From 7b229b13d78d112e2c5d4a60a3c6f602289959fa Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sat, 10 Apr 2021 19:56:05 -0700
Subject: HID: hid-input: add mapping for emoji picker key

HUTRR101 added a new usage code for a key that is supposed to invoke and
dismiss an emoji picker widget to assist users to locate and enter emojis.

This patch adds a new key definition KEY_EMOJI_PICKER and maps 0x0c/0x0d9
usage code to this new keycode. Additionally hid-debug is adjusted to
recognize this new usage code as well.

Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/uapi/linux/input-event-codes.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h
index ee93428ced9a..225ec87d4f22 100644
--- a/include/uapi/linux/input-event-codes.h
+++ b/include/uapi/linux/input-event-codes.h
@@ -611,6 +611,7 @@
 #define KEY_VOICECOMMAND		0x246	/* Listening Voice Command */
 #define KEY_ASSISTANT		0x247	/* AL Context-aware desktop assistant */
 #define KEY_KBD_LAYOUT_NEXT	0x248	/* AC Next Keyboard Layout Select */
+#define KEY_EMOJI_PICKER	0x249	/* Show/hide emoji picker (HUTRR101) */
 
 #define KEY_BRIGHTNESS_MIN		0x250	/* Set Brightness to Minimum */
 #define KEY_BRIGHTNESS_MAX		0x251	/* Set Brightness to Maximum */
-- 
cgit v1.2.3


From 6be388f4a35d2ce5ef7dbf635a8964a5da7f799f Mon Sep 17 00:00:00 2001
From: Anirudh Rayabharam <mail@anirudhrb.com>
Date: Sun, 25 Apr 2021 23:03:53 +0530
Subject: HID: usbhid: fix info leak in hid_submit_ctrl

In hid_submit_ctrl(), the way of calculating the report length doesn't
take into account that report->size can be zero. When running the
syzkaller reproducer, a report of size 0 causes hid_submit_ctrl) to
calculate transfer_buffer_length as 16384. When this urb is passed to
the usb core layer, KMSAN reports an info leak of 16384 bytes.

To fix this, first modify hid_report_len() to account for the zero
report size case by using DIV_ROUND_UP for the division. Then, call it
from hid_submit_ctrl().

Reported-by: syzbot+7c2bb71996f95a82524c@syzkaller.appspotmail.com
Signed-off-by: Anirudh Rayabharam <mail@anirudhrb.com>
Acked-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/usbhid/hid-core.c | 2 +-
 include/linux/hid.h           | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 86257ce6d619..4e9077363c96 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -374,7 +374,7 @@ static int hid_submit_ctrl(struct hid_device *hid)
 	raw_report = usbhid->ctrl[usbhid->ctrltail].raw_report;
 	dir = usbhid->ctrl[usbhid->ctrltail].dir;
 
-	len = ((report->size - 1) >> 3) + 1 + (report->id > 0);
+	len = hid_report_len(report);
 	if (dir == USB_DIR_OUT) {
 		usbhid->urbctrl->pipe = usb_sndctrlpipe(hid_to_usb_dev(hid), 0);
 		usbhid->urbctrl->transfer_buffer_length = len;
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 271021e20a3f..10e922cee4eb 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -1167,8 +1167,7 @@ static inline void hid_hw_wait(struct hid_device *hdev)
  */
 static inline u32 hid_report_len(struct hid_report *report)
 {
-	/* equivalent to DIV_ROUND_UP(report->size, 8) + !!(report->id > 0) */
-	return ((report->size - 1) >> 3) + 1 + (report->id > 0);
+	return DIV_ROUND_UP(report->size, 8) + (report->id > 0);
 }
 
 int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size,
-- 
cgit v1.2.3


From 285c0faddcebdf360412fc9ef9cde63cf98da7f6 Mon Sep 17 00:00:00 2001
From: Bharat Jauhari <bjauhari@habana.ai>
Date: Thu, 25 Mar 2021 18:15:40 +0200
Subject: habanalabs: expose ASIC specific PLL index

Currently the user cannot interpret the PLL information based on index
as its exposed as an integer.

This commit exposes ASIC specific PLL indexes and maps it to a generic
FW compatible index.

Signed-off-by: Bharat Jauhari <bjauhari@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/misc/habanalabs/common/firmware_if.c | 34 ++++++++++-------
 drivers/misc/habanalabs/common/habanalabs.h  | 16 ++++----
 drivers/misc/habanalabs/common/sysfs.c       |  4 +-
 drivers/misc/habanalabs/gaudi/gaudi.c        | 55 ++++++++++------------------
 drivers/misc/habanalabs/gaudi/gaudi_hwmgr.c  | 12 +++---
 drivers/misc/habanalabs/goya/goya.c          | 47 +++++++++---------------
 drivers/misc/habanalabs/goya/goya_hwmgr.c    | 40 ++++++++++----------
 include/uapi/misc/habanalabs.h               | 33 +++++++++++++++++
 8 files changed, 127 insertions(+), 114 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 832dd5c5bb06..7cf82da67dab 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -661,18 +661,13 @@ int hl_fw_cpucp_total_energy_get(struct hl_device *hdev, u64 *total_energy)
 	return rc;
 }
 
-int get_used_pll_index(struct hl_device *hdev, enum pll_index input_pll_index,
+int get_used_pll_index(struct hl_device *hdev, u32 input_pll_index,
 						enum pll_index *pll_index)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	u8 pll_byte, pll_bit_off;
 	bool dynamic_pll;
-
-	if (input_pll_index >= PLL_MAX) {
-		dev_err(hdev->dev, "PLL index %d is out of range\n",
-							input_pll_index);
-		return -EINVAL;
-	}
+	int fw_pll_idx;
 
 	dynamic_pll = prop->fw_security_status_valid &&
 		(prop->fw_app_security_map & CPU_BOOT_DEV_STS0_DYN_PLL_EN);
@@ -680,28 +675,39 @@ int get_used_pll_index(struct hl_device *hdev, enum pll_index input_pll_index,
 	if (!dynamic_pll) {
 		/*
 		 * in case we are working with legacy FW (each asic has unique
-		 * PLL numbering) extract the legacy numbering
+		 * PLL numbering) use the driver based index as they are
+		 * aligned with fw legacy numbering
 		 */
-		*pll_index = hdev->legacy_pll_map[input_pll_index];
+		*pll_index = input_pll_index;
 		return 0;
 	}
 
+	/* retrieve a FW compatible PLL index based on
+	 * ASIC specific user request
+	 */
+	fw_pll_idx = hdev->asic_funcs->map_pll_idx_to_fw_idx(input_pll_index);
+	if (fw_pll_idx < 0) {
+		dev_err(hdev->dev, "Invalid PLL index (%u) error %d\n",
+			input_pll_index, fw_pll_idx);
+		return -EINVAL;
+	}
+
 	/* PLL map is a u8 array */
-	pll_byte = prop->cpucp_info.pll_map[input_pll_index >> 3];
-	pll_bit_off = input_pll_index & 0x7;
+	pll_byte = prop->cpucp_info.pll_map[fw_pll_idx >> 3];
+	pll_bit_off = fw_pll_idx & 0x7;
 
 	if (!(pll_byte & BIT(pll_bit_off))) {
 		dev_err(hdev->dev, "PLL index %d is not supported\n",
-							input_pll_index);
+			fw_pll_idx);
 		return -EINVAL;
 	}
 
-	*pll_index = input_pll_index;
+	*pll_index = fw_pll_idx;
 
 	return 0;
 }
 
-int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, enum pll_index pll_index,
+int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, u32 pll_index,
 		u16 *pll_freq_arr)
 {
 	struct cpucp_packet pkt;
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 44e89da30b4a..91291a8e201e 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -930,6 +930,9 @@ enum div_select_defs {
  *                         driver is ready to receive asynchronous events. This
  *                         function should be called during the first init and
  *                         after every hard-reset of the device
+ * @get_msi_info: Retrieve asic-specific MSI ID of the f/w async event
+ * @map_pll_idx_to_fw_idx: convert driver specific per asic PLL index to
+ *                         generic f/w compatible PLL Indexes
  */
 struct hl_asic_funcs {
 	int (*early_init)(struct hl_device *hdev);
@@ -1054,6 +1057,7 @@ struct hl_asic_funcs {
 			u32 block_id, u32 block_size);
 	void (*enable_events_from_fw)(struct hl_device *hdev);
 	void (*get_msi_info)(u32 *table);
+	int (*map_pll_idx_to_fw_idx)(u32 pll_idx);
 };
 
 
@@ -1950,8 +1954,6 @@ struct hl_mmu_funcs {
  * @aggregated_cs_counters: aggregated cs counters among all contexts
  * @mmu_priv: device-specific MMU data.
  * @mmu_func: device-related MMU functions.
- * @legacy_pll_map: map holding map between dynamic (common) PLL indexes and
- *                  static (asic specific) PLL indexes.
  * @dram_used_mem: current DRAM memory consumption.
  * @timeout_jiffies: device CS timeout value.
  * @max_power: the max power of the device, as configured by the sysadmin. This
@@ -2071,8 +2073,6 @@ struct hl_device {
 	struct hl_mmu_priv		mmu_priv;
 	struct hl_mmu_funcs		mmu_func[MMU_NUM_PGT_LOCATIONS];
 
-	enum pll_index			*legacy_pll_map;
-
 	atomic64_t			dram_used_mem;
 	u64				timeout_jiffies;
 	u64				max_power;
@@ -2387,9 +2387,9 @@ int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev,
 		struct hl_info_pci_counters *counters);
 int hl_fw_cpucp_total_energy_get(struct hl_device *hdev,
 			u64 *total_energy);
-int get_used_pll_index(struct hl_device *hdev, enum pll_index input_pll_index,
+int get_used_pll_index(struct hl_device *hdev, u32 input_pll_index,
 						enum pll_index *pll_index);
-int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, enum pll_index pll_index,
+int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, u32 pll_index,
 		u16 *pll_freq_arr);
 int hl_fw_cpucp_power_get(struct hl_device *hdev, u64 *power);
 int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,
@@ -2411,9 +2411,9 @@ int hl_pci_set_outbound_region(struct hl_device *hdev,
 int hl_pci_init(struct hl_device *hdev);
 void hl_pci_fini(struct hl_device *hdev);
 
-long hl_get_frequency(struct hl_device *hdev, enum pll_index pll_index,
+long hl_get_frequency(struct hl_device *hdev, u32 pll_index,
 								bool curr);
-void hl_set_frequency(struct hl_device *hdev, enum pll_index pll_index,
+void hl_set_frequency(struct hl_device *hdev, u32 pll_index,
 								u64 freq);
 int hl_get_temperature(struct hl_device *hdev,
 		       int sensor_index, u32 attr, long *value);
diff --git a/drivers/misc/habanalabs/common/sysfs.c b/drivers/misc/habanalabs/common/sysfs.c
index 9fa61573a89d..c9f649b31e3a 100644
--- a/drivers/misc/habanalabs/common/sysfs.c
+++ b/drivers/misc/habanalabs/common/sysfs.c
@@ -9,7 +9,7 @@
 
 #include <linux/pci.h>
 
-long hl_get_frequency(struct hl_device *hdev, enum pll_index pll_index,
+long hl_get_frequency(struct hl_device *hdev, u32 pll_index,
 								bool curr)
 {
 	struct cpucp_packet pkt;
@@ -44,7 +44,7 @@ long hl_get_frequency(struct hl_device *hdev, enum pll_index pll_index,
 	return (long) result;
 }
 
-void hl_set_frequency(struct hl_device *hdev, enum pll_index pll_index,
+void hl_set_frequency(struct hl_device *hdev, u32 pll_index,
 								u64 freq)
 {
 	struct cpucp_packet pkt;
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index b751652f80a8..81155f06c126 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -105,36 +105,6 @@
 
 #define GAUDI_PLL_MAX 10
 
-/*
- * this enum kept here for compatibility with old FW (in which each asic has
- * unique PLL numbering
- */
-enum gaudi_pll_index {
-	GAUDI_CPU_PLL = 0,
-	GAUDI_PCI_PLL,
-	GAUDI_SRAM_PLL,
-	GAUDI_HBM_PLL,
-	GAUDI_NIC_PLL,
-	GAUDI_DMA_PLL,
-	GAUDI_MESH_PLL,
-	GAUDI_MME_PLL,
-	GAUDI_TPC_PLL,
-	GAUDI_IF_PLL,
-};
-
-static enum pll_index gaudi_pll_map[PLL_MAX] = {
-	[CPU_PLL] = GAUDI_CPU_PLL,
-	[PCI_PLL] = GAUDI_PCI_PLL,
-	[SRAM_PLL] = GAUDI_SRAM_PLL,
-	[HBM_PLL] = GAUDI_HBM_PLL,
-	[NIC_PLL] = GAUDI_NIC_PLL,
-	[DMA_PLL] = GAUDI_DMA_PLL,
-	[MESH_PLL] = GAUDI_MESH_PLL,
-	[MME_PLL] = GAUDI_MME_PLL,
-	[TPC_PLL] = GAUDI_TPC_PLL,
-	[IF_PLL] = GAUDI_IF_PLL,
-};
-
 static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = {
 		"gaudi cq 0_0", "gaudi cq 0_1", "gaudi cq 0_2", "gaudi cq 0_3",
 		"gaudi cq 1_0", "gaudi cq 1_1", "gaudi cq 1_2", "gaudi cq 1_3",
@@ -810,7 +780,7 @@ static int gaudi_fetch_psoc_frequency(struct hl_device *hdev)
 			freq = 0;
 		}
 	} else {
-		rc = hl_fw_cpucp_pll_info_get(hdev, CPU_PLL, pll_freq_arr);
+		rc = hl_fw_cpucp_pll_info_get(hdev, HL_GAUDI_CPU_PLL, pll_freq_arr);
 
 		if (rc)
 			return rc;
@@ -1652,9 +1622,6 @@ static int gaudi_sw_init(struct hl_device *hdev)
 
 	hdev->asic_specific = gaudi;
 
-	/* store legacy PLL map */
-	hdev->legacy_pll_map = gaudi_pll_map;
-
 	/* Create DMA pool for small allocations */
 	hdev->dma_pool = dma_pool_create(dev_name(hdev->dev),
 			&hdev->pdev->dev, GAUDI_DMA_POOL_BLK_SIZE, 8, 0);
@@ -8783,6 +8750,23 @@ static void gaudi_enable_events_from_fw(struct hl_device *hdev)
 	WREG32(mmGIC_DISTRIBUTOR__5_GICD_SETSPI_NSR, GAUDI_EVENT_INTS_REGISTER);
 }
 
+static int gaudi_map_pll_idx_to_fw_idx(u32 pll_idx)
+{
+	switch (pll_idx) {
+	case HL_GAUDI_CPU_PLL: return CPU_PLL;
+	case HL_GAUDI_PCI_PLL: return PCI_PLL;
+	case HL_GAUDI_NIC_PLL: return NIC_PLL;
+	case HL_GAUDI_DMA_PLL: return DMA_PLL;
+	case HL_GAUDI_MESH_PLL: return MESH_PLL;
+	case HL_GAUDI_MME_PLL: return MME_PLL;
+	case HL_GAUDI_TPC_PLL: return TPC_PLL;
+	case HL_GAUDI_IF_PLL: return IF_PLL;
+	case HL_GAUDI_SRAM_PLL: return SRAM_PLL;
+	case HL_GAUDI_HBM_PLL: return HBM_PLL;
+	default: return -EINVAL;
+	}
+}
+
 static const struct hl_asic_funcs gaudi_funcs = {
 	.early_init = gaudi_early_init,
 	.early_fini = gaudi_early_fini,
@@ -8866,7 +8850,8 @@ static const struct hl_asic_funcs gaudi_funcs = {
 	.ack_protection_bits_errors = gaudi_ack_protection_bits_errors,
 	.get_hw_block_id = gaudi_get_hw_block_id,
 	.hw_block_mmap = gaudi_block_mmap,
-	.enable_events_from_fw = gaudi_enable_events_from_fw
+	.enable_events_from_fw = gaudi_enable_events_from_fw,
+	.map_pll_idx_to_fw_idx = gaudi_map_pll_idx_to_fw_idx
 };
 
 /**
diff --git a/drivers/misc/habanalabs/gaudi/gaudi_hwmgr.c b/drivers/misc/habanalabs/gaudi/gaudi_hwmgr.c
index 8c49da4bcbd5..9b60eadd4c35 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi_hwmgr.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi_hwmgr.c
@@ -13,7 +13,7 @@ void gaudi_set_pll_profile(struct hl_device *hdev, enum hl_pll_frequency freq)
 	struct gaudi_device *gaudi = hdev->asic_specific;
 
 	if (freq == PLL_LAST)
-		hl_set_frequency(hdev, MME_PLL, gaudi->max_freq_value);
+		hl_set_frequency(hdev, HL_GAUDI_MME_PLL, gaudi->max_freq_value);
 }
 
 int gaudi_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk)
@@ -23,7 +23,7 @@ int gaudi_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk)
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, MME_PLL, false);
+	value = hl_get_frequency(hdev, HL_GAUDI_MME_PLL, false);
 
 	if (value < 0) {
 		dev_err(hdev->dev, "Failed to retrieve device max clock %ld\n",
@@ -33,7 +33,7 @@ int gaudi_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk)
 
 	*max_clk = (value / 1000 / 1000);
 
-	value = hl_get_frequency(hdev, MME_PLL, true);
+	value = hl_get_frequency(hdev, HL_GAUDI_MME_PLL, true);
 
 	if (value < 0) {
 		dev_err(hdev->dev,
@@ -57,7 +57,7 @@ static ssize_t clk_max_freq_mhz_show(struct device *dev,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, MME_PLL, false);
+	value = hl_get_frequency(hdev, HL_GAUDI_MME_PLL, false);
 
 	gaudi->max_freq_value = value;
 
@@ -85,7 +85,7 @@ static ssize_t clk_max_freq_mhz_store(struct device *dev,
 
 	gaudi->max_freq_value = value * 1000 * 1000;
 
-	hl_set_frequency(hdev, MME_PLL, gaudi->max_freq_value);
+	hl_set_frequency(hdev, HL_GAUDI_MME_PLL, gaudi->max_freq_value);
 
 fail:
 	return count;
@@ -100,7 +100,7 @@ static ssize_t clk_cur_freq_mhz_show(struct device *dev,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, MME_PLL, true);
+	value = hl_get_frequency(hdev, HL_GAUDI_MME_PLL, true);
 
 	return sprintf(buf, "%lu\n", (value / 1000 / 1000));
 }
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index e27338f4aad2..e0ad2a269779 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -118,30 +118,6 @@
 #define IS_MME_IDLE(mme_arch_sts) \
 	(((mme_arch_sts) & MME_ARCH_IDLE_MASK) == MME_ARCH_IDLE_MASK)
 
-/*
- * this enum kept here for compatibility with old FW (in which each asic has
- * unique PLL numbering
- */
-enum goya_pll_index {
-	GOYA_CPU_PLL = 0,
-	GOYA_IC_PLL,
-	GOYA_MC_PLL,
-	GOYA_MME_PLL,
-	GOYA_PCI_PLL,
-	GOYA_EMMC_PLL,
-	GOYA_TPC_PLL,
-};
-
-static enum pll_index goya_pll_map[PLL_MAX] = {
-	[CPU_PLL] = GOYA_CPU_PLL,
-	[IC_PLL] = GOYA_IC_PLL,
-	[MC_PLL] = GOYA_MC_PLL,
-	[MME_PLL] = GOYA_MME_PLL,
-	[PCI_PLL] = GOYA_PCI_PLL,
-	[EMMC_PLL] = GOYA_EMMC_PLL,
-	[TPC_PLL] = GOYA_TPC_PLL,
-};
-
 static const char goya_irq_name[GOYA_MSIX_ENTRIES][GOYA_MAX_STRING_LEN] = {
 		"goya cq 0", "goya cq 1", "goya cq 2", "goya cq 3",
 		"goya cq 4", "goya cpu eq"
@@ -775,7 +751,8 @@ static void goya_fetch_psoc_frequency(struct hl_device *hdev)
 			freq = 0;
 		}
 	} else {
-		rc = hl_fw_cpucp_pll_info_get(hdev, PCI_PLL, pll_freq_arr);
+		rc = hl_fw_cpucp_pll_info_get(hdev, HL_GOYA_PCI_PLL,
+				pll_freq_arr);
 
 		if (rc)
 			return;
@@ -897,9 +874,6 @@ static int goya_sw_init(struct hl_device *hdev)
 
 	hdev->asic_specific = goya;
 
-	/* store legacy PLL map */
-	hdev->legacy_pll_map = goya_pll_map;
-
 	/* Create DMA pool for small allocations */
 	hdev->dma_pool = dma_pool_create(dev_name(hdev->dev),
 			&hdev->pdev->dev, GOYA_DMA_POOL_BLK_SIZE, 8, 0);
@@ -5512,6 +5486,20 @@ static void goya_enable_events_from_fw(struct hl_device *hdev)
 			GOYA_ASYNC_EVENT_ID_INTS_REGISTER);
 }
 
+static int goya_map_pll_idx_to_fw_idx(u32 pll_idx)
+{
+	switch (pll_idx) {
+	case HL_GOYA_CPU_PLL: return CPU_PLL;
+	case HL_GOYA_PCI_PLL: return PCI_PLL;
+	case HL_GOYA_MME_PLL: return MME_PLL;
+	case HL_GOYA_TPC_PLL: return TPC_PLL;
+	case HL_GOYA_IC_PLL: return IC_PLL;
+	case HL_GOYA_MC_PLL: return MC_PLL;
+	case HL_GOYA_EMMC_PLL: return EMMC_PLL;
+	default: return -EINVAL;
+	}
+}
+
 static const struct hl_asic_funcs goya_funcs = {
 	.early_init = goya_early_init,
 	.early_fini = goya_early_fini,
@@ -5595,7 +5583,8 @@ static const struct hl_asic_funcs goya_funcs = {
 	.ack_protection_bits_errors = goya_ack_protection_bits_errors,
 	.get_hw_block_id = goya_get_hw_block_id,
 	.hw_block_mmap = goya_block_mmap,
-	.enable_events_from_fw = goya_enable_events_from_fw
+	.enable_events_from_fw = goya_enable_events_from_fw,
+	.map_pll_idx_to_fw_idx = goya_map_pll_idx_to_fw_idx
 };
 
 /*
diff --git a/drivers/misc/habanalabs/goya/goya_hwmgr.c b/drivers/misc/habanalabs/goya/goya_hwmgr.c
index 3acb36a1a902..7d007125727f 100644
--- a/drivers/misc/habanalabs/goya/goya_hwmgr.c
+++ b/drivers/misc/habanalabs/goya/goya_hwmgr.c
@@ -13,19 +13,19 @@ void goya_set_pll_profile(struct hl_device *hdev, enum hl_pll_frequency freq)
 
 	switch (freq) {
 	case PLL_HIGH:
-		hl_set_frequency(hdev, MME_PLL, hdev->high_pll);
-		hl_set_frequency(hdev, TPC_PLL, hdev->high_pll);
-		hl_set_frequency(hdev, IC_PLL, hdev->high_pll);
+		hl_set_frequency(hdev, HL_GOYA_MME_PLL, hdev->high_pll);
+		hl_set_frequency(hdev, HL_GOYA_TPC_PLL, hdev->high_pll);
+		hl_set_frequency(hdev, HL_GOYA_IC_PLL, hdev->high_pll);
 		break;
 	case PLL_LOW:
-		hl_set_frequency(hdev, MME_PLL, GOYA_PLL_FREQ_LOW);
-		hl_set_frequency(hdev, TPC_PLL, GOYA_PLL_FREQ_LOW);
-		hl_set_frequency(hdev, IC_PLL, GOYA_PLL_FREQ_LOW);
+		hl_set_frequency(hdev, HL_GOYA_MME_PLL, GOYA_PLL_FREQ_LOW);
+		hl_set_frequency(hdev, HL_GOYA_TPC_PLL, GOYA_PLL_FREQ_LOW);
+		hl_set_frequency(hdev, HL_GOYA_IC_PLL, GOYA_PLL_FREQ_LOW);
 		break;
 	case PLL_LAST:
-		hl_set_frequency(hdev, MME_PLL, goya->mme_clk);
-		hl_set_frequency(hdev, TPC_PLL, goya->tpc_clk);
-		hl_set_frequency(hdev, IC_PLL, goya->ic_clk);
+		hl_set_frequency(hdev, HL_GOYA_MME_PLL, goya->mme_clk);
+		hl_set_frequency(hdev, HL_GOYA_TPC_PLL, goya->tpc_clk);
+		hl_set_frequency(hdev, HL_GOYA_IC_PLL, goya->ic_clk);
 		break;
 	default:
 		dev_err(hdev->dev, "unknown frequency setting\n");
@@ -39,7 +39,7 @@ int goya_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk)
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, MME_PLL, false);
+	value = hl_get_frequency(hdev, HL_GOYA_MME_PLL, false);
 
 	if (value < 0) {
 		dev_err(hdev->dev, "Failed to retrieve device max clock %ld\n",
@@ -49,7 +49,7 @@ int goya_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk)
 
 	*max_clk = (value / 1000 / 1000);
 
-	value = hl_get_frequency(hdev, MME_PLL, true);
+	value = hl_get_frequency(hdev, HL_GOYA_MME_PLL, true);
 
 	if (value < 0) {
 		dev_err(hdev->dev,
@@ -72,7 +72,7 @@ static ssize_t mme_clk_show(struct device *dev, struct device_attribute *attr,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, MME_PLL, false);
+	value = hl_get_frequency(hdev, HL_GOYA_MME_PLL, false);
 
 	if (value < 0)
 		return value;
@@ -105,7 +105,7 @@ static ssize_t mme_clk_store(struct device *dev, struct device_attribute *attr,
 		goto fail;
 	}
 
-	hl_set_frequency(hdev, MME_PLL, value);
+	hl_set_frequency(hdev, HL_GOYA_MME_PLL, value);
 	goya->mme_clk = value;
 
 fail:
@@ -121,7 +121,7 @@ static ssize_t tpc_clk_show(struct device *dev, struct device_attribute *attr,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, TPC_PLL, false);
+	value = hl_get_frequency(hdev, HL_GOYA_TPC_PLL, false);
 
 	if (value < 0)
 		return value;
@@ -154,7 +154,7 @@ static ssize_t tpc_clk_store(struct device *dev, struct device_attribute *attr,
 		goto fail;
 	}
 
-	hl_set_frequency(hdev, TPC_PLL, value);
+	hl_set_frequency(hdev, HL_GOYA_TPC_PLL, value);
 	goya->tpc_clk = value;
 
 fail:
@@ -170,7 +170,7 @@ static ssize_t ic_clk_show(struct device *dev, struct device_attribute *attr,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, IC_PLL, false);
+	value = hl_get_frequency(hdev, HL_GOYA_IC_PLL, false);
 
 	if (value < 0)
 		return value;
@@ -203,7 +203,7 @@ static ssize_t ic_clk_store(struct device *dev, struct device_attribute *attr,
 		goto fail;
 	}
 
-	hl_set_frequency(hdev, IC_PLL, value);
+	hl_set_frequency(hdev, HL_GOYA_IC_PLL, value);
 	goya->ic_clk = value;
 
 fail:
@@ -219,7 +219,7 @@ static ssize_t mme_clk_curr_show(struct device *dev,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, MME_PLL, true);
+	value = hl_get_frequency(hdev, HL_GOYA_MME_PLL, true);
 
 	if (value < 0)
 		return value;
@@ -236,7 +236,7 @@ static ssize_t tpc_clk_curr_show(struct device *dev,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, TPC_PLL, true);
+	value = hl_get_frequency(hdev, HL_GOYA_TPC_PLL, true);
 
 	if (value < 0)
 		return value;
@@ -253,7 +253,7 @@ static ssize_t ic_clk_curr_show(struct device *dev,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, IC_PLL, true);
+	value = hl_get_frequency(hdev, HL_GOYA_IC_PLL, true);
 
 	if (value < 0)
 		return value;
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index d3e017b5f0db..6d2d34c9f375 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -239,6 +239,39 @@ enum gaudi_engine_id {
 	GAUDI_ENGINE_ID_SIZE
 };
 
+/*
+ * ASIC specific PLL index
+ *
+ * Used to retrieve in frequency info of different IPs via
+ * HL_INFO_PLL_FREQUENCY under HL_IOCTL_INFO IOCTL. The enums need to be
+ * used as an index in struct hl_pll_frequency_info
+ */
+
+enum hl_goya_pll_index {
+	HL_GOYA_CPU_PLL = 0,
+	HL_GOYA_IC_PLL,
+	HL_GOYA_MC_PLL,
+	HL_GOYA_MME_PLL,
+	HL_GOYA_PCI_PLL,
+	HL_GOYA_EMMC_PLL,
+	HL_GOYA_TPC_PLL,
+	HL_GOYA_PLL_MAX
+};
+
+enum hl_gaudi_pll_index {
+	HL_GAUDI_CPU_PLL = 0,
+	HL_GAUDI_PCI_PLL,
+	HL_GAUDI_SRAM_PLL,
+	HL_GAUDI_HBM_PLL,
+	HL_GAUDI_NIC_PLL,
+	HL_GAUDI_DMA_PLL,
+	HL_GAUDI_MESH_PLL,
+	HL_GAUDI_MME_PLL,
+	HL_GAUDI_TPC_PLL,
+	HL_GAUDI_IF_PLL,
+	HL_GAUDI_PLL_MAX
+};
+
 enum hl_device_status {
 	HL_DEVICE_STATUS_OPERATIONAL,
 	HL_DEVICE_STATUS_IN_RESET,
-- 
cgit v1.2.3


From 35f3f8504c3b60a1ae5576e178b27fc0ddd6157d Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 10 May 2021 16:12:42 +0300
Subject: spi: Switch to signed types for *_native_cs SPI controller fields

While fixing undefined behaviour the commit f60d7270c8a3 ("spi: Avoid
undefined behaviour when counting unused native CSs") missed the case
when all CSs are GPIOs and thus unused_native_cs will be evaluated to
-1 in unsigned representation. This will falsely trigger a condition
in the spi_get_gpio_descs().

Switch to signed types for *_native_cs SPI controller fields to fix above.

Fixes: f60d7270c8a3 ("spi: Avoid undefined behaviour when counting unused native CSs")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20210510131242.49455-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/spi.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 360a3bc767ca..74239d65c7fd 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -644,8 +644,8 @@ struct spi_controller {
 	int			*cs_gpios;
 	struct gpio_desc	**cs_gpiods;
 	bool			use_gpio_descriptors;
-	u8			unused_native_cs;
-	u8			max_native_cs;
+	s8			unused_native_cs;
+	s8			max_native_cs;
 
 	/* statistics */
 	struct spi_statistics	statistics;
-- 
cgit v1.2.3


From a1d5ff5651ea592c67054233b14b30bf4452999c Mon Sep 17 00:00:00 2001
From: Mathy Vanhoef <Mathy.Vanhoef@kuleuven.be>
Date: Tue, 11 May 2021 20:02:44 +0200
Subject: mac80211: properly handle A-MSDUs that start with an RFC 1042 header

Properly parse A-MSDUs whose first 6 bytes happen to equal a rfc1042
header. This can occur in practice when the destination MAC address
equals AA:AA:03:00:00:00. More importantly, this simplifies the next
patch to mitigate A-MSDU injection attacks.

Cc: stable@vger.kernel.org
Signed-off-by: Mathy Vanhoef <Mathy.Vanhoef@kuleuven.be>
Link: https://lore.kernel.org/r/20210511200110.0b2b886492f0.I23dd5d685fe16d3b0ec8106e8f01b59f499dffed@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 4 ++--
 net/mac80211/rx.c      | 2 +-
 net/wireless/util.c    | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 5224f885a99a..58c2cd417e89 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5760,7 +5760,7 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr);
  */
 int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
 				  const u8 *addr, enum nl80211_iftype iftype,
-				  u8 data_offset);
+				  u8 data_offset, bool is_amsdu);
 
 /**
  * ieee80211_data_to_8023 - convert an 802.11 data frame to 802.3
@@ -5772,7 +5772,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
 static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
 					 enum nl80211_iftype iftype)
 {
-	return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype, 0);
+	return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype, 0, false);
 }
 
 /**
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 531232b91bc4..f14d32a5001d 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2682,7 +2682,7 @@ __ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset)
 	if (ieee80211_data_to_8023_exthdr(skb, &ethhdr,
 					  rx->sdata->vif.addr,
 					  rx->sdata->vif.type,
-					  data_offset))
+					  data_offset, true))
 		return RX_DROP_UNUSABLE;
 
 	ieee80211_amsdu_to_8023s(skb, &frame_list, dev->dev_addr,
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 382c5262d997..39966a873e40 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -542,7 +542,7 @@ EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen);
 
 int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
 				  const u8 *addr, enum nl80211_iftype iftype,
-				  u8 data_offset)
+				  u8 data_offset, bool is_amsdu)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
 	struct {
@@ -629,7 +629,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
 	skb_copy_bits(skb, hdrlen, &payload, sizeof(payload));
 	tmp.h_proto = payload.proto;
 
-	if (likely((ether_addr_equal(payload.hdr, rfc1042_header) &&
+	if (likely((!is_amsdu && ether_addr_equal(payload.hdr, rfc1042_header) &&
 		    tmp.h_proto != htons(ETH_P_AARP) &&
 		    tmp.h_proto != htons(ETH_P_IPX)) ||
 		   ether_addr_equal(payload.hdr, bridge_tunnel_header)))
-- 
cgit v1.2.3


From 47c1131633ef6210add63b8b5704497023a3462a Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Wed, 12 May 2021 08:09:08 +0900
Subject: ASoC: soc-dai.h: Align the word of comment for SND_SOC_DAIFMT_CBC_CFC

Let's use "consumer" instead of "follower".

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/8735usc1gr.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dai.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index 1358a0ceb4d0..0bc29c4516e7 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -81,7 +81,7 @@ struct snd_compr_stream;
 #define SND_SOC_DAIFMT_CBP_CFP		(1 << 12) /* codec clk provider & frame provider */
 #define SND_SOC_DAIFMT_CBC_CFP		(2 << 12) /* codec clk consumer & frame provider */
 #define SND_SOC_DAIFMT_CBP_CFC		(3 << 12) /* codec clk provider & frame consumer */
-#define SND_SOC_DAIFMT_CBC_CFC		(4 << 12) /* codec clk consumer & frame follower */
+#define SND_SOC_DAIFMT_CBC_CFC		(4 << 12) /* codec clk consumer & frame consumer */
 
 /* previous definitions kept for backwards-compatibility, do not use in new contributions */
 #define SND_SOC_DAIFMT_CBM_CFM		SND_SOC_DAIFMT_CBP_CFP
-- 
cgit v1.2.3


From ca0760e7d79e2bb9c342e6b3f925b1ef01c6303e Mon Sep 17 00:00:00 2001
From: Wei Ming Chen <jj251510319013@gmail.com>
Date: Thu, 6 May 2021 20:30:51 +0800
Subject: Compiler Attributes: Add continue in comment

Add "continue;" for switch/case block according to Doc[1]

[1] https://www.kernel.org/doc/html/latest/process/deprecated.html?highlight=fallthrough#implicit-switch-case-fall-through

Signed-off-by: Wei Ming Chen <jj251510319013@gmail.com>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 include/linux/compiler_attributes.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index c043b8d2b17b..183ddd5fd072 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -199,6 +199,7 @@
  * must end with any of these keywords:
  *   break;
  *   fallthrough;
+ *   continue;
  *   goto <label>;
  *   return [expression];
  *
-- 
cgit v1.2.3


From 098116e7e640ba677d9e345cbee83d253c13d556 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 11 May 2021 10:35:21 +0200
Subject: net: really orphan skbs tied to closing sk

If the owing socket is shutting down - e.g. the sock reference
count already dropped to 0 and only sk_wmem_alloc is keeping
the sock alive, skb_orphan_partial() becomes a no-op.

When forwarding packets over veth with GRO enabled, the above
causes refcount errors.

This change addresses the issue with a plain skb_orphan() call
in the critical scenario.

Fixes: 9adc89af724f ("net: let skb_orphan_partial wake-up waiters.")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 4 +++-
 net/core/sock.c    | 8 ++++----
 2 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 42bc5e1a627f..0e962d8bc73b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2231,13 +2231,15 @@ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	sk_mem_charge(sk, skb->truesize);
 }
 
-static inline void skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk)
+static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk)
 {
 	if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) {
 		skb_orphan(skb);
 		skb->destructor = sock_efree;
 		skb->sk = sk;
+		return true;
 	}
+	return false;
 }
 
 void sk_reset_timer(struct sock *sk, struct timer_list *timer,
diff --git a/net/core/sock.c b/net/core/sock.c
index c761c4a0b66b..958614ea16ed 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2132,10 +2132,10 @@ void skb_orphan_partial(struct sk_buff *skb)
 	if (skb_is_tcp_pure_ack(skb))
 		return;
 
-	if (can_skb_orphan_partial(skb))
-		skb_set_owner_sk_safe(skb, skb->sk);
-	else
-		skb_orphan(skb);
+	if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk))
+		return;
+
+	skb_orphan(skb);
 }
 EXPORT_SYMBOL(skb_orphan_partial);
 
-- 
cgit v1.2.3


From 640d1eaff2c09e382a23bd831094ebbfaa16fef5 Mon Sep 17 00:00:00 2001
From: Jim Cromie <jim.cromie@gmail.com>
Date: Tue, 4 May 2021 16:22:34 -0600
Subject: dyndbg: avoid calling dyndbg_emit_prefix when it has no work

Wrap function in a static-inline one, which checks flags to avoid
calling the function unnecessarily.

And hoist its output-buffer initialization to the grand-caller, which
is already allocating the buffer on the stack, and can trivially
initialize it too.

Signed-off-by: Jim Cromie <jim.cromie@gmail.com>
Link: https://lore.kernel.org/r/20210504222235.1033685-2-jim.cromie@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/dynamic_debug.h |  5 +++++
 lib/dynamic_debug.c           | 19 ++++++++++++-------
 2 files changed, 17 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index a57ee75342cf..dce631e678dd 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -32,6 +32,11 @@ struct _ddebug {
 #define _DPRINTK_FLAGS_INCL_FUNCNAME	(1<<2)
 #define _DPRINTK_FLAGS_INCL_LINENO	(1<<3)
 #define _DPRINTK_FLAGS_INCL_TID		(1<<4)
+
+#define _DPRINTK_FLAGS_INCL_ANY		\
+	(_DPRINTK_FLAGS_INCL_MODNAME | _DPRINTK_FLAGS_INCL_FUNCNAME |\
+	 _DPRINTK_FLAGS_INCL_LINENO  | _DPRINTK_FLAGS_INCL_TID)
+
 #if defined DEBUG
 #define _DPRINTK_FLAGS_DEFAULT _DPRINTK_FLAGS_PRINT
 #else
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 921d0a654243..398920403321 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -586,13 +586,11 @@ static int remaining(int wrote)
 	return 0;
 }
 
-static char *dynamic_emit_prefix(const struct _ddebug *desc, char *buf)
+static char *__dynamic_emit_prefix(const struct _ddebug *desc, char *buf)
 {
 	int pos_after_tid;
 	int pos = 0;
 
-	*buf = '\0';
-
 	if (desc->flags & _DPRINTK_FLAGS_INCL_TID) {
 		if (in_interrupt())
 			pos += snprintf(buf + pos, remaining(pos), "<intr> ");
@@ -618,11 +616,18 @@ static char *dynamic_emit_prefix(const struct _ddebug *desc, char *buf)
 	return buf;
 }
 
+static inline char *dynamic_emit_prefix(struct _ddebug *desc, char *buf)
+{
+	if (unlikely(desc->flags & _DPRINTK_FLAGS_INCL_ANY))
+		return __dynamic_emit_prefix(desc, buf);
+	return buf;
+}
+
 void __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...)
 {
 	va_list args;
 	struct va_format vaf;
-	char buf[PREFIX_SIZE];
+	char buf[PREFIX_SIZE] = "";
 
 	BUG_ON(!descriptor);
 	BUG_ON(!fmt);
@@ -655,7 +660,7 @@ void __dynamic_dev_dbg(struct _ddebug *descriptor,
 	if (!dev) {
 		printk(KERN_DEBUG "(NULL device *): %pV", &vaf);
 	} else {
-		char buf[PREFIX_SIZE];
+		char buf[PREFIX_SIZE] = "";
 
 		dev_printk_emit(LOGLEVEL_DEBUG, dev, "%s%s %s: %pV",
 				dynamic_emit_prefix(descriptor, buf),
@@ -684,7 +689,7 @@ void __dynamic_netdev_dbg(struct _ddebug *descriptor,
 	vaf.va = &args;
 
 	if (dev && dev->dev.parent) {
-		char buf[PREFIX_SIZE];
+		char buf[PREFIX_SIZE] = "";
 
 		dev_printk_emit(LOGLEVEL_DEBUG, dev->dev.parent,
 				"%s%s %s %s%s: %pV",
@@ -720,7 +725,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 	vaf.va = &args;
 
 	if (ibdev && ibdev->dev.parent) {
-		char buf[PREFIX_SIZE];
+		char buf[PREFIX_SIZE] = "";
 
 		dev_printk_emit(LOGLEVEL_DEBUG, ibdev->dev.parent,
 				"%s%s %s %s: %pV",
-- 
cgit v1.2.3


From c07531c01d8284aedaf95708ea90e76d11af0e21 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@nvidia.com>
Date: Mon, 10 May 2021 14:50:24 +0300
Subject: netfilter: flowtable: Remove redundant hw refresh bit

Offloading conns could fail for multiple reasons and a hw refresh bit is
set to try to reoffload it in next sw packet.
But it could be in some cases and future points that the hw refresh bit
is not set but a refresh could succeed.
Remove the hw refresh bit and do offload refresh if requested.
There won't be a new work entry if a work is already pending
anyway as there is the hw pending bit.

Fixes: 8b3646d6e0c4 ("net/sched: act_ct: Support refreshing the flow table entries")
Signed-off-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_flow_table.h | 1 -
 net/netfilter/nf_flow_table_core.c    | 3 +--
 net/netfilter/nf_flow_table_offload.c | 7 ++++---
 3 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 51d8eb99764d..48ef7460ff30 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -157,7 +157,6 @@ enum nf_flow_flags {
 	NF_FLOW_HW,
 	NF_FLOW_HW_DYING,
 	NF_FLOW_HW_DEAD,
-	NF_FLOW_HW_REFRESH,
 	NF_FLOW_HW_PENDING,
 };
 
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 39c02d1aeedf..1d02650dd715 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -306,8 +306,7 @@ void flow_offload_refresh(struct nf_flowtable *flow_table,
 {
 	flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT;
 
-	if (likely(!nf_flowtable_hw_offload(flow_table) ||
-		   !test_and_clear_bit(NF_FLOW_HW_REFRESH, &flow->flags)))
+	if (likely(!nf_flowtable_hw_offload(flow_table)))
 		return;
 
 	nf_flow_offload_add(flow_table, flow);
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 2af7bdb38407..528b2f172684 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -902,10 +902,11 @@ static void flow_offload_work_add(struct flow_offload_work *offload)
 
 	err = flow_offload_rule_add(offload, flow_rule);
 	if (err < 0)
-		set_bit(NF_FLOW_HW_REFRESH, &offload->flow->flags);
-	else
-		set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status);
+		goto out;
+
+	set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status);
 
+out:
 	nf_flow_offload_destroy(flow_rule);
 }
 
-- 
cgit v1.2.3


From a90c57f2cedd52a511f739fb55e6244e22e1a2fb Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Fri, 14 May 2021 11:16:59 +0800
Subject: net: sched: fix packet stuck problem for lockless qdisc

Lockless qdisc has below concurrent problem:
    cpu0                 cpu1
     .                     .
q->enqueue                 .
     .                     .
qdisc_run_begin()          .
     .                     .
dequeue_skb()              .
     .                     .
sch_direct_xmit()          .
     .                     .
     .                q->enqueue
     .             qdisc_run_begin()
     .            return and do nothing
     .                     .
qdisc_run_end()            .

cpu1 enqueue a skb without calling __qdisc_run() because cpu0
has not released the lock yet and spin_trylock() return false
for cpu1 in qdisc_run_begin(), and cpu0 do not see the skb
enqueued by cpu1 when calling dequeue_skb() because cpu1 may
enqueue the skb after cpu0 calling dequeue_skb() and before
cpu0 calling qdisc_run_end().

Lockless qdisc has below another concurrent problem when
tx_action is involved:

cpu0(serving tx_action)     cpu1             cpu2
          .                   .                .
          .              q->enqueue            .
          .            qdisc_run_begin()       .
          .              dequeue_skb()         .
          .                   .            q->enqueue
          .                   .                .
          .             sch_direct_xmit()      .
          .                   .         qdisc_run_begin()
          .                   .       return and do nothing
          .                   .                .
 clear __QDISC_STATE_SCHED    .                .
 qdisc_run_begin()            .                .
 return and do nothing        .                .
          .                   .                .
          .            qdisc_run_end()         .

This patch fixes the above data race by:
1. If the first spin_trylock() return false and STATE_MISSED is
   not set, set STATE_MISSED and retry another spin_trylock() in
   case other CPU may not see STATE_MISSED after it releases the
   lock.
2. reschedule if STATE_MISSED is set after the lock is released
   at the end of qdisc_run_end().

For tx_action case, STATE_MISSED is also set when cpu1 is at the
end if qdisc_run_end(), so tx_action will be rescheduled again
to dequeue the skb enqueued by cpu2.

Clear STATE_MISSED before retrying a dequeuing when dequeuing
returns NULL in order to reduce the overhead of the second
spin_trylock() and __netif_schedule() calling.

Also clear the STATE_MISSED before calling __netif_schedule()
at the end of qdisc_run_end() to avoid doing another round of
dequeuing in the pfifo_fast_dequeue().

The performance impact of this patch, tested using pktgen and
dummy netdev with pfifo_fast qdisc attached:

 threads  without+this_patch   with+this_patch      delta
    1        2.61Mpps            2.60Mpps           -0.3%
    2        3.97Mpps            3.82Mpps           -3.7%
    4        5.62Mpps            5.59Mpps           -0.5%
    8        2.78Mpps            2.77Mpps           -0.3%
   16        2.22Mpps            2.22Mpps           -0.0%

Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking")
Acked-by: Jakub Kicinski <kuba@kernel.org>
Tested-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 35 ++++++++++++++++++++++++++++++++++-
 net/sched/sch_generic.c   | 19 +++++++++++++++++++
 2 files changed, 53 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index f7a6e14491fb..1e625519ae96 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -36,6 +36,7 @@ struct qdisc_rate_table {
 enum qdisc_state_t {
 	__QDISC_STATE_SCHED,
 	__QDISC_STATE_DEACTIVATED,
+	__QDISC_STATE_MISSED,
 };
 
 struct qdisc_size_table {
@@ -159,8 +160,33 @@ static inline bool qdisc_is_empty(const struct Qdisc *qdisc)
 static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 {
 	if (qdisc->flags & TCQ_F_NOLOCK) {
+		if (spin_trylock(&qdisc->seqlock))
+			goto nolock_empty;
+
+		/* If the MISSED flag is set, it means other thread has
+		 * set the MISSED flag before second spin_trylock(), so
+		 * we can return false here to avoid multi cpus doing
+		 * the set_bit() and second spin_trylock() concurrently.
+		 */
+		if (test_bit(__QDISC_STATE_MISSED, &qdisc->state))
+			return false;
+
+		/* Set the MISSED flag before the second spin_trylock(),
+		 * if the second spin_trylock() return false, it means
+		 * other cpu holding the lock will do dequeuing for us
+		 * or it will see the MISSED flag set after releasing
+		 * lock and reschedule the net_tx_action() to do the
+		 * dequeuing.
+		 */
+		set_bit(__QDISC_STATE_MISSED, &qdisc->state);
+
+		/* Retry again in case other CPU may not see the new flag
+		 * after it releases the lock at the end of qdisc_run_end().
+		 */
 		if (!spin_trylock(&qdisc->seqlock))
 			return false;
+
+nolock_empty:
 		WRITE_ONCE(qdisc->empty, false);
 	} else if (qdisc_is_running(qdisc)) {
 		return false;
@@ -176,8 +202,15 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 static inline void qdisc_run_end(struct Qdisc *qdisc)
 {
 	write_seqcount_end(&qdisc->running);
-	if (qdisc->flags & TCQ_F_NOLOCK)
+	if (qdisc->flags & TCQ_F_NOLOCK) {
 		spin_unlock(&qdisc->seqlock);
+
+		if (unlikely(test_bit(__QDISC_STATE_MISSED,
+				      &qdisc->state))) {
+			clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
+			__netif_schedule(qdisc);
+		}
+	}
 }
 
 static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 44991ea726fc..795d986e7030 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -640,8 +640,10 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
 {
 	struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
 	struct sk_buff *skb = NULL;
+	bool need_retry = true;
 	int band;
 
+retry:
 	for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) {
 		struct skb_array *q = band2list(priv, band);
 
@@ -652,6 +654,23 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
 	}
 	if (likely(skb)) {
 		qdisc_update_stats_at_dequeue(qdisc, skb);
+	} else if (need_retry &&
+		   test_bit(__QDISC_STATE_MISSED, &qdisc->state)) {
+		/* Delay clearing the STATE_MISSED here to reduce
+		 * the overhead of the second spin_trylock() in
+		 * qdisc_run_begin() and __netif_schedule() calling
+		 * in qdisc_run_end().
+		 */
+		clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
+
+		/* Make sure dequeuing happens after clearing
+		 * STATE_MISSED.
+		 */
+		smp_mb__after_atomic();
+
+		need_retry = false;
+
+		goto retry;
 	} else {
 		WRITE_ONCE(qdisc->empty, true);
 	}
-- 
cgit v1.2.3


From 102b55ee92f9fda4dde7a45d2b20538e6e3e3d1e Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Fri, 14 May 2021 11:17:00 +0800
Subject: net: sched: fix tx action rescheduling issue during deactivation

Currently qdisc_run() checks the STATE_DEACTIVATED of lockless
qdisc before calling __qdisc_run(), which ultimately clear the
STATE_MISSED when all the skb is dequeued. If STATE_DEACTIVATED
is set before clearing STATE_MISSED, there may be rescheduling
of net_tx_action() at the end of qdisc_run_end(), see below:

CPU0(net_tx_atcion)  CPU1(__dev_xmit_skb)  CPU2(dev_deactivate)
          .                   .                     .
          .            set STATE_MISSED             .
          .           __netif_schedule()            .
          .                   .           set STATE_DEACTIVATED
          .                   .                qdisc_reset()
          .                   .                     .
          .<---------------   .              synchronize_net()
clear __QDISC_STATE_SCHED  |  .                     .
          .                |  .                     .
          .                |  .            some_qdisc_is_busy()
          .                |  .               return *false*
          .                |  .                     .
  test STATE_DEACTIVATED   |  .                     .
__qdisc_run() *not* called |  .                     .
          .                |  .                     .
   test STATE_MISS         |  .                     .
 __netif_schedule()--------|  .                     .
          .                   .                     .
          .                   .                     .

__qdisc_run() is not called by net_tx_atcion() in CPU0 because
CPU2 has set STATE_DEACTIVATED flag during dev_deactivate(), and
STATE_MISSED is only cleared in __qdisc_run(), __netif_schedule
is called at the end of qdisc_run_end(), causing tx action
rescheduling problem.

qdisc_run() called by net_tx_action() runs in the softirq context,
which should has the same semantic as the qdisc_run() called by
__dev_xmit_skb() protected by rcu_read_lock_bh(). And there is a
synchronize_net() between STATE_DEACTIVATED flag being set and
qdisc_reset()/some_qdisc_is_busy in dev_deactivate(), we can safely
bail out for the deactived lockless qdisc in net_tx_action(), and
qdisc_reset() will reset all skb not dequeued yet.

So add the rcu_read_lock() explicitly to protect the qdisc_run()
and do the STATE_DEACTIVATED checking in net_tx_action() before
calling qdisc_run_begin(). Another option is to do the checking in
the qdisc_run_end(), but it will add unnecessary overhead for
non-tx_action case, because __dev_queue_xmit() will not see qdisc
with STATE_DEACTIVATED after synchronize_net(), the qdisc with
STATE_DEACTIVATED can only be seen by net_tx_action() because of
__netif_schedule().

The STATE_DEACTIVATED checking in qdisc_run() is to avoid race
between net_tx_action() and qdisc_reset(), see:
commit d518d2ed8640 ("net/sched: fix race between deactivation
and dequeue for NOLOCK qdisc"). As the bailout added above for
deactived lockless qdisc in net_tx_action() provides better
protection for the race without calling qdisc_run() at all, so
remove the STATE_DEACTIVATED checking in qdisc_run().

After qdisc_reset(), there is no skb in qdisc to be dequeued, so
clear the STATE_MISSED in dev_reset_queue() too.

Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking")
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
V8: Clearing STATE_MISSED before calling __netif_schedule() has
    avoid the endless rescheduling problem, but there may still
    be a unnecessary rescheduling, so adjust the commit log.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_sched.h |  7 +------
 net/core/dev.c          | 26 ++++++++++++++++++++++----
 net/sched/sch_generic.c |  4 +++-
 3 files changed, 26 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index f5c1bee0cd6a..6d7b12cba015 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -128,12 +128,7 @@ void __qdisc_run(struct Qdisc *q);
 static inline void qdisc_run(struct Qdisc *q)
 {
 	if (qdisc_run_begin(q)) {
-		/* NOLOCK qdisc must check 'state' under the qdisc seqlock
-		 * to avoid racing with dev_qdisc_reset()
-		 */
-		if (!(q->flags & TCQ_F_NOLOCK) ||
-		    likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
-			__qdisc_run(q);
+		__qdisc_run(q);
 		qdisc_run_end(q);
 	}
 }
diff --git a/net/core/dev.c b/net/core/dev.c
index 222b1d322c96..d596cd746353 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5025,25 +5025,43 @@ static __latent_entropy void net_tx_action(struct softirq_action *h)
 		sd->output_queue_tailp = &sd->output_queue;
 		local_irq_enable();
 
+		rcu_read_lock();
+
 		while (head) {
 			struct Qdisc *q = head;
 			spinlock_t *root_lock = NULL;
 
 			head = head->next_sched;
 
-			if (!(q->flags & TCQ_F_NOLOCK)) {
-				root_lock = qdisc_lock(q);
-				spin_lock(root_lock);
-			}
 			/* We need to make sure head->next_sched is read
 			 * before clearing __QDISC_STATE_SCHED
 			 */
 			smp_mb__before_atomic();
+
+			if (!(q->flags & TCQ_F_NOLOCK)) {
+				root_lock = qdisc_lock(q);
+				spin_lock(root_lock);
+			} else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
+						     &q->state))) {
+				/* There is a synchronize_net() between
+				 * STATE_DEACTIVATED flag being set and
+				 * qdisc_reset()/some_qdisc_is_busy() in
+				 * dev_deactivate(), so we can safely bail out
+				 * early here to avoid data race between
+				 * qdisc_deactivate() and some_qdisc_is_busy()
+				 * for lockless qdisc.
+				 */
+				clear_bit(__QDISC_STATE_SCHED, &q->state);
+				continue;
+			}
+
 			clear_bit(__QDISC_STATE_SCHED, &q->state);
 			qdisc_run(q);
 			if (root_lock)
 				spin_unlock(root_lock);
 		}
+
+		rcu_read_unlock();
 	}
 
 	xfrm_dev_backlog(sd);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 795d986e7030..d86c4cca2cab 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1177,8 +1177,10 @@ static void dev_reset_queue(struct net_device *dev,
 	qdisc_reset(qdisc);
 
 	spin_unlock_bh(qdisc_lock(qdisc));
-	if (nolock)
+	if (nolock) {
+		clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
 		spin_unlock_bh(&qdisc->seqlock);
+	}
 }
 
 static bool some_qdisc_is_busy(struct net_device *dev)
-- 
cgit v1.2.3


From 0cfe5a6e758fb20be8ad3e8f10cb087cc8033eeb Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Thu, 1 Apr 2021 17:41:04 +0200
Subject: gpu: host1x: Split up client initalization and registration

In some cases we may need to initialize the host1x client first before
registering it. This commit adds a new helper that will do nothing but
the initialization of the data structure.

At the same time, the initialization is removed from the registration
function. Note, however, that for simplicity we explicitly initialize
the client when the host1x_client_register() function is called, as
opposed to the low-level __host1x_client_register() function. This
allows existing callers to remain unchanged.

Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/host1x/bus.c | 30 ++++++++++++++++++++++++------
 include/linux/host1x.h   | 30 ++++++++++++++++++++++++------
 2 files changed, 48 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index 46f69c532b6b..218e3718fd68 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -735,6 +735,29 @@ void host1x_driver_unregister(struct host1x_driver *driver)
 }
 EXPORT_SYMBOL(host1x_driver_unregister);
 
+/**
+ * __host1x_client_init() - initialize a host1x client
+ * @client: host1x client
+ * @key: lock class key for the client-specific mutex
+ */
+void __host1x_client_init(struct host1x_client *client, struct lock_class_key *key)
+{
+	INIT_LIST_HEAD(&client->list);
+	__mutex_init(&client->lock, "host1x client lock", key);
+	client->usecount = 0;
+}
+EXPORT_SYMBOL(__host1x_client_init);
+
+/**
+ * host1x_client_exit() - uninitialize a host1x client
+ * @client: host1x client
+ */
+void host1x_client_exit(struct host1x_client *client)
+{
+	mutex_destroy(&client->lock);
+}
+EXPORT_SYMBOL(host1x_client_exit);
+
 /**
  * __host1x_client_register() - register a host1x client
  * @client: host1x client
@@ -747,16 +770,11 @@ EXPORT_SYMBOL(host1x_driver_unregister);
  * device and call host1x_device_init(), which will in turn call each client's
  * &host1x_client_ops.init implementation.
  */
-int __host1x_client_register(struct host1x_client *client,
-			     struct lock_class_key *key)
+int __host1x_client_register(struct host1x_client *client)
 {
 	struct host1x *host1x;
 	int err;
 
-	INIT_LIST_HEAD(&client->list);
-	__mutex_init(&client->lock, "host1x client lock", key);
-	client->usecount = 0;
-
 	mutex_lock(&devices_lock);
 
 	list_for_each_entry(host1x, &devices, list) {
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index 232e1bd507a7..9b0487c88571 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -332,12 +332,30 @@ static inline struct host1x_device *to_host1x_device(struct device *dev)
 int host1x_device_init(struct host1x_device *device);
 int host1x_device_exit(struct host1x_device *device);
 
-int __host1x_client_register(struct host1x_client *client,
-			     struct lock_class_key *key);
-#define host1x_client_register(class) \
-	({ \
-		static struct lock_class_key __key; \
-		__host1x_client_register(class, &__key); \
+void __host1x_client_init(struct host1x_client *client, struct lock_class_key *key);
+void host1x_client_exit(struct host1x_client *client);
+
+#define host1x_client_init(client)			\
+	({						\
+		static struct lock_class_key __key;	\
+		__host1x_client_init(client, &__key);	\
+	})
+
+int __host1x_client_register(struct host1x_client *client);
+
+/*
+ * Note that this wrapper calls __host1x_client_init() for compatibility
+ * with existing callers. Callers that want to separately initialize and
+ * register a host1x client must first initialize using either of the
+ * __host1x_client_init() or host1x_client_init() functions and then use
+ * the low-level __host1x_client_register() function to avoid the client
+ * getting reinitialized.
+ */
+#define host1x_client_register(client)			\
+	({						\
+		static struct lock_class_key __key;	\
+		__host1x_client_init(client, &__key);	\
+		__host1x_client_register(client);	\
 	})
 
 int host1x_client_unregister(struct host1x_client *client);
-- 
cgit v1.2.3


From e0652f8bb44d6294eeeac06d703185357f25d50b Mon Sep 17 00:00:00 2001
From: Dongliang Mu <mudongliangabcd@gmail.com>
Date: Sat, 15 May 2021 07:29:06 +0800
Subject: NFC: nci: fix memory leak in nci_allocate_device

nfcmrvl_disconnect fails to free the hci_dev field in struct nci_dev.
Fix this by freeing hci_dev in nci_free_device.

BUG: memory leak
unreferenced object 0xffff888111ea6800 (size 1024):
  comm "kworker/1:0", pid 19, jiffies 4294942308 (age 13.580s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 60 fd 0c 81 88 ff ff  .........`......
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<000000004bc25d43>] kmalloc include/linux/slab.h:552 [inline]
    [<000000004bc25d43>] kzalloc include/linux/slab.h:682 [inline]
    [<000000004bc25d43>] nci_hci_allocate+0x21/0xd0 net/nfc/nci/hci.c:784
    [<00000000c59cff92>] nci_allocate_device net/nfc/nci/core.c:1170 [inline]
    [<00000000c59cff92>] nci_allocate_device+0x10b/0x160 net/nfc/nci/core.c:1132
    [<00000000006e0a8e>] nfcmrvl_nci_register_dev+0x10a/0x1c0 drivers/nfc/nfcmrvl/main.c:153
    [<000000004da1b57e>] nfcmrvl_probe+0x223/0x290 drivers/nfc/nfcmrvl/usb.c:345
    [<00000000d506aed9>] usb_probe_interface+0x177/0x370 drivers/usb/core/driver.c:396
    [<00000000bc632c92>] really_probe+0x159/0x4a0 drivers/base/dd.c:554
    [<00000000f5009125>] driver_probe_device+0x84/0x100 drivers/base/dd.c:740
    [<000000000ce658ca>] __device_attach_driver+0xee/0x110 drivers/base/dd.c:846
    [<000000007067d05f>] bus_for_each_drv+0xb7/0x100 drivers/base/bus.c:431
    [<00000000f8e13372>] __device_attach+0x122/0x250 drivers/base/dd.c:914
    [<000000009cf68860>] bus_probe_device+0xc6/0xe0 drivers/base/bus.c:491
    [<00000000359c965a>] device_add+0x5be/0xc30 drivers/base/core.c:3109
    [<00000000086e4bd3>] usb_set_configuration+0x9d9/0xb90 drivers/usb/core/message.c:2164
    [<00000000ca036872>] usb_generic_driver_probe+0x8c/0xc0 drivers/usb/core/generic.c:238
    [<00000000d40d36f6>] usb_probe_device+0x5c/0x140 drivers/usb/core/driver.c:293
    [<00000000bc632c92>] really_probe+0x159/0x4a0 drivers/base/dd.c:554

Reported-by: syzbot+19bcfc64a8df1318d1c3@syzkaller.appspotmail.com
Fixes: 11f54f228643 ("NFC: nci: Add HCI over NCI protocol support")
Signed-off-by: Dongliang Mu <mudongliangabcd@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/nfc/nci_core.h | 1 +
 net/nfc/nci/core.c         | 1 +
 net/nfc/nci/hci.c          | 5 +++++
 3 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index bd76e8e082c0..1df0f8074c9d 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -298,6 +298,7 @@ int nci_nfcc_loopback(struct nci_dev *ndev, void *data, size_t data_len,
 		      struct sk_buff **resp);
 
 struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev);
+void nci_hci_deallocate(struct nci_dev *ndev);
 int nci_hci_send_event(struct nci_dev *ndev, u8 gate, u8 event,
 		       const u8 *param, size_t param_len);
 int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate,
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 9a585332ea84..da7fe9db1b00 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1191,6 +1191,7 @@ EXPORT_SYMBOL(nci_allocate_device);
 void nci_free_device(struct nci_dev *ndev)
 {
 	nfc_free_device(ndev->nfc_dev);
+	nci_hci_deallocate(ndev);
 	kfree(ndev);
 }
 EXPORT_SYMBOL(nci_free_device);
diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c
index 6b275a387a92..96865142104f 100644
--- a/net/nfc/nci/hci.c
+++ b/net/nfc/nci/hci.c
@@ -792,3 +792,8 @@ struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev)
 
 	return hdev;
 }
+
+void nci_hci_deallocate(struct nci_dev *ndev)
+{
+	kfree(ndev->hci_dev);
+}
-- 
cgit v1.2.3


From 4d7b324e231366ea772ab10df46be31273ca39af Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 18 May 2021 09:47:23 +0300
Subject: bus: ti-sysc: Fix am335x resume hang for usb otg module

On am335x, suspend and resume only works once, and the system hangs if
suspend is attempted again. However, turns out suspend and resume works
fine multiple times if the USB OTG driver for musb controller is loaded.

The issue is caused my the interconnect target module losing context
during suspend, and it needs a restore on resume to be reconfigure again
as debugged earlier by Dave Gerlach <d-gerlach@ti.com>.

There are also other modules that need a restore on resume, like gpmc as
noted by Dave. So let's add a common way to restore an interconnect
target module based on a quirk flag. For now, let's enable the quirk for
am335x otg only to fix the suspend and resume issue.

As gpmc is not causing hangs based on tests with BeagleBone, let's patch
gpmc separately. For gpmc, we also need a hardware reset done before
restore according to Dave.

To reinit the modules, we decouple system suspend from PM runtime. We
replace calls to pm_runtime_force_suspend() and pm_runtime_force_resume()
with direct calls to internal functions and rely on the driver internal
state. There no point trying to handle complex system suspend and resume
quirks via PM runtime.

This is issue should have already been noticed with commit 1819ef2e2d12
("bus: ti-sysc: Use swsup quirks also for am335x musb") when quirk
handling was added for am335x otg for swsup. But the issue went unnoticed
as having musb driver loaded hides the issue, and suspend and resume works
once without the driver loaded.

Fixes: 1819ef2e2d12 ("bus: ti-sysc: Use swsup quirks also for am335x musb")
Suggested-by: Dave Gerlach <d-gerlach@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 drivers/bus/ti-sysc.c                 | 53 +++++++++++++++++++++++++++++++++--
 include/linux/platform_data/ti-sysc.h |  1 +
 2 files changed, 51 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index 50a9f34b9e6c..4ff319863be2 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -1334,6 +1334,34 @@ err_allow_idle:
 	return error;
 }
 
+static int sysc_reinit_module(struct sysc *ddata, bool leave_enabled)
+{
+	struct device *dev = ddata->dev;
+	int error;
+
+	/* Disable target module if it is enabled */
+	if (ddata->enabled) {
+		error = sysc_runtime_suspend(dev);
+		if (error)
+			dev_warn(dev, "reinit suspend failed: %i\n", error);
+	}
+
+	/* Enable target module */
+	error = sysc_runtime_resume(dev);
+	if (error)
+		dev_warn(dev, "reinit resume failed: %i\n", error);
+
+	if (leave_enabled)
+		return error;
+
+	/* Disable target module if no leave_enabled was set */
+	error = sysc_runtime_suspend(dev);
+	if (error)
+		dev_warn(dev, "reinit suspend failed: %i\n", error);
+
+	return error;
+}
+
 static int __maybe_unused sysc_noirq_suspend(struct device *dev)
 {
 	struct sysc *ddata;
@@ -1344,12 +1372,18 @@ static int __maybe_unused sysc_noirq_suspend(struct device *dev)
 	    (SYSC_QUIRK_LEGACY_IDLE | SYSC_QUIRK_NO_IDLE))
 		return 0;
 
-	return pm_runtime_force_suspend(dev);
+	if (!ddata->enabled)
+		return 0;
+
+	ddata->needs_resume = 1;
+
+	return sysc_runtime_suspend(dev);
 }
 
 static int __maybe_unused sysc_noirq_resume(struct device *dev)
 {
 	struct sysc *ddata;
+	int error = 0;
 
 	ddata = dev_get_drvdata(dev);
 
@@ -1357,7 +1391,19 @@ static int __maybe_unused sysc_noirq_resume(struct device *dev)
 	    (SYSC_QUIRK_LEGACY_IDLE | SYSC_QUIRK_NO_IDLE))
 		return 0;
 
-	return pm_runtime_force_resume(dev);
+	if (ddata->cfg.quirks & SYSC_QUIRK_REINIT_ON_RESUME) {
+		error = sysc_reinit_module(ddata, ddata->needs_resume);
+		if (error)
+			dev_warn(dev, "noirq_resume failed: %i\n", error);
+	} else if (ddata->needs_resume) {
+		error = sysc_runtime_resume(dev);
+		if (error)
+			dev_warn(dev, "noirq_resume failed: %i\n", error);
+	}
+
+	ddata->needs_resume = 0;
+
+	return error;
 }
 
 static const struct dev_pm_ops sysc_pm_ops = {
@@ -1468,7 +1514,8 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = {
 	SYSC_QUIRK("usb_otg_hs", 0, 0x400, 0x404, 0x408, 0x00000050,
 		   0xffffffff, SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY),
 	SYSC_QUIRK("usb_otg_hs", 0, 0, 0x10, -ENODEV, 0x4ea2080d, 0xffffffff,
-		   SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY),
+		   SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY |
+		   SYSC_QUIRK_REINIT_ON_RESUME),
 	SYSC_QUIRK("wdt", 0, 0, 0x10, 0x14, 0x502a0500, 0xfffff0f0,
 		   SYSC_MODULE_QUIRK_WDT),
 	/* PRUSS on am3, am4 and am5 */
diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h
index fafc1beea504..9837fb011f2f 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_QUIRK_REINIT_ON_RESUME	BIT(27)
 #define SYSC_QUIRK_GPMC_DEBUG		BIT(26)
 #define SYSC_MODULE_QUIRK_ENA_RESETDONE	BIT(25)
 #define SYSC_MODULE_QUIRK_PRUSS		BIT(24)
-- 
cgit v1.2.3


From add0b32ef9146a8559a60aed54c37692a5f9d34f Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 30 Apr 2021 17:06:01 -0500
Subject: siginfo: Move si_trapno inside the union inside _si_fault

It turns out that linux uses si_trapno very sparingly, and as such it
can be considered extra information for a very narrow selection of
signals, rather than information that is present with every fault
reported in siginfo.

As such move si_trapno inside the union inside of _si_fault.  This
results in no change in placement, and makes it eaiser
to extend _si_fault in the future as this reduces the number of
special cases.  In particular with si_trapno included in the union it
is no longer a concern that the union must be pointer aligned on most
architectures because the union follows immediately after si_addr
which is a pointer.

This change results in a difference in siginfo field placement on
sparc and alpha for the fields si_addr_lsb, si_lower, si_upper,
si_pkey, and si_perf.  These architectures do not implement the
signals that would use si_addr_lsb, si_lower, si_upper, si_pkey, and
si_perf.  Further these architecture have not yet implemented the
userspace that would use si_perf.

The point of this change is in fact to correct these placement issues
before sparc or alpha grow userspace that cares.  This change was
discussed[1] and the agreement is that this change is currently safe.

[1]: https://lkml.kernel.org/r/CAK8P3a0+uKYwL1NhY6Hvtieghba2hKYGD6hcKx5n8=4Gtt+pHA@mail.gmail.com
Acked-by: Marco Elver <elver@google.com>
v1: https://lkml.kernel.org/r/m1tunns7yf.fsf_-_@fess.ebiederm.org
v2: https://lkml.kernel.org/r/20210505141101.11519-5-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20210517195748.8880-1-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 arch/x86/kernel/signal_compat.c    | 3 +++
 include/linux/compat.h             | 5 ++---
 include/uapi/asm-generic/siginfo.h | 7 ++-----
 kernel/signal.c                    | 1 +
 4 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index 0e5d0a7e203b..a9fcabd8a5e5 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -127,6 +127,9 @@ static inline void signal_compat_build_tests(void)
 	BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x10);
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr) != 0x0C);
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_trapno) != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_trapno) != 0x10);
+
 	BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x18);
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr_lsb) != 0x10);
 
diff --git a/include/linux/compat.h b/include/linux/compat.h
index f0d2dd35d408..6af7bef15e94 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -214,12 +214,11 @@ typedef struct compat_siginfo {
 		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGTRAP, SIGEMT */
 		struct {
 			compat_uptr_t _addr;	/* faulting insn/memory ref. */
-#ifdef __ARCH_SI_TRAPNO
-			int _trapno;	/* TRAP # which caused the signal */
-#endif
 #define __COMPAT_ADDR_BND_PKEY_PAD  (__alignof__(compat_uptr_t) < sizeof(short) ? \
 				     sizeof(short) : __alignof__(compat_uptr_t))
 			union {
+				/* used on alpha and sparc */
+				int _trapno;	/* TRAP # which caused the signal */
 				/*
 				 * used when si_code=BUS_MCEERR_AR or
 				 * used when si_code=BUS_MCEERR_AO
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index 03d6f6d2c1fe..e663bf117b46 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -63,9 +63,6 @@ union __sifields {
 	/* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGTRAP, SIGEMT */
 	struct {
 		void __user *_addr; /* faulting insn/memory ref. */
-#ifdef __ARCH_SI_TRAPNO
-		int _trapno;	/* TRAP # which caused the signal */
-#endif
 #ifdef __ia64__
 		int _imm;		/* immediate value for "break" */
 		unsigned int _flags;	/* see ia64 si_flags */
@@ -75,6 +72,8 @@ union __sifields {
 #define __ADDR_BND_PKEY_PAD  (__alignof__(void *) < sizeof(short) ? \
 			      sizeof(short) : __alignof__(void *))
 		union {
+			/* used on alpha and sparc */
+			int _trapno;	/* TRAP # which caused the signal */
 			/*
 			 * used when si_code=BUS_MCEERR_AR or
 			 * used when si_code=BUS_MCEERR_AO
@@ -150,9 +149,7 @@ typedef struct siginfo {
 #define si_int		_sifields._rt._sigval.sival_int
 #define si_ptr		_sifields._rt._sigval.sival_ptr
 #define si_addr		_sifields._sigfault._addr
-#ifdef __ARCH_SI_TRAPNO
 #define si_trapno	_sifields._sigfault._trapno
-#endif
 #define si_addr_lsb	_sifields._sigfault._addr_lsb
 #define si_lower	_sifields._sigfault._addr_bnd._lower
 #define si_upper	_sifields._sigfault._addr_bnd._upper
diff --git a/kernel/signal.c b/kernel/signal.c
index c3017aa8024a..65888aec65a0 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -4607,6 +4607,7 @@ static inline void siginfo_buildtime_checks(void)
 
 	/* sigfault */
 	CHECK_OFFSET(si_addr);
+	CHECK_OFFSET(si_trapno);
 	CHECK_OFFSET(si_addr_lsb);
 	CHECK_OFFSET(si_lower);
 	CHECK_OFFSET(si_upper);
-- 
cgit v1.2.3


From 9abcabe3111811aeae0f3a14e159b14248631875 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 30 Apr 2021 17:29:36 -0500
Subject: signal: Implement SIL_FAULT_TRAPNO

Now that si_trapno is part of the union in _si_fault and available on
all architectures, add SIL_FAULT_TRAPNO and update siginfo_layout to
return SIL_FAULT_TRAPNO when the code assumes si_trapno is valid.

There is room for future changes to reduce when si_trapno is valid but
this is all that is needed to make si_trapno and the other members of
the the union in _sigfault mutually exclusive.

Update the code that uses siginfo_layout to deal with SIL_FAULT_TRAPNO
and have the same code ignore si_trapno in in all other cases.

v1: https://lkml.kernel.org/r/m1o8dvs7s7.fsf_-_@fess.ebiederm.org
v2: https://lkml.kernel.org/r/20210505141101.11519-6-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20210517195748.8880-2-ebiederm@xmission.com
Reviewed-by: Marco Elver <elver@google.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/signalfd.c          |  8 +++-----
 include/linux/signal.h |  1 +
 kernel/signal.c        | 34 ++++++++++++----------------------
 3 files changed, 16 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/fs/signalfd.c b/fs/signalfd.c
index 040a1142915f..e87e59581653 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -123,15 +123,13 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 		 */
 	case SIL_FAULT:
 		new.ssi_addr = (long) kinfo->si_addr;
-#ifdef __ARCH_SI_TRAPNO
+		break;
+	case SIL_FAULT_TRAPNO:
+		new.ssi_addr = (long) kinfo->si_addr;
 		new.ssi_trapno = kinfo->si_trapno;
-#endif
 		break;
 	case SIL_FAULT_MCEERR:
 		new.ssi_addr = (long) kinfo->si_addr;
-#ifdef __ARCH_SI_TRAPNO
-		new.ssi_trapno = kinfo->si_trapno;
-#endif
 		new.ssi_addr_lsb = (short) kinfo->si_addr_lsb;
 		break;
 	case SIL_PERF_EVENT:
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 1e98548d7cf6..5160fd45e5ca 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -40,6 +40,7 @@ enum siginfo_layout {
 	SIL_TIMER,
 	SIL_POLL,
 	SIL_FAULT,
+	SIL_FAULT_TRAPNO,
 	SIL_FAULT_MCEERR,
 	SIL_FAULT_BNDERR,
 	SIL_FAULT_PKUERR,
diff --git a/kernel/signal.c b/kernel/signal.c
index 65888aec65a0..597594ee72de 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1194,6 +1194,7 @@ static inline bool has_si_pid_and_uid(struct kernel_siginfo *info)
 	case SIL_TIMER:
 	case SIL_POLL:
 	case SIL_FAULT:
+	case SIL_FAULT_TRAPNO:
 	case SIL_FAULT_MCEERR:
 	case SIL_FAULT_BNDERR:
 	case SIL_FAULT_PKUERR:
@@ -2527,6 +2528,7 @@ static void hide_si_addr_tag_bits(struct ksignal *ksig)
 {
 	switch (siginfo_layout(ksig->sig, ksig->info.si_code)) {
 	case SIL_FAULT:
+	case SIL_FAULT_TRAPNO:
 	case SIL_FAULT_MCEERR:
 	case SIL_FAULT_BNDERR:
 	case SIL_FAULT_PKUERR:
@@ -3214,6 +3216,10 @@ enum siginfo_layout siginfo_layout(unsigned sig, int si_code)
 #endif
 			else if ((sig == SIGTRAP) && (si_code == TRAP_PERF))
 				layout = SIL_PERF_EVENT;
+#ifdef __ARCH_SI_TRAPNO
+			else if (layout == SIL_FAULT)
+				layout = SIL_FAULT_TRAPNO;
+#endif
 		}
 		else if (si_code <= NSIGPOLL)
 			layout = SIL_POLL;
@@ -3317,30 +3323,22 @@ void copy_siginfo_to_external32(struct compat_siginfo *to,
 		break;
 	case SIL_FAULT:
 		to->si_addr = ptr_to_compat(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
+		break;
+	case SIL_FAULT_TRAPNO:
+		to->si_addr = ptr_to_compat(from->si_addr);
 		to->si_trapno = from->si_trapno;
-#endif
 		break;
 	case SIL_FAULT_MCEERR:
 		to->si_addr = ptr_to_compat(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
-		to->si_trapno = from->si_trapno;
-#endif
 		to->si_addr_lsb = from->si_addr_lsb;
 		break;
 	case SIL_FAULT_BNDERR:
 		to->si_addr = ptr_to_compat(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
-		to->si_trapno = from->si_trapno;
-#endif
 		to->si_lower = ptr_to_compat(from->si_lower);
 		to->si_upper = ptr_to_compat(from->si_upper);
 		break;
 	case SIL_FAULT_PKUERR:
 		to->si_addr = ptr_to_compat(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
-		to->si_trapno = from->si_trapno;
-#endif
 		to->si_pkey = from->si_pkey;
 		break;
 	case SIL_PERF_EVENT:
@@ -3401,30 +3399,22 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to,
 		break;
 	case SIL_FAULT:
 		to->si_addr = compat_ptr(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
+		break;
+	case SIL_FAULT_TRAPNO:
+		to->si_addr = compat_ptr(from->si_addr);
 		to->si_trapno = from->si_trapno;
-#endif
 		break;
 	case SIL_FAULT_MCEERR:
 		to->si_addr = compat_ptr(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
-		to->si_trapno = from->si_trapno;
-#endif
 		to->si_addr_lsb = from->si_addr_lsb;
 		break;
 	case SIL_FAULT_BNDERR:
 		to->si_addr = compat_ptr(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
-		to->si_trapno = from->si_trapno;
-#endif
 		to->si_lower = compat_ptr(from->si_lower);
 		to->si_upper = compat_ptr(from->si_upper);
 		break;
 	case SIL_FAULT_PKUERR:
 		to->si_addr = compat_ptr(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
-		to->si_trapno = from->si_trapno;
-#endif
 		to->si_pkey = from->si_pkey;
 		break;
 	case SIL_PERF_EVENT:
-- 
cgit v1.2.3


From af5eeab7e8e8c2f0fad10e4ab8cc8092012a2d5b Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sun, 2 May 2021 14:27:24 -0500
Subject: signal: Factor force_sig_perf out of perf_sigtrap

Separate filling in siginfo for TRAP_PERF from deciding that
siginal needs to be sent.

There are enough little details that need to be correct when
properly filling in siginfo_t that it is easy to make mistakes
if filling in the siginfo_t is in the same function with other
logic.  So factor out force_sig_perf to reduce the cognative
load of on reviewers, maintainers and implementors.

v1: https://lkml.kernel.org/r/m17dkjqqxz.fsf_-_@fess.ebiederm.org
v2: https://lkml.kernel.org/r/20210505141101.11519-10-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20210517195748.8880-3-ebiederm@xmission.com
Reviewed-by: Marco Elver <elver@google.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/sched/signal.h |  1 +
 kernel/events/core.c         | 11 ++---------
 kernel/signal.c              | 13 +++++++++++++
 3 files changed, 16 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 3f6a0fcaa10c..7f4278fa21fe 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -326,6 +326,7 @@ int send_sig_mceerr(int code, void __user *, short, struct task_struct *);
 
 int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper);
 int force_sig_pkuerr(void __user *addr, u32 pkey);
+int force_sig_perf(void __user *addr, u32 type, u64 sig_data);
 
 int force_sig_ptrace_errno_trap(int errno, void __user *addr);
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 928b166d888e..48ea8863183b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6394,8 +6394,6 @@ void perf_event_wakeup(struct perf_event *event)
 
 static void perf_sigtrap(struct perf_event *event)
 {
-	struct kernel_siginfo info;
-
 	/*
 	 * We'd expect this to only occur if the irq_work is delayed and either
 	 * ctx->task or current has changed in the meantime. This can be the
@@ -6410,13 +6408,8 @@ static void perf_sigtrap(struct perf_event *event)
 	if (current->flags & PF_EXITING)
 		return;
 
-	clear_siginfo(&info);
-	info.si_signo = SIGTRAP;
-	info.si_code = TRAP_PERF;
-	info.si_errno = event->attr.type;
-	info.si_perf = event->attr.sig_data;
-	info.si_addr = (void __user *)event->pending_addr;
-	force_sig_info(&info);
+	force_sig_perf((void __user *)event->pending_addr,
+		       event->attr.type, event->attr.sig_data);
 }
 
 static void perf_pending_event_disable(struct perf_event *event)
diff --git a/kernel/signal.c b/kernel/signal.c
index 597594ee72de..3a18d13c39b2 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1763,6 +1763,19 @@ int force_sig_pkuerr(void __user *addr, u32 pkey)
 }
 #endif
 
+int force_sig_perf(void __user *addr, u32 type, u64 sig_data)
+{
+	struct kernel_siginfo info;
+
+	clear_siginfo(&info);
+	info.si_signo = SIGTRAP;
+	info.si_errno = type;
+	info.si_code  = TRAP_PERF;
+	info.si_addr  = addr;
+	info.si_perf  = sig_data;
+	return force_sig_info(&info);
+}
+
 /* For the crazy architectures that include trap information in
  * the errno field, instead of an actual errno value.
  */
-- 
cgit v1.2.3


From 0683b53197b55343a166f1507086823030809a19 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sun, 2 May 2021 17:28:31 -0500
Subject: signal: Deliver all of the siginfo perf data in _perf

Don't abuse si_errno and deliver all of the perf data in _perf member
of siginfo_t.

Note: The data field in the perf data structures in a u64 to allow a
pointer to be encoded without needed to implement a 32bit and 64bit
version of the same structure.  There already exists a 32bit and 64bit
versions siginfo_t, and the 32bit version can not include a 64bit
member as it only has 32bit alignment.  So unsigned long is used in
siginfo_t instead of a u64 as unsigned long can encode a pointer on
all architectures linux supports.

v1: https://lkml.kernel.org/r/m11rarqqx2.fsf_-_@fess.ebiederm.org
v2: https://lkml.kernel.org/r/20210503203814.25487-10-ebiederm@xmission.com
v3: https://lkml.kernel.org/r/20210505141101.11519-11-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20210517195748.8880-4-ebiederm@xmission.com
Reviewed-by: Marco Elver <elver@google.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 arch/m68k/kernel/signal.c                           |  3 ++-
 arch/x86/kernel/signal_compat.c                     |  6 ++++--
 fs/signalfd.c                                       |  3 ++-
 include/linux/compat.h                              |  5 ++++-
 include/uapi/asm-generic/siginfo.h                  |  8 ++++++--
 include/uapi/linux/perf_event.h                     |  2 +-
 include/uapi/linux/signalfd.h                       |  4 ++--
 kernel/signal.c                                     | 21 +++++++++++++--------
 .../testing/selftests/perf_events/sigtrap_threads.c | 14 +++++++-------
 9 files changed, 41 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index a4b7ee1df211..8f215e79e70e 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -623,7 +623,8 @@ static inline void siginfo_build_tests(void)
 	BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x12);
 
 	/* _sigfault._perf */
-	BUILD_BUG_ON(offsetof(siginfo_t, si_perf) != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x14);
 
 	/* _sigpoll */
 	BUILD_BUG_ON(offsetof(siginfo_t, si_band)   != 0x0c);
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index a9fcabd8a5e5..06743ec054d2 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -141,8 +141,10 @@ static inline void signal_compat_build_tests(void)
 	BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20);
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14);
 
-	BUILD_BUG_ON(offsetof(siginfo_t, si_perf) != 0x18);
-	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf) != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x18);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x20);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_data) != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_type) != 0x14);
 
 	CHECK_CSI_OFFSET(_sigpoll);
 	CHECK_CSI_SIZE  (_sigpoll, 2*sizeof(int));
diff --git a/fs/signalfd.c b/fs/signalfd.c
index e87e59581653..373df2f12415 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -134,7 +134,8 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 		break;
 	case SIL_PERF_EVENT:
 		new.ssi_addr = (long) kinfo->si_addr;
-		new.ssi_perf = kinfo->si_perf;
+		new.ssi_perf_type = kinfo->si_perf_type;
+		new.ssi_perf_data = kinfo->si_perf_data;
 		break;
 	case SIL_CHLD:
 		new.ssi_pid    = kinfo->si_pid;
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 6af7bef15e94..a27fffaae121 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -236,7 +236,10 @@ typedef struct compat_siginfo {
 					u32 _pkey;
 				} _addr_pkey;
 				/* used when si_code=TRAP_PERF */
-				compat_ulong_t _perf;
+				struct {
+					compat_ulong_t _data;
+					u32 _type;
+				} _perf;
 			};
 		} _sigfault;
 
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index e663bf117b46..5a3c221f4c9d 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -91,7 +91,10 @@ union __sifields {
 				__u32 _pkey;
 			} _addr_pkey;
 			/* used when si_code=TRAP_PERF */
-			unsigned long _perf;
+			struct {
+				unsigned long _data;
+				__u32 _type;
+			} _perf;
 		};
 	} _sigfault;
 
@@ -154,7 +157,8 @@ typedef struct siginfo {
 #define si_lower	_sifields._sigfault._addr_bnd._lower
 #define si_upper	_sifields._sigfault._addr_bnd._upper
 #define si_pkey		_sifields._sigfault._addr_pkey._pkey
-#define si_perf		_sifields._sigfault._perf
+#define si_perf_data	_sifields._sigfault._perf._data
+#define si_perf_type	_sifields._sigfault._perf._type
 #define si_band		_sifields._sigpoll._band
 #define si_fd		_sifields._sigpoll._fd
 #define si_call_addr	_sifields._sigsys._call_addr
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index e54e639248c8..7b14753b3d38 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -464,7 +464,7 @@ struct perf_event_attr {
 
 	/*
 	 * User provided data if sigtrap=1, passed back to user via
-	 * siginfo_t::si_perf, e.g. to permit user to identify the event.
+	 * siginfo_t::si_perf_data, e.g. to permit user to identify the event.
 	 */
 	__u64	sig_data;
 };
diff --git a/include/uapi/linux/signalfd.h b/include/uapi/linux/signalfd.h
index 7e333042c7e3..e78dddf433fc 100644
--- a/include/uapi/linux/signalfd.h
+++ b/include/uapi/linux/signalfd.h
@@ -39,8 +39,8 @@ struct signalfd_siginfo {
 	__s32 ssi_syscall;
 	__u64 ssi_call_addr;
 	__u32 ssi_arch;
-	__u32 __pad3;
-	__u64 ssi_perf;
+	__u32 ssi_perf_type;
+	__u64 ssi_perf_data;
 
 	/*
 	 * Pad strcture to 128 bytes. Remember to update the
diff --git a/kernel/signal.c b/kernel/signal.c
index 3a18d13c39b2..dca53515ae3f 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1768,11 +1768,13 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data)
 	struct kernel_siginfo info;
 
 	clear_siginfo(&info);
-	info.si_signo = SIGTRAP;
-	info.si_errno = type;
-	info.si_code  = TRAP_PERF;
-	info.si_addr  = addr;
-	info.si_perf  = sig_data;
+	info.si_signo     = SIGTRAP;
+	info.si_errno     = 0;
+	info.si_code      = TRAP_PERF;
+	info.si_addr      = addr;
+	info.si_perf_data = sig_data;
+	info.si_perf_type = type;
+
 	return force_sig_info(&info);
 }
 
@@ -3356,7 +3358,8 @@ void copy_siginfo_to_external32(struct compat_siginfo *to,
 		break;
 	case SIL_PERF_EVENT:
 		to->si_addr = ptr_to_compat(from->si_addr);
-		to->si_perf = from->si_perf;
+		to->si_perf_data = from->si_perf_data;
+		to->si_perf_type = from->si_perf_type;
 		break;
 	case SIL_CHLD:
 		to->si_pid = from->si_pid;
@@ -3432,7 +3435,8 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to,
 		break;
 	case SIL_PERF_EVENT:
 		to->si_addr = compat_ptr(from->si_addr);
-		to->si_perf = from->si_perf;
+		to->si_perf_data = from->si_perf_data;
+		to->si_perf_type = from->si_perf_type;
 		break;
 	case SIL_CHLD:
 		to->si_pid    = from->si_pid;
@@ -4615,7 +4619,8 @@ static inline void siginfo_buildtime_checks(void)
 	CHECK_OFFSET(si_lower);
 	CHECK_OFFSET(si_upper);
 	CHECK_OFFSET(si_pkey);
-	CHECK_OFFSET(si_perf);
+	CHECK_OFFSET(si_perf_data);
+	CHECK_OFFSET(si_perf_type);
 
 	/* sigpoll */
 	CHECK_OFFSET(si_band);
diff --git a/tools/testing/selftests/perf_events/sigtrap_threads.c b/tools/testing/selftests/perf_events/sigtrap_threads.c
index 78ddf5e11625..8e83cf91513a 100644
--- a/tools/testing/selftests/perf_events/sigtrap_threads.c
+++ b/tools/testing/selftests/perf_events/sigtrap_threads.c
@@ -43,7 +43,7 @@ static struct {
 	siginfo_t first_siginfo;	/* First observed siginfo_t. */
 } ctx;
 
-/* Unique value to check si_perf is correctly set from perf_event_attr::sig_data. */
+/* Unique value to check si_perf_data is correctly set from perf_event_attr::sig_data. */
 #define TEST_SIG_DATA(addr) (~(unsigned long)(addr))
 
 static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr)
@@ -164,8 +164,8 @@ TEST_F(sigtrap_threads, enable_event)
 	EXPECT_EQ(ctx.signal_count, NUM_THREADS);
 	EXPECT_EQ(ctx.tids_want_signal, 0);
 	EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
-	EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT);
-	EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on));
+	EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
+	EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
 
 	/* Check enabled for parent. */
 	ctx.iterate_on = 0;
@@ -183,8 +183,8 @@ TEST_F(sigtrap_threads, modify_and_enable_event)
 	EXPECT_EQ(ctx.signal_count, NUM_THREADS);
 	EXPECT_EQ(ctx.tids_want_signal, 0);
 	EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
-	EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT);
-	EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on));
+	EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
+	EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
 
 	/* Check enabled for parent. */
 	ctx.iterate_on = 0;
@@ -203,8 +203,8 @@ TEST_F(sigtrap_threads, signal_stress)
 	EXPECT_EQ(ctx.signal_count, NUM_THREADS * ctx.iterate_on);
 	EXPECT_EQ(ctx.tids_want_signal, 0);
 	EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
-	EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT);
-	EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on));
+	EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
+	EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
 }
 
 TEST_HARNESS_MAIN
-- 
cgit v1.2.3


From 922e3013046b79b444c87eda5baf43afae1326a8 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 3 May 2021 12:52:43 -0500
Subject: signalfd: Remove SIL_PERF_EVENT fields from signalfd_siginfo

With the addition of ssi_perf_data and ssi_perf_type struct signalfd_siginfo
is dangerously close to running out of space.  All that remains is just
enough space for two additional 64bit fields.  A practice of adding all
possible siginfo_t fields into struct singalfd_siginfo can not be supported
as adding the missing fields ssi_lower, ssi_upper, and ssi_pkey would
require two 64bit fields and one 32bit fields.  In practice the fields
ssi_perf_data and ssi_perf_type can never be used by signalfd as the signal
that generates them always delivers them synchronously to the thread that
triggers them.

Therefore until someone actually needs the fields ssi_perf_data and
ssi_perf_type in signalfd_siginfo remove them.  This leaves a bit more room
for future expansion.

v1: https://lkml.kernel.org/r/20210503203814.25487-12-ebiederm@xmission.com
v2: https://lkml.kernel.org/r/20210505141101.11519-12-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20210517195748.8880-5-ebiederm@xmission.com
Reviewed-by: Marco Elver <elver@google.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/signalfd.c                 | 16 ++++++----------
 include/uapi/linux/signalfd.h |  4 +---
 2 files changed, 7 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/signalfd.c b/fs/signalfd.c
index 373df2f12415..167b5889db4b 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -114,12 +114,13 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 		break;
 	case SIL_FAULT_BNDERR:
 	case SIL_FAULT_PKUERR:
+	case SIL_PERF_EVENT:
 		/*
-		 * Fall through to the SIL_FAULT case.  Both SIL_FAULT_BNDERR
-		 * and SIL_FAULT_PKUERR are only generated by faults that
-		 * deliver them synchronously to userspace.  In case someone
-		 * injects one of these signals and signalfd catches it treat
-		 * it as SIL_FAULT.
+		 * Fall through to the SIL_FAULT case.  SIL_FAULT_BNDERR,
+		 * SIL_FAULT_PKUERR, and SIL_PERF_EVENT are only
+		 * generated by faults that deliver them synchronously to
+		 * userspace.  In case someone injects one of these signals
+		 * and signalfd catches it treat it as SIL_FAULT.
 		 */
 	case SIL_FAULT:
 		new.ssi_addr = (long) kinfo->si_addr;
@@ -132,11 +133,6 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 		new.ssi_addr = (long) kinfo->si_addr;
 		new.ssi_addr_lsb = (short) kinfo->si_addr_lsb;
 		break;
-	case SIL_PERF_EVENT:
-		new.ssi_addr = (long) kinfo->si_addr;
-		new.ssi_perf_type = kinfo->si_perf_type;
-		new.ssi_perf_data = kinfo->si_perf_data;
-		break;
 	case SIL_CHLD:
 		new.ssi_pid    = kinfo->si_pid;
 		new.ssi_uid    = kinfo->si_uid;
diff --git a/include/uapi/linux/signalfd.h b/include/uapi/linux/signalfd.h
index e78dddf433fc..83429a05b698 100644
--- a/include/uapi/linux/signalfd.h
+++ b/include/uapi/linux/signalfd.h
@@ -39,8 +39,6 @@ struct signalfd_siginfo {
 	__s32 ssi_syscall;
 	__u64 ssi_call_addr;
 	__u32 ssi_arch;
-	__u32 ssi_perf_type;
-	__u64 ssi_perf_data;
 
 	/*
 	 * Pad strcture to 128 bytes. Remember to update the
@@ -51,7 +49,7 @@ struct signalfd_siginfo {
 	 * comes out of a read(2) and we really don't want to have
 	 * a compat on read(2).
 	 */
-	__u8 __pad[16];
+	__u8 __pad[28];
 };
 
 
-- 
cgit v1.2.3


From 3410fbcd47dc6479af4309febf760ccaa5efb472 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@nvidia.com>
Date: Wed, 12 May 2021 13:52:27 +0300
Subject: {net, RDMA}/mlx5: Fix override of log_max_qp by other device

mlx5_core_dev holds pointer to static profile, hence when the
log_max_qp of the profile is override by some device, then it
effect all other mlx5 devices that share the same profile.
Fix it by having a profile instance for every mlx5 device.

Fixes: 883371c453b9 ("net/mlx5: Check FW limitations on log_max_qp before setting it")
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/infiniband/hw/mlx5/mr.c                |  4 +--
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 11 +++----
 include/linux/mlx5/driver.h                    | 44 +++++++++++++-------------
 3 files changed, 29 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 4388afeff251..9662cd39c7ff 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -743,10 +743,10 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 		ent->xlt = (1 << ent->order) * sizeof(struct mlx5_mtt) /
 			   MLX5_IB_UMR_OCTOWORD;
 		ent->access_mode = MLX5_MKC_ACCESS_MODE_MTT;
-		if ((dev->mdev->profile->mask & MLX5_PROF_MASK_MR_CACHE) &&
+		if ((dev->mdev->profile.mask & MLX5_PROF_MASK_MR_CACHE) &&
 		    !dev->is_rep && mlx5_core_is_pf(dev->mdev) &&
 		    mlx5_ib_can_load_pas_with_umr(dev, 0))
-			ent->limit = dev->mdev->profile->mr_cache[i].limit;
+			ent->limit = dev->mdev->profile.mr_cache[i].limit;
 		else
 			ent->limit = 0;
 		spin_lock_irq(&ent->lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c114365eb126..a1d67bd7fb43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -503,7 +503,7 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
 
 static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 {
-	struct mlx5_profile *prof = dev->profile;
+	struct mlx5_profile *prof = &dev->profile;
 	void *set_hca_cap;
 	int err;
 
@@ -524,11 +524,11 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 		 to_fw_pkey_sz(dev, 128));
 
 	/* Check log_max_qp from HCA caps to set in current profile */
-	if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < profile[prof_sel].log_max_qp) {
+	if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < prof->log_max_qp) {
 		mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n",
-			       profile[prof_sel].log_max_qp,
+			       prof->log_max_qp,
 			       MLX5_CAP_GEN_MAX(dev, log_max_qp));
-		profile[prof_sel].log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp);
+		prof->log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp);
 	}
 	if (prof->mask & MLX5_PROF_MASK_QP_SIZE)
 		MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp,
@@ -1381,8 +1381,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	struct mlx5_priv *priv = &dev->priv;
 	int err;
 
-	dev->profile = &profile[profile_idx];
-
+	memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile));
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
 	mutex_init(&dev->intf_state_mutex);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f8e8d7e90616..020a8f7fdbdd 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -703,6 +703,27 @@ struct mlx5_hv_vhca;
 #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity))
 #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev))
 
+enum {
+	MLX5_PROF_MASK_QP_SIZE		= (u64)1 << 0,
+	MLX5_PROF_MASK_MR_CACHE		= (u64)1 << 1,
+};
+
+enum {
+	MR_CACHE_LAST_STD_ENTRY = 20,
+	MLX5_IMR_MTT_CACHE_ENTRY,
+	MLX5_IMR_KSM_CACHE_ENTRY,
+	MAX_MR_CACHE_ENTRIES
+};
+
+struct mlx5_profile {
+	u64	mask;
+	u8	log_max_qp;
+	struct {
+		int	size;
+		int	limit;
+	} mr_cache[MAX_MR_CACHE_ENTRIES];
+};
+
 struct mlx5_core_dev {
 	struct device *device;
 	enum mlx5_coredev_type coredev_type;
@@ -731,7 +752,7 @@ struct mlx5_core_dev {
 	struct mutex		intf_state_mutex;
 	unsigned long		intf_state;
 	struct mlx5_priv	priv;
-	struct mlx5_profile	*profile;
+	struct mlx5_profile	profile;
 	u32			issi;
 	struct mlx5e_resources  mlx5e_res;
 	struct mlx5_dm          *dm;
@@ -1083,18 +1104,6 @@ static inline u8 mlx5_mkey_variant(u32 mkey)
 	return mkey & 0xff;
 }
 
-enum {
-	MLX5_PROF_MASK_QP_SIZE		= (u64)1 << 0,
-	MLX5_PROF_MASK_MR_CACHE		= (u64)1 << 1,
-};
-
-enum {
-	MR_CACHE_LAST_STD_ENTRY = 20,
-	MLX5_IMR_MTT_CACHE_ENTRY,
-	MLX5_IMR_KSM_CACHE_ENTRY,
-	MAX_MR_CACHE_ENTRIES
-};
-
 /* Async-atomic event notifier used by mlx5 core to forward FW
  * evetns recived from event queue to mlx5 consumers.
  * Optimise event queue dipatching.
@@ -1148,15 +1157,6 @@ int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev,
 			    struct ib_device *device,
 			    struct rdma_netdev_alloc_params *params);
 
-struct mlx5_profile {
-	u64	mask;
-	u8	log_max_qp;
-	struct {
-		int	size;
-		int	limit;
-	} mr_cache[MAX_MR_CACHE_ENTRIES];
-};
-
 enum {
 	MLX5_PCI_DEV_IS_VF		= 1 << 0,
 };
-- 
cgit v1.2.3


From 7c9f131f366ab414691907fa0407124ea2b2f3bc Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Thu, 22 Apr 2021 15:48:10 +0300
Subject: {net,vdpa}/mlx5: Configure interface MAC into mpfs L2 table

net/mlx5: Expose MPFS configuration API

MPFS is the multi physical function switch that bridges traffic between
the physical port and any physical functions associated with it. The
driver is required to add or remove MAC entries to properly forward
incoming traffic to the correct physical function.

We export the API to control MPFS so that other drivers, such as
mlx5_vdpa are able to add MAC addresses of their network interfaces.

The MAC address of the vdpa interface must be configured into the MPFS L2
address. Failing to do so could cause, in some NIC configurations, failure
to forward packets to the vdpa network device instance.

Fix this by adding calls to update the MPFS table.

CC: <mst@redhat.com>
CC: <jasowang@redhat.com>
CC: <virtualization@lists.linux-foundation.org>
Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices")
Signed-off-by: Eli Cohen <elic@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_fs.c    |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c |  3 +++
 drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h |  5 +----
 drivers/vdpa/mlx5/net/mlx5_vnet.c                  | 19 ++++++++++++++++++-
 include/linux/mlx5/mpfs.h                          | 18 ++++++++++++++++++
 6 files changed, 42 insertions(+), 5 deletions(-)
 create mode 100644 include/linux/mlx5/mpfs.h

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 0d571a0c76d9..0b75fab41ae8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -35,6 +35,7 @@
 #include <linux/ipv6.h>
 #include <linux/tcp.h>
 #include <linux/mlx5/fs.h>
+#include <linux/mlx5/mpfs.h>
 #include "en.h"
 #include "en_rep.h"
 #include "lib/mpfs.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 570f2280823c..b88705a3a1a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -35,6 +35,7 @@
 #include <linux/mlx5/mlx5_ifc.h>
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
+#include <linux/mlx5/mpfs.h>
 #include "esw/acl/lgcy.h"
 #include "esw/legacy.h"
 #include "mlx5_core.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
index fd8449ff9e17..839a01da110f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
@@ -33,6 +33,7 @@
 #include <linux/etherdevice.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/mpfs.h>
 #include <linux/mlx5/eswitch.h>
 #include "mlx5_core.h"
 #include "lib/mpfs.h"
@@ -175,6 +176,7 @@ out:
 	mutex_unlock(&mpfs->lock);
 	return err;
 }
+EXPORT_SYMBOL(mlx5_mpfs_add_mac);
 
 int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac)
 {
@@ -206,3 +208,4 @@ unlock:
 	mutex_unlock(&mpfs->lock);
 	return err;
 }
+EXPORT_SYMBOL(mlx5_mpfs_del_mac);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h
index 4a7b2c3203a7..4a293542a7aa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h
@@ -84,12 +84,9 @@ struct l2addr_node {
 #ifdef CONFIG_MLX5_MPFS
 int  mlx5_mpfs_init(struct mlx5_core_dev *dev);
 void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev);
-int  mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac);
-int  mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac);
 #else /* #ifndef CONFIG_MLX5_MPFS */
 static inline int  mlx5_mpfs_init(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) {}
-static inline int  mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; }
-static inline int  mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; }
 #endif
+
 #endif
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 189e4385df40..dda5dc6f7737 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -15,6 +15,7 @@
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
 #include <linux/mlx5/mlx5_ifc_vdpa.h>
+#include <linux/mlx5/mpfs.h>
 #include "mlx5_vdpa.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
@@ -1859,11 +1860,16 @@ static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb
 static void mlx5_vdpa_free(struct vdpa_device *vdev)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+	struct mlx5_core_dev *pfmdev;
 	struct mlx5_vdpa_net *ndev;
 
 	ndev = to_mlx5_vdpa_ndev(mvdev);
 
 	free_resources(ndev);
+	if (!is_zero_ether_addr(ndev->config.mac)) {
+		pfmdev = pci_get_drvdata(pci_physfn(mvdev->mdev->pdev));
+		mlx5_mpfs_del_mac(pfmdev, ndev->config.mac);
+	}
 	mlx5_vdpa_free_resources(&ndev->mvdev);
 	mutex_destroy(&ndev->reslock);
 }
@@ -1990,6 +1996,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
 {
 	struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev);
 	struct virtio_net_config *config;
+	struct mlx5_core_dev *pfmdev;
 	struct mlx5_vdpa_dev *mvdev;
 	struct mlx5_vdpa_net *ndev;
 	struct mlx5_core_dev *mdev;
@@ -2023,10 +2030,17 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
 	if (err)
 		goto err_mtu;
 
+	if (!is_zero_ether_addr(config->mac)) {
+		pfmdev = pci_get_drvdata(pci_physfn(mdev->pdev));
+		err = mlx5_mpfs_add_mac(pfmdev, config->mac);
+		if (err)
+			goto err_mtu;
+	}
+
 	mvdev->vdev.dma_dev = mdev->device;
 	err = mlx5_vdpa_alloc_resources(&ndev->mvdev);
 	if (err)
-		goto err_mtu;
+		goto err_mpfs;
 
 	err = alloc_resources(ndev);
 	if (err)
@@ -2044,6 +2058,9 @@ err_reg:
 	free_resources(ndev);
 err_res:
 	mlx5_vdpa_free_resources(&ndev->mvdev);
+err_mpfs:
+	if (!is_zero_ether_addr(config->mac))
+		mlx5_mpfs_del_mac(pfmdev, config->mac);
 err_mtu:
 	mutex_destroy(&ndev->reslock);
 	put_device(&mvdev->vdev.dev);
diff --git a/include/linux/mlx5/mpfs.h b/include/linux/mlx5/mpfs.h
new file mode 100644
index 000000000000..bf700c8d5516
--- /dev/null
+++ b/include/linux/mlx5/mpfs.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+ * Copyright (c) 2021 Mellanox Technologies Ltd.
+ */
+
+#ifndef _MLX5_MPFS_
+#define _MLX5_MPFS_
+
+struct mlx5_core_dev;
+
+#ifdef CONFIG_MLX5_MPFS
+int  mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac);
+int  mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac);
+#else /* #ifndef CONFIG_MLX5_MPFS */
+static inline int  mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; }
+static inline int  mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; }
+#endif
+
+#endif
-- 
cgit v1.2.3


From ba6e1d8422bd476ad79da409639a773c02f0cbad Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 14 May 2021 22:04:36 +0200
Subject: platform/surface: aggregator: avoid clang -Wconstant-conversion
 warning

Clang complains about the assignment of SSAM_ANY_IID to
ssam_device_uid->instance:

drivers/platform/surface/surface_aggregator_registry.c:478:25: error: implicit conversion from 'int' to '__u8' (aka 'unsigned char') changes value from 65535 to 255 [-Werror,-Wconstant-conversion]
        { SSAM_VDEV(HUB, 0x02, SSAM_ANY_IID, 0x00) },
        ~                      ^~~~~~~~~~~~
include/linux/surface_aggregator/device.h:71:23: note: expanded from macro 'SSAM_ANY_IID'
 #define SSAM_ANY_IID            0xffff
                                ^~~~~~
include/linux/surface_aggregator/device.h:126:63: note: expanded from macro 'SSAM_VDEV'
        SSAM_DEVICE(SSAM_DOMAIN_VIRTUAL, SSAM_VIRTUAL_TC_##cat, tid, iid, fun)
                                                                     ^~~
include/linux/surface_aggregator/device.h:102:41: note: expanded from macro 'SSAM_DEVICE'
        .instance = ((iid) != SSAM_ANY_IID) ? (iid) : 0,                        \
                                               ^~~

The assignment doesn't actually happen, but clang checks the type limits
before checking whether this assignment is reached. Replace the ?:
operator with a __builtin_choose_expr() invocation that avoids the
warning for the untaken part.

Fixes: eb0e90a82098 ("platform/surface: aggregator: Add dedicated bus and device type")
Cc: platform-driver-x86@vger.kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Maximilian Luz <luzmaximilian@gmail.com>
Link: https://lore.kernel.org/r/20210514200453.1542978-1-arnd@kernel.org
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 include/linux/surface_aggregator/device.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h
index 4441ad667c3f..6ff9c58b3e17 100644
--- a/include/linux/surface_aggregator/device.h
+++ b/include/linux/surface_aggregator/device.h
@@ -98,9 +98,9 @@ struct ssam_device_uid {
 		     | (((fun) != SSAM_ANY_FUN) ? SSAM_MATCH_FUNCTION : 0),	\
 	.domain   = d,								\
 	.category = cat,							\
-	.target   = ((tid) != SSAM_ANY_TID) ? (tid) : 0,			\
-	.instance = ((iid) != SSAM_ANY_IID) ? (iid) : 0,			\
-	.function = ((fun) != SSAM_ANY_FUN) ? (fun) : 0				\
+	.target   = __builtin_choose_expr((tid) != SSAM_ANY_TID, (tid), 0),	\
+	.instance = __builtin_choose_expr((iid) != SSAM_ANY_IID, (iid), 0),	\
+	.function = __builtin_choose_expr((fun) != SSAM_ANY_FUN, (fun), 0)
 
 /**
  * SSAM_VDEV() - Initialize a &struct ssam_device_id as virtual device with
-- 
cgit v1.2.3


From 6c60ff048ca1e0739f39aa25996543c6e662a46c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 14 May 2021 15:18:41 +0200
Subject: block: prevent block device lookups at the beginning of del_gendisk

As an artifact of how gendisk lookup used to work in earlier kernels,
GENHD_FL_UP is only cleared very late in del_gendisk, and a global lock
is used to prevent opens from succeeding while del_gendisk is tearing
down the gendisk.  Switch to clearing the flag early and under bd_mutex
so that callers can use bd_mutex to stabilize the flag, which removes
the need for the global mutex.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20210514131842.1600568-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c         | 11 +----------
 fs/block_dev.c        | 15 +++++----------
 include/linux/genhd.h |  2 --
 3 files changed, 6 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/block/genhd.c b/block/genhd.c
index 39ca97b0edc6..9f8cb7beaad1 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -29,8 +29,6 @@
 
 static struct kobject *block_depr;
 
-DECLARE_RWSEM(bdev_lookup_sem);
-
 /* for extended dynamic devt allocation, currently only one major is used */
 #define NR_EXT_DEVT		(1 << MINORBITS)
 static DEFINE_IDA(ext_devt_ida);
@@ -609,13 +607,8 @@ void del_gendisk(struct gendisk *disk)
 	blk_integrity_del(disk);
 	disk_del_events(disk);
 
-	/*
-	 * Block lookups of the disk until all bdevs are unhashed and the
-	 * disk is marked as dead (GENHD_FL_UP cleared).
-	 */
-	down_write(&bdev_lookup_sem);
-
 	mutex_lock(&disk->part0->bd_mutex);
+	disk->flags &= ~GENHD_FL_UP;
 	blk_drop_partitions(disk);
 	mutex_unlock(&disk->part0->bd_mutex);
 
@@ -629,8 +622,6 @@ void del_gendisk(struct gendisk *disk)
 	remove_inode_hash(disk->part0->bd_inode);
 
 	set_capacity(disk, 0);
-	disk->flags &= ~GENHD_FL_UP;
-	up_write(&bdev_lookup_sem);
 
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
diff --git a/fs/block_dev.c b/fs/block_dev.c
index eb265d72fce8..580bae995b87 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1298,6 +1298,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 	struct gendisk *disk = bdev->bd_disk;
 	int ret = 0;
 
+	if (!(disk->flags & GENHD_FL_UP))
+		return -ENXIO;
+
 	if (!bdev->bd_openers) {
 		if (!bdev_is_partition(bdev)) {
 			ret = 0;
@@ -1332,8 +1335,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 			whole->bd_part_count++;
 			mutex_unlock(&whole->bd_mutex);
 
-			if (!(disk->flags & GENHD_FL_UP) ||
-			    !bdev_nr_sectors(bdev)) {
+			if (!bdev_nr_sectors(bdev)) {
 				__blkdev_put(whole, mode, 1);
 				bdput(whole);
 				return -ENXIO;
@@ -1364,16 +1366,12 @@ struct block_device *blkdev_get_no_open(dev_t dev)
 	struct block_device *bdev;
 	struct gendisk *disk;
 
-	down_read(&bdev_lookup_sem);
 	bdev = bdget(dev);
 	if (!bdev) {
-		up_read(&bdev_lookup_sem);
 		blk_request_module(dev);
-		down_read(&bdev_lookup_sem);
-
 		bdev = bdget(dev);
 		if (!bdev)
-			goto unlock;
+			return NULL;
 	}
 
 	disk = bdev->bd_disk;
@@ -1383,14 +1381,11 @@ struct block_device *blkdev_get_no_open(dev_t dev)
 		goto put_disk;
 	if (!try_module_get(bdev->bd_disk->fops->owner))
 		goto put_disk;
-	up_read(&bdev_lookup_sem);
 	return bdev;
 put_disk:
 	put_disk(disk);
 bdput:
 	bdput(bdev);
-unlock:
-	up_read(&bdev_lookup_sem);
 	return NULL;
 }
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 7e9660ea967d..6fc26f7bdf71 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -306,8 +306,6 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev,
 }
 #endif /* CONFIG_SYSFS */
 
-extern struct rw_semaphore bdev_lookup_sem;
-
 dev_t blk_lookup_devt(const char *name, int partno);
 void blk_request_module(dev_t devt);
 #ifdef CONFIG_BLOCK
-- 
cgit v1.2.3


From 80dd33cf72d1ab4f0af303f1fa242c6d6c8d328f Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 14 May 2021 14:10:15 +0200
Subject: drivers: base: Fix device link removal

When device_link_free() drops references to the supplier and
consumer devices of the device link going away and the reference
being dropped turns out to be the last one for any of those
device objects, its ->release callback will be invoked and it
may sleep which goes against the SRCU callback execution
requirements.

To address this issue, make the device link removal code carry out
the device_link_free() actions preceded by SRCU synchronization from
a separate work item (the "long" workqueue is used for that, because
it does not matter when the device link memory is released and it may
take time to get to that point) instead of using SRCU callbacks.

While at it, make the code work analogously when SRCU is not enabled
to reduce the differences between the SRCU and non-SRCU cases.

Fixes: 843e600b8a2b ("driver core: Fix sleeping in invalid context during device link deletion")
Cc: stable <stable@vger.kernel.org>
Reported-by: chenxiang (M) <chenxiang66@hisilicon.com>
Tested-by: chenxiang (M) <chenxiang66@hisilicon.com>
Reviewed-by: Saravana Kannan <saravanak@google.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/5722787.lOV4Wx5bFT@kreacher
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 37 +++++++++++++++++++++++--------------
 include/linux/device.h |  6 ++----
 2 files changed, 25 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 628e33939aca..61c19641e1d0 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -194,6 +194,11 @@ int device_links_read_lock_held(void)
 {
 	return srcu_read_lock_held(&device_links_srcu);
 }
+
+static void device_link_synchronize_removal(void)
+{
+	synchronize_srcu(&device_links_srcu);
+}
 #else /* !CONFIG_SRCU */
 static DECLARE_RWSEM(device_links_lock);
 
@@ -224,6 +229,10 @@ int device_links_read_lock_held(void)
 	return lockdep_is_held(&device_links_lock);
 }
 #endif
+
+static inline void device_link_synchronize_removal(void)
+{
+}
 #endif /* !CONFIG_SRCU */
 
 static bool device_is_ancestor(struct device *dev, struct device *target)
@@ -445,8 +454,13 @@ static struct attribute *devlink_attrs[] = {
 };
 ATTRIBUTE_GROUPS(devlink);
 
-static void device_link_free(struct device_link *link)
+static void device_link_release_fn(struct work_struct *work)
 {
+	struct device_link *link = container_of(work, struct device_link, rm_work);
+
+	/* Ensure that all references to the link object have been dropped. */
+	device_link_synchronize_removal();
+
 	while (refcount_dec_not_one(&link->rpm_active))
 		pm_runtime_put(link->supplier);
 
@@ -455,24 +469,19 @@ static void device_link_free(struct device_link *link)
 	kfree(link);
 }
 
-#ifdef CONFIG_SRCU
-static void __device_link_free_srcu(struct rcu_head *rhead)
-{
-	device_link_free(container_of(rhead, struct device_link, rcu_head));
-}
-
 static void devlink_dev_release(struct device *dev)
 {
 	struct device_link *link = to_devlink(dev);
 
-	call_srcu(&device_links_srcu, &link->rcu_head, __device_link_free_srcu);
-}
-#else
-static void devlink_dev_release(struct device *dev)
-{
-	device_link_free(to_devlink(dev));
+	INIT_WORK(&link->rm_work, device_link_release_fn);
+	/*
+	 * It may take a while to complete this work because of the SRCU
+	 * synchronization in device_link_release_fn() and if the consumer or
+	 * supplier devices get deleted when it runs, so put it into the "long"
+	 * workqueue.
+	 */
+	queue_work(system_long_wq, &link->rm_work);
 }
-#endif
 
 static struct class devlink_class = {
 	.name = "devlink",
diff --git a/include/linux/device.h b/include/linux/device.h
index 38a2071cf776..f1a00040fa53 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -570,7 +570,7 @@ struct device {
  * @flags: Link flags.
  * @rpm_active: Whether or not the consumer device is runtime-PM-active.
  * @kref: Count repeated addition of the same link.
- * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks.
+ * @rm_work: Work structure used for removing the link.
  * @supplier_preactivated: Supplier has been made active before consumer probe.
  */
 struct device_link {
@@ -583,9 +583,7 @@ struct device_link {
 	u32 flags;
 	refcount_t rpm_active;
 	struct kref kref;
-#ifdef CONFIG_SRCU
-	struct rcu_head rcu_head;
-#endif
+	struct work_struct rm_work;
 	bool supplier_preactivated; /* Owned by consumer probe. */
 };
 
-- 
cgit v1.2.3


From f747e6667ebb2ffb8133486c9cd19800d72b0d98 Mon Sep 17 00:00:00 2001
From: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Date: Sat, 22 May 2021 17:42:02 -0700
Subject: linux/bits.h: fix compilation error with GENMASK

GENMASK() has an input check which uses __builtin_choose_expr() to
enable a compile time sanity check of its inputs if they are known at
compile time.

However, it turns out that __builtin_constant_p() does not always return
a compile time constant [0].  It was thought this problem was fixed with
gcc 4.9 [1], but apparently this is not the case [2].

Switch to use __is_constexpr() instead which always returns a compile time
constant, regardless of its inputs.

Link: https://lore.kernel.org/lkml/42b4342b-aefc-a16a-0d43-9f9c0d63ba7a@rasmusvillemoes.dk [0]
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=19449 [1]
Link: https://lore.kernel.org/lkml/1ac7bbc2-45d9-26ed-0b33-bf382b8d858b@I-love.SAKURA.ne.jp [2]
Link: https://lkml.kernel.org/r/20210511203716.117010-1-rikard.falkeborn@gmail.com
Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Yury Norov <yury.norov@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bits.h        |  2 +-
 include/linux/const.h       |  8 ++++++++
 include/linux/minmax.h      | 10 ++--------
 tools/include/linux/bits.h  |  2 +-
 tools/include/linux/const.h |  8 ++++++++
 5 files changed, 20 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/bits.h b/include/linux/bits.h
index 7f475d59a097..87d112650dfb 100644
--- a/include/linux/bits.h
+++ b/include/linux/bits.h
@@ -22,7 +22,7 @@
 #include <linux/build_bug.h>
 #define GENMASK_INPUT_CHECK(h, l) \
 	(BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
-		__builtin_constant_p((l) > (h)), (l) > (h), 0)))
+		__is_constexpr((l) > (h)), (l) > (h), 0)))
 #else
 /*
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
diff --git a/include/linux/const.h b/include/linux/const.h
index 81b8aae5a855..435ddd72d2c4 100644
--- a/include/linux/const.h
+++ b/include/linux/const.h
@@ -3,4 +3,12 @@
 
 #include <vdso/const.h>
 
+/*
+ * This returns a constant expression while determining if an argument is
+ * a constant expression, most importantly without evaluating the argument.
+ * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
+ */
+#define __is_constexpr(x) \
+	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
+
 #endif /* _LINUX_CONST_H */
diff --git a/include/linux/minmax.h b/include/linux/minmax.h
index c0f57b0c64d9..5433c08fcc68 100644
--- a/include/linux/minmax.h
+++ b/include/linux/minmax.h
@@ -2,6 +2,8 @@
 #ifndef _LINUX_MINMAX_H
 #define _LINUX_MINMAX_H
 
+#include <linux/const.h>
+
 /*
  * min()/max()/clamp() macros must accomplish three things:
  *
@@ -17,14 +19,6 @@
 #define __typecheck(x, y) \
 	(!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
 
-/*
- * This returns a constant expression while determining if an argument is
- * a constant expression, most importantly without evaluating the argument.
- * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
- */
-#define __is_constexpr(x) \
-	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
-
 #define __no_side_effects(x, y) \
 		(__is_constexpr(x) && __is_constexpr(y))
 
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 7f475d59a097..87d112650dfb 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -22,7 +22,7 @@
 #include <linux/build_bug.h>
 #define GENMASK_INPUT_CHECK(h, l) \
 	(BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
-		__builtin_constant_p((l) > (h)), (l) > (h), 0)))
+		__is_constexpr((l) > (h)), (l) > (h), 0)))
 #else
 /*
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
diff --git a/tools/include/linux/const.h b/tools/include/linux/const.h
index 81b8aae5a855..435ddd72d2c4 100644
--- a/tools/include/linux/const.h
+++ b/tools/include/linux/const.h
@@ -3,4 +3,12 @@
 
 #include <vdso/const.h>
 
+/*
+ * This returns a constant expression while determining if an argument is
+ * a constant expression, most importantly without evaluating the argument.
+ * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
+ */
+#define __is_constexpr(x) \
+	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
+
 #endif /* _LINUX_CONST_H */
-- 
cgit v1.2.3


From 0514582a1a5b4ac1a3fd64792826d392d7ae9ddc Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Sun, 23 May 2021 15:10:44 +0800
Subject: regulator: bd70528: Fix off-by-one for buck123 .n_voltages setting

The valid selectors for bd70528 bucks are 0 ~ 0xf, so the .n_voltages
should be 16 (0x10). Use 0x10 to make it consistent with BD70528_LDO_VOLTS.
Also remove redundant defines for BD70528_BUCK_VOLTS.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Acked-by: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
Link: https://lore.kernel.org/r/20210523071045.2168904-1-axel.lin@ingics.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/mfd/rohm-bd70528.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/mfd/rohm-bd70528.h b/include/linux/mfd/rohm-bd70528.h
index a57af878fd0c..4a5966475a35 100644
--- a/include/linux/mfd/rohm-bd70528.h
+++ b/include/linux/mfd/rohm-bd70528.h
@@ -26,9 +26,7 @@ struct bd70528_data {
 	struct mutex rtc_timer_lock;
 };
 
-#define BD70528_BUCK_VOLTS 17
-#define BD70528_BUCK_VOLTS 17
-#define BD70528_BUCK_VOLTS 17
+#define BD70528_BUCK_VOLTS 0x10
 #define BD70528_LDO_VOLTS 0x20
 
 #define BD70528_REG_BUCK1_EN	0x0F
-- 
cgit v1.2.3


From 4c668630bf8ea90a041fc69c9984486e0f56682d Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Sun, 23 May 2021 15:10:45 +0800
Subject: regulator: bd71828: Fix .n_voltages settings

Current .n_voltages settings do not cover the latest 2 valid selectors,
so it fails to set voltage for the hightest voltage support.
The latest linear range has step_uV = 0, so it does not matter if we
count the .n_voltages to maximum selector + 1 or the first selector of
latest linear range + 1.
To simplify calculating the n_voltages, let's just set the
.n_voltages to maximum selector + 1.

Fixes: 522498f8cb8c ("regulator: bd71828: Basic support for ROHM bd71828 PMIC regulators")
Signed-off-by: Axel Lin <axel.lin@ingics.com>
Reviewed-by: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
Link: https://lore.kernel.org/r/20210523071045.2168904-2-axel.lin@ingics.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/mfd/rohm-bd71828.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/mfd/rohm-bd71828.h b/include/linux/mfd/rohm-bd71828.h
index 017a4c01cb31..61f0974c33d7 100644
--- a/include/linux/mfd/rohm-bd71828.h
+++ b/include/linux/mfd/rohm-bd71828.h
@@ -26,11 +26,11 @@ enum {
 	BD71828_REGULATOR_AMOUNT,
 };
 
-#define BD71828_BUCK1267_VOLTS		0xEF
-#define BD71828_BUCK3_VOLTS		0x10
-#define BD71828_BUCK4_VOLTS		0x20
-#define BD71828_BUCK5_VOLTS		0x10
-#define BD71828_LDO_VOLTS		0x32
+#define BD71828_BUCK1267_VOLTS		0x100
+#define BD71828_BUCK3_VOLTS		0x20
+#define BD71828_BUCK4_VOLTS		0x40
+#define BD71828_BUCK5_VOLTS		0x20
+#define BD71828_LDO_VOLTS		0x40
 /* LDO6 is fixed 1.8V voltage */
 #define BD71828_LDO_6_VOLTAGE		1800000
 
-- 
cgit v1.2.3


From 179d9ba5559a756f4322583388b3213fe4e391b0 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 24 May 2021 17:10:18 +0200
Subject: netfilter: nf_tables: fix table flag updates

The dormant flag need to be updated from the preparation phase,
otherwise, two consecutive requests to dorm a table in the same batch
might try to remove the same hooks twice, resulting in the following
warning:

 hook not found, pf 3 num 0
 WARNING: CPU: 0 PID: 334 at net/netfilter/core.c:480 __nf_unregister_net_hook+0x1eb/0x610 net/netfilter/core.c:480
 Modules linked in:
 CPU: 0 PID: 334 Comm: kworker/u4:5 Not tainted 5.12.0-syzkaller #0
 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
 Workqueue: netns cleanup_net
 RIP: 0010:__nf_unregister_net_hook+0x1eb/0x610 net/netfilter/core.c:480

This patch is a partial revert of 0ce7cf4127f1 ("netfilter: nftables:
update table flags from the commit phase") to restore the previous
behaviour.

However, there is still another problem: A batch containing a series of
dorm-wakeup-dorm table and vice-versa also trigger the warning above
since hook unregistration happens from the preparation phase, while hook
registration occurs from the commit phase.

To fix this problem, this patch adds two internal flags to annotate the
original dormant flag status which are __NFT_TABLE_F_WAS_DORMANT and
__NFT_TABLE_F_WAS_AWAKEN, to restore it from the abort path.

The __NFT_TABLE_F_UPDATE bitmask allows to handle the dormant flag update
with one single transaction.

Reported-by: syzbot+7ad5cd1615f2d89c6e7e@syzkaller.appspotmail.com
Fixes: 0ce7cf4127f1 ("netfilter: nftables: update table flags from the commit phase")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |  6 ----
 net/netfilter/nf_tables_api.c     | 59 ++++++++++++++++++++++++++-------------
 2 files changed, 40 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 27eeb613bb4e..0a5655e300b5 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1506,16 +1506,10 @@ struct nft_trans_chain {
 
 struct nft_trans_table {
 	bool				update;
-	u8				state;
-	u32				flags;
 };
 
 #define nft_trans_table_update(trans)	\
 	(((struct nft_trans_table *)trans->data)->update)
-#define nft_trans_table_state(trans)	\
-	(((struct nft_trans_table *)trans->data)->state)
-#define nft_trans_table_flags(trans)	\
-	(((struct nft_trans_table *)trans->data)->flags)
 
 struct nft_trans_elem {
 	struct nft_set			*set;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c34a3c0a0d9c..72bc759179ef 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -736,7 +736,8 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 		goto nla_put_failure;
 
 	if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) ||
-	    nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)) ||
+	    nla_put_be32(skb, NFTA_TABLE_FLAGS,
+			 htonl(table->flags & NFT_TABLE_F_MASK)) ||
 	    nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)) ||
 	    nla_put_be64(skb, NFTA_TABLE_HANDLE, cpu_to_be64(table->handle),
 			 NFTA_TABLE_PAD))
@@ -947,20 +948,22 @@ err_register_hooks:
 
 static void nf_tables_table_disable(struct net *net, struct nft_table *table)
 {
+	table->flags &= ~NFT_TABLE_F_DORMANT;
 	nft_table_disable(net, table, 0);
+	table->flags |= NFT_TABLE_F_DORMANT;
 }
 
-enum {
-	NFT_TABLE_STATE_UNCHANGED	= 0,
-	NFT_TABLE_STATE_DORMANT,
-	NFT_TABLE_STATE_WAKEUP
-};
+#define __NFT_TABLE_F_INTERNAL		(NFT_TABLE_F_MASK + 1)
+#define __NFT_TABLE_F_WAS_DORMANT	(__NFT_TABLE_F_INTERNAL << 0)
+#define __NFT_TABLE_F_WAS_AWAKEN	(__NFT_TABLE_F_INTERNAL << 1)
+#define __NFT_TABLE_F_UPDATE		(__NFT_TABLE_F_WAS_DORMANT | \
+					 __NFT_TABLE_F_WAS_AWAKEN)
 
 static int nf_tables_updtable(struct nft_ctx *ctx)
 {
 	struct nft_trans *trans;
 	u32 flags;
-	int ret = 0;
+	int ret;
 
 	if (!ctx->nla[NFTA_TABLE_FLAGS])
 		return 0;
@@ -985,21 +988,27 @@ static int nf_tables_updtable(struct nft_ctx *ctx)
 
 	if ((flags & NFT_TABLE_F_DORMANT) &&
 	    !(ctx->table->flags & NFT_TABLE_F_DORMANT)) {
-		nft_trans_table_state(trans) = NFT_TABLE_STATE_DORMANT;
+		ctx->table->flags |= NFT_TABLE_F_DORMANT;
+		if (!(ctx->table->flags & __NFT_TABLE_F_UPDATE))
+			ctx->table->flags |= __NFT_TABLE_F_WAS_AWAKEN;
 	} else if (!(flags & NFT_TABLE_F_DORMANT) &&
 		   ctx->table->flags & NFT_TABLE_F_DORMANT) {
-		ret = nf_tables_table_enable(ctx->net, ctx->table);
-		if (ret >= 0)
-			nft_trans_table_state(trans) = NFT_TABLE_STATE_WAKEUP;
+		ctx->table->flags &= ~NFT_TABLE_F_DORMANT;
+		if (!(ctx->table->flags & __NFT_TABLE_F_UPDATE)) {
+			ret = nf_tables_table_enable(ctx->net, ctx->table);
+			if (ret < 0)
+				goto err_register_hooks;
+
+			ctx->table->flags |= __NFT_TABLE_F_WAS_DORMANT;
+		}
 	}
-	if (ret < 0)
-		goto err;
 
-	nft_trans_table_flags(trans) = flags;
 	nft_trans_table_update(trans) = true;
 	nft_trans_commit_list_add_tail(ctx->net, trans);
+
 	return 0;
-err:
+
+err_register_hooks:
 	nft_trans_destroy(trans);
 	return ret;
 }
@@ -8556,10 +8565,14 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 		switch (trans->msg_type) {
 		case NFT_MSG_NEWTABLE:
 			if (nft_trans_table_update(trans)) {
-				if (nft_trans_table_state(trans) == NFT_TABLE_STATE_DORMANT)
+				if (!(trans->ctx.table->flags & __NFT_TABLE_F_UPDATE)) {
+					nft_trans_destroy(trans);
+					break;
+				}
+				if (trans->ctx.table->flags & NFT_TABLE_F_DORMANT)
 					nf_tables_table_disable(net, trans->ctx.table);
 
-				trans->ctx.table->flags = nft_trans_table_flags(trans);
+				trans->ctx.table->flags &= ~__NFT_TABLE_F_UPDATE;
 			} else {
 				nft_clear(net, trans->ctx.table);
 			}
@@ -8777,9 +8790,17 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 		switch (trans->msg_type) {
 		case NFT_MSG_NEWTABLE:
 			if (nft_trans_table_update(trans)) {
-				if (nft_trans_table_state(trans) == NFT_TABLE_STATE_WAKEUP)
+				if (!(trans->ctx.table->flags & __NFT_TABLE_F_UPDATE)) {
+					nft_trans_destroy(trans);
+					break;
+				}
+				if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_DORMANT) {
 					nf_tables_table_disable(net, trans->ctx.table);
-
+					trans->ctx.table->flags |= NFT_TABLE_F_DORMANT;
+				} else if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_AWAKEN) {
+					trans->ctx.table->flags &= ~NFT_TABLE_F_DORMANT;
+				}
+				trans->ctx.table->flags &= ~__NFT_TABLE_F_UPDATE;
 				nft_trans_destroy(trans);
 			} else {
 				list_del_rcu(&trans->ctx.table->list);
-- 
cgit v1.2.3


From 08b2b6fdf6b26032f025084ce2893924a0cdb4a2 Mon Sep 17 00:00:00 2001
From: Zhen Lei <thunder.leizhen@huawei.com>
Date: Mon, 24 May 2021 16:29:43 +0800
Subject: cgroup: fix spelling mistakes

Fix some spelling mistakes in comments:
hierarhcy ==> hierarchy
automtically ==> automatically
overriden ==> overridden
In absense of .. or ==> In absence of .. and
assocaited ==> associated
taget ==> target
initate ==> initiate
succeded ==> succeeded
curremt ==> current
udpated ==> updated

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup-defs.h | 6 +++---
 include/linux/cgroup.h      | 2 +-
 kernel/cgroup/cgroup-v1.c   | 2 +-
 kernel/cgroup/cgroup.c      | 8 ++++----
 kernel/cgroup/cpuset.c      | 2 +-
 kernel/cgroup/rdma.c        | 2 +-
 kernel/cgroup/rstat.c       | 2 +-
 7 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 559ee05f86b2..fb8f6d2cd104 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -232,7 +232,7 @@ struct css_set {
 	struct list_head task_iters;
 
 	/*
-	 * On the default hierarhcy, ->subsys[ssid] may point to a css
+	 * On the default hierarchy, ->subsys[ssid] may point to a css
 	 * attached to an ancestor instead of the cgroup this css_set is
 	 * associated with.  The following node is anchored at
 	 * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to
@@ -668,7 +668,7 @@ struct cgroup_subsys {
 	 */
 	bool threaded:1;
 
-	/* the following two fields are initialized automtically during boot */
+	/* the following two fields are initialized automatically during boot */
 	int id;
 	const char *name;
 
@@ -757,7 +757,7 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {}
  * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer.
  * On boot, sock_cgroup_data records the cgroup that the sock was created
  * in so that cgroup2 matches can be made; however, once either net_prio or
- * net_cls starts being used, the area is overriden to carry prioidx and/or
+ * net_cls starts being used, the area is overridden to carry prioidx and/or
  * classid.  The two modes are distinguished by whether the lowest bit is
  * set.  Clear bit indicates cgroup pointer while set bit prioidx and
  * classid.
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 4f2f79de083e..6bc9c76680b2 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -32,7 +32,7 @@ struct kernel_clone_args;
 #ifdef CONFIG_CGROUPS
 
 /*
- * All weight knobs on the default hierarhcy should use the following min,
+ * All weight knobs on the default hierarchy should use the following min,
  * default and max values.  The default value is the logarithmic center of
  * MIN and MAX and allows 100x to be expressed in both directions.
  */
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 391aa570369b..8190b6bfc978 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -1001,7 +1001,7 @@ static int check_cgroupfs_options(struct fs_context *fc)
 	ctx->subsys_mask &= enabled;
 
 	/*
-	 * In absense of 'none', 'name=' or subsystem name options,
+	 * In absence of 'none', 'name=' and subsystem name options,
 	 * let's default to 'all'.
 	 */
 	if (!ctx->subsys_mask && !ctx->none && !ctx->name)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index e7a9a2998245..21ecc6ee6a6d 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -468,7 +468,7 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
  * @cgrp: the cgroup of interest
  * @ss: the subsystem of interest
  *
- * Find and get @cgrp's css assocaited with @ss.  If the css doesn't exist
+ * Find and get @cgrp's css associated with @ss.  If the css doesn't exist
  * or is offline, %NULL is returned.
  */
 static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp,
@@ -1633,7 +1633,7 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
 
 /**
  * css_clear_dir - remove subsys files in a cgroup directory
- * @css: taget css
+ * @css: target css
  */
 static void css_clear_dir(struct cgroup_subsys_state *css)
 {
@@ -5350,7 +5350,7 @@ out_unlock:
 /*
  * This is called when the refcnt of a css is confirmed to be killed.
  * css_tryget_online() is now guaranteed to fail.  Tell the subsystem to
- * initate destruction and put the css ref from kill_css().
+ * initiate destruction and put the css ref from kill_css().
  */
 static void css_killed_work_fn(struct work_struct *work)
 {
@@ -6052,7 +6052,7 @@ out_revert:
  * @kargs: the arguments passed to create the child process
  *
  * This calls the cancel_fork() callbacks if a fork failed *after*
- * cgroup_can_fork() succeded and cleans up references we took to
+ * cgroup_can_fork() succeeded and cleans up references we took to
  * prepare a new css_set for the child process in cgroup_can_fork().
  */
 void cgroup_cancel_fork(struct task_struct *child,
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index a945504c0ae7..adb5190c4429 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -3376,7 +3376,7 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
 }
 
 /**
- * cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed
+ * cpuset_nodemask_valid_mems_allowed - check nodemask vs. current mems_allowed
  * @nodemask: the nodemask to be checked
  *
  * Are any of the nodes in the nodemask allowed in current->mems_allowed?
diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c
index ae042c347c64..3135406608c7 100644
--- a/kernel/cgroup/rdma.c
+++ b/kernel/cgroup/rdma.c
@@ -244,7 +244,7 @@ EXPORT_SYMBOL(rdmacg_uncharge);
  * This function follows charging resource in hierarchical way.
  * It will fail if the charge would cause the new value to exceed the
  * hierarchical limit.
- * Returns 0 if the charge succeded, otherwise -EAGAIN, -ENOMEM or -EINVAL.
+ * Returns 0 if the charge succeeded, otherwise -EAGAIN, -ENOMEM or -EINVAL.
  * Returns pointer to rdmacg for this resource when charging is successful.
  *
  * Charger needs to account resources on two criteria.
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 3a3fd2993a65..cee265cb535c 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -75,7 +75,7 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
  * @root: root of the tree to traversal
  * @cpu: target cpu
  *
- * Walks the udpated rstat_cpu tree on @cpu from @root.  %NULL @pos starts
+ * Walks the updated rstat_cpu tree on @cpu from @root.  %NULL @pos starts
  * the traversal and %NULL return indicates the end.  During traversal,
  * each returned cgroup is unlinked from the tree.  Must be called with the
  * matching cgroup_rstat_cpu_lock held.
-- 
cgit v1.2.3


From 1cb61759d40716643281b8e0f8c7afebc8699249 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Fri, 21 May 2021 09:26:10 +0200
Subject: init: verify that function is initcall_t at compile-time

In the spirit of making it hard to misuse an interface, add a
compile-time assertion in the CONFIG_HAVE_ARCH_PREL32_RELOCATIONS case
to verify the initcall function matches initcall_t, because the inline
asm bypasses any type-checking the compiler would otherwise do. This
will help developers catch incorrect API use in all configurations.

A recent example of this is:
https://lkml.kernel.org/r/20210514140015.2944744-1-arnd@kernel.org

Signed-off-by: Marco Elver <elver@google.com>
Reviewed-by: Miguel Ojeda <ojeda@kernel.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20210521072610.2880286-1-elver@google.com
---
 include/linux/init.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/init.h b/include/linux/init.h
index 045ad1650ed1..d82b4b2e1d25 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -242,7 +242,8 @@ extern bool initcall_debug;
 	asm(".section	\"" __sec "\", \"a\"		\n"	\
 	    __stringify(__name) ":			\n"	\
 	    ".long	" __stringify(__stub) " - .	\n"	\
-	    ".previous					\n");
+	    ".previous					\n");	\
+	static_assert(__same_type(initcall_t, &fn));
 #else
 #define ____define_initcall(fn, __unused, __name, __sec)	\
 	static initcall_t __name __used 			\
-- 
cgit v1.2.3


From a8b98c808eab3ec8f1b5a64be967b0f4af4cae43 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Mon, 24 May 2021 16:53:21 +0300
Subject: fanotify: fix permission model of unprivileged group

Reporting event->pid should depend on the privileges of the user that
initialized the group, not the privileges of the user reading the
events.

Use an internal group flag FANOTIFY_UNPRIV to record the fact that the
group was initialized by an unprivileged user.

To be on the safe side, the premissions to setup filesystem and mount
marks now require that both the user that initialized the group and
the user setting up the mark have CAP_SYS_ADMIN.

Link: https://lore.kernel.org/linux-fsdevel/CAOQ4uxiA77_P5vtv7e83g0+9d7B5W9ZTE4GfQEYbWmfT1rA=VA@mail.gmail.com/
Fixes: 7cea2a3c505e ("fanotify: support limited functionality for unprivileged users")
Cc: <Stable@vger.kernel.org> # v5.12+
Link: https://lore.kernel.org/r/20210524135321.2190062-1-amir73il@gmail.com
Reviewed-by: Matthew Bobrowski <repnop@google.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fanotify/fanotify_user.c | 30 ++++++++++++++++++++++++------
 fs/notify/fdinfo.c                 |  2 +-
 include/linux/fanotify.h           |  4 ++++
 3 files changed, 29 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 71fefb30e015..be5b6d2c01e7 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -424,11 +424,18 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	 * events generated by the listener process itself, without disclosing
 	 * the pids of other processes.
 	 */
-	if (!capable(CAP_SYS_ADMIN) &&
+	if (FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) &&
 	    task_tgid(current) != event->pid)
 		metadata.pid = 0;
 
-	if (path && path->mnt && path->dentry) {
+	/*
+	 * For now, fid mode is required for an unprivileged listener and
+	 * fid mode does not report fd in events.  Keep this check anyway
+	 * for safety in case fid mode requirement is relaxed in the future
+	 * to allow unprivileged listener to get events with no fd and no fid.
+	 */
+	if (!FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) &&
+	    path && path->mnt && path->dentry) {
 		fd = create_fd(group, path, &f);
 		if (fd < 0)
 			return fd;
@@ -1040,6 +1047,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	int f_flags, fd;
 	unsigned int fid_mode = flags & FANOTIFY_FID_BITS;
 	unsigned int class = flags & FANOTIFY_CLASS_BITS;
+	unsigned int internal_flags = 0;
 
 	pr_debug("%s: flags=%x event_f_flags=%x\n",
 		 __func__, flags, event_f_flags);
@@ -1053,6 +1061,13 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 		 */
 		if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || !fid_mode)
 			return -EPERM;
+
+		/*
+		 * Setting the internal flag FANOTIFY_UNPRIV on the group
+		 * prevents setting mount/filesystem marks on this group and
+		 * prevents reporting pid and open fd in events.
+		 */
+		internal_flags |= FANOTIFY_UNPRIV;
 	}
 
 #ifdef CONFIG_AUDITSYSCALL
@@ -1105,7 +1120,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 		goto out_destroy_group;
 	}
 
-	group->fanotify_data.flags = flags;
+	group->fanotify_data.flags = flags | internal_flags;
 	group->memcg = get_mem_cgroup_from_mm(current->mm);
 
 	group->fanotify_data.merge_hash = fanotify_alloc_merge_hash();
@@ -1305,11 +1320,13 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	group = f.file->private_data;
 
 	/*
-	 * An unprivileged user is not allowed to watch a mount point nor
-	 * a filesystem.
+	 * An unprivileged user is not allowed to setup mount nor filesystem
+	 * marks.  This also includes setting up such marks by a group that
+	 * was initialized by an unprivileged user.
 	 */
 	ret = -EPERM;
-	if (!capable(CAP_SYS_ADMIN) &&
+	if ((!capable(CAP_SYS_ADMIN) ||
+	     FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV)) &&
 	    mark_type != FAN_MARK_INODE)
 		goto fput_and_out;
 
@@ -1460,6 +1477,7 @@ static int __init fanotify_user_setup(void)
 	max_marks = clamp(max_marks, FANOTIFY_OLD_DEFAULT_MAX_MARKS,
 				     FANOTIFY_DEFAULT_MAX_USER_MARKS);
 
+	BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS);
 	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 10);
 	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9);
 
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index a712b2aaa9ac..57f0d5d9f934 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -144,7 +144,7 @@ void fanotify_show_fdinfo(struct seq_file *m, struct file *f)
 	struct fsnotify_group *group = f->private_data;
 
 	seq_printf(m, "fanotify flags:%x event-flags:%x\n",
-		   group->fanotify_data.flags,
+		   group->fanotify_data.flags & FANOTIFY_INIT_FLAGS,
 		   group->fanotify_data.f_flags);
 
 	show_fdinfo(m, f, fanotify_fdinfo);
diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index bad41bcb25df..a16dbeced152 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -51,6 +51,10 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */
 #define FANOTIFY_INIT_FLAGS	(FANOTIFY_ADMIN_INIT_FLAGS | \
 				 FANOTIFY_USER_INIT_FLAGS)
 
+/* Internal group flags */
+#define FANOTIFY_UNPRIV		0x80000000
+#define FANOTIFY_INTERNAL_GROUP_FLAGS	(FANOTIFY_UNPRIV)
+
 #define FANOTIFY_MARK_TYPE_BITS	(FAN_MARK_INODE | FAN_MARK_MOUNT | \
 				 FAN_MARK_FILESYSTEM)
 
-- 
cgit v1.2.3


From 9453d45ecb6c2199d72e73c993e9d98677a2801b Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@nvidia.com>
Date: Tue, 25 May 2021 16:21:52 +0300
Subject: net: zero-initialize tc skb extension on allocation

Function skb_ext_add() doesn't initialize created skb extension with any
value and leaves it up to the user. However, since extension of type
TC_SKB_EXT originally contained only single value tc_skb_ext->chain its
users used to just assign the chain value without setting whole extension
memory to zero first. This assumption changed when TC_SKB_EXT extension was
extended with additional fields but not all users were updated to
initialize the new fields which leads to use of uninitialized memory
afterwards. UBSAN log:

[  778.299821] UBSAN: invalid-load in net/openvswitch/flow.c:899:28
[  778.301495] load of value 107 is not a valid value for type '_Bool'
[  778.303215] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.12.0-rc7+ #2
[  778.304933] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[  778.307901] Call Trace:
[  778.308680]  <IRQ>
[  778.309358]  dump_stack+0xbb/0x107
[  778.310307]  ubsan_epilogue+0x5/0x40
[  778.311167]  __ubsan_handle_load_invalid_value.cold+0x43/0x48
[  778.312454]  ? memset+0x20/0x40
[  778.313230]  ovs_flow_key_extract.cold+0xf/0x14 [openvswitch]
[  778.314532]  ovs_vport_receive+0x19e/0x2e0 [openvswitch]
[  778.315749]  ? ovs_vport_find_upcall_portid+0x330/0x330 [openvswitch]
[  778.317188]  ? create_prof_cpu_mask+0x20/0x20
[  778.318220]  ? arch_stack_walk+0x82/0xf0
[  778.319153]  ? secondary_startup_64_no_verify+0xb0/0xbb
[  778.320399]  ? stack_trace_save+0x91/0xc0
[  778.321362]  ? stack_trace_consume_entry+0x160/0x160
[  778.322517]  ? lock_release+0x52e/0x760
[  778.323444]  netdev_frame_hook+0x323/0x610 [openvswitch]
[  778.324668]  ? ovs_netdev_get_vport+0xe0/0xe0 [openvswitch]
[  778.325950]  __netif_receive_skb_core+0x771/0x2db0
[  778.327067]  ? lock_downgrade+0x6e0/0x6f0
[  778.328021]  ? lock_acquire+0x565/0x720
[  778.328940]  ? generic_xdp_tx+0x4f0/0x4f0
[  778.329902]  ? inet_gro_receive+0x2a7/0x10a0
[  778.330914]  ? lock_downgrade+0x6f0/0x6f0
[  778.331867]  ? udp4_gro_receive+0x4c4/0x13e0
[  778.332876]  ? lock_release+0x52e/0x760
[  778.333808]  ? dev_gro_receive+0xcc8/0x2380
[  778.334810]  ? lock_downgrade+0x6f0/0x6f0
[  778.335769]  __netif_receive_skb_list_core+0x295/0x820
[  778.336955]  ? process_backlog+0x780/0x780
[  778.337941]  ? mlx5e_rep_tc_netdevice_event_unregister+0x20/0x20 [mlx5_core]
[  778.339613]  ? seqcount_lockdep_reader_access.constprop.0+0xa7/0xc0
[  778.341033]  ? kvm_clock_get_cycles+0x14/0x20
[  778.342072]  netif_receive_skb_list_internal+0x5f5/0xcb0
[  778.343288]  ? __kasan_kmalloc+0x7a/0x90
[  778.344234]  ? mlx5e_handle_rx_cqe_mpwrq+0x9e0/0x9e0 [mlx5_core]
[  778.345676]  ? mlx5e_xmit_xdp_frame_mpwqe+0x14d0/0x14d0 [mlx5_core]
[  778.347140]  ? __netif_receive_skb_list_core+0x820/0x820
[  778.348351]  ? mlx5e_post_rx_mpwqes+0xa6/0x25d0 [mlx5_core]
[  778.349688]  ? napi_gro_flush+0x26c/0x3c0
[  778.350641]  napi_complete_done+0x188/0x6b0
[  778.351627]  mlx5e_napi_poll+0x373/0x1b80 [mlx5_core]
[  778.352853]  __napi_poll+0x9f/0x510
[  778.353704]  ? mlx5_flow_namespace_set_mode+0x260/0x260 [mlx5_core]
[  778.355158]  net_rx_action+0x34c/0xa40
[  778.356060]  ? napi_threaded_poll+0x3d0/0x3d0
[  778.357083]  ? sched_clock_cpu+0x18/0x190
[  778.358041]  ? __common_interrupt+0x8e/0x1a0
[  778.359045]  __do_softirq+0x1ce/0x984
[  778.359938]  __irq_exit_rcu+0x137/0x1d0
[  778.360865]  irq_exit_rcu+0xa/0x20
[  778.361708]  common_interrupt+0x80/0xa0
[  778.362640]  </IRQ>
[  778.363212]  asm_common_interrupt+0x1e/0x40
[  778.364204] RIP: 0010:native_safe_halt+0xe/0x10
[  778.365273] Code: 4f ff ff ff 4c 89 e7 e8 50 3f 40 fe e9 dc fe ff ff 48 89 df e8 43 3f 40 fe eb 90 cc e9 07 00 00 00 0f 00 2d 74 05 62 00 fb f4 <c3> 90 e9 07 00 00 00 0f 00 2d 64 05 62 00 f4 c3 cc cc 0f 1f 44 00
[  778.369355] RSP: 0018:ffffffff84407e48 EFLAGS: 00000246
[  778.370570] RAX: ffff88842de46a80 RBX: ffffffff84425840 RCX: ffffffff83418468
[  778.372143] RDX: 000000000026f1da RSI: 0000000000000004 RDI: ffffffff8343af5e
[  778.373722] RBP: fffffbfff0884b08 R08: 0000000000000000 R09: ffff88842de46bcb
[  778.375292] R10: ffffed1085bc8d79 R11: 0000000000000001 R12: 0000000000000000
[  778.376860] R13: ffffffff851124a0 R14: 0000000000000000 R15: dffffc0000000000
[  778.378491]  ? rcu_eqs_enter.constprop.0+0xb8/0xe0
[  778.379606]  ? default_idle_call+0x5e/0xe0
[  778.380578]  default_idle+0xa/0x10
[  778.381406]  default_idle_call+0x96/0xe0
[  778.382350]  do_idle+0x3d4/0x550
[  778.383153]  ? arch_cpu_idle_exit+0x40/0x40
[  778.384143]  cpu_startup_entry+0x19/0x20
[  778.385078]  start_kernel+0x3c7/0x3e5
[  778.385978]  secondary_startup_64_no_verify+0xb0/0xbb

Fix the issue by providing new function tc_skb_ext_alloc() that allocates
tc skb extension and initializes its memory to 0 before returning it to the
caller. Change all existing users to use new API instead of calling
skb_ext_add() directly.

Fixes: 038ebb1a713d ("net/sched: act_ct: fix miss set mru for ovs after defrag in act_ct")
Fixes: d29334c15d33 ("net/sched: act_api: fix miss set post_ct for ovs after do conntrack in act_ct")
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Acked-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c     |  2 +-
 include/net/pkt_cls.h                               | 11 +++++++++++
 net/sched/cls_api.c                                 |  2 +-
 4 files changed, 14 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index 6cdc52d50a48..311382261840 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -626,7 +626,7 @@ static bool mlx5e_restore_skb(struct sk_buff *skb, u32 chain, u32 reg_c1,
 		struct mlx5_eswitch *esw;
 		u32 zone_restore_id;
 
-		tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT);
+		tc_skb_ext = tc_skb_ext_alloc(skb);
 		if (!tc_skb_ext) {
 			WARN_ON(1);
 			return false;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index bccdb43a880b..2c776e7a7692 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -5090,7 +5090,7 @@ bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe,
 
 	if (mapped_obj.type == MLX5_MAPPED_OBJ_CHAIN) {
 		chain = mapped_obj.chain;
-		tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT);
+		tc_skb_ext = tc_skb_ext_alloc(skb);
 		if (WARN_ON(!tc_skb_ext))
 			return false;
 
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 255e4f4b521f..ec7823921bd2 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -709,6 +709,17 @@ tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common,
 		cls_common->extack = extack;
 }
 
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb)
+{
+	struct tc_skb_ext *tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT);
+
+	if (tc_skb_ext)
+		memset(tc_skb_ext, 0, sizeof(*tc_skb_ext));
+	return tc_skb_ext;
+}
+#endif
+
 enum tc_matchall_command {
 	TC_CLSMATCHALL_REPLACE,
 	TC_CLSMATCHALL_DESTROY,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 40fbea626dfd..279f9e2a2319 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1624,7 +1624,7 @@ int tcf_classify_ingress(struct sk_buff *skb,
 
 	/* If we missed on some chain */
 	if (ret == TC_ACT_UNSPEC && last_executed_chain) {
-		ext = skb_ext_add(skb, TC_SKB_EXT);
+		ext = tc_skb_ext_alloc(skb);
 		if (WARN_ON_ONCE(!ext))
 			return TC_ACT_SHOT;
 		ext->chain = last_executed_chain;
-- 
cgit v1.2.3


From 85aabbd7b315c65673084b6227bee92c00405239 Mon Sep 17 00:00:00 2001
From: Jean-Philippe Brucker <jean-philippe@linaro.org>
Date: Mon, 10 May 2021 19:31:30 +0200
Subject: PCI/MSI: Fix MSIs for generic hosts that use device-tree's "msi-map"

Since commit 9ec37efb8783 ("PCI/MSI: Make pci_host_common_probe() declare
its reliance on MSI domains"), platforms that rely on the "msi-map"
device-tree property don't get MSIs anymore.

On the Arm Fast Model for example [1], the host bridge doesn't have a
"msi-parent" property since it doesn't itself generate MSIs, and so doesn't
get a MSI domain. It has an "msi-map" property instead to describe MSI
controllers of child devices. As a result, due to the new msi_domain check
in pci_register_host_bridge(), the whole bus gets PCI_BUS_FLAGS_NO_MSI.

Check whether the root complex has an "msi-map" property before giving
up on MSIs.

[1] arch/arm64/boot/dts/arm/fvp-base-revc.dts

Fixes: 9ec37efb8783 ("PCI/MSI: Make pci_host_common_probe() declare its reliance on MSI domains")
Link: https://lore.kernel.org/r/20210510173129.750496-1-jean-philippe@linaro.org
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Marc Zyngier <maz@kernel.org>
---
 drivers/pci/of.c    | 7 +++++++
 drivers/pci/probe.c | 3 ++-
 include/linux/pci.h | 2 ++
 3 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index da5b414d585a..85dcb7097da4 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -103,6 +103,13 @@ struct irq_domain *pci_host_bridge_of_msi_domain(struct pci_bus *bus)
 #endif
 }
 
+bool pci_host_of_has_msi_map(struct device *dev)
+{
+	if (dev && dev->of_node)
+		return of_get_property(dev->of_node, "msi-map", NULL);
+	return false;
+}
+
 static inline int __of_pci_pci_compare(struct device_node *node,
 				       unsigned int data)
 {
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 3a62d09b8869..275204646c68 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -925,7 +925,8 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 	device_enable_async_suspend(bus->bridge);
 	pci_set_bus_of_node(bus);
 	pci_set_bus_msi_domain(bus);
-	if (bridge->msi_domain && !dev_get_msi_domain(&bus->dev))
+	if (bridge->msi_domain && !dev_get_msi_domain(&bus->dev) &&
+	    !pci_host_of_has_msi_map(parent))
 		bus->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
 
 	if (!parent)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c20211e59a57..24306504226a 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2344,6 +2344,7 @@ int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off,
 struct device_node;
 struct irq_domain;
 struct irq_domain *pci_host_bridge_of_msi_domain(struct pci_bus *bus);
+bool pci_host_of_has_msi_map(struct device *dev);
 
 /* Arch may override this (weak) */
 struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus);
@@ -2351,6 +2352,7 @@ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus);
 #else	/* CONFIG_OF */
 static inline struct irq_domain *
 pci_host_bridge_of_msi_domain(struct pci_bus *bus) { return NULL; }
+static inline bool pci_host_of_has_msi_map(struct device *dev) { return false; }
 #endif  /* CONFIG_OF */
 
 static inline struct device_node *
-- 
cgit v1.2.3


From e86be3a04bc4aeaf12f93af35f08f8d4385bcd98 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Tue, 25 May 2021 18:43:38 -0400
Subject: SUNRPC: More fixes for backlog congestion

Ensure that we fix the XPRT_CONGESTED starvation issue for RDMA as well
as socket based transports.
Ensure we always initialise the request after waking up from the backlog
list.

Fixes: e877a88d1f06 ("SUNRPC in case of backlog, hand free slots directly to waiting task")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/xprt.h     |  2 ++
 net/sunrpc/xprt.c               | 58 ++++++++++++++++++++---------------------
 net/sunrpc/xprtrdma/transport.c | 12 ++++-----
 net/sunrpc/xprtrdma/verbs.c     | 18 ++++++++++---
 net/sunrpc/xprtrdma/xprt_rdma.h |  1 +
 5 files changed, 52 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index d81fe8b364d0..61b622e334ee 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -368,6 +368,8 @@ struct rpc_xprt *	xprt_alloc(struct net *net, size_t size,
 				unsigned int num_prealloc,
 				unsigned int max_req);
 void			xprt_free(struct rpc_xprt *);
+void			xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task);
+bool			xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req);
 
 static inline int
 xprt_enable_swap(struct rpc_xprt *xprt)
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 5b3981fd3783..3509a7f139b9 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1607,11 +1607,18 @@ xprt_transmit(struct rpc_task *task)
 	spin_unlock(&xprt->queue_lock);
 }
 
-static void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task)
+static void xprt_complete_request_init(struct rpc_task *task)
+{
+	if (task->tk_rqstp)
+		xprt_request_init(task);
+}
+
+void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task)
 {
 	set_bit(XPRT_CONGESTED, &xprt->state);
-	rpc_sleep_on(&xprt->backlog, task, NULL);
+	rpc_sleep_on(&xprt->backlog, task, xprt_complete_request_init);
 }
+EXPORT_SYMBOL_GPL(xprt_add_backlog);
 
 static bool __xprt_set_rq(struct rpc_task *task, void *data)
 {
@@ -1619,14 +1626,13 @@ static bool __xprt_set_rq(struct rpc_task *task, void *data)
 
 	if (task->tk_rqstp == NULL) {
 		memset(req, 0, sizeof(*req));	/* mark unused */
-		task->tk_status = -EAGAIN;
 		task->tk_rqstp = req;
 		return true;
 	}
 	return false;
 }
 
-static bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req)
+bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req)
 {
 	if (rpc_wake_up_first(&xprt->backlog, __xprt_set_rq, req) == NULL) {
 		clear_bit(XPRT_CONGESTED, &xprt->state);
@@ -1634,6 +1640,7 @@ static bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req)
 	}
 	return true;
 }
+EXPORT_SYMBOL_GPL(xprt_wake_up_backlog);
 
 static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task)
 {
@@ -1643,7 +1650,7 @@ static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task
 		goto out;
 	spin_lock(&xprt->reserve_lock);
 	if (test_bit(XPRT_CONGESTED, &xprt->state)) {
-		rpc_sleep_on(&xprt->backlog, task, NULL);
+		xprt_add_backlog(xprt, task);
 		ret = true;
 	}
 	spin_unlock(&xprt->reserve_lock);
@@ -1812,10 +1819,6 @@ xprt_request_init(struct rpc_task *task)
 	struct rpc_xprt *xprt = task->tk_xprt;
 	struct rpc_rqst	*req = task->tk_rqstp;
 
-	if (req->rq_task)
-		/* Already initialized */
-		return;
-
 	req->rq_task	= task;
 	req->rq_xprt    = xprt;
 	req->rq_buffer  = NULL;
@@ -1876,10 +1879,8 @@ void xprt_retry_reserve(struct rpc_task *task)
 	struct rpc_xprt *xprt = task->tk_xprt;
 
 	task->tk_status = 0;
-	if (task->tk_rqstp != NULL) {
-		xprt_request_init(task);
+	if (task->tk_rqstp != NULL)
 		return;
-	}
 
 	task->tk_status = -EAGAIN;
 	xprt_do_reserve(xprt, task);
@@ -1904,24 +1905,21 @@ void xprt_release(struct rpc_task *task)
 	}
 
 	xprt = req->rq_xprt;
-	if (xprt) {
-		xprt_request_dequeue_xprt(task);
-		spin_lock(&xprt->transport_lock);
-		xprt->ops->release_xprt(xprt, task);
-		if (xprt->ops->release_request)
-			xprt->ops->release_request(task);
-		xprt_schedule_autodisconnect(xprt);
-		spin_unlock(&xprt->transport_lock);
-		if (req->rq_buffer)
-			xprt->ops->buf_free(task);
-		xdr_free_bvec(&req->rq_rcv_buf);
-		xdr_free_bvec(&req->rq_snd_buf);
-		if (req->rq_cred != NULL)
-			put_rpccred(req->rq_cred);
-		if (req->rq_release_snd_buf)
-			req->rq_release_snd_buf(req);
-	} else
-		xprt = task->tk_xprt;
+	xprt_request_dequeue_xprt(task);
+	spin_lock(&xprt->transport_lock);
+	xprt->ops->release_xprt(xprt, task);
+	if (xprt->ops->release_request)
+		xprt->ops->release_request(task);
+	xprt_schedule_autodisconnect(xprt);
+	spin_unlock(&xprt->transport_lock);
+	if (req->rq_buffer)
+		xprt->ops->buf_free(task);
+	xdr_free_bvec(&req->rq_rcv_buf);
+	xdr_free_bvec(&req->rq_snd_buf);
+	if (req->rq_cred != NULL)
+		put_rpccred(req->rq_cred);
+	if (req->rq_release_snd_buf)
+		req->rq_release_snd_buf(req);
 
 	task->tk_rqstp = NULL;
 	if (likely(!bc_prealloc(req)))
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 09953597d055..19a49d26b1e4 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -520,9 +520,8 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task)
 	return;
 
 out_sleep:
-	set_bit(XPRT_CONGESTED, &xprt->state);
-	rpc_sleep_on(&xprt->backlog, task, NULL);
 	task->tk_status = -EAGAIN;
+	xprt_add_backlog(xprt, task);
 }
 
 /**
@@ -537,10 +536,11 @@ xprt_rdma_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *rqst)
 	struct rpcrdma_xprt *r_xprt =
 		container_of(xprt, struct rpcrdma_xprt, rx_xprt);
 
-	memset(rqst, 0, sizeof(*rqst));
-	rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst));
-	if (unlikely(!rpc_wake_up_next(&xprt->backlog)))
-		clear_bit(XPRT_CONGESTED, &xprt->state);
+	rpcrdma_reply_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst));
+	if (!xprt_wake_up_backlog(xprt, rqst)) {
+		memset(rqst, 0, sizeof(*rqst));
+		rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst));
+	}
 }
 
 static bool rpcrdma_check_regbuf(struct rpcrdma_xprt *r_xprt,
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 1e965a380896..649c23518ec0 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1200,6 +1200,20 @@ rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt)
 	return mr;
 }
 
+/**
+ * rpcrdma_reply_put - Put reply buffers back into pool
+ * @buffers: buffer pool
+ * @req: object to return
+ *
+ */
+void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req)
+{
+	if (req->rl_reply) {
+		rpcrdma_rep_put(buffers, req->rl_reply);
+		req->rl_reply = NULL;
+	}
+}
+
 /**
  * rpcrdma_buffer_get - Get a request buffer
  * @buffers: Buffer pool from which to obtain a buffer
@@ -1228,9 +1242,7 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
  */
 void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req)
 {
-	if (req->rl_reply)
-		rpcrdma_rep_put(buffers, req->rl_reply);
-	req->rl_reply = NULL;
+	rpcrdma_reply_put(buffers, req);
 
 	spin_lock(&buffers->rb_lock);
 	list_add(&req->rl_list, &buffers->rb_send_bufs);
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 436ad7312614..5d231d94e944 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -479,6 +479,7 @@ struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *);
 void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers,
 			struct rpcrdma_req *req);
 void rpcrdma_rep_put(struct rpcrdma_buffer *buf, struct rpcrdma_rep *rep);
+void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req);
 
 bool rpcrdma_regbuf_realloc(struct rpcrdma_regbuf *rb, size_t size,
 			    gfp_t flags);
-- 
cgit v1.2.3


From 62f3415db237b8d2aa9a804ff84ce2efa87df179 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 26 May 2021 11:46:17 -0700
Subject: net: phy: Document phydev::dev_flags bits allocation

Document the phydev::dev_flags bit allocation to allow bits 15:0 to
define PHY driver specific behavior, bits 23:16 to be reserved for now,
and bits 31:24 to hold generic PHY driver flags.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/20210526184617.3105012-1-f.fainelli@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/phy.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 60d2b26026a2..852743f07e3e 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -496,6 +496,11 @@ struct macsec_ops;
  * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY
  * @state: State of the PHY for management purposes
  * @dev_flags: Device-specific flags used by the PHY driver.
+ *		Bits [15:0] are free to use by the PHY driver to communicate
+ *			    driver specific behavior.
+ *		Bits [23:16] are currently reserved for future use.
+ *		Bits [31:24] are reserved for defining generic
+ *			     PHY driver behavior.
  * @irq: IRQ number of the PHY's interrupt (-1 if none)
  * @phy_timer: The timer for handling the state machine
  * @phylink: Pointer to phylink instance for this PHY
-- 
cgit v1.2.3


From 6bd5b743686243dae7351d5dcceeb7f171201bb4 Mon Sep 17 00:00:00 2001
From: Wanpeng Li <wanpengli@tencent.com>
Date: Tue, 18 May 2021 05:00:31 -0700
Subject: KVM: PPC: exit halt polling on need_resched()

This is inspired by commit 262de4102c7bb8 (kvm: exit halt polling on
need_resched() as well). Due to PPC implements an arch specific halt
polling logic, we have to the need_resched() check there as well. This
patch adds a helper function that can be shared between book3s and generic
halt-polling loops.

Reviewed-by: David Matlack <dmatlack@google.com>
Reviewed-by: Venkatesh Srinivas <venkateshs@chromium.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Venkatesh Srinivas <venkateshs@chromium.org>
Cc: Jim Mattson <jmattson@google.com>
Cc: David Matlack <dmatlack@google.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Message-Id: <1621339235-11131-1-git-send-email-wanpengli@tencent.com>
[Make the function inline. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/powerpc/kvm/book3s_hv.c | 2 +-
 include/linux/kvm_host.h     | 6 ++++++
 virt/kvm/kvm_main.c          | 3 +--
 3 files changed, 8 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 28a80d240b76..7360350e66ff 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3936,7 +3936,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 				break;
 			}
 			cur = ktime_get();
-		} while (single_task_running() && ktime_before(cur, stop));
+		} while (kvm_vcpu_can_poll(cur, stop));
 
 		spin_lock(&vc->lock);
 		vc->vcore_state = VCORE_INACTIVE;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2f34487e21f2..5d4b96b36ec0 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -10,6 +10,7 @@
 #include <linux/spinlock.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
+#include <linux/sched/stat.h>
 #include <linux/bug.h>
 #include <linux/minmax.h>
 #include <linux/mm.h>
@@ -265,6 +266,11 @@ static inline bool kvm_vcpu_mapped(struct kvm_host_map *map)
 	return !!map->hva;
 }
 
+static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop)
+{
+	return single_task_running() && !need_resched() && ktime_before(cur, stop);
+}
+
 /*
  * Sometimes a large or cross-page mmio needs to be broken up into separate
  * exits for userspace servicing.
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 6b4feb92dc79..5f40725144f5 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2973,8 +2973,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 				goto out;
 			}
 			poll_end = cur = ktime_get();
-		} while (single_task_running() && !need_resched() &&
-			 ktime_before(cur, stop));
+		} while (kvm_vcpu_can_poll(cur, stop));
 	}
 
 	prepare_to_rcuwait(&vcpu->wait);
-- 
cgit v1.2.3


From fb1070d18edb37daf3979662975bc54625a19953 Mon Sep 17 00:00:00 2001
From: Joe Richey <joerichey@google.com>
Date: Fri, 21 May 2021 01:58:43 -0700
Subject: KVM: X86: Use _BITUL() macro in UAPI headers

Replace BIT() in KVM's UPAI header with _BITUL(). BIT() is not defined
in the UAPI headers and its usage may cause userspace build errors.

Fixes: fb04a1eddb1a ("KVM: X86: Implement ring-based dirty memory tracking")
Signed-off-by: Joe Richey <joerichey@google.com>
Message-Id: <20210521085849.37676-3-joerichey94@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/uapi/linux/kvm.h       | 5 +++--
 tools/include/uapi/linux/kvm.h | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 3fd9a7e9d90c..79d9c44d1ad7 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -8,6 +8,7 @@
  * Note: you must update KVM_API_VERSION if you change this interface.
  */
 
+#include <linux/const.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
 #include <linux/ioctl.h>
@@ -1879,8 +1880,8 @@ struct kvm_hyperv_eventfd {
  * conversion after harvesting an entry.  Also, it must not skip any
  * dirty bits, so that dirty bits are always harvested in sequence.
  */
-#define KVM_DIRTY_GFN_F_DIRTY           BIT(0)
-#define KVM_DIRTY_GFN_F_RESET           BIT(1)
+#define KVM_DIRTY_GFN_F_DIRTY           _BITUL(0)
+#define KVM_DIRTY_GFN_F_RESET           _BITUL(1)
 #define KVM_DIRTY_GFN_F_MASK            0x3
 
 /*
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f6afee209620..26e6d94d64ed 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -8,6 +8,7 @@
  * Note: you must update KVM_API_VERSION if you change this interface.
  */
 
+#include <linux/const.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
 #include <linux/ioctl.h>
@@ -1834,8 +1835,8 @@ struct kvm_hyperv_eventfd {
  * conversion after harvesting an entry.  Also, it must not skip any
  * dirty bits, so that dirty bits are always harvested in sequence.
  */
-#define KVM_DIRTY_GFN_F_DIRTY           BIT(0)
-#define KVM_DIRTY_GFN_F_RESET           BIT(1)
+#define KVM_DIRTY_GFN_F_DIRTY           _BITUL(0)
+#define KVM_DIRTY_GFN_F_RESET           _BITUL(1)
 #define KVM_DIRTY_GFN_F_MASK            0x3
 
 /*
-- 
cgit v1.2.3


From 084071d5e9226add45a6031928bf10e6afc855fd Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Tue, 25 May 2021 10:41:17 -0300
Subject: KVM: rename KVM_REQ_PENDING_TIMER to KVM_REQ_UNBLOCK

KVM_REQ_UNBLOCK will be used to exit a vcpu from
its inner vcpu halt emulation loop.

Rename KVM_REQ_PENDING_TIMER to KVM_REQ_UNBLOCK, switch
PowerPC to arch specific request bit.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Message-Id: <20210525134321.303768132@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/vcpu-requests.rst | 8 +++++---
 arch/powerpc/include/asm/kvm_host.h      | 1 +
 arch/x86/kvm/lapic.c                     | 2 +-
 arch/x86/kvm/x86.c                       | 2 +-
 include/linux/kvm_host.h                 | 2 +-
 virt/kvm/kvm_main.c                      | 2 ++
 6 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/Documentation/virt/kvm/vcpu-requests.rst b/Documentation/virt/kvm/vcpu-requests.rst
index 5feb3706a7ae..af1b37441e0a 100644
--- a/Documentation/virt/kvm/vcpu-requests.rst
+++ b/Documentation/virt/kvm/vcpu-requests.rst
@@ -118,10 +118,12 @@ KVM_REQ_MMU_RELOAD
   necessary to inform each VCPU to completely refresh the tables.  This
   request is used for that.
 
-KVM_REQ_PENDING_TIMER
+KVM_REQ_UNBLOCK
 
-  This request may be made from a timer handler run on the host on behalf
-  of a VCPU.  It informs the VCPU thread to inject a timer interrupt.
+  This request informs the vCPU to exit kvm_vcpu_block.  It is used for
+  example from timer handlers that run on the host on behalf of a vCPU,
+  or in order to update the interrupt routing and ensure that assigned
+  devices will wake up the vCPU.
 
 KVM_REQ_UNHALT
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 1e83359f286b..7f2e90db2050 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -51,6 +51,7 @@
 /* PPC-specific vcpu->requests bit members */
 #define KVM_REQ_WATCHDOG	KVM_ARCH_REQ(0)
 #define KVM_REQ_EPR_EXIT	KVM_ARCH_REQ(1)
+#define KVM_REQ_PENDING_TIMER	KVM_ARCH_REQ(2)
 
 #include <linux/mmu_notifier.h>
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 5d91f2367c31..8120e8614b92 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1669,7 +1669,7 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn)
 	}
 
 	atomic_inc(&apic->lapic_timer.pending);
-	kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+	kvm_make_request(KVM_REQ_UNBLOCK, vcpu);
 	if (from_timer_fn)
 		kvm_vcpu_kick(vcpu);
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 98538b1cb453..fe464b66898f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9501,7 +9501,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 		if (r <= 0)
 			break;
 
-		kvm_clear_request(KVM_REQ_PENDING_TIMER, vcpu);
+		kvm_clear_request(KVM_REQ_UNBLOCK, vcpu);
 		if (kvm_cpu_has_pending_timer(vcpu))
 			kvm_inject_pending_timer_irqs(vcpu);
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 5d4b96b36ec0..76102efbf079 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -147,7 +147,7 @@ static inline bool is_error_page(struct page *page)
  */
 #define KVM_REQ_TLB_FLUSH         (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_MMU_RELOAD        (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_PENDING_TIMER     2
+#define KVM_REQ_UNBLOCK           2
 #define KVM_REQ_UNHALT            3
 #define KVM_REQUEST_ARCH_BASE     8
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5f40725144f5..37a2d500a148 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2929,6 +2929,8 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu)
 		goto out;
 	if (signal_pending(current))
 		goto out;
+	if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu))
+		goto out;
 
 	ret = 0;
 out:
-- 
cgit v1.2.3


From f268c3737ecaefcfeecfb4cb5e44958a8976f067 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Thu, 27 May 2021 13:34:41 +0200
Subject: tick/nohz: Only check for RCU deferred wakeup on user/guest entry
 when needed

Checking for and processing RCU-nocb deferred wakeup upon user/guest
entry is only relevant when nohz_full runs on the local CPU, otherwise
the periodic tick should take care of it.

Make sure we don't needlessly pollute these fast-paths as a -3%
performance regression on a will-it-scale.per_process_ops has been
reported so far.

Fixes: 47b8ff194c1f (entry: Explicitly flush pending rcuog wakeup before last rescheduling point)
Fixes: 4ae7dc97f726 (entry/kvm: Explicitly flush pending rcuog wakeup before last rescheduling point)
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20210527113441.465489-1-frederic@kernel.org
---
 include/linux/entry-kvm.h | 3 ++-
 include/linux/tick.h      | 7 +++++++
 kernel/entry/common.c     | 5 +++--
 kernel/time/tick-sched.c  | 1 +
 4 files changed, 13 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h
index 8b2b1d68b954..136b8d97d8c0 100644
--- a/include/linux/entry-kvm.h
+++ b/include/linux/entry-kvm.h
@@ -3,6 +3,7 @@
 #define __LINUX_ENTRYKVM_H
 
 #include <linux/entry-common.h>
+#include <linux/tick.h>
 
 /* Transfer to guest mode work */
 #ifdef CONFIG_KVM_XFER_TO_GUEST_WORK
@@ -57,7 +58,7 @@ int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu);
 static inline void xfer_to_guest_mode_prepare(void)
 {
 	lockdep_assert_irqs_disabled();
-	rcu_nocb_flush_deferred_wakeup();
+	tick_nohz_user_enter_prepare();
 }
 
 /**
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 7340613c7eff..1a0ff88fa107 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -11,6 +11,7 @@
 #include <linux/context_tracking_state.h>
 #include <linux/cpumask.h>
 #include <linux/sched.h>
+#include <linux/rcupdate.h>
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern void __init tick_init(void);
@@ -300,4 +301,10 @@ static inline void tick_nohz_task_switch(void)
 		__tick_nohz_task_switch();
 }
 
+static inline void tick_nohz_user_enter_prepare(void)
+{
+	if (tick_nohz_full_cpu(smp_processor_id()))
+		rcu_nocb_flush_deferred_wakeup();
+}
+
 #endif
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index a0b3b04fb596..bf16395b9e13 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -5,6 +5,7 @@
 #include <linux/highmem.h>
 #include <linux/livepatch.h>
 #include <linux/audit.h>
+#include <linux/tick.h>
 
 #include "common.h"
 
@@ -186,7 +187,7 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 		local_irq_disable_exit_to_user();
 
 		/* Check if any of the above work has queued a deferred wakeup */
-		rcu_nocb_flush_deferred_wakeup();
+		tick_nohz_user_enter_prepare();
 
 		ti_work = READ_ONCE(current_thread_info()->flags);
 	}
@@ -202,7 +203,7 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
 	lockdep_assert_irqs_disabled();
 
 	/* Flush pending rcuog wakeup before the last need_resched() check */
-	rcu_nocb_flush_deferred_wakeup();
+	tick_nohz_user_enter_prepare();
 
 	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
 		ti_work = exit_to_user_mode_loop(regs, ti_work);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 828b091501ca..6784f27a3099 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -230,6 +230,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 
 #ifdef CONFIG_NO_HZ_FULL
 cpumask_var_t tick_nohz_full_mask;
+EXPORT_SYMBOL_GPL(tick_nohz_full_mask);
 bool tick_nohz_full_running;
 EXPORT_SYMBOL_GPL(tick_nohz_full_running);
 static atomic_t tick_dep_mask;
-- 
cgit v1.2.3


From 34fb4db5abc1fe6708522cbf13f637e0eefb1a50 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Wed, 5 May 2021 13:28:29 -0700
Subject: mac80211: correct ieee80211_iterate_active_interfaces_mtx() locking
 comments

Commit a05829a7222e ("cfg80211: avoid holding the RTNL when calling the
driver") dropped usage of RTNL here and replaced it with
hw->wiphy->mutex. But we didn't update the comments.

Fixes: a05829a7222e ("cfg80211: avoid holding the RTNL when calling the driver")
Signed-off-by: Brian Norris <briannorris@chromium.org>
Link: https://lore.kernel.org/r/20210505202829.1039400-1-briannorris@chromium.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 445b66c6eb7e..e7c59b4e2c44 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -5537,7 +5537,7 @@ void ieee80211_iterate_active_interfaces_atomic(struct ieee80211_hw *hw,
  *
  * This function iterates over the interfaces associated with a given
  * hardware that are currently active and calls the callback for them.
- * This version can only be used while holding the RTNL.
+ * This version can only be used while holding the wiphy mutex.
  *
  * @hw: the hardware struct of which the interfaces should be iterated over
  * @iter_flags: iteration flags, see &enum ieee80211_interface_iteration_flags
-- 
cgit v1.2.3


From bddc0c411a45d3718ac535a070f349be8eca8d48 Mon Sep 17 00:00:00 2001
From: Mathy Vanhoef <Mathy.Vanhoef@kuleuven.be>
Date: Sun, 30 May 2021 15:32:26 +0200
Subject: mac80211: Fix NULL ptr deref for injected rate info

The commit cb17ed29a7a5 ("mac80211: parse radiotap header when selecting Tx
queue") moved the code to validate the radiotap header from
ieee80211_monitor_start_xmit to ieee80211_parse_tx_radiotap. This made is
possible to share more code with the new Tx queue selection code for
injected frames. But at the same time, it now required the call of
ieee80211_parse_tx_radiotap at the beginning of functions which wanted to
handle the radiotap header. And this broke the rate parser for radiotap
header parser.

The radiotap parser for rates is operating most of the time only on the
data in the actual radiotap header. But for the 802.11a/b/g rates, it must
also know the selected band from the chandef information. But this
information is only written to the ieee80211_tx_info at the end of the
ieee80211_monitor_start_xmit - long after ieee80211_parse_tx_radiotap was
already called. The info->band information was therefore always 0
(NL80211_BAND_2GHZ) when the parser code tried to access it.

For a 5GHz only device, injecting a frame with 802.11a rates would cause a
NULL pointer dereference because local->hw.wiphy->bands[NL80211_BAND_2GHZ]
would most likely have been NULL when the radiotap parser searched for the
correct rate index of the driver.

Cc: stable@vger.kernel.org
Reported-by: Ben Greear <greearb@candelatech.com>
Fixes: cb17ed29a7a5 ("mac80211: parse radiotap header when selecting Tx queue")
Signed-off-by: Mathy Vanhoef <Mathy.Vanhoef@kuleuven.be>
[sven@narfation.org: added commit message]
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Link: https://lore.kernel.org/r/20210530133226.40587-1-sven@narfation.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  7 ++++++-
 net/mac80211/tx.c      | 52 ++++++++++++++++++++++++++++++++++----------------
 2 files changed, 42 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index e7c59b4e2c44..e89530d0d9c6 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -6392,7 +6392,12 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw,
 
 /**
  * ieee80211_parse_tx_radiotap - Sanity-check and parse the radiotap header
- *				 of injected frames
+ *				 of injected frames.
+ *
+ * To accurately parse and take into account rate and retransmission fields,
+ * you must initialize the chandef field in the ieee80211_tx_info structure
+ * of the skb before calling this function.
+ *
  * @skb: packet injected by userspace
  * @dev: the &struct device of this 802.11 device
  */
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 0b719f3d2dec..2651498d05e8 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -2014,6 +2014,26 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata,
 	ieee80211_tx(sdata, sta, skb, false);
 }
 
+static bool ieee80211_validate_radiotap_len(struct sk_buff *skb)
+{
+	struct ieee80211_radiotap_header *rthdr =
+		(struct ieee80211_radiotap_header *)skb->data;
+
+	/* check for not even having the fixed radiotap header part */
+	if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header)))
+		return false; /* too short to be possibly valid */
+
+	/* is it a header version we can trust to find length from? */
+	if (unlikely(rthdr->it_version))
+		return false; /* only version 0 is supported */
+
+	/* does the skb contain enough to deliver on the alleged length? */
+	if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data)))
+		return false; /* skb too short for claimed rt header extent */
+
+	return true;
+}
+
 bool ieee80211_parse_tx_radiotap(struct sk_buff *skb,
 				 struct net_device *dev)
 {
@@ -2022,8 +2042,6 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb,
 	struct ieee80211_radiotap_header *rthdr =
 		(struct ieee80211_radiotap_header *) skb->data;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct ieee80211_supported_band *sband =
-		local->hw.wiphy->bands[info->band];
 	int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len,
 						   NULL);
 	u16 txflags;
@@ -2036,17 +2054,8 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb,
 	u8 vht_mcs = 0, vht_nss = 0;
 	int i;
 
-	/* check for not even having the fixed radiotap header part */
-	if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header)))
-		return false; /* too short to be possibly valid */
-
-	/* is it a header version we can trust to find length from? */
-	if (unlikely(rthdr->it_version))
-		return false; /* only version 0 is supported */
-
-	/* does the skb contain enough to deliver on the alleged length? */
-	if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data)))
-		return false; /* skb too short for claimed rt header extent */
+	if (!ieee80211_validate_radiotap_len(skb))
+		return false;
 
 	info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT |
 		       IEEE80211_TX_CTL_DONTFRAG;
@@ -2186,6 +2195,9 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb,
 		return false;
 
 	if (rate_found) {
+		struct ieee80211_supported_band *sband =
+			local->hw.wiphy->bands[info->band];
+
 		info->control.flags |= IEEE80211_TX_CTRL_RATE_INJECT;
 
 		for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) {
@@ -2199,7 +2211,7 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb,
 		} else if (rate_flags & IEEE80211_TX_RC_VHT_MCS) {
 			ieee80211_rate_set_vht(info->control.rates, vht_mcs,
 					       vht_nss);
-		} else {
+		} else if (sband) {
 			for (i = 0; i < sband->n_bitrates; i++) {
 				if (rate * 5 != sband->bitrates[i].bitrate)
 					continue;
@@ -2236,8 +2248,8 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 	info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS |
 		      IEEE80211_TX_CTL_INJECTED;
 
-	/* Sanity-check and process the injection radiotap header */
-	if (!ieee80211_parse_tx_radiotap(skb, dev))
+	/* Sanity-check the length of the radiotap header */
+	if (!ieee80211_validate_radiotap_len(skb))
 		goto fail;
 
 	/* we now know there is a radiotap header with a length we can use */
@@ -2351,6 +2363,14 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 	ieee80211_select_queue_80211(sdata, skb, hdr);
 	skb_set_queue_mapping(skb, ieee80211_ac_from_tid(skb->priority));
 
+	/*
+	 * Process the radiotap header. This will now take into account the
+	 * selected chandef above to accurately set injection rates and
+	 * retransmissions.
+	 */
+	if (!ieee80211_parse_tx_radiotap(skb, dev))
+		goto fail_rcu;
+
 	/* remove the injection radiotap header */
 	skb_pull(skb, len_rthdr);
 
-- 
cgit v1.2.3


From 0b78f8bcf4951af30b0ae83ea4fad27d641ab617 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 1 Jun 2021 15:30:30 +0100
Subject: Revert "fb_defio: Remove custom address_space_operations"

Commit ccf953d8f3d6 makes framebuffers which use deferred I/O stop
displaying updates after the first one.  This is because the pages
handled by fb_defio no longer have a page_mapping().  That prevents
page_mkclean() from marking the PTEs as clean, and so writes are only
noticed the first time.

Reported-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/YLZEhv0cpZp8uVE3@casper.infradead.org
---
 drivers/video/fbdev/core/fb_defio.c | 35 +++++++++++++++++++++++++++++++++++
 drivers/video/fbdev/core/fbmem.c    |  4 ++++
 include/linux/fb.h                  |  3 +++
 3 files changed, 42 insertions(+)

(limited to 'include')

diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c
index b292887a2481..a591d291b231 100644
--- a/drivers/video/fbdev/core/fb_defio.c
+++ b/drivers/video/fbdev/core/fb_defio.c
@@ -52,6 +52,13 @@ static vm_fault_t fb_deferred_io_fault(struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 
 	get_page(page);
+
+	if (vmf->vma->vm_file)
+		page->mapping = vmf->vma->vm_file->f_mapping;
+	else
+		printk(KERN_ERR "no mapping available\n");
+
+	BUG_ON(!page->mapping);
 	page->index = vmf->pgoff;
 
 	vmf->page = page;
@@ -144,6 +151,17 @@ static const struct vm_operations_struct fb_deferred_io_vm_ops = {
 	.page_mkwrite	= fb_deferred_io_mkwrite,
 };
 
+static int fb_deferred_io_set_page_dirty(struct page *page)
+{
+	if (!PageDirty(page))
+		SetPageDirty(page);
+	return 0;
+}
+
+static const struct address_space_operations fb_deferred_io_aops = {
+	.set_page_dirty = fb_deferred_io_set_page_dirty,
+};
+
 int fb_deferred_io_mmap(struct fb_info *info, struct vm_area_struct *vma)
 {
 	vma->vm_ops = &fb_deferred_io_vm_ops;
@@ -194,12 +212,29 @@ void fb_deferred_io_init(struct fb_info *info)
 }
 EXPORT_SYMBOL_GPL(fb_deferred_io_init);
 
+void fb_deferred_io_open(struct fb_info *info,
+			 struct inode *inode,
+			 struct file *file)
+{
+	file->f_mapping->a_ops = &fb_deferred_io_aops;
+}
+EXPORT_SYMBOL_GPL(fb_deferred_io_open);
+
 void fb_deferred_io_cleanup(struct fb_info *info)
 {
 	struct fb_deferred_io *fbdefio = info->fbdefio;
+	struct page *page;
+	int i;
 
 	BUG_ON(!fbdefio);
 	cancel_delayed_work_sync(&info->deferred_work);
+
+	/* clear out the mapping that we setup */
+	for (i = 0 ; i < info->fix.smem_len; i += PAGE_SIZE) {
+		page = fb_deferred_io_page(info, i);
+		page->mapping = NULL;
+	}
+
 	mutex_destroy(&fbdefio->lock);
 }
 EXPORT_SYMBOL_GPL(fb_deferred_io_cleanup);
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index 072780b0e570..98f193078c05 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -1415,6 +1415,10 @@ __releases(&info->lock)
 		if (res)
 			module_put(info->fbops->owner);
 	}
+#ifdef CONFIG_FB_DEFERRED_IO
+	if (info->fbdefio)
+		fb_deferred_io_open(info, inode, file);
+#endif
 out:
 	unlock_fb_info(info);
 	if (res)
diff --git a/include/linux/fb.h b/include/linux/fb.h
index a8dccd23c249..ecfbcc0553a5 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -659,6 +659,9 @@ static inline void __fb_pad_aligned_buffer(u8 *dst, u32 d_pitch,
 /* drivers/video/fb_defio.c */
 int fb_deferred_io_mmap(struct fb_info *info, struct vm_area_struct *vma);
 extern void fb_deferred_io_init(struct fb_info *info);
+extern void fb_deferred_io_open(struct fb_info *info,
+				struct inode *inode,
+				struct file *file);
 extern void fb_deferred_io_cleanup(struct fb_info *info);
 extern int fb_deferred_io_fsync(struct file *file, loff_t start,
 				loff_t end, int datasync);
-- 
cgit v1.2.3


From 05fc8b6cbd4f979a6f25759c4a17dd5f657f7ecd Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@nvidia.com>
Date: Tue, 1 Jun 2021 15:07:59 +0300
Subject: net/tls: Replace TLS_RX_SYNC_RUNNING with RCU

RCU synchronization is guaranteed to finish in finite time, unlike a
busy loop that polls a flag. This patch is a preparation for the bugfix
in the next patch, where the same synchronize_net() call will also be
used to sync with the TX datapath.

Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h    |  1 -
 net/tls/tls_device.c | 10 +++-------
 2 files changed, 3 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/tls.h b/include/net/tls.h
index 3eccb525e8f7..6531ace2a68b 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -193,7 +193,6 @@ struct tls_offload_context_tx {
 	(sizeof(struct tls_offload_context_tx) + TLS_DRIVER_STATE_SIZE_TX)
 
 enum tls_context_flags {
-	TLS_RX_SYNC_RUNNING = 0,
 	/* Unlike RX where resync is driven entirely by the core in TX only
 	 * the driver knows when things went out of sync, so we need the flag
 	 * to be atomic.
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 76a6f8c2eec4..171752cd6910 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -680,15 +680,13 @@ static void tls_device_resync_rx(struct tls_context *tls_ctx,
 	struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx);
 	struct net_device *netdev;
 
-	if (WARN_ON(test_and_set_bit(TLS_RX_SYNC_RUNNING, &tls_ctx->flags)))
-		return;
-
 	trace_tls_device_rx_resync_send(sk, seq, rcd_sn, rx_ctx->resync_type);
+	rcu_read_lock();
 	netdev = READ_ONCE(tls_ctx->netdev);
 	if (netdev)
 		netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn,
 						   TLS_OFFLOAD_CTX_DIR_RX);
-	clear_bit_unlock(TLS_RX_SYNC_RUNNING, &tls_ctx->flags);
+	rcu_read_unlock();
 	TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXDEVICERESYNC);
 }
 
@@ -1300,9 +1298,7 @@ static int tls_device_down(struct net_device *netdev)
 			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
 							TLS_OFFLOAD_CTX_DIR_RX);
 		WRITE_ONCE(ctx->netdev, NULL);
-		smp_mb__before_atomic(); /* pairs with test_and_set_bit() */
-		while (test_bit(TLS_RX_SYNC_RUNNING, &ctx->flags))
-			usleep_range(10, 200);
+		synchronize_net();
 		dev_put(netdev);
 		list_del_init(&ctx->list);
 
-- 
cgit v1.2.3


From c55dcdd435aa6c6ad6ccac0a4c636d010ee367a4 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@nvidia.com>
Date: Tue, 1 Jun 2021 15:08:00 +0300
Subject: net/tls: Fix use-after-free after the TLS device goes down and up

When a netdev with active TLS offload goes down, tls_device_down is
called to stop the offload and tear down the TLS context. However, the
socket stays alive, and it still points to the TLS context, which is now
deallocated. If a netdev goes up, while the connection is still active,
and the data flow resumes after a number of TCP retransmissions, it will
lead to a use-after-free of the TLS context.

This commit addresses this bug by keeping the context alive until its
normal destruction, and implements the necessary fallbacks, so that the
connection can resume in software (non-offloaded) kTLS mode.

On the TX side tls_sw_fallback is used to encrypt all packets. The RX
side already has all the necessary fallbacks, because receiving
non-decrypted packets is supported. The thing needed on the RX side is
to block resync requests, which are normally produced after receiving
non-decrypted packets.

The necessary synchronization is implemented for a graceful teardown:
first the fallbacks are deployed, then the driver resources are released
(it used to be possible to have a tls_dev_resync after tls_dev_del).

A new flag called TLS_RX_DEV_DEGRADED is added to indicate the fallback
mode. It's used to skip the RX resync logic completely, as it becomes
useless, and some objects may be released (for example, resync_async,
which is allocated and freed by the driver).

Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure")
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h             |  9 ++++++++
 net/tls/tls_device.c          | 52 ++++++++++++++++++++++++++++++++++++++-----
 net/tls/tls_device_fallback.c |  7 ++++++
 net/tls/tls_main.c            |  1 +
 4 files changed, 64 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/tls.h b/include/net/tls.h
index 6531ace2a68b..8341a8d1e807 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -193,6 +193,11 @@ struct tls_offload_context_tx {
 	(sizeof(struct tls_offload_context_tx) + TLS_DRIVER_STATE_SIZE_TX)
 
 enum tls_context_flags {
+	/* tls_device_down was called after the netdev went down, device state
+	 * was released, and kTLS works in software, even though rx_conf is
+	 * still TLS_HW (needed for transition).
+	 */
+	TLS_RX_DEV_DEGRADED = 0,
 	/* Unlike RX where resync is driven entirely by the core in TX only
 	 * the driver knows when things went out of sync, so we need the flag
 	 * to be atomic.
@@ -265,6 +270,7 @@ struct tls_context {
 
 	/* cache cold stuff */
 	struct proto *sk_proto;
+	struct sock *sk;
 
 	void (*sk_destruct)(struct sock *sk);
 
@@ -447,6 +453,9 @@ static inline u16 tls_user_config(struct tls_context *ctx, bool tx)
 struct sk_buff *
 tls_validate_xmit_skb(struct sock *sk, struct net_device *dev,
 		      struct sk_buff *skb);
+struct sk_buff *
+tls_validate_xmit_skb_sw(struct sock *sk, struct net_device *dev,
+			 struct sk_buff *skb);
 
 static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
 {
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 171752cd6910..bd9f1567aa39 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -50,6 +50,7 @@ static void tls_device_gc_task(struct work_struct *work);
 static DECLARE_WORK(tls_device_gc_work, tls_device_gc_task);
 static LIST_HEAD(tls_device_gc_list);
 static LIST_HEAD(tls_device_list);
+static LIST_HEAD(tls_device_down_list);
 static DEFINE_SPINLOCK(tls_device_lock);
 
 static void tls_device_free_ctx(struct tls_context *ctx)
@@ -759,6 +760,8 @@ void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq)
 
 	if (tls_ctx->rx_conf != TLS_HW)
 		return;
+	if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags)))
+		return;
 
 	prot = &tls_ctx->prot_info;
 	rx_ctx = tls_offload_ctx_rx(tls_ctx);
@@ -961,6 +964,17 @@ int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx,
 
 	ctx->sw.decrypted |= is_decrypted;
 
+	if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags))) {
+		if (likely(is_encrypted || is_decrypted))
+			return 0;
+
+		/* After tls_device_down disables the offload, the next SKB will
+		 * likely have initial fragments decrypted, and final ones not
+		 * decrypted. We need to reencrypt that single SKB.
+		 */
+		return tls_device_reencrypt(sk, skb);
+	}
+
 	/* Return immediately if the record is either entirely plaintext or
 	 * entirely ciphertext. Otherwise handle reencrypt partially decrypted
 	 * record.
@@ -1290,6 +1304,26 @@ static int tls_device_down(struct net_device *netdev)
 	spin_unlock_irqrestore(&tls_device_lock, flags);
 
 	list_for_each_entry_safe(ctx, tmp, &list, list)	{
+		/* Stop offloaded TX and switch to the fallback.
+		 * tls_is_sk_tx_device_offloaded will return false.
+		 */
+		WRITE_ONCE(ctx->sk->sk_validate_xmit_skb, tls_validate_xmit_skb_sw);
+
+		/* Stop the RX and TX resync.
+		 * tls_dev_resync must not be called after tls_dev_del.
+		 */
+		WRITE_ONCE(ctx->netdev, NULL);
+
+		/* Start skipping the RX resync logic completely. */
+		set_bit(TLS_RX_DEV_DEGRADED, &ctx->flags);
+
+		/* Sync with inflight packets. After this point:
+		 * TX: no non-encrypted packets will be passed to the driver.
+		 * RX: resync requests from the driver will be ignored.
+		 */
+		synchronize_net();
+
+		/* Release the offload context on the driver side. */
 		if (ctx->tx_conf == TLS_HW)
 			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
 							TLS_OFFLOAD_CTX_DIR_TX);
@@ -1297,13 +1331,21 @@ static int tls_device_down(struct net_device *netdev)
 		    !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);
-		synchronize_net();
+
 		dev_put(netdev);
-		list_del_init(&ctx->list);
 
-		if (refcount_dec_and_test(&ctx->refcount))
-			tls_device_free_ctx(ctx);
+		/* Move the context to a separate list for two reasons:
+		 * 1. When the context is deallocated, list_del is called.
+		 * 2. It's no longer an offloaded context, so we don't want to
+		 *    run offload-specific code on this context.
+		 */
+		spin_lock_irqsave(&tls_device_lock, flags);
+		list_move_tail(&ctx->list, &tls_device_down_list);
+		spin_unlock_irqrestore(&tls_device_lock, flags);
+
+		/* Device contexts for RX and TX will be freed in on sk_destruct
+		 * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW.
+		 */
 	}
 
 	up_write(&device_offload_lock);
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index cacf040872c7..e40bedd112b6 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -431,6 +431,13 @@ struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
 }
 EXPORT_SYMBOL_GPL(tls_validate_xmit_skb);
 
+struct sk_buff *tls_validate_xmit_skb_sw(struct sock *sk,
+					 struct net_device *dev,
+					 struct sk_buff *skb)
+{
+	return tls_sw_fallback(sk, skb);
+}
+
 struct sk_buff *tls_encrypt_skb(struct sk_buff *skb)
 {
 	return tls_sw_fallback(skb->sk, skb);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 47b7c5334c34..fde56ff49163 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -636,6 +636,7 @@ struct tls_context *tls_ctx_create(struct sock *sk)
 	mutex_init(&ctx->tx_lock);
 	rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
 	ctx->sk_proto = READ_ONCE(sk->sk_prot);
+	ctx->sk = sk;
 	return ctx;
 }
 
-- 
cgit v1.2.3


From 216214c64a8c1cb9078c2c0aec7bb4a2f8e75397 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Wed, 9 Dec 2020 16:40:38 +0200
Subject: net/mlx5: DR, Create multi-destination flow table with level less
 than 64

Flow table that contains flow pointing to multiple flow tables or multiple
TIRs must have a level lower than 64. In our case it applies to muli-
destination flow table.
Fix the level of the created table to comply with HW Spec definitions, and
still make sure that its level lower than SW-owned tables, so that it
would be possible to point from the multi-destination FW table to SW
tables.

Fixes: 34583beea4b7 ("net/mlx5: DR, Create multi-destination table for SW-steering use")
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c | 3 ++-
 include/linux/mlx5/mlx5_ifc.h                            | 2 ++
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
index 1fbcd012bb85..7ccfd40586ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
@@ -112,7 +112,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn,
 	int ret;
 
 	ft_attr.table_type = MLX5_FLOW_TABLE_TYPE_FDB;
-	ft_attr.level = dmn->info.caps.max_ft_level - 2;
+	ft_attr.level = min_t(int, dmn->info.caps.max_ft_level - 2,
+			      MLX5_FT_MAX_MULTIPATH_LEVEL);
 	ft_attr.reformat_en = reformat_req;
 	ft_attr.decap_en = reformat_req;
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6d16eed6850e..eb86e80e4643 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1289,6 +1289,8 @@ enum mlx5_fc_bulk_alloc_bitmask {
 
 #define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum))
 
+#define MLX5_FT_MAX_MULTIPATH_LEVEL 63
+
 enum {
 	MLX5_STEERING_FORMAT_CONNECTX_5   = 0,
 	MLX5_STEERING_FORMAT_CONNECTX_6DX = 1,
-- 
cgit v1.2.3


From 6490fa565534fa83593278267785a694fd378a2b Mon Sep 17 00:00:00 2001
From: Kyle Tso <kyletso@google.com>
Date: Fri, 28 May 2021 16:16:13 +0800
Subject: usb: pd: Set PD_T_SINK_WAIT_CAP to 310ms

Current timer PD_T_SINK_WAIT_CAP is set to 240ms which will violate the
SinkWaitCapTimer (tTypeCSinkWaitCap 310 - 620 ms) defined in the PD
Spec if the port is faster enough when running the state machine. Set it
to the lower bound 310ms to ensure the timeout is in Spec.

Fixes: f0690a25a140 ("staging: typec: USB Type-C Port Manager (tcpm)")
Cc: stable <stable@vger.kernel.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Kyle Tso <kyletso@google.com>
Link: https://lore.kernel.org/r/20210528081613.730661-1-kyletso@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/pd.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h
index bf00259493e0..96b7ff66f074 100644
--- a/include/linux/usb/pd.h
+++ b/include/linux/usb/pd.h
@@ -460,7 +460,7 @@ static inline unsigned int rdo_max_power(u32 rdo)
 #define PD_T_RECEIVER_RESPONSE	15	/* 15ms max */
 #define PD_T_SOURCE_ACTIVITY	45
 #define PD_T_SINK_ACTIVITY	135
-#define PD_T_SINK_WAIT_CAP	240
+#define PD_T_SINK_WAIT_CAP	310	/* 310 - 620 ms */
 #define PD_T_PS_TRANSITION	500
 #define PD_T_SRC_TRANSITION	35
 #define PD_T_DRP_SNK		40
-- 
cgit v1.2.3


From d4c6399900364facd84c9e35ce1540b6046c345f Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 5 May 2021 17:14:11 -0700
Subject: vmlinux.lds.h: Avoid orphan section with !SMP

With x86_64_defconfig and the following configs, there is an orphan
section warning:

CONFIG_SMP=n
CONFIG_AMD_MEM_ENCRYPT=y
CONFIG_HYPERVISOR_GUEST=y
CONFIG_KVM=y
CONFIG_PARAVIRT=y

ld: warning: orphan section `.data..decrypted' from `arch/x86/kernel/cpu/vmware.o' being placed in section `.data..decrypted'
ld: warning: orphan section `.data..decrypted' from `arch/x86/kernel/kvm.o' being placed in section `.data..decrypted'

These sections are created with DEFINE_PER_CPU_DECRYPTED, which
ultimately turns into __PCPU_ATTRS, which in turn has a section
attribute with a value of PER_CPU_BASE_SECTION + the section name. When
CONFIG_SMP is not set, the base section is .data and that is not
currently handled in any linker script.

Add .data..decrypted to PERCPU_DECRYPTED_SECTION, which is included in
PERCPU_INPUT -> PERCPU_SECTION, which is include in the x86 linker
script when either CONFIG_X86_64 or CONFIG_SMP is unset, taking care of
the warning.

Fixes: ac26963a1175 ("percpu: Introduce DEFINE_PER_CPU_DECRYPTED")
Link: https://github.com/ClangBuiltLinux/linux/issues/1360
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nick Desaulniers <ndesaulniers@google.com> # build
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20210506001410.1026691-1-nathan@kernel.org
---
 include/asm-generic/vmlinux.lds.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 40a9c101565e..17325416e2de 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -960,6 +960,7 @@
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 #define PERCPU_DECRYPTED_SECTION					\
 	. = ALIGN(PAGE_SIZE);						\
+	*(.data..decrypted)						\
 	*(.data..percpu..decrypted)					\
 	. = ALIGN(PAGE_SIZE);
 #else
-- 
cgit v1.2.3


From 68d7a190682aa4eb02db477328088ebad15acc83 Mon Sep 17 00:00:00 2001
From: Dietmar Eggemann <dietmar.eggemann@arm.com>
Date: Wed, 2 Jun 2021 16:58:08 +0200
Subject: sched/fair: Fix util_est UTIL_AVG_UNCHANGED handling

The util_est internal UTIL_AVG_UNCHANGED flag which is used to prevent
unnecessary util_est updates uses the LSB of util_est.enqueued. It is
exposed via _task_util_est() (and task_util_est()).

Commit 92a801e5d5b7 ("sched/fair: Mask UTIL_AVG_UNCHANGED usages")
mentions that the LSB is lost for util_est resolution but
find_energy_efficient_cpu() checks if task_util_est() returns 0 to
return prev_cpu early.

_task_util_est() returns the max value of util_est.ewma and
util_est.enqueued or'ed w/ UTIL_AVG_UNCHANGED.
So task_util_est() returning the max of task_util() and
_task_util_est() will never return 0 under the default
SCHED_FEAT(UTIL_EST, true).

To fix this use the MSB of util_est.enqueued instead and keep the flag
util_est internal, i.e. don't export it via _task_util_est().

The maximal possible util_avg value for a task is 1024 so the MSB of
'unsigned int util_est.enqueued' isn't used to store a util value.

As a caveat the code behind the util_est_se trace point has to filter
UTIL_AVG_UNCHANGED to see the real util_est.enqueued value which should
be easy to do.

This also fixes an issue report by Xuewen Yan that util_est_update()
only used UTIL_AVG_UNCHANGED for the subtrahend of the equation:

  last_enqueued_diff = ue.enqueued - (task_util() | UTIL_AVG_UNCHANGED)

Fixes: b89997aa88f0b sched/pelt: Fix task util_est update filtering
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Xuewen Yan <xuewen.yan@unisoc.com>
Reviewed-by: Vincent Donnefort <vincent.donnefort@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20210602145808.1562603-1-dietmar.eggemann@arm.com
---
 include/linux/sched.h |  8 ++++++++
 kernel/sched/debug.c  |  3 ++-
 kernel/sched/fair.c   |  5 +++--
 kernel/sched/pelt.h   | 11 +----------
 4 files changed, 14 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d2c881384517..28a98fc4ded4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -350,11 +350,19 @@ struct load_weight {
  * Only for tasks we track a moving average of the past instantaneous
  * estimated utilization. This allows to absorb sporadic drops in utilization
  * of an otherwise almost periodic task.
+ *
+ * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg
+ * updates. When a task is dequeued, its util_est should not be updated if its
+ * util_avg has not been updated in the meantime.
+ * This information is mapped into the MSB bit of util_est.enqueued at dequeue
+ * time. Since max value of util_est.enqueued for a task is 1024 (PELT util_avg
+ * for a task) it is safe to use MSB.
  */
 struct util_est {
 	unsigned int			enqueued;
 	unsigned int			ewma;
 #define UTIL_EST_WEIGHT_SHIFT		2
+#define UTIL_AVG_UNCHANGED		0x80000000
 } __attribute__((__aligned__(sizeof(u64))));
 
 /*
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 9c882f20803e..c5aacbd492a1 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -885,6 +885,7 @@ static const struct seq_operations sched_debug_sops = {
 #define __PS(S, F) SEQ_printf(m, "%-45s:%21Ld\n", S, (long long)(F))
 #define __P(F) __PS(#F, F)
 #define   P(F) __PS(#F, p->F)
+#define   PM(F, M) __PS(#F, p->F & (M))
 #define __PSN(S, F) SEQ_printf(m, "%-45s:%14Ld.%06ld\n", S, SPLIT_NS((long long)(F)))
 #define __PN(F) __PSN(#F, F)
 #define   PN(F) __PSN(#F, p->F)
@@ -1011,7 +1012,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	P(se.avg.util_avg);
 	P(se.avg.last_update_time);
 	P(se.avg.util_est.ewma);
-	P(se.avg.util_est.enqueued);
+	PM(se.avg.util_est.enqueued, ~UTIL_AVG_UNCHANGED);
 #endif
 #ifdef CONFIG_UCLAMP_TASK
 	__PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7b98fb37330a..2c8a9352590d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3907,7 +3907,7 @@ static inline unsigned long _task_util_est(struct task_struct *p)
 {
 	struct util_est ue = READ_ONCE(p->se.avg.util_est);
 
-	return (max(ue.ewma, ue.enqueued) | UTIL_AVG_UNCHANGED);
+	return max(ue.ewma, (ue.enqueued & ~UTIL_AVG_UNCHANGED));
 }
 
 static inline unsigned long task_util_est(struct task_struct *p)
@@ -4007,7 +4007,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	 * Reset EWMA on utilization increases, the moving average is used only
 	 * to smooth utilization decreases.
 	 */
-	ue.enqueued = (task_util(p) | UTIL_AVG_UNCHANGED);
+	ue.enqueued = task_util(p);
 	if (sched_feat(UTIL_EST_FASTUP)) {
 		if (ue.ewma < ue.enqueued) {
 			ue.ewma = ue.enqueued;
@@ -4056,6 +4056,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	ue.ewma  += last_ewma_diff;
 	ue.ewma >>= UTIL_EST_WEIGHT_SHIFT;
 done:
+	ue.enqueued |= UTIL_AVG_UNCHANGED;
 	WRITE_ONCE(p->se.avg.util_est, ue);
 
 	trace_sched_util_est_se_tp(&p->se);
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index 1462846d244e..cfe94ffd2b38 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -42,15 +42,6 @@ static inline u32 get_pelt_divider(struct sched_avg *avg)
 	return LOAD_AVG_MAX - 1024 + avg->period_contrib;
 }
 
-/*
- * When a task is dequeued, its estimated utilization should not be update if
- * its util_avg has not been updated at least once.
- * This flag is used to synchronize util_avg updates with util_est updates.
- * We map this information into the LSB bit of the utilization saved at
- * dequeue time (i.e. util_est.dequeued).
- */
-#define UTIL_AVG_UNCHANGED 0x1
-
 static inline void cfs_se_util_change(struct sched_avg *avg)
 {
 	unsigned int enqueued;
@@ -58,7 +49,7 @@ static inline void cfs_se_util_change(struct sched_avg *avg)
 	if (!sched_feat(UTIL_EST))
 		return;
 
-	/* Avoid store if the flag has been already set */
+	/* Avoid store if the flag has been already reset */
 	enqueued = avg->util_est.enqueued;
 	if (!(enqueued & UTIL_AVG_UNCHANGED))
 		return;
-- 
cgit v1.2.3


From 404e5a12691fe797486475fe28cc0b80cb8bef2c Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 3 Jun 2021 16:19:39 +0300
Subject: RDMA/mlx4: Do not map the core_clock page to user space unless
 enabled

Currently when mlx4 maps the hca_core_clock page to the user space there
are read-modifiable registers, one of which is semaphore, on this page as
well as the clock counter. If user reads the wrong offset, it can modify
the semaphore and hang the device.

Do not map the hca_core_clock page to the user space unless the device has
been put in a backwards compatibility mode to support this feature.

After this patch, mlx4 core_clock won't be mapped to user space on the
majority of existing devices and the uverbs device time feature in
ibv_query_rt_values_ex() will be disabled.

Fixes: 52033cfb5aab ("IB/mlx4: Add mmap call to map the hardware clock")
Link: https://lore.kernel.org/r/9632304e0d6790af84b3b706d8c18732bc0d5e27.1622726305.git.leonro@nvidia.com
Signed-off-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx4/main.c         | 5 +----
 drivers/net/ethernet/mellanox/mlx4/fw.c   | 3 +++
 drivers/net/ethernet/mellanox/mlx4/fw.h   | 1 +
 drivers/net/ethernet/mellanox/mlx4/main.c | 6 ++++++
 include/linux/mlx4/device.h               | 1 +
 5 files changed, 12 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 22898d97ecbd..16704262fc3a 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -581,12 +581,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->cq_caps.max_cq_moderation_count = MLX4_MAX_CQ_COUNT;
 	props->cq_caps.max_cq_moderation_period = MLX4_MAX_CQ_PERIOD;
 
-	if (!mlx4_is_slave(dev->dev))
-		err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
-
 	if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) {
 		resp.response_length += sizeof(resp.hca_core_clock_offset);
-		if (!err && !mlx4_is_slave(dev->dev)) {
+		if (!mlx4_get_internal_clock_params(dev->dev, &clock_params)) {
 			resp.comp_mask |= MLX4_IB_QUERY_DEV_RESP_MASK_CORE_CLOCK_OFFSET;
 			resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index f6cfec81ccc3..dc4ac1a2b6b6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -823,6 +823,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_MAD_DEMUX_OFFSET		0xb0
 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET	0xa8
 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET	0xac
+#define QUERY_DEV_CAP_MAP_CLOCK_TO_USER 0xc1
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET	0xcc
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET	0xd0
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET	0xd2
@@ -841,6 +842,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 
 	if (mlx4_is_mfunc(dev))
 		disable_unsupported_roce_caps(outbox);
+	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAP_CLOCK_TO_USER);
+	dev_cap->map_clock_to_user = field & 0x80;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_QP_OFFSET);
 	dev_cap->reserved_qps = 1 << (field & 0xf);
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_QP_OFFSET);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 8f020f26ebf5..cf64e54eecb0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -131,6 +131,7 @@ struct mlx4_dev_cap {
 	u32 health_buffer_addrs;
 	struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1];
 	bool wol_port[MLX4_MAX_PORTS + 1];
+	bool map_clock_to_user;
 };
 
 struct mlx4_func_cap {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index c326b434734e..00c84656b2e7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -498,6 +498,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		}
 	}
 
+	dev->caps.map_clock_to_user  = dev_cap->map_clock_to_user;
 	dev->caps.uar_page_size	     = PAGE_SIZE;
 	dev->caps.num_uars	     = dev_cap->uar_size / PAGE_SIZE;
 	dev->caps.local_ca_ack_delay = dev_cap->local_ca_ack_delay;
@@ -1948,6 +1949,11 @@ int mlx4_get_internal_clock_params(struct mlx4_dev *dev,
 	if (mlx4_is_slave(dev))
 		return -EOPNOTSUPP;
 
+	if (!dev->caps.map_clock_to_user) {
+		mlx4_dbg(dev, "Map clock to user is not supported.\n");
+		return -EOPNOTSUPP;
+	}
+
 	if (!params)
 		return -EINVAL;
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 236a7d04f891..30bb59fe970c 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -630,6 +630,7 @@ struct mlx4_caps {
 	bool			wol_port[MLX4_MAX_PORTS + 1];
 	struct mlx4_rate_limit_caps rl_caps;
 	u32			health_buffer_addrs;
+	bool			map_clock_to_user;
 };
 
 struct mlx4_buf_list {
-- 
cgit v1.2.3


From a83d958504734f78f42b1e3392d93816297e790a Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Thu, 3 Jun 2021 21:20:26 +0200
Subject: Bluetooth: Fix VIRTIO_ID_BT assigned number

It turned out that the VIRTIO_ID_* are not assigned in the virtio_ids.h
file in the upstream kernel. Picking the next free one was wrong and
there is a process that has been followed now.

See https://github.com/oasis-tcs/virtio-spec/issues/108 for details.

Fixes: afd2daa26c7a ("Bluetooth: Add support for virtio transport driver")
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/uapi/linux/virtio_ids.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h
index f0c35ce8628c..4fe842c3a3a9 100644
--- a/include/uapi/linux/virtio_ids.h
+++ b/include/uapi/linux/virtio_ids.h
@@ -54,7 +54,7 @@
 #define VIRTIO_ID_SOUND			25 /* virtio sound */
 #define VIRTIO_ID_FS			26 /* virtio filesystem */
 #define VIRTIO_ID_PMEM			27 /* virtio pmem */
-#define VIRTIO_ID_BT			28 /* virtio bluetooth */
 #define VIRTIO_ID_MAC80211_HWSIM	29 /* virtio mac80211-hwsim */
+#define VIRTIO_ID_BT			40 /* virtio bluetooth */
 
 #endif /* _LINUX_VIRTIO_IDS_H */
-- 
cgit v1.2.3


From bce130e7f392ddde8cfcb09927808ebd5f9c8669 Mon Sep 17 00:00:00 2001
From: Pavel Skripkin <paskripkin@gmail.com>
Date: Thu, 3 Jun 2021 19:38:12 +0300
Subject: net: caif: added cfserl_release function

Added cfserl_release() function.

Cc: stable@vger.kernel.org
Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/caif/cfserl.h | 1 +
 net/caif/cfserl.c         | 5 +++++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/net/caif/cfserl.h b/include/net/caif/cfserl.h
index 14a55e03bb3c..67cce8757175 100644
--- a/include/net/caif/cfserl.h
+++ b/include/net/caif/cfserl.h
@@ -9,4 +9,5 @@
 #include <net/caif/caif_layer.h>
 
 struct cflayer *cfserl_create(int instance, bool use_stx);
+void cfserl_release(struct cflayer *layer);
 #endif
diff --git a/net/caif/cfserl.c b/net/caif/cfserl.c
index e11725a4bb0e..40cd57ad0a0f 100644
--- a/net/caif/cfserl.c
+++ b/net/caif/cfserl.c
@@ -31,6 +31,11 @@ static int cfserl_transmit(struct cflayer *layr, struct cfpkt *pkt);
 static void cfserl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
 			   int phyid);
 
+void cfserl_release(struct cflayer *layer)
+{
+	kfree(layer);
+}
+
 struct cflayer *cfserl_create(int instance, bool use_stx)
 {
 	struct cfserl *this = kzalloc(sizeof(struct cfserl), GFP_ATOMIC);
-- 
cgit v1.2.3


From a2805dca5107d5603f4bbc027e81e20d93476e96 Mon Sep 17 00:00:00 2001
From: Pavel Skripkin <paskripkin@gmail.com>
Date: Thu, 3 Jun 2021 19:38:51 +0300
Subject: net: caif: add proper error handling

caif_enroll_dev() can fail in some cases. Ingnoring
these cases can lead to memory leak due to not assigning
link_support pointer to anywhere.

Fixes: 7c18d2205ea7 ("caif: Restructure how link caif link layer enroll")
Cc: stable@vger.kernel.org
Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/caif/caif_dev.h |  2 +-
 include/net/caif/cfcnfg.h   |  2 +-
 net/caif/caif_dev.c         |  8 +++++---
 net/caif/cfcnfg.c           | 16 +++++++++++-----
 4 files changed, 18 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/caif/caif_dev.h b/include/net/caif/caif_dev.h
index 48ecca8530ff..b655d8666f55 100644
--- a/include/net/caif/caif_dev.h
+++ b/include/net/caif/caif_dev.h
@@ -119,7 +119,7 @@ void caif_free_client(struct cflayer *adap_layer);
  * The link_support layer is used to add any Link Layer specific
  * framing.
  */
-void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
+int caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
 			struct cflayer *link_support, int head_room,
 			struct cflayer **layer, int (**rcv_func)(
 				struct sk_buff *, struct net_device *,
diff --git a/include/net/caif/cfcnfg.h b/include/net/caif/cfcnfg.h
index 2aa5e91d8457..8819ff4db35a 100644
--- a/include/net/caif/cfcnfg.h
+++ b/include/net/caif/cfcnfg.h
@@ -62,7 +62,7 @@ void cfcnfg_remove(struct cfcnfg *cfg);
  * @fcs:	Specify if checksum is used in CAIF Framing Layer.
  * @head_room:	Head space needed by link specific protocol.
  */
-void
+int
 cfcnfg_add_phy_layer(struct cfcnfg *cnfg,
 		     struct net_device *dev, struct cflayer *phy_layer,
 		     enum cfcnfg_phy_preference pref,
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index c10e5a55758d..fffbe41440b3 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -308,7 +308,7 @@ static void dev_flowctrl(struct net_device *dev, int on)
 	caifd_put(caifd);
 }
 
-void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
+int caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
 		     struct cflayer *link_support, int head_room,
 		     struct cflayer **layer,
 		     int (**rcv_func)(struct sk_buff *, struct net_device *,
@@ -319,11 +319,12 @@ void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
 	enum cfcnfg_phy_preference pref;
 	struct cfcnfg *cfg = get_cfcnfg(dev_net(dev));
 	struct caif_device_entry_list *caifdevs;
+	int res;
 
 	caifdevs = caif_device_list(dev_net(dev));
 	caifd = caif_device_alloc(dev);
 	if (!caifd)
-		return;
+		return -ENOMEM;
 	*layer = &caifd->layer;
 	spin_lock_init(&caifd->flow_lock);
 
@@ -344,7 +345,7 @@ void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
 	strlcpy(caifd->layer.name, dev->name,
 		sizeof(caifd->layer.name));
 	caifd->layer.transmit = transmit;
-	cfcnfg_add_phy_layer(cfg,
+	res = cfcnfg_add_phy_layer(cfg,
 				dev,
 				&caifd->layer,
 				pref,
@@ -354,6 +355,7 @@ void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
 	mutex_unlock(&caifdevs->lock);
 	if (rcv_func)
 		*rcv_func = receive;
+	return res;
 }
 EXPORT_SYMBOL(caif_enroll_dev);
 
diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c
index 399239a14420..cac30e676ac9 100644
--- a/net/caif/cfcnfg.c
+++ b/net/caif/cfcnfg.c
@@ -450,7 +450,7 @@ unlock:
 	rcu_read_unlock();
 }
 
-void
+int
 cfcnfg_add_phy_layer(struct cfcnfg *cnfg,
 		     struct net_device *dev, struct cflayer *phy_layer,
 		     enum cfcnfg_phy_preference pref,
@@ -459,7 +459,7 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg,
 {
 	struct cflayer *frml;
 	struct cfcnfg_phyinfo *phyinfo = NULL;
-	int i;
+	int i, res = 0;
 	u8 phyid;
 
 	mutex_lock(&cnfg->lock);
@@ -473,12 +473,15 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg,
 			goto got_phyid;
 	}
 	pr_warn("Too many CAIF Link Layers (max 6)\n");
+	res = -EEXIST;
 	goto out;
 
 got_phyid:
 	phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC);
-	if (!phyinfo)
+	if (!phyinfo) {
+		res = -ENOMEM;
 		goto out_err;
+	}
 
 	phy_layer->id = phyid;
 	phyinfo->pref = pref;
@@ -492,8 +495,10 @@ got_phyid:
 
 	frml = cffrml_create(phyid, fcs);
 
-	if (!frml)
+	if (!frml) {
+		res = -ENOMEM;
 		goto out_err;
+	}
 	phyinfo->frm_layer = frml;
 	layer_set_up(frml, cnfg->mux);
 
@@ -511,11 +516,12 @@ got_phyid:
 	list_add_rcu(&phyinfo->node, &cnfg->phys);
 out:
 	mutex_unlock(&cnfg->lock);
-	return;
+	return res;
 
 out_err:
 	kfree(phyinfo);
 	mutex_unlock(&cnfg->lock);
+	return res;
 }
 EXPORT_SYMBOL(cfcnfg_add_phy_layer);
 
-- 
cgit v1.2.3


From 9257bd80b917cc7908abd27ed5a5211964563f62 Mon Sep 17 00:00:00 2001
From: Kyle Tso <kyletso@google.com>
Date: Thu, 27 May 2021 20:10:29 +0800
Subject: dt-bindings: connector: Replace BIT macro with generic bit ops

BIT macro is not defined. Replace it with generic bit operations.

Fixes: 630dce2810b9 ("dt-bindings: connector: Add SVDM VDO properties")
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Kyle Tso <kyletso@google.com>
Link: https://lore.kernel.org/r/20210527121029.583611-1-kyletso@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/dt-bindings/usb/pd.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/dt-bindings/usb/pd.h b/include/dt-bindings/usb/pd.h
index fef3ef65967f..cb70b4ceedde 100644
--- a/include/dt-bindings/usb/pd.h
+++ b/include/dt-bindings/usb/pd.h
@@ -163,10 +163,10 @@
 #define UFP_VDO_VER1_2		2
 
 /* Device Capability */
-#define DEV_USB2_CAPABLE	BIT(0)
-#define DEV_USB2_BILLBOARD	BIT(1)
-#define DEV_USB3_CAPABLE	BIT(2)
-#define DEV_USB4_CAPABLE	BIT(3)
+#define DEV_USB2_CAPABLE	(1 << 0)
+#define DEV_USB2_BILLBOARD	(1 << 1)
+#define DEV_USB3_CAPABLE	(1 << 2)
+#define DEV_USB4_CAPABLE	(1 << 3)
 
 /* Connector Type */
 #define UFP_RECEPTACLE		2
@@ -191,9 +191,9 @@
 
 /* Alternate Modes */
 #define UFP_ALTMODE_NOT_SUPP	0
-#define UFP_ALTMODE_TBT3	BIT(0)
-#define UFP_ALTMODE_RECFG	BIT(1)
-#define UFP_ALTMODE_NO_RECFG	BIT(2)
+#define UFP_ALTMODE_TBT3	(1 << 0)
+#define UFP_ALTMODE_RECFG	(1 << 1)
+#define UFP_ALTMODE_NO_RECFG	(1 << 2)
 
 /* USB Highest Speed */
 #define UFP_USB2_ONLY		0
@@ -217,9 +217,9 @@
  * <4:0>   :: Port number
  */
 #define DFP_VDO_VER1_1		1
-#define HOST_USB2_CAPABLE	BIT(0)
-#define HOST_USB3_CAPABLE	BIT(1)
-#define HOST_USB4_CAPABLE	BIT(2)
+#define HOST_USB2_CAPABLE	(1 << 0)
+#define HOST_USB3_CAPABLE	(1 << 1)
+#define HOST_USB4_CAPABLE	(1 << 2)
 #define DFP_RECEPTACLE		2
 #define DFP_CAPTIVE		3
 
-- 
cgit v1.2.3


From 55b54c269beef13d88dc30544df34763a90dc815 Mon Sep 17 00:00:00 2001
From: Kyle Tso <kyletso@google.com>
Date: Tue, 1 Jun 2021 20:31:49 +0800
Subject: dt-bindings: connector: Add PD rev 2.0 VDO definition

Add the VDO definition for USB PD rev 2.0 in the bindings and define a
new property snk-vdos-v1 containing legacy VDOs as the responses to the
port partner which only supports PD rev 2.0.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Kyle Tso <kyletso@google.com>
Link: https://lore.kernel.org/r/20210601123151.3441914-3-kyletso@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../bindings/connector/usb-connector.yaml          | 15 +++++
 include/dt-bindings/usb/pd.h                       | 69 +++++++++++++++++++++-
 2 files changed, 81 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/connector/usb-connector.yaml b/Documentation/devicetree/bindings/connector/usb-connector.yaml
index 32509b98142e..92b49bc37939 100644
--- a/Documentation/devicetree/bindings/connector/usb-connector.yaml
+++ b/Documentation/devicetree/bindings/connector/usb-connector.yaml
@@ -149,6 +149,17 @@ properties:
     maxItems: 6
     $ref: /schemas/types.yaml#/definitions/uint32-array
 
+  sink-vdos-v1:
+    description: An array of u32 with each entry, a Vendor Defined Message Object (VDO),
+      providing additional information corresponding to the product, the detailed bit
+      definitions and the order of each VDO can be found in
+      "USB Power Delivery Specification Revision 2.0, Version 1.3" chapter 6.4.4.3.1 Discover
+      Identity. User can specify the VDO array via VDO_IDH/_CERT/_PRODUCT/_CABLE/_AMA defined in
+      dt-bindings/usb/pd.h.
+    minItems: 3
+    maxItems: 6
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+
   op-sink-microwatt:
     description: Sink required operating power in microwatt, if source can't
       offer the power, Capability Mismatch is set. Required for power sink and
@@ -207,6 +218,10 @@ properties:
       SNK_READY for non-pd link.
     type: boolean
 
+dependencies:
+  sink-vdos-v1: [ 'sink-vdos' ]
+  sink-vdos: [ 'sink-vdos-v1' ]
+
 required:
   - compatible
 
diff --git a/include/dt-bindings/usb/pd.h b/include/dt-bindings/usb/pd.h
index cb70b4ceedde..e6526b138174 100644
--- a/include/dt-bindings/usb/pd.h
+++ b/include/dt-bindings/usb/pd.h
@@ -106,6 +106,10 @@
  * <20:16>  :: Reserved, Shall be set to zero
  * <15:0>   :: USB-IF assigned VID for this cable vendor
  */
+
+/* PD Rev2.0 definition */
+#define IDH_PTYPE_UNDEF		0
+
 /* SOP Product Type (UFP) */
 #define IDH_PTYPE_NOT_UFP       0
 #define IDH_PTYPE_HUB           1
@@ -228,7 +232,25 @@
 	 | ((pnum) & 0x1f))
 
 /*
- * Passive Cable VDO
+ * Cable VDO (for both Passive and Active Cable VDO in PD Rev2.0)
+ * ---------
+ * <31:28> :: Cable HW version
+ * <27:24> :: Cable FW version
+ * <23:20> :: Reserved, Shall be set to zero
+ * <19:18> :: type-C to Type-A/B/C/Captive (00b == A, 01 == B, 10 == C, 11 == Captive)
+ * <17>    :: Reserved, Shall be set to zero
+ * <16:13> :: cable latency (0001 == <10ns(~1m length))
+ * <12:11> :: cable termination type (11b == both ends active VCONN req)
+ * <10>    :: SSTX1 Directionality support (0b == fixed, 1b == cfgable)
+ * <9>     :: SSTX2 Directionality support
+ * <8>     :: SSRX1 Directionality support
+ * <7>     :: SSRX2 Directionality support
+ * <6:5>   :: Vbus current handling capability (01b == 3A, 10b == 5A)
+ * <4>     :: Vbus through cable (0b == no, 1b == yes)
+ * <3>     :: SOP" controller present? (0b == no, 1b == yes)
+ * <2:0>   :: USB SS Signaling support
+ *
+ * Passive Cable VDO (PD Rev3.0+)
  * ---------
  * <31:28> :: Cable HW version
  * <27:24> :: Cable FW version
@@ -244,7 +266,7 @@
  * <4:3>   :: Reserved, Shall be set to zero
  * <2:0>   :: USB highest speed
  *
- * Active Cable VDO 1
+ * Active Cable VDO 1 (PD Rev3.0+)
  * ---------
  * <31:28> :: Cable HW version
  * <27:24> :: Cable FW version
@@ -266,7 +288,9 @@
 #define CABLE_VDO_VER1_0	0
 #define CABLE_VDO_VER1_3	3
 
-/* Connector Type */
+/* Connector Type (_ATYPE and _BTYPE are for PD Rev2.0 only) */
+#define CABLE_ATYPE		0
+#define CABLE_BTYPE		1
 #define CABLE_CTYPE		2
 #define CABLE_CAPTIVE		3
 
@@ -303,12 +327,22 @@
 #define CABLE_CURR_3A		1
 #define CABLE_CURR_5A		2
 
+/* USB SuperSpeed Signaling Support (PD Rev2.0) */
+#define CABLE_USBSS_U2_ONLY	0
+#define CABLE_USBSS_U31_GEN1	1
+#define CABLE_USBSS_U31_GEN2	2
+
 /* USB Highest Speed */
 #define CABLE_USB2_ONLY		0
 #define CABLE_USB32_GEN1	1
 #define CABLE_USB32_4_GEN2	2
 #define CABLE_USB4_GEN3		3
 
+#define VDO_CABLE(hw, fw, cbl, lat, term, tx1d, tx2d, rx1d, rx2d, cur, vps, sopp, usbss) \
+	(((hw) & 0x7) << 28 | ((fw) & 0x7) << 24 | ((cbl) & 0x3) << 18		\
+	 | ((lat) & 0x7) << 13 | ((term) & 0x3) << 11 | (tx1d) << 10		\
+	 | (tx2d) << 9 | (rx1d) << 8 | (rx2d) << 7 | ((cur) & 0x3) << 5		\
+	 | (vps) << 4 | (sopp) << 3 | ((usbss) & 0x7))
 #define VDO_PCABLE(hw, fw, ver, conn, lat, term, vbm, cur, spd)			\
 	(((hw) & 0xf) << 28 | ((fw) & 0xf) << 24 | ((ver) & 0x7) << 21		\
 	 | ((conn) & 0x3) << 18 | ((lat) & 0xf) << 13 | ((term) & 0x3) << 11	\
@@ -373,6 +407,35 @@
 	 | ((hops) & 0x3) << 6 | (u2) << 5 | (u32) << 4 | (lane) << 3		\
 	 | (iso) << 2 | (gen))
 
+/*
+ * AMA VDO (PD Rev2.0)
+ * ---------
+ * <31:28> :: Cable HW version
+ * <27:24> :: Cable FW version
+ * <23:12> :: Reserved, Shall be set to zero
+ * <11>    :: SSTX1 Directionality support (0b == fixed, 1b == cfgable)
+ * <10>    :: SSTX2 Directionality support
+ * <9>     :: SSRX1 Directionality support
+ * <8>     :: SSRX2 Directionality support
+ * <7:5>   :: Vconn power
+ * <4>     :: Vconn power required
+ * <3>     :: Vbus power required
+ * <2:0>   :: USB SS Signaling support
+ */
+#define VDO_AMA(hw, fw, tx1d, tx2d, rx1d, rx2d, vcpwr, vcr, vbr, usbss) \
+	(((hw) & 0x7) << 28 | ((fw) & 0x7) << 24			\
+	 | (tx1d) << 11 | (tx2d) << 10 | (rx1d) << 9 | (rx2d) << 8	\
+	 | ((vcpwr) & 0x7) << 5 | (vcr) << 4 | (vbr) << 3		\
+	 | ((usbss) & 0x7))
+
+#define PD_VDO_AMA_VCONN_REQ(vdo)	(((vdo) >> 4) & 1)
+#define PD_VDO_AMA_VBUS_REQ(vdo)	(((vdo) >> 3) & 1)
+
+#define AMA_USBSS_U2_ONLY	0
+#define AMA_USBSS_U31_GEN1	1
+#define AMA_USBSS_U31_GEN2	2
+#define AMA_USBSS_BBONLY	3
+
 /*
  * VPD VDO
  * ---------
-- 
cgit v1.2.3


From 063933f47a7af01650af9c4fbcc5831f1c4eb7d9 Mon Sep 17 00:00:00 2001
From: Kyle Tso <kyletso@google.com>
Date: Tue, 1 Jun 2021 00:49:28 +0800
Subject: usb: typec: tcpm: Properly handle Alert and Status Messages

When receiving Alert Message, if it is not unexpected but is
unsupported for some reason, the port should return Not_Supported
Message response.

Also, according to PD3.0 Spec 6.5.2.1.4 Event Flags Field, the
OTP/OVP/OCP flags in the Event Flags field in Status Message no longer
require Get_PPS_Status Message to clear them. Thus remove it when
receiving Status Message with those flags being set.

In addition, add the missing AMS operations for Status Message.

Fixes: 64f7c494a3c0 ("typec: tcpm: Add support for sink PPS related messages")
Fixes: 0908c5aca31e ("usb: typec: tcpm: AMS and Collision Avoidance")
Signed-off-by: Kyle Tso <kyletso@google.com>
Link: https://lore.kernel.org/r/20210531164928.2368606-1-kyletso@google.com
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c  | 52 ++++++++++++++++++++++--------------------
 include/linux/usb/pd_ext_sdb.h |  4 ----
 2 files changed, 27 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 6161a0c1dc0e..938a1afd43ec 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -2188,20 +2188,25 @@ static void tcpm_handle_alert(struct tcpm_port *port, const __le32 *payload,
 
 	if (!type) {
 		tcpm_log(port, "Alert message received with no type");
+		tcpm_queue_message(port, PD_MSG_CTRL_NOT_SUPP);
 		return;
 	}
 
 	/* Just handling non-battery alerts for now */
 	if (!(type & USB_PD_ADO_TYPE_BATT_STATUS_CHANGE)) {
-		switch (port->state) {
-		case SRC_READY:
-		case SNK_READY:
+		if (port->pwr_role == TYPEC_SOURCE) {
+			port->upcoming_state = GET_STATUS_SEND;
+			tcpm_ams_start(port, GETTING_SOURCE_SINK_STATUS);
+		} else {
+			/*
+			 * Do not check SinkTxOk here in case the Source doesn't set its Rp to
+			 * SinkTxOk in time.
+			 */
+			port->ams = GETTING_SOURCE_SINK_STATUS;
 			tcpm_set_state(port, GET_STATUS_SEND, 0);
-			break;
-		default:
-			tcpm_queue_message(port, PD_MSG_CTRL_WAIT);
-			break;
 		}
+	} else {
+		tcpm_queue_message(port, PD_MSG_CTRL_NOT_SUPP);
 	}
 }
 
@@ -2445,7 +2450,12 @@ static void tcpm_pd_data_request(struct tcpm_port *port,
 		tcpm_pd_handle_state(port, BIST_RX, BIST, 0);
 		break;
 	case PD_DATA_ALERT:
-		tcpm_handle_alert(port, msg->payload, cnt);
+		if (port->state != SRC_READY && port->state != SNK_READY)
+			tcpm_pd_handle_state(port, port->pwr_role == TYPEC_SOURCE ?
+					     SRC_SOFT_RESET_WAIT_SNK_TX : SNK_SOFT_RESET,
+					     NONE_AMS, 0);
+		else
+			tcpm_handle_alert(port, msg->payload, cnt);
 		break;
 	case PD_DATA_BATT_STATUS:
 	case PD_DATA_GET_COUNTRY_INFO:
@@ -2769,24 +2779,16 @@ static void tcpm_pd_ext_msg_request(struct tcpm_port *port,
 
 	switch (type) {
 	case PD_EXT_STATUS:
-		/*
-		 * If PPS related events raised then get PPS status to clear
-		 * (see USB PD 3.0 Spec, 6.5.2.4)
-		 */
-		if (msg->ext_msg.data[USB_PD_EXT_SDB_EVENT_FLAGS] &
-		    USB_PD_EXT_SDB_PPS_EVENTS)
-			tcpm_pd_handle_state(port, GET_PPS_STATUS_SEND,
-					     GETTING_SOURCE_SINK_STATUS, 0);
-
-		else
-			tcpm_pd_handle_state(port, ready_state(port), NONE_AMS, 0);
-		break;
 	case PD_EXT_PPS_STATUS:
-		/*
-		 * For now the PPS status message is used to clear events
-		 * and nothing more.
-		 */
-		tcpm_pd_handle_state(port, ready_state(port), NONE_AMS, 0);
+		if (port->ams == GETTING_SOURCE_SINK_STATUS) {
+			tcpm_ams_finish(port);
+			tcpm_set_state(port, ready_state(port), 0);
+		} else {
+			/* unexpected Status or PPS_Status Message */
+			tcpm_pd_handle_state(port, port->pwr_role == TYPEC_SOURCE ?
+					     SRC_SOFT_RESET_WAIT_SNK_TX : SNK_SOFT_RESET,
+					     NONE_AMS, 0);
+		}
 		break;
 	case PD_EXT_SOURCE_CAP_EXT:
 	case PD_EXT_GET_BATT_CAP:
diff --git a/include/linux/usb/pd_ext_sdb.h b/include/linux/usb/pd_ext_sdb.h
index 0eb83ce19597..b517ebc8f0ff 100644
--- a/include/linux/usb/pd_ext_sdb.h
+++ b/include/linux/usb/pd_ext_sdb.h
@@ -24,8 +24,4 @@ enum usb_pd_ext_sdb_fields {
 #define USB_PD_EXT_SDB_EVENT_OVP		BIT(3)
 #define USB_PD_EXT_SDB_EVENT_CF_CV_MODE		BIT(4)
 
-#define USB_PD_EXT_SDB_PPS_EVENTS	(USB_PD_EXT_SDB_EVENT_OCP |	\
-					 USB_PD_EXT_SDB_EVENT_OTP |	\
-					 USB_PD_EXT_SDB_EVENT_OVP)
-
 #endif /* __LINUX_USB_PD_EXT_SDB_H */
-- 
cgit v1.2.3


From 519d8ab17682da5f2fae5941d906d85b9fd3593a Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Wed, 19 May 2021 21:43:50 +0200
Subject: virtchnl: Add missing padding to virtchnl_proto_hdrs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On m68k (Coldfire M547x):

      CC      drivers/net/ethernet/intel/i40e/i40e_main.o
    In file included from drivers/net/ethernet/intel/i40e/i40e_prototype.h:9,
		     from drivers/net/ethernet/intel/i40e/i40e.h:41,
		     from drivers/net/ethernet/intel/i40e/i40e_main.c:12:
    include/linux/avf/virtchnl.h:153:36: warning: division by zero [-Wdiv-by-zero]
      153 |  { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) }
	  |                                    ^
    include/linux/avf/virtchnl.h:844:1: note: in expansion of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’
      844 | VIRTCHNL_CHECK_STRUCT_LEN(2312, virtchnl_proto_hdrs);
	  | ^~~~~~~~~~~~~~~~~~~~~~~~~
    include/linux/avf/virtchnl.h:844:33: error: enumerator value for ‘virtchnl_static_assert_virtchnl_proto_hdrs’ is not an integer constant
      844 | VIRTCHNL_CHECK_STRUCT_LEN(2312, virtchnl_proto_hdrs);
	  |                                 ^~~~~~~~~~~~~~~~~~~

On m68k, integers are aligned on addresses that are multiples of two,
not four, bytes.  Hence the size of a structure containing integers may
not be divisible by 4.

Fix this by adding explicit padding.

Fixes: 1f7ea1cd6a374842 ("ice: Enable FDIR Configure for AVF")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 include/linux/avf/virtchnl.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 565deea6ffe8..8612f8fc86c1 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -830,6 +830,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_proto_hdr);
 
 struct virtchnl_proto_hdrs {
 	u8 tunnel_level;
+	u8 pad[3];
 	/**
 	 * specify where protocol header start from.
 	 * 0 - from the outer layer
-- 
cgit v1.2.3


From 50c25ee97cf6ab011542167ab590c17012cea4ed Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Date: Fri, 4 Jun 2021 20:01:08 -0700
Subject: Revert "MIPS: make userspace mapping young by default"

This reverts commit f685a533a7fab35c5d069dcd663f59c8e4171a75.

The MIPS cache flush logic needs to know whether the mapping was already
established to decide how to flush caches.  This is done by checking the
valid bit in the PTE.  The commit above breaks this logic by setting the
valid in the PTE in new mappings, which causes kernel crashes.

Link: https://lkml.kernel.org/r/20210526094335.92948-1-tsbogend@alpha.franken.de
Fixes: f685a533a7f ("MIPS: make userspace mapping young by default")
Reported-by: Zhou Yanjie <zhouyanjie@wanyeetech.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huang Pei <huangpei@loongson.cn>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/mips/mm/cache.c    | 30 ++++++++++++++----------------
 include/linux/pgtable.h |  8 ++++++++
 mm/memory.c             |  4 ++++
 3 files changed, 26 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index a7bf0c80371c..830ab91e574f 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -158,31 +158,29 @@ unsigned long _page_cachable_default;
 EXPORT_SYMBOL(_page_cachable_default);
 
 #define PM(p)	__pgprot(_page_cachable_default | (p))
-#define PVA(p)	PM(_PAGE_VALID | _PAGE_ACCESSED | (p))
 
 static inline void setup_protection_map(void)
 {
 	protection_map[0]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
-	protection_map[1]  = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC);
-	protection_map[2]  = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
-	protection_map[3]  = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC);
-	protection_map[4]  = PVA(_PAGE_PRESENT);
-	protection_map[5]  = PVA(_PAGE_PRESENT);
-	protection_map[6]  = PVA(_PAGE_PRESENT);
-	protection_map[7]  = PVA(_PAGE_PRESENT);
+	protection_map[1]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC);
+	protection_map[2]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
+	protection_map[3]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC);
+	protection_map[4]  = PM(_PAGE_PRESENT);
+	protection_map[5]  = PM(_PAGE_PRESENT);
+	protection_map[6]  = PM(_PAGE_PRESENT);
+	protection_map[7]  = PM(_PAGE_PRESENT);
 
 	protection_map[8]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
-	protection_map[9]  = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC);
-	protection_map[10] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE |
+	protection_map[9]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC);
+	protection_map[10] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE |
 				_PAGE_NO_READ);
-	protection_map[11] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE);
-	protection_map[12] = PVA(_PAGE_PRESENT);
-	protection_map[13] = PVA(_PAGE_PRESENT);
-	protection_map[14] = PVA(_PAGE_PRESENT);
-	protection_map[15] = PVA(_PAGE_PRESENT);
+	protection_map[11] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE);
+	protection_map[12] = PM(_PAGE_PRESENT);
+	protection_map[13] = PM(_PAGE_PRESENT);
+	protection_map[14] = PM(_PAGE_PRESENT | _PAGE_WRITE);
+	protection_map[15] = PM(_PAGE_PRESENT | _PAGE_WRITE);
 }
 
-#undef _PVA
 #undef PM
 
 void cpu_cache_init(void)
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 46b13780c2c8..a43047b1030d 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -432,6 +432,14 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres
  * To be differentiate with macro pte_mkyoung, this macro is used on platforms
  * where software maintains page access bit.
  */
+#ifndef pte_sw_mkyoung
+static inline pte_t pte_sw_mkyoung(pte_t pte)
+{
+	return pte;
+}
+#define pte_sw_mkyoung	pte_sw_mkyoung
+#endif
+
 #ifndef pte_savedwrite
 #define pte_savedwrite pte_write
 #endif
diff --git a/mm/memory.c b/mm/memory.c
index 730daa00952b..f3ffab9b9e39 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2939,6 +2939,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		}
 		flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
 		entry = mk_pte(new_page, vma->vm_page_prot);
+		entry = pte_sw_mkyoung(entry);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 
 		/*
@@ -3602,6 +3603,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	__SetPageUptodate(page);
 
 	entry = mk_pte(page, vma->vm_page_prot);
+	entry = pte_sw_mkyoung(entry);
 	if (vma->vm_flags & VM_WRITE)
 		entry = pte_mkwrite(pte_mkdirty(entry));
 
@@ -3786,6 +3788,8 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
 
 	if (prefault && arch_wants_old_prefaulted_pte())
 		entry = pte_mkold(entry);
+	else
+		entry = pte_sw_mkyoung(entry);
 
 	if (write)
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-- 
cgit v1.2.3


From da27a83fd6cc7780fea190e1f5c19e87019da65c Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Tue, 8 Jun 2021 15:31:42 -0400
Subject: kvm: avoid speculation-based attacks from out-of-range memslot
 accesses

KVM's mechanism for accessing guest memory translates a guest physical
address (gpa) to a host virtual address using the right-shifted gpa
(also known as gfn) and a struct kvm_memory_slot.  The translation is
performed in __gfn_to_hva_memslot using the following formula:

      hva = slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE

It is expected that gfn falls within the boundaries of the guest's
physical memory.  However, a guest can access invalid physical addresses
in such a way that the gfn is invalid.

__gfn_to_hva_memslot is called from kvm_vcpu_gfn_to_hva_prot, which first
retrieves a memslot through __gfn_to_memslot.  While __gfn_to_memslot
does check that the gfn falls within the boundaries of the guest's
physical memory or not, a CPU can speculate the result of the check and
continue execution speculatively using an illegal gfn. The speculation
can result in calculating an out-of-bounds hva.  If the resulting host
virtual address is used to load another guest physical address, this
is effectively a Spectre gadget consisting of two consecutive reads,
the second of which is data dependent on the first.

Right now it's not clear if there are any cases in which this is
exploitable.  One interesting case was reported by the original author
of this patch, and involves visiting guest page tables on x86.  Right
now these are not vulnerable because the hva read goes through get_user(),
which contains an LFENCE speculation barrier.  However, there are
patches in progress for x86 uaccess.h to mask kernel addresses instead of
using LFENCE; once these land, a guest could use speculation to read
from the VMM's ring 3 address space.  Other architectures such as ARM
already use the address masking method, and would be susceptible to
this same kind of data-dependent access gadgets.  Therefore, this patch
proactively protects from these attacks by masking out-of-bounds gfns
in __gfn_to_hva_memslot, which blocks speculation of invalid hvas.

Sean Christopherson noted that this patch does not cover
kvm_read_guest_offset_cached.  This however is limited to a few bytes
past the end of the cache, and therefore it is unlikely to be useful in
the context of building a chain of data dependent accesses.

Reported-by: Artemiy Margaritov <artemiy.margaritov@gmail.com>
Co-developed-by: Artemiy Margaritov <artemiy.margaritov@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 76102efbf079..74995f0a2a3c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1185,7 +1185,15 @@ __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn)
 static inline unsigned long
 __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE;
+	/*
+	 * The index was checked originally in search_memslots.  To avoid
+	 * that a malicious guest builds a Spectre gadget out of e.g. page
+	 * table walks, do not let the processor speculate loads outside
+	 * the guest's registered memslots.
+	 */
+	unsigned long offset = array_index_nospec(gfn - slot->base_gfn,
+						  slot->npages);
+	return slot->userspace_addr + offset * PAGE_SIZE;
 }
 
 static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
-- 
cgit v1.2.3


From 4422829e8053068e0225e4d0ef42dc41ea7c9ef5 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 9 Jun 2021 01:49:13 -0400
Subject: kvm: fix previous commit for 32-bit builds

array_index_nospec does not work for uint64_t on 32-bit builds.
However, the size of a memory slot must be less than 20 bits wide
on those system, since the memory slot must fit in the user
address space.  So just store it in an unsigned long.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 74995f0a2a3c..8583ed3ff344 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1191,8 +1191,8 @@ __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn)
 	 * table walks, do not let the processor speculate loads outside
 	 * the guest's registered memslots.
 	 */
-	unsigned long offset = array_index_nospec(gfn - slot->base_gfn,
-						  slot->npages);
+	unsigned long offset = gfn - slot->base_gfn;
+	offset = array_index_nospec(offset, slot->npages);
 	return slot->userspace_addr + offset * PAGE_SIZE;
 }
 
-- 
cgit v1.2.3


From 3df4fce739e2b263120f528c5e0fe6b2f8937b5b Mon Sep 17 00:00:00 2001
From: Ricky Wu <ricky_wu@realtek.com>
Date: Mon, 7 Jun 2021 18:16:34 +0800
Subject: misc: rtsx: separate aspm mode into MODE_REG and MODE_CFG

aspm (Active State Power Management)
rtsx_comm_set_aspm: this function is for driver to make sure
not enter power saving when processing of init and card_detcct
ASPM_MODE_CFG: 8411 5209 5227 5229 5249 5250
Change back to use original way to control aspm
ASPM_MODE_REG: 5227A 524A 5250A 5260 5261 5228
Keep the new way to control aspm

Fixes: 121e9c6b5c4c ("misc: rtsx: modify and fix init_hw function")
Reported-by: Chris Chiu <chris.chiu@canonical.com>
Tested-by: Gordon Lack <gordon.lack@dsl.pipex.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Ricky Wu <ricky_wu@realtek.com>
Link: https://lore.kernel.org/r/20210607101634.4948-1-ricky_wu@realtek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/cardreader/rtl8411.c  |  1 +
 drivers/misc/cardreader/rts5209.c  |  1 +
 drivers/misc/cardreader/rts5227.c  |  2 ++
 drivers/misc/cardreader/rts5228.c  |  1 +
 drivers/misc/cardreader/rts5229.c  |  1 +
 drivers/misc/cardreader/rts5249.c  |  3 +++
 drivers/misc/cardreader/rts5260.c  |  1 +
 drivers/misc/cardreader/rts5261.c  |  1 +
 drivers/misc/cardreader/rtsx_pcr.c | 44 +++++++++++++++++++++++++++-----------
 include/linux/rtsx_pci.h           |  2 ++
 10 files changed, 44 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/cardreader/rtl8411.c b/drivers/misc/cardreader/rtl8411.c
index a07674ed0596..4c5621b17a6f 100644
--- a/drivers/misc/cardreader/rtl8411.c
+++ b/drivers/misc/cardreader/rtl8411.c
@@ -468,6 +468,7 @@ static void rtl8411_init_common_params(struct rtsx_pcr *pcr)
 	pcr->sd30_drive_sel_1v8 = DRIVER_TYPE_B;
 	pcr->sd30_drive_sel_3v3 = DRIVER_TYPE_D;
 	pcr->aspm_en = ASPM_L1_EN;
+	pcr->aspm_mode = ASPM_MODE_CFG;
 	pcr->tx_initial_phase = SET_CLOCK_PHASE(23, 7, 14);
 	pcr->rx_initial_phase = SET_CLOCK_PHASE(4, 3, 10);
 	pcr->ic_version = rtl8411_get_ic_version(pcr);
diff --git a/drivers/misc/cardreader/rts5209.c b/drivers/misc/cardreader/rts5209.c
index 39a6a7ecc32e..29f5414072bf 100644
--- a/drivers/misc/cardreader/rts5209.c
+++ b/drivers/misc/cardreader/rts5209.c
@@ -255,6 +255,7 @@ void rts5209_init_params(struct rtsx_pcr *pcr)
 	pcr->sd30_drive_sel_1v8 = DRIVER_TYPE_B;
 	pcr->sd30_drive_sel_3v3 = DRIVER_TYPE_D;
 	pcr->aspm_en = ASPM_L1_EN;
+	pcr->aspm_mode = ASPM_MODE_CFG;
 	pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 27, 16);
 	pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5);
 
diff --git a/drivers/misc/cardreader/rts5227.c b/drivers/misc/cardreader/rts5227.c
index 8200af22b529..4bcfbc9afbac 100644
--- a/drivers/misc/cardreader/rts5227.c
+++ b/drivers/misc/cardreader/rts5227.c
@@ -358,6 +358,7 @@ void rts5227_init_params(struct rtsx_pcr *pcr)
 	pcr->sd30_drive_sel_1v8 = CFG_DRIVER_TYPE_B;
 	pcr->sd30_drive_sel_3v3 = CFG_DRIVER_TYPE_B;
 	pcr->aspm_en = ASPM_L1_EN;
+	pcr->aspm_mode = ASPM_MODE_CFG;
 	pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 27, 15);
 	pcr->rx_initial_phase = SET_CLOCK_PHASE(30, 7, 7);
 
@@ -483,6 +484,7 @@ void rts522a_init_params(struct rtsx_pcr *pcr)
 
 	rts5227_init_params(pcr);
 	pcr->ops = &rts522a_pcr_ops;
+	pcr->aspm_mode = ASPM_MODE_REG;
 	pcr->tx_initial_phase = SET_CLOCK_PHASE(20, 20, 11);
 	pcr->reg_pm_ctrl3 = RTS522A_PM_CTRL3;
 
diff --git a/drivers/misc/cardreader/rts5228.c b/drivers/misc/cardreader/rts5228.c
index 781a86def59a..ffc128278613 100644
--- a/drivers/misc/cardreader/rts5228.c
+++ b/drivers/misc/cardreader/rts5228.c
@@ -718,6 +718,7 @@ void rts5228_init_params(struct rtsx_pcr *pcr)
 	pcr->sd30_drive_sel_1v8 = CFG_DRIVER_TYPE_B;
 	pcr->sd30_drive_sel_3v3 = CFG_DRIVER_TYPE_B;
 	pcr->aspm_en = ASPM_L1_EN;
+	pcr->aspm_mode = ASPM_MODE_REG;
 	pcr->tx_initial_phase = SET_CLOCK_PHASE(28, 27, 11);
 	pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5);
 
diff --git a/drivers/misc/cardreader/rts5229.c b/drivers/misc/cardreader/rts5229.c
index 89e6f124ca5c..c748eaf1ec1f 100644
--- a/drivers/misc/cardreader/rts5229.c
+++ b/drivers/misc/cardreader/rts5229.c
@@ -246,6 +246,7 @@ void rts5229_init_params(struct rtsx_pcr *pcr)
 	pcr->sd30_drive_sel_1v8 = DRIVER_TYPE_B;
 	pcr->sd30_drive_sel_3v3 = DRIVER_TYPE_D;
 	pcr->aspm_en = ASPM_L1_EN;
+	pcr->aspm_mode = ASPM_MODE_CFG;
 	pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 27, 15);
 	pcr->rx_initial_phase = SET_CLOCK_PHASE(30, 6, 6);
 
diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c
index b2676e7f5027..53f3a1f45c4a 100644
--- a/drivers/misc/cardreader/rts5249.c
+++ b/drivers/misc/cardreader/rts5249.c
@@ -566,6 +566,7 @@ void rts5249_init_params(struct rtsx_pcr *pcr)
 	pcr->sd30_drive_sel_1v8 = CFG_DRIVER_TYPE_B;
 	pcr->sd30_drive_sel_3v3 = CFG_DRIVER_TYPE_B;
 	pcr->aspm_en = ASPM_L1_EN;
+	pcr->aspm_mode = ASPM_MODE_CFG;
 	pcr->tx_initial_phase = SET_CLOCK_PHASE(1, 29, 16);
 	pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5);
 
@@ -729,6 +730,7 @@ static const struct pcr_ops rts524a_pcr_ops = {
 void rts524a_init_params(struct rtsx_pcr *pcr)
 {
 	rts5249_init_params(pcr);
+	pcr->aspm_mode = ASPM_MODE_REG;
 	pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 29, 11);
 	pcr->option.ltr_l1off_sspwrgate = LTR_L1OFF_SSPWRGATE_5250_DEF;
 	pcr->option.ltr_l1off_snooze_sspwrgate =
@@ -845,6 +847,7 @@ static const struct pcr_ops rts525a_pcr_ops = {
 void rts525a_init_params(struct rtsx_pcr *pcr)
 {
 	rts5249_init_params(pcr);
+	pcr->aspm_mode = ASPM_MODE_REG;
 	pcr->tx_initial_phase = SET_CLOCK_PHASE(25, 29, 11);
 	pcr->option.ltr_l1off_sspwrgate = LTR_L1OFF_SSPWRGATE_5250_DEF;
 	pcr->option.ltr_l1off_snooze_sspwrgate =
diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c
index 080a7d67a8e1..9b42b20a3e5a 100644
--- a/drivers/misc/cardreader/rts5260.c
+++ b/drivers/misc/cardreader/rts5260.c
@@ -628,6 +628,7 @@ void rts5260_init_params(struct rtsx_pcr *pcr)
 	pcr->sd30_drive_sel_1v8 = CFG_DRIVER_TYPE_B;
 	pcr->sd30_drive_sel_3v3 = CFG_DRIVER_TYPE_B;
 	pcr->aspm_en = ASPM_L1_EN;
+	pcr->aspm_mode = ASPM_MODE_REG;
 	pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 29, 11);
 	pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5);
 
diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c
index 6c64dade8e1a..1fd4e0e50730 100644
--- a/drivers/misc/cardreader/rts5261.c
+++ b/drivers/misc/cardreader/rts5261.c
@@ -783,6 +783,7 @@ void rts5261_init_params(struct rtsx_pcr *pcr)
 	pcr->sd30_drive_sel_1v8 = 0x00;
 	pcr->sd30_drive_sel_3v3 = 0x00;
 	pcr->aspm_en = ASPM_L1_EN;
+	pcr->aspm_mode = ASPM_MODE_REG;
 	pcr->tx_initial_phase = SET_CLOCK_PHASE(27, 27, 11);
 	pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5);
 
diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index 273311184669..baf83594a01d 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -85,12 +85,18 @@ static void rtsx_comm_set_aspm(struct rtsx_pcr *pcr, bool enable)
 	if (pcr->aspm_enabled == enable)
 		return;
 
-	if (pcr->aspm_en & 0x02)
-		rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, FORCE_ASPM_CTL0 |
-			FORCE_ASPM_CTL1, enable ? 0 : FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1);
-	else
-		rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, FORCE_ASPM_CTL0 |
-			FORCE_ASPM_CTL1, FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1);
+	if (pcr->aspm_mode == ASPM_MODE_CFG) {
+		pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL,
+						PCI_EXP_LNKCTL_ASPMC,
+						enable ? pcr->aspm_en : 0);
+	} else if (pcr->aspm_mode == ASPM_MODE_REG) {
+		if (pcr->aspm_en & 0x02)
+			rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, FORCE_ASPM_CTL0 |
+				FORCE_ASPM_CTL1, enable ? 0 : FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1);
+		else
+			rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, FORCE_ASPM_CTL0 |
+				FORCE_ASPM_CTL1, FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1);
+	}
 
 	if (!enable && (pcr->aspm_en & 0x02))
 		mdelay(10);
@@ -1394,7 +1400,8 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 			return err;
 	}
 
-	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0x30, 0x30);
+	if (pcr->aspm_mode == ASPM_MODE_REG)
+		rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0x30, 0x30);
 
 	/* No CD interrupt if probing driver with card inserted.
 	 * So we need to initialize pcr->card_exist here.
@@ -1410,6 +1417,8 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 static int rtsx_pci_init_chip(struct rtsx_pcr *pcr)
 {
 	int err;
+	u16 cfg_val;
+	u8 val;
 
 	spin_lock_init(&pcr->lock);
 	mutex_init(&pcr->pcr_mutex);
@@ -1477,6 +1486,21 @@ static int rtsx_pci_init_chip(struct rtsx_pcr *pcr)
 	if (!pcr->slots)
 		return -ENOMEM;
 
+	if (pcr->aspm_mode == ASPM_MODE_CFG) {
+		pcie_capability_read_word(pcr->pci, PCI_EXP_LNKCTL, &cfg_val);
+		if (cfg_val & PCI_EXP_LNKCTL_ASPM_L1)
+			pcr->aspm_enabled = true;
+		else
+			pcr->aspm_enabled = false;
+
+	} else if (pcr->aspm_mode == ASPM_MODE_REG) {
+		rtsx_pci_read_register(pcr, ASPM_FORCE_CTL, &val);
+		if (val & FORCE_ASPM_CTL0 && val & FORCE_ASPM_CTL1)
+			pcr->aspm_enabled = false;
+		else
+			pcr->aspm_enabled = true;
+	}
+
 	if (pcr->ops->fetch_vendor_settings)
 		pcr->ops->fetch_vendor_settings(pcr);
 
@@ -1506,7 +1530,6 @@ static int rtsx_pci_probe(struct pci_dev *pcidev,
 	struct pcr_handle *handle;
 	u32 base, len;
 	int ret, i, bar = 0;
-	u8 val;
 
 	dev_dbg(&(pcidev->dev),
 		": Realtek PCI-E Card Reader found at %s [%04x:%04x] (rev %x)\n",
@@ -1572,11 +1595,6 @@ static int rtsx_pci_probe(struct pci_dev *pcidev,
 	pcr->host_cmds_addr = pcr->rtsx_resv_buf_addr;
 	pcr->host_sg_tbl_ptr = pcr->rtsx_resv_buf + HOST_CMDS_BUF_LEN;
 	pcr->host_sg_tbl_addr = pcr->rtsx_resv_buf_addr + HOST_CMDS_BUF_LEN;
-	rtsx_pci_read_register(pcr, ASPM_FORCE_CTL, &val);
-	if (val & FORCE_ASPM_CTL0 && val & FORCE_ASPM_CTL1)
-		pcr->aspm_enabled = false;
-	else
-		pcr->aspm_enabled = true;
 	pcr->card_inserted = 0;
 	pcr->card_removed = 0;
 	INIT_DELAYED_WORK(&pcr->carddet_work, rtsx_pci_card_detect);
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index 6f155f99aa16..4ab7bfc675f1 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -1109,6 +1109,7 @@ struct pcr_ops {
 };
 
 enum PDEV_STAT  {PDEV_STAT_IDLE, PDEV_STAT_RUN};
+enum ASPM_MODE  {ASPM_MODE_CFG, ASPM_MODE_REG};
 
 #define ASPM_L1_1_EN			BIT(0)
 #define ASPM_L1_2_EN			BIT(1)
@@ -1234,6 +1235,7 @@ struct rtsx_pcr {
 	u8				card_drive_sel;
 #define ASPM_L1_EN			0x02
 	u8				aspm_en;
+	enum ASPM_MODE			aspm_mode;
 	bool				aspm_enabled;
 
 #define PCR_MS_PMOS			(1 << 0)
-- 
cgit v1.2.3


From a3e5fd9314dfc4314a9567cde96e1aef83a7458a Mon Sep 17 00:00:00 2001
From: Dima Chumak <dchumak@nvidia.com>
Date: Wed, 26 May 2021 13:45:10 +0300
Subject: net/mlx5e: Fix page reclaim for dead peer hairpin

When adding a hairpin flow, a firmware-side send queue is created for
the peer net device, which claims some host memory pages for its
internal ring buffer. If the peer net device is removed/unbound before
the hairpin flow is deleted, then the send queue is not destroyed which
leads to a stack trace on pci device remove:

[ 748.005230] mlx5_core 0000:08:00.2: wait_func:1094:(pid 12985): MANAGE_PAGES(0x108) timeout. Will cause a leak of a command resource
[ 748.005231] mlx5_core 0000:08:00.2: reclaim_pages:514:(pid 12985): failed reclaiming pages: err -110
[ 748.001835] mlx5_core 0000:08:00.2: mlx5_reclaim_root_pages:653:(pid 12985): failed reclaiming pages (-110) for func id 0x0
[ 748.002171] ------------[ cut here ]------------
[ 748.001177] FW pages counter is 4 after reclaiming all pages
[ 748.001186] WARNING: CPU: 1 PID: 12985 at drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c:685 mlx5_reclaim_startup_pages+0x34b/0x460 [mlx5_core]                      [  +0.002771] Modules linked in: cls_flower mlx5_ib mlx5_core ptp pps_core act_mirred sch_ingress openvswitch nsh xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 br_netfilter rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi rdma_cm ib_umad ib_ipoib iw_cm ib_cm ib_uverbs ib_core overlay fuse [last unloaded: pps_core]
[ 748.007225] CPU: 1 PID: 12985 Comm: tee Not tainted 5.12.0+ #1
[ 748.001376] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[ 748.002315] RIP: 0010:mlx5_reclaim_startup_pages+0x34b/0x460 [mlx5_core]
[ 748.001679] Code: 28 00 00 00 0f 85 22 01 00 00 48 81 c4 b0 00 00 00 31 c0 5b 5d 41 5c 41 5d 41 5e 41 5f c3 48 c7 c7 40 cc 19 a1 e8 9f 71 0e e2 <0f> 0b e9 30 ff ff ff 48 c7 c7 a0 cc 19 a1 e8 8c 71 0e e2 0f 0b e9
[ 748.003781] RSP: 0018:ffff88815220faf8 EFLAGS: 00010286
[ 748.001149] RAX: 0000000000000000 RBX: ffff8881b4900280 RCX: 0000000000000000
[ 748.001445] RDX: 0000000000000027 RSI: 0000000000000004 RDI: ffffed102a441f51
[ 748.001614] RBP: 00000000000032b9 R08: 0000000000000001 R09: ffffed1054a15ee8
[ 748.001446] R10: ffff8882a50af73b R11: ffffed1054a15ee7 R12: fffffbfff07c1e30
[ 748.001447] R13: dffffc0000000000 R14: ffff8881b492cba8 R15: 0000000000000000
[ 748.001429] FS:  00007f58bd08b580(0000) GS:ffff8882a5080000(0000) knlGS:0000000000000000
[ 748.001695] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 748.001309] CR2: 000055a026351740 CR3: 00000001d3b48006 CR4: 0000000000370ea0
[ 748.001506] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 748.001483] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 748.001654] Call Trace:
[ 748.000576]  ? mlx5_satisfy_startup_pages+0x290/0x290 [mlx5_core]
[ 748.001416]  ? mlx5_cmd_teardown_hca+0xa2/0xd0 [mlx5_core]
[ 748.001354]  ? mlx5_cmd_init_hca+0x280/0x280 [mlx5_core]
[ 748.001203]  mlx5_function_teardown+0x30/0x60 [mlx5_core]
[ 748.001275]  mlx5_uninit_one+0xa7/0xc0 [mlx5_core]
[ 748.001200]  remove_one+0x5f/0xc0 [mlx5_core]
[ 748.001075]  pci_device_remove+0x9f/0x1d0
[ 748.000833]  device_release_driver_internal+0x1e0/0x490
[ 748.001207]  unbind_store+0x19f/0x200
[ 748.000942]  ? sysfs_file_ops+0x170/0x170
[ 748.001000]  kernfs_fop_write_iter+0x2bc/0x450
[ 748.000970]  new_sync_write+0x373/0x610
[ 748.001124]  ? new_sync_read+0x600/0x600
[ 748.001057]  ? lock_acquire+0x4d6/0x700
[ 748.000908]  ? lockdep_hardirqs_on_prepare+0x400/0x400
[ 748.001126]  ? fd_install+0x1c9/0x4d0
[ 748.000951]  vfs_write+0x4d0/0x800
[ 748.000804]  ksys_write+0xf9/0x1d0
[ 748.000868]  ? __x64_sys_read+0xb0/0xb0
[ 748.000811]  ? filp_open+0x50/0x50
[ 748.000919]  ? syscall_enter_from_user_mode+0x1d/0x50
[ 748.001223]  do_syscall_64+0x3f/0x80
[ 748.000892]  entry_SYSCALL_64_after_hwframe+0x44/0xae
[ 748.001026] RIP: 0033:0x7f58bcfb22f7
[ 748.000944] Code: 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24
[ 748.003925] RSP: 002b:00007fffd7f2aaa8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[ 748.001732] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f58bcfb22f7
[ 748.001426] RDX: 000000000000000d RSI: 00007fffd7f2abc0 RDI: 0000000000000003
[ 748.001746] RBP: 00007fffd7f2abc0 R08: 0000000000000000 R09: 0000000000000001
[ 748.001631] R10: 00000000000001b6 R11: 0000000000000246 R12: 000000000000000d
[ 748.001537] R13: 00005597ac2c24a0 R14: 000000000000000d R15: 00007f58bd084700
[ 748.001564] irq event stamp: 0
[ 748.000787] hardirqs last  enabled at (0): [<0000000000000000>] 0x0
[ 748.001399] hardirqs last disabled at (0): [<ffffffff813132cf>] copy_process+0x146f/0x5eb0
[ 748.001854] softirqs last  enabled at (0): [<ffffffff8131330e>] copy_process+0x14ae/0x5eb0
[ 748.013431] softirqs last disabled at (0): [<0000000000000000>] 0x0
[ 748.001492] ---[ end trace a6fabd773d1c51ae ]---

Fix by destroying the send queue of a hairpin peer net device that is
being removed/unbound, which returns the allocated ring buffer pages to
the host.

Fixes: 4d8fcf216c90 ("net/mlx5e: Avoid unbounded peer devices when unpairing TC hairpin rules")
Signed-off-by: Dima Chumak <dchumak@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/transobj.c | 30 +++++++++++++++++-----
 include/linux/mlx5/transobj.h                      |  1 +
 3 files changed, 26 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index dd64878e5b38..d4b0f270b6bb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4765,7 +4765,7 @@ static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv,
 	list_for_each_entry_safe(hpe, tmp, &init_wait_list, dead_peer_wait_list) {
 		wait_for_completion(&hpe->res_ready);
 		if (!IS_ERR_OR_NULL(hpe->hp) && hpe->peer_vhca_id == peer_vhca_id)
-			hpe->hp->pair->peer_gone = true;
+			mlx5_core_hairpin_clear_dead_peer(hpe->hp->pair);
 
 		mlx5e_hairpin_put(priv, hpe);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index 01cc00ad8acf..b6931bbe52d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -424,6 +424,15 @@ err_modify_sq:
 	return err;
 }
 
+static void mlx5_hairpin_unpair_peer_sq(struct mlx5_hairpin *hp)
+{
+	int i;
+
+	for (i = 0; i < hp->num_channels; i++)
+		mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY,
+				       MLX5_SQC_STATE_RST, 0, 0);
+}
+
 static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp)
 {
 	int i;
@@ -432,13 +441,9 @@ static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp)
 	for (i = 0; i < hp->num_channels; i++)
 		mlx5_hairpin_modify_rq(hp->func_mdev, hp->rqn[i], MLX5_RQC_STATE_RDY,
 				       MLX5_RQC_STATE_RST, 0, 0);
-
 	/* unset peer SQs */
-	if (hp->peer_gone)
-		return;
-	for (i = 0; i < hp->num_channels; i++)
-		mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY,
-				       MLX5_SQC_STATE_RST, 0, 0);
+	if (!hp->peer_gone)
+		mlx5_hairpin_unpair_peer_sq(hp);
 }
 
 struct mlx5_hairpin *
@@ -485,3 +490,16 @@ void mlx5_core_hairpin_destroy(struct mlx5_hairpin *hp)
 	mlx5_hairpin_destroy_queues(hp);
 	kfree(hp);
 }
+
+void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp)
+{
+	int i;
+
+	mlx5_hairpin_unpair_peer_sq(hp);
+
+	/* destroy peer SQ */
+	for (i = 0; i < hp->num_channels; i++)
+		mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]);
+
+	hp->peer_gone = true;
+}
diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h
index 028f442530cf..60ffeb6b67ae 100644
--- a/include/linux/mlx5/transobj.h
+++ b/include/linux/mlx5/transobj.h
@@ -85,4 +85,5 @@ mlx5_core_hairpin_create(struct mlx5_core_dev *func_mdev,
 			 struct mlx5_hairpin_params *params);
 
 void mlx5_core_hairpin_destroy(struct mlx5_hairpin *pair);
+void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp);
 #endif /* __TRANSOBJ_H__ */
-- 
cgit v1.2.3


From f13ef10059ccf5f4ed201cd050176df62ec25bb8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Jun 2021 07:27:37 -0700
Subject: net: annotate data race in sock_error()

sock_error() is known to be racy. The code avoids
an atomic operation is sk_err is zero, and this field
could be changed under us, this is fine.

Sysbot reported:

BUG: KCSAN: data-race in sock_alloc_send_pskb / unix_release_sock

write to 0xffff888131855630 of 4 bytes by task 9365 on cpu 1:
 unix_release_sock+0x2e9/0x6e0 net/unix/af_unix.c:550
 unix_release+0x2f/0x50 net/unix/af_unix.c:859
 __sock_release net/socket.c:599 [inline]
 sock_close+0x6c/0x150 net/socket.c:1258
 __fput+0x25b/0x4e0 fs/file_table.c:280
 ____fput+0x11/0x20 fs/file_table.c:313
 task_work_run+0xae/0x130 kernel/task_work.c:164
 tracehook_notify_resume include/linux/tracehook.h:189 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:174 [inline]
 exit_to_user_mode_prepare+0x156/0x190 kernel/entry/common.c:208
 __syscall_exit_to_user_mode_work kernel/entry/common.c:290 [inline]
 syscall_exit_to_user_mode+0x20/0x40 kernel/entry/common.c:301
 do_syscall_64+0x56/0x90 arch/x86/entry/common.c:57
 entry_SYSCALL_64_after_hwframe+0x44/0xae

read to 0xffff888131855630 of 4 bytes by task 9385 on cpu 0:
 sock_error include/net/sock.h:2269 [inline]
 sock_alloc_send_pskb+0xe4/0x4e0 net/core/sock.c:2336
 unix_dgram_sendmsg+0x478/0x1610 net/unix/af_unix.c:1671
 unix_seqpacket_sendmsg+0xc2/0x100 net/unix/af_unix.c:2055
 sock_sendmsg_nosec net/socket.c:654 [inline]
 sock_sendmsg net/socket.c:674 [inline]
 ____sys_sendmsg+0x360/0x4d0 net/socket.c:2350
 __sys_sendmsg_sock+0x25/0x30 net/socket.c:2416
 io_sendmsg fs/io_uring.c:4367 [inline]
 io_issue_sqe+0x231a/0x6750 fs/io_uring.c:6135
 __io_queue_sqe+0xe9/0x360 fs/io_uring.c:6414
 __io_req_task_submit fs/io_uring.c:2039 [inline]
 io_async_task_func+0x312/0x590 fs/io_uring.c:5074
 __tctx_task_work fs/io_uring.c:1910 [inline]
 tctx_task_work+0x1d4/0x3d0 fs/io_uring.c:1924
 task_work_run+0xae/0x130 kernel/task_work.c:164
 tracehook_notify_signal include/linux/tracehook.h:212 [inline]
 handle_signal_work kernel/entry/common.c:145 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:171 [inline]
 exit_to_user_mode_prepare+0xf8/0x190 kernel/entry/common.c:208
 __syscall_exit_to_user_mode_work kernel/entry/common.c:290 [inline]
 syscall_exit_to_user_mode+0x20/0x40 kernel/entry/common.c:301
 do_syscall_64+0x56/0x90 arch/x86/entry/common.c:57
 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0x00000000 -> 0x00000068

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 9385 Comm: syz-executor.3 Not tainted 5.13.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 0e962d8bc73b..2fc513aa114c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2266,8 +2266,13 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk);
 static inline int sock_error(struct sock *sk)
 {
 	int err;
-	if (likely(!sk->sk_err))
+
+	/* Avoid an atomic operation for the common case.
+	 * This is racy since another cpu/thread can change sk_err under us.
+	 */
+	if (likely(data_race(!sk->sk_err)))
 		return 0;
+
 	err = xchg(&sk->sk_err, 0);
 	return -err;
 }
-- 
cgit v1.2.3


From b71eaed8c04f72a919a9c44e83e4ee254e69e7f3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Jun 2021 07:44:11 -0700
Subject: inet: annotate date races around sk->sk_txhash

UDP sendmsg() path can be lockless, it is possible for another
thread to re-connect an change sk->sk_txhash under us.

There is no serious impact, but we can use READ_ONCE()/WRITE_ONCE()
pair to document the race.

BUG: KCSAN: data-race in __ip4_datagram_connect / skb_set_owner_w

write to 0xffff88813397920c of 4 bytes by task 30997 on cpu 1:
 sk_set_txhash include/net/sock.h:1937 [inline]
 __ip4_datagram_connect+0x69e/0x710 net/ipv4/datagram.c:75
 __ip6_datagram_connect+0x551/0x840 net/ipv6/datagram.c:189
 ip6_datagram_connect+0x2a/0x40 net/ipv6/datagram.c:272
 inet_dgram_connect+0xfd/0x180 net/ipv4/af_inet.c:580
 __sys_connect_file net/socket.c:1837 [inline]
 __sys_connect+0x245/0x280 net/socket.c:1854
 __do_sys_connect net/socket.c:1864 [inline]
 __se_sys_connect net/socket.c:1861 [inline]
 __x64_sys_connect+0x3d/0x50 net/socket.c:1861
 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47
 entry_SYSCALL_64_after_hwframe+0x44/0xae

read to 0xffff88813397920c of 4 bytes by task 31039 on cpu 0:
 skb_set_hash_from_sk include/net/sock.h:2211 [inline]
 skb_set_owner_w+0x118/0x220 net/core/sock.c:2101
 sock_alloc_send_pskb+0x452/0x4e0 net/core/sock.c:2359
 sock_alloc_send_skb+0x2d/0x40 net/core/sock.c:2373
 __ip6_append_data+0x1743/0x21a0 net/ipv6/ip6_output.c:1621
 ip6_make_skb+0x258/0x420 net/ipv6/ip6_output.c:1983
 udpv6_sendmsg+0x160a/0x16b0 net/ipv6/udp.c:1527
 inet6_sendmsg+0x5f/0x80 net/ipv6/af_inet6.c:642
 sock_sendmsg_nosec net/socket.c:654 [inline]
 sock_sendmsg net/socket.c:674 [inline]
 ____sys_sendmsg+0x360/0x4d0 net/socket.c:2350
 ___sys_sendmsg net/socket.c:2404 [inline]
 __sys_sendmmsg+0x315/0x4b0 net/socket.c:2490
 __do_sys_sendmmsg net/socket.c:2519 [inline]
 __se_sys_sendmmsg net/socket.c:2516 [inline]
 __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2516
 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47
 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0xbca3c43d -> 0xfdb309e0

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 31039 Comm: syz-executor.2 Not tainted 5.13.0-rc3-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 2fc513aa114c..7a7058f4f265 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1934,7 +1934,8 @@ static inline u32 net_tx_rndhash(void)
 
 static inline void sk_set_txhash(struct sock *sk)
 {
-	sk->sk_txhash = net_tx_rndhash();
+	/* This pairs with READ_ONCE() in skb_set_hash_from_sk() */
+	WRITE_ONCE(sk->sk_txhash, net_tx_rndhash());
 }
 
 static inline bool sk_rethink_txhash(struct sock *sk)
@@ -2206,9 +2207,12 @@ static inline void sock_poll_wait(struct file *filp, struct socket *sock,
 
 static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk)
 {
-	if (sk->sk_txhash) {
+	/* This pairs with WRITE_ONCE() in sk_set_txhash() */
+	u32 txhash = READ_ONCE(sk->sk_txhash);
+
+	if (txhash) {
 		skb->l4_hash = 1;
-		skb->hash = sk->sk_txhash;
+		skb->hash = txhash;
 	}
 }
 
-- 
cgit v1.2.3


From 992da01aa932b432ef8dc3885fa76415b5dbe43f Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 10 Jun 2021 16:37:37 +0100
Subject: io_uring: change registration/upd/rsrc tagging ABI

There are ABI moments about recently added rsrc registration/update and
tagging that might become a nuisance in the future. First,
IORING_REGISTER_RSRC[_UPD] hide different types of resources under it,
so breaks fine control over them by restrictions. It works for now, but
once those are wanted under restrictions it would require a rework.

It was also inconvenient trying to fit a new resource not supporting
all the features (e.g. dynamic update) into the interface, so better
to return to IORING_REGISTER_* top level dispatching.

Second, register/update were considered to accept a type of resource,
however that's not a good idea because there might be several ways of
registration of a single resource type, e.g. we may want to add
non-contig buffers or anything more exquisite as dma mapped memory.
So, remove IORING_RSRC_[FILE,BUFFER] out of the ABI, and place them
internally for now to limit changes.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/9b554897a7c17ad6e3becc48dfed2f7af9f423d5.1623339162.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c                 | 39 +++++++++++++++++++++++++++------------
 include/uapi/linux/io_uring.h | 18 +++++++++---------
 2 files changed, 36 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 42380ed563c4..663fef3d56df 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -783,6 +783,11 @@ struct io_task_work {
 	task_work_func_t	func;
 };
 
+enum {
+	IORING_RSRC_FILE		= 0,
+	IORING_RSRC_BUFFER		= 1,
+};
+
 /*
  * NOTE! Each of the iocb union members has the file pointer
  * as the first entry in their struct definition. So you can
@@ -9911,7 +9916,7 @@ static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg,
 }
 
 static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
-				   unsigned size)
+				   unsigned size, unsigned type)
 {
 	struct io_uring_rsrc_update2 up;
 
@@ -9919,13 +9924,13 @@ static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
 		return -EINVAL;
 	if (copy_from_user(&up, arg, sizeof(up)))
 		return -EFAULT;
-	if (!up.nr)
+	if (!up.nr || up.resv)
 		return -EINVAL;
-	return __io_register_rsrc_update(ctx, up.type, &up, up.nr);
+	return __io_register_rsrc_update(ctx, type, &up, up.nr);
 }
 
 static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
-			    unsigned int size)
+			    unsigned int size, unsigned int type)
 {
 	struct io_uring_rsrc_register rr;
 
@@ -9936,10 +9941,10 @@ static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
 	memset(&rr, 0, sizeof(rr));
 	if (copy_from_user(&rr, arg, size))
 		return -EFAULT;
-	if (!rr.nr)
+	if (!rr.nr || rr.resv || rr.resv2)
 		return -EINVAL;
 
-	switch (rr.type) {
+	switch (type) {
 	case IORING_RSRC_FILE:
 		return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data),
 					     rr.nr, u64_to_user_ptr(rr.tags));
@@ -9961,8 +9966,10 @@ static bool io_register_op_must_quiesce(int op)
 	case IORING_REGISTER_PROBE:
 	case IORING_REGISTER_PERSONALITY:
 	case IORING_UNREGISTER_PERSONALITY:
-	case IORING_REGISTER_RSRC:
-	case IORING_REGISTER_RSRC_UPDATE:
+	case IORING_REGISTER_FILES2:
+	case IORING_REGISTER_FILES_UPDATE2:
+	case IORING_REGISTER_BUFFERS2:
+	case IORING_REGISTER_BUFFERS_UPDATE:
 		return false;
 	default:
 		return true;
@@ -10088,11 +10095,19 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 	case IORING_REGISTER_RESTRICTIONS:
 		ret = io_register_restrictions(ctx, arg, nr_args);
 		break;
-	case IORING_REGISTER_RSRC:
-		ret = io_register_rsrc(ctx, arg, nr_args);
+	case IORING_REGISTER_FILES2:
+		ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE);
+		break;
+	case IORING_REGISTER_FILES_UPDATE2:
+		ret = io_register_rsrc_update(ctx, arg, nr_args,
+					      IORING_RSRC_FILE);
+		break;
+	case IORING_REGISTER_BUFFERS2:
+		ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER);
 		break;
-	case IORING_REGISTER_RSRC_UPDATE:
-		ret = io_register_rsrc_update(ctx, arg, nr_args);
+	case IORING_REGISTER_BUFFERS_UPDATE:
+		ret = io_register_rsrc_update(ctx, arg, nr_args,
+					      IORING_RSRC_BUFFER);
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index e1ae46683301..48b4ddcd56ff 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -298,8 +298,12 @@ enum {
 	IORING_UNREGISTER_PERSONALITY		= 10,
 	IORING_REGISTER_RESTRICTIONS		= 11,
 	IORING_REGISTER_ENABLE_RINGS		= 12,
-	IORING_REGISTER_RSRC			= 13,
-	IORING_REGISTER_RSRC_UPDATE		= 14,
+
+	/* extended with tagging */
+	IORING_REGISTER_FILES2			= 13,
+	IORING_REGISTER_FILES_UPDATE2		= 14,
+	IORING_REGISTER_BUFFERS2		= 15,
+	IORING_REGISTER_BUFFERS_UPDATE		= 16,
 
 	/* this goes last */
 	IORING_REGISTER_LAST
@@ -312,14 +316,10 @@ struct io_uring_files_update {
 	__aligned_u64 /* __s32 * */ fds;
 };
 
-enum {
-	IORING_RSRC_FILE		= 0,
-	IORING_RSRC_BUFFER		= 1,
-};
-
 struct io_uring_rsrc_register {
-	__u32 type;
 	__u32 nr;
+	__u32 resv;
+	__u64 resv2;
 	__aligned_u64 data;
 	__aligned_u64 tags;
 };
@@ -335,8 +335,8 @@ struct io_uring_rsrc_update2 {
 	__u32 resv;
 	__aligned_u64 data;
 	__aligned_u64 tags;
-	__u32 type;
 	__u32 nr;
+	__u32 resv2;
 };
 
 /* Skip updating fd indexes set to this value in the fd table */
-- 
cgit v1.2.3


From 9690557e22d63f13534fd167d293ac8ed8b104f9 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 10 Jun 2021 16:37:38 +0100
Subject: io_uring: add feature flag for rsrc tags

Add IORING_FEAT_RSRC_TAGS indicating that io_uring supports a bunch of
new IORING_REGISTER operations, in particular
IORING_REGISTER_[FILES[,UPDATE]2,BUFFERS[2,UPDATE]] that support rsrc
tagging, and also indicating implemented dynamic fixed buffer updates.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/9b995d4045b6c6b4ab7510ca124fd25ac2203af7.1623339162.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c                 | 3 ++-
 include/uapi/linux/io_uring.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 663fef3d56df..fa8794c61af7 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -9676,7 +9676,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
 			IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
 			IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL |
 			IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED |
-			IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS;
+			IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS |
+			IORING_FEAT_RSRC_TAGS;
 
 	if (copy_to_user(params, p, sizeof(*p))) {
 		ret = -EFAULT;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 48b4ddcd56ff..162ff99ed2cb 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -280,6 +280,7 @@ struct io_uring_params {
 #define IORING_FEAT_SQPOLL_NONFIXED	(1U << 7)
 #define IORING_FEAT_EXT_ARG		(1U << 8)
 #define IORING_FEAT_NATIVE_WORKERS	(1U << 9)
+#define IORING_FEAT_RSRC_TAGS		(1U << 10)
 
 /*
  * io_uring_register(2) opcodes and arguments
-- 
cgit v1.2.3


From ea6932d70e223e02fea3ae20a4feff05d7c1ea9a Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@gmail.com>
Date: Fri, 11 Jun 2021 22:29:59 +0800
Subject: net: make get_net_ns return error if NET_NS is disabled

There is a panic in socket ioctl cmd SIOCGSKNS when NET_NS is not enabled.
The reason is that nsfs tries to access ns->ops but the proc_ns_operations
is not implemented in this case.

[7.670023] Unable to handle kernel NULL pointer dereference at virtual address 00000010
[7.670268] pgd = 32b54000
[7.670544] [00000010] *pgd=00000000
[7.671861] Internal error: Oops: 5 [#1] SMP ARM
[7.672315] Modules linked in:
[7.672918] CPU: 0 PID: 1 Comm: systemd Not tainted 5.13.0-rc3-00375-g6799d4f2da49 #16
[7.673309] Hardware name: Generic DT based system
[7.673642] PC is at nsfs_evict+0x24/0x30
[7.674486] LR is at clear_inode+0x20/0x9c

The same to tun SIOCGSKNS command.

To fix this problem, we make get_net_ns() return -EINVAL when NET_NS is
disabled. Meanwhile move it to right place net/core/net_namespace.c.

Signed-off-by: Changbin Du <changbin.du@gmail.com>
Fixes: c62cce2caee5 ("net: add an ioctl to get a socket network namespace")
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: David Laight <David.Laight@ACULAB.COM>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/socket.h      |  2 --
 include/net/net_namespace.h |  7 +++++++
 net/core/net_namespace.c    | 12 ++++++++++++
 net/socket.c                | 13 -------------
 4 files changed, 19 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/socket.h b/include/linux/socket.h
index b8fc5c53ba6f..0d8e3dcb7f88 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -438,6 +438,4 @@ extern int __sys_socketpair(int family, int type, int protocol,
 			    int __user *usockvec);
 extern int __sys_shutdown_sock(struct socket *sock, int how);
 extern int __sys_shutdown(int fd, int how);
-
-extern struct ns_common *get_net_ns(struct ns_common *ns);
 #endif /* _LINUX_SOCKET_H */
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index fa5887143f0d..6412d7833d97 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -184,6 +184,8 @@ struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns,
 void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid);
 
 void net_ns_barrier(void);
+
+struct ns_common *get_net_ns(struct ns_common *ns);
 #else /* CONFIG_NET_NS */
 #include <linux/sched.h>
 #include <linux/nsproxy.h>
@@ -203,6 +205,11 @@ static inline void net_ns_get_ownership(const struct net *net,
 }
 
 static inline void net_ns_barrier(void) {}
+
+static inline struct ns_common *get_net_ns(struct ns_common *ns)
+{
+	return ERR_PTR(-EINVAL);
+}
 #endif /* CONFIG_NET_NS */
 
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 43b6ac4c4439..cc8dafb25d61 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -641,6 +641,18 @@ void __put_net(struct net *net)
 }
 EXPORT_SYMBOL_GPL(__put_net);
 
+/**
+ * get_net_ns - increment the refcount of the network namespace
+ * @ns: common namespace (net)
+ *
+ * Returns the net's common namespace.
+ */
+struct ns_common *get_net_ns(struct ns_common *ns)
+{
+	return &get_net(container_of(ns, struct net, ns))->ns;
+}
+EXPORT_SYMBOL_GPL(get_net_ns);
+
 struct net *get_net_ns_by_fd(int fd)
 {
 	struct file *file;
diff --git a/net/socket.c b/net/socket.c
index 27e3e7d53f8e..4f2c6d2795d0 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1072,19 +1072,6 @@ static long sock_do_ioctl(struct net *net, struct socket *sock,
  *	what to do with it - that's up to the protocol still.
  */
 
-/**
- *	get_net_ns - increment the refcount of the network namespace
- *	@ns: common namespace (net)
- *
- *	Returns the net's common namespace.
- */
-
-struct ns_common *get_net_ns(struct ns_common *ns)
-{
-	return &get_net(container_of(ns, struct net, ns))->ns;
-}
-EXPORT_SYMBOL_GPL(get_net_ns);
-
 static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
 	struct socket *sock;
-- 
cgit v1.2.3


From 2e3025434a6ba090c85871a1d4080ff784109e1f Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Fri, 11 Jun 2021 09:54:42 +0800
Subject: mm: relocate 'write_protect_seq' in struct mm_struct

0day robot reported a 9.2% regression for will-it-scale mmap1 test
case[1], caused by commit 57efa1fe5957 ("mm/gup: prevent gup_fast from
racing with COW during fork").

Further debug shows the regression is due to that commit changes the
offset of hot fields 'mmap_lock' inside structure 'mm_struct', thus some
cache alignment changes.

From the perf data, the contention for 'mmap_lock' is very severe and
takes around 95% cpu cycles, and it is a rw_semaphore

        struct rw_semaphore {
                atomic_long_t count;	/* 8 bytes */
                atomic_long_t owner;	/* 8 bytes */
                struct optimistic_spin_queue osq; /* spinner MCS lock */
                ...

Before commit 57efa1fe5957 adds the 'write_protect_seq', it happens to
have a very optimal cache alignment layout, as Linus explained:

 "and before the addition of the 'write_protect_seq' field, the
  mmap_sem was at offset 120 in 'struct mm_struct'.

  Which meant that count and owner were in two different cachelines,
  and then when you have contention and spend time in
  rwsem_down_write_slowpath(), this is probably *exactly* the kind
  of layout you want.

  Because first the rwsem_write_trylock() will do a cmpxchg on the
  first cacheline (for the optimistic fast-path), and then in the
  case of contention, rwsem_down_write_slowpath() will just access
  the second cacheline.

  Which is probably just optimal for a load that spends a lot of
  time contended - new waiters touch that first cacheline, and then
  they queue themselves up on the second cacheline."

After the commit, the rw_semaphore is at offset 128, which means the
'count' and 'owner' fields are now in the same cacheline, and causes
more cache bouncing.

Currently there are 3 "#ifdef CONFIG_XXX" before 'mmap_lock' which will
affect its offset:

  CONFIG_MMU
  CONFIG_MEMBARRIER
  CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES

The layout above is on 64 bits system with 0day's default kernel config
(similar to RHEL-8.3's config), in which all these 3 options are 'y'.
And the layout can vary with different kernel configs.

Relayouting a structure is usually a double-edged sword, as sometimes it
can helps one case, but hurt other cases.  For this case, one solution
is, as the newly added 'write_protect_seq' is a 4 bytes long seqcount_t
(when CONFIG_DEBUG_LOCK_ALLOC=n), placing it into an existing 4 bytes
hole in 'mm_struct' will not change other fields' alignment, while
restoring the regression.

Link: https://lore.kernel.org/lkml/20210525031636.GB7744@xsang-OptiPlex-9020/ [1]
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm_types.h | 27 ++++++++++++++++++++-------
 1 file changed, 20 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 5aacc1c10a45..8f0fb62e8975 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -445,13 +445,6 @@ struct mm_struct {
 		 */
 		atomic_t has_pinned;
 
-		/**
-		 * @write_protect_seq: Locked when any thread is write
-		 * protecting pages mapped by this mm to enforce a later COW,
-		 * for instance during page table copying for fork().
-		 */
-		seqcount_t write_protect_seq;
-
 #ifdef CONFIG_MMU
 		atomic_long_t pgtables_bytes;	/* PTE page table pages */
 #endif
@@ -460,6 +453,18 @@ struct mm_struct {
 		spinlock_t page_table_lock; /* Protects page tables and some
 					     * counters
 					     */
+		/*
+		 * With some kernel config, the current mmap_lock's offset
+		 * inside 'mm_struct' is at 0x120, which is very optimal, as
+		 * its two hot fields 'count' and 'owner' sit in 2 different
+		 * cachelines,  and when mmap_lock is highly contended, both
+		 * of the 2 fields will be accessed frequently, current layout
+		 * will help to reduce cache bouncing.
+		 *
+		 * So please be careful with adding new fields before
+		 * mmap_lock, which can easily push the 2 fields into one
+		 * cacheline.
+		 */
 		struct rw_semaphore mmap_lock;
 
 		struct list_head mmlist; /* List of maybe swapped mm's.	These
@@ -480,7 +485,15 @@ struct mm_struct {
 		unsigned long stack_vm;	   /* VM_STACK */
 		unsigned long def_flags;
 
+		/**
+		 * @write_protect_seq: Locked when any thread is write
+		 * protecting pages mapped by this mm to enforce a later COW,
+		 * for instance during page table copying for fork().
+		 */
+		seqcount_t write_protect_seq;
+
 		spinlock_t arg_lock; /* protect the below fields */
+
 		unsigned long start_code, end_code, start_data, end_data;
 		unsigned long start_brk, brk, start_stack;
 		unsigned long arg_start, arg_end, env_start, env_end;
-- 
cgit v1.2.3


From 771fac5e26c17845de8c679e6a947a4371e86ffc Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Fri, 11 Jun 2021 08:48:02 +0530
Subject: Revert "cpufreq: CPPC: Add support for frequency invariance"

This reverts commit 4c38f2df71c8e33c0b64865992d693f5022eeaad.

There are few races in the frequency invariance support for CPPC driver,
namely the driver doesn't stop the kthread_work and irq_work on policy
exit during suspend/resume or CPU hotplug.

A proper fix won't be possible for the 5.13-rc, as it requires a lot of
changes. Lets revert the patch instead for now.

Fixes: 4c38f2df71c8 ("cpufreq: CPPC: Add support for frequency invariance")
Reported-by: Qian Cai <quic_qiancai@quicinc.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/Kconfig.arm    |  10 --
 drivers/cpufreq/cppc_cpufreq.c | 245 ++---------------------------------------
 include/linux/arch_topology.h  |   1 -
 kernel/sched/core.c            |   1 -
 4 files changed, 12 insertions(+), 245 deletions(-)

(limited to 'include')

diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index a5c5f70acfc9..e65e0a43be64 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -19,16 +19,6 @@ config ACPI_CPPC_CPUFREQ
 
 	  If in doubt, say N.
 
-config ACPI_CPPC_CPUFREQ_FIE
-	bool "Frequency Invariance support for CPPC cpufreq driver"
-	depends on ACPI_CPPC_CPUFREQ && GENERIC_ARCH_TOPOLOGY
-	default y
-	help
-	  This extends frequency invariance support in the CPPC cpufreq driver,
-	  by using CPPC delivered and reference performance counters.
-
-	  If in doubt, say N.
-
 config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM
 	tristate "Allwinner nvmem based SUN50I CPUFreq driver"
 	depends on ARCH_SUNXI
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 3848b4c222e1..2f769b1630c5 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -10,18 +10,14 @@
 
 #define pr_fmt(fmt)	"CPPC Cpufreq:"	fmt
 
-#include <linux/arch_topology.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/dmi.h>
-#include <linux/irq_work.h>
-#include <linux/kthread.h>
 #include <linux/time.h>
 #include <linux/vmalloc.h>
-#include <uapi/linux/sched/types.h>
 
 #include <asm/unaligned.h>
 
@@ -61,204 +57,6 @@ static struct cppc_workaround_oem_info wa_info[] = {
 	}
 };
 
-#ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
-
-/* Frequency invariance support */
-struct cppc_freq_invariance {
-	int cpu;
-	struct irq_work irq_work;
-	struct kthread_work work;
-	struct cppc_perf_fb_ctrs prev_perf_fb_ctrs;
-	struct cppc_cpudata *cpu_data;
-};
-
-static DEFINE_PER_CPU(struct cppc_freq_invariance, cppc_freq_inv);
-static struct kthread_worker *kworker_fie;
-static bool fie_disabled;
-
-static struct cpufreq_driver cppc_cpufreq_driver;
-static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu);
-static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
-				 struct cppc_perf_fb_ctrs fb_ctrs_t0,
-				 struct cppc_perf_fb_ctrs fb_ctrs_t1);
-
-/**
- * cppc_scale_freq_workfn - CPPC arch_freq_scale updater for frequency invariance
- * @work: The work item.
- *
- * The CPPC driver register itself with the topology core to provide its own
- * implementation (cppc_scale_freq_tick()) of topology_scale_freq_tick() which
- * gets called by the scheduler on every tick.
- *
- * Note that the arch specific counters have higher priority than CPPC counters,
- * if available, though the CPPC driver doesn't need to have any special
- * handling for that.
- *
- * On an invocation of cppc_scale_freq_tick(), we schedule an irq work (since we
- * reach here from hard-irq context), which then schedules a normal work item
- * and cppc_scale_freq_workfn() updates the per_cpu arch_freq_scale variable
- * based on the counter updates since the last tick.
- */
-static void cppc_scale_freq_workfn(struct kthread_work *work)
-{
-	struct cppc_freq_invariance *cppc_fi;
-	struct cppc_perf_fb_ctrs fb_ctrs = {0};
-	struct cppc_cpudata *cpu_data;
-	unsigned long local_freq_scale;
-	u64 perf;
-
-	cppc_fi = container_of(work, struct cppc_freq_invariance, work);
-	cpu_data = cppc_fi->cpu_data;
-
-	if (cppc_get_perf_ctrs(cppc_fi->cpu, &fb_ctrs)) {
-		pr_warn("%s: failed to read perf counters\n", __func__);
-		return;
-	}
-
-	cppc_fi->prev_perf_fb_ctrs = fb_ctrs;
-	perf = cppc_perf_from_fbctrs(cpu_data, cppc_fi->prev_perf_fb_ctrs,
-				     fb_ctrs);
-
-	perf <<= SCHED_CAPACITY_SHIFT;
-	local_freq_scale = div64_u64(perf, cpu_data->perf_caps.highest_perf);
-	if (WARN_ON(local_freq_scale > 1024))
-		local_freq_scale = 1024;
-
-	per_cpu(arch_freq_scale, cppc_fi->cpu) = local_freq_scale;
-}
-
-static void cppc_irq_work(struct irq_work *irq_work)
-{
-	struct cppc_freq_invariance *cppc_fi;
-
-	cppc_fi = container_of(irq_work, struct cppc_freq_invariance, irq_work);
-	kthread_queue_work(kworker_fie, &cppc_fi->work);
-}
-
-static void cppc_scale_freq_tick(void)
-{
-	struct cppc_freq_invariance *cppc_fi = &per_cpu(cppc_freq_inv, smp_processor_id());
-
-	/*
-	 * cppc_get_perf_ctrs() can potentially sleep, call that from the right
-	 * context.
-	 */
-	irq_work_queue(&cppc_fi->irq_work);
-}
-
-static struct scale_freq_data cppc_sftd = {
-	.source = SCALE_FREQ_SOURCE_CPPC,
-	.set_freq_scale = cppc_scale_freq_tick,
-};
-
-static void cppc_freq_invariance_policy_init(struct cpufreq_policy *policy,
-					     struct cppc_cpudata *cpu_data)
-{
-	struct cppc_perf_fb_ctrs fb_ctrs = {0};
-	struct cppc_freq_invariance *cppc_fi;
-	int i, ret;
-
-	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
-		return;
-
-	if (fie_disabled)
-		return;
-
-	for_each_cpu(i, policy->cpus) {
-		cppc_fi = &per_cpu(cppc_freq_inv, i);
-		cppc_fi->cpu = i;
-		cppc_fi->cpu_data = cpu_data;
-		kthread_init_work(&cppc_fi->work, cppc_scale_freq_workfn);
-		init_irq_work(&cppc_fi->irq_work, cppc_irq_work);
-
-		ret = cppc_get_perf_ctrs(i, &fb_ctrs);
-		if (ret) {
-			pr_warn("%s: failed to read perf counters: %d\n",
-				__func__, ret);
-			fie_disabled = true;
-		} else {
-			cppc_fi->prev_perf_fb_ctrs = fb_ctrs;
-		}
-	}
-}
-
-static void __init cppc_freq_invariance_init(void)
-{
-	struct sched_attr attr = {
-		.size		= sizeof(struct sched_attr),
-		.sched_policy	= SCHED_DEADLINE,
-		.sched_nice	= 0,
-		.sched_priority	= 0,
-		/*
-		 * Fake (unused) bandwidth; workaround to "fix"
-		 * priority inheritance.
-		 */
-		.sched_runtime	= 1000000,
-		.sched_deadline = 10000000,
-		.sched_period	= 10000000,
-	};
-	int ret;
-
-	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
-		return;
-
-	if (fie_disabled)
-		return;
-
-	kworker_fie = kthread_create_worker(0, "cppc_fie");
-	if (IS_ERR(kworker_fie))
-		return;
-
-	ret = sched_setattr_nocheck(kworker_fie->task, &attr);
-	if (ret) {
-		pr_warn("%s: failed to set SCHED_DEADLINE: %d\n", __func__,
-			ret);
-		kthread_destroy_worker(kworker_fie);
-		return;
-	}
-
-	/* Register for freq-invariance */
-	topology_set_scale_freq_source(&cppc_sftd, cpu_present_mask);
-}
-
-static void cppc_freq_invariance_exit(void)
-{
-	struct cppc_freq_invariance *cppc_fi;
-	int i;
-
-	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
-		return;
-
-	if (fie_disabled)
-		return;
-
-	topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_CPPC, cpu_present_mask);
-
-	for_each_possible_cpu(i) {
-		cppc_fi = &per_cpu(cppc_freq_inv, i);
-		irq_work_sync(&cppc_fi->irq_work);
-	}
-
-	kthread_destroy_worker(kworker_fie);
-	kworker_fie = NULL;
-}
-
-#else
-static inline void
-cppc_freq_invariance_policy_init(struct cpufreq_policy *policy,
-				 struct cppc_cpudata *cpu_data)
-{
-}
-
-static inline void cppc_freq_invariance_init(void)
-{
-}
-
-static inline void cppc_freq_invariance_exit(void)
-{
-}
-#endif /* CONFIG_ACPI_CPPC_CPUFREQ_FIE */
-
 /* Callback function used to retrieve the max frequency from DMI */
 static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
 {
@@ -547,12 +345,9 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	cpu_data->perf_ctrls.desired_perf =  caps->highest_perf;
 
 	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
-	if (ret) {
+	if (ret)
 		pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n",
 			 caps->highest_perf, cpu, ret);
-	} else {
-		cppc_freq_invariance_policy_init(policy, cpu_data);
-	}
 
 	return ret;
 }
@@ -565,12 +360,12 @@ static inline u64 get_delta(u64 t1, u64 t0)
 	return (u32)t1 - (u32)t0;
 }
 
-static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
-				 struct cppc_perf_fb_ctrs fb_ctrs_t0,
-				 struct cppc_perf_fb_ctrs fb_ctrs_t1)
+static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t0,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t1)
 {
 	u64 delta_reference, delta_delivered;
-	u64 reference_perf;
+	u64 reference_perf, delivered_perf;
 
 	reference_perf = fb_ctrs_t0.reference_perf;
 
@@ -579,21 +374,12 @@ static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
 	delta_delivered = get_delta(fb_ctrs_t1.delivered,
 				    fb_ctrs_t0.delivered);
 
-	/* Check to avoid divide-by zero and invalid delivered_perf */
-	if (!delta_reference || !delta_delivered)
-		return cpu_data->perf_ctrls.desired_perf;
-
-	return (reference_perf * delta_delivered) / delta_reference;
-}
-
-static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data,
-				     struct cppc_perf_fb_ctrs fb_ctrs_t0,
-				     struct cppc_perf_fb_ctrs fb_ctrs_t1)
-{
-	u64 delivered_perf;
-
-	delivered_perf = cppc_perf_from_fbctrs(cpu_data, fb_ctrs_t0,
-					       fb_ctrs_t1);
+	/* Check to avoid divide-by zero */
+	if (delta_reference || delta_delivered)
+		delivered_perf = (reference_perf * delta_delivered) /
+					delta_reference;
+	else
+		delivered_perf = cpu_data->perf_ctrls.desired_perf;
 
 	return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf);
 }
@@ -718,8 +504,6 @@ static void cppc_check_hisi_workaround(void)
 
 static int __init cppc_cpufreq_init(void)
 {
-	int ret;
-
 	if ((acpi_disabled) || !acpi_cpc_valid())
 		return -ENODEV;
 
@@ -727,11 +511,7 @@ static int __init cppc_cpufreq_init(void)
 
 	cppc_check_hisi_workaround();
 
-	ret = cpufreq_register_driver(&cppc_cpufreq_driver);
-	if (!ret)
-		cppc_freq_invariance_init();
-
-	return ret;
+	return cpufreq_register_driver(&cppc_cpufreq_driver);
 }
 
 static inline void free_cpu_data(void)
@@ -748,7 +528,6 @@ static inline void free_cpu_data(void)
 
 static void __exit cppc_cpufreq_exit(void)
 {
-	cppc_freq_invariance_exit();
 	cpufreq_unregister_driver(&cppc_cpufreq_driver);
 
 	free_cpu_data();
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index f180240dc95f..11e555cfaecb 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -37,7 +37,6 @@ bool topology_scale_freq_invariant(void);
 enum scale_freq_source {
 	SCALE_FREQ_SOURCE_CPUFREQ = 0,
 	SCALE_FREQ_SOURCE_ARCH,
-	SCALE_FREQ_SOURCE_CPPC,
 };
 
 struct scale_freq_data {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5226cc26a095..4ca80df205ce 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6389,7 +6389,6 @@ int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
 {
 	return __sched_setscheduler(p, attr, false, true);
 }
-EXPORT_SYMBOL_GPL(sched_setattr_nocheck);
 
 /**
  * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
-- 
cgit v1.2.3


From 8b1462b67f23da548f27b779a36b8ea75f5ef249 Mon Sep 17 00:00:00 2001
From: Marcin Juszkiewicz <marcin@juszkiewicz.com.pl>
Date: Mon, 14 Jun 2021 17:37:12 +0200
Subject: quota: finish disable quotactl_path syscall

In commit 5b9fedb31e47 ("quota: Disable quotactl_path syscall") Jan Kara
disabled quotactl_path syscall on several architectures.

This commit disables it on all architectures using unified list of
system calls:

- arm64
- arc
- csky
- h8300
- hexagon
- nds32
- nios2
- openrisc
- riscv (32/64)

CC: Jan Kara <jack@suse.cz>
CC: Christian Brauner <christian.brauner@ubuntu.com>
CC: Sascha Hauer <s.hauer@pengutronix.de>
Link: https://lore.kernel.org/lkml/20210512153621.n5u43jsytbik4yze@wittgenstein
Link: https://lore.kernel.org/r/20210614153712.313707-1-marcin@juszkiewicz.com.pl
Fixes: 5b9fedb31e47 ("quota: Disable quotactl_path syscall")
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Marcin Juszkiewicz <marcin@juszkiewicz.com.pl>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 include/uapi/asm-generic/unistd.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 6de5a7fc066b..d2a942086fcb 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -863,8 +863,7 @@ __SYSCALL(__NR_process_madvise, sys_process_madvise)
 __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2)
 #define __NR_mount_setattr 442
 __SYSCALL(__NR_mount_setattr, sys_mount_setattr)
-#define __NR_quotactl_path 443
-__SYSCALL(__NR_quotactl_path, sys_quotactl_path)
+/* 443 is reserved for quotactl_path */
 
 #define __NR_landlock_create_ruleset 444
 __SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset)
-- 
cgit v1.2.3


From 475b92f932168a78da8109acd10bfb7578b8f2bb Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Jun 2021 15:24:05 -0700
Subject: ptp: improve max_adj check against unreasonable values

Scaled PPM conversion to PPB may (on 64bit systems) result
in a value larger than s32 can hold (freq/scaled_ppm is a long).
This means the kernel will not correctly reject unreasonably
high ->freq values (e.g. > 4294967295ppb, 281474976645 scaled PPM).

The conversion is equivalent to a division by ~66 (65.536),
so the value of ppb is always smaller than ppm, but not small
enough to assume narrowing the type from long -> s32 is okay.

Note that reasonable user space (e.g. ptp4l) will not use such
high values, anyway, 4289046510ppb ~= 4.3x, so the fix is
somewhat pedantic.

Fixes: d39a743511cd ("ptp: validate the requested frequency adjustment.")
Fixes: d94ba80ebbea ("ptp: Added a brand new class driver for ptp clocks.")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_clock.c          | 6 +++---
 include/linux/ptp_clock_kernel.h | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 03a246e60fd9..21c4c34c52d8 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -63,7 +63,7 @@ static void enqueue_external_timestamp(struct timestamp_event_queue *queue,
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
 
-s32 scaled_ppm_to_ppb(long ppm)
+long scaled_ppm_to_ppb(long ppm)
 {
 	/*
 	 * The 'freq' field in the 'struct timex' is in parts per
@@ -80,7 +80,7 @@ s32 scaled_ppm_to_ppb(long ppm)
 	s64 ppb = 1 + ppm;
 	ppb *= 125;
 	ppb >>= 13;
-	return (s32) ppb;
+	return (long) ppb;
 }
 EXPORT_SYMBOL(scaled_ppm_to_ppb);
 
@@ -138,7 +138,7 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx)
 		delta = ktime_to_ns(kt);
 		err = ops->adjtime(ops, delta);
 	} else if (tx->modes & ADJ_FREQUENCY) {
-		s32 ppb = scaled_ppm_to_ppb(tx->freq);
+		long ppb = scaled_ppm_to_ppb(tx->freq);
 		if (ppb > ops->max_adj || ppb < -ops->max_adj)
 			return -ERANGE;
 		if (ops->adjfine)
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index 0d47fd33b228..51d7f1b8b32a 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -235,7 +235,7 @@ extern int ptp_clock_index(struct ptp_clock *ptp);
  * @ppm:    Parts per million, but with a 16 bit binary fractional field
  */
 
-extern s32 scaled_ppm_to_ppb(long ppm);
+extern long scaled_ppm_to_ppb(long ppm);
 
 /**
  * ptp_find_pin() - obtain the pin index of a given auxiliary function
-- 
cgit v1.2.3


From e34492dea68d4f09e9989e518fc76cd41909d707 Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@gmail.com>
Date: Tue, 15 Jun 2021 07:52:43 +0800
Subject: net: inline function get_net_ns_by_fd if NET_NS is disabled

The function get_net_ns_by_fd() could be inlined when NET_NS is not
enabled.

Signed-off-by: Changbin Du <changbin.du@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h | 7 ++++++-
 net/core/net_namespace.c    | 8 +-------
 2 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 6412d7833d97..bdc0459a595e 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -186,6 +186,7 @@ void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid);
 void net_ns_barrier(void);
 
 struct ns_common *get_net_ns(struct ns_common *ns);
+struct net *get_net_ns_by_fd(int fd);
 #else /* CONFIG_NET_NS */
 #include <linux/sched.h>
 #include <linux/nsproxy.h>
@@ -210,13 +211,17 @@ static inline struct ns_common *get_net_ns(struct ns_common *ns)
 {
 	return ERR_PTR(-EINVAL);
 }
+
+static inline struct net *get_net_ns_by_fd(int fd)
+{
+	return ERR_PTR(-EINVAL);
+}
 #endif /* CONFIG_NET_NS */
 
 
 extern struct list_head net_namespace_list;
 
 struct net *get_net_ns_by_pid(pid_t pid);
-struct net *get_net_ns_by_fd(int fd);
 
 #ifdef CONFIG_SYSCTL
 void ipx_register_sysctl(void);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index cc8dafb25d61..9b5a767eddd5 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -672,14 +672,8 @@ struct net *get_net_ns_by_fd(int fd)
 	fput(file);
 	return net;
 }
-
-#else
-struct net *get_net_ns_by_fd(int fd)
-{
-	return ERR_PTR(-EINVAL);
-}
-#endif
 EXPORT_SYMBOL_GPL(get_net_ns_by_fd);
+#endif
 
 struct net *get_net_ns_by_pid(pid_t pid)
 {
-- 
cgit v1.2.3


From 25182f05ffed0b45602438693e4eed5d7f3ebadd Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Date: Tue, 15 Jun 2021 18:23:13 -0700
Subject: mm,hwpoison: fix race with hugetlb page allocation

When hugetlb page fault (under overcommitting situation) and
memory_failure() race, VM_BUG_ON_PAGE() is triggered by the following
race:

    CPU0:                           CPU1:

                                    gather_surplus_pages()
                                      page = alloc_surplus_huge_page()
    memory_failure_hugetlb()
      get_hwpoison_page(page)
        __get_hwpoison_page(page)
          get_page_unless_zero(page)
                                      zero = put_page_testzero(page)
                                      VM_BUG_ON_PAGE(!zero, page)
                                      enqueue_huge_page(h, page)
      put_page(page)

__get_hwpoison_page() only checks the page refcount before taking an
additional one for memory error handling, which is not enough because
there's a time window where compound pages have non-zero refcount during
hugetlb page initialization.

So make __get_hwpoison_page() check page status a bit more for hugetlb
pages with get_hwpoison_huge_page().  Checking hugetlb-specific flags
under hugetlb_lock makes sure that the hugetlb page is not transitive.
It's notable that another new function, HWPoisonHandlable(), is helpful
to prevent a race against other transitive page states (like a generic
compound page just before PageHuge becomes true).

Link: https://lkml.kernel.org/r/20210603233632.2964832-2-nao.horiguchi@gmail.com
Fixes: ead07f6a867b ("mm/memory-failure: introduce get_hwpoison_page() for consistent refcount handling")
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reported-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: <stable@vger.kernel.org>	[5.12+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h |  6 ++++++
 mm/hugetlb.c            | 15 +++++++++++++++
 mm/memory-failure.c     | 29 +++++++++++++++++++++++++++--
 3 files changed, 48 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index b92f25ccef58..790ae618548d 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -149,6 +149,7 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
 						long freed);
 bool isolate_huge_page(struct page *page, struct list_head *list);
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb);
 void putback_active_hugepage(struct page *page);
 void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
 void free_huge_page(struct page *page);
@@ -339,6 +340,11 @@ static inline bool isolate_huge_page(struct page *page, struct list_head *list)
 	return false;
 }
 
+static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+{
+	return 0;
+}
+
 static inline void putback_active_hugepage(struct page *page)
 {
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5560b50876fb..85f42ec1a927 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5857,6 +5857,21 @@ unlock:
 	return ret;
 }
 
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+{
+	int ret = 0;
+
+	*hugetlb = false;
+	spin_lock_irq(&hugetlb_lock);
+	if (PageHeadHuge(page)) {
+		*hugetlb = true;
+		if (HPageFreed(page) || HPageMigratable(page))
+			ret = get_page_unless_zero(page);
+	}
+	spin_unlock_irq(&hugetlb_lock);
+	return ret;
+}
+
 void putback_active_hugepage(struct page *page)
 {
 	spin_lock_irq(&hugetlb_lock);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 85ad98c00fd9..29ab7b70d326 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -949,6 +949,17 @@ static int page_action(struct page_state *ps, struct page *p,
 	return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY;
 }
 
+/*
+ * Return true if a page type of a given page is supported by hwpoison
+ * mechanism (while handling could fail), otherwise false.  This function
+ * does not return true for hugetlb or device memory pages, so it's assumed
+ * to be called only in the context where we never have such pages.
+ */
+static inline bool HWPoisonHandlable(struct page *page)
+{
+	return PageLRU(page) || __PageMovable(page);
+}
+
 /**
  * __get_hwpoison_page() - Get refcount for memory error handling:
  * @page:	raw error page (hit by memory error)
@@ -959,8 +970,22 @@ static int page_action(struct page_state *ps, struct page *p,
 static int __get_hwpoison_page(struct page *page)
 {
 	struct page *head = compound_head(page);
+	int ret = 0;
+	bool hugetlb = false;
+
+	ret = get_hwpoison_huge_page(head, &hugetlb);
+	if (hugetlb)
+		return ret;
+
+	/*
+	 * This check prevents from calling get_hwpoison_unless_zero()
+	 * for any unsupported type of page in order to reduce the risk of
+	 * unexpected races caused by taking a page refcount.
+	 */
+	if (!HWPoisonHandlable(head))
+		return 0;
 
-	if (!PageHuge(head) && PageTransHuge(head)) {
+	if (PageTransHuge(head)) {
 		/*
 		 * Non anonymous thp exists only in allocation/free time. We
 		 * can't handle such a case correctly, so let's give it up.
@@ -1017,7 +1042,7 @@ try_again:
 			ret = -EIO;
 		}
 	} else {
-		if (PageHuge(p) || PageLRU(p) || __PageMovable(p)) {
+		if (PageHuge(p) || HWPoisonHandlable(p)) {
 			ret = 1;
 		} else {
 			/*
-- 
cgit v1.2.3


From 099dd6878b9b12d6bbfa6bf29ce0c8ddd38f6901 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 15 Jun 2021 18:23:16 -0700
Subject: mm/swap: fix pte_same_as_swp() not removing uffd-wp bit when compare

I found it by pure code review, that pte_same_as_swp() of unuse_vma()
didn't take uffd-wp bit into account when comparing ptes.
pte_same_as_swp() returning false negative could cause failure to
swapoff swap ptes that was wr-protected by userfaultfd.

Link: https://lkml.kernel.org/r/20210603180546.9083-1-peterx@redhat.com
Fixes: f45ec5ff16a7 ("userfaultfd: wp: support swap and page migration")
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>	[5.7+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swapops.h | 15 +++++++++++----
 mm/swapfile.c           |  2 +-
 2 files changed, 12 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index d9b7c9132c2f..6430a94c6981 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -23,6 +23,16 @@
 #define SWP_TYPE_SHIFT	(BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT)
 #define SWP_OFFSET_MASK	((1UL << SWP_TYPE_SHIFT) - 1)
 
+/* Clear all flags but only keep swp_entry_t related information */
+static inline pte_t pte_swp_clear_flags(pte_t pte)
+{
+	if (pte_swp_soft_dirty(pte))
+		pte = pte_swp_clear_soft_dirty(pte);
+	if (pte_swp_uffd_wp(pte))
+		pte = pte_swp_clear_uffd_wp(pte);
+	return pte;
+}
+
 /*
  * Store a type+offset into a swp_entry_t in an arch-independent format
  */
@@ -66,10 +76,7 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte)
 {
 	swp_entry_t arch_entry;
 
-	if (pte_swp_soft_dirty(pte))
-		pte = pte_swp_clear_soft_dirty(pte);
-	if (pte_swp_uffd_wp(pte))
-		pte = pte_swp_clear_uffd_wp(pte);
+	pte = pte_swp_clear_flags(pte);
 	arch_entry = __pte_to_swp_entry(pte);
 	return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
 }
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 149e77454e3c..996afa8131c8 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1900,7 +1900,7 @@ unsigned int count_swap_pages(int type, int free)
 
 static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte)
 {
-	return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte);
+	return pte_same(pte_swp_clear_flags(pte), swp_pte);
 }
 
 /*
-- 
cgit v1.2.3


From 846be08578edb81f02bc8534577e6c367ef34f41 Mon Sep 17 00:00:00 2001
From: Mike Kravetz <mike.kravetz@oracle.com>
Date: Tue, 15 Jun 2021 18:23:29 -0700
Subject: mm/hugetlb: expand restore_reserve_on_error functionality

The routine restore_reserve_on_error is called to restore reservation
information when an error occurs after page allocation.  The routine
alloc_huge_page modifies the mapping reserve map and potentially the
reserve count during allocation.  If code calling alloc_huge_page
encounters an error after allocation and needs to free the page, the
reservation information needs to be adjusted.

Currently, restore_reserve_on_error only takes action on pages for which
the reserve count was adjusted(HPageRestoreReserve flag).  There is
nothing wrong with these adjustments.  However, alloc_huge_page ALWAYS
modifies the reserve map during allocation even if the reserve count is
not adjusted.  This can cause issues as observed during development of
this patch [1].

One specific series of operations causing an issue is:

 - Create a shared hugetlb mapping
   Reservations for all pages created by default

 - Fault in a page in the mapping
   Reservation exists so reservation count is decremented

 - Punch a hole in the file/mapping at index previously faulted
   Reservation and any associated pages will be removed

 - Allocate a page to fill the hole
   No reservation entry, so reserve count unmodified
   Reservation entry added to map by alloc_huge_page

 - Error after allocation and before instantiating the page
   Reservation entry remains in map

 - Allocate a page to fill the hole
   Reservation entry exists, so decrement reservation count

This will cause a reservation count underflow as the reservation count
was decremented twice for the same index.

A user would observe a very large number for HugePages_Rsvd in
/proc/meminfo.  This would also likely cause subsequent allocations of
hugetlb pages to fail as it would 'appear' that all pages are reserved.

This sequence of operations is unlikely to happen, however they were
easily reproduced and observed using hacked up code as described in [1].

Address the issue by having the routine restore_reserve_on_error take
action on pages where HPageRestoreReserve is not set.  In this case, we
need to remove any reserve map entry created by alloc_huge_page.  A new
helper routine vma_del_reservation assists with this operation.

There are three callers of alloc_huge_page which do not currently call
restore_reserve_on error before freeing a page on error paths.  Add
those missing calls.

[1] https://lore.kernel.org/linux-mm/20210528005029.88088-1-almasrymina@google.com/

Link: https://lkml.kernel.org/r/20210607204510.22617-1-mike.kravetz@oracle.com
Fixes: 96b96a96ddee ("mm/hugetlb: fix huge page reservation leak in private mapping error paths"
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/hugetlbfs/inode.c    |   1 +
 include/linux/hugetlb.h |   2 +
 mm/hugetlb.c            | 120 ++++++++++++++++++++++++++++++++++++++----------
 3 files changed, 100 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 55efd3dd04f6..30dee68458c7 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -735,6 +735,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		__SetPageUptodate(page);
 		error = huge_add_to_page_cache(page, mapping, index);
 		if (unlikely(error)) {
+			restore_reserve_on_error(h, &pseudo_vma, addr, page);
 			put_page(page);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			goto out;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 790ae618548d..6504346a1947 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -610,6 +610,8 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 				unsigned long address);
 int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 			pgoff_t idx);
+void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
+				unsigned long address, struct page *page);
 
 /* arch callback */
 int __init __alloc_bootmem_huge_page(struct hstate *h);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 85f42ec1a927..e0a5f9cbbece 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2121,12 +2121,18 @@ out:
  * be restored when a newly allocated huge page must be freed.  It is
  * to be called after calling vma_needs_reservation to determine if a
  * reservation exists.
+ *
+ * vma_del_reservation is used in error paths where an entry in the reserve
+ * map was created during huge page allocation and must be removed.  It is to
+ * be called after calling vma_needs_reservation to determine if a reservation
+ * exists.
  */
 enum vma_resv_mode {
 	VMA_NEEDS_RESV,
 	VMA_COMMIT_RESV,
 	VMA_END_RESV,
 	VMA_ADD_RESV,
+	VMA_DEL_RESV,
 };
 static long __vma_reservation_common(struct hstate *h,
 				struct vm_area_struct *vma, unsigned long addr,
@@ -2170,11 +2176,21 @@ static long __vma_reservation_common(struct hstate *h,
 			ret = region_del(resv, idx, idx + 1);
 		}
 		break;
+	case VMA_DEL_RESV:
+		if (vma->vm_flags & VM_MAYSHARE) {
+			region_abort(resv, idx, idx + 1, 1);
+			ret = region_del(resv, idx, idx + 1);
+		} else {
+			ret = region_add(resv, idx, idx + 1, 1, NULL, NULL);
+			/* region_add calls of range 1 should never fail. */
+			VM_BUG_ON(ret < 0);
+		}
+		break;
 	default:
 		BUG();
 	}
 
-	if (vma->vm_flags & VM_MAYSHARE)
+	if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV)
 		return ret;
 	/*
 	 * We know private mapping must have HPAGE_RESV_OWNER set.
@@ -2222,25 +2238,39 @@ static long vma_add_reservation(struct hstate *h,
 	return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV);
 }
 
+static long vma_del_reservation(struct hstate *h,
+			struct vm_area_struct *vma, unsigned long addr)
+{
+	return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV);
+}
+
 /*
- * This routine is called to restore a reservation on error paths.  In the
- * specific error paths, a huge page was allocated (via alloc_huge_page)
- * and is about to be freed.  If a reservation for the page existed,
- * alloc_huge_page would have consumed the reservation and set
- * HPageRestoreReserve in the newly allocated page.  When the page is freed
- * via free_huge_page, the global reservation count will be incremented if
- * HPageRestoreReserve is set.  However, free_huge_page can not adjust the
- * reserve map.  Adjust the reserve map here to be consistent with global
- * reserve count adjustments to be made by free_huge_page.
+ * This routine is called to restore reservation information on error paths.
+ * It should ONLY be called for pages allocated via alloc_huge_page(), and
+ * the hugetlb mutex should remain held when calling this routine.
+ *
+ * It handles two specific cases:
+ * 1) A reservation was in place and the page consumed the reservation.
+ *    HPageRestoreReserve is set in the page.
+ * 2) No reservation was in place for the page, so HPageRestoreReserve is
+ *    not set.  However, alloc_huge_page always updates the reserve map.
+ *
+ * In case 1, free_huge_page later in the error path will increment the
+ * global reserve count.  But, free_huge_page does not have enough context
+ * to adjust the reservation map.  This case deals primarily with private
+ * mappings.  Adjust the reserve map here to be consistent with global
+ * reserve count adjustments to be made by free_huge_page.  Make sure the
+ * reserve map indicates there is a reservation present.
+ *
+ * In case 2, simply undo reserve map modifications done by alloc_huge_page.
  */
-static void restore_reserve_on_error(struct hstate *h,
-			struct vm_area_struct *vma, unsigned long address,
-			struct page *page)
+void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
+			unsigned long address, struct page *page)
 {
-	if (unlikely(HPageRestoreReserve(page))) {
-		long rc = vma_needs_reservation(h, vma, address);
+	long rc = vma_needs_reservation(h, vma, address);
 
-		if (unlikely(rc < 0)) {
+	if (HPageRestoreReserve(page)) {
+		if (unlikely(rc < 0))
 			/*
 			 * Rare out of memory condition in reserve map
 			 * manipulation.  Clear HPageRestoreReserve so that
@@ -2253,16 +2283,57 @@ static void restore_reserve_on_error(struct hstate *h,
 			 * accounting of reserve counts.
 			 */
 			ClearHPageRestoreReserve(page);
-		} else if (rc) {
-			rc = vma_add_reservation(h, vma, address);
-			if (unlikely(rc < 0))
+		else if (rc)
+			(void)vma_add_reservation(h, vma, address);
+		else
+			vma_end_reservation(h, vma, address);
+	} else {
+		if (!rc) {
+			/*
+			 * This indicates there is an entry in the reserve map
+			 * added by alloc_huge_page.  We know it was added
+			 * before the alloc_huge_page call, otherwise
+			 * HPageRestoreReserve would be set on the page.
+			 * Remove the entry so that a subsequent allocation
+			 * does not consume a reservation.
+			 */
+			rc = vma_del_reservation(h, vma, address);
+			if (rc < 0)
 				/*
-				 * See above comment about rare out of
-				 * memory condition.
+				 * VERY rare out of memory condition.  Since
+				 * we can not delete the entry, set
+				 * HPageRestoreReserve so that the reserve
+				 * count will be incremented when the page
+				 * is freed.  This reserve will be consumed
+				 * on a subsequent allocation.
 				 */
-				ClearHPageRestoreReserve(page);
+				SetHPageRestoreReserve(page);
+		} else if (rc < 0) {
+			/*
+			 * Rare out of memory condition from
+			 * vma_needs_reservation call.  Memory allocation is
+			 * only attempted if a new entry is needed.  Therefore,
+			 * this implies there is not an entry in the
+			 * reserve map.
+			 *
+			 * For shared mappings, no entry in the map indicates
+			 * no reservation.  We are done.
+			 */
+			if (!(vma->vm_flags & VM_MAYSHARE))
+				/*
+				 * For private mappings, no entry indicates
+				 * a reservation is present.  Since we can
+				 * not add an entry, set SetHPageRestoreReserve
+				 * on the page so reserve count will be
+				 * incremented when freed.  This reserve will
+				 * be consumed on a subsequent allocation.
+				 */
+				SetHPageRestoreReserve(page);
 		} else
-			vma_end_reservation(h, vma, address);
+			/*
+			 * No reservation present, do nothing
+			 */
+			 vma_end_reservation(h, vma, address);
 	}
 }
 
@@ -4037,6 +4108,8 @@ again:
 				spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 				entry = huge_ptep_get(src_pte);
 				if (!pte_same(src_pte_old, entry)) {
+					restore_reserve_on_error(h, vma, addr,
+								new);
 					put_page(new);
 					/* dst_entry won't change as in child */
 					goto again;
@@ -5006,6 +5079,7 @@ out_release_unlock:
 	if (vm_shared || is_continue)
 		unlock_page(page);
 out_release_nounlock:
+	restore_reserve_on_error(h, dst_vma, dst_addr, page);
 	put_page(page);
 	goto out;
 }
-- 
cgit v1.2.3


From 3b77e8c8cde581dadab9a0f1543a347e24315f11 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hughd@google.com>
Date: Tue, 15 Jun 2021 18:23:49 -0700
Subject: mm/thp: make is_huge_zero_pmd() safe and quicker

Most callers of is_huge_zero_pmd() supply a pmd already verified
present; but a few (notably zap_huge_pmd()) do not - it might be a pmd
migration entry, in which the pfn is encoded differently from a present
pmd: which might pass the is_huge_zero_pmd() test (though not on x86,
since L1TF forced us to protect against that); or perhaps even crash in
pmd_page() applied to a swap-like entry.

Make it safe by adding pmd_present() check into is_huge_zero_pmd()
itself; and make it quicker by saving huge_zero_pfn, so that
is_huge_zero_pmd() will not need to do that pmd_page() lookup each time.

__split_huge_pmd_locked() checked pmd_trans_huge() before: that worked,
but is unnecessary now that is_huge_zero_pmd() checks present.

Link: https://lkml.kernel.org/r/21ea9ca-a1f5-8b90-5e88-95fb1c49bbfa@google.com
Fixes: e71769ae5260 ("mm: enable thp migration for shmem thp")
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jue Wang <juew@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h | 8 +++++++-
 mm/huge_memory.c        | 5 ++++-
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 9626fda5efce..2a8ebe6c222e 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -286,6 +286,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
 vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
 
 extern struct page *huge_zero_page;
+extern unsigned long huge_zero_pfn;
 
 static inline bool is_huge_zero_page(struct page *page)
 {
@@ -294,7 +295,7 @@ static inline bool is_huge_zero_page(struct page *page)
 
 static inline bool is_huge_zero_pmd(pmd_t pmd)
 {
-	return is_huge_zero_page(pmd_page(pmd));
+	return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd);
 }
 
 static inline bool is_huge_zero_pud(pud_t pud)
@@ -440,6 +441,11 @@ static inline bool is_huge_zero_page(struct page *page)
 	return false;
 }
 
+static inline bool is_huge_zero_pmd(pmd_t pmd)
+{
+	return false;
+}
+
 static inline bool is_huge_zero_pud(pud_t pud)
 {
 	return false;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 42cfefc6e66e..5885c5f5836f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -62,6 +62,7 @@ static struct shrinker deferred_split_shrinker;
 
 static atomic_t huge_zero_refcount;
 struct page *huge_zero_page __read_mostly;
+unsigned long huge_zero_pfn __read_mostly = ~0UL;
 
 bool transparent_hugepage_enabled(struct vm_area_struct *vma)
 {
@@ -98,6 +99,7 @@ retry:
 		__free_pages(zero_page, compound_order(zero_page));
 		goto retry;
 	}
+	WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page));
 
 	/* We take additional reference here. It will be put back by shrinker */
 	atomic_set(&huge_zero_refcount, 2);
@@ -147,6 +149,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
 	if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
 		struct page *zero_page = xchg(&huge_zero_page, NULL);
 		BUG_ON(zero_page == NULL);
+		WRITE_ONCE(huge_zero_pfn, ~0UL);
 		__free_pages(zero_page, compound_order(zero_page));
 		return HPAGE_PMD_NR;
 	}
@@ -2071,7 +2074,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		return;
 	}
 
-	if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
+	if (is_huge_zero_pmd(*pmd)) {
 		/*
 		 * FIXME: Do we want to invalidate secondary mmu by calling
 		 * mmu_notifier_invalidate_range() see comments below inside
-- 
cgit v1.2.3


From 732ed55823fc3ad998d43b86bf771887bcc5ec67 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hughd@google.com>
Date: Tue, 15 Jun 2021 18:23:53 -0700
Subject: mm/thp: try_to_unmap() use TTU_SYNC for safe splitting

Stressing huge tmpfs often crashed on unmap_page()'s VM_BUG_ON_PAGE
(!unmap_success): with dump_page() showing mapcount:1, but then its raw
struct page output showing _mapcount ffffffff i.e.  mapcount 0.

And even if that particular VM_BUG_ON_PAGE(!unmap_success) is removed,
it is immediately followed by a VM_BUG_ON_PAGE(compound_mapcount(head)),
and further down an IS_ENABLED(CONFIG_DEBUG_VM) total_mapcount BUG():
all indicative of some mapcount difficulty in development here perhaps.
But the !CONFIG_DEBUG_VM path handles the failures correctly and
silently.

I believe the problem is that once a racing unmap has cleared pte or
pmd, try_to_unmap_one() may skip taking the page table lock, and emerge
from try_to_unmap() before the racing task has reached decrementing
mapcount.

Instead of abandoning the unsafe VM_BUG_ON_PAGE(), and the ones that
follow, use PVMW_SYNC in try_to_unmap_one() in this case: adding
TTU_SYNC to the options, and passing that from unmap_page().

When CONFIG_DEBUG_VM, or for non-debug too? Consensus is to do the same
for both: the slight overhead added should rarely matter, except perhaps
if splitting sparsely-populated multiply-mapped shmem.  Once confident
that bugs are fixed, TTU_SYNC here can be removed, and the race
tolerated.

Link: https://lkml.kernel.org/r/c1e95853-8bcd-d8fd-55fa-e7f2488e78f@google.com
Fixes: fec89c109f3a ("thp: rewrite freeze_page()/unfreeze_page() with generic rmap walkers")
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jue Wang <juew@google.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/rmap.h |  1 +
 mm/huge_memory.c     |  2 +-
 mm/page_vma_mapped.c | 11 +++++++++++
 mm/rmap.c            | 17 ++++++++++++++++-
 4 files changed, 29 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index def5c62c93b3..8d04e7deedc6 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -91,6 +91,7 @@ enum ttu_flags {
 
 	TTU_SPLIT_HUGE_PMD	= 0x4,	/* split huge PMD if any */
 	TTU_IGNORE_MLOCK	= 0x8,	/* ignore mlock */
+	TTU_SYNC		= 0x10,	/* avoid racy checks with PVMW_SYNC */
 	TTU_IGNORE_HWPOISON	= 0x20,	/* corrupted page is recoverable */
 	TTU_BATCH_FLUSH		= 0x40,	/* Batch TLB flushes where possible
 					 * and caller guarantees they will
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5885c5f5836f..84ab735139dc 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2350,7 +2350,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 
 static void unmap_page(struct page *page)
 {
-	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK |
+	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_SYNC |
 		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
 	bool unmap_success;
 
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 2cf01d933f13..5b559967410e 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -212,6 +212,17 @@ restart:
 			pvmw->ptl = NULL;
 		}
 	} else if (!pmd_present(pmde)) {
+		/*
+		 * If PVMW_SYNC, take and drop THP pmd lock so that we
+		 * cannot return prematurely, while zap_huge_pmd() has
+		 * cleared *pmd but not decremented compound_mapcount().
+		 */
+		if ((pvmw->flags & PVMW_SYNC) &&
+		    PageTransCompound(pvmw->page)) {
+			spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
+
+			spin_unlock(ptl);
+		}
 		return false;
 	}
 	if (!map_pte(pvmw))
diff --git a/mm/rmap.c b/mm/rmap.c
index 693a610e181d..07811b4ae793 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1405,6 +1405,15 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	struct mmu_notifier_range range;
 	enum ttu_flags flags = (enum ttu_flags)(long)arg;
 
+	/*
+	 * When racing against e.g. zap_pte_range() on another cpu,
+	 * in between its ptep_get_and_clear_full() and page_remove_rmap(),
+	 * try_to_unmap() may return false when it is about to become true,
+	 * if page table locking is skipped: use TTU_SYNC to wait for that.
+	 */
+	if (flags & TTU_SYNC)
+		pvmw.flags = PVMW_SYNC;
+
 	/* munlock has nothing to gain from examining un-locked vmas */
 	if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
 		return true;
@@ -1777,7 +1786,13 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags)
 	else
 		rmap_walk(page, &rwc);
 
-	return !page_mapcount(page) ? true : false;
+	/*
+	 * When racing against e.g. zap_pte_range() on another cpu,
+	 * in between its ptep_get_and_clear_full() and page_remove_rmap(),
+	 * try_to_unmap() may return false when it is about to become true,
+	 * if page table locking is skipped: use TTU_SYNC to wait for that.
+	 */
+	return !page_mapcount(page);
 }
 
 /**
-- 
cgit v1.2.3


From 22061a1ffabdb9c3385de159c5db7aac3a4df1cc Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hughd@google.com>
Date: Tue, 15 Jun 2021 18:24:03 -0700
Subject: mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page()

There is a race between THP unmapping and truncation, when truncate sees
pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared
it, but before its page_remove_rmap() gets to decrement
compound_mapcount: generating false "BUG: Bad page cache" reports that
the page is still mapped when deleted.  This commit fixes that, but not
in the way I hoped.

The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK)
instead of unmap_mapping_range() in truncate_cleanup_page(): it has
often been an annoyance that we usually call unmap_mapping_range() with
no pages locked, but there apply it to a single locked page.
try_to_unmap() looks more suitable for a single locked page.

However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page):
it is used to insert THP migration entries, but not used to unmap THPs.
Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB
needs are different, I'm too ignorant of the DAX cases, and couldn't
decide how far to go for anon+swap.  Set that aside.

The second attempt took a different tack: make no change in truncate.c,
but modify zap_huge_pmd() to insert an invalidated huge pmd instead of
clearing it initially, then pmd_clear() between page_remove_rmap() and
unlocking at the end.  Nice.  But powerpc blows that approach out of the
water, with its serialize_against_pte_lookup(), and interesting pgtable
usage.  It would need serious help to get working on powerpc (with a
minor optimization issue on s390 too).  Set that aside.

Just add an "if (page_mapped(page)) synchronize_rcu();" or other such
delay, after unmapping in truncate_cleanup_page()? Perhaps, but though
that's likely to reduce or eliminate the number of incidents, it would
give less assurance of whether we had identified the problem correctly.

This successful iteration introduces "unmap_mapping_page(page)" instead
of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route,
with an addition to details.  Then zap_pmd_range() watches for this
case, and does spin_unlock(pmd_lock) if so - just like
page_vma_mapped_walk() now does in the PVMW_SYNC case.  Not pretty, but
safe.

Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to
assert its interface; but currently that's only used to make sure that
page->mapping is stable, and zap_pmd_range() doesn't care if the page is
locked or not.  Along these lines, in invalidate_inode_pages2_range()
move the initial unmap_mapping_range() out from under page lock, before
then calling unmap_mapping_page() under page lock if still mapped.

Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com
Fixes: fc127da085c2 ("truncate: handle file thp")
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jue Wang <juew@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |  3 +++
 mm/memory.c        | 41 +++++++++++++++++++++++++++++++++++++++++
 mm/truncate.c      | 43 +++++++++++++++++++------------------------
 3 files changed, 63 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index c274f75efcf9..8ae31622deef 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1719,6 +1719,7 @@ struct zap_details {
 	struct address_space *check_mapping;	/* Check page->mapping if set */
 	pgoff_t	first_index;			/* Lowest page->index to unmap */
 	pgoff_t last_index;			/* Highest page->index to unmap */
+	struct page *single_page;		/* Locked page to be unmapped */
 };
 
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
@@ -1766,6 +1767,7 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
 extern int fixup_user_fault(struct mm_struct *mm,
 			    unsigned long address, unsigned int fault_flags,
 			    bool *unlocked);
+void unmap_mapping_page(struct page *page);
 void unmap_mapping_pages(struct address_space *mapping,
 		pgoff_t start, pgoff_t nr, bool even_cows);
 void unmap_mapping_range(struct address_space *mapping,
@@ -1786,6 +1788,7 @@ static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address,
 	BUG();
 	return -EFAULT;
 }
+static inline void unmap_mapping_page(struct page *page) { }
 static inline void unmap_mapping_pages(struct address_space *mapping,
 		pgoff_t start, pgoff_t nr, bool even_cows) { }
 static inline void unmap_mapping_range(struct address_space *mapping,
diff --git a/mm/memory.c b/mm/memory.c
index f3ffab9b9e39..486f4a2874e7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1361,7 +1361,18 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 			else if (zap_huge_pmd(tlb, vma, pmd, addr))
 				goto next;
 			/* fall through */
+		} else if (details && details->single_page &&
+			   PageTransCompound(details->single_page) &&
+			   next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) {
+			spinlock_t *ptl = pmd_lock(tlb->mm, pmd);
+			/*
+			 * Take and drop THP pmd lock so that we cannot return
+			 * prematurely, while zap_huge_pmd() has cleared *pmd,
+			 * but not yet decremented compound_mapcount().
+			 */
+			spin_unlock(ptl);
 		}
+
 		/*
 		 * Here there can be other concurrent MADV_DONTNEED or
 		 * trans huge page faults running, and if the pmd is
@@ -3236,6 +3247,36 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root,
 	}
 }
 
+/**
+ * unmap_mapping_page() - Unmap single page from processes.
+ * @page: The locked page to be unmapped.
+ *
+ * Unmap this page from any userspace process which still has it mmaped.
+ * Typically, for efficiency, the range of nearby pages has already been
+ * unmapped by unmap_mapping_pages() or unmap_mapping_range().  But once
+ * truncation or invalidation holds the lock on a page, it may find that
+ * the page has been remapped again: and then uses unmap_mapping_page()
+ * to unmap it finally.
+ */
+void unmap_mapping_page(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct zap_details details = { };
+
+	VM_BUG_ON(!PageLocked(page));
+	VM_BUG_ON(PageTail(page));
+
+	details.check_mapping = mapping;
+	details.first_index = page->index;
+	details.last_index = page->index + thp_nr_pages(page) - 1;
+	details.single_page = page;
+
+	i_mmap_lock_write(mapping);
+	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)))
+		unmap_mapping_range_tree(&mapping->i_mmap, &details);
+	i_mmap_unlock_write(mapping);
+}
+
 /**
  * unmap_mapping_pages() - Unmap pages from processes.
  * @mapping: The address space containing pages to be unmapped.
diff --git a/mm/truncate.c b/mm/truncate.c
index 95af244b112a..234ddd879caa 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -167,13 +167,10 @@ void do_invalidatepage(struct page *page, unsigned int offset,
  * its lock, b) when a concurrent invalidate_mapping_pages got there first and
  * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space.
  */
-static void
-truncate_cleanup_page(struct address_space *mapping, struct page *page)
+static void truncate_cleanup_page(struct page *page)
 {
-	if (page_mapped(page)) {
-		unsigned int nr = thp_nr_pages(page);
-		unmap_mapping_pages(mapping, page->index, nr, false);
-	}
+	if (page_mapped(page))
+		unmap_mapping_page(page);
 
 	if (page_has_private(page))
 		do_invalidatepage(page, 0, thp_size(page));
@@ -218,7 +215,7 @@ int truncate_inode_page(struct address_space *mapping, struct page *page)
 	if (page->mapping != mapping)
 		return -EIO;
 
-	truncate_cleanup_page(mapping, page);
+	truncate_cleanup_page(page);
 	delete_from_page_cache(page);
 	return 0;
 }
@@ -325,7 +322,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 		index = indices[pagevec_count(&pvec) - 1] + 1;
 		truncate_exceptional_pvec_entries(mapping, &pvec, indices);
 		for (i = 0; i < pagevec_count(&pvec); i++)
-			truncate_cleanup_page(mapping, pvec.pages[i]);
+			truncate_cleanup_page(pvec.pages[i]);
 		delete_from_page_cache_batch(mapping, &pvec);
 		for (i = 0; i < pagevec_count(&pvec); i++)
 			unlock_page(pvec.pages[i]);
@@ -639,6 +636,16 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 				continue;
 			}
 
+			if (!did_range_unmap && page_mapped(page)) {
+				/*
+				 * If page is mapped, before taking its lock,
+				 * zap the rest of the file in one hit.
+				 */
+				unmap_mapping_pages(mapping, index,
+						(1 + end - index), false);
+				did_range_unmap = 1;
+			}
+
 			lock_page(page);
 			WARN_ON(page_to_index(page) != index);
 			if (page->mapping != mapping) {
@@ -646,23 +653,11 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 				continue;
 			}
 			wait_on_page_writeback(page);
-			if (page_mapped(page)) {
-				if (!did_range_unmap) {
-					/*
-					 * Zap the rest of the file in one hit.
-					 */
-					unmap_mapping_pages(mapping, index,
-						(1 + end - index), false);
-					did_range_unmap = 1;
-				} else {
-					/*
-					 * Just zap this page
-					 */
-					unmap_mapping_pages(mapping, index,
-								1, false);
-				}
-			}
+
+			if (page_mapped(page))
+				unmap_mapping_page(page);
 			BUG_ON(page_mapped(page));
+
 			ret2 = do_launder_page(mapping, page);
 			if (ret2 == 0) {
 				if (!invalidate_complete_page2(mapping, page))
-- 
cgit v1.2.3


From a5ae8fc9058e37437c8c1f82b3d412b4abd1b9e6 Mon Sep 17 00:00:00 2001
From: Dmytro Linkin <dlinkin@nvidia.com>
Date: Fri, 14 May 2021 11:14:19 +0300
Subject: net/mlx5e: Don't create devices during unload flow

Running devlink reload command for port in switchdev mode cause
resources to corrupt: driver can't release allocated EQ and reclaim
memory pages, because "rdma" auxiliary device had add CQs which blocks
EQ from deletion.
Erroneous sequence happens during reload-down phase, and is following:

1. detach device - suspends auxiliary devices which support it, destroys
   others. During this step "eth-rep" and "rdma-rep" are destroyed,
   "eth" - suspended.
2. disable SRIOV - moves device to legacy mode; as part of disablement -
   rescans drivers. This step adds "rdma" auxiliary device.
3. destroy EQ table - <failure>.

Driver shouldn't create any device during unload flows. To handle that
implement MLX5_PRIV_FLAGS_DETACH flag, set it on device detach and unset
on device attach. If flag is set do no-op on drivers rescan.

Fixes: a925b5e309c9 ("net/mlx5: Register mlx5 devices to auxiliary virtual bus")
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c | 4 ++++
 include/linux/mlx5/driver.h                   | 4 ++++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 8de118adfb54..ceebfc20f65e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -303,6 +303,7 @@ int mlx5_attach_device(struct mlx5_core_dev *dev)
 	int ret = 0, i;
 
 	mutex_lock(&mlx5_intf_mutex);
+	priv->flags &= ~MLX5_PRIV_FLAGS_DETACH;
 	for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) {
 		if (!priv->adev[i]) {
 			bool is_supported = false;
@@ -375,6 +376,7 @@ skip_suspend:
 		del_adev(&priv->adev[i]->adev);
 		priv->adev[i] = NULL;
 	}
+	priv->flags |= MLX5_PRIV_FLAGS_DETACH;
 	mutex_unlock(&mlx5_intf_mutex);
 }
 
@@ -463,6 +465,8 @@ int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev)
 	struct mlx5_priv *priv = &dev->priv;
 
 	lockdep_assert_held(&mlx5_intf_mutex);
+	if (priv->flags & MLX5_PRIV_FLAGS_DETACH)
+		return 0;
 
 	delete_drivers(dev);
 	if (priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 020a8f7fdbdd..f8902bcd91e2 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -542,6 +542,10 @@ struct mlx5_core_roce {
 enum {
 	MLX5_PRIV_FLAGS_DISABLE_IB_ADEV = 1 << 0,
 	MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV = 1 << 1,
+	/* Set during device detach to block any further devices
+	 * creation/deletion on drivers rescan. Unset during device attach.
+	 */
+	MLX5_PRIV_FLAGS_DETACH = 1 << 2,
 };
 
 struct mlx5_adev {
-- 
cgit v1.2.3


From 321827477360934dc040e9d3c626bf1de6c3ab3c Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Fri, 18 Jun 2021 13:04:35 +0200
Subject: icmp: don't send out ICMP messages with a source address of 0.0.0.0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When constructing ICMP response messages, the kernel will try to pick a
suitable source address for the outgoing packet. However, if no IPv4
addresses are configured on the system at all, this will fail and we end up
producing an ICMP message with a source address of 0.0.0.0. This can happen
on a box routing IPv4 traffic via v6 nexthops, for instance.

Since 0.0.0.0 is not generally routable on the internet, there's a good
chance that such ICMP messages will never make it back to the sender of the
original packet that the ICMP message was sent in response to. This, in
turn, can create connectivity and PMTUd problems for senders. Fortunately,
RFC7600 reserves a dummy address to be used as a source for ICMP
messages (192.0.0.8/32), so let's teach the kernel to substitute that
address as a last resort if the regular source address selection procedure
fails.

Below is a quick example reproducing this issue with network namespaces:

ip netns add ns0
ip l add type veth peer netns ns0
ip l set dev veth0 up
ip a add 10.0.0.1/24 dev veth0
ip a add fc00:dead:cafe:42::1/64 dev veth0
ip r add 10.1.0.0/24 via inet6 fc00:dead:cafe:42::2
ip -n ns0 l set dev veth0 up
ip -n ns0 a add fc00:dead:cafe:42::2/64 dev veth0
ip -n ns0 r add 10.0.0.0/24 via inet6 fc00:dead:cafe:42::1
ip netns exec ns0 sysctl -w net.ipv4.icmp_ratelimit=0
ip netns exec ns0 sysctl -w net.ipv4.ip_forward=1
tcpdump -tpni veth0 -c 2 icmp &
ping -w 1 10.1.0.1 > /dev/null
tcpdump: verbose output suppressed, use -v[v]... for full protocol decode
listening on veth0, link-type EN10MB (Ethernet), snapshot length 262144 bytes
IP 10.0.0.1 > 10.1.0.1: ICMP echo request, id 29, seq 1, length 64
IP 0.0.0.0 > 10.0.0.1: ICMP net 10.1.0.1 unreachable, length 92
2 packets captured
2 packets received by filter
0 packets dropped by kernel

With this patch the above capture changes to:
IP 10.0.0.1 > 10.1.0.1: ICMP echo request, id 31127, seq 1, length 64
IP 192.0.0.8 > 10.0.0.1: ICMP net 10.1.0.1 unreachable, length 92

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Juliusz Chroboczek <jch@irif.fr>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/in.h | 3 +++
 net/ipv4/icmp.c         | 7 +++++++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 7d6687618d80..d1b327036ae4 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -289,6 +289,9 @@ struct sockaddr_in {
 /* Address indicating an error return. */
 #define	INADDR_NONE		((unsigned long int) 0xffffffff)
 
+/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */
+#define	INADDR_DUMMY		((unsigned long int) 0xc0000008)
+
 /* Network number for local host loopback. */
 #define	IN_LOOPBACKNET		127
 
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 7b6931a4d775..752e392083e6 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -759,6 +759,13 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 		icmp_param.data_len = room;
 	icmp_param.head_len = sizeof(struct icmphdr);
 
+	/* if we don't have a source address at this point, fall back to the
+	 * dummy address instead of sending out a packet with a source address
+	 * of 0.0.0.0
+	 */
+	if (!fl4.saddr)
+		fl4.saddr = htonl(INADDR_DUMMY);
+
 	icmp_push_reply(&icmp_param, &fl4, &ipc, &rt);
 ende:
 	ip_rt_put(rt);
-- 
cgit v1.2.3