_PAT_PID, + .new_psi_section = false, + .continuity_counter = args->continuity_counter, + .is_crc = false, + .dest_buf_sz = args->buf_sz, + }; + struct crc32_write_args c_args = { + .dest_buf = args->buf, + .pid = VIDTV_PAT_PID, + .dest_buf_sz = args->buf_sz, + }; u32 crc = INITIAL_CRC; u32 nbytes = 0; - vidtv_psi_pat_table_update_sec_len(args.pat); + vidtv_psi_pat_table_update_sec_len(args->pat); - h_args.dest_buf = args.buf; - h_args.dest_offset = args.offset; - h_args.h = &args.pat->header; - h_args.pid = pat_pid; - h_args.continuity_counter = args.continuity_counter; - h_args.dest_buf_sz = args.buf_sz; h_args.crc = &crc; nbytes += vidtv_psi_table_header_write_into(&h_args); /* note that the field 'u16 programs' is not really part of the PAT */ - psi_args.dest_buf = args.buf; - psi_args.pid = pat_pid; - psi_args.new_psi_section = false; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = false; - psi_args.dest_buf_sz = args.buf_sz; - psi_args.crc = &crc; + psi_args.crc = &crc; while (p) { /* copy the PAT programs */ psi_args.from = p; /* skip the pointer */ psi_args.len = sizeof(*p) - - sizeof(struct vidtv_psi_table_pat_program *); - psi_args.dest_offset = args.offset + nbytes; + sizeof(struct vidtv_psi_table_pat_program *); + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); p = p->next; } - c_args.dest_buf = args.buf; - c_args.dest_offset = args.offset + nbytes; + c_args.dest_offset = args->offset + nbytes; + c_args.continuity_counter = args->continuity_counter; c_args.crc = cpu_to_be32(crc); - c_args.pid = pat_pid; - c_args.continuity_counter = args.continuity_counter; - c_args.dest_buf_sz = args.buf_sz; /* Write the CRC32 at the end */ nbytes += table_section_crc32_write_into(&c_args); diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index d30c8dd53d11..b6c0518ef4a4 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -556,7 +556,7 @@ struct vidtv_psi_pat_write_args { * equal to the size of the PAT, since more space is needed for TS headers during TS * encapsulation. */ -u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args args); +u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args *args); /** * struct vidtv_psi_sdt_write_args - Arguments for writing a SDT table -- cgit v1.2.3 From db9569f67e2ea14f896d1a6303906294bef900ad Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 24 Nov 2020 09:58:31 +0100 Subject: media: vidtv: cleanup PMT write table function - Pass struct vidtv_psi_pmt_write_args as a pointer; - Avoid initializing structs multiple times. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_mux.c | 2 +- drivers/media/test-drivers/vidtv/vidtv_psi.c | 91 ++++++++++++++-------------- drivers/media/test-drivers/vidtv/vidtv_psi.h | 2 +- 3 files changed, 46 insertions(+), 49 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index 200a8000603f..239e0a242b6e 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -193,7 +193,7 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) pmt_args.continuity_counter = &pmt_ctx->cc; /* write each section into buffer */ - m->mux_buf_offset += vidtv_psi_pmt_write_into(pmt_args); + m->mux_buf_offset += vidtv_psi_pmt_write_into(&pmt_args); } sdt_args.offset = m->mux_buf_offset; diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index 722be777ff01..677cf7fac731 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -1159,54 +1159,58 @@ struct vidtv_psi_table_pmt *vidtv_psi_pmt_table_init(u16 program_number, return pmt; } -u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) +u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args *args) { - struct vidtv_psi_desc *table_descriptor = args.pmt->descriptor; - struct vidtv_psi_table_pmt_stream *stream = args.pmt->stream; + struct vidtv_psi_desc *table_descriptor = args->pmt->descriptor; + struct vidtv_psi_table_pmt_stream *stream = args->pmt->stream; struct vidtv_psi_desc *stream_descriptor; - struct header_write_args h_args = {}; - struct psi_write_args psi_args = {}; - struct desc_write_args d_args = {}; - struct crc32_write_args c_args = {}; + struct header_write_args h_args = { + .dest_buf = args->buf, + .dest_offset = args->offset, + .h = &args->pmt->header, + .pid = args->pid, + .continuity_counter = args->continuity_counter, + .dest_buf_sz = args->buf_sz, + }; + struct psi_write_args psi_args = { + .dest_buf = args->buf, + .from = &args->pmt->bitfield, + .len = sizeof_field(struct vidtv_psi_table_pmt, bitfield) + + sizeof_field(struct vidtv_psi_table_pmt, bitfield2), + .pid = args->pid, + .new_psi_section = false, + .is_crc = false, + .dest_buf_sz = args->buf_sz, + }; + struct desc_write_args d_args = { + .dest_buf = args->buf, + .desc = table_descriptor, + .pid = args->pid, + .dest_buf_sz = args->buf_sz, + }; + struct crc32_write_args c_args = { + .dest_buf = args->buf, + .pid = args->pid, + .dest_buf_sz = args->buf_sz, + }; u32 crc = INITIAL_CRC; u32 nbytes = 0; - vidtv_psi_pmt_table_update_sec_len(args.pmt); + vidtv_psi_pmt_table_update_sec_len(args->pmt); - h_args.dest_buf = args.buf; - h_args.dest_offset = args.offset; - h_args.h = &args.pmt->header; - h_args.pid = args.pid; - h_args.continuity_counter = args.continuity_counter; - h_args.dest_buf_sz = args.buf_sz; h_args.crc = &crc; nbytes += vidtv_psi_table_header_write_into(&h_args); /* write the two bitfields */ - psi_args.dest_buf = args.buf; - psi_args.from = &args.pmt->bitfield; - psi_args.len = sizeof_field(struct vidtv_psi_table_pmt, bitfield) + - sizeof_field(struct vidtv_psi_table_pmt, bitfield2); - - psi_args.dest_offset = args.offset + nbytes; - psi_args.pid = args.pid; - psi_args.new_psi_section = false; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = false; - psi_args.dest_buf_sz = args.buf_sz; - psi_args.crc = &crc; - + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); while (table_descriptor) { /* write the descriptors, if any */ - d_args.dest_buf = args.buf; - d_args.dest_offset = args.offset + nbytes; - d_args.desc = table_descriptor; - d_args.pid = args.pid; - d_args.continuity_counter = args.continuity_counter; - d_args.dest_buf_sz = args.buf_sz; + d_args.dest_offset = args->offset + nbytes; + d_args.continuity_counter = args->continuity_counter; d_args.crc = &crc; nbytes += vidtv_psi_desc_write_into(&d_args); @@ -1214,13 +1218,12 @@ u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) table_descriptor = table_descriptor->next; } + psi_args.len += sizeof_field(struct vidtv_psi_table_pmt_stream, type); while (stream) { /* write the streams, if any */ psi_args.from = stream; - psi_args.len = sizeof_field(struct vidtv_psi_table_pmt_stream, type) + - sizeof_field(struct vidtv_psi_table_pmt_stream, bitfield) + - sizeof_field(struct vidtv_psi_table_pmt_stream, bitfield2); - psi_args.dest_offset = args.offset + nbytes; + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); @@ -1228,12 +1231,9 @@ u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) while (stream_descriptor) { /* write the stream descriptors, if any */ - d_args.dest_buf = args.buf; - d_args.dest_offset = args.offset + nbytes; + d_args.dest_offset = args->offset + nbytes; d_args.desc = stream_descriptor; - d_args.pid = args.pid; - d_args.continuity_counter = args.continuity_counter; - d_args.dest_buf_sz = args.buf_sz; + d_args.continuity_counter = args->continuity_counter; d_args.crc = &crc; nbytes += vidtv_psi_desc_write_into(&d_args); @@ -1244,12 +1244,9 @@ u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) stream = stream->next; } - c_args.dest_buf = args.buf; - c_args.dest_offset = args.offset + nbytes; + c_args.dest_offset = args->offset + nbytes; c_args.crc = cpu_to_be32(crc); - c_args.pid = args.pid; - c_args.continuity_counter = args.continuity_counter; - c_args.dest_buf_sz = args.buf_sz; + c_args.continuity_counter = args->continuity_counter; /* Write the CRC32 at the end */ nbytes += table_section_crc32_write_into(&c_args); diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index b6c0518ef4a4..e1a30455ebbb 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -621,7 +621,7 @@ struct vidtv_psi_pmt_write_args { * equal to the size of the PMT section, since more space is needed for TS headers * during TS encapsulation. */ -u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args); +u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args *args); /** * vidtv_psi_find_pmt_sec - Finds the PMT section for 'program_num' -- cgit v1.2.3 From 6286a4b79b6cc5b4696145a1c3216d0c264efcf7 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 24 Nov 2020 10:20:23 +0100 Subject: media: vidtv: simplify SDT write function - pass struct vidtv_psi_sdt_write_args as a pointer; - avoid initializing struct fields multiple times. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_mux.c | 2 +- drivers/media/test-drivers/vidtv/vidtv_psi.c | 85 ++++++++++++++-------------- drivers/media/test-drivers/vidtv/vidtv_psi.h | 2 +- 3 files changed, 46 insertions(+), 43 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index 239e0a242b6e..ff1c7c586838 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -199,7 +199,7 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) sdt_args.offset = m->mux_buf_offset; sdt_args.continuity_counter = &sdt_ctx->cc; - m->mux_buf_offset += vidtv_psi_sdt_write_into(sdt_args); + m->mux_buf_offset += vidtv_psi_sdt_write_into(&sdt_args); nit_args.offset = m->mux_buf_offset; nit_args.continuity_counter = &nit_ctx->cc; diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index 677cf7fac731..f8cfcd7f42d3 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -1306,57 +1306,66 @@ struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 network_id, return sdt; } -u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) +u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args *args) { - struct vidtv_psi_table_sdt_service *service = args.sdt->service; + struct header_write_args h_args = { + .dest_buf = args->buf, + .dest_offset = args->offset, + .h = &args->sdt->header, + .pid = VIDTV_SDT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct psi_write_args psi_args = { + .dest_buf = args->buf, + .len = sizeof_field(struct vidtv_psi_table_sdt, network_id) + + sizeof_field(struct vidtv_psi_table_sdt, reserved), + .pid = VIDTV_SDT_PID, + .new_psi_section = false, + .is_crc = false, + .dest_buf_sz = args->buf_sz, + }; + struct desc_write_args d_args = { + .dest_buf = args->buf, + .pid = VIDTV_SDT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct crc32_write_args c_args = { + .dest_buf = args->buf, + .pid = VIDTV_SDT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct vidtv_psi_table_sdt_service *service = args->sdt->service; struct vidtv_psi_desc *service_desc; - struct header_write_args h_args = {}; - struct psi_write_args psi_args = {}; - struct desc_write_args d_args = {}; - struct crc32_write_args c_args = {}; - u16 sdt_pid = VIDTV_SDT_PID; u32 nbytes = 0; u32 crc = INITIAL_CRC; /* see ETSI EN 300 468 v1.15.1 p. 11 */ - vidtv_psi_sdt_table_update_sec_len(args.sdt); + vidtv_psi_sdt_table_update_sec_len(args->sdt); - h_args.dest_buf = args.buf; - h_args.dest_offset = args.offset; - h_args.h = &args.sdt->header; - h_args.pid = sdt_pid; - h_args.continuity_counter = args.continuity_counter; - h_args.dest_buf_sz = args.buf_sz; + h_args.continuity_counter = args->continuity_counter; h_args.crc = &crc; nbytes += vidtv_psi_table_header_write_into(&h_args); - psi_args.dest_buf = args.buf; - psi_args.from = &args.sdt->network_id; - - psi_args.len = sizeof_field(struct vidtv_psi_table_sdt, network_id) + - sizeof_field(struct vidtv_psi_table_sdt, reserved); - - psi_args.dest_offset = args.offset + nbytes; - psi_args.pid = sdt_pid; - psi_args.new_psi_section = false; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = false; - psi_args.dest_buf_sz = args.buf_sz; + psi_args.from = &args->sdt->network_id; + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; psi_args.crc = &crc; /* copy u16 network_id + u8 reserved)*/ nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + /* skip both pointers at the end */ + psi_args.len = sizeof(struct vidtv_psi_table_sdt_service) - + sizeof(struct vidtv_psi_desc *) - + sizeof(struct vidtv_psi_table_sdt_service *); + while (service) { /* copy the services, if any */ psi_args.from = service; - /* skip both pointers at the end */ - psi_args.len = sizeof(struct vidtv_psi_table_sdt_service) - - sizeof(struct vidtv_psi_desc *) - - sizeof(struct vidtv_psi_table_sdt_service *); - psi_args.dest_offset = args.offset + nbytes; + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); @@ -1364,12 +1373,9 @@ u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) while (service_desc) { /* copy the service descriptors, if any */ - d_args.dest_buf = args.buf; - d_args.dest_offset = args.offset + nbytes; + d_args.dest_offset = args->offset + nbytes; d_args.desc = service_desc; - d_args.pid = sdt_pid; - d_args.continuity_counter = args.continuity_counter; - d_args.dest_buf_sz = args.buf_sz; + d_args.continuity_counter = args->continuity_counter; d_args.crc = &crc; nbytes += vidtv_psi_desc_write_into(&d_args); @@ -1380,12 +1386,9 @@ u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) service = service->next; } - c_args.dest_buf = args.buf; - c_args.dest_offset = args.offset + nbytes; + c_args.dest_offset = args->offset + nbytes; c_args.crc = cpu_to_be32(crc); - c_args.pid = sdt_pid; - c_args.continuity_counter = args.continuity_counter; - c_args.dest_buf_sz = args.buf_sz; + c_args.continuity_counter = args->continuity_counter; /* Write the CRC at the end */ nbytes += table_section_crc32_write_into(&c_args); diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index e1a30455ebbb..e3913fbe7832 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -588,7 +588,7 @@ struct vidtv_psi_sdt_write_args { * equal to the size of the SDT, since more space is needed for TS headers during TS * encapsulation. */ -u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args); +u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args *args); /** * struct vidtv_psi_pmt_write_args - Arguments for writing a PMT section -- cgit v1.2.3 From 5a5b9fb1a1117b2cf71a162309e370850a626dbf Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 24 Nov 2020 10:37:12 +0100 Subject: media: vidtv: simplify NIT write function - pass struct vidtv_psi_nit_write_args as a pointer; - avoid initializing struct fields multiple times. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_mux.c | 2 +- drivers/media/test-drivers/vidtv/vidtv_psi.c | 91 ++++++++++++++-------------- drivers/media/test-drivers/vidtv/vidtv_psi.h | 2 +- 3 files changed, 47 insertions(+), 48 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index ff1c7c586838..77d691f4ff92 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -204,7 +204,7 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) nit_args.offset = m->mux_buf_offset; nit_args.continuity_counter = &nit_ctx->cc; - m->mux_buf_offset += vidtv_psi_nit_write_into(nit_args); + m->mux_buf_offset += vidtv_psi_nit_write_into(&nit_args); eit_args.offset = m->mux_buf_offset; eit_args.continuity_counter = &eit_ctx->cc; diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index f8cfcd7f42d3..b03e235b0a67 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -1647,53 +1647,60 @@ free_nit: return NULL; } -u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) +u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args *args) { - struct vidtv_psi_desc *table_descriptor = args.nit->descriptor; - struct vidtv_psi_table_transport *transport = args.nit->transport; + struct header_write_args h_args = { + .dest_buf = args->buf, + .dest_offset = args->offset, + .h = &args->nit->header, + .pid = VIDTV_NIT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct psi_write_args psi_args = { + .dest_buf = args->buf, + .from = &args->nit->bitfield, + .len = sizeof_field(struct vidtv_psi_table_nit, bitfield), + .pid = VIDTV_NIT_PID, + .new_psi_section = false, + .is_crc = false, + .dest_buf_sz = args->buf_sz, + }; + struct desc_write_args d_args = { + .dest_buf = args->buf, + .pid = VIDTV_NIT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct crc32_write_args c_args = { + .dest_buf = args->buf, + .pid = VIDTV_NIT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct vidtv_psi_desc *table_descriptor = args->nit->descriptor; + struct vidtv_psi_table_transport *transport = args->nit->transport; struct vidtv_psi_desc *transport_descriptor; - struct header_write_args h_args = {}; - struct psi_write_args psi_args = {}; - struct desc_write_args d_args = {}; - struct crc32_write_args c_args = {}; u32 crc = INITIAL_CRC; u32 nbytes = 0; - vidtv_psi_nit_table_update_sec_len(args.nit); + vidtv_psi_nit_table_update_sec_len(args->nit); - h_args.dest_buf = args.buf; - h_args.dest_offset = args.offset; - h_args.h = &args.nit->header; - h_args.pid = VIDTV_NIT_PID; - h_args.continuity_counter = args.continuity_counter; - h_args.dest_buf_sz = args.buf_sz; + h_args.continuity_counter = args->continuity_counter; h_args.crc = &crc; nbytes += vidtv_psi_table_header_write_into(&h_args); /* write the bitfield */ - psi_args.dest_buf = args.buf; - psi_args.from = &args.nit->bitfield; - psi_args.len = sizeof_field(struct vidtv_psi_table_nit, bitfield); - psi_args.dest_offset = args.offset + nbytes; - psi_args.pid = VIDTV_NIT_PID; - psi_args.new_psi_section = false; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = false; - psi_args.dest_buf_sz = args.buf_sz; + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; psi_args.crc = &crc; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); while (table_descriptor) { /* write the descriptors, if any */ - d_args.dest_buf = args.buf; - d_args.dest_offset = args.offset + nbytes; + d_args.dest_offset = args->offset + nbytes; d_args.desc = table_descriptor; - d_args.pid = VIDTV_NIT_PID; - d_args.continuity_counter = args.continuity_counter; - d_args.dest_buf_sz = args.buf_sz; + d_args.continuity_counter = args->continuity_counter; d_args.crc = &crc; nbytes += vidtv_psi_desc_write_into(&d_args); @@ -1702,21 +1709,19 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) } /* write the second bitfield */ - psi_args.dest_buf = args.buf; - psi_args.from = &args.nit->bitfield2; + psi_args.from = &args->nit->bitfield2; psi_args.len = sizeof_field(struct vidtv_psi_table_nit, bitfield2); - psi_args.dest_offset = args.offset + nbytes; - psi_args.pid = VIDTV_NIT_PID; + psi_args.dest_offset = args->offset + nbytes; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + psi_args.len = sizeof_field(struct vidtv_psi_table_transport, transport_id) + + sizeof_field(struct vidtv_psi_table_transport, network_id) + + sizeof_field(struct vidtv_psi_table_transport, bitfield); while (transport) { /* write the transport sections, if any */ psi_args.from = transport; - psi_args.len = sizeof_field(struct vidtv_psi_table_transport, transport_id) + - sizeof_field(struct vidtv_psi_table_transport, network_id) + - sizeof_field(struct vidtv_psi_table_transport, bitfield); - psi_args.dest_offset = args.offset + nbytes; + psi_args.dest_offset = args->offset + nbytes; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); @@ -1724,12 +1729,9 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) while (transport_descriptor) { /* write the transport descriptors, if any */ - d_args.dest_buf = args.buf; - d_args.dest_offset = args.offset + nbytes; + d_args.dest_offset = args->offset + nbytes; d_args.desc = transport_descriptor; - d_args.pid = VIDTV_NIT_PID; - d_args.continuity_counter = args.continuity_counter; - d_args.dest_buf_sz = args.buf_sz; + d_args.continuity_counter = args->continuity_counter; d_args.crc = &crc; nbytes += vidtv_psi_desc_write_into(&d_args); @@ -1740,12 +1742,9 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args) transport = transport->next; } - c_args.dest_buf = args.buf; - c_args.dest_offset = args.offset + nbytes; + c_args.dest_offset = args->offset + nbytes; c_args.crc = cpu_to_be32(crc); - c_args.pid = VIDTV_NIT_PID; - c_args.continuity_counter = args.continuity_counter; - c_args.dest_buf_sz = args.buf_sz; + c_args.continuity_counter = args->continuity_counter; /* Write the CRC32 at the end */ nbytes += table_section_crc32_write_into(&c_args); diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index e3913fbe7832..8e366ea44cca 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -709,7 +709,7 @@ struct vidtv_psi_nit_write_args { * equal to the size of the NIT, since more space is needed for TS headers during TS * encapsulation. */ -u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args args); +u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args *args); void vidtv_psi_nit_table_destroy(struct vidtv_psi_table_nit *nit); -- cgit v1.2.3 From b087982886e24dd9b50457d4263910ae671be177 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 24 Nov 2020 10:50:58 +0100 Subject: media: vidtv: simplify EIT write function - pass struct vidtv_psi_eit_write_args as a pointer; - avoid initializing struct fields multiple times. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_mux.c | 2 +- drivers/media/test-drivers/vidtv/vidtv_psi.c | 86 ++++++++++++++-------------- drivers/media/test-drivers/vidtv/vidtv_psi.h | 2 +- 3 files changed, 46 insertions(+), 44 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index 77d691f4ff92..b51e6a3b8cbe 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -209,7 +209,7 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) eit_args.offset = m->mux_buf_offset; eit_args.continuity_counter = &eit_ctx->cc; - m->mux_buf_offset += vidtv_psi_eit_write_into(eit_args); + m->mux_buf_offset += vidtv_psi_eit_write_into(&eit_args); nbytes = m->mux_buf_offset - initial_offset; diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index b03e235b0a67..4511a2a98405 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -1857,55 +1857,63 @@ struct vidtv_psi_table_eit return eit; } -u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) +u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args *args) { - struct vidtv_psi_table_eit_event *event = args.eit->event; + struct header_write_args h_args = { + .dest_buf = args->buf, + .dest_offset = args->offset, + .h = &args->eit->header, + .pid = VIDTV_EIT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct psi_write_args psi_args = { + .dest_buf = args->buf, + .len = sizeof_field(struct vidtv_psi_table_eit, transport_id) + + sizeof_field(struct vidtv_psi_table_eit, network_id) + + sizeof_field(struct vidtv_psi_table_eit, last_segment) + + sizeof_field(struct vidtv_psi_table_eit, last_table_id), + .pid = VIDTV_EIT_PID, + .new_psi_section = false, + .is_crc = false, + .dest_buf_sz = args->buf_sz, + }; + struct desc_write_args d_args = { + .dest_buf = args->buf, + .pid = VIDTV_EIT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct crc32_write_args c_args = { + .dest_buf = args->buf, + .pid = VIDTV_EIT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct vidtv_psi_table_eit_event *event = args->eit->event; struct vidtv_psi_desc *event_descriptor; - struct header_write_args h_args = {}; - struct psi_write_args psi_args = {}; - struct desc_write_args d_args = {}; - struct crc32_write_args c_args = {}; u32 crc = INITIAL_CRC; u32 nbytes = 0; - vidtv_psi_eit_table_update_sec_len(args.eit); + vidtv_psi_eit_table_update_sec_len(args->eit); - h_args.dest_buf = args.buf; - h_args.dest_offset = args.offset; - h_args.h = &args.eit->header; - h_args.pid = VIDTV_EIT_PID; - h_args.continuity_counter = args.continuity_counter; - h_args.dest_buf_sz = args.buf_sz; + h_args.continuity_counter = args->continuity_counter; h_args.crc = &crc; nbytes += vidtv_psi_table_header_write_into(&h_args); - psi_args.dest_buf = args.buf; - psi_args.from = &args.eit->transport_id; - - psi_args.len = sizeof_field(struct vidtv_psi_table_eit, transport_id) + - sizeof_field(struct vidtv_psi_table_eit, network_id) + - sizeof_field(struct vidtv_psi_table_eit, last_segment) + - sizeof_field(struct vidtv_psi_table_eit, last_table_id); - - psi_args.dest_offset = args.offset + nbytes; - psi_args.pid = VIDTV_EIT_PID; - psi_args.new_psi_section = false; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = false; - psi_args.dest_buf_sz = args.buf_sz; + psi_args.from = &args->eit->transport_id; + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; psi_args.crc = &crc; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + /* skip both pointers at the end */ + psi_args.len = sizeof(struct vidtv_psi_table_eit_event) - + sizeof(struct vidtv_psi_desc *) - + sizeof(struct vidtv_psi_table_eit_event *); while (event) { /* copy the events, if any */ psi_args.from = event; - /* skip both pointers at the end */ - psi_args.len = sizeof(struct vidtv_psi_table_eit_event) - - sizeof(struct vidtv_psi_desc *) - - sizeof(struct vidtv_psi_table_eit_event *); - psi_args.dest_offset = args.offset + nbytes; + psi_args.dest_offset = args->offset + nbytes; nbytes += vidtv_psi_ts_psi_write_into(&psi_args); @@ -1913,12 +1921,9 @@ u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) while (event_descriptor) { /* copy the event descriptors, if any */ - d_args.dest_buf = args.buf; - d_args.dest_offset = args.offset + nbytes; + d_args.dest_offset = args->offset + nbytes; d_args.desc = event_descriptor; - d_args.pid = VIDTV_EIT_PID; - d_args.continuity_counter = args.continuity_counter; - d_args.dest_buf_sz = args.buf_sz; + d_args.continuity_counter = args->continuity_counter; d_args.crc = &crc; nbytes += vidtv_psi_desc_write_into(&d_args); @@ -1929,12 +1934,9 @@ u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args) event = event->next; } - c_args.dest_buf = args.buf; - c_args.dest_offset = args.offset + nbytes; + c_args.dest_offset = args->offset + nbytes; c_args.crc = cpu_to_be32(crc); - c_args.pid = VIDTV_EIT_PID; - c_args.continuity_counter = args.continuity_counter; - c_args.dest_buf_sz = args.buf_sz; + c_args.continuity_counter = args->continuity_counter; /* Write the CRC at the end */ nbytes += table_section_crc32_write_into(&c_args); diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index 8e366ea44cca..7a5901f11a37 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -773,7 +773,7 @@ struct vidtv_psi_eit_write_args { * equal to the size of the EIT, since more space is needed for TS headers during TS * encapsulation. */ -u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args args); +u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args *args); void vidtv_psi_eit_table_destroy(struct vidtv_psi_table_eit *eit); -- cgit v1.2.3 From 020120af21a643c6adaa4f090c3abf275e3edd68 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 19 Nov 2020 12:17:49 +0100 Subject: media: vidtv.rst: update vidtv documentation Update the vidtv documentation with the relevant changes after the last patches. Signed-off-by: Mauro Carvalho Chehab --- Documentation/driver-api/media/drivers/vidtv.rst | 85 ++++++++++++++++++++---- 1 file changed, 72 insertions(+), 13 deletions(-) diff --git a/Documentation/driver-api/media/drivers/vidtv.rst b/Documentation/driver-api/media/drivers/vidtv.rst index edaceef2808c..52c201798d78 100644 --- a/Documentation/driver-api/media/drivers/vidtv.rst +++ b/Documentation/driver-api/media/drivers/vidtv.rst @@ -258,6 +258,42 @@ Using dvb-fe-tool The first step to check whether the demod loaded successfully is to run:: $ dvb-fe-tool + Device Dummy demod for DVB-T/T2/C/S/S2 (/dev/dvb/adapter0/frontend0) capabilities: + CAN_FEC_1_2 + CAN_FEC_2_3 + CAN_FEC_3_4 + CAN_FEC_4_5 + CAN_FEC_5_6 + CAN_FEC_6_7 + CAN_FEC_7_8 + CAN_FEC_8_9 + CAN_FEC_AUTO + CAN_GUARD_INTERVAL_AUTO + CAN_HIERARCHY_AUTO + CAN_INVERSION_AUTO + CAN_QAM_16 + CAN_QAM_32 + CAN_QAM_64 + CAN_QAM_128 + CAN_QAM_256 + CAN_QAM_AUTO + CAN_QPSK + CAN_TRANSMISSION_MODE_AUTO + DVB API Version 5.11, Current v5 delivery system: DVBC/ANNEX_A + Supported delivery systems: + DVBT + DVBT2 + [DVBC/ANNEX_A] + DVBS + DVBS2 + Frequency range for the current standard: + From: 51.0 MHz + To: 2.15 GHz + Step: 62.5 kHz + Tolerance: 29.5 MHz + Symbol rate ranges for the current standard: + From: 1.00 MBauds + To: 45.0 MBauds This should return what is currently set up at the demod struct, i.e.:: @@ -316,7 +352,7 @@ For this, one should provide a configuration file known as a 'scan file', here's an example:: [Channel] - FREQUENCY = 330000000 + FREQUENCY = 474000000 MODULATION = QAM/AUTO SYMBOL_RATE = 6940000 INNER_FEC = AUTO @@ -337,6 +373,14 @@ You can browse scan tables online here: `dvb-scan-tables Assuming this channel is named 'channel.conf', you can then run:: $ dvbv5-scan channel.conf + dvbv5-scan ~/vidtv.conf + ERROR command BANDWIDTH_HZ (5) not found during retrieve + Cannot calc frequency shift. Either bandwidth/symbol-rate is unavailable (yet). + Scanning frequency #1 330000000 + (0x00) Signal= -68.00dBm + Scanning frequency #2 474000000 + Lock (0x1f) Signal= -34.45dBm C/N= 33.74dB UCB= 0 + Service Beethoven, provider LinuxTV.org: digital television For more information on dvb-scan, check its documentation online here: `dvb-scan Documentation `_. @@ -346,23 +390,38 @@ Using dvb-zap dvbv5-zap is a command line tool that can be used to record MPEG-TS to disk. The typical use is to tune into a channel and put it into record mode. The example -below - which is taken from the documentation - illustrates that:: +below - which is taken from the documentation - illustrates that\ [1]_:: - $ dvbv5-zap -c dvb_channel.conf "trilhas sonoras" -r - using demux '/dev/dvb/adapter0/demux0' + $ dvbv5-zap -c dvb_channel.conf "beethoven" -o music.ts -P -t 10 + using demux 'dvb0.demux0' reading channels from file 'dvb_channel.conf' - service has pid type 05: 204 - tuning to 573000000 Hz - audio pid 104 - dvb_set_pesfilter 104 - Lock (0x1f) Quality= Good Signal= 100.00% C/N= -13.80dB UCB= 70 postBER= 3.14x10^-3 PER= 0 - DVR interface '/dev/dvb/adapter0/dvr0' can now be opened + tuning to 474000000 Hz + pass all PID's to TS + dvb_set_pesfilter 8192 + dvb_dev_set_bufsize: buffer set to 6160384 + Lock (0x1f) Quality= Good Signal= -34.66dBm C/N= 33.41dB UCB= 0 postBER= 0 preBER= 1.05x10^-3 PER= 0 + Lock (0x1f) Quality= Good Signal= -34.57dBm C/N= 33.46dB UCB= 0 postBER= 0 preBER= 1.05x10^-3 PER= 0 + Record to file 'music.ts' started + received 24587768 bytes (2401 Kbytes/sec) + Lock (0x1f) Quality= Good Signal= -34.42dBm C/N= 33.89dB UCB= 0 postBER= 0 preBER= 2.44x10^-3 PER= 0 -The channel can be watched by playing the contents of the DVR interface, with -some player that recognizes the MPEG-TS format, such as *mplayer* or *vlc*. +.. [1] In this example, it records 10 seconds with all program ID's stored + at the music.ts file. + + +The channel can be watched by playing the contents of the stream with some +player that recognizes the MPEG-TS format, such as ``mplayer`` or ``vlc``. By playing the contents of the stream one can visually inspect the workings of -vidtv, e.g.:: +vidtv, e.g., to play a recorded TS file with:: + + $ mplayer music.ts + +or, alternatively, running this command on one terminal:: + + $ dvbv5-zap -c dvb_channel.conf "beethoven" -P -r & + +And, on a second terminal, playing the contents from DVR interface with:: $ mplayer /dev/dvb/adapter0/dvr0 -- cgit v1.2.3 From 44f28934af141149959c4e6495bb60c1903bda32 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 24 Nov 2020 11:27:42 +0100 Subject: media: vidtv.rst: add kernel-doc markups Fix existing issues at the kernel-doc markups and add them to the vidtv.rst file. Signed-off-by: Mauro Carvalho Chehab --- Documentation/driver-api/media/drivers/vidtv.rst | 27 ++++++++++++++++ drivers/media/test-drivers/vidtv/vidtv_bridge.h | 2 +- drivers/media/test-drivers/vidtv/vidtv_channel.h | 1 + drivers/media/test-drivers/vidtv/vidtv_demod.h | 10 +++--- drivers/media/test-drivers/vidtv/vidtv_encoder.h | 4 ++- drivers/media/test-drivers/vidtv/vidtv_mux.h | 5 ++- drivers/media/test-drivers/vidtv/vidtv_pes.h | 5 ++- drivers/media/test-drivers/vidtv/vidtv_psi.h | 39 ++++++++++++------------ drivers/media/test-drivers/vidtv/vidtv_s302m.h | 5 ++- drivers/media/test-drivers/vidtv/vidtv_ts.h | 4 +-- 10 files changed, 70 insertions(+), 32 deletions(-) diff --git a/Documentation/driver-api/media/drivers/vidtv.rst b/Documentation/driver-api/media/drivers/vidtv.rst index 52c201798d78..673bdff919ea 100644 --- a/Documentation/driver-api/media/drivers/vidtv.rst +++ b/Documentation/driver-api/media/drivers/vidtv.rst @@ -484,3 +484,30 @@ A nice addition is to simulate some noise when the signal quality is bad by: - Updating the error statistics accordingly (e.g. BER, etc). - Simulating some noise in the encoded data. + +Functions and structs used within vidtv +--------------------------------------- + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_bridge.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_channel.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_demod.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_encoder.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_mux.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_pes.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_psi.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_s302m.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_ts.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_tuner.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_common.c + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_tuner.c diff --git a/drivers/media/test-drivers/vidtv/vidtv_bridge.h b/drivers/media/test-drivers/vidtv/vidtv_bridge.h index a85068bffd0f..2528adaee27d 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_bridge.h +++ b/drivers/media/test-drivers/vidtv/vidtv_bridge.h @@ -34,7 +34,7 @@ * @adapter: Represents a DTV adapter. See 'dvb_register_adapter'. * @demux: The demux used by the dvb_dmx_swfilter_packets() call. * @dmx_dev: Represents a demux device. - * @dmx_frontend: The frontends associated with the demux. + * @dmx_fe: The frontends associated with the demux. * @i2c_adapter: The i2c_adapter associated with the bridge driver. * @i2c_client_demod: The i2c_clients associated with the demodulator modules. * @i2c_client_tuner: The i2c_clients associated with the tuner modules. diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.h b/drivers/media/test-drivers/vidtv/vidtv_channel.h index 4bc2a4c0980d..fff2e501d375 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.h +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.h @@ -39,6 +39,7 @@ * Every stream will have its corresponding encoder polled to produce TS packets * These packets may be interleaved by the mux and then delivered to the bridge * + * @name: name of the channel * @transport_stream_id: a number to identify the TS, chosen at will. * @service: A _single_ service. Will be concatenated into the SDT. * @program_num: The link between PAT, PMT and SDT. diff --git a/drivers/media/test-drivers/vidtv/vidtv_demod.h b/drivers/media/test-drivers/vidtv/vidtv_demod.h index ab84044f33ba..2b8404661348 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_demod.h +++ b/drivers/media/test-drivers/vidtv/vidtv_demod.h @@ -20,6 +20,9 @@ * modulation and fec_inner * @modulation: see enum fe_modulation * @fec: see enum fe_fec_rate + * @cnr_ok: S/N threshold to consider the signal as OK. Below that, there's + * a chance of losing sync. + * @cnr_good: S/N threshold to consider the signal strong. * * This struct matches values for 'good' and 'ok' CNRs given the combination * of modulation and fec_inner in use. We might simulate some noise if the @@ -53,13 +56,8 @@ struct vidtv_demod_config { * struct vidtv_demod_state - The demodulator state * @frontend: The frontend structure allocated by the demod. * @config: The config used to init the demod. - * @poll_snr: The task responsible for periodically checking the simulated - * signal quality, eventually dropping or reacquiring the TS lock. * @status: the demod status. - * @cold_start: Whether the demod has not been init yet. - * @poll_snr_thread_running: Whether the task responsible for periodically - * checking the simulated signal quality is running. - * @poll_snr_thread_restart: Whether we should restart the poll_snr task. + * @tuner_cnr: current S/N ratio for the signal carrier */ struct vidtv_demod_state { struct dvb_frontend frontend; diff --git a/drivers/media/test-drivers/vidtv/vidtv_encoder.h b/drivers/media/test-drivers/vidtv/vidtv_encoder.h index 0ac5b1e3f666..50e3cf4eb4eb 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_encoder.h +++ b/drivers/media/test-drivers/vidtv/vidtv_encoder.h @@ -103,14 +103,16 @@ enum musical_notes { * @encoder_buf_sz: The encoder buffer size, in bytes * @encoder_buf_offset: Our byte position in the encoder buffer. * @sample_count: How many samples we have encoded in total. + * @access_units: encoder payload units, used for clock references * @src_buf: The source of raw data to be encoded, encoder might set a * default if null. + * @src_buf_sz: size of @src_buf. * @src_buf_offset: Our position in the source buffer. * @is_video_encoder: Whether this a video encoder (as opposed to audio) * @ctx: Encoder-specific state. * @stream_id: Examples: Audio streams (0xc0-0xdf), Video streams * (0xe0-0xef). - * @es_id: The TS PID to use for the elementary stream in this encoder. + * @es_pid: The TS PID to use for the elementary stream in this encoder. * @encode: Prepare enough AUs for the given amount of time. * @clear: Clear the encoder output. * @sync: Attempt to synchronize with this encoder. diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.h b/drivers/media/test-drivers/vidtv/vidtv_mux.h index e186094c4fb7..ad82eb72b841 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.h +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.h @@ -59,6 +59,7 @@ struct vidtv_mux_timing { * @pat: The PAT in use by the muxer. * @pmt_secs: The PMT sections in use by the muxer. One for each program in the PAT. * @sdt: The SDT in use by the muxer. + * @nit: The NIT in use by the muxer. * @eit: the EIT in use by the muxer. */ struct vidtv_mux_si { @@ -86,8 +87,10 @@ struct vidtv_mux_pid_ctx { /** * struct vidtv_mux - A muxer abstraction loosely based in libavcodec/mpegtsenc.c - * @mux_rate_kbytes_sec: The bit rate for the TS, in kbytes. + * @fe: The frontend structure allocated by the muxer. + * @dev: pointer to struct device. * @timing: Keeps track of timing related information. + * @mux_rate_kbytes_sec: The bit rate for the TS, in kbytes. * @pid_ctx: A hash table to keep track of per-PID metadata. * @on_new_packets_available_cb: A callback to inform of new TS packets ready. * @mux_buf: A pointer to a buffer for this muxer. TS packets are stored there diff --git a/drivers/media/test-drivers/vidtv/vidtv_pes.h b/drivers/media/test-drivers/vidtv/vidtv_pes.h index 99f45056adc2..963c59155e72 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_pes.h +++ b/drivers/media/test-drivers/vidtv/vidtv_pes.h @@ -113,8 +113,10 @@ struct pes_header_write_args { * @dest_buf_sz: The size of the dest_buffer * @pid: The PID to use for the TS packets. * @continuity_counter: Incremented on every new TS packet. - * @n_pes_h_s_bytes: Padding bytes. Might be used by an encoder if needed, gets + * @wrote_pes_header: Flag to indicate that the PES header was written + * @n_stuffing_bytes: Padding bytes. Might be used by an encoder if needed, gets * discarded by the decoder. + * @pcr: counter driven by a 27Mhz clock. */ struct pes_ts_header_write_args { void *dest_buf; @@ -145,6 +147,7 @@ struct pes_ts_header_write_args { * @dts: DTS value to send. * @n_pes_h_s_bytes: Padding bytes. Might be used by an encoder if needed, gets * discarded by the decoder. + * @pcr: counter driven by a 27Mhz clock. */ struct pes_write_args { void *dest_buf; diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index 7a5901f11a37..340c9fb8d583 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -43,7 +43,7 @@ enum vidtv_psi_stream_types { STREAM_PRIVATE_DATA = 0x06, /* see ISO/IEC 13818-1 2000 p. 48 */ }; -/** +/* * struct vidtv_psi_desc - A generic PSI descriptor type. * The descriptor length is an 8-bit field specifying the total number of bytes of the data portion * of the descriptor following the byte defining the value of this field. @@ -55,7 +55,7 @@ struct vidtv_psi_desc { u8 data[]; } __packed; -/** +/* * struct vidtv_psi_desc_service - Service descriptor. * See ETSI EN 300 468 section 6.2.33. */ @@ -71,7 +71,7 @@ struct vidtv_psi_desc_service { char *service_name; } __packed; -/** +/* * struct vidtv_psi_desc_registration - A registration descriptor. * See ISO/IEC 13818-1 section 2.6.8 */ @@ -93,7 +93,7 @@ struct vidtv_psi_desc_registration { u8 additional_identification_info[]; } __packed; -/** +/* * struct vidtv_psi_desc_network_name - A network name descriptor * see ETSI EN 300 468 v1.15.1 section 6.2.27 */ @@ -110,7 +110,7 @@ struct vidtv_psi_desc_service_list_entry { struct vidtv_psi_desc_service_list_entry *next; } __packed; -/** +/* * struct vidtv_psi_desc_service_list - A service list descriptor * see ETSI EN 300 468 v1.15.1 section 6.2.35 */ @@ -121,7 +121,7 @@ struct vidtv_psi_desc_service_list { struct vidtv_psi_desc_service_list_entry *service_list; } __packed; -/** +/* * struct vidtv_psi_desc_short_event - A short event descriptor * see ETSI EN 300 468 v1.15.1 section 6.2.37 */ @@ -142,7 +142,7 @@ struct vidtv_psi_desc_short_event char *event_name, char *text); -/** +/* * struct vidtv_psi_table_header - A header that is present for all PSI tables. */ struct vidtv_psi_table_header { @@ -158,7 +158,7 @@ struct vidtv_psi_table_header { u8 last_section; /* last_section_number */ } __packed; -/** +/* * struct vidtv_psi_table_pat_program - A single program in the PAT * See ISO/IEC 13818-1 : 2000 p.43 */ @@ -168,7 +168,7 @@ struct vidtv_psi_table_pat_program { struct vidtv_psi_table_pat_program *next; } __packed; -/** +/* * struct vidtv_psi_table_pat - The Program Allocation Table (PAT) * See ISO/IEC 13818-1 : 2000 p.43 */ @@ -179,7 +179,7 @@ struct vidtv_psi_table_pat { struct vidtv_psi_table_pat_program *program; } __packed; -/** +/* * struct vidtv_psi_table_sdt_service - Represents a service in the SDT. * see ETSI EN 300 468 v1.15.1 section 5.2.3. */ @@ -193,7 +193,7 @@ struct vidtv_psi_table_sdt_service { struct vidtv_psi_table_sdt_service *next; } __packed; -/** +/* * struct vidtv_psi_table_sdt - Represents the Service Description Table * see ETSI EN 300 468 v1.15.1 section 5.2.3. */ @@ -205,7 +205,7 @@ struct vidtv_psi_table_sdt { struct vidtv_psi_table_sdt_service *service; } __packed; -/** +/* * enum service_running_status - Status of a SDT service. * see ETSI EN 300 468 v1.15.1 section 5.2.3 table 6. */ @@ -213,7 +213,7 @@ enum service_running_status { RUNNING = 0x4, }; -/** +/* * enum service_type - The type of a SDT service. * see ETSI EN 300 468 v1.15.1 section 6.2.33, table 81. */ @@ -223,7 +223,7 @@ enum service_type { DIGITAL_RADIO_SOUND_SERVICE = 0X2, }; -/** +/* * struct vidtv_psi_table_pmt_stream - A single stream in the PMT. * See ISO/IEC 13818-1 : 2000 p.46. */ @@ -235,7 +235,7 @@ struct vidtv_psi_table_pmt_stream { struct vidtv_psi_table_pmt_stream *next; } __packed; -/** +/* * struct vidtv_psi_table_pmt - The Program Map Table (PMT). * See ISO/IEC 13818-1 : 2000 p.46. */ @@ -477,7 +477,6 @@ struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc); * vidtv_psi_create_sec_for_each_pat_entry - Create a PMT section for each * program found in the PAT * @pat: The PAT to look for programs. - * @s: The stream loop (one or more streams) * @pcr_pid: packet ID for the PCR to be used for the program described in this * PMT section */ @@ -595,9 +594,11 @@ u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args *args); * @buf: The destination buffer. * @offset: The offset into the destination buffer. * @pmt: A pointer to the PMT. + * @pid: Program ID * @buf_sz: The size of the destination buffer. * @continuity_counter: A pointer to the CC. Incremented on every new packet. - * + * @pcr_pid: The TS PID used for the PSI packets. All channels will share the + * same PCR. */ struct vidtv_psi_pmt_write_args { char *buf; @@ -713,7 +714,7 @@ u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args *args); void vidtv_psi_nit_table_destroy(struct vidtv_psi_table_nit *nit); -/** +/* * struct vidtv_psi_desc_short_event - A short event descriptor * see ETSI EN 300 468 v1.15.1 section 6.2.37 */ @@ -748,7 +749,7 @@ struct vidtv_psi_table_eit * struct vidtv_psi_eit_write_args - Arguments for writing an EIT section * @buf: The destination buffer. * @offset: The offset into the destination buffer. - * @nit: A pointer to the NIT + * @eit: A pointer to the EIT * @buf_sz: The size of the destination buffer. * @continuity_counter: A pointer to the CC. Incremented on every new packet. * diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.h b/drivers/media/test-drivers/vidtv/vidtv_s302m.h index e990b755bb20..9cc94e4a8924 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.h +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.h @@ -33,6 +33,9 @@ * @enc: A pointer to the containing encoder structure. * @frame_index: The current frame in a block * @au_count: The total number of access units encoded up to now + * @last_duration: Duration of the tone currently being played + * @note_offset: Position at the music tone array + * @last_tone: Tone currently being played */ struct vidtv_s302m_ctx { struct vidtv_encoder *enc; @@ -43,7 +46,7 @@ struct vidtv_s302m_ctx { enum musical_notes last_tone; }; -/** +/* * struct vidtv_smpte_s302m_es - s302m MPEG Elementary Stream header. * * See SMPTE 302M 2007 table 1. diff --git a/drivers/media/test-drivers/vidtv/vidtv_ts.h b/drivers/media/test-drivers/vidtv/vidtv_ts.h index 6b989a2c1433..10838a2b8389 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_ts.h +++ b/drivers/media/test-drivers/vidtv/vidtv_ts.h @@ -53,7 +53,7 @@ struct vidtv_mpeg_ts { * @dest_offset: The byte offset into the buffer. * @pid: The TS PID for the PCR packets. * @buf_sz: The size of the buffer in bytes. - * @countinuity_counter: The TS continuity_counter. + * @continuity_counter: The TS continuity_counter. * @pcr: A sample from the system clock. */ struct pcr_write_args { @@ -70,7 +70,7 @@ struct pcr_write_args { * @dest_buf: The buffer to write into. * @dest_offset: The byte offset into the buffer. * @buf_sz: The size of the buffer in bytes. - * @countinuity_counter: The TS continuity_counter. + * @continuity_counter: The TS continuity_counter. */ struct null_packet_write_args { void *dest_buf; -- cgit v1.2.3 From c7acb6b9c07b4b75dffadc3b6466b1b43b3fda21 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Wed, 25 Nov 2020 15:35:19 -0700 Subject: MAINTAINERS: Adding help for coresight subsystem With the steady stream of new features coming into the subsystem it has been clear for some time now that help is needed. Suzuki and Leo have worked extensively on various parts of the project and have agreed to help. While at it add the new location for the coresight git tree. Acked-by: Leo Yan Acked-by : Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20201125223519.734388-1-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index e451dcce054f..b9c823c08b57 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1723,11 +1723,13 @@ F: arch/arm/mach-ep93xx/micro9.c ARM/CORESIGHT FRAMEWORK AND DRIVERS M: Mathieu Poirier -R: Suzuki K Poulose +M: Suzuki K Poulose R: Mike Leach +R: Leo Yan L: coresight@lists.linaro.org (moderated for non-subscribers) L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/coresight/linux.git F: Documentation/ABI/testing/sysfs-bus-coresight-devices-* F: Documentation/devicetree/bindings/arm/coresight-cpu-debug.txt F: Documentation/devicetree/bindings/arm/coresight-cti.yaml -- cgit v1.2.3 From 4ba1cb39fce4464151517a37ce0ac0a1a3f580d6 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Thu, 19 Nov 2020 14:03:17 +0100 Subject: can: gs_usb: fix endianess problem with candleLight firmware The firmware on the original USB2CAN by Geschwister Schneider Technologie Entwicklungs- und Vertriebs UG exchanges all data between the host and the device in host byte order. This is done with the struct gs_host_config::byte_order member, which is sent first to indicate the desired byte order. The widely used open source firmware candleLight doesn't support this feature and exchanges the data in little endian byte order. This breaks if a device with candleLight firmware is used on big endianess systems. To fix this problem, all u32 (but not the struct gs_host_frame::echo_id, which is a transparent cookie) are converted to __le32. Cc: Maximilian Schneider Cc: Hubert Denkmair Reported-by: Michael Rausch Link: https://lore.kernel.org/r/b58aace7-61f3-6df7-c6df-69fee2c66906@netadair.de Tested-by: Oleksij Rempel Fixes: d08e973a77d1 ("can: gs_usb: Added support for the GS_USB CAN devices") Link: https://lore.kernel.org/r/20201120103818.3386964-1-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/gs_usb.c | 131 +++++++++++++++++++++++-------------------- 1 file changed, 70 insertions(+), 61 deletions(-) diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 3005157059ca..018ca3b057a3 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -63,21 +63,27 @@ enum gs_can_identify_mode { }; /* data types passed between host and device */ + +/* The firmware on the original USB2CAN by Geschwister Schneider + * Technologie Entwicklungs- und Vertriebs UG exchanges all data + * between the host and the device in host byte order. This is done + * with the struct gs_host_config::byte_order member, which is sent + * first to indicate the desired byte order. + * + * The widely used open source firmware candleLight doesn't support + * this feature and exchanges the data in little endian byte order. + */ struct gs_host_config { - u32 byte_order; + __le32 byte_order; } __packed; -/* All data exchanged between host and device is exchanged in host byte order, - * thanks to the struct gs_host_config byte_order member, which is sent first - * to indicate the desired byte order. - */ struct gs_device_config { u8 reserved1; u8 reserved2; u8 reserved3; u8 icount; - u32 sw_version; - u32 hw_version; + __le32 sw_version; + __le32 hw_version; } __packed; #define GS_CAN_MODE_NORMAL 0 @@ -87,26 +93,26 @@ struct gs_device_config { #define GS_CAN_MODE_ONE_SHOT BIT(3) struct gs_device_mode { - u32 mode; - u32 flags; + __le32 mode; + __le32 flags; } __packed; struct gs_device_state { - u32 state; - u32 rxerr; - u32 txerr; + __le32 state; + __le32 rxerr; + __le32 txerr; } __packed; struct gs_device_bittiming { - u32 prop_seg; - u32 phase_seg1; - u32 phase_seg2; - u32 sjw; - u32 brp; + __le32 prop_seg; + __le32 phase_seg1; + __le32 phase_seg2; + __le32 sjw; + __le32 brp; } __packed; struct gs_identify_mode { - u32 mode; + __le32 mode; } __packed; #define GS_CAN_FEATURE_LISTEN_ONLY BIT(0) @@ -117,23 +123,23 @@ struct gs_identify_mode { #define GS_CAN_FEATURE_IDENTIFY BIT(5) struct gs_device_bt_const { - u32 feature; - u32 fclk_can; - u32 tseg1_min; - u32 tseg1_max; - u32 tseg2_min; - u32 tseg2_max; - u32 sjw_max; - u32 brp_min; - u32 brp_max; - u32 brp_inc; + __le32 feature; + __le32 fclk_can; + __le32 tseg1_min; + __le32 tseg1_max; + __le32 tseg2_min; + __le32 tseg2_max; + __le32 sjw_max; + __le32 brp_min; + __le32 brp_max; + __le32 brp_inc; } __packed; #define GS_CAN_FLAG_OVERFLOW 1 struct gs_host_frame { u32 echo_id; - u32 can_id; + __le32 can_id; u8 can_dlc; u8 channel; @@ -329,13 +335,13 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) if (!skb) return; - cf->can_id = hf->can_id; + cf->can_id = le32_to_cpu(hf->can_id); cf->can_dlc = get_can_dlc(hf->can_dlc); memcpy(cf->data, hf->data, 8); /* ERROR frames tell us information about the controller */ - if (hf->can_id & CAN_ERR_FLAG) + if (le32_to_cpu(hf->can_id) & CAN_ERR_FLAG) gs_update_state(dev, cf); netdev->stats.rx_packets++; @@ -418,11 +424,11 @@ static int gs_usb_set_bittiming(struct net_device *netdev) if (!dbt) return -ENOMEM; - dbt->prop_seg = bt->prop_seg; - dbt->phase_seg1 = bt->phase_seg1; - dbt->phase_seg2 = bt->phase_seg2; - dbt->sjw = bt->sjw; - dbt->brp = bt->brp; + dbt->prop_seg = cpu_to_le32(bt->prop_seg); + dbt->phase_seg1 = cpu_to_le32(bt->phase_seg1); + dbt->phase_seg2 = cpu_to_le32(bt->phase_seg2); + dbt->sjw = cpu_to_le32(bt->sjw); + dbt->brp = cpu_to_le32(bt->brp); /* request bit timings */ rc = usb_control_msg(interface_to_usbdev(intf), @@ -503,7 +509,7 @@ static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, cf = (struct can_frame *)skb->data; - hf->can_id = cf->can_id; + hf->can_id = cpu_to_le32(cf->can_id); hf->can_dlc = cf->can_dlc; memcpy(hf->data, cf->data, cf->can_dlc); @@ -573,6 +579,7 @@ static int gs_can_open(struct net_device *netdev) int rc, i; struct gs_device_mode *dm; u32 ctrlmode; + u32 flags = 0; rc = open_candev(netdev); if (rc) @@ -640,24 +647,24 @@ static int gs_can_open(struct net_device *netdev) /* flags */ ctrlmode = dev->can.ctrlmode; - dm->flags = 0; if (ctrlmode & CAN_CTRLMODE_LOOPBACK) - dm->flags |= GS_CAN_MODE_LOOP_BACK; + flags |= GS_CAN_MODE_LOOP_BACK; else if (ctrlmode & CAN_CTRLMODE_LISTENONLY) - dm->flags |= GS_CAN_MODE_LISTEN_ONLY; + flags |= GS_CAN_MODE_LISTEN_ONLY; /* Controller is not allowed to retry TX * this mode is unavailable on atmels uc3c hardware */ if (ctrlmode & CAN_CTRLMODE_ONE_SHOT) - dm->flags |= GS_CAN_MODE_ONE_SHOT; + flags |= GS_CAN_MODE_ONE_SHOT; if (ctrlmode & CAN_CTRLMODE_3_SAMPLES) - dm->flags |= GS_CAN_MODE_TRIPLE_SAMPLE; + flags |= GS_CAN_MODE_TRIPLE_SAMPLE; /* finally start device */ - dm->mode = GS_CAN_MODE_START; + dm->mode = cpu_to_le32(GS_CAN_MODE_START); + dm->flags = cpu_to_le32(flags); rc = usb_control_msg(interface_to_usbdev(dev->iface), usb_sndctrlpipe(interface_to_usbdev(dev->iface), 0), GS_USB_BREQ_MODE, @@ -737,9 +744,9 @@ static int gs_usb_set_identify(struct net_device *netdev, bool do_identify) return -ENOMEM; if (do_identify) - imode->mode = GS_CAN_IDENTIFY_ON; + imode->mode = cpu_to_le32(GS_CAN_IDENTIFY_ON); else - imode->mode = GS_CAN_IDENTIFY_OFF; + imode->mode = cpu_to_le32(GS_CAN_IDENTIFY_OFF); rc = usb_control_msg(interface_to_usbdev(dev->iface), usb_sndctrlpipe(interface_to_usbdev(dev->iface), @@ -790,6 +797,7 @@ static struct gs_can *gs_make_candev(unsigned int channel, struct net_device *netdev; int rc; struct gs_device_bt_const *bt_const; + u32 feature; bt_const = kmalloc(sizeof(*bt_const), GFP_KERNEL); if (!bt_const) @@ -830,14 +838,14 @@ static struct gs_can *gs_make_candev(unsigned int channel, /* dev setup */ strcpy(dev->bt_const.name, "gs_usb"); - dev->bt_const.tseg1_min = bt_const->tseg1_min; - dev->bt_const.tseg1_max = bt_const->tseg1_max; - dev->bt_const.tseg2_min = bt_const->tseg2_min; - dev->bt_const.tseg2_max = bt_const->tseg2_max; - dev->bt_const.sjw_max = bt_const->sjw_max; - dev->bt_const.brp_min = bt_const->brp_min; - dev->bt_const.brp_max = bt_const->brp_max; - dev->bt_const.brp_inc = bt_const->brp_inc; + dev->bt_const.tseg1_min = le32_to_cpu(bt_const->tseg1_min); + dev->bt_const.tseg1_max = le32_to_cpu(bt_const->tseg1_max); + dev->bt_const.tseg2_min = le32_to_cpu(bt_const->tseg2_min); + dev->bt_const.tseg2_max = le32_to_cpu(bt_const->tseg2_max); + dev->bt_const.sjw_max = le32_to_cpu(bt_const->sjw_max); + dev->bt_const.brp_min = le32_to_cpu(bt_const->brp_min); + dev->bt_const.brp_max = le32_to_cpu(bt_const->brp_max); + dev->bt_const.brp_inc = le32_to_cpu(bt_const->brp_inc); dev->udev = interface_to_usbdev(intf); dev->iface = intf; @@ -854,28 +862,29 @@ static struct gs_can *gs_make_candev(unsigned int channel, /* can setup */ dev->can.state = CAN_STATE_STOPPED; - dev->can.clock.freq = bt_const->fclk_can; + dev->can.clock.freq = le32_to_cpu(bt_const->fclk_can); dev->can.bittiming_const = &dev->bt_const; dev->can.do_set_bittiming = gs_usb_set_bittiming; dev->can.ctrlmode_supported = 0; - if (bt_const->feature & GS_CAN_FEATURE_LISTEN_ONLY) + feature = le32_to_cpu(bt_const->feature); + if (feature & GS_CAN_FEATURE_LISTEN_ONLY) dev->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY; - if (bt_const->feature & GS_CAN_FEATURE_LOOP_BACK) + if (feature & GS_CAN_FEATURE_LOOP_BACK) dev->can.ctrlmode_supported |= CAN_CTRLMODE_LOOPBACK; - if (bt_const->feature & GS_CAN_FEATURE_TRIPLE_SAMPLE) + if (feature & GS_CAN_FEATURE_TRIPLE_SAMPLE) dev->can.ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES; - if (bt_const->feature & GS_CAN_FEATURE_ONE_SHOT) + if (feature & GS_CAN_FEATURE_ONE_SHOT) dev->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT; SET_NETDEV_DEV(netdev, &intf->dev); - if (dconf->sw_version > 1) - if (bt_const->feature & GS_CAN_FEATURE_IDENTIFY) + if (le32_to_cpu(dconf->sw_version) > 1) + if (feature & GS_CAN_FEATURE_IDENTIFY) netdev->ethtool_ops = &gs_usb_ethtool_ops; kfree(bt_const); @@ -910,7 +919,7 @@ static int gs_usb_probe(struct usb_interface *intf, if (!hconf) return -ENOMEM; - hconf->byte_order = 0x0000beef; + hconf->byte_order = cpu_to_le32(0x0000beef); /* send host config */ rc = usb_control_msg(interface_to_usbdev(intf), -- cgit v1.2.3 From 1a1c436bad340cea1cff815dd2cbb2c4f6af8d43 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Sat, 21 Nov 2020 20:14:19 +0100 Subject: can: mcp251xfd: mcp251xfd_probe(): bail out if no IRQ was given This patch add a check to the mcp251xfd_probe() function to bail out and give the user a proper error message if no IRQ is specified. Otherwise the driver will probe just fine but ifup will fail with a meaningless "RTNETLINK answers: Invalid argument" error message. Link: https://lore.kernel.org/r/20201123113522.3820052-1-mkl@pengutronix.de Reported-by: Niels Petter Signed-off-by: Marc Kleine-Budde --- drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 9c215f7c5f81..8a39be076e14 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -2738,6 +2738,10 @@ static int mcp251xfd_probe(struct spi_device *spi) u32 freq; int err; + if (!spi->irq) + return dev_err_probe(&spi->dev, -ENXIO, + "No IRQ specified (maybe node \"interrupts-extended\" in DT missing)!\n"); + rx_int = devm_gpiod_get_optional(&spi->dev, "microchip,rx-int", GPIOD_IN); if (PTR_ERR(rx_int) == -EPROBE_DEFER) -- cgit v1.2.3 From 777ee15e88616c275ba59db88d3ece20eae0ca9a Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 20 Nov 2020 22:13:06 +0100 Subject: drm: mxsfb: fix fence synchronization The conversion away from the simple display pipeline helper missed to convert the prepare_fb plane callback, so no fences are attached to the atomic state, breaking synchronization with other devices. Fix this by plugging in the drm_gem_fb_prepare_fb helper function. Fixes: ae1ed0093281 ("drm: mxsfb: Stop using DRM simple display pipeline helper") Signed-off-by: Lucas Stach Reviewed-by: Stefan Agner Signed-off-by: Stefan Agner Link: https://patchwork.freedesktop.org/patch/msgid/20201120211306.325841-1-l.stach@pengutronix.de --- drivers/gpu/drm/mxsfb/mxsfb_kms.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/mxsfb/mxsfb_kms.c b/drivers/gpu/drm/mxsfb/mxsfb_kms.c index b721b8b262ce..4d556532281a 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_kms.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_kms.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -485,11 +486,13 @@ static void mxsfb_plane_overlay_atomic_update(struct drm_plane *plane, } static const struct drm_plane_helper_funcs mxsfb_plane_primary_helper_funcs = { + .prepare_fb = drm_gem_fb_prepare_fb, .atomic_check = mxsfb_plane_atomic_check, .atomic_update = mxsfb_plane_primary_atomic_update, }; static const struct drm_plane_helper_funcs mxsfb_plane_overlay_helper_funcs = { + .prepare_fb = drm_gem_fb_prepare_fb, .atomic_check = mxsfb_plane_atomic_check, .atomic_update = mxsfb_plane_overlay_atomic_update, }; -- cgit v1.2.3 From c70582bbf299986234ecf06d128454b4b38ecd2e Mon Sep 17 00:00:00 2001 From: Daniel Abrecht Date: Sun, 8 Nov 2020 21:00:01 +0000 Subject: drm: mxsfb: Implement .format_mod_supported This will make sure applications which use the IN_FORMATS blob to figure out which modifiers they can use will pick up the linear modifier which is needed by mxsfb. Such applications will not work otherwise if an incompatible implicit modifier ends up being selected. Before commit ae1ed0093281 ("drm: mxsfb: Stop using DRM simple display pipeline helper"), the DRM simple display pipeline helper took care of this. Signed-off-by: Daniel Abrecht Fixes: ae1ed0093281 ("drm: mxsfb: Stop using DRM simple display pipeline helper") Reviewed-by: Stefan Agner Signed-off-by: Stefan Agner Link: https://patchwork.freedesktop.org/patch/msgid/2a99ffffc2378209307e0992a6e97e70@nodmarc.danielabrecht.ch --- drivers/gpu/drm/mxsfb/mxsfb_kms.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/gpu/drm/mxsfb/mxsfb_kms.c b/drivers/gpu/drm/mxsfb/mxsfb_kms.c index 4d556532281a..9e1224d54729 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_kms.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_kms.c @@ -485,6 +485,13 @@ static void mxsfb_plane_overlay_atomic_update(struct drm_plane *plane, writel(ctrl, mxsfb->base + LCDC_AS_CTRL); } +static bool mxsfb_format_mod_supported(struct drm_plane *plane, + uint32_t format, + uint64_t modifier) +{ + return modifier == DRM_FORMAT_MOD_LINEAR; +} + static const struct drm_plane_helper_funcs mxsfb_plane_primary_helper_funcs = { .prepare_fb = drm_gem_fb_prepare_fb, .atomic_check = mxsfb_plane_atomic_check, @@ -498,6 +505,7 @@ static const struct drm_plane_helper_funcs mxsfb_plane_overlay_helper_funcs = { }; static const struct drm_plane_funcs mxsfb_plane_funcs = { + .format_mod_supported = mxsfb_format_mod_supported, .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, .destroy = drm_plane_cleanup, -- cgit v1.2.3 From aa4cb898b80a28a610e26d1513e6dd42d995c225 Mon Sep 17 00:00:00 2001 From: Shuming Fan Date: Thu, 26 Nov 2020 17:27:59 +0800 Subject: ASoC: rt5682: change SAR voltage threshold To fix errors in some 4 poles headset detection cases, this patch adjusts the voltage threshold for mic detection. Signed-off-by: Shuming Fan Link: https://lore.kernel.org/r/20201126092759.9427-1-shumingf@realtek.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt5682.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index a9acce7b6cca..d9878173ff89 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -43,6 +43,7 @@ static const struct reg_sequence patch_list[] = { {RT5682_DAC_ADC_DIG_VOL1, 0xa020}, {RT5682_I2C_CTRL, 0x000f}, {RT5682_PLL2_INTERNAL, 0x8266}, + {RT5682_SAR_IL_CMD_3, 0x8365}, }; void rt5682_apply_patch_list(struct rt5682_priv *rt5682, struct device *dev) -- cgit v1.2.3 From 5844cc25fd121074de7895181a2fa1ce100a0fdd Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 26 Nov 2020 20:25:27 +1000 Subject: powerpc/64s: Fix hash ISA v3.0 TLBIEL instruction generation A typo has the R field of the instruction assigned by lucky dip a la register allocator. Fixes: d4748276ae14c ("powerpc/64s: Improve local TLB flush for boot and MCE on POWER9") Signed-off-by: Nicholas Piggin Reviewed-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201126102530.691335-2-npiggin@gmail.com --- arch/powerpc/mm/book3s64/hash_native.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c index 0203cdf48c54..97fa42d7027e 100644 --- a/arch/powerpc/mm/book3s64/hash_native.c +++ b/arch/powerpc/mm/book3s64/hash_native.c @@ -68,7 +68,7 @@ static __always_inline void tlbiel_hash_set_isa300(unsigned int set, unsigned in rs = ((unsigned long)pid << PPC_BITLSHIFT(31)); asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) - : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "r"(r) + : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "i"(r) : "memory"); } -- cgit v1.2.3 From c0b27c517acf8a2b359dd373a7e7e88b01a8308e Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 26 Nov 2020 20:25:28 +1000 Subject: powerpc/64s/pseries: Fix hash tlbiel_all_isa300 for guest kernels tlbiel_all() can not be usable in !HVMODE when running hash presently, remove HV privileged flushes when running in guest to make it usable. Signed-off-by: Nicholas Piggin Reviewed-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201126102530.691335-3-npiggin@gmail.com --- arch/powerpc/mm/book3s64/hash_native.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c index 97fa42d7027e..52e170bd95ae 100644 --- a/arch/powerpc/mm/book3s64/hash_native.c +++ b/arch/powerpc/mm/book3s64/hash_native.c @@ -92,16 +92,15 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) asm volatile("ptesync": : :"memory"); /* - * Flush the first set of the TLB, and any caching of partition table - * entries. Then flush the remaining sets of the TLB. Hash mode uses - * partition scoped TLB translations. + * Flush the partition table cache if this is HV mode. */ - tlbiel_hash_set_isa300(0, is, 0, 2, 0); - for (set = 1; set < num_sets; set++) - tlbiel_hash_set_isa300(set, is, 0, 0, 0); + if (early_cpu_has_feature(CPU_FTR_HVMODE)) + tlbiel_hash_set_isa300(0, is, 0, 2, 0); /* - * Now invalidate the process table cache. + * Now invalidate the process table cache. UPRT=0 HPT modes (what + * current hardware implements) do not use the process table, but + * add the flushes anyway. * * From ISA v3.0B p. 1078: * The following forms are invalid. @@ -110,6 +109,14 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) */ tlbiel_hash_set_isa300(0, is, 0, 2, 1); + /* + * Then flush the sets of the TLB proper. Hash mode uses + * partition scoped TLB translations, which may be flushed + * in !HV mode. + */ + for (set = 0; set < num_sets; set++) + tlbiel_hash_set_isa300(set, is, 0, 0, 0); + ppc_after_tlbiel_barrier(); asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory"); -- cgit v1.2.3 From 8ff00399b153440c1c83e20c43020385b416415b Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 26 Nov 2020 20:25:29 +1000 Subject: kernel/cpu: add arch override for clear_tasks_mm_cpumask() mm handling powerpc/64s keeps a counter in the mm which counts bits set in mm_cpumask as well as other things. This means it can't use generic code to clear bits out of the mask and doesn't adjust the arch specific counter. Add an arch override that allows powerpc/64s to use clear_tasks_mm_cpumask(). Signed-off-by: Nicholas Piggin Reviewed-by: Aneesh Kumar K.V Acked-by: Peter Zijlstra (Intel) Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201126102530.691335-4-npiggin@gmail.com --- kernel/cpu.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/cpu.c b/kernel/cpu.c index 6ff2578ecf17..2b8d7a5db383 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -815,6 +815,10 @@ void __init cpuhp_threads_init(void) } #ifdef CONFIG_HOTPLUG_CPU +#ifndef arch_clear_mm_cpumask_cpu +#define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) +#endif + /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id @@ -850,7 +854,7 @@ void clear_tasks_mm_cpumask(int cpu) t = find_lock_task_mm(p); if (!t) continue; - cpumask_clear_cpu(cpu, mm_cpumask(t->mm)); + arch_clear_mm_cpumask_cpu(cpu, t->mm); task_unlock(t); } rcu_read_unlock(); -- cgit v1.2.3 From 01b0f0eae0812e80efeee4ee17687e5386335e08 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 26 Nov 2020 20:25:30 +1000 Subject: powerpc/64s: Trim offlined CPUs from mm_cpumasks When offlining a CPU, powerpc/64s does not flush TLBs, rather it just leaves the CPU set in mm_cpumasks, so it continues to receive TLBIEs to manage its TLBs. However the exit_flush_lazy_tlbs() function expects that after returning, all CPUs (except self) have flushed TLBs for that mm, in which case TLBIEL can be used for this flush. This breaks for offline CPUs because they don't get the IPI to flush their TLB. This can lead to stale translations. Fix this by clearing the CPU from mm_cpumasks, then flushing all TLBs before going offline. These offlined CPU bits stuck in the cpumask also prevents the cpumask from being trimmed back to local mode, which means continual broadcast IPIs or TLBIEs are needed for TLB flushing. This patch prevents that situation too. A cast of many were involved in working this out, but in particular Milton, Aneesh, Paul made key discoveries. Fixes: 0cef77c7798a7 ("powerpc/64s/radix: flush remote CPUs out of single-threaded mm_cpumask") Signed-off-by: Nicholas Piggin Reviewed-by: Aneesh Kumar K.V Debugged-by: Milton Miller Debugged-by: Aneesh Kumar K.V Debugged-by: Paul Mackerras Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201126102530.691335-5-npiggin@gmail.com --- arch/powerpc/include/asm/book3s/64/mmu.h | 12 ++++++++++++ arch/powerpc/mm/book3s64/mmu_context.c | 20 ++++++++++++++++++++ arch/powerpc/platforms/powermac/smp.c | 2 ++ arch/powerpc/platforms/powernv/smp.c | 3 +++ arch/powerpc/platforms/pseries/hotplug-cpu.c | 3 +++ 5 files changed, 40 insertions(+) diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index e0b52940e43c..750918451dd2 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -242,6 +242,18 @@ extern void radix_init_pseries(void); static inline void radix_init_pseries(void) { }; #endif +#ifdef CONFIG_HOTPLUG_CPU +#define arch_clear_mm_cpumask_cpu(cpu, mm) \ + do { \ + if (cpumask_test_cpu(cpu, mm_cpumask(mm))) { \ + atomic_dec(&(mm)->context.active_cpus); \ + cpumask_clear_cpu(cpu, mm_cpumask(mm)); \ + } \ + } while (0) + +void cleanup_cpu_mmu_context(void); +#endif + static inline int get_user_context(mm_context_t *ctx, unsigned long ea) { int index = ea >> MAX_EA_BITS_PER_CONTEXT; diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c index 1c54821de7bf..0c8557220ae2 100644 --- a/arch/powerpc/mm/book3s64/mmu_context.c +++ b/arch/powerpc/mm/book3s64/mmu_context.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -307,3 +308,22 @@ void radix__switch_mmu_context(struct mm_struct *prev, struct mm_struct *next) isync(); } #endif + +/** + * cleanup_cpu_mmu_context - Clean up MMU details for this CPU (newly offlined) + * + * This clears the CPU from mm_cpumask for all processes, and then flushes the + * local TLB to ensure TLB coherency in case the CPU is onlined again. + * + * KVM guest translations are not necessarily flushed here. If KVM started + * using mm_cpumask or the Linux APIs which do, this would have to be resolved. + */ +#ifdef CONFIG_HOTPLUG_CPU +void cleanup_cpu_mmu_context(void) +{ + int cpu = smp_processor_id(); + + clear_tasks_mm_cpumask(cpu); + tlbiel_all(); +} +#endif diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index 74ebe664b016..adae2a6712e1 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -911,6 +911,8 @@ static int smp_core99_cpu_disable(void) mpic_cpu_set_priority(0xf); + cleanup_cpu_mmu_context(); + return 0; } diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 54c4ba45c7ce..cbb67813cd5d 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -143,6 +143,9 @@ static int pnv_smp_cpu_disable(void) xive_smp_disable_cpu(); else xics_migrate_irqs_away(); + + cleanup_cpu_mmu_context(); + return 0; } diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index f2837e33bf5d..a02012f1b04a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -90,6 +90,9 @@ static int pseries_cpu_disable(void) xive_smp_disable_cpu(); else xics_migrate_irqs_away(); + + cleanup_cpu_mmu_context(); + return 0; } -- cgit v1.2.3 From 15d89c9f6f4a186ade7aefbe77e7ede9746b6c47 Mon Sep 17 00:00:00 2001 From: Iakov 'Jake' Kirilenko Date: Thu, 5 Nov 2020 18:25:56 +0300 Subject: platform/x86: thinkpad_acpi: add P1 gen3 second fan support Tested on my P1 gen3, works fine with `thinkfan`. Since thinkpad_acpi fan control is off by default, it is safe to add 2nd fan control for brave overclockers Signed-off-by: Iakov 'Jake' Kirilenko Link: https://lore.kernel.org/r/20201105152556.34073-1-jake.kirilenko@gmail.com Signed-off-by: Hans de Goede --- drivers/platform/x86/thinkpad_acpi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index e3810675090a..4d64ba29132b 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -8776,6 +8776,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('N', '2', 'C', TPACPI_FAN_2CTL), /* P52 / P72 */ TPACPI_Q_LNV3('N', '2', 'E', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (1st gen) */ TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (2nd gen) */ + TPACPI_Q_LNV3('N', '2', 'V', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (3nd gen) */ }; static int __init fan_init(struct ibm_init_struct *iibm) -- cgit v1.2.3 From f2eae1888cf22590c38764b8fa3c989c0283870e Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 6 Nov 2020 15:01:30 +0100 Subject: platform/x86: thinkpad_acpi: Do not report SW_TABLET_MODE on Yoga 11e The Yoga 11e series has 2 accelerometers described by a BOSC0200 ACPI node. This setup relies on a Windows service which reads both accelerometers and then calculates the angle between the 2 halves to determine laptop / tent / tablet mode and then reports the calculated mode back to the EC by calling special ACPI methods on the BOSC0200 node. The bmc150 iio driver does not support this (it involves double calculations requiring sqrt and arccos so this really needs to be done in userspace), as a result of this on the Yoga 11e the thinkpad_acpi code always reports SW_TABLET_MODE=0, starting with GNOME 3.38 reporting SW_TABLET_MODE=0 causes GNOME to: 1. Not show the onscreen keyboard when a text-input field is focussed with the touchscreen. 2. Disable accelerometer based auto display-rotation. This makes sense when in laptop-mode but not when in tablet-mode. But since for the Yoga 11e the thinkpad_acpi code always reports SW_TABLET_MODE=0, GNOME does not know when the device is in tablet-mode. Stop reporting the broken (always 0) SW_TABLET_MODE on Yoga 11e models to fix this. Note there are plans for userspace to support 360 degree hinges style 2-in-1s with 2 accelerometers and figure out the mode by itself, see: https://gitlab.freedesktop.org/hadess/iio-sensor-proxy/-/issues/216 Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20201106140130.46820-1-hdegoede@redhat.com --- drivers/platform/x86/thinkpad_acpi.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 4d64ba29132b..e479c844c2bc 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -3218,7 +3218,14 @@ static int hotkey_init_tablet_mode(void) in_tablet_mode = hotkey_gmms_get_tablet_mode(res, &has_tablet_mode); - if (has_tablet_mode) + /* + * The Yoga 11e series has 2 accelerometers described by a + * BOSC0200 ACPI node. This setup relies on a Windows service + * which calls special ACPI methods on this node to report + * the laptop/tent/tablet mode to the EC. The bmc150 iio driver + * does not support this, so skip the hotkey on these models. + */ + if (has_tablet_mode && !acpi_dev_present("BOSC0200", "1", -1)) tp_features.hotkey_tablet = TP_HOTKEY_TABLET_USES_GMMS; type = "GMMS"; } else if (acpi_evalf(hkey_handle, &res, "MHKG", "qd")) { -- cgit v1.2.3 From c986a7024916c92a775fc8d853fba3cae1d5fde4 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 9 Nov 2020 11:35:50 +0100 Subject: platform/x86: thinkpad_acpi: Add BAT1 is primary battery quirk for Thinkpad Yoga 11e 4th gen The Thinkpad Yoga 11e 4th gen with the N3450 / Celeron CPU only has one battery which is named BAT1 instead of the expected BAT0, add a quirk for this. This fixes not being able to set the charging tresholds on this model; and this alsoe fixes the following errors in dmesg: ACPI: \_SB_.PCI0.LPCB.EC__.HKEY: BCTG evaluated but flagged as error thinkpad_acpi: Error probing battery 2 battery: extension failed to load: ThinkPad Battery Extension battery: extension unregistered: ThinkPad Battery Extension Note that the added quirk is for the "R0K" BIOS versions which are used on the Thinkpad Yoga 11e 4th gen's with a Celeron CPU, there is a separate "R0L" BIOS for the i3/i5 based versions. This may also need the same quirk, but if that really is necessary is unknown. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20201109103550.16265-1-hdegoede@redhat.com --- drivers/platform/x86/thinkpad_acpi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index e479c844c2bc..36d9594bca7f 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -9711,6 +9711,7 @@ static const struct tpacpi_quirk battery_quirk_table[] __initconst = { TPACPI_Q_LNV3('R', '0', 'B', true), /* Thinkpad 11e gen 3 */ TPACPI_Q_LNV3('R', '0', 'C', true), /* Thinkpad 13 */ TPACPI_Q_LNV3('R', '0', 'J', true), /* Thinkpad 13 gen 2 */ + TPACPI_Q_LNV3('R', '0', 'K', true), /* Thinkpad 11e gen 4 celeron BIOS */ }; static int __init tpacpi_battery_init(struct ibm_init_struct *ibm) -- cgit v1.2.3 From e40cc1b476d60f22628741e53cf3446a29e6e6b9 Mon Sep 17 00:00:00 2001 From: Benjamin Berg Date: Mon, 23 Nov 2020 14:21:57 +0100 Subject: platform/x86: thinkpad_acpi: Send tablet mode switch at wakeup time The lid state may change while the machine is suspended. As such, we may need to re-check the state at wake-up time (at least when waking up from hibernation). Add the appropriate call to the resume handler in order to sync the SW_TABLET_MODE switch state with the hardware state. Fixes: dda3ec0aa631 ("platform/x86: thinkpad_acpi: Implement tablet mode using GMMS method") BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=210269 Signed-off-by: Benjamin Berg Acked-by: Henrique de Moraes Holschuh Link: https://lore.kernel.org/r/20201123132157.866303-1-benjamin@sipsolutions.net Signed-off-by: Hans de Goede --- drivers/platform/x86/thinkpad_acpi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 36d9594bca7f..0778458ead83 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -4235,6 +4235,7 @@ static void hotkey_resume(void) pr_err("error while attempting to reset the event firmware interface\n"); tpacpi_send_radiosw_update(); + tpacpi_input_send_tabletsw(); hotkey_tablet_mode_notify_change(); hotkey_wakeup_reason_notify_change(); hotkey_wakeup_hotunplug_complete_notify_change(); -- cgit v1.2.3 From 80a8c3185f5047dc7438ed226b72385bf93b4071 Mon Sep 17 00:00:00 2001 From: Matthias Maier Date: Wed, 25 Nov 2020 18:04:16 -0600 Subject: platform/x86: thinkpad_acpi: Whitelist P15 firmware for dual fan control This commit enables dual fan control for the following new Lenovo models: P15, P15v. Signed-off-by: Matthias Maier Link: https://lore.kernel.org/r/20201126000416.2459645-2-tamiko-ibm-acpi-devel@43-1.org Signed-off-by: Hans de Goede --- drivers/platform/x86/thinkpad_acpi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 0778458ead83..c404706379d9 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -8785,6 +8785,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('N', '2', 'E', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (1st gen) */ TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (2nd gen) */ TPACPI_Q_LNV3('N', '2', 'V', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (3nd gen) */ + TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL), /* P15 (1st gen) / P15v (1st gen) */ }; static int __init fan_init(struct ibm_init_struct *iibm) -- cgit v1.2.3 From 9e7a005ad56aa7d6ea5830c5ffcc60bf35de380b Mon Sep 17 00:00:00 2001 From: Timo Witte Date: Tue, 4 Aug 2020 02:14:23 +0200 Subject: platform/x86: acer-wmi: add automatic keyboard background light toggle key as KEY_LIGHTS_TOGGLE Got a dmesg message on my AMD Renoir based Acer laptop: "acer_wmi: Unknown key number - 0x84" when toggling keyboard background light Signed-off-by: Timo Witte Reviewed-by: "Lee, Chun-Yi" Link: https://lore.kernel.org/r/20200804001423.36778-1-timo.witte@gmail.com Signed-off-by: Hans de Goede --- drivers/platform/x86/acer-wmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index 49f4b73be513..5592a929b593 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -111,6 +111,7 @@ static const struct key_entry acer_wmi_keymap[] __initconst = { {KE_KEY, 0x64, {KEY_SWITCHVIDEOMODE} }, /* Display Switch */ {KE_IGNORE, 0x81, {KEY_SLEEP} }, {KE_KEY, 0x82, {KEY_TOUCHPAD_TOGGLE} }, /* Touch Pad Toggle */ + {KE_IGNORE, 0x84, {KEY_KBDILLUMTOGGLE} }, /* Automatic Keyboard background light toggle */ {KE_KEY, KEY_TOUCHPAD_ON, {KEY_TOUCHPAD_ON} }, {KE_KEY, KEY_TOUCHPAD_OFF, {KEY_TOUCHPAD_OFF} }, {KE_IGNORE, 0x83, {KEY_TOUCHPAD_TOGGLE} }, -- cgit v1.2.3 From 2a72c46ac4d665614faa25e267c3fb27fb729ed7 Mon Sep 17 00:00:00 2001 From: Kaixu Xia Date: Sun, 22 Nov 2020 13:49:37 +0800 Subject: platform/x86: toshiba_acpi: Fix the wrong variable assignment The commit 78429e55e4057 ("platform/x86: toshiba_acpi: Clean up variable declaration") cleans up variable declaration in video_proc_write(). Seems it does the variable assignment in the wrong place, this results in dead code and changes the source code logic. Fix it by doing the assignment at the beginning of the funciton. Fixes: 78429e55e4057 ("platform/x86: toshiba_acpi: Clean up variable declaration") Reported-by: Tosk Robot Signed-off-by: Kaixu Xia Link: https://lore.kernel.org/r/1606024177-16481-1-git-send-email-kaixuxia@tencent.com Signed-off-by: Hans de Goede --- drivers/platform/x86/toshiba_acpi.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index e557d757c647..fa7232ad8c39 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -1478,7 +1478,7 @@ static ssize_t video_proc_write(struct file *file, const char __user *buf, struct toshiba_acpi_dev *dev = PDE_DATA(file_inode(file)); char *buffer; char *cmd; - int lcd_out, crt_out, tv_out; + int lcd_out = -1, crt_out = -1, tv_out = -1; int remain = count; int value; int ret; @@ -1510,7 +1510,6 @@ static ssize_t video_proc_write(struct file *file, const char __user *buf, kfree(cmd); - lcd_out = crt_out = tv_out = -1; ret = get_video_status(dev, &video_out); if (!ret) { unsigned int new_video_out = video_out; -- cgit v1.2.3 From 8b205d3e1bf52ab31cdd5c55f87c87a227793d84 Mon Sep 17 00:00:00 2001 From: Max Verevkin Date: Tue, 24 Nov 2020 15:16:52 +0200 Subject: platform/x86: intel-vbtn: Support for tablet mode on HP Pavilion 13 x360 PC The Pavilion 13 x360 PC has a chassis-type which does not indicate it is a convertible, while it is actually a convertible. Add it to the dmi_switches_allow_list. Signed-off-by: Max Verevkin Link: https://lore.kernel.org/r/20201124131652.11165-1-me@maxverevkin.tk Signed-off-by: Hans de Goede --- drivers/platform/x86/intel-vbtn.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index f5901b0b07cd..0419c8001fe3 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -206,6 +206,12 @@ static const struct dmi_system_id dmi_switches_allow_list[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Stream x360 Convertible PC 11"), }, }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion 13 x360 PC"), + }, + }, {} /* Array terminator */ }; -- cgit v1.2.3 From 0f511edc6ac12f1ccf1c6c2d4412f5ed7ba426a6 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 15 Oct 2020 21:49:49 +0200 Subject: platform/x86: touchscreen_dmi: Add info for the Predia Basic tablet Add touchscreen info for the Predia Basic tablet. Signed-off-by: Hans de Goede Acked-by: Andy Shevchenko Link: https://lore.kernel.org/r/20201015194949.50566-1-hdegoede@redhat.com --- drivers/platform/x86/touchscreen_dmi.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index dda60f89c951..26cbf7cc8129 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -623,6 +623,23 @@ static const struct ts_dmi_data pov_mobii_wintab_p1006w_v10_data = { .properties = pov_mobii_wintab_p1006w_v10_props, }; +static const struct property_entry predia_basic_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 3), + PROPERTY_ENTRY_U32("touchscreen-min-y", 10), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1728), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1144), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl3680-predia-basic.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data predia_basic_data = { + .acpi_name = "MSSL1680:00", + .properties = predia_basic_props, +}; + static const struct property_entry schneider_sct101ctm_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1715), PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), @@ -1109,6 +1126,16 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_BIOS_DATE, "10/24/2014"), }, }, + { + /* Predia Basic tablet) */ + .driver_data = (void *)&predia_basic_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "CherryTrail"), + /* Above matches are too generic, add bios-version match */ + DMI_MATCH(DMI_BIOS_VERSION, "Mx.WT107.KUBNGEA"), + }, + }, { /* Point of View mobii wintab p800w (v2.1) */ .driver_data = (void *)&pov_mobii_wintab_p800w_v21_data, -- cgit v1.2.3 From c9aa128080cbce92f8715a9328f88d8ca3134279 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 24 Nov 2020 12:04:54 +0100 Subject: platform/x86: touchscreen_dmi: Add info for the Irbis TW118 tablet Add touchscreen info for the Irbis TW118 tablet. Reported-and-tested-by: russianneuromancer Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20201124110454.114286-1-hdegoede@redhat.com --- drivers/platform/x86/touchscreen_dmi.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 26cbf7cc8129..5783139d0a11 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -295,6 +295,21 @@ static const struct ts_dmi_data irbis_tw90_data = { .properties = irbis_tw90_props, }; +static const struct property_entry irbis_tw118_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 20), + PROPERTY_ENTRY_U32("touchscreen-min-y", 30), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1960), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1510), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-irbis-tw118.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct ts_dmi_data irbis_tw118_data = { + .acpi_name = "MSSL1680:00", + .properties = irbis_tw118_props, +}; + static const struct property_entry itworks_tw891_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-x", 1), PROPERTY_ENTRY_U32("touchscreen-min-y", 5), @@ -953,6 +968,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "TW90"), }, }, + { + /* Irbis TW118 */ + .driver_data = (void *)&irbis_tw118_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "IRBIS"), + DMI_MATCH(DMI_PRODUCT_NAME, "TW118"), + }, + }, { /* I.T.Works TW891 */ .driver_data = (void *)&itworks_tw891_data, -- cgit v1.2.3 From d76b42e92780c3587c1a998a3a943b501c137553 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 26 Nov 2020 11:13:51 +0000 Subject: iommu/vt-d: Don't read VCCAP register unless it exists My virtual IOMMU implementation is whining that the guest is reading a register that doesn't exist. Only read the VCCAP_REG if the corresponding capability is set in ECAP_REG to indicate that it actually exists. Fixes: 3375303e8287 ("iommu/vt-d: Add custom allocator for IOASID") Signed-off-by: David Woodhouse Reviewed-by: Liu Yi L Cc: stable@vger.kernel.org # v5.7+ Acked-by: Lu Baolu Link: https://lore.kernel.org/r/de32b150ffaa752e0cff8571b17dfb1213fbe71c.camel@infradead.org Signed-off-by: Will Deacon --- drivers/iommu/intel/dmar.c | 3 ++- drivers/iommu/intel/iommu.c | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 11319e4dce4a..b46dbfa6d0ed 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -986,7 +986,8 @@ static int map_iommu(struct intel_iommu *iommu, u64 phys_addr) warn_invalid_dmar(phys_addr, " returns all ones"); goto unmap; } - iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG); + if (ecap_vcs(iommu->ecap)) + iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG); /* the registers might be more than one page */ map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap), diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 4d9b298002f0..30979c2c7082 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1833,7 +1833,7 @@ static void free_dmar_iommu(struct intel_iommu *iommu) if (ecap_prs(iommu->ecap)) intel_svm_finish_prq(iommu); } - if (ecap_vcs(iommu->ecap) && vccap_pasid(iommu->vccap)) + if (vccap_pasid(iommu->vccap)) ioasid_unregister_allocator(&iommu->pasid_allocator); #endif @@ -3212,7 +3212,7 @@ static void register_pasid_allocator(struct intel_iommu *iommu) * is active. All vIOMMU allocators will eventually be calling the same * host allocator. */ - if (!ecap_vcs(iommu->ecap) || !vccap_pasid(iommu->vccap)) + if (!vccap_pasid(iommu->vccap)) return; pr_info("Register custom PASID allocator\n"); -- cgit v1.2.3 From ebed7b7ca47f3aa95ebf2185a526227744616ac1 Mon Sep 17 00:00:00 2001 From: Wenpeng Liang Date: Thu, 26 Nov 2020 17:26:52 +0800 Subject: RDMA/hns: Fix wrong field of SRQ number the device supports The SRQ capacity is got from the firmware, whose field should be ended at bit 19. Fixes: ba6bb7e97421 ("RDMA/hns: Add interfaces to get pf capabilities from firmware") Link: https://lore.kernel.org/r/1606382812-23636-1-git-send-email-liweihang@huawei.com Signed-off-by: Wenpeng Liang Signed-off-by: Weihang Li Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 29c9dd4bcbc6..be7f2fe1e883 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -1661,7 +1661,7 @@ struct hns_roce_query_pf_caps_d { __le32 rsv_uars_rsv_qps; }; #define V2_QUERY_PF_CAPS_D_NUM_SRQS_S 0 -#define V2_QUERY_PF_CAPS_D_NUM_SRQS_M GENMASK(20, 0) +#define V2_QUERY_PF_CAPS_D_NUM_SRQS_M GENMASK(19, 0) #define V2_QUERY_PF_CAPS_D_RQWQE_HOP_NUM_S 20 #define V2_QUERY_PF_CAPS_D_RQWQE_HOP_NUM_M GENMASK(21, 20) -- cgit v1.2.3 From ab6f7248cc446b85fe9e31091670ad7c4293d7fd Mon Sep 17 00:00:00 2001 From: Wenpeng Liang Date: Thu, 26 Nov 2020 17:29:37 +0800 Subject: RDMA/hns: Fix retry_cnt and rnr_cnt when querying QP The maximum number of retransmission should be returned when querying QP, not the value of retransmission counter. Fixes: 99fcf82521d9 ("RDMA/hns: Fix the wrong value of rnr_retry when querying qp") Fixes: 926a01dc000d ("RDMA/hns: Add QP operations support for hip08 SoC") Link: https://lore.kernel.org/r/1606382977-21431-1-git-send-email-liweihang@huawei.com Signed-off-by: Wenpeng Liang Signed-off-by: Weihang Li Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 6d30850696c5..ce4a476c9550 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -4989,11 +4989,11 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, V2_QPC_BYTE_28_AT_M, V2_QPC_BYTE_28_AT_S); qp_attr->retry_cnt = roce_get_field(context.byte_212_lsn, - V2_QPC_BYTE_212_RETRY_CNT_M, - V2_QPC_BYTE_212_RETRY_CNT_S); + V2_QPC_BYTE_212_RETRY_NUM_INIT_M, + V2_QPC_BYTE_212_RETRY_NUM_INIT_S); qp_attr->rnr_retry = roce_get_field(context.byte_244_rnr_rxack, - V2_QPC_BYTE_244_RNR_CNT_M, - V2_QPC_BYTE_244_RNR_CNT_S); + V2_QPC_BYTE_244_RNR_NUM_INIT_M, + V2_QPC_BYTE_244_RNR_NUM_INIT_S); done: qp_attr->cur_qp_state = qp_attr->qp_state; -- cgit v1.2.3 From 17475e104dcb74217c282781817f8f52b46130d3 Mon Sep 17 00:00:00 2001 From: Yixian Liu Date: Thu, 26 Nov 2020 18:26:12 +0800 Subject: RDMA/hns: Bugfix for memory window mtpt configuration When a memory window is bound to a memory region, the local write access should be set for its mtpt table. Fixes: c7c28191408b ("RDMA/hns: Add MW support for hip08") Link: https://lore.kernel.org/r/1606386372-21094-1-git-send-email-liweihang@huawei.com Signed-off-by: Yixian Liu Signed-off-by: Weihang Li Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index ce4a476c9550..0468028ffe39 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -2936,6 +2936,7 @@ static int hns_roce_v2_mw_write_mtpt(void *mb_buf, struct hns_roce_mw *mw) roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_R_INV_EN_S, 1); roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_L_INV_EN_S, 1); + roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_LW_EN_S, 1); roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_PA_S, 0); roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_MR_MW_S, 1); -- cgit v1.2.3 From af60470347de6ac2b9f0cc3703975a543a3de075 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 25 Nov 2020 18:41:28 +0000 Subject: io_uring: fix files grab/cancel race When one task is in io_uring_cancel_files() and another is doing io_prep_async_work() a race may happen. That's because after accounting a request inflight in first call to io_grab_identity() it still may fail and go to io_identity_cow(), which migh briefly keep dangling work.identity and not only. Grab files last, so io_prep_async_work() won't fail if it did get into ->inflight_list. note: the bug shouldn't exist after making io_uring_cancel_files() not poking into other tasks' requests. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index ff6deffe5aa9..1023f7b44cea 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1313,22 +1313,6 @@ static bool io_grab_identity(struct io_kiocb *req) return false; req->work.flags |= IO_WQ_WORK_FSIZE; } - - if (!(req->work.flags & IO_WQ_WORK_FILES) && - (def->work_flags & IO_WQ_WORK_FILES) && - !(req->flags & REQ_F_NO_FILE_TABLE)) { - if (id->files != current->files || - id->nsproxy != current->nsproxy) - return false; - atomic_inc(&id->files->count); - get_nsproxy(id->nsproxy); - req->flags |= REQ_F_INFLIGHT; - - spin_lock_irq(&ctx->inflight_lock); - list_add(&req->inflight_entry, &ctx->inflight_list); - spin_unlock_irq(&ctx->inflight_lock); - req->work.flags |= IO_WQ_WORK_FILES; - } #ifdef CONFIG_BLK_CGROUP if (!(req->work.flags & IO_WQ_WORK_BLKCG) && (def->work_flags & IO_WQ_WORK_BLKCG)) { @@ -1370,6 +1354,21 @@ static bool io_grab_identity(struct io_kiocb *req) } spin_unlock(¤t->fs->lock); } + if (!(req->work.flags & IO_WQ_WORK_FILES) && + (def->work_flags & IO_WQ_WORK_FILES) && + !(req->flags & REQ_F_NO_FILE_TABLE)) { + if (id->files != current->files || + id->nsproxy != current->nsproxy) + return false; + atomic_inc(&id->files->count); + get_nsproxy(id->nsproxy); + req->flags |= REQ_F_INFLIGHT; + + spin_lock_irq(&ctx->inflight_lock); + list_add(&req->inflight_entry, &ctx->inflight_list); + spin_unlock_irq(&ctx->inflight_lock); + req->work.flags |= IO_WQ_WORK_FILES; + } return true; } -- cgit v1.2.3 From aea656b0d05ec5b8ed5beb2f94c4dd42ea834e9d Mon Sep 17 00:00:00 2001 From: Christian König Date: Thu, 26 Nov 2020 13:35:08 +0100 Subject: drm/nouveau: make sure ret is initialized in nouveau_ttm_io_mem_reserve MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This wasn't initialized for pre NV50 hardware. Signed-off-by: Christian König Reported-and-Tested-by: Mark Hounschell Reviewed-by: Karol Herbst Link: https://patchwork.freedesktop.org/series/84298/ --- drivers/gpu/drm/nouveau/nouveau_bo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 2ee75646ad6f..d02f3a58adb6 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1215,8 +1215,8 @@ retry: } reg->bus.offset = handle; - ret = 0; } + ret = 0; break; default: ret = -EINVAL; -- cgit v1.2.3 From 4df910620bebb5cfe234af16ac8f6474b60215fd Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Wed, 25 Nov 2020 13:22:21 +0800 Subject: mm: memcg: relayout structure mem_cgroup to avoid cache interference 0day reported one -22.7% regression for will-it-scale page_fault2 case [1] on a 4 sockets 144 CPU platform, and bisected to it to be caused by Waiman's optimization (commit bd0b230fe1) of saving one 'struct page_counter' space for 'struct mem_cgroup'. Initially we thought it was due to the cache alignment change introduced by the patch, but further debug shows that it is due to some hot data members ('vmstats_local', 'vmstats_percpu', 'vmstats') sit in 2 adjacent cacheline (2N and 2N+1 cacheline), and when adjacent cache line prefetch is enabled, it triggers an "extended level" of cache false sharing for 2 adjacent cache lines. So exchange the 2 member blocks, while keeping mostly the original cache alignment, which can restore and even enhance the performance, and save 64 bytes of space for 'struct mem_cgroup' (from 2880 to 2816, with 0day's default RHEL-8.3 kernel config) [1]. https://lore.kernel.org/lkml/20201102091543.GM31092@shao2-debian/ Fixes: bd0b230fe145 ("mm/memcg: unify swap and memsw page counters") Reported-by: kernel test robot Signed-off-by: Feng Tang Acked-by: Waiman Long Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a80c59af2c60..922a7f600465 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -282,20 +282,6 @@ struct mem_cgroup { MEMCG_PADDING(_pad1_); - /* - * set > 0 if pages under this cgroup are moving to other cgroup. - */ - atomic_t moving_account; - struct task_struct *move_lock_task; - - /* Legacy local VM stats and events */ - struct memcg_vmstats_percpu __percpu *vmstats_local; - - /* Subtree VM stats and events (batched updates) */ - struct memcg_vmstats_percpu __percpu *vmstats_percpu; - - MEMCG_PADDING(_pad2_); - atomic_long_t vmstats[MEMCG_NR_STAT]; atomic_long_t vmevents[NR_VM_EVENT_ITEMS]; @@ -317,6 +303,20 @@ struct mem_cgroup { struct list_head objcg_list; /* list of inherited objcgs */ #endif + MEMCG_PADDING(_pad2_); + + /* + * set > 0 if pages under this cgroup are moving to other cgroup. + */ + atomic_t moving_account; + struct task_struct *move_lock_task; + + /* Legacy local VM stats and events */ + struct memcg_vmstats_percpu __percpu *vmstats_local; + + /* Subtree VM stats and events (batched updates) */ + struct memcg_vmstats_percpu __percpu *vmstats_percpu; + #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; -- cgit v1.2.3 From bf3a3cdcad40e5928a22ea0fd200d17fd6d6308d Mon Sep 17 00:00:00 2001 From: Qinglang Miao Date: Fri, 30 Oct 2020 09:34:24 +0800 Subject: drm/tegra: sor: Disable clocks on error in tegra_sor_init() Fix the missing clk_disable_unprepare() before return from tegra_sor_init() in the error handling case. Signed-off-by: Qinglang Miao Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/sor.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index 00656d8b98e2..cc2aa2308a51 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -3143,6 +3143,7 @@ static int tegra_sor_init(struct host1x_client *client) if (err < 0) { dev_err(sor->dev, "failed to deassert SOR reset: %d\n", err); + clk_disable_unprepare(sor->clk); return err; } @@ -3150,12 +3151,17 @@ static int tegra_sor_init(struct host1x_client *client) } err = clk_prepare_enable(sor->clk_safe); - if (err < 0) + if (err < 0) { + clk_disable_unprepare(sor->clk); return err; + } err = clk_prepare_enable(sor->clk_dp); - if (err < 0) + if (err < 0) { + clk_disable_unprepare(sor->clk_safe); + clk_disable_unprepare(sor->clk); return err; + } return 0; } -- cgit v1.2.3 From 82e938bd5382b322ce81e6cb8fd030987f2da022 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 25 Nov 2020 23:37:18 +0100 Subject: gfs2: Upgrade shared glocks for atime updates Commit 20f829999c38 ("gfs2: Rework read and page fault locking") lifted the glock lock taking from the low-level ->readpage and ->readahead address space operations to the higher-level ->read_iter file and ->fault vm operations. The glocks are still taken in LM_ST_SHARED mode only. On filesystems mounted without the noatime option, ->read_iter sometimes needs to update the atime as well, though. Right now, this leads to a failed locking mode assertion in gfs2_dirty_inode. Fix that by introducing a new update_time inode operation. There, if the glock is held non-exclusively, upgrade it to an exclusive lock. Reported-by: Alexander Aring Fixes: 20f829999c38 ("gfs2: Rework read and page fault locking") Cc: stable@vger.kernel.org # v5.8+ Signed-off-by: Andreas Gruenbacher --- fs/gfs2/inode.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 077ccb1b3ccc..eed1a1bac6f6 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -2116,6 +2116,25 @@ loff_t gfs2_seek_hole(struct file *file, loff_t offset) return vfs_setpos(file, ret, inode->i_sb->s_maxbytes); } +static int gfs2_update_time(struct inode *inode, struct timespec64 *time, + int flags) +{ + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_glock *gl = ip->i_gl; + struct gfs2_holder *gh; + int error; + + gh = gfs2_glock_is_locked_by_me(gl); + if (gh && !gfs2_glock_is_held_excl(gl)) { + gfs2_glock_dq(gh); + gfs2_holder_reinit(LM_ST_EXCLUSIVE, 0, gh); + error = gfs2_glock_nq(gh); + if (error) + return error; + } + return generic_update_time(inode, time, flags); +} + const struct inode_operations gfs2_file_iops = { .permission = gfs2_permission, .setattr = gfs2_setattr, @@ -2124,6 +2143,7 @@ const struct inode_operations gfs2_file_iops = { .fiemap = gfs2_fiemap, .get_acl = gfs2_get_acl, .set_acl = gfs2_set_acl, + .update_time = gfs2_update_time, }; const struct inode_operations gfs2_dir_iops = { @@ -2143,6 +2163,7 @@ const struct inode_operations gfs2_dir_iops = { .fiemap = gfs2_fiemap, .get_acl = gfs2_get_acl, .set_acl = gfs2_set_acl, + .update_time = gfs2_update_time, .atomic_open = gfs2_atomic_open, }; -- cgit v1.2.3 From 4ca23e2c2074465bff55ea14221175fecdf63c5f Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Thu, 26 Nov 2020 18:15:06 +0100 Subject: batman-adv: Consider fragmentation for needed_headroom MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If a batman-adv packets has to be fragmented, then the original batman-adv packet header is not stripped away. Instead, only a new header is added in front of the packet after it was split. This size must be considered to avoid cost intensive reallocations during the transmission through the various device layers. Fixes: 7bca68c7844b ("batman-adv: Add lower layer needed_(head|tail)room to own ones") Reported-by: Linus Lüssing Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- net/batman-adv/hard-interface.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index dad99641df2a..33904595fc56 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -554,6 +554,9 @@ static void batadv_hardif_recalc_extra_skbroom(struct net_device *soft_iface) needed_headroom = lower_headroom + (lower_header_len - ETH_HLEN); needed_headroom += batadv_max_header_len(); + /* fragmentation headers don't strip the unicast/... header */ + needed_headroom += sizeof(struct batadv_frag_packet); + soft_iface->needed_headroom = needed_headroom; soft_iface->needed_tailroom = lower_tailroom; } -- cgit v1.2.3 From c5cbfc87558168ef4c3c27ce36eba6b83391db19 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Wed, 25 Nov 2020 13:16:43 +0100 Subject: batman-adv: Reserve needed_*room for fragments The batadv net_device is trying to propagate the needed_headroom and needed_tailroom from the lower devices. This is needed to avoid cost intensive reallocations using pskb_expand_head during the transmission. But the fragmentation code split the skb's without adding extra room at the end/beginning of the various fragments. This reduced the performance of transmissions over complex scenarios (batadv on vxlan on wireguard) because the lower devices had to perform the reallocations at least once. Fixes: ee75ed88879a ("batman-adv: Fragment and send skbs larger than mtu") Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- net/batman-adv/fragmentation.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 9a47ef8b95c4..8de1fb567fd7 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -391,6 +391,7 @@ out: /** * batadv_frag_create() - create a fragment from skb + * @net_dev: outgoing device for fragment * @skb: skb to create fragment from * @frag_head: header to use in new fragment * @fragment_size: size of new fragment @@ -401,22 +402,25 @@ out: * * Return: the new fragment, NULL on error. */ -static struct sk_buff *batadv_frag_create(struct sk_buff *skb, +static struct sk_buff *batadv_frag_create(struct net_device *net_dev, + struct sk_buff *skb, struct batadv_frag_packet *frag_head, unsigned int fragment_size) { + unsigned int ll_reserved = LL_RESERVED_SPACE(net_dev); + unsigned int tailroom = net_dev->needed_tailroom; struct sk_buff *skb_fragment; unsigned int header_size = sizeof(*frag_head); unsigned int mtu = fragment_size + header_size; - skb_fragment = netdev_alloc_skb(NULL, mtu + ETH_HLEN); + skb_fragment = dev_alloc_skb(ll_reserved + mtu + tailroom); if (!skb_fragment) goto err; skb_fragment->priority = skb->priority; /* Eat the last mtu-bytes of the skb */ - skb_reserve(skb_fragment, header_size + ETH_HLEN); + skb_reserve(skb_fragment, ll_reserved + header_size); skb_split(skb, skb_fragment, skb->len - fragment_size); /* Add the header */ @@ -439,11 +443,12 @@ int batadv_frag_send_packet(struct sk_buff *skb, struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node) { + struct net_device *net_dev = neigh_node->if_incoming->net_dev; struct batadv_priv *bat_priv; struct batadv_hard_iface *primary_if = NULL; struct batadv_frag_packet frag_header; struct sk_buff *skb_fragment; - unsigned int mtu = neigh_node->if_incoming->net_dev->mtu; + unsigned int mtu = net_dev->mtu; unsigned int header_size = sizeof(frag_header); unsigned int max_fragment_size, num_fragments; int ret; @@ -503,7 +508,7 @@ int batadv_frag_send_packet(struct sk_buff *skb, goto put_primary_if; } - skb_fragment = batadv_frag_create(skb, &frag_header, + skb_fragment = batadv_frag_create(net_dev, skb, &frag_header, max_fragment_size); if (!skb_fragment) { ret = -ENOMEM; -- cgit v1.2.3 From 992b03b88e36254e26e9a4977ab948683e21bd9f Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Thu, 26 Nov 2020 18:24:49 +0100 Subject: batman-adv: Don't always reallocate the fragmentation skb head When a packet is fragmented by batman-adv, the original batman-adv header is not modified. Only a new fragmentation is inserted between the original one and the ethernet header. The code must therefore make sure that it has a writable region of this size in the skbuff head. But it is not useful to always reallocate the skbuff by this size even when there would be more than enough headroom still in the skb. The reallocation is just to costly during in this codepath. Fixes: ee75ed88879a ("batman-adv: Fragment and send skbs larger than mtu") Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- net/batman-adv/fragmentation.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 8de1fb567fd7..1f1f5b0873b2 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -527,13 +527,14 @@ int batadv_frag_send_packet(struct sk_buff *skb, frag_header.no++; } - /* Make room for the fragment header. */ - if (batadv_skb_head_push(skb, header_size) < 0 || - pskb_expand_head(skb, header_size + ETH_HLEN, 0, GFP_ATOMIC) < 0) { - ret = -ENOMEM; + /* make sure that there is at least enough head for the fragmentation + * and ethernet headers + */ + ret = skb_cow_head(skb, ETH_HLEN + header_size); + if (ret < 0) goto put_primary_if; - } + skb_push(skb, header_size); memcpy(skb->data, &frag_header, header_size); /* Send the last fragment */ -- cgit v1.2.3 From e5782a5d5054bf1e03cb7fbd87035037c2a22698 Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Fri, 27 Nov 2020 14:39:23 +0800 Subject: ALSA: hda/realtek - Add new codec supported for ALC897 Enable new codec supported for ALC897. Signed-off-by: Kailang Yang Cc: Link: https://lore.kernel.org/r/3b00520f304842aab8291eb8d9191bd8@realtek.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 34ad24d2c970..fcd1fb18ece9 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -446,6 +446,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) alc_update_coef_idx(codec, 0x7, 1<<5, 0); break; case 0x10ec0892: + case 0x10ec0897: alc_update_coef_idx(codec, 0x7, 1<<5, 0); break; case 0x10ec0899: @@ -10214,6 +10215,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = { HDA_CODEC_ENTRY(0x10ec0888, "ALC888", patch_alc882), HDA_CODEC_ENTRY(0x10ec0889, "ALC889", patch_alc882), HDA_CODEC_ENTRY(0x10ec0892, "ALC892", patch_alc662), + HDA_CODEC_ENTRY(0x10ec0897, "ALC897", patch_alc662), HDA_CODEC_ENTRY(0x10ec0899, "ALC898", patch_alc882), HDA_CODEC_ENTRY(0x10ec0900, "ALC1150", patch_alc882), HDA_CODEC_ENTRY(0x10ec0b00, "ALCS1200A", patch_alc882), -- cgit v1.2.3 From 865f5b671b48d0088ce981cff1e822d9f7da441f Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Fri, 27 Nov 2020 08:35:12 +0100 Subject: can: m_can: m_can_open(): remove IRQF_TRIGGER_FALLING from request_threaded_irq()'s flags The threaded IRQ handler is used for the tcan4x5x driver only. The IRQ pin of the tcan4x5x controller is active low, so better not use IRQF_TRIGGER_FALLING when requesting the IRQ. As this can result in missing interrupts. Further, if the device tree specified the interrupt as "IRQ_TYPE_LEVEL_LOW", unloading and reloading of the driver results in the following error during ifup: | irq: type mismatch, failed to map hwirq-31 for gpio@20a8000! | tcan4x5x spi1.1: m_can device registered (irq=0, version=32) | tcan4x5x spi1.1 can2: TCAN4X5X successfully initialized. | tcan4x5x spi1.1 can2: failed to request interrupt This patch fixes the problem by removing the IRQF_TRIGGER_FALLING from the request_threaded_irq(). Fixes: f524f829b75a ("can: m_can: Create a m_can platform framework") Cc: Dan Murphy Cc: Sriram Dash Cc: Pankaj Sharma Link: https://lore.kernel.org/r/20201127093548.509253-1-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/m_can.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index f3fc37e96b08..c62439bdee28 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1653,7 +1653,7 @@ static int m_can_open(struct net_device *dev) INIT_WORK(&cdev->tx_work, m_can_tx_work_queue); err = request_threaded_irq(dev->irq, NULL, m_can_isr, - IRQF_ONESHOT | IRQF_TRIGGER_FALLING, + IRQF_ONESHOT, dev->name, dev); } else { err = request_irq(dev->irq, m_can_isr, IRQF_SHARED, dev->name, -- cgit v1.2.3 From e3409e4192535fbcc86a84b7a65d9351f46039ec Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Tue, 24 Nov 2020 19:47:38 +0100 Subject: can: m_can: fix nominal bitiming tseg2 min for version >= 3.1 At lest the revision 3.3.0 of the bosch m_can IP core specifies that valid register values for "Nominal Time segment after sample point (NTSEG2)" are from 1 to 127. As the hardware uses a value of one more than the programmed value, mean tseg2_min is 2. This patch fixes the tseg2_min value accordingly. Cc: Dan Murphy Cc: Mario Huettel Acked-by: Sriram Dash Link: https://lore.kernel.org/r/20201124190751.3972238-1-mkl@pengutronix.de Fixes: b03cfc5bb0e1 ("can: m_can: Enable M_CAN version dependent initialization") Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/m_can.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index c62439bdee28..d4030abad935 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1033,7 +1033,7 @@ static const struct can_bittiming_const m_can_bittiming_const_31X = { .name = KBUILD_MODNAME, .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ .tseg1_max = 256, - .tseg2_min = 1, /* Time segment 2 = phase_seg2 */ + .tseg2_min = 2, /* Time segment 2 = phase_seg2 */ .tseg2_max = 128, .sjw_max = 128, .brp_min = 1, -- cgit v1.2.3 From 5c7d55bded77da6db7c5d249610e3a2eed730b3c Mon Sep 17 00:00:00 2001 From: Pankaj Sharma Date: Thu, 26 Nov 2020 10:21:42 +0530 Subject: can: m_can: m_can_dev_setup(): add support for bosch mcan version 3.3.0 Add support for mcan bit timing and control mode according to bosch mcan IP version 3.3.0. The mcan version read from the Core Release field of CREL register would be 33. Accordingly the properties are to be set for mcan v3.3.0 Signed-off-by: Pankaj Sharma Link: https://lore.kernel.org/r/1606366302-5520-1-git-send-email-pankj.sharma@samsung.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/m_can.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index d4030abad935..61a93b192037 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1385,6 +1385,8 @@ static int m_can_dev_setup(struct m_can_classdev *m_can_dev) &m_can_data_bittiming_const_31X; break; case 32: + case 33: + /* Support both MCAN version v3.2.x and v3.3.0 */ m_can_dev->can.bittiming_const = m_can_dev->bit_timing ? m_can_dev->bit_timing : &m_can_bittiming_const_31X; -- cgit v1.2.3 From d73ff9b7c4eacaba0fd956d14882bcae970f8307 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Thu, 26 Nov 2020 20:21:40 +0100 Subject: can: af_can: can_rx_unregister(): remove WARN() statement from list operation sanity check To detect potential bugs in CAN protocol implementations (double removal of receiver entries) a WARN() statement has been used if no matching list item was found for removal. The fault injection issued by syzkaller was able to create a situation where the closing of a socket runs simultaneously to the notifier call chain for removing the CAN network device in use. This case is very unlikely in real life but it doesn't break anything. Therefore we just replace the WARN() statement with pr_warn() to preserve the notification for the CAN protocol development. Reported-by: syzbot+381d06e0c8eaacb8706f@syzkaller.appspotmail.com Reported-by: syzbot+d0ddd88c9a7432f041e6@syzkaller.appspotmail.com Reported-by: syzbot+76d62d3b8162883c7d11@syzkaller.appspotmail.com Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/r/20201126192140.14350-1-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- net/can/af_can.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/can/af_can.c b/net/can/af_can.c index 5d124c155904..4c343b43067f 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -541,10 +541,13 @@ void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id, /* Check for bugs in CAN protocol implementations using af_can.c: * 'rcv' will be NULL if no matching list item was found for removal. + * As this case may potentially happen when closing a socket while + * the notifier for removing the CAN netdev is running we just print + * a warning here. */ if (!rcv) { - WARN(1, "BUG: receive list entry not found for dev %s, id %03X, mask %03X\n", - DNAME(dev), can_id, mask); + pr_warn("can: receive list entry not found for dev %s, id %03X, mask %03X\n", + DNAME(dev), can_id, mask); goto out; } -- cgit v1.2.3 From 6d6556c04ebaeaf4e7fa8b791c97e2a7c41b38a3 Mon Sep 17 00:00:00 2001 From: Giacinto Cifelli Date: Wed, 25 Nov 2020 15:53:04 +0100 Subject: USB: serial: option: add support for Thales Cinterion EXS82 There is a single option port in this modem, and it is used as debug port. lsusb -v for this device: Bus 001 Device 002: ID 1e2d:006c Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 2.00 bDeviceClass 239 Miscellaneous Device bDeviceSubClass 2 ? bDeviceProtocol 1 Interface Association bMaxPacketSize0 64 idVendor 0x1e2d idProduct 0x006c bcdDevice 0.00 iManufacturer 4 iProduct 3 iSerial 5 bNumConfigurations 1 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 243 bNumInterfaces 7 bConfigurationValue 1 iConfiguration 2 bmAttributes 0xe0 Self Powered Remote Wakeup MaxPower 500mA Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 255 Vendor Specific Protocol iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x01 EP 1 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Association: bLength 8 bDescriptorType 11 bFirstInterface 1 bInterfaceCount 2 bFunctionClass 2 Communications bFunctionSubClass 2 Abstract (modem) bFunctionProtocol 1 AT-commands (v.25ter) iFunction 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 2 Abstract (modem) bInterfaceProtocol 1 AT-commands (v.25ter) iInterface 0 CDC Header: bcdCDC 1.10 CDC ACM: bmCapabilities 0x02 line coding and serial state CDC Call Management: bmCapabilities 0x03 call management use DataInterface bDataInterface 2 CDC Union: bMasterInterface 1 bSlaveInterface 2 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x82 EP 2 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 2 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 Unused bInterfaceProtocol 0 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x83 EP 3 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x02 EP 2 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Association: bLength 8 bDescriptorType 11 bFirstInterface 3 bInterfaceCount 2 bFunctionClass 2 Communications bFunctionSubClass 2 Abstract (modem) bFunctionProtocol 1 AT-commands (v.25ter) iFunction 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 3 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 2 Abstract (modem) bInterfaceProtocol 1 AT-commands (v.25ter) iInterface 0 CDC Header: bcdCDC 1.10 CDC ACM: bmCapabilities 0x02 line coding and serial state CDC Call Management: bmCapabilities 0x03 call management use DataInterface bDataInterface 4 CDC Union: bMasterInterface 3 bSlaveInterface 4 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x84 EP 4 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 4 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 Unused bInterfaceProtocol 0 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x85 EP 5 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x03 EP 3 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Association: bLength 8 bDescriptorType 11 bFirstInterface 5 bInterfaceCount 2 bFunctionClass 2 Communications bFunctionSubClass 2 Abstract (modem) bFunctionProtocol 1 AT-commands (v.25ter) iFunction 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 5 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 6 Ethernet Networking bInterfaceProtocol 0 iInterface 0 CDC Header: bcdCDC 1.10 CDC Ethernet: iMacAddress 1 (??) bmEthernetStatistics 0x00000000 wMaxSegmentSize 16384 wNumberMCFilters 0x0001 bNumberPowerFilters 0 CDC Union: bMasterInterface 5 bSlaveInterface 6 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x86 EP 6 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 6 bAlternateSetting 0 bNumEndpoints 0 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 Unused bInterfaceProtocol 0 iInterface 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 6 bAlternateSetting 1 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 Unused bInterfaceProtocol 0 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x87 EP 7 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x04 EP 4 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Signed-off-by: Giacinto Cifelli Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 2aa31173997f..653da1d2945c 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -419,6 +419,7 @@ static void option_instat_callback(struct urb *urb); #define CINTERION_PRODUCT_PH8 0x0053 #define CINTERION_PRODUCT_AHXX 0x0055 #define CINTERION_PRODUCT_PLXX 0x0060 +#define CINTERION_PRODUCT_EXS82 0x006c #define CINTERION_PRODUCT_PH8_2RMNET 0x0082 #define CINTERION_PRODUCT_PH8_AUDIO 0x0083 #define CINTERION_PRODUCT_AHXX_2RMNET 0x0084 @@ -1902,6 +1903,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX_AUDIO, 0xff) }, { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_CLS8, 0xff), .driver_info = RSVD(0) | RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EXS82, 0xff) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) }, { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDM) }, -- cgit v1.2.3 From 4ad9921af4f18490980369f7d60f90ade0195812 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 26 Nov 2020 12:54:36 +0106 Subject: printk: finalize records with trailing newlines Any record with a trailing newline (LOG_NEWLINE flag) cannot be continued because the newline has been stripped and will not be visible if the message is appended. This was already handled correctly when committing in log_output() but was not handled correctly when committing in log_store(). Fixes: f5f022e53b87 ("printk: reimplement log_cont using record extension") Link: https://lore.kernel.org/r/20201126114836.14750-1-john.ogness@linutronix.de Reported-by: Kefeng Wang Signed-off-by: John Ogness Tested-by: Kefeng Wang Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek --- kernel/printk/printk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index fe64a49344bf..bc1e3b5a97bd 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -528,8 +528,8 @@ static int log_store(u32 caller_id, int facility, int level, if (dev_info) memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info)); - /* insert message */ - if ((flags & LOG_CONT) || !(flags & LOG_NEWLINE)) + /* A message without a trailing newline can be continued. */ + if (!(flags & LOG_NEWLINE)) prb_commit(&e); else prb_final_commit(&e); -- cgit v1.2.3 From 10f78fd0dabbc3856ddd67b09a46abdedb045913 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Fri, 27 Nov 2020 11:07:38 +0530 Subject: powerpc/numa: Fix a regression on memoryless node 0 Commit e75130f20b1f ("powerpc/numa: Offline memoryless cpuless node 0") offlines node 0 and expects nodes to be subsequently onlined when CPUs or nodes are detected. Commit 6398eaa26816 ("powerpc/numa: Prefer node id queried from vphn") skips onlining node 0 when CPUs are associated with node 0. On systems with node 0 having CPUs but no memory, this causes node 0 be marked offline. This causes issues at boot time when trying to set memory node for online CPUs while building the zonelist. 0:mon> t [link register ] c000000000400354 __build_all_zonelists+0x164/0x280 [c00000000161bda0] c0000000016533c8 node_states+0x20/0xa0 (unreliable) [c00000000161bdc0] c000000000400384 __build_all_zonelists+0x194/0x280 [c00000000161be30] c000000001041800 build_all_zonelists_init+0x4c/0x118 [c00000000161be80] c0000000004020d0 build_all_zonelists+0x190/0x1b0 [c00000000161bef0] c000000001003cf8 start_kernel+0x18c/0x6a8 [c00000000161bf90] c00000000000adb4 start_here_common+0x1c/0x3e8 0:mon> r R00 = c000000000400354 R16 = 000000000b57a0e8 R01 = c00000000161bda0 R17 = 000000000b57a6b0 R02 = c00000000161ce00 R18 = 000000000b5afee8 R03 = 0000000000000000 R19 = 000000000b6448a0 R04 = 0000000000000000 R20 = fffffffffffffffd R05 = 0000000000000000 R21 = 0000000001400000 R06 = 0000000000000000 R22 = 000000001ec00000 R07 = 0000000000000001 R23 = c000000001175580 R08 = 0000000000000000 R24 = c000000001651ed8 R09 = c0000000017e84d8 R25 = c000000001652480 R10 = 0000000000000000 R26 = c000000001175584 R11 = c000000c7fac0d10 R27 = c0000000019568d0 R12 = c000000000400180 R28 = 0000000000000000 R13 = c000000002200000 R29 = c00000000164dd78 R14 = 000000000b579f78 R30 = 0000000000000000 R15 = 000000000b57a2b8 R31 = c000000001175584 pc = c000000000400194 local_memory_node+0x24/0x80 cfar= c000000000074334 mcount+0xc/0x10 lr = c000000000400354 __build_all_zonelists+0x164/0x280 msr = 8000000002001033 cr = 44002284 ctr = c000000000400180 xer = 0000000000000001 trap = 380 dar = 0000000000001388 dsisr = c00000000161bc90 0:mon> Fix this by setting node to be online while onlining CPUs that belong to node 0. Fixes: e75130f20b1f ("powerpc/numa: Offline memoryless cpuless node 0") Fixes: 6398eaa26816 ("powerpc/numa: Prefer node id queried from vphn") Reported-by: Milan Mohanty Signed-off-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201127053738.10085-1-srikar@linux.vnet.ibm.com --- arch/powerpc/mm/numa.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 63f61d8b55e5..f2bf98bdcea2 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -742,8 +742,7 @@ static int __init parse_numa_properties(void) of_node_put(cpu); } - if (likely(nid > 0)) - node_set_online(nid); + node_set_online(nid); } get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells); -- cgit v1.2.3 From 4bc3c8dc9f5f1eff0d3bfa59491383ac11308b6b Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Tue, 24 Nov 2020 16:07:49 +0800 Subject: ipvs: fix possible memory leak in ip_vs_control_net_init kmemleak report a memory leak as follows: BUG: memory leak unreferenced object 0xffff8880759ea000 (size 256): backtrace: [<00000000c0bf2deb>] kmem_cache_zalloc include/linux/slab.h:656 [inline] [<00000000c0bf2deb>] __proc_create+0x23d/0x7d0 fs/proc/generic.c:421 [<000000009d718d02>] proc_create_reg+0x8e/0x140 fs/proc/generic.c:535 [<0000000097bbfc4f>] proc_create_net_data+0x8c/0x1b0 fs/proc/proc_net.c:126 [<00000000652480fc>] ip_vs_control_net_init+0x308/0x13a0 net/netfilter/ipvs/ip_vs_ctl.c:4169 [<000000004c927ebe>] __ip_vs_init+0x211/0x400 net/netfilter/ipvs/ip_vs_core.c:2429 [<00000000aa6b72d9>] ops_init+0xa8/0x3c0 net/core/net_namespace.c:151 [<00000000153fd114>] setup_net+0x2de/0x7e0 net/core/net_namespace.c:341 [<00000000be4e4f07>] copy_net_ns+0x27d/0x530 net/core/net_namespace.c:482 [<00000000f1c23ec9>] create_new_namespaces+0x382/0xa30 kernel/nsproxy.c:110 [<00000000098a5757>] copy_namespaces+0x2e6/0x3b0 kernel/nsproxy.c:179 [<0000000026ce39e9>] copy_process+0x220a/0x5f00 kernel/fork.c:2072 [<00000000b71f4efe>] _do_fork+0xc7/0xda0 kernel/fork.c:2428 [<000000002974ee96>] __do_sys_clone3+0x18a/0x280 kernel/fork.c:2703 [<0000000062ac0a4d>] do_syscall_64+0x33/0x40 arch/x86/entry/common.c:46 [<0000000093f1ce2c>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 In the error path of ip_vs_control_net_init(), remove_proc_entry() needs to be called to remove the added proc entry, otherwise a memory leak will occur. Also, add some '#ifdef CONFIG_PROC_FS' because proc_create_net* return NULL when PROC is not used. Fixes: b17fc9963f83 ("IPVS: netns, ip_vs_stats and its procfs") Fixes: 61b1ab4583e2 ("IPVS: netns, add basic init per netns.") Reported-by: Hulk Robot Signed-off-by: Wang Hai Acked-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_ctl.c | 31 +++++++++++++++++++++++++------ 1 file changed, 25 insertions(+), 6 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index e279ded4e306..d45dbcba8b49 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -4167,12 +4167,18 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) spin_lock_init(&ipvs->tot_stats.lock); - proc_create_net("ip_vs", 0, ipvs->net->proc_net, &ip_vs_info_seq_ops, - sizeof(struct ip_vs_iter)); - proc_create_net_single("ip_vs_stats", 0, ipvs->net->proc_net, - ip_vs_stats_show, NULL); - proc_create_net_single("ip_vs_stats_percpu", 0, ipvs->net->proc_net, - ip_vs_stats_percpu_show, NULL); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs", 0, ipvs->net->proc_net, + &ip_vs_info_seq_ops, sizeof(struct ip_vs_iter))) + goto err_vs; + if (!proc_create_net_single("ip_vs_stats", 0, ipvs->net->proc_net, + ip_vs_stats_show, NULL)) + goto err_stats; + if (!proc_create_net_single("ip_vs_stats_percpu", 0, + ipvs->net->proc_net, + ip_vs_stats_percpu_show, NULL)) + goto err_percpu; +#endif if (ip_vs_control_net_init_sysctl(ipvs)) goto err; @@ -4180,6 +4186,17 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) return 0; err: +#ifdef CONFIG_PROC_FS + remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net); + +err_percpu: + remove_proc_entry("ip_vs_stats", ipvs->net->proc_net); + +err_stats: + remove_proc_entry("ip_vs", ipvs->net->proc_net); + +err_vs: +#endif free_percpu(ipvs->tot_stats.cpustats); return -ENOMEM; } @@ -4188,9 +4205,11 @@ void __net_exit ip_vs_control_net_cleanup(struct netns_ipvs *ipvs) { ip_vs_trash_cleanup(ipvs); ip_vs_control_net_cleanup_sysctl(ipvs); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net); remove_proc_entry("ip_vs_stats", ipvs->net->proc_net); remove_proc_entry("ip_vs", ipvs->net->proc_net); +#endif free_percpu(ipvs->tot_stats.cpustats); } -- cgit v1.2.3 From 3c78e9e0d33a27ab8050e4492c03c6a1f8d0ed6b Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 25 Nov 2020 23:50:07 +0100 Subject: netfilter: nftables_offload: set address type in control dissector This patch adds nft_flow_rule_set_addr_type() to set the address type from the nft_payload expression accordingly. If the address type is not set in the control dissector then a rule that matches either on source or destination IP address does not work. After this patch, nft hardware offload generates the flow dissector configuration as tc-flower does to match on an IP address. This patch has been also tested functionally to make sure packets are filtered out by the NIC. This is also getting the code aligned with the existing netfilter flow offload infrastructure which is also setting the control dissector. Fixes: c9626a2cbdb2 ("netfilter: nf_tables: add hardware offload support") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_offload.h | 4 ++++ net/netfilter/nf_tables_offload.c | 17 +++++++++++++++++ net/netfilter/nft_payload.c | 4 ++++ 3 files changed, 25 insertions(+) diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h index ea7d1d78b92d..bddd34c5bd79 100644 --- a/include/net/netfilter/nf_tables_offload.h +++ b/include/net/netfilter/nf_tables_offload.h @@ -37,6 +37,7 @@ void nft_offload_update_dependency(struct nft_offload_ctx *ctx, struct nft_flow_key { struct flow_dissector_key_basic basic; + struct flow_dissector_key_control control; union { struct flow_dissector_key_ipv4_addrs ipv4; struct flow_dissector_key_ipv6_addrs ipv6; @@ -62,6 +63,9 @@ struct nft_flow_rule { #define NFT_OFFLOAD_F_ACTION (1 << 0) +void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, + enum flow_dissector_key_id addr_type); + struct nft_rule; struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule); void nft_flow_rule_destroy(struct nft_flow_rule *flow); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 9f625724a20f..9ae14270c543 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -28,6 +28,23 @@ static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions) return flow; } +void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, + enum flow_dissector_key_id addr_type) +{ + struct nft_flow_match *match = &flow->match; + struct nft_flow_key *mask = &match->mask; + struct nft_flow_key *key = &match->key; + + if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) + return; + + key->control.addr_type = addr_type; + mask->control.addr_type = 0xffff; + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); + match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] = + offsetof(struct nft_flow_key, control); +} + struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule) { diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index dcd3c7b8a367..bbf811d030d5 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -244,6 +244,7 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx, NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, src, sizeof(struct in_addr), reg); + nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV4_ADDRS); break; case offsetof(struct iphdr, daddr): if (priv->len != sizeof(struct in_addr)) @@ -251,6 +252,7 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx, NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, dst, sizeof(struct in_addr), reg); + nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV4_ADDRS); break; case offsetof(struct iphdr, protocol): if (priv->len != sizeof(__u8)) @@ -280,6 +282,7 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx, NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, src, sizeof(struct in6_addr), reg); + nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV6_ADDRS); break; case offsetof(struct ipv6hdr, daddr): if (priv->len != sizeof(struct in6_addr)) @@ -287,6 +290,7 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx, NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, dst, sizeof(struct in6_addr), reg); + nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV6_ADDRS); break; case offsetof(struct ipv6hdr, nexthdr): if (priv->len != sizeof(__u8)) -- cgit v1.2.3 From a5d45bc0dc50f9dd83703510e9804d813a9cac32 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 25 Nov 2020 23:50:17 +0100 Subject: netfilter: nftables_offload: build mask based from the matching bytes Userspace might match on prefix bytes of header fields if they are on the byte boundary, this requires that the mask is adjusted accordingly. Use NFT_OFFLOAD_MATCH_EXACT() for meta since prefix byte matching is not allowed for this type of selector. The bitwise expression might be optimized out by userspace, hence the kernel needs to infer the prefix from the number of payload bytes to match on. This patch adds nft_payload_offload_mask() to calculate the bitmask to match on the prefix. Fixes: c9626a2cbdb2 ("netfilter: nf_tables: add hardware offload support") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_offload.h | 3 ++ net/netfilter/nft_cmp.c | 8 ++-- net/netfilter/nft_meta.c | 16 ++++---- net/netfilter/nft_payload.c | 66 +++++++++++++++++++++++-------- 4 files changed, 64 insertions(+), 29 deletions(-) diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h index bddd34c5bd79..1d34fe154fe0 100644 --- a/include/net/netfilter/nf_tables_offload.h +++ b/include/net/netfilter/nf_tables_offload.h @@ -78,6 +78,9 @@ int nft_flow_rule_offload_commit(struct net *net); offsetof(struct nft_flow_key, __base.__field); \ (__reg)->len = __len; \ (__reg)->key = __key; \ + +#define NFT_OFFLOAD_MATCH_EXACT(__key, __base, __field, __len, __reg) \ + NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \ memset(&(__reg)->mask, 0xff, (__reg)->len); int nft_chain_offload_priority(struct nft_base_chain *basechain); diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index bc079d68a536..00e563a72d3d 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -123,11 +123,11 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx, u8 *mask = (u8 *)&flow->match.mask; u8 *key = (u8 *)&flow->match.key; - if (priv->op != NFT_CMP_EQ || reg->len != priv->len) + if (priv->op != NFT_CMP_EQ || priv->len > reg->len) return -EOPNOTSUPP; - memcpy(key + reg->offset, &priv->data, priv->len); - memcpy(mask + reg->offset, ®->mask, priv->len); + memcpy(key + reg->offset, &priv->data, reg->len); + memcpy(mask + reg->offset, ®->mask, reg->len); flow->match.dissector.used_keys |= BIT(reg->key); flow->match.dissector.offset[reg->key] = reg->base_offset; @@ -137,7 +137,7 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx, nft_reg_load16(priv->data.data) != ARPHRD_ETHER) return -EOPNOTSUPP; - nft_offload_update_dependency(ctx, &priv->data, priv->len); + nft_offload_update_dependency(ctx, &priv->data, reg->len); return 0; } diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index b37bd02448d8..bf4b3ad5314c 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -724,22 +724,22 @@ static int nft_meta_get_offload(struct nft_offload_ctx *ctx, switch (priv->key) { case NFT_META_PROTOCOL: - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, n_proto, - sizeof(__u16), reg); + NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_BASIC, basic, n_proto, + sizeof(__u16), reg); nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK); break; case NFT_META_L4PROTO: - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, - sizeof(__u8), reg); + NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, + sizeof(__u8), reg); nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT); break; case NFT_META_IIF: - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_META, meta, - ingress_ifindex, sizeof(__u32), reg); + NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_META, meta, + ingress_ifindex, sizeof(__u32), reg); break; case NFT_META_IIFTYPE: - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_META, meta, - ingress_iftype, sizeof(__u16), reg); + NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_META, meta, + ingress_iftype, sizeof(__u16), reg); break; default: return -EOPNOTSUPP; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index bbf811d030d5..47d4e0e21651 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -165,6 +165,34 @@ nla_put_failure: return -1; } +static bool nft_payload_offload_mask(struct nft_offload_reg *reg, + u32 priv_len, u32 field_len) +{ + unsigned int remainder, delta, k; + struct nft_data mask = {}; + __be32 remainder_mask; + + if (priv_len == field_len) { + memset(®->mask, 0xff, priv_len); + return true; + } else if (priv_len > field_len) { + return false; + } + + memset(&mask, 0xff, field_len); + remainder = priv_len % sizeof(u32); + if (remainder) { + k = priv_len / sizeof(u32); + delta = field_len - priv_len; + remainder_mask = htonl(~((1 << (delta * BITS_PER_BYTE)) - 1)); + mask.data[k] = (__force u32)remainder_mask; + } + + memcpy(®->mask, &mask, field_len); + + return true; +} + static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow, const struct nft_payload *priv) @@ -173,21 +201,21 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct ethhdr, h_source): - if (priv->len != ETH_ALEN) + if (!nft_payload_offload_mask(reg, priv->len, ETH_ALEN)) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs, src, ETH_ALEN, reg); break; case offsetof(struct ethhdr, h_dest): - if (priv->len != ETH_ALEN) + if (!nft_payload_offload_mask(reg, priv->len, ETH_ALEN)) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs, dst, ETH_ALEN, reg); break; case offsetof(struct ethhdr, h_proto): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, @@ -195,14 +223,14 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK); break; case offsetof(struct vlan_ethhdr, h_vlan_TCI): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_VLAN, vlan, vlan_tci, sizeof(__be16), reg); break; case offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_VLAN, vlan, @@ -210,7 +238,7 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK); break; case offsetof(struct vlan_ethhdr, h_vlan_TCI) + sizeof(struct vlan_hdr): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_CVLAN, vlan, @@ -218,7 +246,7 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, break; case offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto) + sizeof(struct vlan_hdr): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_CVLAN, vlan, @@ -239,7 +267,8 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct iphdr, saddr): - if (priv->len != sizeof(struct in_addr)) + if (!nft_payload_offload_mask(reg, priv->len, + sizeof(struct in_addr))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, src, @@ -247,7 +276,8 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx, nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV4_ADDRS); break; case offsetof(struct iphdr, daddr): - if (priv->len != sizeof(struct in_addr)) + if (!nft_payload_offload_mask(reg, priv->len, + sizeof(struct in_addr))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, dst, @@ -255,7 +285,7 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx, nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV4_ADDRS); break; case offsetof(struct iphdr, protocol): - if (priv->len != sizeof(__u8)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__u8))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, @@ -277,7 +307,8 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct ipv6hdr, saddr): - if (priv->len != sizeof(struct in6_addr)) + if (!nft_payload_offload_mask(reg, priv->len, + sizeof(struct in6_addr))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, src, @@ -285,7 +316,8 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx, nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV6_ADDRS); break; case offsetof(struct ipv6hdr, daddr): - if (priv->len != sizeof(struct in6_addr)) + if (!nft_payload_offload_mask(reg, priv->len, + sizeof(struct in6_addr))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, dst, @@ -293,7 +325,7 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx, nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV6_ADDRS); break; case offsetof(struct ipv6hdr, nexthdr): - if (priv->len != sizeof(__u8)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__u8))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, @@ -335,14 +367,14 @@ static int nft_payload_offload_tcp(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct tcphdr, source): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src, sizeof(__be16), reg); break; case offsetof(struct tcphdr, dest): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst, @@ -363,14 +395,14 @@ static int nft_payload_offload_udp(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct udphdr, source): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src, sizeof(__be16), reg); break; case offsetof(struct udphdr, dest): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst, -- cgit v1.2.3 From 484cfbe5fb61469a5f5a276258a8b3973164b56f Mon Sep 17 00:00:00 2001 From: Amelie Delaunay Date: Fri, 27 Nov 2020 14:17:35 +0100 Subject: usb: typec: stusb160x: fix power-opmode property with typec-power-opmode Device tree property is named typec-power-opmode, not power-opmode. Fixes: da0cb6310094 ("usb: typec: add support for STUSB160x Type-C controller family") Signed-off-by: Amelie Delaunay Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20201127131735.28280-1-amelie.delaunay@st.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/stusb160x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/typec/stusb160x.c b/drivers/usb/typec/stusb160x.c index 2a618f02f4f1..d21750bbbb44 100644 --- a/drivers/usb/typec/stusb160x.c +++ b/drivers/usb/typec/stusb160x.c @@ -562,7 +562,7 @@ static int stusb160x_get_fw_caps(struct stusb160x *chip, * Supported power operation mode can be configured through device tree * else it is read from chip registers in stusb160x_get_caps. */ - ret = fwnode_property_read_string(fwnode, "power-opmode", &cap_str); + ret = fwnode_property_read_string(fwnode, "typec-power-opmode", &cap_str); if (!ret) { ret = typec_find_pwr_opmode(cap_str); /* Power delivery not yet supported */ -- cgit v1.2.3 From 402d5840b0d40a2a26c8651165d29b534abb6d36 Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Fri, 27 Nov 2020 22:26:35 +0900 Subject: ALSA: usb-audio: US16x08: fix value count for level meters The level meter control returns 34 integers of info. This fixes: snd-usb-audio 3-1:1.0: control 2:0:0:Level Meter:0: access overflow Fixes: d2bb390a2081 ("ALSA: usb-audio: Tascam US-16x08 DSP mixer quirk") Cc: stable@vger.kernel.org Signed-off-by: Hector Martin Link: https://lore.kernel.org/r/20201127132635.18947-1-marcan@marcan.st Signed-off-by: Takashi Iwai --- sound/usb/mixer_us16x08.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/usb/mixer_us16x08.c b/sound/usb/mixer_us16x08.c index 92b1a6d9c931..bd63a9ce6a70 100644 --- a/sound/usb/mixer_us16x08.c +++ b/sound/usb/mixer_us16x08.c @@ -607,7 +607,7 @@ static int snd_us16x08_eq_put(struct snd_kcontrol *kcontrol, static int snd_us16x08_meter_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { - uinfo->count = 1; + uinfo->count = 34; uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; uinfo->value.integer.max = 0x7FFF; uinfo->value.integer.min = 0; -- cgit v1.2.3 From 72c3bcdcda494cbd600712a32e67702cdee60c07 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 27 Nov 2020 08:53:52 +0100 Subject: KVM: x86: handle !lapic_in_kernel case in kvm_cpu_*_extint Centralize handling of interrupts from the userspace APIC in kvm_cpu_has_extint and kvm_cpu_get_extint, since userspace APIC interrupts are handled more or less the same as ExtINTs are with split irqchip. This removes duplicated code from kvm_cpu_has_injectable_intr and kvm_cpu_has_interrupt, and makes the code more similar between kvm_cpu_has_{extint,interrupt} on one side and kvm_cpu_get_{extint,interrupt} on the other. Cc: stable@vger.kernel.org Reviewed-by: Filippo Sironi Reviewed-by: David Woodhouse Tested-by: David Woodhouse Signed-off-by: Paolo Bonzini --- arch/x86/kvm/irq.c | 83 +++++++++++++++++++++------------------------------- arch/x86/kvm/lapic.c | 2 +- 2 files changed, 34 insertions(+), 51 deletions(-) diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 99d118ffc67d..ee94671272e3 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -41,28 +41,9 @@ static int pending_userspace_extint(struct kvm_vcpu *v) * non-APIC source without intack. */ static int kvm_cpu_has_extint(struct kvm_vcpu *v) -{ - u8 accept = kvm_apic_accept_pic_intr(v); - - if (accept) { - if (irqchip_split(v->kvm)) - return pending_userspace_extint(v); - else - return v->kvm->arch.vpic->output; - } else - return 0; -} - -/* - * check if there is injectable interrupt: - * when virtual interrupt delivery enabled, - * interrupt from apic will handled by hardware, - * we don't need to check it here. - */ -int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) { /* - * FIXME: interrupt.injected represents an interrupt that it's + * FIXME: interrupt.injected represents an interrupt whose * side-effects have already been applied (e.g. bit from IRR * already moved to ISR). Therefore, it is incorrect to rely * on interrupt.injected to know if there is a pending @@ -75,6 +56,23 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) if (!lapic_in_kernel(v)) return v->arch.interrupt.injected; + if (!kvm_apic_accept_pic_intr(v)) + return 0; + + if (irqchip_split(v->kvm)) + return pending_userspace_extint(v); + else + return v->kvm->arch.vpic->output; +} + +/* + * check if there is injectable interrupt: + * when virtual interrupt delivery enabled, + * interrupt from apic will handled by hardware, + * we don't need to check it here. + */ +int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) +{ if (kvm_cpu_has_extint(v)) return 1; @@ -91,20 +89,6 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_injectable_intr); */ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) { - /* - * FIXME: interrupt.injected represents an interrupt that it's - * side-effects have already been applied (e.g. bit from IRR - * already moved to ISR). Therefore, it is incorrect to rely - * on interrupt.injected to know if there is a pending - * interrupt in the user-mode LAPIC. - * This leads to nVMX/nSVM not be able to distinguish - * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on - * pending interrupt or should re-inject an injected - * interrupt. - */ - if (!lapic_in_kernel(v)) - return v->arch.interrupt.injected; - if (kvm_cpu_has_extint(v)) return 1; @@ -118,16 +102,21 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); */ static int kvm_cpu_get_extint(struct kvm_vcpu *v) { - if (kvm_cpu_has_extint(v)) { - if (irqchip_split(v->kvm)) { - int vector = v->arch.pending_external_vector; - - v->arch.pending_external_vector = -1; - return vector; - } else - return kvm_pic_read_irq(v->kvm); /* PIC */ - } else + if (!kvm_cpu_has_extint(v)) { + WARN_ON(!lapic_in_kernel(v)); return -1; + } + + if (!lapic_in_kernel(v)) + return v->arch.interrupt.nr; + + if (irqchip_split(v->kvm)) { + int vector = v->arch.pending_external_vector; + + v->arch.pending_external_vector = -1; + return vector; + } else + return kvm_pic_read_irq(v->kvm); /* PIC */ } /* @@ -135,13 +124,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) */ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) { - int vector; - - if (!lapic_in_kernel(v)) - return v->arch.interrupt.nr; - - vector = kvm_cpu_get_extint(v); - + int vector = kvm_cpu_get_extint(v); if (vector != -1) return vector; /* PIC */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 105e7859d1f2..86c33d53c90a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2465,7 +2465,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; u32 ppr; - if (!kvm_apic_hw_enabled(apic)) + if (!kvm_apic_present(vcpu)) return -1; __apic_update_ppr(apic, &ppr); -- cgit v1.2.3 From 71cc849b7093bb83af966c0e60cb11b7f35cd746 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 27 Nov 2020 09:18:20 +0100 Subject: KVM: x86: Fix split-irqchip vs interrupt injection window request kvm_cpu_accept_dm_intr and kvm_vcpu_ready_for_interrupt_injection are a hodge-podge of conditions, hacked together to get something that more or less works. But what is actually needed is much simpler; in both cases the fundamental question is, do we have a place to stash an interrupt if userspace does KVM_INTERRUPT? In userspace irqchip mode, that is !vcpu->arch.interrupt.injected. Currently kvm_event_needs_reinjection(vcpu) covers it, but it is unnecessarily restrictive. In split irqchip mode it's a bit more complicated, we need to check kvm_apic_accept_pic_intr(vcpu) (the IRQ window exit is basically an INTACK cycle and thus requires ExtINTs not to be masked) as well as !pending_userspace_extint(vcpu). However, there is no need to check kvm_event_needs_reinjection(vcpu), since split irqchip keeps pending ExtINT state separate from event injection state, and checking kvm_cpu_has_interrupt(vcpu) is wrong too since ExtINT has higher priority than APIC interrupts. In fact the latter fixes a bug: when userspace requests an IRQ window vmexit, an interrupt in the local APIC can cause kvm_cpu_has_interrupt() to be true and thus kvm_vcpu_ready_for_interrupt_injection() to return false. When this happens, vcpu_run does not exit to userspace but the interrupt window vmexits keep occurring. The VM loops without any hope of making progress. Once we try to fix these with something like return kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && - !kvm_event_needs_reinjection(vcpu) && - kvm_cpu_accept_dm_intr(vcpu); + (!lapic_in_kernel(vcpu) + ? !vcpu->arch.interrupt.injected + : (kvm_apic_accept_pic_intr(vcpu) + && !pending_userspace_extint(v))); we realize two things. First, thanks to the previous patch the complex conditional can reuse !kvm_cpu_has_extint(vcpu). Second, the interrupt window request in vcpu_enter_guest() bool req_int_win = dm_request_for_irq_injection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); should be kept in sync with kvm_vcpu_ready_for_interrupt_injection(): it is unnecessary to ask the processor for an interrupt window if we would not be able to return to userspace. Therefore, kvm_cpu_accept_dm_intr(vcpu) is basically !kvm_cpu_has_extint(vcpu) ANDed with the existing check for masked ExtINT. It all makes sense: - we can accept an interrupt from userspace if there is a place to stash it (and, for irqchip split, ExtINTs are not masked). Interrupts from userspace _can_ be accepted even if right now EFLAGS.IF=0. - in order to tell userspace we will inject its interrupt ("IRQ window open" i.e. kvm_vcpu_ready_for_interrupt_injection), both KVM and the vCPU need to be ready to accept the interrupt. ... and this is what the patch implements. Reported-by: David Woodhouse Analyzed-by: David Woodhouse Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini Reviewed-by: Nikos Tsironis Reviewed-by: David Woodhouse Tested-by: David Woodhouse --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/irq.c | 2 +- arch/x86/kvm/x86.c | 18 ++++++++++-------- 3 files changed, 12 insertions(+), 9 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 324ddd7fd0aa..7e5f33a0d0e2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1656,6 +1656,7 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); +int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index ee94671272e3..814698e5b152 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -40,7 +40,7 @@ static int pending_userspace_extint(struct kvm_vcpu *v) * check if there is pending interrupt from * non-APIC source without intack. */ -static int kvm_cpu_has_extint(struct kvm_vcpu *v) +int kvm_cpu_has_extint(struct kvm_vcpu *v) { /* * FIXME: interrupt.injected represents an interrupt whose diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 078a39d489fe..e545a8a613b1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4051,21 +4051,23 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) { + /* + * We can accept userspace's request for interrupt injection + * as long as we have a place to store the interrupt number. + * The actual injection will happen when the CPU is able to + * deliver the interrupt. + */ + if (kvm_cpu_has_extint(vcpu)) + return false; + + /* Acknowledging ExtINT does not happen if LINT0 is masked. */ return (!lapic_in_kernel(vcpu) || kvm_apic_accept_pic_intr(vcpu)); } -/* - * if userspace requested an interrupt window, check that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) { return kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && - !kvm_event_needs_reinjection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); } -- cgit v1.2.3 From 9a2a0d3ca163fc645991804b8b032f7d59326bb5 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Thu, 26 Nov 2020 12:02:06 +0100 Subject: kvm: x86/mmu: Fix get_mmio_spte() on CPUs supporting 5-level PT Commit 95fb5b0258b7 ("kvm: x86/mmu: Support MMIO in the TDP MMU") caused the following WARNING on an Intel Ice Lake CPU: get_mmio_spte: detect reserved bits on spte, addr 0xb80a0, dump hierarchy: ------ spte 0xb80a0 level 5. ------ spte 0xfcd210107 level 4. ------ spte 0x1004c40107 level 3. ------ spte 0x1004c41107 level 2. ------ spte 0x1db00000000b83b6 level 1. WARNING: CPU: 109 PID: 10254 at arch/x86/kvm/mmu/mmu.c:3569 kvm_mmu_page_fault.cold.150+0x54/0x22f [kvm] ... Call Trace: ? kvm_io_bus_get_first_dev+0x55/0x110 [kvm] vcpu_enter_guest+0xaa1/0x16a0 [kvm] ? vmx_get_cs_db_l_bits+0x17/0x30 [kvm_intel] ? skip_emulated_instruction+0xaa/0x150 [kvm_intel] kvm_arch_vcpu_ioctl_run+0xca/0x520 [kvm] The guest triggering this crashes. Note, this happens with the traditional MMU and EPT enabled, not with the newly introduced TDP MMU. Turns out, there was a subtle change in the above mentioned commit. Previously, walk_shadow_page_get_mmio_spte() was setting 'root' to 'iterator.level' which is returned by shadow_walk_init() and this equals to 'vcpu->arch.mmu->shadow_root_level'. Now, get_mmio_spte() sets it to 'int root = vcpu->arch.mmu->root_level'. The difference between 'root_level' and 'shadow_root_level' on CPUs supporting 5-level page tables is that in some case we don't want to use 5-level, in particular when 'cpuid_maxphyaddr(vcpu) <= 48' kvm_mmu_get_tdp_level() returns '4'. In case upper layer is not used, the corresponding SPTE will fail '__is_rsvd_bits_set()' check. Revert to using 'shadow_root_level'. Fixes: 95fb5b0258b7 ("kvm: x86/mmu: Support MMIO in the TDP MMU") Signed-off-by: Vitaly Kuznetsov Message-Id: <20201126110206.2118959-1-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 5bb1939b65d8..7a6ae9e90bd7 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3517,7 +3517,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { u64 sptes[PT64_ROOT_MAX_LEVEL]; struct rsvd_bits_validate *rsvd_check; - int root = vcpu->arch.mmu->root_level; + int root = vcpu->arch.mmu->shadow_root_level; int leaf; int level; bool reserved = false; -- cgit v1.2.3 From 25bc65d8ddfc17cc1d7a45bd48e9bdc0e729ced3 Mon Sep 17 00:00:00 2001 From: Gabriele Paoloni Date: Fri, 27 Nov 2020 16:18:15 +0000 Subject: x86/mce: Do not overwrite no_way_out if mce_end() fails Currently, if mce_end() fails, no_way_out - the variable denoting whether the machine can recover from this MCE - is determined by whether the worst severity that was found across the MCA banks associated with the current CPU, is of panic severity. However, at this point no_way_out could have been already set by mca_start() after looking at all severities of all CPUs that entered the MCE handler. If mce_end() fails, check first if no_way_out is already set and, if so, stick to it, otherwise use the local worst value. [ bp: Massage. ] Signed-off-by: Gabriele Paoloni Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Cc: Link: https://lkml.kernel.org/r/20201127161819.3106432-2-gabriele.paoloni@intel.com --- arch/x86/kernel/cpu/mce/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 4102b866e7c0..32b7099e3511 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1384,8 +1384,10 @@ noinstr void do_machine_check(struct pt_regs *regs) * When there's any problem use only local no_way_out state. */ if (!lmce) { - if (mce_end(order) < 0) - no_way_out = worst >= MCE_PANIC_SEVERITY; + if (mce_end(order) < 0) { + if (!no_way_out) + no_way_out = worst >= MCE_PANIC_SEVERITY; + } } else { /* * If there was a fatal machine check we should have -- cgit v1.2.3 From 3b13eaf0ba1d5ab59368e23ff5e5350f51c1a352 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 18 Nov 2020 08:32:33 -0300 Subject: perf tools: Update copy of libbpf's hashmap.c To pick the changes in: 7a078d2d18801bba ("libbpf, hashmap: Fix undefined behavior in hash_bits") That don't entail any changes in tools/perf. This addresses this perf build warning: Warning: Kernel ABI header at 'tools/perf/util/hashmap.h' differs from latest version at 'tools/lib/bpf/hashmap.h' diff -u tools/perf/util/hashmap.h tools/lib/bpf/hashmap.h Not a kernel ABI, its just that this uses the mechanism in place for checking kernel ABI files drift. Cc: Adrian Hunter Cc: Daniel Borkmann Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hashmap.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h index d9b385fe808c..10a4c4cd13cf 100644 --- a/tools/perf/util/hashmap.h +++ b/tools/perf/util/hashmap.h @@ -15,6 +15,9 @@ static inline size_t hash_bits(size_t h, int bits) { /* shuffle bits and return requested number of upper bits */ + if (bits == 0) + return 0; + #if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__) /* LP64 case */ return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits); @@ -174,17 +177,17 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value); * @key: key to iterate entries for */ #define hashmap__for_each_key_entry(map, cur, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur; \ cur = cur->next) \ if (map->equal_fn(cur->key, (_key), map->ctx)) #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - cur = map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur && ({ tmp = cur->next; true; }); \ cur = tmp) \ if (map->equal_fn(cur->key, (_key), map->ctx)) -- cgit v1.2.3 From 9713070028b9ab317f395ee130fa2c4ea741bab4 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Tue, 24 Nov 2020 18:36:52 +0800 Subject: perf diff: Fix error return value in __cmd_diff() An appropriate return value should be set on the failed path. Fixes: 2a09a84c720b436a ("perf diff: Support hot streams comparison") Reported-by: Hulk Robot Signed-off-by: Zhen Lei Acked-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Jin Yao Cc: Mark Rutland Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20201124103652.438-1-thunder.leizhen@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-diff.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 584e2e1a3793..cefc71506409 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -1222,8 +1222,10 @@ static int __cmd_diff(void) if (compute == COMPUTE_STREAM) { d->evlist_streams = evlist__create_streams( d->session->evlist, 5); - if (!d->evlist_streams) + if (!d->evlist_streams) { + ret = -ENOMEM; goto out_delete; + } } } -- cgit v1.2.3 From aa50d953c169e876413bf237319e728dd41d9fdd Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 27 Nov 2020 14:43:56 +0900 Subject: perf record: Synthesize cgroup events only if needed It didn't check the tool->cgroup_events bit which is set when the --all-cgroups option is given. Without it, samples will not have cgroup info so no reason to synthesize. We can check the PERF_RECORD_CGROUP records after running perf record *WITHOUT* the --all-cgroups option: Before: $ perf report -D | grep CGROUP 0 0 0x8430 [0x38]: PERF_RECORD_CGROUP cgroup: 1 / CGROUP events: 1 CGROUP events: 0 CGROUP events: 0 After: $ perf report -D | grep CGROUP CGROUP events: 0 CGROUP events: 0 CGROUP events: 0 Committer testing: Before: # perf record -a sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 2.208 MB perf.data (10003 samples) ] # perf report -D | grep "CGROUP events" CGROUP events: 146 CGROUP events: 0 CGROUP events: 0 # After: # perf record -a sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 2.208 MB perf.data (10448 samples) ] # perf report -D | grep "CGROUP events" CGROUP events: 0 CGROUP events: 0 CGROUP events: 0 # With all-cgroups: # perf record --all-cgroups -a sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 2.374 MB perf.data (11526 samples) ] # perf report -D | grep "CGROUP events" CGROUP events: 146 CGROUP events: 0 CGROUP events: 0 # Fixes: 8fb4b67939e16 ("perf record: Add --all-cgroups option") Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Ian Rogers Cc: Mark Rutland Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20201127054356.405481-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/synthetic-events.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 8a23391558cf..d9c624377da7 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -563,6 +563,9 @@ int perf_event__synthesize_cgroups(struct perf_tool *tool, char cgrp_root[PATH_MAX]; size_t mount_len; /* length of mount point in the path */ + if (!tool || !tool->cgroup_events) + return 0; + if (cgroupfs_find_mountpoint(cgrp_root, PATH_MAX, "perf_event") < 0) { pr_debug("cannot find cgroup mount point\n"); return -1; -- cgit v1.2.3 From c0ee1d5ae8c8650031badcfca6483a28c0f94f38 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 27 Nov 2020 13:14:03 +0900 Subject: perf stat: Use proper cpu for shadow stats Currently perf stat shows some metrics (like IPC) for defined events. But when no aggregation mode is used (-A option), it shows incorrect values since it used a value from a different cpu. Before: $ perf stat -aA -e cycles,instructions sleep 1 Performance counter stats for 'system wide': CPU0 116,057,380 cycles CPU1 86,084,722 cycles CPU2 99,423,125 cycles CPU3 98,272,994 cycles CPU0 53,369,217 instructions # 0.46 insn per cycle CPU1 33,378,058 instructions # 0.29 insn per cycle CPU2 58,150,086 instructions # 0.50 insn per cycle CPU3 40,029,703 instructions # 0.34 insn per cycle 1.001816971 seconds time elapsed So the IPC for CPU1 should be 0.38 (= 33,378,058 / 86,084,722) but it was 0.29 (= 33,378,058 / 116,057,380) and so on. After: $ perf stat -aA -e cycles,instructions sleep 1 Performance counter stats for 'system wide': CPU0 109,621,384 cycles CPU1 159,026,454 cycles CPU2 99,460,366 cycles CPU3 124,144,142 cycles CPU0 44,396,706 instructions # 0.41 insn per cycle CPU1 120,195,425 instructions # 0.76 insn per cycle CPU2 44,763,978 instructions # 0.45 insn per cycle CPU3 69,049,079 instructions # 0.56 insn per cycle 1.001910444 seconds time elapsed Fixes: 44d49a600259 ("perf stat: Support metrics in --per-core/socket mode") Reported-by: Sam Xi Signed-off-by: Namhyung Kim Reviewed-by: Andi Kleen Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Ian Rogers Cc: Mark Rutland Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20201127041404.390276-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-display.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 4b57c0c07632..a963b5b8eb72 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -324,13 +324,10 @@ static int first_shadow_cpu(struct perf_stat_config *config, struct evlist *evlist = evsel->evlist; int i; - if (!config->aggr_get_id) - return 0; - if (config->aggr_mode == AGGR_NONE) return id; - if (config->aggr_mode == AGGR_GLOBAL) + if (!config->aggr_get_id) return 0; for (i = 0; i < evsel__nr_cpus(evsel); i++) { -- cgit v1.2.3 From ab4200c17ba6fe71d2da64317aae8a8aa684624c Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 27 Nov 2020 14:48:46 +0900 Subject: perf probe: Fix to die_entrypc() returns error correctly Fix die_entrypc() to return error correctly if the DIE has no DW_AT_ranges attribute. Since dwarf_ranges() will treat the case as an empty ranges and return 0, we have to check it by ourselves. Fixes: 91e2f539eeda ("perf probe: Fix to show function entry line as probe-able") Signed-off-by: Masami Hiramatsu Cc: Sumanth Korikkar Cc: Thomas Richter Link: http://lore.kernel.org/lkml/160645612634.2824037.5284932731175079426.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dwarf-aux.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index aa898014ad12..03c1a39c312a 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -373,6 +373,7 @@ bool die_is_func_def(Dwarf_Die *dw_die) int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr) { Dwarf_Addr base, end; + Dwarf_Attribute attr; if (!addr) return -EINVAL; @@ -380,6 +381,13 @@ int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr) if (dwarf_entrypc(dw_die, addr) == 0) return 0; + /* + * Since the dwarf_ranges() will return 0 if there is no + * DW_AT_ranges attribute, we should check it first. + */ + if (!dwarf_attr(dw_die, DW_AT_ranges, &attr)) + return -ENOENT; + return dwarf_ranges(dw_die, 0, &base, addr, &end) < 0 ? -ENOENT : 0; } -- cgit v1.2.3 From a9ffd0484eb4426e6befd07e7be6c01108716302 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 27 Nov 2020 14:48:55 +0900 Subject: perf probe: Change function definition check due to broken DWARF Since some gcc generates a broken DWARF which lacks DW_AT_declaration attribute from the subprogram DIE of function prototype. (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97060) So, in addition to the DW_AT_declaration check, we also check the subprogram DIE has DW_AT_inline or actual entry pc. Committer testing: # cat /etc/fedora-release Fedora release 33 (Thirty Three) # Before: # perf test vfs_getname 78: Use vfs_getname probe to get syscall args filenames : FAILED! 79: Check open filename arg using perf trace + vfs_getname : FAILED! 81: Add vfs_getname probe to get syscall args filenames : FAILED! # After: # perf test vfs_getname 78: Use vfs_getname probe to get syscall args filenames : Ok 79: Check open filename arg using perf trace + vfs_getname : Ok 81: Add vfs_getname probe to get syscall args filenames : Ok # Reported-by: Thomas Richter Signed-off-by: Masami Hiramatsu Tested-by: Arnaldo Carvalho de Melo Cc: Sumanth Korikkar Link: http://lore.kernel.org/lkml/160645613571.2824037.7441351537890235895.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dwarf-aux.c | 20 ++++++++++++++++++-- tools/perf/util/probe-finder.c | 3 +-- 2 files changed, 19 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 03c1a39c312a..7b2d471a6419 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -356,9 +356,25 @@ bool die_is_signed_type(Dwarf_Die *tp_die) bool die_is_func_def(Dwarf_Die *dw_die) { Dwarf_Attribute attr; + Dwarf_Addr addr = 0; + + if (dwarf_tag(dw_die) != DW_TAG_subprogram) + return false; + + if (dwarf_attr(dw_die, DW_AT_declaration, &attr)) + return false; - return (dwarf_tag(dw_die) == DW_TAG_subprogram && - dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL); + /* + * DW_AT_declaration can be lost from function declaration + * by gcc's bug #97060. + * So we need to check this subprogram DIE has DW_AT_inline + * or an entry address. + */ + if (!dwarf_attr(dw_die, DW_AT_inline, &attr) && + die_entrypc(dw_die, &addr) < 0) + return false; + + return true; } /** diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 2c4061035f77..76dd349aa48d 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1885,8 +1885,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die))) return DWARF_CB_OK; - if (die_is_func_def(sp_die) && - die_match_name(sp_die, lr->function)) { + if (die_match_name(sp_die, lr->function) && die_is_func_def(sp_die)) { lf->fname = dwarf_decl_file(sp_die); dwarf_decl_line(sp_die, &lr->offset); pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset); -- cgit v1.2.3 From 69929d4c49e182f8526d42c43b37b460d562d3a0 Mon Sep 17 00:00:00 2001 From: Eelco Chaudron Date: Tue, 24 Nov 2020 07:34:44 -0500 Subject: net: openvswitch: fix TTL decrement action netlink message format Currently, the openvswitch module is not accepting the correctly formated netlink message for the TTL decrement action. For both setting and getting the dec_ttl action, the actions should be nested in the OVS_DEC_TTL_ATTR_ACTION attribute as mentioned in the openvswitch.h uapi. When the original patch was sent, it was tested with a private OVS userspace implementation. This implementation was unfortunately not upstreamed and reviewed, hence an erroneous version of this patch was sent out. Leaving the patch as-is would cause problems as the kernel module could interpret additional attributes as actions and vice-versa, due to the actions not being encapsulated/nested within the actual attribute, but being concatinated after it. Fixes: 744676e77720 ("openvswitch: add TTL decrement action") Signed-off-by: Eelco Chaudron Link: https://lore.kernel.org/r/160622121495.27296.888010441924340582.stgit@wsfd-netdev64.ntdv.lab.eng.bos.redhat.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/openvswitch.h | 2 ++ net/openvswitch/actions.c | 7 ++-- net/openvswitch/flow_netlink.c | 74 +++++++++++++++++++++++++++++----------- 3 files changed, 60 insertions(+), 23 deletions(-) diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 8300cc29dec8..8d16744edc31 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -1058,4 +1058,6 @@ enum ovs_dec_ttl_attr { __OVS_DEC_TTL_ATTR_MAX }; +#define OVS_DEC_TTL_ATTR_MAX (__OVS_DEC_TTL_ATTR_MAX - 1) + #endif /* _LINUX_OPENVSWITCH_H */ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index b87bfc82f44f..5829a020b81c 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -958,14 +958,13 @@ static int dec_ttl_exception_handler(struct datapath *dp, struct sk_buff *skb, { /* The first action is always 'OVS_DEC_TTL_ATTR_ARG'. */ struct nlattr *dec_ttl_arg = nla_data(attr); - int rem = nla_len(attr); if (nla_len(dec_ttl_arg)) { - struct nlattr *actions = nla_next(dec_ttl_arg, &rem); + struct nlattr *actions = nla_data(dec_ttl_arg); if (actions) - return clone_execute(dp, skb, key, 0, actions, rem, - last, false); + return clone_execute(dp, skb, key, 0, nla_data(actions), + nla_len(actions), last, false); } consume_skb(skb); return 0; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 9d3e50c4d29f..ec0689ddc635 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2503,28 +2503,42 @@ static int validate_and_copy_dec_ttl(struct net *net, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, bool log) { - int start, err; - u32 nested = true; + const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1]; + int start, action_start, err, rem; + const struct nlattr *a, *actions; + + memset(attrs, 0, sizeof(attrs)); + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); - if (!nla_len(attr)) - return ovs_nla_add_action(sfa, OVS_ACTION_ATTR_DEC_TTL, - NULL, 0, log); + /* Ignore unknown attributes to be future proof. */ + if (type > OVS_DEC_TTL_ATTR_MAX) + continue; + + if (!type || attrs[type]) + return -EINVAL; + + attrs[type] = a; + } + + actions = attrs[OVS_DEC_TTL_ATTR_ACTION]; + if (rem || !actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN)) + return -EINVAL; start = add_nested_action_start(sfa, OVS_ACTION_ATTR_DEC_TTL, log); if (start < 0) return start; - err = ovs_nla_add_action(sfa, OVS_DEC_TTL_ATTR_ACTION, &nested, - sizeof(nested), log); - - if (err) - return err; + action_start = add_nested_action_start(sfa, OVS_DEC_TTL_ATTR_ACTION, log); + if (action_start < 0) + return start; - err = __ovs_nla_copy_actions(net, attr, key, sfa, eth_type, + err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, vlan_tci, mpls_label_count, log); if (err) return err; + add_nested_action_end(*sfa, action_start); add_nested_action_end(*sfa, start); return 0; } @@ -3487,20 +3501,42 @@ out: static int dec_ttl_action_to_attr(const struct nlattr *attr, struct sk_buff *skb) { - int err = 0, rem = nla_len(attr); - struct nlattr *start; + struct nlattr *start, *action_start; + const struct nlattr *a; + int err = 0, rem; start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_DEC_TTL); - if (!start) return -EMSGSIZE; - err = ovs_nla_put_actions(nla_data(attr), rem, skb); - if (err) - nla_nest_cancel(skb, start); - else - nla_nest_end(skb, start); + nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) { + switch (nla_type(a)) { + case OVS_DEC_TTL_ATTR_ACTION: + + action_start = nla_nest_start_noflag(skb, OVS_DEC_TTL_ATTR_ACTION); + if (!action_start) { + err = -EMSGSIZE; + goto out; + } + + err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb); + if (err) + goto out; + + nla_nest_end(skb, action_start); + break; + default: + /* Ignore all other option to be future compatible */ + break; + } + } + + nla_nest_end(skb, start); + return 0; + +out: + nla_nest_cancel(skb, start); return err; } -- cgit v1.2.3 From d3ab78858f1451351221061a1c365495df196500 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 26 Nov 2020 15:17:53 +0100 Subject: mptcp: fix NULL ptr dereference on bad MPJ If an msk listener receives an MPJ carrying an invalid token, it will zero the request socket msk entry. That should later cause fallback and subflow reset - as per RFC - at subflow_syn_recv_sock() time due to failing hmac validation. Since commit 4cf8b7e48a09 ("subflow: introduce and use mptcp_can_accept_new_subflow()"), we unconditionally dereference - in mptcp_can_accept_new_subflow - the subflow request msk before performing hmac validation. In the above scenario we hit a NULL ptr dereference. Address the issue doing the hmac validation earlier. Fixes: 4cf8b7e48a09 ("subflow: introduce and use mptcp_can_accept_new_subflow()") Tested-by: Davide Caratti Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Link: https://lore.kernel.org/r/03b2cfa3ac80d8fc18272edc6442a9ddf0b1e34e.1606400227.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- net/mptcp/subflow.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ac4a1fe3550b..953906e40742 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -543,9 +543,8 @@ create_msk: fallback = true; } else if (subflow_req->mp_join) { mptcp_get_options(skb, &mp_opt); - if (!mp_opt.mp_join || - !mptcp_can_accept_new_subflow(subflow_req->msk) || - !subflow_hmac_valid(req, &mp_opt)) { + if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) || + !mptcp_can_accept_new_subflow(subflow_req->msk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); fallback = true; } -- cgit v1.2.3 From 985f7337421a811cb354ca93882f943c8335a6f5 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 26 Nov 2020 10:12:20 -0500 Subject: sock: set sk_err to ee_errno on dequeue from errq When setting sk_err, set it to ee_errno, not ee_origin. Commit f5f99309fa74 ("sock: do not set sk_err in sock_dequeue_err_skb") disabled updating sk_err on errq dequeue, which is correct for most error types (origins): - sk->sk_err = err; Commit 38b257938ac6 ("sock: reset sk_err when the error queue is empty") reenabled the behavior for IMCP origins, which do require it: + if (icmp_next) + sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_origin; But read from ee_errno. Fixes: 38b257938ac6 ("sock: reset sk_err when the error queue is empty") Reported-by: Ayush Ranjan Signed-off-by: Willem de Bruijn Acked-by: Soheil Hassas Yeganeh Link: https://lore.kernel.org/r/20201126151220.2819322-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- net/core/skbuff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1ba8f0163744..06c526e0d810 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4549,7 +4549,7 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk) if (skb && (skb_next = skb_peek(q))) { icmp_next = is_icmp_err_skb(skb_next); if (icmp_next) - sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_origin; + sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno; } spin_unlock_irqrestore(&q->lock, flags); -- cgit v1.2.3 From 242d990c158d5b1dabd166516e21992baef5f26a Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 27 Nov 2020 15:11:03 +0100 Subject: ALSA: hda/generic: Add option to enforce preferred_dacs pairs The generic parser accepts the preferred_dacs[] pairs as a hint for assigning a DAC to each pin, but this hint doesn't work always effectively. Currently it's merely a secondary choice after the trial with the path index failed. This made sometimes it difficult to assign DACs without mimicking the connection list and/or the badness table. This patch adds a new flag, obey_preferred_dacs, that changes the behavior of the parser. As its name stands, the parser obeys the given preferred_dacs[] pairs by skipping the path index matching and giving a high penalty if no DAC is assigned by the pairs. This mode will help for assigning the fixed DACs forcibly from the codec driver. Cc: Link: https://lore.kernel.org/r/20201127141104.11041-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_generic.c | 12 ++++++++---- sound/pci/hda/hda_generic.h | 1 + 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index bbb17481159e..8060cc86dfea 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -1364,16 +1364,20 @@ static int try_assign_dacs(struct hda_codec *codec, int num_outs, struct nid_path *path; hda_nid_t pin = pins[i]; - path = snd_hda_get_path_from_idx(codec, path_idx[i]); - if (path) { - badness += assign_out_path_ctls(codec, path); - continue; + if (!spec->obey_preferred_dacs) { + path = snd_hda_get_path_from_idx(codec, path_idx[i]); + if (path) { + badness += assign_out_path_ctls(codec, path); + continue; + } } dacs[i] = get_preferred_dac(codec, pin); if (dacs[i]) { if (is_dac_already_used(codec, dacs[i])) badness += bad->shared_primary; + } else if (spec->obey_preferred_dacs) { + badness += BAD_NO_PRIMARY_DAC; } if (!dacs[i]) diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h index a43f0bb77dae..0886bc81f40b 100644 --- a/sound/pci/hda/hda_generic.h +++ b/sound/pci/hda/hda_generic.h @@ -237,6 +237,7 @@ struct hda_gen_spec { unsigned int power_down_unused:1; /* power down unused widgets */ unsigned int dac_min_mute:1; /* minimal = mute for DACs */ unsigned int suppress_vmaster:1; /* don't create vmaster kctls */ + unsigned int obey_preferred_dacs:1; /* obey preferred_dacs assignment */ /* other internal flags */ unsigned int no_analog:1; /* digital I/O only */ -- cgit v1.2.3 From c84bfedce60192c08455ee2d25dd13d19274a266 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 27 Nov 2020 15:11:04 +0100 Subject: ALSA: hda/realtek: Fix bass speaker DAC assignment on Asus Zephyrus G14 ASUS Zephyrus G14 has two speaker pins, and the auto-parser tries to assign an individual DAC to each pin as much as possible. Unfortunately the third DAC has no volume control unlike the two DACs, and this resulted in the inconsistent speaker volumes. As a workaround, wire both speaker pins to the same DAC by modifying the existing quirk (ALC289_FIXUP_ASUS_GA401) applied to this device. Since this quirk entry is chained by another, we need to avoid applying the DAC assignment change for it. Luckily, there is another quirk entry (ALC289_FIXUP_ASUS_GA502) doing the very same thing, so we can chain to the GA502 quirk instead. Note that this patch uses a new flag of the generic parser, obey_preferred_dacs, for enforcing the DACs. BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=210359 Cc: Link: https://lore.kernel.org/r/20201127141104.11041-2-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index fcd1fb18ece9..c7e8680a7190 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6027,6 +6027,21 @@ static void alc274_fixup_bind_dacs(struct hda_codec *codec, codec->power_save_node = 0; } +/* avoid DAC 0x06 for bass speaker 0x17; it has no volume control */ +static void alc289_fixup_asus_ga401(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + static const hda_nid_t preferred_pairs[] = { + 0x14, 0x02, 0x17, 0x02, 0x21, 0x03, 0 + }; + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + spec->gen.preferred_dacs = preferred_pairs; + spec->gen.obey_preferred_dacs = 1; + } +} + /* The DAC of NID 0x3 will introduce click/pop noise on headphones, so invalidate it */ static void alc285_fixup_invalidate_dacs(struct hda_codec *codec, const struct hda_fixup *fix, int action) @@ -7600,11 +7615,10 @@ static const struct hda_fixup alc269_fixups[] = { .chain_id = ALC269_FIXUP_HEADSET_MIC }, [ALC289_FIXUP_ASUS_GA401] = { - .type = HDA_FIXUP_PINS, - .v.pins = (const struct hda_pintbl[]) { - { 0x19, 0x03a11020 }, /* headset mic with jack detect */ - { } - }, + .type = HDA_FIXUP_FUNC, + .v.func = alc289_fixup_asus_ga401, + .chained = true, + .chain_id = ALC289_FIXUP_ASUS_GA502, }, [ALC289_FIXUP_ASUS_GA502] = { .type = HDA_FIXUP_PINS, @@ -7728,7 +7742,7 @@ static const struct hda_fixup alc269_fixups[] = { { } }, .chained = true, - .chain_id = ALC289_FIXUP_ASUS_GA401 + .chain_id = ALC289_FIXUP_ASUS_GA502 }, [ALC274_FIXUP_HP_MIC] = { .type = HDA_FIXUP_VERBS, -- cgit v1.2.3 From aeedad2504997be262c98f6e3228173225a8d868 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sat, 28 Nov 2020 10:00:15 +0100 Subject: ALSA: hda/realtek: Add mute LED quirk to yet another HP x360 model HP Spectre x360 Convertible 15" version (SSID 103c:827f) needs the same quirk to make the mute LED working like other models. System Information Manufacturer: HP Product Name: HP Spectre x360 Convertible 15-bl1XX Sound Codec: Codec: Realtek ALC295 Vendor Id: 0x10ec0295 Subsystem Id: 0x103c827f Revision Id: 0x100002 Reported-by: Cc: Link: https://lore.kernel.org/r/20201128090015.7743-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index c7e8680a7190..8616c5624870 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7934,6 +7934,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8256, "HP", ALC221_FIXUP_HP_FRONT_MIC), SND_PCI_QUIRK(0x103c, 0x827e, "HP x360", ALC295_FIXUP_HP_X360), + SND_PCI_QUIRK(0x103c, 0x827f, "HP x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x82bf, "HP G3 mini", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x82c0, "HP G3 mini premium", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), -- cgit v1.2.3 From 44f64f23bae2f0fad25503bc7ab86cd08d04cd47 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Mon, 23 Nov 2020 18:49:02 +0100 Subject: netfilter: bridge: reset skb->pkt_type after NF_INET_POST_ROUTING traversal Netfilter changes PACKET_OTHERHOST to PACKET_HOST before invoking the hooks as, while it's an expected value for a bridge, routing expects PACKET_HOST. The change is undone later on after hook traversal. This can be seen with pairs of functions updating skb>pkt_type and then reverting it to its original value: For hook NF_INET_PRE_ROUTING: setup_pre_routing / br_nf_pre_routing_finish For hook NF_INET_FORWARD: br_nf_forward_ip / br_nf_forward_finish But the third case where netfilter does this, for hook NF_INET_POST_ROUTING, the packet type is changed in br_nf_post_routing but never reverted. A comment says: /* We assume any code from br_dev_queue_push_xmit onwards doesn't care * about the value of skb->pkt_type. */ But when having a tunnel (say vxlan) attached to a bridge we have the following call trace: br_nf_pre_routing br_nf_pre_routing_ipv6 br_nf_pre_routing_finish br_nf_forward_ip br_nf_forward_finish br_nf_post_routing <- pkt_type is updated to PACKET_HOST br_nf_dev_queue_xmit <- but not reverted to its original value vxlan_xmit vxlan_xmit_one skb_tunnel_check_pmtu <- a check on pkt_type is performed In this specific case, this creates issues such as when an ICMPv6 PTB should be sent back. When CONFIG_BRIDGE_NETFILTER is enabled, the PTB isn't sent (as skb_tunnel_check_pmtu checks if pkt_type is PACKET_HOST and returns early). If the comment is right and no one cares about the value of skb->pkt_type after br_dev_queue_push_xmit (which isn't true), resetting it to its original value should be safe. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Antoine Tenart Reviewed-by: Florian Westphal Link: https://lore.kernel.org/r/20201123174902.622102-1-atenart@kernel.org Signed-off-by: Jakub Kicinski --- net/bridge/br_netfilter_hooks.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 04c3f9a82650..8edfb98ae1d5 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -735,6 +735,11 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff mtu_reserved = nf_bridge_mtu_reduction(skb); mtu = skb->dev->mtu; + if (nf_bridge->pkt_otherhost) { + skb->pkt_type = PACKET_OTHERHOST; + nf_bridge->pkt_otherhost = false; + } + if (nf_bridge->frag_max_size && nf_bridge->frag_max_size < mtu) mtu = nf_bridge->frag_max_size; @@ -835,8 +840,6 @@ static unsigned int br_nf_post_routing(void *priv, else return NF_ACCEPT; - /* We assume any code from br_dev_queue_push_xmit onwards doesn't care - * about the value of skb->pkt_type. */ if (skb->pkt_type == PACKET_OTHERHOST) { skb->pkt_type = PACKET_HOST; nf_bridge->pkt_otherhost = true; -- cgit v1.2.3 From 1ebf179037cb46c19da3a9c1e2ca16e7a754b75e Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Thu, 26 Nov 2020 19:09:22 +0100 Subject: ipv4: Fix tos mask in inet_rtm_getroute() When inet_rtm_getroute() was converted to use the RCU variants of ip_route_input() and ip_route_output_key(), the TOS parameters stopped being masked with IPTOS_RT_MASK before doing the route lookup. As a result, "ip route get" can return a different route than what would be used when sending real packets. For example: $ ip route add 192.0.2.11/32 dev eth0 $ ip route add unreachable 192.0.2.11/32 tos 2 $ ip route get 192.0.2.11 tos 2 RTNETLINK answers: No route to host But, packets with TOS 2 (ECT(0) if interpreted as an ECN bit) would actually be routed using the first route: $ ping -c 1 -Q 2 192.0.2.11 PING 192.0.2.11 (192.0.2.11) 56(84) bytes of data. 64 bytes from 192.0.2.11: icmp_seq=1 ttl=64 time=0.173 ms --- 192.0.2.11 ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 0.173/0.173/0.173/0.000 ms This patch re-applies IPTOS_RT_MASK in inet_rtm_getroute(), to return results consistent with real route lookups. Fixes: 3765d35ed8b9 ("net: ipv4: Convert inet_rtm_getroute to rcu versions of route lookup") Signed-off-by: Guillaume Nault Reviewed-by: David Ahern Link: https://lore.kernel.org/r/b2d237d08317ca55926add9654a48409ac1b8f5b.1606412894.git.gnault@redhat.com Signed-off-by: Jakub Kicinski --- net/ipv4/route.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index dc2a399cd9f4..9f43abeac3a8 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3222,7 +3222,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.daddr = dst; fl4.saddr = src; - fl4.flowi4_tos = rtm->rtm_tos; + fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK; fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; @@ -3246,8 +3246,9 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; - err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos, - dev, &res); + err = ip_route_input_rcu(skb, dst, src, + rtm->rtm_tos & IPTOS_RT_MASK, dev, + &res); rt = skb_rtable(skb); if (err == 0 && rt->dst.error) -- cgit v1.2.3 From e14038a7ead09faa180eb072adc4a2157a0b475f Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Thu, 26 Nov 2020 19:47:47 +0100 Subject: selftests: tc-testing: enable CONFIG_NET_SCH_RED as a module a proper kernel configuration for running kselftest can be obtained with: $ yes | make kselftest-merge enable compile support for the 'red' qdisc: otherwise, tdc kselftest fail when trying to run tdc test items contained in red.json. Signed-off-by: Davide Caratti Link: https://lore.kernel.org/r/cfa23f2d4f672401e6cebca3a321dd1901a9ff07.1606416464.git.dcaratti@redhat.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/tc-testing/config | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index c33a7aac27ff..b71828df5a6d 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -59,6 +59,7 @@ CONFIG_NET_IFE_SKBPRIO=m CONFIG_NET_IFE_SKBTCINDEX=m CONFIG_NET_SCH_FIFO=y CONFIG_NET_SCH_ETS=m +CONFIG_NET_SCH_RED=m # ## Network testing -- cgit v1.2.3 From 31d6b4036098f6b59bcfa20375626b500c7d7417 Mon Sep 17 00:00:00 2001 From: Dany Madden Date: Wed, 25 Nov 2020 18:04:24 -0600 Subject: ibmvnic: handle inconsistent login with reset Inconsistent login with the vnicserver is causing the device to be removed. This does not give the device a chance to recover from error state. This patch schedules a FATAL reset instead to bring the adapter up. Fixes: 032c5e82847a2 ("Driver for IBM System i/p VNIC protocol") Signed-off-by: Dany Madden Signed-off-by: Lijun Pan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 2491ebc97871..b28a979061dc 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -4414,7 +4414,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, adapter->req_rx_add_queues != be32_to_cpu(login_rsp->num_rxadd_subcrqs))) { dev_err(dev, "FATAL: Inconsistent login and login rsp\n"); - ibmvnic_remove(adapter->vdev); + ibmvnic_reset(adapter, VNIC_RESET_FATAL); return -EIO; } size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + -- cgit v1.2.3 From 18f141bf97d42f65abfdf17fd93fb3a0dac100e7 Mon Sep 17 00:00:00 2001 From: Dany Madden Date: Wed, 25 Nov 2020 18:04:25 -0600 Subject: ibmvnic: stop free_all_rwi on failed reset When ibmvnic fails to reset, it breaks out of the reset loop and frees all of the remaining resets from the workqueue. Doing so prevents the adapter from recovering if no reset is scheduled after that. Instead, have the driver continue to process resets on the workqueue. Remove the no longer need free_all_rwi(). Fixes: ed651a10875f1 ("ibmvnic: Updated reset handling") Signed-off-by: Dany Madden Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 22 +++------------------- 1 file changed, 3 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index b28a979061dc..e9243d8c5abc 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2173,17 +2173,6 @@ static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter) return rwi; } -static void free_all_rwi(struct ibmvnic_adapter *adapter) -{ - struct ibmvnic_rwi *rwi; - - rwi = get_next_rwi(adapter); - while (rwi) { - kfree(rwi); - rwi = get_next_rwi(adapter); - } -} - static void __ibmvnic_reset(struct work_struct *work) { struct ibmvnic_rwi *rwi; @@ -2252,9 +2241,9 @@ static void __ibmvnic_reset(struct work_struct *work) else adapter->state = reset_state; rc = 0; - } else if (rc && rc != IBMVNIC_INIT_FAILED && - !adapter->force_reset_recovery) - break; + } + if (rc) + netdev_dbg(adapter->netdev, "Reset failed, rc=%d\n", rc); rwi = get_next_rwi(adapter); @@ -2268,11 +2257,6 @@ static void __ibmvnic_reset(struct work_struct *work) complete(&adapter->reset_done); } - if (rc) { - netdev_dbg(adapter->netdev, "Reset failed\n"); - free_all_rwi(adapter); - } - clear_bit_unlock(0, &adapter->resetting); } -- cgit v1.2.3 From 9281cf2d584083a450fd65fd27cc5f0e692f6e30 Mon Sep 17 00:00:00 2001 From: Dany Madden Date: Wed, 25 Nov 2020 18:04:26 -0600 Subject: ibmvnic: avoid memset null scrq msgs scrq->msgs could be NULL during device reset, causing Linux to crash. So, check before memset scrq->msgs. Fixes: c8b2ad0a4a901 ("ibmvnic: Sanitize entire SCRQ buffer on reset") Signed-off-by: Dany Madden Signed-off-by: Lijun Pan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index e9243d8c5abc..939a276dae7d 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2844,15 +2844,26 @@ static int reset_one_sub_crq_queue(struct ibmvnic_adapter *adapter, { int rc; + if (!scrq) { + netdev_dbg(adapter->netdev, + "Invalid scrq reset. irq (%d) or msgs (%p).\n", + scrq->irq, scrq->msgs); + return -EINVAL; + } + if (scrq->irq) { free_irq(scrq->irq, scrq); irq_dispose_mapping(scrq->irq); scrq->irq = 0; } - - memset(scrq->msgs, 0, 4 * PAGE_SIZE); - atomic_set(&scrq->used, 0); - scrq->cur = 0; + if (scrq->msgs) { + memset(scrq->msgs, 0, 4 * PAGE_SIZE); + atomic_set(&scrq->used, 0); + scrq->cur = 0; + } else { + netdev_dbg(adapter->netdev, "Invalid scrq reset\n"); + return -EINVAL; + } rc = h_reg_sub_crq(adapter->vdev->unit_address, scrq->msg_token, 4 * PAGE_SIZE, &scrq->crq_num, &scrq->hw_irq); -- cgit v1.2.3 From 0cb4bc66ba5ea2d3b94ec2a00775888130db628a Mon Sep 17 00:00:00 2001 From: Dany Madden Date: Wed, 25 Nov 2020 18:04:27 -0600 Subject: ibmvnic: restore adapter state on failed reset In a failed reset, driver could end up in VNIC_PROBED or VNIC_CLOSED state and cannot recover in subsequent resets, leaving it offline. This patch restores the adapter state to reset_state, the original state when reset was called. Fixes: b27507bb59ed5 ("net/ibmvnic: unlock rtnl_lock in reset so linkwatch_event can run") Fixes: 2770a7984db58 ("ibmvnic: Introduce hard reset recovery") Signed-off-by: Dany Madden Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 67 ++++++++++++++++++++------------------ 1 file changed, 36 insertions(+), 31 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 939a276dae7d..5ce9f70984ee 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1857,7 +1857,7 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter, if (reset_state == VNIC_OPEN) { rc = __ibmvnic_close(netdev); if (rc) - return rc; + goto out; } release_resources(adapter); @@ -1875,24 +1875,25 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter, } rc = ibmvnic_reset_init(adapter, true); - if (rc) - return IBMVNIC_INIT_FAILED; + if (rc) { + rc = IBMVNIC_INIT_FAILED; + goto out; + } /* If the adapter was in PROBE state prior to the reset, * exit here. */ if (reset_state == VNIC_PROBED) - return 0; + goto out; rc = ibmvnic_login(netdev); if (rc) { - adapter->state = reset_state; - return rc; + goto out; } rc = init_resources(adapter); if (rc) - return rc; + goto out; ibmvnic_disable_irqs(adapter); @@ -1902,8 +1903,10 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter, return 0; rc = __ibmvnic_open(netdev); - if (rc) - return IBMVNIC_OPEN_FAILED; + if (rc) { + rc = IBMVNIC_OPEN_FAILED; + goto out; + } /* refresh device's multicast list */ ibmvnic_set_multi(netdev); @@ -1912,7 +1915,10 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter, for (i = 0; i < adapter->req_rx_queues; i++) napi_schedule(&adapter->napi[i]); - return 0; +out: + if (rc) + adapter->state = reset_state; + return rc; } /** @@ -2015,7 +2021,6 @@ static int do_reset(struct ibmvnic_adapter *adapter, rc = ibmvnic_login(netdev); if (rc) { - adapter->state = reset_state; goto out; } @@ -2083,6 +2088,9 @@ static int do_reset(struct ibmvnic_adapter *adapter, rc = 0; out: + /* restore the adapter state if reset failed */ + if (rc) + adapter->state = reset_state; rtnl_unlock(); return rc; @@ -2115,43 +2123,46 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter, if (rc) { netdev_err(adapter->netdev, "Couldn't initialize crq. rc=%d\n", rc); - return rc; + goto out; } rc = ibmvnic_reset_init(adapter, false); if (rc) - return rc; + goto out; /* If the adapter was in PROBE state prior to the reset, * exit here. */ if (reset_state == VNIC_PROBED) - return 0; + goto out; rc = ibmvnic_login(netdev); - if (rc) { - adapter->state = VNIC_PROBED; - return 0; - } + if (rc) + goto out; rc = init_resources(adapter); if (rc) - return rc; + goto out; ibmvnic_disable_irqs(adapter); adapter->state = VNIC_CLOSED; if (reset_state == VNIC_CLOSED) - return 0; + goto out; rc = __ibmvnic_open(netdev); - if (rc) - return IBMVNIC_OPEN_FAILED; + if (rc) { + rc = IBMVNIC_OPEN_FAILED; + goto out; + } call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev); call_netdevice_notifiers(NETDEV_RESEND_IGMP, netdev); - - return 0; +out: + /* restore adapter state if reset failed */ + if (rc) + adapter->state = reset_state; + return rc; } static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter) @@ -2235,13 +2246,7 @@ static void __ibmvnic_reset(struct work_struct *work) rc = do_reset(adapter, rwi, reset_state); } kfree(rwi); - if (rc == IBMVNIC_OPEN_FAILED) { - if (list_empty(&adapter->rwi_list)) - adapter->state = VNIC_CLOSED; - else - adapter->state = reset_state; - rc = 0; - } + if (rc) netdev_dbg(adapter->netdev, "Reset failed, rc=%d\n", rc); -- cgit v1.2.3 From f15fde9d47b887b406f5e76490d601cfc26643c9 Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Wed, 25 Nov 2020 18:04:28 -0600 Subject: ibmvnic: delay next reset if hard reset fails If auto-priority failover is enabled, the backing device needs time to settle if hard resetting fails for any reason. Add a delay of 60 seconds before retrying the hard-reset. Fixes: 2770a7984db5 ("ibmvnic: Introduce hard reset recovery") Signed-off-by: Sukadev Bhattiprolu Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5ce9f70984ee..d4d40b349788 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2241,6 +2241,14 @@ static void __ibmvnic_reset(struct work_struct *work) rc = do_hard_reset(adapter, rwi, reset_state); rtnl_unlock(); } + if (rc) { + /* give backing device time to settle down */ + netdev_dbg(adapter->netdev, + "[S:%d] Hard reset failed, waiting 60 secs\n", + adapter->state); + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(60 * HZ); + } } else if (!(rwi->reset_reason == VNIC_RESET_FATAL && adapter->from_passive_init)) { rc = do_reset(adapter, rwi, reset_state); -- cgit v1.2.3 From 76cdc5c5d99ce4856ad0ac38facc33b52fa64f77 Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Wed, 25 Nov 2020 18:04:29 -0600 Subject: ibmvnic: track pending login If after ibmvnic sends a LOGIN it gets a FAILOVER, it is possible that the worker thread will start reset process and free the login response buffer before it gets a (now stale) LOGIN_RSP. The ibmvnic tasklet will then try to access the login response buffer and crash. Have ibmvnic track pending logins and discard any stale login responses. Fixes: 032c5e82847a ("Driver for IBM System i/p VNIC protocol") Signed-off-by: Sukadev Bhattiprolu Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 17 +++++++++++++++++ drivers/net/ethernet/ibm/ibmvnic.h | 1 + 2 files changed, 18 insertions(+) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index d4d40b349788..13eae1666477 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3841,6 +3841,8 @@ static int send_login(struct ibmvnic_adapter *adapter) crq.login.cmd = LOGIN; crq.login.ioba = cpu_to_be32(buffer_token); crq.login.len = cpu_to_be32(buffer_size); + + adapter->login_pending = true; ibmvnic_send_crq(adapter, &crq); return 0; @@ -4393,6 +4395,15 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, u64 *size_array; int i; + /* CHECK: Test/set of login_pending does not need to be atomic + * because only ibmvnic_tasklet tests/clears this. + */ + if (!adapter->login_pending) { + netdev_warn(netdev, "Ignoring unexpected login response\n"); + return 0; + } + adapter->login_pending = false; + dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz, DMA_TO_DEVICE); dma_unmap_single(dev, adapter->login_rsp_buf_token, @@ -4764,6 +4775,11 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, case IBMVNIC_CRQ_INIT: dev_info(dev, "Partner initialized\n"); adapter->from_passive_init = true; + /* Discard any stale login responses from prev reset. + * CHECK: should we clear even on INIT_COMPLETE? + */ + adapter->login_pending = false; + if (!completion_done(&adapter->init_done)) { complete(&adapter->init_done); adapter->init_done_rc = -EIO; @@ -5196,6 +5212,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) dev_set_drvdata(&dev->dev, netdev); adapter->vdev = dev; adapter->netdev = netdev; + adapter->login_pending = false; ether_addr_copy(adapter->mac_addr, mac_addr_p); ether_addr_copy(netdev->dev_addr, adapter->mac_addr); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 47a3fd71c96f..bffa7f939ee1 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -1086,6 +1086,7 @@ struct ibmvnic_adapter { struct delayed_work ibmvnic_delayed_reset; unsigned long resetting; bool napi_enabled, from_passive_init; + bool login_pending; bool failover_pending; bool force_reset_recovery; -- cgit v1.2.3 From c98d9cc4170da7e16a1012563d0f9fbe1c7cfe27 Mon Sep 17 00:00:00 2001 From: Dany Madden Date: Wed, 25 Nov 2020 18:04:30 -0600 Subject: ibmvnic: send_login should check for crq errors send_login() does not check for the result of ibmvnic_send_crq() of the login request. This results in the driver needlessly retrying the login 10 times even when CRQ is no longer active. Check the return code and give up in case of errors in sending the CRQ. The only time we want to retry is if we get a PARITALSUCCESS response from the partner. Fixes: 032c5e82847a2 ("Driver for IBM System i/p VNIC protocol") Signed-off-by: Dany Madden Signed-off-by: Sukadev Bhattiprolu Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 13eae1666477..5154e0421175 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -850,10 +850,8 @@ static int ibmvnic_login(struct net_device *netdev) adapter->init_done_rc = 0; reinit_completion(&adapter->init_done); rc = send_login(adapter); - if (rc) { - netdev_warn(netdev, "Unable to login\n"); + if (rc) return rc; - } if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { @@ -3729,15 +3727,16 @@ static int send_login(struct ibmvnic_adapter *adapter) struct ibmvnic_login_rsp_buffer *login_rsp_buffer; struct ibmvnic_login_buffer *login_buffer; struct device *dev = &adapter->vdev->dev; + struct vnic_login_client_data *vlcd; dma_addr_t rsp_buffer_token; dma_addr_t buffer_token; size_t rsp_buffer_size; union ibmvnic_crq crq; + int client_data_len; size_t buffer_size; __be64 *tx_list_p; __be64 *rx_list_p; - int client_data_len; - struct vnic_login_client_data *vlcd; + int rc; int i; if (!adapter->tx_scrq || !adapter->rx_scrq) { @@ -3843,16 +3842,23 @@ static int send_login(struct ibmvnic_adapter *adapter) crq.login.len = cpu_to_be32(buffer_size); adapter->login_pending = true; - ibmvnic_send_crq(adapter, &crq); + rc = ibmvnic_send_crq(adapter, &crq); + if (rc) { + adapter->login_pending = false; + netdev_err(adapter->netdev, "Failed to send login, rc=%d\n", rc); + goto buf_rsp_map_failed; + } return 0; buf_rsp_map_failed: kfree(login_rsp_buffer); + adapter->login_rsp_buf = NULL; buf_rsp_alloc_failed: dma_unmap_single(dev, buffer_token, buffer_size, DMA_TO_DEVICE); buf_map_failed: kfree(login_buffer); + adapter->login_buf = NULL; buf_alloc_failed: return -1; } -- cgit v1.2.3 From a86d5c682b798b2dadaa4171c1d124cf3c45a17c Mon Sep 17 00:00:00 2001 From: Dany Madden Date: Wed, 25 Nov 2020 18:04:31 -0600 Subject: ibmvnic: no reset timeout for 5 seconds after reset Reset timeout is going off right after adapter reset. This patch ensures that timeout is scheduled if it has been 5 seconds since the last reset. 5 seconds is the default watchdog timeout. Fixes: ed651a10875f1 ("ibmvnic: Updated reset handling") Signed-off-by: Dany Madden Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 11 +++++++++-- drivers/net/ethernet/ibm/ibmvnic.h | 2 ++ 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5154e0421175..d48a694b92c9 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2252,6 +2252,7 @@ static void __ibmvnic_reset(struct work_struct *work) rc = do_reset(adapter, rwi, reset_state); } kfree(rwi); + adapter->last_reset_time = jiffies; if (rc) netdev_dbg(adapter->netdev, "Reset failed, rc=%d\n", rc); @@ -2355,7 +2356,13 @@ static void ibmvnic_tx_timeout(struct net_device *dev, unsigned int txqueue) "Adapter is resetting, skip timeout reset\n"); return; } - + /* No queuing up reset until at least 5 seconds (default watchdog val) + * after last reset + */ + if (time_before(jiffies, (adapter->last_reset_time + dev->watchdog_timeo))) { + netdev_dbg(dev, "Not yet time to tx timeout.\n"); + return; + } ibmvnic_reset(adapter, VNIC_RESET_TIMEOUT); } @@ -5282,7 +5289,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) adapter->state = VNIC_PROBED; adapter->wait_for_reset = false; - + adapter->last_reset_time = jiffies; return 0; ibmvnic_register_fail: diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index bffa7f939ee1..21e7ea858cda 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -1087,6 +1087,8 @@ struct ibmvnic_adapter { unsigned long resetting; bool napi_enabled, from_passive_init; bool login_pending; + /* last device reset time */ + unsigned long last_reset_time; bool failover_pending; bool force_reset_recovery; -- cgit v1.2.3 From 98c41f04a67abf5e7f7191d55d286e905d1430ef Mon Sep 17 00:00:00 2001 From: Dany Madden Date: Wed, 25 Nov 2020 18:04:32 -0600 Subject: ibmvnic: reduce wait for completion time Reduce the wait time for Command Response Queue response from 30 seconds to 20 seconds, as recommended by VIOS and Power Hypervisor teams. Fixes: bd0b672313941 ("ibmvnic: Move login and queue negotiation into ibmvnic_open") Fixes: 53da09e92910f ("ibmvnic: Add set_link_state routine for setting adapter link state") Signed-off-by: Dany Madden Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index d48a694b92c9..bca1becd33f0 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -834,7 +834,7 @@ static void release_napi(struct ibmvnic_adapter *adapter) static int ibmvnic_login(struct net_device *netdev) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - unsigned long timeout = msecs_to_jiffies(30000); + unsigned long timeout = msecs_to_jiffies(20000); int retry_count = 0; int retries = 10; bool retry; @@ -938,7 +938,7 @@ static void release_resources(struct ibmvnic_adapter *adapter) static int set_link_state(struct ibmvnic_adapter *adapter, u8 link_state) { struct net_device *netdev = adapter->netdev; - unsigned long timeout = msecs_to_jiffies(30000); + unsigned long timeout = msecs_to_jiffies(20000); union ibmvnic_crq crq; bool resend; int rc; @@ -5130,7 +5130,7 @@ map_failed: static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset) { struct device *dev = &adapter->vdev->dev; - unsigned long timeout = msecs_to_jiffies(30000); + unsigned long timeout = msecs_to_jiffies(20000); u64 old_num_rx_queues, old_num_tx_queues; int rc; -- cgit v1.2.3 From 4d521943f76bd0d1e68ea5e02df7aadd30b2838a Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 26 Oct 2020 16:36:20 +0100 Subject: dt-bindings: net: correct interrupt flags in examples GPIO_ACTIVE_x flags are not correct in the context of interrupt flags. These are simple defines so they could be used in DTS but they will not have the same meaning: 1. GPIO_ACTIVE_HIGH = 0 = IRQ_TYPE_NONE 2. GPIO_ACTIVE_LOW = 1 = IRQ_TYPE_EDGE_RISING Correct the interrupt flags, assuming the author of the code wanted same logical behavior behind the name "ACTIVE_xxx", this is: ACTIVE_LOW => IRQ_TYPE_LEVEL_LOW ACTIVE_HIGH => IRQ_TYPE_LEVEL_HIGH Fixes: a1a8b4594f8d ("NFC: pn544: i2c: Add DTS Documentation") Fixes: 6be88670fc59 ("NFC: nxp-nci_i2c: Add I2C support to NXP NCI driver") Fixes: e3b329221567 ("dt-bindings: can: tcan4x5x: Update binding to use interrupt property") Signed-off-by: Krzysztof Kozlowski Acked-by: Rob Herring Acked-by: Marc Kleine-Budde # for tcan4x5x.txt Link: https://lore.kernel.org/r/20201026153620.89268-1-krzk@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/devicetree/bindings/net/can/tcan4x5x.txt | 2 +- Documentation/devicetree/bindings/net/nfc/nxp-nci.txt | 2 +- Documentation/devicetree/bindings/net/nfc/pn544.txt | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt index 3613c2c8f75d..0968b40aef1e 100644 --- a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt +++ b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt @@ -33,7 +33,7 @@ tcan4x5x: tcan4x5x@0 { spi-max-frequency = <10000000>; bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>; interrupt-parent = <&gpio1>; - interrupts = <14 GPIO_ACTIVE_LOW>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>; device-state-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; device-wake-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; reset-gpios = <&gpio1 27 GPIO_ACTIVE_HIGH>; diff --git a/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt b/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt index cfaf88998918..9e4dc510a40a 100644 --- a/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt +++ b/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt @@ -25,7 +25,7 @@ Example (for ARM-based BeagleBone with NPC100 NFC controller on I2C2): clock-frequency = <100000>; interrupt-parent = <&gpio1>; - interrupts = <29 GPIO_ACTIVE_HIGH>; + interrupts = <29 IRQ_TYPE_LEVEL_HIGH>; enable-gpios = <&gpio0 30 GPIO_ACTIVE_HIGH>; firmware-gpios = <&gpio0 31 GPIO_ACTIVE_HIGH>; diff --git a/Documentation/devicetree/bindings/net/nfc/pn544.txt b/Documentation/devicetree/bindings/net/nfc/pn544.txt index 92f399ec22b8..2bd82562ce8e 100644 --- a/Documentation/devicetree/bindings/net/nfc/pn544.txt +++ b/Documentation/devicetree/bindings/net/nfc/pn544.txt @@ -25,7 +25,7 @@ Example (for ARM-based BeagleBone with PN544 on I2C2): clock-frequency = <400000>; interrupt-parent = <&gpio1>; - interrupts = <17 GPIO_ACTIVE_HIGH>; + interrupts = <17 IRQ_TYPE_LEVEL_HIGH>; enable-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; firmware-gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>; -- cgit v1.2.3 From aec9fe892812ed10d0bffcf309d2a8fc380d8ce6 Mon Sep 17 00:00:00 2001 From: Paul Kocialkowski Date: Tue, 10 Nov 2020 21:04:30 +0100 Subject: drm/rockchip: Avoid uninitialized use of endpoint id in LVDS In the Rockchip DRM LVDS component driver, the endpoint id provided to drm_of_find_panel_or_bridge is grabbed from the endpoint's reg property. However, the property may be missing in the case of a single endpoint. Initialize the endpoint_id variable to 0 to avoid using an uninitialized variable in that case. Fixes: 34cc0aa25456 ("drm/rockchip: Add support for Rockchip Soc LVDS") Signed-off-by: Paul Kocialkowski Signed-off-by: Heiko Stuebner Link: https://patchwork.freedesktop.org/patch/msgid/20201110200430.1713467-1-paul.kocialkowski@bootlin.com --- drivers/gpu/drm/rockchip/rockchip_lvds.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c index f292c6a6e20f..41edd0a421b2 100644 --- a/drivers/gpu/drm/rockchip/rockchip_lvds.c +++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c @@ -544,7 +544,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, struct device_node *port, *endpoint; int ret = 0, child_count = 0; const char *name; - u32 endpoint_id; + u32 endpoint_id = 0; lvds->drm_dev = drm_dev; port = of_graph_get_port_by_id(dev->of_node, 1); -- cgit v1.2.3 From 7c4bada12d320d8648ba3ede6f9b6f9e10f1126a Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 27 Nov 2020 21:04:29 +0100 Subject: drm/panel: sony-acx565akm: Fix race condition in probe The probe routine acquires the reset GPIO using GPIOD_OUT_LOW. Directly afterwards it calls acx565akm_detect(), which sets the GPIO value to HIGH. If the bootloader initialized the GPIO to HIGH before the probe routine was called, there is only a very short time period of a few instructions where the reset signal is LOW. Exact time depends on compiler optimizations, kernel configuration and alignment of the stars, but I expect it to be always way less than 10us. There are no public datasheets for the panel, but acx565akm_power_on() has a comment with timings and reset period should be at least 10us. So this potentially brings the panel into a half-reset state. The result is, that panel may not work after boot and can get into a working state by re-enabling it (e.g. by blanking + unblanking), since that does a clean reset cycle. This bug has recently been hit by Ivaylo Dimitrov, but there are some older reports which are probably the same bug. At least Tony Lindgren, Peter Ujfalusi and Jarkko Nikula have experienced it in 2017 describing the blank/unblank procedure as possible workaround. Note, that the bug really goes back in time. It has originally been introduced in the predecessor of the omapfb driver in commit 3c45d05be382 ("OMAPDSS: acx565akm panel: handle gpios in panel driver") in 2012. That driver eventually got replaced by a newer one, which had the bug from the beginning in commit 84192742d9c2 ("OMAPDSS: Add Sony ACX565AKM panel driver") and still exists in fbdev world. That driver has later been copied to omapdrm and then was used as a basis for this driver. Last but not least the omapdrm specific driver has been removed in commit 45f16c82db7e ("drm/omap: displays: Remove unused panel drivers"). Reported-by: Jarkko Nikula Reported-by: Peter Ujfalusi Reported-by: Tony Lindgren Reported-by: Aaro Koskinen Reported-by: Ivaylo Dimitrov Cc: Merlijn Wajer Cc: Laurent Pinchart Cc: Tomi Valkeinen Fixes: 1c8fc3f0c5d2 ("drm/panel: Add driver for the Sony ACX565AKM panel") Signed-off-by: Sebastian Reichel Tested-by: Ivaylo Dimitrov Tested-by: Aaro Koskinen Tested-by: Jarkko Nikula Signed-off-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20201127200429.129868-1-sebastian.reichel@collabora.com --- drivers/gpu/drm/panel/panel-sony-acx565akm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/panel/panel-sony-acx565akm.c b/drivers/gpu/drm/panel/panel-sony-acx565akm.c index e95fdfb16b6c..ba0b3ead150f 100644 --- a/drivers/gpu/drm/panel/panel-sony-acx565akm.c +++ b/drivers/gpu/drm/panel/panel-sony-acx565akm.c @@ -629,7 +629,7 @@ static int acx565akm_probe(struct spi_device *spi) lcd->spi = spi; mutex_init(&lcd->mutex); - lcd->reset_gpio = devm_gpiod_get(&spi->dev, "reset", GPIOD_OUT_LOW); + lcd->reset_gpio = devm_gpiod_get(&spi->dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(lcd->reset_gpio)) { dev_err(&spi->dev, "failed to get reset GPIO\n"); return PTR_ERR(lcd->reset_gpio); -- cgit v1.2.3 From b65054597872ce3aefbc6a666385eabdf9e288da Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 29 Nov 2020 15:50:50 -0800 Subject: Linux 5.10-rc6 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 56c0782bde56..43ecedeb3f02 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Kleptomaniac Octopus # *DOCUMENTATION* -- cgit v1.2.3 From 6703052fe30fa0d85f1fbbf50171486cb0148d2d Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Wed, 25 Nov 2020 14:49:36 +0200 Subject: usb: cdns3: Fix hardware based role switch Hardware based role switch is broken as the driver always skips it. Fix this by registering for SW role switch only if 'usb-role-switch' property is present in the device tree. Fixes: 50642709f659 ("usb: cdns3: core: quit if it uses role switch class") Signed-off-by: Roger Quadros Signed-off-by: Peter Chen --- drivers/usb/cdns3/core.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c index a0f73d4711ae..170deb3eacf0 100644 --- a/drivers/usb/cdns3/core.c +++ b/drivers/usb/cdns3/core.c @@ -427,7 +427,6 @@ static irqreturn_t cdns3_wakeup_irq(int irq, void *data) */ static int cdns3_probe(struct platform_device *pdev) { - struct usb_role_switch_desc sw_desc = { }; struct device *dev = &pdev->dev; struct resource *res; struct cdns3 *cdns; @@ -529,18 +528,21 @@ static int cdns3_probe(struct platform_device *pdev) if (ret) goto err2; - sw_desc.set = cdns3_role_set; - sw_desc.get = cdns3_role_get; - sw_desc.allow_userspace_control = true; - sw_desc.driver_data = cdns; - if (device_property_read_bool(dev, "usb-role-switch")) + if (device_property_read_bool(dev, "usb-role-switch")) { + struct usb_role_switch_desc sw_desc = { }; + + sw_desc.set = cdns3_role_set; + sw_desc.get = cdns3_role_get; + sw_desc.allow_userspace_control = true; + sw_desc.driver_data = cdns; sw_desc.fwnode = dev->fwnode; - cdns->role_sw = usb_role_switch_register(dev, &sw_desc); - if (IS_ERR(cdns->role_sw)) { - ret = PTR_ERR(cdns->role_sw); - dev_warn(dev, "Unable to register Role Switch\n"); - goto err3; + cdns->role_sw = usb_role_switch_register(dev, &sw_desc); + if (IS_ERR(cdns->role_sw)) { + ret = PTR_ERR(cdns->role_sw); + dev_warn(dev, "Unable to register Role Switch\n"); + goto err3; + } } if (cdns->wakeup_irq) { @@ -582,7 +584,8 @@ static int cdns3_probe(struct platform_device *pdev) return 0; err4: cdns3_drd_exit(cdns); - usb_role_switch_unregister(cdns->role_sw); + if (cdns->role_sw) + usb_role_switch_unregister(cdns->role_sw); err3: set_phy_power_off(cdns); err2: -- cgit v1.2.3 From 24fdaeeb294c14ea743ec99ada92380c060a428a Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Wed, 25 Nov 2020 20:35:23 +0800 Subject: usb: cdns3: gadget: clear trb->length as zero after preparing every trb It clears trb->length as zero before preparing td, but if scatter buffer is used for td, there are several trbs within td, it needs to clear every trb->length as zero, otherwise, the default value for trb->length may not be zero after it begins to use the second round of trb rings. Fixes: abc6b579048e ("usb: cdns3: gadget: using correct sg operations") Signed-off-by: Peter Chen --- drivers/usb/cdns3/gadget.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c index 365f30fb1159..0aa85cc07ff1 100644 --- a/drivers/usb/cdns3/gadget.c +++ b/drivers/usb/cdns3/gadget.c @@ -1260,6 +1260,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, priv_req->end_trb = priv_ep->enqueue; cdns3_ep_inc_enq(priv_ep); trb = priv_ep->trb_pool + priv_ep->enqueue; + trb->length = 0; } while (sg_iter < num_trb); trb = priv_req->trb; -- cgit v1.2.3 From 6b8137517e70f6e96d0251a98930b1f29d0be161 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Thu, 26 Nov 2020 14:02:38 +0800 Subject: usb: cdns3: core: fix goto label for error path The usb_role_switch_register has been already called, so if the devm_request_irq has failed, it needs to call usb_role_switch_unregister. Fixes: b1234e3b3b26 ("usb: cdns3: add runtime PM support") Signed-off-by: Peter Chen --- drivers/usb/cdns3/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c index 170deb3eacf0..039ab5d2435e 100644 --- a/drivers/usb/cdns3/core.c +++ b/drivers/usb/cdns3/core.c @@ -553,7 +553,7 @@ static int cdns3_probe(struct platform_device *pdev) if (ret) { dev_err(cdns->dev, "couldn't register wakeup irq handler\n"); - goto err3; + goto err4; } } -- cgit v1.2.3 From f0992098cadb4c9c6a00703b66cafe604e178fea Mon Sep 17 00:00:00 2001 From: Samuel Thibault Date: Sun, 29 Nov 2020 20:35:23 +0100 Subject: speakup: Reject setting the speakup line discipline outside of speakup Speakup exposing a line discipline allows userland to try to use it, while it is deemed to be useless, and thus uselessly exposes potential bugs. One of them is simply that in such a case if the line sends data, spk_ttyio_receive_buf2 is called and crashes since spk_ttyio_synth is NULL. This change restricts the use of the speakup line discipline to speakup drivers, thus avoiding such kind of issues altogether. Cc: stable@vger.kernel.org Reported-by: Shisong Qin Signed-off-by: Samuel Thibault Tested-by: Shisong Qin Link: https://lore.kernel.org/r/20201129193523.hm3f6n5xrn6fiyyc@function Signed-off-by: Greg Kroah-Hartman --- drivers/accessibility/speakup/spk_ttyio.c | 37 +++++++++++++++++++------------ 1 file changed, 23 insertions(+), 14 deletions(-) diff --git a/drivers/accessibility/speakup/spk_ttyio.c b/drivers/accessibility/speakup/spk_ttyio.c index 669392f31d4e..6284aff434a1 100644 --- a/drivers/accessibility/speakup/spk_ttyio.c +++ b/drivers/accessibility/speakup/spk_ttyio.c @@ -47,27 +47,20 @@ static int spk_ttyio_ldisc_open(struct tty_struct *tty) { struct spk_ldisc_data *ldisc_data; + if (tty != speakup_tty) + /* Somebody tried to use this line discipline outside speakup */ + return -ENODEV; + if (!tty->ops->write) return -EOPNOTSUPP; - mutex_lock(&speakup_tty_mutex); - if (speakup_tty) { - mutex_unlock(&speakup_tty_mutex); - return -EBUSY; - } - speakup_tty = tty; - ldisc_data = kmalloc(sizeof(*ldisc_data), GFP_KERNEL); - if (!ldisc_data) { - speakup_tty = NULL; - mutex_unlock(&speakup_tty_mutex); + if (!ldisc_data) return -ENOMEM; - } init_completion(&ldisc_data->completion); ldisc_data->buf_free = true; - speakup_tty->disc_data = ldisc_data; - mutex_unlock(&speakup_tty_mutex); + tty->disc_data = ldisc_data; return 0; } @@ -191,9 +184,25 @@ static int spk_ttyio_initialise_ldisc(struct spk_synth *synth) tty_unlock(tty); + mutex_lock(&speakup_tty_mutex); + speakup_tty = tty; ret = tty_set_ldisc(tty, N_SPEAKUP); if (ret) - pr_err("speakup: Failed to set N_SPEAKUP on tty\n"); + speakup_tty = NULL; + mutex_unlock(&speakup_tty_mutex); + + if (!ret) + /* Success */ + return 0; + + pr_err("speakup: Failed to set N_SPEAKUP on tty\n"); + + tty_lock(tty); + if (tty->ops->close) + tty->ops->close(tty, NULL); + tty_unlock(tty); + + tty_kclose(tty); return ret; } -- cgit v1.2.3 From c8c39fbd01d42c30454e42c16bcd69c17260b90a Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Thu, 26 Nov 2020 13:01:11 +0200 Subject: habanalabs: free host huge va_range if not used If huge range is not valid, driver uses the host range also for huge page allocations, but driver never frees its allocation. This introduces a memory leak every time a user closes its context. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/memory.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c index 84227819e4d1..bfe223abf142 100644 --- a/drivers/misc/habanalabs/common/memory.c +++ b/drivers/misc/habanalabs/common/memory.c @@ -1626,6 +1626,7 @@ static int vm_ctx_init_with_ranges(struct hl_ctx *ctx, goto host_hpage_range_err; } } else { + kfree(ctx->host_huge_va_range); ctx->host_huge_va_range = ctx->host_va_range; } -- cgit v1.2.3 From 5555b7c56bdec7a29c789fec27f84d40f52fbdfa Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Sun, 29 Nov 2020 09:34:12 +0200 Subject: habanalabs: put devices before driver removal Driver never puts its device and control_device objects, hence a memory leak is introduced every driver removal. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/device.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index 20572224099a..783bbdcb1e61 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -231,16 +231,16 @@ delete_cdev_device: static void device_cdev_sysfs_del(struct hl_device *hdev) { - /* device_release() won't be called so must free devices explicitly */ - if (!hdev->cdev_sysfs_created) { - kfree(hdev->dev_ctrl); - kfree(hdev->dev); - return; - } + if (!hdev->cdev_sysfs_created) + goto put_devices; hl_sysfs_fini(hdev); cdev_device_del(&hdev->cdev_ctrl, hdev->dev_ctrl); cdev_device_del(&hdev->cdev, hdev->dev); + +put_devices: + put_device(hdev->dev); + put_device(hdev->dev_ctrl); } /* @@ -1371,9 +1371,9 @@ sw_fini: early_fini: device_early_fini(hdev); free_dev_ctrl: - kfree(hdev->dev_ctrl); + put_device(hdev->dev_ctrl); free_dev: - kfree(hdev->dev); + put_device(hdev->dev); out_disabled: hdev->disabled = true; if (add_cdev_sysfs_on_err) -- cgit v1.2.3 From 509920aee72ae23235615a009c5148cdb38794c3 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 28 Nov 2020 10:37:07 +0000 Subject: MAINTAINERS: Move Jason Cooper to CREDITS Jason's email address has now been bouncing for weeks, and no reply was received when trying to reach out on other addresses. We really hope he is OK. But until we hear of his whereabouts, let's move him to the CREDITS file so that people stop Cc-ing him. Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Acked-by: Gregory CLEMENT Acked-by: Andrew Lunn Link: https://lore.kernel.org/r/20201128103707.332874-1-maz@kernel.org --- CREDITS | 5 +++++ MAINTAINERS | 4 ---- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/CREDITS b/CREDITS index 748301954ab7..e88d1a783a80 100644 --- a/CREDITS +++ b/CREDITS @@ -740,6 +740,11 @@ S: (ask for current address) S: Portland, Oregon S: USA +N: Jason Cooper +D: ARM/Marvell SOC co-maintainer +D: irqchip co-maintainer +D: MVEBU PCI DRIVER co-maintainer + N: Robin Cornelius E: robincornelius@users.sourceforge.net D: Ralink rt2x00 WLAN driver diff --git a/MAINTAINERS b/MAINTAINERS index 2daa6ee673f7..4f27f43b2e0c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2014,7 +2014,6 @@ M: Philipp Zabel S: Maintained ARM/Marvell Dove/MV78xx0/Orion SOC support -M: Jason Cooper M: Andrew Lunn M: Sebastian Hesselbarth M: Gregory Clement @@ -2031,7 +2030,6 @@ F: arch/arm/plat-orion/ F: drivers/soc/dove/ ARM/Marvell Kirkwood and Armada 370, 375, 38x, 39x, XP, 3700, 7K/8K, CN9130 SOC support -M: Jason Cooper M: Andrew Lunn M: Gregory Clement M: Sebastian Hesselbarth @@ -9248,7 +9246,6 @@ F: kernel/irq/ IRQCHIP DRIVERS M: Thomas Gleixner -M: Jason Cooper M: Marc Zyngier L: linux-kernel@vger.kernel.org S: Maintained @@ -13394,7 +13391,6 @@ F: drivers/pci/controller/mobiveil/pcie-mobiveil* PCI DRIVER FOR MVEBU (Marvell Armada 370 and Armada XP SOC support) M: Thomas Petazzoni -M: Jason Cooper L: linux-pci@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -- cgit v1.2.3 From fd4e788e971ce763e50762d7b1a0048992949dd0 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Fri, 27 Nov 2020 10:52:41 +0200 Subject: drm/omap: sdi: fix bridge enable/disable When the SDI output was converted to DRM bridge, the atomic versions of enable and disable funcs were used. This was not intended, as that would require implementing other atomic funcs too. This leads to: WARNING: CPU: 0 PID: 18 at drivers/gpu/drm/drm_bridge.c:708 drm_atomic_helper_commit_modeset_enables+0x134/0x268 and display not working. Fix this by using the legacy enable/disable funcs. Fixes: 8bef8a6d5da81b909a190822b96805a47348146f ("drm/omap: sdi: Register a drm_bridge") Reported-by: Aaro Koskinen Signed-off-by: Tomi Valkeinen Tested-by: Ivaylo Dimitrov Tested-by: Aaro Koskinen Reviewed-by: Laurent Pinchart Cc: stable@vger.kernel.org # v5.7+ Link: https://patchwork.freedesktop.org/patch/msgid/20201127085241.848461-1-tomi.valkeinen@ti.com --- drivers/gpu/drm/omapdrm/dss/sdi.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/omapdrm/dss/sdi.c b/drivers/gpu/drm/omapdrm/dss/sdi.c index 033fd30074b0..282e4c837cd9 100644 --- a/drivers/gpu/drm/omapdrm/dss/sdi.c +++ b/drivers/gpu/drm/omapdrm/dss/sdi.c @@ -195,8 +195,7 @@ static void sdi_bridge_mode_set(struct drm_bridge *bridge, sdi->pixelclock = adjusted_mode->clock * 1000; } -static void sdi_bridge_enable(struct drm_bridge *bridge, - struct drm_bridge_state *bridge_state) +static void sdi_bridge_enable(struct drm_bridge *bridge) { struct sdi_device *sdi = drm_bridge_to_sdi(bridge); struct dispc_clock_info dispc_cinfo; @@ -259,8 +258,7 @@ err_get_dispc: regulator_disable(sdi->vdds_sdi_reg); } -static void sdi_bridge_disable(struct drm_bridge *bridge, - struct drm_bridge_state *bridge_state) +static void sdi_bridge_disable(struct drm_bridge *bridge) { struct sdi_device *sdi = drm_bridge_to_sdi(bridge); @@ -278,8 +276,8 @@ static const struct drm_bridge_funcs sdi_bridge_funcs = { .mode_valid = sdi_bridge_mode_valid, .mode_fixup = sdi_bridge_mode_fixup, .mode_set = sdi_bridge_mode_set, - .atomic_enable = sdi_bridge_enable, - .atomic_disable = sdi_bridge_disable, + .enable = sdi_bridge_enable, + .disable = sdi_bridge_disable, }; static void sdi_bridge_init(struct sdi_device *sdi) -- cgit v1.2.3 From bb4c6910c8b41623104c2e64a30615682689a54d Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Thu, 26 Nov 2020 09:28:51 +0100 Subject: genirq/irqdomain: Add an irq_create_mapping_affinity() function There is currently no way to convey the affinity of an interrupt via irq_create_mapping(), which creates issues for devices that expect that affinity to be managed by the kernel. In order to sort this out, rename irq_create_mapping() to irq_create_mapping_affinity() with an additional affinity parameter that can be passed down to irq_domain_alloc_descs(). irq_create_mapping() is re-implemented as a wrapper around irq_create_mapping_affinity(). No functional change. Fixes: e75eafb9b039 ("genirq/msi: Switch to new irq spreading infrastructure") Signed-off-by: Laurent Vivier Signed-off-by: Thomas Gleixner Reviewed-by: Greg Kurz Cc: Michael Ellerman Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20201126082852.1178497-2-lvivier@redhat.com --- include/linux/irqdomain.h | 12 ++++++++++-- kernel/irq/irqdomain.c | 13 ++++++++----- 2 files changed, 18 insertions(+), 7 deletions(-) diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 71535e87109f..ea5a337e0f8b 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -384,11 +384,19 @@ extern void irq_domain_associate_many(struct irq_domain *domain, extern void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq); -extern unsigned int irq_create_mapping(struct irq_domain *host, - irq_hw_number_t hwirq); +extern unsigned int irq_create_mapping_affinity(struct irq_domain *host, + irq_hw_number_t hwirq, + const struct irq_affinity_desc *affinity); extern unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec); extern void irq_dispose_mapping(unsigned int virq); +static inline unsigned int irq_create_mapping(struct irq_domain *host, + irq_hw_number_t hwirq) +{ + return irq_create_mapping_affinity(host, hwirq, NULL); +} + + /** * irq_linear_revmap() - Find a linux irq from a hw irq number. * @domain: domain owning this hardware interrupt diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index cf8b374b892d..e4ca69608f3b 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -624,17 +624,19 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain) EXPORT_SYMBOL_GPL(irq_create_direct_mapping); /** - * irq_create_mapping() - Map a hardware interrupt into linux irq space + * irq_create_mapping_affinity() - Map a hardware interrupt into linux irq space * @domain: domain owning this hardware interrupt or NULL for default domain * @hwirq: hardware irq number in that domain space + * @affinity: irq affinity * * Only one mapping per hardware interrupt is permitted. Returns a linux * irq number. * If the sense/trigger is to be specified, set_irq_type() should be called * on the number returned from that call. */ -unsigned int irq_create_mapping(struct irq_domain *domain, - irq_hw_number_t hwirq) +unsigned int irq_create_mapping_affinity(struct irq_domain *domain, + irq_hw_number_t hwirq, + const struct irq_affinity_desc *affinity) { struct device_node *of_node; int virq; @@ -660,7 +662,8 @@ unsigned int irq_create_mapping(struct irq_domain *domain, } /* Allocate a virtual interrupt number */ - virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), NULL); + virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), + affinity); if (virq <= 0) { pr_debug("-> virq allocation failed\n"); return 0; @@ -676,7 +679,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain, return virq; } -EXPORT_SYMBOL_GPL(irq_create_mapping); +EXPORT_SYMBOL_GPL(irq_create_mapping_affinity); /** * irq_create_strict_mappings() - Map a range of hw irqs to fixed linux irqs -- cgit v1.2.3 From 9ea69a55b3b9a71cded9726af591949c1138f235 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Thu, 26 Nov 2020 09:28:52 +0100 Subject: powerpc/pseries: Pass MSI affinity to irq_create_mapping() With virtio multiqueue, normally each queue IRQ is mapped to a CPU. Commit 0d9f0a52c8b9f ("virtio_scsi: use virtio IRQ affinity") exposed an existing shortcoming of the arch code by moving virtio_scsi to the automatic IRQ affinity assignment. The affinity is correctly computed in msi_desc but this is not applied to the system IRQs. It appears the affinity is correctly passed to rtas_setup_msi_irqs() but lost at this point and never passed to irq_domain_alloc_descs() (see commit 06ee6d571f0e ("genirq: Add affinity hint to irq allocation")) because irq_create_mapping() doesn't take an affinity parameter. Use the new irq_create_mapping_affinity() function, which allows to forward the affinity setting from rtas_setup_msi_irqs() to irq_domain_alloc_descs(). With this change, the virtqueues are correctly dispatched between the CPUs on pseries. Fixes: e75eafb9b039 ("genirq/msi: Switch to new irq spreading infrastructure") Signed-off-by: Laurent Vivier Signed-off-by: Thomas Gleixner Reviewed-by: Greg Kurz Acked-by: Michael Ellerman Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20201126082852.1178497-3-lvivier@redhat.com --- arch/powerpc/platforms/pseries/msi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 133f6adcb39c..b3ac2455faad 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -458,7 +458,8 @@ again: return hwirq; } - virq = irq_create_mapping(NULL, hwirq); + virq = irq_create_mapping_affinity(NULL, hwirq, + entry->affinity); if (!virq) { pr_debug("rtas_msi: Failed mapping hwirq %d\n", hwirq); -- cgit v1.2.3 From ad1f5e826d91d6c27ecd36a607ad7c7f4d0b0733 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Fri, 27 Nov 2020 16:17:11 +0100 Subject: can: m_can: tcan4x5x_can_probe(): fix error path: remove erroneous clk_disable_unprepare() The clocks mcan_class->cclk and mcan_class->hclk are not prepared by any call during tcan4x5x_can_probe(), so remove erroneous clk_disable_unprepare() on them. Fixes: 5443c226ba91 ("can: tcan4x5x: Add tcan4x5x driver to the kernel") Link: http://lore.kernel.org/r/20201130114252.215334-1-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/tcan4x5x.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c index e5d7d85e0b6d..7347ab39c5b6 100644 --- a/drivers/net/can/m_can/tcan4x5x.c +++ b/drivers/net/can/m_can/tcan4x5x.c @@ -489,18 +489,18 @@ static int tcan4x5x_can_probe(struct spi_device *spi) spi->bits_per_word = 32; ret = spi_setup(spi); if (ret) - goto out_clk; + goto out_m_can_class_free_dev; priv->regmap = devm_regmap_init(&spi->dev, &tcan4x5x_bus, &spi->dev, &tcan4x5x_regmap); if (IS_ERR(priv->regmap)) { ret = PTR_ERR(priv->regmap); - goto out_clk; + goto out_m_can_class_free_dev; } ret = tcan4x5x_power_enable(priv->power, 1); if (ret) - goto out_clk; + goto out_m_can_class_free_dev; ret = tcan4x5x_parse_config(mcan_class); if (ret) @@ -519,11 +519,6 @@ static int tcan4x5x_can_probe(struct spi_device *spi) out_power: tcan4x5x_power_enable(priv->power, 0); -out_clk: - if (!IS_ERR(mcan_class->cclk)) { - clk_disable_unprepare(mcan_class->cclk); - clk_disable_unprepare(mcan_class->hclk); - } out_m_can_class_free_dev: m_can_class_free_dev(mcan_class->net); dev_err(&spi->dev, "Probe failed, err=%d\n", ret); -- cgit v1.2.3 From bd0ccb92efb09c7da5b55162b283b42a93539ed7 Mon Sep 17 00:00:00 2001 From: Jeroen Hofstee Date: Fri, 27 Nov 2020 10:59:38 +0100 Subject: can: sja1000: sja1000_err(): don't count arbitration lose as an error Losing arbitration is normal in a CAN-bus network, it means that a higher priority frame is being send and the pending message will be retried later. Hence most driver only increment arbitration_lost, but the sja1000 driver also incremeants tx_error, causing errors to be reported on a normal functioning CAN-bus. So stop counting them as errors. Fixes: 8935f57e68c4 ("can: sja1000: fix network statistics update") Signed-off-by: Jeroen Hofstee Link: https://lore.kernel.org/r/20201127095941.21609-1-jhofstee@victronenergy.com [mkl: split into two seperate patches] Signed-off-by: Marc Kleine-Budde --- drivers/net/can/sja1000/sja1000.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c index 9f107798f904..25a4d7d0b349 100644 --- a/drivers/net/can/sja1000/sja1000.c +++ b/drivers/net/can/sja1000/sja1000.c @@ -474,7 +474,6 @@ static int sja1000_err(struct net_device *dev, uint8_t isrc, uint8_t status) netdev_dbg(dev, "arbitration lost interrupt\n"); alc = priv->read_reg(priv, SJA1000_ALC); priv->can.can_stats.arbitration_lost++; - stats->tx_errors++; cf->can_id |= CAN_ERR_LOSTARB; cf->data[0] = alc & 0x1f; } -- cgit v1.2.3 From c2d095eff797813461a426b97242e3ffc50e4134 Mon Sep 17 00:00:00 2001 From: Jeroen Hofstee Date: Fri, 27 Nov 2020 10:59:38 +0100 Subject: can: sun4i_can: sun4i_can_err(): don't count arbitration lose as an error Losing arbitration is normal in a CAN-bus network, it means that a higher priority frame is being send and the pending message will be retried later. Hence most driver only increment arbitration_lost, but the sun4i driver also incremeants tx_error, causing errors to be reported on a normal functioning CAN-bus. So stop counting them as errors. Fixes: 0738eff14d81 ("can: Allwinner A10/A20 CAN Controller support - Kernel module") Signed-off-by: Jeroen Hofstee Link: https://lore.kernel.org/r/20201127095941.21609-1-jhofstee@victronenergy.com [mkl: split into two seperate patches] Signed-off-by: Marc Kleine-Budde --- drivers/net/can/sun4i_can.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index e2c6cf4b2228..b3f2f4fe5ee0 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -604,7 +604,6 @@ static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status) netdev_dbg(dev, "arbitration lost interrupt\n"); alc = readl(priv->base + SUN4I_REG_STA_ADDR); priv->can.can_stats.arbitration_lost++; - stats->tx_errors++; if (likely(skb)) { cf->can_id |= CAN_ERR_LOSTARB; cf->data[0] = (alc >> 8) & 0x1f; -- cgit v1.2.3 From 44cef0c0ffbd8d61143712ce874be68a273b7884 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Sat, 28 Nov 2020 21:39:21 +0800 Subject: can: c_can: c_can_power_up(): fix error handling In the error handling in c_can_power_up(), there are two bugs: 1) c_can_pm_runtime_get_sync() will increase usage counter if device is not empty. Forgetting to call c_can_pm_runtime_put_sync() will result in a reference leak here. 2) c_can_reset_ram() operation will set start bit when enable is true. We should clear it in the error handling. We fix it by adding c_can_pm_runtime_put_sync() for 1), and c_can_reset_ram(enable is false) for 2) in the error handling. Fixes: 8212003260c60 ("can: c_can: Add d_can suspend resume support") Fixes: 52cde85acc23f ("can: c_can: Add d_can raminit support") Signed-off-by: Zhang Qilong Link: https://lore.kernel.org/r/20201128133922.3276973-2-zhangqilong3@huawei.com [mkl: return "0" instead of "ret"] Signed-off-by: Marc Kleine-Budde --- drivers/net/can/c_can/c_can.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index 1ccdbe89585b..1a9e9b9a4bf6 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -1295,12 +1295,22 @@ int c_can_power_up(struct net_device *dev) time_after(time_out, jiffies)) cpu_relax(); - if (time_after(jiffies, time_out)) - return -ETIMEDOUT; + if (time_after(jiffies, time_out)) { + ret = -ETIMEDOUT; + goto err_out; + } ret = c_can_start(dev); - if (!ret) - c_can_irq_control(priv, true); + if (ret) + goto err_out; + + c_can_irq_control(priv, true); + + return 0; + +err_out: + c_can_reset_ram(priv, false); + c_can_pm_runtime_put_sync(priv); return ret; } -- cgit v1.2.3 From 13a84cf37a4cf1155a41684236c2314eb40cd65c Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Sat, 28 Nov 2020 21:39:22 +0800 Subject: can: kvaser_pciefd: kvaser_pciefd_open(): fix error handling If kvaser_pciefd_bus_on() failed, we should call close_candev() to avoid reference leak. Fixes: 26ad340e582d3 ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Signed-off-by: Zhang Qilong Link: https://lore.kernel.org/r/20201128133922.3276973-3-zhangqilong3@huawei.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 72acd1ba162d..43151dd6cb1c 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -692,8 +692,10 @@ static int kvaser_pciefd_open(struct net_device *netdev) return err; err = kvaser_pciefd_bus_on(can); - if (err) + if (err) { + close_candev(netdev); return err; + } return 0; } -- cgit v1.2.3 From ca1314d73eed493c49bb1932c60a8605530db2e4 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 30 Nov 2020 11:59:40 +0000 Subject: arm64: syscall: exit userspace before unmasking exceptions In el0_svc_common() we unmask exceptions before we call user_exit(), and so there's a window where an IRQ or debug exception can be taken while RCU is not watching. In do_debug_exception() we account for this in via debug_exception_{enter,exit}(), but in the el1_irq asm we do not and we call trace functions which rely on RCU before we have a guarantee that RCU is watching. Let's avoid this by having el0_svc_common() exit userspace before unmasking exceptions, matching what we do for all other EL0 entry paths. We can use user_exit_irqoff() to avoid the pointless save/restore of IRQ flags while we're sure exceptions are masked in DAIF. The workaround for Cortex-A76 erratum 1463225 may trigger a debug exception before this point, but the debug code invoked in this case is safe even when RCU is not watching. Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20201130115950.22492-2-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/syscall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index e4c0dadf0d92..13fe79f8e2db 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -120,8 +120,8 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, */ cortex_a76_erratum_1463225_svc_handler(); + user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); - user_exit(); if (system_supports_mte() && (flags & _TIF_MTE_ASYNC_FAULT)) { /* -- cgit v1.2.3 From 114e0a684753516ef4b71ccb55a8ebcfa8735edb Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 30 Nov 2020 11:59:41 +0000 Subject: arm64: mark idle code as noinstr Core code disables RCU when calling arch_cpu_idle(), so it's not safe for arch_cpu_idle() or its calees to be instrumented, as the instrumentation callbacks may attempt to use RCU or other features which are unsafe to use in this context. Mark them noinstr to prevent issues. The use of local_irq_enable() in arch_cpu_idle() is similarly problematic, and the "sched/idle: Fix arch_cpu_idle() vs tracing" patch queued in the tip tree addresses that case. Reported-by: Marco Elver Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20201130115950.22492-3-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/process.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index a47a40ec6ad9..0c65a91f8f53 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -72,13 +72,13 @@ EXPORT_SYMBOL_GPL(pm_power_off); void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd); -static void __cpu_do_idle(void) +static void noinstr __cpu_do_idle(void) { dsb(sy); wfi(); } -static void __cpu_do_idle_irqprio(void) +static void noinstr __cpu_do_idle_irqprio(void) { unsigned long pmr; unsigned long daif_bits; @@ -108,7 +108,7 @@ static void __cpu_do_idle_irqprio(void) * ensure that interrupts are not masked at the PMR (because the core will * not wake up if we block the wake up signal in the interrupt controller). */ -void cpu_do_idle(void) +void noinstr cpu_do_idle(void) { if (system_uses_irq_prio_masking()) __cpu_do_idle_irqprio(); @@ -119,7 +119,7 @@ void cpu_do_idle(void) /* * This is our default idle handler. */ -void arch_cpu_idle(void) +void noinstr arch_cpu_idle(void) { /* * This should do all the clock switching and wait for interrupt -- cgit v1.2.3 From da192676483232a0a9478c89cdddd412e5167470 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 30 Nov 2020 11:59:42 +0000 Subject: arm64: entry: mark entry code as noinstr Functions in entry-common.c are marked as notrace and NOKPROBE_SYMBOL(), but they're still subject to other instrumentation which may rely on lockdep/rcu/context-tracking being up-to-date, and may cause nested exceptions (e.g. for WARN/BUG or KASAN's use of BRK) which will corrupt exceptions registers which have not yet been read. Prevent this by marking all functions in entry-common.c as noinstr to prevent compiler instrumentation. This also blacklists the functions for tracing and kprobes, so we don't need to handle that separately. Functions elsewhere will be dealt with in subsequent patches. Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20201130115950.22492-4-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/entry-common.c | 75 ++++++++++++++-------------------------- 1 file changed, 25 insertions(+), 50 deletions(-) diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 43d4c329775f..75e99161f79e 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -17,7 +17,7 @@ #include #include -static void notrace el1_abort(struct pt_regs *regs, unsigned long esr) +static void noinstr el1_abort(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); @@ -25,32 +25,28 @@ static void notrace el1_abort(struct pt_regs *regs, unsigned long esr) far = untagged_addr(far); do_mem_abort(far, esr, regs); } -NOKPROBE_SYMBOL(el1_abort); -static void notrace el1_pc(struct pt_regs *regs, unsigned long esr) +static void noinstr el1_pc(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); local_daif_inherit(regs); do_sp_pc_abort(far, esr, regs); } -NOKPROBE_SYMBOL(el1_pc); -static void notrace el1_undef(struct pt_regs *regs) +static void noinstr el1_undef(struct pt_regs *regs) { local_daif_inherit(regs); do_undefinstr(regs); } -NOKPROBE_SYMBOL(el1_undef); -static void notrace el1_inv(struct pt_regs *regs, unsigned long esr) +static void noinstr el1_inv(struct pt_regs *regs, unsigned long esr) { local_daif_inherit(regs); bad_mode(regs, 0, esr); } -NOKPROBE_SYMBOL(el1_inv); -static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr) +static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); @@ -64,16 +60,14 @@ static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr) do_debug_exception(far, esr, regs); } -NOKPROBE_SYMBOL(el1_dbg); -static void notrace el1_fpac(struct pt_regs *regs, unsigned long esr) +static void noinstr el1_fpac(struct pt_regs *regs, unsigned long esr) { local_daif_inherit(regs); do_ptrauth_fault(regs, esr); } -NOKPROBE_SYMBOL(el1_fpac); -asmlinkage void notrace el1_sync_handler(struct pt_regs *regs) +asmlinkage void noinstr el1_sync_handler(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); @@ -106,9 +100,8 @@ asmlinkage void notrace el1_sync_handler(struct pt_regs *regs) el1_inv(regs, esr); } } -NOKPROBE_SYMBOL(el1_sync_handler); -static void notrace el0_da(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_da(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); @@ -117,9 +110,8 @@ static void notrace el0_da(struct pt_regs *regs, unsigned long esr) far = untagged_addr(far); do_mem_abort(far, esr, regs); } -NOKPROBE_SYMBOL(el0_da); -static void notrace el0_ia(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_ia(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); @@ -135,41 +127,36 @@ static void notrace el0_ia(struct pt_regs *regs, unsigned long esr) local_daif_restore(DAIF_PROCCTX); do_mem_abort(far, esr, regs); } -NOKPROBE_SYMBOL(el0_ia); -static void notrace el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr) { user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); do_fpsimd_acc(esr, regs); } -NOKPROBE_SYMBOL(el0_fpsimd_acc); -static void notrace el0_sve_acc(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_sve_acc(struct pt_regs *regs, unsigned long esr) { user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); do_sve_acc(esr, regs); } -NOKPROBE_SYMBOL(el0_sve_acc); -static void notrace el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) { user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); do_fpsimd_exc(esr, regs); } -NOKPROBE_SYMBOL(el0_fpsimd_exc); -static void notrace el0_sys(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_sys(struct pt_regs *regs, unsigned long esr) { user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); do_sysinstr(esr, regs); } -NOKPROBE_SYMBOL(el0_sys); -static void notrace el0_pc(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_pc(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); @@ -180,41 +167,36 @@ static void notrace el0_pc(struct pt_regs *regs, unsigned long esr) local_daif_restore(DAIF_PROCCTX); do_sp_pc_abort(far, esr, regs); } -NOKPROBE_SYMBOL(el0_pc); -static void notrace el0_sp(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_sp(struct pt_regs *regs, unsigned long esr) { user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); do_sp_pc_abort(regs->sp, esr, regs); } -NOKPROBE_SYMBOL(el0_sp); -static void notrace el0_undef(struct pt_regs *regs) +static void noinstr el0_undef(struct pt_regs *regs) { user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); do_undefinstr(regs); } -NOKPROBE_SYMBOL(el0_undef); -static void notrace el0_bti(struct pt_regs *regs) +static void noinstr el0_bti(struct pt_regs *regs) { user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); do_bti(regs); } -NOKPROBE_SYMBOL(el0_bti); -static void notrace el0_inv(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_inv(struct pt_regs *regs, unsigned long esr) { user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); bad_el0_sync(regs, 0, esr); } -NOKPROBE_SYMBOL(el0_inv); -static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_dbg(struct pt_regs *regs, unsigned long esr) { /* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */ unsigned long far = read_sysreg(far_el1); @@ -226,26 +208,23 @@ static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr) do_debug_exception(far, esr, regs); local_daif_restore(DAIF_PROCCTX_NOIRQ); } -NOKPROBE_SYMBOL(el0_dbg); -static void notrace el0_svc(struct pt_regs *regs) +static void noinstr el0_svc(struct pt_regs *regs) { if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); do_el0_svc(regs); } -NOKPROBE_SYMBOL(el0_svc); -static void notrace el0_fpac(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_fpac(struct pt_regs *regs, unsigned long esr) { user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); do_ptrauth_fault(regs, esr); } -NOKPROBE_SYMBOL(el0_fpac); -asmlinkage void notrace el0_sync_handler(struct pt_regs *regs) +asmlinkage void noinstr el0_sync_handler(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); @@ -297,27 +276,24 @@ asmlinkage void notrace el0_sync_handler(struct pt_regs *regs) el0_inv(regs, esr); } } -NOKPROBE_SYMBOL(el0_sync_handler); #ifdef CONFIG_COMPAT -static void notrace el0_cp15(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr) { user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); do_cp15instr(esr, regs); } -NOKPROBE_SYMBOL(el0_cp15); -static void notrace el0_svc_compat(struct pt_regs *regs) +static void noinstr el0_svc_compat(struct pt_regs *regs) { if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); do_el0_svc_compat(regs); } -NOKPROBE_SYMBOL(el0_svc_compat); -asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs) +asmlinkage void noinstr el0_sync_compat_handler(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); @@ -360,5 +336,4 @@ asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs) el0_inv(regs, esr); } } -NOKPROBE_SYMBOL(el0_sync_compat_handler); #endif /* CONFIG_COMPAT */ -- cgit v1.2.3 From 2f911d494f3f028bbe6346e383a354225682cf1b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 30 Nov 2020 11:59:43 +0000 Subject: arm64: entry: move enter_from_user_mode to entry-common.c In later patches we'll want to extend enter_from_user_mode() and add a corresponding exit_to_user_mode(). As these will be common for all entries/exits from userspace, it'd be better for these to live in entry-common.c with the rest of the entry logic. This patch moves enter_from_user_mode() into entry-common.c. As with other functions in entry-common.c it is marked as noinstr (which prevents all instrumentation, tracing, and kprobes) but there are no other functional changes. Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20201130115950.22492-5-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/entry-common.c | 6 ++++++ arch/arm64/kernel/traps.c | 7 ------- 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 75e99161f79e..9a685e7686fe 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -101,6 +101,12 @@ asmlinkage void noinstr el1_sync_handler(struct pt_regs *regs) } } +asmlinkage void noinstr enter_from_user_mode(void) +{ + CT_WARN_ON(ct_state() != CONTEXT_USER); + user_exit_irqoff(); +} + static void noinstr el0_da(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 8af4e0e85736..580c60afc39a 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -876,13 +876,6 @@ asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr) nmi_exit(); } -asmlinkage void enter_from_user_mode(void) -{ - CT_WARN_ON(ct_state() != CONTEXT_USER); - user_exit_irqoff(); -} -NOKPROBE_SYMBOL(enter_from_user_mode); - /* GENERIC_BUG traps */ int is_valid_bugaddr(unsigned long addr) -- cgit v1.2.3 From 3cb5ed4d76c15fb97c10e5e9f5268d92c68222ca Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 30 Nov 2020 11:59:44 +0000 Subject: arm64: entry: prepare ret_to_user for function call In a subsequent patch ret_to_user will need to make a C function call (in some configurations) which may clobber x0-x18 at the start of the finish_ret_to_user block, before enable_step_tsk consumes the flags loaded into x1. In preparation for this, let's load the flags into x19, which is preserved across C function calls. This avoids a redundant reload of the flags and ensures we operate on a consistent shapshot regardless. There should be no functional change as a result of this patch. At this point of the entry/exit paths we only need to preserve x28 (tsk) and the sp, and x19 is free for this use. Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20201130115950.22492-6-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/entry.S | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index b295fb912b12..84aec600eeed 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -774,13 +774,13 @@ SYM_CODE_END(el0_error) SYM_CODE_START_LOCAL(ret_to_user) disable_daif gic_prio_kentry_setup tmp=x3 - ldr x1, [tsk, #TSK_TI_FLAGS] - and x2, x1, #_TIF_WORK_MASK + ldr x19, [tsk, #TSK_TI_FLAGS] + and x2, x19, #_TIF_WORK_MASK cbnz x2, work_pending finish_ret_to_user: /* Ignore asynchronous tag check faults in the uaccess routines */ clear_mte_async_tcf - enable_step_tsk x1, x2 + enable_step_tsk x19, x2 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK bl stackleak_erase #endif @@ -791,11 +791,12 @@ finish_ret_to_user: */ work_pending: mov x0, sp // 'regs' + mov x1, x19 bl do_notify_resume #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_on // enabled while in userspace #endif - ldr x1, [tsk, #TSK_TI_FLAGS] // re-check for single-step + ldr x19, [tsk, #TSK_TI_FLAGS] // re-check for single-step b finish_ret_to_user SYM_CODE_END(ret_to_user) -- cgit v1.2.3 From 105fc3352077bba5faaf12cf39f7e3aad26fb70b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 30 Nov 2020 11:59:45 +0000 Subject: arm64: entry: move el1 irq/nmi logic to C In preparation for reworking the EL1 irq/nmi entry code, move the existing logic to C. We no longer need the asm_nmi_enter() and asm_nmi_exit() wrappers, so these are removed. The new C functions are marked noinstr, which prevents compiler instrumentation and runtime probing. In subsequent patches we'll want the new C helpers to be called in all cases, so we don't bother wrapping the calls with ifdeferry. Even when the new C functions are stubs the trivial calls are unlikely to have a measurable impact on the IRQ or NMI paths anyway. Prototypes are added to as otherwise (in some configurations) GCC will complain about the lack of a forward declaration. We already do this for existing function, e.g. enter_from_user_mode(). The new helpers are marked as noinstr (which prevents all instrumentation, tracing, and kprobes). Otherwise, there should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20201130115950.22492-7-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/exception.h | 2 ++ arch/arm64/kernel/entry-common.c | 16 ++++++++++++++++ arch/arm64/kernel/entry.S | 34 ++++------------------------------ arch/arm64/kernel/irq.c | 15 --------------- 4 files changed, 22 insertions(+), 45 deletions(-) diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 99b9383cd036..d69d53dd7be7 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -31,6 +31,8 @@ static inline u32 disr_to_esr(u64 disr) return esr; } +asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs); +asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs); asmlinkage void enter_from_user_mode(void); void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); void do_undefinstr(struct pt_regs *regs); diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 9a685e7686fe..920da254be1d 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -17,6 +17,22 @@ #include #include +asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs)) + nmi_enter(); + + trace_hardirqs_off(); +} + +asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs)) + nmi_exit(); + else + trace_hardirqs_on(); +} + static void noinstr el1_abort(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 84aec600eeed..53e30750fc28 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -637,16 +637,8 @@ SYM_CODE_START_LOCAL_NOALIGN(el1_irq) gic_prio_irq_setup pmr=x20, tmp=x1 enable_da_f -#ifdef CONFIG_ARM64_PSEUDO_NMI - test_irqs_unmasked res=x0, pmr=x20 - cbz x0, 1f - bl asm_nmi_enter -1: -#endif - -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif + mov x0, sp + bl enter_el1_irq_or_nmi irq_handler @@ -665,26 +657,8 @@ alternative_else_nop_endif 1: #endif -#ifdef CONFIG_ARM64_PSEUDO_NMI - /* - * When using IRQ priority masking, we can get spurious interrupts while - * PMR is set to GIC_PRIO_IRQOFF. An NMI might also have occurred in a - * section with interrupts disabled. Skip tracing in those cases. - */ - test_irqs_unmasked res=x0, pmr=x20 - cbz x0, 1f - bl asm_nmi_exit -1: -#endif - -#ifdef CONFIG_TRACE_IRQFLAGS -#ifdef CONFIG_ARM64_PSEUDO_NMI - test_irqs_unmasked res=x0, pmr=x20 - cbnz x0, 1f -#endif - bl trace_hardirqs_on -1: -#endif + mov x0, sp + bl exit_el1_irq_or_nmi kernel_exit 1 SYM_CODE_END(el1_irq) diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 9cf2fb87584a..60456a62da11 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -67,18 +67,3 @@ void __init init_IRQ(void) local_daif_restore(DAIF_PROCCTX_NOIRQ); } } - -/* - * Stubs to make nmi_enter/exit() code callable from ASM - */ -asmlinkage void notrace asm_nmi_enter(void) -{ - nmi_enter(); -} -NOKPROBE_SYMBOL(asm_nmi_enter); - -asmlinkage void notrace asm_nmi_exit(void) -{ - nmi_exit(); -} -NOKPROBE_SYMBOL(asm_nmi_exit); -- cgit v1.2.3 From 23529049c68423820487304f244144e0d576e85a Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 30 Nov 2020 11:59:46 +0000 Subject: arm64: entry: fix non-NMI user<->kernel transitions When built with PROVE_LOCKING, NO_HZ_FULL, and CONTEXT_TRACKING_FORCE will WARN() at boot time that interrupts are enabled when we call context_tracking_user_enter(), despite the DAIF flags indicating that IRQs are masked. The problem is that we're not tracking IRQ flag changes accurately, and so lockdep believes interrupts are enabled when they are not (and vice-versa). We can shuffle things so to make this more accurate. For kernel->user transitions there are a number of constraints we need to consider: 1) When we call __context_tracking_user_enter() HW IRQs must be disabled and lockdep must be up-to-date with this. 2) Userspace should be treated as having IRQs enabled from the PoV of both lockdep and tracing. 3) As context_tracking_user_enter() stops RCU from watching, we cannot use RCU after calling it. 4) IRQ flag tracing and lockdep have state that must be manipulated before RCU is disabled. ... with similar constraints applying for user->kernel transitions, with the ordering reversed. The generic entry code has enter_from_user_mode() and exit_to_user_mode() helpers to handle this. We can't use those directly, so we add arm64 copies for now (without the instrumentation markers which aren't used on arm64). These replace the existing user_exit() and user_exit_irqoff() calls spread throughout handlers, and the exception unmasking is left as-is. Note that: * The accounting for debug exceptions from userspace now happens in el0_dbg() and ret_to_user(), so this is removed from debug_exception_enter() and debug_exception_exit(). As user_exit_irqoff() wakes RCU, the userspace-specific check is removed. * The accounting for syscalls now happens in el0_svc(), el0_svc_compat(), and ret_to_user(), so this is removed from el0_svc_common(). This does not adversely affect the workaround for erratum 1463225, as this does not depend on any of the state tracking. * In ret_to_user() we mask interrupts with local_daif_mask(), and so we need to inform lockdep and tracing. Here a trace_hardirqs_off() is sufficient and safe as we have not yet exited kernel context and RCU is usable. * As PROVE_LOCKING selects TRACE_IRQFLAGS, the ifdeferry in entry.S only needs to check for the latter. * EL0 SError handling will be dealt with in a subsequent patch, as this needs to be treated as an NMI. Prior to this patch, booting an appropriately-configured kernel would result in spats as below: | DEBUG_LOCKS_WARN_ON(lockdep_hardirqs_enabled()) | WARNING: CPU: 2 PID: 1 at kernel/locking/lockdep.c:5280 check_flags.part.54+0x1dc/0x1f0 | Modules linked in: | CPU: 2 PID: 1 Comm: init Not tainted 5.10.0-rc3 #3 | Hardware name: linux,dummy-virt (DT) | pstate: 804003c5 (Nzcv DAIF +PAN -UAO -TCO BTYPE=--) | pc : check_flags.part.54+0x1dc/0x1f0 | lr : check_flags.part.54+0x1dc/0x1f0 | sp : ffff80001003bd80 | x29: ffff80001003bd80 x28: ffff66ce801e0000 | x27: 00000000ffffffff x26: 00000000000003c0 | x25: 0000000000000000 x24: ffffc31842527258 | x23: ffffc31842491368 x22: ffffc3184282d000 | x21: 0000000000000000 x20: 0000000000000001 | x19: ffffc318432ce000 x18: 0080000000000000 | x17: 0000000000000000 x16: ffffc31840f18a78 | x15: 0000000000000001 x14: ffffc3184285c810 | x13: 0000000000000001 x12: 0000000000000000 | x11: ffffc318415857a0 x10: ffffc318406614c0 | x9 : ffffc318415857a0 x8 : ffffc31841f1d000 | x7 : 647261685f706564 x6 : ffffc3183ff7c66c | x5 : ffff66ce801e0000 x4 : 0000000000000000 | x3 : ffffc3183fe00000 x2 : ffffc31841500000 | x1 : e956dc24146b3500 x0 : 0000000000000000 | Call trace: | check_flags.part.54+0x1dc/0x1f0 | lock_is_held_type+0x10c/0x188 | rcu_read_lock_sched_held+0x70/0x98 | __context_tracking_enter+0x310/0x350 | context_tracking_enter.part.3+0x5c/0xc8 | context_tracking_user_enter+0x6c/0x80 | finish_ret_to_user+0x2c/0x13cr Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20201130115950.22492-8-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/exception.h | 1 + arch/arm64/kernel/entry-common.c | 40 +++++++++++++++++++++++++------------- arch/arm64/kernel/entry.S | 35 +++++++++++++-------------------- arch/arm64/kernel/syscall.c | 1 - arch/arm64/mm/fault.c | 22 ++++++++++----------- 5 files changed, 51 insertions(+), 48 deletions(-) diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index d69d53dd7be7..d579b2e6db7a 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -34,6 +34,7 @@ static inline u32 disr_to_esr(u64 disr) asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs); asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs); asmlinkage void enter_from_user_mode(void); +asmlinkage void exit_to_user_mode(void); void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); void do_undefinstr(struct pt_regs *regs); void do_bti(struct pt_regs *regs); diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 920da254be1d..49d1c1dd9baf 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -119,15 +119,25 @@ asmlinkage void noinstr el1_sync_handler(struct pt_regs *regs) asmlinkage void noinstr enter_from_user_mode(void) { + lockdep_hardirqs_off(CALLER_ADDR0); CT_WARN_ON(ct_state() != CONTEXT_USER); user_exit_irqoff(); + trace_hardirqs_off_finish(); +} + +asmlinkage void noinstr exit_to_user_mode(void) +{ + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + user_enter_irqoff(); + lockdep_hardirqs_on(CALLER_ADDR0); } static void noinstr el0_da(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); far = untagged_addr(far); do_mem_abort(far, esr, regs); @@ -145,35 +155,35 @@ static void noinstr el0_ia(struct pt_regs *regs, unsigned long esr) if (!is_ttbr0_addr(far)) arm64_apply_bp_hardening(); - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_mem_abort(far, esr, regs); } static void noinstr el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_fpsimd_acc(esr, regs); } static void noinstr el0_sve_acc(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_sve_acc(esr, regs); } static void noinstr el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_fpsimd_exc(esr, regs); } static void noinstr el0_sys(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_sysinstr(esr, regs); } @@ -185,35 +195,35 @@ static void noinstr el0_pc(struct pt_regs *regs, unsigned long esr) if (!is_ttbr0_addr(instruction_pointer(regs))) arm64_apply_bp_hardening(); - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_sp_pc_abort(far, esr, regs); } static void noinstr el0_sp(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_sp_pc_abort(regs->sp, esr, regs); } static void noinstr el0_undef(struct pt_regs *regs) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_undefinstr(regs); } static void noinstr el0_bti(struct pt_regs *regs) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_bti(regs); } static void noinstr el0_inv(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); bad_el0_sync(regs, 0, esr); } @@ -226,7 +236,7 @@ static void noinstr el0_dbg(struct pt_regs *regs, unsigned long esr) if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - user_exit_irqoff(); + enter_from_user_mode(); do_debug_exception(far, esr, regs); local_daif_restore(DAIF_PROCCTX_NOIRQ); } @@ -236,12 +246,13 @@ static void noinstr el0_svc(struct pt_regs *regs) if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + enter_from_user_mode(); do_el0_svc(regs); } static void noinstr el0_fpac(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_ptrauth_fault(regs, esr); } @@ -302,7 +313,7 @@ asmlinkage void noinstr el0_sync_handler(struct pt_regs *regs) #ifdef CONFIG_COMPAT static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_cp15instr(esr, regs); } @@ -312,6 +323,7 @@ static void noinstr el0_svc_compat(struct pt_regs *regs) if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + enter_from_user_mode(); do_el0_svc_compat(regs); } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 53e30750fc28..d72c818b019c 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -30,18 +30,18 @@ #include /* - * Context tracking subsystem. Used to instrument transitions - * between user and kernel mode. + * Context tracking and irqflag tracing need to instrument transitions between + * user and kernel mode. */ - .macro ct_user_exit_irqoff -#ifdef CONFIG_CONTEXT_TRACKING + .macro user_exit_irqoff +#if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS) bl enter_from_user_mode #endif .endm - .macro ct_user_enter -#ifdef CONFIG_CONTEXT_TRACKING - bl context_tracking_user_enter + .macro user_enter_irqoff +#if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS) + bl exit_to_user_mode #endif .endm @@ -298,9 +298,6 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING alternative_else_nop_endif ldp x21, x22, [sp, #S_PC] // load ELR, SPSR - .if \el == 0 - ct_user_enter - .endif #ifdef CONFIG_ARM64_SW_TTBR0_PAN alternative_if_not ARM64_HAS_PAN @@ -700,21 +697,14 @@ SYM_CODE_START_LOCAL_NOALIGN(el0_irq) kernel_entry 0 el0_irq_naked: gic_prio_irq_setup pmr=x20, tmp=x0 - ct_user_exit_irqoff + user_exit_irqoff enable_da_f -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif - tbz x22, #55, 1f bl do_el0_irq_bp_hardening 1: irq_handler -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_on -#endif b ret_to_user SYM_CODE_END(el0_irq) @@ -733,7 +723,7 @@ SYM_CODE_START_LOCAL(el0_error) el0_error_naked: mrs x25, esr_el1 gic_prio_kentry_setup tmp=x2 - ct_user_exit_irqoff + user_exit_irqoff enable_dbg mov x0, sp mov x1, x25 @@ -748,10 +738,14 @@ SYM_CODE_END(el0_error) SYM_CODE_START_LOCAL(ret_to_user) disable_daif gic_prio_kentry_setup tmp=x3 +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off +#endif ldr x19, [tsk, #TSK_TI_FLAGS] and x2, x19, #_TIF_WORK_MASK cbnz x2, work_pending finish_ret_to_user: + user_enter_irqoff /* Ignore asynchronous tag check faults in the uaccess routines */ clear_mte_async_tcf enable_step_tsk x19, x2 @@ -767,9 +761,6 @@ work_pending: mov x0, sp // 'regs' mov x1, x19 bl do_notify_resume -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_on // enabled while in userspace -#endif ldr x19, [tsk, #TSK_TI_FLAGS] // re-check for single-step b finish_ret_to_user SYM_CODE_END(ret_to_user) diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 13fe79f8e2db..f8f758e4a306 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -120,7 +120,6 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, */ cortex_a76_erratum_1463225_svc_handler(); - user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); if (system_supports_mte() && (flags & _TIF_MTE_ASYNC_FAULT)) { diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 1ee94002801f..1f450b784d2c 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -789,16 +789,14 @@ void __init hook_debug_fault_code(int nr, */ static void debug_exception_enter(struct pt_regs *regs) { - /* - * Tell lockdep we disabled irqs in entry.S. Do nothing if they were - * already disabled to preserve the last enabled/disabled addresses. - */ - if (interrupts_enabled(regs)) - trace_hardirqs_off(); + if (!user_mode(regs)) { + /* + * Tell lockdep we disabled irqs in entry.S. Do nothing if they were + * already disabled to preserve the last enabled/disabled addresses. + */ + if (interrupts_enabled(regs)) + trace_hardirqs_off(); - if (user_mode(regs)) { - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - } else { /* * We might have interrupted pretty much anything. In * fact, if we're a debug exception, we can even interrupt @@ -819,8 +817,10 @@ static void debug_exception_exit(struct pt_regs *regs) { preempt_enable_no_resched(); - if (!user_mode(regs)) - rcu_nmi_exit(); + if (user_mode(regs)) + return; + + rcu_nmi_exit(); if (interrupts_enabled(regs)) trace_hardirqs_on(); -- cgit v1.2.3 From 1ec2f2c05b2ab845d068bff29bd32dbfc6a6ad4c Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 30 Nov 2020 11:59:47 +0000 Subject: arm64: ptrace: prepare for EL1 irq/rcu tracking Exceptions from EL1 may be taken when RCU isn't watching (e.g. in idle sequences), or when the lockdep hardirqs transiently out-of-sync with the hardware state (e.g. in the middle of local_irq_enable()). To correctly handle these cases, we'll need to save/restore this state across some exceptions taken from EL1. A series of subsequent patches will update EL1 exception handlers to handle this. In preparation for this, and to avoid dependencies between those patches, this patch adds two new fields to struct pt_regs so that exception handlers can track this state. Note that this is placed in pt_regs as some entry/exit sequences such as el1_irq are invoked from assembly, which makes it very difficult to add a separate structure as with the irqentry_state used by x86. We can separate this once more of the exception logic is moved to C. While the fields only need to be bool, they are both made u64 to keep pt_regs 16-byte aligned. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20201130115950.22492-9-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/ptrace.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 997cf8c8cd52..28c85b87b8cd 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -193,6 +193,10 @@ struct pt_regs { /* Only valid when ARM64_HAS_IRQ_PRIO_MASKING is enabled. */ u64 pmr_save; u64 stackframe[2]; + + /* Only valid for some EL1 exceptions. */ + u64 lockdep_hardirqs; + u64 exit_rcu; }; static inline bool in_syscall(struct pt_regs const *regs) -- cgit v1.2.3 From 7cd1ea1010acbede7eb87b6abb6198921fb36957 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 30 Nov 2020 11:59:48 +0000 Subject: arm64: entry: fix non-NMI kernel<->kernel transitions There are periods in kernel mode when RCU is not watching and/or the scheduler tick is disabled, but we can still take exceptions such as interrupts. The arm64 exception handlers do not account for this, and it's possible that RCU is not watching while an exception handler runs. The x86/generic entry code handles this by ensuring that all (non-NMI) kernel exception handlers call irqentry_enter() and irqentry_exit(), which handle RCU, lockdep, and IRQ flag tracing. We can't yet move to the generic entry code, and already hadnle the user<->kernel transitions elsewhere, so we add new kernel<->kernel transition helpers alog the lines of the generic entry code. Since we now track interrupts becoming masked when an exception is taken, local_daif_inherit() is modified to track interrupts becoming re-enabled when the original context is inherited. To balance the entry/exit paths, each handler masks all DAIF exceptions before exit_to_kernel_mode(). Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20201130115950.22492-10-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/daifflags.h | 3 ++ arch/arm64/kernel/entry-common.c | 67 ++++++++++++++++++++++++++++++++++++-- 2 files changed, 67 insertions(+), 3 deletions(-) diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index ec213b4a1650..1c26d7baa67f 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -128,6 +128,9 @@ static inline void local_daif_inherit(struct pt_regs *regs) { unsigned long flags = regs->pstate & DAIF_MASK; + if (interrupts_enabled(regs)) + trace_hardirqs_on(); + /* * We can't use local_daif_restore(regs->pstate) here as * system_has_prio_mask_debugging() won't restore the I bit if it can diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 49d1c1dd9baf..86622d8dd0d8 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -17,12 +17,58 @@ #include #include +/* + * This is intended to match the logic in irqentry_enter(), handling the kernel + * mode transitions only. + */ +static void noinstr enter_from_kernel_mode(struct pt_regs *regs) +{ + regs->exit_rcu = false; + + if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) { + lockdep_hardirqs_off(CALLER_ADDR0); + rcu_irq_enter(); + trace_hardirqs_off_finish(); + + regs->exit_rcu = true; + return; + } + + lockdep_hardirqs_off(CALLER_ADDR0); + rcu_irq_enter_check_tick(); + trace_hardirqs_off_finish(); +} + +/* + * This is intended to match the logic in irqentry_exit(), handling the kernel + * mode transitions only, and with preemption handled elsewhere. + */ +static void noinstr exit_to_kernel_mode(struct pt_regs *regs) +{ + lockdep_assert_irqs_disabled(); + + if (interrupts_enabled(regs)) { + if (regs->exit_rcu) { + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + rcu_irq_exit(); + lockdep_hardirqs_on(CALLER_ADDR0); + return; + } + + trace_hardirqs_on(); + } else { + if (regs->exit_rcu) + rcu_irq_exit(); + } +} + asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs) { if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs)) nmi_enter(); - - trace_hardirqs_off(); + else + enter_from_kernel_mode(regs); } asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs) @@ -30,36 +76,48 @@ asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs) if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs)) nmi_exit(); else - trace_hardirqs_on(); + exit_to_kernel_mode(regs); } static void noinstr el1_abort(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); + enter_from_kernel_mode(regs); local_daif_inherit(regs); far = untagged_addr(far); do_mem_abort(far, esr, regs); + local_daif_mask(); + exit_to_kernel_mode(regs); } static void noinstr el1_pc(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); + enter_from_kernel_mode(regs); local_daif_inherit(regs); do_sp_pc_abort(far, esr, regs); + local_daif_mask(); + exit_to_kernel_mode(regs); } static void noinstr el1_undef(struct pt_regs *regs) { + enter_from_kernel_mode(regs); local_daif_inherit(regs); do_undefinstr(regs); + local_daif_mask(); + exit_to_kernel_mode(regs); } static void noinstr el1_inv(struct pt_regs *regs, unsigned long esr) { + enter_from_kernel_mode(regs); local_daif_inherit(regs); bad_mode(regs, 0, esr); + local_daif_mask(); + exit_to_kernel_mode(regs); } static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr) @@ -79,8 +137,11 @@ static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr) static void noinstr el1_fpac(struct pt_regs *regs, unsigned long esr) { + enter_from_kernel_mode(regs); local_daif_inherit(regs); do_ptrauth_fault(regs, esr); + local_daif_mask(); + exit_to_kernel_mode(regs); } asmlinkage void noinstr el1_sync_handler(struct pt_regs *regs) -- cgit v1.2.3 From f0cd5ac1e4c53cb691b3ed3cda1031e1c42153e2 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 30 Nov 2020 11:59:49 +0000 Subject: arm64: entry: fix NMI {user, kernel}->kernel transitions Exceptions which can be taken at (almost) any time are consdiered to be NMIs. On arm64 that includes: * SDEI events * GICv3 Pseudo-NMIs * Kernel stack overflows * Unexpected/unhandled exceptions ... but currently debug exceptions (BRKs, breakpoints, watchpoints, single-step) are not considered NMIs. As these can be taken at any time, kernel features (lockdep, RCU, ftrace) may not be in a consistent kernel state. For example, we may take an NMI from the idle code or partway through an entry/exit path. While nmi_enter() and nmi_exit() handle most of this state, notably they don't save/restore the lockdep state across an NMI being taken and handled. When interrupts are enabled and an NMI is taken, lockdep may see interrupts become disabled within the NMI code, but not see interrupts become enabled when returning from the NMI, leaving lockdep believing interrupts are disabled when they are actually disabled. The x86 code handles this in idtentry_{enter,exit}_nmi(), which will shortly be moved to the generic entry code. As we can't use either yet, we copy the x86 approach in arm64-specific helpers. All the NMI entrypoints are marked as noinstr to prevent any instrumentation handling code being invoked before the state has been corrected. Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20201130115950.22492-11-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/exception.h | 2 ++ arch/arm64/kernel/entry-common.c | 34 ++++++++++++++++++++++++++++++++-- arch/arm64/kernel/sdei.c | 7 ++++--- arch/arm64/kernel/traps.c | 15 ++++++++++----- 4 files changed, 48 insertions(+), 10 deletions(-) diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index d579b2e6db7a..0756191f44f6 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -35,6 +35,8 @@ asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs); asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs); asmlinkage void enter_from_user_mode(void); asmlinkage void exit_to_user_mode(void); +void arm64_enter_nmi(struct pt_regs *regs); +void arm64_exit_nmi(struct pt_regs *regs); void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); void do_undefinstr(struct pt_regs *regs); void do_bti(struct pt_regs *regs); diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 86622d8dd0d8..6d70be0d3e8f 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -63,10 +63,40 @@ static void noinstr exit_to_kernel_mode(struct pt_regs *regs) } } +void noinstr arm64_enter_nmi(struct pt_regs *regs) +{ + regs->lockdep_hardirqs = lockdep_hardirqs_enabled(); + + __nmi_enter(); + lockdep_hardirqs_off(CALLER_ADDR0); + lockdep_hardirq_enter(); + rcu_nmi_enter(); + + trace_hardirqs_off_finish(); + ftrace_nmi_enter(); +} + +void noinstr arm64_exit_nmi(struct pt_regs *regs) +{ + bool restore = regs->lockdep_hardirqs; + + ftrace_nmi_exit(); + if (restore) { + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + } + + rcu_nmi_exit(); + lockdep_hardirq_exit(); + if (restore) + lockdep_hardirqs_on(CALLER_ADDR0); + __nmi_exit(); +} + asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs) { if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs)) - nmi_enter(); + arm64_enter_nmi(regs); else enter_from_kernel_mode(regs); } @@ -74,7 +104,7 @@ asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs) asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs) { if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs)) - nmi_exit(); + arm64_exit_nmi(regs); else exit_to_kernel_mode(regs); } diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index 7689f2031c0c..793c46d6a447 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -10,6 +10,7 @@ #include #include +#include #include #include #include @@ -223,16 +224,16 @@ static __kprobes unsigned long _sdei_handler(struct pt_regs *regs, } -asmlinkage __kprobes notrace unsigned long +asmlinkage noinstr unsigned long __sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg) { unsigned long ret; - nmi_enter(); + arm64_enter_nmi(regs); ret = _sdei_handler(regs, arg); - nmi_exit(); + arm64_exit_nmi(regs); return ret; } diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 580c60afc39a..2059d8f43f55 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -753,8 +754,10 @@ const char *esr_get_class_string(u32 esr) * bad_mode handles the impossible case in the exception vector. This is always * fatal. */ -asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) +asmlinkage void notrace bad_mode(struct pt_regs *regs, int reason, unsigned int esr) { + arm64_enter_nmi(regs); + console_verbose(); pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n", @@ -786,7 +789,7 @@ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack) __aligned(16); -asmlinkage void handle_bad_stack(struct pt_regs *regs) +asmlinkage void noinstr handle_bad_stack(struct pt_regs *regs) { unsigned long tsk_stk = (unsigned long)current->stack; unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr); @@ -794,6 +797,8 @@ asmlinkage void handle_bad_stack(struct pt_regs *regs) unsigned int esr = read_sysreg(esr_el1); unsigned long far = read_sysreg(far_el1); + arm64_enter_nmi(regs); + console_verbose(); pr_emerg("Insufficient stack space to handle exception!"); @@ -865,15 +870,15 @@ bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr) } } -asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr) +asmlinkage void noinstr do_serror(struct pt_regs *regs, unsigned int esr) { - nmi_enter(); + arm64_enter_nmi(regs); /* non-RAS errors are not containable */ if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr)) arm64_serror_panic(regs, esr); - nmi_exit(); + arm64_exit_nmi(regs); } /* GENERIC_BUG traps */ -- cgit v1.2.3 From 2a9b3e6ac69a8bf177d8496a11e749e2dc72fa22 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 30 Nov 2020 11:59:50 +0000 Subject: arm64: entry: fix EL1 debug transitions In debug_exception_enter() and debug_exception_exit() we trace hardirqs on/off while RCU isn't guaranteed to be watching, and we don't save and restore the hardirq state, and so may return with this having changed. Handle this appropriately with new entry/exit helpers which do the bare minimum to ensure this is appropriately maintained, without marking debug exceptions as NMIs. These are placed in entry-common.c with the other entry/exit helpers. In future we'll want to reconsider whether some debug exceptions should be NMIs, but this will require a significant refactoring, and for now this should prevent issues with lockdep and RCU. Signed-off-by: Mark Rutland Cc: Catalin Marins Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20201130115950.22492-12-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/entry-common.c | 26 ++++++++++++++++++++++++++ arch/arm64/mm/fault.c | 25 ------------------------- 2 files changed, 26 insertions(+), 25 deletions(-) diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 6d70be0d3e8f..70e0a7591245 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -150,6 +150,30 @@ static void noinstr el1_inv(struct pt_regs *regs, unsigned long esr) exit_to_kernel_mode(regs); } +static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs) +{ + regs->lockdep_hardirqs = lockdep_hardirqs_enabled(); + + lockdep_hardirqs_off(CALLER_ADDR0); + rcu_nmi_enter(); + + trace_hardirqs_off_finish(); +} + +static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs) +{ + bool restore = regs->lockdep_hardirqs; + + if (restore) { + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + } + + rcu_nmi_exit(); + if (restore) + lockdep_hardirqs_on(CALLER_ADDR0); +} + static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); @@ -162,7 +186,9 @@ static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr) if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + arm64_enter_el1_dbg(regs); do_debug_exception(far, esr, regs); + arm64_exit_el1_dbg(regs); } static void noinstr el1_fpac(struct pt_regs *regs, unsigned long esr) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 1f450b784d2c..795d224f184f 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -789,23 +789,6 @@ void __init hook_debug_fault_code(int nr, */ static void debug_exception_enter(struct pt_regs *regs) { - if (!user_mode(regs)) { - /* - * Tell lockdep we disabled irqs in entry.S. Do nothing if they were - * already disabled to preserve the last enabled/disabled addresses. - */ - if (interrupts_enabled(regs)) - trace_hardirqs_off(); - - /* - * We might have interrupted pretty much anything. In - * fact, if we're a debug exception, we can even interrupt - * NMI processing. We don't want this code makes in_nmi() - * to return true, but we need to notify RCU. - */ - rcu_nmi_enter(); - } - preempt_disable(); /* This code is a bit fragile. Test it. */ @@ -816,14 +799,6 @@ NOKPROBE_SYMBOL(debug_exception_enter); static void debug_exception_exit(struct pt_regs *regs) { preempt_enable_no_resched(); - - if (user_mode(regs)) - return; - - rcu_nmi_exit(); - - if (interrupts_enabled(regs)) - trace_hardirqs_on(); } NOKPROBE_SYMBOL(debug_exception_exit); -- cgit v1.2.3 From 63e2fffa59a9dd91e443b08832656399fd80b7f0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 15 Nov 2020 17:37:37 -0500 Subject: pNFS/flexfiles: Fix array overflow when flexfiles mirroring is enabled If the flexfiles mirroring is enabled, then the read code expects to be able to set pgio->pg_mirror_idx to point to the data server that is being used for this particular read. However it does not change the pg_mirror_count because we only need to send a single read. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/flexfilelayout/flexfilelayout.c | 27 +++++++++++++++++++------ fs/nfs/pagelist.c | 36 +++++++++++++++++++++++++--------- include/linux/nfs_page.h | 4 ++++ 3 files changed, 52 insertions(+), 15 deletions(-) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index a163533446fa..24bf5797f88a 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -838,7 +838,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_pgio_mirror *pgm; struct nfs4_ff_layout_mirror *mirror; struct nfs4_pnfs_ds *ds; - u32 ds_idx, i; + u32 ds_idx; retry: ff_layout_pg_check_layout(pgio, req); @@ -864,11 +864,9 @@ retry: goto retry; } - for (i = 0; i < pgio->pg_mirror_count; i++) { - mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); - pgm = &pgio->pg_mirrors[i]; - pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; - } + mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx); + pgm = &pgio->pg_mirrors[0]; + pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; pgio->pg_mirror_idx = ds_idx; @@ -985,6 +983,21 @@ out: return 1; } +static u32 +ff_layout_pg_set_mirror_write(struct nfs_pageio_descriptor *desc, u32 idx) +{ + u32 old = desc->pg_mirror_idx; + + desc->pg_mirror_idx = idx; + return old; +} + +static struct nfs_pgio_mirror * +ff_layout_pg_get_mirror_write(struct nfs_pageio_descriptor *desc, u32 idx) +{ + return &desc->pg_mirrors[idx]; +} + static const struct nfs_pageio_ops ff_layout_pg_read_ops = { .pg_init = ff_layout_pg_init_read, .pg_test = pnfs_generic_pg_test, @@ -998,6 +1011,8 @@ static const struct nfs_pageio_ops ff_layout_pg_write_ops = { .pg_doio = pnfs_generic_pg_writepages, .pg_get_mirror_count = ff_layout_pg_get_mirror_count_write, .pg_cleanup = pnfs_generic_pg_cleanup, + .pg_get_mirror = ff_layout_pg_get_mirror_write, + .pg_set_mirror = ff_layout_pg_set_mirror_write, }; static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 6985cacf4700..78c9c4bdef2b 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -31,13 +31,29 @@ static struct kmem_cache *nfs_page_cachep; static const struct rpc_call_ops nfs_pgio_common_ops; +static struct nfs_pgio_mirror * +nfs_pgio_get_mirror(struct nfs_pageio_descriptor *desc, u32 idx) +{ + if (desc->pg_ops->pg_get_mirror) + return desc->pg_ops->pg_get_mirror(desc, idx); + return &desc->pg_mirrors[0]; +} + struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc) { - return &desc->pg_mirrors[desc->pg_mirror_idx]; + return nfs_pgio_get_mirror(desc, desc->pg_mirror_idx); } EXPORT_SYMBOL_GPL(nfs_pgio_current_mirror); +static u32 +nfs_pgio_set_current_mirror(struct nfs_pageio_descriptor *desc, u32 idx) +{ + if (desc->pg_ops->pg_set_mirror) + return desc->pg_ops->pg_set_mirror(desc, idx); + return desc->pg_mirror_idx; +} + void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)) @@ -1259,7 +1275,7 @@ static void nfs_pageio_error_cleanup(struct nfs_pageio_descriptor *desc) return; for (midx = 0; midx < desc->pg_mirror_count; midx++) { - mirror = &desc->pg_mirrors[midx]; + mirror = nfs_pgio_get_mirror(desc, midx); desc->pg_completion_ops->error_cleanup(&mirror->pg_list, desc->pg_error); } @@ -1293,12 +1309,12 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, goto out_failed; } - desc->pg_mirror_idx = midx; + nfs_pgio_set_current_mirror(desc, midx); if (!nfs_pageio_add_request_mirror(desc, dupreq)) goto out_cleanup_subreq; } - desc->pg_mirror_idx = 0; + nfs_pgio_set_current_mirror(desc, 0); if (!nfs_pageio_add_request_mirror(desc, req)) goto out_failed; @@ -1320,10 +1336,12 @@ out_failed: static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, u32 mirror_idx) { - struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[mirror_idx]; - u32 restore_idx = desc->pg_mirror_idx; + struct nfs_pgio_mirror *mirror; + u32 restore_idx; + + restore_idx = nfs_pgio_set_current_mirror(desc, mirror_idx); + mirror = nfs_pgio_current_mirror(desc); - desc->pg_mirror_idx = mirror_idx; for (;;) { nfs_pageio_doio(desc); if (desc->pg_error < 0 || !mirror->pg_recoalesce) @@ -1331,7 +1349,7 @@ static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, if (!nfs_do_recoalesce(desc)) break; } - desc->pg_mirror_idx = restore_idx; + nfs_pgio_set_current_mirror(desc, restore_idx); } /* @@ -1405,7 +1423,7 @@ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index) u32 midx; for (midx = 0; midx < desc->pg_mirror_count; midx++) { - mirror = &desc->pg_mirrors[midx]; + mirror = nfs_pgio_get_mirror(desc, midx); if (!list_empty(&mirror->pg_list)) { prev = nfs_list_entry(mirror->pg_list.prev); if (index != prev->wb_index + 1) { diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index c32c15216da3..f0373a6cb5fb 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -55,6 +55,7 @@ struct nfs_page { unsigned short wb_nio; /* Number of I/O attempts */ }; +struct nfs_pgio_mirror; struct nfs_pageio_descriptor; struct nfs_pageio_ops { void (*pg_init)(struct nfs_pageio_descriptor *, struct nfs_page *); @@ -64,6 +65,9 @@ struct nfs_pageio_ops { unsigned int (*pg_get_mirror_count)(struct nfs_pageio_descriptor *, struct nfs_page *); void (*pg_cleanup)(struct nfs_pageio_descriptor *); + struct nfs_pgio_mirror * + (*pg_get_mirror)(struct nfs_pageio_descriptor *, u32); + u32 (*pg_set_mirror)(struct nfs_pageio_descriptor *, u32); }; struct nfs_rw_ops { -- cgit v1.2.3 From 9e5344e0ffc33f4fee899f98b6939a0682b1d9c3 Mon Sep 17 00:00:00 2001 From: Vincenzo Frascino Date: Mon, 30 Nov 2020 17:07:09 +0000 Subject: arm64: mte: Fix typo in macro definition UL in the definition of SYS_TFSR_EL1_TF1 was misspelled causing compilation issues when trying to implement in kernel MTE async mode. Fix the macro correcting the typo. Note: MTE async mode will be introduced with a future series. Fixes: c058b1c4a5ea ("arm64: mte: system register definitions") Cc: Catalin Marinas Cc: Will Deacon Signed-off-by: Vincenzo Frascino Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/20201130170709.22309-1-vincenzo.frascino@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/sysreg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 174817ba119c..c8ab9900293f 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -983,7 +983,7 @@ #define SYS_TFSR_EL1_TF0_SHIFT 0 #define SYS_TFSR_EL1_TF1_SHIFT 1 #define SYS_TFSR_EL1_TF0 (UL(1) << SYS_TFSR_EL1_TF0_SHIFT) -#define SYS_TFSR_EL1_TF1 (UK(2) << SYS_TFSR_EL1_TF1_SHIFT) +#define SYS_TFSR_EL1_TF1 (UL(1) << SYS_TFSR_EL1_TF1_SHIFT) /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */ #define SYS_MPIDR_SAFE_VAL (BIT(31)) -- cgit v1.2.3 From 2d280bc8930ba9ed1705cfd548c6c8924949eaf1 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sun, 29 Nov 2020 18:33:32 +0000 Subject: io_uring: fix recvmsg setup with compat buf-select __io_compat_recvmsg_copy_hdr() with REQ_F_BUFFER_SELECT reads out iov len but never assigns it to iov/fast_iov, leaving sr->len with garbage. Hopefully, following io_buffer_select() truncates it to the selected buffer size, but the value is still may be under what was specified. Cc: # 5.7 Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 1023f7b44cea..a2a7c65a77aa 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4499,7 +4499,8 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, return -EFAULT; if (clen < 0) return -EINVAL; - sr->len = iomsg->iov[0].iov_len; + sr->len = clen; + iomsg->iov[0].iov_len = clen; iomsg->iov = NULL; } else { ret = __import_iovec(READ, (struct iovec __user *)uiov, len, -- cgit v1.2.3 From 55ea4cf403800af2ce6b125bc3d853117e0c0456 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 27 Nov 2020 11:20:58 -0500 Subject: ring-buffer: Update write stamp with the correct ts The write stamp, used to calculate deltas between events, was updated with the stale "ts" value in the "info" structure, and not with the updated "ts" variable. This caused the deltas between events to be inaccurate, and when crossing into a new sub buffer, had time go backwards. Link: https://lkml.kernel.org/r/20201124223917.795844-1-elavila@google.com Cc: stable@vger.kernel.org Fixes: a389d86f7fd09 ("ring-buffer: Have nested events still record running time stamp") Reported-by: "J. Avila" Tested-by: Daniel Mentz Tested-by: Will McVicker Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index dc83b3fa9fe7..bccaf88d3706 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3291,7 +3291,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* Nothing came after this event between C and E */ info->delta = ts - info->after; (void)rb_time_cmpxchg(&cpu_buffer->write_stamp, - info->after, info->ts); + info->after, ts); info->ts = ts; } else { /* -- cgit v1.2.3 From 8785f51a17083eee7c37606079c6447afc6ba102 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Sat, 28 Nov 2020 10:15:17 +0100 Subject: ring-buffer: Set the right timestamp in the slow path of __rb_reserve_next() In the slow path of __rb_reserve_next() a nested event(s) can happen between evaluating the timestamp delta of the current event and updating write_stamp via local_cmpxchg(); in this case the delta is not valid anymore and it should be set to 0 (same timestamp as the interrupting event), since the event that we are currently processing is not the last event in the buffer. Link: https://lkml.kernel.org/r/X8IVJcp1gRE+FJCJ@xps-13-7390 Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: stable@vger.kernel.org Link: https://lwn.net/Articles/831207 Fixes: a389d86f7fd0 ("ring-buffer: Have nested events still record running time stamp") Signed-off-by: Andrea Righi Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index bccaf88d3706..35d91b20d47a 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3287,11 +3287,11 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, ts = rb_time_stamp(cpu_buffer->buffer); barrier(); /*E*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) && - info->after < ts) { + info->after < ts && + rb_time_cmpxchg(&cpu_buffer->write_stamp, + info->after, ts)) { /* Nothing came after this event between C and E */ info->delta = ts - info->after; - (void)rb_time_cmpxchg(&cpu_buffer->write_stamp, - info->after, ts); info->ts = ts; } else { /* -- cgit v1.2.3 From 6988a619f5b79e4efadea6e19dcfe75fbcd350b5 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Sat, 28 Nov 2020 15:57:06 -0300 Subject: cifs: allow syscalls to be restarted in __smb_send_rqst() A customer has reported that several files in their multi-threaded app were left with size of 0 because most of the read(2) calls returned -EINTR and they assumed no bytes were read. Obviously, they could have fixed it by simply retrying on -EINTR. We noticed that most of the -EINTR on read(2) were due to real-time signals sent by glibc to process wide credential changes (SIGRT_1), and its signal handler had been established with SA_RESTART, in which case those calls could have been automatically restarted by the kernel. Let the kernel decide to whether or not restart the syscalls when there is a signal pending in __smb_send_rqst() by returning -ERESTARTSYS. If it can't, it will return -EINTR anyway. Signed-off-by: Paulo Alcantara (SUSE) CC: Stable Reviewed-by: Ronnie Sahlberg Reviewed-by: Pavel Shilovsky Signed-off-by: Steve French --- fs/cifs/transport.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index e27e255d40dd..36b2ece43403 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -339,8 +339,8 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, return -EAGAIN; if (signal_pending(current)) { - cifs_dbg(FYI, "signal is pending before sending any data\n"); - return -EINTR; + cifs_dbg(FYI, "signal pending before send request\n"); + return -ERESTARTSYS; } /* cork the socket */ -- cgit v1.2.3 From 212253367dc7b49ed3fc194ce71b0992eacaecf2 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Sat, 28 Nov 2020 16:54:02 -0300 Subject: cifs: fix potential use-after-free in cifs_echo_request() This patch fixes a potential use-after-free bug in cifs_echo_request(). For instance, thread 1 -------- cifs_demultiplex_thread() clean_demultiplex_info() kfree(server) thread 2 (workqueue) -------- apic_timer_interrupt() smp_apic_timer_interrupt() irq_exit() __do_softirq() run_timer_softirq() call_timer_fn() cifs_echo_request() <- use-after-free in server ptr Signed-off-by: Paulo Alcantara (SUSE) CC: Stable Reviewed-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/connect.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index c38156f324dd..28c1459fb0fc 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -876,6 +876,8 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) list_del_init(&server->tcp_ses_list); spin_unlock(&cifs_tcp_ses_lock); + cancel_delayed_work_sync(&server->echo); + spin_lock(&GlobalMid_Lock); server->tcpStatus = CifsExiting; spin_unlock(&GlobalMid_Lock); -- cgit v1.2.3 From 271e0c9dce1b02a825b3cc1a7aa1fab7c381d44b Mon Sep 17 00:00:00 2001 From: Libo Chen Date: Fri, 20 Nov 2020 18:12:43 -0800 Subject: ktest.pl: Fix incorrect reboot for grub2bls This issue was first noticed when I was testing different kernels on Oracle Linux 8 which as Fedora 30+ adopts BLS as default. Even though a kernel entry was added successfully and the index of that kernel entry was retrieved correctly, ktest still wouldn't reboot the system into user-specified kernel. The bug was spotted in subroutine reboot_to where the if-statement never checks for REBOOT_TYPE "grub2bls", therefore the desired entry will not be set for the next boot. Add a check for "grub2bls" so that $grub_reboot $grub_number can be run before a reboot if REBOOT_TYPE is "grub2bls" then we can boot to the correct kernel. Link: https://lkml.kernel.org/r/20201121021243.1532477-1-libo.chen@oracle.com Cc: stable@vger.kernel.org Fixes: ac2466456eaa ("ktest: introduce grub2bls REBOOT_TYPE option") Signed-off-by: Libo Chen Signed-off-by: Steven Rostedt (VMware) --- tools/testing/ktest/ktest.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index cb16d2aac51c..54188ee16c48 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -2040,7 +2040,7 @@ sub reboot_to { if ($reboot_type eq "grub") { run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch)'"; - } elsif ($reboot_type eq "grub2") { + } elsif (($reboot_type eq "grub2") or ($reboot_type eq "grub2bls")) { run_ssh "$grub_reboot $grub_number"; } elsif ($reboot_type eq "syslinux") { run_ssh "$syslinux --once \\\"$syslinux_label\\\" $syslinux_path"; -- cgit v1.2.3 From ed1182dc004dbcc7cfe64fb0e8ac520b25431715 Mon Sep 17 00:00:00 2001 From: Björn Töpel Date: Fri, 27 Nov 2020 18:17:26 +0100 Subject: xdp: Handle MEM_TYPE_XSK_BUFF_POOL correctly in xdp_return_buff() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It turns out that it does exist a path where xdp_return_buff() is being passed an XDP buffer of type MEM_TYPE_XSK_BUFF_POOL. This path is when AF_XDP zero-copy mode is enabled, and a buffer is redirected to a DEVMAP with an attached XDP program that drops the buffer. This change simply puts the handling of MEM_TYPE_XSK_BUFF_POOL back into xdp_return_buff(). Fixes: 82c41671ca4f ("xdp: Simplify xdp_return_{frame, frame_rx_napi, buff}") Reported-by: Maxim Mikityanskiy Signed-off-by: Björn Töpel Signed-off-by: Daniel Borkmann Acked-by: Maxim Mikityanskiy Link: https://lore.kernel.org/bpf/20201127171726.123627-1-bjorn.topel@gmail.com --- net/core/xdp.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/net/core/xdp.c b/net/core/xdp.c index 48aba933a5a8..491ad569a79c 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -335,11 +335,10 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); * scenarios (e.g. queue full), it is possible to return the xdp_frame * while still leveraging this protection. The @napi_direct boolean * is used for those calls sites. Thus, allowing for faster recycling - * of xdp_frames/pages in those cases. This path is never used by the - * MEM_TYPE_XSK_BUFF_POOL memory type, so it's explicitly not part of - * the switch-statement. + * of xdp_frames/pages in those cases. */ -static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct) +static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, + struct xdp_buff *xdp) { struct xdp_mem_allocator *xa; struct page *page; @@ -361,6 +360,10 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct) page = virt_to_page(data); /* Assumes order0 page*/ put_page(page); break; + case MEM_TYPE_XSK_BUFF_POOL: + /* NB! Only valid from an xdp_buff! */ + xsk_buff_free(xdp); + break; default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ WARN(1, "Incorrect XDP memory type (%d) usage", mem->type); @@ -370,19 +373,19 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct) void xdp_return_frame(struct xdp_frame *xdpf) { - __xdp_return(xdpf->data, &xdpf->mem, false); + __xdp_return(xdpf->data, &xdpf->mem, false, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { - __xdp_return(xdpf->data, &xdpf->mem, true); + __xdp_return(xdpf->data, &xdpf->mem, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); void xdp_return_buff(struct xdp_buff *xdp) { - __xdp_return(xdp->data, &xdp->rxq->mem, true); + __xdp_return(xdp->data, &xdp->rxq->mem, true, xdp); } /* Only called for MEM_TYPE_PAGE_POOL see xdp.h */ -- cgit v1.2.3 From dd0ecf544125639e54056d851e4887dbb94b6d2f Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 30 Nov 2020 16:07:25 +0100 Subject: gfs2: Fix deadlock between gfs2_{create_inode,inode_lookup} and delete_work_func In gfs2_create_inode and gfs2_inode_lookup, make sure to cancel any pending delete work before taking the inode glock. Otherwise, gfs2_cancel_delete_work may block waiting for delete_work_func to complete, and delete_work_func may block trying to acquire the inode glock in gfs2_inode_lookup. Reported-by: Alexander Aring Fixes: a0e3cc65fa29 ("gfs2: Turn gl_delete into a delayed work") Cc: stable@vger.kernel.org # v5.8+ Signed-off-by: Andreas Gruenbacher --- fs/gfs2/inode.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index eed1a1bac6f6..65ae4fc28ede 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -150,6 +150,8 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (unlikely(error)) goto fail; + if (blktype != GFS2_BLKST_UNLINKED) + gfs2_cancel_delete_work(io_gl); if (type == DT_UNKNOWN || blktype != GFS2_BLKST_FREE) { /* @@ -180,8 +182,6 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); if (unlikely(error)) goto fail; - if (blktype != GFS2_BLKST_UNLINKED) - gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl); glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_glock_put(io_gl); io_gl = NULL; @@ -725,13 +725,19 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, flush_delayed_work(&ip->i_gl->gl_work); glock_set_object(ip->i_gl, ip); - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); + error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (error) goto fail_free_inode; + gfs2_cancel_delete_work(io_gl); + glock_set_object(io_gl, ip); + + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); + if (error) + goto fail_gunlock2; error = gfs2_trans_begin(sdp, blocks, 0); if (error) - goto fail_free_inode; + goto fail_gunlock2; if (blocks > 1) { ip->i_eattr = ip->i_no_addr + 1; @@ -740,18 +746,12 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, init_dinode(dip, ip, symname); gfs2_trans_end(sdp); - error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl); - if (error) - goto fail_free_inode; - BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags)); error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); if (error) goto fail_gunlock2; - gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl); - glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_set_iop(inode); insert_inode_hash(inode); @@ -803,6 +803,7 @@ fail_gunlock3: gfs2_glock_dq_uninit(&ip->i_iopen_gh); fail_gunlock2: clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); + glock_clear_object(io_gl, ip); gfs2_glock_put(io_gl); fail_free_inode: if (ip->i_gl) { -- cgit v1.2.3 From 70e734fed740939704d1b3b76d6f2e6909698586 Mon Sep 17 00:00:00 2001 From: Robert Karszniewicz Date: Fri, 20 Nov 2020 18:51:24 +0100 Subject: ARM: imx: Use correct SRC base address Commit 4a4fb66119eb ("ARM: imx: Add missing of_node_put()") accidentally forgot to rename a variable, which caused the wrong address to be used and, in our case, the ULL getting falsely identified as ULZ. Fixes: 4a4fb66119eb ("ARM: imx: Add missing of_node_put()") Signed-off-by: Robert Karszniewicz Reviewed-by: Fabio Estevam Signed-off-by: Shawn Guo --- arch/arm/mach-imx/anatop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-imx/anatop.c b/arch/arm/mach-imx/anatop.c index d841bed8664d..7bb47eb3fc07 100644 --- a/arch/arm/mach-imx/anatop.c +++ b/arch/arm/mach-imx/anatop.c @@ -136,7 +136,7 @@ void __init imx_init_revision_from_anatop(void) src_np = of_find_compatible_node(NULL, NULL, "fsl,imx6ul-src"); - src_base = of_iomap(np, 0); + src_base = of_iomap(src_np, 0); of_node_put(src_np); WARN_ON(!src_base); sbmr2 = readl_relaxed(src_base + SRC_SBMR2); -- cgit v1.2.3 From 777a7717d60ccdc9b84f35074f848d3f746fc3bf Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 26 Nov 2020 14:08:41 +0000 Subject: drm/i915/gt: Program mocs:63 for cache eviction on gen9 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Ville noticed that the last mocs entry is used unconditionally by the HW when it performs cache evictions, and noted that while the value is not meant to be writable by the driver, we should program it to a reasonable value nevertheless. As it turns out, we can change the value of mocs:63 and the value we were programming into it would cause hard hangs in conjunction with atomic operations. v2: Add details from bspec about how it is used by HW Suggested-by: Ville Syrjälä Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2707 Fixes: 3bbaba0ceaa2 ("drm/i915: Added Programming of the MOCS") Signed-off-by: Chris Wilson Cc: Ville Syrjälä Cc: Jason Ekstrand Cc: # v4.3+ Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20201126140841.1982-1-chris@chris-wilson.co.uk (cherry picked from commit 977933b5da7c16f39295c4c1d4259a58ece65dbe) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_mocs.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index 313e51e7d4f7..4f74706967fd 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -131,7 +131,19 @@ static const struct drm_i915_mocs_entry skl_mocs_table[] = { GEN9_MOCS_ENTRIES, MOCS_ENTRY(I915_MOCS_CACHED, LE_3_WB | LE_TC_2_LLC_ELLC | LE_LRUM(3), - L3_3_WB) + L3_3_WB), + + /* + * mocs:63 + * - used by the L3 for all of its evictions. + * Thus it is expected to allow LLC cacheability to enable coherent + * flows to be maintained. + * - used to force L3 uncachable cycles. + * Thus it is expected to make the surface L3 uncacheable. + */ + MOCS_ENTRY(63, + LE_3_WB | LE_TC_1_LLC | LE_LRUM(3), + L3_1_UC) }; /* NOTE: the LE_TGT_CACHE is not used on Broxton */ -- cgit v1.2.3 From 58d6bca5efc73235b0f84c0d53321737177c651e Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Mon, 30 Nov 2020 17:54:47 -0300 Subject: ARM: dts: imx6qdl-wandboard-revd1: Remove PAD_GPIO_6 from enetgrp Since commit 8ad2d1dcce54 ("ARM: dts: imx6qdl-wandboard: Add OV5645 camera support") the PAD_GPIO_6 is used for providing the camera sensor clock. Remove it from the enetgrp to fix the following IOMXU conflict: [ 9.972414] imx6q-pinctrl 20e0000.pinctrl: pin MX6Q_PAD_GPIO_6 already requested by 2188000.ethernet; cannot claim for 1-003c [ 9.983857] imx6q-pinctrl 20e0000.pinctrl: pin-140 (1-003c) status -22 [ 9.990514] imx6q-pinctrl 20e0000.pinctrl: could not request pin 140 (MX6Q_PAD_GPIO_6) from group ov5645grp on device 20e0000.pinctrl Fixes: 8ad2d1dcce54 ("ARM: dts: imx6qdl-wandboard: Add OV5645 camera support") Signed-off-by: Fabio Estevam Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6qdl-wandboard-revd1.dtsi | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6qdl-wandboard-revd1.dtsi b/arch/arm/boot/dts/imx6qdl-wandboard-revd1.dtsi index 93909796885a..b9b698f72b26 100644 --- a/arch/arm/boot/dts/imx6qdl-wandboard-revd1.dtsi +++ b/arch/arm/boot/dts/imx6qdl-wandboard-revd1.dtsi @@ -166,7 +166,6 @@ MX6QDL_PAD_RGMII_RD2__RGMII_RD2 0x1b030 MX6QDL_PAD_RGMII_RD3__RGMII_RD3 0x1b030 MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b030 - MX6QDL_PAD_GPIO_6__ENET_IRQ 0x000b1 >; }; -- cgit v1.2.3 From 19ba8fb810c60b46869acc9f455613de454e0fca Mon Sep 17 00:00:00 2001 From: Bernd Bauer Date: Thu, 26 Nov 2020 18:56:28 +0100 Subject: ARM: dts: imx6qdl-kontron-samx6i: fix I2C_PM scl pin Use the correct pin for the i2c scl signal else we can't access the SoM eeprom. Fixes: 2a51f9dae13d ("ARM: dts: imx6qdl-kontron-samx6i: Add iMX6-based Kontron SMARC-sAMX6i module") Signed-off-by: Bernd Bauer [m.felsch@pengutronix.de: Adapt commit message] Signed-off-by: Marco Felsch Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi index 265f5f3dbff6..24f793ca2886 100644 --- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi @@ -551,7 +551,7 @@ pinctrl_i2c3: i2c3grp { fsl,pins = < - MX6QDL_PAD_GPIO_3__I2C3_SCL 0x4001b8b1 + MX6QDL_PAD_GPIO_5__I2C3_SCL 0x4001b8b1 MX6QDL_PAD_GPIO_16__I2C3_SDA 0x4001b8b1 >; }; -- cgit v1.2.3 From e3d5e971d2f83d8ddd4b91a50cea4517fb488383 Mon Sep 17 00:00:00 2001 From: Vinay Kumar Yadav Date: Thu, 26 Nov 2020 03:19:14 +0530 Subject: chelsio/chtls: fix panic during unload reload chtls there is kernel panic in inet_twsk_free() while chtls module unload when socket is in TIME_WAIT state because sk_prot_creator was not preserved on connection socket. Fixes: cc35c88ae4db ("crypto : chtls - CPL handler definition") Signed-off-by: Udai Sharma Signed-off-by: Vinay Kumar Yadav Link: https://lore.kernel.org/r/20201125214913.16938-1-vinay.yadav@chelsio.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index 96d561653496..50e3a70e5a29 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -1206,6 +1206,7 @@ static struct sock *chtls_recv_sock(struct sock *lsk, sk_setup_caps(newsk, dst); ctx = tls_get_ctx(lsk); newsk->sk_destruct = ctx->sk_destruct; + newsk->sk_prot_creator = lsk->sk_prot_creator; csk->sk = newsk; csk->passive_reap_next = oreq; csk->tx_chan = cxgb4_port_chan(ndev); -- cgit v1.2.3 From 0a35dc41fea67ac4495ce7584406bf9557a6e7d0 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Thu, 26 Nov 2020 13:52:46 +0100 Subject: vxlan: Add needed_headroom for lower device It was observed that sending data via batadv over vxlan (on top of wireguard) reduced the performance massively compared to raw ethernet or batadv on raw ethernet. A check of perf data showed that the vxlan_build_skb was calling all the time pskb_expand_head to allocate enough headroom for: min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + VXLAN_HLEN + iphdr_len; But the vxlan_config_apply only requested needed headroom for: lowerdev->hard_header_len + VXLAN6_HEADROOM or VXLAN_HEADROOM So it completely ignored the needed_headroom of the lower device. The first caller of net_dev_xmit could therefore never make sure that enough headroom was allocated for the rest of the transmit path. Cc: Annika Wickert Signed-off-by: Sven Eckelmann Tested-by: Annika Wickert Link: https://lore.kernel.org/r/20201126125247.1047977-1-sven@narfation.org Signed-off-by: Jakub Kicinski --- drivers/net/vxlan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 1a557aeba32b..55fa3fbb80f1 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3798,6 +3798,7 @@ static void vxlan_config_apply(struct net_device *dev, dev->gso_max_segs = lowerdev->gso_max_segs; needed_headroom = lowerdev->hard_header_len; + needed_headroom += lowerdev->needed_headroom; max_mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); -- cgit v1.2.3 From a5e74021e84bb5eadf760aaf2c583304f02269be Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Thu, 26 Nov 2020 13:52:47 +0100 Subject: vxlan: Copy needed_tailroom from lowerdev While vxlan doesn't need any extra tailroom, the lowerdev might need it. In that case, copy it over to reduce the chance for additional (re)allocations in the transmit path. Signed-off-by: Sven Eckelmann Link: https://lore.kernel.org/r/20201126125247.1047977-2-sven@narfation.org Signed-off-by: Jakub Kicinski --- drivers/net/vxlan.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 55fa3fbb80f1..032f78261913 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3800,6 +3800,8 @@ static void vxlan_config_apply(struct net_device *dev, needed_headroom = lowerdev->hard_header_len; needed_headroom += lowerdev->needed_headroom; + dev->needed_tailroom = lowerdev->needed_tailroom; + max_mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); if (max_mtu < ETH_MIN_MTU) -- cgit v1.2.3 From 983df5f2699f83f78643b19d3399b160d1e64f5b Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 13 Nov 2020 10:34:14 -0800 Subject: samples/ftrace: Mark my_tramp[12]? global my_tramp[12]? are declared as global functions in C, but they are not marked global in the inline assembly definition. This mismatch confuses Clang's Control-Flow Integrity checking. Fix the definitions by adding .globl. Link: https://lkml.kernel.org/r/20201113183414.1446671-1-samitolvanen@google.com Fixes: 9d907f1ae80b8 ("ftrace/samples: Add a sample module that implements modify_ftrace_direct()") Reviewed-by: Kees Cook Signed-off-by: Sami Tolvanen Signed-off-by: Steven Rostedt (VMware) --- samples/ftrace/ftrace-direct-modify.c | 2 ++ samples/ftrace/ftrace-direct-too.c | 1 + samples/ftrace/ftrace-direct.c | 1 + 3 files changed, 4 insertions(+) diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c index c13a5bc5095b..5b9a09957c6e 100644 --- a/samples/ftrace/ftrace-direct-modify.c +++ b/samples/ftrace/ftrace-direct-modify.c @@ -21,6 +21,7 @@ static unsigned long my_ip = (unsigned long)schedule; asm ( " .pushsection .text, \"ax\", @progbits\n" " .type my_tramp1, @function\n" +" .globl my_tramp1\n" " my_tramp1:" " pushq %rbp\n" " movq %rsp, %rbp\n" @@ -29,6 +30,7 @@ asm ( " .size my_tramp1, .-my_tramp1\n" " ret\n" " .type my_tramp2, @function\n" +" .globl my_tramp2\n" " my_tramp2:" " pushq %rbp\n" " movq %rsp, %rbp\n" diff --git a/samples/ftrace/ftrace-direct-too.c b/samples/ftrace/ftrace-direct-too.c index d5c5022be664..3f0079c9bd6f 100644 --- a/samples/ftrace/ftrace-direct-too.c +++ b/samples/ftrace/ftrace-direct-too.c @@ -16,6 +16,7 @@ extern void my_tramp(void *); asm ( " .pushsection .text, \"ax\", @progbits\n" " .type my_tramp, @function\n" +" .globl my_tramp\n" " my_tramp:" " pushq %rbp\n" " movq %rsp, %rbp\n" diff --git a/samples/ftrace/ftrace-direct.c b/samples/ftrace/ftrace-direct.c index 63ca06d42c80..a2729d1ef17f 100644 --- a/samples/ftrace/ftrace-direct.c +++ b/samples/ftrace/ftrace-direct.c @@ -14,6 +14,7 @@ extern void my_tramp(void *); asm ( " .pushsection .text, \"ax\", @progbits\n" " .type my_tramp, @function\n" +" .globl my_tramp\n" " my_tramp:" " pushq %rbp\n" " movq %rsp, %rbp\n" -- cgit v1.2.3 From 310e3a4b5a4fc718a72201c1e4cf5c64ac6f5442 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Wed, 18 Nov 2020 15:05:20 +0300 Subject: tracing: Remove WARN_ON in start_thread() This patch reverts commit 978defee11a5 ("tracing: Do a WARN_ON() if start_thread() in hwlat is called when thread exists") .start hook can be legally called several times if according tracer is stopped screen window 1 [root@localhost ~]# echo 1 > /sys/kernel/tracing/events/kmem/kfree/enable [root@localhost ~]# echo 1 > /sys/kernel/tracing/options/pause-on-trace [root@localhost ~]# less -F /sys/kernel/tracing/trace screen window 2 [root@localhost ~]# cat /sys/kernel/debug/tracing/tracing_on 0 [root@localhost ~]# echo hwlat > /sys/kernel/debug/tracing/current_tracer [root@localhost ~]# echo 1 > /sys/kernel/debug/tracing/tracing_on [root@localhost ~]# cat /sys/kernel/debug/tracing/tracing_on 0 [root@localhost ~]# echo 2 > /sys/kernel/debug/tracing/tracing_on triggers warning in dmesg: WARNING: CPU: 3 PID: 1403 at kernel/trace/trace_hwlat.c:371 hwlat_tracer_start+0xc9/0xd0 Link: https://lkml.kernel.org/r/bd4d3e70-400d-9c82-7b73-a2d695e86b58@virtuozzo.com Cc: Ingo Molnar Cc: stable@vger.kernel.org Fixes: 978defee11a5 ("tracing: Do a WARN_ON() if start_thread() in hwlat is called when thread exists") Signed-off-by: Vasily Averin Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_hwlat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index c9ad5c6fbaad..d071fc271eef 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -368,7 +368,7 @@ static int start_kthread(struct trace_array *tr) struct task_struct *kthread; int next_cpu; - if (WARN_ON(hwlat_kthread)) + if (hwlat_kthread) return 0; /* Just pick the first CPU on first iteration */ -- cgit v1.2.3 From 8fa655a3a0013a0c2a2aada6f39a93ee6fc25549 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Wed, 25 Nov 2020 14:56:54 -0800 Subject: tracing: Fix alignment of static buffer With 5.9 kernel on ARM64, I found ftrace_dump output was broken but it had no problem with normal output "cat /sys/kernel/debug/tracing/trace". With investigation, it seems coping the data into temporal buffer seems to break the align binary printf expects if the static buffer is not aligned with 4-byte. IIUC, get_arg in bstr_printf expects that args has already right align to be decoded and seq_buf_bprintf says ``the arguments are saved in a 32bit word array that is defined by the format string constraints``. So if we don't keep the align under copy to temporal buffer, the output will be broken by shifting some bytes. This patch fixes it. Link: https://lkml.kernel.org/r/20201125225654.1618966-1-minchan@kernel.org Cc: Fixes: 8e99cf91b99bb ("tracing: Do not allocate buffer in trace_find_next_entry() in atomic") Signed-off-by: Namhyung Kim Signed-off-by: Minchan Kim Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 410cfeb16db5..7d53c5bdea3e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3534,7 +3534,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, } #define STATIC_TEMP_BUF_SIZE 128 -static char static_temp_buf[STATIC_TEMP_BUF_SIZE]; +static char static_temp_buf[STATIC_TEMP_BUF_SIZE] __aligned(4); /* Find the next real entry, without updating the iterator itself */ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, -- cgit v1.2.3 From 4c75b0ff4e4bf7a45b5aef9639799719c28d0073 Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Thu, 26 Nov 2020 23:38:38 +0530 Subject: ftrace: Fix updating FTRACE_FL_TRAMP On powerpc, kprobe-direct.tc triggered FTRACE_WARN_ON() in ftrace_get_addr_new() followed by the below message: Bad trampoline accounting at: 000000004222522f (wake_up_process+0xc/0x20) (f0000001) The set of steps leading to this involved: - modprobe ftrace-direct-too - enable_probe - modprobe ftrace-direct - rmmod ftrace-direct <-- trigger The problem turned out to be that we were not updating flags in the ftrace record properly. From the above message about the trampoline accounting being bad, it can be seen that the ftrace record still has FTRACE_FL_TRAMP set though ftrace-direct module is going away. This happens because we are checking if any ftrace_ops has the FTRACE_FL_TRAMP flag set _before_ updating the filter hash. The fix for this is to look for any _other_ ftrace_ops that also needs FTRACE_FL_TRAMP. Link: https://lkml.kernel.org/r/56c113aa9c3e10c19144a36d9684c7882bf09af5.1606412433.git.naveen.n.rao@linux.vnet.ibm.com Cc: stable@vger.kernel.org Fixes: a124692b698b0 ("ftrace: Enable trampoline when rec count returns back to one") Signed-off-by: Naveen N. Rao Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 8185f7240095..9c1bba8cc51b 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1629,6 +1629,8 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec) static struct ftrace_ops * ftrace_find_tramp_ops_any(struct dyn_ftrace *rec); static struct ftrace_ops * +ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude); +static struct ftrace_ops * ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops); static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, @@ -1778,7 +1780,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, * to it. */ if (ftrace_rec_count(rec) == 1 && - ftrace_find_tramp_ops_any(rec)) + ftrace_find_tramp_ops_any_other(rec, ops)) rec->flags |= FTRACE_FL_TRAMP; else rec->flags &= ~FTRACE_FL_TRAMP; @@ -2244,6 +2246,24 @@ ftrace_find_tramp_ops_any(struct dyn_ftrace *rec) return NULL; } +static struct ftrace_ops * +ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude) +{ + struct ftrace_ops *op; + unsigned long ip = rec->ip; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + + if (op == op_exclude || !op->trampoline) + continue; + + if (hash_contains_ip(ip, op->func_hash)) + return op; + } while_for_each_ftrace_op(op); + + return NULL; +} + static struct ftrace_ops * ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *op) -- cgit v1.2.3 From 49a962c075dfa41c78e34784772329bc8784d217 Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Thu, 26 Nov 2020 23:38:39 +0530 Subject: ftrace: Fix DYNAMIC_FTRACE_WITH_DIRECT_CALLS dependency DYNAMIC_FTRACE_WITH_DIRECT_CALLS should depend on DYNAMIC_FTRACE_WITH_REGS since we need ftrace_regs_caller(). Link: https://lkml.kernel.org/r/fc4b257ea8689a36f086d2389a9ed989496ca63a.1606412433.git.naveen.n.rao@linux.vnet.ibm.com Cc: stable@vger.kernel.org Fixes: 763e34e74bb7d5c ("ftrace: Add register_ftrace_direct()") Signed-off-by: Naveen N. Rao Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index a4020c0b4508..e1bf5228fb69 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -202,7 +202,7 @@ config DYNAMIC_FTRACE_WITH_REGS config DYNAMIC_FTRACE_WITH_DIRECT_CALLS def_bool y - depends on DYNAMIC_FTRACE + depends on DYNAMIC_FTRACE_WITH_REGS depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS config FUNCTION_PROFILER -- cgit v1.2.3 From 6112ff4e8f393e7e297dff04eff0987f94d37fa1 Mon Sep 17 00:00:00 2001 From: Jing Xiangfeng Date: Fri, 27 Nov 2020 11:02:06 +0800 Subject: scsi: storvsc: Fix error return in storvsc_probe() Return -ENOMEM from the error handling case instead of 0. Link: https://lore.kernel.org/r/20201127030206.104616-1-jingxiangfeng@huawei.com Fixes: 436ad9413353 ("scsi: storvsc: Allow only one remove lun work item to be issued per lun") Reviewed-by: Michael Kelley Signed-off-by: Jing Xiangfeng Signed-off-by: Martin K. Petersen --- drivers/scsi/storvsc_drv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 0c65fbd41035..ded00a89bfc4 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1994,8 +1994,10 @@ static int storvsc_probe(struct hv_device *device, alloc_ordered_workqueue("storvsc_error_wq_%d", WQ_MEM_RECLAIM, host->host_no); - if (!host_dev->handle_error_wq) + if (!host_dev->handle_error_wq) { + ret = -ENOMEM; goto err_out2; + } INIT_WORK(&host_dev->host_scan_work, storvsc_host_scan); /* Register the HBA and start the scsi bus scan */ ret = scsi_add_host(host, &device->device); -- cgit v1.2.3 From 68e10d5ff512b503dcba1246ad5620f32035e135 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 30 Nov 2020 23:16:03 -0500 Subject: ring-buffer: Always check to put back before stamp when crossing pages The current ring buffer logic checks to see if the updating of the event buffer was interrupted, and if it is, it will try to fix up the before stamp with the write stamp to make them equal again. This logic is flawed, because if it is not interrupted, the two are guaranteed to be different, as the current event just updated the before stamp before allocation. This guarantees that the next event (this one or another interrupting one) will think it interrupted the time updates of a previous event and inject an absolute time stamp to compensate. The correct logic is to always update the timestamps when traversing to a new sub buffer. Cc: stable@vger.kernel.org Fixes: a389d86f7fd09 ("ring-buffer: Have nested events still record running time stamp") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 35d91b20d47a..a6268e09160a 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3234,14 +3234,12 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* See if we shot pass the end of this buffer page */ if (unlikely(write > BUF_PAGE_SIZE)) { - if (tail != w) { - /* before and after may now different, fix it up*/ - b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - if (a_ok && b_ok && info->before != info->after) - (void)rb_time_cmpxchg(&cpu_buffer->before_stamp, - info->before, info->after); - } + /* before and after may now different, fix it up*/ + b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); + a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); + if (a_ok && b_ok && info->before != info->after) + (void)rb_time_cmpxchg(&cpu_buffer->before_stamp, + info->before, info->after); return rb_move_tail(cpu_buffer, tail, info); } -- cgit v1.2.3 From 24aed09451270b6a2a78adf8a34918d12ffb7dcf Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 20 Nov 2020 11:29:04 +0900 Subject: bootconfig: Load size and checksum in the footer as le32 Load the size and the checksum fields in the footer as le32 instead of u32. This will allow us to apply bootconfig to the cross build initrd without caring the endianness. Link: https://lkml.kernel.org/r/160583934457.547349.10504070298990791074.stgit@devnote2 Reported-by: Steven Rostedt Suggested-by: Linus Torvalds Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- init/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/init/main.c b/init/main.c index 20baced721ad..32b2a8affafd 100644 --- a/init/main.c +++ b/init/main.c @@ -288,8 +288,8 @@ static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) found: hdr = (u32 *)(data - 8); - size = hdr[0]; - csum = hdr[1]; + size = le32_to_cpu(hdr[0]); + csum = le32_to_cpu(hdr[1]); data = ((void *)hdr) - size; if ((unsigned long)data < initrd_start) { -- cgit v1.2.3 From e86843580d1bb1ce12544bca3115cf11d51603ff Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 20 Nov 2020 11:29:13 +0900 Subject: tools/bootconfig: Store size and checksum in footer as le32 Store the size and the checksum fields in the footer as le32 instead of u32. This will allow us to apply bootconfig to the cross build initrd without caring the endianness. Link: https://lkml.kernel.org/r/160583935332.547349.5897811300636587426.stgit@devnote2 Reported-by: Steven Rostedt Suggested-by: Linus Torvalds Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- tools/bootconfig/main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 4a445b6304bb..7362bef1a368 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -183,9 +184,11 @@ static int load_xbc_from_initrd(int fd, char **buf) if (read(fd, &size, sizeof(u32)) < 0) return pr_errno("Failed to read size", -errno); + size = le32toh(size); if (read(fd, &csum, sizeof(u32)) < 0) return pr_errno("Failed to read checksum", -errno); + csum = le32toh(csum); /* Wrong size error */ if (stat.st_size < size + 8 + BOOTCONFIG_MAGIC_LEN) { @@ -407,10 +410,10 @@ static int apply_xbc(const char *path, const char *xbc_path) /* Add a footer */ p = data + size; - *(u32 *)p = size; + *(u32 *)p = htole32(size); p += sizeof(u32); - *(u32 *)p = csum; + *(u32 *)p = htole32(csum); p += sizeof(u32); memcpy(p, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); -- cgit v1.2.3 From 05227490c5f0f1bbd3693a7a70b3fb5b09d2a996 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 20 Nov 2020 11:29:22 +0900 Subject: docs: bootconfig: Add the endianness of fields Add a description about the endianness of the size and the checksum fields. Those must be stored as le32 instead of u32. This will allow us to apply bootconfig to the cross build initrd without caring the endianness. Link: https://lkml.kernel.org/r/160583936246.547349.10964204130590955409.stgit@devnote2 Reported-by: Steven Rostedt Suggested-by: Linus Torvalds Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- Documentation/admin-guide/bootconfig.rst | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst index 363599683784..9b90efcc3a35 100644 --- a/Documentation/admin-guide/bootconfig.rst +++ b/Documentation/admin-guide/bootconfig.rst @@ -140,7 +140,9 @@ Since the boot configuration file is loaded with initrd, it will be added to the end of the initrd (initramfs) image file with padding, size, checksum and 12-byte magic word as below. -[initrd][bootconfig][padding][size(u32)][checksum(u32)][#BOOTCONFIG\n] +[initrd][bootconfig][padding][size(le32)][checksum(le32)][#BOOTCONFIG\n] + +The size and checksum fields are unsigned 32bit little endian value. When the boot configuration is added to the initrd image, the total file size is aligned to 4 bytes. To fill the gap, null characters -- cgit v1.2.3 From 3b8c72d076c42bf27284cda7b2b2b522810686f8 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Wed, 18 Nov 2020 15:53:48 +0100 Subject: scsi: storvsc: Validate length of incoming packet in storvsc_on_channel_callback() Check that the packet is of the expected size at least, don't copy data past the packet. Link: https://lore.kernel.org/r/20201118145348.109879-1-parri.andrea@gmail.com Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: linux-scsi@vger.kernel.org Reported-by: Saruhan Karademir Signed-off-by: Andrea Parri (Microsoft) Signed-off-by: Martin K. Petersen --- drivers/scsi/storvsc_drv.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index ded00a89bfc4..99c8ff81de74 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1246,6 +1246,11 @@ static void storvsc_on_channel_callback(void *context) request = (struct storvsc_cmd_request *) ((unsigned long)desc->trans_id); + if (hv_pkt_datalen(desc) < sizeof(struct vstor_packet) - vmscsi_size_delta) { + dev_err(&device->device, "Invalid packet len\n"); + continue; + } + if (request == &stor_device->init_request || request == &stor_device->reset_request) { memcpy(&request->vstor_packet, packet, -- cgit v1.2.3 From 42f687038bcc34aa919e0e4c29b04e4cda3f6a79 Mon Sep 17 00:00:00 2001 From: Suganath Prabu S Date: Wed, 25 Nov 2020 15:18:38 +0530 Subject: scsi: mpt3sas: Fix ioctl timeout Commit c1a6c5ac4278 ("scsi: mpt3sas: For NVME device, issue a protocol level reset") modified the ioctl path 'timeout' variable type to u8 from unsigned long, limiting the maximum timeout value that the driver can support to 255 seconds. If the management application is requesting a higher value the resulting timeout will be zero. The operation times out immediately and the ioctl request fails. Change datatype back to unsigned long. Link: https://lore.kernel.org/r/20201125094838.4340-1-suganath-prabu.subramani@broadcom.com Fixes: c1a6c5ac4278 ("scsi: mpt3sas: For NVME device, issue a protocol level reset") Cc: #v4.18+ Signed-off-by: Suganath Prabu S Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_ctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index 0f2b681449e6..edd26a2570fa 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -664,7 +664,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg, Mpi26NVMeEncapsulatedRequest_t *nvme_encap_request = NULL; struct _pcie_device *pcie_device = NULL; u16 smid; - u8 timeout; + unsigned long timeout; u8 issue_reset; u32 sz, sz_arg; void *psge; -- cgit v1.2.3 From 85dad327d9b58b4c9ce08189a2707167de392d23 Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Mon, 30 Nov 2020 13:57:33 +0530 Subject: scsi: mpt3sas: Increase IOCInit request timeout to 30s Currently the IOCInit request message timeout is set to 10s. This is not sufficient in some scenarios such as during HBA FW downgrade operations. Increase the IOCInit request timeout to 30s. Link: https://lore.kernel.org/r/20201130082733.26120-1-sreekanth.reddy@broadcom.com Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index e4cc92bc4d94..bb940cbcbb5d 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -6459,7 +6459,7 @@ _base_send_ioc_init(struct MPT3SAS_ADAPTER *ioc) r = _base_handshake_req_reply_wait(ioc, sizeof(Mpi2IOCInitRequest_t), (u32 *)&mpi_request, - sizeof(Mpi2IOCInitReply_t), (u16 *)&mpi_reply, 10); + sizeof(Mpi2IOCInitReply_t), (u16 *)&mpi_reply, 30); if (r != 0) { ioc_err(ioc, "%s: handshake failed (r=%d)\n", __func__, r); -- cgit v1.2.3 From a48491c65b513e5cdc3e7a886a4db915f848a5f5 Mon Sep 17 00:00:00 2001 From: Po-Hsu Lin Date: Mon, 30 Nov 2020 22:39:40 -0800 Subject: Input: i8042 - add ByteSpeed touchpad to noloop table It looks like the C15B laptop got another vendor: ByteSpeed LLC. Avoid AUX loopback on this touchpad as well, thus input subsystem will be able to recognize a Synaptics touchpad in the AUX port. BugLink: https://bugs.launchpad.net/bugs/1906128 Signed-off-by: Po-Hsu Lin Link: https://lore.kernel.org/r/20201201054723.5939-1-po-hsu.lin@canonical.com Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/serio/i8042-x86ia64io.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index a4c9b9652560..7ecb65176c1a 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -219,6 +219,10 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"), DMI_MATCH(DMI_PRODUCT_NAME, "C15B"), }, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ByteSpeed LLC"), + DMI_MATCH(DMI_PRODUCT_NAME, "ByteSpeed Laptop C15B"), + }, }, { } }; -- cgit v1.2.3 From 2aab1561439032be2e98811dd0ddbeb5b2ae4c61 Mon Sep 17 00:00:00 2001 From: Sanjay Govind Date: Mon, 30 Nov 2020 23:41:48 -0800 Subject: Input: xpad - support Ardwiino Controllers This commit adds support for Ardwiino Controllers Signed-off-by: Sanjay Govind Link: https://lore.kernel.org/r/20201201071922.131666-1-sanjay.govind9@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/joystick/xpad.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index c77cdb3b62b5..8c73377ac82c 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -241,6 +241,7 @@ static const struct xpad_device { { 0x1038, 0x1430, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 }, { 0x1038, 0x1431, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 }, { 0x11c9, 0x55f0, "Nacon GC-100XF", 0, XTYPE_XBOX360 }, + { 0x1209, 0x2882, "Ardwiino Controller", 0, XTYPE_XBOX360 }, { 0x12ab, 0x0004, "Honey Bee Xbox360 dancepad", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 }, { 0x12ab, 0x0301, "PDP AFTERGLOW AX.1", 0, XTYPE_XBOX360 }, { 0x12ab, 0x0303, "Mortal Kombat Klassic FightStick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, @@ -418,6 +419,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOXONE_VENDOR(0x0f0d), /* Hori Controllers */ XPAD_XBOX360_VENDOR(0x1038), /* SteelSeries Controllers */ XPAD_XBOX360_VENDOR(0x11c9), /* Nacon GC100XF */ + XPAD_XBOX360_VENDOR(0x1209), /* Ardwiino Controllers */ XPAD_XBOX360_VENDOR(0x12ab), /* X-Box 360 dance pads */ XPAD_XBOX360_VENDOR(0x1430), /* RedOctane X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x146b), /* BigBen Interactive Controllers */ -- cgit v1.2.3 From c98fff7332dbd6e028969f8c2bda3d7bc7a024d8 Mon Sep 17 00:00:00 2001 From: Bjørn Mork Date: Tue, 1 Dec 2020 11:03:18 +0100 Subject: USB: serial: option: fix Quectel BG96 matching MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is a partial revert of commit 2bb70f0a4b23 ("USB: serial: option: support dynamic Quectel USB compositions") The Quectel BG96 is different from most other modern Quectel modems, having serial functions with 3 endpoints using ff/ff/ff and ff/fe/ff class/subclass/protocol. Including it in the change to accommodate dynamic function mapping was incorrect. Revert to interface number matching for the BG96, assuming static layout of the RMNET function on interface 4. This restores support for the serial functions on interfaces 2 and 3. Full lsusb output for the BG96: Bus 002 Device 003: ID 2c7c:0296 Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 2.00 bDeviceClass 0 (Defined at Interface level) bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 64 idVendor 0x2c7c idProduct 0x0296 bcdDevice 0.00 iManufacturer 3 Qualcomm, Incorporated iProduct 2 Qualcomm CDMA Technologies MSM iSerial 4 d1098243 bNumConfigurations 1 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 145 bNumInterfaces 5 bConfigurationValue 1 iConfiguration 1 Qualcomm Configuration bmAttributes 0xe0 Self Powered Remote Wakeup MaxPower 500mA Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 255 Vendor Specific Protocol iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x01 EP 1 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 255 Vendor Specific Protocol iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x82 EP 2 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x02 EP 2 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 2 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 255 Vendor Specific Protocol iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x83 EP 3 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x84 EP 4 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x03 EP 3 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 3 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 254 bInterfaceProtocol 255 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x85 EP 5 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x86 EP 6 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x04 EP 4 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 4 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 255 Vendor Specific Protocol iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x87 EP 7 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x88 EP 8 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x05 EP 5 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Device Qualifier (for other device speed): bLength 10 bDescriptorType 6 bcdUSB 2.00 bDeviceClass 0 (Defined at Interface level) bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 64 bNumConfigurations 1 Device Status: 0x0000 (Bus Powered) Cc: Sebastian Sjoholm Fixes: 2bb70f0a4b23 ("USB: serial: option: support dynamic Quectel USB compositions") Signed-off-by: Bjørn Mork Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 653da1d2945c..56d6f6d83bd7 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1106,9 +1106,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0xff, 0xff), .driver_info = NUMEP2 }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0, 0) }, - { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96, 0xff, 0xff, 0xff), - .driver_info = NUMEP2 }, - { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96, 0xff, 0, 0) }, + { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96), + .driver_info = RSVD(4) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff), .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) }, -- cgit v1.2.3 From c2b111e59a7be1534bbd62b3f8f933f714c5ba71 Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Sun, 29 Nov 2020 17:26:27 +0100 Subject: arm64: dts: allwinner: A64 Sopine: phy-mode rgmii-id Since commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config") iSCSI booting fails on the Pine A64 LTS. This patch changes the phy-mode to use internal delays both for RX and TX as has been done for other boards affected by the same commit. Fixes: bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config") Signed-off-by: Heinrich Schuchardt Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20201129162627.1244808-1-xypron.glpk@gmx.de --- arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts index 9ebb9e07fae3..d4069749d721 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts @@ -79,7 +79,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_dc1sw>; status = "okay"; -- cgit v1.2.3 From d0c6707ca4235b78d06bcd62f0e24fbeac3e6d10 Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Sun, 29 Nov 2020 20:45:12 +0100 Subject: arm64: dts: allwinner: H5: NanoPi Neo Plus2: phy-mode rgmii-id Since commit bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config") network is broken on the NanoPi Neo Plus2. This patch changes the phy-mode to use internal delays both for RX and TX as has been done for other boards affected by the same commit. Fixes: bbc4d71d6354 ("net: phy: realtek: fix rtl8211e rx/tx delay config") Signed-off-by: Heinrich Schuchardt Signed-off-by: Maxime Ripard Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20201129194512.1475586-1-xypron.glpk@gmx.de --- arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo-plus2.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo-plus2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo-plus2.dts index 4f9ba53ffaae..9d93fe153689 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo-plus2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo-plus2.dts @@ -96,7 +96,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; -- cgit v1.2.3 From f54db39fbe40731c40aefdd3bc26e7d56d668c64 Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Mon, 30 Nov 2020 13:19:27 +0100 Subject: KVM: PPC: Book3S HV: XIVE: Fix vCPU id sanity check MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 062cfab7069f ("KVM: PPC: Book3S HV: XIVE: Make VP block size configurable") updated kvmppc_xive_vcpu_id_valid() in a way that allows userspace to trigger an assertion in skiboot and crash the host: [ 696.186248988,3] XIVE[ IC 08 ] eq_blk != vp_blk (0 vs. 1) for target 0x4300008c/0 [ 696.186314757,0] Assert fail: hw/xive.c:2370:0 [ 696.186342458,0] Aborting! xive-kvCPU 0043 Backtrace: S: 0000000031e2b8f0 R: 0000000030013840 .backtrace+0x48 S: 0000000031e2b990 R: 000000003001b2d0 ._abort+0x4c S: 0000000031e2ba10 R: 000000003001b34c .assert_fail+0x34 S: 0000000031e2ba90 R: 0000000030058984 .xive_eq_for_target.part.20+0xb0 S: 0000000031e2bb40 R: 0000000030059fdc .xive_setup_silent_gather+0x2c S: 0000000031e2bc20 R: 000000003005a334 .opal_xive_set_vp_info+0x124 S: 0000000031e2bd20 R: 00000000300051a4 opal_entry+0x134 --- OPAL call token: 0x8a caller R1: 0xc000001f28563850 --- XIVE maintains the interrupt context state of non-dispatched vCPUs in an internal VP structure. We allocate a bunch of those on startup to accommodate all possible vCPUs. Each VP has an id, that we derive from the vCPU id for efficiency: static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server) { return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server); } The KVM XIVE device used to allocate KVM_MAX_VCPUS VPs. This was limitting the number of concurrent VMs because the VP space is limited on the HW. Since most of the time, VMs run with a lot less vCPUs, commit 062cfab7069f ("KVM: PPC: Book3S HV: XIVE: Make VP block size configurable") gave the possibility for userspace to tune the size of the VP block through the KVM_DEV_XIVE_NR_SERVERS attribute. The check in kvmppc_pack_vcpu_id() was changed from cpu < KVM_MAX_VCPUS * xive->kvm->arch.emul_smt_mode to cpu < xive->nr_servers * xive->kvm->arch.emul_smt_mode The previous check was based on the fact that the VP block had KVM_MAX_VCPUS entries and that kvmppc_pack_vcpu_id() guarantees that packed vCPU ids are below KVM_MAX_VCPUS. We've changed the size of the VP block, but kvmppc_pack_vcpu_id() has nothing to do with it and it certainly doesn't ensure that the packed vCPU ids are below xive->nr_servers. kvmppc_xive_vcpu_id_valid() might thus return true when the VM was configured with a non-standard VSMT mode, even if the packed vCPU id is higher than what we expect. We end up using an unallocated VP id, which confuses OPAL. The assert in OPAL is probably abusive and should be converted to a regular error that the kernel can handle, but we shouldn't really use broken VP ids in the first place. Fix kvmppc_xive_vcpu_id_valid() so that it checks the packed vCPU id is below xive->nr_servers, which is explicitly what we want. Fixes: 062cfab7069f ("KVM: PPC: Book3S HV: XIVE: Make VP block size configurable") Cc: stable@vger.kernel.org # v5.5+ Signed-off-by: Greg Kurz Reviewed-by: Cédric Le Goater Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/160673876747.695514.1809676603724514920.stgit@bahia.lan --- arch/powerpc/kvm/book3s_xive.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 85215e79db42..a0ebc29f30b2 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1214,12 +1214,9 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu) static bool kvmppc_xive_vcpu_id_valid(struct kvmppc_xive *xive, u32 cpu) { /* We have a block of xive->nr_servers VPs. We just need to check - * raw vCPU ids are below the expected limit for this guest's - * core stride ; kvmppc_pack_vcpu_id() will pack them down to an - * index that can be safely used to compute a VP id that belongs - * to the VP block. + * packed vCPU ids are below that. */ - return cpu < xive->nr_servers * xive->kvm->arch.emul_smt_mode; + return kvmppc_pack_vcpu_id(xive->kvm, cpu) < xive->nr_servers; } int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp) -- cgit v1.2.3 From 59612b24f78a0b61fe078ec9dff2e48e9cec52c0 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 19 Nov 2020 13:46:56 -0700 Subject: kbuild: Hoist '--orphan-handling' into Kconfig Currently, '--orphan-handling=warn' is spread out across four different architectures in their respective Makefiles, which makes it a little unruly to deal with in case it needs to be disabled for a specific linker version (in this case, ld.lld 10.0.1). To make it easier to control this, hoist this warning into Kconfig and the main Makefile so that disabling it is simpler, as the warning will only be enabled in a couple places (main Makefile and a couple of compressed boot folders that blow away LDFLAGS_vmlinx) and making it conditional is easier due to Kconfig syntax. One small additional benefit of this is saving a call to ld-option on incremental builds because we will have already evaluated it for CONFIG_LD_ORPHAN_WARN. To keep the list of supported architectures the same, introduce CONFIG_ARCH_WANT_LD_ORPHAN_WARN, which an architecture can select to gain this automatically after all of the sections are specified and size asserted. A special thanks to Kees Cook for the help text on this config. Link: https://github.com/ClangBuiltLinux/linux/issues/1187 Acked-by: Kees Cook Acked-by: Michael Ellerman (powerpc) Reviewed-by: Nick Desaulniers Tested-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Signed-off-by: Masahiro Yamada --- Makefile | 6 ++++++ arch/Kconfig | 9 +++++++++ arch/arm/Kconfig | 1 + arch/arm/Makefile | 4 ---- arch/arm/boot/compressed/Makefile | 4 +++- arch/arm64/Kconfig | 1 + arch/arm64/Makefile | 4 ---- arch/powerpc/Kconfig | 1 + arch/powerpc/Makefile | 1 - arch/x86/Kconfig | 1 + arch/x86/Makefile | 3 --- arch/x86/boot/compressed/Makefile | 4 +++- init/Kconfig | 5 +++++ 13 files changed, 30 insertions(+), 14 deletions(-) diff --git a/Makefile b/Makefile index ae1592c1f5d6..8327725e5d76 100644 --- a/Makefile +++ b/Makefile @@ -986,6 +986,12 @@ ifeq ($(CONFIG_RELR),y) LDFLAGS_vmlinux += --pack-dyn-relocs=relr endif +# We never want expected sections to be placed heuristically by the +# linker. All sections should be explicitly named in the linker script. +ifdef CONFIG_LD_ORPHAN_WARN +LDFLAGS_vmlinux += --orphan-handling=warn +endif + # Align the bit size of userspace programs with the kernel KBUILD_USERCFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS)) KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS)) diff --git a/arch/Kconfig b/arch/Kconfig index 56b6ccc0e32d..ba4e966484ab 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1028,6 +1028,15 @@ config HAVE_STATIC_CALL_INLINE bool depends on HAVE_STATIC_CALL +config ARCH_WANT_LD_ORPHAN_WARN + bool + help + An arch should select this symbol once all linker sections are explicitly + included, size-asserted, or discarded in the linker scripts. This is + important because we never want expected sections to be placed heuristically + by the linker, since the locations of such sections can change between linker + versions. + source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index fe2f17eb2b50..002e0cf025f5 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -35,6 +35,7 @@ config ARM select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU select ARCH_WANT_IPC_PARSE_VERSION + select ARCH_WANT_LD_ORPHAN_WARN select BINFMT_FLAT_ARGVP_ENVP_ON_STACK select BUILDTIME_TABLE_SORT if MMU select CLONE_BACKWARDS diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 4d76eab2b22d..e15f76ca2887 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -16,10 +16,6 @@ LDFLAGS_vmlinux += --be8 KBUILD_LDFLAGS_MODULE += --be8 endif -# We never want expected sections to be placed heuristically by the -# linker. All sections should be explicitly named in the linker script. -LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn) - GZFLAGS :=-9 #KBUILD_CFLAGS +=-pipe diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 47f001ca5499..e1567418a2b1 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -129,7 +129,9 @@ LDFLAGS_vmlinux += --no-undefined # Delete all temporary local symbols LDFLAGS_vmlinux += -X # Report orphan sections -LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn) +ifdef CONFIG_LD_ORPHAN_WARN +LDFLAGS_vmlinux += --orphan-handling=warn +endif # Next argument is a linker script LDFLAGS_vmlinux += -T diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 1515f6f153a0..a6b5b7ef40ae 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -81,6 +81,7 @@ config ARM64 select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36) + select ARCH_WANT_LD_ORPHAN_WARN select ARCH_HAS_UBSAN_SANITIZE_ALL select ARM_AMBA select ARM_ARCH_TIMER diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 5789c2d18d43..6a87d592bd00 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -28,10 +28,6 @@ LDFLAGS_vmlinux += --fix-cortex-a53-843419 endif endif -# We never want expected sections to be placed heuristically by the -# linker. All sections should be explicitly named in the linker script. -LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn) - ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS), y) ifneq ($(CONFIG_ARM64_LSE_ATOMICS), y) $(warning LSE atomics not supported by binutils) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index e9f13fe08492..5181872f9452 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -152,6 +152,7 @@ config PPC select ARCH_USE_QUEUED_SPINLOCKS if PPC_QUEUED_SPINLOCKS select ARCH_WANT_IPC_PARSE_VERSION select ARCH_WANT_IRQS_OFF_ACTIVATE_MM + select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WEAK_RELEASE_ACQUIRE select BINFMT_ELF select BUILDTIME_TABLE_SORT diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index a4d56f0a41d9..d9eb0da845e1 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -123,7 +123,6 @@ endif LDFLAGS_vmlinux-y := -Bstatic LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) := -pie LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y) -LDFLAGS_vmlinux += $(call ld-option,--orphan-handling=warn) ifdef CONFIG_PPC64 ifeq ($(call cc-option-yn,-mcmodel=medium),y) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f6946b81f74a..fbf26e0f7a6a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -100,6 +100,7 @@ config X86 select ARCH_WANT_DEFAULT_BPF_JIT if X86_64 select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANT_HUGE_PMD_SHARE + select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANTS_THP_SWAP if X86_64 select BUILDTIME_TABLE_SORT select CLKEVT_I8253 diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 154259f18b8b..1bf21746f4ce 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -209,9 +209,6 @@ ifdef CONFIG_X86_64 LDFLAGS_vmlinux += -z max-page-size=0x200000 endif -# We never want expected sections to be placed heuristically by the -# linker. All sections should be explicitly named in the linker script. -LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn) archscripts: scripts_basic $(Q)$(MAKE) $(build)=arch/x86/tools relocs diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index ee249088cbfe..40b8fd375d52 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -61,7 +61,9 @@ KBUILD_LDFLAGS += $(call ld-option,--no-ld-generated-unwind-info) # Compressed kernel should be built as PIE since it may be loaded at any # address by the bootloader. LDFLAGS_vmlinux := -pie $(call ld-option, --no-dynamic-linker) -LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn) +ifdef CONFIG_LD_ORPHAN_WARN +LDFLAGS_vmlinux += --orphan-handling=warn +endif LDFLAGS_vmlinux += -T hostprogs := mkpiggy diff --git a/init/Kconfig b/init/Kconfig index c9446911cf41..92c58b45abb8 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1348,6 +1348,11 @@ config LD_DEAD_CODE_DATA_ELIMINATION present. This option is not well tested yet, so use at your own risk. +config LD_ORPHAN_WARN + def_bool y + depends on ARCH_WANT_LD_ORPHAN_WARN + depends on $(ld-option,--orphan-handling=warn) + config SYSCTL bool -- cgit v1.2.3 From d5750cd3c5486e9c0fa11100df01de8ca0c13fa7 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 19 Nov 2020 13:46:58 -0700 Subject: kbuild: Disable CONFIG_LD_ORPHAN_WARN for ld.lld 10.0.1 ld.lld 10.0.1 spews a bunch of various warnings about .rela sections, along with a few others. Newer versions of ld.lld do not have these warnings. As a result, do not add '--orphan-handling=warn' to LDFLAGS_vmlinux if ld.lld's version is not new enough. Link: https://github.com/ClangBuiltLinux/linux/issues/1187 Link: https://github.com/ClangBuiltLinux/linux/issues/1193 Reported-by: Arvind Sankar Reported-by: kernelci.org bot Reported-by: Mark Brown Reviewed-by: Kees Cook Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Signed-off-by: Masahiro Yamada --- MAINTAINERS | 1 + init/Kconfig | 5 +++++ scripts/lld-version.sh | 20 ++++++++++++++++++++ 3 files changed, 26 insertions(+) create mode 100755 scripts/lld-version.sh diff --git a/MAINTAINERS b/MAINTAINERS index a008b70f3c16..286ed8e6b924 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4274,6 +4274,7 @@ B: https://github.com/ClangBuiltLinux/linux/issues C: irc://chat.freenode.net/clangbuiltlinux F: Documentation/kbuild/llvm.rst F: scripts/clang-tools/ +F: scripts/lld-version.sh K: \b(?i:clang|llvm)\b CLEANCACHE API diff --git a/init/Kconfig b/init/Kconfig index 92c58b45abb8..b9037d6c5ab3 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -47,6 +47,10 @@ config CLANG_VERSION int default $(shell,$(srctree)/scripts/clang-version.sh $(CC)) +config LLD_VERSION + int + default $(shell,$(srctree)/scripts/lld-version.sh $(LD)) + config CC_CAN_LINK bool default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(m64-flag)) if 64BIT @@ -1351,6 +1355,7 @@ config LD_DEAD_CODE_DATA_ELIMINATION config LD_ORPHAN_WARN def_bool y depends on ARCH_WANT_LD_ORPHAN_WARN + depends on !LD_IS_LLD || LLD_VERSION >= 110000 depends on $(ld-option,--orphan-handling=warn) config SYSCTL diff --git a/scripts/lld-version.sh b/scripts/lld-version.sh new file mode 100755 index 000000000000..d70edb4d8a4f --- /dev/null +++ b/scripts/lld-version.sh @@ -0,0 +1,20 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Usage: $ ./scripts/lld-version.sh ld.lld +# +# Print the linker version of `ld.lld' in a 5 or 6-digit form +# such as `100001' for ld.lld 10.0.1 etc. + +linker_string="$($* --version)" + +if ! ( echo $linker_string | grep -q LLD ); then + echo 0 + exit 1 +fi + +VERSION=$(echo $linker_string | cut -d ' ' -f 2) +MAJOR=$(echo $VERSION | cut -d . -f 1) +MINOR=$(echo $VERSION | cut -d . -f 2) +PATCHLEVEL=$(echo $VERSION | cut -d . -f 3) +printf "%d%02d%02d\\n" $MAJOR $MINOR $PATCHLEVEL -- cgit v1.2.3 From d904eb0b351fe5545d9ba5b85844342f49025923 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Sun, 29 Nov 2020 18:01:26 +0100 Subject: media: mtk-cir: fix calculation of chk period Since commit 528222d853f9 ("media: rc: harmonize infrared durations to microseconds"), the calculation of the chk period is wrong. As a result, all reported IR will have incorrect timings. Now that the calculations are done in microseconds rather than nanoseconds, we can fold the calculations in a simpler form with less rounding error. Tested-by: Frank Wunderlich Fixes: 528222d853f9 ("media: rc: harmonize infrared durations to microseconds") Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- drivers/media/rc/mtk-cir.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/media/rc/mtk-cir.c b/drivers/media/rc/mtk-cir.c index 5051a5e5244b..65a136c0fac2 100644 --- a/drivers/media/rc/mtk-cir.c +++ b/drivers/media/rc/mtk-cir.c @@ -151,15 +151,12 @@ static inline u32 mtk_chk_period(struct mtk_ir *ir) { u32 val; - /* Period of raw software sampling in ns */ - val = DIV_ROUND_CLOSEST(1000000000ul, - clk_get_rate(ir->bus) / ir->data->div); - /* * Period for software decoder used in the * unit of raw software sampling */ - val = DIV_ROUND_CLOSEST(MTK_IR_SAMPLE, val); + val = DIV_ROUND_CLOSEST(clk_get_rate(ir->bus), + USEC_PER_SEC * ir->data->div / MTK_IR_SAMPLE); dev_dbg(ir->dev, "@pwm clk = \t%lu\n", clk_get_rate(ir->bus) / ir->data->div); @@ -412,7 +409,7 @@ static int mtk_ir_probe(struct platform_device *pdev) mtk_irq_enable(ir, MTK_IRINT_EN); dev_info(dev, "Initialized MT7623 IR driver, sample period = %dus\n", - DIV_ROUND_CLOSEST(MTK_IR_SAMPLE, 1000)); + MTK_IR_SAMPLE); return 0; -- cgit v1.2.3 From 024e01dead12c2b9fbe31216f2099401ebb78a4a Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 27 Nov 2020 10:36:32 +0100 Subject: media: pulse8-cec: fix duplicate free at disconnect or probe error Commit 601282d65b96 ("media: pulse8-cec: use adap_free callback") used the adap_free callback to clean up on disconnect. What I forgot was that in the probe it will call cec_delete_adapter() followed by kfree(pulse8) if an error occurs. But by using the adap_free callback, cec_delete_adapter() is already freeing the pulse8 struct. This wasn't noticed since normally the probe works fine, but Pulse-Eight published a new firmware version that caused a probe error, so now it hits this bug. This affects firmware version 12, but probably any version >= 10. Commit aa9eda76129c ("media: pulse8-cec: close serio in disconnect, not adap_free") made this worse by adding the line 'pulse8->serio = NULL' right after the call to cec_unregister_adapter in the disconnect() function. Unfortunately, cec_unregister_adapter will typically call cec_delete_adapter (unless a filehandle to the cec device is still open), which frees the pulse8 struct. So now it will also crash on a simple unplug of the Pulse-Eight device. With this fix both the unplug issue and a probe() error situation are handled correctly again. It will still fail to probe() with a v12 firmware, that's something to look at separately. Signed-off-by: Hans Verkuil Reported-by: Maxime Ripard Tested-by: Maxime Ripard Fixes: aa9eda76129c ("media: pulse8-cec: close serio in disconnect, not adap_free") Fixes: 601282d65b96 ("media: pulse8-cec: use adap_free callback") Cc: Signed-off-by: Mauro Carvalho Chehab --- drivers/media/cec/usb/pulse8/pulse8-cec.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/media/cec/usb/pulse8/pulse8-cec.c b/drivers/media/cec/usb/pulse8/pulse8-cec.c index e4d8446b87da..5d3a3f775bc8 100644 --- a/drivers/media/cec/usb/pulse8/pulse8-cec.c +++ b/drivers/media/cec/usb/pulse8/pulse8-cec.c @@ -650,7 +650,6 @@ static void pulse8_disconnect(struct serio *serio) struct pulse8 *pulse8 = serio_get_drvdata(serio); cec_unregister_adapter(pulse8->adap); - pulse8->serio = NULL; serio_set_drvdata(serio, NULL); serio_close(serio); } @@ -830,8 +829,10 @@ static int pulse8_connect(struct serio *serio, struct serio_driver *drv) pulse8->adap = cec_allocate_adapter(&pulse8_cec_adap_ops, pulse8, dev_name(&serio->dev), caps, 1); err = PTR_ERR_OR_ZERO(pulse8->adap); - if (err < 0) - goto free_device; + if (err < 0) { + kfree(pulse8); + return err; + } pulse8->dev = &serio->dev; serio_set_drvdata(serio, pulse8); @@ -874,8 +875,6 @@ close_serio: serio_close(serio); delete_adap: cec_delete_adapter(pulse8->adap); -free_device: - kfree(pulse8); return err; } -- cgit v1.2.3 From 45ba1c0ba3e589ad3ef0d0603c822eb27ea16563 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 27 Nov 2020 12:52:30 +0100 Subject: media: pulse8-cec: add support for FW v10 and up Starting with firmware version 10 the GET/SET_HDMI_VERSION message was removed and GET/SET_AUTO_POWER_ON was added. The removal of GET/SET_HDMI_VERSION caused the probe of the Pulse-Eight to fail. Add a version check to handle this gracefully. Also show (but do not set) the Auto Power On value. Signed-off-by: Hans Verkuil Reported-by: Maxime Ripard Tested-by: Maxime Ripard Cc: Signed-off-by: Mauro Carvalho Chehab --- drivers/media/cec/usb/pulse8/pulse8-cec.c | 43 +++++++++++++++++++++---------- 1 file changed, 30 insertions(+), 13 deletions(-) diff --git a/drivers/media/cec/usb/pulse8/pulse8-cec.c b/drivers/media/cec/usb/pulse8/pulse8-cec.c index 5d3a3f775bc8..04b13cdc38d2 100644 --- a/drivers/media/cec/usb/pulse8/pulse8-cec.c +++ b/drivers/media/cec/usb/pulse8/pulse8-cec.c @@ -88,13 +88,15 @@ enum pulse8_msgcodes { MSGCODE_SET_PHYSICAL_ADDRESS, /* 0x20 */ MSGCODE_GET_DEVICE_TYPE, MSGCODE_SET_DEVICE_TYPE, - MSGCODE_GET_HDMI_VERSION, + MSGCODE_GET_HDMI_VERSION, /* Removed in FW >= 10 */ MSGCODE_SET_HDMI_VERSION, MSGCODE_GET_OSD_NAME, MSGCODE_SET_OSD_NAME, MSGCODE_WRITE_EEPROM, MSGCODE_GET_ADAPTER_TYPE, /* 0x28 */ MSGCODE_SET_ACTIVE_SOURCE, + MSGCODE_GET_AUTO_POWER_ON, /* New for FW >= 10 */ + MSGCODE_SET_AUTO_POWER_ON, MSGCODE_FRAME_EOM = 0x80, MSGCODE_FRAME_ACK = 0x40, @@ -143,6 +145,8 @@ static const char * const pulse8_msgnames[] = { "WRITE_EEPROM", "GET_ADAPTER_TYPE", "SET_ACTIVE_SOURCE", + "GET_AUTO_POWER_ON", + "SET_AUTO_POWER_ON", }; static const char *pulse8_msgname(u8 cmd) @@ -579,12 +583,14 @@ static int pulse8_cec_adap_log_addr(struct cec_adapter *adap, u8 log_addr) if (err) goto unlock; - cmd[0] = MSGCODE_SET_HDMI_VERSION; - cmd[1] = adap->log_addrs.cec_version; - err = pulse8_send_and_wait(pulse8, cmd, 2, - MSGCODE_COMMAND_ACCEPTED, 0); - if (err) - goto unlock; + if (pulse8->vers < 10) { + cmd[0] = MSGCODE_SET_HDMI_VERSION; + cmd[1] = adap->log_addrs.cec_version; + err = pulse8_send_and_wait(pulse8, cmd, 2, + MSGCODE_COMMAND_ACCEPTED, 0); + if (err) + goto unlock; + } if (adap->log_addrs.osd_name[0]) { size_t osd_len = strlen(adap->log_addrs.osd_name); @@ -691,6 +697,14 @@ static int pulse8_setup(struct pulse8 *pulse8, struct serio *serio, dev_dbg(pulse8->dev, "Autonomous mode: %s", data[0] ? "on" : "off"); + if (pulse8->vers >= 10) { + cmd[0] = MSGCODE_GET_AUTO_POWER_ON; + err = pulse8_send_and_wait(pulse8, cmd, 1, cmd[0], 1); + if (!err) + dev_dbg(pulse8->dev, "Auto Power On: %s", + data[0] ? "on" : "off"); + } + cmd[0] = MSGCODE_GET_DEVICE_TYPE; err = pulse8_send_and_wait(pulse8, cmd, 1, cmd[0], 1); if (err) @@ -752,12 +766,15 @@ static int pulse8_setup(struct pulse8 *pulse8, struct serio *serio, dev_dbg(pulse8->dev, "Physical address: %x.%x.%x.%x\n", cec_phys_addr_exp(*pa)); - cmd[0] = MSGCODE_GET_HDMI_VERSION; - err = pulse8_send_and_wait(pulse8, cmd, 1, cmd[0], 1); - if (err) - return err; - log_addrs->cec_version = data[0]; - dev_dbg(pulse8->dev, "CEC version: %d\n", log_addrs->cec_version); + log_addrs->cec_version = CEC_OP_CEC_VERSION_1_4; + if (pulse8->vers < 10) { + cmd[0] = MSGCODE_GET_HDMI_VERSION; + err = pulse8_send_and_wait(pulse8, cmd, 1, cmd[0], 1); + if (err) + return err; + log_addrs->cec_version = data[0]; + dev_dbg(pulse8->dev, "CEC version: %d\n", log_addrs->cec_version); + } cmd[0] = MSGCODE_GET_OSD_NAME; err = pulse8_send_and_wait(pulse8, cmd, 1, cmd[0], 0); -- cgit v1.2.3 From fae3a13d2a3d49a89391889808428cf1e72afbd7 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Mon, 30 Nov 2020 09:57:20 -0600 Subject: x86/resctrl: Fix AMD L3 QOS CDP enable/disable When the AMD QoS feature CDP (code and data prioritization) is enabled or disabled, the CDP bit in MSR 0000_0C81 is written on one of the CPUs in an L3 domain (core complex). That is not correct - the CDP bit needs to be updated on all the logical CPUs in the domain. This was not spelled out clearly in the spec earlier. The specification has been updated and the updated document, "AMD64 Technology Platform Quality of Service Extensions Publication # 56375 Revision: 1.02 Issue Date: October 2020" is available now. Refer the section: Code and Data Prioritization. Fix the issue by adding a new flag arch_has_per_cpu_cfg in rdt_cache data structure. The documentation can be obtained at: https://developer.amd.com/wp-content/resources/56375.pdf Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 [ bp: Massage commit message. ] Fixes: 4d05bf71f157 ("x86/resctrl: Introduce AMD QOS feature") Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov Reviewed-by: Reinette Chatre Link: https://lkml.kernel.org/r/160675180380.15628.3309402017215002347.stgit@bmoger-ubuntu --- arch/x86/kernel/cpu/resctrl/core.c | 4 ++++ arch/x86/kernel/cpu/resctrl/internal.h | 3 +++ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 9 +++++++-- 3 files changed, 14 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index e5f4ee8f4c3b..e8b5f1cf1ae8 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -570,6 +570,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) if (d) { cpumask_set_cpu(cpu, &d->cpu_mask); + if (r->cache.arch_has_per_cpu_cfg) + rdt_domain_reconfigure_cdp(r); return; } @@ -923,6 +925,7 @@ static __init void rdt_init_res_defs_intel(void) r->rid == RDT_RESOURCE_L2CODE) { r->cache.arch_has_sparse_bitmaps = false; r->cache.arch_has_empty_bitmaps = false; + r->cache.arch_has_per_cpu_cfg = false; } else if (r->rid == RDT_RESOURCE_MBA) { r->msr_base = MSR_IA32_MBA_THRTL_BASE; r->msr_update = mba_wrmsr_intel; @@ -943,6 +946,7 @@ static __init void rdt_init_res_defs_amd(void) r->rid == RDT_RESOURCE_L2CODE) { r->cache.arch_has_sparse_bitmaps = true; r->cache.arch_has_empty_bitmaps = true; + r->cache.arch_has_per_cpu_cfg = true; } else if (r->rid == RDT_RESOURCE_MBA) { r->msr_base = MSR_IA32_MBA_BW_BASE; r->msr_update = mba_wrmsr_amd; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 80fa997fae60..f65d3c0dbc41 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -360,6 +360,8 @@ struct msr_param { * executing entities * @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid. * @arch_has_empty_bitmaps: True if the '0' bitmap is valid. + * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache + * level has CPU scope. */ struct rdt_cache { unsigned int cbm_len; @@ -369,6 +371,7 @@ struct rdt_cache { unsigned int shareable_bits; bool arch_has_sparse_bitmaps; bool arch_has_empty_bitmaps; + bool arch_has_per_cpu_cfg; }; /** diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 6f4ca4bea625..f3418428682b 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1909,8 +1909,13 @@ static int set_cache_qos_cfg(int level, bool enable) r_l = &rdt_resources_all[level]; list_for_each_entry(d, &r_l->domains, list) { - /* Pick one CPU from each domain instance to update MSR */ - cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + if (r_l->cache.arch_has_per_cpu_cfg) + /* Pick all the CPUs in the domain instance */ + for_each_cpu(cpu, &d->cpu_mask) + cpumask_set_cpu(cpu, cpu_mask); + else + /* Pick one CPU from each domain instance to update MSR */ + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); } cpu = get_cpu(); /* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */ -- cgit v1.2.3 From cf03f316ad20dac16b5adae3f6dedd7d188c7f65 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Tue, 1 Dec 2020 14:54:09 +0100 Subject: fs: 9p: add generic splice_read file operations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The v9fs file operations were missing the splice_read operations, which breaks sendfile() of files on such a filesystem. I discovered this while trying to load an eBPF program using iproute2 inside a 'virtme' environment which uses 9pfs for the virtual file system. iproute2 relies on sendfile() with an AF_ALG socket to hash files, which was erroring out in the virtual environment. Since generic_file_splice_read() seems to just implement splice_read in terms of the read_iter operation, I simply added the generic implementation to the file operations, which fixed the error I was seeing. A quick grep indicates that this is what most other file systems do as well. Link: http://lkml.kernel.org/r/20201201135409.55510-1-toke@redhat.com Fixes: 36e2c7421f02 ("fs: don't allow splice read/write without explicit ops") Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Dominique Martinet --- fs/9p/vfs_file.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index b177fd3b1eb3..01026b47018c 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -655,6 +655,7 @@ const struct file_operations v9fs_cached_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = v9fs_file_mmap, + .splice_read = generic_file_splice_read, .fsync = v9fs_file_fsync, }; @@ -667,6 +668,7 @@ const struct file_operations v9fs_cached_file_operations_dotl = { .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, .mmap = v9fs_file_mmap, + .splice_read = generic_file_splice_read, .fsync = v9fs_file_fsync_dotl, }; @@ -678,6 +680,7 @@ const struct file_operations v9fs_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = generic_file_readonly_mmap, + .splice_read = generic_file_splice_read, .fsync = v9fs_file_fsync, }; @@ -690,6 +693,7 @@ const struct file_operations v9fs_file_operations_dotl = { .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, .mmap = generic_file_readonly_mmap, + .splice_read = generic_file_splice_read, .fsync = v9fs_file_fsync_dotl, }; @@ -701,6 +705,7 @@ const struct file_operations v9fs_mmap_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = v9fs_mmap_file_mmap, + .splice_read = generic_file_splice_read, .fsync = v9fs_file_fsync, }; @@ -713,5 +718,6 @@ const struct file_operations v9fs_mmap_file_operations_dotl = { .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, .mmap = v9fs_mmap_file_mmap, + .splice_read = generic_file_splice_read, .fsync = v9fs_file_fsync_dotl, }; -- cgit v1.2.3 From 1a16af33ba88ef25e206a13366379179cae79d23 Mon Sep 17 00:00:00 2001 From: David Gow Date: Sat, 21 Nov 2020 16:15:49 -0800 Subject: fpga: Specify HAS_IOMEM dependency for FPGA_DFL Because dfl.c uses the 'devm_ioremap', 'devm_iounmap', 'devm_ioremap_resource', and 'devm_platform_ioremap_resource' functions, it should depend on HAS_IOMEM. This fixes make allyesconfig under UML (ARCH=um), which doesn't provide HAS_IOMEM. [mdf@kernel.org: Removed "drivers: " in commit message] Fixes: 89eb35e810a8 ("fpga: dfl: map feature mmio resources in their own feature drivers") Signed-off-by: David Gow Signed-off-by: Moritz Fischer Link: https://lore.kernel.org/r/20201122001549.107023-2-mdf@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/fpga/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig index 7cd5a29fc437..5645226ca3ce 100644 --- a/drivers/fpga/Kconfig +++ b/drivers/fpga/Kconfig @@ -142,6 +142,7 @@ config FPGA_DFL tristate "FPGA Device Feature List (DFL) support" select FPGA_BRIDGE select FPGA_REGION + depends on HAS_IOMEM help Device Feature List (DFL) defines a feature list structure that creates a linked list of feature headers within the MMIO space -- cgit v1.2.3 From 8c3b55a299c325830a987de21dab6a89ecb71164 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 1 Dec 2020 09:55:29 -0800 Subject: Input: atmel_mxt_ts - fix lost interrupts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After commit 74d905d2d38a devices requiring the workaround for edge triggered interrupts stopped working. The hardware needs the quirk to be used before even proceeding to check if the quirk is needed because mxt_acquire_irq() is called before mxt_check_retrigen() is called and at this point pending IRQs need to be checked, and if the workaround is not active, all interrupts will be lost from this point. Solve this by switching the calls around. Reported-by: Andre Müller Tested-by: Andre Müller Suggested-by: Dmitry Torokhov Fixes: 74d905d2d38a ("Input: atmel_mxt_ts - only read messages in mxt_acquire_irq() when necessary") Signed-off-by: Linus Walleij Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20201201123026.1416743-1-linus.walleij@linaro.org Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/atmel_mxt_ts.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index 6b71b0aff115..99a33cd5e675 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -2183,11 +2183,11 @@ static int mxt_initialize(struct mxt_data *data) msleep(MXT_FW_RESET_TIME); } - error = mxt_acquire_irq(data); + error = mxt_check_retrigen(data); if (error) return error; - error = mxt_check_retrigen(data); + error = mxt_acquire_irq(data); if (error) return error; -- cgit v1.2.3 From 7e7986f9d3ba69a7375a41080a1f8c8012cb0923 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 1 Dec 2020 11:07:09 -0500 Subject: block: use gcd() to fix chunk_sectors limit stacking commit 22ada802ede8 ("block: use lcm_not_zero() when stacking chunk_sectors") broke chunk_sectors limit stacking. chunk_sectors must reflect the most limited of all devices in the IO stack. Otherwise malformed IO may result. E.g.: prior to this fix, ->chunk_sectors = lcm_not_zero(8, 128) would result in blk_max_size_offset() splitting IO at 128 sectors rather than the required more restrictive 8 sectors. And since commit 07d098e6bbad ("block: allow 'chunk_sectors' to be non-power-of-2") care must be taken to properly stack chunk_sectors to be compatible with the possibility that a non-power-of-2 chunk_sectors may be stacked. This is why gcd() is used instead of reverting back to using min_not_zero(). Fixes: 22ada802ede8 ("block: use lcm_not_zero() when stacking chunk_sectors") Fixes: 07d098e6bbad ("block: allow 'chunk_sectors' to be non-power-of-2") Reported-by: John Dorminy Reported-by: Bruce Johnston Signed-off-by: Mike Snitzer Reviewed-by: John Dorminy Cc: stable@vger.kernel.org Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/blk-settings.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/block/blk-settings.c b/block/blk-settings.c index 9741d1d83e98..659cdb8a07fe 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -547,7 +547,10 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->io_min = max(t->io_min, b->io_min); t->io_opt = lcm_not_zero(t->io_opt, b->io_opt); - t->chunk_sectors = lcm_not_zero(t->chunk_sectors, b->chunk_sectors); + + /* Set non-power-of-2 compatible chunk_sectors boundary */ + if (b->chunk_sectors) + t->chunk_sectors = gcd(t->chunk_sectors, b->chunk_sectors); /* Physical block size a multiple of the logical block size? */ if (t->physical_block_size & (t->logical_block_size - 1)) { -- cgit v1.2.3 From b71ec952234610b4f90ef17a2fdcb124d5320070 Mon Sep 17 00:00:00 2001 From: Thomas Falcon Date: Tue, 1 Dec 2020 09:52:10 -0600 Subject: ibmvnic: Ensure that SCRQ entry reads are correctly ordered Ensure that received Subordinate Command-Response Queue (SCRQ) entries are properly read in order by the driver. These queues are used in the ibmvnic device to process RX buffer and TX completion descriptors. dma_rmb barriers have been added after checking for a pending descriptor to ensure the correct descriptor entry is checked and after reading the SCRQ descriptor to ensure the entire descriptor is read before processing. Fixes: 032c5e82847a ("Driver for IBM System i/p VNIC protocol") Signed-off-by: Thomas Falcon Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index bca1becd33f0..0e34c36c3e86 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2404,6 +2404,12 @@ restart_poll: if (!pending_scrq(adapter, adapter->rx_scrq[scrq_num])) break; + /* The queue entry at the current index is peeked at above + * to determine that there is a valid descriptor awaiting + * processing. We want to be sure that the current slot + * holds a valid descriptor before reading its contents. + */ + dma_rmb(); next = ibmvnic_next_scrq(adapter, adapter->rx_scrq[scrq_num]); rx_buff = (struct ibmvnic_rx_buff *)be64_to_cpu(next-> @@ -3113,6 +3119,13 @@ restart_loop: unsigned int pool = scrq->pool_index; int num_entries = 0; + /* The queue entry at the current index is peeked at above + * to determine that there is a valid descriptor awaiting + * processing. We want to be sure that the current slot + * holds a valid descriptor before reading its contents. + */ + dma_rmb(); + next = ibmvnic_next_scrq(adapter, scrq); for (i = 0; i < next->tx_comp.num_comps; i++) { if (next->tx_comp.rcs[i]) { @@ -3513,6 +3526,11 @@ static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *adapter, } spin_unlock_irqrestore(&scrq->lock, flags); + /* Ensure that the entire buffer descriptor has been + * loaded before reading its contents + */ + dma_rmb(); + return entry; } -- cgit v1.2.3 From ba246c175116e2e8fa4fdfa5f8e958e086a9a818 Mon Sep 17 00:00:00 2001 From: Thomas Falcon Date: Tue, 1 Dec 2020 09:52:11 -0600 Subject: ibmvnic: Fix TX completion error handling TX completions received with an error return code are not being processed properly. When an error code is seen, do not proceed to the next completion before cleaning up the existing entry's data structures. Fixes: 032c5e82847a ("Driver for IBM System i/p VNIC protocol") Signed-off-by: Thomas Falcon Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 0e34c36c3e86..da9450f18717 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3128,11 +3128,9 @@ restart_loop: next = ibmvnic_next_scrq(adapter, scrq); for (i = 0; i < next->tx_comp.num_comps; i++) { - if (next->tx_comp.rcs[i]) { + if (next->tx_comp.rcs[i]) dev_err(dev, "tx error %x\n", next->tx_comp.rcs[i]); - continue; - } index = be32_to_cpu(next->tx_comp.correlators[i]); if (index & IBMVNIC_TSO_POOL_MASK) { tx_pool = &adapter->tso_pool[pool]; -- cgit v1.2.3 From 14483cbf040fcb38113497161088a1ce8ce5d713 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 28 Nov 2020 23:08:43 -0800 Subject: net: broadcom CNIC: requires MMU The CNIC kconfig symbol selects UIO and UIO depends on MMU. Since 'select' does not follow dependency chains, add the same MMU dependency to CNIC. Quietens this kconfig warning: WARNING: unmet direct dependencies detected for UIO Depends on [n]: MMU [=n] Selected by [m]: - CNIC [=m] && NETDEVICES [=y] && ETHERNET [=y] && NET_VENDOR_BROADCOM [=y] && PCI [=y] && (IPV6 [=m] || IPV6 [=m]=n) Fixes: adfc5217e9db ("broadcom: Move the Broadcom drivers") Signed-off-by: Randy Dunlap Cc: Jeff Kirsher Cc: Rasesh Mody Cc: GR-Linux-NIC-Dev@marvell.com Cc: "David S. Miller" Cc: Jakub Kicinski Cc: netdev@vger.kernel.org Link: https://lore.kernel.org/r/20201129070843.3859-1-rdunlap@infradead.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 7fb42f388d59..7b79528d6eed 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -88,6 +88,7 @@ config BNX2 config CNIC tristate "QLogic CNIC support" depends on PCI && (IPV6 || IPV6=n) + depends on MMU select BNX2 select UIO help -- cgit v1.2.3 From 960f4f8a4e60da610af73c1264673f71f5a36efd Mon Sep 17 00:00:00 2001 From: Dominique Martinet Date: Tue, 1 Dec 2020 16:09:37 +0100 Subject: fs: 9p: add generic splice_write file operation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The default splice operations got removed recently, add it back to 9p with iter_file_splice_write like many other filesystems do. Link: http://lkml.kernel.org/r/1606837496-21717-1-git-send-email-asmadeus@codewreck.org Fixes: 36e2c7421f02 ("fs: don't allow splice read/write without explicit ops") Signed-off-by: Dominique Martinet Acked-by: Toke Høiland-Jørgensen Reviewed-by: Christoph Hellwig --- fs/9p/vfs_file.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 01026b47018c..be5768949cb1 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -656,6 +656,7 @@ const struct file_operations v9fs_cached_file_operations = { .lock = v9fs_file_lock, .mmap = v9fs_file_mmap, .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, }; @@ -669,6 +670,7 @@ const struct file_operations v9fs_cached_file_operations_dotl = { .flock = v9fs_file_flock_dotl, .mmap = v9fs_file_mmap, .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, }; @@ -681,6 +683,7 @@ const struct file_operations v9fs_file_operations = { .lock = v9fs_file_lock, .mmap = generic_file_readonly_mmap, .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, }; @@ -694,6 +697,7 @@ const struct file_operations v9fs_file_operations_dotl = { .flock = v9fs_file_flock_dotl, .mmap = generic_file_readonly_mmap, .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, }; @@ -706,6 +710,7 @@ const struct file_operations v9fs_mmap_file_operations = { .lock = v9fs_file_lock, .mmap = v9fs_mmap_file_mmap, .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, }; @@ -719,5 +724,6 @@ const struct file_operations v9fs_mmap_file_operations_dotl = { .flock = v9fs_file_flock_dotl, .mmap = v9fs_mmap_file_mmap, .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, }; -- cgit v1.2.3 From 35d2835d2ac41dc0b3e3469f8e2b08ce9709ace8 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Tue, 10 Nov 2020 18:41:40 -0800 Subject: Revert "dm cache: fix arm link errors with inline" This reverts commit 43aeaa29573924df76f44eda2bbd94ca36e407b5. Since commit 0bddd227f3dc ("Documentation: update for gcc 4.9 requirement") the minimum supported version of GCC is gcc-4.9. It's now safe to remove this code. Link: https://github.com/ClangBuiltLinux/linux/issues/427 Signed-off-by: Nick Desaulniers Acked-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- drivers/md/dm-cache-target.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 9644424591da..4bc453f5bbaa 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -712,10 +712,6 @@ static bool block_size_is_power_of_two(struct cache *cache) return cache->sectors_per_block_shift >= 0; } -/* gcc on ARM generates spurious references to __udivdi3 and __umoddi3 */ -#if defined(CONFIG_ARM) && __GNUC__ == 4 && __GNUC_MINOR__ <= 6 -__always_inline -#endif static dm_block_t block_div(dm_block_t b, uint32_t n) { do_div(b, n); -- cgit v1.2.3 From 89478335718c98557f10470a9bc5c555b9261c4e Mon Sep 17 00:00:00 2001 From: Sergei Shtepa Date: Wed, 11 Nov 2020 15:55:46 +0300 Subject: dm: fix bug with RCU locking in dm_blk_report_zones The dm_get_live_table() function makes RCU read lock so dm_put_live_table() must be called even if dm_table map is not found. Fixes: e76239a3748c9 ("block: add a report_zones method") Cc: stable@vger.kernel.org Signed-off-by: Sergei Shtepa Signed-off-by: Mike Snitzer --- drivers/md/dm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c18fc2548518..98866e725f25 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -476,8 +476,10 @@ static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, return -EAGAIN; map = dm_get_live_table(md, &srcu_idx); - if (!map) - return -EIO; + if (!map) { + ret = -EIO; + goto out; + } do { struct dm_target *tgt; -- cgit v1.2.3 From e7b624183d921b49ef0a96329f21647d38865ee9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 13 Nov 2020 15:19:10 +0100 Subject: dm table: Remove BUG_ON(in_interrupt()) The BUG_ON(in_interrupt()) in dm_table_event() is a historic leftover from a rework of the dm table code which changed the calling context. Issuing a BUG for a wrong calling context is frowned upon and in_interrupt() is deprecated and only covering parts of the wrong contexts. The sanity check for the context is covered by CONFIG_DEBUG_ATOMIC_SLEEP and other debug facilities already. Signed-off-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Mike Snitzer --- drivers/md/dm-table.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index ce543b761be7..2073ee8d18f4 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1247,12 +1247,6 @@ void dm_table_event_callback(struct dm_table *t, void dm_table_event(struct dm_table *t) { - /* - * You can no longer call dm_table_event() from interrupt - * context, use a bottom half instead. - */ - BUG_ON(in_interrupt()); - mutex_lock(&_event_lock); if (t->event_fn) t->event_fn(t->event_context); -- cgit v1.2.3 From 857c4c0a8b2888d806f4308c58f59a6a81a1dee9 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 13 Nov 2020 14:52:28 -0800 Subject: dm writecache: remove BUG() and fail gracefully instead Building on arch/s390/ results in this build error: cc1: some warnings being treated as errors ../drivers/md/dm-writecache.c: In function 'persistent_memory_claim': ../drivers/md/dm-writecache.c:323:1: error: no return statement in function returning non-void [-Werror=return-type] Fix this by replacing the BUG() with an -EOPNOTSUPP return. Fixes: 48debafe4f2f ("dm: add writecache target") Reported-by: Randy Dunlap Signed-off-by: Mike Snitzer --- drivers/md/dm-writecache.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 7d277de26b3a..d5223a0e5cc5 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -319,7 +319,7 @@ err1: #else static int persistent_memory_claim(struct dm_writecache *wc) { - BUG(); + return -EOPNOTSUPP; } #endif -- cgit v1.2.3 From 0643334902fcdc770e2d9555811200213339a3f6 Mon Sep 17 00:00:00 2001 From: Hoang Le Date: Mon, 30 Nov 2020 09:55:44 +0700 Subject: tipc: fix incompatible mtu of transmission In commit 682cd3cf946b6 ("tipc: confgiure and apply UDP bearer MTU on running links"), we introduced a function to change UDP bearer MTU and applied this new value across existing per-link. However, we did not apply this new MTU value at node level. This lead to packet dropped at link level if its size is greater than new MTU value. To fix this issue, we also apply this new MTU value for node level. Fixes: 682cd3cf946b6 ("tipc: confgiure and apply UDP bearer MTU on running links") Acked-by: Jon Maloy Signed-off-by: Hoang Le Link: https://lore.kernel.org/r/20201130025544.3602-1-hoang.h.le@dektech.com.au Signed-off-by: Jakub Kicinski --- net/tipc/node.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/tipc/node.c b/net/tipc/node.c index d269ebe382e1..c95d037fde51 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2182,6 +2182,8 @@ void tipc_node_apply_property(struct net *net, struct tipc_bearer *b, else if (prop == TIPC_NLA_PROP_MTU) tipc_link_set_mtu(e->link, b->mtu); } + /* Update MTU for node link entry */ + e->mtu = tipc_link_mss(e->link); tipc_node_write_unlock(n); tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr, NULL); } -- cgit v1.2.3 From 0191c271debfc3d171e8b2d81875d7036982d02c Mon Sep 17 00:00:00 2001 From: Alok Prasad Date: Fri, 27 Nov 2020 16:32:51 +0000 Subject: RDMA/qedr: iWARP invalid(zero) doorbell address fix This patch fixes issue introduced by a previous commit where iWARP doorbell address wasn't initialized, causing call trace when any RDMA application wants to use this interface: Illegal doorbell address: 0000000000000000. Legal range for doorbell addresses is [0000000011431e08..00000000ec3799d3] WARNING: CPU: 11 PID: 11990 at drivers/net/ethernet/qlogic/qed/qed_dev.c:93 qed_db_rec_sanity.isra.12+0x48/0x70 [qed] ... hpsa scsi_transport_sas [last unloaded: crc8] CPU: 11 PID: 11990 Comm: rping Tainted: G S 5.10.0-rc1 #29 Hardware name: HP ProLiant DL380 Gen9/ProLiant DL380 Gen9, BIOS P89 01/22/2018 RIP: 0010:qed_db_rec_sanity.isra.12+0x48/0x70 [qed] ... RSP: 0018:ffffafc28458fa88 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff8d0d4c620000 RCX: 0000000000000000 RDX: ffff8d10afde7d50 RSI: ffff8d10afdd8b40 RDI: ffff8d10afdd8b40 RBP: ffffafc28458fe38 R08: 0000000000000003 R09: 0000000000007fff R10: 0000000000000001 R11: ffffafc28458f888 R12: 0000000000000000 R13: 0000000000000000 R14: ffff8d0d43ccbbd0 R15: ffff8d0d48dae9c0 FS: 00007fbd5267e740(0000) GS:ffff8d10afdc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fbd4f258fb8 CR3: 0000000108d96003 CR4: 00000000001706e0 Call Trace: qed_db_recovery_add+0x6d/0x1f0 [qed] qedr_create_user_qp+0x57e/0xd30 [qedr] qedr_create_qp+0x5f3/0xab0 [qedr] ? lookup_get_idr_uobject.part.12+0x45/0x90 [ib_uverbs] create_qp+0x45d/0xb30 [ib_uverbs] ? ib_uverbs_cq_event_handler+0x30/0x30 [ib_uverbs] ib_uverbs_create_qp+0xb9/0xe0 [ib_uverbs] ib_uverbs_write+0x3f9/0x570 [ib_uverbs] ? security_mmap_file+0x62/0xe0 vfs_write+0xb7/0x200 ksys_write+0xaf/0xd0 ? syscall_trace_enter.isra.25+0x152/0x200 do_syscall_64+0x2d/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 06e8d1df46ed ("RDMA/qedr: Add support for user mode XRC-SRQ's") Link: https://lore.kernel.org/r/20201127163251.14533-1-palok@marvell.com Signed-off-by: Michal Kalderon Signed-off-by: Igor Russkikh Signed-off-by: Alok Prasad Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/qedr/verbs.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 019642ff24a7..511c95bb3d01 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1936,6 +1936,15 @@ static int qedr_create_user_qp(struct qedr_dev *dev, } if (rdma_protocol_iwarp(&dev->ibdev, 1)) { + qp->urq.db_rec_db2_addr = ctx->dpi_addr + uresp.rq_db2_offset; + + /* calculate the db_rec_db2 data since it is constant so no + * need to reflect from user + */ + qp->urq.db_rec_db2_data.data.icid = cpu_to_le16(qp->icid); + qp->urq.db_rec_db2_data.data.value = + cpu_to_le16(DQ_TCM_IWARP_POST_RQ_CF_CMD); + rc = qedr_db_recovery_add(dev, qp->urq.db_rec_db2_addr, &qp->urq.db_rec_db2_data, DB_REC_WIDTH_32B, -- cgit v1.2.3 From 93416ab0f994f6cf16fa0c695577f8b19d30c533 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Tue, 1 Dec 2020 11:17:24 +0200 Subject: RDMA/efa: Use the correct current and new states in modify QP The local variables cur_state and new_state hold the state that should be used for the modify QP operation instead of the ones in the ib_qp_attr struct. Fixes: 40909f664d27 ("RDMA/efa: Add EFA verbs implementation") Link: https://lore.kernel.org/r/20201201091724.37016-1-galpress@amazon.com Reviewed-by: Firas JahJah Reviewed-by: Yossi Leybovich Signed-off-by: Gal Pressman Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/efa/efa_verbs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 191e0843f090..4e940fc50bba 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -940,8 +940,8 @@ int efa_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, 1); EFA_SET(¶ms.modify_mask, EFA_ADMIN_MODIFY_QP_CMD_CUR_QP_STATE, 1); - params.cur_qp_state = qp_attr->cur_qp_state; - params.qp_state = qp_attr->qp_state; + params.cur_qp_state = cur_state; + params.qp_state = new_state; } if (qp_attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY) { -- cgit v1.2.3 From 2867e1eac61016f59b3d730e3f7aa488e186e917 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Mon, 30 Nov 2020 19:37:05 +0100 Subject: inet_ecn: Fix endianness of checksum update when setting ECT(1) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When adding support for propagating ECT(1) marking in IP headers it seems I suffered from endianness-confusion in the checksum update calculation: In fact the ECN field is in the *lower* bits of the first 16-bit word of the IP header when calculating in network byte order. This means that the addition performed to update the checksum field was wrong; let's fix that. Fixes: b723748750ec ("tunnel: Propagate ECT(1) when decapsulating as recommended by RFC6040") Reported-by: Jonathan Morton Tested-by: Pete Heist Signed-off-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20201130183705.17540-1-toke@redhat.com Signed-off-by: Jakub Kicinski --- include/net/inet_ecn.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index e1eaf1780288..563457fec557 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -107,7 +107,7 @@ static inline int IP_ECN_set_ect1(struct iphdr *iph) if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0) return 0; - check += (__force u16)htons(0x100); + check += (__force u16)htons(0x1); iph->check = (__force __sum16)(check + (check>=0xFFFF)); iph->tos ^= INET_ECN_MASK; -- cgit v1.2.3 From 4179b00c04d18ea7013f68d578d80f3c9d13150a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 1 Dec 2020 01:05:07 -0800 Subject: geneve: pull IP header before ECN decapsulation IP_ECN_decapsulate() and IP6_ECN_decapsulate() assume IP header is already pulled. geneve does not ensure this yet. Fixing this generically in IP_ECN_decapsulate() and IP6_ECN_decapsulate() is not possible, since callers pass a pointer that might be freed by pskb_may_pull() syzbot reported : BUG: KMSAN: uninit-value in __INET_ECN_decapsulate include/net/inet_ecn.h:238 [inline] BUG: KMSAN: uninit-value in INET_ECN_decapsulate+0x345/0x1db0 include/net/inet_ecn.h:260 CPU: 1 PID: 8941 Comm: syz-executor.0 Not tainted 5.10.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x21c/0x280 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118 __msan_warning+0x5f/0xa0 mm/kmsan/kmsan_instr.c:197 __INET_ECN_decapsulate include/net/inet_ecn.h:238 [inline] INET_ECN_decapsulate+0x345/0x1db0 include/net/inet_ecn.h:260 geneve_rx+0x2103/0x2980 include/net/inet_ecn.h:306 geneve_udp_encap_recv+0x105c/0x1340 drivers/net/geneve.c:377 udp_queue_rcv_one_skb+0x193a/0x1af0 net/ipv4/udp.c:2093 udp_queue_rcv_skb+0x282/0x1050 net/ipv4/udp.c:2167 udp_unicast_rcv_skb net/ipv4/udp.c:2325 [inline] __udp4_lib_rcv+0x399d/0x5880 net/ipv4/udp.c:2394 udp_rcv+0x5c/0x70 net/ipv4/udp.c:2564 ip_protocol_deliver_rcu+0x572/0xc50 net/ipv4/ip_input.c:204 ip_local_deliver_finish net/ipv4/ip_input.c:231 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ip_local_deliver+0x583/0x8d0 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:449 [inline] ip_rcv_finish net/ipv4/ip_input.c:428 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ip_rcv+0x5c3/0x840 net/ipv4/ip_input.c:539 __netif_receive_skb_one_core net/core/dev.c:5315 [inline] __netif_receive_skb+0x1ec/0x640 net/core/dev.c:5429 process_backlog+0x523/0xc10 net/core/dev.c:6319 napi_poll+0x420/0x1010 net/core/dev.c:6763 net_rx_action+0x35c/0xd40 net/core/dev.c:6833 __do_softirq+0x1a9/0x6fa kernel/softirq.c:298 asm_call_irq_on_stack+0xf/0x20 __run_on_irqstack arch/x86/include/asm/irq_stack.h:26 [inline] run_on_irqstack_cond arch/x86/include/asm/irq_stack.h:77 [inline] do_softirq_own_stack+0x6e/0x90 arch/x86/kernel/irq_64.c:77 do_softirq kernel/softirq.c:343 [inline] __local_bh_enable_ip+0x184/0x1d0 kernel/softirq.c:195 local_bh_enable+0x36/0x40 include/linux/bottom_half.h:32 rcu_read_unlock_bh include/linux/rcupdate.h:730 [inline] __dev_queue_xmit+0x3a9b/0x4520 net/core/dev.c:4167 dev_queue_xmit+0x4b/0x60 net/core/dev.c:4173 packet_snd net/packet/af_packet.c:2992 [inline] packet_sendmsg+0x86f9/0x99d0 net/packet/af_packet.c:3017 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] __sys_sendto+0x9dc/0xc80 net/socket.c:1992 __do_sys_sendto net/socket.c:2004 [inline] __se_sys_sendto+0x107/0x130 net/socket.c:2000 __x64_sys_sendto+0x6e/0x90 net/socket.c:2000 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 2d07dc79fe04 ("geneve: add initial netdev driver for GENEVE tunnels") Signed-off-by: Eric Dumazet Reported-by: syzbot Link: https://lore.kernel.org/r/20201201090507.4137906-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/geneve.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 1426bfc009bc..8ae9ce2014a4 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -257,11 +257,21 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, skb_dst_set(skb, &tun_dst->dst); /* Ignore packet loops (and multicast echo) */ - if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) { - geneve->dev->stats.rx_errors++; - goto drop; - } + if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) + goto rx_error; + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): + if (pskb_may_pull(skb, sizeof(struct iphdr))) + goto rx_error; + break; + case htons(ETH_P_IPV6): + if (pskb_may_pull(skb, sizeof(struct ipv6hdr))) + goto rx_error; + break; + default: + goto rx_error; + } oiph = skb_network_header(skb); skb_reset_network_header(skb); @@ -298,6 +308,8 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, dev_sw_netstats_rx_add(geneve->dev, len); return; +rx_error: + geneve->dev->stats.rx_errors++; drop: /* Consume bad packet */ kfree_skb(skb); -- cgit v1.2.3 From f6a8250ea1e42ad1f4f3bab01c851ec5fd48f0e7 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 30 Nov 2020 14:33:35 -0800 Subject: libbpf: Fix ring_buffer__poll() to return number of consumed samples Fix ring_buffer__poll() to return the number of non-discarded records consumed, just like its documentation states. It's also consistent with ring_buffer__consume() return. Fix up selftests with wrong expected results. Fixes: bf99c936f947 ("libbpf: Add BPF ring buffer support") Fixes: cb1c9ddd5525 ("selftests/bpf: Add BPF ringbuf selftests") Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201130223336.904192-1-andrii@kernel.org --- tools/lib/bpf/ringbuf.c | 2 +- tools/testing/selftests/bpf/prog_tests/ringbuf.c | 2 +- tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index 5c6522c89af1..98537ff2679e 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -278,7 +278,7 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms) err = ringbuf_process_ring(ring); if (err < 0) return err; - res += cnt; + res += err; } return cnt < 0 ? -errno : res; } diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index c1650548433c..1a48c6f7f54e 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -217,7 +217,7 @@ void test_ringbuf(void) if (CHECK(err, "join_bg", "err %d\n", err)) goto cleanup; - if (CHECK(bg_ret != 1, "bg_ret", "epoll_wait result: %ld", bg_ret)) + if (CHECK(bg_ret <= 0, "bg_ret", "epoll_wait result: %ld", bg_ret)) goto cleanup; /* 3 rounds, 2 samples each */ diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c index 78e450609803..d37161e59bb2 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c @@ -81,7 +81,7 @@ void test_ringbuf_multi(void) /* poll for samples, should get 2 ringbufs back */ err = ring_buffer__poll(ringbuf, -1); - if (CHECK(err != 4, "poll_res", "expected 4 records, got %d\n", err)) + if (CHECK(err != 2, "poll_res", "expected 2 records, got %d\n", err)) goto cleanup; /* expect extra polling to return nothing */ -- cgit v1.2.3 From 156c9b70dbfb83eeeff39e9202eb5f8bb6d0fd04 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 30 Nov 2020 14:33:36 -0800 Subject: selftests/bpf: Drain ringbuf samples at the end of test Avoid occasional test failures due to the last sample being delayed to another ring_buffer__poll() call. Instead, drain samples completely with ring_buffer__consume(). This is supposed to fix a rare and non-deterministic test failure in libbpf CI. Fixes: cb1c9ddd5525 ("selftests/bpf: Add BPF ringbuf selftests") Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201130223336.904192-2-andrii@kernel.org --- tools/testing/selftests/bpf/prog_tests/ringbuf.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index 1a48c6f7f54e..fddbc5db5d6a 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -220,6 +220,12 @@ void test_ringbuf(void) if (CHECK(bg_ret <= 0, "bg_ret", "epoll_wait result: %ld", bg_ret)) goto cleanup; + /* due to timing variations, there could still be non-notified + * samples, so consume them here to collect all the samples + */ + err = ring_buffer__consume(ringbuf); + CHECK(err < 0, "rb_consume", "failed: %d\b", err); + /* 3 rounds, 2 samples each */ cnt = atomic_xchg(&sample_cnt, 0); CHECK(cnt != 6, "cnt", "exp %d samples, got %d\n", 6, cnt); -- cgit v1.2.3 From 98701a2a861fa87a5055cf2809758e8725e8b146 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 28 Nov 2020 13:39:05 -0800 Subject: vdpa: mlx5: fix vdpa/vhost dependencies drivers/vdpa/mlx5/ uses vhost_iotlb*() interfaces, so select VHOST_IOTLB to make them be built. However, if VHOST_IOTLB is the only VHOST symbol that is set/enabled, the object file still won't be built because drivers/Makefile won't descend into drivers/vhost/ to build it, so make drivers/Makefile build the needed binary whenever VHOST_IOTLB is set, like it does for VHOST_RING. Fixes these build errors: ERROR: modpost: "vhost_iotlb_itree_next" [drivers/vdpa/mlx5/mlx5_vdpa.ko] undefined! ERROR: modpost: "vhost_iotlb_itree_first" [drivers/vdpa/mlx5/mlx5_vdpa.ko] undefined! Fixes: 29064bfdabd5 ("vdpa/mlx5: Add support library for mlx5 VDPA implementation") Fixes: aff90770e54c ("vdpa/mlx5: Fix dependency on MLX5_CORE") Reported-by: kernel test robot Signed-off-by: Randy Dunlap Cc: Eli Cohen Cc: Parav Pandit Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: virtualization@lists.linux-foundation.org Cc: Saeed Mahameed Cc: Leon Romanovsky Cc: netdev@vger.kernel.org Link: https://lore.kernel.org/r/20201128213905.27409-1-rdunlap@infradead.org Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/Makefile | 1 + drivers/vdpa/Kconfig | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/Makefile b/drivers/Makefile index c0cd1b9075e3..576228037718 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -145,6 +145,7 @@ obj-$(CONFIG_OF) += of/ obj-$(CONFIG_SSB) += ssb/ obj-$(CONFIG_BCMA) += bcma/ obj-$(CONFIG_VHOST_RING) += vhost/ +obj-$(CONFIG_VHOST_IOTLB) += vhost/ obj-$(CONFIG_VHOST) += vhost/ obj-$(CONFIG_VLYNQ) += vlynq/ obj-$(CONFIG_GREYBUS) += greybus/ diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index 358f6048dd3c..6caf539091e5 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -32,6 +32,7 @@ config IFCVF config MLX5_VDPA bool + select VHOST_IOTLB help Support library for Mellanox VDPA drivers. Provides code that is common for all types of VDPA drivers. The following drivers are planned: -- cgit v1.2.3 From 2c602741b51daa12f8457f222ce9ce9c4825d067 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 2 Dec 2020 09:44:43 +0300 Subject: vhost_vdpa: return -EFAULT if copy_to_user() fails The copy_to_user() function returns the number of bytes remaining to be copied but this should return -EFAULT to the user. Fixes: 1b48dc03e575 ("vhost: vdpa: report iova range") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/X8c32z5EtDsMyyIL@mwanda Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang Reviewed-by: Stefano Garzarella --- drivers/vhost/vdpa.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index f2db99031e2f..29ed4173f04e 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -348,7 +348,9 @@ static long vhost_vdpa_get_iova_range(struct vhost_vdpa *v, u32 __user *argp) .last = v->range.last, }; - return copy_to_user(argp, &range, sizeof(range)); + if (copy_to_user(argp, &range, sizeof(range))) + return -EFAULT; + return 0; } static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, -- cgit v1.2.3 From 0ac22098de6f9fd460ac1b1cbf6dbd324312161c Mon Sep 17 00:00:00 2001 From: Zheng Liang Date: Tue, 24 Nov 2020 11:06:06 +0800 Subject: gpio: arizona: disable pm_runtime in case of failure pm_runtime_enable will increase power disable depth. Thus a pairing decrement is needed on the error handling path to keep it balanced. Fixes:27a49ed17e224(gpio: arizona: Add support for GPIOs that) Reported-by: Hulk Robot Signed-off-by: Zheng Liang Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-arizona.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpio/gpio-arizona.c b/drivers/gpio/gpio-arizona.c index 5bda38e0780f..2bc173c352ce 100644 --- a/drivers/gpio/gpio-arizona.c +++ b/drivers/gpio/gpio-arizona.c @@ -192,6 +192,7 @@ static int arizona_gpio_probe(struct platform_device *pdev) ret = devm_gpiochip_add_data(&pdev->dev, &arizona_gpio->gpio_chip, arizona_gpio); if (ret < 0) { + pm_runtime_disable(&pdev->dev); dev_err(&pdev->dev, "Could not register gpiochip, %d\n", ret); return ret; -- cgit v1.2.3 From 60593df667e087b009ee0fc20d92e9c4c096a9b5 Mon Sep 17 00:00:00 2001 From: Luo Jiaxing Date: Fri, 27 Nov 2020 16:50:02 +0800 Subject: gpio: dwapb: fix NULL pointer dereference at dwapb_gpio_suspend() Following Calltrace is found when running echo freeze > /sys/power/state. [ 272.755506] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000010 [ 272.755585] Call trace: [ 272.755587] dwapb_gpio_suspend+0x18/0x318 [ 272.755588] pm_generic_suspend+0x2c/0x48 [ 272.755595] acpi_subsys_suspend+0x60/0x70 [ 272.755599] dpm_run_callback.isra.18+0x40/0xe0 [ 272.755601] __device_suspend+0xf4/0x360 The reason is platform_set_drvdata() is deleted, and dwapb_gpio_suspend() get *gpio by dev_get_drvdata(). Fixes: feeaefd378ca ("gpio: dwapb: Use resource managed GPIO-chip add data method") Signed-off-by: Luo Jiaxing Acked-by: Serge Semin Reviewed-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-dwapb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index 2a9046c0fb16..4275c18a097a 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -724,6 +724,8 @@ static int dwapb_gpio_probe(struct platform_device *pdev) return err; } + platform_set_drvdata(pdev, gpio); + return 0; } -- cgit v1.2.3 From 6dbbf84603961d4e8eaea46e3530373c8cffee67 Mon Sep 17 00:00:00 2001 From: Edmond Chung Date: Mon, 30 Nov 2020 22:47:53 +0000 Subject: gpiolib: Don't free if pin ranges are not defined A similar check was added in gpiochip_generic_request, but not in free. This has caused an imbalance count of request vs. free calls to the pinctrl driver. This patch is targeted to fix that issue. Fixes: 2ab73c6d8323 ("gpio: Support GPIO controllers without pin-ranges") Signed-off-by: Edmond Chung Signed-off-by: Andrew Chant Signed-off-by: Will McVicker Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpiolib.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 089ddcaa9bc6..6e3c4d7a7d14 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1806,6 +1806,11 @@ EXPORT_SYMBOL_GPL(gpiochip_generic_request); */ void gpiochip_generic_free(struct gpio_chip *gc, unsigned offset) { +#ifdef CONFIG_PINCTRL + if (list_empty(&gc->gpiodev->pin_ranges)) + return; +#endif + pinctrl_gpio_free(gc->gpiodev->base + offset); } EXPORT_SYMBOL_GPL(gpiochip_generic_free); -- cgit v1.2.3 From 7f57b295f990c0fa07f96d51ca1c82c52dbf79cc Mon Sep 17 00:00:00 2001 From: Qinglang Miao Date: Fri, 27 Nov 2020 17:44:45 +0800 Subject: gpio: zynq: fix reference leak in zynq_gpio functions pm_runtime_get_sync will increment pm usage counter even it failed. Forgetting to putting operation will result in a reference leak here. A new function pm_runtime_resume_and_get is introduced in [0] to keep usage counter balanced. So We fix the reference leak by replacing it with new funtion. [0] dd8088d5a896 ("PM: runtime: Add pm_runtime_resume_and_get to deal with usage counter") Fixes: c2df3de0d07e ("gpio: zynq: properly support runtime PM for GPIO used as interrupts") Reported-by: Hulk Robot Signed-off-by: Qinglang Miao Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-zynq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c index 0b5a17ab996f..3521c1dc3ac0 100644 --- a/drivers/gpio/gpio-zynq.c +++ b/drivers/gpio/gpio-zynq.c @@ -574,7 +574,7 @@ static int zynq_gpio_irq_reqres(struct irq_data *d) struct gpio_chip *chip = irq_data_get_irq_chip_data(d); int ret; - ret = pm_runtime_get_sync(chip->parent); + ret = pm_runtime_resume_and_get(chip->parent); if (ret < 0) return ret; @@ -942,7 +942,7 @@ static int zynq_gpio_probe(struct platform_device *pdev) pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) goto err_pm_dis; -- cgit v1.2.3 From 5c646b7e1d8bcb12317426287c516dfa4c5171c2 Mon Sep 17 00:00:00 2001 From: Yanan Wang Date: Wed, 2 Dec 2020 04:10:32 +0800 Subject: KVM: arm64: Fix memory leak on stage2 update of a valid PTE When installing a new leaf PTE onto an invalid ptep, we need to get_page(ptep) to account for the new mapping. However, simply updating a valid PTE shouldn't result in any additional refcounting, as there is new mapping. This otherwise results in a page being forever wasted. Address this by fixing-up the refcount in stage2_map_walker_try_leaf() if the PTE was already valid, balancing out the later get_page() in stage2_map_walk_leaf(). Signed-off-by: Yanan Wang [maz: update commit message, add comment in the code] Signed-off-by: Marc Zyngier Acked-by: Will Deacon Link: https://lore.kernel.org/r/20201201201034.116760-2-wangyanan55@huawei.com --- arch/arm64/kvm/hyp/pgtable.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 0271b4a3b9fe..2beba1dc40ec 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -470,6 +470,15 @@ static bool stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level, if (!kvm_block_mapping_supported(addr, end, phys, level)) return false; + /* + * If the PTE was already valid, drop the refcount on the table + * early, as it will be bumped-up again in stage2_map_walk_leaf(). + * This ensures that the refcount stays constant across a valid to + * valid PTE update. + */ + if (kvm_pte_valid(*ptep)) + put_page(virt_to_page(ptep)); + if (kvm_set_valid_leaf_pte(ptep, phys, data->attr, level)) goto out; -- cgit v1.2.3 From 3a0b870e3448302ca2ba703bea1b79b61c3f33c6 Mon Sep 17 00:00:00 2001 From: Yanan Wang Date: Wed, 2 Dec 2020 04:10:33 +0800 Subject: KVM: arm64: Fix handling of merging tables into a block entry When dirty logging is enabled, we collapse block entries into tables as necessary. If dirty logging gets canceled, we can end-up merging tables back into block entries. When this happens, we must not only free the non-huge page-table pages but also invalidate all the TLB entries that can potentially cover the block. Otherwise, we end-up with multiple possible translations for the same physical page, which can legitimately result in a TLB conflict. To address this, replease the bogus invalidation by IPA with a full VM invalidation. Although this is pretty heavy handed, it happens very infrequently and saves a bunch of invalidations by IPA. Signed-off-by: Yanan Wang [maz: fixup commit message] Signed-off-by: Marc Zyngier Acked-by: Will Deacon Link: https://lore.kernel.org/r/20201201201034.116760-3-wangyanan55@huawei.com --- arch/arm64/kvm/hyp/pgtable.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 2beba1dc40ec..bdf8e55ed308 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -502,7 +502,13 @@ static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level, return 0; kvm_set_invalid_pte(ptep); - kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, data->mmu, addr, 0); + + /* + * Invalidate the whole stage-2, as we may have numerous leaf + * entries below us which would otherwise need invalidating + * individually. + */ + kvm_call_hyp(__kvm_tlb_flush_vmid, data->mmu); data->anchor = ptep; return 0; } -- cgit v1.2.3 From 7d894834a305568a0168c55d4729216f5f8cb4e6 Mon Sep 17 00:00:00 2001 From: Yanan Wang Date: Wed, 2 Dec 2020 04:10:34 +0800 Subject: KVM: arm64: Add usage of stage 2 fault lookup level in user_mem_abort() If we get a FSC_PERM fault, just using (logging_active && writable) to determine calling kvm_pgtable_stage2_map(). There will be two more cases we should consider. (1) After logging_active is configged back to false from true. When we get a FSC_PERM fault with write_fault and adjustment of hugepage is needed, we should merge tables back to a block entry. This case is ignored by still calling kvm_pgtable_stage2_relax_perms(), which will lead to an endless loop and guest panic due to soft lockup. (2) We use (FSC_PERM && logging_active && writable) to determine collapsing a block entry into a table by calling kvm_pgtable_stage2_map(). But sometimes we may only need to relax permissions when trying to write to a page other than a block. In this condition,using kvm_pgtable_stage2_relax_perms() will be fine. The ISS filed bit[1:0] in ESR_EL2 regesiter indicates the stage2 lookup level at which a D-abort or I-abort occurred. By comparing granule of the fault lookup level with vma_pagesize, we can strictly distinguish conditions of calling kvm_pgtable_stage2_relax_perms() or kvm_pgtable_stage2_map(), and the above two cases will be well considered. Suggested-by: Keqian Zhu Signed-off-by: Yanan Wang Signed-off-by: Marc Zyngier Acked-by: Will Deacon Link: https://lore.kernel.org/r/20201201201034.116760-4-wangyanan55@huawei.com --- arch/arm64/include/asm/esr.h | 1 + arch/arm64/include/asm/kvm_emulate.h | 5 +++++ arch/arm64/kvm/mmu.c | 11 +++++++++-- 3 files changed, 15 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 22c81f1edda2..85a3e49f92f4 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -104,6 +104,7 @@ /* Shared ISS fault status code(IFSC/DFSC) for Data/Instruction aborts */ #define ESR_ELx_FSC (0x3F) #define ESR_ELx_FSC_TYPE (0x3C) +#define ESR_ELx_FSC_LEVEL (0x03) #define ESR_ELx_FSC_EXTABT (0x10) #define ESR_ELx_FSC_SERROR (0x11) #define ESR_ELx_FSC_ACCESS (0x08) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 5ef2669ccd6c..00bc6f1234ba 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -350,6 +350,11 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vc return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE; } +static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_LEVEL; +} + static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu) { switch (kvm_vcpu_trap_get_fault(vcpu)) { diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 1a01da9fdc99..75814a02d189 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -754,10 +754,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, gfn_t gfn; kvm_pfn_t pfn; bool logging_active = memslot_is_logging(memslot); - unsigned long vma_pagesize; + unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu); + unsigned long vma_pagesize, fault_granule; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; struct kvm_pgtable *pgt; + fault_granule = 1UL << ARM64_HW_PGTABLE_LEVEL_SHIFT(fault_level); write_fault = kvm_is_write_fault(vcpu); exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); VM_BUG_ON(write_fault && exec_fault); @@ -896,7 +898,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, else if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC)) prot |= KVM_PGTABLE_PROT_X; - if (fault_status == FSC_PERM && !(logging_active && writable)) { + /* + * Under the premise of getting a FSC_PERM fault, we just need to relax + * permissions only if vma_pagesize equals fault_granule. Otherwise, + * kvm_pgtable_stage2_map() should be called to change block size. + */ + if (fault_status == FSC_PERM && vma_pagesize == fault_granule) { ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot); } else { ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize, -- cgit v1.2.3 From 7ee1a01e47403f72b9f38839a737692f6991263e Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Wed, 2 Dec 2020 09:15:32 +0200 Subject: gpio: mvebu: fix potential user-after-free on probe When mvebu_pwm_probe() fails IRQ domain is not released. Move pwm probe before IRQ domain allocation. Add pwm cleanup code to the failure path. Fixes: 757642f9a584 ("gpio: mvebu: Add limited PWM support") Reported-by: Andrew Lunn Signed-off-by: Baruch Siach Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-mvebu.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index 433e2c3f3fd5..2f245594a90a 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -1197,6 +1197,13 @@ static int mvebu_gpio_probe(struct platform_device *pdev) devm_gpiochip_add_data(&pdev->dev, &mvchip->chip, mvchip); + /* Some MVEBU SoCs have simple PWM support for GPIO lines */ + if (IS_ENABLED(CONFIG_PWM)) { + err = mvebu_pwm_probe(pdev, mvchip, id); + if (err) + return err; + } + /* Some gpio controllers do not provide irq support */ if (!have_irqs) return 0; @@ -1206,7 +1213,8 @@ static int mvebu_gpio_probe(struct platform_device *pdev) if (!mvchip->domain) { dev_err(&pdev->dev, "couldn't allocate irq domain %s (DT).\n", mvchip->chip.label); - return -ENODEV; + err = -ENODEV; + goto err_pwm; } err = irq_alloc_domain_generic_chips( @@ -1254,14 +1262,12 @@ static int mvebu_gpio_probe(struct platform_device *pdev) mvchip); } - /* Some MVEBU SoCs have simple PWM support for GPIO lines */ - if (IS_ENABLED(CONFIG_PWM)) - return mvebu_pwm_probe(pdev, mvchip, id); - return 0; err_domain: irq_domain_remove(mvchip->domain); +err_pwm: + pwmchip_remove(&mvchip->mvpwm->chip); return err; } -- cgit v1.2.3 From bac63f1239aceb092e94fee3ef112dbaea79b372 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Mon, 30 Nov 2020 16:00:54 +0100 Subject: media: vb2: set cache sync hints when init buffers We need to set ->need_cache_sync_on_prepare and ->need_cache_sync_on_finish when we initialize vb2 buffer. Currently these flags are set/adjusted only in V4L2's vb2_queue_or_prepare_buf(), which means that for the code paths that don't use V4L2 vb2 will always tell videobuf2 core to skip ->prepare() and ->finish() cache syncs/flushes. Fix this by setting cache sync hints for new buffers; except VB2_MEMORY_DMABUF buffers, for which DMA exporter syncs caches. Fixes: f5f5fa73fbfb ("media: videobuf2: handle V4L2 buffer cache flags") Reported-by: Tomasz Figa Signed-off-by: Sergey Senozhatsky Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/common/videobuf2/videobuf2-core.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index 4eab6d81cce1..89e38392509c 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -414,6 +414,17 @@ static int __vb2_queue_alloc(struct vb2_queue *q, enum vb2_memory memory, vb->index = q->num_buffers + buffer; vb->type = q->type; vb->memory = memory; + /* + * We need to set these flags here so that the videobuf2 core + * will call ->prepare()/->finish() cache sync/flush on vb2 + * buffers when appropriate. However, we can avoid explicit + * ->prepare() and ->finish() cache sync for DMABUF buffers, + * because DMA exporter takes care of it. + */ + if (q->memory != VB2_MEMORY_DMABUF) { + vb->need_cache_sync_on_prepare = 1; + vb->need_cache_sync_on_finish = 1; + } for (plane = 0; plane < num_planes; ++plane) { vb->planes[plane].length = plane_sizes[plane]; vb->planes[plane].min_length = plane_sizes[plane]; -- cgit v1.2.3 From 3c0dde35e6aee456abc8d8549ff7ee0963274214 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 27 Nov 2020 14:28:32 +0100 Subject: media: [next] media: vidtv: fix a read from an object after it has been freed Currently the call to vidtv_psi_pat_table_destroy frees the object m->si.pat however m->si.pat->num_pmt is being accessed after the free. Fix this by destroying m->si.pat after the m->si.pmt_secs[] objects have been freed. Addresses-Coverity: ("Read from pointer after free") Reported-by: Cengiz Can # sent a similar fix about the same time Fixes: 039b7caed173 ("media: vidtv: add a PID entry for the NIT table") Signed-off-by: Colin Ian King Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_channel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index 8ad6c0744d36..7838e6272712 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -504,11 +504,11 @@ void vidtv_channel_si_destroy(struct vidtv_mux *m) { u32 i; - vidtv_psi_pat_table_destroy(m->si.pat); - for (i = 0; i < m->si.pat->num_pmt; ++i) vidtv_psi_pmt_table_destroy(m->si.pmt_secs[i]); + vidtv_psi_pat_table_destroy(m->si.pat); + kfree(m->si.pmt_secs); vidtv_psi_sdt_table_destroy(m->si.sdt); vidtv_psi_nit_table_destroy(m->si.nit); -- cgit v1.2.3 From a1ee28117077c3bf24e5ab6324c835eaab629c45 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 28 Nov 2020 17:07:21 +1000 Subject: powerpc/64s/powernv: Fix memory corruption when saving SLB entries on MCE This can be hit by an HPT guest running on an HPT host and bring down the host, so it's quite important to fix. Fixes: 7290f3b3d3e6 ("powerpc/64s/powernv: machine check dump SLB contents") Cc: stable@vger.kernel.org # v5.4+ Signed-off-by: Nicholas Piggin Acked-by: Mahesh Salgaonkar Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201128070728.825934-2-npiggin@gmail.com --- arch/powerpc/platforms/powernv/setup.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 46115231a3b2..4426a109ec2f 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -211,11 +211,16 @@ static void __init pnv_init(void) add_preferred_console("hvc", 0, NULL); if (!radix_enabled()) { + size_t size = sizeof(struct slb_entry) * mmu_slb_size; int i; /* Allocate per cpu area to save old slb contents during MCE */ - for_each_possible_cpu(i) - paca_ptrs[i]->mce_faulty_slbs = memblock_alloc_node(mmu_slb_size, __alignof__(*paca_ptrs[i]->mce_faulty_slbs), cpu_to_node(i)); + for_each_possible_cpu(i) { + paca_ptrs[i]->mce_faulty_slbs = + memblock_alloc_node(size, + __alignof__(struct slb_entry), + cpu_to_node(i)); + } } } -- cgit v1.2.3 From cc2ff9730e0fe649ebf064632c9d0e04218e2f25 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 2 Dec 2020 08:51:28 +0100 Subject: media: vidtv: fix kernel-doc markups Some functions has a different name between their prototypes and the corresponding kernel-doc markups. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_psi.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index 340c9fb8d583..6651cc91bda1 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -420,7 +420,7 @@ void vidtv_psi_desc_assign(struct vidtv_psi_desc **to, struct vidtv_psi_desc *desc); /** - * vidtv_psi_pmt_desc_assign - Assigns a descriptor loop at some point in a PMT section. + * vidtv_pmt_desc_assign - Assigns a descriptor loop at some point in a PMT section. * @pmt: The PMT section that will contain the descriptor loop * @to: Where in the PMT to assign this descriptor loop to * @desc: The descriptor loop that will be assigned. @@ -434,7 +434,7 @@ void vidtv_pmt_desc_assign(struct vidtv_psi_table_pmt *pmt, struct vidtv_psi_desc *desc); /** - * vidtv_psi_sdt_desc_assign - Assigns a descriptor loop at some point in a SDT. + * vidtv_sdt_desc_assign - Assigns a descriptor loop at some point in a SDT. * @sdt: The SDT that will contain the descriptor loop * @to: Where in the PMT to assign this descriptor loop to * @desc: The descriptor loop that will be assigned. @@ -474,7 +474,7 @@ void vidtv_psi_pmt_stream_assign(struct vidtv_psi_table_pmt *pmt, struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc); /** - * vidtv_psi_create_sec_for_each_pat_entry - Create a PMT section for each + * vidtv_psi_pmt_create_sec_for_each_pat_entry - Create a PMT section for each * program found in the PAT * @pat: The PAT to look for programs. * @pcr_pid: packet ID for the PCR to be used for the program described in this -- cgit v1.2.3 From e9acf0298c664f825e6f1158f2a97341bf9e03ca Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Mon, 16 Nov 2020 22:10:58 +0800 Subject: i2c: qup: Fix error return code in qup_i2c_bam_schedule_desc() Fix to return the error code from qup_i2c_change_state() instaed of 0 in qup_i2c_bam_schedule_desc(). Fixes: fbf9921f8b35d9b2 ("i2c: qup: Fix error handling") Reported-by: Hulk Robot Signed-off-by: Zhihao Cheng Reviewed-by: Bjorn Andersson Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-qup.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c index fbc04b60cfd1..5a47915869ae 100644 --- a/drivers/i2c/busses/i2c-qup.c +++ b/drivers/i2c/busses/i2c-qup.c @@ -801,7 +801,8 @@ static int qup_i2c_bam_schedule_desc(struct qup_i2c_dev *qup) if (ret || qup->bus_err || qup->qup_err) { reinit_completion(&qup->xfer); - if (qup_i2c_change_state(qup, QUP_RUN_STATE)) { + ret = qup_i2c_change_state(qup, QUP_RUN_STATE); + if (ret) { dev_err(qup->dev, "change to run state timed out"); goto desc_err; } -- cgit v1.2.3 From 14718b3e129b058cb716a60c6faf40ef68661c54 Mon Sep 17 00:00:00 2001 From: Robert Foss Date: Mon, 30 Nov 2020 11:04:45 +0100 Subject: i2c: qcom: Fix IRQ error misassignement During cci_isr() errors read from register fields belonging to i2c master1 are currently assigned to the status field belonging to i2c master0. This patch corrects this error, and always assigns master1 errors to the status field of master1. Fixes: e517526195de ("i2c: Add Qualcomm CCI I2C driver") Reported-by: Loic Poulain Suggested-by: Loic Poulain Signed-off-by: Robert Foss Reviewed-by: Manivannan Sadhasivam Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-qcom-cci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-qcom-cci.c b/drivers/i2c/busses/i2c-qcom-cci.c index f13735beca58..1c259b5188de 100644 --- a/drivers/i2c/busses/i2c-qcom-cci.c +++ b/drivers/i2c/busses/i2c-qcom-cci.c @@ -194,9 +194,9 @@ static irqreturn_t cci_isr(int irq, void *dev) if (unlikely(val & CCI_IRQ_STATUS_0_I2C_M1_ERROR)) { if (val & CCI_IRQ_STATUS_0_I2C_M1_Q0_NACK_ERR || val & CCI_IRQ_STATUS_0_I2C_M1_Q1_NACK_ERR) - cci->master[0].status = -ENXIO; + cci->master[1].status = -ENXIO; else - cci->master[0].status = -EIO; + cci->master[1].status = -EIO; writel(CCI_HALT_REQ_I2C_M1_Q0Q1, cci->base + CCI_HALT_REQ); ret = IRQ_HANDLED; -- cgit v1.2.3 From a2bd4097b3ec242f4de4924db463a9c94530e03a Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Thu, 26 Nov 2020 18:00:37 +0100 Subject: s390/pci: fix CPU address in MSI for directed IRQ The directed MSIs are delivered to CPUs whose address is written to the MSI message address. The current code assumes that a CPU logical number (as it is seen by the kernel) is also the CPU address. The above assumption is not correct, as the CPU address is rather the value returned by STAP instruction. That value does not necessarily match the kernel logical CPU number. Fixes: e979ce7bced2 ("s390/pci: provide support for CPU directed interrupts") Cc: # v5.2+ Signed-off-by: Alexander Gordeev Reviewed-by: Halil Pasic Reviewed-by: Niklas Schnelle Signed-off-by: Niklas Schnelle Signed-off-by: Heiko Carstens --- arch/s390/pci/pci_irq.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 743f257cf2cb..75217fb63d7b 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -103,9 +103,10 @@ static int zpci_set_irq_affinity(struct irq_data *data, const struct cpumask *de { struct msi_desc *entry = irq_get_msi_desc(data->irq); struct msi_msg msg = entry->msg; + int cpu_addr = smp_cpu_get_cpu_address(cpumask_first(dest)); msg.address_lo &= 0xff0000ff; - msg.address_lo |= (cpumask_first(dest) << 8); + msg.address_lo |= (cpu_addr << 8); pci_write_msi_msg(data->irq, &msg); return IRQ_SET_MASK_OK; @@ -238,6 +239,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) unsigned long bit; struct msi_desc *msi; struct msi_msg msg; + int cpu_addr; int rc, irq; zdev->aisb = -1UL; @@ -287,9 +289,15 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) handle_percpu_irq); msg.data = hwirq - bit; if (irq_delivery == DIRECTED) { + if (msi->affinity) + cpu = cpumask_first(&msi->affinity->mask); + else + cpu = 0; + cpu_addr = smp_cpu_get_cpu_address(cpu); + msg.address_lo = zdev->msi_addr & 0xff0000ff; - msg.address_lo |= msi->affinity ? - (cpumask_first(&msi->affinity->mask) << 8) : 0; + msg.address_lo |= (cpu_addr << 8); + for_each_possible_cpu(cpu) { airq_iv_set_data(zpci_ibv[cpu], hwirq, irq); } -- cgit v1.2.3 From b1cae1f84a0f609a34ebcaa087fbecef32f69882 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 2 Dec 2020 11:46:01 +0100 Subject: s390: fix irq state tracing With commit 58c644ba512c ("sched/idle: Fix arch_cpu_idle() vs tracing") common code calls arch_cpu_idle() with a lockdep state that tells irqs are on. This doesn't work very well for s390: psw_idle() will enable interrupts to wait for an interrupt. As soon as an interrupt occurs the interrupt handler will verify if the old context was psw_idle(). If that is the case the interrupt enablement bits in the old program status word will be cleared. A subsequent test in both the external as well as the io interrupt handler checks if in the old context interrupts were enabled. Due to the above patching of the old program status word it is assumed the old context had interrupts disabled, and therefore a call to TRACE_IRQS_OFF (aka trace_hardirqs_off_caller) is skipped. Which in turn makes lockdep incorrectly "think" that interrupts are enabled within the interrupt handler. Fix this by unconditionally calling TRACE_IRQS_OFF when entering interrupt handlers. Also call unconditionally TRACE_IRQS_ON when leaving interrupts handlers. This leaves the special psw_idle() case, which now returns with interrupts disabled, but has an "irqs on" lockdep state. So callers of psw_idle() must adjust the state on their own, if required. This is currently only __udelay_disabled(). Fixes: 58c644ba512c ("sched/idle: Fix arch_cpu_idle() vs tracing") Acked-by: Peter Zijlstra (Intel) Signed-off-by: Heiko Carstens --- arch/s390/kernel/entry.S | 15 --------------- arch/s390/lib/delay.c | 5 ++--- 2 files changed, 2 insertions(+), 18 deletions(-) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 26bb0603c5a1..92beb1444644 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -763,12 +763,7 @@ ENTRY(io_int_handler) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ jo .Lio_restore -#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) - tmhh %r8,0x300 - jz 1f TRACE_IRQS_OFF -1: -#endif xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) .Lio_loop: lgr %r2,%r11 # pass pointer to pt_regs @@ -791,12 +786,7 @@ ENTRY(io_int_handler) TSTMSK __LC_CPU_FLAGS,_CIF_WORK jnz .Lio_work .Lio_restore: -#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) - tm __PT_PSW(%r11),3 - jno 0f TRACE_IRQS_ON -0: -#endif mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) tm __PT_PSW+1(%r11),0x01 # returning to user ? jno .Lio_exit_kernel @@ -976,12 +966,7 @@ ENTRY(ext_int_handler) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ jo .Lio_restore -#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) - tmhh %r8,0x300 - jz 1f TRACE_IRQS_OFF -1: -#endif xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs lghi %r3,EXT_INTERRUPT diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index daca7bad66de..8c0c68e7770e 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -33,7 +33,7 @@ EXPORT_SYMBOL(__delay); static void __udelay_disabled(unsigned long long usecs) { - unsigned long cr0, cr0_new, psw_mask, flags; + unsigned long cr0, cr0_new, psw_mask; struct s390_idle_data idle; u64 end; @@ -45,9 +45,8 @@ static void __udelay_disabled(unsigned long long usecs) psw_mask = __extract_psw() | PSW_MASK_EXT | PSW_MASK_WAIT; set_clock_comparator(end); set_cpu_flag(CIF_IGNORE_IRQ); - local_irq_save(flags); psw_idle(&idle, psw_mask); - local_irq_restore(flags); + trace_hardirqs_off(); clear_cpu_flag(CIF_IGNORE_IRQ); set_clock_comparator(S390_lowcore.clock_comparator); __ctl_load(cr0, 0, 0); -- cgit v1.2.3 From 2d586494c4a001312650f0b919d534e429dd1e09 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 28 Nov 2020 23:09:16 -0800 Subject: scsi: bnx2i: Requires MMU The SCSI_BNX2_ISCSI kconfig symbol selects CNIC and CNIC selects UIO, which depends on MMU. Since 'select' does not follow dependency chains, add the same MMU dependency to SCSI_BNX2_ISCSI. Quietens this kconfig warning: WARNING: unmet direct dependencies detected for CNIC Depends on [n]: NETDEVICES [=y] && ETHERNET [=y] && NET_VENDOR_BROADCOM [=y] && PCI [=y] && (IPV6 [=m] || IPV6 [=m]=n) && MMU [=n] Selected by [m]: - SCSI_BNX2_ISCSI [=m] && SCSI_LOWLEVEL [=y] && SCSI [=y] && NET [=y] && PCI [=y] && (IPV6 [=m] || IPV6 [=m]=n) Link: https://lore.kernel.org/r/20201129070916.3919-1-rdunlap@infradead.org Fixes: cf4e6363859d ("[SCSI] bnx2i: Add bnx2i iSCSI driver.") Cc: linux-scsi@vger.kernel.org Cc: Nilesh Javali Cc: Manish Rangankar Cc: GR-QLogic-Storage-Upstream@marvell.com Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Signed-off-by: Randy Dunlap Signed-off-by: Martin K. Petersen --- drivers/scsi/bnx2i/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/bnx2i/Kconfig b/drivers/scsi/bnx2i/Kconfig index 75ace2302fed..0cc06c2ce0b8 100644 --- a/drivers/scsi/bnx2i/Kconfig +++ b/drivers/scsi/bnx2i/Kconfig @@ -4,6 +4,7 @@ config SCSI_BNX2_ISCSI depends on NET depends on PCI depends on (IPV6 || IPV6=n) + depends on MMU select SCSI_ISCSI_ATTRS select NETDEVICES select ETHERNET -- cgit v1.2.3 From abfccc3af786bb33210e39638268ea3a7bf80e63 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 29 Nov 2020 15:14:38 +0200 Subject: iwlwifi: update MAINTAINERS entry Reflect the fact that the linuxwifi@intel.com address will disappear, and that neither Emmanuel nor myself are really much involved with the maintenance these days. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/iwlwifi.20201129151117.a25afe6d2c7f.I8f13a5689dd353825fb2b9bd5b6f0fbce92cb12b@changeid --- MAINTAINERS | 3 --- 1 file changed, 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 900ff33789eb..60dd9fe60fe0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9097,10 +9097,7 @@ S: Supported F: drivers/net/wireless/intel/iwlegacy/ INTEL WIRELESS WIFI LINK (iwlwifi) -M: Johannes Berg -M: Emmanuel Grumbach M: Luca Coelho -M: Intel Linux Wireless L: linux-wireless@vger.kernel.org S: Supported W: https://wireless.wiki.kernel.org/en/users/drivers/iwlwifi -- cgit v1.2.3 From 5febcdef30902fa870128b9789b873199f13aff1 Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Wed, 2 Dec 2020 14:41:49 +0200 Subject: iwlwifi: pcie: add one missing entry for AX210 The 0x0024 subsytem device ID was missing from the list, so some AX210 devices were not recognized. Add it. Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/iwlwifi.20201202143859.308eab4db42c.I3763196cd3f7bb36f3dcabf02ec4e7c4fe859c0f@changeid --- drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 129021f26791..466a967da39c 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -536,6 +536,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2725, 0x0090, iwlax211_2ax_cfg_so_gf_a0)}, {IWL_PCI_DEVICE(0x2725, 0x0020, iwlax210_2ax_cfg_ty_gf_a0)}, + {IWL_PCI_DEVICE(0x2725, 0x0024, iwlax210_2ax_cfg_ty_gf_a0)}, {IWL_PCI_DEVICE(0x2725, 0x0310, iwlax210_2ax_cfg_ty_gf_a0)}, {IWL_PCI_DEVICE(0x2725, 0x0510, iwlax210_2ax_cfg_ty_gf_a0)}, {IWL_PCI_DEVICE(0x2725, 0x0A10, iwlax210_2ax_cfg_ty_gf_a0)}, -- cgit v1.2.3 From 568d3434178b00274615190a19d29c3d235b4e6d Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Wed, 2 Dec 2020 14:41:50 +0200 Subject: iwlwifi: pcie: invert values of NO_160 device config entries The NO_160 flag specifies if the device doesn't have 160 MHz support, but we errorneously assumed the opposite. If the flag was set, we were considering that 160 MHz was supported, but it's actually the opposite. Fix it by inverting the bits, i.e. NO_160 is 0x1 and 160 is 0x0. Fixes: d6f2134a3831 ("iwlwifi: add mac/rf types and 160MHz to the device tables") Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/iwlwifi.20201202143859.375bec857ccb.I83884286b688965293e9810381808039bd7eedae@changeid --- drivers/net/wireless/intel/iwlwifi/iwl-config.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index ca4967b81d01..580b07a43856 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -491,8 +491,8 @@ struct iwl_cfg { #define IWL_CFG_RF_ID_HR 0x7 #define IWL_CFG_RF_ID_HR1 0x4 -#define IWL_CFG_NO_160 0x0 -#define IWL_CFG_160 0x1 +#define IWL_CFG_NO_160 0x1 +#define IWL_CFG_160 0x0 #define IWL_CFG_CORES_BT 0x0 #define IWL_CFG_CORES_BT_GNSS 0x5 -- cgit v1.2.3 From 9b15596c5006d82b2f82810e8cbf80d8c6e7e7b4 Mon Sep 17 00:00:00 2001 From: Golan Ben Ami Date: Wed, 2 Dec 2020 14:41:51 +0200 Subject: iwlwifi: pcie: add some missing entries for AX210 Some subsytem device IDs were missing from the list, so some AX210 devices were not recognized. Add them. Signed-off-by: Golan Ben Ami Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/iwlwifi.20201202143859.a06ba7540449.I7390305d088a49c1043c9b489154fe057989c18f@changeid Link: https://lore.kernel.org/r/20201121003411.9450-1-ikegami.t@gmail.com --- drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 466a967da39c..7b5ece380fbf 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -540,6 +540,11 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2725, 0x0310, iwlax210_2ax_cfg_ty_gf_a0)}, {IWL_PCI_DEVICE(0x2725, 0x0510, iwlax210_2ax_cfg_ty_gf_a0)}, {IWL_PCI_DEVICE(0x2725, 0x0A10, iwlax210_2ax_cfg_ty_gf_a0)}, + {IWL_PCI_DEVICE(0x2725, 0xE020, iwlax210_2ax_cfg_ty_gf_a0)}, + {IWL_PCI_DEVICE(0x2725, 0xE024, iwlax210_2ax_cfg_ty_gf_a0)}, + {IWL_PCI_DEVICE(0x2725, 0x4020, iwlax210_2ax_cfg_ty_gf_a0)}, + {IWL_PCI_DEVICE(0x2725, 0x6020, iwlax210_2ax_cfg_ty_gf_a0)}, + {IWL_PCI_DEVICE(0x2725, 0x6024, iwlax210_2ax_cfg_ty_gf_a0)}, {IWL_PCI_DEVICE(0x2725, 0x00B0, iwlax411_2ax_cfg_sosnj_gf4_a0)}, {IWL_PCI_DEVICE(0x2726, 0x0070, iwlax201_cfg_snj_hr_b0)}, {IWL_PCI_DEVICE(0x2726, 0x0074, iwlax201_cfg_snj_hr_b0)}, -- cgit v1.2.3 From 807982017730cfe853fce49ba26d453e31c84898 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Thu, 26 Nov 2020 13:55:20 +0100 Subject: mt76: usb: fix crash on device removal Currently 'while (q->queued > 0)' loop was removed from mt76u_stop_tx() code. This causes crash on device removal as we try to cleanup empty queue: [ 96.495571] kernel BUG at include/linux/skbuff.h:2297! [ 96.498983] invalid opcode: 0000 [#1] SMP PTI [ 96.501162] CPU: 3 PID: 27 Comm: kworker/3:0 Not tainted 5.10.0-rc5+ #11 [ 96.502754] Hardware name: LENOVO 20DGS08H00/20DGS08H00, BIOS J5ET48WW (1.19 ) 08/27/2015 [ 96.504378] Workqueue: usb_hub_wq hub_event [ 96.505983] RIP: 0010:skb_pull+0x2d/0x30 [ 96.507576] Code: 00 00 8b 47 70 39 c6 77 1e 29 f0 89 47 70 3b 47 74 72 17 48 8b 87 c8 00 00 00 89 f6 48 01 f0 48 89 87 c8 00 00 00 c3 31 c0 c3 <0f> 0b 90 0f 1f 44 00 00 53 48 89 fb 48 8b bf c8 00 00 00 8b 43 70 [ 96.509296] RSP: 0018:ffffb11b801639b8 EFLAGS: 00010287 [ 96.511038] RAX: 000000001c6939ed RBX: ffffb11b801639f8 RCX: 0000000000000000 [ 96.512964] RDX: ffffb11b801639f8 RSI: 0000000000000018 RDI: ffff90c64e4fb800 [ 96.514710] RBP: ffff90c654551ee0 R08: ffff90c652bce7a8 R09: ffffb11b80163728 [ 96.516450] R10: 0000000000000001 R11: 0000000000000001 R12: ffff90c64e4fb800 [ 96.519749] R13: 0000000000000010 R14: 0000000000000020 R15: ffff90c64e352ce8 [ 96.523455] FS: 0000000000000000(0000) GS:ffff90c96eec0000(0000) knlGS:0000000000000000 [ 96.527171] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 96.530900] CR2: 0000242556f18288 CR3: 0000000146a10002 CR4: 00000000003706e0 [ 96.534678] Call Trace: [ 96.538418] mt76x02u_tx_complete_skb+0x1f/0x50 [mt76x02_usb] [ 96.542231] mt76_queue_tx_complete+0x23/0x50 [mt76] [ 96.546028] mt76u_stop_tx.cold+0x71/0xa2 [mt76_usb] [ 96.549797] mt76x0u_stop+0x2f/0x90 [mt76x0u] [ 96.553638] drv_stop+0x33/0xd0 [mac80211] [ 96.557449] ieee80211_do_stop+0x558/0x860 [mac80211] [ 96.561262] ? dev_deactivate_many+0x298/0x2d0 [ 96.565101] ieee80211_stop+0x16/0x20 [mac80211] Fix that by adding while loop again. We need loop, not just single check, to clean all pending entries. Additionally move mt76_worker_disable/enable after !mt76_has_tx_pending() as we want to tx_worker to run to process tx queues, while we wait for exactly that. I was a bit worried about accessing q->queued without lock, but mt76_worker_disable() -> kthread_park() should assure this value will be seen updated on other cpus. Fixes: fe5b5ab52e9d ("mt76: unify queue tx cleanup code") Signed-off-by: Stanislaw Gruszka Acked-by: Felix Fietkau Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20201126125520.72912-1-stf_xl@wp.pl --- drivers/net/wireless/mediatek/mt76/usb.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c index 7d3f0a2e5fa0..f1ae9ff835b2 100644 --- a/drivers/net/wireless/mediatek/mt76/usb.c +++ b/drivers/net/wireless/mediatek/mt76/usb.c @@ -1020,8 +1020,6 @@ void mt76u_stop_tx(struct mt76_dev *dev) { int ret; - mt76_worker_disable(&dev->tx_worker); - ret = wait_event_timeout(dev->tx_wait, !mt76_has_tx_pending(&dev->phy), HZ / 5); if (!ret) { @@ -1040,6 +1038,8 @@ void mt76u_stop_tx(struct mt76_dev *dev) usb_kill_urb(q->entry[j].urb); } + mt76_worker_disable(&dev->tx_worker); + /* On device removal we maight queue skb's, but mt76u_tx_kick() * will fail to submit urb, cleanup those skb's manually. */ @@ -1048,18 +1048,19 @@ void mt76u_stop_tx(struct mt76_dev *dev) if (!q) continue; - entry = q->entry[q->tail]; - q->entry[q->tail].done = false; - - mt76_queue_tx_complete(dev, q, &entry); + while (q->queued > 0) { + entry = q->entry[q->tail]; + q->entry[q->tail].done = false; + mt76_queue_tx_complete(dev, q, &entry); + } } + + mt76_worker_enable(&dev->tx_worker); } cancel_work_sync(&dev->usb.stat_work); clear_bit(MT76_READING_STATS, &dev->phy.state); - mt76_worker_enable(&dev->tx_worker); - mt76_tx_status_check(dev, NULL, true); } EXPORT_SYMBOL_GPL(mt76u_stop_tx); -- cgit v1.2.3 From 832ba596494b2c9eac7760259eff2d8b7dcad0ee Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Mon, 30 Nov 2020 17:19:11 +0100 Subject: net: ip6_gre: set dev->hard_header_len when using header_ops syzkaller managed to crash the kernel using an NBMA ip6gre interface. I could reproduce it creating an NBMA ip6gre interface and forwarding traffic to it: skbuff: skb_under_panic: text:ffffffff8250e927 len:148 put:44 head:ffff8c03c7a33 ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:109! Call Trace: skb_push+0x10/0x10 ip6gre_header+0x47/0x1b0 neigh_connected_output+0xae/0xf0 ip6gre tunnel provides its own header_ops->create, and sets it conditionally when initializing the tunnel in NBMA mode. When header_ops->create is used, dev->hard_header_len should reflect the length of the header created. Otherwise, when not used, dev->needed_headroom should be used. Fixes: eb95f52fc72d ("net: ipv6_gre: Fix GRO to work on IPv6 over GRE tap") Cc: Maria Pasechnik Signed-off-by: Antoine Tenart Link: https://lore.kernel.org/r/20201130161911.464106-1-atenart@kernel.org Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_gre.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 931b186d2e48..cf6e1380b527 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1133,8 +1133,13 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu, return; if (rt->dst.dev) { - dev->needed_headroom = rt->dst.dev->hard_header_len + - t_hlen; + unsigned short dst_len = rt->dst.dev->hard_header_len + + t_hlen; + + if (t->dev->header_ops) + dev->hard_header_len = dst_len; + else + dev->needed_headroom = dst_len; if (set_mtu) { dev->mtu = rt->dst.dev->mtu - t_hlen; @@ -1159,7 +1164,12 @@ static int ip6gre_calc_hlen(struct ip6_tnl *tunnel) tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; t_hlen = tunnel->hlen + sizeof(struct ipv6hdr); - tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; + + if (tunnel->dev->header_ops) + tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen; + else + tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; + return t_hlen; } -- cgit v1.2.3 From 07500a6085806d97039ebcba8d9b8b29129f0106 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Tue, 1 Dec 2020 15:52:58 +0800 Subject: dpaa_eth: copy timestamp fields to new skb in A-050385 workaround The timestamp fields should be copied to new skb too in A-050385 workaround for later TX timestamping handling. Fixes: 3c68b8fffb48 ("dpaa_eth: FMan erratum A050385 workaround") Signed-off-by: Yangbo Lu Acked-by: Camelia Groza Link: https://lore.kernel.org/r/20201201075258.1875-1-yangbo.lu@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index d9c285948fc2..cb7c028b1bf5 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2120,6 +2120,15 @@ workaround: skb_copy_header(new_skb, skb); new_skb->dev = skb->dev; + /* Copy relevant timestamp info from the old skb to the new */ + if (priv->tx_tstamp) { + skb_shinfo(new_skb)->tx_flags = skb_shinfo(skb)->tx_flags; + skb_shinfo(new_skb)->hwtstamps = skb_shinfo(skb)->hwtstamps; + skb_shinfo(new_skb)->tskey = skb_shinfo(skb)->tskey; + if (skb->sk) + skb_set_owner_w(new_skb, skb->sk); + } + /* We move the headroom when we align it so we have to reset the * network and transport header offsets relative to the new data * pointer. The checksum offload relies on these offsets. @@ -2127,7 +2136,6 @@ workaround: skb_set_network_header(new_skb, skb_network_offset(skb)); skb_set_transport_header(new_skb, skb_transport_offset(skb)); - /* TODO: does timestamping need the result in the old skb? */ dev_kfree_skb(skb); *s = new_skb; -- cgit v1.2.3 From 384a9565f70a876c2e78e58c5ca0bbf0547e4f6d Mon Sep 17 00:00:00 2001 From: Christian Eggers Date: Fri, 9 Oct 2020 13:03:18 +0200 Subject: i2c: imx: Fix reset of I2SR_IAL flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to the "VFxxx Controller Reference Manual" (and the comment block starting at line 97), Vybrid requires writing a one for clearing an interrupt flag. Syncing the method for clearing I2SR_IIF in i2c_imx_isr(). Signed-off-by: Christian Eggers Fixes: 4b775022f6fd ("i2c: imx: add struct to hold more configurable quirks") Reviewed-by: Uwe Kleine-König Acked-by: Oleksij Rempel Cc: stable@vger.kernel.org Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-imx.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index c98529c76348..39e98d216016 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -412,6 +412,19 @@ static void i2c_imx_dma_free(struct imx_i2c_struct *i2c_imx) dma->chan_using = NULL; } +static void i2c_imx_clear_irq(struct imx_i2c_struct *i2c_imx, unsigned int bits) +{ + unsigned int temp; + + /* + * i2sr_clr_opcode is the value to clear all interrupts. Here we want to + * clear only , so we write ~i2sr_clr_opcode with just + * toggled. This is required because i.MX needs W0C and Vybrid uses W1C. + */ + temp = ~i2c_imx->hwdata->i2sr_clr_opcode ^ bits; + imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2SR); +} + static int i2c_imx_bus_busy(struct imx_i2c_struct *i2c_imx, int for_busy, bool atomic) { unsigned long orig_jiffies = jiffies; @@ -424,8 +437,7 @@ static int i2c_imx_bus_busy(struct imx_i2c_struct *i2c_imx, int for_busy, bool a /* check for arbitration lost */ if (temp & I2SR_IAL) { - temp &= ~I2SR_IAL; - imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2SR); + i2c_imx_clear_irq(i2c_imx, I2SR_IAL); return -EAGAIN; } @@ -469,7 +481,7 @@ static int i2c_imx_trx_complete(struct imx_i2c_struct *i2c_imx, bool atomic) */ readb_poll_timeout_atomic(addr, regval, regval & I2SR_IIF, 5, 1000 + 100); i2c_imx->i2csr = regval; - imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2SR); + i2c_imx_clear_irq(i2c_imx, I2SR_IIF | I2SR_IAL); } else { wait_event_timeout(i2c_imx->queue, i2c_imx->i2csr & I2SR_IIF, HZ / 10); } @@ -623,9 +635,7 @@ static irqreturn_t i2c_imx_isr(int irq, void *dev_id) if (temp & I2SR_IIF) { /* save status register */ i2c_imx->i2csr = temp; - temp &= ~I2SR_IIF; - temp |= (i2c_imx->hwdata->i2sr_clr_opcode & I2SR_IIF); - imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2SR); + i2c_imx_clear_irq(i2c_imx, I2SR_IIF); wake_up(&i2c_imx->queue); return IRQ_HANDLED; } -- cgit v1.2.3 From 1de67a3dee7a279ebe4d892b359fe3696938ec15 Mon Sep 17 00:00:00 2001 From: Christian Eggers Date: Fri, 9 Oct 2020 13:03:19 +0200 Subject: i2c: imx: Check for I2SR_IAL after every byte Arbitration Lost (IAL) can happen after every single byte transfer. If arbitration is lost, the I2C hardware will autonomously switch from master mode to slave. If a transfer is not aborted in this state, consecutive transfers will not be executed by the hardware and will timeout. Signed-off-by: Christian Eggers Tested (not extensively) on Vybrid VF500 (Toradex VF50): Tested-by: Krzysztof Kozlowski Acked-by: Oleksij Rempel Cc: stable@vger.kernel.org Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-imx.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 39e98d216016..a2abae124342 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -490,6 +490,16 @@ static int i2c_imx_trx_complete(struct imx_i2c_struct *i2c_imx, bool atomic) dev_dbg(&i2c_imx->adapter.dev, "<%s> Timeout\n", __func__); return -ETIMEDOUT; } + + /* check for arbitration lost */ + if (i2c_imx->i2csr & I2SR_IAL) { + dev_dbg(&i2c_imx->adapter.dev, "<%s> Arbitration lost\n", __func__); + i2c_imx_clear_irq(i2c_imx, I2SR_IAL); + + i2c_imx->i2csr = 0; + return -EAGAIN; + } + dev_dbg(&i2c_imx->adapter.dev, "<%s> TRX complete\n", __func__); i2c_imx->i2csr = 0; return 0; -- cgit v1.2.3 From 61e6fe59ede155881a622f5901551b1cc8748f6a Mon Sep 17 00:00:00 2001 From: Christian Eggers Date: Fri, 9 Oct 2020 13:03:20 +0200 Subject: i2c: imx: Don't generate STOP condition if arbitration has been lost If arbitration is lost, the master automatically changes to slave mode. I2SR_IBB may or may not be reset by hardware. Raising a STOP condition by resetting I2CR_MSTA has no effect and will not clear I2SR_IBB. So calling i2c_imx_bus_busy() is not required and would busy-wait until timeout. Signed-off-by: Christian Eggers Tested (not extensively) on Vybrid VF500 (Toradex VF50): Tested-by: Krzysztof Kozlowski Acked-by: Oleksij Rempel Cc: stable@vger.kernel.org # Requires trivial backporting, simple remove # the 3rd argument from the calls to # i2c_imx_bus_busy(). Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-imx.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index a2abae124342..e6f8d6e45a15 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -615,6 +615,8 @@ static void i2c_imx_stop(struct imx_i2c_struct *i2c_imx, bool atomic) /* Stop I2C transaction */ dev_dbg(&i2c_imx->adapter.dev, "<%s>\n", __func__); temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); + if (!(temp & I2CR_MSTA)) + i2c_imx->stopped = 1; temp &= ~(I2CR_MSTA | I2CR_MTX); if (i2c_imx->dma) temp &= ~I2CR_DMAEN; @@ -778,9 +780,12 @@ static int i2c_imx_dma_read(struct imx_i2c_struct *i2c_imx, */ dev_dbg(dev, "<%s> clear MSTA\n", __func__); temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); + if (!(temp & I2CR_MSTA)) + i2c_imx->stopped = 1; temp &= ~(I2CR_MSTA | I2CR_MTX); imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR); - i2c_imx_bus_busy(i2c_imx, 0, false); + if (!i2c_imx->stopped) + i2c_imx_bus_busy(i2c_imx, 0, false); } else { /* * For i2c master receiver repeat restart operation like: @@ -905,9 +910,12 @@ static int i2c_imx_read(struct imx_i2c_struct *i2c_imx, struct i2c_msg *msgs, dev_dbg(&i2c_imx->adapter.dev, "<%s> clear MSTA\n", __func__); temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); + if (!(temp & I2CR_MSTA)) + i2c_imx->stopped = 1; temp &= ~(I2CR_MSTA | I2CR_MTX); imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR); - i2c_imx_bus_busy(i2c_imx, 0, atomic); + if (!i2c_imx->stopped) + i2c_imx_bus_busy(i2c_imx, 0, atomic); } else { /* * For i2c master receiver repeat restart operation like: -- cgit v1.2.3 From f5da54187e33dce9bea63170667dbb0ca8d98194 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Tue, 1 Dec 2020 21:56:57 +0800 Subject: xsk: Replace datagram_poll by sock_poll_wait datagram_poll will judge the current socket status (EPOLLIN, EPOLLOUT) based on the traditional socket information (eg: sk_wmem_alloc), but this does not apply to xsk. So this patch uses sock_poll_wait instead of datagram_poll, and the mask is calculated by xsk_poll. Fixes: c497176cb2e4 ("xsk: add Rx receive functions and poll support") Signed-off-by: Xuan Zhuo Signed-off-by: Daniel Borkmann Acked-by: Magnus Karlsson Link: https://lore.kernel.org/bpf/e82f4697438cd63edbf271ebe1918db8261b7c09.1606555939.git.xuanzhuo@linux.alibaba.com --- net/xdp/xsk.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index b7b039bd9d03..9bbfd8adbb73 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -471,11 +471,13 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) static __poll_t xsk_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { - __poll_t mask = datagram_poll(file, sock, wait); + __poll_t mask = 0; struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct xsk_buff_pool *pool; + sock_poll_wait(file, sock, wait); + if (unlikely(!xsk_is_bound(xs))) return mask; -- cgit v1.2.3 From 3413f04141aa440c71da187755e8e22f5093ce83 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Tue, 1 Dec 2020 21:56:58 +0800 Subject: xsk: Change the tx writeable condition Modify the tx writeable condition from the queue is not full to the number of present tx queues is less than the half of the total number of queues. Because the tx queue not full is a very short time, this will cause a large number of EPOLLOUT events, and cause a large number of process wake up. Fixes: 35fcde7f8deb ("xsk: support for Tx") Signed-off-by: Xuan Zhuo Signed-off-by: Daniel Borkmann Acked-by: Magnus Karlsson Link: https://lore.kernel.org/bpf/508fef55188d4e1160747ead64c6dcda36735880.1606555939.git.xuanzhuo@linux.alibaba.com --- net/xdp/xsk.c | 16 +++++++++++++--- net/xdp/xsk_queue.h | 6 ++++++ 2 files changed, 19 insertions(+), 3 deletions(-) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 9bbfd8adbb73..62504471fd20 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -211,6 +211,14 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len, return 0; } +static bool xsk_tx_writeable(struct xdp_sock *xs) +{ + if (xskq_cons_present_entries(xs->tx) > xs->tx->nentries / 2) + return false; + + return true; +} + static bool xsk_is_bound(struct xdp_sock *xs) { if (READ_ONCE(xs->state) == XSK_BOUND) { @@ -296,7 +304,8 @@ void xsk_tx_release(struct xsk_buff_pool *pool) rcu_read_lock(); list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { __xskq_cons_release(xs->tx); - xs->sk.sk_write_space(&xs->sk); + if (xsk_tx_writeable(xs)) + xs->sk.sk_write_space(&xs->sk); } rcu_read_unlock(); } @@ -436,7 +445,8 @@ static int xsk_generic_xmit(struct sock *sk) out: if (sent_frame) - sk->sk_write_space(sk); + if (xsk_tx_writeable(xs)) + sk->sk_write_space(sk); mutex_unlock(&xs->mutex); return err; @@ -493,7 +503,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, if (xs->rx && !xskq_prod_is_empty(xs->rx)) mask |= EPOLLIN | EPOLLRDNORM; - if (xs->tx && !xskq_cons_is_full(xs->tx)) + if (xs->tx && xsk_tx_writeable(xs)) mask |= EPOLLOUT | EPOLLWRNORM; return mask; diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index cdb9cf3cd136..9e71b9f27679 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -264,6 +264,12 @@ static inline bool xskq_cons_is_full(struct xsk_queue *q) q->nentries; } +static inline u32 xskq_cons_present_entries(struct xsk_queue *q) +{ + /* No barriers needed since data is not accessed */ + return READ_ONCE(q->ring->producer) - READ_ONCE(q->ring->consumer); +} + /* Functions for producers */ static inline bool xskq_prod_is_full(struct xsk_queue *q) -- cgit v1.2.3 From 9261a1db80bc81dd445cd6dcfb466b632ad9faa8 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 26 Nov 2020 14:04:05 +0000 Subject: drm/i915/gt: Protect context lifetime with RCU Allow a brief period for continued access to a dead intel_context by deferring the release of the struct until after an RCU grace period. As we are using a dedicated slab cache for the contexts, we can defer the release of the slab pages via RCU, with the caveat that individual structs may be reused from the freelist within an RCU grace period. To handle that, we have to avoid clearing members of the zombie struct. This is required for a later patch to handle locking around virtual requests in the signaler, as those requests may want to move between engines and be destroyed while we are holding b->irq_lock on a physical engine. v2: Drop mutex_reinit(), if we never mark the mutex as destroyed we don't need to reset the debug code, at the loss of having the mutex debug code spot us attempting to destroy a locked mutex. v3: As the intended use will remain strongly referenced counted, with very little inflight access across reuse, drop the ctor. v4: Drop the unrequired change to remove the temporary reference around dropping the active context, and add back some more missing ctor operations. v5: The ctor is back. Tvrtko spotted that ce->signal_lock [introduced later] maybe accessed under RCU and so needs special care not to be reinitialised. v6: Don't mix SLAB_TYPESAFE_BY_RCU and RCU list iteration. Signed-off-by: Chris Wilson Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20201126140407.31952-3-chris@chris-wilson.co.uk (cherry picked from commit 14d1eaf08845c534963c83f754afe0cb14cb2512) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_context.c | 12 +++++++++--- drivers/gpu/drm/i915/gt/intel_context_types.h | 11 ++++++++++- 2 files changed, 19 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 92a3f25c4006..d3a835212167 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -25,11 +25,18 @@ static struct intel_context *intel_context_alloc(void) return kmem_cache_zalloc(global.slab_ce, GFP_KERNEL); } -void intel_context_free(struct intel_context *ce) +static void rcu_context_free(struct rcu_head *rcu) { + struct intel_context *ce = container_of(rcu, typeof(*ce), rcu); + kmem_cache_free(global.slab_ce, ce); } +void intel_context_free(struct intel_context *ce) +{ + call_rcu(&ce->rcu, rcu_context_free); +} + struct intel_context * intel_context_create(struct intel_engine_cs *engine) { @@ -356,8 +363,7 @@ static int __intel_context_active(struct i915_active *active) } void -intel_context_init(struct intel_context *ce, - struct intel_engine_cs *engine) +intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine) { GEM_BUG_ON(!engine->cops); GEM_BUG_ON(!engine->gt->vm); diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 552cb57a2e8c..20cb5835d1c3 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -44,7 +44,16 @@ struct intel_context_ops { }; struct intel_context { - struct kref ref; + /* + * Note: Some fields may be accessed under RCU. + * + * Unless otherwise noted a field can safely be assumed to be protected + * by strong reference counting. + */ + union { + struct kref ref; /* no kref_get_unless_zero()! */ + struct rcu_head rcu; + }; struct intel_engine_cs *engine; struct intel_engine_cs *inflight; -- cgit v1.2.3 From 2bfdf302465a5eab941e551e2869a96bb473f66f Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 26 Nov 2020 14:04:06 +0000 Subject: drm/i915/gt: Split the breadcrumb spinlock between global and contexts As we funnel more and more contexts into the breadcrumbs on an engine, the hold time of b->irq_lock grows. As we may then contend with the b->irq_lock during request submission, this increases the burden upon the engine->active.lock and so directly impacts both our execution latency and client latency. If we split the b->irq_lock by introducing a per-context spinlock to manage the signalers within a context, we then only need the b->irq_lock for enabling/disabling the interrupt and can avoid taking the lock for walking the list of contexts within the signal worker. Even with the current setup, this greatly reduces the number of times we have to take and fight for b->irq_lock. Furthermore, this closes the race between enabling the signaling context while it is in the process of being signaled and removed: <4>[ 416.208555] list_add corruption. prev->next should be next (ffff8881951d5910), but was dead000000000100. (prev=ffff8882781bb870). <4>[ 416.208573] WARNING: CPU: 7 PID: 0 at lib/list_debug.c:28 __list_add_valid+0x4d/0x70 <4>[ 416.208575] Modules linked in: i915(+) vgem snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio mei_hdcp x86_pkg_temp_thermal coretemp ax88179_178a usbnet mii crct10dif_pclmul snd_intel_dspcfg crc32_pclmul snd_hda_codec snd_hwdep ghash_clmulni_intel snd_hda_core e1000e snd_pcm ptp pps_core mei_me mei prime_numbers intel_lpss_pci [last unloaded: i915] <4>[ 416.208611] CPU: 7 PID: 0 Comm: swapper/7 Tainted: G U 5.8.0-CI-CI_DRM_8852+ #1 <4>[ 416.208614] Hardware name: Intel Corporation Ice Lake Client Platform/IceLake Y LPDDR4x T4 RVP TLC, BIOS ICLSFWR1.R00.3212.A00.1905212112 05/21/2019 <4>[ 416.208627] RIP: 0010:__list_add_valid+0x4d/0x70 <4>[ 416.208631] Code: c3 48 89 d1 48 c7 c7 60 18 33 82 48 89 c2 e8 ea e0 b6 ff 0f 0b 31 c0 c3 48 89 c1 4c 89 c6 48 c7 c7 b0 18 33 82 e8 d3 e0 b6 ff <0f> 0b 31 c0 c3 48 89 f2 4c 89 c1 48 89 fe 48 c7 c7 00 19 33 82 e8 <4>[ 416.208633] RSP: 0018:ffffc90000280e18 EFLAGS: 00010086 <4>[ 416.208636] RAX: 0000000000000000 RBX: ffff888250a44880 RCX: 0000000000000105 <4>[ 416.208639] RDX: 0000000000000105 RSI: ffffffff82320c5b RDI: 00000000ffffffff <4>[ 416.208641] RBP: ffff8882781bb870 R08: 0000000000000000 R09: 0000000000000001 <4>[ 416.208643] R10: 00000000054d2957 R11: 000000006abbd991 R12: ffff8881951d58c8 <4>[ 416.208646] R13: ffff888286073880 R14: ffff888286073848 R15: ffff8881951d5910 <4>[ 416.208669] FS: 0000000000000000(0000) GS:ffff88829c180000(0000) knlGS:0000000000000000 <4>[ 416.208671] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 416.208673] CR2: 0000556231326c48 CR3: 0000000005610001 CR4: 0000000000760ee0 <4>[ 416.208675] PKRU: 55555554 <4>[ 416.208677] Call Trace: <4>[ 416.208679] <4>[ 416.208751] i915_request_enable_breadcrumb+0x278/0x400 [i915] <4>[ 416.208839] __i915_request_submit+0xca/0x2a0 [i915] <4>[ 416.208892] __execlists_submission_tasklet+0x480/0x1830 [i915] <4>[ 416.208942] execlists_submission_tasklet+0xc4/0x130 [i915] <4>[ 416.208947] tasklet_action_common.isra.17+0x6c/0x1c0 <4>[ 416.208954] __do_softirq+0xdf/0x498 <4>[ 416.208960] ? handle_fasteoi_irq+0x150/0x150 <4>[ 416.208964] asm_call_on_stack+0xf/0x20 <4>[ 416.208966] <4>[ 416.208969] do_softirq_own_stack+0xa1/0xc0 <4>[ 416.208972] irq_exit_rcu+0xb5/0xc0 <4>[ 416.208976] common_interrupt+0xf7/0x260 <4>[ 416.208980] asm_common_interrupt+0x1e/0x40 <4>[ 416.208985] RIP: 0010:cpuidle_enter_state+0xb6/0x410 <4>[ 416.208987] Code: 00 31 ff e8 9c 3e 89 ff 80 7c 24 0b 00 74 12 9c 58 f6 c4 02 0f 85 31 03 00 00 31 ff e8 e3 6c 90 ff e8 fe a4 94 ff fb 45 85 ed <0f> 88 c7 02 00 00 49 63 c5 4c 2b 24 24 48 8d 14 40 48 8d 14 90 48 <4>[ 416.208989] RSP: 0018:ffffc90000143e70 EFLAGS: 00000206 <4>[ 416.208991] RAX: 0000000000000007 RBX: ffffe8ffffda8070 RCX: 0000000000000000 <4>[ 416.208993] RDX: 0000000000000000 RSI: ffffffff8238b4ee RDI: ffffffff8233184f <4>[ 416.208995] RBP: ffffffff826b4e00 R08: 0000000000000000 R09: 0000000000000000 <4>[ 416.208997] R10: 0000000000000001 R11: 0000000000000000 R12: 00000060e7f24a8f <4>[ 416.208998] R13: 0000000000000003 R14: 0000000000000003 R15: 0000000000000003 <4>[ 416.209012] cpuidle_enter+0x24/0x40 <4>[ 416.209016] do_idle+0x22f/0x2d0 <4>[ 416.209022] cpu_startup_entry+0x14/0x20 <4>[ 416.209025] start_secondary+0x158/0x1a0 <4>[ 416.209030] secondary_startup_64+0xa4/0xb0 <4>[ 416.209039] irq event stamp: 10186977 <4>[ 416.209042] hardirqs last enabled at (10186976): [] tasklet_action_common.isra.17+0xe3/0x1c0 <4>[ 416.209044] hardirqs last disabled at (10186977): [] _raw_spin_lock_irqsave+0xd/0x50 <4>[ 416.209047] softirqs last enabled at (10186968): [] irq_enter_rcu+0x6a/0x70 <4>[ 416.209049] softirqs last disabled at (10186969): [] asm_call_on_stack+0xf/0x20 <4>[ 416.209317] list_del corruption, ffff8882781bb870->next is LIST_POISON1 (dead000000000100) <4>[ 416.209317] WARNING: CPU: 7 PID: 46 at lib/list_debug.c:47 __list_del_entry_valid+0x4e/0x90 <4>[ 416.209317] Modules linked in: i915(+) vgem snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio mei_hdcp x86_pkg_temp_thermal coretemp ax88179_178a usbnet mii crct10dif_pclmul snd_intel_dspcfg crc32_pclmul snd_hda_codec snd_hwdep ghash_clmulni_intel snd_hda_core e1000e snd_pcm ptp pps_core mei_me mei prime_numbers intel_lpss_pci [last unloaded: i915] <4>[ 416.209317] CPU: 7 PID: 46 Comm: ksoftirqd/7 Tainted: G U W 5.8.0-CI-CI_DRM_8852+ #1 <4>[ 416.209317] Hardware name: Intel Corporation Ice Lake Client Platform/IceLake Y LPDDR4x T4 RVP TLC, BIOS ICLSFWR1.R00.3212.A00.1905212112 05/21/2019 <4>[ 416.209317] RIP: 0010:__list_del_entry_valid+0x4e/0x90 <4>[ 416.209317] Code: 2e 48 8b 32 48 39 fe 75 3a 48 8b 50 08 48 39 f2 75 48 b8 01 00 00 00 c3 48 89 fe 48 89 c2 48 c7 c7 38 19 33 82 e8 62 e0 b6 ff <0f> 0b 31 c0 c3 48 89 fe 48 c7 c7 70 19 33 82 e8 4e e0 b6 ff 0f 0b <4>[ 416.209317] RSP: 0018:ffffc90000280de8 EFLAGS: 00010086 <4>[ 416.209317] RAX: 0000000000000000 RBX: ffff8882781bb848 RCX: 0000000000010104 <4>[ 416.209317] RDX: 0000000000010104 RSI: ffffffff8238b4ee RDI: 00000000ffffffff <4>[ 416.209317] RBP: ffff8882781bb880 R08: 0000000000000000 R09: 0000000000000001 <4>[ 416.209317] R10: 000000009fb6666e R11: 00000000feca9427 R12: ffffc90000280e18 <4>[ 416.209317] R13: ffff8881951d5930 R14: dead0000000000d8 R15: ffff8882781bb880 <4>[ 416.209317] FS: 0000000000000000(0000) GS:ffff88829c180000(0000) knlGS:0000000000000000 <4>[ 416.209317] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 416.209317] CR2: 0000556231326c48 CR3: 0000000005610001 CR4: 0000000000760ee0 <4>[ 416.209317] PKRU: 55555554 <4>[ 416.209317] Call Trace: <4>[ 416.209317] <4>[ 416.209317] remove_signaling_context.isra.13+0xd/0x70 [i915] <4>[ 416.209513] signal_irq_work+0x1f7/0x4b0 [i915] This is caused by virtual engines where although we take the breadcrumb lock on each of the active engines, they may be different engines on different requests, It turns out that the b->irq_lock was not a sufficient proxy for the engine->active.lock in the case of more than one request, so introduce an explicit lock around ce->signals. v2: ce->signal_lock is acquired with only RCU protection and so must be treated carefully and not cleared during reallocation. We also then need to confirm that the ce we lock is the same as we found in the breadcrumb list. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2276 Fixes: c18636f76344 ("drm/i915: Remove requirement for holding i915_request.lock for breadcrumbs") Fixes: 2854d866327a ("drm/i915/gt: Replace intel_engine_transfer_stale_breadcrumbs") Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20201126140407.31952-4-chris@chris-wilson.co.uk (cherry picked from commit c744d50363b714783bbc88d986cc16def13710f7) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 168 ++++++++++------------ drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h | 6 +- drivers/gpu/drm/i915/gt/intel_context.c | 3 +- drivers/gpu/drm/i915/gt/intel_context_types.h | 12 +- drivers/gpu/drm/i915/i915_request.h | 6 +- 5 files changed, 90 insertions(+), 105 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index cf6e05ea4d8f..a24cc1ff08a0 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -101,18 +101,37 @@ static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) intel_gt_pm_put_async(b->irq_engine->gt); } +static void intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) +{ + spin_lock(&b->irq_lock); + if (b->irq_armed) + __intel_breadcrumbs_disarm_irq(b); + spin_unlock(&b->irq_lock); +} + static void add_signaling_context(struct intel_breadcrumbs *b, struct intel_context *ce) { - intel_context_get(ce); - list_add_tail(&ce->signal_link, &b->signalers); + lockdep_assert_held(&ce->signal_lock); + + spin_lock(&b->signalers_lock); + list_add_rcu(&ce->signal_link, &b->signalers); + spin_unlock(&b->signalers_lock); } -static void remove_signaling_context(struct intel_breadcrumbs *b, +static bool remove_signaling_context(struct intel_breadcrumbs *b, struct intel_context *ce) { - list_del(&ce->signal_link); - intel_context_put(ce); + lockdep_assert_held(&ce->signal_lock); + + if (!list_empty(&ce->signals)) + return false; + + spin_lock(&b->signalers_lock); + list_del_rcu(&ce->signal_link); + spin_unlock(&b->signalers_lock); + + return true; } static inline bool __request_completed(const struct i915_request *rq) @@ -175,6 +194,8 @@ static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl) static bool __signal_request(struct i915_request *rq) { + GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)); + if (!__dma_fence_signal(&rq->fence)) { i915_request_put(rq); return false; @@ -195,15 +216,12 @@ static void signal_irq_work(struct irq_work *work) struct intel_breadcrumbs *b = container_of(work, typeof(*b), irq_work); const ktime_t timestamp = ktime_get(); struct llist_node *signal, *sn; - struct intel_context *ce, *cn; - struct list_head *pos, *next; + struct intel_context *ce; signal = NULL; if (unlikely(!llist_empty(&b->signaled_requests))) signal = llist_del_all(&b->signaled_requests); - spin_lock(&b->irq_lock); - /* * Keep the irq armed until the interrupt after all listeners are gone. * @@ -229,47 +247,44 @@ static void signal_irq_work(struct irq_work *work) * interrupt draw less ire from other users of the system and tools * like powertop. */ - if (!signal && b->irq_armed && list_empty(&b->signalers)) - __intel_breadcrumbs_disarm_irq(b); + if (!signal && READ_ONCE(b->irq_armed) && list_empty(&b->signalers)) + intel_breadcrumbs_disarm_irq(b); - list_for_each_entry_safe(ce, cn, &b->signalers, signal_link) { - GEM_BUG_ON(list_empty(&ce->signals)); + rcu_read_lock(); + list_for_each_entry_rcu(ce, &b->signalers, signal_link) { + struct i915_request *rq; - list_for_each_safe(pos, next, &ce->signals) { - struct i915_request *rq = - list_entry(pos, typeof(*rq), signal_link); + list_for_each_entry_rcu(rq, &ce->signals, signal_link) { + bool release; - GEM_BUG_ON(!check_signal_order(ce, rq)); if (!__request_completed(rq)) break; + if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, + &rq->fence.flags)) + break; + /* * Queue for execution after dropping the signaling * spinlock as the callback chain may end up adding * more signalers to the same context or engine. */ - clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); + spin_lock(&ce->signal_lock); + list_del_rcu(&rq->signal_link); + release = remove_signaling_context(b, ce); + spin_unlock(&ce->signal_lock); + if (__signal_request(rq)) /* We own signal_node now, xfer to local list */ signal = slist_add(&rq->signal_node, signal); - } - /* - * We process the list deletion in bulk, only using a list_add - * (not list_move) above but keeping the status of - * rq->signal_link known with the I915_FENCE_FLAG_SIGNAL bit. - */ - if (!list_is_first(pos, &ce->signals)) { - /* Advance the list to the first incomplete request */ - __list_del_many(&ce->signals, pos); - if (&ce->signals == pos) { /* now empty */ + if (release) { add_retire(b, ce->timeline); - remove_signaling_context(b, ce); + intel_context_put(ce); } } } - - spin_unlock(&b->irq_lock); + rcu_read_unlock(); llist_for_each_safe(signal, sn, signal) { struct i915_request *rq = @@ -298,14 +313,15 @@ intel_breadcrumbs_create(struct intel_engine_cs *irq_engine) if (!b) return NULL; - spin_lock_init(&b->irq_lock); + b->irq_engine = irq_engine; + + spin_lock_init(&b->signalers_lock); INIT_LIST_HEAD(&b->signalers); init_llist_head(&b->signaled_requests); + spin_lock_init(&b->irq_lock); init_irq_work(&b->irq_work, signal_irq_work); - b->irq_engine = irq_engine; - return b; } @@ -347,9 +363,9 @@ void intel_breadcrumbs_free(struct intel_breadcrumbs *b) kfree(b); } -static void insert_breadcrumb(struct i915_request *rq, - struct intel_breadcrumbs *b) +static void insert_breadcrumb(struct i915_request *rq) { + struct intel_breadcrumbs *b = READ_ONCE(rq->engine)->breadcrumbs; struct intel_context *ce = rq->context; struct list_head *pos; @@ -371,6 +387,7 @@ static void insert_breadcrumb(struct i915_request *rq, } if (list_empty(&ce->signals)) { + intel_context_get(ce); add_signaling_context(b, ce); pos = &ce->signals; } else { @@ -396,8 +413,9 @@ static void insert_breadcrumb(struct i915_request *rq, break; } } - list_add(&rq->signal_link, pos); + list_add_rcu(&rq->signal_link, pos); GEM_BUG_ON(!check_signal_order(ce, rq)); + GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags)); set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); /* @@ -410,7 +428,7 @@ static void insert_breadcrumb(struct i915_request *rq, bool i915_request_enable_breadcrumb(struct i915_request *rq) { - struct intel_breadcrumbs *b; + struct intel_context *ce = rq->context; /* Serialises with i915_request_retire() using rq->lock */ if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags)) @@ -425,67 +443,30 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq) if (!test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) return true; - /* - * rq->engine is locked by rq->engine->active.lock. That however - * is not known until after rq->engine has been dereferenced and - * the lock acquired. Hence we acquire the lock and then validate - * that rq->engine still matches the lock we hold for it. - * - * Here, we are using the breadcrumb lock as a proxy for the - * rq->engine->active.lock, and we know that since the breadcrumb - * will be serialised within i915_request_submit/i915_request_unsubmit, - * the engine cannot change while active as long as we hold the - * breadcrumb lock on that engine. - * - * From the dma_fence_enable_signaling() path, we are outside of the - * request submit/unsubmit path, and so we must be more careful to - * acquire the right lock. - */ - b = READ_ONCE(rq->engine)->breadcrumbs; - spin_lock(&b->irq_lock); - while (unlikely(b != READ_ONCE(rq->engine)->breadcrumbs)) { - spin_unlock(&b->irq_lock); - b = READ_ONCE(rq->engine)->breadcrumbs; - spin_lock(&b->irq_lock); - } - - /* - * Now that we are finally serialised with request submit/unsubmit, - * [with b->irq_lock] and with i915_request_retire() [via checking - * SIGNALED with rq->lock] confirm the request is indeed active. If - * it is no longer active, the breadcrumb will be attached upon - * i915_request_submit(). - */ + spin_lock(&ce->signal_lock); if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) - insert_breadcrumb(rq, b); - - spin_unlock(&b->irq_lock); + insert_breadcrumb(rq); + spin_unlock(&ce->signal_lock); return true; } void i915_request_cancel_breadcrumb(struct i915_request *rq) { - struct intel_breadcrumbs *b = rq->engine->breadcrumbs; + struct intel_context *ce = rq->context; + bool release; - /* - * We must wait for b->irq_lock so that we know the interrupt handler - * has released its reference to the intel_context and has completed - * the DMA_FENCE_FLAG_SIGNALED_BIT/I915_FENCE_FLAG_SIGNAL dance (if - * required). - */ - spin_lock(&b->irq_lock); - if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) { - struct intel_context *ce = rq->context; + if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) + return; - list_del(&rq->signal_link); - if (list_empty(&ce->signals)) - remove_signaling_context(b, ce); + spin_lock(&ce->signal_lock); + list_del_rcu(&rq->signal_link); + release = remove_signaling_context(rq->engine->breadcrumbs, ce); + spin_unlock(&ce->signal_lock); + if (release) + intel_context_put(ce); - clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); - i915_request_put(rq); - } - spin_unlock(&b->irq_lock); + i915_request_put(rq); } static void print_signals(struct intel_breadcrumbs *b, struct drm_printer *p) @@ -495,18 +476,17 @@ static void print_signals(struct intel_breadcrumbs *b, struct drm_printer *p) drm_printf(p, "Signals:\n"); - spin_lock_irq(&b->irq_lock); - list_for_each_entry(ce, &b->signalers, signal_link) { - list_for_each_entry(rq, &ce->signals, signal_link) { + rcu_read_lock(); + list_for_each_entry_rcu(ce, &b->signalers, signal_link) { + list_for_each_entry_rcu(rq, &ce->signals, signal_link) drm_printf(p, "\t[%llx:%llx%s] @ %dms\n", rq->fence.context, rq->fence.seqno, i915_request_completed(rq) ? "!" : i915_request_started(rq) ? "*" : "", jiffies_to_msecs(jiffies - rq->emitted_jiffies)); - } } - spin_unlock_irq(&b->irq_lock); + rcu_read_unlock(); } void intel_engine_print_breadcrumbs(struct intel_engine_cs *engine, diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h index 3fa19820b37a..a74bb3062bd8 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h @@ -29,18 +29,16 @@ * the overhead of waking that client is much preferred. */ struct intel_breadcrumbs { - spinlock_t irq_lock; /* protects the lists used in hardirq context */ - /* Not all breadcrumbs are attached to physical HW */ struct intel_engine_cs *irq_engine; + spinlock_t signalers_lock; /* protects the list of signalers */ struct list_head signalers; struct llist_head signaled_requests; + spinlock_t irq_lock; /* protects the interrupt from hardirq context */ struct irq_work irq_work; /* for use from inside irq_lock */ - unsigned int irq_enabled; - bool irq_armed; }; diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index d3a835212167..349e7fa1488d 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -379,7 +379,8 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine) ce->vm = i915_vm_get(engine->gt->vm); - INIT_LIST_HEAD(&ce->signal_link); + /* NB ce->signal_link/lock is used under RCU */ + spin_lock_init(&ce->signal_lock); INIT_LIST_HEAD(&ce->signals); mutex_init(&ce->pin_mutex); diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 20cb5835d1c3..52fa9c132746 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -25,6 +25,7 @@ DECLARE_EWMA(runtime, 3, 8); struct i915_gem_context; struct i915_gem_ww_ctx; struct i915_vma; +struct intel_breadcrumbs; struct intel_context; struct intel_ring; @@ -63,8 +64,15 @@ struct intel_context { struct i915_address_space *vm; struct i915_gem_context __rcu *gem_context; - struct list_head signal_link; - struct list_head signals; + /* + * @signal_lock protects the list of requests that need signaling, + * @signals. While there are any requests that need signaling, + * we add the context to the breadcrumbs worker, and remove it + * upon completion/cancellation of the last request. + */ + struct list_head signal_link; /* Accessed under RCU */ + struct list_head signals; /* Guarded by signal_lock */ + spinlock_t signal_lock; /* protects signals, the list of requests */ struct i915_vma *state; struct intel_ring *ring; diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 874af6db6103..620b6fab2c5c 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -177,10 +177,8 @@ struct i915_request { struct intel_ring *ring; struct intel_timeline __rcu *timeline; - union { - struct list_head signal_link; - struct llist_node signal_node; - }; + struct list_head signal_link; + struct llist_node signal_node; /* * The rcu epoch of when this request was allocated. Used to judiciously -- cgit v1.2.3 From 78b2eb8a1f10f366681acad8d21c974c1f66791a Mon Sep 17 00:00:00 2001 From: Venkata Ramana Nayana Date: Fri, 27 Nov 2020 12:07:16 +0000 Subject: drm/i915/gt: Retain default context state across shrinking As we use a shmemfs file to hold the context state, when not in use it may be swapped out, such as across suspend. Since we wrote into the shmemfs without marking the pages as dirty, the contents may be dropped instead of being written back to swap. On re-using the shmemfs file, such as creating a new context after resume, the contents of that file were likely garbage and so the new context could then hang the GPU. Simply mark the page as being written when copying into the shmemfs file, and it the new contents will be retained across swapout. Fixes: be1cb55a07bf ("drm/i915/gt: Keep a no-frills swappable copy of the default context state") Cc: Sudeep Dutt Cc: Matthew Auld Cc: Tvrtko Ursulin Cc: Ramalingam C Signed-off-by: CQ Tang Signed-off-by: Venkata Ramana Nayana Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson Cc: # v5.8+ Link: https://patchwork.freedesktop.org/patch/msgid/20201127120718.454037-161-matthew.auld@intel.com (cherry picked from commit a9d71f76ccfd309f3bd5f7c9b60e91a4decae792) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/shmem_utils.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c index f011ea42487e..463af675fadd 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.c +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c @@ -103,10 +103,13 @@ static int __shmem_rw(struct file *file, loff_t off, return PTR_ERR(page); vaddr = kmap(page); - if (write) + if (write) { memcpy(vaddr + offset_in_page(off), ptr, this); - else + set_page_dirty(page); + } else { memcpy(ptr, vaddr + offset_in_page(off), this); + } + mark_page_accessed(page); kunmap(page); put_page(page); -- cgit v1.2.3 From aff76ab795364569b1cac58c1d0bc7df956e3899 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 24 Nov 2020 18:35:21 +0000 Subject: drm/i915/gt: Limit frequency drop to RPe on parking We treat idling the GT (intel_rps_park) as a downclock event, and reduce the frequency we intend to restart the GT with. Since the two workloads are likely related (e.g. a compositor rendering every 16ms), we want to carry the frequency and load information from across the idling. However, we do also need to update the frequencies so that workloads that run for less than 1ms are autotuned by RPS (otherwise we leave compositors running at max clocks, draining excess power). Conversely, if we try to run too slowly, the next workload has to run longer. Since there is a hysteresis in the power graph, below a certain frequency running a short workload for longer consumes more energy than running it slightly higher for less time. The exact balance point is unknown beforehand, but measurements with 30fps media playback indicate that RPe is a better choice. Reported-by: Edward Baker Tested-by: Edward Baker Fixes: 043cd2d14ede ("drm/i915/gt: Leave rps->cur_freq on unpark") Signed-off-by: Chris Wilson Cc: Edward Baker Cc: Andi Shyti Cc: Lyude Paul Cc: # v5.8+ Reviewed-by: Rodrigo Vivi Reviewed-by: Andi Shyti Link: https://patchwork.freedesktop.org/patch/msgid/20201124183521.28623-1-chris@chris-wilson.co.uk (cherry picked from commit f7ed83cc1925f0b8ce2515044d674354035c3af9) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_rps.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index e6a00eea0631..c1c9cc0ad3b9 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -883,6 +883,10 @@ void intel_rps_park(struct intel_rps *rps) adj = -2; rps->last_adj = adj; rps->cur_freq = max_t(int, rps->cur_freq + adj, rps->min_freq); + if (rps->cur_freq < rps->efficient_freq) { + rps->cur_freq = rps->efficient_freq; + rps->last_adj = 0; + } GT_TRACE(rps_to_gt(rps), "park:%x\n", rps->cur_freq); } -- cgit v1.2.3 From 37eade64eb11c6d548c9a7030ccc655decfb8fa0 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 6 Nov 2020 14:55:27 -0800 Subject: drm/i915/display: return earlier from intel_modeset_init() without display MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit !HAS_DISPLAY() implies !HAS_OVERLAY(), skipping overlay setup anyway, so return earlier from intel_modeset_init() for clarity. Cc: Ville Syrjälä Signed-off-by: Jani Nikula Signed-off-by: Lucas De Marchi Reviewed-by: José Roberto de Souza Link: https://patchwork.freedesktop.org/patch/msgid/20201106225531.920641-4-lucas.demarchi@intel.com (cherry picked from commit 71c8415d0daa78ef1295743d0e11ba0214d0a9b9) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/display/intel_display.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 99e682563d47..c0d920f596f4 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -18039,11 +18039,11 @@ int intel_modeset_init(struct drm_i915_private *i915) { int ret; - intel_overlay_setup(i915); - if (!HAS_DISPLAY(i915)) return 0; + intel_overlay_setup(i915); + ret = intel_fbdev_init(&i915->drm); if (ret) return ret; -- cgit v1.2.3 From ccc9e67ab26feda7e62749bb54c05d7abe07dca9 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 25 Nov 2020 19:30:32 +0000 Subject: drm/i915/display: Defer initial modeset until after GGTT is initialised MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Prior to sanitizing the GGTT, the only operations allowed in intel_display_init_nogem() are those to reserve the preallocated (and active) regions in the GGTT leftover from the BIOS. Trying to allocate a GGTT vma (such as intel_pin_and_fence_fb_obj during the initial modeset) may then conflict with other preallocated regions that have not yet been protected. Move the initial modesetting from the end of init_nogem to the beginning of init so that any vma pinning (either framebuffers or DSB, for example), is after the GGTT is ready to handle it. This will prevent the DSB object from being destroyed too early: [ 53.449241] BUG: KASAN: use-after-free in i915_init_ggtt+0x324/0x9e0 [i915] [ 53.449309] Read of size 8 at addr ffff88811b1e8070 by task systemd-udevd/345 [ 53.449399] CPU: 1 PID: 345 Comm: systemd-udevd Tainted: G W 5.10.0-rc5+ #12 [ 53.449409] Call Trace: [ 53.449418] dump_stack+0x9a/0xcc [ 53.449558] ? i915_init_ggtt+0x324/0x9e0 [i915] [ 53.449565] print_address_description.constprop.0+0x3e/0x60 [ 53.449577] ? _raw_spin_lock_irqsave+0x4e/0x50 [ 53.449718] ? i915_init_ggtt+0x324/0x9e0 [i915] [ 53.449849] ? i915_init_ggtt+0x324/0x9e0 [i915] [ 53.449857] kasan_report.cold+0x1f/0x37 [ 53.449993] ? i915_init_ggtt+0x324/0x9e0 [i915] [ 53.450130] i915_init_ggtt+0x324/0x9e0 [i915] [ 53.450273] ? i915_ggtt_suspend+0x1f0/0x1f0 [i915] [ 53.450281] ? static_obj+0x69/0x80 [ 53.450289] ? lockdep_init_map_waits+0xa9/0x310 [ 53.450431] ? intel_wopcm_init+0x96/0x3d0 [i915] [ 53.450581] ? i915_gem_init+0x75/0x2d0 [i915] [ 53.450720] i915_gem_init+0x75/0x2d0 [i915] [ 53.450852] i915_driver_probe+0x8c2/0x1210 [i915] [ 53.450993] ? i915_pm_prepare+0x630/0x630 [i915] [ 53.451006] ? check_chain_key+0x1e7/0x2e0 [ 53.451025] ? __pm_runtime_resume+0x58/0xb0 [ 53.451157] i915_pci_probe+0xa6/0x2b0 [i915] [ 53.451285] ? i915_pci_remove+0x40/0x40 [i915] [ 53.451295] ? lockdep_hardirqs_on_prepare+0x124/0x230 [ 53.451302] ? _raw_spin_unlock_irqrestore+0x42/0x50 [ 53.451309] ? lockdep_hardirqs_on+0xbf/0x130 [ 53.451315] ? preempt_count_sub+0xf/0xb0 [ 53.451321] ? _raw_spin_unlock_irqrestore+0x2f/0x50 [ 53.451335] pci_device_probe+0xf9/0x190 [ 53.451350] really_probe+0x17f/0x5b0 [ 53.451365] driver_probe_device+0x13a/0x1c0 [ 53.451376] device_driver_attach+0x82/0x90 [ 53.451386] ? device_driver_attach+0x90/0x90 [ 53.451391] __driver_attach+0xab/0x190 [ 53.451401] ? device_driver_attach+0x90/0x90 [ 53.451407] bus_for_each_dev+0xe4/0x140 [ 53.451414] ? subsys_dev_iter_exit+0x10/0x10 [ 53.451423] ? __list_add_valid+0x2b/0xa0 [ 53.451440] bus_add_driver+0x227/0x2e0 [ 53.451454] driver_register+0xd3/0x150 [ 53.451585] i915_init+0x92/0xac [i915] [ 53.451592] ? 0xffffffffa0a20000 [ 53.451598] do_one_initcall+0xb6/0x3b0 [ 53.451606] ? trace_event_raw_event_initcall_finish+0x150/0x150 [ 53.451614] ? __kasan_kmalloc.constprop.0+0xc2/0xd0 [ 53.451627] ? kmem_cache_alloc_trace+0x4a4/0x8e0 [ 53.451634] ? kasan_unpoison_shadow+0x33/0x40 [ 53.451649] do_init_module+0xf8/0x350 [ 53.451662] load_module+0x43de/0x47f0 [ 53.451716] ? module_frob_arch_sections+0x20/0x20 [ 53.451731] ? rw_verify_area+0x5f/0x130 [ 53.451780] ? __do_sys_finit_module+0x10d/0x1a0 [ 53.451785] __do_sys_finit_module+0x10d/0x1a0 [ 53.451792] ? __ia32_sys_init_module+0x40/0x40 [ 53.451800] ? seccomp_do_user_notification.isra.0+0x5c0/0x5c0 [ 53.451829] ? rcu_read_lock_bh_held+0xb0/0xb0 [ 53.451835] ? mark_held_locks+0x24/0x90 [ 53.451856] do_syscall_64+0x33/0x80 [ 53.451863] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.451868] RIP: 0033:0x7fde09b4470d [ 53.451875] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 53 f7 0c 00 f7 d8 64 89 01 48 [ 53.451880] RSP: 002b:00007ffd6abc1718 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 [ 53.451890] RAX: ffffffffffffffda RBX: 000056444e528150 RCX: 00007fde09b4470d [ 53.451895] RDX: 0000000000000000 RSI: 00007fde09a21ded RDI: 000000000000000f [ 53.451899] RBP: 0000000000020000 R08: 0000000000000000 R09: 0000000000000000 [ 53.451904] R10: 000000000000000f R11: 0000000000000246 R12: 00007fde09a21ded [ 53.451909] R13: 0000000000000000 R14: 000056444e329200 R15: 000056444e528150 [ 53.451957] Allocated by task 345: [ 53.451995] kasan_save_stack+0x1b/0x40 [ 53.452001] __kasan_kmalloc.constprop.0+0xc2/0xd0 [ 53.452006] kmem_cache_alloc+0x1cd/0x8d0 [ 53.452146] i915_vma_instance+0x126/0xb70 [i915] [ 53.452304] i915_gem_object_ggtt_pin_ww+0x222/0x3f0 [i915] [ 53.452446] intel_dsb_prepare+0x14f/0x230 [i915] [ 53.452588] intel_atomic_commit+0x183/0x690 [i915] [ 53.452730] intel_initial_commit+0x2bc/0x2f0 [i915] [ 53.452871] intel_modeset_init_nogem+0xa02/0x2af0 [i915] [ 53.452995] i915_driver_probe+0x8af/0x1210 [i915] [ 53.453120] i915_pci_probe+0xa6/0x2b0 [i915] [ 53.453125] pci_device_probe+0xf9/0x190 [ 53.453131] really_probe+0x17f/0x5b0 [ 53.453136] driver_probe_device+0x13a/0x1c0 [ 53.453142] device_driver_attach+0x82/0x90 [ 53.453148] __driver_attach+0xab/0x190 [ 53.453153] bus_for_each_dev+0xe4/0x140 [ 53.453158] bus_add_driver+0x227/0x2e0 [ 53.453164] driver_register+0xd3/0x150 [ 53.453286] i915_init+0x92/0xac [i915] [ 53.453292] do_one_initcall+0xb6/0x3b0 [ 53.453297] do_init_module+0xf8/0x350 [ 53.453302] load_module+0x43de/0x47f0 [ 53.453307] __do_sys_finit_module+0x10d/0x1a0 [ 53.453312] do_syscall_64+0x33/0x80 [ 53.453318] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.453345] Freed by task 82: [ 53.453379] kasan_save_stack+0x1b/0x40 [ 53.453384] kasan_set_track+0x1c/0x30 [ 53.453389] kasan_set_free_info+0x1b/0x30 [ 53.453394] __kasan_slab_free+0x112/0x160 [ 53.453399] kmem_cache_free+0xb2/0x3f0 [ 53.453536] i915_gem_flush_free_objects+0x31a/0x3b0 [i915] [ 53.453542] process_one_work+0x519/0x9f0 [ 53.453547] worker_thread+0x75/0x5c0 [ 53.453552] kthread+0x1da/0x230 [ 53.453557] ret_from_fork+0x22/0x30 [ 53.453584] The buggy address belongs to the object at ffff88811b1e8040 which belongs to the cache i915_vma of size 968 [ 53.453692] The buggy address is located 48 bytes inside of 968-byte region [ffff88811b1e8040, ffff88811b1e8408) [ 53.453792] The buggy address belongs to the page: [ 53.453842] page:00000000b35f7048 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88811b1ef940 pfn:0x11b1e8 [ 53.453847] head:00000000b35f7048 order:3 compound_mapcount:0 compound_pincount:0 [ 53.453853] flags: 0x8000000000010200(slab|head) [ 53.453860] raw: 8000000000010200 ffff888115596248 ffff888115596248 ffff8881155b6340 [ 53.453866] raw: ffff88811b1ef940 0000000000170001 00000001ffffffff 0000000000000000 [ 53.453870] page dumped because: kasan: bad access detected [ 53.453895] Memory state around the buggy address: [ 53.453944] ffff88811b1e7f00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 53.454011] ffff88811b1e7f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 53.454079] >ffff88811b1e8000: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb [ 53.454146] ^ [ 53.454211] ffff88811b1e8080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 53.454279] ffff88811b1e8100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 53.454347] ================================================================== [ 53.454414] Disabling lock debugging due to kernel taint [ 53.454434] general protection fault, probably for non-canonical address 0xdead0000000000d0: 0000 [#1] PREEMPT SMP KASAN PTI [ 53.454446] CPU: 1 PID: 345 Comm: systemd-udevd Tainted: G B W 5.10.0-rc5+ #12 [ 53.454592] RIP: 0010:i915_init_ggtt+0x26f/0x9e0 [i915] [ 53.454602] Code: 89 8d 48 ff ff ff 4c 8d 60 d0 49 39 c7 0f 84 37 02 00 00 4c 89 b5 40 ff ff ff 4d 8d bc 24 90 00 00 00 4c 89 ff e8 c1 97 f8 e0 <49> 83 bc 24 90 00 00 00 00 0f 84 0f 02 00 00 49 8d 7c 24 08 e8 a8 [ 53.454618] RSP: 0018:ffff88812247f430 EFLAGS: 00010286 [ 53.454625] RAX: 0000000000000000 RBX: ffff888136440000 RCX: ffffffffa03fb78f [ 53.454633] RDX: 0000000000000000 RSI: 0000000000000008 RDI: dead000000000160 [ 53.454641] RBP: ffff88812247f500 R08: ffffffff8113589f R09: 0000000000000000 [ 53.454648] R10: ffffffff83063843 R11: fffffbfff060c708 R12: dead0000000000d0 [ 53.454656] R13: ffff888136449ba0 R14: 0000000000002000 R15: dead000000000160 [ 53.454664] FS: 00007fde095c4880(0000) GS:ffff88840c880000(0000) knlGS:0000000000000000 [ 53.454672] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.454679] CR2: 00007fef132b4f28 CR3: 000000012245c002 CR4: 00000000003706e0 [ 53.454686] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.454693] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.454700] Call Trace: [ 53.454833] ? i915_ggtt_suspend+0x1f0/0x1f0 [i915] Reported-by: Matthew Auld Fixes: afeda4f3b1c8 ("drm/i915/dsb: Pre allocate and late cleanup of cmd buffer") Signed-off-by: Chris Wilson Cc: Ville Syrjälä Cc: Matthew Auld Cc: Lucas De Marchi Tested-by: Matthew Auld Reviewed-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20201125193032.29282-1-chris@chris-wilson.co.uk (cherry picked from commit b3bf99daaee96a141536ce5c60a0d6dba6ec1d23) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/display/intel_display.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index c0d920f596f4..3bfe6ed67da1 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -18021,16 +18021,6 @@ int intel_modeset_init_nogem(struct drm_i915_private *i915) if (!HAS_GMCH(i915)) sanitize_watermarks(i915); - /* - * Force all active planes to recompute their states. So that on - * mode_setcrtc after probe, all the intel_plane_state variables - * are already calculated and there is no assert_plane warnings - * during bootup. - */ - ret = intel_initial_commit(dev); - if (ret) - drm_dbg_kms(&i915->drm, "Initial commit in probe failed.\n"); - return 0; } @@ -18042,6 +18032,16 @@ int intel_modeset_init(struct drm_i915_private *i915) if (!HAS_DISPLAY(i915)) return 0; + /* + * Force all active planes to recompute their states. So that on + * mode_setcrtc after probe, all the intel_plane_state variables + * are already calculated and there is no assert_plane warnings + * during bootup. + */ + ret = intel_initial_commit(&i915->drm); + if (ret) + return ret; + intel_overlay_setup(i915); ret = intel_fbdev_init(&i915->drm); -- cgit v1.2.3 From 6ee50c8e262a0f0693dad264c3c99e30e6442a56 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 1 Dec 2020 18:15:12 +0300 Subject: net/x25: prevent a couple of overflows MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .x25_addr[] address comes from the user and is not necessarily NUL terminated. This leads to a couple problems. The first problem is that the strlen() in x25_bind() can read beyond the end of the buffer. The second problem is more subtle and could result in memory corruption. The call tree is: x25_connect() --> x25_write_internal() --> x25_addr_aton() The .x25_addr[] buffers are copied to the "addresses" buffer from x25_write_internal() so it will lead to stack corruption. Verify that the strings are NUL terminated and return -EINVAL if they are not. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Fixes: a9288525d2ae ("X25: Dont let x25_bind use addresses containing characters") Reported-by: "kiyin(尹亮)" Signed-off-by: Dan Carpenter Acked-by: Martin Schiller Link: https://lore.kernel.org/r/X8ZeAKm8FnFpN//B@mwanda Signed-off-by: Jakub Kicinski --- net/x25/af_x25.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index a10487e7574c..e65a50192432 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -681,7 +681,8 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) int len, i, rc = 0; if (addr_len != sizeof(struct sockaddr_x25) || - addr->sx25_family != AF_X25) { + addr->sx25_family != AF_X25 || + strnlen(addr->sx25_addr.x25_addr, X25_ADDR_LEN) == X25_ADDR_LEN) { rc = -EINVAL; goto out; } @@ -775,7 +776,8 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, rc = -EINVAL; if (addr_len != sizeof(struct sockaddr_x25) || - addr->sx25_family != AF_X25) + addr->sx25_family != AF_X25 || + strnlen(addr->sx25_addr.x25_addr, X25_ADDR_LEN) == X25_ADDR_LEN) goto out; rc = -ENETUNREACH; -- cgit v1.2.3 From ff9924897f8bfed82e61894b373ab9d2dfea5b10 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Wed, 2 Dec 2020 17:56:05 +0800 Subject: cxgb3: fix error return code in t3_sge_alloc_qset() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: b1fb1f280d09 ("cxgb3 - Fix dma mapping error path") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Acked-by: Raju Rangoju Link: https://lore.kernel.org/r/1606902965-1646-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/chelsio/cxgb3/sge.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c index e18e9ce27f94..1cc3c51eff71 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c @@ -3175,6 +3175,7 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports, GFP_KERNEL | __GFP_COMP); if (!avail) { CH_ALERT(adapter, "free list queue 0 initialization failed\n"); + ret = -ENOMEM; goto err; } if (avail < q->fl[0].size) -- cgit v1.2.3 From aba84871bd4f52c4dfcf3ad5d4501a6c9d2de90e Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Wed, 2 Dec 2020 17:57:15 +0800 Subject: net: pasemi: fix error return code in pasemi_mac_open() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 72b05b9940f0 ("pasemi_mac: RX/TX ring management cleanup") Fixes: 8d636d8bc5ff ("pasemi_mac: jumbo frame support") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Link: https://lore.kernel.org/r/1606903035-1838-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/pasemi/pasemi_mac.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c index be6660128b55..040a15a828b4 100644 --- a/drivers/net/ethernet/pasemi/pasemi_mac.c +++ b/drivers/net/ethernet/pasemi/pasemi_mac.c @@ -1078,16 +1078,20 @@ static int pasemi_mac_open(struct net_device *dev) mac->tx = pasemi_mac_setup_tx_resources(dev); - if (!mac->tx) + if (!mac->tx) { + ret = -ENOMEM; goto out_tx_ring; + } /* We might already have allocated rings in case mtu was changed * before interface was brought up. */ if (dev->mtu > 1500 && !mac->num_cs) { pasemi_mac_setup_csrings(mac); - if (!mac->num_cs) + if (!mac->num_cs) { + ret = -ENOMEM; goto out_tx_ring; + } } /* Zero out rmon counters */ -- cgit v1.2.3 From 832e09798c261cf58de3a68cfcc6556408c16a5a Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Wed, 2 Dec 2020 17:58:42 +0800 Subject: vxlan: fix error return code in __vxlan_dev_create() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 0ce1822c2a08 ("vxlan: add adjacent link to limit depth level") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Link: https://lore.kernel.org/r/1606903122-2098-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/vxlan.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 032f78261913..977f77e2c2ce 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3880,8 +3880,10 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, if (dst->remote_ifindex) { remote_dev = __dev_get_by_index(net, dst->remote_ifindex); - if (!remote_dev) + if (!remote_dev) { + err = -ENODEV; goto errout; + } err = netdev_upper_dev_link(remote_dev, dev, extack); if (err) -- cgit v1.2.3 From acab02c1af43d3a9051524579b1c3dcfbfa5479d Mon Sep 17 00:00:00 2001 From: Arunpravin Date: Fri, 27 Nov 2020 21:40:24 +0530 Subject: drm/amdgpu/pm/smu11: Fix fan set speed bug Fix fan set speed calculation. Suggested-by: Kenneth Feng Signed-off-by: Arunpravin Acked-by: Alex Deucher Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index 2380759ddf48..6db96fa1df09 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -1164,7 +1164,12 @@ int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu, if (ret) return ret; - crystal_clock_freq = amdgpu_asic_get_xclk(adev); + /* + * crystal_clock_freq div by 4 is required since the fan control + * module refers to 25MHz + */ + + crystal_clock_freq = amdgpu_asic_get_xclk(adev) / 4; tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed); WREG32_SOC15(THM, 0, mmCG_TACH_CTRL, REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_TACH_CTRL), -- cgit v1.2.3 From 7e0b367db85ef7b91399006253759a024eab7653 Mon Sep 17 00:00:00 2001 From: Brandon Syu Date: Thu, 12 Nov 2020 15:35:52 +0800 Subject: drm/amd/display: Init clock value by current vbios CLKs [Why] While booting into OS, driver updates DPP/DISP CLKs. But init clock value is zero which is invalid. [How] Get current clocks value to update init clocks. To avoid underflow. Signed-off-by: Brandon Syu Reviewed-by: Tony Cheng Acked-by: Aurabindo Pillai Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index 2f8fee05547a..c001307b0a59 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -163,8 +163,17 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base, new_clocks->dppclk_khz = 100000; } - if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) { - if (clk_mgr->base.clks.dppclk_khz > new_clocks->dppclk_khz) + /* + * Temporally ignore thew 0 cases for disp and dpp clks. + * We may have a new feature that requires 0 clks in the future. + */ + if (new_clocks->dppclk_khz == 0 || new_clocks->dispclk_khz == 0) { + new_clocks->dppclk_khz = clk_mgr_base->clks.dppclk_khz; + new_clocks->dispclk_khz = clk_mgr_base->clks.dispclk_khz; + } + + if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr_base->clks.dppclk_khz)) { + if (clk_mgr_base->clks.dppclk_khz > new_clocks->dppclk_khz) dpp_clock_lowered = true; clk_mgr_base->clks.dppclk_khz = new_clocks->dppclk_khz; update_dppclk = true; -- cgit v1.2.3 From ac2db9488cf21de0be7899c1e5963e5ac0ff351f Mon Sep 17 00:00:00 2001 From: Boyuan Zhang Date: Sun, 10 May 2020 15:47:03 -0400 Subject: drm/amdgpu/vcn3.0: stall DPG when WPTR/RPTR reset Port from VCN2.5 Add vcn dpg harware synchronization to fix race condition issue between vcn driver and hardware. Signed-off-by: Boyuan Zhang Reviewed-by: James Zhu Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 5.9.x --- drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index e074f7ed388c..2aa84993f42d 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1011,6 +1011,11 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1); WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_CNTL, tmp); + /* Stall DPG before WPTR/RPTR reset */ + WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS), + UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK, + ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); + /* set the write pointer delay */ WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR_CNTL, 0); @@ -1033,6 +1038,10 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr)); + /* Unstall DPG */ + WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS), + 0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); + return 0; } @@ -1556,8 +1565,14 @@ static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev, UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK, UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK); + /* Stall DPG before WPTR/RPTR reset */ + WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS), + UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK, + ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); + /* Restore */ ring = &adev->vcn.inst[inst_idx].ring_enc[0]; + ring->wptr = 0; WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_LO, ring->gpu_addr); WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); WREG32_SOC15(VCN, inst_idx, mmUVD_RB_SIZE, ring->ring_size / 4); @@ -1565,6 +1580,7 @@ static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev, WREG32_SOC15(VCN, inst_idx, mmUVD_RB_WPTR, lower_32_bits(ring->wptr)); ring = &adev->vcn.inst[inst_idx].ring_enc[1]; + ring->wptr = 0; WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_LO2, ring->gpu_addr); WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr)); WREG32_SOC15(VCN, inst_idx, mmUVD_RB_SIZE2, ring->ring_size / 4); @@ -1574,6 +1590,10 @@ static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev, WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR, RREG32_SOC15(VCN, inst_idx, mmUVD_SCRATCH2) & 0x7FFFFFFF); + /* Unstall DPG */ + WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS), + 0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); + SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); } -- cgit v1.2.3 From efd6d85a18102241538dd1cc257948a0dbe6fae6 Mon Sep 17 00:00:00 2001 From: Boyuan Zhang Date: Tue, 19 May 2020 11:38:44 -0400 Subject: drm/amdgpu/vcn3.0: remove old DPG workaround Port from VCN2.5 SCRATCH2 is used to keep decode wptr as a workaround which fix a hardware DPG decode wptr update bug for vcn2.5 beforehand. Signed-off-by: Boyuan Zhang Reviewed-by: James Zhu Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 5.9.x --- drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 2aa84993f42d..b5f8f3d731cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1587,9 +1587,6 @@ static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev, WREG32_SOC15(VCN, inst_idx, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr)); WREG32_SOC15(VCN, inst_idx, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr)); - WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR, - RREG32_SOC15(VCN, inst_idx, mmUVD_SCRATCH2) & 0x7FFFFFFF); - /* Unstall DPG */ WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS), 0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); @@ -1650,10 +1647,6 @@ static void vcn_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - WREG32_SOC15(VCN, ring->me, mmUVD_SCRATCH2, - lower_32_bits(ring->wptr) | 0x80000000); - if (ring->use_doorbell) { adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr); WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr)); -- cgit v1.2.3 From 4d916140bf28ff027997144ea1bb4299e1536f87 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 30 Nov 2020 12:54:34 +0100 Subject: intel_idle: Build fix Because CONFIG_ soup. Fixes: 6e1d2bc675bd ("intel_idle: Fix intel_idle() vs tracing") Reported-by: Randy Dunlap Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20201130115402.GO3040@hirez.programming.kicks-ass.net --- drivers/idle/intel_idle.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 7ee7ffe22ae3..d79335506ecd 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1140,6 +1140,20 @@ static bool __init intel_idle_max_cstate_reached(int cstate) return false; } +static bool __init intel_idle_state_needs_timer_stop(struct cpuidle_state *state) +{ + unsigned long eax = flg2MWAIT(state->flags); + + if (boot_cpu_has(X86_FEATURE_ARAT)) + return false; + + /* + * Switch over to one-shot tick broadcast if the target C-state + * is deeper than C1. + */ + return !!((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK); +} + #ifdef CONFIG_ACPI_PROCESSOR_CSTATE #include @@ -1210,20 +1224,6 @@ static bool __init intel_idle_acpi_cst_extract(void) return false; } -static bool __init intel_idle_state_needs_timer_stop(struct cpuidle_state *state) -{ - unsigned long eax = flg2MWAIT(state->flags); - - if (boot_cpu_has(X86_FEATURE_ARAT)) - return false; - - /* - * Switch over to one-shot tick broadcast if the target C-state - * is deeper than C1. - */ - return !!((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK); -} - static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv) { int cstate, limit = min_t(int, CPUIDLE_STATE_MAX, acpi_state_table.count); -- cgit v1.2.3 From 5debf02131227d39988e44adf5090fb796fa8466 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 26 Nov 2020 20:09:21 +0900 Subject: perf/x86/intel: Fix a warning on x86_pmu_stop() with large PEBS The commit 3966c3feca3f ("x86/perf/amd: Remove need to check "running" bit in NMI handler") introduced this. It seems x86_pmu_stop can be called recursively (like when it losts some samples) like below: x86_pmu_stop intel_pmu_disable_event (x86_pmu_disable) intel_pmu_pebs_disable intel_pmu_drain_pebs_nhm (x86_pmu_drain_pebs_buffer) x86_pmu_stop While commit 35d1ce6bec13 ("perf/x86/intel/ds: Fix x86_pmu_stop warning for large PEBS") fixed it for the normal cases, there's another path to call x86_pmu_stop() recursively when a PEBS error was detected (like two or more counters overflowed at the same time). Like in the Kan's previous fix, we can skip the interrupt accounting for large PEBS, so check the iregs which is set for PMI only. Fixes: 3966c3feca3f ("x86/perf/amd: Remove need to check "running" bit in NMI handler") Reported-by: John Sperbeck Suggested-by: Peter Zijlstra Signed-off-by: Namhyung Kim Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20201126110922.317681-1-namhyung@kernel.org --- arch/x86/events/intel/ds.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index b47cc4226934..89dba588636e 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1940,7 +1940,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d if (error[bit]) { perf_log_lost_samples(event, error[bit]); - if (perf_event_account_interrupt(event)) + if (iregs && perf_event_account_interrupt(event)) x86_pmu_stop(event, 0); } -- cgit v1.2.3 From fc17db8aa4c53cbd2d5469bb0521ea0f0a6dbb27 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 26 Nov 2020 20:09:22 +0900 Subject: perf/x86/intel: Check PEBS status correctly The kernel cannot disambiguate when 2+ PEBS counters overflow at the same time. This is what the comment for this code suggests. However, I see the comparison is done with the unfiltered p->status which is a copy of IA32_PERF_GLOBAL_STATUS at the time of the sample. This register contains more than the PEBS counter overflow bits. It also includes many other bits which could also be set. Signed-off-by: Namhyung Kim Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20201126110922.317681-2-namhyung@kernel.org --- arch/x86/events/intel/ds.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 89dba588636e..485c5066f8b8 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1916,7 +1916,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d * that caused the PEBS record. It's called collision. * If collision happened, the record will be dropped. */ - if (p->status != (1ULL << bit)) { + if (pebs_status != (1ULL << bit)) { for_each_set_bit(i, (unsigned long *)&pebs_status, size) error[i]++; continue; -- cgit v1.2.3 From 46ee4abb10a07bd8f8ce910ee6b4ae6a947d7f63 Mon Sep 17 00:00:00 2001 From: Jan-Niklas Burfeind Date: Thu, 3 Dec 2020 04:03:59 +0100 Subject: USB: serial: ch341: add new Product ID for CH341A Add PID for CH340 that's found on a ch341 based Programmer made by keeyees. The specific device that contains the serial converter is described here: http://www.keeyees.com/a/Products/ej/36.html The driver works flawlessly as soon as the new PID (0x5512) is added to it. Signed-off-by: Jan-Niklas Burfeind Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/ch341.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c index a2e2f56c88cd..b157a230178d 100644 --- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -84,6 +84,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x4348, 0x5523) }, { USB_DEVICE(0x1a86, 0x7522) }, { USB_DEVICE(0x1a86, 0x7523) }, + { USB_DEVICE(0x1a86, 0x5512) }, { USB_DEVICE(0x1a86, 0x5523) }, { }, }; -- cgit v1.2.3 From bf193bfc12dbc3754fc8a6e0e1e3702f1af2f772 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 3 Dec 2020 10:11:59 +0100 Subject: USB: serial: ch341: sort device-id entries Keep the device-id entries sorted to make it easier to add new ones in the right spot. Reviewed-by: Greg Kroah-Hartman Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/ch341.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c index b157a230178d..28deaaec581f 100644 --- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -81,11 +81,11 @@ #define CH341_QUIRK_SIMULATE_BREAK BIT(1) static const struct usb_device_id id_table[] = { - { USB_DEVICE(0x4348, 0x5523) }, - { USB_DEVICE(0x1a86, 0x7522) }, - { USB_DEVICE(0x1a86, 0x7523) }, { USB_DEVICE(0x1a86, 0x5512) }, { USB_DEVICE(0x1a86, 0x5523) }, + { USB_DEVICE(0x1a86, 0x7522) }, + { USB_DEVICE(0x1a86, 0x7523) }, + { USB_DEVICE(0x4348, 0x5523) }, { }, }; MODULE_DEVICE_TABLE(usb, id_table); -- cgit v1.2.3 From 74a8c816fa8fa7862df870660e9821abb56649fe Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 3 Dec 2020 11:43:37 +0300 Subject: rtw88: debug: Fix uninitialized memory in debugfs code This code does not ensure that the whole buffer is initialized and none of the callers check for errors so potentially none of the buffer is initialized. Add a memset to eliminate this bug. Fixes: e3037485c68e ("rtw88: new Realtek 802.11ac driver") Signed-off-by: Dan Carpenter Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/X8ilOfVz3pf0T5ec@mwanda --- drivers/net/wireless/realtek/rtw88/debug.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/wireless/realtek/rtw88/debug.c b/drivers/net/wireless/realtek/rtw88/debug.c index 3852c4f0ac0b..efbba9caef3b 100644 --- a/drivers/net/wireless/realtek/rtw88/debug.c +++ b/drivers/net/wireless/realtek/rtw88/debug.c @@ -147,6 +147,8 @@ static int rtw_debugfs_copy_from_user(char tmp[], int size, { int tmp_len; + memset(tmp, 0, size); + if (count < num) return -EFAULT; -- cgit v1.2.3 From 8dcc0e19dfbd73ad6b3172924d6da8f7f3f8b3b0 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Thu, 3 Dec 2020 09:22:52 -0600 Subject: x86/platform/uv: Fix UV4 hub revision adjustment Currently, UV4 is incorrectly identified as UV4A and UV4A as UV5. Hub chip starts with revision 1, fix it. [ bp: Massage commit message. ] Fixes: 647128f1536e ("x86/platform/uv: Update UV MMRs for UV5") Signed-off-by: Mike Travis Signed-off-by: Borislav Petkov Reviewed-by: Steve Wahl Acked-by: Dimitri Sivanich Link: https://lkml.kernel.org/r/20201203152252.371199-1-mike.travis@hpe.com --- arch/x86/kernel/apic/x2apic_uv_x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 1b98f8c12b96..235f5cde06fc 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -161,7 +161,7 @@ static int __init early_set_hub_type(void) /* UV4/4A only have a revision difference */ case UV4_HUB_PART_NUMBER: uv_min_hub_revision_id = node_id.s.revision - + UV4_HUB_REVISION_BASE; + + UV4_HUB_REVISION_BASE - 1; uv_hub_type_set(UV4); if (uv_min_hub_revision_id == UV4A_HUB_REVISION_BASE) uv_hub_type_set(UV4|UV4A); -- cgit v1.2.3 From 0c55f867f0c96dff93d4e0b5973975d65afb26d8 Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Wed, 2 Dec 2020 21:35:36 +0100 Subject: selftests: kvm/set_memory_region_test: Fix race in move region test The current memory region move test correctly handles the situation that the second (realigning) memslot move operation would temporarily trigger MMIO until it completes, however it does not handle the case in which the first (misaligning) move operation does this, too. This results in false test assertions in case it does so. Fix this by handling temporary MMIO from the first memslot move operation in the test guest code, too. Fixes: 8a0639fe9201 ("KVM: sefltests: Add explicit synchronization to move mem region test") Signed-off-by: Maciej S. Szmigiero Message-Id: <0fdddb94bb0e31b7da129a809a308d91c10c0b5e.1606941224.git.maciej.szmigiero@oracle.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/set_memory_region_test.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index b3ece55a2da6..6f441dd9f33c 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -156,14 +156,23 @@ static void guest_code_move_memory_region(void) GUEST_SYNC(0); /* - * Spin until the memory region is moved to a misaligned address. This - * may or may not trigger MMIO, as the window where the memslot is - * invalid is quite small. + * Spin until the memory region starts getting moved to a + * misaligned address. + * Every region move may or may not trigger MMIO, as the + * window where the memslot is invalid is usually quite small. */ val = guest_spin_on_val(0); GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val); - /* Spin until the memory region is realigned. */ + /* Spin until the misaligning memory region move completes. */ + val = guest_spin_on_val(MMIO_VAL); + GUEST_ASSERT_1(val == 1 || val == 0, val); + + /* Spin until the memory region starts to get re-aligned. */ + val = guest_spin_on_val(0); + GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val); + + /* Spin until the re-aligning memory region move completes. */ val = guest_spin_on_val(MMIO_VAL); GUEST_ASSERT_1(val == 1, val); -- cgit v1.2.3 From 4f134b89a24b965991e7c345b9a4591821f7c2a6 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 30 Nov 2020 08:36:48 +0100 Subject: lib/syscall: fix syscall registers retrieval on 32-bit platforms Lilith >_> and Claudio Bozzato of Cisco Talos security team reported that collect_syscall() improperly casts the syscall registers to 64-bit values leaking the uninitialized last 24 bytes on 32-bit platforms, that are visible in /proc/self/syscall. The cause is that info->data.args are u64 while syscall_get_arguments() uses longs, as hinted by the bogus pointer cast in the function. Let's just proceed like the other call places, by retrieving the registers into an array of longs before assigning them to the caller's array. This was successfully tested on x86_64, i386 and ppc32. Reference: CVE-2020-28588, TALOS-2020-1211 Fixes: 631b7abacd02 ("ptrace: Remove maxargs from task_current_syscall()") Cc: Greg KH Reviewed-by: Kees Cook Tested-by: Michael Ellerman (ppc32) Signed-off-by: Willy Tarreau Reviewed-by: Thomas Gleixner Signed-off-by: Linus Torvalds --- lib/syscall.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/lib/syscall.c b/lib/syscall.c index 8533d2fea2d7..ba13e924c430 100644 --- a/lib/syscall.c +++ b/lib/syscall.c @@ -7,6 +7,7 @@ static int collect_syscall(struct task_struct *target, struct syscall_info *info) { + unsigned long args[6] = { }; struct pt_regs *regs; if (!try_get_task_stack(target)) { @@ -27,8 +28,14 @@ static int collect_syscall(struct task_struct *target, struct syscall_info *info info->data.nr = syscall_get_nr(target, regs); if (info->data.nr != -1L) - syscall_get_arguments(target, regs, - (unsigned long *)&info->data.args[0]); + syscall_get_arguments(target, regs, args); + + info->data.args[0] = args[0]; + info->data.args[1] = args[1]; + info->data.args[2] = args[2]; + info->data.args[3] = args[3]; + info->data.args[4] = args[4]; + info->data.args[5] = args[5]; put_task_stack(target); return 0; -- cgit v1.2.3 From 062c9cdf60a1e581b1002d372f1cf8e745fe3c16 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Thu, 3 Dec 2020 09:41:42 +0100 Subject: pwm: sl28cpld: fix getting driver data in pwm callbacks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently .get_state() and .apply() use dev_get_drvdata() on the struct device related to the pwm chip. This only works after .probe() called platform_set_drvdata() which in this driver happens only after pwmchip_add() and so comes possibly too late. Instead of setting the driver data earlier use the traditional container_of approach as this way the driver data is conceptually and computational nearer. Fixes: 9db33d221efc ("pwm: Add support for sl28cpld PWM controller") Tested-by: Michael Walle Signed-off-by: Uwe Kleine-König Signed-off-by: Linus Torvalds --- drivers/pwm/pwm-sl28cpld.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/pwm/pwm-sl28cpld.c b/drivers/pwm/pwm-sl28cpld.c index 5046b6b7fd35..b4c651fc749c 100644 --- a/drivers/pwm/pwm-sl28cpld.c +++ b/drivers/pwm/pwm-sl28cpld.c @@ -84,12 +84,14 @@ struct sl28cpld_pwm { struct regmap *regmap; u32 offset; }; +#define sl28cpld_pwm_from_chip(_chip) \ + container_of(_chip, struct sl28cpld_pwm, pwm_chip) static void sl28cpld_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, struct pwm_state *state) { - struct sl28cpld_pwm *priv = dev_get_drvdata(chip->dev); + struct sl28cpld_pwm *priv = sl28cpld_pwm_from_chip(chip); unsigned int reg; int prescaler; @@ -118,7 +120,7 @@ static void sl28cpld_pwm_get_state(struct pwm_chip *chip, static int sl28cpld_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, const struct pwm_state *state) { - struct sl28cpld_pwm *priv = dev_get_drvdata(chip->dev); + struct sl28cpld_pwm *priv = sl28cpld_pwm_from_chip(chip); unsigned int cycle, prescaler; bool write_duty_cycle_first; int ret; -- cgit v1.2.3 From 72d1249e2ffdbc344e465031ec5335fa3489d62e Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Tue, 1 Dec 2020 17:21:40 -0600 Subject: uapi: fix statx attribute value overlap for DAX & MOUNT_ROOT STATX_ATTR_MOUNT_ROOT and STATX_ATTR_DAX got merged with the same value, so one of them needs fixing. Move STATX_ATTR_DAX. While we're in here, clarify the value-matching scheme for some of the attributes, and explain why the value for DAX does not match. Fixes: 80340fe3605c ("statx: add mount_root") Fixes: 712b2698e4c0 ("fs/stat: Define DAX statx attribute") Link: https://lore.kernel.org/linux-fsdevel/7027520f-7c79-087e-1d00-743bdefa1a1e@redhat.com/ Link: https://lore.kernel.org/lkml/20201202214629.1563760-1-ira.weiny@intel.com/ Reported-by: David Howells Signed-off-by: Eric Sandeen Reviewed-by: David Howells Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Ira Weiny Cc: # 5.8 Signed-off-by: Linus Torvalds --- include/uapi/linux/stat.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 82cc58fe9368..1500a0f58041 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -171,9 +171,12 @@ struct statx { * be of use to ordinary userspace programs such as GUIs or ls rather than * specialised tools. * - * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS + * Note that the flags marked [I] correspond to the FS_IOC_SETFLAGS flags * semantically. Where possible, the numerical value is picked to correspond - * also. + * also. Note that the DAX attribute indicates that the file is in the CPU + * direct access state. It does not correspond to the per-inode flag that + * some filesystems support. + * */ #define STATX_ATTR_COMPRESSED 0x00000004 /* [I] File is compressed by the fs */ #define STATX_ATTR_IMMUTABLE 0x00000010 /* [I] File is marked immutable */ @@ -183,7 +186,7 @@ struct statx { #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ -#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */ +#define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ #endif /* _UAPI_LINUX_STAT_H */ -- cgit v1.2.3 From 391119fb5c5c4bdb4d57c7ffeb5e8d18560783d1 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 3 Dec 2020 11:44:31 +0300 Subject: chelsio/chtls: fix a double free in chtls_setkey() The "skb" is freed by the transmit code in cxgb4_ofld_send() and we shouldn't use it again. But in the current code, if we hit an error later on in the function then the clean up code will call kfree_skb(skb) and so it causes a double free. Set the "skb" to NULL and that makes the kfree_skb() a no-op. Fixes: d25f2f71f653 ("crypto: chtls - Program the TLS session Key") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/X8ilb6PtBRLWiSHp@mwanda Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c index 62c829023da5..a4fb463af22a 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c @@ -391,6 +391,7 @@ int chtls_setkey(struct chtls_sock *csk, u32 keylen, csk->wr_unacked += DIV_ROUND_UP(len, 16); enqueue_wr(csk, skb); cxgb4_ofld_send(csk->egress_dev, skb); + skb = NULL; chtls_set_scmd(csk); /* Clear quiesce for Rx key */ -- cgit v1.2.3 From 82a10dc7f0960735f40e8d7d3bee56934291600f Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Thu, 3 Dec 2020 22:18:06 +0800 Subject: net: mvpp2: Fix error return code in mvpp2_open() Fix to return negative error code -ENOENT from invalid configuration error handling case instead of 0, as done elsewhere in this function. Fixes: 4bb043262878 ("net: mvpp2: phylink support") Reported-by: Hulk Robot Signed-off-by: Wang Hai Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20201203141806.37966-1-wanghai38@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index f6616c8933ca..cea886c5bcb5 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4426,6 +4426,7 @@ static int mvpp2_open(struct net_device *dev) if (!valid) { netdev_err(port->dev, "invalid configuration: no dt or link IRQ"); + err = -ENOENT; goto err_free_irq; } -- cgit v1.2.3 From 13de4ed9e3a9ccbe54d05f7d5c773f69ecaf6c64 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Thu, 3 Dec 2020 10:58:21 +0100 Subject: net: skbuff: ensure LSE is pullable before decrementing the MPLS ttl skb_mpls_dec_ttl() reads the LSE without ensuring that it is contained in the skb "linear" area. Fix this calling pskb_may_pull() before reading the current ttl. Found by code inspection. Fixes: 2a2ea50870ba ("net: sched: add mpls manipulation actions to TC") Reported-by: Marcelo Ricardo Leitner Signed-off-by: Davide Caratti Link: https://lore.kernel.org/r/53659f28be8bc336c113b5254dc637cc76bbae91.1606987074.git.dcaratti@redhat.com Signed-off-by: Jakub Kicinski --- net/core/skbuff.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 06c526e0d810..e578544b2cc7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5786,6 +5786,9 @@ int skb_mpls_dec_ttl(struct sk_buff *skb) if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; + if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) + return -ENOMEM; + lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry); ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; if (!--ttl) -- cgit v1.2.3 From 43c13605bad44b8abbc9776d6e63f62ccb7a47d6 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Thu, 3 Dec 2020 10:46:06 +0100 Subject: net: openvswitch: ensure LSE is pullable before reading it when openvswitch is configured to mangle the LSE, the current value is read from the packet dereferencing 4 bytes at mpls_hdr(): ensure that the label is contained in the skb "linear" area. Found by code inspection. Fixes: d27cf5c59a12 ("net: core: add MPLS update core helper and use in OvS") Signed-off-by: Davide Caratti Link: https://lore.kernel.org/r/aa099f245d93218b84b5c056b67b6058ccf81a66.1606987185.git.dcaratti@redhat.com Signed-off-by: Jakub Kicinski --- net/openvswitch/actions.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 5829a020b81c..c3a664871cb5 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -199,6 +199,9 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key, __be32 lse; int err; + if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) + return -ENOMEM; + stack = mpls_hdr(skb); lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask); err = skb_mpls_update_lse(skb, lse); -- cgit v1.2.3 From 9608fa653059c3f72faab0c148ac8773c46e7314 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Thu, 3 Dec 2020 10:37:52 +0100 Subject: net/sched: act_mpls: ensure LSE is pullable before reading it when 'act_mpls' is used to mangle the LSE, the current value is read from the packet dereferencing 4 bytes at mpls_hdr(): ensure that the label is contained in the skb "linear" area. Found by code inspection. v2: - use MPLS_HLEN instead of sizeof(new_lse), thanks to Jakub Kicinski Fixes: 2a2ea50870ba ("net: sched: add mpls manipulation actions to TC") Signed-off-by: Davide Caratti Acked-by: Guillaume Nault Link: https://lore.kernel.org/r/3243506cba43d14858f3bd21ee0994160e44d64a.1606987058.git.dcaratti@redhat.com Signed-off-by: Jakub Kicinski --- net/sched/act_mpls.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 5c7456e5b5cf..d1486ea496a2 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -105,6 +105,9 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, goto drop; break; case TCA_MPLS_ACT_MODIFY: + if (!pskb_may_pull(skb, + skb_network_offset(skb) + MPLS_HLEN)) + goto drop; new_lse = tcf_mpls_get_lse(mpls_hdr(skb), p, false); if (skb_mpls_update_lse(skb, new_lse)) goto drop; -- cgit v1.2.3 From 1d2bb5ad89f47d8ce8aedc70ef85059ab3870292 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Wed, 2 Dec 2020 20:39:43 -0800 Subject: net/mlx5: Fix wrong address reclaim when command interface is down When command interface is down, driver to reclaim all 4K page chucks that were hold by the Firmeware. Fix a bug for 64K page size systems, where driver repeatedly released only the first chunk of the page. Define helper function to fill 4K chunks for a given Firmware pages. Iterate over all unreleased Firmware pages and call the hepler per each. Fixes: 5adff6a08862 ("net/mlx5: Fix incorrect page count when in internal error") Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 150638814517..4d7f8a357df7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -422,6 +422,24 @@ static void release_all_pages(struct mlx5_core_dev *dev, u32 func_id, npages, ec_function, func_id); } +static u32 fwp_fill_manage_pages_out(struct fw_page *fwp, u32 *out, u32 index, + u32 npages) +{ + u32 pages_set = 0; + unsigned int n; + + for_each_clear_bit(n, &fwp->bitmask, MLX5_NUM_4K_IN_PAGE) { + MLX5_ARRAY_SET64(manage_pages_out, out, pas, index + pages_set, + fwp->addr + (n * MLX5_ADAPTER_PAGE_SIZE)); + pages_set++; + + if (!--npages) + break; + } + + return pages_set; +} + static int reclaim_pages_cmd(struct mlx5_core_dev *dev, u32 *in, int in_size, u32 *out, int out_size) { @@ -448,8 +466,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, fwp = rb_entry(p, struct fw_page, rb_node); p = rb_next(p); - MLX5_ARRAY_SET64(manage_pages_out, out, pas, i, fwp->addr); - i++; + i += fwp_fill_manage_pages_out(fwp, out, i, npages - i); } MLX5_SET(manage_pages_out, out, output_num_entries, i); -- cgit v1.2.3 From 8a78a440108e55ddd845b0ef46df575248667520 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 2 Dec 2020 20:39:44 -0800 Subject: net: mlx5e: fix fs_tcp.c build when IPV6 is not enabled Fix build when CONFIG_IPV6 is not enabled by making a function be built conditionally. Fixes these build errors and warnings: ../drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c: In function 'accel_fs_tcp_set_ipv6_flow': ../include/net/sock.h:380:34: error: 'struct sock_common' has no member named 'skc_v6_daddr'; did you mean 'skc_daddr'? 380 | #define sk_v6_daddr __sk_common.skc_v6_daddr | ^~~~~~~~~~~~ ../drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c:55:14: note: in expansion of macro 'sk_v6_daddr' 55 | &sk->sk_v6_daddr, 16); | ^~~~~~~~~~~ At top level: ../drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c:47:13: warning: 'accel_fs_tcp_set_ipv6_flow' defined but not used [-Wunused-function] 47 | static void accel_fs_tcp_set_ipv6_flow(struct mlx5_flow_spec *spec, struct sock *sk) Fixes: 5229a96e59ec ("net/mlx5e: Accel, Expose flow steering API for rules add/del") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c index 97f1594cee11..e51f60b55daa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c @@ -44,6 +44,7 @@ static void accel_fs_tcp_set_ipv4_flow(struct mlx5_flow_spec *spec, struct sock outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4); } +#if IS_ENABLED(CONFIG_IPV6) static void accel_fs_tcp_set_ipv6_flow(struct mlx5_flow_spec *spec, struct sock *sk) { MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol); @@ -63,6 +64,7 @@ static void accel_fs_tcp_set_ipv6_flow(struct mlx5_flow_spec *spec, struct sock outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), 0xff, 16); } +#endif void mlx5e_accel_fs_del_sk(struct mlx5_flow_handle *rule) { -- cgit v1.2.3 From b336e6b25e2d053c482ee4339787e6428f390864 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 2 Dec 2020 20:39:45 -0800 Subject: net/mlx5e: kTLS, Enforce HW TX csum offload with kTLS Checksum calculation cannot be done in SW for TX kTLS HW offloaded packets. Offload it to the device, disregard the declared state of the TX csum offload feature. Fixes: d2ead1f360e8 ("net/mlx5e: Add kTLS TX HW offload support") Signed-off-by: Tariq Toukan Reviewed-by: Maxim Mikityanskiy Reviewed-by: Boris Pismenny Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 6dd3ea3cbbed..d97203cf6a00 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -161,7 +161,9 @@ ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, } static inline void -mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) +mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5e_accel_tx_state *accel, + struct mlx5_wqe_eth_seg *eseg) { if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; @@ -173,6 +175,11 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial++; } +#ifdef CONFIG_MLX5_EN_TLS + } else if (unlikely(accel && accel->tls.tls_tisn)) { + eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM; + sq->stats->csum_partial++; +#endif } else if (unlikely(eseg->flow_table_metadata & cpu_to_be32(MLX5_ETH_WQE_FT_META_IPSEC))) { ipsec_txwqe_build_eseg_csum(sq, skb, eseg); @@ -607,12 +614,13 @@ void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq) } static bool mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq, - struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) + struct sk_buff *skb, struct mlx5e_accel_tx_state *accel, + struct mlx5_wqe_eth_seg *eseg) { if (unlikely(!mlx5e_accel_tx_eseg(priv, skb, eseg))) return false; - mlx5e_txwqe_build_eseg_csum(sq, skb, eseg); + mlx5e_txwqe_build_eseg_csum(sq, skb, accel, eseg); return true; } @@ -639,7 +647,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) if (mlx5e_tx_skb_supports_mpwqe(skb, &attr)) { struct mlx5_wqe_eth_seg eseg = {}; - if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &eseg))) + if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg))) return NETDEV_TX_OK; mlx5e_sq_xmit_mpwqe(sq, skb, &eseg, netdev_xmit_more()); @@ -656,7 +664,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) /* May update the WQE, but may not post other WQEs. */ mlx5e_accel_tx_finish(sq, wqe, &accel, (struct mlx5_wqe_inline_seg *)(wqe->data + wqe_attr.ds_cnt_inl)); - if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &wqe->eth))) + if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth))) return NETDEV_TX_OK; mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, netdev_xmit_more()); @@ -675,7 +683,7 @@ void mlx5e_sq_xmit_simple(struct mlx5e_txqsq *sq, struct sk_buff *skb, bool xmit mlx5e_sq_calc_wqe_attr(skb, &attr, &wqe_attr); pi = mlx5e_txqsq_get_next_pi(sq, wqe_attr.num_wqebbs); wqe = MLX5E_TX_FETCH_WQE(sq, pi); - mlx5e_txwqe_build_eseg_csum(sq, skb, &wqe->eth); + mlx5e_txwqe_build_eseg_csum(sq, skb, NULL, &wqe->eth); mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, xmit_more); } @@ -944,7 +952,7 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, mlx5i_txwqe_build_datagram(av, dqpn, dqkey, datagram); - mlx5e_txwqe_build_eseg_csum(sq, skb, eseg); + mlx5e_txwqe_build_eseg_csum(sq, skb, NULL, eseg); eseg->mss = attr.mss; -- cgit v1.2.3 From d421e466c2373095f165ddd25cbabd6c5b077928 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Wed, 2 Dec 2020 20:39:46 -0800 Subject: net/mlx5: DR, Proper handling of unsupported Connect-X6DX SW steering STEs format for Connect-X5 and Connect-X6DX different. Currently, on Connext-X6DX the SW steering would break at some point when building STEs w/o giving a proper error message. Fix this by checking the STE format of the current device when initializing domain: add mlx5_ifc definitions for Connect-X6DX SW steering, read FW capability to get the current format version, and check this version when domain is being created. Fixes: 26d688e33f88 ("net/mlx5: DR, Add Steering entry (STE) utilities") Signed-off-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c | 5 +++++ drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h | 1 + include/linux/mlx5/mlx5_ifc.h | 9 ++++++++- 4 files changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 6bd34b293007..51bbd88ff021 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -92,6 +92,7 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, caps->eswitch_manager = MLX5_CAP_GEN(mdev, eswitch_manager); caps->gvmi = MLX5_CAP_GEN(mdev, vhca_id); caps->flex_protocols = MLX5_CAP_GEN(mdev, flex_parser_protocols); + caps->sw_format_ver = MLX5_CAP_GEN(mdev, steering_format_version); if (mlx5dr_matcher_supp_flex_parser_icmp_v4(caps)) { caps->flex_parser_id_icmp_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 890767a2a7cb..aa2c2d6c44e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -223,6 +223,11 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, if (ret) return ret; + if (dmn->info.caps.sw_format_ver != MLX5_STEERING_FORMAT_CONNECTX_5) { + mlx5dr_err(dmn, "SW steering is not supported on this device\n"); + return -EOPNOTSUPP; + } + ret = dr_domain_query_fdb_caps(mdev, dmn); if (ret) return ret; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index f50f3b107aa3..cf62ea4f882e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -625,6 +625,7 @@ struct mlx5dr_cmd_caps { u8 max_ft_level; u16 roce_min_src_udp; u8 num_esw_ports; + u8 sw_format_ver; bool eswitch_manager; bool rx_sw_owner; bool tx_sw_owner; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a092346c7b2d..233352447b1a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1223,6 +1223,11 @@ enum mlx5_fc_bulk_alloc_bitmask { #define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum)) +enum { + MLX5_STEERING_FORMAT_CONNECTX_5 = 0, + MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, +}; + struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x30]; u8 vhca_id[0x10]; @@ -1521,7 +1526,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 general_obj_types[0x40]; - u8 reserved_at_440[0x20]; + u8 reserved_at_440[0x4]; + u8 steering_format_version[0x4]; + u8 create_qp_start_hint[0x18]; u8 reserved_at_460[0x3]; u8 log_max_uctx[0x5]; -- cgit v1.2.3 From eeaf06af6f87e1dba371fbe42674e6f963220b9c Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 3 Dec 2020 15:18:26 +0300 Subject: scsi: be2iscsi: Revert "Fix a theoretical leak in beiscsi_create_eqs()" My patch caused kernel Oopses and delays in boot. Revert it. The problem was that I moved the "mem->dma = paddr;" before the call to be_fill_queue(). But the first thing that the be_fill_queue() function does is memset the whole struct to zero which overwrites the assignment. Link: https://lore.kernel.org/r/X8jXkt6eThjyVP1v@mwanda Fixes: 38b2db564d9a ("scsi: be2iscsi: Fix a theoretical leak in beiscsi_create_eqs()") Cc: stable Reported-by: Thomas Lamprecht Signed-off-by: Dan Carpenter Signed-off-by: Martin K. Petersen --- drivers/scsi/be2iscsi/be_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c index 202ba925c494..5c3513a4b450 100644 --- a/drivers/scsi/be2iscsi/be_main.c +++ b/drivers/scsi/be2iscsi/be_main.c @@ -3020,7 +3020,6 @@ static int beiscsi_create_eqs(struct beiscsi_hba *phba, goto create_eq_error; } - mem->dma = paddr; mem->va = eq_vaddress; ret = be_fill_queue(eq, phba->params.num_eq_entries, sizeof(struct be_eq_entry), eq_vaddress); @@ -3030,6 +3029,7 @@ static int beiscsi_create_eqs(struct beiscsi_hba *phba, goto create_eq_error; } + mem->dma = paddr; ret = beiscsi_cmd_eq_create(&phba->ctrl, eq, BEISCSI_EQ_DELAY_DEF); if (ret) { @@ -3086,7 +3086,6 @@ static int beiscsi_create_cqs(struct beiscsi_hba *phba, goto create_cq_error; } - mem->dma = paddr; ret = be_fill_queue(cq, phba->params.num_cq_entries, sizeof(struct sol_cqe), cq_vaddress); if (ret) { @@ -3096,6 +3095,7 @@ static int beiscsi_create_cqs(struct beiscsi_hba *phba, goto create_cq_error; } + mem->dma = paddr; ret = beiscsi_cmd_cq_create(&phba->ctrl, cq, eq, false, false, 0); if (ret) { -- cgit v1.2.3 From 796317848517292eb951d8876773b98867cf3c28 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 3 Dec 2020 12:31:36 +0900 Subject: smb3: set COMPOUND_FID to FileID field of subsequent compound request For an operation compounded with an SMB2 CREATE request, client must set COMPOUND_FID(0xFFFFFFFFFFFFFFFF) to FileID field of smb2 ioctl. Signed-off-by: Namjae Jeon Fixes: 2e4564b31b645 ("smb3: add support stat of WSL reparse points for special file types") Reviewed-by: Aurelien Aptel Reviewed-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/smb2ops.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index dab94f67c988..3d914d7d0d11 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3114,8 +3114,8 @@ smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon, rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE; rc = SMB2_ioctl_init(tcon, server, - &rqst[1], fid.persistent_fid, - fid.volatile_fid, FSCTL_GET_REPARSE_POINT, + &rqst[1], COMPOUND_FID, + COMPOUND_FID, FSCTL_GET_REPARSE_POINT, true /* is_fctl */, NULL, 0, CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - -- cgit v1.2.3 From 59463eb88829f646aed13283fd84d02a475334fe Mon Sep 17 00:00:00 2001 From: Aurelien Aptel Date: Thu, 3 Dec 2020 19:46:08 +0100 Subject: cifs: add NULL check for ses->tcon_ipc In some scenarios (DFS and BAD_NETWORK_NAME) set_root_set() can be called with a NULL ses->tcon_ipc. Signed-off-by: Aurelien Aptel Reviewed-by: Paulo Alcantara (SUSE) CC: Stable Signed-off-by: Steve French --- fs/cifs/connect.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 28c1459fb0fc..44f9cce57099 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -4546,7 +4546,8 @@ static void set_root_ses(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, if (ses) { spin_lock(&cifs_tcp_ses_lock); ses->ses_count++; - ses->tcon_ipc->remap = cifs_remap(cifs_sb); + if (ses->tcon_ipc) + ses->tcon_ipc->remap = cifs_remap(cifs_sb); spin_unlock(&cifs_tcp_ses_lock); } *root_ses = ses; -- cgit v1.2.3 From ea64370bcae126a88cd26a16f1abcc23ab2b9a55 Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Mon, 30 Nov 2020 11:29:20 +1000 Subject: cifs: refactor create_sd_buf() and and avoid corrupting the buffer When mounting with "idsfromsid" mount option, Azure corrupted the owner SIDs due to excessive padding caused by placing the owner fields at the end of the security descriptor on create. Placing owners at the front of the security descriptor (rather than the end) is also safer, as the number of ACEs (that follow it) are variable. Signed-off-by: Ronnie Sahlberg Suggested-by: Rohith Surabattula CC: Stable # v5.8 Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 71 +++++++++++++++++++++++++++++-------------------------- fs/cifs/smb2pdu.h | 2 -- 2 files changed, 38 insertions(+), 35 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 445e80862865..acb72705062d 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2272,17 +2272,15 @@ static struct crt_sd_ctxt * create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) { struct crt_sd_ctxt *buf; - struct cifs_ace *pace; - unsigned int sdlen, acelen; + __u8 *ptr, *aclptr; + unsigned int acelen, acl_size, ace_count; unsigned int owner_offset = 0; unsigned int group_offset = 0; + struct smb3_acl acl; - *len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 2), 8); + *len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8); if (set_owner) { - /* offset fields are from beginning of security descriptor not of create context */ - owner_offset = sizeof(struct smb3_acl) + (sizeof(struct cifs_ace) * 2); - /* sizeof(struct owner_group_sids) is already multiple of 8 so no need to round */ *len += sizeof(struct owner_group_sids); } @@ -2291,26 +2289,22 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) if (buf == NULL) return buf; + ptr = (__u8 *)&buf[1]; if (set_owner) { + /* offset fields are from beginning of security descriptor not of create context */ + owner_offset = ptr - (__u8 *)&buf->sd; buf->sd.OffsetOwner = cpu_to_le32(owner_offset); - group_offset = owner_offset + sizeof(struct owner_sid); + group_offset = owner_offset + offsetof(struct owner_group_sids, group); buf->sd.OffsetGroup = cpu_to_le32(group_offset); + + setup_owner_group_sids(ptr); + ptr += sizeof(struct owner_group_sids); } else { buf->sd.OffsetOwner = 0; buf->sd.OffsetGroup = 0; } - sdlen = sizeof(struct smb3_sd) + sizeof(struct smb3_acl) + - 2 * sizeof(struct cifs_ace); - if (set_owner) { - sdlen += sizeof(struct owner_group_sids); - setup_owner_group_sids(owner_offset + sizeof(struct create_context) + 8 /* name */ - + (char *)buf); - } - - buf->ccontext.DataOffset = cpu_to_le16(offsetof - (struct crt_sd_ctxt, sd)); - buf->ccontext.DataLength = cpu_to_le32(sdlen); + buf->ccontext.DataOffset = cpu_to_le16(offsetof(struct crt_sd_ctxt, sd)); buf->ccontext.NameOffset = cpu_to_le16(offsetof(struct crt_sd_ctxt, Name)); buf->ccontext.NameLength = cpu_to_le16(4); /* SMB2_CREATE_SD_BUFFER_TOKEN is "SecD" */ @@ -2319,6 +2313,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) buf->Name[2] = 'c'; buf->Name[3] = 'D'; buf->sd.Revision = 1; /* Must be one see MS-DTYP 2.4.6 */ + /* * ACL is "self relative" ie ACL is stored in contiguous block of memory * and "DP" ie the DACL is present @@ -2326,28 +2321,38 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) buf->sd.Control = cpu_to_le16(ACL_CONTROL_SR | ACL_CONTROL_DP); /* offset owner, group and Sbz1 and SACL are all zero */ - buf->sd.OffsetDacl = cpu_to_le32(sizeof(struct smb3_sd)); - buf->acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */ + buf->sd.OffsetDacl = cpu_to_le32(ptr - (__u8 *)&buf->sd); + /* Ship the ACL for now. we will copy it into buf later. */ + aclptr = ptr; + ptr += sizeof(struct cifs_acl); /* create one ACE to hold the mode embedded in reserved special SID */ - pace = (struct cifs_ace *)(sizeof(struct crt_sd_ctxt) + (char *)buf); - acelen = setup_special_mode_ACE(pace, (__u64)mode); + acelen = setup_special_mode_ACE((struct cifs_ace *)ptr, (__u64)mode); + ptr += acelen; + acl_size = acelen + sizeof(struct smb3_acl); + ace_count = 1; if (set_owner) { /* we do not need to reallocate buffer to add the two more ACEs. plenty of space */ - pace = (struct cifs_ace *)(acelen + (sizeof(struct crt_sd_ctxt) + (char *)buf)); - acelen += setup_special_user_owner_ACE(pace); - /* it does not appear necessary to add an ACE for the NFS group SID */ - buf->acl.AceCount = cpu_to_le16(3); - } else - buf->acl.AceCount = cpu_to_le16(2); + acelen = setup_special_user_owner_ACE((struct cifs_ace *)ptr); + ptr += acelen; + acl_size += acelen; + ace_count += 1; + } /* and one more ACE to allow access for authenticated users */ - pace = (struct cifs_ace *)(acelen + (sizeof(struct crt_sd_ctxt) + - (char *)buf)); - acelen += setup_authusers_ACE(pace); - - buf->acl.AclSize = cpu_to_le16(sizeof(struct cifs_acl) + acelen); + acelen = setup_authusers_ACE((struct cifs_ace *)ptr); + ptr += acelen; + acl_size += acelen; + ace_count += 1; + + acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */ + acl.AclSize = cpu_to_le16(acl_size); + acl.AceCount = cpu_to_le16(ace_count); + memcpy(aclptr, &acl, sizeof(struct cifs_acl)); + + buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd); + *len = ptr - (__u8 *)buf; return buf; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index f05f9b12f689..fa57b03ca98c 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -963,8 +963,6 @@ struct crt_sd_ctxt { struct create_context ccontext; __u8 Name[8]; struct smb3_sd sd; - struct smb3_acl acl; - /* Followed by at least 4 ACEs */ } __packed; -- cgit v1.2.3 From a2b2d4bf5076832339762556b816eec58ca38f77 Mon Sep 17 00:00:00 2001 From: Jacob Xu Date: Thu, 3 Dec 2020 12:59:39 -0800 Subject: kvm: svm: de-allocate svm_cpu_data for all cpus in svm_cpu_uninit() The cpu arg for svm_cpu_uninit() was previously ignored resulting in the per cpu structure svm_cpu_data not being de-allocated for all cpus. Signed-off-by: Jacob Xu Message-Id: <20201203205939.1783969-1-jacobhxu@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 79b3a564f1c9..da7eb4aaf44f 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -530,12 +530,12 @@ static int svm_hardware_enable(void) static void svm_cpu_uninit(int cpu) { - struct svm_cpu_data *sd = per_cpu(svm_data, raw_smp_processor_id()); + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); if (!sd) return; - per_cpu(svm_data, raw_smp_processor_id()) = NULL; + per_cpu(svm_data, cpu) = NULL; kfree(sd->sev_vmcbs); __free_page(sd->save_area); kfree(sd); -- cgit v1.2.3 From 339f5a7fb2d6350fdb11f067da5240fd97e4f284 Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Thu, 3 Dec 2020 15:11:20 -0800 Subject: kvm: x86/mmu: Use cpuid to determine max gfn In the TDP MMU, use shadow_phys_bits to dermine the maximum possible GFN mapped in the guest for zapping operations. boot_cpu_data.x86_phys_bits may be reduced in the case of HW features that steal HPA bits for other purposes. However, this doesn't necessarily reduce GPA space that can be accessed via TDP. So zap based on a maximum gfn calculated with MAXPHYADDR retrieved from CPUID. This is already stored in shadow_phys_bits, so use it instead of x86_phys_bits. Fixes: faaf05b00aec ("kvm: x86/mmu: Support zapping SPTEs in the TDP MMU") Signed-off-by: Rick Edgecombe Message-Id: <20201203231120.27307-1-rick.p.edgecombe@intel.com> Reviewed-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index ff28a5c6abd6..84c8f06bec26 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -66,7 +66,7 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root) { - gfn_t max_gfn = 1ULL << (boot_cpu_data.x86_phys_bits - PAGE_SHIFT); + gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); lockdep_assert_held(&kvm->mmu_lock); @@ -456,7 +456,7 @@ bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end) void kvm_tdp_mmu_zap_all(struct kvm *kvm) { - gfn_t max_gfn = 1ULL << (boot_cpu_data.x86_phys_bits - PAGE_SHIFT); + gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); bool flush; flush = kvm_tdp_mmu_zap_gfn_range(kvm, 0, max_gfn); -- cgit v1.2.3 From 47a0001436352c9853d72bf2071e85b316d688a2 Mon Sep 17 00:00:00 2001 From: Coiby Xu Date: Wed, 25 Nov 2020 21:03:19 +0800 Subject: pinctrl: amd: remove debounce filter setting in IRQ type setting Debounce filter setting should be independent from IRQ type setting because according to the ACPI specs, there are separate arguments for specifying debounce timeout and IRQ type in GpioIo() and GpioInt(). Together with commit 06abe8291bc31839950f7d0362d9979edc88a666 ("pinctrl: amd: fix incorrect way to disable debounce filter") and Andy's patch "gpiolib: acpi: Take into account debounce settings" [1], this will fix broken touchpads for laptops whose BIOS set the debounce timeout to a relatively large value. For example, the BIOS of Lenovo AMD gaming laptops including Legion-5 15ARH05 (R7000), Legion-5P (R7000P) and IdeaPad Gaming 3 15ARH05, set the debounce timeout to 124.8ms. This led to the kernel receiving only ~7 HID reports per second from the Synaptics touchpad (MSFT0001:00 06CB:7F28). Existing touchpads like [2][3] are not troubled by this bug because the debounce timeout has been set to 0 by the BIOS before enabling the debounce filter in setting IRQ type. [1] https://lore.kernel.org/linux-gpio/20201111222008.39993-11-andriy.shevchenko@linux.intel.com/ 8dcb7a15a585 ("gpiolib: acpi: Take into account debounce settings") [2] https://github.com/Syniurge/i2c-amd-mp2/issues/11#issuecomment-721331582 [3] https://forum.manjaro.org/t/random-short-touchpad-freezes/30832/28 Signed-off-by: Coiby Xu Reviewed-by: Andy Shevchenko Cc: Hans de Goede Cc: Andy Shevchenko Cc: Benjamin Tissoires Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-gpio/CAHp75VcwiGREBUJ0A06EEw-SyabqYsp%2Bdqs2DpSrhaY-2GVdAA%40mail.gmail.com/ BugLink: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1887190 Link: https://lore.kernel.org/r/20201125130320.311059-1-coiby.xu@gmail.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-amd.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 4aea3e05e8c6..899c16c17b6d 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -429,7 +429,6 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type) pin_reg &= ~BIT(LEVEL_TRIG_OFF); pin_reg &= ~(ACTIVE_LEVEL_MASK << ACTIVE_LEVEL_OFF); pin_reg |= ACTIVE_HIGH << ACTIVE_LEVEL_OFF; - pin_reg |= DB_TYPE_REMOVE_GLITCH << DB_CNTRL_OFF; irq_set_handler_locked(d, handle_edge_irq); break; @@ -437,7 +436,6 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type) pin_reg &= ~BIT(LEVEL_TRIG_OFF); pin_reg &= ~(ACTIVE_LEVEL_MASK << ACTIVE_LEVEL_OFF); pin_reg |= ACTIVE_LOW << ACTIVE_LEVEL_OFF; - pin_reg |= DB_TYPE_REMOVE_GLITCH << DB_CNTRL_OFF; irq_set_handler_locked(d, handle_edge_irq); break; @@ -445,7 +443,6 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type) pin_reg &= ~BIT(LEVEL_TRIG_OFF); pin_reg &= ~(ACTIVE_LEVEL_MASK << ACTIVE_LEVEL_OFF); pin_reg |= BOTH_EADGE << ACTIVE_LEVEL_OFF; - pin_reg |= DB_TYPE_REMOVE_GLITCH << DB_CNTRL_OFF; irq_set_handler_locked(d, handle_edge_irq); break; @@ -453,8 +450,6 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type) pin_reg |= LEVEL_TRIGGER << LEVEL_TRIG_OFF; pin_reg &= ~(ACTIVE_LEVEL_MASK << ACTIVE_LEVEL_OFF); pin_reg |= ACTIVE_HIGH << ACTIVE_LEVEL_OFF; - pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF); - pin_reg |= DB_TYPE_PRESERVE_LOW_GLITCH << DB_CNTRL_OFF; irq_set_handler_locked(d, handle_level_irq); break; @@ -462,8 +457,6 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type) pin_reg |= LEVEL_TRIGGER << LEVEL_TRIG_OFF; pin_reg &= ~(ACTIVE_LEVEL_MASK << ACTIVE_LEVEL_OFF); pin_reg |= ACTIVE_LOW << ACTIVE_LEVEL_OFF; - pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF); - pin_reg |= DB_TYPE_PRESERVE_HIGH_GLITCH << DB_CNTRL_OFF; irq_set_handler_locked(d, handle_level_irq); break; -- cgit v1.2.3 From 4e302c3b568eaf2aeebba804c07aba5d921a8c9e Mon Sep 17 00:00:00 2001 From: Diego Santa Cruz Date: Thu, 3 Dec 2020 22:47:03 +0100 Subject: misc: eeprom: at24: fix NVMEM name with custom AT24 device name When the "label" property is set on the AT24 EEPROM the NVMEM devid is set to NVMEM_DEVID_NONE, but it is not effective since there is a leftover line setting it back to NVMEM_DEVID_AUTO a few lines after. Fixes: 61f764c307f6 ("eeprom: at24: Support custom device names for AT24 EEPROMs") Signed-off-by: Diego Santa Cruz Signed-off-by: Bartosz Golaszewski --- drivers/misc/eeprom/at24.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 1c0a41803bb6..926408b41270 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -736,7 +736,6 @@ static int at24_probe(struct i2c_client *client) nvmem_config.type = NVMEM_TYPE_EEPROM; nvmem_config.dev = dev; - nvmem_config.id = NVMEM_DEVID_AUTO; nvmem_config.read_only = !writable; nvmem_config.root_only = !(flags & AT24_FLAG_IRUGO); nvmem_config.owner = THIS_MODULE; -- cgit v1.2.3 From 3f203f057edfcf6bd02c6b942799262bfcf31f73 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 4 Dec 2020 09:55:19 +0100 Subject: USB: serial: kl5kusb105: fix memleak on open Fix memory leak of control-message transfer buffer on successful open(). Fixes: 6774d5f53271 ("USB: serial: kl5kusb105: fix open error path") Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/kl5kusb105.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/usb/serial/kl5kusb105.c b/drivers/usb/serial/kl5kusb105.c index 5ee48b0650c4..5f6b82ebccc5 100644 --- a/drivers/usb/serial/kl5kusb105.c +++ b/drivers/usb/serial/kl5kusb105.c @@ -276,12 +276,12 @@ static int klsi_105_open(struct tty_struct *tty, struct usb_serial_port *port) priv->cfg.unknown2 = cfg->unknown2; spin_unlock_irqrestore(&priv->lock, flags); + kfree(cfg); + /* READ_ON and urb submission */ rc = usb_serial_generic_open(tty, port); - if (rc) { - retval = rc; - goto err_free_cfg; - } + if (rc) + return rc; rc = usb_control_msg(port->serial->dev, usb_sndctrlpipe(port->serial->dev, 0), @@ -324,8 +324,6 @@ err_disable_read: KLSI_TIMEOUT); err_generic_close: usb_serial_generic_close(port); -err_free_cfg: - kfree(cfg); return retval; } -- cgit v1.2.3 From 32a9e0c445fa5abfd8730461c3ae0be1860bc6b2 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 25 Nov 2020 21:49:53 +0100 Subject: mmc: tmio: improve bringing HW to a sane state with MMC_POWER_OFF Further testing of error cases revealed that downgrade is not enough, so we need to reset the SCC which is done by calling the custom reset function. This reset function can distinguish between the various SDHI variants, so protecting the call with MIN_RCAR2 is enough here. Fixes: 24ce2d7b8bea ("mmc: tmio: bring tuning HW to a sane state with MMC_POWER_OFF") Reported-by: Yoshihiro Shimoda Signed-off-by: Wolfram Sang Reviewed-by: Yoshihiro Shimoda Tested-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/20201125204953.3344-1-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/tmio_mmc_core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index cb4149fd12e0..ac4e7874a3f1 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -927,9 +927,9 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) switch (ios->power_mode) { case MMC_POWER_OFF: tmio_mmc_power_off(host); - /* Downgrade ensures a sane state for tuning HW (e.g. SCC) */ - if (host->mmc->ops->hs400_downgrade) - host->mmc->ops->hs400_downgrade(host->mmc); + /* For R-Car Gen2+, we need to reset SDHI specific SCC */ + if (host->pdata->flags & TMIO_MMC_MIN_RCAR2) + host->reset(host); host->set_clock(host, 0); break; case MMC_POWER_UP: -- cgit v1.2.3 From 8fca2b8706f39f86312c086229e0cb364f8b4f97 Mon Sep 17 00:00:00 2001 From: Wen Gong Date: Mon, 23 Nov 2020 16:45:52 +0800 Subject: mac80211: fix return value of ieee80211_chandef_he_6ghz_oper ieee80211_chandef_he_6ghz_oper() needs to return true if it determined a value 6 GHz chandef, fix that. Fixes: 1d00ce807efa ("mac80211: support S1G association") Signed-off-by: Wen Gong Link: https://lore.kernel.org/r/1606121152-3452-1-git-send-email-wgong@codeaurora.org [rewrite commit message] Signed-off-by: Johannes Berg --- net/mac80211/util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 49342060490f..94e624e9439b 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3455,7 +3455,7 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, *chandef = he_chandef; - return false; + return true; } bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper, -- cgit v1.2.3 From f495acd8851d7b345e5f0e521b2645b1e1f928a0 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Sun, 29 Nov 2020 17:30:44 +0200 Subject: cfg80211: initialize rekey_data In case we have old supplicant, the akm field is uninitialized. Signed-off-by: Sara Sharon Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20201129172929.930f0ab7ebee.Ic546e384efab3f4a89f318eafddc3eb7d556aecb@changeid Signed-off-by: Johannes Berg --- net/wireless/nl80211.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index a77174b99b07..f67ddf2cebcb 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12634,7 +12634,7 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; struct nlattr *tb[NUM_NL80211_REKEY_DATA]; - struct cfg80211_gtk_rekey_data rekey_data; + struct cfg80211_gtk_rekey_data rekey_data = {}; int err; if (!info->attrs[NL80211_ATTR_REKEY_DATA]) -- cgit v1.2.3 From bdeca45a0cc58f864f1eb2e919304203ff5c5f39 Mon Sep 17 00:00:00 2001 From: "Borwankar, Antara" Date: Sun, 29 Nov 2020 17:30:53 +0200 Subject: mac80211: set SDATA_STATE_RUNNING for monitor interfaces During restarrt, mac80211 is supposed to reconfigure the driver. When there's a monitor interface, the interface is added and the channel context for it was created, but not assigned to it as it was not considered running during the restart. Fix this by setting SDATA_STATE_RUNNING while adding monitor interfaces. Signed-off-by: Borwankar, Antara Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20201129172929.e1df99693a4c.I494579f28018c2d0b9d4083a664cf872c28405ae@changeid [reword commit log] Signed-off-by: Johannes Berg --- net/mac80211/iface.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 1be775979132..44154cc596cd 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -948,6 +948,8 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) return ret; } + set_bit(SDATA_STATE_RUNNING, &sdata->state); + ret = ieee80211_check_queues(sdata, NL80211_IFTYPE_MONITOR); if (ret) { kfree(sdata); -- cgit v1.2.3 From 6246d7c9d15aaff0bc3863f67900c6a6e6be921b Mon Sep 17 00:00:00 2001 From: Bean Huo Date: Wed, 2 Dec 2020 21:23:20 +0100 Subject: mmc: block: Fixup condition for CMD13 polling for RPMB requests The CMD13 polling is needed for commands with R1B responses. In commit a0d4c7eb71dd ("mmc: block: Add CMD13 polling for MMC IOCTLS with R1B response"), the intent was to introduce this for requests targeted to the RPMB partition. However, the condition to trigger the polling loop became wrong, leading to unnecessary polling. Let's fix the condition to avoid this. Fixes: a0d4c7eb71dd ("mmc: block: Add CMD13 polling for MMC IOCTLS with R1B response") Cc: stable@vger.kernel.org Reported-by: Zhan Liu Signed-off-by: Zhan Liu Signed-off-by: Bean Huo Link: https://lore.kernel.org/r/20201202202320.22165-1-huobean@gmail.com Signed-off-by: Ulf Hansson --- drivers/mmc/core/block.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 8d3df0be0355..42e27a298218 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -580,7 +580,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, memcpy(&(idata->ic.response), cmd.resp, sizeof(cmd.resp)); - if (idata->rpmb || (cmd.flags & MMC_RSP_R1B)) { + if (idata->rpmb || (cmd.flags & MMC_RSP_R1B) == MMC_RSP_R1B) { /* * Ensure RPMB/R1B command has completed by polling CMD13 * "Send Status". -- cgit v1.2.3 From c0d638a03bc5dfdb08fb95d0a79ecada25f40da8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 3 Dec 2020 23:29:16 +0100 Subject: mmc: mediatek: mark PM functions as __maybe_unused The #ifdef check for the suspend/resume functions is wrong: drivers/mmc/host/mtk-sd.c:2765:12: error: unused function 'msdc_suspend' [-Werror,-Wunused-function] static int msdc_suspend(struct device *dev) drivers/mmc/host/mtk-sd.c:2779:12: error: unused function 'msdc_resume' [-Werror,-Wunused-function] static int msdc_resume(struct device *dev) Remove the #ifdef and mark all four as __maybe_unused to aovid the problem. Fixes: c0a2074ac575 ("mmc: mediatek: Fix system suspend/resume support for CQHCI") Cc: stable@vger.kernel.org Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20201203222922.1067522-1-arnd@kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/mtk-sd.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 7eb99255ae3d..004fbfc23672 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -2604,7 +2604,6 @@ static int msdc_drv_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM static void msdc_save_reg(struct msdc_host *host) { u32 tune_reg = host->dev_comp->pad_tune_reg; @@ -2663,7 +2662,7 @@ static void msdc_restore_reg(struct msdc_host *host) __msdc_enable_sdio_irq(host, 1); } -static int msdc_runtime_suspend(struct device *dev) +static int __maybe_unused msdc_runtime_suspend(struct device *dev) { struct mmc_host *mmc = dev_get_drvdata(dev); struct msdc_host *host = mmc_priv(mmc); @@ -2673,7 +2672,7 @@ static int msdc_runtime_suspend(struct device *dev) return 0; } -static int msdc_runtime_resume(struct device *dev) +static int __maybe_unused msdc_runtime_resume(struct device *dev) { struct mmc_host *mmc = dev_get_drvdata(dev); struct msdc_host *host = mmc_priv(mmc); @@ -2683,7 +2682,7 @@ static int msdc_runtime_resume(struct device *dev) return 0; } -static int msdc_suspend(struct device *dev) +static int __maybe_unused msdc_suspend(struct device *dev) { struct mmc_host *mmc = dev_get_drvdata(dev); int ret; @@ -2697,11 +2696,10 @@ static int msdc_suspend(struct device *dev) return pm_runtime_force_suspend(dev); } -static int msdc_resume(struct device *dev) +static int __maybe_unused msdc_resume(struct device *dev) { return pm_runtime_force_resume(dev); } -#endif static const struct dev_pm_ops msdc_dev_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(msdc_suspend, msdc_resume) -- cgit v1.2.3 From da881ded10a65885cdcb87ab817eea3acf23dcf9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 4 Dec 2020 15:59:27 +0100 Subject: Revert "uas: bump hw_max_sectors to 2048 blocks for SS or faster drives" This reverts commit 5df7ef7d32fec1d6d1c34dbec019b461a12ce870 as Hans reports it causes problems on some systems. Until a "real" fix for this can be found, revert this change to get normal functionality back. Link: https://lore.kernel.org/r/70ca74c2-4a80-e25b-eca9-a63a75516673@redhat.com Cc: Tom Yan Cc: Alan Stern Tested-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/uas.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index c8a577309e8f..9369c6df80c3 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -849,8 +849,6 @@ static int uas_slave_configure(struct scsi_device *sdev) blk_queue_max_hw_sectors(sdev->request_queue, 64); else if (devinfo->flags & US_FL_MAX_SECTORS_240) blk_queue_max_hw_sectors(sdev->request_queue, 240); - else if (devinfo->udev->speed >= USB_SPEED_SUPER) - blk_queue_max_hw_sectors(sdev->request_queue, 2048); blk_queue_max_hw_sectors(sdev->request_queue, min_t(size_t, queue_max_hw_sectors(sdev->request_queue), -- cgit v1.2.3 From d5c65d32dc240bf600d9e54250a8133e93ece60a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 4 Dec 2020 16:00:34 +0100 Subject: Revert "uas: fix sdev->host->dma_dev" This reverts commit 558033c2828f832ab3b68c6f8b8710e0de6faef0 as Hans reports it causes problems on some systems. Until a "real" fix for this can be found, revert this change to get normal functionality back. Link: https://lore.kernel.org/r/70ca74c2-4a80-e25b-eca9-a63a75516673@redhat.com Cc: Tom Yan Cc: Alan Stern Tested-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/uas.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 9369c6df80c3..652d6d6f1f36 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -837,22 +837,17 @@ static int uas_slave_alloc(struct scsi_device *sdev) */ blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1)); + if (devinfo->flags & US_FL_MAX_SECTORS_64) + blk_queue_max_hw_sectors(sdev->request_queue, 64); + else if (devinfo->flags & US_FL_MAX_SECTORS_240) + blk_queue_max_hw_sectors(sdev->request_queue, 240); + return 0; } static int uas_slave_configure(struct scsi_device *sdev) { struct uas_dev_info *devinfo = sdev->hostdata; - struct device *dev = sdev->host->dma_dev; - - if (devinfo->flags & US_FL_MAX_SECTORS_64) - blk_queue_max_hw_sectors(sdev->request_queue, 64); - else if (devinfo->flags & US_FL_MAX_SECTORS_240) - blk_queue_max_hw_sectors(sdev->request_queue, 240); - - blk_queue_max_hw_sectors(sdev->request_queue, - min_t(size_t, queue_max_hw_sectors(sdev->request_queue), - dma_max_mapping_size(dev) >> SECTOR_SHIFT)); if (devinfo->flags & US_FL_NO_REPORT_OPCODES) sdev->no_report_opcodes = 1; @@ -1038,7 +1033,7 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) shost->can_queue = devinfo->qdepth - 2; usb_set_intfdata(intf, shost); - result = scsi_add_host_with_dma(shost, &intf->dev, udev->bus->sysdev); + result = scsi_add_host(shost, &intf->dev); if (result) goto free_streams; -- cgit v1.2.3 From 97ad4a77f23e30801d2c0ef0c12b59f0e5760e6e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 4 Dec 2020 16:01:23 +0100 Subject: Revert "usb-storage: fix sdev->host->dma_dev" This reverts commit 0154012f8018bba4d9971d1007c12ffd48539ddb as Hans reports it causes problems on some systems. Until a "real" fix for this can be found, revert this change to get normal functionality back. Link: https://lore.kernel.org/r/70ca74c2-4a80-e25b-eca9-a63a75516673@redhat.com Cc: Tom Yan Cc: Alan Stern Tested-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/scsiglue.c | 2 +- drivers/usb/storage/usb.c | 5 ++--- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 560efd1479ba..e5a971b83e3f 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -92,7 +92,7 @@ static int slave_alloc (struct scsi_device *sdev) static int slave_configure(struct scsi_device *sdev) { struct us_data *us = host_to_us(sdev->host); - struct device *dev = sdev->host->dma_dev; + struct device *dev = us->pusb_dev->bus->sysdev; /* * Many devices have trouble transferring more than 32KB at a time, diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c index c2ef367cf257..94a64729dc27 100644 --- a/drivers/usb/storage/usb.c +++ b/drivers/usb/storage/usb.c @@ -1049,9 +1049,8 @@ int usb_stor_probe2(struct us_data *us) goto BadDevice; usb_autopm_get_interface_no_resume(us->pusb_intf); snprintf(us->scsi_name, sizeof(us->scsi_name), "usb-storage %s", - dev_name(dev)); - result = scsi_add_host_with_dma(us_to_host(us), dev, - us->pusb_dev->bus->sysdev); + dev_name(&us->pusb_intf->dev)); + result = scsi_add_host(us_to_host(us), dev); if (result) { dev_warn(dev, "Unable to add the scsi host\n"); -- cgit v1.2.3 From 45c5775460f32ed8cdb7c16986ae1a2c254346b3 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 30 Nov 2020 09:30:33 +0100 Subject: usb: ohci-omap: Fix descriptor conversion There were a bunch of issues with the patch converting the OMAP1 OSK board to use descriptors for controlling the USB host: - The chip label was incorrect - The GPIO offset was off-by-one - The code should use sleeping accessors This patch tries to fix all issues at the same time. Cc: Aaro Koskinen Reported-by: Aaro Koskinen Fixes: 15d157e87443 ("usb: ohci-omap: Convert to use GPIO descriptors") Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20201130083033.29435-1-linus.walleij@linaro.org Signed-off-by: Greg Kroah-Hartman --- arch/arm/mach-omap1/board-osk.c | 2 +- drivers/usb/host/ohci-omap.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c index 144b9caa935c..a720259099ed 100644 --- a/arch/arm/mach-omap1/board-osk.c +++ b/arch/arm/mach-omap1/board-osk.c @@ -288,7 +288,7 @@ static struct gpiod_lookup_table osk_usb_gpio_table = { .dev_id = "ohci", .table = { /* Power GPIO on the I2C-attached TPS65010 */ - GPIO_LOOKUP("i2c-tps65010", 1, "power", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("tps65010", 0, "power", GPIO_ACTIVE_HIGH), GPIO_LOOKUP(OMAP_GPIO_LABEL, 9, "overcurrent", GPIO_ACTIVE_HIGH), }, diff --git a/drivers/usb/host/ohci-omap.c b/drivers/usb/host/ohci-omap.c index 9ccdf2c216b5..6374501ba139 100644 --- a/drivers/usb/host/ohci-omap.c +++ b/drivers/usb/host/ohci-omap.c @@ -91,14 +91,14 @@ static int omap_ohci_transceiver_power(struct ohci_omap_priv *priv, int on) | ((1 << 5/*usb1*/) | (1 << 3/*usb2*/)), INNOVATOR_FPGA_CAM_USB_CONTROL); else if (priv->power) - gpiod_set_value(priv->power, 0); + gpiod_set_value_cansleep(priv->power, 0); } else { if (machine_is_omap_innovator() && cpu_is_omap1510()) __raw_writeb(__raw_readb(INNOVATOR_FPGA_CAM_USB_CONTROL) & ~((1 << 5/*usb1*/) | (1 << 3/*usb2*/)), INNOVATOR_FPGA_CAM_USB_CONTROL); else if (priv->power) - gpiod_set_value(priv->power, 1); + gpiod_set_value_cansleep(priv->power, 1); } return 0; -- cgit v1.2.3 From a4b98a7512f18534ce33a7e98e49115af59ffa00 Mon Sep 17 00:00:00 2001 From: Vamsi Krishna Samavedam Date: Mon, 30 Nov 2020 12:34:53 -0800 Subject: usb: gadget: f_fs: Use local copy of descriptors for userspace copy The function may be unbound causing the ffs_ep and its descriptors to be freed while userspace is in the middle of an ioctl requesting the same descriptors. Avoid dangling pointer reference by first making a local copy of desctiptors before releasing the spinlock. Fixes: c559a3534109 ("usb: gadget: f_fs: add ioctl returning ep descriptor") Reviewed-by: Peter Chen Signed-off-by: Vamsi Krishna Samavedam Signed-off-by: Jack Pham Cc: stable Link: https://lore.kernel.org/r/20201130203453.28154-1-jackp@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_fs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 046f770a76da..c727cb5de871 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1324,7 +1324,7 @@ static long ffs_epfile_ioctl(struct file *file, unsigned code, case FUNCTIONFS_ENDPOINT_DESC: { int desc_idx; - struct usb_endpoint_descriptor *desc; + struct usb_endpoint_descriptor desc1, *desc; switch (epfile->ffs->gadget->speed) { case USB_SPEED_SUPER: @@ -1336,10 +1336,12 @@ static long ffs_epfile_ioctl(struct file *file, unsigned code, default: desc_idx = 0; } + desc = epfile->ep->descs[desc_idx]; + memcpy(&desc1, desc, desc->bLength); spin_unlock_irq(&epfile->ffs->eps_lock); - ret = copy_to_user((void __user *)value, desc, desc->bLength); + ret = copy_to_user((void __user *)value, &desc1, desc1.bLength); if (ret) ret = -EFAULT; return ret; -- cgit v1.2.3 From 12c8a8ca117f3d734babc3fba131fdaa329d2163 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Fri, 4 Dec 2020 18:21:16 +0800 Subject: xsk: Return error code if force_zc is set If force_zc is set, we should exit out with an error, not fall back to copy mode. Fixes: 921b68692abb ("xsk: Enable sharing of dma mappings") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Signed-off-by: Daniel Borkmann Acked-by: Magnus Karlsson Link: https://lore.kernel.org/bpf/1607077277-41995-1-git-send-email-zhangchangzhong@huawei.com --- net/xdp/xsk_buff_pool.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 9287eddec52c..d5adeee9d5d9 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -175,6 +175,7 @@ static int __xp_assign_dev(struct xsk_buff_pool *pool, if (!pool->dma_pages) { WARN(1, "Driver did not DMA map zero-copy buffers"); + err = -EINVAL; goto err_unreg_xsk; } pool->umem->zc = true; -- cgit v1.2.3 From 54ffccbf053b5b6ca4f6e45094b942fab92a25fc Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Thu, 3 Dec 2020 02:25:04 +0100 Subject: tty: Fix ->pgrp locking in tiocspgrp() tiocspgrp() takes two tty_struct pointers: One to the tty that userspace passed to ioctl() (`tty`) and one to the TTY being changed (`real_tty`). These pointers are different when ioctl() is called with a master fd. To properly lock real_tty->pgrp, we must take real_tty->ctrl_lock. This bug makes it possible for racing ioctl(TIOCSPGRP, ...) calls on both sides of a PTY pair to corrupt the refcount of `struct pid`, leading to use-after-free errors. Fixes: 47f86834bbd4 ("redo locking of tty->pgrp") CC: stable@kernel.org Signed-off-by: Jann Horn Reviewed-by: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_jobctrl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/tty_jobctrl.c b/drivers/tty/tty_jobctrl.c index 28a23a0fef21..baadeea4a289 100644 --- a/drivers/tty/tty_jobctrl.c +++ b/drivers/tty/tty_jobctrl.c @@ -494,10 +494,10 @@ static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t if (session_of_pgrp(pgrp) != task_session(current)) goto out_unlock; retval = 0; - spin_lock_irq(&tty->ctrl_lock); + spin_lock_irq(&real_tty->ctrl_lock); put_pid(real_tty->pgrp); real_tty->pgrp = get_pid(pgrp); - spin_unlock_irq(&tty->ctrl_lock); + spin_unlock_irq(&real_tty->ctrl_lock); out_unlock: rcu_read_unlock(); return retval; -- cgit v1.2.3 From c8bcd9c5be24fb9e6132e97da5a35e55a83e36b9 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Thu, 3 Dec 2020 02:25:05 +0100 Subject: tty: Fix ->session locking Currently, locking of ->session is very inconsistent; most places protect it using the legacy tty mutex, but disassociate_ctty(), __do_SAK(), tiocspgrp() and tiocgsid() don't. Two of the writers hold the ctrl_lock (because they already need it for ->pgrp), but __proc_set_tty() doesn't do that yet. On a PREEMPT=y system, an unprivileged user can theoretically abuse this broken locking to read 4 bytes of freed memory via TIOCGSID if tiocgsid() is preempted long enough at the right point. (Other things might also go wrong, especially if root-only ioctls are involved; I'm not sure about that.) Change the locking on ->session such that: - tty_lock() is held by all writers: By making disassociate_ctty() hold it. This should be fine because the same lock can already be taken through the call to tty_vhangup_session(). The tricky part is that we need to shorten the area covered by siglock to be able to take tty_lock() without ugly retry logic; as far as I can tell, this should be fine, since nothing in the signal_struct is touched in the `if (tty)` branch. - ctrl_lock is held by all writers: By changing __proc_set_tty() to hold the lock a little longer. - All readers that aren't holding tty_lock() hold ctrl_lock: By adding locking to tiocgsid() and __do_SAK(), and expanding the area covered by ctrl_lock in tiocspgrp(). Cc: stable@kernel.org Signed-off-by: Jann Horn Reviewed-by: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_io.c | 7 ++++++- drivers/tty/tty_jobctrl.c | 44 +++++++++++++++++++++++++++++++------------- include/linux/tty.h | 4 ++++ 3 files changed, 41 insertions(+), 14 deletions(-) diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 9f8b9a567b35..56ade99ef99f 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2897,10 +2897,14 @@ void __do_SAK(struct tty_struct *tty) struct task_struct *g, *p; struct pid *session; int i; + unsigned long flags; if (!tty) return; - session = tty->session; + + spin_lock_irqsave(&tty->ctrl_lock, flags); + session = get_pid(tty->session); + spin_unlock_irqrestore(&tty->ctrl_lock, flags); tty_ldisc_flush(tty); @@ -2932,6 +2936,7 @@ void __do_SAK(struct tty_struct *tty) task_unlock(p); } while_each_thread(g, p); read_unlock(&tasklist_lock); + put_pid(session); #endif } diff --git a/drivers/tty/tty_jobctrl.c b/drivers/tty/tty_jobctrl.c index baadeea4a289..aa6d0537b379 100644 --- a/drivers/tty/tty_jobctrl.c +++ b/drivers/tty/tty_jobctrl.c @@ -103,8 +103,8 @@ static void __proc_set_tty(struct tty_struct *tty) put_pid(tty->session); put_pid(tty->pgrp); tty->pgrp = get_pid(task_pgrp(current)); - spin_unlock_irqrestore(&tty->ctrl_lock, flags); tty->session = get_pid(task_session(current)); + spin_unlock_irqrestore(&tty->ctrl_lock, flags); if (current->signal->tty) { tty_debug(tty, "current tty %s not NULL!!\n", current->signal->tty->name); @@ -293,20 +293,23 @@ void disassociate_ctty(int on_exit) spin_lock_irq(¤t->sighand->siglock); put_pid(current->signal->tty_old_pgrp); current->signal->tty_old_pgrp = NULL; - tty = tty_kref_get(current->signal->tty); + spin_unlock_irq(¤t->sighand->siglock); + if (tty) { unsigned long flags; + + tty_lock(tty); spin_lock_irqsave(&tty->ctrl_lock, flags); put_pid(tty->session); put_pid(tty->pgrp); tty->session = NULL; tty->pgrp = NULL; spin_unlock_irqrestore(&tty->ctrl_lock, flags); + tty_unlock(tty); tty_kref_put(tty); } - spin_unlock_irq(¤t->sighand->siglock); /* Now clear signal->tty under the lock */ read_lock(&tasklist_lock); session_clear_tty(task_session(current)); @@ -477,14 +480,19 @@ static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t return -ENOTTY; if (retval) return retval; - if (!current->signal->tty || - (current->signal->tty != real_tty) || - (real_tty->session != task_session(current))) - return -ENOTTY; + if (get_user(pgrp_nr, p)) return -EFAULT; if (pgrp_nr < 0) return -EINVAL; + + spin_lock_irq(&real_tty->ctrl_lock); + if (!current->signal->tty || + (current->signal->tty != real_tty) || + (real_tty->session != task_session(current))) { + retval = -ENOTTY; + goto out_unlock_ctrl; + } rcu_read_lock(); pgrp = find_vpid(pgrp_nr); retval = -ESRCH; @@ -494,12 +502,12 @@ static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t if (session_of_pgrp(pgrp) != task_session(current)) goto out_unlock; retval = 0; - spin_lock_irq(&real_tty->ctrl_lock); put_pid(real_tty->pgrp); real_tty->pgrp = get_pid(pgrp); - spin_unlock_irq(&real_tty->ctrl_lock); out_unlock: rcu_read_unlock(); +out_unlock_ctrl: + spin_unlock_irq(&real_tty->ctrl_lock); return retval; } @@ -511,20 +519,30 @@ out_unlock: * * Obtain the session id of the tty. If there is no session * return an error. - * - * Locking: none. Reference to current->signal->tty is safe. */ static int tiocgsid(struct tty_struct *tty, struct tty_struct *real_tty, pid_t __user *p) { + unsigned long flags; + pid_t sid; + /* * (tty == real_tty) is a cheap way of * testing if the tty is NOT a master pty. */ if (tty == real_tty && current->signal->tty != real_tty) return -ENOTTY; + + spin_lock_irqsave(&real_tty->ctrl_lock, flags); if (!real_tty->session) - return -ENOTTY; - return put_user(pid_vnr(real_tty->session), p); + goto err; + sid = pid_vnr(real_tty->session); + spin_unlock_irqrestore(&real_tty->ctrl_lock, flags); + + return put_user(sid, p); + +err: + spin_unlock_irqrestore(&real_tty->ctrl_lock, flags); + return -ENOTTY; } /* diff --git a/include/linux/tty.h b/include/linux/tty.h index a99e9b8e4e31..eb33d948788c 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -306,6 +306,10 @@ struct tty_struct { struct termiox *termiox; /* May be NULL for unsupported */ char name[64]; struct pid *pgrp; /* Protected by ctrl lock */ + /* + * Writes protected by both ctrl lock and legacy mutex, readers must use + * at least one of them. + */ struct pid *session; unsigned long flags; int count; -- cgit v1.2.3 From 3ee16db390b42b8a21f2ad2ea2518f3469c6e532 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Mon, 30 Nov 2020 10:57:43 -0500 Subject: dm: fix IO splitting Commit 882ec4e609c1 ("dm table: stack 'chunk_sectors' limit to account for target-specific splitting") caused a couple regressions: 1) Using lcm_not_zero() when stacking chunk_sectors was a bug because chunk_sectors must reflect the most limited of all devices in the IO stack. 2) DM targets that set max_io_len but that do _not_ provide an .iterate_devices method no longer had there IO split properly. And commit 5091cdec56fa ("dm: change max_io_len() to use blk_max_size_offset()") also caused a regression where DM no longer supported varied (per target) IO splitting. The implication being the potential for severely reduced performance for IO stacks that use a DM target like dm-cache to hide performance limitations of a slower device (e.g. one that requires 4K IO splitting). Coming full circle: Fix all these issues by discontinuing stacking chunk_sectors up using ti->max_io_len in dm_calculate_queue_limits(), add optional chunk_sectors override argument to blk_max_size_offset() and update DM's max_io_len() to pass ti->max_io_len to its blk_max_size_offset() call. Passing in an optional chunk_sectors override to blk_max_size_offset() allows for code reuse of block's centralized calculation for max IO size based on provided offset and split boundary. Fixes: 882ec4e609c1 ("dm table: stack 'chunk_sectors' limit to account for target-specific splitting") Fixes: 5091cdec56fa ("dm: change max_io_len() to use blk_max_size_offset()") Cc: stable@vger.kernel.org Reported-by: John Dorminy Reported-by: Bruce Johnston Reported-by: Kirill Tkhai Reviewed-by: John Dorminy Signed-off-by: Mike Snitzer Reviewed-by: Jens Axboe --- block/blk-merge.c | 2 +- drivers/md/dm-table.c | 5 ----- drivers/md/dm.c | 19 +++++++++++-------- include/linux/blkdev.h | 11 ++++++----- 4 files changed, 18 insertions(+), 19 deletions(-) diff --git a/block/blk-merge.c b/block/blk-merge.c index bcf5e4580603..97b7c2821565 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -144,7 +144,7 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q, static inline unsigned get_max_io_size(struct request_queue *q, struct bio *bio) { - unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector); + unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector, 0); unsigned max_sectors = sectors; unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT; unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 2073ee8d18f4..7eeb7c4169c9 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -1449,10 +1448,6 @@ int dm_calculate_queue_limits(struct dm_table *table, zone_sectors = ti_limits.chunk_sectors; } - /* Stack chunk_sectors if target-specific splitting is required */ - if (ti->max_io_len) - ti_limits.chunk_sectors = lcm_not_zero(ti->max_io_len, - ti_limits.chunk_sectors); /* Set I/O hints portion of queue limits */ if (ti->type->io_hints) ti->type->io_hints(ti, &ti_limits); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 98866e725f25..f7eb3d2964f3 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1039,15 +1039,18 @@ static sector_t max_io_len(struct dm_target *ti, sector_t sector) sector_t max_len; /* - * Does the target need to split even further? - * - q->limits.chunk_sectors reflects ti->max_io_len so - * blk_max_size_offset() provides required splitting. - * - blk_max_size_offset() also respects q->limits.max_sectors + * Does the target need to split IO even further? + * - varied (per target) IO splitting is a tenet of DM; this + * explains why stacked chunk_sectors based splitting via + * blk_max_size_offset() isn't possible here. So pass in + * ti->max_io_len to override stacked chunk_sectors. */ - max_len = blk_max_size_offset(ti->table->md->queue, - target_offset); - if (len > max_len) - len = max_len; + if (ti->max_io_len) { + max_len = blk_max_size_offset(ti->table->md->queue, + target_offset, ti->max_io_len); + if (len > max_len) + len = max_len; + } return len; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 639cae2c158b..24ae504cf77d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1073,11 +1073,12 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, * file system requests. */ static inline unsigned int blk_max_size_offset(struct request_queue *q, - sector_t offset) + sector_t offset, + unsigned int chunk_sectors) { - unsigned int chunk_sectors = q->limits.chunk_sectors; - - if (!chunk_sectors) + if (!chunk_sectors && q->limits.chunk_sectors) + chunk_sectors = q->limits.chunk_sectors; + else return q->limits.max_sectors; if (likely(is_power_of_2(chunk_sectors))) @@ -1101,7 +1102,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, req_op(rq) == REQ_OP_SECURE_ERASE) return blk_queue_get_max_sectors(q, req_op(rq)); - return min(blk_max_size_offset(q, offset), + return min(blk_max_size_offset(q, offset, 0), blk_queue_get_max_sectors(q, req_op(rq))); } -- cgit v1.2.3 From f05c4403db5bba881d4964e731f6da35be46aabd Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 4 Dec 2020 15:19:27 -0500 Subject: dm: fix double RCU unlock in dm_dax_zero_page_range() error path Remove redundant dm_put_live_table() in dm_dax_zero_page_range() error path to fix sparse warning: drivers/md/dm.c:1208:9: warning: context imbalance in 'dm_dax_zero_page_range' - unexpected unlock Fixes: cdf6cdcd3b99a ("dm,dax: Add dax zero_page_range operation") Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer --- drivers/md/dm.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index f7eb3d2964f3..45c623ff931a 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1201,11 +1201,9 @@ static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, * ->zero_page_range() is mandatory dax operation. If we are * here, something is wrong. */ - dm_put_live_table(md, srcu_idx); goto out; } ret = ti->type->dax_zero_page_range(ti, pgoff, nr_pages); - out: dm_put_live_table(md, srcu_idx); -- cgit v1.2.3 From bde3808bc8c2741ad3d804f84720409aee0c2972 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 4 Dec 2020 15:25:18 -0500 Subject: dm: remove invalid sparse __acquires and __releases annotations Fixes sparse warnings: drivers/md/dm.c:508:12: warning: context imbalance in 'dm_prepare_ioctl' - wrong count at exit drivers/md/dm.c:543:13: warning: context imbalance in 'dm_unprepare_ioctl' - wrong count at exit Fixes: 971888c46993f ("dm: hold DM table for duration of ioctl rather than use blkdev_get") Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer --- drivers/md/dm.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 45c623ff931a..4e0cbfe3f14d 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -509,7 +509,6 @@ out: static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx, struct block_device **bdev) - __acquires(md->io_barrier) { struct dm_target *tgt; struct dm_table *map; @@ -543,7 +542,6 @@ retry: } static void dm_unprepare_ioctl(struct mapped_device *md, int srcu_idx) - __releases(md->io_barrier) { dm_put_live_table(md, srcu_idx); } -- cgit v1.2.3 From bcee5278958802b40ee8b26679155a6d9231783e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 4 Dec 2020 16:36:16 -0500 Subject: tracing: Fix userstacktrace option for instances When the instances were able to use their own options, the userstacktrace option was left hardcoded for the top level. This made the instance userstacktrace option bascially into a nop, and will confuse users that set it, but nothing happens (I was confused when it happened to me!) Cc: stable@vger.kernel.org Fixes: 16270145ce6b ("tracing: Add trace options for core options to instances") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 7d53c5bdea3e..06134189e9a7 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -163,7 +163,8 @@ static union trace_eval_map_item *trace_eval_maps; #endif /* CONFIG_TRACE_EVAL_MAP_FILE */ int tracing_set_tracer(struct trace_array *tr, const char *buf); -static void ftrace_trace_userstack(struct trace_buffer *buffer, +static void ftrace_trace_userstack(struct trace_array *tr, + struct trace_buffer *buffer, unsigned long flags, int pc); #define MAX_TRACER_SIZE 100 @@ -2870,7 +2871,7 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, * two. They are not that meaningful. */ ftrace_trace_stack(tr, buffer, flags, regs ? 0 : STACK_SKIP, pc, regs); - ftrace_trace_userstack(buffer, flags, pc); + ftrace_trace_userstack(tr, buffer, flags, pc); } /* @@ -3056,13 +3057,14 @@ EXPORT_SYMBOL_GPL(trace_dump_stack); static DEFINE_PER_CPU(int, user_stack_count); static void -ftrace_trace_userstack(struct trace_buffer *buffer, unsigned long flags, int pc) +ftrace_trace_userstack(struct trace_array *tr, + struct trace_buffer *buffer, unsigned long flags, int pc) { struct trace_event_call *call = &event_user_stack; struct ring_buffer_event *event; struct userstack_entry *entry; - if (!(global_trace.trace_flags & TRACE_ITER_USERSTACKTRACE)) + if (!(tr->trace_flags & TRACE_ITER_USERSTACKTRACE)) return; /* @@ -3101,7 +3103,8 @@ ftrace_trace_userstack(struct trace_buffer *buffer, unsigned long flags, int pc) preempt_enable(); } #else /* CONFIG_USER_STACKTRACE_SUPPORT */ -static void ftrace_trace_userstack(struct trace_buffer *buffer, +static void ftrace_trace_userstack(struct trace_array *tr, + struct trace_buffer *buffer, unsigned long flags, int pc) { } -- cgit v1.2.3 From 4eef8b1f36f2ff06966b8f7c2143ef0c447877de Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Thu, 3 Dec 2020 19:40:47 +0100 Subject: net/sched: fq_pie: initialize timer earlier in fq_pie_init() with the following tdc testcase: 83be: (qdisc, fq_pie) Create FQ-PIE with invalid number of flows as fq_pie_init() fails, fq_pie_destroy() is called to clean up. Since the timer is not yet initialized, it's possible to observe a splat like this: INFO: trying to register non-static key. the code is fine but needs lockdep annotation. turning off the locking correctness validator. CPU: 0 PID: 975 Comm: tc Not tainted 5.10.0-rc4+ #298 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 Call Trace: dump_stack+0x99/0xcb register_lock_class+0x12dd/0x1750 __lock_acquire+0xfe/0x3970 lock_acquire+0x1c8/0x7f0 del_timer_sync+0x49/0xd0 fq_pie_destroy+0x3f/0x80 [sch_fq_pie] qdisc_create+0x916/0x1160 tc_modify_qdisc+0x3c4/0x1630 rtnetlink_rcv_msg+0x346/0x8e0 netlink_unicast+0x439/0x630 netlink_sendmsg+0x719/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5ba/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 [...] ODEBUG: assert_init not available (active state 0) object type: timer_list hint: 0x0 WARNING: CPU: 0 PID: 975 at lib/debugobjects.c:508 debug_print_object+0x162/0x210 [...] Call Trace: debug_object_assert_init+0x268/0x380 try_to_del_timer_sync+0x6a/0x100 del_timer_sync+0x9e/0xd0 fq_pie_destroy+0x3f/0x80 [sch_fq_pie] qdisc_create+0x916/0x1160 tc_modify_qdisc+0x3c4/0x1630 rtnetlink_rcv_msg+0x346/0x8e0 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x719/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5ba/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 fix it moving timer_setup() before any failure, like it was done on 'red' with former commit 608b4adab178 ("net_sched: initialize timer earlier in red_init()"). Fixes: ec97ecf1ebe4 ("net: sched: add Flow Queue PIE packet scheduler") Signed-off-by: Davide Caratti Reviewed-by: Cong Wang Link: https://lore.kernel.org/r/2e78e01c504c633ebdff18d041833cf2e079a3a4.1607020450.git.dcaratti@redhat.com Signed-off-by: Jakub Kicinski --- net/sched/sch_fq_pie.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 4dda15588cf4..949163fe68af 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -401,6 +401,7 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, INIT_LIST_HEAD(&q->new_flows); INIT_LIST_HEAD(&q->old_flows); + timer_setup(&q->adapt_timer, fq_pie_timer, 0); if (opt) { err = fq_pie_change(sch, opt, extack); @@ -426,7 +427,6 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, pie_vars_init(&flow->vars); } - timer_setup(&q->adapt_timer, fq_pie_timer, 0); mod_timer(&q->adapt_timer, jiffies + HZ / 2); return 0; -- cgit v1.2.3 From 65f33b35722952fa076811d5686bfd8a611a80fa Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 4 Dec 2020 17:21:03 -0500 Subject: block: fix incorrect branching in blk_max_size_offset() If non-zero 'chunk_sectors' is passed in to blk_max_size_offset() that override will be incorrectly ignored. Old blk_max_size_offset() branching, prior to commit 3ee16db390b4, must be used only if passed 'chunk_sectors' override is zero. Fixes: 3ee16db390b4 ("dm: fix IO splitting") Cc: stable@vger.kernel.org # 5.9 Reported-by: John Dorminy Signed-off-by: Mike Snitzer --- include/linux/blkdev.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 24ae504cf77d..033eb5f73b65 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1076,10 +1076,12 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q, sector_t offset, unsigned int chunk_sectors) { - if (!chunk_sectors && q->limits.chunk_sectors) - chunk_sectors = q->limits.chunk_sectors; - else - return q->limits.max_sectors; + if (!chunk_sectors) { + if (q->limits.chunk_sectors) + chunk_sectors = q->limits.chunk_sectors; + else + return q->limits.max_sectors; + } if (likely(is_power_of_2(chunk_sectors))) chunk_sectors -= offset & (chunk_sectors - 1); -- cgit v1.2.3 From 1130b252480f3c98cf468e78c1c5c516b390a29c Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 3 Dec 2020 15:51:06 -0600 Subject: net: ipa: pass the correct size when freeing DMA memory When the coherent memory is freed in gsi_trans_pool_exit_dma(), we are mistakenly passing the size of a single element in the pool rather than the actual allocated size. Fix this bug. Fixes: 9dd441e4ed575 ("soc: qcom: ipa: GSI transactions") Reported-by: Stephen Boyd Tested-by: Sujit Kautkar Signed-off-by: Alex Elder Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20201203215106.17450-1-elder@linaro.org Signed-off-by: Jakub Kicinski --- drivers/net/ipa/gsi_trans.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index e8599bb948c0..6c3ed5b17b80 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -156,6 +156,9 @@ int gsi_trans_pool_init_dma(struct device *dev, struct gsi_trans_pool *pool, /* The allocator will give us a power-of-2 number of pages. But we * can't guarantee that, so request it. That way we won't waste any * memory that would be available beyond the required space. + * + * Note that gsi_trans_pool_exit_dma() assumes the total allocated + * size is exactly (count * size). */ total_size = get_order(total_size) << PAGE_SHIFT; @@ -175,7 +178,9 @@ int gsi_trans_pool_init_dma(struct device *dev, struct gsi_trans_pool *pool, void gsi_trans_pool_exit_dma(struct device *dev, struct gsi_trans_pool *pool) { - dma_free_coherent(dev, pool->size, pool->base, pool->addr); + size_t total_size = pool->count * pool->size; + + dma_free_coherent(dev, total_size, pool->base, pool->addr); memset(pool, 0, sizeof(*pool)); } -- cgit v1.2.3 From 0b32e91fdfd87314af9943e69eb85a88adb4233c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 4 Dec 2020 00:20:37 +0100 Subject: ethernet: select CONFIG_CRC32 as needed A number of ethernet drivers require crc32 functionality to be avaialable in the kernel, causing a link error otherwise: arm-linux-gnueabi-ld: drivers/net/ethernet/agere/et131x.o: in function `et1310_setup_device_for_multicast': et131x.c:(.text+0x5918): undefined reference to `crc32_le' arm-linux-gnueabi-ld: drivers/net/ethernet/cadence/macb_main.o: in function `macb_start_xmit': macb_main.c:(.text+0x4b88): undefined reference to `crc32_le' arm-linux-gnueabi-ld: drivers/net/ethernet/faraday/ftgmac100.o: in function `ftgmac100_set_rx_mode': ftgmac100.c:(.text+0x2b38): undefined reference to `crc32_le' arm-linux-gnueabi-ld: drivers/net/ethernet/freescale/fec_main.o: in function `set_multicast_list': fec_main.c:(.text+0x6120): undefined reference to `crc32_le' arm-linux-gnueabi-ld: drivers/net/ethernet/freescale/fman/fman_dtsec.o: in function `dtsec_add_hash_mac_address': fman_dtsec.c:(.text+0x830): undefined reference to `crc32_le' arm-linux-gnueabi-ld: drivers/net/ethernet/freescale/fman/fman_dtsec.o:fman_dtsec.c:(.text+0xb68): more undefined references to `crc32_le' follow arm-linux-gnueabi-ld: drivers/net/ethernet/netronome/nfp/nfpcore/nfp_hwinfo.o: in function `nfp_hwinfo_read': nfp_hwinfo.c:(.text+0x250): undefined reference to `crc32_be' arm-linux-gnueabi-ld: nfp_hwinfo.c:(.text+0x288): undefined reference to `crc32_be' arm-linux-gnueabi-ld: drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.o: in function `nfp_resource_acquire': nfp_resource.c:(.text+0x144): undefined reference to `crc32_be' arm-linux-gnueabi-ld: nfp_resource.c:(.text+0x158): undefined reference to `crc32_be' arm-linux-gnueabi-ld: drivers/net/ethernet/nxp/lpc_eth.o: in function `lpc_eth_set_multicast_list': lpc_eth.c:(.text+0x1934): undefined reference to `crc32_le' arm-linux-gnueabi-ld: drivers/net/ethernet/rocker/rocker_ofdpa.o: in function `ofdpa_flow_tbl_do': rocker_ofdpa.c:(.text+0x2e08): undefined reference to `crc32_le' arm-linux-gnueabi-ld: drivers/net/ethernet/rocker/rocker_ofdpa.o: in function `ofdpa_flow_tbl_del': rocker_ofdpa.c:(.text+0x3074): undefined reference to `crc32_le' arm-linux-gnueabi-ld: drivers/net/ethernet/rocker/rocker_ofdpa.o: in function `ofdpa_port_fdb': arm-linux-gnueabi-ld: drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.o: in function `mlx5dr_ste_calc_hash_index': dr_ste.c:(.text+0x354): undefined reference to `crc32_le' arm-linux-gnueabi-ld: drivers/net/ethernet/microchip/lan743x_main.o: in function `lan743x_netdev_set_multicast': lan743x_main.c:(.text+0x5dc4): undefined reference to `crc32_le' Add the missing 'select CRC32' entries in Kconfig for each of them. Signed-off-by: Arnd Bergmann Acked-by: Nicolas Ferre Acked-by: Madalin Bucur Acked-by: Mark Einon Acked-by: Simon Horman Link: https://lore.kernel.org/r/20201203232114.1485603-1-arnd@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/agere/Kconfig | 1 + drivers/net/ethernet/cadence/Kconfig | 1 + drivers/net/ethernet/faraday/Kconfig | 1 + drivers/net/ethernet/freescale/Kconfig | 1 + drivers/net/ethernet/freescale/fman/Kconfig | 1 + drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 1 + drivers/net/ethernet/microchip/Kconfig | 1 + drivers/net/ethernet/netronome/Kconfig | 1 + drivers/net/ethernet/nxp/Kconfig | 1 + drivers/net/ethernet/rocker/Kconfig | 1 + 10 files changed, 10 insertions(+) diff --git a/drivers/net/ethernet/agere/Kconfig b/drivers/net/ethernet/agere/Kconfig index d92516ae59cc..9cd750184947 100644 --- a/drivers/net/ethernet/agere/Kconfig +++ b/drivers/net/ethernet/agere/Kconfig @@ -21,6 +21,7 @@ config ET131X tristate "Agere ET-1310 Gigabit Ethernet support" depends on PCI select PHYLIB + select CRC32 help This driver supports Agere ET-1310 ethernet adapters. diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig index 85858163bac5..e432a68ac520 100644 --- a/drivers/net/ethernet/cadence/Kconfig +++ b/drivers/net/ethernet/cadence/Kconfig @@ -23,6 +23,7 @@ config MACB tristate "Cadence MACB/GEM support" depends on HAS_DMA && COMMON_CLK select PHYLINK + select CRC32 help The Cadence MACB ethernet interface is found on many Atmel AT32 and AT91 parts. This driver also supports the Cadence GEM (Gigabit diff --git a/drivers/net/ethernet/faraday/Kconfig b/drivers/net/ethernet/faraday/Kconfig index c2677ec0564d..3d1e9a302148 100644 --- a/drivers/net/ethernet/faraday/Kconfig +++ b/drivers/net/ethernet/faraday/Kconfig @@ -33,6 +33,7 @@ config FTGMAC100 depends on !64BIT || BROKEN select PHYLIB select MDIO_ASPEED if MACH_ASPEED_G6 + select CRC32 help This driver supports the FTGMAC100 Gigabit Ethernet controller from Faraday. It is used on Faraday A369, Andes AG102 and some diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index a1d53ddf1593..3f9175bdce77 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -25,6 +25,7 @@ config FEC depends on (M523x || M527x || M5272 || M528x || M520x || M532x || \ ARCH_MXC || SOC_IMX28 || COMPILE_TEST) default ARCH_MXC || SOC_IMX28 if ARM + select CRC32 select PHYLIB imply PTP_1588_CLOCK help diff --git a/drivers/net/ethernet/freescale/fman/Kconfig b/drivers/net/ethernet/freescale/fman/Kconfig index 34150182cc35..48bf8088795d 100644 --- a/drivers/net/ethernet/freescale/fman/Kconfig +++ b/drivers/net/ethernet/freescale/fman/Kconfig @@ -4,6 +4,7 @@ config FSL_FMAN depends on FSL_SOC || ARCH_LAYERSCAPE || COMPILE_TEST select GENERIC_ALLOCATOR select PHYLIB + select CRC32 default n help Freescale Data-Path Acceleration Architecture Frame Manager diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 99f1ec3b2575..3e371d24c462 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -198,6 +198,7 @@ config MLX5_EN_TLS config MLX5_SW_STEERING bool "Mellanox Technologies software-managed steering" depends on MLX5_CORE_EN && MLX5_ESWITCH + select CRC32 default y help Build support for software-managed steering in the NIC. diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig index 31f9a82dc113..d0f6dfe0dcf3 100644 --- a/drivers/net/ethernet/microchip/Kconfig +++ b/drivers/net/ethernet/microchip/Kconfig @@ -47,6 +47,7 @@ config LAN743X depends on PCI select PHYLIB select CRC16 + select CRC32 help Support for the Microchip LAN743x PCI Express Gigabit Ethernet chip diff --git a/drivers/net/ethernet/netronome/Kconfig b/drivers/net/ethernet/netronome/Kconfig index d8b99d6a0356..b82758d5beed 100644 --- a/drivers/net/ethernet/netronome/Kconfig +++ b/drivers/net/ethernet/netronome/Kconfig @@ -22,6 +22,7 @@ config NFP depends on VXLAN || VXLAN=n depends on TLS && TLS_DEVICE || TLS_DEVICE=n select NET_DEVLINK + select CRC32 help This driver supports the Netronome(R) NFP4000/NFP6000 based cards working as a advanced Ethernet NIC. It works with both diff --git a/drivers/net/ethernet/nxp/Kconfig b/drivers/net/ethernet/nxp/Kconfig index ee83a71c2509..c84997db828c 100644 --- a/drivers/net/ethernet/nxp/Kconfig +++ b/drivers/net/ethernet/nxp/Kconfig @@ -3,6 +3,7 @@ config LPC_ENET tristate "NXP ethernet MAC on LPC devices" depends on ARCH_LPC32XX || COMPILE_TEST select PHYLIB + select CRC32 help Say Y or M here if you want to use the NXP ethernet MAC included on some NXP LPC devices. You can safely enable this option for LPC32xx diff --git a/drivers/net/ethernet/rocker/Kconfig b/drivers/net/ethernet/rocker/Kconfig index 99e1290e0307..2318811ff75a 100644 --- a/drivers/net/ethernet/rocker/Kconfig +++ b/drivers/net/ethernet/rocker/Kconfig @@ -19,6 +19,7 @@ if NET_VENDOR_ROCKER config ROCKER tristate "Rocker switch driver (EXPERIMENTAL)" depends on PCI && NET_SWITCHDEV && BRIDGE + select CRC32 help This driver supports Rocker switch device. -- cgit v1.2.3 From b410f04eb5b482b5efc4eee90de81ad35d3d923b Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Fri, 4 Dec 2020 16:48:14 +0800 Subject: ipv4: fix error return code in rtm_to_fib_config() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: d15662682db2 ("ipv4: Allow ipv6 gateway with ipv4 routes") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Reviewed-by: David Ahern Link: https://lore.kernel.org/r/1607071695-33740-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- net/ipv4/fib_frontend.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index b87140a1fa28..cdf6ec5aa45d 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -825,7 +825,7 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, if (has_gw && has_via) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); - goto errout; + return -EINVAL; } return 0; -- cgit v1.2.3 From ee4f52a8de2c6f78b01f10b4c330867d88c1653a Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Fri, 4 Dec 2020 16:48:56 +0800 Subject: net: bridge: vlan: fix error return code in __vlan_add() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: f8ed289fab84 ("bridge: vlan: use br_vlan_(get|put)_master to deal with refcounts") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/1607071737-33875-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- net/bridge/br_vlan.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 3e493eb85bb2..08c77418c687 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -266,8 +266,10 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, } masterv = br_vlan_get_master(br, v->vid, extack); - if (!masterv) + if (!masterv) { + err = -ENOMEM; goto out_filt; + } v->brvlan = masterv; if (br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)) { v->stats = netdev_alloc_pcpu_stats(struct br_vlan_stats); -- cgit v1.2.3 From bb2da7651a47dc042cb7fc9c40cd77092b6b4445 Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Fri, 4 Dec 2020 19:43:14 +0800 Subject: openvswitch: fix error return code in validate_and_copy_dec_ttl() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Changing 'return start' to 'return action_start' can fix this bug. Fixes: 69929d4c49e1 ("net: openvswitch: fix TTL decrement action netlink message format") Reported-by: Hulk Robot Signed-off-by: Wang Hai Reviewed-by: Eelco Chaudron Link: https://lore.kernel.org/r/20201204114314.1596-1-wanghai38@huawei.com Signed-off-by: Jakub Kicinski --- net/openvswitch/flow_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index ec0689ddc635..4c5c2331e764 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2531,7 +2531,7 @@ static int validate_and_copy_dec_ttl(struct net *net, action_start = add_nested_action_start(sfa, OVS_DEC_TTL_ATTR_ACTION, log); if (action_start < 0) - return start; + return action_start; err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, vlan_tci, mpls_label_count, log); -- cgit v1.2.3 From ed9b25d1970a4787ac6a39c2091e63b127ecbfc1 Mon Sep 17 00:00:00 2001 From: Serge Hallyn Date: Sun, 15 Nov 2020 21:55:31 -0600 Subject: [SECURITY] fix namespaced fscaps when !CONFIG_SECURITY MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Namespaced file capabilities were introduced in 8db6c34f1dbc . When userspace reads an xattr for a namespaced capability, a virtualized representation of it is returned if the caller is in a user namespace owned by the capability's owning rootid. The function which performs this virtualization was not hooked up if CONFIG_SECURITY=n. Therefore in that case the original xattr was shown instead of the virtualized one. To test this using libcap-bin (*1), $ v=$(mktemp) $ unshare -Ur setcap cap_sys_admin-eip $v $ unshare -Ur setcap -v cap_sys_admin-eip $v /tmp/tmp.lSiIFRvt8Y: OK "setcap -v" verifies the values instead of setting them, and will check whether the rootid value is set. Therefore, with this bug un-fixed, and with CONFIG_SECURITY=n, setcap -v will fail: $ v=$(mktemp) $ unshare -Ur setcap cap_sys_admin=eip $v $ unshare -Ur setcap -v cap_sys_admin=eip $v nsowner[got=1000, want=0],/tmp/tmp.HHDiOOl9fY differs in [] Fix this bug by calling cap_inode_getsecurity() in security_inode_getsecurity() instead of returning -EOPNOTSUPP, when CONFIG_SECURITY=n. *1 - note, if libcap is too old for getcap to have the '-n' option, then use verify-caps instead. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=209689 Cc: Hervé Guillemet Acked-by: Casey Schaufler Signed-off-by: Serge Hallyn Signed-off-by: Andrew G. Morgan Signed-off-by: James Morris --- include/linux/security.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/security.h b/include/linux/security.h index 0a0a03b36a3b..2befc0a25eb3 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -864,7 +864,7 @@ static inline int security_inode_killpriv(struct dentry *dentry) static inline int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) { - return -EOPNOTSUPP; + return cap_inode_getsecurity(inode, name, buffer, alloc); } static inline int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) -- cgit v1.2.3 From 905b2032fa424f253d9126271439cc1db2b01130 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Dec 2020 08:24:28 -0800 Subject: mac80211: mesh: fix mesh_pathtbl_init() error path If tbl_mpp can not be allocated, we call mesh_table_free(tbl_path) while tbl_path rhashtable has not yet been initialized, which causes panics. Simply factorize the rhashtable_init() call into mesh_table_alloc() WARNING: CPU: 1 PID: 8474 at kernel/workqueue.c:3040 __flush_work kernel/workqueue.c:3040 [inline] WARNING: CPU: 1 PID: 8474 at kernel/workqueue.c:3040 __cancel_work_timer+0x514/0x540 kernel/workqueue.c:3136 Modules linked in: CPU: 1 PID: 8474 Comm: syz-executor663 Not tainted 5.10.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__flush_work kernel/workqueue.c:3040 [inline] RIP: 0010:__cancel_work_timer+0x514/0x540 kernel/workqueue.c:3136 Code: 5d c3 e8 bf ae 29 00 0f 0b e9 f0 fd ff ff e8 b3 ae 29 00 0f 0b 43 80 3c 3e 00 0f 85 31 ff ff ff e9 34 ff ff ff e8 9c ae 29 00 <0f> 0b e9 dc fe ff ff 89 e9 80 e1 07 80 c1 03 38 c1 0f 8c 7d fd ff RSP: 0018:ffffc9000165f5a0 EFLAGS: 00010293 RAX: ffffffff814b7064 RBX: 0000000000000001 RCX: ffff888021c80000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff888024039ca0 R08: dffffc0000000000 R09: fffffbfff1dd3e64 R10: fffffbfff1dd3e64 R11: 0000000000000000 R12: 1ffff920002cbebd R13: ffff888024039c88 R14: 1ffff11004807391 R15: dffffc0000000000 FS: 0000000001347880(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000140 CR3: 000000002cc0a000 CR4: 00000000001506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: rhashtable_free_and_destroy+0x25/0x9c0 lib/rhashtable.c:1137 mesh_table_free net/mac80211/mesh_pathtbl.c:69 [inline] mesh_pathtbl_init+0x287/0x2e0 net/mac80211/mesh_pathtbl.c:785 ieee80211_mesh_init_sdata+0x2ee/0x530 net/mac80211/mesh.c:1591 ieee80211_setup_sdata+0x733/0xc40 net/mac80211/iface.c:1569 ieee80211_if_add+0xd5c/0x1cd0 net/mac80211/iface.c:1987 ieee80211_add_iface+0x59/0x130 net/mac80211/cfg.c:125 rdev_add_virtual_intf net/wireless/rdev-ops.h:45 [inline] nl80211_new_interface+0x563/0xb40 net/wireless/nl80211.c:3855 genl_family_rcv_msg_doit net/netlink/genetlink.c:739 [inline] genl_family_rcv_msg net/netlink/genetlink.c:783 [inline] genl_rcv_msg+0xe4e/0x1280 net/netlink/genetlink.c:800 netlink_rcv_skb+0x190/0x3a0 net/netlink/af_netlink.c:2494 genl_rcv+0x24/0x40 net/netlink/genetlink.c:811 netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline] netlink_unicast+0x780/0x930 net/netlink/af_netlink.c:1330 netlink_sendmsg+0x9a8/0xd40 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0x519/0x800 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x2b1/0x360 net/socket.c:2440 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 60854fd94573 ("mac80211: mesh: convert path table to rhashtable") Signed-off-by: Eric Dumazet Reported-by: syzbot Reviewed-by: Johannes Berg Link: https://lore.kernel.org/r/20201204162428.2583119-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- net/mac80211/mesh_pathtbl.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 48f31ac9233c..620ecf922408 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -60,6 +60,7 @@ static struct mesh_table *mesh_table_alloc(void) atomic_set(&newtbl->entries, 0); spin_lock_init(&newtbl->gates_lock); spin_lock_init(&newtbl->walk_lock); + rhashtable_init(&newtbl->rhead, &mesh_rht_params); return newtbl; } @@ -773,9 +774,6 @@ int mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata) goto free_path; } - rhashtable_init(&tbl_path->rhead, &mesh_rht_params); - rhashtable_init(&tbl_mpp->rhead, &mesh_rht_params); - sdata->u.mesh.mesh_paths = tbl_path; sdata->u.mesh.mpp_paths = tbl_mpp; -- cgit v1.2.3 From c62dac0a35bb6d351cd568e97090c5fd3e7aa532 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 3 Dec 2020 23:32:50 +0100 Subject: i2c: mlxbf: select CONFIG_I2C_SLAVE If this is not enabled, the interfaces used in this driver do not work: drivers/i2c/busses/i2c-mlxbf.c:1888:3: error: implicit declaration of function 'i2c_slave_event' [-Werror,-Wimplicit-function-declaration] i2c_slave_event(slave, I2C_SLAVE_WRITE_REQUESTED, &value); ^ drivers/i2c/busses/i2c-mlxbf.c:1888:26: error: use of undeclared identifier 'I2C_SLAVE_WRITE_REQUESTED' i2c_slave_event(slave, I2C_SLAVE_WRITE_REQUESTED, &value); ^ drivers/i2c/busses/i2c-mlxbf.c:1890:32: error: use of undeclared identifier 'I2C_SLAVE_WRITE_RECEIVED' ret = i2c_slave_event(slave, I2C_SLAVE_WRITE_RECEIVED, ^ drivers/i2c/busses/i2c-mlxbf.c:1892:26: error: use of undeclared identifier 'I2C_SLAVE_STOP' i2c_slave_event(slave, I2C_SLAVE_STOP, &value); ^ Fixes: b5b5b32081cd ("i2c: mlxbf: I2C SMBus driver for Mellanox BlueField SoC") Signed-off-by: Arnd Bergmann Acked-by: Khalil Blaiech Signed-off-by: Wolfram Sang --- drivers/i2c/busses/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index a97a9d058198..a49e0ed4a599 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -734,6 +734,7 @@ config I2C_LPC2K config I2C_MLXBF tristate "Mellanox BlueField I2C controller" depends on MELLANOX_PLATFORM && ARM64 + select I2C_SLAVE help Enabling this option will add I2C SMBus support for Mellanox BlueField system. -- cgit v1.2.3 From 2bf9545626f8d09f552ab86d0047a415fe9a07a0 Mon Sep 17 00:00:00 2001 From: Wang Xiaojun Date: Wed, 2 Dec 2020 20:46:47 -0500 Subject: i2c: mlxbf: Fix the return check of devm_ioremap and ioremap devm_ioremap and ioremap may return NULL which cannot be checked by IS_ERR. Signed-off-by: Wang Xiaojun Reported-by: Hulk Robot Acked-by: Khalil Blaiech Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-mlxbf.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/i2c/busses/i2c-mlxbf.c b/drivers/i2c/busses/i2c-mlxbf.c index 33574d40ea9c..2fb0532d8a16 100644 --- a/drivers/i2c/busses/i2c-mlxbf.c +++ b/drivers/i2c/busses/i2c-mlxbf.c @@ -1258,9 +1258,9 @@ static int mlxbf_i2c_get_gpio(struct platform_device *pdev, return -EFAULT; gpio_res->io = devm_ioremap(dev, params->start, size); - if (IS_ERR(gpio_res->io)) { + if (!gpio_res->io) { devm_release_mem_region(dev, params->start, size); - return PTR_ERR(gpio_res->io); + return -ENOMEM; } return 0; @@ -1323,9 +1323,9 @@ static int mlxbf_i2c_get_corepll(struct platform_device *pdev, return -EFAULT; corepll_res->io = devm_ioremap(dev, params->start, size); - if (IS_ERR(corepll_res->io)) { + if (!corepll_res->io) { devm_release_mem_region(dev, params->start, size); - return PTR_ERR(corepll_res->io); + return -ENOMEM; } return 0; @@ -1717,9 +1717,9 @@ static int mlxbf_i2c_init_coalesce(struct platform_device *pdev, return -EFAULT; coalesce_res->io = ioremap(params->start, size); - if (IS_ERR(coalesce_res->io)) { + if (!coalesce_res->io) { release_mem_region(params->start, size); - return PTR_ERR(coalesce_res->io); + return -ENOMEM; } priv->coalesce = coalesce_res; -- cgit v1.2.3 From a54ba3465d86fa5dd7d41bb88c0b5e71fb3b627e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 3 Dec 2020 23:26:16 +0100 Subject: ch_ktls: fix build warning for ipv4-only config When CONFIG_IPV6 is disabled, clang complains that a variable is uninitialized for non-IPv4 data: drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c:1046:6: error: variable 'cntrl1' is used uninitialized whenever 'if' condition is false [-Werror,-Wsometimes-uninitialized] if (tx_info->ip_family == AF_INET) { ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c:1059:2: note: uninitialized use occurs here cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) | ^~~~~~ Replace the preprocessor conditional with the corresponding C version, and make the ipv4 case unconditional in this configuration to improve readability and avoid the warning. Fixes: 86716b51d14f ("ch_ktls: Update cheksum information") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20201203222641.964234-1-arnd@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c index 7f90b828d159..1b7e8c91b541 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c @@ -987,9 +987,7 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, struct fw_eth_tx_pkt_wr *wr; struct cpl_tx_pkt_core *cpl; u32 ctrl, iplen, maclen; -#if IS_ENABLED(CONFIG_IPV6) struct ipv6hdr *ip6; -#endif unsigned int ndesc; struct tcphdr *tcp; int len16, pktlen; @@ -1043,17 +1041,15 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, cpl->len = htons(pktlen); memcpy(buf, skb->data, pktlen); - if (tx_info->ip_family == AF_INET) { + if (!IS_ENABLED(CONFIG_IPV6) || tx_info->ip_family == AF_INET) { /* we need to correct ip header len */ ip = (struct iphdr *)(buf + maclen); ip->tot_len = htons(pktlen - maclen); cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP); -#if IS_ENABLED(CONFIG_IPV6) } else { ip6 = (struct ipv6hdr *)(buf + maclen); ip6->payload_len = htons(pktlen - maclen - iplen); cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP6); -#endif } cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) | -- cgit v1.2.3 From 4d1be581ec6b92a338bb7ed23e1381f45ddf336f Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Fri, 4 Dec 2020 14:35:06 +0100 Subject: can: softing: softing_netdev_open(): fix error handling If softing_netdev_open() fails, we should call close_candev() to avoid reference leak. Fixes: 03fd3cf5a179d ("can: add driver for Softing card") Signed-off-by: Zhang Qilong Acked-by: Kurt Van Dijck Link: https://lore.kernel.org/r/20201202151632.1343786-1-zhangqilong3@huawei.com Signed-off-by: Marc Kleine-Budde Link: https://lore.kernel.org/r/20201204133508.742120-2-mkl@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/can/softing/softing_main.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c index 9d2faaa39ce4..c9ca8b9fceb9 100644 --- a/drivers/net/can/softing/softing_main.c +++ b/drivers/net/can/softing/softing_main.c @@ -382,8 +382,13 @@ static int softing_netdev_open(struct net_device *ndev) /* check or determine and set bittime */ ret = open_candev(ndev); - if (!ret) - ret = softing_startstop(ndev, 1); + if (ret) + return ret; + + ret = softing_startstop(ndev, 1); + if (ret < 0) + close_candev(ndev); + return ret; } -- cgit v1.2.3 From 205704c618af0ab2366015d2281a3b0814d918a0 Mon Sep 17 00:00:00 2001 From: Stephen Suryaputra Date: Thu, 3 Dec 2020 22:06:04 -0500 Subject: vrf: packets with lladdr src needs dst at input with orig_iif when needs strict Depending on the order of the routes to fe80::/64 are installed on the VRF table, the NS for the source link-local address of the originator might be sent to the wrong interface. This patch ensures that packets with link-local addr source is doing a lookup with the orig_iif when the destination addr indicates that it is strict. Add the reproducer as a use case in self test script fcnal-test.sh. Fixes: b4869aa2f881 ("net: vrf: ipv6 support for local traffic to local addresses") Signed-off-by: Stephen Suryaputra Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20201204030604.18828-1-ssuryaextr@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/vrf.c | 10 +++- tools/testing/selftests/net/fcnal-test.sh | 95 +++++++++++++++++++++++++++++++ 2 files changed, 103 insertions(+), 2 deletions(-) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index f2793ffde191..b9b7e00b72a8 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1315,11 +1315,17 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, int orig_iif = skb->skb_iif; bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); bool is_ndisc = ipv6_ndisc_frame(skb); + bool is_ll_src; /* loopback, multicast & non-ND link-local traffic; do not push through - * packet taps again. Reset pkt_type for upper layers to process skb + * packet taps again. Reset pkt_type for upper layers to process skb. + * for packets with lladdr src, however, skip so that the dst can be + * determine at input using original ifindex in the case that daddr + * needs strict */ - if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) { + is_ll_src = ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL; + if (skb->pkt_type == PACKET_LOOPBACK || + (need_strict && !is_ndisc && !is_ll_src)) { skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IP6CB(skb)->flags |= IP6SKB_L3SLAVE; diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index fb5c55dd6df8..02b0b9ead40b 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -256,6 +256,28 @@ setup_cmd_nsb() fi } +setup_cmd_nsc() +{ + local cmd="$*" + local rc + + run_cmd_nsc ${cmd} + rc=$? + if [ $rc -ne 0 ]; then + # show user the command if not done so already + if [ "$VERBOSE" = "0" ]; then + echo "setup command: $cmd" + fi + echo "failed. stopping tests" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue" + read a + fi + exit $rc + fi +} + # set sysctl values in NS-A set_sysctl() { @@ -471,6 +493,36 @@ setup() sleep 1 } +setup_lla_only() +{ + # make sure we are starting with a clean slate + kill_procs + cleanup 2>/dev/null + + log_debug "Configuring network namespaces" + set -e + + create_ns ${NSA} "-" "-" + create_ns ${NSB} "-" "-" + create_ns ${NSC} "-" "-" + connect_ns ${NSA} ${NSA_DEV} "-" "-" \ + ${NSB} ${NSB_DEV} "-" "-" + connect_ns ${NSA} ${NSA_DEV2} "-" "-" \ + ${NSC} ${NSC_DEV} "-" "-" + + NSA_LINKIP6=$(get_linklocal ${NSA} ${NSA_DEV}) + NSB_LINKIP6=$(get_linklocal ${NSB} ${NSB_DEV}) + NSC_LINKIP6=$(get_linklocal ${NSC} ${NSC_DEV}) + + create_vrf ${NSA} ${VRF} ${VRF_TABLE} "-" "-" + ip -netns ${NSA} link set dev ${NSA_DEV} vrf ${VRF} + ip -netns ${NSA} link set dev ${NSA_DEV2} vrf ${VRF} + + set +e + + sleep 1 +} + ################################################################################ # IPv4 @@ -3787,10 +3839,53 @@ use_case_br() setup_cmd_nsb ip li del vlan100 2>/dev/null } +# VRF only. +# ns-A device is connected to both ns-B and ns-C on a single VRF but only has +# LLA on the interfaces +use_case_ping_lla_multi() +{ + setup_lla_only + # only want reply from ns-A + setup_cmd_nsb sysctl -qw net.ipv6.icmp.echo_ignore_multicast=1 + setup_cmd_nsc sysctl -qw net.ipv6.icmp.echo_ignore_multicast=1 + + log_start + run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV} + log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Pre cycle, ping out ns-B" + + run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV} + log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Pre cycle, ping out ns-C" + + # cycle/flap the first ns-A interface + setup_cmd ip link set ${NSA_DEV} down + setup_cmd ip link set ${NSA_DEV} up + sleep 1 + + log_start + run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV} + log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV}, ping out ns-B" + run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV} + log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV}, ping out ns-C" + + # cycle/flap the second ns-A interface + setup_cmd ip link set ${NSA_DEV2} down + setup_cmd ip link set ${NSA_DEV2} up + sleep 1 + + log_start + run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV} + log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV2}, ping out ns-B" + run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV} + log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV2}, ping out ns-C" +} + use_cases() { log_section "Use cases" + log_subsection "Device enslaved to bridge" use_case_br + log_subsection "Ping LLA with multiple interfaces" + use_case_ping_lla_multi } ################################################################################ -- cgit v1.2.3 From 4de377b659035309ba48638d70f3150d5c67611f Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Fri, 4 Dec 2020 16:49:42 +0800 Subject: net: marvell: prestera: Fix error return code in prestera_port_create() Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function. Fixes: 501ef3066c89 ("net: marvell: prestera: Add driver for Prestera family ASIC devices") Reported-by: Hulk Robot Signed-off-by: Zhang Changzhong Link: https://lore.kernel.org/r/1607071782-34006-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/prestera/prestera_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 0f20e0788cce..da4b286d1337 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -318,8 +318,10 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) goto err_port_init; } - if (port->fp_id >= PRESTERA_MAC_ADDR_NUM_MAX) + if (port->fp_id >= PRESTERA_MAC_ADDR_NUM_MAX) { + err = -EINVAL; goto err_port_init; + } /* firmware requires that port's MAC address consist of the first * 5 bytes of the base MAC address -- cgit v1.2.3 From edd2410b165e2ef00b2264ae362edf7441ca929c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 4 Dec 2020 19:54:16 +0200 Subject: net: mscc: ocelot: fix dropping of unknown IPv4 multicast on Seville The current assumption is that the felix DSA driver has flooding knobs per traffic class, while ocelot switchdev has a single flooding knob. This was correct for felix VSC9959 and ocelot VSC7514, but with the introduction of seville VSC9953, we see a switch driven by felix.c which has a single flooding knob. So it is clear that we must do what should have been done from the beginning, which is not to overwrite the configuration done by ocelot.c in felix, but instead to teach the common ocelot library about the differences in our switches, and set up the flooding PGIDs centrally. The effect that the bogus iteration through FELIX_NUM_TC has upon seville is quite dramatic. ANA_FLOODING is located at 0x00b548, and ANA_FLOODING_IPMC is located at 0x00b54c. So the bogus iteration will actually overwrite ANA_FLOODING_IPMC when attempting to write ANA_FLOODING[1]. There is no ANA_FLOODING[1] in sevile, just ANA_FLOODING. And when ANA_FLOODING_IPMC is overwritten with a bogus value, the effect is that ANA_FLOODING_IPMC gets the value of 0x0003CF7D: MC6_DATA = 61, MC6_CTRL = 61, MC4_DATA = 60, MC4_CTRL = 0. Because MC4_CTRL is zero, this means that IPv4 multicast control packets are not flooded, but dropped. An invalid configuration, and this is how the issue was actually spotted. Reported-by: Eldar Gasanov Reported-by: Maxim Kochetkov Tested-by: Eldar Gasanov Fixes: 84705fc16552 ("net: dsa: felix: introduce support for Seville VSC9953 switch") Fixes: 3c7b51bd39b2 ("net: dsa: felix: allow flooding for all traffic classes") Signed-off-by: Vladimir Oltean Reviewed-by: Alexandre Belloni Link: https://lore.kernel.org/r/20201204175416.1445937-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/ocelot/felix.c | 7 ------- drivers/net/dsa/ocelot/felix_vsc9959.c | 1 + drivers/net/dsa/ocelot/seville_vsc9953.c | 1 + drivers/net/ethernet/mscc/ocelot.c | 9 +++++---- drivers/net/ethernet/mscc/ocelot_vsc7514.c | 1 + include/soc/mscc/ocelot.h | 3 +++ 6 files changed, 11 insertions(+), 11 deletions(-) diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index f791860d495f..c444ef3da3e2 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -569,7 +569,6 @@ static int felix_setup(struct dsa_switch *ds) struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); int port, err; - int tc; err = felix_init_structs(felix, ds->num_ports); if (err) @@ -608,12 +607,6 @@ static int felix_setup(struct dsa_switch *ds) ocelot_write_rix(ocelot, ANA_PGID_PGID_PGID(GENMASK(ocelot->num_phys_ports, 0)), ANA_PGID_PGID, PGID_UC); - /* Setup the per-traffic class flooding PGIDs */ - for (tc = 0; tc < FELIX_NUM_TC; tc++) - ocelot_write_rix(ocelot, ANA_FLOODING_FLD_MULTICAST(PGID_MC) | - ANA_FLOODING_FLD_BROADCAST(PGID_MC) | - ANA_FLOODING_FLD_UNICAST(PGID_UC), - ANA_FLOODING, tc); ds->mtu_enforcement_ingress = true; ds->configure_vlan_while_not_filtering = true; diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 3e925b8d5306..2e5bbdca5ea4 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1429,6 +1429,7 @@ static int felix_pci_probe(struct pci_dev *pdev, pci_set_drvdata(pdev, felix); ocelot = &felix->ocelot; ocelot->dev = &pdev->dev; + ocelot->num_flooding_pgids = FELIX_NUM_TC; felix->info = &felix_info_vsc9959; felix->switch_base = pci_resource_start(pdev, felix->info->switch_pci_bar); diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 1d420c4a2f0f..ebbaf6817ec8 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -1210,6 +1210,7 @@ static int seville_probe(struct platform_device *pdev) ocelot = &felix->ocelot; ocelot->dev = &pdev->dev; + ocelot->num_flooding_pgids = 1; felix->info = &seville_info_vsc9953; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 70bf8c67d7ef..a53bd36b11c6 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1489,10 +1489,11 @@ int ocelot_init(struct ocelot *ocelot) SYS_FRM_AGING_MAX_AGE(307692), SYS_FRM_AGING); /* Setup flooding PGIDs */ - ocelot_write_rix(ocelot, ANA_FLOODING_FLD_MULTICAST(PGID_MC) | - ANA_FLOODING_FLD_BROADCAST(PGID_MC) | - ANA_FLOODING_FLD_UNICAST(PGID_UC), - ANA_FLOODING, 0); + for (i = 0; i < ocelot->num_flooding_pgids; i++) + ocelot_write_rix(ocelot, ANA_FLOODING_FLD_MULTICAST(PGID_MC) | + ANA_FLOODING_FLD_BROADCAST(PGID_MC) | + ANA_FLOODING_FLD_UNICAST(PGID_UC), + ANA_FLOODING, i); ocelot_write(ocelot, ANA_FLOODING_IPMC_FLD_MC6_DATA(PGID_MCIPV6) | ANA_FLOODING_IPMC_FLD_MC6_CTRL(PGID_MC) | ANA_FLOODING_IPMC_FLD_MC4_DATA(PGID_MCIPV4) | diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index dc00772950e5..1e7729421a82 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -1254,6 +1254,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev) } ocelot->num_phys_ports = of_get_child_count(ports); + ocelot->num_flooding_pgids = 1; ocelot->vcap = vsc7514_vcap_props; ocelot->inj_prefix = OCELOT_TAG_PREFIX_NONE; diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 1e9db9577441..49b46df476f2 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -618,6 +618,9 @@ struct ocelot { /* Keep track of the vlan port masks */ u32 vlan_mask[VLAN_N_VID]; + /* Switches like VSC9959 have flooding per traffic class */ + int num_flooding_pgids; + /* In tables like ANA:PORT and the ANA:PGID:PGID mask, * the CPU is located after the physical ports (at the * num_phys_ports index). -- cgit v1.2.3 From 4e9a5ae8df5b3365183150f6df49e49dece80d8c Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 3 Dec 2020 13:50:37 +0900 Subject: x86/uprobes: Do not use prefixes.nbytes when looping over prefixes.bytes Since insn.prefixes.nbytes can be bigger than the size of insn.prefixes.bytes[] when a prefix is repeated, the proper check must be insn.prefixes.bytes[i] != 0 and i < 4 instead of using insn.prefixes.nbytes. Introduce a for_each_insn_prefix() macro for this purpose. Debugged by Kees Cook . [ bp: Massage commit message, sync with the respective header in tools/ and drop "we". ] Fixes: 2b1444983508 ("uprobes, mm, x86: Add the ability to install and remove uprobes breakpoints") Reported-by: syzbot+9b64b619f10f19d19a7c@syzkaller.appspotmail.com Signed-off-by: Masami Hiramatsu Signed-off-by: Borislav Petkov Reviewed-by: Srikar Dronamraju Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/160697103739.3146288.7437620795200799020.stgit@devnote2 --- arch/x86/include/asm/insn.h | 15 +++++++++++++++ arch/x86/kernel/uprobes.c | 10 ++++++---- tools/arch/x86/include/asm/insn.h | 15 +++++++++++++++ 3 files changed, 36 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index 5c1ae3eff9d4..a8c3d284fa46 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -201,6 +201,21 @@ static inline int insn_offset_immediate(struct insn *insn) return insn_offset_displacement(insn) + insn->displacement.nbytes; } +/** + * for_each_insn_prefix() -- Iterate prefixes in the instruction + * @insn: Pointer to struct insn. + * @idx: Index storage. + * @prefix: Prefix byte. + * + * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix + * and the index is stored in @idx (note that this @idx is just for a cursor, + * do not change it.) + * Since prefixes.nbytes can be bigger than 4 if some prefixes + * are repeated, it cannot be used for looping over the prefixes. + */ +#define for_each_insn_prefix(insn, idx, prefix) \ + for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++) + #define POP_SS_OPCODE 0x1f #define MOV_SREG_OPCODE 0x8e diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 3fdaa042823d..138bdb1fd136 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -255,12 +255,13 @@ static volatile u32 good_2byte_insns[256 / 32] = { static bool is_prefix_bad(struct insn *insn) { + insn_byte_t p; int i; - for (i = 0; i < insn->prefixes.nbytes; i++) { + for_each_insn_prefix(insn, i, p) { insn_attr_t attr; - attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]); + attr = inat_get_opcode_attribute(p); switch (attr) { case INAT_MAKE_PREFIX(INAT_PFX_ES): case INAT_MAKE_PREFIX(INAT_PFX_CS): @@ -715,6 +716,7 @@ static const struct uprobe_xol_ops push_xol_ops = { static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) { u8 opc1 = OPCODE1(insn); + insn_byte_t p; int i; switch (opc1) { @@ -746,8 +748,8 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) * Intel and AMD behavior differ in 64-bit mode: Intel ignores 66 prefix. * No one uses these insns, reject any branch insns with such prefix. */ - for (i = 0; i < insn->prefixes.nbytes; i++) { - if (insn->prefixes.bytes[i] == 0x66) + for_each_insn_prefix(insn, i, p) { + if (p == 0x66) return -ENOTSUPP; } diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h index 568854b14d0a..52c6262e6bfd 100644 --- a/tools/arch/x86/include/asm/insn.h +++ b/tools/arch/x86/include/asm/insn.h @@ -201,6 +201,21 @@ static inline int insn_offset_immediate(struct insn *insn) return insn_offset_displacement(insn) + insn->displacement.nbytes; } +/** + * for_each_insn_prefix() -- Iterate prefixes in the instruction + * @insn: Pointer to struct insn. + * @idx: Index storage. + * @prefix: Prefix byte. + * + * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix + * and the index is stored in @idx (note that this @idx is just for a cursor, + * do not change it.) + * Since prefixes.nbytes can be bigger than 4 if some prefixes + * are repeated, it cannot be used for looping over the prefixes. + */ +#define for_each_insn_prefix(insn, idx, prefix) \ + for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++) + #define POP_SS_OPCODE 0x1f #define MOV_SREG_OPCODE 0x8e -- cgit v1.2.3 From 12cb908a11b2544b5f53e9af856e6b6a90ed5533 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 3 Dec 2020 13:50:50 +0900 Subject: x86/insn-eval: Use new for_each_insn_prefix() macro to loop over prefixes bytes Since insn.prefixes.nbytes can be bigger than the size of insn.prefixes.bytes[] when a prefix is repeated, the proper check must be insn.prefixes.bytes[i] != 0 and i < 4 instead of using insn.prefixes.nbytes. Use the new for_each_insn_prefix() macro which does it correctly. Debugged by Kees Cook . [ bp: Massage commit message. ] Fixes: 32d0b95300db ("x86/insn-eval: Add utility functions to get segment selector") Reported-by: syzbot+9b64b619f10f19d19a7c@syzkaller.appspotmail.com Signed-off-by: Masami Hiramatsu Signed-off-by: Borislav Petkov Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/160697104969.3146288.16329307586428270032.stgit@devnote2 --- arch/x86/lib/insn-eval.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 58f7fb95c7f4..4229950a5d78 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -63,13 +63,12 @@ static bool is_string_insn(struct insn *insn) */ bool insn_has_rep_prefix(struct insn *insn) { + insn_byte_t p; int i; insn_get_prefixes(insn); - for (i = 0; i < insn->prefixes.nbytes; i++) { - insn_byte_t p = insn->prefixes.bytes[i]; - + for_each_insn_prefix(insn, i, p) { if (p == 0xf2 || p == 0xf3) return true; } @@ -95,14 +94,15 @@ static int get_seg_reg_override_idx(struct insn *insn) { int idx = INAT_SEG_REG_DEFAULT; int num_overrides = 0, i; + insn_byte_t p; insn_get_prefixes(insn); /* Look for any segment override prefixes. */ - for (i = 0; i < insn->prefixes.nbytes; i++) { + for_each_insn_prefix(insn, i, p) { insn_attr_t attr; - attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]); + attr = inat_get_opcode_attribute(p); switch (attr) { case INAT_MAKE_PREFIX(INAT_PFX_CS): idx = INAT_SEG_REG_CS; -- cgit v1.2.3 From 84da009f06e60cf59d5e861f8e2101d2d3885517 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 3 Dec 2020 13:51:01 +0900 Subject: x86/sev-es: Use new for_each_insn_prefix() macro to loop over prefixes bytes Since insn.prefixes.nbytes can be bigger than the size of insn.prefixes.bytes[] when a prefix is repeated, the proper check must be: insn.prefixes.bytes[i] != 0 and i < 4 instead of using insn.prefixes.nbytes. Use the new for_each_insn_prefix() macro which does it correctly. Debugged by Kees Cook . [ bp: Massage commit message. ] Fixes: 25189d08e516 ("x86/sev-es: Add support for handling IOIO exceptions") Reported-by: syzbot+9b64b619f10f19d19a7c@syzkaller.appspotmail.com Signed-off-by: Masami Hiramatsu Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/160697106089.3146288.2052422845039649176.stgit@devnote2 --- arch/x86/boot/compressed/sev-es.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index 954cb2702e23..27826c265aab 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -32,13 +32,12 @@ struct ghcb *boot_ghcb; */ static bool insn_has_rep_prefix(struct insn *insn) { + insn_byte_t p; int i; insn_get_prefixes(insn); - for (i = 0; i < insn->prefixes.nbytes; i++) { - insn_byte_t p = insn->prefixes.bytes[i]; - + for_each_insn_prefix(insn, i, p) { if (p == 0xf2 || p == 0xf3) return true; } -- cgit v1.2.3 From 264f53b41946dcabb2b3304190839ab5670c7825 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Sat, 5 Dec 2020 14:38:46 -0500 Subject: Revert "mei: virtio: virtualization frontend driver" This reverts commit d162219c655c8cf8003128a13840d6c1e183fb80. The device uses a VIRTIO device ID out of a not-for-production range. Releasing Linux using an ID out of this range will make it conflict with development setups. An official request to reserve an ID for an MEI device is yet to be submitted to the virtio TC, thus there's no chance it will be reserved and fixed in time before the next release. Once requested it usually takes 2-3 weeks to land in the spec, which means the device can be supported with the official ID in the next Linux version if contributors act quickly. Signed-off-by: Michael S. Tsirkin Cc: Tomas Winkler Cc: Alexander Usyskin Cc: Wang Yu Cc: Liu Shuo Link: https://lore.kernel.org/r/20201205193625.469773-1-mst@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/Kconfig | 10 - drivers/misc/mei/Makefile | 3 - drivers/misc/mei/hw-virtio.c | 874 ------------------------------------------- 3 files changed, 887 deletions(-) delete mode 100644 drivers/misc/mei/hw-virtio.c diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig index c06581ffa7bd..f5fd5b786607 100644 --- a/drivers/misc/mei/Kconfig +++ b/drivers/misc/mei/Kconfig @@ -46,14 +46,4 @@ config INTEL_MEI_TXE Supported SoCs: Intel Bay Trail -config INTEL_MEI_VIRTIO - tristate "Intel MEI interface emulation with virtio framework" - select INTEL_MEI - depends on X86 && PCI && VIRTIO_PCI - help - This module implements mei hw emulation over virtio transport. - The module will be called mei_virtio. - Enable this if your virtual machine supports virtual mei - device over virtio. - source "drivers/misc/mei/hdcp/Kconfig" diff --git a/drivers/misc/mei/Makefile b/drivers/misc/mei/Makefile index 52aefaab5c1b..f1c76f7ee804 100644 --- a/drivers/misc/mei/Makefile +++ b/drivers/misc/mei/Makefile @@ -22,9 +22,6 @@ obj-$(CONFIG_INTEL_MEI_TXE) += mei-txe.o mei-txe-objs := pci-txe.o mei-txe-objs += hw-txe.o -obj-$(CONFIG_INTEL_MEI_VIRTIO) += mei-virtio.o -mei-virtio-objs := hw-virtio.o - mei-$(CONFIG_EVENT_TRACING) += mei-trace.o CFLAGS_mei-trace.o = -I$(src) diff --git a/drivers/misc/mei/hw-virtio.c b/drivers/misc/mei/hw-virtio.c deleted file mode 100644 index 899dc1c5e7ca..000000000000 --- a/drivers/misc/mei/hw-virtio.c +++ /dev/null @@ -1,874 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2018-2020, Intel Corporation. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "mei_dev.h" -#include "hbm.h" -#include "client.h" - -#define MEI_VIRTIO_RPM_TIMEOUT 500 -/* ACRN virtio device types */ -#ifndef VIRTIO_ID_MEI -#define VIRTIO_ID_MEI 0xFFFE /* virtio mei */ -#endif - -/** - * struct mei_virtio_cfg - settings passed from the virtio backend - * @buf_depth: read buffer depth in slots (4bytes) - * @hw_ready: hw is ready for operation - * @host_reset: synchronize reset with virtio backend - * @reserved: reserved for alignment - * @fw_status: FW status - */ -struct mei_virtio_cfg { - u32 buf_depth; - u8 hw_ready; - u8 host_reset; - u8 reserved[2]; - u32 fw_status[MEI_FW_STATUS_MAX]; -} __packed; - -struct mei_virtio_hw { - struct mei_device mdev; - char name[32]; - - struct virtqueue *in; - struct virtqueue *out; - - bool host_ready; - struct work_struct intr_handler; - - u32 *recv_buf; - u8 recv_rdy; - size_t recv_sz; - u32 recv_idx; - u32 recv_len; - - /* send buffer */ - atomic_t hbuf_ready; - const void *send_hdr; - const void *send_buf; - - struct mei_virtio_cfg cfg; -}; - -#define to_virtio_hw(_dev) container_of(_dev, struct mei_virtio_hw, mdev) - -/** - * mei_virtio_fw_status() - read status register of mei - * @dev: mei device - * @fw_status: fw status register values - * - * Return: always 0 - */ -static int mei_virtio_fw_status(struct mei_device *dev, - struct mei_fw_status *fw_status) -{ - struct virtio_device *vdev = dev_to_virtio(dev->dev); - - fw_status->count = MEI_FW_STATUS_MAX; - virtio_cread_bytes(vdev, offsetof(struct mei_virtio_cfg, fw_status), - fw_status->status, sizeof(fw_status->status)); - return 0; -} - -/** - * mei_virtio_pg_state() - translate internal pg state - * to the mei power gating state - * There is no power management in ACRN mode always return OFF - * @dev: mei device - * - * Return: - * * MEI_PG_OFF - if aliveness is on (always) - * * MEI_PG_ON - (never) - */ -static inline enum mei_pg_state mei_virtio_pg_state(struct mei_device *dev) -{ - return MEI_PG_OFF; -} - -/** - * mei_virtio_hw_config() - configure hw dependent settings - * - * @dev: mei device - * - * Return: always 0 - */ -static int mei_virtio_hw_config(struct mei_device *dev) -{ - return 0; -} - -/** - * mei_virtio_hbuf_empty_slots() - counts write empty slots. - * @dev: the device structure - * - * Return: always return frontend buf size if buffer is ready, 0 otherwise - */ -static int mei_virtio_hbuf_empty_slots(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - return (atomic_read(&hw->hbuf_ready) == 1) ? hw->cfg.buf_depth : 0; -} - -/** - * mei_virtio_hbuf_is_ready() - checks if write buffer is ready - * @dev: the device structure - * - * Return: true if hbuf is ready - */ -static bool mei_virtio_hbuf_is_ready(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - return atomic_read(&hw->hbuf_ready) == 1; -} - -/** - * mei_virtio_hbuf_max_depth() - returns depth of FE write buffer. - * @dev: the device structure - * - * Return: size of frontend write buffer in bytes - */ -static u32 mei_virtio_hbuf_depth(const struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - return hw->cfg.buf_depth; -} - -/** - * mei_virtio_intr_clear() - clear and stop interrupts - * @dev: the device structure - */ -static void mei_virtio_intr_clear(struct mei_device *dev) -{ - /* - * In our virtio solution, there are two types of interrupts, - * vq interrupt and config change interrupt. - * 1) start/reset rely on virtio config changed interrupt; - * 2) send/recv rely on virtio virtqueue interrupts. - * They are all virtual interrupts. So, we don't have corresponding - * operation to do here. - */ -} - -/** - * mei_virtio_intr_enable() - enables mei BE virtqueues callbacks - * @dev: the device structure - */ -static void mei_virtio_intr_enable(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - struct virtio_device *vdev = dev_to_virtio(dev->dev); - - virtio_config_enable(vdev); - - virtqueue_enable_cb(hw->in); - virtqueue_enable_cb(hw->out); -} - -/** - * mei_virtio_intr_disable() - disables mei BE virtqueues callbacks - * - * @dev: the device structure - */ -static void mei_virtio_intr_disable(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - struct virtio_device *vdev = dev_to_virtio(dev->dev); - - virtio_config_disable(vdev); - - virtqueue_disable_cb(hw->in); - virtqueue_disable_cb(hw->out); -} - -/** - * mei_virtio_synchronize_irq() - wait for pending IRQ handlers for all - * virtqueue - * @dev: the device structure - */ -static void mei_virtio_synchronize_irq(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - /* - * Now, all IRQ handlers are converted to workqueue. - * Change synchronize irq to flush this work. - */ - flush_work(&hw->intr_handler); -} - -static void mei_virtio_free_outbufs(struct mei_virtio_hw *hw) -{ - kfree(hw->send_hdr); - kfree(hw->send_buf); - hw->send_hdr = NULL; - hw->send_buf = NULL; -} - -/** - * mei_virtio_write_message() - writes a message to mei virtio back-end service. - * @dev: the device structure - * @hdr: mei header of message - * @hdr_len: header length - * @data: message payload will be written - * @data_len: message payload length - * - * Return: - * * 0: on success - * * -EIO: if write has failed - * * -ENOMEM: on memory allocation failure - */ -static int mei_virtio_write_message(struct mei_device *dev, - const void *hdr, size_t hdr_len, - const void *data, size_t data_len) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - struct scatterlist sg[2]; - const void *hbuf, *dbuf; - int ret; - - if (WARN_ON(!atomic_add_unless(&hw->hbuf_ready, -1, 0))) - return -EIO; - - hbuf = kmemdup(hdr, hdr_len, GFP_KERNEL); - hw->send_hdr = hbuf; - - dbuf = kmemdup(data, data_len, GFP_KERNEL); - hw->send_buf = dbuf; - - if (!hbuf || !dbuf) { - ret = -ENOMEM; - goto fail; - } - - sg_init_table(sg, 2); - sg_set_buf(&sg[0], hbuf, hdr_len); - sg_set_buf(&sg[1], dbuf, data_len); - - ret = virtqueue_add_outbuf(hw->out, sg, 2, hw, GFP_KERNEL); - if (ret) { - dev_err(dev->dev, "failed to add outbuf\n"); - goto fail; - } - - virtqueue_kick(hw->out); - return 0; -fail: - - mei_virtio_free_outbufs(hw); - - return ret; -} - -/** - * mei_virtio_count_full_read_slots() - counts read full slots. - * @dev: the device structure - * - * Return: -EOVERFLOW if overflow, otherwise filled slots count - */ -static int mei_virtio_count_full_read_slots(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - if (hw->recv_idx > hw->recv_len) - return -EOVERFLOW; - - return hw->recv_len - hw->recv_idx; -} - -/** - * mei_virtio_read_hdr() - Reads 32bit dword from mei virtio receive buffer - * - * @dev: the device structure - * - * Return: 32bit dword of receive buffer (u32) - */ -static inline u32 mei_virtio_read_hdr(const struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - WARN_ON(hw->cfg.buf_depth < hw->recv_idx + 1); - - return hw->recv_buf[hw->recv_idx++]; -} - -static int mei_virtio_read(struct mei_device *dev, unsigned char *buffer, - unsigned long len) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - u32 slots = mei_data2slots(len); - - if (WARN_ON(hw->cfg.buf_depth < hw->recv_idx + slots)) - return -EOVERFLOW; - - /* - * Assumption: There is only one MEI message in recv_buf each time. - * Backend service need follow this rule too. - */ - memcpy(buffer, hw->recv_buf + hw->recv_idx, len); - hw->recv_idx += slots; - - return 0; -} - -static bool mei_virtio_pg_is_enabled(struct mei_device *dev) -{ - return false; -} - -static bool mei_virtio_pg_in_transition(struct mei_device *dev) -{ - return false; -} - -static void mei_virtio_add_recv_buf(struct mei_virtio_hw *hw) -{ - struct scatterlist sg; - - if (hw->recv_rdy) /* not needed */ - return; - - /* refill the recv_buf to IN virtqueue to get next message */ - sg_init_one(&sg, hw->recv_buf, mei_slots2data(hw->cfg.buf_depth)); - hw->recv_len = 0; - hw->recv_idx = 0; - hw->recv_rdy = 1; - virtqueue_add_inbuf(hw->in, &sg, 1, hw->recv_buf, GFP_KERNEL); - virtqueue_kick(hw->in); -} - -/** - * mei_virtio_hw_is_ready() - check whether the BE(hw) has turned ready - * @dev: mei device - * Return: bool - */ -static bool mei_virtio_hw_is_ready(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - struct virtio_device *vdev = dev_to_virtio(dev->dev); - - virtio_cread(vdev, struct mei_virtio_cfg, - hw_ready, &hw->cfg.hw_ready); - - dev_dbg(dev->dev, "hw ready %d\n", hw->cfg.hw_ready); - - return hw->cfg.hw_ready; -} - -/** - * mei_virtio_hw_reset - resets virtio hw. - * - * @dev: the device structure - * @intr_enable: virtio use data/config callbacks - * - * Return: 0 on success an error code otherwise - */ -static int mei_virtio_hw_reset(struct mei_device *dev, bool intr_enable) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - struct virtio_device *vdev = dev_to_virtio(dev->dev); - - dev_dbg(dev->dev, "hw reset\n"); - - dev->recvd_hw_ready = false; - hw->host_ready = false; - atomic_set(&hw->hbuf_ready, 0); - hw->recv_len = 0; - hw->recv_idx = 0; - - hw->cfg.host_reset = 1; - virtio_cwrite(vdev, struct mei_virtio_cfg, - host_reset, &hw->cfg.host_reset); - - mei_virtio_hw_is_ready(dev); - - if (intr_enable) - mei_virtio_intr_enable(dev); - - return 0; -} - -/** - * mei_virtio_hw_reset_release() - release device from the reset - * @dev: the device structure - */ -static void mei_virtio_hw_reset_release(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - struct virtio_device *vdev = dev_to_virtio(dev->dev); - - dev_dbg(dev->dev, "hw reset release\n"); - hw->cfg.host_reset = 0; - virtio_cwrite(vdev, struct mei_virtio_cfg, - host_reset, &hw->cfg.host_reset); -} - -/** - * mei_virtio_hw_ready_wait() - wait until the virtio(hw) has turned ready - * or timeout is reached - * @dev: mei device - * - * Return: 0 on success, error otherwise - */ -static int mei_virtio_hw_ready_wait(struct mei_device *dev) -{ - mutex_unlock(&dev->device_lock); - wait_event_timeout(dev->wait_hw_ready, - dev->recvd_hw_ready, - mei_secs_to_jiffies(MEI_HW_READY_TIMEOUT)); - mutex_lock(&dev->device_lock); - if (!dev->recvd_hw_ready) { - dev_err(dev->dev, "wait hw ready failed\n"); - return -ETIMEDOUT; - } - - dev->recvd_hw_ready = false; - return 0; -} - -/** - * mei_virtio_hw_start() - hw start routine - * @dev: mei device - * - * Return: 0 on success, error otherwise - */ -static int mei_virtio_hw_start(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - int ret; - - dev_dbg(dev->dev, "hw start\n"); - mei_virtio_hw_reset_release(dev); - - ret = mei_virtio_hw_ready_wait(dev); - if (ret) - return ret; - - mei_virtio_add_recv_buf(hw); - atomic_set(&hw->hbuf_ready, 1); - dev_dbg(dev->dev, "hw is ready\n"); - hw->host_ready = true; - - return 0; -} - -/** - * mei_virtio_host_is_ready() - check whether the FE has turned ready - * @dev: mei device - * - * Return: bool - */ -static bool mei_virtio_host_is_ready(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - dev_dbg(dev->dev, "host ready %d\n", hw->host_ready); - - return hw->host_ready; -} - -/** - * mei_virtio_data_in() - The callback of recv virtqueue of virtio mei - * @vq: receiving virtqueue - */ -static void mei_virtio_data_in(struct virtqueue *vq) -{ - struct mei_virtio_hw *hw = vq->vdev->priv; - - /* disable interrupts (enabled again from in the interrupt worker) */ - virtqueue_disable_cb(hw->in); - - schedule_work(&hw->intr_handler); -} - -/** - * mei_virtio_data_out() - The callback of send virtqueue of virtio mei - * @vq: transmitting virtqueue - */ -static void mei_virtio_data_out(struct virtqueue *vq) -{ - struct mei_virtio_hw *hw = vq->vdev->priv; - - schedule_work(&hw->intr_handler); -} - -static void mei_virtio_intr_handler(struct work_struct *work) -{ - struct mei_virtio_hw *hw = - container_of(work, struct mei_virtio_hw, intr_handler); - struct mei_device *dev = &hw->mdev; - LIST_HEAD(complete_list); - s32 slots; - int rets = 0; - void *data; - unsigned int len; - - mutex_lock(&dev->device_lock); - - if (dev->dev_state == MEI_DEV_DISABLED) { - dev_warn(dev->dev, "Interrupt in disabled state.\n"); - mei_virtio_intr_disable(dev); - goto end; - } - - /* check if ME wants a reset */ - if (!mei_hw_is_ready(dev) && dev->dev_state != MEI_DEV_RESETTING) { - dev_warn(dev->dev, "BE service not ready: resetting.\n"); - schedule_work(&dev->reset_work); - goto end; - } - - /* check if we need to start the dev */ - if (!mei_host_is_ready(dev)) { - if (mei_hw_is_ready(dev)) { - dev_dbg(dev->dev, "we need to start the dev.\n"); - dev->recvd_hw_ready = true; - wake_up(&dev->wait_hw_ready); - } else { - dev_warn(dev->dev, "Spurious Interrupt\n"); - } - goto end; - } - - /* read */ - if (hw->recv_rdy) { - data = virtqueue_get_buf(hw->in, &len); - if (!data || !len) { - dev_dbg(dev->dev, "No data %d", len); - } else { - dev_dbg(dev->dev, "data_in %d\n", len); - WARN_ON(data != hw->recv_buf); - hw->recv_len = mei_data2slots(len); - hw->recv_rdy = 0; - } - } - - /* write */ - if (!atomic_read(&hw->hbuf_ready)) { - if (!virtqueue_get_buf(hw->out, &len)) { - dev_warn(dev->dev, "Failed to getbuf\n"); - } else { - mei_virtio_free_outbufs(hw); - atomic_inc(&hw->hbuf_ready); - } - } - - /* check slots available for reading */ - slots = mei_count_full_read_slots(dev); - while (slots > 0) { - dev_dbg(dev->dev, "slots to read = %08x\n", slots); - rets = mei_irq_read_handler(dev, &complete_list, &slots); - - if (rets && - (dev->dev_state != MEI_DEV_RESETTING && - dev->dev_state != MEI_DEV_POWER_DOWN)) { - dev_err(dev->dev, "mei_irq_read_handler ret = %d.\n", - rets); - schedule_work(&dev->reset_work); - goto end; - } - } - - dev->hbuf_is_ready = mei_hbuf_is_ready(dev); - - mei_irq_write_handler(dev, &complete_list); - - dev->hbuf_is_ready = mei_hbuf_is_ready(dev); - - mei_irq_compl_handler(dev, &complete_list); - - mei_virtio_add_recv_buf(hw); - -end: - if (dev->dev_state != MEI_DEV_DISABLED) { - if (!virtqueue_enable_cb(hw->in)) - schedule_work(&hw->intr_handler); - } - - mutex_unlock(&dev->device_lock); -} - -static void mei_virtio_config_changed(struct virtio_device *vdev) -{ - struct mei_virtio_hw *hw = vdev->priv; - struct mei_device *dev = &hw->mdev; - - virtio_cread(vdev, struct mei_virtio_cfg, - hw_ready, &hw->cfg.hw_ready); - - if (dev->dev_state == MEI_DEV_DISABLED) { - dev_dbg(dev->dev, "disabled state don't start\n"); - return; - } - - /* Run intr handler once to handle reset notify */ - schedule_work(&hw->intr_handler); -} - -static void mei_virtio_remove_vqs(struct virtio_device *vdev) -{ - struct mei_virtio_hw *hw = vdev->priv; - - virtqueue_detach_unused_buf(hw->in); - hw->recv_len = 0; - hw->recv_idx = 0; - hw->recv_rdy = 0; - - virtqueue_detach_unused_buf(hw->out); - - mei_virtio_free_outbufs(hw); - - vdev->config->del_vqs(vdev); -} - -/* - * There are two virtqueues, one is for send and another is for recv. - */ -static int mei_virtio_init_vqs(struct mei_virtio_hw *hw, - struct virtio_device *vdev) -{ - struct virtqueue *vqs[2]; - - vq_callback_t *cbs[] = { - mei_virtio_data_in, - mei_virtio_data_out, - }; - static const char * const names[] = { - "in", - "out", - }; - int ret; - - ret = virtio_find_vqs(vdev, 2, vqs, cbs, names, NULL); - if (ret) - return ret; - - hw->in = vqs[0]; - hw->out = vqs[1]; - - return 0; -} - -static const struct mei_hw_ops mei_virtio_ops = { - .fw_status = mei_virtio_fw_status, - .pg_state = mei_virtio_pg_state, - - .host_is_ready = mei_virtio_host_is_ready, - - .hw_is_ready = mei_virtio_hw_is_ready, - .hw_reset = mei_virtio_hw_reset, - .hw_config = mei_virtio_hw_config, - .hw_start = mei_virtio_hw_start, - - .pg_in_transition = mei_virtio_pg_in_transition, - .pg_is_enabled = mei_virtio_pg_is_enabled, - - .intr_clear = mei_virtio_intr_clear, - .intr_enable = mei_virtio_intr_enable, - .intr_disable = mei_virtio_intr_disable, - .synchronize_irq = mei_virtio_synchronize_irq, - - .hbuf_free_slots = mei_virtio_hbuf_empty_slots, - .hbuf_is_ready = mei_virtio_hbuf_is_ready, - .hbuf_depth = mei_virtio_hbuf_depth, - - .write = mei_virtio_write_message, - - .rdbuf_full_slots = mei_virtio_count_full_read_slots, - .read_hdr = mei_virtio_read_hdr, - .read = mei_virtio_read, -}; - -static int mei_virtio_probe(struct virtio_device *vdev) -{ - struct mei_virtio_hw *hw; - int ret; - - hw = devm_kzalloc(&vdev->dev, sizeof(*hw), GFP_KERNEL); - if (!hw) - return -ENOMEM; - - vdev->priv = hw; - - INIT_WORK(&hw->intr_handler, mei_virtio_intr_handler); - - ret = mei_virtio_init_vqs(hw, vdev); - if (ret) - goto vqs_failed; - - virtio_cread(vdev, struct mei_virtio_cfg, - buf_depth, &hw->cfg.buf_depth); - - hw->recv_buf = kzalloc(mei_slots2data(hw->cfg.buf_depth), GFP_KERNEL); - if (!hw->recv_buf) { - ret = -ENOMEM; - goto hbuf_failed; - } - atomic_set(&hw->hbuf_ready, 0); - - virtio_device_ready(vdev); - - mei_device_init(&hw->mdev, &vdev->dev, &mei_virtio_ops); - - pm_runtime_get_noresume(&vdev->dev); - pm_runtime_set_active(&vdev->dev); - pm_runtime_enable(&vdev->dev); - - ret = mei_start(&hw->mdev); - if (ret) - goto mei_start_failed; - - pm_runtime_set_autosuspend_delay(&vdev->dev, MEI_VIRTIO_RPM_TIMEOUT); - pm_runtime_use_autosuspend(&vdev->dev); - - ret = mei_register(&hw->mdev, &vdev->dev); - if (ret) - goto mei_failed; - - pm_runtime_put(&vdev->dev); - - return 0; - -mei_failed: - mei_stop(&hw->mdev); -mei_start_failed: - mei_cancel_work(&hw->mdev); - mei_disable_interrupts(&hw->mdev); - kfree(hw->recv_buf); -hbuf_failed: - vdev->config->del_vqs(vdev); -vqs_failed: - return ret; -} - -static int __maybe_unused mei_virtio_pm_runtime_idle(struct device *device) -{ - struct virtio_device *vdev = dev_to_virtio(device); - struct mei_virtio_hw *hw = vdev->priv; - - dev_dbg(&vdev->dev, "rpm: mei_virtio : runtime_idle\n"); - - if (!hw) - return -ENODEV; - - if (mei_write_is_idle(&hw->mdev)) - pm_runtime_autosuspend(device); - - return -EBUSY; -} - -static int __maybe_unused mei_virtio_pm_runtime_suspend(struct device *device) -{ - return 0; -} - -static int __maybe_unused mei_virtio_pm_runtime_resume(struct device *device) -{ - return 0; -} - -static int __maybe_unused mei_virtio_freeze(struct virtio_device *vdev) -{ - struct mei_virtio_hw *hw = vdev->priv; - - dev_dbg(&vdev->dev, "freeze\n"); - - if (!hw) - return -ENODEV; - - mei_stop(&hw->mdev); - mei_disable_interrupts(&hw->mdev); - cancel_work_sync(&hw->intr_handler); - vdev->config->reset(vdev); - mei_virtio_remove_vqs(vdev); - - return 0; -} - -static int __maybe_unused mei_virtio_restore(struct virtio_device *vdev) -{ - struct mei_virtio_hw *hw = vdev->priv; - int ret; - - dev_dbg(&vdev->dev, "restore\n"); - - if (!hw) - return -ENODEV; - - ret = mei_virtio_init_vqs(hw, vdev); - if (ret) - return ret; - - virtio_device_ready(vdev); - - ret = mei_restart(&hw->mdev); - if (ret) - return ret; - - /* Start timer if stopped in suspend */ - schedule_delayed_work(&hw->mdev.timer_work, HZ); - - return 0; -} - -static const struct dev_pm_ops mei_virtio_pm_ops = { - SET_RUNTIME_PM_OPS(mei_virtio_pm_runtime_suspend, - mei_virtio_pm_runtime_resume, - mei_virtio_pm_runtime_idle) -}; - -static void mei_virtio_remove(struct virtio_device *vdev) -{ - struct mei_virtio_hw *hw = vdev->priv; - - mei_stop(&hw->mdev); - mei_disable_interrupts(&hw->mdev); - cancel_work_sync(&hw->intr_handler); - mei_deregister(&hw->mdev); - vdev->config->reset(vdev); - mei_virtio_remove_vqs(vdev); - kfree(hw->recv_buf); - pm_runtime_disable(&vdev->dev); -} - -static struct virtio_device_id id_table[] = { - { VIRTIO_ID_MEI, VIRTIO_DEV_ANY_ID }, - { } -}; - -static struct virtio_driver mei_virtio_driver = { - .id_table = id_table, - .probe = mei_virtio_probe, - .remove = mei_virtio_remove, - .config_changed = mei_virtio_config_changed, - .driver = { - .name = KBUILD_MODNAME, - .owner = THIS_MODULE, - .pm = &mei_virtio_pm_ops, - }, -#ifdef CONFIG_PM_SLEEP - .freeze = mei_virtio_freeze, - .restore = mei_virtio_restore, -#endif -}; - -module_virtio_driver(mei_virtio_driver); -MODULE_DEVICE_TABLE(virtio, id_table); -MODULE_DESCRIPTION("Virtio MEI frontend driver"); -MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From 7d32358be8acb119dcfe39b6cf67ec6d94bf1fe7 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 4 Dec 2020 02:55:51 +0900 Subject: kbuild: avoid split lines in .mod files "xargs echo" is not a safe way to remove line breaks because the input may exceed the command line limit and xargs may break it up into multiple invocations of echo. This should never happen because scripts/gen_autoksyms.sh expects all undefined symbols are placed in the second line of .mod files. One possible way is to replace "xargs echo" with "sed ':x;N;$!bx;s/\n/ /g'" or something, but I rewrote the code by using awk because it is more readable. This issue was reported by Sami Tolvanen; in his Clang LTO patch set, $(multi-used-m) is no longer an ELF object, but a thin archive that contains LLVM bitcode files. llvm-nm prints out symbols for each archive member separately, which results a lot of dupications, in some places, beyond the system-defined limit. This problem must be fixed irrespective of LTO, and we must ensure zero possibility of having this issue. Link: https://lkml.org/lkml/2020/12/1/1658 Reported-by: Sami Tolvanen Signed-off-by: Masahiro Yamada Reviewed-by: Sami Tolvanen --- scripts/Makefile.build | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index ae647379b579..4c058f12dd73 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -252,6 +252,9 @@ objtool_dep = $(objtool_obj) \ ifdef CONFIG_TRIM_UNUSED_KSYMS cmd_gen_ksymdeps = \ $(CONFIG_SHELL) $(srctree)/scripts/gen_ksymdeps.sh $@ >> $(dot-target).cmd + +# List module undefined symbols +undefined_syms = $(NM) $< | $(AWK) '$$1 == "U" { printf("%s%s", x++ ? " " : "", $$2) }'; endif define rule_cc_o_c @@ -271,13 +274,6 @@ define rule_as_o_S $(call cmd,modversions_S) endef -# List module undefined symbols (or empty line if not enabled) -ifdef CONFIG_TRIM_UNUSED_KSYMS -cmd_undef_syms = $(NM) $< | sed -n 's/^ *U //p' | xargs echo -else -cmd_undef_syms = echo -endif - # Built-in and composite module parts $(obj)/%.o: $(src)/%.c $(recordmcount_source) $(objtool_dep) FORCE $(call if_changed_rule,cc_o_c) @@ -285,7 +281,7 @@ $(obj)/%.o: $(src)/%.c $(recordmcount_source) $(objtool_dep) FORCE cmd_mod = { \ echo $(if $($*-objs)$($*-y)$($*-m), $(addprefix $(obj)/, $($*-objs) $($*-y) $($*-m)), $(@:.mod=.o)); \ - $(cmd_undef_syms); \ + $(undefined_syms) echo; \ } > $@ $(obj)/%.mod: $(obj)/%.o FORCE -- cgit v1.2.3 From 11fb479ff5d9872ddff02dd533c16d60372c86b2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 5 Dec 2020 22:14:38 -0800 Subject: zlib: export S390 symbols for zlib modules Fix build errors when ZLIB_INFLATE=m and ZLIB_DEFLATE=m and ZLIB_DFLTCC=y by exporting the 2 needed symbols in dfltcc_inflate.c. Fixes these build errors: ERROR: modpost: "dfltcc_inflate" [lib/zlib_inflate/zlib_inflate.ko] undefined! ERROR: modpost: "dfltcc_can_inflate" [lib/zlib_inflate/zlib_inflate.ko] undefined! Fixes: 126196100063 ("lib/zlib: add s390 hardware support for kernel zlib_inflate") Reported-by: kernel test robot Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Acked-by: Ilya Leoshkevich Cc: Mikhail Zaslonko Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Link: https://lkml.kernel.org/r/20201123191712.4882-1-rdunlap@infradead.org Signed-off-by: Linus Torvalds --- lib/zlib_dfltcc/dfltcc_inflate.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/lib/zlib_dfltcc/dfltcc_inflate.c b/lib/zlib_dfltcc/dfltcc_inflate.c index aa9ef23474df..db107016d29b 100644 --- a/lib/zlib_dfltcc/dfltcc_inflate.c +++ b/lib/zlib_dfltcc/dfltcc_inflate.c @@ -4,6 +4,7 @@ #include "dfltcc_util.h" #include "dfltcc.h" #include +#include #include /* @@ -29,6 +30,7 @@ int dfltcc_can_inflate( return is_bit_set(dfltcc_state->af.fns, DFLTCC_XPND) && is_bit_set(dfltcc_state->af.fmts, DFLTCC_FMT0); } +EXPORT_SYMBOL(dfltcc_can_inflate); static int dfltcc_was_inflate_used( z_streamp strm @@ -147,3 +149,4 @@ dfltcc_inflate_action dfltcc_inflate( return (cc == DFLTCC_CC_OP1_TOO_SHORT || cc == DFLTCC_CC_OP2_TOO_SHORT) ? DFLTCC_INFLATE_BREAK : DFLTCC_INFLATE_CONTINUE; } +EXPORT_SYMBOL(dfltcc_inflate); -- cgit v1.2.3 From 2bf509d96d84c3336d08375e8af34d1b85ee71c8 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 5 Dec 2020 22:14:42 -0800 Subject: coredump: fix core_pattern parse error 'format_corename()' will splite 'core_pattern' on spaces when it is in pipe mode, and take helper_argv[0] as the path to usermode executable. It works fine in most cases. However, if there is a space between '|' and '/file/path', such as '| /usr/lib/systemd/systemd-coredump %P %u %g', then helper_argv[0] will be parsed as '', and users will get a 'Core dump to | disabled'. It is not friendly to users, as the pattern above was valid previously. Fix this by ignoring the spaces between '|' and '/file/path'. Fixes: 315c69261dd3 ("coredump: split pipe command whitespace before expanding template") Signed-off-by: Menglong Dong Signed-off-by: Andrew Morton Cc: Paul Wise Cc: Jakub Wilk [https://bugs.debian.org/924398] Cc: Neil Horman Cc: Link: https://lkml.kernel.org/r/5fb62870.1c69fb81.8ef5d.af76@mx.google.com Signed-off-by: Linus Torvalds --- fs/coredump.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/coredump.c b/fs/coredump.c index 0cd9056d79cc..c6acfc694f65 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -229,7 +229,8 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm, */ if (ispipe) { if (isspace(*pat_ptr)) { - was_space = true; + if (cn->used != 0) + was_space = true; pat_ptr++; continue; } else if (was_space) { -- cgit v1.2.3 From becaba65f62f88e553ec92ed98370e9d2b18e629 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Sat, 5 Dec 2020 22:14:45 -0800 Subject: mm: memcg/slab: fix obj_cgroup_charge() return value handling Commit 10befea91b61 ("mm: memcg/slab: use a single set of kmem_caches for all allocations") introduced a regression into the handling of the obj_cgroup_charge() return value. If a non-zero value is returned (indicating of exceeding one of memory.max limits), the allocation should fail, instead of falling back to non-accounted mode. To make the code more readable, move memcg_slab_pre_alloc_hook() and memcg_slab_post_alloc_hook() calling conditions into bodies of these hooks. Fixes: 10befea91b61 ("mm: memcg/slab: use a single set of kmem_caches for all allocations") Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Cc: Johannes Weiner Cc: Michal Hocko Cc: Link: https://lkml.kernel.org/r/20201127161828.GD840171@carbon.dhcp.thefacebook.com Signed-off-by: Linus Torvalds --- mm/slab.h | 40 ++++++++++++++++++++++++---------------- 1 file changed, 24 insertions(+), 16 deletions(-) diff --git a/mm/slab.h b/mm/slab.h index 6d7c6a5056ba..f9977d6613d6 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -274,22 +274,32 @@ static inline size_t obj_full_size(struct kmem_cache *s) return s->size + sizeof(struct obj_cgroup *); } -static inline struct obj_cgroup *memcg_slab_pre_alloc_hook(struct kmem_cache *s, - size_t objects, - gfp_t flags) +/* + * Returns false if the allocation should fail. + */ +static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, + struct obj_cgroup **objcgp, + size_t objects, gfp_t flags) { struct obj_cgroup *objcg; + if (!memcg_kmem_enabled()) + return true; + + if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT)) + return true; + objcg = get_obj_cgroup_from_current(); if (!objcg) - return NULL; + return true; if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) { obj_cgroup_put(objcg); - return NULL; + return false; } - return objcg; + *objcgp = objcg; + return true; } static inline void mod_objcg_state(struct obj_cgroup *objcg, @@ -315,7 +325,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, unsigned long off; size_t i; - if (!objcg) + if (!memcg_kmem_enabled() || !objcg) return; flags &= ~__GFP_ACCOUNT; @@ -400,11 +410,11 @@ static inline void memcg_free_page_obj_cgroups(struct page *page) { } -static inline struct obj_cgroup *memcg_slab_pre_alloc_hook(struct kmem_cache *s, - size_t objects, - gfp_t flags) +static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, + struct obj_cgroup **objcgp, + size_t objects, gfp_t flags) { - return NULL; + return true; } static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, @@ -508,9 +518,8 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, if (should_failslab(s, flags)) return NULL; - if (memcg_kmem_enabled() && - ((flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT))) - *objcgp = memcg_slab_pre_alloc_hook(s, size, flags); + if (!memcg_slab_pre_alloc_hook(s, objcgp, size, flags)) + return NULL; return s; } @@ -529,8 +538,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, s->flags, flags); } - if (memcg_kmem_enabled()) - memcg_slab_post_alloc_hook(s, objcg, flags, size, p); + memcg_slab_post_alloc_hook(s, objcg, flags, size, p); } #ifndef CONFIG_SLOB -- cgit v1.2.3 From 8199be001a470209f5c938570cc199abb012fe53 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Sat, 5 Dec 2020 22:14:48 -0800 Subject: mm: list_lru: set shrinker map bit when child nr_items is not zero When investigating a slab cache bloat problem, significant amount of negative dentry cache was seen, but confusingly they neither got shrunk by reclaimer (the host has very tight memory) nor be shrunk by dropping cache. The vmcore shows there are over 14M negative dentry objects on lru, but tracing result shows they were even not scanned at all. Further investigation shows the memcg's vfs shrinker_map bit is not set. So the reclaimer or dropping cache just skip calling vfs shrinker. So we have to reboot the hosts to get the memory back. I didn't manage to come up with a reproducer in test environment, and the problem can't be reproduced after rebooting. But it seems there is race between shrinker map bit clear and reparenting by code inspection. The hypothesis is elaborated as below. The memcg hierarchy on our production environment looks like: root / \ system user The main workloads are running under user slice's children, and it creates and removes memcg frequently. So reparenting happens very often under user slice, but no task is under user slice directly. So with the frequent reparenting and tight memory pressure, the below hypothetical race condition may happen: CPU A CPU B reparent dst->nr_items == 0 shrinker: total_objects == 0 add src->nr_items to dst set_bit return SHRINK_EMPTY clear_bit child memcg offline replace child's kmemcg_id with parent's (in memcg_offline_kmem()) list_lru_del() between shrinker runs see parent's kmemcg_id dec dst->nr_items reparent again dst->nr_items may go negative due to concurrent list_lru_del() The second run of shrinker: read nr_items without any synchronization, so it may see intermediate negative nr_items then total_objects may return 0 coincidently keep the bit cleared dst->nr_items != 0 skip set_bit add scr->nr_item to dst After this point dst->nr_item may never go zero, so reparenting will not set shrinker_map bit anymore. And since there is no task under user slice directly, so no new object will be added to its lru to set the shrinker map bit either. That bit is kept cleared forever. How does list_lru_del() race with reparenting? It is because reparenting replaces children's kmemcg_id to parent's without protecting from nlru->lock, so list_lru_del() may see parent's kmemcg_id but actually deleting items from child's lru, but dec'ing parent's nr_items, so the parent's nr_items may go negative as commit 2788cf0c401c ("memcg: reparent list_lrus and free kmemcg_id on css offline") says. Since it is impossible that dst->nr_items goes negative and src->nr_items goes zero at the same time, so it seems we could set the shrinker map bit iff src->nr_items != 0. We could synchronize list_lru_count_one() and reparenting with nlru->lock, but it seems checking src->nr_items in reparenting is the simplest and avoids lock contention. Fixes: fae91d6d8be5 ("mm/list_lru.c: set bit in memcg shrinker bitmap on first list_lru item appearance") Suggested-by: Roman Gushchin Signed-off-by: Yang Shi Signed-off-by: Andrew Morton Reviewed-by: Roman Gushchin Reviewed-by: Shakeel Butt Acked-by: Kirill Tkhai Cc: Vladimir Davydov Cc: [4.19] Link: https://lkml.kernel.org/r/20201202171749.264354-1-shy828301@gmail.com Signed-off-by: Linus Torvalds --- mm/list_lru.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/mm/list_lru.c b/mm/list_lru.c index 5aa6e44bc2ae..fe230081690b 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -534,7 +534,6 @@ static void memcg_drain_list_lru_node(struct list_lru *lru, int nid, struct list_lru_node *nlru = &lru->node[nid]; int dst_idx = dst_memcg->kmemcg_id; struct list_lru_one *src, *dst; - bool set; /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, @@ -546,11 +545,12 @@ static void memcg_drain_list_lru_node(struct list_lru *lru, int nid, dst = list_lru_from_memcg_idx(nlru, dst_idx); list_splice_init(&src->list, &dst->list); - set = (!dst->nr_items && src->nr_items); - dst->nr_items += src->nr_items; - if (set) + + if (src->nr_items) { + dst->nr_items += src->nr_items; memcg_set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); - src->nr_items = 0; + src->nr_items = 0; + } spin_unlock_irq(&nlru->lock); } -- cgit v1.2.3 From e91d8d78237de8d7120c320b3645b7100848f24d Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Sat, 5 Dec 2020 22:14:51 -0800 Subject: mm/zsmalloc.c: drop ZSMALLOC_PGTABLE_MAPPING While I was doing zram testing, I found sometimes decompression failed since the compression buffer was corrupted. With investigation, I found below commit calls cond_resched unconditionally so it could make a problem in atomic context if the task is reschedule. BUG: sleeping function called from invalid context at mm/vmalloc.c:108 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 946, name: memhog 3 locks held by memhog/946: #0: ffff9d01d4b193e8 (&mm->mmap_lock#2){++++}-{4:4}, at: __mm_populate+0x103/0x160 #1: ffffffffa3d53de0 (fs_reclaim){+.+.}-{0:0}, at: __alloc_pages_slowpath.constprop.0+0xa98/0x1160 #2: ffff9d01d56b8110 (&zspage->lock){.+.+}-{3:3}, at: zs_map_object+0x8e/0x1f0 CPU: 0 PID: 946 Comm: memhog Not tainted 5.9.3-00011-gc5bfc0287345-dirty #316 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014 Call Trace: unmap_kernel_range_noflush+0x2eb/0x350 unmap_kernel_range+0x14/0x30 zs_unmap_object+0xd5/0xe0 zram_bvec_rw.isra.0+0x38c/0x8e0 zram_rw_page+0x90/0x101 bdev_write_page+0x92/0xe0 __swap_writepage+0x94/0x4a0 pageout+0xe3/0x3a0 shrink_page_list+0xb94/0xd60 shrink_inactive_list+0x158/0x460 We can fix this by removing the ZSMALLOC_PGTABLE_MAPPING feature (which contains the offending calling code) from zsmalloc. Even though this option showed some amount improvement(e.g., 30%) in some arm32 platforms, it has been headache to maintain since it have abused APIs[1](e.g., unmap_kernel_range in atomic context). Since we are approaching to deprecate 32bit machines and already made the config option available for only builtin build since v5.8, lastly it has been not default option in zsmalloc, it's time to drop the option for better maintenance. [1] http://lore.kernel.org/linux-mm/20201105170249.387069-1-minchan@kernel.org Fixes: e47110e90584 ("mm/vunmap: add cond_resched() in vunmap_pmd_range") Signed-off-by: Minchan Kim Signed-off-by: Andrew Morton Reviewed-by: Sergey Senozhatsky Cc: Tony Lindgren Cc: Christoph Hellwig Cc: Harish Sriram Cc: Uladzislau Rezki Cc: Link: https://lkml.kernel.org/r/20201117202916.GA3856507@google.com Signed-off-by: Linus Torvalds --- arch/arm/configs/omap2plus_defconfig | 1 - include/linux/zsmalloc.h | 1 - mm/Kconfig | 13 --------- mm/zsmalloc.c | 54 ------------------------------------ 4 files changed, 69 deletions(-) diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 34793aabdb65..58df9fd79a76 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -81,7 +81,6 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_BINFMT_MISC=y CONFIG_CMA=y CONFIG_ZSMALLOC=m -CONFIG_ZSMALLOC_PGTABLE_MAPPING=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index 0fdbf653b173..4807ca4d52e0 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -20,7 +20,6 @@ * zsmalloc mapping modes * * NOTE: These only make a difference when a mapped object spans pages. - * They also have no effect when ZSMALLOC_PGTABLE_MAPPING is selected. */ enum zs_mapmode { ZS_MM_RW, /* normal read-write mapping */ diff --git a/mm/Kconfig b/mm/Kconfig index d42423f884a7..390165ffbb0f 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -707,19 +707,6 @@ config ZSMALLOC returned by an alloc(). This handle must be mapped in order to access the allocated space. -config ZSMALLOC_PGTABLE_MAPPING - bool "Use page table mapping to access object in zsmalloc" - depends on ZSMALLOC=y - help - By default, zsmalloc uses a copy-based object mapping method to - access allocations that span two pages. However, if a particular - architecture (ex, ARM) performs VM mapping faster than copying, - then you should select this. This causes zsmalloc to use page table - mapping rather than copying for object mapping. - - You can check speed with zsmalloc benchmark: - https://github.com/spartacus06/zsmapbench - config ZSMALLOC_STAT bool "Export zsmalloc statistics" depends on ZSMALLOC diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 918c7b019b3d..cdfaaadea8ff 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -293,11 +293,7 @@ struct zspage { }; struct mapping_area { -#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING - struct vm_struct *vm; /* vm area for mapping object that span pages */ -#else char *vm_buf; /* copy buffer for objects that span pages */ -#endif char *vm_addr; /* address of kmap_atomic()'ed pages */ enum zs_mapmode vm_mm; /* mapping mode */ }; @@ -1113,54 +1109,6 @@ static struct zspage *find_get_zspage(struct size_class *class) return zspage; } -#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING -static inline int __zs_cpu_up(struct mapping_area *area) -{ - /* - * Make sure we don't leak memory if a cpu UP notification - * and zs_init() race and both call zs_cpu_up() on the same cpu - */ - if (area->vm) - return 0; - area->vm = get_vm_area(PAGE_SIZE * 2, 0); - if (!area->vm) - return -ENOMEM; - - /* - * Populate ptes in advance to avoid pte allocation with GFP_KERNEL - * in non-preemtible context of zs_map_object. - */ - return apply_to_page_range(&init_mm, (unsigned long)area->vm->addr, - PAGE_SIZE * 2, NULL, NULL); -} - -static inline void __zs_cpu_down(struct mapping_area *area) -{ - if (area->vm) - free_vm_area(area->vm); - area->vm = NULL; -} - -static inline void *__zs_map_object(struct mapping_area *area, - struct page *pages[2], int off, int size) -{ - unsigned long addr = (unsigned long)area->vm->addr; - - BUG_ON(map_kernel_range(addr, PAGE_SIZE * 2, PAGE_KERNEL, pages) < 0); - area->vm_addr = area->vm->addr; - return area->vm_addr + off; -} - -static inline void __zs_unmap_object(struct mapping_area *area, - struct page *pages[2], int off, int size) -{ - unsigned long addr = (unsigned long)area->vm_addr; - - unmap_kernel_range(addr, PAGE_SIZE * 2); -} - -#else /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */ - static inline int __zs_cpu_up(struct mapping_area *area) { /* @@ -1241,8 +1189,6 @@ out: pagefault_enable(); } -#endif /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */ - static int zs_cpu_prepare(unsigned int cpu) { struct mapping_area *area; -- cgit v1.2.3 From b11a76b37a5aa7b07c3e3eeeaae20b25475bddd3 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Sat, 5 Dec 2020 22:14:55 -0800 Subject: mm/swapfile: do not sleep with a spin lock held We can't call kvfree() with a spin lock held, so defer it. Fixes a might_sleep() runtime warning. Fixes: 873d7bcfd066 ("mm/swapfile.c: use kvzalloc for swap_info_struct allocation") Signed-off-by: Qian Cai Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Cc: Hugh Dickins Cc: Link: https://lkml.kernel.org/r/20201202151549.10350-1-qcai@redhat.com Signed-off-by: Linus Torvalds --- mm/swapfile.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mm/swapfile.c b/mm/swapfile.c index c4a613688a17..d58361109066 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2867,6 +2867,7 @@ late_initcall(max_swapfiles_check); static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; + struct swap_info_struct *defer = NULL; unsigned int type; int i; @@ -2895,7 +2896,7 @@ static struct swap_info_struct *alloc_swap_info(void) smp_wmb(); WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1); } else { - kvfree(p); + defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() @@ -2908,6 +2909,7 @@ static struct swap_info_struct *alloc_swap_info(void) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); + kvfree(defer); spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); -- cgit v1.2.3 From 4e60340c5ca560278c938726235bc0daa5fc8c7f Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Sat, 5 Dec 2020 22:14:58 -0800 Subject: mailmap: add two more addresses of Uwe Kleine-König MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes attribution for the commits (among others) - d4097456cd1d ("video/framebuffer: move the probe func into .devinit.text in Blackfin LCD driver") - 0312e024d6cd ("mfd: mc13xxx: Add support for mc34708") Signed-off-by: Uwe Kleine-König Signed-off-by: Andrew Morton Link: https://lkml.kernel.org/r/20201127213358.3440830-1-u.kleine-koenig@pengutronix.de Signed-off-by: Linus Torvalds --- .mailmap | 2 ++ 1 file changed, 2 insertions(+) diff --git a/.mailmap b/.mailmap index d9fb83d67055..225546cc8028 100644 --- a/.mailmap +++ b/.mailmap @@ -322,6 +322,8 @@ TripleX Chung Tsuneo Yoshioka Tycho Andersen Uwe Kleine-König +Uwe Kleine-König +Uwe Kleine-König Uwe Kleine-König Uwe Kleine-König Valdis Kletnieks -- cgit v1.2.3 From d8cbe8bfa7df3c680ddfd5e1eee3a5c86d8dc764 Mon Sep 17 00:00:00 2001 From: Xingxing Su Date: Sat, 5 Dec 2020 22:15:02 -0800 Subject: tools/testing/selftests/vm: fix build error Only x86 and PowerPC implement the pkey-xxx.h, and an error was reported when compiling protection_keys.c. Add a Arch judgment to compile "protection_keys" in the Makefile. If other arch implement this, add the arch name to the Makefile. eg: ifneq (,$(findstring $(ARCH),powerpc mips ... )) Following build errors: pkey-helpers.h:93:2: error: #error Architecture not supported #error Architecture not supported pkey-helpers.h:96:20: error: `PKEY_DISABLE_ACCESS' undeclared #define PKEY_MASK (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE) ^ protection_keys.c:218:45: error: `PKEY_DISABLE_WRITE' undeclared pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE)); ^ Signed-off-by: Xingxing Su Signed-off-by: Andrew Morton Cc: Shuah Khan Cc: Sandipan Das Cc: John Hubbard Cc: Dave Hansen Cc: "Kirill A. Shutemov" Cc: Brian Geffon Cc: Mina Almasry Link: https://lkml.kernel.org/r/1606826876-30656-1-git-send-email-suxingxing@loongson.cn Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/Makefile | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 30873b19d04b..691893afc15d 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -60,9 +60,13 @@ ifeq ($(CAN_BUILD_X86_64),1) TEST_GEN_FILES += $(BINARIES_64) endif else + +ifneq (,$(findstring $(ARCH),powerpc)) TEST_GEN_FILES += protection_keys endif +endif + ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64)) TEST_GEN_FILES += va_128TBswitch TEST_GEN_FILES += virtual_address_range -- cgit v1.2.3 From 573a259336f8c57739bdaf035aa7abbae7d9a713 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Sat, 5 Dec 2020 22:15:05 -0800 Subject: userfaultfd: selftests: fix SIGSEGV if huge mmap fails The error handling in hugetlb_allocate_area() was incorrect for the hugetlb_shared test case. Previously the behavior was: - mmap a hugetlb area - If this fails, set the pointer to NULL, and carry on - mmap an alias of the same hugetlb fd - If this fails, munmap the original area If the original mmap failed, it's likely the second one did too. If both failed, we'd blindly try to munmap a NULL pointer, causing a SIGSEGV. Instead, "goto fail" so we return before trying to mmap the alias. This issue can be hit "in real life" by forgetting to set /proc/sys/vm/nr_hugepages (leaving it at 0), and then trying to run the hugetlb_shared test. Another small improvement is, when the original mmap fails, don't just print "it failed": perror(), so we can see *why*. :) Signed-off-by: Axel Rasmussen Signed-off-by: Andrew Morton Cc: Shuah Khan Cc: Peter Xu Cc: Joe Perches Cc: Mike Rapoport Cc: Andrea Arcangeli Cc: David Alan Gilbert Link: https://lkml.kernel.org/r/20201204203443.2714693-1-axelrasmussen@google.com Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/userfaultfd.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 9b0912a01777..c4425597769a 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -206,19 +206,19 @@ static int hugetlb_release_pages(char *rel_area) return ret; } - static void hugetlb_allocate_area(void **alloc_area) { void *area_alias = NULL; char **alloc_area_alias; + *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, (map_shared ? MAP_SHARED : MAP_PRIVATE) | MAP_HUGETLB, huge_fd, *alloc_area == area_src ? 0 : nr_pages * page_size); if (*alloc_area == MAP_FAILED) { - fprintf(stderr, "mmap of hugetlbfs file failed\n"); - *alloc_area = NULL; + perror("mmap of hugetlbfs file failed"); + goto fail; } if (map_shared) { @@ -227,14 +227,11 @@ static void hugetlb_allocate_area(void **alloc_area) huge_fd, *alloc_area == area_src ? 0 : nr_pages * page_size); if (area_alias == MAP_FAILED) { - if (munmap(*alloc_area, nr_pages * page_size) < 0) { - perror("hugetlb munmap"); - exit(1); - } - *alloc_area = NULL; - return; + perror("mmap of hugetlb file alias failed"); + goto fail_munmap; } } + if (*alloc_area == area_src) { huge_fd_off0 = *alloc_area; alloc_area_alias = &area_src_alias; @@ -243,6 +240,16 @@ static void hugetlb_allocate_area(void **alloc_area) } if (area_alias) *alloc_area_alias = area_alias; + + return; + +fail_munmap: + if (munmap(*alloc_area, nr_pages * page_size) < 0) { + perror("hugetlb munmap"); + exit(1); + } +fail: + *alloc_area = NULL; } static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset) -- cgit v1.2.3 From 3351b16af4946fff0d46481d155fb91adb28b1f9 Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Sat, 5 Dec 2020 22:15:09 -0800 Subject: mm/filemap: add static for function __add_to_page_cache_locked mm/filemap.c:830:14: warning: no previous prototype for `__add_to_page_cache_locked' [-Wmissing-prototypes] Signed-off-by: Alex Shi Signed-off-by: Andrew Morton Cc: Souptick Joarder Link: https://lkml.kernel.org/r/1604661895-5495-1-git-send-email-alex.shi@linux.alibaba.com Signed-off-by: Linus Torvalds --- mm/filemap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/filemap.c b/mm/filemap.c index 0b2067b3c328..331f4261d723 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -827,7 +827,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); -noinline int __add_to_page_cache_locked(struct page *page, +static noinline int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp, void **shadowp) -- cgit v1.2.3 From 7a5bde37983d37783161681ff7c6122dfd081791 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Sat, 5 Dec 2020 22:15:12 -0800 Subject: hugetlb_cgroup: fix offline of hugetlb cgroup with reservations Adrian Moreno was ruuning a kubernetes 1.19 + containerd/docker workload using hugetlbfs. In this environment the issue is reproduced by: - Start a simple pod that uses the recently added HugePages medium feature (pod yaml attached) - Start a DPDK app. It doesn't need to run successfully (as in transfer packets) nor interact with real hardware. It seems just initializing the EAL layer (which handles hugepage reservation and locking) is enough to trigger the issue - Delete the Pod (or let it "Complete"). This would result in a kworker thread going into a tight loop (top output): 1425 root 20 0 0 0 0 R 99.7 0.0 5:22.45 kworker/28:7+cgroup_destroy 'perf top -g' reports: - 63.28% 0.01% [kernel] [k] worker_thread - 49.97% worker_thread - 52.64% process_one_work - 62.08% css_killed_work_fn - hugetlb_cgroup_css_offline 41.52% _raw_spin_lock - 2.82% _cond_resched rcu_all_qs 2.66% PageHuge - 0.57% schedule - 0.57% __schedule We are spinning in the do-while loop in hugetlb_cgroup_css_offline. Worse yet, we are holding the master cgroup lock (cgroup_mutex) while infinitely spinning. Little else can be done on the system as the cgroup_mutex can not be acquired. Do note that the issue can be reproduced by simply offlining a hugetlb cgroup containing pages with reservation counts. The loop in hugetlb_cgroup_css_offline is moving page counts from the cgroup being offlined to the parent cgroup. This is done for each hstate, and is repeated until hugetlb_cgroup_have_usage returns false. The routine moving counts (hugetlb_cgroup_move_parent) is only moving 'usage' counts. The routine hugetlb_cgroup_have_usage is checking for both 'usage' and 'reservation' counts. Discussion about what to do with reservation counts when reparenting was discussed here: https://lore.kernel.org/linux-kselftest/CAHS8izMFAYTgxym-Hzb_JmkTK1N_S9tGN71uS6MFV+R7swYu5A@mail.gmail.com/ The decision was made to leave a zombie cgroup for with reservation counts. Unfortunately, the code checking reservation counts was incorrectly added to hugetlb_cgroup_have_usage. To fix the issue, simply remove the check for reservation counts. While fixing this issue, a related bug in hugetlb_cgroup_css_offline was noticed. The hstate index is not reinitialized each time through the do-while loop. Fix this as well. Fixes: 1adc4d419aa2 ("hugetlb_cgroup: add interface for charge/uncharge hugetlb reservations") Reported-by: Adrian Moreno Signed-off-by: Mike Kravetz Signed-off-by: Andrew Morton Tested-by: Adrian Moreno Reviewed-by: Shakeel Butt Cc: Mina Almasry Cc: David Rientjes Cc: Greg Thelen Cc: Sandipan Das Cc: Shuah Khan Cc: Link: https://lkml.kernel.org/r/20201203220242.158165-1-mike.kravetz@oracle.com Signed-off-by: Linus Torvalds --- mm/hugetlb_cgroup.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 1f87aec9ab5c..9182848dda3e 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -82,11 +82,8 @@ static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) for (idx = 0; idx < hugetlb_max_hstate; idx++) { if (page_counter_read( - hugetlb_cgroup_counter_from_cgroup(h_cg, idx)) || - page_counter_read(hugetlb_cgroup_counter_from_cgroup_rsvd( - h_cg, idx))) { + hugetlb_cgroup_counter_from_cgroup(h_cg, idx))) return true; - } } return false; } @@ -202,9 +199,10 @@ static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); struct hstate *h; struct page *page; - int idx = 0; + int idx; do { + idx = 0; for_each_hstate(h) { spin_lock(&hugetlb_lock); list_for_each_entry(page, &h->hugepage_activelist, lru) -- cgit v1.2.3 From 309d08d9b3a3659ab3f239d27d4e38b670b08fc9 Mon Sep 17 00:00:00 2001 From: Liu Zixian Date: Sat, 5 Dec 2020 22:15:15 -0800 Subject: mm/mmap.c: fix mmap return value when vma is merged after call_mmap() On success, mmap should return the begin address of newly mapped area, but patch "mm: mmap: merge vma after call_mmap() if possible" set vm_start of newly merged vma to return value addr. Users of mmap will get wrong address if vma is merged after call_mmap(). We fix this by moving the assignment to addr before merging vma. We have a driver which changes vm_flags, and this bug is found by our testcases. Fixes: d70cec898324 ("mm: mmap: merge vma after call_mmap() if possible") Signed-off-by: Liu Zixian Signed-off-by: Andrew Morton Reviewed-by: Jason Gunthorpe Reviewed-by: David Hildenbrand Cc: Miaohe Lin Cc: Hongxiang Lou Cc: Hu Shiyuan Cc: Matthew Wilcox Link: https://lkml.kernel.org/r/20201203085350.22624-1-liuzixian4@huawei.com Signed-off-by: Linus Torvalds --- mm/mmap.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index d91ecb00d38c..5c8b4485860d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1808,6 +1808,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr, if (error) goto unmap_and_free_vma; + /* Can addr have changed?? + * + * Answer: Yes, several device drivers can do it in their + * f_op->mmap method. -DaveM + * Bug: If addr is changed, prev, rb_link, rb_parent should + * be updated for vma_link() + */ + WARN_ON_ONCE(addr != vma->vm_start); + + addr = vma->vm_start; + /* If vm_flags changed after call_mmap(), we should try merge vma again * as we may succeed this time. */ @@ -1822,25 +1833,12 @@ unsigned long mmap_region(struct file *file, unsigned long addr, fput(vma->vm_file); vm_area_free(vma); vma = merge; - /* Update vm_flags and possible addr to pick up the change. We don't - * warn here if addr changed as the vma is not linked by vma_link(). - */ - addr = vma->vm_start; + /* Update vm_flags to pick up the change. */ vm_flags = vma->vm_flags; goto unmap_writable; } } - /* Can addr have changed?? - * - * Answer: Yes, several device drivers can do it in their - * f_op->mmap method. -DaveM - * Bug: If addr is changed, prev, rb_link, rb_parent should - * be updated for vma_link() - */ - WARN_ON_ONCE(addr != vma->vm_start); - - addr = vma->vm_start; vm_flags = vma->vm_flags; } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); -- cgit v1.2.3 From 0477e92881850d44910a7e94fc2c46f96faa131f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 6 Dec 2020 14:25:12 -0800 Subject: Linux 5.10-rc7 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index a2ded5029084..9ec53d947628 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Kleptomaniac Octopus # *DOCUMENTATION* -- cgit v1.2.3 From 3b384bd6c3f2d6d3526c77bfb264dfbaf737bc2a Mon Sep 17 00:00:00 2001 From: Furquan Shaikh Date: Sun, 6 Dec 2020 22:05:13 -0800 Subject: Input: raydium_ts_i2c - do not split tx transactions Raydium device does not like splitting of tx transactions into multiple messages - one for the register address and one for the actual data. This results in incorrect behavior on the device side. This change updates raydium_i2c_read and raydium_i2c_write to create i2c_msg arrays separately and passes those arrays into raydium_i2c_xfer which decides based on the address whether the bank switch command should be sent. The bank switch header is still added by raydium_i2c_read and raydium_i2c_write to ensure that all these operations are performed as part of a single I2C transfer. It guarantees that no other transactions are initiated to any other device on the same bus after the bank switch command is sent. Signed-off-by: Furquan Shaikh Link: https://lore.kernel.org/r/20201205005941.1427643-1-furquan@google.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/raydium_i2c_ts.c | 126 ++++++++++++++++++++--------- 1 file changed, 88 insertions(+), 38 deletions(-) diff --git a/drivers/input/touchscreen/raydium_i2c_ts.c b/drivers/input/touchscreen/raydium_i2c_ts.c index e694a9b2b1e5..603a948460d6 100644 --- a/drivers/input/touchscreen/raydium_i2c_ts.c +++ b/drivers/input/touchscreen/raydium_i2c_ts.c @@ -137,45 +137,25 @@ struct raydium_data { bool wake_irq_enabled; }; -static int raydium_i2c_xfer(struct i2c_client *client, - u32 addr, void *data, size_t len, bool is_read) -{ - struct raydium_bank_switch_header { - u8 cmd; - __be32 be_addr; - } __packed header = { - .cmd = RM_CMD_BANK_SWITCH, - .be_addr = cpu_to_be32(addr), - }; - - u8 reg_addr = addr & 0xff; - - struct i2c_msg xfer[] = { - { - .addr = client->addr, - .len = sizeof(header), - .buf = (u8 *)&header, - }, - { - .addr = client->addr, - .len = 1, - .buf = ®_addr, - }, - { - .addr = client->addr, - .len = len, - .buf = data, - .flags = is_read ? I2C_M_RD : 0, - } - }; +/* + * Header to be sent for RM_CMD_BANK_SWITCH command. This is used by + * raydium_i2c_{read|send} below. + */ +struct __packed raydium_bank_switch_header { + u8 cmd; + __be32 be_addr; +}; +static int raydium_i2c_xfer(struct i2c_client *client, u32 addr, + struct i2c_msg *xfer, size_t xfer_count) +{ + int ret; /* * If address is greater than 255, then RM_CMD_BANK_SWITCH needs to be * sent first. Else, skip the header i.e. xfer[0]. */ int xfer_start_idx = (addr > 0xff) ? 0 : 1; - size_t xfer_count = ARRAY_SIZE(xfer) - xfer_start_idx; - int ret; + xfer_count -= xfer_start_idx; ret = i2c_transfer(client->adapter, &xfer[xfer_start_idx], xfer_count); if (likely(ret == xfer_count)) @@ -189,10 +169,46 @@ static int raydium_i2c_send(struct i2c_client *client, { int tries = 0; int error; + u8 *tx_buf; + u8 reg_addr = addr & 0xff; + + tx_buf = kmalloc(len + 1, GFP_KERNEL); + if (!tx_buf) + return -ENOMEM; + + tx_buf[0] = reg_addr; + memcpy(tx_buf + 1, data, len); do { - error = raydium_i2c_xfer(client, addr, (void *)data, len, - false); + struct raydium_bank_switch_header header = { + .cmd = RM_CMD_BANK_SWITCH, + .be_addr = cpu_to_be32(addr), + }; + + /* + * Perform as a single i2c_transfer transaction to ensure that + * no other I2C transactions are initiated on the bus to any + * other device in between. Initiating transacations to other + * devices after RM_CMD_BANK_SWITCH is sent is known to cause + * issues. This is also why regmap infrastructure cannot be used + * for this driver. Regmap handles page(bank) switch and reads + * as separate i2c_transfer() operations. This can result in + * problems if the Raydium device is on a shared I2C bus. + */ + struct i2c_msg xfer[] = { + { + .addr = client->addr, + .len = sizeof(header), + .buf = (u8 *)&header, + }, + { + .addr = client->addr, + .len = len + 1, + .buf = tx_buf, + }, + }; + + error = raydium_i2c_xfer(client, addr, xfer, ARRAY_SIZE(xfer)); if (likely(!error)) return 0; @@ -206,12 +222,46 @@ static int raydium_i2c_send(struct i2c_client *client, static int raydium_i2c_read(struct i2c_client *client, u32 addr, void *data, size_t len) { - size_t xfer_len; int error; while (len) { - xfer_len = min_t(size_t, len, RM_MAX_READ_SIZE); - error = raydium_i2c_xfer(client, addr, data, xfer_len, true); + u8 reg_addr = addr & 0xff; + struct raydium_bank_switch_header header = { + .cmd = RM_CMD_BANK_SWITCH, + .be_addr = cpu_to_be32(addr), + }; + size_t xfer_len = min_t(size_t, len, RM_MAX_READ_SIZE); + + /* + * Perform as a single i2c_transfer transaction to ensure that + * no other I2C transactions are initiated on the bus to any + * other device in between. Initiating transacations to other + * devices after RM_CMD_BANK_SWITCH is sent is known to cause + * issues. This is also why regmap infrastructure cannot be used + * for this driver. Regmap handles page(bank) switch and writes + * as separate i2c_transfer() operations. This can result in + * problems if the Raydium device is on a shared I2C bus. + */ + struct i2c_msg xfer[] = { + { + .addr = client->addr, + .len = sizeof(header), + .buf = (u8 *)&header, + }, + { + .addr = client->addr, + .len = 1, + .buf = ®_addr, + }, + { + .addr = client->addr, + .len = xfer_len, + .buf = data, + .flags = I2C_M_RD, + } + }; + + error = raydium_i2c_xfer(client, addr, xfer, ARRAY_SIZE(xfer)); if (unlikely(error)) return error; -- cgit v1.2.3 From 223f61b8c5ad80f01900bc25f8073dfa4f23a2be Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 6 Dec 2020 21:59:42 -0800 Subject: Input: soc_button_array - add Lenovo Yoga Tablet2 1051L to the dmi_use_low_level_irq list Add the Lenovo Yoga Tablet2 1051L to the list of devices where the ACPI AML code is poking the GPIO config register directly changing the IRQ type to a low_level_irq, which we need to work around. This fixes the home button on the Lenovo Yoga Tablet2 1051L not working. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20201206161245.24798-1-hdegoede@redhat.com Signed-off-by: Dmitry Torokhov --- drivers/input/misc/soc_button_array.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index d14a65683c5e..cb6ec59a045d 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -83,6 +83,17 @@ static const struct dmi_system_id dmi_use_low_level_irq[] = { DMI_MATCH(DMI_PRODUCT_NAME, "One S1003"), }, }, + { + /* + * Lenovo Yoga Tab2 1051L, something messes with the home-button + * IRQ settings, leading to a non working home-button. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "60073"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1051L"), + }, + }, {} /* Terminating entry */ }; -- cgit v1.2.3 From 61f54de2e9194f01874d5eda12037b0978e77519 Mon Sep 17 00:00:00 2001 From: Huazhong Tan Date: Mon, 7 Dec 2020 15:20:25 +0800 Subject: net: hns3: remove a misused pragma packed hclge_dbg_reg_info[] is defined as an array of packed structure accidentally. However, this array contains pointers, which are no longer aligned naturally, and cannot be relocated on PPC64. Hence, when compile-testing this driver on PPC64 with CONFIG_RELOCATABLE=y (e.g. PowerPC allyesconfig), there will be some warnings. Since each field in structure hclge_qos_pri_map_cmd and hclge_dbg_bitmap_cmd is type u8, the pragma packed is unnecessary for these two structures as well, so remove the pragma packed in hclge_debugfs.h to fix this issue, and this increases hclge_dbg_reg_info[] by 4 bytes per entry. Fixes: a582b78dfc33 ("net: hns3: code optimization for debugfs related to "dump reg"") Reported-by: Stephen Rothwell Signed-off-by: Huazhong Tan Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h index a9066e6ff697..ca2ab6cf84d9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h @@ -35,8 +35,6 @@ #define HCLGE_DBG_DFX_SSU_2_OFFSET 12 -#pragma pack(1) - struct hclge_qos_pri_map_cmd { u8 pri0_tc : 4, pri1_tc : 4; @@ -85,8 +83,6 @@ struct hclge_dbg_reg_type_info { struct hclge_dbg_reg_common_msg reg_msg; }; -#pragma pack() - static const struct hclge_dbg_dfx_message hclge_dbg_bios_common_reg[] = { {false, "Reserved"}, {true, "BP_CPU_STATE"}, -- cgit v1.2.3 From 10c678bd0a035ac2c64a9b26b222f20556227a53 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 7 Dec 2020 15:55:40 +0800 Subject: udp: fix the proto value passed to ip_protocol_deliver_rcu for the segments Guillaume noticed that: for segments udp_queue_rcv_one_skb() returns the proto, and it should pass "ret" unmodified to ip_protocol_deliver_rcu(). Otherwize, with a negtive value passed, it will underflow inet_protos. This can be reproduced with IPIP FOU: # ip fou add port 5555 ipproto 4 # ethtool -K eth1 rx-gro-list on Fixes: cf329aa42b66 ("udp: cope with UDP GRO packet misdirection") Reported-by: Guillaume Nault Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/ipv4/udp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 09f0a23d1a01..9eeebd4a0054 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2173,7 +2173,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) __skb_pull(skb, skb_transport_offset(skb)); ret = udp_queue_rcv_one_skb(sk, skb); if (ret > 0) - ip_protocol_deliver_rcu(dev_net(skb->dev), skb, -ret); + ip_protocol_deliver_rcu(dev_net(skb->dev), skb, ret); } return 0; } -- cgit v1.2.3 From 4165bf015ba9454f45beaad621d16c516d5c5afe Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Mon, 7 Dec 2020 03:19:20 -0600 Subject: iommu/amd: Set DTE[IntTabLen] to represent 512 IRTEs According to the AMD IOMMU spec, the commit 73db2fc595f3 ("iommu/amd: Increase interrupt remapping table limit to 512 entries") also requires the interrupt table length (IntTabLen) to be set to 9 (power of 2) in the device table mapping entry (DTE). Fixes: 73db2fc595f3 ("iommu/amd: Increase interrupt remapping table limit to 512 entries") Reported-by: Jerry Snitselaar Signed-off-by: Suravee Suthikulpanit Reviewed-by: Jerry Snitselaar Link: https://lore.kernel.org/r/20201207091920.3052-1-suravee.suthikulpanit@amd.com Signed-off-by: Will Deacon --- drivers/iommu/amd/amd_iommu_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 89647700bab2..494b42a31b7a 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -257,7 +257,7 @@ #define DTE_IRQ_REMAP_INTCTL_MASK (0x3ULL << 60) #define DTE_IRQ_TABLE_LEN_MASK (0xfULL << 1) #define DTE_IRQ_REMAP_INTCTL (2ULL << 60) -#define DTE_IRQ_TABLE_LEN (8ULL << 1) +#define DTE_IRQ_TABLE_LEN (9ULL << 1) #define DTE_IRQ_REMAP_ENABLE 1ULL #define PAGE_MODE_NONE 0x00 -- cgit v1.2.3 From 9280f726097b436c8c907825131cd346d7eb0c0f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 4 Dec 2020 00:18:40 +0100 Subject: ARM: keystone: remove SECTION_SIZE_BITS/MAX_PHYSMEM_BITS These definitions are evidently left over from the days when sparsemem settings were platform specific. This was no longer the case when the platform got merged. There was no warning in the past, but now the asm/sparsemem.h header ends up being included indirectly, causing this warning: In file included from /git/arm-soc/arch/arm/mach-keystone/keystone.c:24: arch/arm/mach-keystone/memory.h:10:9: warning: 'SECTION_SIZE_BITS' macro redefined [-Wmacro-redefined] #define SECTION_SIZE_BITS 34 ^ arch/arm/include/asm/sparsemem.h:23:9: note: previous definition is here #define SECTION_SIZE_BITS 28 ^ Clearly the definitions never had any effect here, so remove them. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20201203231847.1484900-1-arnd@kernel.org' Signed-off-by: Arnd Bergmann --- arch/arm/mach-keystone/memory.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm/mach-keystone/memory.h b/arch/arm/mach-keystone/memory.h index 9147565d0581..1b9ed1271e05 100644 --- a/arch/arm/mach-keystone/memory.h +++ b/arch/arm/mach-keystone/memory.h @@ -6,9 +6,6 @@ #ifndef __MEMORY_H #define __MEMORY_H -#define MAX_PHYSMEM_BITS 36 -#define SECTION_SIZE_BITS 34 - #define KEYSTONE_LOW_PHYS_START 0x80000000ULL #define KEYSTONE_LOW_PHYS_SIZE 0x80000000ULL /* 2G */ #define KEYSTONE_LOW_PHYS_END (KEYSTONE_LOW_PHYS_START + \ -- cgit v1.2.3 From c99055ec2c3974386f36eb648af77a8dbe887ca9 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 1 Dec 2020 23:15:15 +0200 Subject: MAINTAINERS: correct SoC Git address (formerly: arm-soc) The SoC Git was moved from arm/arm-soc.git to soc/soc.git. Correct the ARM Sub-architectures entry. Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20201201211516.24921-1-krzk@kernel.org' Signed-off-by: Arnd Bergmann --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 6f474153dbec..715c84c25fb5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1489,7 +1489,7 @@ F: drivers/iommu/io-pgtable-arm* ARM SUB-ARCHITECTURES L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc.git F: arch/arm/mach-*/ F: arch/arm/plat-*/ -- cgit v1.2.3 From db2082700a0c7974c3a7787d50abff34b2695b4b Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 1 Dec 2020 23:15:16 +0200 Subject: MAINTAINERS: add a limited ARM and ARM64 SoC entry It is expected for ARM and ARM64 SoC related code to go through sub-architecture maintainers. Their addresses were therefore not documented to push patch traffic through sub-architecture maintainers. However when patches touch generic code, e.g. multi_v7_defconfig, the patch might not be picked up by them and instead should go to the SoC maintainers - Arnd and Olof. Add a minimal maintainer's entry for SoC covering only Makefile, so it will not appear on most of submissions (except new devicetree boards). It will though serve as a documentation and reference for cases when submitter does not know where to send his SoC-related patches. Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20201201211516.24921-2-krzk@kernel.org' Signed-off-by: Arnd Bergmann --- MAINTAINERS | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 715c84c25fb5..52086876ce40 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1486,6 +1486,16 @@ F: Documentation/devicetree/bindings/iommu/arm,smmu* F: drivers/iommu/arm/ F: drivers/iommu/io-pgtable-arm* +ARM AND ARM64 SoC SUB-ARCHITECTURES (COMMON PARTS) +M: Arnd Bergmann +M: Olof Johansson +M: soc@kernel.org +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc.git +F: arch/arm/boot/dts/Makefile +F: arch/arm64/boot/dts/Makefile + ARM SUB-ARCHITECTURES L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -- cgit v1.2.3 From e8c954df234145c5765870382c2bc630a48beec9 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sun, 6 Dec 2020 22:22:46 +0000 Subject: io_uring: fix mis-seting personality's creds After io_identity_cow() copies an work.identity it wants to copy creds to the new just allocated id, not the old one. Otherwise it's akin to req->work.identity->creds = req->work.identity->creds. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index a2a7c65a77aa..908817cea4f5 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1284,7 +1284,7 @@ static bool io_identity_cow(struct io_kiocb *req) */ io_init_identity(id); if (creds) - req->work.identity->creds = creds; + id->creds = creds; /* add one for this request */ refcount_inc(&id->count); -- cgit v1.2.3 From d9054a1ff585ba01029584ab730efc794603d68f Mon Sep 17 00:00:00 2001 From: Dongdong Wang Date: Fri, 4 Dec 2020 23:59:45 -0800 Subject: lwt: Disable BH too in run_lwt_bpf() The per-cpu bpf_redirect_info is shared among all skb_do_redirect() and BPF redirect helpers. Callers on RX path are all in BH context, disabling preemption is not sufficient to prevent BH interruption. In production, we observed strange packet drops because of the race condition between LWT xmit and TC ingress, and we verified this issue is fixed after we disable BH. Although this bug was technically introduced from the beginning, that is commit 3a0af8fd61f9 ("bpf: BPF for lightweight tunnel infrastructure"), at that time call_rcu() had to be call_rcu_bh() to match the RCU context. So this patch may not work well before RCU flavor consolidation has been completed around v5.0. Update the comments above the code too, as call_rcu() is now BH friendly. Signed-off-by: Dongdong Wang Signed-off-by: Alexei Starovoitov Reviewed-by: Cong Wang Link: https://lore.kernel.org/bpf/20201205075946.497763-1-xiyou.wangcong@gmail.com --- net/core/lwt_bpf.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 7d3438215f32..4f3cb7c15ddf 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -39,12 +39,11 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, { int ret; - /* Preempt disable is needed to protect per-cpu redirect_info between - * BPF prog and skb_do_redirect(). The call_rcu in bpf_prog_put() and - * access to maps strictly require a rcu_read_lock() for protection, - * mixing with BH RCU lock doesn't work. + /* Preempt disable and BH disable are needed to protect per-cpu + * redirect_info between BPF prog and skb_do_redirect(). */ preempt_disable(); + local_bh_disable(); bpf_compute_data_pointers(skb); ret = bpf_prog_run_save_cb(lwt->prog, skb); @@ -78,6 +77,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, break; } + local_bh_enable(); preempt_enable(); return ret; -- cgit v1.2.3 From e3366884b383073a7edc1bad9634412ae0a22d4e Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 4 Dec 2020 23:59:46 -0800 Subject: lwt_bpf: Replace preempt_disable() with migrate_disable() migrate_disable() is just a wrapper for preempt_disable() in non-RT kernel. It is safe to replace it, and RT kernel will benefit. Note that it is introduced since Feb 2020. Suggested-by: Alexei Starovoitov Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201205075946.497763-2-xiyou.wangcong@gmail.com --- net/core/lwt_bpf.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 4f3cb7c15ddf..2f7940bcf715 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -39,10 +39,10 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, { int ret; - /* Preempt disable and BH disable are needed to protect per-cpu + /* Migration disable and BH disable are needed to protect per-cpu * redirect_info between BPF prog and skb_do_redirect(). */ - preempt_disable(); + migrate_disable(); local_bh_disable(); bpf_compute_data_pointers(skb); ret = bpf_prog_run_save_cb(lwt->prog, skb); @@ -78,7 +78,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, } local_bh_enable(); - preempt_enable(); + migrate_enable(); return ret; } -- cgit v1.2.3 From e432c04c17993011b2a2f59dcb5738e604bd552e Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Sun, 6 Dec 2020 17:32:38 +0200 Subject: RDMA/core: Fix empty gid table for non IB/RoCE devices The query_gid_table ioctl skips non IB/RoCE ports, which as a result returns an empty gid table for devices such as EFA which have a GID table, but are not IB/RoCE. Fixes: c4b4d548fabc ("RDMA/core: Introduce new GID table query API") Link: https://lore.kernel.org/r/20201206153238.34878-1-galpress@amazon.com Signed-off-by: Gal Pressman Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/cache.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index 8017c40dd110..7989b7e1d1c0 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -1269,9 +1269,6 @@ ssize_t rdma_query_gid_table(struct ib_device *device, unsigned long flags; rdma_for_each_port(device, port_num) { - if (!rdma_ib_or_roce(device, port_num)) - continue; - table = rdma_gid_table(device, port_num); read_lock_irqsave(&table->rwlock, flags); for (i = 0; i < table->sz; i++) { -- cgit v1.2.3 From 6247e31b75308c51476e157c9964823aeefbf5dc Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Mon, 30 Nov 2020 16:46:24 +0800 Subject: clk: imx: scu: fix MXC_CLK_SCU module build break This issue can be reproduced by having a kernel config with CONFIG_IMX_MBOX=m and CONFIG_MXC_CLK_SCU=m. It's caused by the Makefile wanting to build clk-scu.o and clk-imx8qxp.o as different targets but that doesn't work (e.g. MXC_CLK_SCU = y while CLK_IMX8QXP = n) "obj-$(CONFIG_MXC_CLK_SCU) += clk-imx-scu.o clk-imx-lpcg-scu.o clk-imx-scu-$(CONFIG_CLK_IMX8QXP) += clk-scu.o clk-imx8qxp.o" Having MXC_CLK_SCU=y/m while CLK_IMX8QXP=n will cause a linker problem like below: LD [M] drivers/clk/imx/clk-imx-scu.o arm-poky-linux-gnueabi-ld: no input files Make MXC_CLK_SCU be un-selectable by users so it can only be selected by the CLK_IMX8QXP option, ensuring the two symbols are built together. Drop COMPILE_TEST too because this option isn't selectable anymore. We can remove it from MXC_CLK_SCU because CLK_IMX8QXP selects MXC_CLK_SCU which already has COMPILE_TEST. Fixes: e0d0d4d86c766 ("clk: imx8qxp: Support building i.MX8QXP clock driver as module") Acked-by: Sebastian Andrzej Siewior Signed-off-by: Dong Aisheng Link: https://lore.kernel.org/r/20201130084624.21113-1-aisheng.dong@nxp.com [sboyd@kernel.org: Rework commit text] Signed-off-by: Stephen Boyd --- drivers/clk/imx/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/imx/Kconfig b/drivers/clk/imx/Kconfig index 3b393cb07295..3061896503f3 100644 --- a/drivers/clk/imx/Kconfig +++ b/drivers/clk/imx/Kconfig @@ -5,8 +5,8 @@ config MXC_CLK depends on ARCH_MXC || COMPILE_TEST config MXC_CLK_SCU - tristate "IMX SCU clock" - depends on ARCH_MXC || COMPILE_TEST + tristate + depends on ARCH_MXC depends on IMX_SCU && HAVE_ARM_SMCCC config CLK_IMX1 -- cgit v1.2.3 From ceabbf94c317c6175dee6e91805fca4a6353745a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 30 Nov 2020 09:57:43 +0100 Subject: clk: renesas: r9a06g032: Drop __packed for portability The R9A06G032 clock driver uses an array of packed structures to reduce kernel size. However, this array contains pointers, which are no longer aligned naturally, and cannot be relocated on PPC64. Hence when compile-testing this driver on PPC64 with CONFIG_RELOCATABLE=y (e.g. PowerPC allyesconfig), the following warnings are produced: WARNING: 136 bad relocations c000000000616be3 R_PPC64_UADDR64 .rodata+0x00000000000cf338 c000000000616bfe R_PPC64_UADDR64 .rodata+0x00000000000cf370 ... Fix this by dropping the __packed attribute from the r9a06g032_clkdesc definition, trading a small size increase for portability. This increases the 156-entry clock table by 1 byte per entry, but due to the compiler generating more efficient code for unpacked accesses, the net size increase is only 76 bytes (gcc 9.3.0 on arm32). Reported-by: Stephen Rothwell Fixes: 4c3d88526eba2143 ("clk: renesas: Renesas R9A06G032 clock driver") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20201130085743.1656317-1-geert+renesas@glider.be Tested-by: Stephen Rothwell # PowerPC allyesconfig build Acked-by: Stephen Boyd Signed-off-by: Stephen Boyd --- drivers/clk/renesas/r9a06g032-clocks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/renesas/r9a06g032-clocks.c b/drivers/clk/renesas/r9a06g032-clocks.c index d900f6bf53d0..892e91b92f2c 100644 --- a/drivers/clk/renesas/r9a06g032-clocks.c +++ b/drivers/clk/renesas/r9a06g032-clocks.c @@ -55,7 +55,7 @@ struct r9a06g032_clkdesc { u16 sel, g1, r1, g2, r2; } dual; }; -} __packed; +}; #define I_GATE(_clk, _rst, _rdy, _midle, _scon, _mirack, _mistat) \ { .gate = _clk, .reset = _rst, \ -- cgit v1.2.3 From 5eedf9fe8db23313df104576845cec5f481b9b60 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 7 Dec 2020 16:58:01 +0000 Subject: powerpc/mm: Fix KUAP warning by providing copy_from_kernel_nofault_allowed() Since commit c33165253492 ("powerpc: use non-set_fs based maccess routines"), userspace access is not granted anymore when using copy_from_kernel_nofault() However, kthread_probe_data() uses copy_from_kernel_nofault() to check validity of pointers. When the pointer is NULL, it points to userspace, leading to a KUAP fault and triggering the following big hammer warning many times when you request a sysrq "show task": [ 1117.202054] ------------[ cut here ]------------ [ 1117.202102] Bug: fault blocked by AP register ! [ 1117.202261] WARNING: CPU: 0 PID: 377 at arch/powerpc/include/asm/nohash/32/kup-8xx.h:66 do_page_fault+0x4a8/0x5ec [ 1117.202310] Modules linked in: [ 1117.202428] CPU: 0 PID: 377 Comm: sh Tainted: G W 5.10.0-rc5-01340-g83f53be2de31-dirty #4175 [ 1117.202499] NIP: c0012048 LR: c0012048 CTR: 00000000 [ 1117.202573] REGS: cacdbb88 TRAP: 0700 Tainted: G W (5.10.0-rc5-01340-g83f53be2de31-dirty) [ 1117.202625] MSR: 00021032 CR: 24082222 XER: 20000000 [ 1117.202899] [ 1117.202899] GPR00: c0012048 cacdbc40 c2929290 00000023 c092e554 00000001 c09865e8 c092e640 [ 1117.202899] GPR08: 00001032 00000000 00000000 00014efc 28082224 100d166a 100a0920 00000000 [ 1117.202899] GPR16: 100cac0c 100b0000 1080c3fc 1080d685 100d0000 100d0000 00000000 100a0900 [ 1117.202899] GPR24: 100d0000 c07892ec 00000000 c0921510 c21f4440 0000005c c0000000 cacdbc80 [ 1117.204362] NIP [c0012048] do_page_fault+0x4a8/0x5ec [ 1117.204461] LR [c0012048] do_page_fault+0x4a8/0x5ec [ 1117.204509] Call Trace: [ 1117.204609] [cacdbc40] [c0012048] do_page_fault+0x4a8/0x5ec (unreliable) [ 1117.204771] [cacdbc70] [c00112f0] handle_page_fault+0x8/0x34 [ 1117.204911] --- interrupt: 301 at copy_from_kernel_nofault+0x70/0x1c0 [ 1117.204979] NIP: c010dbec LR: c010dbac CTR: 00000001 [ 1117.205053] REGS: cacdbc80 TRAP: 0301 Tainted: G W (5.10.0-rc5-01340-g83f53be2de31-dirty) [ 1117.205104] MSR: 00009032 CR: 28082224 XER: 00000000 [ 1117.205416] DAR: 0000005c DSISR: c0000000 [ 1117.205416] GPR00: c0045948 cacdbd38 c2929290 00000001 00000017 00000017 00000027 0000000f [ 1117.205416] GPR08: c09926ec 00000000 00000000 3ffff000 24082224 [ 1117.206106] NIP [c010dbec] copy_from_kernel_nofault+0x70/0x1c0 [ 1117.206202] LR [c010dbac] copy_from_kernel_nofault+0x30/0x1c0 [ 1117.206258] --- interrupt: 301 [ 1117.206372] [cacdbd38] [c004bbb0] kthread_probe_data+0x44/0x70 (unreliable) [ 1117.206561] [cacdbd58] [c0045948] print_worker_info+0xe0/0x194 [ 1117.206717] [cacdbdb8] [c00548ac] sched_show_task+0x134/0x168 [ 1117.206851] [cacdbdd8] [c005a268] show_state_filter+0x70/0x100 [ 1117.206989] [cacdbe08] [c039baa0] sysrq_handle_showstate+0x14/0x24 [ 1117.207122] [cacdbe18] [c039bf18] __handle_sysrq+0xac/0x1d0 [ 1117.207257] [cacdbe48] [c039c0c0] write_sysrq_trigger+0x4c/0x74 [ 1117.207407] [cacdbe68] [c01fba48] proc_reg_write+0xb4/0x114 [ 1117.207550] [cacdbe88] [c0179968] vfs_write+0x12c/0x478 [ 1117.207686] [cacdbf08] [c0179e60] ksys_write+0x78/0x128 [ 1117.207826] [cacdbf38] [c00110d0] ret_from_syscall+0x0/0x34 [ 1117.207938] --- interrupt: c01 at 0xfd4e784 [ 1117.208008] NIP: 0fd4e784 LR: 0fe0f244 CTR: 10048d38 [ 1117.208083] REGS: cacdbf48 TRAP: 0c01 Tainted: G W (5.10.0-rc5-01340-g83f53be2de31-dirty) [ 1117.208134] MSR: 0000d032 CR: 44002222 XER: 00000000 [ 1117.208470] [ 1117.208470] GPR00: 00000004 7fc34090 77bfb4e0 00000001 1080fa40 00000002 7400000f fefefeff [ 1117.208470] GPR08: 7f7f7f7f 10048d38 1080c414 7fc343c0 00000000 [ 1117.209104] NIP [0fd4e784] 0xfd4e784 [ 1117.209180] LR [0fe0f244] 0xfe0f244 [ 1117.209236] --- interrupt: c01 [ 1117.209274] Instruction dump: [ 1117.209353] 714a4000 418200f0 73ca0001 40820084 73ca0032 408200f8 73c90040 4082ff60 [ 1117.209727] 0fe00000 3c60c082 386399f4 48013b65 <0fe00000> 80010034 3860000b 7c0803a6 [ 1117.210102] ---[ end trace 1927c0323393af3e ]--- To avoid that, copy_from_kernel_nofault_allowed() is used to check whether the address is a valid kernel address. But the default version of it returns true for any address. Provide a powerpc version of copy_from_kernel_nofault_allowed() that returns false when the address is below TASK_USER_MAX, so that copy_from_kernel_nofault() will return -ERANGE. Fixes: c33165253492 ("powerpc: use non-set_fs based maccess routines") Reported-by: Qian Cai Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/18bcb456d32a3e74f5ae241fd6f1580c092d07f5.1607360230.git.christophe.leroy@csgroup.eu --- arch/powerpc/mm/Makefile | 2 +- arch/powerpc/mm/maccess.c | 9 +++++++++ 2 files changed, 10 insertions(+), 1 deletion(-) create mode 100644 arch/powerpc/mm/maccess.c diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 5e147986400d..55b4a8bd408a 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -5,7 +5,7 @@ ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) -obj-y := fault.o mem.o pgtable.o mmap.o \ +obj-y := fault.o mem.o pgtable.o mmap.o maccess.o \ init_$(BITS).o pgtable_$(BITS).o \ pgtable-frag.o ioremap.o ioremap_$(BITS).o \ init-common.o mmu_context.o drmem.o diff --git a/arch/powerpc/mm/maccess.c b/arch/powerpc/mm/maccess.c new file mode 100644 index 000000000000..fa9a7a718fc6 --- /dev/null +++ b/arch/powerpc/mm/maccess.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include + +bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) +{ + return is_kernel_addr((unsigned long)unsafe_src); +} -- cgit v1.2.3 From eb96b686fc2c601e78903cc61b6cf4588ddde013 Mon Sep 17 00:00:00 2001 From: Claudiu Manoil Date: Fri, 4 Dec 2020 19:15:05 +0200 Subject: enetc: Fix reporting of h/w packet counters Noticed some inconsistencies in packet statistics reporting. This patch adds the missing Tx packet counter registers to ethtool reporting and fixes the information strings for a few of them. Fixes: 16eb4c85c964 ("enetc: Add ethtool statistics") Signed-off-by: Claudiu Manoil Link: https://lore.kernel.org/r/20201204171505.21389-1-claudiu.manoil@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc_ethtool.c | 10 +++++++--- drivers/net/ethernet/freescale/enetc/enetc_hw.h | 10 +++++++--- 2 files changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index 8ed1ebd5a183..89e558135432 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -143,8 +143,8 @@ static const struct { { ENETC_PM0_R255, "MAC rx 128-255 byte packets" }, { ENETC_PM0_R511, "MAC rx 256-511 byte packets" }, { ENETC_PM0_R1023, "MAC rx 512-1023 byte packets" }, - { ENETC_PM0_R1518, "MAC rx 1024-1518 byte packets" }, - { ENETC_PM0_R1519X, "MAC rx 1519 to max-octet packets" }, + { ENETC_PM0_R1522, "MAC rx 1024-1522 byte packets" }, + { ENETC_PM0_R1523X, "MAC rx 1523 to max-octet packets" }, { ENETC_PM0_ROVR, "MAC rx oversized packets" }, { ENETC_PM0_RJBR, "MAC rx jabber packets" }, { ENETC_PM0_RFRG, "MAC rx fragment packets" }, @@ -163,9 +163,13 @@ static const struct { { ENETC_PM0_TBCA, "MAC tx broadcast frames" }, { ENETC_PM0_TPKT, "MAC tx packets" }, { ENETC_PM0_TUND, "MAC tx undersized packets" }, + { ENETC_PM0_T64, "MAC tx 64 byte packets" }, { ENETC_PM0_T127, "MAC tx 65-127 byte packets" }, + { ENETC_PM0_T255, "MAC tx 128-255 byte packets" }, + { ENETC_PM0_T511, "MAC tx 256-511 byte packets" }, { ENETC_PM0_T1023, "MAC tx 512-1023 byte packets" }, - { ENETC_PM0_T1518, "MAC tx 1024-1518 byte packets" }, + { ENETC_PM0_T1522, "MAC tx 1024-1522 byte packets" }, + { ENETC_PM0_T1523X, "MAC tx 1523 to max-octet packets" }, { ENETC_PM0_TCNP, "MAC tx control packets" }, { ENETC_PM0_TDFR, "MAC tx deferred packets" }, { ENETC_PM0_TMCOL, "MAC tx multiple collisions" }, diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index eb6bbf1113c7..4cbf1667d7ff 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -267,8 +267,8 @@ enum enetc_bdr_type {TX, RX}; #define ENETC_PM0_R255 0x8180 #define ENETC_PM0_R511 0x8188 #define ENETC_PM0_R1023 0x8190 -#define ENETC_PM0_R1518 0x8198 -#define ENETC_PM0_R1519X 0x81A0 +#define ENETC_PM0_R1522 0x8198 +#define ENETC_PM0_R1523X 0x81A0 #define ENETC_PM0_ROVR 0x81A8 #define ENETC_PM0_RJBR 0x81B0 #define ENETC_PM0_RFRG 0x81B8 @@ -287,9 +287,13 @@ enum enetc_bdr_type {TX, RX}; #define ENETC_PM0_TBCA 0x8250 #define ENETC_PM0_TPKT 0x8260 #define ENETC_PM0_TUND 0x8268 +#define ENETC_PM0_T64 0x8270 #define ENETC_PM0_T127 0x8278 +#define ENETC_PM0_T255 0x8280 +#define ENETC_PM0_T511 0x8288 #define ENETC_PM0_T1023 0x8290 -#define ENETC_PM0_T1518 0x8298 +#define ENETC_PM0_T1522 0x8298 +#define ENETC_PM0_T1523X 0x82A0 #define ENETC_PM0_TCNP 0x82C0 #define ENETC_PM0_TDFR 0x82D0 #define ENETC_PM0_TMCOL 0x82D8 -- cgit v1.2.3 From 851d0a73c90e6c8c63fef106c6c1e73df7e05d9d Mon Sep 17 00:00:00 2001 From: Joseph Huang Date: Fri, 4 Dec 2020 18:56:28 -0500 Subject: bridge: Fix a deadlock when enabling multicast snooping When enabling multicast snooping, bridge module deadlocks on multicast_lock if 1) IPv6 is enabled, and 2) there is an existing querier on the same L2 network. The deadlock was caused by the following sequence: While holding the lock, br_multicast_open calls br_multicast_join_snoopers, which eventually causes IP stack to (attempt to) send out a Listener Report (in igmp6_join_group). Since the destination Ethernet address is a multicast address, br_dev_xmit feeds the packet back to the bridge via br_multicast_rcv, which in turn calls br_multicast_add_group, which then deadlocks on multicast_lock. The fix is to move the call br_multicast_join_snoopers outside of the critical section. This works since br_multicast_join_snoopers only deals with IP and does not modify any multicast data structures of the bridge, so there's no need to hold the lock. Steps to reproduce: 1. sysctl net.ipv6.conf.all.force_mld_version=1 2. have another querier 3. ip link set dev bridge type bridge mcast_snooping 0 && \ ip link set dev bridge type bridge mcast_snooping 1 < deadlock > A typical call trace looks like the following: [ 936.251495] _raw_spin_lock+0x5c/0x68 [ 936.255221] br_multicast_add_group+0x40/0x170 [bridge] [ 936.260491] br_multicast_rcv+0x7ac/0xe30 [bridge] [ 936.265322] br_dev_xmit+0x140/0x368 [bridge] [ 936.269689] dev_hard_start_xmit+0x94/0x158 [ 936.273876] __dev_queue_xmit+0x5ac/0x7f8 [ 936.277890] dev_queue_xmit+0x10/0x18 [ 936.281563] neigh_resolve_output+0xec/0x198 [ 936.285845] ip6_finish_output2+0x240/0x710 [ 936.290039] __ip6_finish_output+0x130/0x170 [ 936.294318] ip6_output+0x6c/0x1c8 [ 936.297731] NF_HOOK.constprop.0+0xd8/0xe8 [ 936.301834] igmp6_send+0x358/0x558 [ 936.305326] igmp6_join_group.part.0+0x30/0xf0 [ 936.309774] igmp6_group_added+0xfc/0x110 [ 936.313787] __ipv6_dev_mc_inc+0x1a4/0x290 [ 936.317885] ipv6_dev_mc_inc+0x10/0x18 [ 936.321677] br_multicast_open+0xbc/0x110 [bridge] [ 936.326506] br_multicast_toggle+0xec/0x140 [bridge] Fixes: 4effd28c1245 ("bridge: join all-snoopers multicast address") Signed-off-by: Joseph Huang Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20201204235628.50653-1-Joseph.Huang@garmin.com Signed-off-by: Jakub Kicinski --- net/bridge/br_device.c | 6 ++++++ net/bridge/br_multicast.c | 34 +++++++++++++++++++++++++--------- net/bridge/br_private.h | 10 ++++++++++ 3 files changed, 41 insertions(+), 9 deletions(-) diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 7730c8f3cb53..d3ea9d0779fb 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -177,6 +177,9 @@ static int br_dev_open(struct net_device *dev) br_stp_enable_bridge(br); br_multicast_open(br); + if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) + br_multicast_join_snoopers(br); + return 0; } @@ -197,6 +200,9 @@ static int br_dev_stop(struct net_device *dev) br_stp_disable_bridge(br); br_multicast_stop(br); + if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) + br_multicast_leave_snoopers(br); + netif_stop_queue(dev); return 0; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index eae898c3cff7..54cb82a69056 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -3286,7 +3286,7 @@ static inline void br_ip6_multicast_join_snoopers(struct net_bridge *br) } #endif -static void br_multicast_join_snoopers(struct net_bridge *br) +void br_multicast_join_snoopers(struct net_bridge *br) { br_ip4_multicast_join_snoopers(br); br_ip6_multicast_join_snoopers(br); @@ -3317,7 +3317,7 @@ static inline void br_ip6_multicast_leave_snoopers(struct net_bridge *br) } #endif -static void br_multicast_leave_snoopers(struct net_bridge *br) +void br_multicast_leave_snoopers(struct net_bridge *br) { br_ip4_multicast_leave_snoopers(br); br_ip6_multicast_leave_snoopers(br); @@ -3336,9 +3336,6 @@ static void __br_multicast_open(struct net_bridge *br, void br_multicast_open(struct net_bridge *br) { - if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) - br_multicast_join_snoopers(br); - __br_multicast_open(br, &br->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) __br_multicast_open(br, &br->ip6_own_query); @@ -3354,9 +3351,6 @@ void br_multicast_stop(struct net_bridge *br) del_timer_sync(&br->ip6_other_query.timer); del_timer_sync(&br->ip6_own_query.timer); #endif - - if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) - br_multicast_leave_snoopers(br); } void br_multicast_dev_del(struct net_bridge *br) @@ -3487,6 +3481,7 @@ static void br_multicast_start_querier(struct net_bridge *br, int br_multicast_toggle(struct net_bridge *br, unsigned long val) { struct net_bridge_port *port; + bool change_snoopers = false; spin_lock_bh(&br->multicast_lock); if (!!br_opt_get(br, BROPT_MULTICAST_ENABLED) == !!val) @@ -3495,7 +3490,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val) br_mc_disabled_update(br->dev, val); br_opt_toggle(br, BROPT_MULTICAST_ENABLED, !!val); if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) { - br_multicast_leave_snoopers(br); + change_snoopers = true; goto unlock; } @@ -3506,9 +3501,30 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val) list_for_each_entry(port, &br->port_list, list) __br_multicast_enable_port(port); + change_snoopers = true; + unlock: spin_unlock_bh(&br->multicast_lock); + /* br_multicast_join_snoopers has the potential to cause + * an MLD Report/Leave to be delivered to br_multicast_rcv, + * which would in turn call br_multicast_add_group, which would + * attempt to acquire multicast_lock. This function should be + * called after the lock has been released to avoid deadlocks on + * multicast_lock. + * + * br_multicast_leave_snoopers does not have the problem since + * br_multicast_rcv first checks BROPT_MULTICAST_ENABLED, and + * returns without calling br_multicast_ipv4/6_rcv if it's not + * enabled. Moved both functions out just for symmetry. + */ + if (change_snoopers) { + if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) + br_multicast_join_snoopers(br); + else + br_multicast_leave_snoopers(br); + } + return 0; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 345118e35c42..8424464186a6 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -792,6 +792,8 @@ void br_multicast_del_port(struct net_bridge_port *port); void br_multicast_enable_port(struct net_bridge_port *port); void br_multicast_disable_port(struct net_bridge_port *port); void br_multicast_init(struct net_bridge *br); +void br_multicast_join_snoopers(struct net_bridge *br); +void br_multicast_leave_snoopers(struct net_bridge *br); void br_multicast_open(struct net_bridge *br); void br_multicast_stop(struct net_bridge *br); void br_multicast_dev_del(struct net_bridge *br); @@ -969,6 +971,14 @@ static inline void br_multicast_init(struct net_bridge *br) { } +static inline void br_multicast_join_snoopers(struct net_bridge *br) +{ +} + +static inline void br_multicast_leave_snoopers(struct net_bridge *br) +{ +} + static inline void br_multicast_open(struct net_bridge *br) { } -- cgit v1.2.3 From f55628b3e7648198e9c072b52080c5dea8678adf Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Sat, 5 Dec 2020 15:56:33 +0800 Subject: mptcp: print new line in mptcp_seq_show() if mptcp isn't in use When do cat /proc/net/netstat, the output isn't append with a new line, it looks like this: [root@localhost ~]# cat /proc/net/netstat ... MPTcpExt: 0 0 0 0 0 0 0 0 0 0 0 0 0[root@localhost ~]# This is because in mptcp_seq_show(), if mptcp isn't in use, net->mib.mptcp_statistics is NULL, so it just puts all 0 after "MPTcpExt:", and return, forgot the '\n'. After this patch: [root@localhost ~]# cat /proc/net/netstat ... MPTcpExt: 0 0 0 0 0 0 0 0 0 0 0 0 0 [root@localhost ~]# Fixes: fc518953bc9c8d7d ("mptcp: add and use MIB counter infrastructure") Signed-off-by: Jianguo Wu Acked-by: Florian Westphal Link: https://lore.kernel.org/r/142e2fd9-58d9-bb13-fb75-951cccc2331e@163.com Signed-off-by: Jakub Kicinski --- net/mptcp/mib.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 84d119436b22..b921cbdd9aaa 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -67,6 +67,7 @@ void mptcp_seq_show(struct seq_file *seq) for (i = 0; mptcp_snmp_list[i].name; i++) seq_puts(seq, " 0"); + seq_putc(seq, '\n'); return; } -- cgit v1.2.3 From bbef72c630b522a9ffbf62dae19b59c880da6ea1 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 6 Dec 2020 16:13:39 +0100 Subject: dpaa2-mac: Add a missing of_node_put after of_device_is_available Add an 'of_node_put()' call when a tested device node is not available. Fixes: 94ae899b2096 ("dpaa2-mac: add PCS support through the Lynx module") Signed-off-by: Christophe JAILLET Reviewed-by: Ioana Ciornei Link: https://lore.kernel.org/r/20201206151339.44306-1-christophe.jaillet@wanadoo.fr Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index 90cd243070d7..828c177df03d 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -269,6 +269,7 @@ static int dpaa2_pcs_create(struct dpaa2_mac *mac, if (!of_device_is_available(node)) { netdev_err(mac->net_dev, "pcs-handle node not available\n"); + of_node_put(node); return -ENODEV; } -- cgit v1.2.3 From 82ca4c922b8992013a238d65cf4e60cc33e12f36 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sat, 5 Dec 2020 22:32:07 +0100 Subject: net: stmmac: dwmac-meson8b: fix mask definition of the m250_sel mux The m250_sel mux clock uses bit 4 in the PRG_ETH0 register. Fix this by shifting the PRG_ETH0_CLK_M250_SEL_MASK accordingly as the "mask" in struct clk_mux expects the mask relative to the "shift" field in the same struct. While here, get rid of the PRG_ETH0_CLK_M250_SEL_SHIFT macro and use __ffs() to determine it from the existing PRG_ETH0_CLK_M250_SEL_MASK macro. Fixes: 566e8251625304 ("net: stmmac: add a glue driver for the Amlogic Meson 8b / GXBB DWMAC") Signed-off-by: Martin Blumenstingl Reviewed-by: Jerome Brunet Link: https://lore.kernel.org/r/20201205213207.519341-1-martin.blumenstingl@googlemail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 5afcf05bbf9c..6d6bd77bb6af 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -30,7 +30,6 @@ #define PRG_ETH0_EXT_RMII_MODE 4 /* mux to choose between fclk_div2 (bit unset) and mpll2 (bit set) */ -#define PRG_ETH0_CLK_M250_SEL_SHIFT 4 #define PRG_ETH0_CLK_M250_SEL_MASK GENMASK(4, 4) /* TX clock delay in ns = "8ns / 4 * tx_dly_val" (where 8ns are exactly one @@ -155,8 +154,9 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) return -ENOMEM; clk_configs->m250_mux.reg = dwmac->regs + PRG_ETH0; - clk_configs->m250_mux.shift = PRG_ETH0_CLK_M250_SEL_SHIFT; - clk_configs->m250_mux.mask = PRG_ETH0_CLK_M250_SEL_MASK; + clk_configs->m250_mux.shift = __ffs(PRG_ETH0_CLK_M250_SEL_MASK); + clk_configs->m250_mux.mask = PRG_ETH0_CLK_M250_SEL_MASK >> + clk_configs->m250_mux.shift; clk = meson8b_dwmac_register_clk(dwmac, "m250_sel", mux_parents, ARRAY_SIZE(mux_parents), &clk_mux_ops, &clk_configs->m250_mux.hw); -- cgit v1.2.3 From 673235f915318ced5d7ec4b2bfd8cb909e6a4a55 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 2 Dec 2020 18:04:19 +0800 Subject: scsi: core: Fix race between handling STS_RESOURCE and completion When queuing I/O request to LLD, STS_RESOURCE may be returned because: - Host is in recovery or blocked - Target queue throttling or target is blocked - LLD rejection In these scenarios BLK_STS_DEV_RESOURCE is returned to the block layer to avoid an unnecessary re-run of the queue. However, all of the requests queued to this SCSI device may complete immediately after reading 'sdev->device_busy' and BLK_STS_DEV_RESOURCE is returned to block layer. In that case the current I/O won't get a chance to get queued since it is invisible at that time for both scsi_run_queue_async() and blk-mq's RESTART. Fix the issue by not returning BLK_STS_DEV_RESOURCE in this situation. Link: https://lore.kernel.org/r/20201202100419.525144-1-ming.lei@redhat.com Fixes: 86ff7c2a80cd ("blk-mq: introduce BLK_STS_DEV_RESOURCE") Cc: Hannes Reinecke Cc: Sumit Saxena Cc: Kashyap Desai Cc: Bart Van Assche Cc: Ewan Milne Cc: Long Li Reported-by: John Garry Tested-by: "chenxiang (M)" Signed-off-by: Ming Lei Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 60c7a7d74852..03c6d0620bfd 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1703,8 +1703,7 @@ out_put_budget: break; case BLK_STS_RESOURCE: case BLK_STS_ZONE_RESOURCE: - if (atomic_read(&sdev->device_busy) || - scsi_device_blocked(sdev)) + if (scsi_device_blocked(sdev)) ret = BLK_STS_DEV_RESOURCE; break; default: -- cgit v1.2.3 From 359db63378eded1ee9c8c9ad72245f9b0158ae95 Mon Sep 17 00:00:00 2001 From: Xiang Chen Date: Mon, 7 Dec 2020 21:30:55 +0800 Subject: scsi: hisi_sas: Select a suitable queue for internal I/Os For when managed interrupts are used (and shost->nr_hw_queues is set), a fixed queue - set per-device - is still used for internal I/Os. If all the CPUs mapped to that queue are offlined, then the completions for that queue are not serviced and any internal I/Os will time out. Fix by selecting a queue for internal I/Os from the queue mapped from the current CPU in this scenario. This is still not ideal as it does not deal with CPU hotplug for inflight internal I/Os, and needs proper support from [0]. [0] https://lore.kernel.org/linux-scsi/20200703130122.111448-1-hare@suse.de/T/#m7d77d049b18f33a24ef206af69ebb66d07440556 Link: https://lore.kernel.org/r/1607347855-59091-1-git-send-email-john.garry@huawei.com Fixes: 8d98416a55eb ("scsi: hisi_sas: Switch v3 hw to MQ") Signed-off-by: Xiang Chen Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- drivers/scsi/hisi_sas/hisi_sas_main.c | 6 ++++++ drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 5 +++++ 2 files changed, 11 insertions(+) diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index c8dd8588f800..274ccf18ce2d 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -452,6 +452,12 @@ static int hisi_sas_task_prep(struct sas_task *task, blk_tag = blk_mq_unique_tag(scmd->request); dq_index = blk_mq_unique_tag_to_hwq(blk_tag); *dq_pointer = dq = &hisi_hba->dq[dq_index]; + } else if (hisi_hba->shost->nr_hw_queues) { + struct Scsi_Host *shost = hisi_hba->shost; + struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; + int queue = qmap->mq_map[raw_smp_processor_id()]; + + *dq_pointer = dq = &hisi_hba->dq[queue]; } else { *dq_pointer = dq = sas_dev->dq; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 7133ca859b5e..960de375ce69 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2452,6 +2452,11 @@ static int interrupt_init_v3_hw(struct hisi_hba *hisi_hba) rc = -ENOENT; goto free_irq_vectors; } + cq->irq_mask = pci_irq_get_affinity(pdev, i + BASE_VECTORS_V3_HW); + if (!cq->irq_mask) { + dev_err(dev, "could not get cq%d irq affinity!\n", i); + return -ENOENT; + } } return 0; -- cgit v1.2.3 From 3d1387b3b8f6cc1ccdbb5f0d7af24df02f4baef9 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 8 Dec 2020 07:57:13 +0100 Subject: media: vidtv: fix some warnings As reported by sparse: drivers/media/test-drivers/vidtv/vidtv_ts.h:47:47: warning: array of flexible structures drivers/media/test-drivers/vidtv/vidtv_channel.c:458:54: warning: incorrect type in argument 3 (different base types) drivers/media/test-drivers/vidtv/vidtv_channel.c:458:54: expected unsigned short [usertype] service_id drivers/media/test-drivers/vidtv/vidtv_channel.c:458:54: got restricted __be16 [usertype] service_id drivers/media/test-drivers/vidtv/vidtv_s302m.c:471 vidtv_s302m_encoder_init() warn: possible memory leak of 'e' Address such warnings. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/test-drivers/vidtv/vidtv_psi.h | 2 +- drivers/media/test-drivers/vidtv/vidtv_s302m.c | 4 +++- drivers/media/test-drivers/vidtv/vidtv_ts.h | 2 +- 3 files changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index 6651cc91bda1..fdc825e54138 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -743,7 +743,7 @@ struct vidtv_psi_table_eit { struct vidtv_psi_table_eit *vidtv_psi_eit_table_init(u16 network_id, u16 transport_stream_id, - u16 service_id); + __be16 service_id); /** * struct vidtv_psi_eit_write_args - Arguments for writing an EIT section diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.c b/drivers/media/test-drivers/vidtv/vidtv_s302m.c index ce7dd6cafc8b..d79b65854627 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.c +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.c @@ -467,8 +467,10 @@ struct vidtv_encoder e->is_video_encoder = false; ctx = kzalloc(priv_sz, GFP_KERNEL); - if (!ctx) + if (!ctx) { + kfree(e); return NULL; + } e->ctx = ctx; ctx->last_duration = 0; diff --git a/drivers/media/test-drivers/vidtv/vidtv_ts.h b/drivers/media/test-drivers/vidtv/vidtv_ts.h index 10838a2b8389..f5e8e1f37f05 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_ts.h +++ b/drivers/media/test-drivers/vidtv/vidtv_ts.h @@ -44,7 +44,7 @@ struct vidtv_mpeg_ts { u8 adaptation_field:1; u8 scrambling:2; } __packed; - struct vidtv_mpeg_ts_adaption adaption[]; + struct vidtv_mpeg_ts_adaption *adaption; } __packed; /** -- cgit v1.2.3 From 7aeb353802611a8e655e019f09a370ff682af1a6 Mon Sep 17 00:00:00 2001 From: Andrew Jeffery Date: Thu, 26 Nov 2020 17:03:37 +1030 Subject: pinctrl: aspeed: Fix GPIO requests on pass-through banks Commit 6726fbff19bf ("pinctrl: aspeed: Fix GPI only function problem.") fixes access to GPIO banks T and U on the AST2600. Both banks contain input-only pins and the GPIO pin function is named GPITx and GPIUx respectively. Unfortunately the fix had a negative impact on GPIO banks D and E for the AST2400 and AST2500 where the GPIO pass-through functions take similar "GPI"-style names. The net effect on the older SoCs was that when the GPIO subsystem requested a pin in banks D or E be muxed for GPIO, they were instead muxed for pass-through mode. Mistakenly muxing pass-through mode e.g. breaks booting the host on IBM's Witherspoon (AC922) platform where GPIOE0 is used for FSI. Further exploit the names in the provided expression structure to differentiate pass-through from pin-specific GPIO modes. This follow-up fix gives the expected behaviour for the following tests: Witherspoon BMC (AST2500): 1. Power-on the Witherspoon host 2. Request GPIOD1 be muxed via /sys/class/gpio/export 3. Request GPIOE1 be muxed via /sys/class/gpio/export 4. Request the balls for GPIOs E2 and E3 be muxed as GPIO pass-through ("GPIE2" mode) via a pinctrl hog in the devicetree Rainier BMC (AST2600): 5. Request GPIT0 be muxed via /sys/class/gpio/export 6. Request GPIU0 be muxed via /sys/class/gpio/export Together the tests demonstrate that all three pieces of functionality (general GPIOs via 1, 2 and 3, input-only GPIOs via 5 and 6, pass-through mode via 4) operate as desired across old and new SoCs. Fixes: 9b92f5c51e9a ("pinctrl: aspeed: Fix GPI only function problem.") Signed-off-by: Andrew Jeffery Tested-by: Joel Stanley Reviewed-by: Joel Stanley Cc: Billy Tsai Cc: Joel Stanley Link: https://lore.kernel.org/r/20201126063337.489927-1-andrew@aj.id.au Signed-off-by: Linus Walleij --- drivers/pinctrl/aspeed/pinctrl-aspeed.c | 74 ++++++++++++++++++++++++++++++--- drivers/pinctrl/aspeed/pinmux-aspeed.h | 7 ++-- 2 files changed, 72 insertions(+), 9 deletions(-) diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c index d6b849552a1e..9c65d560d48f 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c @@ -286,14 +286,76 @@ int aspeed_pinmux_set_mux(struct pinctrl_dev *pctldev, unsigned int function, static bool aspeed_expr_is_gpio(const struct aspeed_sig_expr *expr) { /* - * The signal type is GPIO if the signal name has "GPI" as a prefix. - * strncmp (rather than strcmp) is used to implement the prefix - * requirement. + * We need to differentiate between GPIO and non-GPIO signals to + * implement the gpio_request_enable() interface. For better or worse + * the ASPEED pinctrl driver uses the expression names to determine + * whether an expression will mux a pin for GPIO. * - * expr->signal might look like "GPIOB1" in the GPIO case. - * expr->signal might look like "GPIT0" in the GPI case. + * Generally we have the following - A GPIO such as B1 has: + * + * - expr->signal set to "GPIOB1" + * - expr->function set to "GPIOB1" + * + * Using this fact we can determine whether the provided expression is + * a GPIO expression by testing the signal name for the string prefix + * "GPIO". + * + * However, some GPIOs are input-only, and the ASPEED datasheets name + * them differently. An input-only GPIO such as T0 has: + * + * - expr->signal set to "GPIT0" + * - expr->function set to "GPIT0" + * + * It's tempting to generalise the prefix test from "GPIO" to "GPI" to + * account for both GPIOs and GPIs, but in doing so we run aground on + * another feature: + * + * Some pins in the ASPEED BMC SoCs have a "pass-through" GPIO + * function where the input state of one pin is replicated as the + * output state of another (as if they were shorted together - a mux + * configuration that is typically enabled by hardware strapping). + * This feature allows the BMC to pass e.g. power button state through + * to the host while the BMC is yet to boot, but take control of the + * button state once the BMC has booted by muxing each pin as a + * separate, pin-specific GPIO. + * + * Conceptually this pass-through mode is a form of GPIO and is named + * as such in the datasheets, e.g. "GPID0". This naming similarity + * trips us up with the simple GPI-prefixed-signal-name scheme + * discussed above, as the pass-through configuration is not what we + * want when muxing a pin as GPIO for the GPIO subsystem. + * + * On e.g. the AST2400, a pass-through function "GPID0" is grouped on + * balls A18 and D16, where we have: + * + * For ball A18: + * - expr->signal set to "GPID0IN" + * - expr->function set to "GPID0" + * + * For ball D16: + * - expr->signal set to "GPID0OUT" + * - expr->function set to "GPID0" + * + * By contrast, the pin-specific GPIO expressions for the same pins are + * as follows: + * + * For ball A18: + * - expr->signal looks like "GPIOD0" + * - expr->function looks like "GPIOD0" + * + * For ball D16: + * - expr->signal looks like "GPIOD1" + * - expr->function looks like "GPIOD1" + * + * Testing both the signal _and_ function names gives us the means + * differentiate the pass-through GPIO pinmux configuration from the + * pin-specific configuration that the GPIO subsystem is after: An + * expression is a pin-specific (non-pass-through) GPIO configuration + * if the signal prefix is "GPI" and the signal name matches the + * function name. */ - return strncmp(expr->signal, "GPI", 3) == 0; + return !strncmp(expr->signal, "GPI", 3) && + !strcmp(expr->signal, expr->function); } static bool aspeed_gpio_in_exprs(const struct aspeed_sig_expr **exprs) diff --git a/drivers/pinctrl/aspeed/pinmux-aspeed.h b/drivers/pinctrl/aspeed/pinmux-aspeed.h index f86739e800c3..dba5875ff276 100644 --- a/drivers/pinctrl/aspeed/pinmux-aspeed.h +++ b/drivers/pinctrl/aspeed/pinmux-aspeed.h @@ -452,10 +452,11 @@ struct aspeed_sig_desc { * evaluation of the descriptors. * * @signal: The signal name for the priority level on the pin. If the signal - * type is GPIO, then the signal name must begin with the string - * "GPIO", e.g. GPIOA0, GPIOT4 etc. + * type is GPIO, then the signal name must begin with the + * prefix "GPI", e.g. GPIOA0, GPIT0 etc. * @function: The name of the function the signal participates in for the - * associated expression + * associated expression. For pin-specific GPIO, the function + * name must match the signal name. * @ndescs: The number of signal descriptors in the expression * @descs: Pointer to an array of signal descriptors that comprise the * function expression -- cgit v1.2.3 From cc00bcaa589914096edef7fb87ca5cee4a166b5c Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Wed, 25 Nov 2020 11:27:22 -0700 Subject: netfilter: x_tables: Switch synchronization to RCU When running concurrent iptables rules replacement with data, the per CPU sequence count is checked after the assignment of the new information. The sequence count is used to synchronize with the packet path without the use of any explicit locking. If there are any packets in the packet path using the table information, the sequence count is incremented to an odd value and is incremented to an even after the packet process completion. The new table value assignment is followed by a write memory barrier so every CPU should see the latest value. If the packet path has started with the old table information, the sequence counter will be odd and the iptables replacement will wait till the sequence count is even prior to freeing the old table info. However, this assumes that the new table information assignment and the memory barrier is actually executed prior to the counter check in the replacement thread. If CPU decides to execute the assignment later as there is no user of the table information prior to the sequence check, the packet path in another CPU may use the old table information. The replacement thread would then free the table information under it leading to a use after free in the packet processing context- Unable to handle kernel NULL pointer dereference at virtual address 000000000000008e pc : ip6t_do_table+0x5d0/0x89c lr : ip6t_do_table+0x5b8/0x89c ip6t_do_table+0x5d0/0x89c ip6table_filter_hook+0x24/0x30 nf_hook_slow+0x84/0x120 ip6_input+0x74/0xe0 ip6_rcv_finish+0x7c/0x128 ipv6_rcv+0xac/0xe4 __netif_receive_skb+0x84/0x17c process_backlog+0x15c/0x1b8 napi_poll+0x88/0x284 net_rx_action+0xbc/0x23c __do_softirq+0x20c/0x48c This could be fixed by forcing instruction order after the new table information assignment or by switching to RCU for the synchronization. Fixes: 80055dab5de0 ("netfilter: x_tables: make xt_replace_table wait until old rules are not used anymore") Reported-by: Sean Tranchetti Reported-by: kernel test robot Suggested-by: Florian Westphal Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 5 +++- net/ipv4/netfilter/arp_tables.c | 14 +++++------ net/ipv4/netfilter/ip_tables.c | 14 +++++------ net/ipv6/netfilter/ip6_tables.c | 14 +++++------ net/netfilter/x_tables.c | 49 ++++++++++++-------------------------- 5 files changed, 40 insertions(+), 56 deletions(-) diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 5deb099d156d..8ebb64193757 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -227,7 +227,7 @@ struct xt_table { unsigned int valid_hooks; /* Man behind the curtain... */ - struct xt_table_info *private; + struct xt_table_info __rcu *private; /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; @@ -448,6 +448,9 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); +struct xt_table_info +*xt_table_get_private_protected(const struct xt_table *table); + #ifdef CONFIG_COMPAT #include diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index d1e04d2b5170..563b62b76a5f 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -203,7 +203,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); - private = READ_ONCE(table->private); /* Address dependency. */ + private = rcu_access_pointer(table->private); cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct arpt_entry **)private->jumpstack[cpu]; @@ -649,7 +649,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); /* We need atomic snapshot of counters: rest doesn't change * (other than comefrom, which userspace doesn't care @@ -673,7 +673,7 @@ static int copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct arpt_entry *e; struct xt_counters *counters; - struct xt_table_info *private = table->private; + struct xt_table_info *private = xt_table_get_private_protected(table); int ret = 0; void *loc_cpu_entry; @@ -807,7 +807,7 @@ static int get_info(struct net *net, void __user *user, const int *len) t = xt_request_find_table_lock(net, NFPROTO_ARP, name); if (!IS_ERR(t)) { struct arpt_getinfo info; - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); #ifdef CONFIG_COMPAT struct xt_table_info tmp; @@ -860,7 +860,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr, t = xt_find_table_lock(net, NFPROTO_ARP, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); if (get.size == private->size) ret = copy_entries_to_user(private->size, @@ -1017,7 +1017,7 @@ static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) } local_bh_disable(); - private = t->private; + private = xt_table_get_private_protected(t); if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1330,7 +1330,7 @@ static int compat_copy_entries_to_user(unsigned int total_size, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); void __user *pos; unsigned int size; int ret = 0; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index f15bc21d7301..6e2851f8d3a3 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -258,7 +258,7 @@ ipt_do_table(struct sk_buff *skb, WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); - private = READ_ONCE(table->private); /* Address dependency. */ + private = rcu_access_pointer(table->private); cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; @@ -791,7 +791,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -815,7 +815,7 @@ copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct ipt_entry *e; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); int ret = 0; const void *loc_cpu_entry; @@ -964,7 +964,7 @@ static int get_info(struct net *net, void __user *user, const int *len) t = xt_request_find_table_lock(net, AF_INET, name); if (!IS_ERR(t)) { struct ipt_getinfo info; - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); #ifdef CONFIG_COMPAT struct xt_table_info tmp; @@ -1018,7 +1018,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr, t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); @@ -1173,7 +1173,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len) } local_bh_disable(); - private = t->private; + private = xt_table_get_private_protected(t); if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1543,7 +1543,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); void __user *pos; unsigned int size; int ret = 0; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 2e2119bfcf13..c4f532f4d311 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -280,7 +280,7 @@ ip6t_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); - private = READ_ONCE(table->private); /* Address dependency. */ + private = rcu_access_pointer(table->private); cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; @@ -807,7 +807,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -831,7 +831,7 @@ copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct ip6t_entry *e; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); int ret = 0; const void *loc_cpu_entry; @@ -980,7 +980,7 @@ static int get_info(struct net *net, void __user *user, const int *len) t = xt_request_find_table_lock(net, AF_INET6, name); if (!IS_ERR(t)) { struct ip6t_getinfo info; - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); #ifdef CONFIG_COMPAT struct xt_table_info tmp; @@ -1035,7 +1035,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr, t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { - struct xt_table_info *private = t->private; + struct xt_table_info *private = xt_table_get_private_protected(t); if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); @@ -1189,7 +1189,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len) } local_bh_disable(); - private = t->private; + private = xt_table_get_private_protected(t); if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1552,7 +1552,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); void __user *pos; unsigned int size; int ret = 0; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index af22dbe85e2c..acce622582e3 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1349,6 +1349,14 @@ struct xt_counters *xt_counters_alloc(unsigned int counters) } EXPORT_SYMBOL(xt_counters_alloc); +struct xt_table_info +*xt_table_get_private_protected(const struct xt_table *table) +{ + return rcu_dereference_protected(table->private, + mutex_is_locked(&xt[table->af].mutex)); +} +EXPORT_SYMBOL(xt_table_get_private_protected); + struct xt_table_info * xt_replace_table(struct xt_table *table, unsigned int num_counters, @@ -1356,7 +1364,6 @@ xt_replace_table(struct xt_table *table, int *error) { struct xt_table_info *private; - unsigned int cpu; int ret; ret = xt_jumpstack_alloc(newinfo); @@ -1366,47 +1373,20 @@ xt_replace_table(struct xt_table *table, } /* Do the substitution. */ - local_bh_disable(); - private = table->private; + private = xt_table_get_private_protected(table); /* Check inside lock: is the old number correct? */ if (num_counters != private->number) { pr_debug("num_counters != table->private->number (%u/%u)\n", num_counters, private->number); - local_bh_enable(); *error = -EAGAIN; return NULL; } newinfo->initial_entries = private->initial_entries; - /* - * Ensure contents of newinfo are visible before assigning to - * private. - */ - smp_wmb(); - table->private = newinfo; - - /* make sure all cpus see new ->private value */ - smp_wmb(); - /* - * Even though table entries have now been swapped, other CPU's - * may still be using the old entries... - */ - local_bh_enable(); - - /* ... so wait for even xt_recseq on all cpus */ - for_each_possible_cpu(cpu) { - seqcount_t *s = &per_cpu(xt_recseq, cpu); - u32 seq = raw_read_seqcount(s); - - if (seq & 1) { - do { - cond_resched(); - cpu_relax(); - } while (seq == raw_read_seqcount(s)); - } - } + rcu_assign_pointer(table->private, newinfo); + synchronize_rcu(); audit_log_nfcfg(table->name, table->af, private->number, !private->number ? AUDIT_XT_OP_REGISTER : @@ -1442,12 +1422,12 @@ struct xt_table *xt_register_table(struct net *net, } /* Simplifies replace_table code. */ - table->private = bootstrap; + rcu_assign_pointer(table->private, bootstrap); if (!xt_replace_table(table, 0, newinfo, &ret)) goto unlock; - private = table->private; + private = xt_table_get_private_protected(table); pr_debug("table->private->number = %u\n", private->number); /* save number of initial entries */ @@ -1470,7 +1450,8 @@ void *xt_unregister_table(struct xt_table *table) struct xt_table_info *private; mutex_lock(&xt[table->af].mutex); - private = table->private; + private = xt_table_get_private_protected(table); + RCU_INIT_POINTER(table->private, NULL); list_del(&table->list); mutex_unlock(&xt[table->af].mutex); audit_log_nfcfg(table->name, table->af, private->number, -- cgit v1.2.3 From 352ded44fbd8622670ff95e90ca732a5b036ce79 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 3 Dec 2020 11:45:17 +0300 Subject: drm/i915/gem: Check the correct variable in selftest There is a copy and paste bug in this code. It's supposed to check "obj2" instead of checking "obj" a second time. Fixes: 80f0b679d6f0 ("drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.") Signed-off-by: Dan Carpenter Reviewed-by: Chris Wilson Reviewed-by: Andi Shyti Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/8ilneOcJAjwqU4t@mwand (cherry picked from commit 14f2d7604f7ce4cb3d303aea17292d119dfafa75) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/selftests/i915_gem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c index 23a6132c5f4e..412e21604a05 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem.c @@ -211,8 +211,8 @@ static int igt_gem_ww_ctx(void *arg) return PTR_ERR(obj); obj2 = i915_gem_object_create_internal(i915, PAGE_SIZE); - if (IS_ERR(obj)) { - err = PTR_ERR(obj); + if (IS_ERR(obj2)) { + err = PTR_ERR(obj2); goto put1; } -- cgit v1.2.3 From 0e124e19ce52d20b28ee9f1d5cdb22e2106bfd29 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 3 Dec 2020 10:34:32 +0000 Subject: drm/i915/gem: Propagate error from cancelled submit due to context closure In the course of discovering and closing many races with context closure and execbuf submission, since commit 61231f6bd056 ("drm/i915/gem: Check that the context wasn't closed during setup") we started checking that the context was not closed by another userspace thread during the execbuf ioctl. In doing so we cancelled the inflight request (by telling it to be skipped), but kept reporting success since we do submit a request, albeit one that doesn't execute. As the error is known before we return from the ioctl, we can report the error we detect immediately, rather than leave it on the fence status. With the immediate propagation of the error, it is easier for userspace to handle. Fixes: 61231f6bd056 ("drm/i915/gem: Check that the context wasn't closed during setup") Testcase: igt/gem_ctx_exec/basic-close-race Signed-off-by: Chris Wilson Cc: # v5.7+ Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20201203103432.31526-1-chris@chris-wilson.co.uk (cherry picked from commit ba38b79eaeaeed29d2383f122d5c711ebf5ed3d1) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 1904e6e5ea64..b07dc1156a0e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -3097,7 +3097,7 @@ static void retire_requests(struct intel_timeline *tl, struct i915_request *end) break; } -static void eb_request_add(struct i915_execbuffer *eb) +static int eb_request_add(struct i915_execbuffer *eb, int err) { struct i915_request *rq = eb->request; struct intel_timeline * const tl = i915_request_timeline(rq); @@ -3118,6 +3118,7 @@ static void eb_request_add(struct i915_execbuffer *eb) /* Serialise with context_close via the add_to_timeline */ i915_request_set_error_once(rq, -ENOENT); __i915_request_skip(rq); + err = -ENOENT; /* override any transient errors */ } __i915_request_queue(rq, &attr); @@ -3127,6 +3128,8 @@ static void eb_request_add(struct i915_execbuffer *eb) retire_requests(tl, prev); mutex_unlock(&tl->mutex); + + return err; } static const i915_user_extension_fn execbuf_extensions[] = { @@ -3332,7 +3335,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, err = eb_submit(&eb, batch); err_request: i915_request_get(eb.request); - eb_request_add(&eb); + err = eb_request_add(&eb, err); if (eb.fences) signal_fence_array(&eb); -- cgit v1.2.3 From 5419d93ffd774127b195b8543b063b2b4fa5aea9 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 4 Dec 2020 15:12:31 +0000 Subject: drm/i915/gt: Ignore repeated attempts to suspend request flow across reset Before reseting the engine, we suspend the execution of the guilty request, so that we can continue execution with a new context while we slowly compress the captured error state for the guilty context. However, if the reset fails, we will promptly attempt to reset the same request again, and discover the ongoing capture. Ignore the second attempt to suspend and capture the same request. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/1168 Fixes: 32ff621fd744 ("drm/i915/gt: Allow temporary suspension of inflight requests") Signed-off-by: Chris Wilson Cc: # v5.7+ Reviewed-by: Mika Kuoppala Link: https://patchwork.freedesktop.org/patch/msgid/20201204151234.19729-1-chris@chris-wilson.co.uk (cherry picked from commit b969540500bce60cf1cdfff5464388af32b9a553) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_lrc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 0952bf157234..03fd1fa42a75 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -2788,6 +2788,9 @@ static void __execlists_hold(struct i915_request *rq) static bool execlists_hold(struct intel_engine_cs *engine, struct i915_request *rq) { + if (i915_request_on_hold(rq)) + return false; + spin_lock_irq(&engine->active.lock); if (i915_request_completed(rq)) { /* too late! */ -- cgit v1.2.3 From 0fe8bf4d3edce7aad6c14b9d5d92ff54dc19f0ba Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 4 Dec 2020 15:12:32 +0000 Subject: drm/i915/gt: Cancel the preemption timeout on responding to it We currently presume that the engine reset is successful, cancelling the expired preemption timer in the process. However, engine resets can fail, leaving the timeout still pending and we will then respond to the timeout again next time the tasklet fires. What we want is for the failed engine reset to be promoted to a full device reset, which is kicked by the heartbeat once the engine stops processing events. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/1168 Fixes: 3a7a92aba8fb ("drm/i915/execlists: Force preemption") Signed-off-by: Chris Wilson Cc: # v5.5+ Reviewed-by: Mika Kuoppala Link: https://patchwork.freedesktop.org/patch/msgid/20201204151234.19729-2-chris@chris-wilson.co.uk (cherry picked from commit d997e240ceecb4f732611985d3a939ad1bfc1893) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_lrc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 03fd1fa42a75..724b2cb897d3 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -3172,8 +3172,10 @@ static void execlists_submission_tasklet(unsigned long data) spin_unlock_irqrestore(&engine->active.lock, flags); /* Recheck after serialising with direct-submission */ - if (unlikely(timeout && preempt_timeout(engine))) + if (unlikely(timeout && preempt_timeout(engine))) { + cancel_timer(&engine->execlists.preempt); execlists_reset(engine, "preemption time out"); + } } } -- cgit v1.2.3 From 88c52d805eb61da99aa4607fb5131f41c0ff6bd4 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 2 Oct 2020 18:03:54 +0100 Subject: drm/i915: fix size_t greater or equal to zero comparison Currently the check that the unsigned size_t variable i is >= 0 is always true because the unsigned variable will never be negative, causing the loop to run forever. Fix this by changing the pre-decrement check to a zero check on i followed by a decrement of i. Addresses-Coverity: ("Unsigned compared against 0") Fixes: bfed6708d6c9 ("drm/i915: use vmap in shmem_pin_map") Signed-off-by: Colin Ian King Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20201002170354.94627-1-colin.king@canonical.com (cherry picked from commit e70956a2498dc81d8f2522cba074f55ae910e13c) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/shmem_utils.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c index 463af675fadd..5982b62f913d 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.c +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c @@ -73,7 +73,7 @@ void *shmem_pin_map(struct file *file) mapping_set_unevictable(file->f_mapping); return vaddr; err_page: - while (--i >= 0) + while (i--) put_page(pages[i]); kvfree(pages); return NULL; -- cgit v1.2.3 From f6cbe49be65ed800863ac5ba695555057363f9c2 Mon Sep 17 00:00:00 2001 From: Manasi Navare Date: Fri, 4 Dec 2020 12:58:04 -0800 Subject: drm/i915/display/dp: Compute the correct slice count for VDSC on DP This patch fixes the slice count computation algorithm for calculating the slice count based on Peak pixel rate and the max slice width allowed on the DSC engines. We need to ensure slice count > min slice count req as per DP spec based on peak pixel rate and that it is greater than min slice count based on the max slice width advertised by DPCD. So use max of these two. In the prev patch we were using min of these 2 causing it to violate the max slice width limitation causing a blank screen on 8K@60. Fixes: d9218c8f6cf4 ("drm/i915/dp: Add helpers for Compressed BPP and Slice Count for DSC") Cc: Ankit Nautiyal Cc: Jani Nikula Cc: # v5.0+ Signed-off-by: Manasi Navare Reviewed-by: Ankit Nautiyal Link: https://patchwork.freedesktop.org/patch/msgid/20201204205804.25225-1-manasi.d.navare@intel.com (cherry picked from commit d371d6ea92ad2a47f42bbcaa786ee5f6069c9c14) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/display/intel_dp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index bf1e9cf1c0f3..9bc59fd2f95f 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -573,7 +573,7 @@ static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, return 0; } /* Also take into account max slice width */ - min_slice_count = min_t(u8, min_slice_count, + min_slice_count = max_t(u8, min_slice_count, DIV_ROUND_UP(mode_hdisplay, max_slice_width)); -- cgit v1.2.3 From 7c5c15dffe1e3c42f44735ce9552afb7207f1584 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 27 Nov 2020 10:25:40 +0000 Subject: drm/i915/gt: Declare gen9 has 64 mocs entries! We checked the table size against a hardcoded number of entries, and that number was excluding the special mocs registers at the end. Fixes: 777a7717d60c ("drm/i915/gt: Program mocs:63 for cache eviction on gen9") Signed-off-by: Chris Wilson Cc: # v4.3+ Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20201127102540.13117-1-chris@chris-wilson.co.uk (cherry picked from commit 444fbf5d7058099447c5366ba8bb60d610aeb44b) Signed-off-by: Rodrigo Vivi [backported and updated the Fixes sha] --- drivers/gpu/drm/i915/gt/intel_mocs.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index 4f74706967fd..413dadfac2d1 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -59,8 +59,7 @@ struct drm_i915_mocs_table { #define _L3_CACHEABILITY(value) ((value) << 4) /* Helper defines */ -#define GEN9_NUM_MOCS_ENTRIES 62 /* 62 out of 64 - 63 & 64 are reserved. */ -#define GEN11_NUM_MOCS_ENTRIES 64 /* 63-64 are reserved, but configured. */ +#define GEN9_NUM_MOCS_ENTRIES 64 /* 63-64 are reserved, but configured. */ /* (e)LLC caching options */ /* @@ -328,11 +327,11 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915, if (INTEL_GEN(i915) >= 12) { table->size = ARRAY_SIZE(tgl_mocs_table); table->table = tgl_mocs_table; - table->n_entries = GEN11_NUM_MOCS_ENTRIES; + table->n_entries = GEN9_NUM_MOCS_ENTRIES; } else if (IS_GEN(i915, 11)) { table->size = ARRAY_SIZE(icl_mocs_table); table->table = icl_mocs_table; - table->n_entries = GEN11_NUM_MOCS_ENTRIES; + table->n_entries = GEN9_NUM_MOCS_ENTRIES; } else if (IS_GEN9_BC(i915) || IS_CANNONLAKE(i915)) { table->size = ARRAY_SIZE(skl_mocs_table); table->n_entries = GEN9_NUM_MOCS_ENTRIES; -- cgit v1.2.3 From 932c60558109a9131e54dacfda6070147fd1cdfb Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 4 Dec 2020 15:20:01 -0800 Subject: tools/bpftool: Fix PID fetching with a lot of results In case of having so many PID results that they don't fit into a singe page (4096) bytes, bpftool will erroneously conclude that it got corrupted data due to 4096 not being a multiple of struct pid_iter_entry, so the last entry will be partially truncated. Fix this by sizing the buffer to fit exactly N entries with no truncation in the middle of record. Fixes: d53dee3fe013 ("tools/bpftool: Show info for processes holding BPF map/prog/link/btf FDs") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20201204232002.3589803-1-andrii@kernel.org --- tools/bpf/bpftool/pids.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c index df7d8ec76036..477e55d59c34 100644 --- a/tools/bpf/bpftool/pids.c +++ b/tools/bpf/bpftool/pids.c @@ -89,9 +89,9 @@ libbpf_print_none(__maybe_unused enum libbpf_print_level level, int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type) { - char buf[4096]; - struct pid_iter_bpf *skel; struct pid_iter_entry *e; + char buf[4096 / sizeof(*e) * sizeof(*e)]; + struct pid_iter_bpf *skel; int err, ret, fd = -1, i; libbpf_print_fn_t default_print; -- cgit v1.2.3 From f26c08b444df833b19c00838a530d93963ce9cd0 Mon Sep 17 00:00:00 2001 From: Hillf Danton Date: Tue, 8 Dec 2020 08:54:26 -0700 Subject: io_uring: fix file leak on error path of io ctx creation Put file as part of error handling when setting up io ctx to fix memory leaks like the following one. BUG: memory leak unreferenced object 0xffff888101ea2200 (size 256): comm "syz-executor355", pid 8470, jiffies 4294953658 (age 32.400s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 20 59 03 01 81 88 ff ff 80 87 a8 10 81 88 ff ff Y.............. backtrace: [<000000002e0a7c5f>] kmem_cache_zalloc include/linux/slab.h:654 [inline] [<000000002e0a7c5f>] __alloc_file+0x1f/0x130 fs/file_table.c:101 [<000000001a55b73a>] alloc_empty_file+0x69/0x120 fs/file_table.c:151 [<00000000fb22349e>] alloc_file+0x33/0x1b0 fs/file_table.c:193 [<000000006e1465bb>] alloc_file_pseudo+0xb2/0x140 fs/file_table.c:233 [<000000007118092a>] anon_inode_getfile fs/anon_inodes.c:91 [inline] [<000000007118092a>] anon_inode_getfile+0xaa/0x120 fs/anon_inodes.c:74 [<000000002ae99012>] io_uring_get_fd fs/io_uring.c:9198 [inline] [<000000002ae99012>] io_uring_create fs/io_uring.c:9377 [inline] [<000000002ae99012>] io_uring_setup+0x1125/0x1630 fs/io_uring.c:9411 [<000000008280baad>] do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 [<00000000685d8cf0>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Reported-by: syzbot+71c4697e27c99fddcf17@syzkaller.appspotmail.com Fixes: 0f2122045b94 ("io_uring: don't rely on weak ->files references") Cc: Pavel Begunkov Signed-off-by: Hillf Danton Signed-off-by: Jens Axboe --- fs/io_uring.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 908817cea4f5..86dac2b2e276 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -9183,6 +9183,7 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx) { struct file *file; int ret; + int fd; #if defined(CONFIG_UNIX) ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP, @@ -9194,12 +9195,12 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx) ret = get_unused_fd_flags(O_RDWR | O_CLOEXEC); if (ret < 0) goto err; + fd = ret; file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx, O_RDWR | O_CLOEXEC); if (IS_ERR(file)) { -err_fd: - put_unused_fd(ret); + put_unused_fd(fd); ret = PTR_ERR(file); goto err; } @@ -9207,12 +9208,14 @@ err_fd: #if defined(CONFIG_UNIX) ctx->ring_sock->file = file; #endif - if (unlikely(io_uring_add_task_file(ctx, file))) { - file = ERR_PTR(-ENOMEM); - goto err_fd; + ret = io_uring_add_task_file(ctx, file); + if (ret) { + fput(file); + put_unused_fd(fd); + goto err; } - fd_install(ret, file); - return ret; + fd_install(fd, file); + return fd; err: #if defined(CONFIG_UNIX) sock_release(ctx->ring_sock); -- cgit v1.2.3 From 007ab5345545aba2f9cbe4c096cc35d2fd3275ac Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Sat, 5 Dec 2020 12:22:29 -0500 Subject: bonding: fix feature flag setting at init time Don't try to adjust XFRM support flags if the bond device isn't yet registered. Bad things can currently happen when netdev_change_features() is called without having wanted_features fully filled in yet. This code runs both on post-module-load mode changes, as well as at module init time, and when run at module init time, it is before register_netdevice() has been called and filled in wanted_features. The empty wanted_features led to features also getting emptied out, which was definitely not the intended behavior, so prevent that from happening. Originally, I'd hoped to stop adjusting wanted_features at all in the bonding driver, as it's documented as being something only the network core should touch, but we actually do need to do this to properly update both the features and wanted_features fields when changing the bond type, or we get to a situation where ethtool sees: esp-hw-offload: off [requested on] I do think we should be using netdev_update_features instead of netdev_change_features here though, so we only send notifiers when the features actually changed. Fixes: a3b658cfb664 ("bonding: allow xfrm offload setup post-module-load") Reported-by: Ivan Vecera Suggested-by: Ivan Vecera Cc: Jay Vosburgh Cc: Veaceslav Falico Cc: Andy Gospodarek Signed-off-by: Jarod Wilson Link: https://lore.kernel.org/r/20201205172229.576587-1-jarod@redhat.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_options.c | 22 +++++++++++++++------- include/net/bonding.h | 2 -- 2 files changed, 15 insertions(+), 9 deletions(-) diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 9abfaae1c6f7..a4e4e15f574d 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -745,6 +745,19 @@ const struct bond_option *bond_opt_get(unsigned int option) return &bond_opts[option]; } +static void bond_set_xfrm_features(struct net_device *bond_dev, u64 mode) +{ + if (!IS_ENABLED(CONFIG_XFRM_OFFLOAD)) + return; + + if (mode == BOND_MODE_ACTIVEBACKUP) + bond_dev->wanted_features |= BOND_XFRM_FEATURES; + else + bond_dev->wanted_features &= ~BOND_XFRM_FEATURES; + + netdev_update_features(bond_dev); +} + static int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newval) { @@ -767,13 +780,8 @@ static int bond_option_mode_set(struct bonding *bond, if (newval->value == BOND_MODE_ALB) bond->params.tlb_dynamic_lb = 1; -#ifdef CONFIG_XFRM_OFFLOAD - if (newval->value == BOND_MODE_ACTIVEBACKUP) - bond->dev->wanted_features |= BOND_XFRM_FEATURES; - else - bond->dev->wanted_features &= ~BOND_XFRM_FEATURES; - netdev_change_features(bond->dev); -#endif /* CONFIG_XFRM_OFFLOAD */ + if (bond->dev->reg_state == NETREG_REGISTERED) + bond_set_xfrm_features(bond->dev, newval->value); /* don't cache arp_validate between modes */ bond->params.arp_validate = BOND_ARP_VALIDATE_NONE; diff --git a/include/net/bonding.h b/include/net/bonding.h index d9d0ff3b0ad3..adc3da776970 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -86,10 +86,8 @@ #define bond_for_each_slave_rcu(bond, pos, iter) \ netdev_for_each_lower_private_rcu((bond)->dev, pos, iter) -#ifdef CONFIG_XFRM_OFFLOAD #define BOND_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) -#endif /* CONFIG_XFRM_OFFLOAD */ #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; -- cgit v1.2.3 From 917d80d376ffbaa9725fde9e3c0282f63643f278 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 8 Dec 2020 18:25:53 +0100 Subject: netfilter: nft_dynset: fix timeouts later than 23 days Use nf_msecs_to_jiffies64 and nf_jiffies64_to_msecs as provided by 8e1102d5a159 ("netfilter: nf_tables: support timeouts larger than 23 days"), otherwise ruleset listing breaks. Fixes: a8b1e36d0d1d ("netfilter: nft_dynset: fix element timeout for HZ != 1000") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 4 ++++ net/netfilter/nf_tables_api.c | 4 ++-- net/netfilter/nft_dynset.c | 8 +++++--- 3 files changed, 11 insertions(+), 5 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 55b4cadf290a..c1c0a4ff92ae 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1524,4 +1524,8 @@ void __init nft_chain_route_init(void); void nft_chain_route_fini(void); void nf_tables_trans_destroy_flush_work(void); + +int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result); +__be64 nf_jiffies64_to_msecs(u64 input); + #endif /* _NET_NF_TABLES_H */ diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 23abf1578594..c2f59879a48d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3719,7 +3719,7 @@ cont: return 0; } -static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) +int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) { u64 ms = be64_to_cpu(nla_get_be64(nla)); u64 max = (u64)(~((u64)0)); @@ -3733,7 +3733,7 @@ static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) return 0; } -static __be64 nf_jiffies64_to_msecs(u64 input) +__be64 nf_jiffies64_to_msecs(u64 input) { return cpu_to_be64(jiffies64_to_msecs(input)); } diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 64ca13a1885b..9af4f93c7f0e 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -157,8 +157,10 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (tb[NFTA_DYNSET_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( - tb[NFTA_DYNSET_TIMEOUT]))); + + err = nf_msecs_to_jiffies64(tb[NFTA_DYNSET_TIMEOUT], &timeout); + if (err) + return err; } priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]); @@ -267,7 +269,7 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) if (nla_put_string(skb, NFTA_DYNSET_SET_NAME, priv->set->name)) goto nla_put_failure; if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT, - cpu_to_be64(jiffies_to_msecs(priv->timeout)), + nf_jiffies64_to_msecs(priv->timeout), NFTA_DYNSET_PAD)) goto nla_put_failure; if (priv->expr && nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr)) -- cgit v1.2.3 From 42f1c27120906a54e73101a7d6a12f58813f6a9f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 8 Dec 2020 18:57:02 +0100 Subject: netfilter: nftables: comment indirect serialization of commit_mutex with rtnl_mutex Add an explicit comment in the code to describe the indirect serialization of the holders of the commit_mutex with the rtnl_mutex. Commit 90d2723c6d4c ("netfilter: nf_tables: do not hold reference on netdevice from preparation phase") already describes this, but a comment in this case is better for reference. Reported-by: Vladimir Oltean Reviewed-by: Vladimir Oltean Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c2f59879a48d..9a080767667b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1723,6 +1723,10 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, } nla_strlcpy(ifname, attr, IFNAMSIZ); + /* nf_tables_netdev_event() is called under rtnl_mutex, this is + * indirectly serializing all the other holders of the commit_mutex with + * the rtnl_mutex. + */ dev = __dev_get_by_name(net, ifname); if (!dev) { err = -ENOENT; -- cgit v1.2.3 From 6220e48d9640538ff700f2e7d24c2f9277555fd6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 8 Dec 2020 16:37:47 -0500 Subject: [regression fix] really dumb fuckup in sparc64 __csum_partial_copy() changes ~0U is -1, not 1 Reported-by: Anatoly Pugachev Tested-by: Anatoly Pugachev Fixes: fdf8bee96f9a "sparc64: propagate the calling convention changes down to __csum_partial_copy_...()" X-brown-paperbag: yes Signed-off-by: Al Viro --- arch/sparc/lib/csum_copy.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sparc/lib/csum_copy.S b/arch/sparc/lib/csum_copy.S index 0c0268e77155..d839956407a7 100644 --- a/arch/sparc/lib/csum_copy.S +++ b/arch/sparc/lib/csum_copy.S @@ -71,7 +71,7 @@ FUNC_NAME: /* %o0=src, %o1=dst, %o2=len */ LOAD(prefetch, %o0 + 0x000, #n_reads) xor %o0, %o1, %g1 - mov 1, %o3 + mov -1, %o3 clr %o4 andcc %g1, 0x3, %g0 bne,pn %icc, 95f -- cgit v1.2.3 From 9d14edfdeabf37d8d8f045e63e5873712aadcd6b Mon Sep 17 00:00:00 2001 From: Fugang Duan Date: Mon, 7 Dec 2020 18:51:37 +0800 Subject: net: stmmac: increase the timeout for dma reset Current timeout value is not enough for gmac5 dma reset on imx8mp platform, increase the timeout range. Signed-off-by: Fugang Duan Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index 6e30d7eb4983..0b4ee2dbb691 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -22,7 +22,7 @@ int dwmac4_dma_reset(void __iomem *ioaddr) return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value, !(value & DMA_BUS_MODE_SFT_RESET), - 10000, 100000); + 10000, 1000000); } void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan) -- cgit v1.2.3 From 36d18b5664ef617ccf4da266291d2f2342fab89d Mon Sep 17 00:00:00 2001 From: Fugang Duan Date: Mon, 7 Dec 2020 18:51:38 +0800 Subject: net: stmmac: start phylink instance before stmmac_hw_setup() Start phylink instance and resume back the PHY to supply RX clock to MAC before MAC layer initialization by calling .stmmac_hw_setup(), since DMA reset depends on the RX clock, otherwise DMA reset cost maximum timeout value then finally timeout. Fixes: 74371272f97f ("net: stmmac: Convert to phylink and remove phylib logic") Signed-off-by: Fugang Duan Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ba45fe237512..0cef414f1289 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5247,6 +5247,14 @@ int stmmac_resume(struct device *dev) return ret; } + if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { + rtnl_lock(); + phylink_start(priv->phylink); + /* We may have called phylink_speed_down before */ + phylink_speed_up(priv->phylink); + rtnl_unlock(); + } + rtnl_lock(); mutex_lock(&priv->lock); @@ -5265,14 +5273,6 @@ int stmmac_resume(struct device *dev) mutex_unlock(&priv->lock); rtnl_unlock(); - if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { - rtnl_lock(); - phylink_start(priv->phylink); - /* We may have called phylink_speed_down before */ - phylink_speed_up(priv->phylink); - rtnl_unlock(); - } - phylink_mac_change(priv->phylink, true); netif_device_attach(ndev); -- cgit v1.2.3 From 4ec236c7c51f89abb0224a4da4a6b77f9beb6600 Mon Sep 17 00:00:00 2001 From: Fugang Duan Date: Mon, 7 Dec 2020 18:51:39 +0800 Subject: net: stmmac: free tx skb buffer in stmmac_resume() When do suspend/resume test, there have WARN_ON() log dump from stmmac_xmit() funciton, the code logic: entry = tx_q->cur_tx; first_entry = entry; WARN_ON(tx_q->tx_skbuff[first_entry]); In normal case, tx_q->tx_skbuff[txq->cur_tx] should be NULL because the skb should be handled and freed in stmmac_tx_clean(). But stmmac_resume() reset queue parameters like below, skb buffers may not be freed. tx_q->cur_tx = 0; tx_q->dirty_tx = 0; So free tx skb buffer in stmmac_resume() to avoid warning and memory leak. log: [ 46.139824] ------------[ cut here ]------------ [ 46.144453] WARNING: CPU: 0 PID: 0 at drivers/net/ethernet/stmicro/stmmac/stmmac_main.c:3235 stmmac_xmit+0x7a0/0x9d0 [ 46.154969] Modules linked in: crct10dif_ce vvcam(O) flexcan can_dev [ 46.161328] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G O 5.4.24-2.1.0+g2ad925d15481 #1 [ 46.170369] Hardware name: NXP i.MX8MPlus EVK board (DT) [ 46.175677] pstate: 80000005 (Nzcv daif -PAN -UAO) [ 46.180465] pc : stmmac_xmit+0x7a0/0x9d0 [ 46.184387] lr : dev_hard_start_xmit+0x94/0x158 [ 46.188913] sp : ffff800010003cc0 [ 46.192224] x29: ffff800010003cc0 x28: ffff000177e2a100 [ 46.197533] x27: ffff000176ef0840 x26: ffff000176ef0090 [ 46.202842] x25: 0000000000000000 x24: 0000000000000000 [ 46.208151] x23: 0000000000000003 x22: ffff8000119ddd30 [ 46.213460] x21: ffff00017636f000 x20: ffff000176ef0cc0 [ 46.218769] x19: 0000000000000003 x18: 0000000000000000 [ 46.224078] x17: 0000000000000000 x16: 0000000000000000 [ 46.229386] x15: 0000000000000079 x14: 0000000000000000 [ 46.234695] x13: 0000000000000003 x12: 0000000000000003 [ 46.240003] x11: 0000000000000010 x10: 0000000000000010 [ 46.245312] x9 : ffff00017002b140 x8 : 0000000000000000 [ 46.250621] x7 : ffff00017636f000 x6 : 0000000000000010 [ 46.255930] x5 : 0000000000000001 x4 : ffff000176ef0000 [ 46.261238] x3 : 0000000000000003 x2 : 00000000ffffffff [ 46.266547] x1 : ffff000177e2a000 x0 : 0000000000000000 [ 46.271856] Call trace: [ 46.274302] stmmac_xmit+0x7a0/0x9d0 [ 46.277874] dev_hard_start_xmit+0x94/0x158 [ 46.282056] sch_direct_xmit+0x11c/0x338 [ 46.285976] __qdisc_run+0x118/0x5f0 [ 46.289549] net_tx_action+0x110/0x198 [ 46.293297] __do_softirq+0x120/0x23c [ 46.296958] irq_exit+0xb8/0xd8 [ 46.300098] __handle_domain_irq+0x64/0xb8 [ 46.304191] gic_handle_irq+0x5c/0x148 [ 46.307936] el1_irq+0xb8/0x180 [ 46.311076] cpuidle_enter_state+0x84/0x360 [ 46.315256] cpuidle_enter+0x34/0x48 [ 46.318829] call_cpuidle+0x18/0x38 [ 46.322314] do_idle+0x1e0/0x280 [ 46.325539] cpu_startup_entry+0x24/0x40 [ 46.329460] rest_init+0xd4/0xe0 [ 46.332687] arch_call_rest_init+0xc/0x14 [ 46.336695] start_kernel+0x420/0x44c [ 46.340353] ---[ end trace bc1ee695123cbacd ]--- Fixes: 47dd7a540b8a0 ("net: add support for STMicroelectronics Ethernet controllers.") Signed-off-by: Fugang Duan Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 0cef414f1289..7452f3c1cab9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1533,6 +1533,19 @@ static void dma_free_tx_skbufs(struct stmmac_priv *priv, u32 queue) stmmac_free_tx_buffer(priv, queue, i); } +/** + * stmmac_free_tx_skbufs - free TX skb buffers + * @priv: private structure + */ +static void stmmac_free_tx_skbufs(struct stmmac_priv *priv) +{ + u32 tx_queue_cnt = priv->plat->tx_queues_to_use; + u32 queue; + + for (queue = 0; queue < tx_queue_cnt; queue++) + dma_free_tx_skbufs(priv, queue); +} + /** * free_dma_rx_desc_resources - free RX dma desc resources * @priv: private structure @@ -5260,6 +5273,7 @@ int stmmac_resume(struct device *dev) stmmac_reset_queues_param(priv); + stmmac_free_tx_skbufs(priv); stmmac_clear_descriptors(priv); stmmac_hw_setup(ndev, false); -- cgit v1.2.3 From 5f58591323bf3f342920179f24515935c4b5fd60 Mon Sep 17 00:00:00 2001 From: Fugang Duan Date: Mon, 7 Dec 2020 18:51:40 +0800 Subject: net: stmmac: delete the eee_ctrl_timer after napi disabled There have chance to re-enable the eee_ctrl_timer and fire the timer in napi callback after delete the timer in .stmmac_release(), which introduces to access eee registers in the timer function after clocks are disabled then causes system hang. Found this issue when do suspend/resume and reboot stress test. It is safe to delete the timer after napi disabled and disable lpi mode. Fixes: d765955d2ae0b ("stmmac: add the Energy Efficient Ethernet support") Signed-off-by: Fugang Duan Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7452f3c1cab9..d2521ebb8217 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2908,9 +2908,6 @@ static int stmmac_release(struct net_device *dev) struct stmmac_priv *priv = netdev_priv(dev); u32 chan; - if (priv->eee_enabled) - del_timer_sync(&priv->eee_ctrl_timer); - if (device_may_wakeup(priv->device)) phylink_speed_down(priv->phylink, false); /* Stop and disconnect the PHY */ @@ -2929,6 +2926,11 @@ static int stmmac_release(struct net_device *dev) if (priv->lpi_irq > 0) free_irq(priv->lpi_irq, dev); + if (priv->eee_enabled) { + priv->tx_path_in_lpi_mode = false; + del_timer_sync(&priv->eee_ctrl_timer); + } + /* Stop TX/RX DMA and clear the descriptors */ stmmac_stop_all_dma(priv); @@ -5155,6 +5157,11 @@ int stmmac_suspend(struct device *dev) for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++) del_timer_sync(&priv->tx_queue[chan].txtimer); + if (priv->eee_enabled) { + priv->tx_path_in_lpi_mode = false; + del_timer_sync(&priv->eee_ctrl_timer); + } + /* Stop TX/RX DMA */ stmmac_stop_all_dma(priv); -- cgit v1.2.3 From f119cc9818eb33b66e977ad3af75aef6500bbdc3 Mon Sep 17 00:00:00 2001 From: Fugang Duan Date: Mon, 7 Dec 2020 18:51:41 +0800 Subject: net: stmmac: overwrite the dma_cap.addr64 according to HW design The current IP register MAC_HW_Feature1[ADDR64] only defines 32/40/64 bit width, but some SOCs support others like i.MX8MP support 34 bits but it maps to 40 bits width in MAC_HW_Feature1[ADDR64]. So overwrite dma_cap.addr64 according to HW real design. Fixes: 94abdad6974a ("net: ethernet: dwmac: add ethernet glue logic for NXP imx8 chip") Signed-off-by: Fugang Duan Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c | 9 +-------- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 8 ++++++++ include/linux/stmmac.h | 1 + 3 files changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index efef5476a577..223f69da7e95 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -246,13 +246,7 @@ static int imx_dwmac_probe(struct platform_device *pdev) goto err_parse_dt; } - ret = dma_set_mask_and_coherent(&pdev->dev, - DMA_BIT_MASK(dwmac->ops->addr_width)); - if (ret) { - dev_err(&pdev->dev, "DMA mask set failed\n"); - goto err_dma_mask; - } - + plat_dat->addr64 = dwmac->ops->addr_width; plat_dat->init = imx_dwmac_init; plat_dat->exit = imx_dwmac_exit; plat_dat->fix_mac_speed = imx_dwmac_fix_speed; @@ -272,7 +266,6 @@ static int imx_dwmac_probe(struct platform_device *pdev) err_dwmac_init: err_drv_probe: imx_dwmac_exit(pdev, plat_dat->bsp_priv); -err_dma_mask: err_parse_dt: err_match_data: stmmac_remove_config_dt(pdev, plat_dat); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d2521ebb8217..c33db79cdd0a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4945,6 +4945,14 @@ int stmmac_dvr_probe(struct device *device, dev_info(priv->device, "SPH feature enabled\n"); } + /* The current IP register MAC_HW_Feature1[ADDR64] only define + * 32/40/64 bit width, but some SOC support others like i.MX8MP + * support 34 bits but it map to 40 bits width in MAC_HW_Feature1[ADDR64]. + * So overwrite dma_cap.addr64 according to HW real design. + */ + if (priv->plat->addr64) + priv->dma_cap.addr64 = priv->plat->addr64; + if (priv->dma_cap.addr64) { ret = dma_set_mask_and_coherent(device, DMA_BIT_MASK(priv->dma_cap.addr64)); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 628e28903b8b..15ca6b4167cc 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -170,6 +170,7 @@ struct plat_stmmacenet_data { int unicast_filter_entries; int tx_fifo_size; int rx_fifo_size; + u32 addr64; u32 rx_queues_to_use; u32 tx_queues_to_use; u8 rx_sched_algorithm; -- cgit v1.2.3 From 1a0e1943d8798cb3241fb5edb9a836af1611b60a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 8 Dec 2020 15:00:36 -0800 Subject: Revert "scsi: megaraid_sas: Added support for shared host tagset for cpuhotplug" This reverts commit 103fbf8e4020845e4fcf63819288cedb092a3c91. It turns out that it causes long boot-time latencies (to the point of timeouts and failed boots). The cause is the increase in request queues, and a fix for that is queued up for 5.11, but we're reverting this commit that triggered the problem for now. Reported-and-tested-by: John Garry Reported-and-tested-by: Julia Lawall Reported-by: Qian Cai Acked-by: Jens Axboe Acked-by: Martin K. Petersen Link: https://lore.kernel.org/linux-scsi/fe3dff7dae4494e5a88caffbb4d877bbf472dceb.camel@redhat.com/ Link: https://lore.kernel.org/lkml/alpine.DEB.2.22.394.2012081813310.2680@hadrien/ Link: https://lore.kernel.org/linux-block/20201203012638.543321-1-ming.lei@redhat.com/ Signed-off-by: Linus Torvalds --- drivers/scsi/megaraid/megaraid_sas_base.c | 39 ----------------------------- drivers/scsi/megaraid/megaraid_sas_fusion.c | 29 ++++++++++----------- 2 files changed, 13 insertions(+), 55 deletions(-) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 41cd66fc7d81..e158d3d62056 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -37,7 +37,6 @@ #include #include #include -#include #include #include @@ -114,10 +113,6 @@ unsigned int enable_sdev_max_qd; module_param(enable_sdev_max_qd, int, 0444); MODULE_PARM_DESC(enable_sdev_max_qd, "Enable sdev max qd as can_queue. Default: 0"); -int host_tagset_enable = 1; -module_param(host_tagset_enable, int, 0444); -MODULE_PARM_DESC(host_tagset_enable, "Shared host tagset enable/disable Default: enable(1)"); - MODULE_LICENSE("GPL"); MODULE_VERSION(MEGASAS_VERSION); MODULE_AUTHOR("megaraidlinux.pdl@broadcom.com"); @@ -3124,19 +3119,6 @@ megasas_bios_param(struct scsi_device *sdev, struct block_device *bdev, return 0; } -static int megasas_map_queues(struct Scsi_Host *shost) -{ - struct megasas_instance *instance; - - instance = (struct megasas_instance *)shost->hostdata; - - if (shost->nr_hw_queues == 1) - return 0; - - return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], - instance->pdev, instance->low_latency_index_start); -} - static void megasas_aen_polling(struct work_struct *work); /** @@ -3445,7 +3427,6 @@ static struct scsi_host_template megasas_template = { .eh_timed_out = megasas_reset_timer, .shost_attrs = megaraid_host_attrs, .bios_param = megasas_bios_param, - .map_queues = megasas_map_queues, .change_queue_depth = scsi_change_queue_depth, .max_segment_size = 0xffffffff, }; @@ -6827,26 +6808,6 @@ static int megasas_io_attach(struct megasas_instance *instance) host->max_lun = MEGASAS_MAX_LUN; host->max_cmd_len = 16; - /* Use shared host tagset only for fusion adaptors - * if there are managed interrupts (smp affinity enabled case). - * Single msix_vectors in kdump, so shared host tag is also disabled. - */ - - host->host_tagset = 0; - host->nr_hw_queues = 1; - - if ((instance->adapter_type != MFI_SERIES) && - (instance->msix_vectors > instance->low_latency_index_start) && - host_tagset_enable && - instance->smp_affinity_enable) { - host->host_tagset = 1; - host->nr_hw_queues = instance->msix_vectors - - instance->low_latency_index_start; - } - - dev_info(&instance->pdev->dev, - "Max firmware commands: %d shared with nr_hw_queues = %d\n", - instance->max_fw_cmds, host->nr_hw_queues); /* * Notify the mid-layer about the new controller */ diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index fd607287608e..b0c01cf0428f 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -359,29 +359,24 @@ megasas_get_msix_index(struct megasas_instance *instance, { int sdev_busy; - /* TBD - if sml remove device_busy in future, driver - * should track counter in internal structure. - */ - sdev_busy = atomic_read(&scmd->device->device_busy); + /* nr_hw_queue = 1 for MegaRAID */ + struct blk_mq_hw_ctx *hctx = + scmd->device->request_queue->queue_hw_ctx[0]; + + sdev_busy = atomic_read(&hctx->nr_active); if (instance->perf_mode == MR_BALANCED_PERF_MODE && - sdev_busy > (data_arms * MR_DEVICE_HIGH_IOPS_DEPTH)) { + sdev_busy > (data_arms * MR_DEVICE_HIGH_IOPS_DEPTH)) cmd->request_desc->SCSIIO.MSIxIndex = mega_mod64((atomic64_add_return(1, &instance->high_iops_outstanding) / MR_HIGH_IOPS_BATCH_COUNT), instance->low_latency_index_start); - } else if (instance->msix_load_balance) { + else if (instance->msix_load_balance) cmd->request_desc->SCSIIO.MSIxIndex = (mega_mod64(atomic64_add_return(1, &instance->total_io_count), instance->msix_vectors)); - } else if (instance->host->nr_hw_queues > 1) { - u32 tag = blk_mq_unique_tag(scmd->request); - - cmd->request_desc->SCSIIO.MSIxIndex = blk_mq_unique_tag_to_hwq(tag) + - instance->low_latency_index_start; - } else { + else cmd->request_desc->SCSIIO.MSIxIndex = instance->reply_map[raw_smp_processor_id()]; - } } /** @@ -961,6 +956,9 @@ megasas_alloc_cmds_fusion(struct megasas_instance *instance) if (megasas_alloc_cmdlist_fusion(instance)) goto fail_exit; + dev_info(&instance->pdev->dev, "Configured max firmware commands: %d\n", + instance->max_fw_cmds); + /* The first 256 bytes (SMID 0) is not used. Don't add to the cmd list */ io_req_base = fusion->io_request_frames + MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE; io_req_base_phys = fusion->io_request_frames_phys + MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE; @@ -1104,9 +1102,8 @@ megasas_ioc_init_fusion(struct megasas_instance *instance) MR_HIGH_IOPS_QUEUE_COUNT) && cur_intr_coalescing) instance->perf_mode = MR_BALANCED_PERF_MODE; - dev_info(&instance->pdev->dev, "Performance mode :%s (latency index = %d)\n", - MEGASAS_PERF_MODE_2STR(instance->perf_mode), - instance->low_latency_index_start); + dev_info(&instance->pdev->dev, "Performance mode :%s\n", + MEGASAS_PERF_MODE_2STR(instance->perf_mode)); instance->fw_sync_cache_support = (scratch_pad_1 & MR_CAN_HANDLE_SYNC_CACHE_OFFSET) ? 1 : 0; -- cgit v1.2.3 From 0398ba9e5a4b5675aa571e0445689d3c2e499c2d Mon Sep 17 00:00:00 2001 From: Cengiz Can Date: Mon, 7 Dec 2020 11:14:24 +0300 Subject: net: tipc: prevent possible null deref of link `tipc_node_apply_property` does a null check on a `tipc_link_entry` pointer but also accesses the same pointer out of the null check block. This triggers a warning on Coverity Static Analyzer because we're implying that `e->link` can BE null. Move "Update MTU for node link entry" line into if block to make sure that we're not in a state that `e->link` is null. Signed-off-by: Cengiz Can Signed-off-by: David S. Miller --- net/tipc/node.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/tipc/node.c b/net/tipc/node.c index c95d037fde51..83978d5dae59 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2181,9 +2181,11 @@ void tipc_node_apply_property(struct net *net, struct tipc_bearer *b, &xmitq); else if (prop == TIPC_NLA_PROP_MTU) tipc_link_set_mtu(e->link, b->mtu); + + /* Update MTU for node link entry */ + e->mtu = tipc_link_mss(e->link); } - /* Update MTU for node link entry */ - e->mtu = tipc_link_mss(e->link); + tipc_node_write_unlock(n); tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr, NULL); } -- cgit v1.2.3 From 4cb682964706deffb4861f0a91329ab3a705039f Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 8 Dec 2020 23:52:03 +0000 Subject: afs: Fix memory leak when mounting with multiple source parameters There's a memory leak in afs_parse_source() whereby multiple source= parameters overwrite fc->source in the fs_context struct without freeing the previously recorded source. Fix this by only permitting a single source parameter and rejecting with an error all subsequent ones. This was caught by syzbot with the kernel memory leak detector, showing something like the following trace: unreferenced object 0xffff888114375440 (size 32): comm "repro", pid 5168, jiffies 4294923723 (age 569.948s) backtrace: slab_post_alloc_hook+0x42/0x79 __kmalloc_track_caller+0x125/0x16a kmemdup_nul+0x24/0x3c vfs_parse_fs_string+0x5a/0xa1 generic_parse_monolithic+0x9d/0xc5 do_new_mount+0x10d/0x15a do_mount+0x5f/0x8e __do_sys_mount+0xff/0x127 do_syscall_64+0x2d/0x3a entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 13fcc6837049 ("afs: Add fs_context support") Reported-by: syzbot+86dc6632faaca40133ab@syzkaller.appspotmail.com Signed-off-by: David Howells cc: Randy Dunlap Signed-off-by: Linus Torvalds --- fs/afs/super.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/afs/super.c b/fs/afs/super.c index 6c5900df6aa5..e38bb1e7a4d2 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -230,6 +230,9 @@ static int afs_parse_source(struct fs_context *fc, struct fs_parameter *param) _enter(",%s", name); + if (fc->source) + return invalf(fc, "kAFS: Multiple sources not supported"); + if (!name) { printk(KERN_ERR "kAFS: no volume name specified\n"); return -EINVAL; -- cgit v1.2.3 From cc6596fc7295e9dcd78156ed42f9f8e1221f7530 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Tue, 8 Dec 2020 09:53:42 +0800 Subject: net: ll_temac: Fix potential NULL dereference in temac_probe() platform_get_resource() may fail and in this case a NULL dereference will occur. Fix it to use devm_platform_ioremap_resource() instead of calling platform_get_resource() and devm_ioremap(). This is detected by Coccinelle semantic patch. @@ expression pdev, res, n, t, e, e1, e2; @@ res = \(platform_get_resource\|platform_get_resource_byname\)(pdev, t, n); + if (!res) + return -EINVAL; ... when != res == NULL e = devm_ioremap(e1, res->start, e2); Fixes: 8425c41d1ef7 ("net: ll_temac: Extend support to non-device-tree platforms") Signed-off-by: Zhang Changzhong Acked-by: Esben Haabendal Signed-off-by: David S. Miller --- drivers/net/ethernet/xilinx/ll_temac_main.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 60c199fcb91e..030185301014 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1351,7 +1351,6 @@ static int temac_probe(struct platform_device *pdev) struct device_node *temac_np = dev_of_node(&pdev->dev), *dma_np; struct temac_local *lp; struct net_device *ndev; - struct resource *res; const void *addr; __be32 *p; bool little_endian; @@ -1500,13 +1499,11 @@ static int temac_probe(struct platform_device *pdev) of_node_put(dma_np); } else if (pdata) { /* 2nd memory resource specifies DMA registers */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - lp->sdma_regs = devm_ioremap(&pdev->dev, res->start, - resource_size(res)); - if (!lp->sdma_regs) { + lp->sdma_regs = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(lp->sdma_regs)) { dev_err(&pdev->dev, "could not map DMA registers\n"); - return -ENOMEM; + return PTR_ERR(lp->sdma_regs); } if (pdata->dma_little_endian) { lp->dma_in = temac_dma_in32_le; -- cgit v1.2.3 From 72d05c00d7ecda85df29abd046da7e41cc071c17 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 8 Dec 2020 08:21:31 -0800 Subject: tcp: select sane initial rcvq_space.space for big MSS Before commit a337531b942b ("tcp: up initial rmem to 128KB and SYN rwin to around 64KB") small tcp_rmem[1] values were overridden by tcp_fixup_rcvbuf() to accommodate various MSS. This is no longer the case, and Hazem Mohamed Abuelfotoh reported that DRS would not work for MTU 9000 endpoints receiving regular (1500 bytes) frames. Root cause is that tcp_init_buffer_space() uses tp->rcv_wnd for upper limit of rcvq_space.space computation, while it can select later a smaller value for tp->rcv_ssthresh and tp->window_clamp. ss -temoi on receiver would show : skmem:(r0,rb131072,t0,tb46080,f0,w0,o0,bl0,d0) rcv_space:62496 rcv_ssthresh:56596 This means that TCP can not increase its window in tcp_grow_window(), and that DRS can never kick. Fix this by making sure that rcvq_space.space is not bigger than number of bytes that can be held in TCP receive queue. People unable/unwilling to change their kernel can work around this issue by selecting a bigger tcp_rmem[1] value as in : echo "4096 196608 6291456" >/proc/sys/net/ipv4/tcp_rmem Based on an initial report and patch from Hazem Mohamed Abuelfotoh https://lore.kernel.org/netdev/20201204180622.14285-1-abuehaze@amazon.com/ Fixes: a337531b942b ("tcp: up initial rmem to 128KB and SYN rwin to around 64KB") Fixes: 041a14d26715 ("tcp: start receiver buffer autotuning sooner") Reported-by: Hazem Mohamed Abuelfotoh Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 389d1b340248..ef4bdb038a4b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -510,7 +510,6 @@ static void tcp_init_buffer_space(struct sock *sk) if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) tcp_sndbuf_expand(sk); - tp->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND * tp->advmss); tcp_mstamp_refresh(tp); tp->rcvq_space.time = tp->tcp_mstamp; tp->rcvq_space.seq = tp->copied_seq; @@ -534,6 +533,8 @@ static void tcp_init_buffer_space(struct sock *sk) tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp); tp->snd_cwnd_stamp = tcp_jiffies32; + tp->rcvq_space.space = min3(tp->rcv_ssthresh, tp->rcv_wnd, + (u32)TCP_INIT_CWND * tp->advmss); } /* 4. Recalculate window clamp after socket hit its memory bounds. */ -- cgit v1.2.3 From b62527005d46d52b4733cbc57f2f9b514b673ed9 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 8 Dec 2020 22:49:00 +0100 Subject: bpf, doc: Update KP's email in MAINTAINERS Helps me use a single account to sign off and send patches use appropriate email redirection without needing to update MAINTAINERS. Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201208214900.80684-1-kpsingh@kernel.org --- MAINTAINERS | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 98f0bd050ff5..ba63f61e4ef1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3237,7 +3237,7 @@ R: Martin KaFai Lau R: Song Liu R: Yonghong Song R: John Fastabend -R: KP Singh +R: KP Singh L: netdev@vger.kernel.org L: bpf@vger.kernel.org S: Supported @@ -3356,7 +3356,7 @@ F: arch/x86/net/ X: arch/x86/net/bpf_jit_comp32.c BPF LSM (Security Audit and Enforcement using BPF) -M: KP Singh +M: KP Singh R: Florent Revest R: Brendan Jackman L: bpf@vger.kernel.org -- cgit v1.2.3 From 0e830d2872cf6e75ef6619edd23050ddf3673358 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 1 Dec 2020 17:44:58 -0500 Subject: drm/amdgpu/powerplay: parse fan table for CI asics Set up all the parameters required for SMU fan control if supported. Bug: https://bugzilla.kernel.org/show_bug.cgi?id=201539 Acked-by: Evan Quan Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- .../drm/amd/pm/powerplay/hwmgr/processpptables.c | 103 ++++++++++++++++++++- 1 file changed, 102 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c index 719597c5d27d..6606511891e3 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c @@ -24,6 +24,8 @@ #include #include #include +#include + #include #include "processpptables.h" #include @@ -984,6 +986,8 @@ static int init_thermal_controller( struct pp_hwmgr *hwmgr, const ATOM_PPLIB_POWERPLAYTABLE *powerplay_table) { + struct amdgpu_device *adev = hwmgr->adev; + hwmgr->thermal_controller.ucType = powerplay_table->sThermalController.ucType; hwmgr->thermal_controller.ucI2cLine = @@ -1008,7 +1012,104 @@ static int init_thermal_controller( ATOM_PP_THERMALCONTROLLER_NONE != hwmgr->thermal_controller.ucType, PHM_PlatformCaps_ThermalController); - hwmgr->thermal_controller.use_hw_fan_control = 1; + if (powerplay_table->usTableSize >= sizeof(ATOM_PPLIB_POWERPLAYTABLE3)) { + const ATOM_PPLIB_POWERPLAYTABLE3 *powerplay_table3 = + (const ATOM_PPLIB_POWERPLAYTABLE3 *)powerplay_table; + + if (0 == le16_to_cpu(powerplay_table3->usFanTableOffset)) { + hwmgr->thermal_controller.use_hw_fan_control = 1; + return 0; + } else { + const ATOM_PPLIB_FANTABLE *fan_table = + (const ATOM_PPLIB_FANTABLE *)(((unsigned long)powerplay_table) + + le16_to_cpu(powerplay_table3->usFanTableOffset)); + + if (1 <= fan_table->ucFanTableFormat) { + hwmgr->thermal_controller.advanceFanControlParameters.ucTHyst = + fan_table->ucTHyst; + hwmgr->thermal_controller.advanceFanControlParameters.usTMin = + le16_to_cpu(fan_table->usTMin); + hwmgr->thermal_controller.advanceFanControlParameters.usTMed = + le16_to_cpu(fan_table->usTMed); + hwmgr->thermal_controller.advanceFanControlParameters.usTHigh = + le16_to_cpu(fan_table->usTHigh); + hwmgr->thermal_controller.advanceFanControlParameters.usPWMMin = + le16_to_cpu(fan_table->usPWMMin); + hwmgr->thermal_controller.advanceFanControlParameters.usPWMMed = + le16_to_cpu(fan_table->usPWMMed); + hwmgr->thermal_controller.advanceFanControlParameters.usPWMHigh = + le16_to_cpu(fan_table->usPWMHigh); + hwmgr->thermal_controller.advanceFanControlParameters.usTMax = 10900; + hwmgr->thermal_controller.advanceFanControlParameters.ulCycleDelay = 100000; + + phm_cap_set(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_MicrocodeFanControl); + } + + if (2 <= fan_table->ucFanTableFormat) { + const ATOM_PPLIB_FANTABLE2 *fan_table2 = + (const ATOM_PPLIB_FANTABLE2 *)(((unsigned long)powerplay_table) + + le16_to_cpu(powerplay_table3->usFanTableOffset)); + hwmgr->thermal_controller.advanceFanControlParameters.usTMax = + le16_to_cpu(fan_table2->usTMax); + } + + if (3 <= fan_table->ucFanTableFormat) { + const ATOM_PPLIB_FANTABLE3 *fan_table3 = + (const ATOM_PPLIB_FANTABLE3 *) (((unsigned long)powerplay_table) + + le16_to_cpu(powerplay_table3->usFanTableOffset)); + + hwmgr->thermal_controller.advanceFanControlParameters.ucFanControlMode = + fan_table3->ucFanControlMode; + + if ((3 == fan_table->ucFanTableFormat) && + (0x67B1 == adev->pdev->device)) + hwmgr->thermal_controller.advanceFanControlParameters.usDefaultMaxFanPWM = + 47; + else + hwmgr->thermal_controller.advanceFanControlParameters.usDefaultMaxFanPWM = + le16_to_cpu(fan_table3->usFanPWMMax); + + hwmgr->thermal_controller.advanceFanControlParameters.usDefaultFanOutputSensitivity = + 4836; + hwmgr->thermal_controller.advanceFanControlParameters.usFanOutputSensitivity = + le16_to_cpu(fan_table3->usFanOutputSensitivity); + } + + if (6 <= fan_table->ucFanTableFormat) { + const ATOM_PPLIB_FANTABLE4 *fan_table4 = + (const ATOM_PPLIB_FANTABLE4 *)(((unsigned long)powerplay_table) + + le16_to_cpu(powerplay_table3->usFanTableOffset)); + + phm_cap_set(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_FanSpeedInTableIsRPM); + + hwmgr->thermal_controller.advanceFanControlParameters.usDefaultMaxFanRPM = + le16_to_cpu(fan_table4->usFanRPMMax); + } + + if (7 <= fan_table->ucFanTableFormat) { + const ATOM_PPLIB_FANTABLE5 *fan_table5 = + (const ATOM_PPLIB_FANTABLE5 *)(((unsigned long)powerplay_table) + + le16_to_cpu(powerplay_table3->usFanTableOffset)); + + if (0x67A2 == adev->pdev->device || + 0x67A9 == adev->pdev->device || + 0x67B9 == adev->pdev->device) { + phm_cap_set(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_GeminiRegulatorFanControlSupport); + hwmgr->thermal_controller.advanceFanControlParameters.usFanCurrentLow = + le16_to_cpu(fan_table5->usFanCurrentLow); + hwmgr->thermal_controller.advanceFanControlParameters.usFanCurrentHigh = + le16_to_cpu(fan_table5->usFanCurrentHigh); + hwmgr->thermal_controller.advanceFanControlParameters.usFanRPMLow = + le16_to_cpu(fan_table5->usFanRPMLow); + hwmgr->thermal_controller.advanceFanControlParameters.usFanRPMHigh = + le16_to_cpu(fan_table5->usFanRPMHigh); + } + } + } + } return 0; } -- cgit v1.2.3 From a68a0262abdaa251e12c53715f48e698a18ef402 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 8 Dec 2020 20:57:18 -0800 Subject: mm/madvise: remove racy mm ownership check Jann spotted the security hole due to race of mm ownership check. If the task is sharing the mm_struct but goes through execve() before mm_access(), it could skip process_madvise_behavior_valid check. That makes *any advice hint* to reach into the remote process. This patch removes the mm ownership check. With it, it will lose the ability that local process could give *any* advice hint with vector interface for some reason (e.g., performance). Since there is no concrete example in upstream yet, it would be better to remove the abiliity at this moment and need to review when such new advice comes up. Fixes: ecb8ac8b1f14 ("mm/madvise: introduce process_madvise() syscall: an external memory hinting API") Reported-by: Jann Horn Suggested-by: Jann Horn Signed-off-by: Minchan Kim Signed-off-by: Linus Torvalds --- mm/madvise.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/mm/madvise.c b/mm/madvise.c index a8d8d48a57fe..13f5677b9322 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -1204,8 +1204,7 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, goto put_pid; } - if (task->mm != current->mm && - !process_madvise_behavior_valid(behavior)) { + if (!process_madvise_behavior_valid(behavior)) { ret = -EINVAL; goto release_task; } -- cgit v1.2.3 From e8873c0afd34beb67ec492cd648dd0095b911f65 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 8 Dec 2020 20:24:03 +0200 Subject: pinctrl: intel: Actually disable Tx and Rx buffers on GPIO request Mistakenly the buffers (input and output) become enabled together for a short period of time during GPIO request. This is problematic, because instead of initial motive to disable them in the commit af7e3eeb84e2 ("pinctrl: intel: Disable input and output buffer when switching to GPIO"), the driven value on the pin, which might be used as an IRQ line, brings firmwares of some touch pads to an awkward state that needs a full power off to recover. Fix this, as stated in the culprit commit, by disabling the buffers. Fixes: af7e3eeb84e2 ("pinctrl: intel: Disable input and output buffer when switching to GPIO") BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=210497 Reported-by: Pierre-Louis Bossart Signed-off-by: Andy Shevchenko Acked-by: Mika Westerberg Tested-by: Pierre-Louis Bossart Tested-by: Kai-Heng Feng Link: https://lore.kernel.org/r/20201208182403.40435-1-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- drivers/pinctrl/intel/pinctrl-intel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 1c10ab184783..b6ef1911c1dd 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -442,8 +442,8 @@ static void intel_gpio_set_gpio_mode(void __iomem *padcfg0) value |= PADCFG0_PMODE_GPIO; /* Disable input and output buffers */ - value &= ~PADCFG0_GPIORXDIS; - value &= ~PADCFG0_GPIOTXDIS; + value |= PADCFG0_GPIORXDIS; + value |= PADCFG0_GPIOTXDIS; /* Disable SCI/SMI/NMI generation */ value &= ~(PADCFG0_GPIROUTIOXAPIC | PADCFG0_GPIROUTSCI); -- cgit v1.2.3 From a493d1ca1a03b532871f1da27f8dbda2b28b04c4 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 3 Dec 2020 21:07:03 -0800 Subject: x86/membarrier: Get rid of a dubious optimization sync_core_before_usermode() had an incorrect optimization. If the kernel returns from an interrupt, it can get to usermode without IRET. It just has to schedule to a different task in the same mm and do SYSRET. Fortunately, there were no callers of sync_core_before_usermode() that could have had in_irq() or in_nmi() equal to true, because it's only ever called from the scheduler. While at it, clarify a related comment. Fixes: 70216e18e519 ("membarrier: Provide core serializing command, *_SYNC_CORE") Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Mathieu Desnoyers Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/5afc7632be1422f91eaf7611aaaa1b5b8580a086.1607058304.git.luto@kernel.org --- arch/x86/include/asm/sync_core.h | 9 +++++---- arch/x86/mm/tlb.c | 10 ++++++++-- 2 files changed, 13 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h index 0fd4a9dfb29c..ab7382f92aff 100644 --- a/arch/x86/include/asm/sync_core.h +++ b/arch/x86/include/asm/sync_core.h @@ -98,12 +98,13 @@ static inline void sync_core_before_usermode(void) /* With PTI, we unconditionally serialize before running user code. */ if (static_cpu_has(X86_FEATURE_PTI)) return; + /* - * Return from interrupt and NMI is done through iret, which is core - * serializing. + * Even if we're in an interrupt, we might reschedule before returning, + * in which case we could switch to a different thread in the same mm + * and return using SYSRET or SYSEXIT. Instead of trying to keep + * track of our need to sync the core, just sync right away. */ - if (in_irq() || in_nmi()) - return; sync_core(); } diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 11666ba19b62..569ac1d57f55 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -474,8 +474,14 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, /* * The membarrier system call requires a full memory barrier and * core serialization before returning to user-space, after - * storing to rq->curr. Writing to CR3 provides that full - * memory barrier and core serializing instruction. + * storing to rq->curr, when changing mm. This is because + * membarrier() sends IPIs to all CPUs that are in the target mm + * to make them issue memory barriers. However, if another CPU + * switches to/from the target mm concurrently with + * membarrier(), it can cause that CPU not to receive an IPI + * when it really should issue a memory barrier. Writing to CR3 + * provides that full memory barrier and core serializing + * instruction. */ if (real_prev == next) { VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != -- cgit v1.2.3 From 2ecedd7569080fd05c1a457e8af2165afecfa29f Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 3 Dec 2020 21:07:04 -0800 Subject: membarrier: Add an actual barrier before rseq_preempt() It seems that most RSEQ membarrier users will expect any stores done before the membarrier() syscall to be visible to the target task(s). While this is extremely likely to be true in practice, nothing actually guarantees it by a strict reading of the x86 manuals. Rather than providing this guarantee by accident and potentially causing a problem down the road, just add an explicit barrier. Fixes: 70216e18e519 ("membarrier: Provide core serializing command, *_SYNC_CORE") Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Mathieu Desnoyers Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/d3e7197e034fa4852afcf370ca49c30496e58e40.1607058304.git.luto@kernel.org --- kernel/sched/membarrier.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index e23e74d52db5..7d98ef5d3bcd 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -40,6 +40,14 @@ static void ipi_mb(void *info) static void ipi_rseq(void *info) { + /* + * Ensure that all stores done by the calling thread are visible + * to the current task before the current task resumes. We could + * probably optimize this away on most architectures, but by the + * time we've already sent an IPI, the cost of the extra smp_mb() + * is negligible. + */ + smp_mb(); rseq_preempt(current); } -- cgit v1.2.3 From 758c9373d84168dc7d039cf85a0e920046b17b41 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 3 Dec 2020 21:07:05 -0800 Subject: membarrier: Explicitly sync remote cores when SYNC_CORE is requested membarrier() does not explicitly sync_core() remote CPUs; instead, it relies on the assumption that an IPI will result in a core sync. On x86, this may be true in practice, but it's not architecturally reliable. In particular, the SDM and APM do not appear to guarantee that interrupt delivery is serializing. While IRET does serialize, IPI return can schedule, thereby switching to another task in the same mm that was sleeping in a syscall. The new task could then SYSRET back to usermode without ever executing IRET. Make this more robust by explicitly calling sync_core_before_usermode() on remote cores. (This also helps people who search the kernel tree for instances of sync_core() and sync_core_before_usermode() -- one might be surprised that the core membarrier code doesn't currently show up in a such a search.) Fixes: 70216e18e519 ("membarrier: Provide core serializing command, *_SYNC_CORE") Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Mathieu Desnoyers Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/776b448d5f7bd6b12690707f5ed67bcda7f1d427.1607058304.git.luto@kernel.org --- kernel/sched/membarrier.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 7d98ef5d3bcd..1c278dff4f2d 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -38,6 +38,23 @@ static void ipi_mb(void *info) smp_mb(); /* IPIs should be serializing but paranoid. */ } +static void ipi_sync_core(void *info) +{ + /* + * The smp_mb() in membarrier after all the IPIs is supposed to + * ensure that memory on remote CPUs that occur before the IPI + * become visible to membarrier()'s caller -- see scenario B in + * the big comment at the top of this file. + * + * A sync_core() would provide this guarantee, but + * sync_core_before_usermode() might end up being deferred until + * after membarrier()'s smp_mb(). + */ + smp_mb(); /* IPIs should be serializing but paranoid. */ + + sync_core_before_usermode(); +} + static void ipi_rseq(void *info) { /* @@ -162,6 +179,7 @@ static int membarrier_private_expedited(int flags, int cpu_id) if (!(atomic_read(&mm->membarrier_state) & MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY)) return -EPERM; + ipi_func = ipi_sync_core; } else if (flags == MEMBARRIER_FLAG_RSEQ) { if (!IS_ENABLED(CONFIG_RSEQ)) return -EINVAL; -- cgit v1.2.3 From e45cdc71d1fa5ac3a57b23acc31eb959e4f60135 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 3 Dec 2020 21:07:06 -0800 Subject: membarrier: Execute SYNC_CORE on the calling thread membarrier()'s MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE is documented as syncing the core on all sibling threads but not necessarily the calling thread. This behavior is fundamentally buggy and cannot be used safely. Suppose a user program has two threads. Thread A is on CPU 0 and thread B is on CPU 1. Thread A modifies some text and calls membarrier(MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE). Then thread B executes the modified code. If, at any point after membarrier() decides which CPUs to target, thread A could be preempted and replaced by thread B on CPU 0. This could even happen on exit from the membarrier() syscall. If this happens, thread B will end up running on CPU 0 without having synced. In principle, this could be fixed by arranging for the scheduler to issue sync_core_before_usermode() whenever switching between two threads in the same mm if there is any possibility of a concurrent membarrier() call, but this would have considerable overhead. Instead, make membarrier() sync the calling CPU as well. As an optimization, this avoids an extra smp_mb() in the default barrier-only mode and an extra rseq preempt on the caller. Fixes: 70216e18e519 ("membarrier: Provide core serializing command, *_SYNC_CORE") Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Mathieu Desnoyers Link: https://lore.kernel.org/r/250ded637696d490c69bef1877148db86066881c.1607058304.git.luto@kernel.org --- kernel/sched/membarrier.c | 51 ++++++++++++++++++++++++++++++----------------- 1 file changed, 33 insertions(+), 18 deletions(-) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 1c278dff4f2d..9d8df34bea75 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -194,7 +194,8 @@ static int membarrier_private_expedited(int flags, int cpu_id) return -EPERM; } - if (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1) + if (flags != MEMBARRIER_FLAG_SYNC_CORE && + (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1)) return 0; /* @@ -213,8 +214,6 @@ static int membarrier_private_expedited(int flags, int cpu_id) if (cpu_id >= nr_cpu_ids || !cpu_online(cpu_id)) goto out; - if (cpu_id == raw_smp_processor_id()) - goto out; rcu_read_lock(); p = rcu_dereference(cpu_rq(cpu_id)->curr); if (!p || p->mm != mm) { @@ -229,16 +228,6 @@ static int membarrier_private_expedited(int flags, int cpu_id) for_each_online_cpu(cpu) { struct task_struct *p; - /* - * Skipping the current CPU is OK even through we can be - * migrated at any point. The current CPU, at the point - * where we read raw_smp_processor_id(), is ensured to - * be in program order with respect to the caller - * thread. Therefore, we can skip this CPU from the - * iteration. - */ - if (cpu == raw_smp_processor_id()) - continue; p = rcu_dereference(cpu_rq(cpu)->curr); if (p && p->mm == mm) __cpumask_set_cpu(cpu, tmpmask); @@ -246,12 +235,38 @@ static int membarrier_private_expedited(int flags, int cpu_id) rcu_read_unlock(); } - preempt_disable(); - if (cpu_id >= 0) + if (cpu_id >= 0) { + /* + * smp_call_function_single() will call ipi_func() if cpu_id + * is the calling CPU. + */ smp_call_function_single(cpu_id, ipi_func, NULL, 1); - else - smp_call_function_many(tmpmask, ipi_func, NULL, 1); - preempt_enable(); + } else { + /* + * For regular membarrier, we can save a few cycles by + * skipping the current cpu -- we're about to do smp_mb() + * below, and if we migrate to a different cpu, this cpu + * and the new cpu will execute a full barrier in the + * scheduler. + * + * For SYNC_CORE, we do need a barrier on the current cpu -- + * otherwise, if we are migrated and replaced by a different + * task in the same mm just before, during, or after + * membarrier, we will end up with some thread in the mm + * running without a core sync. + * + * For RSEQ, don't rseq_preempt() the caller. User code + * is not supposed to issue syscalls at all from inside an + * rseq critical section. + */ + if (flags != MEMBARRIER_FLAG_SYNC_CORE) { + preempt_disable(); + smp_call_function_many(tmpmask, ipi_func, NULL, true); + preempt_enable(); + } else { + on_each_cpu_mask(tmpmask, ipi_func, NULL, true); + } + } out: if (cpu_id < 0) -- cgit v1.2.3 From 263ade7166a2e589c5b605272690c155c0637dcb Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Wed, 9 Dec 2020 13:51:06 +0800 Subject: gpio: eic-sprd: break loop when getting NULL device resource EIC controller have unfixed numbers of banks on different Spreadtrum SoCs, and each bank has its own base address, the loop of getting there base address in driver should break if the resource gotten via platform_get_resource() is NULL already. The later ones would be all NULL even if the loop continues. Fixes: 25518e024e3a ("gpio: Add Spreadtrum EIC driver support") Signed-off-by: Chunyan Zhang Link: https://lore.kernel.org/r/20201209055106.840100-1-zhang.lyra@gmail.com Signed-off-by: Linus Walleij --- drivers/gpio/gpio-eic-sprd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c index ad61daf6c212..865ab2b34fdd 100644 --- a/drivers/gpio/gpio-eic-sprd.c +++ b/drivers/gpio/gpio-eic-sprd.c @@ -598,7 +598,7 @@ static int sprd_eic_probe(struct platform_device *pdev) */ res = platform_get_resource(pdev, IORESOURCE_MEM, i); if (!res) - continue; + break; sprd_eic->base[i] = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(sprd_eic->base[i])) -- cgit v1.2.3 From ca33479cc7be2c9b5f8be078c8bf3ac26b7d6186 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 7 Dec 2020 08:31:22 +0100 Subject: xen: add helpers for caching grant mapping pages Instead of having similar helpers in multiple backend drivers use common helpers for caching pages allocated via gnttab_alloc_pages(). Make use of those helpers in blkback and scsiback. Cc: # 5.9 Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- drivers/block/xen-blkback/blkback.c | 89 +++++++------------------------------ drivers/block/xen-blkback/common.h | 4 +- drivers/block/xen-blkback/xenbus.c | 6 +-- drivers/xen/grant-table.c | 72 ++++++++++++++++++++++++++++++ drivers/xen/xen-scsiback.c | 60 +++++-------------------- include/xen/grant_table.h | 13 ++++++ 6 files changed, 116 insertions(+), 128 deletions(-) diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 501e9dacfff9..9ebf53903d7b 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -132,73 +132,12 @@ module_param(log_stats, int, 0644); #define BLKBACK_INVALID_HANDLE (~0) -/* Number of free pages to remove on each call to gnttab_free_pages */ -#define NUM_BATCH_FREE_PAGES 10 - static inline bool persistent_gnt_timeout(struct persistent_gnt *persistent_gnt) { return pgrant_timeout && (jiffies - persistent_gnt->last_used >= HZ * pgrant_timeout); } -static inline int get_free_page(struct xen_blkif_ring *ring, struct page **page) -{ - unsigned long flags; - - spin_lock_irqsave(&ring->free_pages_lock, flags); - if (list_empty(&ring->free_pages)) { - BUG_ON(ring->free_pages_num != 0); - spin_unlock_irqrestore(&ring->free_pages_lock, flags); - return gnttab_alloc_pages(1, page); - } - BUG_ON(ring->free_pages_num == 0); - page[0] = list_first_entry(&ring->free_pages, struct page, lru); - list_del(&page[0]->lru); - ring->free_pages_num--; - spin_unlock_irqrestore(&ring->free_pages_lock, flags); - - return 0; -} - -static inline void put_free_pages(struct xen_blkif_ring *ring, struct page **page, - int num) -{ - unsigned long flags; - int i; - - spin_lock_irqsave(&ring->free_pages_lock, flags); - for (i = 0; i < num; i++) - list_add(&page[i]->lru, &ring->free_pages); - ring->free_pages_num += num; - spin_unlock_irqrestore(&ring->free_pages_lock, flags); -} - -static inline void shrink_free_pagepool(struct xen_blkif_ring *ring, int num) -{ - /* Remove requested pages in batches of NUM_BATCH_FREE_PAGES */ - struct page *page[NUM_BATCH_FREE_PAGES]; - unsigned int num_pages = 0; - unsigned long flags; - - spin_lock_irqsave(&ring->free_pages_lock, flags); - while (ring->free_pages_num > num) { - BUG_ON(list_empty(&ring->free_pages)); - page[num_pages] = list_first_entry(&ring->free_pages, - struct page, lru); - list_del(&page[num_pages]->lru); - ring->free_pages_num--; - if (++num_pages == NUM_BATCH_FREE_PAGES) { - spin_unlock_irqrestore(&ring->free_pages_lock, flags); - gnttab_free_pages(num_pages, page); - spin_lock_irqsave(&ring->free_pages_lock, flags); - num_pages = 0; - } - } - spin_unlock_irqrestore(&ring->free_pages_lock, flags); - if (num_pages != 0) - gnttab_free_pages(num_pages, page); -} - #define vaddr(page) ((unsigned long)pfn_to_kaddr(page_to_pfn(page))) static int do_block_io_op(struct xen_blkif_ring *ring, unsigned int *eoi_flags); @@ -331,7 +270,8 @@ static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *ro unmap_data.count = segs_to_unmap; BUG_ON(gnttab_unmap_refs_sync(&unmap_data)); - put_free_pages(ring, pages, segs_to_unmap); + gnttab_page_cache_put(&ring->free_pages, pages, + segs_to_unmap); segs_to_unmap = 0; } @@ -371,7 +311,8 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work) if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST) { unmap_data.count = segs_to_unmap; BUG_ON(gnttab_unmap_refs_sync(&unmap_data)); - put_free_pages(ring, pages, segs_to_unmap); + gnttab_page_cache_put(&ring->free_pages, pages, + segs_to_unmap); segs_to_unmap = 0; } kfree(persistent_gnt); @@ -379,7 +320,7 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work) if (segs_to_unmap > 0) { unmap_data.count = segs_to_unmap; BUG_ON(gnttab_unmap_refs_sync(&unmap_data)); - put_free_pages(ring, pages, segs_to_unmap); + gnttab_page_cache_put(&ring->free_pages, pages, segs_to_unmap); } } @@ -664,9 +605,10 @@ purge_gnt_list: /* Shrink the free pages pool if it is too large. */ if (time_before(jiffies, blkif->buffer_squeeze_end)) - shrink_free_pagepool(ring, 0); + gnttab_page_cache_shrink(&ring->free_pages, 0); else - shrink_free_pagepool(ring, max_buffer_pages); + gnttab_page_cache_shrink(&ring->free_pages, + max_buffer_pages); if (log_stats && time_after(jiffies, ring->st_print)) print_stats(ring); @@ -697,7 +639,7 @@ void xen_blkbk_free_caches(struct xen_blkif_ring *ring) ring->persistent_gnt_c = 0; /* Since we are shutting down remove all pages from the buffer */ - shrink_free_pagepool(ring, 0 /* All */); + gnttab_page_cache_shrink(&ring->free_pages, 0 /* All */); } static unsigned int xen_blkbk_unmap_prepare( @@ -736,7 +678,7 @@ static void xen_blkbk_unmap_and_respond_callback(int result, struct gntab_unmap_ but is this the best way to deal with this? */ BUG_ON(result); - put_free_pages(ring, data->pages, data->count); + gnttab_page_cache_put(&ring->free_pages, data->pages, data->count); make_response(ring, pending_req->id, pending_req->operation, pending_req->status); free_req(ring, pending_req); @@ -803,7 +745,8 @@ static void xen_blkbk_unmap(struct xen_blkif_ring *ring, if (invcount) { ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount); BUG_ON(ret); - put_free_pages(ring, unmap_pages, invcount); + gnttab_page_cache_put(&ring->free_pages, unmap_pages, + invcount); } pages += batch; num -= batch; @@ -850,7 +793,8 @@ again: pages[i]->page = persistent_gnt->page; pages[i]->persistent_gnt = persistent_gnt; } else { - if (get_free_page(ring, &pages[i]->page)) + if (gnttab_page_cache_get(&ring->free_pages, + &pages[i]->page)) goto out_of_memory; addr = vaddr(pages[i]->page); pages_to_gnt[segs_to_map] = pages[i]->page; @@ -883,7 +827,8 @@ again: BUG_ON(new_map_idx >= segs_to_map); if (unlikely(map[new_map_idx].status != 0)) { pr_debug("invalid buffer -- could not remap it\n"); - put_free_pages(ring, &pages[seg_idx]->page, 1); + gnttab_page_cache_put(&ring->free_pages, + &pages[seg_idx]->page, 1); pages[seg_idx]->handle = BLKBACK_INVALID_HANDLE; ret |= 1; goto next; @@ -944,7 +889,7 @@ next: out_of_memory: pr_alert("%s: out of memory\n", __func__); - put_free_pages(ring, pages_to_gnt, segs_to_map); + gnttab_page_cache_put(&ring->free_pages, pages_to_gnt, segs_to_map); for (i = last_map; i < num; i++) pages[i]->handle = BLKBACK_INVALID_HANDLE; return -ENOMEM; diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index c6ea5d38c509..a1b9df2c4ef1 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -288,9 +288,7 @@ struct xen_blkif_ring { struct work_struct persistent_purge_work; /* Buffer of free pages to map grant refs. */ - spinlock_t free_pages_lock; - int free_pages_num; - struct list_head free_pages; + struct gnttab_page_cache free_pages; struct work_struct free_work; /* Thread shutdown wait queue. */ diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index f5705569e2a7..76912c584a76 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -144,8 +144,7 @@ static int xen_blkif_alloc_rings(struct xen_blkif *blkif) INIT_LIST_HEAD(&ring->pending_free); INIT_LIST_HEAD(&ring->persistent_purge_list); INIT_WORK(&ring->persistent_purge_work, xen_blkbk_unmap_purged_grants); - spin_lock_init(&ring->free_pages_lock); - INIT_LIST_HEAD(&ring->free_pages); + gnttab_page_cache_init(&ring->free_pages); spin_lock_init(&ring->pending_free_lock); init_waitqueue_head(&ring->pending_free_wq); @@ -317,8 +316,7 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) BUG_ON(atomic_read(&ring->persistent_gnt_in_use) != 0); BUG_ON(!list_empty(&ring->persistent_purge_list)); BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts)); - BUG_ON(!list_empty(&ring->free_pages)); - BUG_ON(ring->free_pages_num != 0); + BUG_ON(ring->free_pages.num_pages != 0); BUG_ON(ring->persistent_gnt_c != 0); WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages)); ring->active = false; diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 523dcdf39cc9..e2e42912f241 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -813,6 +813,78 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages) } EXPORT_SYMBOL_GPL(gnttab_alloc_pages); +void gnttab_page_cache_init(struct gnttab_page_cache *cache) +{ + spin_lock_init(&cache->lock); + INIT_LIST_HEAD(&cache->pages); + cache->num_pages = 0; +} +EXPORT_SYMBOL_GPL(gnttab_page_cache_init); + +int gnttab_page_cache_get(struct gnttab_page_cache *cache, struct page **page) +{ + unsigned long flags; + + spin_lock_irqsave(&cache->lock, flags); + + if (list_empty(&cache->pages)) { + spin_unlock_irqrestore(&cache->lock, flags); + return gnttab_alloc_pages(1, page); + } + + page[0] = list_first_entry(&cache->pages, struct page, lru); + list_del(&page[0]->lru); + cache->num_pages--; + + spin_unlock_irqrestore(&cache->lock, flags); + + return 0; +} +EXPORT_SYMBOL_GPL(gnttab_page_cache_get); + +void gnttab_page_cache_put(struct gnttab_page_cache *cache, struct page **page, + unsigned int num) +{ + unsigned long flags; + unsigned int i; + + spin_lock_irqsave(&cache->lock, flags); + + for (i = 0; i < num; i++) + list_add(&page[i]->lru, &cache->pages); + cache->num_pages += num; + + spin_unlock_irqrestore(&cache->lock, flags); +} +EXPORT_SYMBOL_GPL(gnttab_page_cache_put); + +void gnttab_page_cache_shrink(struct gnttab_page_cache *cache, unsigned int num) +{ + struct page *page[10]; + unsigned int i = 0; + unsigned long flags; + + spin_lock_irqsave(&cache->lock, flags); + + while (cache->num_pages > num) { + page[i] = list_first_entry(&cache->pages, struct page, lru); + list_del(&page[i]->lru); + cache->num_pages--; + if (++i == ARRAY_SIZE(page)) { + spin_unlock_irqrestore(&cache->lock, flags); + gnttab_free_pages(i, page); + i = 0; + spin_lock_irqsave(&cache->lock, flags); + } + } + + spin_unlock_irqrestore(&cache->lock, flags); + + if (i != 0) + gnttab_free_pages(i, page); +} +EXPORT_SYMBOL_GPL(gnttab_page_cache_shrink); + void gnttab_pages_clear_private(int nr_pages, struct page **pages) { int i; diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 4acc4e899600..862162dca33c 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -99,6 +99,8 @@ struct vscsibk_info { struct list_head v2p_entry_lists; wait_queue_head_t waiting_to_free; + + struct gnttab_page_cache free_pages; }; /* theoretical maximum of grants for one request */ @@ -188,10 +190,6 @@ module_param_named(max_buffer_pages, scsiback_max_buffer_pages, int, 0644); MODULE_PARM_DESC(max_buffer_pages, "Maximum number of free pages to keep in backend buffer"); -static DEFINE_SPINLOCK(free_pages_lock); -static int free_pages_num; -static LIST_HEAD(scsiback_free_pages); - /* Global spinlock to protect scsiback TPG list */ static DEFINE_MUTEX(scsiback_mutex); static LIST_HEAD(scsiback_list); @@ -207,41 +205,6 @@ static void scsiback_put(struct vscsibk_info *info) wake_up(&info->waiting_to_free); } -static void put_free_pages(struct page **page, int num) -{ - unsigned long flags; - int i = free_pages_num + num, n = num; - - if (num == 0) - return; - if (i > scsiback_max_buffer_pages) { - n = min(num, i - scsiback_max_buffer_pages); - gnttab_free_pages(n, page + num - n); - n = num - n; - } - spin_lock_irqsave(&free_pages_lock, flags); - for (i = 0; i < n; i++) - list_add(&page[i]->lru, &scsiback_free_pages); - free_pages_num += n; - spin_unlock_irqrestore(&free_pages_lock, flags); -} - -static int get_free_page(struct page **page) -{ - unsigned long flags; - - spin_lock_irqsave(&free_pages_lock, flags); - if (list_empty(&scsiback_free_pages)) { - spin_unlock_irqrestore(&free_pages_lock, flags); - return gnttab_alloc_pages(1, page); - } - page[0] = list_first_entry(&scsiback_free_pages, struct page, lru); - list_del(&page[0]->lru); - free_pages_num--; - spin_unlock_irqrestore(&free_pages_lock, flags); - return 0; -} - static unsigned long vaddr_page(struct page *page) { unsigned long pfn = page_to_pfn(page); @@ -302,7 +265,8 @@ static void scsiback_fast_flush_area(struct vscsibk_pend *req) BUG_ON(err); } - put_free_pages(req->pages, req->n_grants); + gnttab_page_cache_put(&req->info->free_pages, req->pages, + req->n_grants); req->n_grants = 0; } @@ -445,8 +409,8 @@ static int scsiback_gnttab_data_map_list(struct vscsibk_pend *pending_req, struct vscsibk_info *info = pending_req->info; for (i = 0; i < cnt; i++) { - if (get_free_page(pg + mapcount)) { - put_free_pages(pg, mapcount); + if (gnttab_page_cache_get(&info->free_pages, pg + mapcount)) { + gnttab_page_cache_put(&info->free_pages, pg, mapcount); pr_err("no grant page\n"); return -ENOMEM; } @@ -796,6 +760,8 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info, cond_resched(); } + gnttab_page_cache_shrink(&info->free_pages, scsiback_max_buffer_pages); + RING_FINAL_CHECK_FOR_REQUESTS(&info->ring, more_to_do); return more_to_do; } @@ -1233,6 +1199,8 @@ static int scsiback_remove(struct xenbus_device *dev) scsiback_release_translation_entry(info); + gnttab_page_cache_shrink(&info->free_pages, 0); + dev_set_drvdata(&dev->dev, NULL); return 0; @@ -1263,6 +1231,7 @@ static int scsiback_probe(struct xenbus_device *dev, info->irq = 0; INIT_LIST_HEAD(&info->v2p_entry_lists); spin_lock_init(&info->v2p_lock); + gnttab_page_cache_init(&info->free_pages); err = xenbus_printf(XBT_NIL, dev->nodename, "feature-sg-grant", "%u", SG_ALL); @@ -1879,13 +1848,6 @@ out: static void __exit scsiback_exit(void) { - struct page *page; - - while (free_pages_num) { - if (get_free_page(&page)) - BUG(); - gnttab_free_pages(1, &page); - } target_unregister_template(&scsiback_ops); xenbus_unregister_driver(&scsiback_driver); } diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 9bc5bc07d4d3..c6ef8ffc1a09 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -198,6 +198,19 @@ void gnttab_free_auto_xlat_frames(void); int gnttab_alloc_pages(int nr_pages, struct page **pages); void gnttab_free_pages(int nr_pages, struct page **pages); +struct gnttab_page_cache { + spinlock_t lock; + struct list_head pages; + unsigned int num_pages; +}; + +void gnttab_page_cache_init(struct gnttab_page_cache *cache); +int gnttab_page_cache_get(struct gnttab_page_cache *cache, struct page **page); +void gnttab_page_cache_put(struct gnttab_page_cache *cache, struct page **page, + unsigned int num); +void gnttab_page_cache_shrink(struct gnttab_page_cache *cache, + unsigned int num); + #ifdef CONFIG_XEN_GRANT_DMA_ALLOC struct gnttab_dma_alloc_args { /* Device for which DMA memory will be/was allocated. */ -- cgit v1.2.3 From ee32f32335e8c7f6154bf397f4ac9b6175b488a8 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 7 Dec 2020 09:36:14 +0100 Subject: xen: don't use page->lru for ZONE_DEVICE memory Commit 9e2369c06c8a18 ("xen: add helpers to allocate unpopulated memory") introduced usage of ZONE_DEVICE memory for foreign memory mappings. Unfortunately this collides with using page->lru for Xen backend private page caches. Fix that by using page->zone_device_data instead. Cc: # 5.9 Fixes: 9e2369c06c8a18 ("xen: add helpers to allocate unpopulated memory") Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Reviewed-by: Jason Andryuk Signed-off-by: Juergen Gross --- drivers/xen/grant-table.c | 65 ++++++++++++++++++++++++++++++++++++----- drivers/xen/unpopulated-alloc.c | 20 +++++++------ include/xen/grant_table.h | 4 +++ 3 files changed, 73 insertions(+), 16 deletions(-) diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index e2e42912f241..3729bea0c989 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -813,10 +813,63 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages) } EXPORT_SYMBOL_GPL(gnttab_alloc_pages); +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC +static inline void cache_init(struct gnttab_page_cache *cache) +{ + cache->pages = NULL; +} + +static inline bool cache_empty(struct gnttab_page_cache *cache) +{ + return !cache->pages; +} + +static inline struct page *cache_deq(struct gnttab_page_cache *cache) +{ + struct page *page; + + page = cache->pages; + cache->pages = page->zone_device_data; + + return page; +} + +static inline void cache_enq(struct gnttab_page_cache *cache, struct page *page) +{ + page->zone_device_data = cache->pages; + cache->pages = page; +} +#else +static inline void cache_init(struct gnttab_page_cache *cache) +{ + INIT_LIST_HEAD(&cache->pages); +} + +static inline bool cache_empty(struct gnttab_page_cache *cache) +{ + return list_empty(&cache->pages); +} + +static inline struct page *cache_deq(struct gnttab_page_cache *cache) +{ + struct page *page; + + page = list_first_entry(&cache->pages, struct page, lru); + list_del(&page->lru); + + return page; +} + +static inline void cache_enq(struct gnttab_page_cache *cache, struct page *page) +{ + list_add(&page->lru, &cache->pages); +} +#endif + void gnttab_page_cache_init(struct gnttab_page_cache *cache) { spin_lock_init(&cache->lock); - INIT_LIST_HEAD(&cache->pages); + cache_init(cache); cache->num_pages = 0; } EXPORT_SYMBOL_GPL(gnttab_page_cache_init); @@ -827,13 +880,12 @@ int gnttab_page_cache_get(struct gnttab_page_cache *cache, struct page **page) spin_lock_irqsave(&cache->lock, flags); - if (list_empty(&cache->pages)) { + if (cache_empty(cache)) { spin_unlock_irqrestore(&cache->lock, flags); return gnttab_alloc_pages(1, page); } - page[0] = list_first_entry(&cache->pages, struct page, lru); - list_del(&page[0]->lru); + page[0] = cache_deq(cache); cache->num_pages--; spin_unlock_irqrestore(&cache->lock, flags); @@ -851,7 +903,7 @@ void gnttab_page_cache_put(struct gnttab_page_cache *cache, struct page **page, spin_lock_irqsave(&cache->lock, flags); for (i = 0; i < num; i++) - list_add(&page[i]->lru, &cache->pages); + cache_enq(cache, page[i]); cache->num_pages += num; spin_unlock_irqrestore(&cache->lock, flags); @@ -867,8 +919,7 @@ void gnttab_page_cache_shrink(struct gnttab_page_cache *cache, unsigned int num) spin_lock_irqsave(&cache->lock, flags); while (cache->num_pages > num) { - page[i] = list_first_entry(&cache->pages, struct page, lru); - list_del(&page[i]->lru); + page[i] = cache_deq(cache); cache->num_pages--; if (++i == ARRAY_SIZE(page)) { spin_unlock_irqrestore(&cache->lock, flags); diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c index 8c512ea550bb..7762c1bb23cb 100644 --- a/drivers/xen/unpopulated-alloc.c +++ b/drivers/xen/unpopulated-alloc.c @@ -12,7 +12,7 @@ #include static DEFINE_MUTEX(list_lock); -static LIST_HEAD(page_list); +static struct page *page_list; static unsigned int list_count; static int fill_list(unsigned int nr_pages) @@ -84,7 +84,8 @@ static int fill_list(unsigned int nr_pages) struct page *pg = virt_to_page(vaddr + PAGE_SIZE * i); BUG_ON(!virt_addr_valid(vaddr + PAGE_SIZE * i)); - list_add(&pg->lru, &page_list); + pg->zone_device_data = page_list; + page_list = pg; list_count++; } @@ -118,12 +119,10 @@ int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages) } for (i = 0; i < nr_pages; i++) { - struct page *pg = list_first_entry_or_null(&page_list, - struct page, - lru); + struct page *pg = page_list; BUG_ON(!pg); - list_del(&pg->lru); + page_list = pg->zone_device_data; list_count--; pages[i] = pg; @@ -134,7 +133,8 @@ int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages) unsigned int j; for (j = 0; j <= i; j++) { - list_add(&pages[j]->lru, &page_list); + pages[j]->zone_device_data = page_list; + page_list = pages[j]; list_count++; } goto out; @@ -160,7 +160,8 @@ void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages) mutex_lock(&list_lock); for (i = 0; i < nr_pages; i++) { - list_add(&pages[i]->lru, &page_list); + pages[i]->zone_device_data = page_list; + page_list = pages[i]; list_count++; } mutex_unlock(&list_lock); @@ -189,7 +190,8 @@ static int __init init(void) struct page *pg = pfn_to_page(xen_extra_mem[i].start_pfn + j); - list_add(&pg->lru, &page_list); + pg->zone_device_data = page_list; + page_list = pg; list_count++; } } diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index c6ef8ffc1a09..b9c937b3a149 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -200,7 +200,11 @@ void gnttab_free_pages(int nr_pages, struct page **pages); struct gnttab_page_cache { spinlock_t lock; +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC + struct page *pages; +#else struct list_head pages; +#endif unsigned int num_pages; }; -- cgit v1.2.3 From 2d94b20b95b009eec1a267dcf026b01af627c0cd Mon Sep 17 00:00:00 2001 From: Brett Mastbergen Date: Tue, 8 Dec 2020 16:39:24 -0500 Subject: netfilter: nft_ct: Remove confirmation check for NFT_CT_ID Since commit 656c8e9cc1ba ("netfilter: conntrack: Use consistent ct id hash calculation") the ct id will not change from initialization to confirmation. Removing the confirmation check allows for things like adding an element to a 'typeof ct id' set in prerouting upon reception of the first packet of a new connection, and then being able to reference that set consistently both before and after the connection is confirmed. Fixes: 656c8e9cc1ba ("netfilter: conntrack: Use consistent ct id hash calculation") Signed-off-by: Brett Mastbergen Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_ct.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 322bd674963e..a1b0aac46e9e 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -177,8 +177,6 @@ static void nft_ct_get_eval(const struct nft_expr *expr, } #endif case NFT_CT_ID: - if (!nf_ct_is_confirmed(ct)) - goto err; *dest = nf_ct_get_id(ct); return; default: -- cgit v1.2.3 From 578b6c487899179fed730e710ffec0b069917971 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 3 Dec 2020 16:06:26 -0500 Subject: drm/amdgpu/disply: set num_crtc earlier To avoid a recently added warning: Bogus possible_crtcs: [ENCODER:65:TMDS-65] possible_crtcs=0xf (full crtc mask=0x7) WARNING: CPU: 3 PID: 439 at drivers/gpu/drm/drm_mode_config.c:617 drm_mode_config_validate+0x178/0x200 [drm] In this case the warning is harmless, but confusing to users. Fixes: 0df108237433 ("drm: Validate encoder->possible_crtcs") Bug: https://bugzilla.kernel.org/show_bug.cgi?id=209123 Reviewed-by: Daniel Vetter Reviewed-by: Nicholas Kazlauskas Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 9b6809f309f4..0f7749e9424d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1058,9 +1058,6 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) goto error; } - /* Update the actual used number of crtc */ - adev->mode_info.num_crtc = adev->dm.display_indexes_num; - /* create fake encoders for MST */ dm_dp_create_fake_mst_encoders(adev); @@ -3251,6 +3248,10 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) enum dc_connection_type new_connection_type = dc_connection_none; const struct dc_plane_cap *plane; + dm->display_indexes_num = dm->dc->caps.max_streams; + /* Update the actual used number of crtc */ + adev->mode_info.num_crtc = adev->dm.display_indexes_num; + link_cnt = dm->dc->caps.max_links; if (amdgpu_dm_mode_config_init(dm->adev)) { DRM_ERROR("DM: Failed to initialize mode config\n"); @@ -3312,8 +3313,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) goto fail; } - dm->display_indexes_num = dm->dc->caps.max_streams; - /* loops over all connectors on the board */ for (i = 0; i < link_cnt; i++) { struct dc_link *link = NULL; -- cgit v1.2.3 From 2343e9d2c5a94459b9de92649f1650e36eb79a10 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 4 Dec 2020 00:06:43 +0100 Subject: drm/amdgpu: fix debugfs creation/removal, again There is still a warning when CONFIG_DEBUG_FS is disabled: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c:1145:13: error: 'amdgpu_ras_debugfs_create_ctrl_node' defined but not used [-Werror=unused-function] 1145 | static void amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *adev) Change the code again to make the compiler actually drop this code but not warn about it. Fixes: ae2bf61ff39e ("drm/amdgpu: guard ras debugfs creation/removal based on CONFIG_DEBUG_FS") Reviewed-by: Tao Zhou Signed-off-by: Arnd Bergmann Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 13 +++++-------- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 6 ------ 2 files changed, 5 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 4e36551ab50b..82cd8e55595a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1172,7 +1172,7 @@ static void amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *adev) con->dir, &con->disable_ras_err_cnt_harvest); } -void amdgpu_ras_debugfs_create(struct amdgpu_device *adev, +static void amdgpu_ras_debugfs_create(struct amdgpu_device *adev, struct ras_fs_if *head) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); @@ -1194,7 +1194,6 @@ void amdgpu_ras_debugfs_create(struct amdgpu_device *adev, void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev) { -#if defined(CONFIG_DEBUG_FS) struct amdgpu_ras *con = amdgpu_ras_get_context(adev); struct ras_manager *obj; struct ras_fs_if fs_info; @@ -1203,7 +1202,7 @@ void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev) * it won't be called in resume path, no need to check * suspend and gpu reset status */ - if (!con) + if (!IS_ENABLED(CONFIG_DEBUG_FS) || !con) return; amdgpu_ras_debugfs_create_ctrl_node(adev); @@ -1217,10 +1216,9 @@ void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev) amdgpu_ras_debugfs_create(adev, &fs_info); } } -#endif } -void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev, +static void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev, struct ras_common_if *head) { struct ras_manager *obj = amdgpu_ras_find_obj(adev, head); @@ -1234,7 +1232,6 @@ void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev, static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev) { -#if defined(CONFIG_DEBUG_FS) struct amdgpu_ras *con = amdgpu_ras_get_context(adev); struct ras_manager *obj, *tmp; @@ -1243,7 +1240,6 @@ static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev) } con->dir = NULL; -#endif } /* debugfs end */ @@ -1291,7 +1287,8 @@ static int amdgpu_ras_fs_init(struct amdgpu_device *adev) static int amdgpu_ras_fs_fini(struct amdgpu_device *adev) { - amdgpu_ras_debugfs_remove_all(adev); + if (IS_ENABLED(CONFIG_DEBUG_FS)) + amdgpu_ras_debugfs_remove_all(adev); amdgpu_ras_sysfs_remove_all(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h index 6b8d7bb83bb3..ec398ed7deb8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h @@ -607,14 +607,8 @@ int amdgpu_ras_sysfs_create(struct amdgpu_device *adev, int amdgpu_ras_sysfs_remove(struct amdgpu_device *adev, struct ras_common_if *head); -void amdgpu_ras_debugfs_create(struct amdgpu_device *adev, - struct ras_fs_if *head); - void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev); -void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev, - struct ras_common_if *head); - int amdgpu_ras_error_query(struct amdgpu_device *adev, struct ras_query_if *info); -- cgit v1.2.3 From c2ffe78b8b1354603a7d5afb719b2a6dfbb582da Mon Sep 17 00:00:00 2001 From: Chris Park Date: Tue, 24 Nov 2020 20:11:25 -0500 Subject: drm/amd/display: Prevent bandwidth overflow [Why] At very high pixel clock, bandwidth calculation exceeds 32 bit size and overflow value. This causes the resulting selection of link rate to be inaccurate. [How] Change order of operation and use fixed point to deal with integer accuracy. Also address bug found when forcing link rate. Signed-off-by: Chris Park Reviewed-by: Wenjing Liu Acked-by: Eryk Brol Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index fec87a2e210c..5b0cedfa824a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -3394,10 +3394,13 @@ uint32_t dc_bandwidth_in_kbps_from_timing( { uint32_t bits_per_channel = 0; uint32_t kbps; + struct fixed31_32 link_bw_kbps; if (timing->flags.DSC) { - kbps = (timing->pix_clk_100hz * timing->dsc_cfg.bits_per_pixel); - kbps = kbps / 160 + ((kbps % 160) ? 1 : 0); + link_bw_kbps = dc_fixpt_from_int(timing->pix_clk_100hz); + link_bw_kbps = dc_fixpt_div_int(link_bw_kbps, 160); + link_bw_kbps = dc_fixpt_mul_int(link_bw_kbps, timing->dsc_cfg.bits_per_pixel); + kbps = dc_fixpt_ceil(link_bw_kbps); return kbps; } -- cgit v1.2.3 From 369b7ebe1792b620b7a9404e7b71daaae13ebfd6 Mon Sep 17 00:00:00 2001 From: Sung Lee Date: Mon, 23 Nov 2020 15:38:54 -0500 Subject: drm/amd/display: Add wm table for Renoir [Why] Without additional HostVM Latency, Renoir takes 2us longer to exit self-refresh. This causes underflow in certain cases. [How] Add table for Renoir with updated sr exit latencies for WM set A. Signed-off-by: Sung Lee Reviewed-by: Yongqiang Sun Reviewed-by: Roman Li Acked-by: Eryk Brol Signed-off-by: Alex Deucher --- .../drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c | 93 +++++++++++++++++++++- 1 file changed, 89 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index c001307b0a59..6b431db146cd 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -579,7 +579,7 @@ static struct clk_bw_params rn_bw_params = { }; -static struct wm_table ddr4_wm_table = { +static struct wm_table ddr4_wm_table_gs = { .entries = { { .wm_inst = WM_A, @@ -616,7 +616,7 @@ static struct wm_table ddr4_wm_table = { } }; -static struct wm_table lpddr4_wm_table = { +static struct wm_table lpddr4_wm_table_gs = { .entries = { { .wm_inst = WM_A, @@ -690,6 +690,80 @@ static struct wm_table lpddr4_wm_table_with_disabled_ppt = { } }; +static struct wm_table ddr4_wm_table_rn = { + .entries = { + { + .wm_inst = WM_A, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 9.09, + .sr_enter_plus_exit_time_us = 10.14, + .valid = true, + }, + { + .wm_inst = WM_B, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 10.12, + .sr_enter_plus_exit_time_us = 11.48, + .valid = true, + }, + { + .wm_inst = WM_C, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 10.12, + .sr_enter_plus_exit_time_us = 11.48, + .valid = true, + }, + { + .wm_inst = WM_D, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 10.12, + .sr_enter_plus_exit_time_us = 11.48, + .valid = true, + }, + } +}; + +static struct wm_table lpddr4_wm_table_rn = { + .entries = { + { + .wm_inst = WM_A, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 7.32, + .sr_enter_plus_exit_time_us = 8.38, + .valid = true, + }, + { + .wm_inst = WM_B, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.82, + .sr_enter_plus_exit_time_us = 11.196, + .valid = true, + }, + { + .wm_inst = WM_C, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.89, + .sr_enter_plus_exit_time_us = 11.24, + .valid = true, + }, + { + .wm_inst = WM_D, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.748, + .sr_enter_plus_exit_time_us = 11.102, + .valid = true, + }, + } +}; + static unsigned int find_dcfclk_for_voltage(struct dpm_clocks *clock_table, unsigned int voltage) { int i; @@ -771,6 +845,11 @@ void rn_clk_mgr_construct( struct dc_debug_options *debug = &ctx->dc->debug; struct dpm_clocks clock_table = { 0 }; enum pp_smu_status status = 0; + int is_green_sardine = 0; + +#if defined(CONFIG_DRM_AMD_DC_DCN) + is_green_sardine = ASICREV_IS_GREEN_SARDINE(ctx->asic_id.hw_internal_rev); +#endif clk_mgr->base.ctx = ctx; clk_mgr->base.funcs = &dcn21_funcs; @@ -811,10 +890,16 @@ void rn_clk_mgr_construct( if (clk_mgr->periodic_retraining_disabled) { rn_bw_params.wm_table = lpddr4_wm_table_with_disabled_ppt; } else { - rn_bw_params.wm_table = lpddr4_wm_table; + if (is_green_sardine) + rn_bw_params.wm_table = lpddr4_wm_table_gs; + else + rn_bw_params.wm_table = lpddr4_wm_table_rn; } } else { - rn_bw_params.wm_table = ddr4_wm_table; + if (is_green_sardine) + rn_bw_params.wm_table = ddr4_wm_table_gs; + else + rn_bw_params.wm_table = ddr4_wm_table_rn; } /* Saved clocks configured at boot for debug purposes */ rn_dump_clk_registers(&clk_mgr->base.boot_snapshot, &clk_mgr->base, &log_info); -- cgit v1.2.3 From 6896887b8676d8fb445c85ea56333b9661a6a8aa Mon Sep 17 00:00:00 2001 From: "Stanley.Yang" Date: Mon, 7 Dec 2020 14:38:33 +0800 Subject: drm/amdgpu: fix sdma instance fw version and feature version init each sdma instance fw_version and feature_version should be set right value when asic type isn't between SIENNA_CICHILD and CHIP_DIMGREY_CAVEFISH Signed-off-by: Stanley.Yang Reviewed-by: Tao Zhou Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 9f3952723c63..2a485052e3ab 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -186,7 +186,7 @@ static int sdma_v5_2_init_microcode(struct amdgpu_device *adev) if (err) goto out; - err = sdma_v5_2_init_inst_ctx(&adev->sdma.instance[0]); + err = sdma_v5_2_init_inst_ctx(&adev->sdma.instance[i]); if (err) goto out; } -- cgit v1.2.3 From ab6e4e9de8dd7febfdf6719741f10dc6693d8ce9 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Tue, 8 Dec 2020 12:23:15 -0500 Subject: drm/amdkfd: Fix leak in dmabuf import Release dmabuf reference before returning from kfd_ioctl_import_dmabuf. amdgpu_amdkfd_gpuvm_import_dmabuf takes a reference to the underlying GEM BO and doesn't keep the reference to the dmabuf wrapper. Signed-off-by: Felix Kuehling Reviewed-by: Kent Russell Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 222f1df1a6b6..8cc51cec988a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1736,6 +1736,7 @@ static int kfd_ioctl_import_dmabuf(struct file *filep, } mutex_unlock(&p->mutex); + dma_buf_put(dmabuf); args->handle = MAKE_HANDLE(args->gpu_id, idr_handle); @@ -1745,6 +1746,7 @@ err_free: amdgpu_amdkfd_gpuvm_free_memory_of_gpu(dev->kgd, (struct kgd_mem *)mem, NULL); err_unlock: mutex_unlock(&p->mutex); + dma_buf_put(dmabuf); return r; } -- cgit v1.2.3 From c9918d1f63a3e77ec20997a77c997a6fa7282f2f Mon Sep 17 00:00:00 2001 From: Changfeng Date: Mon, 7 Dec 2020 15:42:29 +0800 Subject: drm/amd/pm: update smu10.h WORKLOAD_PPLIB setting for raven When using old WORKLOAD_PPLIB setting in smu10.h, there is problem that it can't be able to switch to mak gpu clk during compute workload. It needs to update WORKLOAD_PPLIB setting to fix this issue. Signed-off-by: Changfeng Reviewed-by: Huang Rui Acked-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/pm/inc/smu10.h | 14 ++++++-------- drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c | 9 +++------ 2 files changed, 9 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/inc/smu10.h b/drivers/gpu/drm/amd/pm/inc/smu10.h index b96520528240..9e837a5014c5 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu10.h +++ b/drivers/gpu/drm/amd/pm/inc/smu10.h @@ -136,14 +136,12 @@ #define FEATURE_CORE_CSTATES_MASK (1 << FEATURE_CORE_CSTATES_BIT) /* Workload bits */ -#define WORKLOAD_DEFAULT_BIT 0 -#define WORKLOAD_PPLIB_FULL_SCREEN_3D_BIT 1 -#define WORKLOAD_PPLIB_POWER_SAVING_BIT 2 -#define WORKLOAD_PPLIB_VIDEO_BIT 3 -#define WORKLOAD_PPLIB_VR_BIT 4 -#define WORKLOAD_PPLIB_COMPUTE_BIT 5 -#define WORKLOAD_PPLIB_CUSTOM_BIT 6 -#define WORKLOAD_PPLIB_COUNT 7 +#define WORKLOAD_PPLIB_FULL_SCREEN_3D_BIT 0 +#define WORKLOAD_PPLIB_VIDEO_BIT 2 +#define WORKLOAD_PPLIB_VR_BIT 3 +#define WORKLOAD_PPLIB_COMPUTE_BIT 4 +#define WORKLOAD_PPLIB_CUSTOM_BIT 5 +#define WORKLOAD_PPLIB_COUNT 6 typedef struct { /* MP1_EXT_SCRATCH0 */ diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index cf60f3992303..e6f40ee9f313 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -1297,15 +1297,9 @@ static int conv_power_profile_to_pplib_workload(int power_profile) int pplib_workload = 0; switch (power_profile) { - case PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT: - pplib_workload = WORKLOAD_DEFAULT_BIT; - break; case PP_SMC_POWER_PROFILE_FULLSCREEN3D: pplib_workload = WORKLOAD_PPLIB_FULL_SCREEN_3D_BIT; break; - case PP_SMC_POWER_PROFILE_POWERSAVING: - pplib_workload = WORKLOAD_PPLIB_POWER_SAVING_BIT; - break; case PP_SMC_POWER_PROFILE_VIDEO: pplib_workload = WORKLOAD_PPLIB_VIDEO_BIT; break; @@ -1315,6 +1309,9 @@ static int conv_power_profile_to_pplib_workload(int power_profile) case PP_SMC_POWER_PROFILE_COMPUTE: pplib_workload = WORKLOAD_PPLIB_COMPUTE_BIT; break; + case PP_SMC_POWER_PROFILE_CUSTOM: + pplib_workload = WORKLOAD_PPLIB_CUSTOM_BIT; + break; } return pplib_workload; -- cgit v1.2.3 From 157fe68d74c2ad2db438c91af9ed3d3a51de4ed7 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 7 Dec 2020 13:12:29 -0500 Subject: drm/amdgpu: fix size calculation with stolen vga memory MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If we need to keep the stolen vga memory, make sure it is at least as big as the legacy vga size. Acked-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 36604d751d62..3e4892b7b7d3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -499,6 +499,9 @@ void amdgpu_gmc_get_vbios_allocations(struct amdgpu_device *adev) else size = amdgpu_gmc_get_vbios_fb_size(adev); + if (adev->mman.keep_stolen_vga_memory) + size = max(size, (unsigned)AMDGPU_VBIOS_VGA_ALLOCATION); + /* set to 0 if the pre-OS buffer uses up most of vram */ if ((adev->gmc.real_vram_size - size) < (8 * 1024 * 1024)) size = 0; -- cgit v1.2.3 From ab43234d0bafcf2accd9db4fc4d193180b752f94 Mon Sep 17 00:00:00 2001 From: Andrey Grodzovsky Date: Tue, 8 Dec 2020 15:16:15 -0500 Subject: drm/amdgpu: Initialise drm_gem_object_funcs for imported BOs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For BOs imported from outside of amdgpu, setting of amdgpu_gem_object_funcs was missing in amdgpu_dma_buf_create_obj. Fix by refactoring BO creation and amdgpu_gem_object_funcs setting into single function called from both code paths. Fixes: d693def4fd1c ("drm: Remove obsolete GEM and PRIME callbacks from struct drm_driver") v2: Use use amdgpu_gem_object_create() directly v3: fix warning Reviewed-by: Christian König Signed-off-by: Andrey Grodzovsky Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 8 ++++-- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 41 ++++++++++++++++------------- 2 files changed, 29 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 957934926b24..1b56dbc1f304 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -459,6 +459,7 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) struct amdgpu_device *adev = drm_to_adev(dev); struct amdgpu_bo *bo; struct amdgpu_bo_param bp; + struct drm_gem_object *gobj; int ret; memset(&bp, 0, sizeof(bp)); @@ -469,17 +470,20 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) bp.type = ttm_bo_type_sg; bp.resv = resv; dma_resv_lock(resv, NULL); - ret = amdgpu_bo_create(adev, &bp, &bo); + ret = amdgpu_gem_object_create(adev, dma_buf->size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_CPU, + 0, ttm_bo_type_sg, resv, &gobj); if (ret) goto error; + bo = gem_to_amdgpu_bo(gobj); bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT; bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT; if (dma_buf->ops != &amdgpu_dmabuf_ops) bo->prime_shared_count = 1; dma_resv_unlock(resv); - return &bo->tbo.base; + return gobj; error: dma_resv_unlock(resv); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 7e8265da9f25..e8c76bd8c501 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -66,26 +66,12 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, bp.type = type; bp.resv = resv; bp.preferred_domain = initial_domain; -retry: bp.flags = flags; bp.domain = initial_domain; r = amdgpu_bo_create(adev, &bp, &bo); - if (r) { - if (r != -ERESTARTSYS) { - if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) { - flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - goto retry; - } - - if (initial_domain == AMDGPU_GEM_DOMAIN_VRAM) { - initial_domain |= AMDGPU_GEM_DOMAIN_GTT; - goto retry; - } - DRM_DEBUG("Failed to allocate GEM object (%ld, %d, %u, %d)\n", - size, initial_domain, alignment, r); - } + if (r) return r; - } + *obj = &bo->tbo.base; return 0; @@ -225,7 +211,7 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data, uint64_t size = args->in.bo_size; struct dma_resv *resv = NULL; struct drm_gem_object *gobj; - uint32_t handle; + uint32_t handle, initial_domain; int r; /* reject invalid gem flags */ @@ -269,9 +255,28 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data, resv = vm->root.base.bo->tbo.base.resv; } +retry: + initial_domain = (u32)(0xffffffff & args->in.domains); r = amdgpu_gem_object_create(adev, size, args->in.alignment, - (u32)(0xffffffff & args->in.domains), + initial_domain, flags, ttm_bo_type_device, resv, &gobj); + if (r) { + if (r != -ERESTARTSYS) { + if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) { + flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; + goto retry; + } + + if (initial_domain == AMDGPU_GEM_DOMAIN_VRAM) { + initial_domain |= AMDGPU_GEM_DOMAIN_GTT; + goto retry; + } + DRM_DEBUG("Failed to allocate GEM object (%llu, %d, %llu, %d)\n", + size, initial_domain, args->in.alignment, r); + } + return r; + } + if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) { if (!r) { struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj); -- cgit v1.2.3 From 998f17296234aa8d3676b4a13962eb39f4ad24e0 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Wed, 9 Dec 2020 14:57:37 +0100 Subject: xdp: Remove the xdp_attachment_flags_ok() callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 7f0a838254bd ("bpf, xdp: Maintain info on attached XDP BPF programs in net_device"), the XDP program attachment info is now maintained in the core code. This interacts badly with the xdp_attachment_flags_ok() check that prevents unloading an XDP program with different load flags than it was loaded with. In practice, two kinds of failures are seen: - An XDP program loaded without specifying a mode (and which then ends up in driver mode) cannot be unloaded if the program mode is specified on unload. - The dev_xdp_uninstall() hook always calls the driver callback with the mode set to the type of the program but an empty flags argument, which means the flags_ok() check prevents the program from being removed, leading to bpf prog reference leaks. The original reason this check was added was to avoid ambiguity when multiple programs were loaded. With the way the checks are done in the core now, this is quite simple to enforce in the core code, so let's add a check there and get rid of the xdp_attachment_flags_ok() callback entirely. Fixes: 7f0a838254bd ("bpf, xdp: Maintain info on attached XDP BPF programs in net_device") Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Acked-by: Jakub Kicinski Link: https://lore.kernel.org/bpf/160752225751.110217.10267659521308669050.stgit@toke.dk --- .../net/ethernet/netronome/nfp/nfp_net_common.c | 6 ------ drivers/net/ethernet/ti/cpsw_priv.c | 3 --- drivers/net/netdevsim/bpf.c | 3 --- include/net/xdp.h | 2 -- net/core/dev.c | 22 ++++++++++++++++++++-- net/core/xdp.c | 12 ------------ 6 files changed, 20 insertions(+), 28 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index b150da43adb2..437226866ce8 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3562,9 +3562,6 @@ static int nfp_net_xdp_setup_drv(struct nfp_net *nn, struct netdev_bpf *bpf) struct nfp_net_dp *dp; int err; - if (!xdp_attachment_flags_ok(&nn->xdp, bpf)) - return -EBUSY; - if (!prog == !nn->dp.xdp_prog) { WRITE_ONCE(nn->dp.xdp_prog, prog); xdp_attachment_setup(&nn->xdp, bpf); @@ -3593,9 +3590,6 @@ static int nfp_net_xdp_setup_hw(struct nfp_net *nn, struct netdev_bpf *bpf) { int err; - if (!xdp_attachment_flags_ok(&nn->xdp_hw, bpf)) - return -EBUSY; - err = nfp_app_xdp_offload(nn->app, nn, bpf->prog, bpf->extack); if (err) return err; diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index 31c5e36ff706..424e644724e4 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -1265,9 +1265,6 @@ static int cpsw_xdp_prog_setup(struct cpsw_priv *priv, struct netdev_bpf *bpf) if (!priv->xdpi.prog && !prog) return 0; - if (!xdp_attachment_flags_ok(&priv->xdpi, bpf)) - return -EBUSY; - WRITE_ONCE(priv->xdp_prog, prog); xdp_attachment_setup(&priv->xdpi, bpf); diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 2e90512f3bbe..85546664bdd5 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -190,9 +190,6 @@ nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf, { int err; - if (!xdp_attachment_flags_ok(xdp, bpf)) - return -EBUSY; - if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) { NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS"); return -EOPNOTSUPP; diff --git a/include/net/xdp.h b/include/net/xdp.h index 3814fb631d52..9dab2bc6f187 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -240,8 +240,6 @@ struct xdp_attachment_info { }; struct netdev_bpf; -bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, - struct netdev_bpf *bpf); void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf); diff --git a/net/core/dev.c b/net/core/dev.c index 8588ade790cb..38412e70f761 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8917,6 +8917,17 @@ static struct bpf_prog *dev_xdp_prog(struct net_device *dev, return dev->xdp_state[mode].prog; } +static u8 dev_xdp_prog_count(struct net_device *dev) +{ + u8 count = 0; + int i; + + for (i = 0; i < __MAX_XDP_MODE; i++) + if (dev->xdp_state[i].prog || dev->xdp_state[i].link) + count++; + return count; +} + u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_prog *prog = dev_xdp_prog(dev, mode); @@ -9007,6 +9018,7 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack struct bpf_xdp_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog, u32 flags) { + unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES); struct bpf_prog *cur_prog; enum bpf_xdp_mode mode; bpf_op_t bpf_op; @@ -9022,11 +9034,17 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment"); return -EINVAL; } - /* just one XDP mode bit should be set, zero defaults to SKB mode */ - if (hweight32(flags & XDP_FLAGS_MODES) > 1) { + /* just one XDP mode bit should be set, zero defaults to drv/skb mode */ + if (num_modes > 1) { NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set"); return -EINVAL; } + /* avoid ambiguity if offload + drv/skb mode progs are both loaded */ + if (!num_modes && dev_xdp_prog_count(dev) > 1) { + NL_SET_ERR_MSG(extack, + "More than one program loaded, unset mode is ambiguous"); + return -EINVAL; + } /* old_prog != NULL implies XDP_FLAGS_REPLACE is set */ if (old_prog && !(flags & XDP_FLAGS_REPLACE)) { NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified"); diff --git a/net/core/xdp.c b/net/core/xdp.c index 491ad569a79c..d900cebc0acd 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -403,18 +403,6 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem) } EXPORT_SYMBOL_GPL(__xdp_release_frame); -bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, - struct netdev_bpf *bpf) -{ - if (info->prog && (bpf->flags ^ info->flags) & XDP_FLAGS_MODES) { - NL_SET_ERR_MSG(bpf->extack, - "program loaded with different flags"); - return false; - } - return true; -} -EXPORT_SYMBOL_GPL(xdp_attachment_flags_ok); - void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { -- cgit v1.2.3 From 0b5b6e747c86e57b7ebd64ccb84314a227ccfcc2 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Wed, 9 Dec 2020 14:57:38 +0100 Subject: selftests/bpf/test_offload.py: Remove check for program load flags match MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since we just removed the xdp_attachment_flags_ok() callback, also remove the check for it in test_offload.py, and replace it with a test for the new ambiguity-avoid check when multiple programs are loaded. Fixes: 7f0a838254bd ("bpf, xdp: Maintain info on attached XDP BPF programs in net_device") Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Acked-by: Jakub Kicinski Link: https://lore.kernel.org/bpf/160752225858.110217.13036901876869496246.stgit@toke.dk --- tools/testing/selftests/bpf/test_offload.py | 22 +++++----------------- 1 file changed, 5 insertions(+), 17 deletions(-) diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 43c9cda199b8..becd27b2f4ba 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -716,13 +716,11 @@ def test_multi_prog(simdev, sim, obj, modename, modeid): fail(ret == 0, "Replaced one of programs without -force") check_extack(err, "XDP program already attached.", args) - if modename == "" or modename == "drv": - othermode = "" if modename == "drv" else "drv" - start_test("Test multi-attachment XDP - detach...") - ret, _, err = sim.unset_xdp(othermode, force=True, - fail=False, include_stderr=True) - fail(ret == 0, "Removed program with a bad mode") - check_extack(err, "program loaded with different flags.", args) + start_test("Test multi-attachment XDP - remove without mode...") + ret, _, err = sim.unset_xdp("", force=True, + fail=False, include_stderr=True) + fail(ret == 0, "Removed program without a mode flag") + check_extack(err, "More than one program loaded, unset mode is ambiguous.", args) sim.unset_xdp("offload") xdp = sim.ip_link_show(xdp=True)["xdp"] @@ -1001,16 +999,6 @@ try: check_extack(err, "native and generic XDP can't be active at the same time.", args) - ret, _, err = sim.set_xdp(obj, "", force=True, - fail=False, include_stderr=True) - fail(ret == 0, "Replaced XDP program with a program in different mode") - check_extack(err, "program loaded with different flags.", args) - - start_test("Test XDP prog remove with bad flags...") - ret, _, err = sim.unset_xdp("", force=True, - fail=False, include_stderr=True) - fail(ret == 0, "Removed program with a bad mode") - check_extack(err, "program loaded with different flags.", args) start_test("Test MTU restrictions...") ret, _ = sim.set_mtu(9000, fail=False) -- cgit v1.2.3 From e4ff5aa469403462091eb22e2b0843b894167e10 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Wed, 9 Dec 2020 14:57:39 +0100 Subject: netdevsim: Add debugfs toggle to reject BPF programs in verifier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds a new debugfs toggle ('bpf_bind_verifier_accept') that can be used to make netdevsim reject BPF programs from being accepted by the verifier. If this toggle (which defaults to true) is set to false, nsim_bpf_verify_insn() will return EOPNOTSUPP on the last instruction (after outputting the 'Hello from netdevsim' verifier message). This makes it possible to check the verification callback in the driver from test_offload.py in selftests, since the verifier now clears the verifier log on a successful load, hiding the message from the driver. Fixes: 6f8a57ccf851 ("bpf: Make verifier log more relevant by default") Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Acked-by: Jakub Kicinski Link: https://lore.kernel.org/bpf/160752225964.110217.12584017165318065332.stgit@toke.dk --- drivers/net/netdevsim/bpf.c | 12 ++++++++++-- drivers/net/netdevsim/netdevsim.h | 1 + 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 85546664bdd5..90aafb56f140 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -63,15 +63,20 @@ static int nsim_bpf_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn) { struct nsim_bpf_bound_prog *state; + int ret = 0; state = env->prog->aux->offload->dev_priv; if (state->nsim_dev->bpf_bind_verifier_delay && !insn_idx) msleep(state->nsim_dev->bpf_bind_verifier_delay); - if (insn_idx == env->prog->len - 1) + if (insn_idx == env->prog->len - 1) { pr_vlog(env, "Hello from netdevsim!\n"); - return 0; + if (!state->nsim_dev->bpf_bind_verifier_accept) + ret = -EOPNOTSUPP; + } + + return ret; } static int nsim_bpf_finalize(struct bpf_verifier_env *env) @@ -595,6 +600,9 @@ int nsim_bpf_dev_init(struct nsim_dev *nsim_dev) &nsim_dev->bpf_bind_accept); debugfs_create_u32("bpf_bind_verifier_delay", 0600, nsim_dev->ddir, &nsim_dev->bpf_bind_verifier_delay); + nsim_dev->bpf_bind_verifier_accept = true; + debugfs_create_bool("bpf_bind_verifier_accept", 0600, nsim_dev->ddir, + &nsim_dev->bpf_bind_verifier_accept); return 0; } diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 827fc80f50a0..c4e7ad2a1964 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -189,6 +189,7 @@ struct nsim_dev { struct dentry *take_snapshot; struct bpf_offload_dev *bpf_dev; bool bpf_bind_accept; + bool bpf_bind_verifier_accept; u32 bpf_bind_verifier_delay; struct dentry *ddir_bpf_bound_progs; u32 prog_id_gen; -- cgit v1.2.3 From d8b5e76ae4e02908d000397597c6bc2868362fbb Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Wed, 9 Dec 2020 14:57:40 +0100 Subject: selftests/bpf/test_offload.py: Only check verifier log on verification fails MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 6f8a57ccf851 ("bpf: Make verifier log more relevant by default"), the verifier discards log messages for successfully-verified programs. This broke test_offload.py which is looking for a verification message from the driver callback. Change test_offload.py to use the toggle in netdevsim to make the verification fail before looking for the verification message. Fixes: 6f8a57ccf851 ("bpf: Make verifier log more relevant by default") Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Acked-by: Jakub Kicinski Link: https://lore.kernel.org/bpf/160752226069.110217.12370824996153348073.stgit@toke.dk --- tools/testing/selftests/bpf/test_offload.py | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index becd27b2f4ba..61527b43f067 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -911,11 +911,18 @@ try: sim.tc_flush_filters() + start_test("Test TC offloads failure...") + sim.dfs["dev/bpf_bind_verifier_accept"] = 0 + ret, _, err = sim.cls_bpf_add_filter(obj, verbose=True, skip_sw=True, + fail=False, include_stderr=True) + fail(ret == 0, "TC filter did not reject with TC offloads enabled") + check_verifier_log(err, "[netdevsim] Hello from netdevsim!") + sim.dfs["dev/bpf_bind_verifier_accept"] = 1 + start_test("Test TC offloads work...") ret, _, err = sim.cls_bpf_add_filter(obj, verbose=True, skip_sw=True, fail=False, include_stderr=True) fail(ret != 0, "TC filter did not load with TC offloads enabled") - check_verifier_log(err, "[netdevsim] Hello from netdevsim!") start_test("Test TC offload basics...") dfs = simdev.dfs_get_bound_progs(expected=1) @@ -1032,6 +1039,15 @@ try: rm("/sys/fs/bpf/offload") sim.wait_for_flush() + start_test("Test XDP load failure...") + sim.dfs["dev/bpf_bind_verifier_accept"] = 0 + ret, _, err = bpftool_prog_load("sample_ret0.o", "/sys/fs/bpf/offload", + dev=sim['ifname'], fail=False, include_stderr=True) + fail(ret == 0, "verifier should fail on load") + check_verifier_log(err, "[netdevsim] Hello from netdevsim!") + sim.dfs["dev/bpf_bind_verifier_accept"] = 1 + sim.wait_for_flush() + start_test("Test XDP offload...") _, _, err = sim.set_xdp(obj, "offload", verbose=True, include_stderr=True) ipl = sim.ip_link_show(xdp=True) @@ -1039,7 +1055,6 @@ try: progs = bpftool_prog_list(expected=1) prog = progs[0] fail(link_xdp["id"] != prog["id"], "Loaded program has wrong ID") - check_verifier_log(err, "[netdevsim] Hello from netdevsim!") start_test("Test XDP offload is device bound...") dfs = simdev.dfs_get_bound_progs(expected=1) -- cgit v1.2.3 From 852c2ee338f0ac6026458615b624e1c496142cf6 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Wed, 9 Dec 2020 14:57:41 +0100 Subject: selftests/bpf/test_offload.py: Fix expected case of extack messages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 7f0a838254bd ("bpf, xdp: Maintain info on attached XDP BPF programs in net_device") changed the case of some of the extack messages being returned when attaching of XDP programs failed. This broke test_offload.py, so let's fix the test to reflect this. Fixes: 7f0a838254bd ("bpf, xdp: Maintain info on attached XDP BPF programs in net_device") Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Acked-by: Jakub Kicinski Link: https://lore.kernel.org/bpf/160752226175.110217.11214100824416344952.stgit@toke.dk --- tools/testing/selftests/bpf/test_offload.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 61527b43f067..51a5e4d939cc 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -1004,7 +1004,7 @@ try: fail=False, include_stderr=True) fail(ret == 0, "Replaced XDP program with a program in different mode") check_extack(err, - "native and generic XDP can't be active at the same time.", + "Native and generic XDP can't be active at the same time.", args) start_test("Test MTU restrictions...") @@ -1035,7 +1035,7 @@ try: offload = bpf_pinned("/sys/fs/bpf/offload") ret, _, err = sim.set_xdp(offload, "drv", fail=False, include_stderr=True) fail(ret == 0, "attached offloaded XDP program to drv") - check_extack(err, "using device-bound program without HW_MODE flag is not supported.", args) + check_extack(err, "Using device-bound program without HW_MODE flag is not supported.", args) rm("/sys/fs/bpf/offload") sim.wait_for_flush() -- cgit v1.2.3 From 766e62b7fcd2cf1d43e6594ba37c659dc48f7ddb Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Wed, 9 Dec 2020 14:57:42 +0100 Subject: selftests/bpf/test_offload.py: Reset ethtool features after failed setting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When setting the ethtool feature flag fails (as expected for the test), the kernel now tracks that the feature was requested to be 'off' and refuses to subsequently disable it again. So reset it back to 'on' so a subsequent disable (that's not supposed to fail) can succeed. Fixes: 417ec26477a5 ("selftests/bpf: add offload test based on netdevsim") Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Acked-by: Jakub Kicinski Link: https://lore.kernel.org/bpf/160752226280.110217.10696241563705667871.stgit@toke.dk --- tools/testing/selftests/bpf/test_offload.py | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 51a5e4d939cc..2128fbd8414b 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -946,6 +946,7 @@ try: start_test("Test disabling TC offloads is rejected while filters installed...") ret, _ = sim.set_ethtool_tc_offloads(False, fail=False) fail(ret == 0, "Driver should refuse to disable TC offloads with filters installed...") + sim.set_ethtool_tc_offloads(True) start_test("Test qdisc removal frees things...") sim.tc_flush_filters() -- cgit v1.2.3 From 8158cad13435639cd4962fb88970960f880ef6d9 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Wed, 9 Dec 2020 14:57:43 +0100 Subject: selftests/bpf/test_offload.py: Filter bpftool internal map when counting maps MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A few of the tests in test_offload.py expects to see a certain number of maps created, and checks this by counting the number of maps returned by bpftool. There is already a filter that will remove any maps already there at the beginning of the test, but bpftool now creates a map for the PID iterator rodata on each invocation, which makes the map count wrong. Fix this by also filtering the pid_iter.rodata map by name when counting. Fixes: d53dee3fe013 ("tools/bpftool: Show info for processes holding BPF map/prog/link/btf FDs") Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Acked-by: Jakub Kicinski Link: https://lore.kernel.org/bpf/160752226387.110217.9887866138149423444.stgit@toke.dk --- tools/testing/selftests/bpf/test_offload.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 2128fbd8414b..b99bb8ed3ed4 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -184,9 +184,7 @@ def bpftool_prog_list(expected=None, ns=""): def bpftool_map_list(expected=None, ns=""): _, maps = bpftool("map show", JSON=True, ns=ns, fail=True) # Remove the base maps - for m in base_maps: - if m in maps: - maps.remove(m) + maps = [m for m in maps if m not in base_maps and m.get('name') not in base_map_names] if expected is not None: if len(maps) != expected: fail(True, "%d BPF maps loaded, expected %d" % @@ -770,6 +768,9 @@ ret, progs = bpftool("prog", fail=False) skip(ret != 0, "bpftool not installed") base_progs = progs _, base_maps = bpftool("map") +base_map_names = [ + 'pid_iter.rodata' # created on each bpftool invocation +] # Check netdevsim ret, out = cmd("modprobe netdevsim", fail=False) -- cgit v1.2.3 From 323a391a220c4a234cb1e678689d7f4c3b73f863 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Fri, 4 Dec 2020 14:35:07 +0100 Subject: can: isotp: isotp_setsockopt(): block setsockopt on bound sockets The isotp socket can be widely configured in its behaviour regarding addressing types, fill-ups, receive pattern tests and link layer length. Usually all these settings need to be fixed before bind() and can not be changed afterwards. This patch adds a check to enforce the common usage pattern. Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol") Signed-off-by: Oliver Hartkopp Tested-by: Thomas Wagner Link: https://lore.kernel.org/r/20201203140604.25488-2-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde Link: https://lore.kernel.org/r/20201204133508.742120-3-mkl@pengutronix.de Signed-off-by: Jakub Kicinski --- net/can/isotp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/can/isotp.c b/net/can/isotp.c index d78ab13bd8be..26bdc3c20b7e 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1157,6 +1157,9 @@ static int isotp_setsockopt(struct socket *sock, int level, int optname, if (level != SOL_CAN_ISOTP) return -EINVAL; + if (so->bound) + return -EISCONN; + switch (optname) { case CAN_ISOTP_OPTS: if (optlen != sizeof(struct can_isotp_options)) -- cgit v1.2.3 From 340b940ea0ed12d9adbb8f72dea17d516b2019e8 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Fri, 4 Dec 2020 08:42:05 +0200 Subject: RDMA/cm: Fix an attempt to use non-valid pointer when cleaning timewait MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If cm_create_timewait_info() fails, the timewait_info pointer will contain an error value and will be used in cm_remove_remote() later. general protection fault, probably for non-canonical address 0xdffffc0000000024: 0000 [#1] SMP KASAN PTI KASAN: null-ptr-deref in range [0×0000000000000120-0×0000000000000127] CPU: 2 PID: 12446 Comm: syz-executor.3 Not tainted 5.10.0-rc5-5d4c0742a60e #27 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:cm_remove_remote.isra.0+0x24/0×170 drivers/infiniband/core/cm.c:978 Code: 84 00 00 00 00 00 41 54 55 53 48 89 fb 48 8d ab 2d 01 00 00 e8 7d bf 4b fe 48 89 ea 48 b8 00 00 00 00 00 fc ff df 48 c1 ea 03 <0f> b6 04 02 48 89 ea 83 e2 07 38 d0 7f 08 84 c0 0f 85 fc 00 00 00 RSP: 0018:ffff888013127918 EFLAGS: 00010006 RAX: dffffc0000000000 RBX: fffffffffffffff4 RCX: ffffc9000a18b000 RDX: 0000000000000024 RSI: ffffffff82edc573 RDI: fffffffffffffff4 RBP: 0000000000000121 R08: 0000000000000001 R09: ffffed1002624f1d R10: 0000000000000003 R11: ffffed1002624f1c R12: ffff888107760c70 R13: ffff888107760c40 R14: fffffffffffffff4 R15: ffff888107760c9c FS: 00007fe1ffcc1700(0000) GS:ffff88811a600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b2ff21000 CR3: 000000010f504001 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: cm_destroy_id+0x189/0×15b0 drivers/infiniband/core/cm.c:1155 cma_connect_ib drivers/infiniband/core/cma.c:4029 [inline] rdma_connect_locked+0x1100/0×17c0 drivers/infiniband/core/cma.c:4107 rdma_connect+0x2a/0×40 drivers/infiniband/core/cma.c:4140 ucma_connect+0x277/0×340 drivers/infiniband/core/ucma.c:1069 ucma_write+0x236/0×2f0 drivers/infiniband/core/ucma.c:1724 vfs_write+0x220/0×830 fs/read_write.c:603 ksys_write+0x1df/0×240 fs/read_write.c:658 do_syscall_64+0x33/0×40 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: a977049dacde ("[PATCH] IB: Add the kernel CM implementation") Link: https://lore.kernel.org/r/20201204064205.145795-1-leon@kernel.org Reviewed-by: Maor Gottlieb Reported-by: Amit Matityahu Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/cm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 012156624b82..5afd142fe8c7 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -1522,6 +1522,7 @@ int ib_send_cm_req(struct ib_cm_id *cm_id, id.local_id); if (IS_ERR(cm_id_priv->timewait_info)) { ret = PTR_ERR(cm_id_priv->timewait_info); + cm_id_priv->timewait_info = NULL; goto out; } @@ -2114,6 +2115,7 @@ static int cm_req_handler(struct cm_work *work) id.local_id); if (IS_ERR(cm_id_priv->timewait_info)) { ret = PTR_ERR(cm_id_priv->timewait_info); + cm_id_priv->timewait_info = NULL; goto destroy; } cm_id_priv->timewait_info->work.remote_id = cm_id_priv->id.remote_id; -- cgit v1.2.3 From 387270cb0b4035491c4812effd8b5af0e385a66c Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Mon, 7 Dec 2020 16:47:52 +0800 Subject: ARM: dts: mmp2-olpc-xo-1-75: clear the warnings when make dtbs The check_spi_bus_bridge() in scripts/dtc/checks.c requires that the node have "spi-slave" property must with "#address-cells = <0>" and "#size-cells = <0>". But currently both "#address-cells" and "#size-cells" properties are deleted, the corresponding default values are 2 and 1. As a result, the check fails and below warnings is displayed. arch/arm/boot/dts/mmp2.dtsi:472.23-480.6: Warning (spi_bus_bridge): \ /soc/apb@d4000000/spi@d4037000: incorrect #address-cells for SPI bus also defined at arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts:225.7-237.3 arch/arm/boot/dts/mmp2.dtsi:472.23-480.6: Warning (spi_bus_bridge): \ /soc/apb@d4000000/spi@d4037000: incorrect #size-cells for SPI bus also defined at arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts:225.7-237.3 arch/arm/boot/dts/mmp2-olpc-xo-1-75.dtb: Warning (spi_bus_reg): \ Failed prerequisite 'spi_bus_bridge' Because the value of "#size-cells" is already defined as zero in the node "ssp3: spi@d4037000" in arch/arm/boot/dts/mmp2.dtsi. So we only need to explicitly add "#address-cells = <0>" and keep "#size-cells" no change. Signed-off-by: Zhen Lei Link: https://lore.kernel.org/r/20201207084752.1665-2-thunder.leizhen@huawei.com' Signed-off-by: Arnd Bergmann --- arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts b/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts index adde62d6fce7..342304f5653a 100644 --- a/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts +++ b/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts @@ -223,8 +223,7 @@ }; &ssp3 { - /delete-property/ #address-cells; - /delete-property/ #size-cells; + #address-cells = <0>; spi-slave; status = "okay"; ready-gpios = <&gpio 125 GPIO_ACTIVE_HIGH>; -- cgit v1.2.3 From 69fe24d1d80feac4289778582cf0a15256d59baf Mon Sep 17 00:00:00 2001 From: Zou Wei Date: Tue, 1 Dec 2020 19:51:53 +0800 Subject: firmware: xilinx: Mark pm_api_features_map with static keyword Fix the following sparse warning: drivers/firmware/xilinx/zynqmp.c:32:1: warning: symbol 'pm_api_features_map' was not declared. Should it be static? Signed-off-by: Zou Wei Link: https://lore.kernel.org/r/1606823513-121578-1-git-send-email-zou_wei@huawei.com Signed-off-by: Michal Simek Signed-off-by: Arnd Bergmann --- drivers/firmware/xilinx/zynqmp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index d08ac824c993..fd95edeb702b 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -29,7 +29,7 @@ #define PM_API_FEATURE_CHECK_MAX_ORDER 7 static bool feature_check_enabled; -DEFINE_HASHTABLE(pm_api_features_map, PM_API_FEATURE_CHECK_MAX_ORDER); +static DEFINE_HASHTABLE(pm_api_features_map, PM_API_FEATURE_CHECK_MAX_ORDER); /** * struct pm_api_feature_data - PM API Feature data -- cgit v1.2.3 From c02bd115b1d25931159f89c7d9bf47a30f5d4b41 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 9 Dec 2020 14:39:56 -0800 Subject: Revert "geneve: pull IP header before ECN decapsulation" This reverts commit 4179b00c04d1 ("geneve: pull IP header before ECN decapsulation"). Eric says: "network header should have been pulled already before hitting geneve_rx()". Let's revert the syzbot fix since it's causing more harm than good, and revisit. Suggested-by: Eric Dumazet Reported-by: Jianlin Shi Fixes: 4179b00c04d1 ("geneve: pull IP header before ECN decapsulation") Link: https://bugzilla.kernel.org/show_bug.cgi?id=210569 Link: https://lore.kernel.org/netdev/CANn89iJVWfb=2i7oU1=D55rOyQnBbbikf+Mc6XHMkY7YX-yGEw@mail.gmail.com/ Signed-off-by: Jakub Kicinski --- drivers/net/geneve.c | 20 ++++---------------- 1 file changed, 4 insertions(+), 16 deletions(-) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 8ae9ce2014a4..1426bfc009bc 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -257,21 +257,11 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, skb_dst_set(skb, &tun_dst->dst); /* Ignore packet loops (and multicast echo) */ - if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) - goto rx_error; - - switch (skb_protocol(skb, true)) { - case htons(ETH_P_IP): - if (pskb_may_pull(skb, sizeof(struct iphdr))) - goto rx_error; - break; - case htons(ETH_P_IPV6): - if (pskb_may_pull(skb, sizeof(struct ipv6hdr))) - goto rx_error; - break; - default: - goto rx_error; + if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) { + geneve->dev->stats.rx_errors++; + goto drop; } + oiph = skb_network_header(skb); skb_reset_network_header(skb); @@ -308,8 +298,6 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, dev_sw_netstats_rx_add(geneve->dev, len); return; -rx_error: - geneve->dev->stats.rx_errors++; drop: /* Consume bad packet */ kfree_skb(skb); -- cgit v1.2.3 From cfb33e174fa25d9d830683a1e1b22850546103b5 Mon Sep 17 00:00:00 2001 From: Sven Auhagen Date: Wed, 11 Nov 2020 18:04:48 +0100 Subject: igb: XDP xmit back fix error code The igb XDP xmit back function should only return defined error codes. Fixes: 9cbc948b5a20 ("igb: add XDP support") Reported-by: Dan Carpenter Acked-by: Maciej Fijalkowski Signed-off-by: Sven Auhagen Tested-by: Sandeep Penigalapati Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 5fc2c381da55..08cc6f59aa2e 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2910,7 +2910,7 @@ static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) */ tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; if (unlikely(!tx_ring)) - return -ENXIO; + return IGB_XDP_CONSUMED; nq = txring_txq(tx_ring); __netif_tx_lock(nq, cpu); -- cgit v1.2.3 From b829ec1a66bc3dda4b01ab4c57d41ad1a1f82fed Mon Sep 17 00:00:00 2001 From: Sven Auhagen Date: Wed, 11 Nov 2020 18:04:49 +0100 Subject: igb: take VLAN double header into account Increase the packet header padding to include double VLAN tagging. This patch uses a macro for this. Fixes: 9cbc948b5a20 ("igb: add XDP support") Suggested-by: Maciej Fijalkowski Reviewed-by: Maciej Fijalkowski Acked-by: Maciej Fijalkowski Signed-off-by: Sven Auhagen Tested-by: Sandeep Penigalapati Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb.h | 5 +++++ drivers/net/ethernet/intel/igb/igb_main.c | 7 +++---- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 0286d2fceee4..aaa954aae574 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -138,6 +138,8 @@ struct vf_mac_filter { /* this is the size past which hardware will drop packets when setting LPE=0 */ #define MAXIMUM_ETHERNET_VLAN_SIZE 1522 +#define IGB_ETH_PKT_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) + /* Supported Rx Buffer Sizes */ #define IGB_RXBUFFER_256 256 #define IGB_RXBUFFER_1536 1536 @@ -247,6 +249,9 @@ enum igb_tx_flags { #define IGB_SFF_ADDRESSING_MODE 0x4 #define IGB_SFF_8472_UNSUP 0x00 +/* TX resources are shared between XDP and netstack + * and we need to tag the buffer type to distinguish them + */ enum igb_tx_buf_type { IGB_TYPE_SKB = 0, IGB_TYPE_XDP, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 08cc6f59aa2e..0a9198037b98 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2826,7 +2826,7 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, static int igb_xdp_setup(struct net_device *dev, struct bpf_prog *prog) { - int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + int i, frame_size = dev->mtu + IGB_ETH_PKT_HDR_PAD; struct igb_adapter *adapter = netdev_priv(dev); bool running = netif_running(dev); struct bpf_prog *old_prog; @@ -3950,8 +3950,7 @@ static int igb_sw_init(struct igb_adapter *adapter) /* set default work limits */ adapter->tx_work_limit = IGB_DEFAULT_TX_WORK; - adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + - VLAN_HLEN; + adapter->max_frame_size = netdev->mtu + IGB_ETH_PKT_HDR_PAD; adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; spin_lock_init(&adapter->nfc_lock); @@ -6491,7 +6490,7 @@ static void igb_get_stats64(struct net_device *netdev, static int igb_change_mtu(struct net_device *netdev, int new_mtu) { struct igb_adapter *adapter = netdev_priv(netdev); - int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + int max_frame = new_mtu + IGB_ETH_PKT_HDR_PAD; if (adapter->xdp_prog) { int i; -- cgit v1.2.3 From 2e2bb5594ca0a5885dc93055ab0f9b5fbcdaa403 Mon Sep 17 00:00:00 2001 From: Sven Auhagen Date: Wed, 11 Nov 2020 18:04:50 +0100 Subject: igb: XDP extack message on error Add an extack error message when the RX buffer size is too small for the frame size. Fixes: 9cbc948b5a20 ("igb: add XDP support") Suggested-by: Maciej Fijalkowski Reviewed-by: Maciej Fijalkowski Acked-by: Maciej Fijalkowski Signed-off-by: Sven Auhagen Tested-by: Sandeep Penigalapati Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 0a9198037b98..a0a310a75cc5 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2824,20 +2824,25 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, } } -static int igb_xdp_setup(struct net_device *dev, struct bpf_prog *prog) +static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf) { int i, frame_size = dev->mtu + IGB_ETH_PKT_HDR_PAD; struct igb_adapter *adapter = netdev_priv(dev); + struct bpf_prog *prog = bpf->prog, *old_prog; bool running = netif_running(dev); - struct bpf_prog *old_prog; bool need_reset; /* verify igb ring attributes are sufficient for XDP */ for (i = 0; i < adapter->num_rx_queues; i++) { struct igb_ring *ring = adapter->rx_ring[i]; - if (frame_size > igb_rx_bufsz(ring)) + if (frame_size > igb_rx_bufsz(ring)) { + NL_SET_ERR_MSG_MOD(bpf->extack, + "The RX buffer size is too small for the frame size"); + netdev_warn(dev, "XDP RX buffer size %d is too small for the frame size %d\n", + igb_rx_bufsz(ring), frame_size); return -EINVAL; + } } old_prog = xchg(&adapter->xdp_prog, prog); @@ -2869,7 +2874,7 @@ static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: - return igb_xdp_setup(dev, xdp->prog); + return igb_xdp_setup(dev, xdp); default: return -EINVAL; } @@ -6499,7 +6504,9 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu) struct igb_ring *ring = adapter->rx_ring[i]; if (max_frame > igb_rx_bufsz(ring)) { - netdev_warn(adapter->netdev, "Requested MTU size is not supported with XDP\n"); + netdev_warn(adapter->netdev, + "Requested MTU size is not supported with XDP. Max frame size is %d\n", + max_frame); return -EINVAL; } } -- cgit v1.2.3 From 681429dba99249546dda160e266e56035a2d750b Mon Sep 17 00:00:00 2001 From: Sven Auhagen Date: Wed, 11 Nov 2020 18:04:51 +0100 Subject: igb: skb add metasize for xdp add metasize if it is set in xdp Fixes: 9cbc948b5a20 ("igb: add XDP support") Suggested-by: Maciej Fijalkowski Reviewed-by: Maciej Fijalkowski Acked-by: Maciej Fijalkowski Signed-off-by: Sven Auhagen Tested-by: Sandeep Penigalapati Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a0a310a75cc5..8e412aaba0e3 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8357,6 +8357,7 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, SKB_DATA_ALIGN(xdp->data_end - xdp->data_hard_start); #endif + unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb; /* prefetch first cache line of first page */ @@ -8371,6 +8372,9 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, skb_reserve(skb, xdp->data - xdp->data_hard_start); __skb_put(skb, xdp->data_end - xdp->data); + if (metasize) + skb_metadata_set(skb, metasize); + /* pull timestamp out of packet data */ if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb); -- cgit v1.2.3 From 3eca859008a75a4ad363db65b0fe83be1a3d5ad1 Mon Sep 17 00:00:00 2001 From: Sven Auhagen Date: Wed, 11 Nov 2020 18:04:52 +0100 Subject: igb: use xdp_do_flush Since it is a new XDP implementation change xdp_do_flush_map to xdp_do_flush. Fixes: 9cbc948b5a20 ("igb: add XDP support") Suggested-by: Maciej Fijalkowski Reviewed-by: Maciej Fijalkowski Acked-by: Maciej Fijalkowski Signed-off-by: Sven Auhagen Tested-by: Sandeep Penigalapati Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 8e412aaba0e3..af6ace6c0f87 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8781,7 +8781,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) rx_ring->skb = skb; if (xdp_xmit & IGB_XDP_REDIR) - xdp_do_flush_map(); + xdp_do_flush(); if (xdp_xmit & IGB_XDP_TX) { struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); -- cgit v1.2.3 From ec107e775d84392b35db46f6c3baa441e074042e Mon Sep 17 00:00:00 2001 From: Sven Auhagen Date: Wed, 11 Nov 2020 18:04:53 +0100 Subject: igb: avoid transmit queue timeout in xdp path Since we share the transmit queue with the network stack, it is possible that we run into a transmit queue timeout. This will reset the queue. This happens under high load when XDP is using the transmit queue pretty much exclusively. netdev_start_xmit() sets the trans_start variable of the transmit queue to jiffies which is later utilized by dev_watchdog(), so to avoid timeout, let stack know that XDP xmit happened by bumping the trans_start within XDP Tx routines to jiffies. Fixes: 9cbc948b5a20 ("igb: add XDP support") Acked-by: Maciej Fijalkowski Signed-off-by: Sven Auhagen Tested-by: Sandeep Penigalapati Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index af6ace6c0f87..0d343d050973 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2919,6 +2919,8 @@ static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) nq = txring_txq(tx_ring); __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + nq->trans_start = jiffies; ret = igb_xmit_xdp_ring(adapter, tx_ring, xdpf); __netif_tx_unlock(nq); @@ -2951,6 +2953,9 @@ static int igb_xdp_xmit(struct net_device *dev, int n, nq = txring_txq(tx_ring); __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + nq->trans_start = jiffies; + for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; int err; -- cgit v1.2.3 From 75aab4e10ae6a4593a60f66d13de755d4e91f400 Mon Sep 17 00:00:00 2001 From: Björn Töpel Date: Tue, 25 Aug 2020 19:27:34 +0200 Subject: i40e: avoid premature Rx buffer reuse MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The page recycle code, incorrectly, relied on that a page fragment could not be freed inside xdp_do_redirect(). This assumption leads to that page fragments that are used by the stack/XDP redirect can be reused and overwritten. To avoid this, store the page count prior invoking xdp_do_redirect(). Longer explanation: Intel NICs have a recycle mechanism. The main idea is that a page is split into two parts. One part is owned by the driver, one part might be owned by someone else, such as the stack. t0: Page is allocated, and put on the Rx ring +--------------- used by NIC ->| upper buffer (rx_buffer) +--------------- | lower buffer +--------------- page count == USHRT_MAX rx_buffer->pagecnt_bias == USHRT_MAX t1: Buffer is received, and passed to the stack (e.g.) +--------------- | upper buff (skb) +--------------- used by NIC ->| lower buffer (rx_buffer) +--------------- page count == USHRT_MAX rx_buffer->pagecnt_bias == USHRT_MAX - 1 t2: Buffer is received, and redirected +--------------- | upper buff (skb) +--------------- used by NIC ->| lower buffer (rx_buffer) +--------------- Now, prior calling xdp_do_redirect(): page count == USHRT_MAX rx_buffer->pagecnt_bias == USHRT_MAX - 2 This means that buffer *cannot* be flipped/reused, because the skb is still using it. The problem arises when xdp_do_redirect() actually frees the segment. Then we get: page count == USHRT_MAX - 1 rx_buffer->pagecnt_bias == USHRT_MAX - 2 From a recycle perspective, the buffer can be flipped and reused, which means that the skb data area is passed to the Rx HW ring! To work around this, the page count is stored prior calling xdp_do_redirect(). Note that this is not optimal, since the NIC could actually reuse the "lower buffer" again. However, then we need to track whether XDP_REDIRECT consumed the buffer or not. Fixes: d9314c474d4f ("i40e: add support for XDP_REDIRECT") Reported-and-analyzed-by: Li RongQing Signed-off-by: Björn Töpel Tested-by: George Kuruvinakunnel Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index d43ce13a93c9..3f5825fa67c9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1850,6 +1850,7 @@ static inline bool i40e_page_is_reusable(struct page *page) * the adapter for another receive * * @rx_buffer: buffer containing the page + * @rx_buffer_pgcnt: buffer page refcount pre xdp_do_redirect() call * * If page is reusable, rx_buffer->page_offset is adjusted to point to * an unused region in the page. @@ -1872,7 +1873,8 @@ static inline bool i40e_page_is_reusable(struct page *page) * * In either case, if the page is reusable its refcount is increased. **/ -static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) +static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; @@ -1883,7 +1885,7 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_count(page) - pagecnt_bias) > 1)) + if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) return false; #else #define I40E_LAST_OFFSET \ @@ -1942,16 +1944,24 @@ static void i40e_add_rx_frag(struct i40e_ring *rx_ring, * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use * @rx_ring: rx descriptor ring to transact packets on * @size: size of buffer to add to skb + * @rx_buffer_pgcnt: buffer page refcount * * This function will pull an Rx buffer from the ring and synchronize it * for use by the CPU. */ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, - const unsigned int size) + const unsigned int size, + int *rx_buffer_pgcnt) { struct i40e_rx_buffer *rx_buffer; rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); + *rx_buffer_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buffer->page); +#else + 0; +#endif prefetch_page_address(rx_buffer->page); /* we are reusing so sync this buffer for CPU use */ @@ -2102,14 +2112,16 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, * i40e_put_rx_buffer - Clean up used buffer and either recycle or free * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: rx buffer to pull data from + * @rx_buffer_pgcnt: rx buffer page refcount pre xdp_do_redirect() call * * This function will clean up the contents of the rx_buffer. It will * either recycle the buffer or unmap it and free the associated resources. */ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer) + struct i40e_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) { - if (i40e_can_reuse_rx_page(rx_buffer)) { + if (i40e_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) { /* hand second half of page back to the ring */ i40e_reuse_rx_page(rx_ring, rx_buffer); } else { @@ -2336,6 +2348,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) while (likely(total_rx_packets < (unsigned int)budget)) { struct i40e_rx_buffer *rx_buffer; union i40e_rx_desc *rx_desc; + int rx_buffer_pgcnt; unsigned int size; u64 qword; @@ -2378,7 +2391,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) break; i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb); - rx_buffer = i40e_get_rx_buffer(rx_ring, size); + rx_buffer = i40e_get_rx_buffer(rx_ring, size, &rx_buffer_pgcnt); /* retrieve a buffer from the ring */ if (!skb) { @@ -2421,7 +2434,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) break; } - i40e_put_rx_buffer(rx_ring, rx_buffer); + i40e_put_rx_buffer(rx_ring, rx_buffer, rx_buffer_pgcnt); cleaned_count++; if (i40e_is_non_eop(rx_ring, rx_desc, skb)) -- cgit v1.2.3 From a06316dc87bdc000f7f39a315476957af2ba0f05 Mon Sep 17 00:00:00 2001 From: Björn Töpel Date: Tue, 25 Aug 2020 19:27:35 +0200 Subject: ixgbe: avoid premature Rx buffer reuse MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The page recycle code, incorrectly, relied on that a page fragment could not be freed inside xdp_do_redirect(). This assumption leads to that page fragments that are used by the stack/XDP redirect can be reused and overwritten. To avoid this, store the page count prior invoking xdp_do_redirect(). Fixes: 6453073987ba ("ixgbe: add initial support for xdp redirect") Reported-and-analyzed-by: Li RongQing Signed-off-by: Björn Töpel Tested-by: Sandeep Penigalapati Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 45ae33e15303..f3f449f53920 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1945,7 +1945,8 @@ static inline bool ixgbe_page_is_reserved(struct page *page) return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } -static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer) +static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; @@ -1956,7 +1957,7 @@ static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) + if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) return false; #else /* The last offset is a bit aggressive in that we assume the @@ -2021,11 +2022,18 @@ static void ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, static struct ixgbe_rx_buffer *ixgbe_get_rx_buffer(struct ixgbe_ring *rx_ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff **skb, - const unsigned int size) + const unsigned int size, + int *rx_buffer_pgcnt) { struct ixgbe_rx_buffer *rx_buffer; rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + *rx_buffer_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buffer->page); +#else + 0; +#endif prefetchw(rx_buffer->page); *skb = rx_buffer->skb; @@ -2055,9 +2063,10 @@ skip_sync: static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *rx_buffer, - struct sk_buff *skb) + struct sk_buff *skb, + int rx_buffer_pgcnt) { - if (ixgbe_can_reuse_rx_page(rx_buffer)) { + if (ixgbe_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) { /* hand second half of page back to the ring */ ixgbe_reuse_rx_page(rx_ring, rx_buffer); } else { @@ -2303,6 +2312,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, union ixgbe_adv_rx_desc *rx_desc; struct ixgbe_rx_buffer *rx_buffer; struct sk_buff *skb; + int rx_buffer_pgcnt; unsigned int size; /* return some buffers to hardware, one at a time is too slow */ @@ -2322,7 +2332,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, */ dma_rmb(); - rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size); + rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size, &rx_buffer_pgcnt); /* retrieve a buffer from the ring */ if (!skb) { @@ -2367,7 +2377,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, break; } - ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb); + ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb, rx_buffer_pgcnt); cleaned_count++; /* place incomplete frames back on ring for completion */ -- cgit v1.2.3 From 1beb7830d3b285b28f7cde3644d59d2590a47e51 Mon Sep 17 00:00:00 2001 From: Björn Töpel Date: Tue, 25 Aug 2020 19:27:36 +0200 Subject: ice: avoid premature Rx buffer reuse MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The page recycle code, incorrectly, relied on that a page fragment could not be freed inside xdp_do_redirect(). This assumption leads to that page fragments that are used by the stack/XDP redirect can be reused and overwritten. To avoid this, store the page count prior invoking xdp_do_redirect(). Fixes: efc2214b6047 ("ice: Add support for XDP") Reported-and-analyzed-by: Li RongQing Signed-off-by: Björn Töpel Tested-by: George Kuruvinakunnel Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_txrx.c | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index eae75260fe20..23eca2f0a03b 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -762,13 +762,15 @@ ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size) /** * ice_can_reuse_rx_page - Determine if page can be reused for another Rx * @rx_buf: buffer containing the page + * @rx_buf_pgcnt: rx_buf page refcount pre xdp_do_redirect() call * * If page is reusable, we have a green light for calling ice_reuse_rx_page, * which will assign the current buffer to the buffer that next_to_alloc is * pointing to; otherwise, the DMA mapping needs to be destroyed and * page freed */ -static bool ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) +static bool +ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf, int rx_buf_pgcnt) { unsigned int pagecnt_bias = rx_buf->pagecnt_bias; struct page *page = rx_buf->page; @@ -779,7 +781,7 @@ static bool ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_count(page) - pagecnt_bias) > 1)) + if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1)) return false; #else #define ICE_LAST_OFFSET \ @@ -864,17 +866,24 @@ ice_reuse_rx_page(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf) * @rx_ring: Rx descriptor ring to transact packets on * @skb: skb to be used * @size: size of buffer to add to skb + * @rx_buf_pgcnt: rx_buf page refcount * * This function will pull an Rx buffer from the ring and synchronize it * for use by the CPU. */ static struct ice_rx_buf * ice_get_rx_buf(struct ice_ring *rx_ring, struct sk_buff **skb, - const unsigned int size) + const unsigned int size, int *rx_buf_pgcnt) { struct ice_rx_buf *rx_buf; rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean]; + *rx_buf_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buf->page); +#else + 0; +#endif prefetchw(rx_buf->page); *skb = rx_buf->skb; @@ -1006,12 +1015,15 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, * ice_put_rx_buf - Clean up used buffer and either recycle or free * @rx_ring: Rx descriptor ring to transact packets on * @rx_buf: Rx buffer to pull data from + * @rx_buf_pgcnt: Rx buffer page count pre xdp_do_redirect() * * This function will update next_to_clean and then clean up the contents * of the rx_buf. It will either recycle the buffer or unmap it and free * the associated resources. */ -static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) +static void +ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, + int rx_buf_pgcnt) { u16 ntc = rx_ring->next_to_clean + 1; @@ -1022,7 +1034,7 @@ static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) if (!rx_buf) return; - if (ice_can_reuse_rx_page(rx_buf)) { + if (ice_can_reuse_rx_page(rx_buf, rx_buf_pgcnt)) { /* hand second half of page back to the ring */ ice_reuse_rx_page(rx_ring, rx_buf); } else { @@ -1097,6 +1109,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) struct sk_buff *skb; unsigned int size; u16 stat_err_bits; + int rx_buf_pgcnt; u16 vlan_tag = 0; u8 rx_ptype; @@ -1119,7 +1132,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) dma_rmb(); if (rx_desc->wb.rxdid == FDIR_DESC_RXDID || !rx_ring->netdev) { - ice_put_rx_buf(rx_ring, NULL); + ice_put_rx_buf(rx_ring, NULL, 0); cleaned_count++; continue; } @@ -1128,7 +1141,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) ICE_RX_FLX_DESC_PKT_LEN_M; /* retrieve a buffer from the ring */ - rx_buf = ice_get_rx_buf(rx_ring, &skb, size); + rx_buf = ice_get_rx_buf(rx_ring, &skb, size, &rx_buf_pgcnt); if (!size) { xdp.data = NULL; @@ -1168,7 +1181,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) total_rx_pkts++; cleaned_count++; - ice_put_rx_buf(rx_ring, rx_buf); + ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt); continue; construct_skb: if (skb) { @@ -1187,7 +1200,7 @@ construct_skb: break; } - ice_put_rx_buf(rx_ring, rx_buf); + ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt); cleaned_count++; /* skip if it is NOP desc */ -- cgit v1.2.3 From a379b01cd4b2aa3f12786b281a714871574e5ccb Mon Sep 17 00:00:00 2001 From: Vitaly Lifshits Date: Tue, 8 Dec 2020 12:56:32 -0600 Subject: e1000e: fix S0ix flow to allow S0i3.2 subset entry Changed a configuration in the flows to align with architecture requirements to achieve S0i3.2 substate. This helps both i219V and i219LM configurations. Also fixed a typo in the previous commit 632fbd5eb5b0 ("e1000e: fix S0ix flows for cable connected case"). Fixes: 632fbd5eb5b0 ("e1000e: fix S0ix flows for cable connected case"). Signed-off-by: Vitaly Lifshits Tested-by: Aaron Brown Signed-off-by: Tony Nguyen Reviewed-by: Alexander Duyck Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20201208185632.151052-1-mario.limonciello@dell.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/e1000e/netdev.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index b30f00891c03..128ab6898070 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6475,13 +6475,13 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter) /* Ungate PGCB clock */ mac_data = er32(FEXTNVM9); - mac_data |= BIT(28); + mac_data &= ~BIT(28); ew32(FEXTNVM9, mac_data); /* Enable K1 off to enable mPHY Power Gating */ mac_data = er32(FEXTNVM6); mac_data |= BIT(31); - ew32(FEXTNVM12, mac_data); + ew32(FEXTNVM6, mac_data); /* Enable mPHY power gating for any link and speed */ mac_data = er32(FEXTNVM8); @@ -6525,11 +6525,11 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) /* Disable K1 off */ mac_data = er32(FEXTNVM6); mac_data &= ~BIT(31); - ew32(FEXTNVM12, mac_data); + ew32(FEXTNVM6, mac_data); /* Disable Ungate PGCB clock */ mac_data = er32(FEXTNVM9); - mac_data &= ~BIT(28); + mac_data |= BIT(28); ew32(FEXTNVM9, mac_data); /* Cancel not waking from dynamic -- cgit v1.2.3 From a770bf515613c6e12ae904c3593e26016de99448 Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Tue, 8 Dec 2020 23:13:51 +0100 Subject: ethtool: fix stack overflow in ethnl_parse_bitset() Syzbot reported a stack overflow in bitmap_from_arr32() called from ethnl_parse_bitset() when bitset from netlink message is longer than target bitmap length. While ethnl_compact_sanity_checks() makes sure that trailing part is all zeros (i.e. the request does not try to touch bits kernel does not recognize), we also need to cap change_bits to nbits so that we don't try to write past the prepared bitmaps. Fixes: 88db6d1e4f62 ("ethtool: add ethnl_parse_bitset() helper") Reported-by: syzbot+9d39fa49d4df294aab93@syzkaller.appspotmail.com Signed-off-by: Michal Kubecek Link: https://lore.kernel.org/r/3487ee3a98e14cd526f55b6caaa959d2dcbcad9f.1607465316.git.mkubecek@suse.cz Signed-off-by: Jakub Kicinski --- net/ethtool/bitset.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index 1fb3603d92ad..0515d6604b3b 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -628,6 +628,8 @@ int ethnl_parse_bitset(unsigned long *val, unsigned long *mask, return ret; change_bits = nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]); + if (change_bits > nbits) + change_bits = nbits; bitmap_from_arr32(val, nla_data(tb[ETHTOOL_A_BITSET_VALUE]), change_bits); if (change_bits < nbits) -- cgit v1.2.3 From 8ef44b6fe49d2b8d03ba9aa69063612b474f963b Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 8 Dec 2020 09:55:08 -0800 Subject: tcp: Retain ECT bits for tos reflection For DCTCP, we have to retain the ECT bits set by the congestion control algorithm on the socket when reflecting syn TOS in syn-ack, in order to make ECN work properly. Fixes: ac8f1710c12b ("tcp: reflect tos value received in SYN to the socket") Reported-by: Alexander Duyck Signed-off-by: Wei Wang Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 7 +++++-- net/ipv6/tcp_ipv6.c | 7 +++++-- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 8391aa29e7a4..595dcc3afac5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -984,7 +984,8 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : + (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | + (inet_sk(sk)->tos & INET_ECN_MASK) : inet_sk(sk)->tos; if (!INET_ECN_is_capable(tos) && @@ -1541,7 +1542,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = prandom_u32(); - /* Set ToS of the new socket based upon the value of incoming SYN. */ + /* Set ToS of the new socket based upon the value of incoming SYN. + * ECT bits are set later in tcp_init_transfer(). + */ if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 992cbf3eb9e3..991dc36f95ff 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -528,7 +528,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : + (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | + (np->tclass & INET_ECN_MASK) : np->tclass; if (!INET_ECN_is_capable(tclass) && @@ -1320,7 +1321,9 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * if (np->repflow) newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); - /* Set ToS of the new socket based upon the value of incoming SYN. */ + /* Set ToS of the new socket based upon the value of incoming SYN. + * ECT bits are set later in tcp_init_transfer(). + */ if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; -- cgit v1.2.3 From 5137d303659d8c324e67814b1cc2e1bc0c0d9836 Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Tue, 8 Dec 2020 10:48:35 +0800 Subject: net: flow_offload: Fix memory leak for indirect flow block The offending commit introduces a cleanup callback that is invoked when the driver module is removed to clean up the tunnel device flow block. But it returns on the first iteration of the for loop. The remaining indirect flow blocks will never be freed. Fixes: 1fac52da5942 ("net: flow_offload: consolidate indirect flow_block infrastructure") CC: Pablo Neira Ayuso Signed-off-by: Chris Mi Reviewed-by: Roi Dayan --- net/core/flow_offload.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index d4474c812b64..715b67f6c62f 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -381,10 +381,8 @@ static void __flow_block_indr_cleanup(void (*release)(void *cb_priv), list_for_each_entry_safe(this, next, &flow_block_indr_list, indr.list) { if (this->release == release && - this->indr.cb_priv == cb_priv) { + this->indr.cb_priv == cb_priv) list_move(&this->indr.list, cleanup_list); - return; - } } } -- cgit v1.2.3 From 299bcb55ecd1412f6df606e9dc0912d55610029e Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Tue, 8 Dec 2020 22:57:59 -0500 Subject: tcp: fix cwnd-limited bug for TSO deferral where we send nothing When cwnd is not a multiple of the TSO skb size of N*MSS, we can get into persistent scenarios where we have the following sequence: (1) ACK for full-sized skb of N*MSS arrives -> tcp_write_xmit() transmit full-sized skb with N*MSS -> move pacing release time forward -> exit tcp_write_xmit() because pacing time is in the future (2) TSQ callback or TCP internal pacing timer fires -> try to transmit next skb, but TSO deferral finds remainder of available cwnd is not big enough to trigger an immediate send now, so we defer sending until the next ACK. (3) repeat... So we can get into a case where we never mark ourselves as cwnd-limited for many seconds at a time, even with bulk/infinite-backlog senders, because: o In case (1) above, every time in tcp_write_xmit() we have enough cwnd to send a full-sized skb, we are not fully using the cwnd (because cwnd is not a multiple of the TSO skb size). So every time we send data, we are not cwnd limited, and so in the cwnd-limited tracking code in tcp_cwnd_validate() we mark ourselves as not cwnd-limited. o In case (2) above, every time in tcp_write_xmit() that we try to transmit the "remainder" of the cwnd but defer, we set the local variable is_cwnd_limited to true, but we do not send any packets, so sent_pkts is zero, so we don't call the cwnd-limited logic to update tp->is_cwnd_limited. Fixes: ca8a22634381 ("tcp: make cwnd-limited checks measurement-based, and gentler") Reported-by: Ingemar Johansson Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Acked-by: Soheil Hassas Yeganeh Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20201209035759.1225145-1-ncardwell.kernel@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_output.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index bf48cd73e967..99011768c264 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1880,7 +1880,8 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) * window, and remember whether we were cwnd-limited then. */ if (!before(tp->snd_una, tp->max_packets_seq) || - tp->packets_out > tp->max_packets_out) { + tp->packets_out > tp->max_packets_out || + is_cwnd_limited) { tp->max_packets_out = tp->packets_out; tp->max_packets_seq = tp->snd_nxt; tp->is_cwnd_limited = is_cwnd_limited; @@ -2702,6 +2703,10 @@ repair: else tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED); + is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); + if (likely(sent_pkts || is_cwnd_limited)) + tcp_cwnd_validate(sk, is_cwnd_limited); + if (likely(sent_pkts)) { if (tcp_in_cwnd_reduction(sk)) tp->prr_out += sent_pkts; @@ -2709,8 +2714,6 @@ repair: /* Send one loss probe per tail loss episode. */ if (push_one != 2) tcp_schedule_loss_probe(sk, false); - is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); - tcp_cwnd_validate(sk, is_cwnd_limited); return false; } return !tp->packets_out && !tcp_write_queue_empty(sk); -- cgit v1.2.3 From fed91613c9dd455dd154b22fa8e11b8526466082 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 9 Dec 2020 15:03:38 +0200 Subject: net/mlx4_en: Avoid scheduling restart task if it is already running Add restarting state flag to avoid scheduling another restart task while such task is already running. Change task name from watchdog_task to restart_task to better fit the task role. Fixes: 1e338db56e5a ("mlx4_en: Fix a race at restart task") Signed-off-by: Moshe Shemesh Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 20 +++++++++++++------- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 7 ++++++- 2 files changed, 19 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 106513f772c3..1a2b0bd64aa9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1378,8 +1378,10 @@ static void mlx4_en_tx_timeout(struct net_device *dev, unsigned int txqueue) tx_ring->cons, tx_ring->prod); priv->port_stats.tx_timeout++; - en_dbg(DRV, priv, "Scheduling watchdog\n"); - queue_work(mdev->workqueue, &priv->watchdog_task); + if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) { + en_dbg(DRV, priv, "Scheduling port restart\n"); + queue_work(mdev->workqueue, &priv->restart_task); + } } @@ -1829,6 +1831,7 @@ int mlx4_en_start_port(struct net_device *dev) local_bh_enable(); } + clear_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state); netif_tx_start_all_queues(dev); netif_device_attach(dev); @@ -1999,7 +2002,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach) static void mlx4_en_restart(struct work_struct *work) { struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, - watchdog_task); + restart_task); struct mlx4_en_dev *mdev = priv->mdev; struct net_device *dev = priv->dev; @@ -2377,7 +2380,7 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) if (netif_running(dev)) { mutex_lock(&mdev->state_lock); if (!mdev->device_up) { - /* NIC is probably restarting - let watchdog task reset + /* NIC is probably restarting - let restart task reset * the port */ en_dbg(DRV, priv, "Change MTU called with card down!?\n"); } else { @@ -2386,7 +2389,9 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) if (err) { en_err(priv, "Failed restarting port:%d\n", priv->port); - queue_work(mdev->workqueue, &priv->watchdog_task); + if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, + &priv->state)) + queue_work(mdev->workqueue, &priv->restart_task); } } mutex_unlock(&mdev->state_lock); @@ -2792,7 +2797,8 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) if (err) { en_err(priv, "Failed starting port %d for XDP change\n", priv->port); - queue_work(mdev->workqueue, &priv->watchdog_task); + if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) + queue_work(mdev->workqueue, &priv->restart_task); } } @@ -3165,7 +3171,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv->counter_index = MLX4_SINK_COUNTER_INDEX(mdev->dev); spin_lock_init(&priv->stats_lock); INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode); - INIT_WORK(&priv->watchdog_task, mlx4_en_restart); + INIT_WORK(&priv->restart_task, mlx4_en_restart); INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate); INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats); INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index a46efe37cfa9..fd9535bde1b8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -530,6 +530,10 @@ struct mlx4_en_stats_bitmap { struct mutex mutex; /* for mutual access to stats bitmap */ }; +enum { + MLX4_EN_STATE_FLAG_RESTARTING, +}; + struct mlx4_en_priv { struct mlx4_en_dev *mdev; struct mlx4_en_port_profile *prof; @@ -595,7 +599,7 @@ struct mlx4_en_priv { struct mlx4_en_cq *rx_cq[MAX_RX_RINGS]; struct mlx4_qp drop_qp; struct work_struct rx_mode_task; - struct work_struct watchdog_task; + struct work_struct restart_task; struct work_struct linkstate_task; struct delayed_work stats_task; struct delayed_work service_task; @@ -641,6 +645,7 @@ struct mlx4_en_priv { u32 pflags; u8 rss_key[MLX4_EN_RSS_KEY_SIZE]; u8 rss_hash_fn; + unsigned long state; }; enum mlx4_en_wol { -- cgit v1.2.3 From ba603d9d7b1215c72513d7c7aa02b6775fd4891b Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 9 Dec 2020 15:03:39 +0200 Subject: net/mlx4_en: Handle TX error CQE In case error CQE was found while polling TX CQ, the QP is in error state and all posted WQEs will generate error CQEs without any data transmitted. Fix it by reopening the channels, via same method used for TX timeout handling. In addition add some more info on error CQE and WQE for debug. Fixes: bd2f631d7c60 ("net/mlx4_en: Notify user when TX ring in error state") Signed-off-by: Moshe Shemesh Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_tx.c | 40 +++++++++++++++++++++----- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 5 ++++ 3 files changed, 39 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 1a2b0bd64aa9..6f290319b617 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1735,6 +1735,7 @@ int mlx4_en_start_port(struct net_device *dev) mlx4_en_deactivate_cq(priv, cq); goto tx_err; } + clear_bit(MLX4_EN_TX_RING_STATE_RECOVERING, &tx_ring->state); if (t != TX_XDP) { tx_ring->tx_queue = netdev_get_tx_queue(dev, i); tx_ring->recycle_ring = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 3ddb7268e415..59b097cda327 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -392,6 +392,35 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring) return cnt; } +static void mlx4_en_handle_err_cqe(struct mlx4_en_priv *priv, struct mlx4_err_cqe *err_cqe, + u16 cqe_index, struct mlx4_en_tx_ring *ring) +{ + struct mlx4_en_dev *mdev = priv->mdev; + struct mlx4_en_tx_info *tx_info; + struct mlx4_en_tx_desc *tx_desc; + u16 wqe_index; + int desc_size; + + en_err(priv, "CQE error - cqn 0x%x, ci 0x%x, vendor syndrome: 0x%x syndrome: 0x%x\n", + ring->sp_cqn, cqe_index, err_cqe->vendor_err_syndrome, err_cqe->syndrome); + print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, err_cqe, sizeof(*err_cqe), + false); + + wqe_index = be16_to_cpu(err_cqe->wqe_index) & ring->size_mask; + tx_info = &ring->tx_info[wqe_index]; + desc_size = tx_info->nr_txbb << LOG_TXBB_SIZE; + en_err(priv, "Related WQE - qpn 0x%x, wqe index 0x%x, wqe size 0x%x\n", ring->qpn, + wqe_index, desc_size); + tx_desc = ring->buf + (wqe_index << LOG_TXBB_SIZE); + print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, tx_desc, desc_size, false); + + if (test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) + return; + + en_err(priv, "Scheduling port restart\n"); + queue_work(mdev->workqueue, &priv->restart_task); +} + int mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int napi_budget) { @@ -438,13 +467,10 @@ int mlx4_en_process_tx_cq(struct net_device *dev, dma_rmb(); if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == - MLX4_CQE_OPCODE_ERROR)) { - struct mlx4_err_cqe *cqe_err = (struct mlx4_err_cqe *)cqe; - - en_err(priv, "CQE error - vendor syndrome: 0x%x syndrome: 0x%x\n", - cqe_err->vendor_err_syndrome, - cqe_err->syndrome); - } + MLX4_CQE_OPCODE_ERROR)) + if (!test_and_set_bit(MLX4_EN_TX_RING_STATE_RECOVERING, &ring->state)) + mlx4_en_handle_err_cqe(priv, (struct mlx4_err_cqe *)cqe, index, + ring); /* Skip over last polled CQE */ new_index = be16_to_cpu(cqe->wqe_index) & size_mask; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index fd9535bde1b8..30378e4c90b5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -271,6 +271,10 @@ struct mlx4_en_page_cache { } buf[MLX4_EN_CACHE_SIZE]; }; +enum { + MLX4_EN_TX_RING_STATE_RECOVERING, +}; + struct mlx4_en_priv; struct mlx4_en_tx_ring { @@ -317,6 +321,7 @@ struct mlx4_en_tx_ring { * Only queue_stopped might be used if BQL is not properly working. */ unsigned long queue_stopped; + unsigned long state; struct mlx4_hwq_resources sp_wqres; struct mlx4_qp sp_qp; struct mlx4_qp_context sp_context; -- cgit v1.2.3 From 80db2a087f425b63f0163bc95217abd01c637cb5 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 9 Dec 2020 17:59:53 -0800 Subject: Input: cros_ec_keyb - send 'scancodes' in addition to key events To let userspace know what 'scancodes' should be used in EVIOCGKEYCODE and EVIOCSKEYCODE ioctls, we should send EV_MSC/MSC_SCAN events in addition to EV_KEY/KEY_* events. The driver already declared MSC_SCAN capability, so it is only matter of actually sending the events. Link: https://lore.kernel.org/r/X87aOaSptPTvZ3nZ@google.com Acked-by: Rajat Jain Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/cros_ec_keyb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c index fc1793ca2f17..0a748aed0265 100644 --- a/drivers/input/keyboard/cros_ec_keyb.c +++ b/drivers/input/keyboard/cros_ec_keyb.c @@ -183,6 +183,7 @@ static void cros_ec_keyb_process(struct cros_ec_keyb *ckdev, "changed: [r%d c%d]: byte %02x\n", row, col, new_state); + input_event(idev, EV_MSC, MSC_SCAN, pos); input_report_key(idev, keycodes[pos], new_state); } -- cgit v1.2.3 From c5b58c8c860db330c0b8b891b69014ee9d470dab Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Wed, 9 Dec 2020 16:34:22 +0800 Subject: drm/amd/pm: typo fix (CUSTOM -> COMPUTE) The "COMPUTE" was wrongly spelled as "CUSTOM". Signed-off-by: Evan Quan Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 5.9.x --- drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 895d89bea7fa..cf7c4f0e0a0b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -217,7 +217,7 @@ static struct cmn2asic_mapping sienna_cichlid_workload_map[PP_SMC_POWER_PROFILE_ WORKLOAD_MAP(PP_SMC_POWER_PROFILE_POWERSAVING, WORKLOAD_PPLIB_POWER_SAVING_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO, WORKLOAD_PPLIB_VIDEO_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR, WORKLOAD_PPLIB_VR_BIT), - WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_CUSTOM_BIT), + WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_COMPUTE_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT), }; -- cgit v1.2.3 From 7fdd375e383097a785bb65c66802e468f398bf82 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Wed, 9 Dec 2020 16:48:41 +0100 Subject: net: sched: Fix dump of MPLS_OPT_LSE_LABEL attribute in cls_flower TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL is a u32 attribute (MPLS label is 20 bits long). Fixes the following bug: $ tc filter add dev ethX ingress protocol mpls_uc \ flower mpls lse depth 2 label 256 \ action drop $ tc filter show dev ethX ingress filter protocol mpls_uc pref 49152 flower chain 0 filter protocol mpls_uc pref 49152 flower chain 0 handle 0x1 eth_type 8847 mpls lse depth 2 label 0 <-- invalid label 0, should be 256 ... Fixes: 61aec25a6db5 ("cls_flower: Support filtering on multiple MPLS Label Stack Entries") Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index fed18fd2c50b..1319986693fc 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2424,8 +2424,8 @@ static int fl_dump_key_mpls_opt_lse(struct sk_buff *skb, return err; } if (lse_mask->mpls_label) { - err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL, - lse_key->mpls_label); + err = nla_put_u32(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL, + lse_key->mpls_label); if (err) return err; } -- cgit v1.2.3 From 177745beebe39773004921d6bffd6c94c77dca32 Mon Sep 17 00:00:00 2001 From: Mickey Rachamim Date: Wed, 9 Dec 2020 15:47:39 +0200 Subject: MAINTAINERS: Add entry for Marvell Prestera Ethernet Switch driver Add maintainers info for new Marvell Prestera Ethernet switch driver. Signed-off-by: Mickey Rachamim Signed-off-by: David S. Miller --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index ebe4829cdd4d..0381eb273944 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10555,6 +10555,13 @@ S: Supported F: Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst F: drivers/net/ethernet/marvell/octeontx2/af/ +MARVELL PRESTERA ETHERNET SWITCH DRIVER +M: Vadym Kochan +M: Taras Chornyi +S: Supported +W: https://github.com/Marvell-switching/switchdev-prestera +F: drivers/net/ethernet/marvell/prestera/ + MARVELL SOC MMC/SD/SDIO CONTROLLER DRIVER M: Nicolas Pitre S: Odd Fixes -- cgit v1.2.3 From e2782f560c298efc2e23c7e54b3acf54e8a6ba72 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 9 Dec 2020 13:53:31 -0800 Subject: Revert "dm raid: remove unnecessary discard limits for raid10" This reverts commit f0e90b6c663a7e3b4736cb318c6c7c589f152c28. Matthew Ruffell reported data corruption in raid10 due to the changes in discard handling [1]. Revert these changes before we find a proper fix. [1] https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1907262/ Cc: Matthew Ruffell Cc: Xiao Ni Cc: Mike Snitzer Acked-by: Mike Snitzer Signed-off-by: Song Liu --- drivers/md/dm-raid.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 9c1f7c4de65b..dc8568ab96f2 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3728,6 +3728,17 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits) blk_limits_io_min(limits, chunk_size_bytes); blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs)); + + /* + * RAID10 personality requires bio splitting, + * RAID0/1/4/5/6 don't and process large discard bios properly. + */ + if (rs_is_raid10(rs)) { + limits->discard_granularity = max(chunk_size_bytes, + limits->discard_granularity); + limits->max_discard_sectors = min_not_zero(rs->md.chunk_sectors, + limits->max_discard_sectors); + } } static void raid_postsuspend(struct dm_target *ti) -- cgit v1.2.3 From 82fe9af77cd11ea7bdc133ceed1f7f5fc08f7d25 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 9 Dec 2020 11:38:11 -0800 Subject: Revert "md/raid10: improve discard request for far layout" This reverts commit d3ee2d8415a6256c1c41e1be36e80e640c3e6359. Matthew Ruffell reported data corruption in raid10 due to the changes in discard handling [1]. Revert these changes before we find a proper fix. [1] https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1907262/ Cc: Matthew Ruffell Cc: Xiao Ni Signed-off-by: Song Liu --- drivers/md/raid10.c | 86 ++++++++++++++--------------------------------------- drivers/md/raid10.h | 1 - 2 files changed, 23 insertions(+), 64 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index b7bca6703df8..05773ee1b5ba 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1534,28 +1534,6 @@ static struct bio *raid10_split_bio(struct r10conf *conf, return bio; } -static void raid_end_discard_bio(struct r10bio *r10bio) -{ - struct r10conf *conf = r10bio->mddev->private; - struct r10bio *first_r10bio; - - while (atomic_dec_and_test(&r10bio->remaining)) { - - allow_barrier(conf); - - if (!test_bit(R10BIO_Discard, &r10bio->state)) { - first_r10bio = (struct r10bio *)r10bio->master_bio; - free_r10bio(r10bio); - r10bio = first_r10bio; - } else { - md_write_end(r10bio->mddev); - bio_endio(r10bio->master_bio); - free_r10bio(r10bio); - break; - } - } -} - static void raid10_end_discard_request(struct bio *bio) { struct r10bio *r10_bio = bio->bi_private; @@ -1582,7 +1560,11 @@ static void raid10_end_discard_request(struct bio *bio) rdev = conf->mirrors[dev].rdev; } - raid_end_discard_bio(r10_bio); + if (atomic_dec_and_test(&r10_bio->remaining)) { + md_write_end(r10_bio->mddev); + raid_end_bio_io(r10_bio); + } + rdev_dec_pending(rdev, conf->mddev); } @@ -1595,9 +1577,7 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) { struct r10conf *conf = mddev->private; struct geom *geo = &conf->geo; - struct r10bio *r10_bio, *first_r10bio; - int far_copies = geo->far_copies; - bool first_copy = true; + struct r10bio *r10_bio; int disk; sector_t chunk; @@ -1636,20 +1616,30 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) if (bio_sectors(bio) < stripe_size*2) goto out; - /* For far and far offset layout, if bio is not aligned with stripe size, - * it splits the part that is not aligned with strip size. + /* For far offset layout, if bio is not aligned with stripe size, it splits + * the part that is not aligned with strip size. */ div_u64_rem(bio_start, stripe_size, &remainder); - if ((far_copies > 1) && remainder) { + if (geo->far_offset && remainder) { split_size = stripe_size - remainder; bio = raid10_split_bio(conf, bio, split_size, false); } div_u64_rem(bio_end, stripe_size, &remainder); - if ((far_copies > 1) && remainder) { + if (geo->far_offset && remainder) { split_size = bio_sectors(bio) - remainder; bio = raid10_split_bio(conf, bio, split_size, true); } + r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO); + r10_bio->mddev = mddev; + r10_bio->state = 0; + r10_bio->sectors = 0; + memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * geo->raid_disks); + + wait_blocked_dev(mddev, r10_bio); + + r10_bio->master_bio = bio; + bio_start = bio->bi_iter.bi_sector; bio_end = bio_end_sector(bio); @@ -1675,28 +1665,6 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) end_disk_offset = (bio_end & geo->chunk_mask) + (last_stripe_index << geo->chunk_shift); -retry_discard: - r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO); - r10_bio->mddev = mddev; - r10_bio->state = 0; - r10_bio->sectors = 0; - memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * geo->raid_disks); - wait_blocked_dev(mddev, r10_bio); - - /* For far layout it needs more than one r10bio to cover all regions. - * Inspired by raid10_sync_request, we can use the first r10bio->master_bio - * to record the discard bio. Other r10bio->master_bio record the first - * r10bio. The first r10bio only release after all other r10bios finish. - * The discard bio returns only first r10bio finishes - */ - if (first_copy) { - r10_bio->master_bio = bio; - set_bit(R10BIO_Discard, &r10_bio->state); - first_copy = false; - first_r10bio = r10_bio; - } else - r10_bio->master_bio = (struct bio *)first_r10bio; - rcu_read_lock(); for (disk = 0; disk < geo->raid_disks; disk++) { struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev); @@ -1787,19 +1755,11 @@ retry_discard: } } - if (!geo->far_offset && --far_copies) { - first_stripe_index += geo->stride >> geo->chunk_shift; - start_disk_offset += geo->stride; - last_stripe_index += geo->stride >> geo->chunk_shift; - end_disk_offset += geo->stride; - atomic_inc(&first_r10bio->remaining); - raid_end_discard_bio(r10_bio); - wait_barrier(conf); - goto retry_discard; + if (atomic_dec_and_test(&r10_bio->remaining)) { + md_write_end(r10_bio->mddev); + raid_end_bio_io(r10_bio); } - raid_end_discard_bio(r10_bio); - return 0; out: allow_barrier(conf); diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index 1461fd55311b..79cd2b7d3128 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -179,6 +179,5 @@ enum r10bio_state { R10BIO_Previous, /* failfast devices did receive failfast requests. */ R10BIO_FailFast, - R10BIO_Discard, }; #endif -- cgit v1.2.3 From d7cb6be0d0cdced2a7a96bd80a8f835e77ec5204 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 9 Dec 2020 11:43:08 -0800 Subject: Revert "md/raid10: improve raid10 discard request" This reverts commit bcc90d280465ebd51ab8688be86e1f00c62dccf9. Matthew Ruffell reported data corruption in raid10 due to the changes in discard handling [1]. Revert these changes before we find a proper fix. [1] https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1907262/ Cc: Matthew Ruffell Cc: Xiao Ni Signed-off-by: Song Liu --- drivers/md/raid10.c | 256 +--------------------------------------------------- 1 file changed, 1 insertion(+), 255 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 05773ee1b5ba..4ad8447fa868 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1516,256 +1516,6 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors) raid10_write_request(mddev, bio, r10_bio); } -static struct bio *raid10_split_bio(struct r10conf *conf, - struct bio *bio, sector_t sectors, bool want_first) -{ - struct bio *split; - - split = bio_split(bio, sectors, GFP_NOIO, &conf->bio_split); - bio_chain(split, bio); - allow_barrier(conf); - if (want_first) { - submit_bio_noacct(bio); - bio = split; - } else - submit_bio_noacct(split); - wait_barrier(conf); - - return bio; -} - -static void raid10_end_discard_request(struct bio *bio) -{ - struct r10bio *r10_bio = bio->bi_private; - struct r10conf *conf = r10_bio->mddev->private; - struct md_rdev *rdev = NULL; - int dev; - int slot, repl; - - /* - * We don't care the return value of discard bio - */ - if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) - set_bit(R10BIO_Uptodate, &r10_bio->state); - - dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl); - if (repl) - rdev = conf->mirrors[dev].replacement; - if (!rdev) { - /* raid10_remove_disk uses smp_mb to make sure rdev is set to - * replacement before setting replacement to NULL. It can read - * rdev first without barrier protect even replacment is NULL - */ - smp_rmb(); - rdev = conf->mirrors[dev].rdev; - } - - if (atomic_dec_and_test(&r10_bio->remaining)) { - md_write_end(r10_bio->mddev); - raid_end_bio_io(r10_bio); - } - - rdev_dec_pending(rdev, conf->mddev); -} - -/* There are some limitations to handle discard bio - * 1st, the discard size is bigger than stripe_size*2. - * 2st, if the discard bio spans reshape progress, we use the old way to - * handle discard bio - */ -static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) -{ - struct r10conf *conf = mddev->private; - struct geom *geo = &conf->geo; - struct r10bio *r10_bio; - - int disk; - sector_t chunk; - unsigned int stripe_size; - sector_t split_size; - - sector_t bio_start, bio_end; - sector_t first_stripe_index, last_stripe_index; - sector_t start_disk_offset; - unsigned int start_disk_index; - sector_t end_disk_offset; - unsigned int end_disk_index; - unsigned int remainder; - - if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) - return -EAGAIN; - - wait_barrier(conf); - - /* Check reshape again to avoid reshape happens after checking - * MD_RECOVERY_RESHAPE and before wait_barrier - */ - if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) - goto out; - - stripe_size = geo->raid_disks << geo->chunk_shift; - bio_start = bio->bi_iter.bi_sector; - bio_end = bio_end_sector(bio); - - /* Maybe one discard bio is smaller than strip size or across one stripe - * and discard region is larger than one stripe size. For far offset layout, - * if the discard region is not aligned with stripe size, there is hole - * when we submit discard bio to member disk. For simplicity, we only - * handle discard bio which discard region is bigger than stripe_size*2 - */ - if (bio_sectors(bio) < stripe_size*2) - goto out; - - /* For far offset layout, if bio is not aligned with stripe size, it splits - * the part that is not aligned with strip size. - */ - div_u64_rem(bio_start, stripe_size, &remainder); - if (geo->far_offset && remainder) { - split_size = stripe_size - remainder; - bio = raid10_split_bio(conf, bio, split_size, false); - } - div_u64_rem(bio_end, stripe_size, &remainder); - if (geo->far_offset && remainder) { - split_size = bio_sectors(bio) - remainder; - bio = raid10_split_bio(conf, bio, split_size, true); - } - - r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO); - r10_bio->mddev = mddev; - r10_bio->state = 0; - r10_bio->sectors = 0; - memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * geo->raid_disks); - - wait_blocked_dev(mddev, r10_bio); - - r10_bio->master_bio = bio; - - bio_start = bio->bi_iter.bi_sector; - bio_end = bio_end_sector(bio); - - /* raid10 uses chunk as the unit to store data. It's similar like raid0. - * One stripe contains the chunks from all member disk (one chunk from - * one disk at the same HBA address). For layout detail, see 'man md 4' - */ - chunk = bio_start >> geo->chunk_shift; - chunk *= geo->near_copies; - first_stripe_index = chunk; - start_disk_index = sector_div(first_stripe_index, geo->raid_disks); - if (geo->far_offset) - first_stripe_index *= geo->far_copies; - start_disk_offset = (bio_start & geo->chunk_mask) + - (first_stripe_index << geo->chunk_shift); - - chunk = bio_end >> geo->chunk_shift; - chunk *= geo->near_copies; - last_stripe_index = chunk; - end_disk_index = sector_div(last_stripe_index, geo->raid_disks); - if (geo->far_offset) - last_stripe_index *= geo->far_copies; - end_disk_offset = (bio_end & geo->chunk_mask) + - (last_stripe_index << geo->chunk_shift); - - rcu_read_lock(); - for (disk = 0; disk < geo->raid_disks; disk++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[disk].replacement); - - r10_bio->devs[disk].bio = NULL; - r10_bio->devs[disk].repl_bio = NULL; - - if (rdev && (test_bit(Faulty, &rdev->flags))) - rdev = NULL; - if (rrdev && (test_bit(Faulty, &rrdev->flags))) - rrdev = NULL; - if (!rdev && !rrdev) - continue; - - if (rdev) { - r10_bio->devs[disk].bio = bio; - atomic_inc(&rdev->nr_pending); - } - if (rrdev) { - r10_bio->devs[disk].repl_bio = bio; - atomic_inc(&rrdev->nr_pending); - } - } - rcu_read_unlock(); - - atomic_set(&r10_bio->remaining, 1); - for (disk = 0; disk < geo->raid_disks; disk++) { - sector_t dev_start, dev_end; - struct bio *mbio, *rbio = NULL; - struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[disk].replacement); - - /* - * Now start to calculate the start and end address for each disk. - * The space between dev_start and dev_end is the discard region. - * - * For dev_start, it needs to consider three conditions: - * 1st, the disk is before start_disk, you can imagine the disk in - * the next stripe. So the dev_start is the start address of next - * stripe. - * 2st, the disk is after start_disk, it means the disk is at the - * same stripe of first disk - * 3st, the first disk itself, we can use start_disk_offset directly - */ - if (disk < start_disk_index) - dev_start = (first_stripe_index + 1) * mddev->chunk_sectors; - else if (disk > start_disk_index) - dev_start = first_stripe_index * mddev->chunk_sectors; - else - dev_start = start_disk_offset; - - if (disk < end_disk_index) - dev_end = (last_stripe_index + 1) * mddev->chunk_sectors; - else if (disk > end_disk_index) - dev_end = last_stripe_index * mddev->chunk_sectors; - else - dev_end = end_disk_offset; - - /* It only handles discard bio which size is >= stripe size, so - * dev_end > dev_start all the time - */ - if (r10_bio->devs[disk].bio) { - mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); - mbio->bi_end_io = raid10_end_discard_request; - mbio->bi_private = r10_bio; - r10_bio->devs[disk].bio = mbio; - r10_bio->devs[disk].devnum = disk; - atomic_inc(&r10_bio->remaining); - md_submit_discard_bio(mddev, rdev, mbio, - dev_start + choose_data_offset(r10_bio, rdev), - dev_end - dev_start); - bio_endio(mbio); - } - if (r10_bio->devs[disk].repl_bio) { - rbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); - rbio->bi_end_io = raid10_end_discard_request; - rbio->bi_private = r10_bio; - r10_bio->devs[disk].repl_bio = rbio; - r10_bio->devs[disk].devnum = disk; - atomic_inc(&r10_bio->remaining); - md_submit_discard_bio(mddev, rrdev, rbio, - dev_start + choose_data_offset(r10_bio, rrdev), - dev_end - dev_start); - bio_endio(rbio); - } - } - - if (atomic_dec_and_test(&r10_bio->remaining)) { - md_write_end(r10_bio->mddev); - raid_end_bio_io(r10_bio); - } - - return 0; -out: - allow_barrier(conf); - return -EAGAIN; -} - static bool raid10_make_request(struct mddev *mddev, struct bio *bio) { struct r10conf *conf = mddev->private; @@ -1780,10 +1530,6 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio) if (!md_write_start(mddev, bio)) return false; - if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) - if (!raid10_handle_discard(mddev, bio)) - return true; - /* * If this request crosses a chunk boundary, we need to split * it. @@ -4023,7 +3769,7 @@ static int raid10_run(struct mddev *mddev) if (mddev->queue) { blk_queue_max_discard_sectors(mddev->queue, - UINT_MAX); + mddev->chunk_sectors); blk_queue_max_write_same_sectors(mddev->queue, 0); blk_queue_max_write_zeroes_sectors(mddev->queue, 0); blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); -- cgit v1.2.3 From 4e2c6567efdd6f252e1874c41c8db4abfb0a9bf3 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 9 Dec 2020 11:43:43 -0800 Subject: Revert "md/raid10: pull codes that wait for blocked dev into one function" This reverts commit f046f5d0d79cdb968f219ce249e497fd1accf484. Matthew Ruffell reported data corruption in raid10 due to the changes in discard handling [1]. Revert these changes before we find a proper fix. [1] https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1907262/ Cc: Matthew Ruffell Cc: Xiao Ni Signed-off-by: Song Liu --- drivers/md/raid10.c | 118 +++++++++++++++++++++++----------------------------- 1 file changed, 51 insertions(+), 67 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 4ad8447fa868..f2ec44fda1a0 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1275,75 +1275,12 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, } } -static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio) -{ - int i; - struct r10conf *conf = mddev->private; - struct md_rdev *blocked_rdev; - -retry_wait: - blocked_rdev = NULL; - rcu_read_lock(); - for (i = 0; i < conf->copies; i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[i].replacement); - if (rdev == rrdev) - rrdev = NULL; - if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) { - atomic_inc(&rdev->nr_pending); - blocked_rdev = rdev; - break; - } - if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) { - atomic_inc(&rrdev->nr_pending); - blocked_rdev = rrdev; - break; - } - - if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) { - sector_t first_bad; - sector_t dev_sector = r10_bio->devs[i].addr; - int bad_sectors; - int is_bad; - - /* Discard request doesn't care the write result - * so it doesn't need to wait blocked disk here. - */ - if (!r10_bio->sectors) - continue; - - is_bad = is_badblock(rdev, dev_sector, r10_bio->sectors, - &first_bad, &bad_sectors); - if (is_bad < 0) { - /* Mustn't write here until the bad block - * is acknowledged - */ - atomic_inc(&rdev->nr_pending); - set_bit(BlockedBadBlocks, &rdev->flags); - blocked_rdev = rdev; - break; - } - } - } - rcu_read_unlock(); - - if (unlikely(blocked_rdev)) { - /* Have to wait for this device to get unblocked, then retry */ - allow_barrier(conf); - raid10_log(conf->mddev, "%s wait rdev %d blocked", - __func__, blocked_rdev->raid_disk); - md_wait_for_blocked_rdev(blocked_rdev, mddev); - wait_barrier(conf); - goto retry_wait; - } -} - static void raid10_write_request(struct mddev *mddev, struct bio *bio, struct r10bio *r10_bio) { struct r10conf *conf = mddev->private; int i; + struct md_rdev *blocked_rdev; sector_t sectors; int max_sectors; @@ -1401,9 +1338,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, r10_bio->read_slot = -1; /* make sure repl_bio gets freed */ raid10_find_phys(conf, r10_bio); - - wait_blocked_dev(mddev, r10_bio); - +retry_write: + blocked_rdev = NULL; rcu_read_lock(); max_sectors = r10_bio->sectors; @@ -1414,6 +1350,16 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, conf->mirrors[d].replacement); if (rdev == rrdev) rrdev = NULL; + if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) { + atomic_inc(&rdev->nr_pending); + blocked_rdev = rdev; + break; + } + if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) { + atomic_inc(&rrdev->nr_pending); + blocked_rdev = rrdev; + break; + } if (rdev && (test_bit(Faulty, &rdev->flags))) rdev = NULL; if (rrdev && (test_bit(Faulty, &rrdev->flags))) @@ -1434,6 +1380,15 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, is_bad = is_badblock(rdev, dev_sector, max_sectors, &first_bad, &bad_sectors); + if (is_bad < 0) { + /* Mustn't write here until the bad block + * is acknowledged + */ + atomic_inc(&rdev->nr_pending); + set_bit(BlockedBadBlocks, &rdev->flags); + blocked_rdev = rdev; + break; + } if (is_bad && first_bad <= dev_sector) { /* Cannot write here at all */ bad_sectors -= (dev_sector - first_bad); @@ -1469,6 +1424,35 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, } rcu_read_unlock(); + if (unlikely(blocked_rdev)) { + /* Have to wait for this device to get unblocked, then retry */ + int j; + int d; + + for (j = 0; j < i; j++) { + if (r10_bio->devs[j].bio) { + d = r10_bio->devs[j].devnum; + rdev_dec_pending(conf->mirrors[d].rdev, mddev); + } + if (r10_bio->devs[j].repl_bio) { + struct md_rdev *rdev; + d = r10_bio->devs[j].devnum; + rdev = conf->mirrors[d].replacement; + if (!rdev) { + /* Race with remove_disk */ + smp_mb(); + rdev = conf->mirrors[d].rdev; + } + rdev_dec_pending(rdev, mddev); + } + } + allow_barrier(conf); + raid10_log(conf->mddev, "wait rdev %d blocked", blocked_rdev->raid_disk); + md_wait_for_blocked_rdev(blocked_rdev, mddev); + wait_barrier(conf); + goto retry_write; + } + if (max_sectors < r10_bio->sectors) r10_bio->sectors = max_sectors; -- cgit v1.2.3 From 17c28c2a068730e9d065a0e4ed03beed074d8997 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 9 Dec 2020 11:44:20 -0800 Subject: Revert "md/raid10: extend r10bio devs to raid disks" This reverts commit 8650a889017cb1f6ea6813ccf83a2e9f6fa49dd3. Matthew Ruffell reported data corruption in raid10 due to the changes in discard handling [1]. Revert these changes before we find a proper fix. [1] https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1907262/ Cc: Matthew Ruffell Cc: Xiao Ni Signed-off-by: Song Liu --- drivers/md/raid10.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index f2ec44fda1a0..3b598a3cb462 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -91,7 +91,7 @@ static inline struct r10bio *get_resync_r10bio(struct bio *bio) static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data) { struct r10conf *conf = data; - int size = offsetof(struct r10bio, devs[conf->geo.raid_disks]); + int size = offsetof(struct r10bio, devs[conf->copies]); /* allocate a r10bio with room for raid_disks entries in the * bios array */ @@ -238,7 +238,7 @@ static void put_all_bios(struct r10conf *conf, struct r10bio *r10_bio) { int i; - for (i = 0; i < conf->geo.raid_disks; i++) { + for (i = 0; i < conf->copies; i++) { struct bio **bio = & r10_bio->devs[i].bio; if (!BIO_SPECIAL(*bio)) bio_put(*bio); @@ -327,7 +327,7 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio, int slot; int repl = 0; - for (slot = 0; slot < conf->geo.raid_disks; slot++) { + for (slot = 0; slot < conf->copies; slot++) { if (r10_bio->devs[slot].bio == bio) break; if (r10_bio->devs[slot].repl_bio == bio) { @@ -336,6 +336,7 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio, } } + BUG_ON(slot == conf->copies); update_head_pos(slot, r10_bio); if (slotp) @@ -1492,7 +1493,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors) r10_bio->mddev = mddev; r10_bio->sector = bio->bi_iter.bi_sector; r10_bio->state = 0; - memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->geo.raid_disks); + memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->copies); if (bio_data_dir(bio) == READ) raid10_read_request(mddev, bio, r10_bio); -- cgit v1.2.3 From 57a0f3a81ef21fe51d6223aa78a1a890098d4ada Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 9 Dec 2020 11:44:42 -0800 Subject: Revert "md: add md_submit_discard_bio() for submitting discard bio" This reverts commit 2628089b74d5a64bd0bcb5d247a18f78d7b6f4d0. Matthew Ruffell reported data corruption in raid10 due to the changes in discard handling [1]. Revert these changes before we find a proper fix. [1] https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1907262/ Cc: Matthew Ruffell Cc: Xiao Ni Signed-off-by: Song Liu --- drivers/md/md.c | 20 -------------------- drivers/md/md.h | 2 -- drivers/md/raid0.c | 14 ++++++++++++-- 3 files changed, 12 insertions(+), 24 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 98bac4f304ae..0037c6ecab65 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8582,26 +8582,6 @@ void md_write_end(struct mddev *mddev) EXPORT_SYMBOL(md_write_end); -/* This is used by raid0 and raid10 */ -void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, - struct bio *bio, sector_t start, sector_t size) -{ - struct bio *discard_bio = NULL; - - if (__blkdev_issue_discard(rdev->bdev, start, size, - GFP_NOIO, 0, &discard_bio) || !discard_bio) - return; - - bio_chain(discard_bio, bio); - bio_clone_blkg_association(discard_bio, bio); - if (mddev->gendisk) - trace_block_bio_remap(bdev_get_queue(rdev->bdev), - discard_bio, disk_devt(mddev->gendisk), - bio->bi_iter.bi_sector); - submit_bio_noacct(discard_bio); -} -EXPORT_SYMBOL(md_submit_discard_bio); - /* md_allow_write(mddev) * Calling this ensures that the array is marked 'active' so that writes * may proceed without blocking. It is important to call this before diff --git a/drivers/md/md.h b/drivers/md/md.h index ccfb69868c2e..2175a5ac4f7c 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -713,8 +713,6 @@ extern void md_write_end(struct mddev *mddev); extern void md_done_sync(struct mddev *mddev, int blocks, int ok); extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); -extern void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, - struct bio *bio, sector_t start, sector_t size); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 6f44177593a5..35843df15b5e 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -477,6 +477,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) for (disk = 0; disk < zone->nb_dev; disk++) { sector_t dev_start, dev_end; + struct bio *discard_bio = NULL; struct md_rdev *rdev; if (disk < start_disk_index) @@ -499,9 +500,18 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) rdev = conf->devlist[(zone - conf->strip_zone) * conf->strip_zone[0].nb_dev + disk]; - md_submit_discard_bio(mddev, rdev, bio, + if (__blkdev_issue_discard(rdev->bdev, dev_start + zone->dev_start + rdev->data_offset, - dev_end - dev_start); + dev_end - dev_start, GFP_NOIO, 0, &discard_bio) || + !discard_bio) + continue; + bio_chain(discard_bio, bio); + bio_clone_blkg_association(discard_bio, bio); + if (mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(rdev->bdev), + discard_bio, disk_devt(mddev->gendisk), + bio->bi_iter.bi_sector); + submit_bio_noacct(discard_bio); } bio_endio(bio); } -- cgit v1.2.3 From ce6520b0eafad5962ffc21dc47cd7bd3250e9045 Mon Sep 17 00:00:00 2001 From: Chris Chiu Date: Wed, 9 Dec 2020 20:24:47 -0800 Subject: Input: i8042 - add Acer laptops to the i8042 reset list The touchpad operates in Basic Mode by default in the Acer BIOS setup, but some Aspire/TravelMate models require the i8042 to be reset in order to be correctly detected. Signed-off-by: Chris Chiu Link: https://lore.kernel.org/r/20201207071250.15021-1-chiu@endlessos.org Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/serio/i8042-x86ia64io.h | 42 +++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 7ecb65176c1a..3a2dcf0805f1 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -611,6 +611,48 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "AOA150"), }, }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A114-31"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A314-31"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-31"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-132"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-332"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-432"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate Spin B118-RN"), + }, + }, { /* Advent 4211 */ .matches = { -- cgit v1.2.3 From 6bea0225a4bf14a58af71cb9677a756921469e46 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 9 Dec 2020 20:16:10 +0900 Subject: zonefs: fix page reference and BIO leak In zonefs_file_dio_append(), the pages obtained using bio_iov_iter_get_pages() are not released on completion of the REQ_OP_APPEND BIO, nor when bio_iov_iter_get_pages() fails. Furthermore, a call to bio_put() is missing when bio_iov_iter_get_pages() fails. Fix these resource leaks by adding BIO resource release code (bio_put()i and bio_release_pages()) at the end of the function after the BIO execution and add a jump to this resource cleanup code in case of bio_iov_iter_get_pages() failure. While at it, also fix the call to task_io_account_write() to be passed the correct BIO size instead of bio_iov_iter_get_pages() return value. Reported-by: Christoph Hellwig Fixes: 02ef12a663c7 ("zonefs: use REQ_OP_ZONE_APPEND for sync DIO") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig --- fs/zonefs/super.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index ff5930be096c..bec47f2d074b 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -691,21 +691,23 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) bio->bi_opf |= REQ_FUA; ret = bio_iov_iter_get_pages(bio, from); - if (unlikely(ret)) { - bio_io_error(bio); - return ret; - } + if (unlikely(ret)) + goto out_release; + size = bio->bi_iter.bi_size; - task_io_account_write(ret); + task_io_account_write(size); if (iocb->ki_flags & IOCB_HIPRI) bio_set_polled(bio, iocb); ret = submit_bio_wait(bio); + zonefs_file_write_dio_end_io(iocb, size, ret, 0); + +out_release: + bio_release_pages(bio, false); bio_put(bio); - zonefs_file_write_dio_end_io(iocb, size, ret, 0); if (ret >= 0) { iocb->ki_pos += size; return size; -- cgit v1.2.3 From 29ac40cbed2bc06fa218ca25d7f5e280d3d08a25 Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Wed, 11 Nov 2020 11:09:45 -0500 Subject: x86/mm/mem_encrypt: Fix definition of PMD_FLAGS_DEC_WP The PAT bit is in different locations for 4k and 2M/1G page table entries. Add a definition for _PAGE_LARGE_CACHE_MASK to represent the three caching bits (PWT, PCD, PAT), similar to _PAGE_CACHE_MASK for 4k pages, and use it in the definition of PMD_FLAGS_DEC_WP to get the correct PAT index for write-protected pages. Fixes: 6ebcb060713f ("x86/mm: Add support to encrypt the kernel in-place") Signed-off-by: Arvind Sankar Signed-off-by: Borislav Petkov Tested-by: Tom Lendacky Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20201111160946.147341-1-nivedita@alum.mit.edu --- arch/x86/include/asm/pgtable_types.h | 1 + arch/x86/mm/mem_encrypt_identity.c | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 816b31c68550..394757ee030a 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -155,6 +155,7 @@ enum page_cache_mode { #define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) #define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT) +#define _PAGE_LARGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT_LARGE) #define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC)) #define _PAGE_CACHE_WP (cachemode2protval(_PAGE_CACHE_MODE_WP)) diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index 733b983f3a89..6c5eb6f3f14f 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -45,8 +45,8 @@ #define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) #define PMD_FLAGS_DEC PMD_FLAGS_LARGE -#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ - (_PAGE_PAT | _PAGE_PWT)) +#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_LARGE_CACHE_MASK) | \ + (_PAGE_PAT_LARGE | _PAGE_PWT)) #define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC) -- cgit v1.2.3 From 06c5fe9b12dde1b62821f302f177c972bb1c81f9 Mon Sep 17 00:00:00 2001 From: Xiaochen Shen Date: Fri, 4 Dec 2020 14:27:59 +0800 Subject: x86/resctrl: Fix incorrect local bandwidth when mba_sc is enabled The MBA software controller (mba_sc) is a feedback loop which periodically reads MBM counters and tries to restrict the bandwidth below a user-specified value. It tags along the MBM counter overflow handler to do the updates with 1s interval in mbm_update() and update_mba_bw(). The purpose of mbm_update() is to periodically read the MBM counters to make sure that the hardware counter doesn't wrap around more than once between user samplings. mbm_update() calls __mon_event_count() for local bandwidth updating when mba_sc is not enabled, but calls mbm_bw_count() instead when mba_sc is enabled. __mon_event_count() will not be called for local bandwidth updating in MBM counter overflow handler, but it is still called when reading MBM local bandwidth counter file 'mbm_local_bytes', the call path is as below: rdtgroup_mondata_show() mon_event_read() mon_event_count() __mon_event_count() In __mon_event_count(), m->chunks is updated by delta chunks which is calculated from previous MSR value (m->prev_msr) and current MSR value. When mba_sc is enabled, m->chunks is also updated in mbm_update() by mistake by the delta chunks which is calculated from m->prev_bw_msr instead of m->prev_msr. But m->chunks is not used in update_mba_bw() in the mba_sc feedback loop. When reading MBM local bandwidth counter file, m->chunks was changed unexpectedly by mbm_bw_count(). As a result, the incorrect local bandwidth counter which calculated from incorrect m->chunks is shown to the user. Fix this by removing incorrect m->chunks updating in mbm_bw_count() in MBM counter overflow handler, and always calling __mon_event_count() in mbm_update() to make sure that the hardware local bandwidth counter doesn't wrap around. Test steps: # Run workload with aggressive memory bandwidth (e.g., 10 GB/s) git clone https://github.com/intel/intel-cmt-cat && cd intel-cmt-cat && make ./tools/membw/membw -c 0 -b 10000 --read # Enable MBA software controller mount -t resctrl resctrl -o mba_MBps /sys/fs/resctrl # Create control group c1 mkdir /sys/fs/resctrl/c1 # Set MB throttle to 6 GB/s echo "MB:0=6000;1=6000" > /sys/fs/resctrl/c1/schemata # Write PID of the workload to tasks file echo `pidof membw` > /sys/fs/resctrl/c1/tasks # Read local bytes counters twice with 1s interval, the calculated # local bandwidth is not as expected (approaching to 6 GB/s): local_1=`cat /sys/fs/resctrl/c1/mon_data/mon_L3_00/mbm_local_bytes` sleep 1 local_2=`cat /sys/fs/resctrl/c1/mon_data/mon_L3_00/mbm_local_bytes` echo "local b/w (bytes/s):" `expr $local_2 - $local_1` Before fix: local b/w (bytes/s): 11076796416 After fix: local b/w (bytes/s): 5465014272 Fixes: ba0f26d8529c (x86/intel_rdt/mba_sc: Prepare for feedback loop) Signed-off-by: Xiaochen Shen Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Cc: Link: https://lkml.kernel.org/r/1607063279-19437-1-git-send-email-xiaochen.shen@intel.com --- arch/x86/kernel/cpu/resctrl/monitor.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 54dffe574e67..a98519a3a2e6 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -279,7 +279,6 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) return; chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width); - m->chunks += chunks; cur_bw = (chunks * r->mon_scale) >> 20; if (m->delta_comp) @@ -450,15 +449,14 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) } if (is_mbm_local_enabled()) { rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; + __mon_event_count(rmid, &rr); /* * Call the MBA software controller only for the * control groups and when user has enabled * the software controller explicitly. */ - if (!is_mba_sc(NULL)) - __mon_event_count(rmid, &rr); - else + if (is_mba_sc(NULL)) mbm_bw_count(rmid, &rr); } } -- cgit v1.2.3 From b02709587ea3d699a608568ee8157d8db4fd8cae Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 8 Dec 2020 19:01:51 +0100 Subject: bpf: Fix propagation of 32-bit signed bounds from 64-bit bounds. The 64-bit signed bounds should not affect 32-bit signed bounds unless the verifier knows that upper 32-bits are either all 1s or all 0s. For example the register with smin_value==1 doesn't mean that s32_min_value is also equal to 1, since smax_value could be larger than 32-bit subregister can hold. The verifier refines the smax/s32_max return value from certain helpers in do_refine_retval_range(). Teach the verifier to recognize that smin/s32_min value is also bounded. When both smin and smax bounds fit into 32-bit subregister the verifier can propagate those bounds. Fixes: 3f50f132d840 ("bpf: Verifier, do explicit ALU32 bounds tracking") Reported-by: Jean-Philippe Brucker Acked-by: John Fastabend Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1388bf733071..53fe6ef6d931 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1298,9 +1298,7 @@ static void __reg_combine_32_into_64(struct bpf_reg_state *reg) static bool __reg64_bound_s32(s64 a) { - if (a > S32_MIN && a < S32_MAX) - return true; - return false; + return a > S32_MIN && a < S32_MAX; } static bool __reg64_bound_u32(u64 a) @@ -1314,10 +1312,10 @@ static void __reg_combine_64_into_32(struct bpf_reg_state *reg) { __mark_reg32_unbounded(reg); - if (__reg64_bound_s32(reg->smin_value)) + if (__reg64_bound_s32(reg->smin_value) && __reg64_bound_s32(reg->smax_value)) { reg->s32_min_value = (s32)reg->smin_value; - if (__reg64_bound_s32(reg->smax_value)) reg->s32_max_value = (s32)reg->smax_value; + } if (__reg64_bound_u32(reg->umin_value)) reg->u32_min_value = (u32)reg->umin_value; if (__reg64_bound_u32(reg->umax_value)) @@ -4895,6 +4893,8 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, ret_reg->smax_value = meta->msize_max_value; ret_reg->s32_max_value = meta->msize_max_value; + ret_reg->smin_value = -MAX_ERRNO; + ret_reg->s32_min_value = -MAX_ERRNO; __reg_deduce_bounds(ret_reg); __reg_bound_offset(ret_reg); __update_reg_bounds(ret_reg); -- cgit v1.2.3 From 511a76bcb0ce242a19153658b25437906cc6070e Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Tue, 8 Dec 2020 19:01:52 +0100 Subject: selftests/bpf: Add test for signed 32-bit bound check bug After a 32-bit load followed by a branch, the verifier would reduce the maximum bound of the register to 0x7fffffff, allowing a user to bypass bound checks. Ensure such a program is rejected. In the second test, the 64-bit compare should not sufficient to determine whether the signed 32-bit lower bound is 0, so the verifier should reject the second branch. Signed-off-by: Jean-Philippe Brucker Acked-by: John Fastabend Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/verifier/bounds.c | 41 +++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index dac40de3f868..57ed67b86074 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -703,3 +703,44 @@ .fixup_map_hash_8b = { 3 }, .result = ACCEPT, }, +{ + "bounds checks after 32-bit truncation. test 1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + /* This used to reduce the max bound to 0x7fffffff */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0x7fffffff, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .errstr_unpriv = "R0 leaks addr", + .result_unpriv = REJECT, + .result = ACCEPT, +}, +{ + "bounds checks after 32-bit truncation. test 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_1, 1, 1), + BPF_JMP32_IMM(BPF_JSLT, BPF_REG_1, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .errstr_unpriv = "R0 leaks addr", + .result_unpriv = REJECT, + .result = ACCEPT, +}, -- cgit v1.2.3 From 77ce220c0549dcc3db8226c61c60e83fc59dfafc Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Tue, 8 Dec 2020 19:01:53 +0100 Subject: selftests/bpf: Fix array access with signed variable test The test fails because of a recent fix to the verifier, even though this program is valid. In details what happens is: 7: (61) r1 = *(u32 *)(r0 +0) Load a 32-bit value, with signed bounds [S32_MIN, S32_MAX]. The bounds of the 64-bit value are [0, U32_MAX]... 8: (65) if r1 s> 0xffffffff goto pc+1 ... therefore this is always true (the operand is sign-extended). 10: (b4) w2 = 11 11: (6d) if r2 s> r1 goto pc+1 When true, the 64-bit bounds become [0, 10]. The 32-bit bounds are still [S32_MIN, 10]. 13: (64) w1 <<= 2 Because this is a 32-bit operation, the verifier propagates the new 32-bit bounds to the 64-bit ones, and the knowledge gained from insn 11 is lost. 14: (0f) r0 += r1 15: (7a) *(u64 *)(r0 +0) = 4 Then the verifier considers r0 unbounded here, rejecting the test. To make the test work, change insn 8 to check the sign of the 32-bit value. Signed-off-by: Jean-Philippe Brucker Acked-by: John Fastabend Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/verifier/array_access.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c index 1c4b1939f5a8..bed53b561e04 100644 --- a/tools/testing/selftests/bpf/verifier/array_access.c +++ b/tools/testing/selftests/bpf/verifier/array_access.c @@ -68,7 +68,7 @@ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), - BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 0xffffffff, 1), + BPF_JMP32_IMM(BPF_JSGT, BPF_REG_1, 0xffffffff, 1), BPF_MOV32_IMM(BPF_REG_1, 0), BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES), BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1), -- cgit v1.2.3 From 3615bdf6d9b19db12b1589861609b4f1c6a8d303 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Tue, 8 Dec 2020 19:01:54 +0100 Subject: selftests/bpf: Fix "dubious pointer arithmetic" test The verifier trace changed following a bugfix. After checking the 64-bit sign, only the upper bit mask is known, not bit 31. Update the test accordingly. Signed-off-by: Jean-Philippe Brucker Acked-by: John Fastabend Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/prog_tests/align.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c index 52414058a627..5861446d0777 100644 --- a/tools/testing/selftests/bpf/prog_tests/align.c +++ b/tools/testing/selftests/bpf/prog_tests/align.c @@ -456,10 +456,10 @@ static struct bpf_align_test tests[] = { */ {7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>=0 */ - {9, "R5=inv(id=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"}, + {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* packet pointer + nonnegative (4n+2) */ - {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"}, - {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"}, + {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. * We checked the bounds, but it might have been able * to overflow if the packet pointer started in the @@ -467,7 +467,7 @@ static struct bpf_align_test tests[] = { * So we did not get a 'range' on R6, and the access * attempt will fail. */ - {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"}, + {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, } }, { -- cgit v1.2.3 From 38bf8cd821be292e7d8e6f6283d67c5d9708f887 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 9 Dec 2020 12:21:13 +0100 Subject: selftests: fix poll error in udpgro.sh The test program udpgso_bench_rx always invokes the poll() syscall with a timeout of 10ms. If a larger timeout is specified via the command line, udpgso_bench_rx is supposed to do multiple poll() calls till the timeout is expired or an event is received. Currently the poll() loop errors out after the first invocation with no events, and may causes self-tests failure alike: failed GRO with custom segment size ./udpgso_bench_rx: poll: 0x0 expected 0x1 This change addresses the issue allowing the poll() loop to consume all the configured timeout. Fixes: ada641ff6ed3 ("selftests: fixes for UDP GRO") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- tools/testing/selftests/net/udpgso_bench_rx.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index db3d4a8b5a4c..76a24052f4b4 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -113,6 +113,9 @@ static void do_poll(int fd, int timeout_ms) interrupted = true; break; } + + /* no events and more time to wait, do poll again */ + continue; } if (pfd.revents != POLLIN) error(1, errno, "poll: 0x%x expected 0x%x\n", -- cgit v1.2.3 From 1c87b85162975627d684a234d7347ef630f0e3aa Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 24 Nov 2020 19:15:18 -0500 Subject: NFS: Fix rpcrdma_inline_fixup() crash with new LISTXATTRS operation By switching to an XFS-backed export, I am able to reproduce the ibcomp worker crash on my client with xfstests generic/013. For the failing LISTXATTRS operation, xdr_inline_pages() is called with page_len=12 and buflen=128. - When ->send_request() is called, rpcrdma_marshal_req() does not set up a Reply chunk because buflen is smaller than the inline threshold. Thus rpcrdma_convert_iovs() does not get invoked at all and the transport's XDRBUF_SPARSE_PAGES logic is not invoked on the receive buffer. - During reply processing, rpcrdma_inline_fixup() tries to copy received data into rq_rcv_buf->pages because page_len is positive. But there are no receive pages because rpcrdma_marshal_req() never allocated them. The result is that the ibcomp worker faults and dies. Sometimes that causes a visible crash, and sometimes it results in a transport hang without other symptoms. RPC/RDMA's XDRBUF_SPARSE_PAGES support is not entirely correct, and should eventually be fixed or replaced. However, my preference is that upper-layer operations should explicitly allocate their receive buffers (using GFP_KERNEL) when possible, rather than relying on XDRBUF_SPARSE_PAGES. Reported-by: Olga kornievskaia Suggested-by: Olga kornievskaia Fixes: c10a75145feb ("NFSv4.2: add the extended attribute proc functions.") Signed-off-by: Chuck Lever Reviewed-by: Olga kornievskaia Reviewed-by: Frank van der Linden Tested-by: Olga kornievskaia Signed-off-by: Anna Schumaker --- fs/nfs/nfs42proc.c | 21 +++++++++++++-------- fs/nfs/nfs42xdr.c | 1 - 2 files changed, 13 insertions(+), 9 deletions(-) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 2b2211d1234e..4fc61e3d098d 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -1241,12 +1241,13 @@ static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf, .rpc_resp = &res, }; u32 xdrlen; - int ret, np; + int ret, np, i; + ret = -ENOMEM; res.scratch = alloc_page(GFP_KERNEL); if (!res.scratch) - return -ENOMEM; + goto out; xdrlen = nfs42_listxattr_xdrsize(buflen); if (xdrlen > server->lxasize) @@ -1254,9 +1255,12 @@ static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf, np = xdrlen / PAGE_SIZE + 1; pages = kcalloc(np, sizeof(struct page *), GFP_KERNEL); - if (pages == NULL) { - __free_page(res.scratch); - return -ENOMEM; + if (!pages) + goto out_free_scratch; + for (i = 0; i < np; i++) { + pages[i] = alloc_page(GFP_KERNEL); + if (!pages[i]) + goto out_free_pages; } arg.xattr_pages = pages; @@ -1271,14 +1275,15 @@ static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf, *eofp = res.eof; } +out_free_pages: while (--np >= 0) { if (pages[np]) __free_page(pages[np]); } - - __free_page(res.scratch); kfree(pages); - +out_free_scratch: + __free_page(res.scratch); +out: return ret; } diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 6e060a88f98c..8432bd6b95f0 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -1528,7 +1528,6 @@ static void nfs4_xdr_enc_listxattrs(struct rpc_rqst *req, rpc_prepare_reply_pages(req, args->xattr_pages, 0, args->count, hdr.replen); - req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES; encode_nops(&hdr); } -- cgit v1.2.3 From fe8eb820e388ca81643443b6208001ab516d1cf6 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Mon, 23 Nov 2020 22:15:17 -0500 Subject: NFSv4.2: Fix 5 seconds delay when doing inter server copy Since commit b4868b44c5628 ("NFSv4: Wait for stateid updates after CLOSE/OPEN_DOWNGRADE"), every inter server copy operation suffers 5 seconds delay regardless of the size of the copy. The delay is from nfs_set_open_stateid_locked when the check by nfs_stateid_is_sequential fails because the seqid in both nfs4_state and nfs4_stateid are 0. Fix __nfs42_ssc_open to delay setting of NFS_OPEN_STATE in nfs4_state, until after the call to update_open_stateid, to indicate this is the 1st open. This fix is part of a 2 patches, the other patch is the fix in the source server to return the stateid for COPY_NOTIFY request with seqid 1 instead of 0. Fixes: ce0887ac96d3 ("NFSD add nfs4 inter ssc to nfsd4_copy") Signed-off-by: Dai Ngo Signed-off-by: Anna Schumaker --- fs/nfs/nfs4file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 9d354de613da..57b3821d975a 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -377,10 +377,10 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, goto out_stateowner; set_bit(NFS_SRV_SSC_COPY_STATE, &ctx->state->flags); - set_bit(NFS_OPEN_STATE, &ctx->state->flags); memcpy(&ctx->state->open_stateid.other, &stateid->other, NFS4_STATEID_OTHER_SIZE); update_open_stateid(ctx->state, stateid, NULL, filep->f_mode); + set_bit(NFS_OPEN_STATE, &ctx->state->flags); nfs_file_set_open_context(filep, ctx); put_nfs_open_context(ctx); -- cgit v1.2.3 From 21e31401fc4595aeefa224cd36ab8175ec867b87 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Thu, 3 Dec 2020 15:18:39 -0500 Subject: NFS: Disable READ_PLUS by default We've been seeing failures with xfstests generic/091 and generic/263 when using READ_PLUS. I've made some progress on these issues, and the tests fail later on but still don't pass. Let's disable READ_PLUS by default until we can work out what is going on. Signed-off-by: Anna Schumaker --- fs/nfs/Kconfig | 9 +++++++++ fs/nfs/nfs4proc.c | 2 +- 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 88e1763e02f3..e2a488d403a6 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -205,3 +205,12 @@ config NFS_DISABLE_UDP_SUPPORT Choose Y here to disable the use of NFS over UDP. NFS over UDP on modern networks (1Gb+) can lead to data corruption caused by fragmentation during high loads. + +config NFS_V4_2_READ_PLUS + bool "NFS: Enable support for the NFSv4.2 READ_PLUS operation" + depends on NFS_V4_2 + default n + help + This is intended for developers only. The READ_PLUS operation has + been shown to have issues under specific conditions and should not + be used in production. diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 9e0ca9b2b210..e89468678ae1 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5309,7 +5309,7 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) nfs4_read_done_cb(task, hdr); } -#ifdef CONFIG_NFS_V4_2 +#if defined CONFIG_NFS_V4_2 && defined CONFIG_NFS_V4_2_READ_PLUS static void nfs42_read_plus_support(struct nfs_server *server, struct rpc_message *msg) { if (server->caps & NFS_CAP_READ_PLUS) -- cgit v1.2.3 From 190113b4c6531c8e09b31d5235f9b5175cbb0f72 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 10 Dec 2020 21:18:22 +0100 Subject: x86/apic/vector: Fix ordering in vector assignment Prarit reported that depending on the affinity setting the ' irq $N: Affinity broken due to vector space exhaustion.' message is showing up in dmesg, but the vector space on the CPUs in the affinity mask is definitely not exhausted. Shung-Hsi provided traces and analysis which pinpoints the problem: The ordering of trying to assign an interrupt vector in assign_irq_vector_any_locked() is simply wrong if the interrupt data has a valid node assigned. It does: 1) Try the intersection of affinity mask and node mask 2) Try the node mask 3) Try the full affinity mask 4) Try the full online mask Obviously #2 and #3 are in the wrong order as the requested affinity mask has to take precedence. In the observed cases #1 failed because the affinity mask did not contain CPUs from node 0. That made it allocate a vector from node 0, thereby breaking affinity and emitting the misleading message. Revert the order of #2 and #3 so the full affinity mask without the node intersection is tried before actually affinity is broken. If no node is assigned then only the full affinity mask and if that fails the full online mask is tried. Fixes: d6ffc6ac83b1 ("x86/vector: Respect affinity mask in irq descriptor") Reported-by: Prarit Bhargava Reported-by: Shung-Hsi Yu Signed-off-by: Thomas Gleixner Tested-by: Shung-Hsi Yu Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87ft4djtyp.fsf@nanos.tec.linutronix.de --- arch/x86/kernel/apic/vector.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 1eac53632786..758bbf25ef74 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -273,20 +273,24 @@ static int assign_irq_vector_any_locked(struct irq_data *irqd) const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd); int node = irq_data_get_node(irqd); - if (node == NUMA_NO_NODE) - goto all; - /* Try the intersection of @affmsk and node mask */ - cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk); - if (!assign_vector_locked(irqd, vector_searchmask)) - return 0; - /* Try the node mask */ - if (!assign_vector_locked(irqd, cpumask_of_node(node))) - return 0; -all: + if (node != NUMA_NO_NODE) { + /* Try the intersection of @affmsk and node mask */ + cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk); + if (!assign_vector_locked(irqd, vector_searchmask)) + return 0; + } + /* Try the full affinity mask */ cpumask_and(vector_searchmask, affmsk, cpu_online_mask); if (!assign_vector_locked(irqd, vector_searchmask)) return 0; + + if (node != NUMA_NO_NODE) { + /* Try the node mask */ + if (!assign_vector_locked(irqd, cpumask_of_node(node))) + return 0; + } + /* Try the full online mask */ return assign_vector_locked(irqd, cpu_online_mask); } -- cgit v1.2.3 From b1f195fc49812359296a901e26cc7c0b761d8a70 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 10 Dec 2020 23:07:41 +0000 Subject: drm/i915/display: Go softly softly on initial modeset failure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reduce the module/device probe error into a mere debug to hide issues where the initial modeset is failing (after lies told by hw probe) and the system hangs with a livelock in cleaning up the failed commit. Reported-by: H.J. Lu Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=210619 Fixes: b3bf99daaee9 ("drm/i915/display: Defer initial modeset until after GGTT is initialised") Fixes: ccc9e67ab26f ("drm/i915/display: Defer initial modeset until after GGTT is initialised") Signed-off-by: Chris Wilson Cc: "Ville Syrjälä" Cc: Rodrigo Vivi Cc: H.J. Lu Cc: Dave Airlie Reviewed-by: Rodrigo Vivi Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20201210230741.17140-1-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/display/intel_display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 3bfe6ed67da1..aabf09f89cad 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -18040,7 +18040,7 @@ int intel_modeset_init(struct drm_i915_private *i915) */ ret = intel_initial_commit(&i915->drm); if (ret) - return ret; + drm_dbg_kms(&i915->drm, "Initial modeset failed, %d\n", ret); intel_overlay_setup(i915); -- cgit v1.2.3 From ccbbfd1cbf365b38d014351d1482fedd26282041 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Wed, 25 Nov 2020 11:57:03 -0800 Subject: RISC-V: Define get_cycles64() regardless of M-mode The timer driver uses get_cycles64() unconditionally to obtain the current time. A recent refactoring lost the common definition for some configs, which is now the only one we need. Fixes: d5be89a8d118 ("RISC-V: Resurrect the MMIO timer implementation for M-mode systems") Reported-by: kernel test robot Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/timex.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h index ab104905d4db..81de51e6aa32 100644 --- a/arch/riscv/include/asm/timex.h +++ b/arch/riscv/include/asm/timex.h @@ -60,6 +60,8 @@ static inline u32 get_cycles_hi(void) } #define get_cycles_hi get_cycles_hi +#endif /* !CONFIG_RISCV_M_MODE */ + #ifdef CONFIG_64BIT static inline u64 get_cycles64(void) { @@ -79,8 +81,6 @@ static inline u64 get_cycles64(void) } #endif /* CONFIG_64BIT */ -#endif /* !CONFIG_RISCV_M_MODE */ - #define ARCH_HAS_READ_CURRENT_TIMER static inline int read_current_timer(unsigned long *timer_val) { -- cgit v1.2.3 From 4da3a54f5a025846f9930354cfb80f075b9952e0 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Fri, 11 Dec 2020 14:14:04 +0100 Subject: Revert "scsi: storvsc: Validate length of incoming packet in storvsc_on_channel_callback()" This reverts commit 3b8c72d076c42bf27284cda7b2b2b522810686f8. Dexuan reported a regression where StorVSC fails to probe a device (and where, consequently, the VM may fail to boot). The root-cause analysis led to a long-standing race condition that is exposed by the validation /commit in question. Let's put the new validation aside until a proper solution for that race condition is in place. Link: https://lore.kernel.org/r/20201211131404.21359-1-parri.andrea@gmail.com Fixes: 3b8c72d076c4 ("scsi: storvsc: Validate length of incoming packet in storvsc_on_channel_callback()") Cc: Dexuan Cui Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: linux-scsi@vger.kernel.org Signed-off-by: Andrea Parri (Microsoft) Signed-off-by: Martin K. Petersen --- drivers/scsi/storvsc_drv.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 99c8ff81de74..ded00a89bfc4 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1246,11 +1246,6 @@ static void storvsc_on_channel_callback(void *context) request = (struct storvsc_cmd_request *) ((unsigned long)desc->trans_id); - if (hv_pkt_datalen(desc) < sizeof(struct vstor_packet) - vmscsi_size_delta) { - dev_err(&device->device, "Invalid packet len\n"); - continue; - } - if (request == &stor_device->init_request || request == &stor_device->reset_request) { memcpy(&request->vstor_packet, packet, -- cgit v1.2.3 From 249a9599c9123a4af655dd5800c2506602ffa055 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 3 Dec 2020 20:03:32 +0100 Subject: mtd: rawnand: ams-delta: Do not force a particular software ECC engine Originally, commit d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") kind of broke the logic around the initialization of several ECC engines. Unfortunately, the fix (which indeed moved the ECC initialization to the right place) did not take into account the fact that a different ECC algorithm could have been used thanks to a DT property, considering the "Hamming" algorithm entry a configuration while it was only a default. Add the necessary logic to be sure Hamming keeps being only a default. Fixes: 59d93473323a ("mtd: rawnand: ams-delta: Move the ECC initialization to ->attach_chip()") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201203190340.15522-2-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/ams-delta.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index 0c352b39ad4b..ff1697f899ba 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -218,7 +218,9 @@ static int gpio_nand_setup_interface(struct nand_chip *this, int csline, static int gpio_nand_attach_chip(struct nand_chip *chip) { chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; } -- cgit v1.2.3 From 52277269c4060ced7e7d1a83c77377590d106f44 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 3 Dec 2020 20:03:33 +0100 Subject: mtd: rawnand: au1550: Do not force a particular software ECC engine Originally, commit d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") kind of broke the logic around the initialization of several ECC engines. Unfortunately, the fix (which indeed moved the ECC initialization to the right place) did not take into account the fact that a different ECC algorithm could have been used thanks to a DT property, considering the "Hamming" algorithm entry a configuration while it was only a default. Add the necessary logic to be sure Hamming keeps being only a default. Fixes: dbffc8ccdf3a ("mtd: rawnand: au1550: Move the ECC initialization to ->attach_chip()") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201203190340.15522-3-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/au1550nd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/au1550nd.c b/drivers/mtd/nand/raw/au1550nd.c index 7892022bd6dd..7b6b354f2d39 100644 --- a/drivers/mtd/nand/raw/au1550nd.c +++ b/drivers/mtd/nand/raw/au1550nd.c @@ -239,7 +239,9 @@ static int au1550nd_exec_op(struct nand_chip *this, static int au1550nd_attach_chip(struct nand_chip *chip) { chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; } -- cgit v1.2.3 From bd47fa451315684424d2b39aa95f2ed235fee37a Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 3 Dec 2020 20:03:34 +0100 Subject: mtd: rawnand: gpio: Do not force a particular software ECC engine Originally, commit d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") kind of broke the logic around the initialization of several ECC engines. Unfortunately, the fix (which indeed moved the ECC initialization to the right place) did not take into account the fact that a different ECC algorithm could have been used thanks to a DT property, considering the "Hamming" algorithm entry a configuration while it was only a default. Add the necessary logic to be sure Hamming keeps being only a default. Fixes: f6341f6448e0 ("mtd: rawnand: gpio: Move the ECC initialization to ->attach_chip()") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201203190340.15522-4-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/gpio.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/gpio.c b/drivers/mtd/nand/raw/gpio.c index eb03b8cea1cb..fb7a086de35e 100644 --- a/drivers/mtd/nand/raw/gpio.c +++ b/drivers/mtd/nand/raw/gpio.c @@ -164,7 +164,9 @@ static int gpio_nand_exec_op(struct nand_chip *chip, static int gpio_nand_attach_chip(struct nand_chip *chip) { chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; } -- cgit v1.2.3 From f49bde9fe25cf4cd02440a7ec68f278957ddea37 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 3 Dec 2020 20:03:35 +0100 Subject: mtd: rawnand: mpc5121: Do not force a particular software ECC engine Originally, commit d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") kind of broke the logic around the initialization of several ECC engines. Unfortunately, the fix (which indeed moved the ECC initialization to the right place) did not take into account the fact that a different ECC algorithm could have been used thanks to a DT property, considering the "Hamming" algorithm entry a configuration while it was only a default. Add the necessary logic to be sure Hamming keeps being only a default. Fixes: 6dd09f775b72 ("mtd: rawnand: mpc5121: Move the ECC initialization to ->attach_chip()") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201203190340.15522-5-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/mpc5121_nfc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/mpc5121_nfc.c b/drivers/mtd/nand/raw/mpc5121_nfc.c index fb4c0b11689f..bcd4a556c959 100644 --- a/drivers/mtd/nand/raw/mpc5121_nfc.c +++ b/drivers/mtd/nand/raw/mpc5121_nfc.c @@ -606,7 +606,9 @@ static void mpc5121_nfc_free(struct device *dev, struct mtd_info *mtd) static int mpc5121_nfc_attach_chip(struct nand_chip *chip) { chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; } -- cgit v1.2.3 From f87b720a21641d5c5ccd4f5ccc06d96251b7f282 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 3 Dec 2020 20:03:36 +0100 Subject: mtd: rawnand: orion: Do not force a particular software ECC engine Originally, commit d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") kind of broke the logic around the initialization of several ECC engines. Unfortunately, the fix (which indeed moved the ECC initialization to the right place) did not take into account the fact that a different ECC algorithm could have been used thanks to a DT property, considering the "Hamming" algorithm entry a configuration while it was only a default. Add the necessary logic to be sure Hamming keeps being only a default. Reported-by: Chris Packham Fixes: 553508cec2e8 ("mtd: rawnand: orion: Move the ECC initialization to ->attach_chip()") Signed-off-by: Miquel Raynal Tested-by: Chris Packham Link: https://lore.kernel.org/linux-mtd/20201203190340.15522-6-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/orion_nand.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c index e3bb65fd3ab2..66211c9311d2 100644 --- a/drivers/mtd/nand/raw/orion_nand.c +++ b/drivers/mtd/nand/raw/orion_nand.c @@ -86,7 +86,9 @@ static void orion_nand_read_buf(struct nand_chip *chip, uint8_t *buf, int len) static int orion_nand_attach_chip(struct nand_chip *chip) { chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; } -- cgit v1.2.3 From 9506ab943db438d316386d45eb8a8b60bfeee27c Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 3 Dec 2020 20:03:37 +0100 Subject: mtd: rawnand: pasemi: Do not force a particular software ECC engine Originally, commit d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") kind of broke the logic around the initialization of several ECC engines. Unfortunately, the fix (which indeed moved the ECC initialization to the right place) did not take into account the fact that a different ECC algorithm could have been used thanks to a DT property, considering the "Hamming" algorithm entry a configuration while it was only a default. Add the necessary logic to be sure Hamming keeps being only a default. Fixes: 8fc6f1f042b2 ("mtd: rawnand: pasemi: Move the ECC initialization to ->attach_chip()") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201203190340.15522-7-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/pasemi_nand.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/pasemi_nand.c b/drivers/mtd/nand/raw/pasemi_nand.c index 4dfff34800f4..68c08772d7c2 100644 --- a/drivers/mtd/nand/raw/pasemi_nand.c +++ b/drivers/mtd/nand/raw/pasemi_nand.c @@ -77,7 +77,9 @@ static int pasemi_device_ready(struct nand_chip *chip) static int pasemi_attach_chip(struct nand_chip *chip) { chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; } -- cgit v1.2.3 From 148b4f16159f49c6d05da8189e0941880ad10a46 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 3 Dec 2020 20:03:38 +0100 Subject: mtd: rawnand: plat_nand: Do not force a particular software ECC engine Originally, commit d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") kind of broke the logic around the initialization of several ECC engines. Unfortunately, the fix (which indeed moved the ECC initialization to the right place) did not take into account the fact that a different ECC algorithm could have been used thanks to a DT property, considering the "Hamming" algorithm entry a configuration while it was only a default. Add the necessary logic to be sure Hamming keeps being only a default. Fixes: 612e048e6aab ("mtd: rawnand: plat_nand: Move the ECC initialization to ->attach_chip()") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201203190340.15522-8-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/plat_nand.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c index 93d9f1694dc1..7711e1020c21 100644 --- a/drivers/mtd/nand/raw/plat_nand.c +++ b/drivers/mtd/nand/raw/plat_nand.c @@ -22,7 +22,9 @@ struct plat_nand_data { static int plat_nand_attach_chip(struct nand_chip *chip) { chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; } -- cgit v1.2.3 From cf75f00fc8026040f6ff8f054cfec99e820b62e7 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 3 Dec 2020 20:03:39 +0100 Subject: mtd: rawnand: socrates: Do not force a particular software ECC engine Originally, commit d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") kind of broke the logic around the initialization of several ECC engines. Unfortunately, the fix (which indeed moved the ECC initialization to the right place) did not take into account the fact that a different ECC algorithm could have been used thanks to a DT property, considering the "Hamming" algorithm entry a configuration while it was only a default. Add the necessary logic to be sure Hamming keeps being only a default. Fixes: b36bf0a0fe5d ("mtd: rawnand: socrates: Move the ECC initialization to ->attach_chip()") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201203190340.15522-9-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/socrates_nand.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/socrates_nand.c b/drivers/mtd/nand/raw/socrates_nand.c index 107208311987..70f8305c9b6e 100644 --- a/drivers/mtd/nand/raw/socrates_nand.c +++ b/drivers/mtd/nand/raw/socrates_nand.c @@ -120,7 +120,9 @@ static int socrates_nand_device_ready(struct nand_chip *nand_chip) static int socrates_attach_chip(struct nand_chip *chip) { chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; } -- cgit v1.2.3 From 33d974e76e21e9da8a36b14d2dce6394c36c3e30 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 3 Dec 2020 20:03:40 +0100 Subject: mtd: rawnand: xway: Do not force a particular software ECC engine Originally, commit d7157ff49a5b ("mtd: rawnand: Use the ECC framework user input parsing bits") kind of broke the logic around the initialization of several ECC engines. Unfortunately, the fix (which indeed moved the ECC initialization to the right place) did not take into account the fact that a different ECC algorithm could have been used thanks to a DT property, considering the "Hamming" algorithm entry a configuration while it was only a default. Add the necessary logic to be sure Hamming keeps being only a default. Fixes: d525914b5bd8 ("mtd: rawnand: xway: Move the ECC initialization to ->attach_chip()") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201203190340.15522-10-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/xway_nand.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/xway_nand.c b/drivers/mtd/nand/raw/xway_nand.c index efc5bf5434e0..26751976e502 100644 --- a/drivers/mtd/nand/raw/xway_nand.c +++ b/drivers/mtd/nand/raw/xway_nand.c @@ -149,7 +149,9 @@ static void xway_write_buf(struct nand_chip *chip, const u_char *buf, int len) static int xway_attach_chip(struct nand_chip *chip) { chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; return 0; } -- cgit v1.2.3 From 82e06090473289ce63e23fdeb8737aad59b10645 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 9 Dec 2020 20:13:24 -0800 Subject: Input: cm109 - do not stomp on control URB We need to make sure we are not stomping on the control URB that was issued when opening the device when attempting to toggle buzzer. To do that we need to mark it as pending in cm109_open(). Reported-and-tested-by: syzbot+150f793ac5bc18eee150@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/misc/cm109.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/input/misc/cm109.c b/drivers/input/misc/cm109.c index e413801f0491..f515fae465c3 100644 --- a/drivers/input/misc/cm109.c +++ b/drivers/input/misc/cm109.c @@ -568,12 +568,15 @@ static int cm109_input_open(struct input_dev *idev) dev->ctl_data->byte[HID_OR2] = dev->keybit; dev->ctl_data->byte[HID_OR3] = 0x00; + dev->ctl_urb_pending = 1; error = usb_submit_urb(dev->urb_ctl, GFP_KERNEL); - if (error) + if (error) { + dev->ctl_urb_pending = 0; dev_err(&dev->intf->dev, "%s: usb_submit_urb (urb_ctl) failed %d\n", __func__, error); - else + } else { dev->open = 1; + } mutex_unlock(&dev->pm_mutex); -- cgit v1.2.3 From 16c0cc0ce3059e315a0aab6538061d95a6612589 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 11 Dec 2020 13:36:27 -0800 Subject: revert "mm/filemap: add static for function __add_to_page_cache_locked" Revert commit 3351b16af494 ("mm/filemap: add static for function __add_to_page_cache_locked") due to incompatibility with ALLOW_ERROR_INJECTION which result in build errors. Link: https://lkml.kernel.org/r/CAADnVQJ6tmzBXvtroBuEH6QA0H+q7yaSKxrVvVxhqr3KBZdEXg@mail.gmail.com Tested-by: Justin Forbes Tested-by: Greg Thelen Acked-by: Alexei Starovoitov Cc: Michal Kubecek Cc: Alex Shi Cc: Souptick Joarder Cc: Daniel Borkmann Cc: Josef Bacik Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/filemap.c b/mm/filemap.c index 331f4261d723..0b2067b3c328 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -827,7 +827,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); -static noinline int __add_to_page_cache_locked(struct page *page, +noinline int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp, void **shadowp) -- cgit v1.2.3 From 40d6366e9d86d9a67b5642040e76082fdb5bdcf9 Mon Sep 17 00:00:00 2001 From: Miles Chen Date: Fri, 11 Dec 2020 13:36:31 -0800 Subject: proc: use untagged_addr() for pagemap_read addresses When we try to visit the pagemap of a tagged userspace pointer, we find that the start_vaddr is not correct because of the tag. To fix it, we should untag the userspace pointers in pagemap_read(). I tested with 5.10-rc4 and the issue remains. Explanation from Catalin in [1]: "Arguably, that's a user-space bug since tagged file offsets were never supported. In this case it's not even a tag at bit 56 as per the arm64 tagged address ABI but rather down to bit 47. You could say that the problem is caused by the C library (malloc()) or whoever created the tagged vaddr and passed it to this function. It's not a kernel regression as we've never supported it. Now, pagemap is a special case where the offset is usually not generated as a classic file offset but rather derived by shifting a user virtual address. I guess we can make a concession for pagemap (only) and allow such offset with the tag at bit (56 - PAGE_SHIFT + 3)" My test code is based on [2]: A userspace pointer which has been tagged by 0xb4: 0xb400007662f541c8 userspace program: uint64 OsLayer::VirtualToPhysical(void *vaddr) { uint64 frame, paddr, pfnmask, pagemask; int pagesize = sysconf(_SC_PAGESIZE); off64_t off = ((uintptr_t)vaddr) / pagesize * 8; // off = 0xb400007662f541c8 / pagesize * 8 = 0x5a00003b317aa0 int fd = open(kPagemapPath, O_RDONLY); ... if (lseek64(fd, off, SEEK_SET) != off || read(fd, &frame, 8) != 8) { int err = errno; string errtxt = ErrorString(err); if (fd >= 0) close(fd); return 0; } ... } kernel fs/proc/task_mmu.c: static ssize_t pagemap_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { ... src = *ppos; svpfn = src / PM_ENTRY_BYTES; // svpfn == 0xb400007662f54 start_vaddr = svpfn << PAGE_SHIFT; // start_vaddr == 0xb400007662f54000 end_vaddr = mm->task_size; /* watch out for wraparound */ // svpfn == 0xb400007662f54 // (mm->task_size >> PAGE) == 0x8000000 if (svpfn > mm->task_size >> PAGE_SHIFT) // the condition is true because of the tag 0xb4 start_vaddr = end_vaddr; ret = 0; while (count && (start_vaddr < end_vaddr)) { // we cannot visit correct entry because start_vaddr is set to end_vaddr int len; unsigned long end; ... } ... } [1] https://lore.kernel.org/patchwork/patch/1343258/ [2] https://github.com/stressapptest/stressapptest/blob/master/src/os.cc#L158 Link: https://lkml.kernel.org/r/20201204024347.8295-1-miles.chen@mediatek.com Signed-off-by: Miles Chen Reviewed-by: Vincenzo Frascino Reviewed-by: Catalin Marinas Cc: Alexey Dobriyan Cc: Andrey Konovalov Cc: Alexander Potapenko Cc: Vincenzo Frascino Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Marco Elver Cc: Will Deacon Cc: Eric W. Biederman Cc: Song Bao Hua (Barry Song) Cc: [5.4-] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 217aa2705d5d..ee5a235b3056 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1599,11 +1599,15 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, src = *ppos; svpfn = src / PM_ENTRY_BYTES; - start_vaddr = svpfn << PAGE_SHIFT; end_vaddr = mm->task_size; /* watch out for wraparound */ - if (svpfn > mm->task_size >> PAGE_SHIFT) + start_vaddr = end_vaddr; + if (svpfn <= (ULONG_MAX >> PAGE_SHIFT)) + start_vaddr = untagged_addr(svpfn << PAGE_SHIFT); + + /* Ensure the address is inside the task */ + if (start_vaddr > mm->task_size) start_vaddr = end_vaddr; /* -- cgit v1.2.3 From 84edc2eff82730d45ab513ecec49cb63beb973c9 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 11 Dec 2020 13:36:35 -0800 Subject: selftest/fpu: avoid clang warning With extra warnings enabled, clang complains about the redundant -mhard-float argument: clang: error: argument unused during compilation: '-mhard-float' [-Werror,-Wunused-command-line-argument] Move this into the gcc-only part of the Makefile. Link: https://lkml.kernel.org/r/20201203223652.1320700-1-arnd@kernel.org Fixes: 4185b3b92792 ("selftests/fpu: Add an FPU selftest") Signed-off-by: Arnd Bergmann Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Petteri Aimonen Cc: Borislav Petkov Cc: Arnd Bergmann Cc: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lib/Makefile b/lib/Makefile index ce45af50983a..d415fc7067c5 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -107,7 +107,7 @@ obj-$(CONFIG_TEST_FREE_PAGES) += test_free_pages.o # off the generation of FPU/SSE* instructions for kernel proper but FPU_FLAGS # get appended last to CFLAGS and thus override those previous compiler options. # -FPU_CFLAGS := -mhard-float -msse -msse2 +FPU_CFLAGS := -msse -msse2 ifdef CONFIG_CC_IS_GCC # Stack alignment mismatch, proceed with caution. # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 @@ -120,6 +120,7 @@ ifdef CONFIG_CC_IS_GCC # -mpreferred-stack-boundary=3 is not between 4 and 12 # # can be triggered. Otherwise gcc doesn't complain. +FPU_CFLAGS += -mhard-float FPU_CFLAGS += $(call cc-option,-msse -mpreferred-stack-boundary=3,-mpreferred-stack-boundary=4) endif -- cgit v1.2.3 From 14dc3983b5dff513a90bd5a8cc90acaf7867c3d0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 11 Dec 2020 13:36:38 -0800 Subject: kbuild: avoid static_assert for genksyms genksyms does not know or care about the _Static_assert() built-in, and sometimes falls back to ignoring the later symbols, which causes undefined behavior such as WARNING: modpost: EXPORT symbol "ethtool_set_ethtool_phy_ops" [vmlinux] version generation failed, symbol will not be versioned. ld: net/ethtool/common.o: relocation R_AARCH64_ABS32 against `__crc_ethtool_set_ethtool_phy_ops' can not be used when making a shared object net/ethtool/common.o:(_ftrace_annotated_branch+0x0): dangerous relocation: unsupported relocation Redefine static_assert for genksyms to avoid that. Link: https://lkml.kernel.org/r/20201203230955.1482058-1-arnd@kernel.org Signed-off-by: Arnd Bergmann Suggested-by: Ard Biesheuvel Cc: Masahiro Yamada Cc: Michal Marek Cc: Kees Cook Cc: Rikard Falkeborn Cc: Marco Elver Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/build_bug.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h index e3a0be2c90ad..7bb66e15b481 100644 --- a/include/linux/build_bug.h +++ b/include/linux/build_bug.h @@ -77,4 +77,9 @@ #define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr) #define __static_assert(expr, msg, ...) _Static_assert(expr, msg) +#ifdef __GENKSYMS__ +/* genksyms gets confused by _Static_assert */ +#define _Static_assert(expr, ...) +#endif + #endif /* _LINUX_BUILD_BUG_H */ -- cgit v1.2.3 From 55d5b7dd6451b58489ce384282ca5a4a289eb8d5 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 11 Dec 2020 13:36:42 -0800 Subject: initramfs: fix clang build failure There is only one function in init/initramfs.c that is in the .text section, and it is marked __weak. When building with clang-12 and the integrated assembler, this leads to a bug with recordmcount: ./scripts/recordmcount "init/initramfs.o" Cannot find symbol for section 2: .text. init/initramfs.o: failed I'm not quite sure what exactly goes wrong, but I notice that this function is only ever called from an __init function, and normally inlined. Marking it __init as well is clearly correct and it leads to recordmcount no longer complaining. Link: https://lkml.kernel.org/r/20201204165742.3815221-1-arnd@kernel.org Signed-off-by: Arnd Bergmann Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Barret Rhoden Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/initramfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/init/initramfs.c b/init/initramfs.c index 1f97c0328a7a..55b74d7e5260 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -535,7 +535,7 @@ extern unsigned long __initramfs_size; #include #include -void __weak free_initrd_mem(unsigned long start, unsigned long end) +void __weak __init free_initrd_mem(unsigned long start, unsigned long end) { #ifdef CONFIG_ARCH_KEEP_MEMBLOCK unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE); -- cgit v1.2.3 From 6e7b64b9dd6d96537d816ea07ec26b7dedd397b9 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 11 Dec 2020 13:36:46 -0800 Subject: elfcore: fix building with clang kernel/elfcore.c only contains weak symbols, which triggers a bug with clang in combination with recordmcount: Cannot find symbol for section 2: .text. kernel/elfcore.o: failed Move the empty stubs into linux/elfcore.h as inline functions. As only two architectures use these, just use the architecture specific Kconfig symbols to key off the declaration. Link: https://lkml.kernel.org/r/20201204165742.3815221-2-arnd@kernel.org Signed-off-by: Arnd Bergmann Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Barret Rhoden Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/elfcore.h | 22 ++++++++++++++++++++++ kernel/Makefile | 1 - kernel/elfcore.c | 26 -------------------------- 3 files changed, 22 insertions(+), 27 deletions(-) delete mode 100644 kernel/elfcore.c diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 46c3d691f677..de51c1bef27d 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -104,6 +104,7 @@ static inline int elf_core_copy_task_fpregs(struct task_struct *t, struct pt_reg #endif } +#if defined(CONFIG_UM) || defined(CONFIG_IA64) /* * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out * extra segments containing the gate DSO contents. Dumping its @@ -118,5 +119,26 @@ elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset); extern int elf_core_write_extra_data(struct coredump_params *cprm); extern size_t elf_core_extra_data_size(void); +#else +static inline Elf_Half elf_core_extra_phdrs(void) +{ + return 0; +} + +static inline int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) +{ + return 1; +} + +static inline int elf_core_write_extra_data(struct coredump_params *cprm) +{ + return 1; +} + +static inline size_t elf_core_extra_data_size(void) +{ + return 0; +} +#endif #endif /* _LINUX_ELFCORE_H */ diff --git a/kernel/Makefile b/kernel/Makefile index af601b9bda0e..6c9f19911be0 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -97,7 +97,6 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o obj-$(CONFIG_TRACEPOINTS) += tracepoint.o obj-$(CONFIG_LATENCYTOP) += latencytop.o -obj-$(CONFIG_ELFCORE) += elfcore.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_TRACE_CLOCK) += trace/ diff --git a/kernel/elfcore.c b/kernel/elfcore.c deleted file mode 100644 index 57fb4dcff434..000000000000 --- a/kernel/elfcore.c +++ /dev/null @@ -1,26 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include - -Elf_Half __weak elf_core_extra_phdrs(void) -{ - return 0; -} - -int __weak elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) -{ - return 1; -} - -int __weak elf_core_write_extra_data(struct coredump_params *cprm) -{ - return 1; -} - -size_t __weak elf_core_extra_data_size(void) -{ - return 0; -} -- cgit v1.2.3 From 6c82d45c7f0348b44e00bd7dcccfc47dec7577d1 Mon Sep 17 00:00:00 2001 From: Kuan-Ying Lee Date: Fri, 11 Dec 2020 13:36:49 -0800 Subject: kasan: fix object remaining in offline per-cpu quarantine We hit this issue in our internal test. When enabling generic kasan, a kfree()'d object is put into per-cpu quarantine first. If the cpu goes offline, object still remains in the per-cpu quarantine. If we call kmem_cache_destroy() now, slub will report "Objects remaining" error. ============================================================================= BUG test_module_slab (Not tainted): Objects remaining in test_module_slab on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0x(____ptrval____) objects=34 used=1 fp=0x(____ptrval____) flags=0x2ffff00000010200 CPU: 3 PID: 176 Comm: cat Tainted: G B 5.10.0-rc1-00007-g4525c8781ec0-dirty #10 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x0/0x2b0 show_stack+0x18/0x68 dump_stack+0xfc/0x168 slab_err+0xac/0xd4 __kmem_cache_shutdown+0x1e4/0x3c8 kmem_cache_destroy+0x68/0x130 test_version_show+0x84/0xf0 module_attr_show+0x40/0x60 sysfs_kf_seq_show+0x128/0x1c0 kernfs_seq_show+0xa0/0xb8 seq_read+0x1f0/0x7e8 kernfs_fop_read+0x70/0x338 vfs_read+0xe4/0x250 ksys_read+0xc8/0x180 __arm64_sys_read+0x44/0x58 el0_svc_common.constprop.0+0xac/0x228 do_el0_svc+0x38/0xa0 el0_sync_handler+0x170/0x178 el0_sync+0x174/0x180 INFO: Object 0x(____ptrval____) @offset=15848 INFO: Allocated in test_version_show+0x98/0xf0 age=8188 cpu=6 pid=172 stack_trace_save+0x9c/0xd0 set_track+0x64/0xf0 alloc_debug_processing+0x104/0x1a0 ___slab_alloc+0x628/0x648 __slab_alloc.isra.0+0x2c/0x58 kmem_cache_alloc+0x560/0x588 test_version_show+0x98/0xf0 module_attr_show+0x40/0x60 sysfs_kf_seq_show+0x128/0x1c0 kernfs_seq_show+0xa0/0xb8 seq_read+0x1f0/0x7e8 kernfs_fop_read+0x70/0x338 vfs_read+0xe4/0x250 ksys_read+0xc8/0x180 __arm64_sys_read+0x44/0x58 el0_svc_common.constprop.0+0xac/0x228 kmem_cache_destroy test_module_slab: Slab cache still has objects Register a cpu hotplug function to remove all objects in the offline per-cpu quarantine when cpu is going offline. Set a per-cpu variable to indicate this cpu is offline. [qiang.zhang@windriver.com: fix slab double free when cpu-hotplug] Link: https://lkml.kernel.org/r/20201204102206.20237-1-qiang.zhang@windriver.com Link: https://lkml.kernel.org/r/1606895585-17382-2-git-send-email-Kuan-Ying.Lee@mediatek.com Signed-off-by: Kuan-Ying Lee Signed-off-by: Zqiang Suggested-by: Dmitry Vyukov Reported-by: Guangye Yang Reviewed-by: Dmitry Vyukov Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Matthias Brugger Cc: Nicholas Tang Cc: Miles Chen Cc: Qian Cai Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/quarantine.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 4c5375810449..0e3f8494628f 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -29,6 +29,7 @@ #include #include #include +#include #include "../slab.h" #include "kasan.h" @@ -43,6 +44,7 @@ struct qlist_head { struct qlist_node *head; struct qlist_node *tail; size_t bytes; + bool offline; }; #define QLIST_INIT { NULL, NULL, 0 } @@ -188,6 +190,10 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) local_irq_save(flags); q = this_cpu_ptr(&cpu_quarantine); + if (q->offline) { + local_irq_restore(flags); + return; + } qlist_put(q, &info->quarantine_link, cache->size); if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) { qlist_move_all(q, &temp); @@ -328,3 +334,36 @@ void quarantine_remove_cache(struct kmem_cache *cache) synchronize_srcu(&remove_cache_srcu); } + +static int kasan_cpu_online(unsigned int cpu) +{ + this_cpu_ptr(&cpu_quarantine)->offline = false; + return 0; +} + +static int kasan_cpu_offline(unsigned int cpu) +{ + struct qlist_head *q; + + q = this_cpu_ptr(&cpu_quarantine); + /* Ensure the ordering between the writing to q->offline and + * qlist_free_all. Otherwise, cpu_quarantine may be corrupted + * by interrupt. + */ + WRITE_ONCE(q->offline, true); + barrier(); + qlist_free_all(q, NULL); + return 0; +} + +static int __init kasan_cpu_quarantine_init(void) +{ + int ret = 0; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/kasan:online", + kasan_cpu_online, kasan_cpu_offline); + if (ret < 0) + pr_err("kasan cpu quarantine register failed [%d]\n", ret); + return ret; +} +late_initcall(kasan_cpu_quarantine_init); -- cgit v1.2.3 From ba9c1201beaa86a773e83be5654602a0667e4a4d Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Fri, 11 Dec 2020 13:36:53 -0800 Subject: mm/hugetlb: clear compound_nr before freeing gigantic pages Commit 1378a5ee451a ("mm: store compound_nr as well as compound_order") added compound_nr counter to first tail struct page, overlaying with page->mapping. The overlay itself is fine, but while freeing gigantic hugepages via free_contig_range(), a "bad page" check will trigger for non-NULL page->mapping on the first tail page: BUG: Bad page state in process bash pfn:380001 page:00000000c35f0856 refcount:0 mapcount:0 mapping:00000000126b68aa index:0x0 pfn:0x380001 aops:0x0 flags: 0x3ffff00000000000() raw: 3ffff00000000000 0000000000000100 0000000000000122 0000000100000000 raw: 0000000000000000 0000000000000000 ffffffff00000000 0000000000000000 page dumped because: non-NULL mapping Modules linked in: CPU: 6 PID: 616 Comm: bash Not tainted 5.10.0-rc7-next-20201208 #1 Hardware name: IBM 3906 M03 703 (LPAR) Call Trace: show_stack+0x6e/0xe8 dump_stack+0x90/0xc8 bad_page+0xd6/0x130 free_pcppages_bulk+0x26a/0x800 free_unref_page+0x6e/0x90 free_contig_range+0x94/0xe8 update_and_free_page+0x1c4/0x2c8 free_pool_huge_page+0x11e/0x138 set_max_huge_pages+0x228/0x300 nr_hugepages_store_common+0xb8/0x130 kernfs_fop_write+0xd2/0x218 vfs_write+0xb0/0x2b8 ksys_write+0xac/0xe0 system_call+0xe6/0x288 Disabling lock debugging due to kernel taint This is because only the compound_order is cleared in destroy_compound_gigantic_page(), and compound_nr is set to 1U << order == 1 for order 0 in set_compound_order(page, 0). Fix this by explicitly clearing compound_nr for first tail page after calling set_compound_order(page, 0). Link: https://lkml.kernel.org/r/20201208182813.66391-2-gerald.schaefer@linux.ibm.com Fixes: 1378a5ee451a ("mm: store compound_nr as well as compound_order") Signed-off-by: Gerald Schaefer Reviewed-by: Matthew Wilcox (Oracle) Cc: Heiko Carstens Cc: Mike Kravetz Cc: Christian Borntraeger Cc: [5.9+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 37f15c3c24dc..d029d938d26d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1216,6 +1216,7 @@ static void destroy_compound_gigantic_page(struct page *page, } set_compound_order(page, 0); + page[1].compound_nr = 0; __ClearPageHead(page); } -- cgit v1.2.3 From b7906b70a2337e445b8dca3ce7ba8976b6ebd07d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 11 Dec 2020 22:36:25 +0100 Subject: bpf: Fix enum names for bpf_this_cpu_ptr() and bpf_per_cpu_ptr() helpers Remove bpf_ prefix, which causes these helpers to be reported in verifier dump as bpf_bpf_this_cpu_ptr() and bpf_bpf_per_cpu_ptr(), respectively. Lets fix it as long as it is still possible before UAPI freezes on these helpers. Fixes: eaa6bcb71ef6 ("bpf: Introduce bpf_per_cpu_ptr()") Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Signed-off-by: Linus Torvalds --- include/uapi/linux/bpf.h | 4 ++-- kernel/bpf/helpers.c | 4 ++-- kernel/trace/bpf_trace.c | 4 ++-- tools/include/uapi/linux/bpf.h | 4 ++-- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e6ceac3f7d62..556216dc9703 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3897,8 +3897,8 @@ union bpf_attr { FN(seq_printf_btf), \ FN(skb_cgroup_classid), \ FN(redirect_neigh), \ - FN(bpf_per_cpu_ptr), \ - FN(bpf_this_cpu_ptr), \ + FN(per_cpu_ptr), \ + FN(this_cpu_ptr), \ FN(redirect_peer), \ /* */ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 25520f5eeaf6..deda1185237b 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -717,9 +717,9 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_snprintf_btf_proto; case BPF_FUNC_jiffies64: return &bpf_jiffies64_proto; - case BPF_FUNC_bpf_per_cpu_ptr: + case BPF_FUNC_per_cpu_ptr: return &bpf_per_cpu_ptr_proto; - case BPF_FUNC_bpf_this_cpu_ptr: + case BPF_FUNC_this_cpu_ptr: return &bpf_this_cpu_ptr_proto; default: break; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 048c655315f1..a125ea5e04cd 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1337,9 +1337,9 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; - case BPF_FUNC_bpf_per_cpu_ptr: + case BPF_FUNC_per_cpu_ptr: return &bpf_per_cpu_ptr_proto; - case BPF_FUNC_bpf_this_cpu_ptr: + case BPF_FUNC_this_cpu_ptr: return &bpf_this_cpu_ptr_proto; default: return NULL; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e6ceac3f7d62..556216dc9703 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3897,8 +3897,8 @@ union bpf_attr { FN(seq_printf_btf), \ FN(skb_cgroup_classid), \ FN(redirect_neigh), \ - FN(bpf_per_cpu_ptr), \ - FN(bpf_this_cpu_ptr), \ + FN(per_cpu_ptr), \ + FN(this_cpu_ptr), \ FN(redirect_peer), \ /* */ -- cgit v1.2.3 From 34c0f6f2695a2db81e09a3ab7bdb2853f45d4d3d Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Sat, 5 Dec 2020 01:48:08 +0100 Subject: KVM: mmu: Fix SPTE encoding of MMIO generation upper half Commit cae7ed3c2cb0 ("KVM: x86: Refactor the MMIO SPTE generation handling") cleaned up the computation of MMIO generation SPTE masks, however it introduced a bug how the upper part was encoded: SPTE bits 52-61 were supposed to contain bits 10-19 of the current generation number, however a missing shift encoded bits 1-10 there instead (mostly duplicating the lower part of the encoded generation number that then consisted of bits 1-9). In the meantime, the upper part was shrunk by one bit and moved by subsequent commits to become an upper half of the encoded generation number (bits 9-17 of bits 0-17 encoded in a SPTE). In addition to the above, commit 56871d444bc4 ("KVM: x86: fix overlap between SPTE_MMIO_MASK and generation") has changed the SPTE bit range assigned to encode the generation number and the total number of bits encoded but did not update them in the comment attached to their defines, nor in the KVM MMU doc. Let's do it here, too, since it is too trivial thing to warrant a separate commit. Fixes: cae7ed3c2cb0 ("KVM: x86: Refactor the MMIO SPTE generation handling") Signed-off-by: Maciej S. Szmigiero Message-Id: <156700708db2a5296c5ed7a8b9ac71f1e9765c85.1607129096.git.maciej.szmigiero@oracle.com> Cc: stable@vger.kernel.org [Reorganize macros so that everything is computed from the bit ranges. - Paolo] Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/mmu.rst | 2 +- arch/x86/kvm/mmu/spte.c | 4 ++-- arch/x86/kvm/mmu/spte.h | 25 ++++++++++++++++++------- 3 files changed, 21 insertions(+), 10 deletions(-) diff --git a/Documentation/virt/kvm/mmu.rst b/Documentation/virt/kvm/mmu.rst index 1c030dbac7c4..5bfe28b0728e 100644 --- a/Documentation/virt/kvm/mmu.rst +++ b/Documentation/virt/kvm/mmu.rst @@ -455,7 +455,7 @@ If the generation number of the spte does not equal the global generation number, it will ignore the cached MMIO information and handle the page fault through the slow path. -Since only 19 bits are used to store generation-number on mmio spte, all +Since only 18 bits are used to store generation-number on mmio spte, all pages are zapped when there is an overflow. Unfortunately, a single memory access might access kvm_memslots(kvm) multiple diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index fcac2cac78fe..c51ad544f25b 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -40,8 +40,8 @@ static u64 generation_mmio_spte_mask(u64 gen) WARN_ON(gen & ~MMIO_SPTE_GEN_MASK); BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK); - mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK; - mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK; + mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK; + mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK; return mask; } diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 5c75a451c000..2b3a30bd38b0 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -56,11 +56,11 @@ #define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1)) /* - * Due to limited space in PTEs, the MMIO generation is a 19 bit subset of + * Due to limited space in PTEs, the MMIO generation is a 18 bit subset of * the memslots generation and is derived as follows: * * Bits 0-8 of the MMIO generation are propagated to spte bits 3-11 - * Bits 9-18 of the MMIO generation are propagated to spte bits 52-61 + * Bits 9-17 of the MMIO generation are propagated to spte bits 54-62 * * The KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS flag is intentionally not included in * the MMIO generation number, as doing so would require stealing a bit from @@ -69,18 +69,29 @@ * requires a full MMU zap). The flag is instead explicitly queried when * checking for MMIO spte cache hits. */ -#define MMIO_SPTE_GEN_MASK GENMASK_ULL(17, 0) #define MMIO_SPTE_GEN_LOW_START 3 #define MMIO_SPTE_GEN_LOW_END 11 -#define MMIO_SPTE_GEN_LOW_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \ - MMIO_SPTE_GEN_LOW_START) #define MMIO_SPTE_GEN_HIGH_START PT64_SECOND_AVAIL_BITS_SHIFT #define MMIO_SPTE_GEN_HIGH_END 62 + +#define MMIO_SPTE_GEN_LOW_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \ + MMIO_SPTE_GEN_LOW_START) #define MMIO_SPTE_GEN_HIGH_MASK GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \ MMIO_SPTE_GEN_HIGH_START) +#define MMIO_SPTE_GEN_LOW_BITS (MMIO_SPTE_GEN_LOW_END - MMIO_SPTE_GEN_LOW_START + 1) +#define MMIO_SPTE_GEN_HIGH_BITS (MMIO_SPTE_GEN_HIGH_END - MMIO_SPTE_GEN_HIGH_START + 1) + +/* remember to adjust the comment above as well if you change these */ +static_assert(MMIO_SPTE_GEN_LOW_BITS == 9 && MMIO_SPTE_GEN_HIGH_BITS == 9); + +#define MMIO_SPTE_GEN_LOW_SHIFT (MMIO_SPTE_GEN_LOW_START - 0) +#define MMIO_SPTE_GEN_HIGH_SHIFT (MMIO_SPTE_GEN_HIGH_START - MMIO_SPTE_GEN_LOW_BITS) + +#define MMIO_SPTE_GEN_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0) + extern u64 __read_mostly shadow_nx_mask; extern u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */ extern u64 __read_mostly shadow_user_mask; @@ -228,8 +239,8 @@ static inline u64 get_mmio_spte_generation(u64 spte) { u64 gen; - gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START; - gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START; + gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_SHIFT; + gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_SHIFT; return gen; } -- cgit v1.2.3 From 111d0bda8eeb4b54e0c63897b071effbf9fd9251 Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Tue, 8 Dec 2020 22:08:29 +0100 Subject: tools/kvm_stat: Exempt time-based counters The new counters halt_poll_success_ns and halt_poll_fail_ns do not count events. Instead they provide a time, and mess up our statistics. Therefore, we should exclude them. Removal is currently implemented with an exempt list. If more counters like these appear, we can think about a more general rule like excluding all fields name "*_ns", in case that's a standing convention. Signed-off-by: Stefan Raspl Tested-and-reported-by: Christian Borntraeger Message-Id: <20201208210829.101324-1-raspl@linux.ibm.com> Signed-off-by: Paolo Bonzini --- tools/kvm/kvm_stat/kvm_stat | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index d199a3694be8..b0bf56c5f120 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -742,7 +742,11 @@ class DebugfsProvider(Provider): The fields are all available KVM debugfs files """ - return self.walkdir(PATH_DEBUGFS_KVM)[2] + exempt_list = ['halt_poll_fail_ns', 'halt_poll_success_ns'] + fields = [field for field in self.walkdir(PATH_DEBUGFS_KVM)[2] + if field not in exempt_list] + + return fields def update_fields(self, fields_filter): """Refresh fields, applying fields_filter""" -- cgit v1.2.3 From cffdd6d90482316e18d686060a4397902ea04bd2 Mon Sep 17 00:00:00 2001 From: Simon Beginn Date: Fri, 11 Dec 2020 16:17:32 -0800 Subject: Input: goodix - add upside-down quirk for Teclast X98 Pro tablet The touchscreen on the Teclast x98 Pro is also mounted upside-down in relation to the display orientation. Signed-off-by: Simon Beginn Signed-off-by: Bastien Nocera Link: https://lore.kernel.org/r/20201117004253.27A5A27EFD@localhost Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/goodix.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index 02c75ea385e0..6612f9e2d7e8 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -192,6 +192,18 @@ static const struct dmi_system_id rotated_screen[] = { DMI_MATCH(DMI_BIOS_DATE, "12/19/2014"), }, }, + { + .ident = "Teclast X98 Pro", + .matches = { + /* + * Only match BIOS date, because the manufacturers + * BIOS does not report the board name at all + * (sometimes)... + */ + DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"), + DMI_MATCH(DMI_BIOS_DATE, "10/28/2015"), + }, + }, { .ident = "WinBook TW100", .matches = { -- cgit v1.2.3 From 0d07c0ec4381f630c801539c79ad8dcc627f6e4a Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 11 Dec 2020 16:04:17 +0900 Subject: x86/kprobes: Fix optprobe to detect INT3 padding correctly Commit 7705dc855797 ("x86/vmlinux: Use INT3 instead of NOP for linker fill bytes") changed the padding bytes between functions from NOP to INT3. However, when optprobe decodes a target function it finds INT3 and gives up the jump optimization. Instead of giving up any INT3 detection, check whether the rest of the bytes to the end of the function are INT3. If all of them are INT3, those come from the linker. In that case, continue the optprobe jump optimization. [ bp: Massage commit message. ] Fixes: 7705dc855797 ("x86/vmlinux: Use INT3 instead of NOP for linker fill bytes") Reported-by: Adam Zabrocki Signed-off-by: Masami Hiramatsu Signed-off-by: Borislav Petkov Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/160767025681.3880685.16021570341428835411.stgit@devnote2 --- arch/x86/kernel/kprobes/opt.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 041f0b50bc27..08eb23074f92 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -272,6 +272,19 @@ static int insn_is_indirect_jump(struct insn *insn) return ret; } +static bool is_padding_int3(unsigned long addr, unsigned long eaddr) +{ + unsigned char ops; + + for (; addr < eaddr; addr++) { + if (get_kernel_nofault(ops, (void *)addr) < 0 || + ops != INT3_INSN_OPCODE) + return false; + } + + return true; +} + /* Decode whole function to ensure any instructions don't jump into target */ static int can_optimize(unsigned long paddr) { @@ -310,9 +323,14 @@ static int can_optimize(unsigned long paddr) return 0; kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); insn_get_length(&insn); - /* Another subsystem puts a breakpoint */ + /* + * In the case of detecting unknown breakpoint, this could be + * a padding INT3 between functions. Let's check that all the + * rest of the bytes are also INT3. + */ if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) - return 0; + return is_padding_int3(addr, paddr - offset + size) ? 1 : 0; + /* Recover address */ insn.kaddr = (void *)addr; insn.next_byte = (void *)(addr + insn.length); -- cgit v1.2.3 From 6ffeb1c3f8226244c08105bcdbeecc04bad6b89a Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Sat, 12 Dec 2020 11:55:37 -0500 Subject: md: change mddev 'chunk_sectors' from int to unsigned MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit e2782f560c29 ("Revert "dm raid: remove unnecessary discard limits for raid10"") exposed compiler warnings introduced by commit e0910c8e4f87 ("dm raid: fix discard limits for raid1 and raid10"): In file included from ./include/linux/kernel.h:14, from ./include/asm-generic/bug.h:20, from ./arch/x86/include/asm/bug.h:93, from ./include/linux/bug.h:5, from ./include/linux/mmdebug.h:5, from ./include/linux/gfp.h:5, from ./include/linux/slab.h:15, from drivers/md/dm-raid.c:8: drivers/md/dm-raid.c: In function ‘raid_io_hints’: ./include/linux/minmax.h:18:28: warning: comparison of distinct pointer types lacks a cast (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1))) ^~ ./include/linux/minmax.h:32:4: note: in expansion of macro ‘__typecheck’ (__typecheck(x, y) && __no_side_effects(x, y)) ^~~~~~~~~~~ ./include/linux/minmax.h:42:24: note: in expansion of macro ‘__safe_cmp’ __builtin_choose_expr(__safe_cmp(x, y), \ ^~~~~~~~~~ ./include/linux/minmax.h:51:19: note: in expansion of macro ‘__careful_cmp’ #define min(x, y) __careful_cmp(x, y, <) ^~~~~~~~~~~~~ ./include/linux/minmax.h:84:39: note: in expansion of macro ‘min’ __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); }) ^~~ drivers/md/dm-raid.c:3739:33: note: in expansion of macro ‘min_not_zero’ limits->max_discard_sectors = min_not_zero(rs->md.chunk_sectors, ^~~~~~~~~~~~ Fix this by changing the chunk_sectors member of 'struct mddev' from int to 'unsigned int' to match the type used for the 'chunk_sectors' member of 'struct queue_limits'. Various MD code still uses 'int' but none of it appears to ever make use of signed int; and storing positive signed int in unsigned is perfectly safe. Reported-by: Song Liu Fixes: e2782f560c29 ("Revert "dm raid: remove unnecessary discard limits for raid10"") Fixes: e0910c8e4f87 ("dm raid: fix discard limits for raid1 and raid10") Cc: stable@vger,kernel.org # e0910c8e4f87 was marked for stable@ Signed-off-by: Mike Snitzer Reviewed-by: Song Liu Signed-off-by: Jens Axboe --- drivers/md/md.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/md.h b/drivers/md/md.h index 2175a5ac4f7c..bb645bc3ba6d 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -311,7 +311,7 @@ struct mddev { int external; /* metadata is * managed externally */ char metadata_type[17]; /* externally set*/ - int chunk_sectors; + unsigned int chunk_sectors; time64_t ctime, utime; int level, layout; char clevel[16]; @@ -339,7 +339,7 @@ struct mddev { */ sector_t reshape_position; int delta_disks, new_level, new_layout; - int new_chunk_sectors; + unsigned int new_chunk_sectors; int reshape_backwards; struct md_thread *thread; /* management thread */ -- cgit v1.2.3 From 2c85ebc57b3e1817b6ce1a6b703928e113a90442 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Dec 2020 14:41:30 -0800 Subject: Linux 5.10 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 9ec53d947628..e30cf02da8b8 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = NAME = Kleptomaniac Octopus # *DOCUMENTATION* -- cgit v1.2.3 From 2aa078932ff6c66bf10cc5b3144440dbfa7d813d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 17 Dec 2020 16:31:36 -0800 Subject: KVM: x86/mmu: Use -1 to flag an undefined spte in get_mmio_spte() Return -1 from the get_walk() helpers if the shadow walk doesn't fill at least one spte, which can theoretically happen if the walk hits a not-present PDPTR. Returning the root level in such a case will cause get_mmio_spte() to return garbage (uninitialized stack data). In practice, such a scenario should be impossible as KVM shouldn't get a reserved-bit page fault with a not-present PDPTR. Note, using mmu->root_level in get_walk() is wrong for other reasons, too, but that's now a moot point. Fixes: 95fb5b0258b7 ("kvm: x86/mmu: Support MMIO in the TDP MMU") Cc: Ben Gardon Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20201218003139.2167891-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 7 ++++++- arch/x86/kvm/mmu/tdp_mmu.c | 2 +- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7a6ae9e90bd7..a48cd12c01d7 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3488,7 +3488,7 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) { struct kvm_shadow_walk_iterator iterator; - int leaf = vcpu->arch.mmu->root_level; + int leaf = -1; u64 spte; @@ -3532,6 +3532,11 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) else leaf = get_walk(vcpu, addr, sptes); + if (unlikely(leaf < 0)) { + *sptep = 0ull; + return reserved; + } + rsvd_check = &vcpu->arch.mmu->shadow_zero_check; for (level = root; level >= leaf; level--) { diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 84c8f06bec26..50cec7a15ddb 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1152,8 +1152,8 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) { struct tdp_iter iter; struct kvm_mmu *mmu = vcpu->arch.mmu; - int leaf = vcpu->arch.mmu->shadow_root_level; gfn_t gfn = addr >> PAGE_SHIFT; + int leaf = -1; tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { leaf = iter.level; -- cgit v1.2.3 From 39b4d43e6003cee51cd119596d3c33d0449eb44c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 17 Dec 2020 16:31:37 -0800 Subject: KVM: x86/mmu: Get root level from walkers when retrieving MMIO SPTE Get the so called "root" level from the low level shadow page table walkers instead of manually attempting to calculate it higher up the stack, e.g. in get_mmio_spte(). When KVM is using PAE shadow paging, the starting level of the walk, from the callers perspective, is not the CR3 root but rather the PDPTR "root". Checking for reserved bits from the CR3 root causes get_mmio_spte() to consume uninitialized stack data due to indexing into sptes[] for a level that was not filled by get_walk(). This can result in false positives and/or negatives depending on what garbage happens to be on the stack. Opportunistically nuke a few extra newlines. Fixes: 95fb5b0258b7 ("kvm: x86/mmu: Support MMIO in the TDP MMU") Reported-by: Richard Herbert Cc: Ben Gardon Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20201218003139.2167891-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 15 ++++++--------- arch/x86/kvm/mmu/tdp_mmu.c | 5 ++++- arch/x86/kvm/mmu/tdp_mmu.h | 4 +++- 3 files changed, 13 insertions(+), 11 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index a48cd12c01d7..52f36c879086 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3485,16 +3485,16 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) * Return the level of the lowest level SPTE added to sptes. * That SPTE may be non-present. */ -static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) +static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level) { struct kvm_shadow_walk_iterator iterator; int leaf = -1; u64 spte; - walk_shadow_page_lockless_begin(vcpu); - for (shadow_walk_init(&iterator, vcpu, addr); + for (shadow_walk_init(&iterator, vcpu, addr), + *root_level = iterator.level; shadow_walk_okay(&iterator); __shadow_walk_next(&iterator, spte)) { leaf = iterator.level; @@ -3504,7 +3504,6 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) if (!is_shadow_present_pte(spte)) break; - } walk_shadow_page_lockless_end(vcpu); @@ -3517,9 +3516,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { u64 sptes[PT64_ROOT_MAX_LEVEL]; struct rsvd_bits_validate *rsvd_check; - int root = vcpu->arch.mmu->shadow_root_level; - int leaf; - int level; + int root, leaf, level; bool reserved = false; if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) { @@ -3528,9 +3525,9 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) } if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) - leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes); + leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root); else - leaf = get_walk(vcpu, addr, sptes); + leaf = get_walk(vcpu, addr, sptes, &root); if (unlikely(leaf < 0)) { *sptep = 0ull; diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 50cec7a15ddb..a4f9447f8327 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1148,13 +1148,16 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, * Return the level of the lowest level SPTE added to sptes. * That SPTE may be non-present. */ -int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) +int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, + int *root_level) { struct tdp_iter iter; struct kvm_mmu *mmu = vcpu->arch.mmu; gfn_t gfn = addr >> PAGE_SHIFT; int leaf = -1; + *root_level = vcpu->arch.mmu->shadow_root_level; + tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { leaf = iter.level; sptes[leaf - 1] = iter.old_spte; diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 556e065503f6..cbbdbadd1526 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -44,5 +44,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn); -int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes); +int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, + int *root_level); + #endif /* __KVM_X86_MMU_TDP_MMU_H */ -- cgit v1.2.3 From dde81f9477d018a96fba991c5928c6ab8cc109f8 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 17 Dec 2020 16:31:38 -0800 Subject: KVM: x86/mmu: Use raw level to index into MMIO walks' sptes array Bump the size of the sptes array by one and use the raw level of the SPTE to index into the sptes array. Using the SPTE level directly improves readability by eliminating the need to reason out why the level is being adjusted when indexing the array. The array is on the stack and is not explicitly initialized; bumping its size is nothing more than a superficial adjustment to the stack frame. Signed-off-by: Sean Christopherson Message-Id: <20201218003139.2167891-4-seanjc@google.com> Reviewed-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 15 +++++++-------- arch/x86/kvm/mmu/tdp_mmu.c | 2 +- 2 files changed, 8 insertions(+), 9 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 52f36c879086..4798a4472066 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3500,7 +3500,7 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level leaf = iterator.level; spte = mmu_spte_get_lockless(iterator.sptep); - sptes[leaf - 1] = spte; + sptes[leaf] = spte; if (!is_shadow_present_pte(spte)) break; @@ -3514,7 +3514,7 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level /* return true if reserved bit is detected on spte. */ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { - u64 sptes[PT64_ROOT_MAX_LEVEL]; + u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; struct rsvd_bits_validate *rsvd_check; int root, leaf, level; bool reserved = false; @@ -3537,16 +3537,15 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) rsvd_check = &vcpu->arch.mmu->shadow_zero_check; for (level = root; level >= leaf; level--) { - if (!is_shadow_present_pte(sptes[level - 1])) + if (!is_shadow_present_pte(sptes[level])) break; /* * Use a bitwise-OR instead of a logical-OR to aggregate the * reserved bit and EPT's invalid memtype/XWR checks to avoid * adding a Jcc in the loop. */ - reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level - 1]) | - __is_rsvd_bits_set(rsvd_check, sptes[level - 1], - level); + reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level]) | + __is_rsvd_bits_set(rsvd_check, sptes[level], level); } if (reserved) { @@ -3554,10 +3553,10 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) __func__, addr); for (level = root; level >= leaf; level--) pr_err("------ spte 0x%llx level %d.\n", - sptes[level - 1], level); + sptes[level], level); } - *sptep = sptes[leaf - 1]; + *sptep = sptes[leaf]; return reserved; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index a4f9447f8327..efef571806ad 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1160,7 +1160,7 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { leaf = iter.level; - sptes[leaf - 1] = iter.old_spte; + sptes[leaf] = iter.old_spte; } return leaf; -- cgit v1.2.3 From 9aa418792f5f11ef5d6f72265e1f8ae07efd5784 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 17 Dec 2020 16:31:39 -0800 Subject: KVM: x86/mmu: Optimize not-present/MMIO SPTE check in get_mmio_spte() Check only the terminal leaf for a "!PRESENT || MMIO" SPTE when looking for reserved bits on valid, non-MMIO SPTEs. The get_walk() helpers terminate their walks if a not-present or MMIO SPTE is encountered, i.e. the non-terminal SPTEs have already been verified to be regular SPTEs. This eliminates an extra check-and-branch in a relatively hot loop. Signed-off-by: Sean Christopherson Message-Id: <20201218003139.2167891-5-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4798a4472066..769855f5f0a1 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3511,7 +3511,7 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level return leaf; } -/* return true if reserved bit is detected on spte. */ +/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; @@ -3534,11 +3534,20 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) return reserved; } + *sptep = sptes[leaf]; + + /* + * Skip reserved bits checks on the terminal leaf if it's not a valid + * SPTE. Note, this also (intentionally) skips MMIO SPTEs, which, by + * design, always have reserved bits set. The purpose of the checks is + * to detect reserved bits on non-MMIO SPTEs. i.e. buggy SPTEs. + */ + if (!is_shadow_present_pte(sptes[leaf])) + leaf++; + rsvd_check = &vcpu->arch.mmu->shadow_zero_check; - for (level = root; level >= leaf; level--) { - if (!is_shadow_present_pte(sptes[level])) - break; + for (level = root; level >= leaf; level--) /* * Use a bitwise-OR instead of a logical-OR to aggregate the * reserved bit and EPT's invalid memtype/XWR checks to avoid @@ -3546,7 +3555,6 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) */ reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level]) | __is_rsvd_bits_set(rsvd_check, sptes[level], level); - } if (reserved) { pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n", @@ -3556,8 +3564,6 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) sptes[level], level); } - *sptep = sptes[leaf]; - return reserved; } -- cgit v1.2.3