diff options
Diffstat (limited to 'arch')
1115 files changed, 20184 insertions, 22476 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index e9c9334507dd..180ea33164dc 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -336,17 +336,6 @@ config HAVE_ARCH_SECCOMP_FILTER results in the system call being skipped immediately. - seccomp syscall wired up - For best performance, an arch should use seccomp_phase1 and - seccomp_phase2 directly. It should call seccomp_phase1 for all - syscalls if TIF_SECCOMP is set, but seccomp_phase1 does not - need to be called from a ptrace-safe context. It must then - call seccomp_phase2 if seccomp_phase1 returns anything other - than SECCOMP_PHASE1_OK or SECCOMP_PHASE1_SKIP. - - As an additional optimization, an arch may provide seccomp_data - directly to seccomp_phase1; this avoids multiple calls - to the syscall_xyz helpers for every syscall. - config SECCOMP_FILTER def_bool y depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET @@ -707,4 +696,38 @@ config ARCH_NO_COHERENT_DMA_MMAP config CPU_NO_EFFICIENT_FFS def_bool n +config HAVE_ARCH_VMAP_STACK + def_bool n + help + An arch should select this symbol if it can support kernel stacks + in vmalloc space. This means: + + - vmalloc space must be large enough to hold many kernel stacks. + This may rule out many 32-bit architectures. + + - Stacks in vmalloc space need to work reliably. For example, if + vmap page tables are created on demand, either this mechanism + needs to work while the stack points to a virtual address with + unpopulated page tables or arch code (switch_to() and switch_mm(), + most likely) needs to ensure that the stack's page table entries + are populated before running on a possibly unpopulated stack. + + - If the stack overflows into a guard page, something reasonable + should happen. The definition of "reasonable" is flexible, but + instantly rebooting without logging anything would be unfriendly. + +config VMAP_STACK + default y + bool "Use a virtually-mapped stack" + depends on HAVE_ARCH_VMAP_STACK && !KASAN + ---help--- + Enable this if you want the use virtually-mapped kernel stacks + with guard pages. This causes kernel stack overflows to be + caught immediately rather than causing difficult-to-diagnose + corruption. + + This is presently incompatible with KASAN because KASAN expects + the stack to map directly to the KASAN shadow map using a formula + that is incorrect if the stack is in vmalloc space. + source "kernel/gcov/Kconfig" diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h index c419b43c461d..466e42e96bfa 100644 --- a/arch/alpha/include/asm/uaccess.h +++ b/arch/alpha/include/asm/uaccess.h @@ -371,14 +371,6 @@ __copy_tofrom_user_nocheck(void *to, const void *from, long len) return __cu_len; } -extern inline long -__copy_tofrom_user(void *to, const void *from, long len, const void __user *validate) -{ - if (__access_ok((unsigned long)validate, len, get_fs())) - len = __copy_tofrom_user_nocheck(to, from, len); - return len; -} - #define __copy_to_user(to, from, n) \ ({ \ __chk_user_ptr(to); \ @@ -393,17 +385,22 @@ __copy_tofrom_user(void *to, const void *from, long len, const void __user *vali #define __copy_to_user_inatomic __copy_to_user #define __copy_from_user_inatomic __copy_from_user - extern inline long copy_to_user(void __user *to, const void *from, long n) { - return __copy_tofrom_user((__force void *)to, from, n, to); + if (likely(__access_ok((unsigned long)to, n, get_fs()))) + n = __copy_tofrom_user_nocheck((__force void *)to, from, n); + return n; } extern inline long copy_from_user(void *to, const void __user *from, long n) { - return __copy_tofrom_user(to, (__force void *)from, n, from); + if (likely(__access_ok((unsigned long)from, n, get_fs()))) + n = __copy_tofrom_user_nocheck(to, (__force void *)from, n); + else + memset(to, 0, n); + return n; } extern void __do_clear_user(void); diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 0d3e59f56974..ecd12379e2cd 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -13,7 +13,7 @@ config ARC select CLKSRC_OF select CLONE_BACKWARDS select COMMON_CLK - select GENERIC_ATOMIC64 + select GENERIC_ATOMIC64 if !ISA_ARCV2 || !(ARC_HAS_LL64 && ARC_HAS_LLSC) select GENERIC_CLOCKEVENTS select GENERIC_FIND_FIRST_BIT # for now, we don't need GENERIC_IRQ_PROBE, CONFIG_GENERIC_IRQ_CHIP @@ -353,8 +353,8 @@ endchoice config NODES_SHIFT int "Maximum NUMA Nodes (as a power of 2)" - default "1" if !DISCONTIGMEM - default "2" if DISCONTIGMEM + default "0" if !DISCONTIGMEM + default "1" if DISCONTIGMEM depends on NEED_MULTIPLE_NODES ---help--- Accessing memory beyond 1GB (with or w/o PAE) requires 2 memory diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 601ed173080b..aa82d13d4213 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -47,7 +47,6 @@ endif upto_gcc44 := $(call cc-ifversion, -le, 0404, y) atleast_gcc44 := $(call cc-ifversion, -ge, 0404, y) -atleast_gcc48 := $(call cc-ifversion, -ge, 0408, y) cflags-$(atleast_gcc44) += -fsection-anchors @@ -66,10 +65,8 @@ endif endif -# By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok -ifeq ($(atleast_gcc48),y) -cflags-$(CONFIG_ARC_DW2_UNWIND) += -gdwarf-2 -endif +cfi := $(call as-instr,.cfi_startproc\n.cfi_endproc,-DARC_DW2_UNWIND_AS_CFI) +cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables $(cfi) ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE # Generic build system uses -O2, we want -O3 diff --git a/arch/arc/boot/dts/abilis_tb100_dvk.dts b/arch/arc/boot/dts/abilis_tb100_dvk.dts index 3dd6ed941464..3acf04db8030 100644 --- a/arch/arc/boot/dts/abilis_tb100_dvk.dts +++ b/arch/arc/boot/dts/abilis_tb100_dvk.dts @@ -24,6 +24,7 @@ /include/ "abilis_tb100.dtsi" / { + model = "abilis,tb100"; chosen { bootargs = "earlycon=uart8250,mmio32,0xff100000,9600n8 console=ttyS0,9600n8"; }; diff --git a/arch/arc/boot/dts/abilis_tb101_dvk.dts b/arch/arc/boot/dts/abilis_tb101_dvk.dts index 1cf51c280f28..37d88c5dd181 100644 --- a/arch/arc/boot/dts/abilis_tb101_dvk.dts +++ b/arch/arc/boot/dts/abilis_tb101_dvk.dts @@ -24,6 +24,7 @@ /include/ "abilis_tb101.dtsi" / { + model = "abilis,tb101"; chosen { bootargs = "earlycon=uart8250,mmio32,0xff100000,9600n8 console=ttyS0,9600n8"; }; diff --git a/arch/arc/boot/dts/axs101.dts b/arch/arc/boot/dts/axs101.dts index 3f9b0582e734..d9b9b9dcfc4c 100644 --- a/arch/arc/boot/dts/axs101.dts +++ b/arch/arc/boot/dts/axs101.dts @@ -13,6 +13,7 @@ /include/ "axs10x_mb.dtsi" / { + model = "snps,axs101"; compatible = "snps,axs101", "snps,arc-sdp"; chosen { diff --git a/arch/arc/boot/dts/axs103.dts b/arch/arc/boot/dts/axs103.dts index e6d0e31ea299..ec7fb277a067 100644 --- a/arch/arc/boot/dts/axs103.dts +++ b/arch/arc/boot/dts/axs103.dts @@ -16,6 +16,7 @@ /include/ "axs10x_mb.dtsi" / { + model = "snps,axs103"; compatible = "snps,axs103", "snps,arc-sdp"; chosen { diff --git a/arch/arc/boot/dts/axs103_idu.dts b/arch/arc/boot/dts/axs103_idu.dts index f999fef5a60a..070c29782216 100644 --- a/arch/arc/boot/dts/axs103_idu.dts +++ b/arch/arc/boot/dts/axs103_idu.dts @@ -16,6 +16,7 @@ /include/ "axs10x_mb.dtsi" / { + model = "snps,axs103-smp"; compatible = "snps,axs103", "snps,arc-sdp"; chosen { diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts index 63970513e4ae..ce0ccd20b5bf 100644 --- a/arch/arc/boot/dts/nsim_700.dts +++ b/arch/arc/boot/dts/nsim_700.dts @@ -10,6 +10,7 @@ /include/ "skeleton.dtsi" / { + model = "snps,nsim"; compatible = "snps,nsim"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts index bf05fe5f67b0..3772c40c245e 100644 --- a/arch/arc/boot/dts/nsim_hs.dts +++ b/arch/arc/boot/dts/nsim_hs.dts @@ -10,6 +10,7 @@ /include/ "skeleton_hs.dtsi" / { + model = "snps,nsim_hs"; compatible = "snps,nsim_hs"; #address-cells = <2>; #size-cells = <2>; diff --git a/arch/arc/boot/dts/nsim_hs_idu.dts b/arch/arc/boot/dts/nsim_hs_idu.dts index 99eabe1a2bf6..48434d7c4498 100644 --- a/arch/arc/boot/dts/nsim_hs_idu.dts +++ b/arch/arc/boot/dts/nsim_hs_idu.dts @@ -10,6 +10,7 @@ /include/ "skeleton_hs_idu.dtsi" / { + model = "snps,nsim_hs-smp"; compatible = "snps,nsim_hs"; interrupt-parent = <&core_intc>; diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts index e659a340ca8a..bcf603142a33 100644 --- a/arch/arc/boot/dts/nsimosci.dts +++ b/arch/arc/boot/dts/nsimosci.dts @@ -10,6 +10,7 @@ /include/ "skeleton.dtsi" / { + model = "snps,nsimosci"; compatible = "snps,nsimosci"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts index 16ce5d65cfde..14a727cbf4c9 100644 --- a/arch/arc/boot/dts/nsimosci_hs.dts +++ b/arch/arc/boot/dts/nsimosci_hs.dts @@ -10,6 +10,7 @@ /include/ "skeleton_hs.dtsi" / { + model = "snps,nsimosci_hs"; compatible = "snps,nsimosci_hs"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts index ce8dfbc30c4d..cbf65b6cc7c6 100644 --- a/arch/arc/boot/dts/nsimosci_hs_idu.dts +++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts @@ -10,6 +10,7 @@ /include/ "skeleton_hs_idu.dtsi" / { + model = "snps,nsimosci_hs-smp"; compatible = "snps,nsimosci_hs"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/boot/dts/vdk_hs38.dts b/arch/arc/boot/dts/vdk_hs38.dts index 5d803dd2de59..3c51103f0cd0 100644 --- a/arch/arc/boot/dts/vdk_hs38.dts +++ b/arch/arc/boot/dts/vdk_hs38.dts @@ -13,6 +13,7 @@ /include/ "vdk_axs10x_mb.dtsi" / { + model = "snps,vdk_archs"; compatible = "snps,axs103"; chosen { diff --git a/arch/arc/boot/dts/vdk_hs38_smp.dts b/arch/arc/boot/dts/vdk_hs38_smp.dts index 2ba60c399d99..6be68001a6f0 100644 --- a/arch/arc/boot/dts/vdk_hs38_smp.dts +++ b/arch/arc/boot/dts/vdk_hs38_smp.dts @@ -13,6 +13,7 @@ /include/ "vdk_axs10x_mb.dtsi" / { + model = "snps,vdk_archs-smp"; compatible = "snps,axs103"; chosen { diff --git a/arch/arc/boot/dts/zebu_hs.dts b/arch/arc/boot/dts/zebu_hs.dts new file mode 100644 index 000000000000..1c1324e84965 --- /dev/null +++ b/arch/arc/boot/dts/zebu_hs.dts @@ -0,0 +1,69 @@ +/* + * Copyright (C) 2016-2014 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +/dts-v1/; + +/include/ "skeleton_hs.dtsi" + +/ { + model = "snps,zebu_hs"; + compatible = "snps,zebu_hs"; + #address-cells = <1>; + #size-cells = <1>; + interrupt-parent = <&core_intc>; + + memory { + device_type = "memory"; + reg = <0x80000000 0x20000000>; /* 512 */ + }; + + chosen { + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1"; + }; + + aliases { + serial0 = &uart0; + }; + + fpga { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + + /* child and parent address space 1:1 mapped */ + ranges; + + core_clk: core_clk { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <50000000>; + }; + + core_intc: interrupt-controller { + compatible = "snps,archs-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + + uart0: serial@f0000000 { + compatible = "ns8250"; + reg = <0xf0000000 0x2000>; + interrupts = <24>; + clock-frequency = <50000000>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + no-loopback-test = <1>; + }; + + arcpct0: pct { + compatible = "snps,archs-pct"; + #interrupt-cells = <1>; + interrupts = <20>; + }; + }; +}; diff --git a/arch/arc/boot/dts/zebu_hs_idu.dts b/arch/arc/boot/dts/zebu_hs_idu.dts new file mode 100644 index 000000000000..65204b4c0f13 --- /dev/null +++ b/arch/arc/boot/dts/zebu_hs_idu.dts @@ -0,0 +1,85 @@ +/* + * Copyright (C) 2016-2014 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +/dts-v1/; + +/include/ "skeleton_hs_idu.dtsi" + +/ { + model = "snps,zebu_hs-smp"; + compatible = "snps,zebu_hs"; + #address-cells = <1>; + #size-cells = <1>; + interrupt-parent = <&core_intc>; + + memory { + device_type = "memory"; + reg = <0x80000000 0x20000000>; /* 512 */ + }; + + chosen { + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug"; + }; + + aliases { + serial0 = &uart0; + }; + + fpga { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + + /* child and parent address space 1:1 mapped */ + ranges; + + core_clk: core_clk { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <50000000>; /* 50 MHZ */ + }; + + core_intc: interrupt-controller { + compatible = "snps,archs-intc"; + interrupt-controller; + #interrupt-cells = <1>; +/* interrupts = <16 17 18 19 20 21 22 23 24 25>; */ + }; + + idu_intc: idu-interrupt-controller { + compatible = "snps,archs-idu-intc"; + interrupt-controller; + interrupt-parent = <&core_intc>; + /* <hwirq distribution> + distribution: 0=RR; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3 */ + #interrupt-cells = <2>; + interrupts = <24 25 26 27 28 29 30 31>; + + }; + + uart0: serial@f0000000 { + /* compatible = "ns8250"; Doesn't use FIFOs */ + compatible = "ns16550a"; + reg = <0xf0000000 0x2000>; + interrupt-parent = <&idu_intc>; + /* interrupts = <0 1>; DEST=1*/ + /* interrupts = <0 2>; DEST=2*/ + interrupts = <0 0>; /* RR*/ + clock-frequency = <50000000>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + no-loopback-test = <1>; + }; + + arcpct0: pct { + compatible = "snps,archs-pct"; + #interrupt-cells = <1>; + interrupts = <20>; + }; + }; +}; diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index 6cdffea3a914..0a0eaf09aac7 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -18,6 +18,9 @@ CONFIG_PERF_EVENTS=y # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_PARTITION_ADVANCED=y CONFIG_ARC_PLAT_AXS10X=y CONFIG_AXS101=y diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index 491b3b5f22bd..2233f5777a71 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -18,6 +18,9 @@ CONFIG_PERF_EVENTS=y # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_PARTITION_ADVANCED=y CONFIG_ARC_PLAT_AXS10X=y CONFIG_AXS103=y diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index b25ee73b2e79..110874705085 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -18,6 +18,9 @@ CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_PARTITION_ADVANCED=y CONFIG_ARC_PLAT_AXS10X=y CONFIG_AXS103=y diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index a99dc7a3f0af..65ab9fbf83f2 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -11,13 +11,16 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" +CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set CONFIG_KPROBES=y CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index 59f221fc9a41..3b3990cddbe1 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -16,6 +16,9 @@ CONFIG_EMBEDDED=y # CONFIG_COMPAT_BRK is not set CONFIG_KPROBES=y CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set diff --git a/arch/arc/configs/zebu_hs_defconfig b/arch/arc/configs/zebu_hs_defconfig new file mode 100644 index 000000000000..9f6166be7145 --- /dev/null +++ b/arch/arc/configs/zebu_hs_defconfig @@ -0,0 +1,86 @@ +CONFIG_DEFAULT_HOSTNAME="ARCLinux" +# CONFIG_SWAP is not set +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_NO_HZ_IDLE=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_NAMESPACES=y +# CONFIG_UTS_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" +CONFIG_EXPERT=y +CONFIG_PERF_EVENTS=y +# CONFIG_COMPAT_BRK is not set +CONFIG_SLAB=y +CONFIG_MODULES=y +# CONFIG_LBDAF is not set +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_IOSCHED_DEADLINE is not set +# CONFIG_IOSCHED_CFQ is not set +CONFIG_ARC_PLAT_SIM=y +CONFIG_ISA_ARCV2=y +CONFIG_ARC_BUILTIN_DTB_NAME="zebu_hs" +CONFIG_PREEMPT=y +# CONFIG_COMPACTION is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_PACKET_DIAG=y +CONFIG_UNIX=y +CONFIG_UNIX_DIAG=y +CONFIG_NET_KEY=y +CONFIG_INET=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_IPV6 is not set +# CONFIG_WIRELESS is not set +CONFIG_DEVTMPFS=y +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_FIRMWARE_IN_KERNEL is not set +# CONFIG_BLK_DEV is not set +CONFIG_NETDEVICES=y +# CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_SEEQ is not set +# CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_WLAN is not set +CONFIG_INPUT_EVDEV=y +CONFIG_MOUSE_PS2_TOUCHKIT=y +# CONFIG_SERIO_SERPORT is not set +CONFIG_SERIO_ARC_PS2=y +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=1 +CONFIG_SERIAL_8250_RUNTIME_UARTS=1 +CONFIG_SERIAL_8250_DW=y +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +CONFIG_FB=y +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_LOGO=y +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_TMPFS=y +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_NFS_FS=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_DEBUG_MEMORY_INIT=y +# CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/zebu_hs_smp_defconfig b/arch/arc/configs/zebu_hs_smp_defconfig new file mode 100644 index 000000000000..44e9693f4257 --- /dev/null +++ b/arch/arc/configs/zebu_hs_smp_defconfig @@ -0,0 +1,89 @@ +CONFIG_DEFAULT_HOSTNAME="ARCLinux" +# CONFIG_SWAP is not set +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_NO_HZ_IDLE=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_NAMESPACES=y +# CONFIG_UTS_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" +CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_SLAB=y +CONFIG_KPROBES=y +CONFIG_MODULES=y +# CONFIG_LBDAF is not set +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_IOSCHED_DEADLINE is not set +# CONFIG_IOSCHED_CFQ is not set +CONFIG_ARC_PLAT_SIM=y +CONFIG_ISA_ARCV2=y +CONFIG_SMP=y +CONFIG_ARC_BUILTIN_DTB_NAME="zebu_hs_idu" +CONFIG_PREEMPT=y +# CONFIG_COMPACTION is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_PACKET_DIAG=y +CONFIG_UNIX=y +CONFIG_UNIX_DIAG=y +CONFIG_NET_KEY=y +CONFIG_INET=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_IPV6 is not set +# CONFIG_WIRELESS is not set +CONFIG_DEVTMPFS=y +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_FIRMWARE_IN_KERNEL is not set +# CONFIG_BLK_DEV is not set +CONFIG_NETDEVICES=y +# CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_SEEQ is not set +# CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_WLAN is not set +CONFIG_INPUT_EVDEV=y +CONFIG_MOUSE_PS2_TOUCHKIT=y +# CONFIG_SERIO_SERPORT is not set +CONFIG_SERIO_ARC_PS2=y +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=1 +CONFIG_SERIAL_8250_RUNTIME_UARTS=1 +CONFIG_SERIAL_8250_DW=y +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +CONFIG_FB=y +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_LOGO=y +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_TMPFS=y +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_NFS_FS=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_LOCKUP_DETECTOR=y +# CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index 0b10ef2a4372..c332604606dd 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -25,6 +25,7 @@ generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += mman.h generic-y += msgbuf.h +generic-y += msi.h generic-y += param.h generic-y += parport.h generic-y += pci.h diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index 7fbaea00a336..db25c65155cb 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -95,7 +95,7 @@ /* Auxiliary registers */ #define AUX_IDENTITY 4 #define AUX_INTR_VEC_BASE 0x25 -#define AUX_NON_VOL 0x5e +#define AUX_VOL 0x5e /* * Floating Pt Registers @@ -240,14 +240,6 @@ struct bcr_extn_xymem { #endif }; -struct bcr_perip { -#ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int start:8, pad2:8, sz:8, ver:8; -#else - unsigned int ver:8, sz:8, pad2:8, start:8; -#endif -}; - struct bcr_iccm_arcompact { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int base:16, pad:5, sz:3, ver:8; diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 4e3c1b6b0806..b65930a49589 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -20,6 +20,7 @@ #ifndef CONFIG_ARC_PLAT_EZNPS #define atomic_read(v) READ_ONCE((v)->counter) +#define ATOMIC_INIT(i) { (i) } #ifdef CONFIG_ARC_HAS_LLSC @@ -284,6 +285,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3) #define atomic_sub(i, v) atomic_add(-(i), (v)) #define atomic_sub_return(i, v) atomic_add_return(-(i), (v)) +#define atomic_fetch_sub(i, v) atomic_fetch_add(-(i), (v)) #undef ATOMIC_OPS #define ATOMIC_OPS(op, c_op, asm_op) \ @@ -292,6 +294,7 @@ ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3) ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3) #define atomic_andnot(mask, v) atomic_and(~(mask), (v)) +#define atomic_fetch_andnot(mask, v) atomic_fetch_and(~(mask), (v)) ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3) ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) @@ -343,10 +346,266 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) #define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0) -#define ATOMIC_INIT(i) { (i) } + +#ifdef CONFIG_GENERIC_ATOMIC64 #include <asm-generic/atomic64.h> -#endif +#else /* Kconfig ensures this is only enabled with needed h/w assist */ + +/* + * ARCv2 supports 64-bit exclusive load (LLOCKD) / store (SCONDD) + * - The address HAS to be 64-bit aligned + * - There are 2 semantics involved here: + * = exclusive implies no interim update between load/store to same addr + * = both words are observed/updated together: this is guaranteed even + * for regular 64-bit load (LDD) / store (STD). Thus atomic64_set() + * is NOT required to use LLOCKD+SCONDD, STD suffices + */ + +typedef struct { + aligned_u64 counter; +} atomic64_t; + +#define ATOMIC64_INIT(a) { (a) } + +static inline long long atomic64_read(const atomic64_t *v) +{ + unsigned long long val; + + __asm__ __volatile__( + " ldd %0, [%1] \n" + : "=r"(val) + : "r"(&v->counter)); + + return val; +} + +static inline void atomic64_set(atomic64_t *v, long long a) +{ + /* + * This could have been a simple assignment in "C" but would need + * explicit volatile. Otherwise gcc optimizers could elide the store + * which borked atomic64 self-test + * In the inline asm version, memory clobber needed for exact same + * reason, to tell gcc about the store. + * + * This however is not needed for sibling atomic64_add() etc since both + * load/store are explicitly done in inline asm. As long as API is used + * for each access, gcc has no way to optimize away any load/store + */ + __asm__ __volatile__( + " std %0, [%1] \n" + : + : "r"(a), "r"(&v->counter) + : "memory"); +} + +#define ATOMIC64_OP(op, op1, op2) \ +static inline void atomic64_##op(long long a, atomic64_t *v) \ +{ \ + unsigned long long val; \ + \ + __asm__ __volatile__( \ + "1: \n" \ + " llockd %0, [%1] \n" \ + " " #op1 " %L0, %L0, %L2 \n" \ + " " #op2 " %H0, %H0, %H2 \n" \ + " scondd %0, [%1] \n" \ + " bnz 1b \n" \ + : "=&r"(val) \ + : "r"(&v->counter), "ir"(a) \ + : "cc"); \ +} \ + +#define ATOMIC64_OP_RETURN(op, op1, op2) \ +static inline long long atomic64_##op##_return(long long a, atomic64_t *v) \ +{ \ + unsigned long long val; \ + \ + smp_mb(); \ + \ + __asm__ __volatile__( \ + "1: \n" \ + " llockd %0, [%1] \n" \ + " " #op1 " %L0, %L0, %L2 \n" \ + " " #op2 " %H0, %H0, %H2 \n" \ + " scondd %0, [%1] \n" \ + " bnz 1b \n" \ + : [val] "=&r"(val) \ + : "r"(&v->counter), "ir"(a) \ + : "cc"); /* memory clobber comes from smp_mb() */ \ + \ + smp_mb(); \ + \ + return val; \ +} + +#define ATOMIC64_FETCH_OP(op, op1, op2) \ +static inline long long atomic64_fetch_##op(long long a, atomic64_t *v) \ +{ \ + unsigned long long val, orig; \ + \ + smp_mb(); \ + \ + __asm__ __volatile__( \ + "1: \n" \ + " llockd %0, [%2] \n" \ + " " #op1 " %L1, %L0, %L3 \n" \ + " " #op2 " %H1, %H0, %H3 \n" \ + " scondd %1, [%2] \n" \ + " bnz 1b \n" \ + : "=&r"(orig), "=&r"(val) \ + : "r"(&v->counter), "ir"(a) \ + : "cc"); /* memory clobber comes from smp_mb() */ \ + \ + smp_mb(); \ + \ + return orig; \ +} + +#define ATOMIC64_OPS(op, op1, op2) \ + ATOMIC64_OP(op, op1, op2) \ + ATOMIC64_OP_RETURN(op, op1, op2) \ + ATOMIC64_FETCH_OP(op, op1, op2) + +#define atomic64_andnot atomic64_andnot + +ATOMIC64_OPS(add, add.f, adc) +ATOMIC64_OPS(sub, sub.f, sbc) +ATOMIC64_OPS(and, and, and) +ATOMIC64_OPS(andnot, bic, bic) +ATOMIC64_OPS(or, or, or) +ATOMIC64_OPS(xor, xor, xor) + +#undef ATOMIC64_OPS +#undef ATOMIC64_FETCH_OP +#undef ATOMIC64_OP_RETURN +#undef ATOMIC64_OP + +static inline long long +atomic64_cmpxchg(atomic64_t *ptr, long long expected, long long new) +{ + long long prev; + + smp_mb(); + + __asm__ __volatile__( + "1: llockd %0, [%1] \n" + " brne %L0, %L2, 2f \n" + " brne %H0, %H2, 2f \n" + " scondd %3, [%1] \n" + " bnz 1b \n" + "2: \n" + : "=&r"(prev) + : "r"(ptr), "ir"(expected), "r"(new) + : "cc"); /* memory clobber comes from smp_mb() */ + + smp_mb(); + + return prev; +} + +static inline long long atomic64_xchg(atomic64_t *ptr, long long new) +{ + long long prev; + + smp_mb(); + + __asm__ __volatile__( + "1: llockd %0, [%1] \n" + " scondd %2, [%1] \n" + " bnz 1b \n" + "2: \n" + : "=&r"(prev) + : "r"(ptr), "r"(new) + : "cc"); /* memory clobber comes from smp_mb() */ + + smp_mb(); + + return prev; +} + +/** + * atomic64_dec_if_positive - decrement by 1 if old value positive + * @v: pointer of type atomic64_t + * + * The function returns the old value of *v minus 1, even if + * the atomic variable, v, was not decremented. + */ + +static inline long long atomic64_dec_if_positive(atomic64_t *v) +{ + long long val; + + smp_mb(); + + __asm__ __volatile__( + "1: llockd %0, [%1] \n" + " sub.f %L0, %L0, 1 # w0 - 1, set C on borrow\n" + " sub.c %H0, %H0, 1 # if C set, w1 - 1\n" + " brlt %H0, 0, 2f \n" + " scondd %0, [%1] \n" + " bnz 1b \n" + "2: \n" + : "=&r"(val) + : "r"(&v->counter) + : "cc"); /* memory clobber comes from smp_mb() */ + + smp_mb(); + + return val; +} + +/** + * atomic64_add_unless - add unless the number is a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * if (v != u) { v += a; ret = 1} else {ret = 0} + * Returns 1 iff @v was not @u (i.e. if add actually happened) + */ +static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) +{ + long long val; + int op_done; + + smp_mb(); + + __asm__ __volatile__( + "1: llockd %0, [%2] \n" + " mov %1, 1 \n" + " brne %L0, %L4, 2f # continue to add since v != u \n" + " breq.d %H0, %H4, 3f # return since v == u \n" + " mov %1, 0 \n" + "2: \n" + " add.f %L0, %L0, %L3 \n" + " adc %H0, %H0, %H3 \n" + " scondd %0, [%2] \n" + " bnz 1b \n" + "3: \n" + : "=&r"(val), "=&r" (op_done) + : "r"(&v->counter), "r"(a), "r"(u) + : "cc"); /* memory clobber comes from smp_mb() */ + + smp_mb(); + + return op_done; +} + +#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) +#define atomic64_inc(v) atomic64_add(1LL, (v)) +#define atomic64_inc_return(v) atomic64_add_return(1LL, (v)) +#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) +#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) +#define atomic64_dec(v) atomic64_sub(1LL, (v)) +#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) +#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) +#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) + +#endif /* !CONFIG_GENERIC_ATOMIC64 */ + +#endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index 23706c635c30..fb781e34f322 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -54,7 +54,7 @@ extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len); extern void read_decode_cache_bcr(void); extern int ioc_exists; -extern unsigned long perip_base; +extern unsigned long perip_base, perip_end; #endif /* !__ASSEMBLY__ */ diff --git a/arch/arc/include/asm/dwarf.h b/arch/arc/include/asm/dwarf.h new file mode 100644 index 000000000000..bb7bdbc59a44 --- /dev/null +++ b/arch/arc/include/asm/dwarf.h @@ -0,0 +1,38 @@ +/* + * Copyright (C) 2016-17 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _ASM_ARC_DWARF_H +#define _ASM_ARC_DWARF_H + +#ifdef __ASSEMBLY__ + +#ifdef ARC_DW2_UNWIND_AS_CFI + +#define CFI_STARTPROC .cfi_startproc +#define CFI_ENDPROC .cfi_endproc +#define CFI_DEF_CFA .cfi_def_cfa +#define CFI_REGISTER .cfi_register +#define CFI_REL_OFFSET .cfi_rel_offset +#define CFI_UNDEFINED .cfi_undefined + +#else + +#define CFI_IGNORE # + +#define CFI_STARTPROC CFI_IGNORE +#define CFI_ENDPROC CFI_IGNORE +#define CFI_DEF_CFA CFI_IGNORE +#define CFI_REGISTER CFI_IGNORE +#define CFI_REL_OFFSET CFI_IGNORE +#define CFI_UNDEFINED CFI_IGNORE + +#endif /* !ARC_DW2_UNWIND_AS_CFI */ + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_ARC_DWARF_H */ diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h index 51a99e25fe33..7096f97a1434 100644 --- a/arch/arc/include/asm/elf.h +++ b/arch/arc/include/asm/elf.h @@ -23,8 +23,7 @@ /* ARC Relocations (kernel Modules only) */ #define R_ARC_32 0x4 #define R_ARC_32_ME 0x1B -#define R_ARC_S25H_PCREL 0x10 -#define R_ARC_S25W_PCREL 0x11 +#define R_ARC_32_PCREL 0x31 /*to set parameters in the core dumps */ #define ELF_ARCH EM_ARCOMPACT diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h index d1ec7f6b31e0..e880dfa3fcd3 100644 --- a/arch/arc/include/asm/irqflags-arcv2.h +++ b/arch/arc/include/asm/irqflags-arcv2.h @@ -112,7 +112,7 @@ static inline long arch_local_save_flags(void) */ temp = (1 << 5) | ((!!(temp & STATUS_IE_MASK)) << CLRI_STATUS_IE_BIT) | - (temp & CLRI_STATUS_E_MASK); + ((temp >> 1) & CLRI_STATUS_E_MASK); return temp; } diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h index 5faad17118b4..b29f1a9fd6f7 100644 --- a/arch/arc/include/asm/linkage.h +++ b/arch/arc/include/asm/linkage.h @@ -9,6 +9,8 @@ #ifndef __ASM_LINKAGE_H #define __ASM_LINKAGE_H +#include <asm/dwarf.h> + #ifdef __ASSEMBLY__ #define ASM_NL ` /* use '`' to mark new line in macro */ @@ -32,6 +34,16 @@ #endif .endm +#define ENTRY_CFI(name) \ + .globl name ASM_NL \ + ALIGN ASM_NL \ + name: ASM_NL \ + CFI_STARTPROC ASM_NL + +#define END_CFI(name) \ + CFI_ENDPROC ASM_NL \ + .size name, .-name + #else /* !__ASSEMBLY__ */ #ifdef CONFIG_ARC_HAS_ICCM diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h index 5f071762fb1c..9185541035cc 100644 --- a/arch/arc/include/asm/perf_event.h +++ b/arch/arc/include/asm/perf_event.h @@ -118,6 +118,9 @@ static const char * const arc_pmu_ev_hw_map[] = { [PERF_COUNT_ARC_ICM] = "icm", /* I-cache Miss */ [PERF_COUNT_ARC_EDTLB] = "edtlb", /* D-TLB Miss */ [PERF_COUNT_ARC_EITLB] = "eitlb", /* I-TLB Miss */ + + [PERF_COUNT_HW_CACHE_REFERENCES] = "imemrdc", /* Instr: mem read cached */ + [PERF_COUNT_HW_CACHE_MISSES] = "dclm", /* D-cache Load Miss */ }; #define C(_x) PERF_COUNT_HW_CACHE_##_x diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h index a78d5670884f..41faf17cd28d 100644 --- a/arch/arc/include/asm/uaccess.h +++ b/arch/arc/include/asm/uaccess.h @@ -83,7 +83,10 @@ "2: ;nop\n" \ " .section .fixup, \"ax\"\n" \ " .align 4\n" \ - "3: mov %0, %3\n" \ + "3: # return -EFAULT\n" \ + " mov %0, %3\n" \ + " # zero out dst ptr\n" \ + " mov %1, 0\n" \ " j 2b\n" \ " .previous\n" \ " .section __ex_table, \"a\"\n" \ @@ -101,7 +104,11 @@ "2: ;nop\n" \ " .section .fixup, \"ax\"\n" \ " .align 4\n" \ - "3: mov %0, %3\n" \ + "3: # return -EFAULT\n" \ + " mov %0, %3\n" \ + " # zero out dst ptr\n" \ + " mov %1, 0\n" \ + " mov %R1, 0\n" \ " j 2b\n" \ " .previous\n" \ " .section __ex_table, \"a\"\n" \ diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S index e6890b1f8650..7c1f365ef3d2 100644 --- a/arch/arc/kernel/ctx_sw_asm.S +++ b/arch/arc/kernel/ctx_sw_asm.S @@ -23,6 +23,7 @@ .global __switch_to .type __switch_to, @function __switch_to: + CFI_STARTPROC /* Save regs on kernel mode stack of task */ st.a blink, [sp, -4] @@ -59,4 +60,4 @@ __switch_to: ld.ab blink, [sp, 4] j [blink] -END(__switch_to) +END_CFI(__switch_to) diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 2efb0625331d..1eea99beecc3 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -35,7 +35,7 @@ ENTRY(sys_clone_wrapper) btst r10, TIF_SYSCALL_TRACE bnz tracesys_exit - b ret_from_system_call + b .Lret_from_system_call END(sys_clone_wrapper) ENTRY(ret_from_fork) @@ -61,18 +61,6 @@ ENTRY(ret_from_fork) b ret_from_exception END(ret_from_fork) -#ifdef CONFIG_ARC_DW2_UNWIND -; Workaround for bug 94179 (STAR ): -; Despite -fasynchronous-unwind-tables, linker is not making dwarf2 unwinder -; section (.debug_frame) as loadable. So we force it here. -; This also fixes STAR 9000487933 where the prev-workaround (objcopy --setflag) -; would not work after a clean build due to kernel build system dependencies. -.section .debug_frame, "wa",@progbits - -; Reset to .text as this file is included in entry-<isa>.S -.section .text, "ax",@progbits -#endif - ;################### Non TLB Exception Handling ############################# ; --------------------------------------------- @@ -260,20 +248,18 @@ ENTRY(EV_Trap) ; syscall num shd not exceed the total system calls avail cmp r8, NR_syscalls mov.hi r0, -ENOSYS - bhi ret_from_system_call + bhi .Lret_from_system_call ; Offset into the syscall_table and call handler ld.as r9,[sys_call_table, r8] jl [r9] ; Entry into Sys Call Handler - ; fall through to ret_from_system_call -END(EV_Trap) - -ENTRY(ret_from_system_call) +.Lret_from_system_call: st r0, [sp, PT_r0] ; sys call return value in pt_regs - ; fall through yet again to ret_from_exception + ; fall through to ret_from_exception +END(EV_Trap) ;############# Return from Intr/Excp/Trap (Linux Specifics) ############## ; diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c index 6c24faf48b16..62b59409a5d9 100644 --- a/arch/arc/kernel/intc-arcv2.c +++ b/arch/arc/kernel/intc-arcv2.c @@ -74,7 +74,7 @@ void arc_init_IRQ(void) tmp = read_aux_reg(0xa); tmp |= STATUS_AD_MASK | (irq_prio << 1); tmp &= ~STATUS_IE_MASK; - asm volatile("flag %0 \n"::"r"(tmp)); + asm volatile("kflag %0 \n"::"r"(tmp)); } static void arcv2_irq_mask(struct irq_data *data) diff --git a/arch/arc/kernel/module.c b/arch/arc/kernel/module.c index 376e04622962..9a2849756022 100644 --- a/arch/arc/kernel/module.c +++ b/arch/arc/kernel/module.c @@ -22,13 +22,9 @@ static inline void arc_write_me(unsigned short *addr, unsigned long value) *(addr + 1) = (value & 0xffff); } -/* ARC specific section quirks - before relocation loop in generic loader - * - * For dwarf unwinding out of modules, this needs to - * 1. Ensure the .debug_frame is allocatable (ARC Linker bug: despite - * -fasynchronous-unwind-tables it doesn't). - * 2. Since we are iterating thru sec hdr tbl anyways, make a note of - * the exact section index, for later use. +/* + * This gets called before relocation loop in generic loader + * Make a note of the section index of unwinding section */ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, char *secstr, struct module *mod) @@ -40,8 +36,7 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, mod->arch.unw_info = NULL; for (i = 1; i < hdr->e_shnum; i++) { - if (strcmp(secstr+sechdrs[i].sh_name, ".debug_frame") == 0) { - sechdrs[i].sh_flags |= SHF_ALLOC; + if (strcmp(secstr+sechdrs[i].sh_name, ".eh_frame") == 0) { mod->arch.unw_sec_idx = i; break; } @@ -106,10 +101,12 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, */ relo_type = ELF32_R_TYPE(rel_entry[i].r_info); - if (likely(R_ARC_32_ME == relo_type)) + if (likely(R_ARC_32_ME == relo_type)) /* ME ( S + A ) */ arc_write_me((unsigned short *)location, relocation); - else if (R_ARC_32 == relo_type) + else if (R_ARC_32 == relo_type) /* ( S + A ) */ *((Elf32_Addr *) location) = relocation; + else if (R_ARC_32_PCREL == relo_type) /* ( S + A ) - PDATA ) */ + *((Elf32_Addr *) location) = relocation - location; else goto relo_err; diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 08f03d9b5b3e..2ce24e74f879 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -179,8 +179,8 @@ static int arc_pmu_event_init(struct perf_event *event) if (arc_pmu->ev_hw_idx[event->attr.config] < 0) return -ENOENT; hwc->config |= arc_pmu->ev_hw_idx[event->attr.config]; - pr_debug("init event %d with h/w %d \'%s\'\n", - (int) event->attr.config, (int) hwc->config, + pr_debug("init event %d with h/w %08x \'%s\'\n", + (int)event->attr.config, (int)hwc->config, arc_pmu_ev_hw_map[event->attr.config]); return 0; @@ -189,6 +189,8 @@ static int arc_pmu_event_init(struct perf_event *event) if (ret < 0) return ret; hwc->config |= arc_pmu->ev_hw_idx[ret]; + pr_debug("init cache event with h/w %08x \'%s\'\n", + (int)hwc->config, arc_pmu_ev_hw_map[ret]); return 0; default: return -ENOENT; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index f52a0d0dc462..3df7f9c72f42 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -171,6 +171,7 @@ static const struct cpuinfo_data arc_cpu_tbl[] = { #else { {0x50, "ARC HS38 R2.0"}, 0x51}, { {0x52, "ARC HS38 R2.1"}, 0x52}, + { {0x53, "ARC HS38 R3.0"}, 0x53}, #endif { {0x00, NULL } } }; @@ -272,8 +273,8 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) FIX_PTR(cpu); n += scnprintf(buf + n, len - n, - "Vector Table\t: %#x\nUncached Base\t: %#lx\n", - cpu->vec_base, perip_base); + "Vector Table\t: %#x\nPeripherals\t: %#lx:%#lx\n", + cpu->vec_base, perip_base, perip_end); if (cpu->extn.fpu_sp || cpu->extn.fpu_dp) n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n", diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 0587bf121d11..61fd1ce63c56 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -111,6 +111,8 @@ UNW_REGISTER_INFO}; #define DW_EH_PE_indirect 0x80 #define DW_EH_PE_omit 0xff +#define CIE_ID 0 + typedef unsigned long uleb128_t; typedef signed long sleb128_t; @@ -232,6 +234,7 @@ void __init arc_unwind_init(void) static const u32 bad_cie, not_fde; static const u32 *cie_for_fde(const u32 *fde, const struct unwind_table *); +static const u32 *__cie_for_fde(const u32 *fde); static signed fde_pointer_type(const u32 *cie); struct eh_frame_hdr_table_entry { @@ -338,10 +341,9 @@ static void init_unwind_hdr(struct unwind_table *table, for (fde = table->address, tableSize = table->size, n = 0; tableSize; tableSize -= sizeof(*fde) + *fde, fde += 1 + *fde / sizeof(*fde)) { - /* const u32 *cie = fde + 1 - fde[1] / sizeof(*fde); */ - const u32 *cie = (const u32 *)(fde[1]); + const u32 *cie = __cie_for_fde(fde); - if (fde[1] == 0xffffffff) + if (fde[1] == CIE_ID) continue; /* this is a CIE */ ptr = (const u8 *)(fde + 2); header->table[n].start = read_pointer(&ptr, @@ -504,6 +506,15 @@ static sleb128_t get_sleb128(const u8 **pcur, const u8 *end) return value; } +static const u32 *__cie_for_fde(const u32 *fde) +{ + const u32 *cie; + + cie = fde + 1 - fde[1] / sizeof(*fde); + + return cie; +} + static const u32 *cie_for_fde(const u32 *fde, const struct unwind_table *table) { const u32 *cie; @@ -511,19 +522,18 @@ static const u32 *cie_for_fde(const u32 *fde, const struct unwind_table *table) if (!*fde || (*fde & (sizeof(*fde) - 1))) return &bad_cie; - if (fde[1] == 0xffffffff) + if (fde[1] == CIE_ID) return ¬_fde; /* this is a CIE */ if ((fde[1] & (sizeof(*fde) - 1))) /* || fde[1] > (unsigned long)(fde + 1) - (unsigned long)table->address) */ return NULL; /* this is not a valid FDE */ - /* cie = fde + 1 - fde[1] / sizeof(*fde); */ - cie = (u32 *) fde[1]; + cie = __cie_for_fde(fde); if (*cie <= sizeof(*cie) + 4 || *cie >= fde[1] - sizeof(*fde) || (*cie & (sizeof(*cie) - 1)) - || (cie[1] != 0xffffffff)) + || (cie[1] != CIE_ID)) return NULL; /* this is not a (valid) CIE */ return cie; } diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index 894e696bddaa..36611072305f 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -82,14 +82,6 @@ SECTIONS PERCPU_SECTION(L1_CACHE_BYTES) - /* - * .exit.text is discard at runtime, not link time, to deal with - * references from .debug_frame - * It will be init freed, being inside [__init_start : __init_end] - */ - .exit.text : { EXIT_TEXT } - .exit.data : { EXIT_DATA } - . = ALIGN(PAGE_SIZE); __init_end = .; @@ -120,18 +112,13 @@ SECTIONS #ifdef CONFIG_ARC_DW2_UNWIND . = ALIGN(PAGE_SIZE); - .debug_frame : { + .eh_frame : { __start_unwind = .; - *(.debug_frame) + *(.eh_frame) __end_unwind = .; } - /* - * gcc 4.8 generates this for -fasynchonous-unwind-tables, - * while we still use the .debug_frame based unwinder - */ - /DISCARD/ : { *(.eh_frame) } #else - /DISCARD/ : { *(.debug_frame) } + /DISCARD/ : { *(.eh_frame) } #endif NOTES @@ -148,7 +135,7 @@ SECTIONS } #ifndef CONFIG_DEBUG_INFO - /* open-coded because we need .debug_frame seperately for unwinding */ + /DISCARD/ : { *(.debug_frame) } /DISCARD/ : { *(.debug_aranges) } /DISCARD/ : { *(.debug_pubnames) } /DISCARD/ : { *(.debug_info) } diff --git a/arch/arc/lib/memcmp.S b/arch/arc/lib/memcmp.S index a4015e7d9ab7..21a103044b70 100644 --- a/arch/arc/lib/memcmp.S +++ b/arch/arc/lib/memcmp.S @@ -16,7 +16,7 @@ #define SHIFT r2 #endif -ENTRY(memcmp) +ENTRY_CFI(memcmp) or r12,r0,r1 asl_s r12,r12,30 sub r3,r2,1 @@ -149,4 +149,4 @@ ENTRY(memcmp) .Lnil: j_s.d [blink] mov r0,0 -END(memcmp) +END_CFI(memcmp) diff --git a/arch/arc/lib/memcpy-700.S b/arch/arc/lib/memcpy-700.S index 3222573e50de..ba0beccdaafd 100644 --- a/arch/arc/lib/memcpy-700.S +++ b/arch/arc/lib/memcpy-700.S @@ -8,7 +8,7 @@ #include <linux/linkage.h> -ENTRY(memcpy) +ENTRY_CFI(memcpy) or r3,r0,r1 asl_s r3,r3,30 mov_s r5,r0 @@ -63,4 +63,4 @@ ENTRY(memcpy) .Lendbloop: j_s.d [blink] stb r12,[r5,0] -END(memcpy) +END_CFI(memcpy) diff --git a/arch/arc/lib/memcpy-archs.S b/arch/arc/lib/memcpy-archs.S index f96c75edf30a..d61044dd8b58 100644 --- a/arch/arc/lib/memcpy-archs.S +++ b/arch/arc/lib/memcpy-archs.S @@ -40,7 +40,7 @@ # define ZOLAND 0xF #endif -ENTRY(memcpy) +ENTRY_CFI(memcpy) prefetch [r1] ; Prefetch the read location prefetchw [r0] ; Prefetch the write location mov.f 0, r2 @@ -233,4 +233,4 @@ ENTRY(memcpy) .Lcopybytewise_3: j [blink] -END(memcpy) +END_CFI(memcpy) diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S index 365b18364815..62ad4bcb841a 100644 --- a/arch/arc/lib/memset-archs.S +++ b/arch/arc/lib/memset-archs.S @@ -10,7 +10,7 @@ #undef PREALLOC_NOT_AVAIL -ENTRY(memset) +ENTRY_CFI(memset) prefetchw [r0] ; Prefetch the write location mov.f 0, r2 ;;; if size is zero @@ -112,11 +112,11 @@ ENTRY(memset) j [blink] -END(memset) +END_CFI(memset) -ENTRY(memzero) +ENTRY_CFI(memzero) ; adjust bzero args to memset args mov r2, r1 b.d memset ;tail call so need to tinker with blink mov r1, 0 -END(memzero) +END_CFI(memzero) diff --git a/arch/arc/lib/memset.S b/arch/arc/lib/memset.S index d36bd43fc98d..cf736f9aa403 100644 --- a/arch/arc/lib/memset.S +++ b/arch/arc/lib/memset.S @@ -10,7 +10,7 @@ #define SMALL 7 /* Must be at least 6 to deal with alignment/loop issues. */ -ENTRY(memset) +ENTRY_CFI(memset) mov_s r4,r0 or r12,r0,r2 bmsk.f r12,r12,1 @@ -46,14 +46,14 @@ ENTRY(memset) stb.ab r1,[r4,1] .Ltiny_end: j_s [blink] -END(memset) +END_CFI(memset) ; memzero: @r0 = mem, @r1 = size_t ; memset: @r0 = mem, @r1 = char, @r2 = size_t -ENTRY(memzero) +ENTRY_CFI(memzero) ; adjust bzero args to memset args mov r2, r1 mov r1, 0 b memset ;tail call so need to tinker with blink -END(memzero) +END_CFI(memzero) diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S index b725d5862107..2d300daae2ae 100644 --- a/arch/arc/lib/strchr-700.S +++ b/arch/arc/lib/strchr-700.S @@ -13,7 +13,7 @@ #include <linux/linkage.h> -ENTRY(strchr) +ENTRY_CFI(strchr) extb_s r1,r1 asl r5,r1,8 bmsk r2,r0,1 @@ -130,4 +130,4 @@ ENTRY(strchr) j_s.d [blink] mov.mi r0,0 #endif /* ENDIAN */ -END(strchr) +END_CFI(strchr) diff --git a/arch/arc/lib/strcmp-archs.S b/arch/arc/lib/strcmp-archs.S index 4f338eec3365..fae9e82a09eb 100644 --- a/arch/arc/lib/strcmp-archs.S +++ b/arch/arc/lib/strcmp-archs.S @@ -8,7 +8,7 @@ #include <linux/linkage.h> -ENTRY(strcmp) +ENTRY_CFI(strcmp) or r2, r0, r1 bmsk_s r2, r2, 1 brne r2, 0, @.Lcharloop @@ -75,4 +75,4 @@ ENTRY(strcmp) .Lcmpend: j_s.d [blink] sub r0, r2, r3 -END(strcmp) +END_CFI(strcmp) diff --git a/arch/arc/lib/strcmp.S b/arch/arc/lib/strcmp.S index 3544600fefe6..fb20096e5008 100644 --- a/arch/arc/lib/strcmp.S +++ b/arch/arc/lib/strcmp.S @@ -15,7 +15,7 @@ #include <linux/linkage.h> -ENTRY(strcmp) +ENTRY_CFI(strcmp) or r2,r0,r1 bmsk_s r2,r2,1 brne r2,0,.Lcharloop @@ -93,4 +93,4 @@ ENTRY(strcmp) .Lcmpend: j_s.d [blink] sub r0,r2,r3 -END(strcmp) +END_CFI(strcmp) diff --git a/arch/arc/lib/strcpy-700.S b/arch/arc/lib/strcpy-700.S index 8422f38e1218..6a6c1553807d 100644 --- a/arch/arc/lib/strcpy-700.S +++ b/arch/arc/lib/strcpy-700.S @@ -18,7 +18,7 @@ #include <linux/linkage.h> -ENTRY(strcpy) +ENTRY_CFI(strcpy) or r2,r0,r1 bmsk_s r2,r2,1 brne.d r2,0,charloop @@ -67,4 +67,4 @@ charloop: brne.d r3,0,charloop stb.ab r3,[r10,1] j [blink] -END(strcpy) +END_CFI(strcpy) diff --git a/arch/arc/lib/strlen.S b/arch/arc/lib/strlen.S index 53cfd5685a5f..839b44b8d055 100644 --- a/arch/arc/lib/strlen.S +++ b/arch/arc/lib/strlen.S @@ -8,7 +8,7 @@ #include <linux/linkage.h> -ENTRY(strlen) +ENTRY_CFI(strlen) or r3,r0,7 ld r2,[r3,-7] ld.a r6,[r3,-3] @@ -80,4 +80,4 @@ ENTRY(strlen) .Learly_end: b.d .Lend sub_s.ne r1,r1,r1 -END(strlen) +END_CFI(strlen) diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 0b10efe3a6a7..97dddbefb86a 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -25,6 +25,7 @@ static int l2_line_sz; int ioc_exists; volatile int slc_enable = 1, ioc_enable = 1; unsigned long perip_base = ARC_UNCACHED_ADDR_SPACE; /* legacy value for boot */ +unsigned long perip_end = 0xFFFFFFFF; /* legacy value */ void (*_cache_line_loop_ic_fn)(phys_addr_t paddr, unsigned long vaddr, unsigned long sz, const int cacheop); @@ -76,7 +77,6 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len) static void read_decode_cache_bcr_arcv2(int cpu) { struct cpuinfo_arc_cache *p_slc = &cpuinfo_arc700[cpu].slc; - struct bcr_generic uncached_space; struct bcr_generic sbcr; struct bcr_slc_cfg { @@ -95,6 +95,15 @@ static void read_decode_cache_bcr_arcv2(int cpu) #endif } cbcr; + struct bcr_volatile { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int start:4, limit:4, pad:22, order:1, disable:1; +#else + unsigned int disable:1, order:1, pad:22, limit:4, start:4; +#endif + } vol; + + READ_BCR(ARC_REG_SLC_BCR, sbcr); if (sbcr.ver) { READ_BCR(ARC_REG_SLC_CFG, slc_cfg); @@ -107,10 +116,14 @@ static void read_decode_cache_bcr_arcv2(int cpu) if (cbcr.c && ioc_enable) ioc_exists = 1; - /* Legacy Data Uncached BCR is deprecated from v3 onwards */ - READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space); - if (uncached_space.ver > 2) - perip_base = read_aux_reg(AUX_NON_VOL) & 0xF0000000; + /* HS 2.0 didn't have AUX_VOL */ + if (cpuinfo_arc700[cpu].core.family > 0x51) { + READ_BCR(AUX_VOL, vol); + perip_base = vol.start << 28; + /* HS 3.0 has limit and strict-ordering fields */ + if (cpuinfo_arc700[cpu].core.family > 0x52) + perip_end = (vol.limit << 28) - 1; + } } void read_decode_cache_bcr(void) diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c index f52b7db67fd3..9881bd740ccc 100644 --- a/arch/arc/mm/ioremap.c +++ b/arch/arc/mm/ioremap.c @@ -19,7 +19,7 @@ static inline bool arc_uncached_addr_space(phys_addr_t paddr) if (is_isa_arcompact()) { if (paddr >= ARC_UNCACHED_ADDR_SPACE) return true; - } else if (paddr >= perip_base && paddr <= 0xFFFFFFFF) { + } else if (paddr >= perip_base && paddr <= perip_end) { return true; } diff --git a/arch/arc/plat-sim/platform.c b/arch/arc/plat-sim/platform.c index e4fe51456808..aea87389e44b 100644 --- a/arch/arc/plat-sim/platform.c +++ b/arch/arc/plat-sim/platform.c @@ -24,6 +24,7 @@ static const char *simulation_compat[] __initconst = { "snps,nsim_hs", "snps,nsimosci", "snps,nsimosci_hs", + "snps,zebu_hs", NULL, }; diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index a9c4e48bb7ec..125657b602a4 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1,6 +1,7 @@ config ARM bool default y + select ARCH_CLOCKSOURCE_DATA select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE @@ -278,10 +279,9 @@ config PHYS_OFFSET ARCH_INTEGRATOR || \ ARCH_IOP13XX || \ ARCH_KS8695 || \ - (ARCH_REALVIEW && !REALVIEW_HIGH_PHYS_OFFSET) + ARCH_REALVIEW default 0x10000000 if ARCH_OMAP1 || ARCH_RPC default 0x20000000 if ARCH_S5PV210 - default 0x70000000 if REALVIEW_HIGH_PHYS_OFFSET default 0xc0000000 if ARCH_SA1100 help Please provide the physical address corresponding to the @@ -337,6 +337,7 @@ config ARCH_MULTIPLATFORM select GENERIC_CLOCKEVENTS select MIGHT_HAVE_PCI select MULTI_IRQ_HANDLER + select PCI_DOMAINS if PCI select SPARSE_IRQ select USE_OF @@ -878,6 +879,7 @@ config ARCH_STM32 select CLKSRC_STM32 select PINCTRL select RESET_CONTROLLER + select STM32_EXTI help Support for STMicroelectronics STM32 processors. diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 61f6ccc19cfa..6be9ee148b78 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -23,7 +23,6 @@ ifeq ($(CONFIG_ARM_MODULE_PLTS),y) LDFLAGS_MODULE += -T $(srctree)/arch/arm/kernel/module.lds endif -OBJCOPYFLAGS :=-O binary -R .comment -S GZFLAGS :=-9 #KBUILD_CFLAGS +=-pipe diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile index bdc1d5af03d2..50f8d1be7fcb 100644 --- a/arch/arm/boot/Makefile +++ b/arch/arm/boot/Makefile @@ -11,6 +11,8 @@ # Copyright (C) 1995-2002 Russell King # +OBJCOPYFLAGS :=-O binary -R .comment -S + ifneq ($(MACHINE),) include $(MACHINE)/Makefile.boot endif diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index af11c2f8f3b7..fc6d541549a2 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -779,7 +779,7 @@ __armv7_mmu_cache_on: orrne r0, r0, #1 @ MMU enabled movne r1, #0xfffffffd @ domain 0 = client bic r6, r6, #1 << 31 @ 32-bit translation system - bic r6, r6, #3 << 0 @ use only ttbr0 + bic r6, r6, #(7 << 0) | (1 << 4) @ use only ttbr0 mcrne p15, 0, r3, c2, c0, 0 @ load page table pointer mcrne p15, 0, r1, c3, c0, 0 @ load domain access control mcrne p15, 0, r6, c2, c0, 2 @ load ttb control diff --git a/arch/arm/boot/dts/am335x-baltos.dtsi b/arch/arm/boot/dts/am335x-baltos.dtsi index c8609d8d2c55..b689172632ef 100644 --- a/arch/arm/boot/dts/am335x-baltos.dtsi +++ b/arch/arm/boot/dts/am335x-baltos.dtsi @@ -226,7 +226,7 @@ #address-cells = <1>; #size-cells = <1>; - elm_id = <&elm>; + ti,elm-id = <&elm>; }; }; diff --git a/arch/arm/boot/dts/am335x-igep0033.dtsi b/arch/arm/boot/dts/am335x-igep0033.dtsi index df63484ef9b3..e7d9ca1305fa 100644 --- a/arch/arm/boot/dts/am335x-igep0033.dtsi +++ b/arch/arm/boot/dts/am335x-igep0033.dtsi @@ -161,7 +161,7 @@ #address-cells = <1>; #size-cells = <1>; - elm_id = <&elm>; + ti,elm-id = <&elm>; /* MTD partition table */ partition@0 { diff --git a/arch/arm/boot/dts/am335x-phycore-som.dtsi b/arch/arm/boot/dts/am335x-phycore-som.dtsi index 86f773165d5c..1263c9d4cba3 100644 --- a/arch/arm/boot/dts/am335x-phycore-som.dtsi +++ b/arch/arm/boot/dts/am335x-phycore-som.dtsi @@ -197,7 +197,7 @@ gpmc,wr-access-ns = <30>; gpmc,wr-data-mux-bus-ns = <0>; - elm_id = <&elm>; + ti,elm-id = <&elm>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/armada-388-clearfog.dts b/arch/arm/boot/dts/armada-388-clearfog.dts index 2e0556af6e5e..d3e6bd805006 100644 --- a/arch/arm/boot/dts/armada-388-clearfog.dts +++ b/arch/arm/boot/dts/armada-388-clearfog.dts @@ -390,12 +390,12 @@ port@0 { reg = <0>; - label = "lan1"; + label = "lan5"; }; port@1 { reg = <1>; - label = "lan2"; + label = "lan4"; }; port@2 { @@ -405,12 +405,12 @@ port@3 { reg = <3>; - label = "lan4"; + label = "lan2"; }; port@4 { reg = <4>; - label = "lan5"; + label = "lan1"; }; port@5 { diff --git a/arch/arm/boot/dts/bcm2835-rpi.dtsi b/arch/arm/boot/dts/bcm2835-rpi.dtsi index caf2707680c1..e9b47b2bbc33 100644 --- a/arch/arm/boot/dts/bcm2835-rpi.dtsi +++ b/arch/arm/boot/dts/bcm2835-rpi.dtsi @@ -2,6 +2,7 @@ / { memory { + device_type = "memory"; reg = <0 0x10000000>; }; diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi index b98252232d20..445624a1a1de 100644 --- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -2,7 +2,6 @@ #include <dt-bindings/clock/bcm2835.h> #include <dt-bindings/clock/bcm2835-aux.h> #include <dt-bindings/gpio/gpio.h> -#include "skeleton.dtsi" /* This include file covers the common peripherals and configuration between * bcm2835 and bcm2836 implementations, leaving the CPU configuration to @@ -13,6 +12,8 @@ compatible = "brcm,bcm2835"; model = "BCM2835"; interrupt-parent = <&intc>; + #address-cells = <1>; + #size-cells = <1>; chosen { bootargs = "earlyprintk console=ttyAMA0"; diff --git a/arch/arm/boot/dts/exynos5410-odroidxu.dts b/arch/arm/boot/dts/exynos5410-odroidxu.dts index d9499310a301..f6d135245a4b 100644 --- a/arch/arm/boot/dts/exynos5410-odroidxu.dts +++ b/arch/arm/boot/dts/exynos5410-odroidxu.dts @@ -447,14 +447,11 @@ samsung,dw-mshc-ciu-div = <3>; samsung,dw-mshc-sdr-timing = <0 4>; samsung,dw-mshc-ddr-timing = <0 2>; - samsung,dw-mshc-hs400-timing = <0 2>; - samsung,read-strobe-delay = <90>; pinctrl-names = "default"; pinctrl-0 = <&sd0_clk &sd0_cmd &sd0_bus1 &sd0_bus4 &sd0_bus8 &sd0_cd>; bus-width = <8>; cap-mmc-highspeed; mmc-hs200-1_8v; - mmc-hs400-1_8v; vmmc-supply = <&ldo20_reg>; vqmmc-supply = <&ldo11_reg>; }; diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index b620ac884cfd..b13b0b2db881 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -243,7 +243,7 @@ clocks = <&clks IMX6QDL_CLK_SPDIF_GCLK>, <&clks IMX6QDL_CLK_OSC>, <&clks IMX6QDL_CLK_SPDIF>, <&clks IMX6QDL_CLK_ASRC>, <&clks IMX6QDL_CLK_DUMMY>, <&clks IMX6QDL_CLK_ESAI_EXTAL>, - <&clks IMX6QDL_CLK_IPG>, <&clks IMX6QDL_CLK_MLB>, + <&clks IMX6QDL_CLK_IPG>, <&clks IMX6QDL_CLK_DUMMY>, <&clks IMX6QDL_CLK_DUMMY>, <&clks IMX6QDL_CLK_SPBA>; clock-names = "core", "rxtx0", "rxtx1", "rxtx2", diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts index 96ea936eeeb0..240a2864d044 100644 --- a/arch/arm/boot/dts/imx6sx-sabreauto.dts +++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts @@ -64,7 +64,7 @@ cd-gpios = <&gpio7 11 GPIO_ACTIVE_LOW>; no-1-8-v; keep-power-in-suspend; - enable-sdio-wakup; + wakeup-source; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts index 95ee268ed510..2f33c463cbce 100644 --- a/arch/arm/boot/dts/imx7d-sdb.dts +++ b/arch/arm/boot/dts/imx7d-sdb.dts @@ -131,7 +131,7 @@ ti,y-min = /bits/ 16 <0>; ti,y-max = /bits/ 16 <0>; ti,pressure-max = /bits/ 16 <0>; - ti,x-plat-ohms = /bits/ 16 <400>; + ti,x-plate-ohms = /bits/ 16 <400>; wakeup-source; }; }; diff --git a/arch/arm/boot/dts/kirkwood-ib62x0.dts b/arch/arm/boot/dts/kirkwood-ib62x0.dts index ef84d8699a76..5bf62897014c 100644 --- a/arch/arm/boot/dts/kirkwood-ib62x0.dts +++ b/arch/arm/boot/dts/kirkwood-ib62x0.dts @@ -113,7 +113,7 @@ partition@e0000 { label = "u-boot environment"; - reg = <0xe0000 0x100000>; + reg = <0xe0000 0x20000>; }; partition@100000 { diff --git a/arch/arm/boot/dts/kirkwood-openrd.dtsi b/arch/arm/boot/dts/kirkwood-openrd.dtsi index e4ecab112601..7175511a92da 100644 --- a/arch/arm/boot/dts/kirkwood-openrd.dtsi +++ b/arch/arm/boot/dts/kirkwood-openrd.dtsi @@ -116,6 +116,10 @@ }; }; +&pciec { + status = "okay"; +}; + &pcie0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index 365f39ff58bb..0ff1c2de95bf 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -35,10 +35,15 @@ ranges = <0 0 0x00000000 0x1000000>; /* CS0: 16MB for NAND */ nand@0,0 { - linux,mtd-name = "micron,mt29f4g16abbda3w"; + compatible = "ti,omap2-nand"; reg = <0 0 4>; /* CS0, offset 0, IO size 4 */ + interrupt-parent = <&gpmc>; + interrupts = <0 IRQ_TYPE_NONE>, /* fifoevent */ + <1 IRQ_TYPE_NONE>; /* termcount */ + linux,mtd-name = "micron,mt29f4g16abbda3w"; nand-bus-width = <16>; ti,nand-ecc-opt = "bch8"; + rb-gpios = <&gpmc 0 GPIO_ACTIVE_HIGH>; /* gpmc_wait0 */ gpmc,sync-clk-ps = <0>; gpmc,cs-on-ns = <0>; gpmc,cs-rd-off-ns = <44>; @@ -54,10 +59,6 @@ gpmc,wr-access-ns = <40>; gpmc,wr-data-mux-bus-ns = <0>; gpmc,device-width = <2>; - - gpmc,page-burst-access-ns = <5>; - gpmc,cycle2cycle-delay-ns = <50>; - #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index 5e9a13c0eaf7..1c2c74655416 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -46,6 +46,7 @@ linux,mtd-name = "micron,mt29f4g16abbda3w"; nand-bus-width = <16>; ti,nand-ecc-opt = "bch8"; + rb-gpios = <&gpmc 0 GPIO_ACTIVE_HIGH>; /* gpmc_wait0 */ gpmc,sync-clk-ps = <0>; gpmc,cs-on-ns = <0>; gpmc,cs-rd-off-ns = <44>; diff --git a/arch/arm/boot/dts/omap3-overo-base.dtsi b/arch/arm/boot/dts/omap3-overo-base.dtsi index de256fa8da48..3e946cac55f3 100644 --- a/arch/arm/boot/dts/omap3-overo-base.dtsi +++ b/arch/arm/boot/dts/omap3-overo-base.dtsi @@ -223,7 +223,9 @@ }; &gpmc { - ranges = <0 0 0x00000000 0x20000000>; + ranges = <0 0 0x30000000 0x1000000>, /* CS0 */ + <4 0 0x2b000000 0x1000000>, /* CS4 */ + <5 0 0x2c000000 0x1000000>; /* CS5 */ nand@0,0 { compatible = "ti,omap2-nand"; diff --git a/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi b/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi index 7df27926ead2..4f4c6efbd518 100644 --- a/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi +++ b/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi @@ -55,8 +55,6 @@ #include "omap-gpmc-smsc9221.dtsi" &gpmc { - ranges = <5 0 0x2c000000 0x1000000>; /* CS5 */ - ethernet@gpmc { reg = <5 0 0xff>; interrupt-parent = <&gpio6>; diff --git a/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi index 9e24b6a1d07b..1b304e2f1bd2 100644 --- a/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi +++ b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi @@ -27,8 +27,6 @@ #include "omap-gpmc-smsc9221.dtsi" &gpmc { - ranges = <5 0 0x2c000000 0x1000000>; /* CS5 */ - ethernet@gpmc { reg = <5 0 0xff>; interrupt-parent = <&gpio6>; diff --git a/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi b/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi index 334109e14613..82e98ee3023a 100644 --- a/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi +++ b/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi @@ -15,9 +15,6 @@ #include "omap-gpmc-smsc9221.dtsi" &gpmc { - ranges = <4 0 0x2b000000 0x1000000>, /* CS4 */ - <5 0 0x2c000000 0x1000000>; /* CS5 */ - smsc1: ethernet@gpmc { reg = <5 0 0xff>; interrupt-parent = <&gpio6>; diff --git a/arch/arm/boot/dts/rk3066a.dtsi b/arch/arm/boot/dts/rk3066a.dtsi index c0ba86c3a2ab..0d0dae3a1694 100644 --- a/arch/arm/boot/dts/rk3066a.dtsi +++ b/arch/arm/boot/dts/rk3066a.dtsi @@ -197,6 +197,8 @@ clock-names = "saradc", "apb_pclk"; interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>; #io-channel-cells = <1>; + resets = <&cru SRST_SARADC>; + reset-names = "saradc-apb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index cd33f0170890..91c4b3c7a8d5 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -279,6 +279,8 @@ #io-channel-cells = <1>; clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>; clock-names = "saradc", "apb_pclk"; + resets = <&cru SRST_SARADC>; + reset-names = "saradc-apb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/rk3xxx.dtsi b/arch/arm/boot/dts/rk3xxx.dtsi index 99bbcc2c9b89..e2cd683b4e4b 100644 --- a/arch/arm/boot/dts/rk3xxx.dtsi +++ b/arch/arm/boot/dts/rk3xxx.dtsi @@ -399,6 +399,8 @@ #io-channel-cells = <1>; clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>; clock-names = "saradc", "apb_pclk"; + resets = <&cru SRST_SARADC>; + reset-names = "saradc-apb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi index 94000cbe576b..f520cbff5e1c 100644 --- a/arch/arm/boot/dts/socfpga_arria10.dtsi +++ b/arch/arm/boot/dts/socfpga_arria10.dtsi @@ -639,6 +639,22 @@ interrupts = <5 IRQ_TYPE_LEVEL_HIGH>, <37 IRQ_TYPE_LEVEL_HIGH>; }; + + dma-ecc@ff8c8000 { + compatible = "altr,socfpga-dma-ecc"; + reg = <0xff8c8000 0x400>; + altr,ecc-parent = <&pdma>; + interrupts = <10 IRQ_TYPE_LEVEL_HIGH>, + <42 IRQ_TYPE_LEVEL_HIGH>; + }; + + usb0-ecc@ff8c8800 { + compatible = "altr,socfpga-usb-ecc"; + reg = <0xff8c8800 0x400>; + altr,ecc-parent = <&usb0>; + interrupts = <2 IRQ_TYPE_LEVEL_HIGH>, + <34 IRQ_TYPE_LEVEL_HIGH>; + }; }; rst: rstmgr@ffd05000 { diff --git a/arch/arm/boot/dts/socfpga_arria10_socdk_sdmmc.dts b/arch/arm/boot/dts/socfpga_arria10_socdk_sdmmc.dts index 8a7dfa473e98..040a164ba148 100644 --- a/arch/arm/boot/dts/socfpga_arria10_socdk_sdmmc.dts +++ b/arch/arm/boot/dts/socfpga_arria10_socdk_sdmmc.dts @@ -25,3 +25,15 @@ broken-cd; bus-width = <4>; }; + +&eccmgr { + sdmmca-ecc@ff8c2c00 { + compatible = "altr,socfpga-sdmmc-ecc"; + reg = <0xff8c2c00 0x400>; + altr,ecc-parent = <&mmc>; + interrupts = <15 IRQ_TYPE_LEVEL_HIGH>, + <47 IRQ_TYPE_LEVEL_HIGH>, + <16 IRQ_TYPE_LEVEL_HIGH>, + <48 IRQ_TYPE_LEVEL_HIGH>; + }; +}; diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi index d294e82447a2..8b063ab10c19 100644 --- a/arch/arm/boot/dts/stih407-family.dtsi +++ b/arch/arm/boot/dts/stih407-family.dtsi @@ -550,8 +550,9 @@ interrupt-names = "mmcirq"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_mmc0>; - clock-names = "mmc"; - clocks = <&clk_s_c0_flexgen CLK_MMC_0>; + clock-names = "mmc", "icn"; + clocks = <&clk_s_c0_flexgen CLK_MMC_0>, + <&clk_s_c0_flexgen CLK_RX_ICN_HVA>; bus-width = <8>; non-removable; }; @@ -565,8 +566,9 @@ interrupt-names = "mmcirq"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_sd1>; - clock-names = "mmc"; - clocks = <&clk_s_c0_flexgen CLK_MMC_1>; + clock-names = "mmc", "icn"; + clocks = <&clk_s_c0_flexgen CLK_MMC_1>, + <&clk_s_c0_flexgen CLK_RX_ICN_HVA>; resets = <&softreset STIH407_MMC1_SOFTRESET>; bus-width = <4>; }; diff --git a/arch/arm/boot/dts/stih410.dtsi b/arch/arm/boot/dts/stih410.dtsi index 18ed1ad10d32..40318869c733 100644 --- a/arch/arm/boot/dts/stih410.dtsi +++ b/arch/arm/boot/dts/stih410.dtsi @@ -41,7 +41,8 @@ compatible = "st,st-ohci-300x"; reg = <0x9a03c00 0x100>; interrupts = <GIC_SPI 180 IRQ_TYPE_NONE>; - clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>; + clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>, + <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>; resets = <&powerdown STIH407_USB2_PORT0_POWERDOWN>, <&softreset STIH407_USB2_PORT0_SOFTRESET>; reset-names = "power", "softreset"; @@ -57,7 +58,8 @@ interrupts = <GIC_SPI 151 IRQ_TYPE_NONE>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usb0>; - clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>; + clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>, + <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>; resets = <&powerdown STIH407_USB2_PORT0_POWERDOWN>, <&softreset STIH407_USB2_PORT0_SOFTRESET>; reset-names = "power", "softreset"; @@ -71,7 +73,8 @@ compatible = "st,st-ohci-300x"; reg = <0x9a83c00 0x100>; interrupts = <GIC_SPI 181 IRQ_TYPE_NONE>; - clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>; + clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>, + <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>; resets = <&powerdown STIH407_USB2_PORT1_POWERDOWN>, <&softreset STIH407_USB2_PORT1_SOFTRESET>; reset-names = "power", "softreset"; @@ -87,7 +90,8 @@ interrupts = <GIC_SPI 153 IRQ_TYPE_NONE>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usb1>; - clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>; + clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>, + <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>; resets = <&powerdown STIH407_USB2_PORT1_POWERDOWN>, <&softreset STIH407_USB2_PORT1_SOFTRESET>; reset-names = "power", "softreset"; diff --git a/arch/arm/boot/dts/stm32f429.dtsi b/arch/arm/boot/dts/stm32f429.dtsi index 35df462559ca..1a189d44ad38 100644 --- a/arch/arm/boot/dts/stm32f429.dtsi +++ b/arch/arm/boot/dts/stm32f429.dtsi @@ -176,6 +176,14 @@ reg = <0x40013800 0x400>; }; + exti: interrupt-controller@40013c00 { + compatible = "st,stm32-exti"; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x40013C00 0x400>; + interrupts = <1>, <2>, <3>, <6>, <7>, <8>, <9>, <10>, <23>, <40>, <41>, <42>, <62>, <76>; + }; + pin-controller { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi index e012890e0cf2..a17ba0243db3 100644 --- a/arch/arm/boot/dts/sun5i-a13.dtsi +++ b/arch/arm/boot/dts/sun5i-a13.dtsi @@ -84,7 +84,7 @@ trips { cpu_alert0: cpu_alert0 { /* milliCelsius */ - temperature = <850000>; + temperature = <85000>; hysteresis = <2000>; type = "passive"; }; diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi index 1867af24ff52..0d24f107ede0 100644 --- a/arch/arm/boot/dts/sun6i-a31.dtsi +++ b/arch/arm/boot/dts/sun6i-a31.dtsi @@ -469,7 +469,7 @@ }; mmc0: mmc@01c0f000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c0f000 0x1000>; clocks = <&ahb1_gates 8>, <&mmc0_clk 0>, @@ -488,7 +488,7 @@ }; mmc1: mmc@01c10000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c10000 0x1000>; clocks = <&ahb1_gates 9>, <&mmc1_clk 0>, @@ -507,7 +507,7 @@ }; mmc2: mmc@01c11000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c11000 0x1000>; clocks = <&ahb1_gates 10>, <&mmc2_clk 0>, @@ -526,7 +526,7 @@ }; mmc3: mmc@01c12000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c12000 0x1000>; clocks = <&ahb1_gates 11>, <&mmc3_clk 0>, diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index bd0c47660243..94cf5a1c7172 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -905,7 +905,7 @@ }; mmc0: mmc@01c0f000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c0f000 0x1000>; clocks = <&ahb_gates 8>, <&mmc0_clk 0>, @@ -922,7 +922,7 @@ }; mmc1: mmc@01c10000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c10000 0x1000>; clocks = <&ahb_gates 9>, <&mmc1_clk 0>, @@ -939,7 +939,7 @@ }; mmc2: mmc@01c11000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c11000 0x1000>; clocks = <&ahb_gates 10>, <&mmc2_clk 0>, @@ -956,7 +956,7 @@ }; mmc3: mmc@01c12000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c12000 0x1000>; clocks = <&ahb_gates 11>, <&mmc3_clk 0>, diff --git a/arch/arm/boot/dts/sun8i-a23-a33.dtsi b/arch/arm/boot/dts/sun8i-a23-a33.dtsi index 7e05e09e61c7..e3b196e08ccf 100644 --- a/arch/arm/boot/dts/sun8i-a23-a33.dtsi +++ b/arch/arm/boot/dts/sun8i-a23-a33.dtsi @@ -266,7 +266,7 @@ }; mmc0: mmc@01c0f000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c0f000 0x1000>; clocks = <&ahb1_gates 8>, <&mmc0_clk 0>, @@ -285,7 +285,7 @@ }; mmc1: mmc@01c10000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c10000 0x1000>; clocks = <&ahb1_gates 9>, <&mmc1_clk 0>, @@ -304,7 +304,7 @@ }; mmc2: mmc@01c11000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c11000 0x1000>; clocks = <&ahb1_gates 10>, <&mmc2_clk 0>, diff --git a/arch/arm/boot/dts/sun8i-h3.dtsi b/arch/arm/boot/dts/sun8i-h3.dtsi index fdf9fdbda267..8a95e3613488 100644 --- a/arch/arm/boot/dts/sun8i-h3.dtsi +++ b/arch/arm/boot/dts/sun8i-h3.dtsi @@ -150,7 +150,7 @@ }; mmc0: mmc@01c0f000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c0f000 0x1000>; clocks = <&ccu CLK_BUS_MMC0>, <&ccu CLK_MMC0>, @@ -169,7 +169,7 @@ }; mmc1: mmc@01c10000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c10000 0x1000>; clocks = <&ccu CLK_BUS_MMC1>, <&ccu CLK_MMC1>, @@ -188,7 +188,7 @@ }; mmc2: mmc@01c11000 { - compatible = "allwinner,sun5i-a13-mmc"; + compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c11000 0x1000>; clocks = <&ccu CLK_BUS_MMC2>, <&ccu CLK_MMC2>, diff --git a/arch/arm/boot/dts/tegra114-dalmore.dts b/arch/arm/boot/dts/tegra114-dalmore.dts index 1dfc492cc004..1444fbd543e7 100644 --- a/arch/arm/boot/dts/tegra114-dalmore.dts +++ b/arch/arm/boot/dts/tegra114-dalmore.dts @@ -897,7 +897,7 @@ palmas: tps65913@58 { compatible = "ti,palmas"; reg = <0x58>; - interrupts = <0 86 IRQ_TYPE_LEVEL_LOW>; + interrupts = <0 86 IRQ_TYPE_LEVEL_HIGH>; #interrupt-cells = <2>; interrupt-controller; diff --git a/arch/arm/boot/dts/tegra114-roth.dts b/arch/arm/boot/dts/tegra114-roth.dts index 70cf40996c3f..966a7fc044af 100644 --- a/arch/arm/boot/dts/tegra114-roth.dts +++ b/arch/arm/boot/dts/tegra114-roth.dts @@ -802,7 +802,7 @@ palmas: pmic@58 { compatible = "ti,palmas"; reg = <0x58>; - interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_LOW>; + interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>; #interrupt-cells = <2>; interrupt-controller; diff --git a/arch/arm/boot/dts/tegra114-tn7.dts b/arch/arm/boot/dts/tegra114-tn7.dts index 17dd14545862..a161fa1dfb61 100644 --- a/arch/arm/boot/dts/tegra114-tn7.dts +++ b/arch/arm/boot/dts/tegra114-tn7.dts @@ -63,7 +63,7 @@ palmas: pmic@58 { compatible = "ti,palmas"; reg = <0x58>; - interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_LOW>; + interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>; #interrupt-cells = <2>; interrupt-controller; diff --git a/arch/arm/boot/dts/tegra124-jetson-tk1.dts b/arch/arm/boot/dts/tegra124-jetson-tk1.dts index 6403e0de540e..e52b82449a79 100644 --- a/arch/arm/boot/dts/tegra124-jetson-tk1.dts +++ b/arch/arm/boot/dts/tegra124-jetson-tk1.dts @@ -1382,7 +1382,7 @@ * Pin 41: BR_UART1_TXD * Pin 44: BR_UART1_RXD */ - serial@0,70006000 { + serial@70006000 { compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart"; status = "okay"; }; @@ -1394,7 +1394,7 @@ * Pin 71: UART2_CTS_L * Pin 74: UART2_RTS_L */ - serial@0,70006040 { + serial@70006040 { compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart"; status = "okay"; }; diff --git a/arch/arm/common/bL_switcher_dummy_if.c b/arch/arm/common/bL_switcher_dummy_if.c index 3f47f1203c6b..6053f64c3752 100644 --- a/arch/arm/common/bL_switcher_dummy_if.c +++ b/arch/arm/common/bL_switcher_dummy_if.c @@ -56,16 +56,4 @@ static struct miscdevice bL_switcher_device = { "b.L_switcher", &bL_switcher_fops }; - -static int __init bL_switcher_dummy_if_init(void) -{ - return misc_register(&bL_switcher_device); -} - -static void __exit bL_switcher_dummy_if_exit(void) -{ - misc_deregister(&bL_switcher_device); -} - -module_init(bL_switcher_dummy_if_init); -module_exit(bL_switcher_dummy_if_exit); +module_misc_device(bL_switcher_device); diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c index 0e97b4b871f9..6c7b06854fce 100644 --- a/arch/arm/common/locomo.c +++ b/arch/arm/common/locomo.c @@ -140,7 +140,7 @@ static struct locomo_dev_info locomo_devices[] = { static void locomo_handler(struct irq_desc *desc) { - struct locomo *lchip = irq_desc_get_chip_data(desc); + struct locomo *lchip = irq_desc_get_handler_data(desc); int req, i; /* Acknowledge the parent IRQ */ @@ -200,8 +200,7 @@ static void locomo_setup_irq(struct locomo *lchip) * Install handler for IRQ_LOCOMO_HW. */ irq_set_irq_type(lchip->irq, IRQ_TYPE_EDGE_FALLING); - irq_set_chip_data(lchip->irq, lchip); - irq_set_chained_handler(lchip->irq, locomo_handler); + irq_set_chained_handler_and_data(lchip->irq, locomo_handler, lchip); /* Install handlers for IRQ_LOCOMO_* */ for ( ; irq <= lchip->irq_base + 3; irq++) { diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c index fb0a0a4dfea4..4ecd5120fce7 100644 --- a/arch/arm/common/sa1111.c +++ b/arch/arm/common/sa1111.c @@ -15,6 +15,7 @@ * from machine specific code with proper arguments when required. */ #include <linux/module.h> +#include <linux/gpio/driver.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/kernel.h> @@ -107,6 +108,7 @@ struct sa1111 { spinlock_t lock; void __iomem *base; struct sa1111_platform_data *pdata; + struct gpio_chip gc; #ifdef CONFIG_PM void *saved_state; #endif @@ -231,132 +233,44 @@ static void sa1111_irq_handler(struct irq_desc *desc) #define SA1111_IRQMASK_LO(x) (1 << (x - sachip->irq_base)) #define SA1111_IRQMASK_HI(x) (1 << (x - sachip->irq_base - 32)) -static void sa1111_ack_irq(struct irq_data *d) -{ -} - -static void sa1111_mask_lowirq(struct irq_data *d) +static u32 sa1111_irqmask(struct irq_data *d) { struct sa1111 *sachip = irq_data_get_irq_chip_data(d); - void __iomem *mapbase = sachip->base + SA1111_INTC; - unsigned long ie0; - ie0 = sa1111_readl(mapbase + SA1111_INTEN0); - ie0 &= ~SA1111_IRQMASK_LO(d->irq); - writel(ie0, mapbase + SA1111_INTEN0); + return BIT((d->irq - sachip->irq_base) & 31); } -static void sa1111_unmask_lowirq(struct irq_data *d) +static int sa1111_irqbank(struct irq_data *d) { struct sa1111 *sachip = irq_data_get_irq_chip_data(d); - void __iomem *mapbase = sachip->base + SA1111_INTC; - unsigned long ie0; - ie0 = sa1111_readl(mapbase + SA1111_INTEN0); - ie0 |= SA1111_IRQMASK_LO(d->irq); - sa1111_writel(ie0, mapbase + SA1111_INTEN0); + return ((d->irq - sachip->irq_base) / 32) * 4; } -/* - * Attempt to re-trigger the interrupt. The SA1111 contains a register - * (INTSET) which claims to do this. However, in practice no amount of - * manipulation of INTEN and INTSET guarantees that the interrupt will - * be triggered. In fact, its very difficult, if not impossible to get - * INTSET to re-trigger the interrupt. - */ -static int sa1111_retrigger_lowirq(struct irq_data *d) -{ - struct sa1111 *sachip = irq_data_get_irq_chip_data(d); - void __iomem *mapbase = sachip->base + SA1111_INTC; - unsigned int mask = SA1111_IRQMASK_LO(d->irq); - unsigned long ip0; - int i; - - ip0 = sa1111_readl(mapbase + SA1111_INTPOL0); - for (i = 0; i < 8; i++) { - sa1111_writel(ip0 ^ mask, mapbase + SA1111_INTPOL0); - sa1111_writel(ip0, mapbase + SA1111_INTPOL0); - if (sa1111_readl(mapbase + SA1111_INTSTATCLR0) & mask) - break; - } - - if (i == 8) - pr_err("Danger Will Robinson: failed to re-trigger IRQ%d\n", - d->irq); - return i == 8 ? -1 : 0; -} - -static int sa1111_type_lowirq(struct irq_data *d, unsigned int flags) -{ - struct sa1111 *sachip = irq_data_get_irq_chip_data(d); - void __iomem *mapbase = sachip->base + SA1111_INTC; - unsigned int mask = SA1111_IRQMASK_LO(d->irq); - unsigned long ip0; - - if (flags == IRQ_TYPE_PROBE) - return 0; - - if ((!(flags & IRQ_TYPE_EDGE_RISING) ^ !(flags & IRQ_TYPE_EDGE_FALLING)) == 0) - return -EINVAL; - - ip0 = sa1111_readl(mapbase + SA1111_INTPOL0); - if (flags & IRQ_TYPE_EDGE_RISING) - ip0 &= ~mask; - else - ip0 |= mask; - sa1111_writel(ip0, mapbase + SA1111_INTPOL0); - sa1111_writel(ip0, mapbase + SA1111_WAKEPOL0); - - return 0; -} - -static int sa1111_wake_lowirq(struct irq_data *d, unsigned int on) +static void sa1111_ack_irq(struct irq_data *d) { - struct sa1111 *sachip = irq_data_get_irq_chip_data(d); - void __iomem *mapbase = sachip->base + SA1111_INTC; - unsigned int mask = SA1111_IRQMASK_LO(d->irq); - unsigned long we0; - - we0 = sa1111_readl(mapbase + SA1111_WAKEEN0); - if (on) - we0 |= mask; - else - we0 &= ~mask; - sa1111_writel(we0, mapbase + SA1111_WAKEEN0); - - return 0; } -static struct irq_chip sa1111_low_chip = { - .name = "SA1111-l", - .irq_ack = sa1111_ack_irq, - .irq_mask = sa1111_mask_lowirq, - .irq_unmask = sa1111_unmask_lowirq, - .irq_retrigger = sa1111_retrigger_lowirq, - .irq_set_type = sa1111_type_lowirq, - .irq_set_wake = sa1111_wake_lowirq, -}; - -static void sa1111_mask_highirq(struct irq_data *d) +static void sa1111_mask_irq(struct irq_data *d) { struct sa1111 *sachip = irq_data_get_irq_chip_data(d); - void __iomem *mapbase = sachip->base + SA1111_INTC; - unsigned long ie1; + void __iomem *mapbase = sachip->base + SA1111_INTC + sa1111_irqbank(d); + u32 ie; - ie1 = sa1111_readl(mapbase + SA1111_INTEN1); - ie1 &= ~SA1111_IRQMASK_HI(d->irq); - sa1111_writel(ie1, mapbase + SA1111_INTEN1); + ie = sa1111_readl(mapbase + SA1111_INTEN0); + ie &= ~sa1111_irqmask(d); + sa1111_writel(ie, mapbase + SA1111_INTEN0); } -static void sa1111_unmask_highirq(struct irq_data *d) +static void sa1111_unmask_irq(struct irq_data *d) { struct sa1111 *sachip = irq_data_get_irq_chip_data(d); - void __iomem *mapbase = sachip->base + SA1111_INTC; - unsigned long ie1; + void __iomem *mapbase = sachip->base + SA1111_INTC + sa1111_irqbank(d); + u32 ie; - ie1 = sa1111_readl(mapbase + SA1111_INTEN1); - ie1 |= SA1111_IRQMASK_HI(d->irq); - sa1111_writel(ie1, mapbase + SA1111_INTEN1); + ie = sa1111_readl(mapbase + SA1111_INTEN0); + ie |= sa1111_irqmask(d); + sa1111_writel(ie, mapbase + SA1111_INTEN0); } /* @@ -366,19 +280,18 @@ static void sa1111_unmask_highirq(struct irq_data *d) * be triggered. In fact, its very difficult, if not impossible to get * INTSET to re-trigger the interrupt. */ -static int sa1111_retrigger_highirq(struct irq_data *d) +static int sa1111_retrigger_irq(struct irq_data *d) { struct sa1111 *sachip = irq_data_get_irq_chip_data(d); - void __iomem *mapbase = sachip->base + SA1111_INTC; - unsigned int mask = SA1111_IRQMASK_HI(d->irq); - unsigned long ip1; + void __iomem *mapbase = sachip->base + SA1111_INTC + sa1111_irqbank(d); + u32 ip, mask = sa1111_irqmask(d); int i; - ip1 = sa1111_readl(mapbase + SA1111_INTPOL1); + ip = sa1111_readl(mapbase + SA1111_INTPOL0); for (i = 0; i < 8; i++) { - sa1111_writel(ip1 ^ mask, mapbase + SA1111_INTPOL1); - sa1111_writel(ip1, mapbase + SA1111_INTPOL1); - if (sa1111_readl(mapbase + SA1111_INTSTATCLR1) & mask) + sa1111_writel(ip ^ mask, mapbase + SA1111_INTPOL0); + sa1111_writel(ip, mapbase + SA1111_INTPOL0); + if (sa1111_readl(mapbase + SA1111_INTSTATCLR0) & mask) break; } @@ -388,12 +301,11 @@ static int sa1111_retrigger_highirq(struct irq_data *d) return i == 8 ? -1 : 0; } -static int sa1111_type_highirq(struct irq_data *d, unsigned int flags) +static int sa1111_type_irq(struct irq_data *d, unsigned int flags) { struct sa1111 *sachip = irq_data_get_irq_chip_data(d); - void __iomem *mapbase = sachip->base + SA1111_INTC; - unsigned int mask = SA1111_IRQMASK_HI(d->irq); - unsigned long ip1; + void __iomem *mapbase = sachip->base + SA1111_INTC + sa1111_irqbank(d); + u32 ip, mask = sa1111_irqmask(d); if (flags == IRQ_TYPE_PROBE) return 0; @@ -401,42 +313,41 @@ static int sa1111_type_highirq(struct irq_data *d, unsigned int flags) if ((!(flags & IRQ_TYPE_EDGE_RISING) ^ !(flags & IRQ_TYPE_EDGE_FALLING)) == 0) return -EINVAL; - ip1 = sa1111_readl(mapbase + SA1111_INTPOL1); + ip = sa1111_readl(mapbase + SA1111_INTPOL0); if (flags & IRQ_TYPE_EDGE_RISING) - ip1 &= ~mask; + ip &= ~mask; else - ip1 |= mask; - sa1111_writel(ip1, mapbase + SA1111_INTPOL1); - sa1111_writel(ip1, mapbase + SA1111_WAKEPOL1); + ip |= mask; + sa1111_writel(ip, mapbase + SA1111_INTPOL0); + sa1111_writel(ip, mapbase + SA1111_WAKEPOL0); return 0; } -static int sa1111_wake_highirq(struct irq_data *d, unsigned int on) +static int sa1111_wake_irq(struct irq_data *d, unsigned int on) { struct sa1111 *sachip = irq_data_get_irq_chip_data(d); - void __iomem *mapbase = sachip->base + SA1111_INTC; - unsigned int mask = SA1111_IRQMASK_HI(d->irq); - unsigned long we1; + void __iomem *mapbase = sachip->base + SA1111_INTC + sa1111_irqbank(d); + u32 we, mask = sa1111_irqmask(d); - we1 = sa1111_readl(mapbase + SA1111_WAKEEN1); + we = sa1111_readl(mapbase + SA1111_WAKEEN0); if (on) - we1 |= mask; + we |= mask; else - we1 &= ~mask; - sa1111_writel(we1, mapbase + SA1111_WAKEEN1); + we &= ~mask; + sa1111_writel(we, mapbase + SA1111_WAKEEN0); return 0; } -static struct irq_chip sa1111_high_chip = { - .name = "SA1111-h", +static struct irq_chip sa1111_irq_chip = { + .name = "SA1111", .irq_ack = sa1111_ack_irq, - .irq_mask = sa1111_mask_highirq, - .irq_unmask = sa1111_unmask_highirq, - .irq_retrigger = sa1111_retrigger_highirq, - .irq_set_type = sa1111_type_highirq, - .irq_set_wake = sa1111_wake_highirq, + .irq_mask = sa1111_mask_irq, + .irq_unmask = sa1111_unmask_irq, + .irq_retrigger = sa1111_retrigger_irq, + .irq_set_type = sa1111_type_irq, + .irq_set_wake = sa1111_wake_irq, }; static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base) @@ -472,8 +383,8 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base) * specifies that S0ReadyInt and S1ReadyInt should be '1'. */ sa1111_writel(0, irqbase + SA1111_INTPOL0); - sa1111_writel(SA1111_IRQMASK_HI(IRQ_S0_READY_NINT) | - SA1111_IRQMASK_HI(IRQ_S1_READY_NINT), + sa1111_writel(BIT(IRQ_S0_READY_NINT & 31) | + BIT(IRQ_S1_READY_NINT & 31), irqbase + SA1111_INTPOL1); /* clear all IRQs */ @@ -482,16 +393,14 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base) for (i = IRQ_GPAIN0; i <= SSPROR; i++) { irq = sachip->irq_base + i; - irq_set_chip_and_handler(irq, &sa1111_low_chip, - handle_edge_irq); + irq_set_chip_and_handler(irq, &sa1111_irq_chip, handle_edge_irq); irq_set_chip_data(irq, sachip); irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE); } for (i = AUDXMTDMADONEA; i <= IRQ_S1_BVD1_STSCHG; i++) { irq = sachip->irq_base + i; - irq_set_chip_and_handler(irq, &sa1111_high_chip, - handle_edge_irq); + irq_set_chip_and_handler(irq, &sa1111_irq_chip, handle_edge_irq); irq_set_chip_data(irq, sachip); irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE); } @@ -509,6 +418,181 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base) return 0; } +static void sa1111_remove_irq(struct sa1111 *sachip) +{ + void __iomem *irqbase = sachip->base + SA1111_INTC; + + /* disable all IRQs */ + sa1111_writel(0, irqbase + SA1111_INTEN0); + sa1111_writel(0, irqbase + SA1111_INTEN1); + sa1111_writel(0, irqbase + SA1111_WAKEEN0); + sa1111_writel(0, irqbase + SA1111_WAKEEN1); + + if (sachip->irq != NO_IRQ) { + irq_set_chained_handler_and_data(sachip->irq, NULL, NULL); + irq_free_descs(sachip->irq_base, SA1111_IRQ_NR); + + release_mem_region(sachip->phys + SA1111_INTC, 512); + } +} + +enum { + SA1111_GPIO_PXDDR = (SA1111_GPIO_PADDR - SA1111_GPIO_PADDR), + SA1111_GPIO_PXDRR = (SA1111_GPIO_PADRR - SA1111_GPIO_PADDR), + SA1111_GPIO_PXDWR = (SA1111_GPIO_PADWR - SA1111_GPIO_PADDR), + SA1111_GPIO_PXSDR = (SA1111_GPIO_PASDR - SA1111_GPIO_PADDR), + SA1111_GPIO_PXSSR = (SA1111_GPIO_PASSR - SA1111_GPIO_PADDR), +}; + +static struct sa1111 *gc_to_sa1111(struct gpio_chip *gc) +{ + return container_of(gc, struct sa1111, gc); +} + +static void __iomem *sa1111_gpio_map_reg(struct sa1111 *sachip, unsigned offset) +{ + void __iomem *reg = sachip->base + SA1111_GPIO; + + if (offset < 4) + return reg + SA1111_GPIO_PADDR; + if (offset < 10) + return reg + SA1111_GPIO_PBDDR; + if (offset < 18) + return reg + SA1111_GPIO_PCDDR; + return NULL; +} + +static u32 sa1111_gpio_map_bit(unsigned offset) +{ + if (offset < 4) + return BIT(offset); + if (offset < 10) + return BIT(offset - 4); + if (offset < 18) + return BIT(offset - 10); + return 0; +} + +static void sa1111_gpio_modify(void __iomem *reg, u32 mask, u32 set) +{ + u32 val; + + val = readl_relaxed(reg); + val &= ~mask; + val |= mask & set; + writel_relaxed(val, reg); +} + +static int sa1111_gpio_get_direction(struct gpio_chip *gc, unsigned offset) +{ + struct sa1111 *sachip = gc_to_sa1111(gc); + void __iomem *reg = sa1111_gpio_map_reg(sachip, offset); + u32 mask = sa1111_gpio_map_bit(offset); + + return !!(readl_relaxed(reg + SA1111_GPIO_PXDDR) & mask); +} + +static int sa1111_gpio_direction_input(struct gpio_chip *gc, unsigned offset) +{ + struct sa1111 *sachip = gc_to_sa1111(gc); + unsigned long flags; + void __iomem *reg = sa1111_gpio_map_reg(sachip, offset); + u32 mask = sa1111_gpio_map_bit(offset); + + spin_lock_irqsave(&sachip->lock, flags); + sa1111_gpio_modify(reg + SA1111_GPIO_PXDDR, mask, mask); + sa1111_gpio_modify(reg + SA1111_GPIO_PXSDR, mask, mask); + spin_unlock_irqrestore(&sachip->lock, flags); + + return 0; +} + +static int sa1111_gpio_direction_output(struct gpio_chip *gc, unsigned offset, + int value) +{ + struct sa1111 *sachip = gc_to_sa1111(gc); + unsigned long flags; + void __iomem *reg = sa1111_gpio_map_reg(sachip, offset); + u32 mask = sa1111_gpio_map_bit(offset); + + spin_lock_irqsave(&sachip->lock, flags); + sa1111_gpio_modify(reg + SA1111_GPIO_PXDWR, mask, value ? mask : 0); + sa1111_gpio_modify(reg + SA1111_GPIO_PXSSR, mask, value ? mask : 0); + sa1111_gpio_modify(reg + SA1111_GPIO_PXDDR, mask, 0); + sa1111_gpio_modify(reg + SA1111_GPIO_PXSDR, mask, 0); + spin_unlock_irqrestore(&sachip->lock, flags); + + return 0; +} + +static int sa1111_gpio_get(struct gpio_chip *gc, unsigned offset) +{ + struct sa1111 *sachip = gc_to_sa1111(gc); + void __iomem *reg = sa1111_gpio_map_reg(sachip, offset); + u32 mask = sa1111_gpio_map_bit(offset); + + return !!(readl_relaxed(reg + SA1111_GPIO_PXDRR) & mask); +} + +static void sa1111_gpio_set(struct gpio_chip *gc, unsigned offset, int value) +{ + struct sa1111 *sachip = gc_to_sa1111(gc); + unsigned long flags; + void __iomem *reg = sa1111_gpio_map_reg(sachip, offset); + u32 mask = sa1111_gpio_map_bit(offset); + + spin_lock_irqsave(&sachip->lock, flags); + sa1111_gpio_modify(reg + SA1111_GPIO_PXDWR, mask, value ? mask : 0); + sa1111_gpio_modify(reg + SA1111_GPIO_PXSSR, mask, value ? mask : 0); + spin_unlock_irqrestore(&sachip->lock, flags); +} + +static void sa1111_gpio_set_multiple(struct gpio_chip *gc, unsigned long *mask, + unsigned long *bits) +{ + struct sa1111 *sachip = gc_to_sa1111(gc); + unsigned long flags; + void __iomem *reg = sachip->base + SA1111_GPIO; + u32 msk, val; + + msk = *mask; + val = *bits; + + spin_lock_irqsave(&sachip->lock, flags); + sa1111_gpio_modify(reg + SA1111_GPIO_PADWR, msk & 15, val); + sa1111_gpio_modify(reg + SA1111_GPIO_PASSR, msk & 15, val); + sa1111_gpio_modify(reg + SA1111_GPIO_PBDWR, (msk >> 4) & 255, val >> 4); + sa1111_gpio_modify(reg + SA1111_GPIO_PBSSR, (msk >> 4) & 255, val >> 4); + sa1111_gpio_modify(reg + SA1111_GPIO_PCDWR, (msk >> 12) & 255, val >> 12); + sa1111_gpio_modify(reg + SA1111_GPIO_PCSSR, (msk >> 12) & 255, val >> 12); + spin_unlock_irqrestore(&sachip->lock, flags); +} + +static int sa1111_gpio_to_irq(struct gpio_chip *gc, unsigned offset) +{ + struct sa1111 *sachip = gc_to_sa1111(gc); + + return sachip->irq_base + offset; +} + +static int sa1111_setup_gpios(struct sa1111 *sachip) +{ + sachip->gc.label = "sa1111"; + sachip->gc.parent = sachip->dev; + sachip->gc.owner = THIS_MODULE; + sachip->gc.get_direction = sa1111_gpio_get_direction; + sachip->gc.direction_input = sa1111_gpio_direction_input; + sachip->gc.direction_output = sa1111_gpio_direction_output; + sachip->gc.get = sa1111_gpio_get; + sachip->gc.set = sa1111_gpio_set; + sachip->gc.set_multiple = sa1111_gpio_set_multiple; + sachip->gc.to_irq = sa1111_gpio_to_irq; + sachip->gc.base = -1; + sachip->gc.ngpio = 18; + + return devm_gpiochip_add_data(sachip->dev, &sachip->gc, sachip); +} + /* * Bring the SA1111 out of reset. This requires a set procedure: * 1. nRESET asserted (by hardware) @@ -607,7 +691,7 @@ sa1111_configure_smc(struct sa1111 *sachip, int sdram, unsigned int drac, static void sa1111_dev_release(struct device *_dev) { - struct sa1111_dev *dev = SA1111_DEV(_dev); + struct sa1111_dev *dev = to_sa1111_device(_dev); kfree(dev); } @@ -696,19 +780,17 @@ static int __sa1111_probe(struct device *me, struct resource *mem, int irq) if (!pd) return -EINVAL; - sachip = kzalloc(sizeof(struct sa1111), GFP_KERNEL); + sachip = devm_kzalloc(me, sizeof(struct sa1111), GFP_KERNEL); if (!sachip) return -ENOMEM; - sachip->clk = clk_get(me, "SA1111_CLK"); - if (IS_ERR(sachip->clk)) { - ret = PTR_ERR(sachip->clk); - goto err_free; - } + sachip->clk = devm_clk_get(me, "SA1111_CLK"); + if (IS_ERR(sachip->clk)) + return PTR_ERR(sachip->clk); ret = clk_prepare(sachip->clk); if (ret) - goto err_clkput; + return ret; spin_lock_init(&sachip->lock); @@ -754,9 +836,14 @@ static int __sa1111_probe(struct device *me, struct resource *mem, int irq) if (sachip->irq != NO_IRQ) { ret = sa1111_setup_irq(sachip, pd->irq_base); if (ret) - goto err_unmap; + goto err_clk; } + /* Setup the GPIOs - should really be done after the IRQ setup */ + ret = sa1111_setup_gpios(sachip); + if (ret) + goto err_irq; + #ifdef CONFIG_ARCH_SA1100 { unsigned int val; @@ -799,20 +886,22 @@ static int __sa1111_probe(struct device *me, struct resource *mem, int irq) return 0; + err_irq: + sa1111_remove_irq(sachip); + err_clk: + clk_disable(sachip->clk); err_unmap: iounmap(sachip->base); err_clk_unprep: clk_unprepare(sachip->clk); - err_clkput: - clk_put(sachip->clk); - err_free: - kfree(sachip); return ret; } static int sa1111_remove_one(struct device *dev, void *data) { - struct sa1111_dev *sadev = SA1111_DEV(dev); + struct sa1111_dev *sadev = to_sa1111_device(dev); + if (dev->bus != &sa1111_bus_type) + return 0; device_del(&sadev->dev); release_resource(&sadev->res); put_device(&sadev->dev); @@ -821,29 +910,14 @@ static int sa1111_remove_one(struct device *dev, void *data) static void __sa1111_remove(struct sa1111 *sachip) { - void __iomem *irqbase = sachip->base + SA1111_INTC; - device_for_each_child(sachip->dev, NULL, sa1111_remove_one); - /* disable all IRQs */ - sa1111_writel(0, irqbase + SA1111_INTEN0); - sa1111_writel(0, irqbase + SA1111_INTEN1); - sa1111_writel(0, irqbase + SA1111_WAKEEN0); - sa1111_writel(0, irqbase + SA1111_WAKEEN1); + sa1111_remove_irq(sachip); clk_disable(sachip->clk); clk_unprepare(sachip->clk); - if (sachip->irq != NO_IRQ) { - irq_set_chained_handler_and_data(sachip->irq, NULL, NULL); - irq_free_descs(sachip->irq_base, SA1111_IRQ_NR); - - release_mem_region(sachip->phys + SA1111_INTC, 512); - } - iounmap(sachip->base); - clk_put(sachip->clk); - kfree(sachip); } struct sa1111_save_data { @@ -869,9 +943,9 @@ struct sa1111_save_data { #ifdef CONFIG_PM -static int sa1111_suspend(struct platform_device *dev, pm_message_t state) +static int sa1111_suspend_noirq(struct device *dev) { - struct sa1111 *sachip = platform_get_drvdata(dev); + struct sa1111 *sachip = dev_get_drvdata(dev); struct sa1111_save_data *save; unsigned long flags; unsigned int val; @@ -934,9 +1008,9 @@ static int sa1111_suspend(struct platform_device *dev, pm_message_t state) * restored by their respective drivers, and must be called * via LDM after this function. */ -static int sa1111_resume(struct platform_device *dev) +static int sa1111_resume_noirq(struct device *dev) { - struct sa1111 *sachip = platform_get_drvdata(dev); + struct sa1111 *sachip = dev_get_drvdata(dev); struct sa1111_save_data *save; unsigned long flags, id; void __iomem *base; @@ -952,7 +1026,7 @@ static int sa1111_resume(struct platform_device *dev) id = sa1111_readl(sachip->base + SA1111_SKID); if ((id & SKID_ID_MASK) != SKID_SA1111_ID) { __sa1111_remove(sachip); - platform_set_drvdata(dev, NULL); + dev_set_drvdata(dev, NULL); kfree(save); return 0; } @@ -1003,8 +1077,8 @@ static int sa1111_resume(struct platform_device *dev) } #else -#define sa1111_suspend NULL -#define sa1111_resume NULL +#define sa1111_suspend_noirq NULL +#define sa1111_resume_noirq NULL #endif static int sa1111_probe(struct platform_device *pdev) @@ -1017,7 +1091,7 @@ static int sa1111_probe(struct platform_device *pdev) return -EINVAL; irq = platform_get_irq(pdev, 0); if (irq < 0) - return -ENXIO; + return irq; return __sa1111_probe(&pdev->dev, mem, irq); } @@ -1038,6 +1112,11 @@ static int sa1111_remove(struct platform_device *pdev) return 0; } +static struct dev_pm_ops sa1111_pm_ops = { + .suspend_noirq = sa1111_suspend_noirq, + .resume_noirq = sa1111_resume_noirq, +}; + /* * Not sure if this should be on the system bus or not yet. * We really want some way to register a system device at @@ -1050,10 +1129,9 @@ static int sa1111_remove(struct platform_device *pdev) static struct platform_driver sa1111_device_driver = { .probe = sa1111_probe, .remove = sa1111_remove, - .suspend = sa1111_suspend, - .resume = sa1111_resume, .driver = { .name = "sa1111", + .pm = &sa1111_pm_ops, }, }; @@ -1279,6 +1357,14 @@ void sa1111_disable_device(struct sa1111_dev *sadev) } EXPORT_SYMBOL(sa1111_disable_device); +int sa1111_get_irq(struct sa1111_dev *sadev, unsigned num) +{ + if (num >= ARRAY_SIZE(sadev->irq)) + return -EINVAL; + return sadev->irq[num]; +} +EXPORT_SYMBOL_GPL(sa1111_get_irq); + /* * SA1111 "Register Access Bus." * @@ -1287,7 +1373,7 @@ EXPORT_SYMBOL(sa1111_disable_device); */ static int sa1111_match(struct device *_dev, struct device_driver *_drv) { - struct sa1111_dev *dev = SA1111_DEV(_dev); + struct sa1111_dev *dev = to_sa1111_device(_dev); struct sa1111_driver *drv = SA1111_DRV(_drv); return !!(dev->devid & drv->devid); @@ -1295,7 +1381,7 @@ static int sa1111_match(struct device *_dev, struct device_driver *_drv) static int sa1111_bus_suspend(struct device *dev, pm_message_t state) { - struct sa1111_dev *sadev = SA1111_DEV(dev); + struct sa1111_dev *sadev = to_sa1111_device(dev); struct sa1111_driver *drv = SA1111_DRV(dev->driver); int ret = 0; @@ -1306,7 +1392,7 @@ static int sa1111_bus_suspend(struct device *dev, pm_message_t state) static int sa1111_bus_resume(struct device *dev) { - struct sa1111_dev *sadev = SA1111_DEV(dev); + struct sa1111_dev *sadev = to_sa1111_device(dev); struct sa1111_driver *drv = SA1111_DRV(dev->driver); int ret = 0; @@ -1320,12 +1406,12 @@ static void sa1111_bus_shutdown(struct device *dev) struct sa1111_driver *drv = SA1111_DRV(dev->driver); if (drv && drv->shutdown) - drv->shutdown(SA1111_DEV(dev)); + drv->shutdown(to_sa1111_device(dev)); } static int sa1111_bus_probe(struct device *dev) { - struct sa1111_dev *sadev = SA1111_DEV(dev); + struct sa1111_dev *sadev = to_sa1111_device(dev); struct sa1111_driver *drv = SA1111_DRV(dev->driver); int ret = -ENODEV; @@ -1336,7 +1422,7 @@ static int sa1111_bus_probe(struct device *dev) static int sa1111_bus_remove(struct device *dev) { - struct sa1111_dev *sadev = SA1111_DEV(dev); + struct sa1111_dev *sadev = to_sa1111_device(dev); struct sa1111_driver *drv = SA1111_DRV(dev->driver); int ret = 0; @@ -1401,7 +1487,7 @@ static int sa1111_needs_bounce(struct device *dev, dma_addr_t addr, size_t size) static int sa1111_notifier_call(struct notifier_block *n, unsigned long action, void *data) { - struct sa1111_dev *dev = SA1111_DEV(data); + struct sa1111_dev *dev = to_sa1111_device(data); switch (action) { case BUS_NOTIFY_ADD_DEVICE: diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig index 01986deef7c5..36cc7cc012f9 100644 --- a/arch/arm/configs/exynos_defconfig +++ b/arch/arm/configs/exynos_defconfig @@ -28,7 +28,7 @@ CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m CONFIG_CPU_FREQ_GOV_USERSPACE=m CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m -CONFIG_CPU_FREQ_GOV_SCHEDUTIL=m +CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y CONFIG_CPUFREQ_DT=y CONFIG_CPU_IDLE=y CONFIG_ARM_EXYNOS_CPUIDLE=y diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig index 9083399a8ab1..5f013c9fc1ed 100644 --- a/arch/arm/configs/imx_v4_v5_defconfig +++ b/arch/arm/configs/imx_v4_v5_defconfig @@ -22,14 +22,13 @@ CONFIG_ARCH_MULTI_V4T=y CONFIG_ARCH_MULTI_V5=y # CONFIG_ARCH_MULTI_V7 is not set CONFIG_ARCH_MXC=y -CONFIG_MACH_SCB9328=y -CONFIG_MACH_APF9328=y CONFIG_MACH_MX21ADS=y CONFIG_MACH_MX27ADS=y CONFIG_MACH_MX27_3DS=y CONFIG_MACH_IMX27_VISSTRIM_M10=y CONFIG_MACH_PCA100=y CONFIG_MACH_IMX27_DT=y +CONFIG_SOC_IMX1=y CONFIG_SOC_IMX25=y CONFIG_PREEMPT=y CONFIG_AEABI=y diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig index 71b42e66488a..78cd2f197e01 100644 --- a/arch/arm/configs/keystone_defconfig +++ b/arch/arm/configs/keystone_defconfig @@ -161,6 +161,7 @@ CONFIG_USB_MON=y CONFIG_USB_XHCI_HCD=y CONFIG_USB_STORAGE=y CONFIG_USB_DWC3=y +CONFIG_NOP_USB_XCEIV=y CONFIG_KEYSTONE_USB_PHY=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=y diff --git a/arch/arm/configs/multi_v4t_defconfig b/arch/arm/configs/multi_v4t_defconfig index 433eebb4103f..9a6390c172d6 100644 --- a/arch/arm/configs/multi_v4t_defconfig +++ b/arch/arm/configs/multi_v4t_defconfig @@ -20,9 +20,7 @@ CONFIG_INTEGRATOR_CM720T=y CONFIG_INTEGRATOR_CM920T=y CONFIG_INTEGRATOR_CM922T_XA10=y CONFIG_ARCH_MXC=y -CONFIG_MACH_SCB9328=y -CONFIG_MACH_APF9328=y -CONFIG_MACH_IMX1_DT=y +CONFIG_SOC_IMX1=y CONFIG_ARCH_NSPIRE=y CONFIG_AEABI=y # CONFIG_ATAGS is not set diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 2c8665cd9dc5..58459105cadc 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -135,7 +135,7 @@ CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m CONFIG_CPU_FREQ_GOV_USERSPACE=m CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m -CONFIG_CPU_FREQ_GOV_SCHEDUTIL=m +CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y CONFIG_QORIQ_CPUFREQ=y CONFIG_CPU_IDLE=y CONFIG_ARM_CPUIDLE=y @@ -781,7 +781,7 @@ CONFIG_MXS_DMA=y CONFIG_DMA_BCM2835=y CONFIG_DMA_OMAP=y CONFIG_QCOM_BAM_DMA=y -CONFIG_XILINX_VDMA=y +CONFIG_XILINX_DMA=y CONFIG_DMA_SUN6I=y CONFIG_STAGING=y CONFIG_SENSORS_ISL29018=y diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c index da3c0428507b..aef022a87c53 100644 --- a/arch/arm/crypto/aes-ce-glue.c +++ b/arch/arm/crypto/aes-ce-glue.c @@ -284,7 +284,7 @@ static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE); } - if (nbytes) { + if (walk.nbytes % AES_BLOCK_SIZE) { u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE; u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE; u8 __aligned(8) tail[AES_BLOCK_SIZE]; diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index e08d15184056..a8088290b778 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -22,9 +22,7 @@ #include <linux/io.h> #include <asm/barrier.h> - -#define __ACCESS_CP15(CRn, Op1, CRm, Op2) p15, Op1, %0, CRn, CRm, Op2 -#define __ACCESS_CP15_64(Op1, CRm) p15, Op1, %Q0, %R0, CRm +#include <asm/cp15.h> #define ICC_EOIR1 __ACCESS_CP15(c12, 0, c12, 1) #define ICC_DIR __ACCESS_CP15(c12, 0, c11, 1) @@ -34,6 +32,7 @@ #define ICC_CTLR __ACCESS_CP15(c12, 0, c12, 4) #define ICC_SRE __ACCESS_CP15(c12, 0, c12, 5) #define ICC_IGRPEN1 __ACCESS_CP15(c12, 0, c12, 7) +#define ICC_BPR1 __ACCESS_CP15(c12, 0, c12, 3) #define ICC_HSRE __ACCESS_CP15(c12, 4, c9, 5) @@ -98,65 +97,131 @@ #define ICH_AP1R2 __AP1Rx(2) #define ICH_AP1R3 __AP1Rx(3) +/* A32-to-A64 mappings used by VGIC save/restore */ + +#define CPUIF_MAP(a32, a64) \ +static inline void write_ ## a64(u32 val) \ +{ \ + write_sysreg(val, a32); \ +} \ +static inline u32 read_ ## a64(void) \ +{ \ + return read_sysreg(a32); \ +} \ + +#define CPUIF_MAP_LO_HI(a32lo, a32hi, a64) \ +static inline void write_ ## a64(u64 val) \ +{ \ + write_sysreg(lower_32_bits(val), a32lo);\ + write_sysreg(upper_32_bits(val), a32hi);\ +} \ +static inline u64 read_ ## a64(void) \ +{ \ + u64 val = read_sysreg(a32lo); \ + \ + val |= (u64)read_sysreg(a32hi) << 32; \ + \ + return val; \ +} + +CPUIF_MAP(ICH_HCR, ICH_HCR_EL2) +CPUIF_MAP(ICH_VTR, ICH_VTR_EL2) +CPUIF_MAP(ICH_MISR, ICH_MISR_EL2) +CPUIF_MAP(ICH_EISR, ICH_EISR_EL2) +CPUIF_MAP(ICH_ELSR, ICH_ELSR_EL2) +CPUIF_MAP(ICH_VMCR, ICH_VMCR_EL2) +CPUIF_MAP(ICH_AP0R3, ICH_AP0R3_EL2) +CPUIF_MAP(ICH_AP0R2, ICH_AP0R2_EL2) +CPUIF_MAP(ICH_AP0R1, ICH_AP0R1_EL2) +CPUIF_MAP(ICH_AP0R0, ICH_AP0R0_EL2) +CPUIF_MAP(ICH_AP1R3, ICH_AP1R3_EL2) +CPUIF_MAP(ICH_AP1R2, ICH_AP1R2_EL2) +CPUIF_MAP(ICH_AP1R1, ICH_AP1R1_EL2) +CPUIF_MAP(ICH_AP1R0, ICH_AP1R0_EL2) +CPUIF_MAP(ICC_HSRE, ICC_SRE_EL2) +CPUIF_MAP(ICC_SRE, ICC_SRE_EL1) + +CPUIF_MAP_LO_HI(ICH_LR15, ICH_LRC15, ICH_LR15_EL2) +CPUIF_MAP_LO_HI(ICH_LR14, ICH_LRC14, ICH_LR14_EL2) +CPUIF_MAP_LO_HI(ICH_LR13, ICH_LRC13, ICH_LR13_EL2) +CPUIF_MAP_LO_HI(ICH_LR12, ICH_LRC12, ICH_LR12_EL2) +CPUIF_MAP_LO_HI(ICH_LR11, ICH_LRC11, ICH_LR11_EL2) +CPUIF_MAP_LO_HI(ICH_LR10, ICH_LRC10, ICH_LR10_EL2) +CPUIF_MAP_LO_HI(ICH_LR9, ICH_LRC9, ICH_LR9_EL2) +CPUIF_MAP_LO_HI(ICH_LR8, ICH_LRC8, ICH_LR8_EL2) +CPUIF_MAP_LO_HI(ICH_LR7, ICH_LRC7, ICH_LR7_EL2) +CPUIF_MAP_LO_HI(ICH_LR6, ICH_LRC6, ICH_LR6_EL2) +CPUIF_MAP_LO_HI(ICH_LR5, ICH_LRC5, ICH_LR5_EL2) +CPUIF_MAP_LO_HI(ICH_LR4, ICH_LRC4, ICH_LR4_EL2) +CPUIF_MAP_LO_HI(ICH_LR3, ICH_LRC3, ICH_LR3_EL2) +CPUIF_MAP_LO_HI(ICH_LR2, ICH_LRC2, ICH_LR2_EL2) +CPUIF_MAP_LO_HI(ICH_LR1, ICH_LRC1, ICH_LR1_EL2) +CPUIF_MAP_LO_HI(ICH_LR0, ICH_LRC0, ICH_LR0_EL2) + +#define read_gicreg(r) read_##r() +#define write_gicreg(v, r) write_##r(v) + /* Low-level accessors */ static inline void gic_write_eoir(u32 irq) { - asm volatile("mcr " __stringify(ICC_EOIR1) : : "r" (irq)); + write_sysreg(irq, ICC_EOIR1); isb(); } static inline void gic_write_dir(u32 val) { - asm volatile("mcr " __stringify(ICC_DIR) : : "r" (val)); + write_sysreg(val, ICC_DIR); isb(); } static inline u32 gic_read_iar(void) { - u32 irqstat; + u32 irqstat = read_sysreg(ICC_IAR1); - asm volatile("mrc " __stringify(ICC_IAR1) : "=r" (irqstat)); dsb(sy); + return irqstat; } static inline void gic_write_pmr(u32 val) { - asm volatile("mcr " __stringify(ICC_PMR) : : "r" (val)); + write_sysreg(val, ICC_PMR); } static inline void gic_write_ctlr(u32 val) { - asm volatile("mcr " __stringify(ICC_CTLR) : : "r" (val)); + write_sysreg(val, ICC_CTLR); isb(); } static inline void gic_write_grpen1(u32 val) { - asm volatile("mcr " __stringify(ICC_IGRPEN1) : : "r" (val)); + write_sysreg(val, ICC_IGRPEN1); isb(); } static inline void gic_write_sgi1r(u64 val) { - asm volatile("mcrr " __stringify(ICC_SGI1R) : : "r" (val)); + write_sysreg(val, ICC_SGI1R); } static inline u32 gic_read_sre(void) { - u32 val; - - asm volatile("mrc " __stringify(ICC_SRE) : "=r" (val)); - return val; + return read_sysreg(ICC_SRE); } static inline void gic_write_sre(u32 val) { - asm volatile("mcr " __stringify(ICC_SRE) : : "r" (val)); + write_sysreg(val, ICC_SRE); isb(); } +static inline void gic_write_bpr1(u32 val) +{ + write_sysreg(val, ICC_BPR1); +} + /* * Even in 32bit systems that use LPAE, there is no guarantee that the I/O * interface provides true 64bit atomic accesses, so using strd/ldrd doesn't diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 4eaea2173bf8..68b06f9c65de 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -159,7 +159,11 @@ .endm .macro save_and_disable_irqs_notrace, oldcpsr +#ifdef CONFIG_CPU_V7M + mrs \oldcpsr, primask +#else mrs \oldcpsr, cpsr +#endif disable_irq_notrace .endm diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 9156fc303afd..bdd283bc5842 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -501,21 +501,4 @@ static inline void set_kernel_text_ro(void) { } void flush_uprobe_xol_access(struct page *page, unsigned long uaddr, void *kaddr, unsigned long len); -/** - * secure_flush_area - ensure coherency across the secure boundary - * @addr: virtual address - * @size: size of region - * - * Ensure that the specified area of memory is coherent across the secure - * boundary from the non-secure side. This is used when calling secure - * firmware where the secure firmware does not ensure coherency. - */ -static inline void secure_flush_area(const void *addr, size_t size) -{ - phys_addr_t phys = __pa(addr); - - __cpuc_flush_dcache_area((void *)addr, size); - outer_flush_range(phys, phys + size); -} - #endif diff --git a/arch/arm/include/asm/cachetype.h b/arch/arm/include/asm/cachetype.h index 7ea78144ae22..01509ae0bbec 100644 --- a/arch/arm/include/asm/cachetype.h +++ b/arch/arm/include/asm/cachetype.h @@ -56,4 +56,43 @@ static inline unsigned int __attribute__((pure)) cacheid_is(unsigned int mask) (~__CACHEID_NEVER & __CACHEID_ARCH_MIN & mask & cacheid); } +#define CSSELR_ICACHE 1 +#define CSSELR_DCACHE 0 + +#define CSSELR_L1 (0 << 1) +#define CSSELR_L2 (1 << 1) +#define CSSELR_L3 (2 << 1) +#define CSSELR_L4 (3 << 1) +#define CSSELR_L5 (4 << 1) +#define CSSELR_L6 (5 << 1) +#define CSSELR_L7 (6 << 1) + +#ifndef CONFIG_CPU_V7M +static inline void set_csselr(unsigned int cache_selector) +{ + asm volatile("mcr p15, 2, %0, c0, c0, 0" : : "r" (cache_selector)); +} + +static inline unsigned int read_ccsidr(void) +{ + unsigned int val; + + asm volatile("mrc p15, 1, %0, c0, c0, 0" : "=r" (val)); + return val; +} +#else /* CONFIG_CPU_V7M */ +#include <linux/io.h> +#include "asm/v7m.h" + +static inline void set_csselr(unsigned int cache_selector) +{ + writel(cache_selector, BASEADDR_V7M_SCB + V7M_SCB_CTR); +} + +static inline unsigned int read_ccsidr(void) +{ + return readl(BASEADDR_V7M_SCB + V7M_SCB_CCSIDR); +} +#endif + #endif diff --git a/arch/arm/include/asm/clocksource.h b/arch/arm/include/asm/clocksource.h new file mode 100644 index 000000000000..0b350a7e26f3 --- /dev/null +++ b/arch/arm/include/asm/clocksource.h @@ -0,0 +1,8 @@ +#ifndef _ASM_CLOCKSOURCE_H +#define _ASM_CLOCKSOURCE_H + +struct arch_clocksource_data { + bool vdso_direct; /* Usable for direct VDSO access? */ +}; + +#endif diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h index c3f11524f10c..dbdbce1b3a72 100644 --- a/arch/arm/include/asm/cp15.h +++ b/arch/arm/include/asm/cp15.h @@ -49,6 +49,21 @@ #ifdef CONFIG_CPU_CP15 +#define __ACCESS_CP15(CRn, Op1, CRm, Op2) \ + "mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32 +#define __ACCESS_CP15_64(Op1, CRm) \ + "mrrc", "mcrr", __stringify(p15, Op1, %Q0, %R0, CRm), u64 + +#define __read_sysreg(r, w, c, t) ({ \ + t __val; \ + asm volatile(r " " c : "=r" (__val)); \ + __val; \ +}) +#define read_sysreg(...) __read_sysreg(__VA_ARGS__) + +#define __write_sysreg(v, r, w, c, t) asm volatile(w " " c : : "r" ((t)(v))) +#define write_sysreg(v, ...) __write_sysreg(v, __VA_ARGS__) + extern unsigned long cr_alignment; /* defined in entry-armv.S */ static inline unsigned long get_cr(void) diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index 1ee94c716a7f..522b5feb4eaa 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -55,11 +55,13 @@ #define MPIDR_LEVEL_BITS 8 #define MPIDR_LEVEL_MASK ((1 << MPIDR_LEVEL_BITS) - 1) +#define MPIDR_LEVEL_SHIFT(level) (MPIDR_LEVEL_BITS * level) #define MPIDR_AFFINITY_LEVEL(mpidr, level) \ ((mpidr >> (MPIDR_LEVEL_BITS * level)) & MPIDR_LEVEL_MASK) #define ARM_CPU_IMP_ARM 0x41 +#define ARM_CPU_IMP_DEC 0x44 #define ARM_CPU_IMP_INTEL 0x69 /* ARM implemented processors */ @@ -76,6 +78,17 @@ #define ARM_CPU_PART_CORTEX_A15 0x4100c0f0 #define ARM_CPU_PART_MASK 0xff00fff0 +/* DEC implemented cores */ +#define ARM_CPU_PART_SA1100 0x4400a110 + +/* Intel implemented cores */ +#define ARM_CPU_PART_SA1110 0x6900b110 +#define ARM_CPU_REV_SA1110_A0 0 +#define ARM_CPU_REV_SA1110_B0 4 +#define ARM_CPU_REV_SA1110_B1 5 +#define ARM_CPU_REV_SA1110_B2 6 +#define ARM_CPU_REV_SA1110_B4 8 + #define ARM_CPU_XSCALE_ARCH_MASK 0xe000 #define ARM_CPU_XSCALE_ARCH_V1 0x2000 #define ARM_CPU_XSCALE_ARCH_V2 0x4000 @@ -152,6 +165,11 @@ static inline unsigned int __attribute_const__ read_cpuid_id(void) return read_cpuid(CPUID_ID); } +static inline unsigned int __attribute_const__ read_cpuid_cachetype(void) +{ + return read_cpuid(CPUID_CACHETYPE); +} + #elif defined(CONFIG_CPU_V7M) static inline unsigned int __attribute_const__ read_cpuid_id(void) @@ -159,6 +177,11 @@ static inline unsigned int __attribute_const__ read_cpuid_id(void) return readl(BASEADDR_V7M_SCB + V7M_SCB_CPUID); } +static inline unsigned int __attribute_const__ read_cpuid_cachetype(void) +{ + return readl(BASEADDR_V7M_SCB + V7M_SCB_CTR); +} + #else /* ifdef CONFIG_CPU_CP15 / elif defined(CONFIG_CPU_V7M) */ static inline unsigned int __attribute_const__ read_cpuid_id(void) @@ -173,6 +196,11 @@ static inline unsigned int __attribute_const__ read_cpuid_implementor(void) return (read_cpuid_id() & 0xFF000000) >> 24; } +static inline unsigned int __attribute_const__ read_cpuid_revision(void) +{ + return read_cpuid_id() & 0x0000000f; +} + /* * The CPU part number is meaningless without referring to the CPU * implementer: implementers are free to define their own part numbers @@ -193,11 +221,6 @@ static inline unsigned int __attribute_const__ xscale_cpu_arch_version(void) return read_cpuid_id() & ARM_CPU_XSCALE_ARCH_MASK; } -static inline unsigned int __attribute_const__ read_cpuid_cachetype(void) -{ - return read_cpuid(CPUID_CACHETYPE); -} - static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void) { return read_cpuid(CPUID_TCM); @@ -208,6 +231,10 @@ static inline unsigned int __attribute_const__ read_cpuid_mpidr(void) return read_cpuid(CPUID_MPIDR); } +/* StrongARM-11x0 CPUs */ +#define cpu_is_sa1100() (read_cpuid_part() == ARM_CPU_PART_SA1100) +#define cpu_is_sa1110() (read_cpuid_part() == ARM_CPU_PART_SA1110) + /* * Intel's XScale3 core supports some v6 features (supersections, L2) * but advertises itself as v5 as it does not support the v6 ISA. For diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h index b7a428154355..b1ce037e4380 100644 --- a/arch/arm/include/asm/delay.h +++ b/arch/arm/include/asm/delay.h @@ -10,7 +10,7 @@ #include <asm/param.h> /* HZ */ #define MAX_UDELAY_MS 2 -#define UDELAY_MULT UL(2047 * HZ + 483648 * HZ / 1000000) +#define UDELAY_MULT UL(2147 * HZ + 483648 * HZ / 1000000) #define UDELAY_SHIFT 31 #ifndef __ASSEMBLY__ diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index d009f7911ffc..bf02dbd9ccda 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -111,7 +111,7 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr) /* The ARM override for dma_max_pfn() */ static inline unsigned long dma_max_pfn(struct device *dev) { - return PHYS_PFN_OFFSET + dma_to_pfn(dev, *dev->dma_mask); + return dma_to_pfn(dev, *dev->dma_mask); } #define dma_max_pfn(dev) dma_max_pfn(dev) diff --git a/arch/arm/include/asm/flat.h b/arch/arm/include/asm/flat.h index e847d23351ed..acf1d14b89a6 100644 --- a/arch/arm/include/asm/flat.h +++ b/arch/arm/include/asm/flat.h @@ -8,8 +8,9 @@ #define flat_argvp_envp_on_stack() 1 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, persistent) ((void)persistent,get_unaligned(rp)) -#define flat_put_addr_at_rp(rp, val, relval) put_unaligned(val,rp) +#define flat_get_addr_from_rp(rp, relval, flags, persistent) \ + ({ unsigned long __val; __get_user_unaligned(__val, rp); __val; }) +#define flat_put_addr_at_rp(rp, val, relval) __put_user_unaligned(val, rp) #define flat_get_relocate_addr(rel) (rel) #define flat_set_persistent(relval, p) 0 diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h index cab07f69382d..01c3d92624e5 100644 --- a/arch/arm/include/asm/glue-cache.h +++ b/arch/arm/include/asm/glue-cache.h @@ -118,11 +118,7 @@ #endif #if defined(CONFIG_CPU_V7M) -# ifdef _CACHE # define MULTI_CACHE 1 -# else -# define _CACHE nop -# endif #endif #if !defined(_CACHE) && !defined(MULTI_CACHE) diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h index 3a5ec1c25659..736292b42fca 100644 --- a/arch/arm/include/asm/hardware/cache-l2x0.h +++ b/arch/arm/include/asm/hardware/cache-l2x0.h @@ -87,6 +87,15 @@ #define L310_CACHE_ID_RTL_R3P2 0x08 #define L310_CACHE_ID_RTL_R3P3 0x09 +#define L2X0_EVENT_CNT_CTRL_ENABLE BIT(0) + +#define L2X0_EVENT_CNT_CFG_SRC_SHIFT 2 +#define L2X0_EVENT_CNT_CFG_SRC_MASK 0xf +#define L2X0_EVENT_CNT_CFG_SRC_DISABLED 0 +#define L2X0_EVENT_CNT_CFG_INT_DISABLED 0 +#define L2X0_EVENT_CNT_CFG_INT_INCR 1 +#define L2X0_EVENT_CNT_CFG_INT_OVERFLOW 2 + /* L2C auxiliary control register - bits common to L2C-210/220/310 */ #define L2C_AUX_CTRL_WAY_SIZE_SHIFT 17 #define L2C_AUX_CTRL_WAY_SIZE_MASK (7 << 17) @@ -157,6 +166,16 @@ static inline int l2x0_of_init(u32 aux_val, u32 aux_mask) } #endif +#ifdef CONFIG_CACHE_L2X0_PMU +void l2x0_pmu_register(void __iomem *base, u32 part); +void l2x0_pmu_suspend(void); +void l2x0_pmu_resume(void); +#else +static inline void l2x0_pmu_register(void __iomem *base, u32 part) {} +static inline void l2x0_pmu_suspend(void) {} +static inline void l2x0_pmu_resume(void) {} +#endif + struct l2x0_regs { unsigned long phy_base; unsigned long aux_ctrl; diff --git a/arch/arm/include/asm/hardware/sa1111.h b/arch/arm/include/asm/hardware/sa1111.h index 7c2bbc7f0be1..8979fa3bbf2d 100644 --- a/arch/arm/include/asm/hardware/sa1111.h +++ b/arch/arm/include/asm/hardware/sa1111.h @@ -420,7 +420,7 @@ struct sa1111_dev { u64 dma_mask; }; -#define SA1111_DEV(_d) container_of((_d), struct sa1111_dev, dev) +#define to_sa1111_device(x) container_of(x, struct sa1111_dev, dev) #define sa1111_get_drvdata(d) dev_get_drvdata(&(d)->dev) #define sa1111_set_drvdata(d,p) dev_set_drvdata(&(d)->dev, p) @@ -446,6 +446,8 @@ struct sa1111_driver { int sa1111_enable_device(struct sa1111_dev *); void sa1111_disable_device(struct sa1111_dev *); +int sa1111_get_irq(struct sa1111_dev *, unsigned num); + unsigned int sa1111_pll_clock(struct sa1111_dev *); #define SA1111_AUDIO_ACLINK 0 diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h index 8e427c7b4425..afcaf8bf971b 100644 --- a/arch/arm/include/asm/hw_breakpoint.h +++ b/arch/arm/include/asm/hw_breakpoint.h @@ -114,7 +114,6 @@ struct notifier_block; struct perf_event; struct pmu; -extern struct pmu perf_ops_bp; extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, int *gen_len, int *gen_type); extern int arch_check_bp_in_kernelspace(struct perf_event *bp); diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h index 58faff5f1eb2..d7ea6bcb29bf 100644 --- a/arch/arm/include/asm/kvm_asm.h +++ b/arch/arm/include/asm/kvm_asm.h @@ -21,6 +21,10 @@ #include <asm/virt.h> +#define ARM_EXIT_WITH_ABORT_BIT 31 +#define ARM_EXCEPTION_CODE(x) ((x) & ~(1U << ARM_EXIT_WITH_ABORT_BIT)) +#define ARM_ABORT_PENDING(x) !!((x) & (1U << ARM_EXIT_WITH_ABORT_BIT)) + #define ARM_EXCEPTION_RESET 0 #define ARM_EXCEPTION_UNDEFINED 1 #define ARM_EXCEPTION_SOFTWARE 2 @@ -68,6 +72,9 @@ extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); extern void __init_stage2_translation(void); extern void __kvm_hyp_reset(unsigned long); + +extern u64 __vgic_v3_get_ich_vtr_el2(void); +extern void __vgic_v3_init_lrs(void); #endif #endif /* __ARM_KVM_ASM_H__ */ diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index ee5328fc4b06..9a8a45aaf19a 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -40,18 +40,29 @@ static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, *vcpu_reg(vcpu, reg_num) = val; } -bool kvm_condition_valid(struct kvm_vcpu *vcpu); -void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr); +bool kvm_condition_valid32(const struct kvm_vcpu *vcpu); +void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr); void kvm_inject_undefined(struct kvm_vcpu *vcpu); +void kvm_inject_vabt(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +static inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu) +{ + return kvm_condition_valid32(vcpu); +} + +static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) +{ + kvm_skip_instr32(vcpu, is_wide_instr); +} + static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) { vcpu->arch.hcr = HCR_GUEST_MASK; } -static inline unsigned long vcpu_get_hcr(struct kvm_vcpu *vcpu) +static inline unsigned long vcpu_get_hcr(const struct kvm_vcpu *vcpu) { return vcpu->arch.hcr; } @@ -61,7 +72,7 @@ static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr) vcpu->arch.hcr = hcr; } -static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu) +static inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu) { return 1; } @@ -71,9 +82,9 @@ static inline unsigned long *vcpu_pc(struct kvm_vcpu *vcpu) return &vcpu->arch.ctxt.gp_regs.usr_regs.ARM_pc; } -static inline unsigned long *vcpu_cpsr(struct kvm_vcpu *vcpu) +static inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu) { - return &vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr; + return (unsigned long *)&vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr; } static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) @@ -93,11 +104,21 @@ static inline bool vcpu_mode_priv(struct kvm_vcpu *vcpu) return cpsr_mode > USR_MODE;; } -static inline u32 kvm_vcpu_get_hsr(struct kvm_vcpu *vcpu) +static inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu) { return vcpu->arch.fault.hsr; } +static inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) +{ + u32 hsr = kvm_vcpu_get_hsr(vcpu); + + if (hsr & HSR_CV) + return (hsr & HSR_COND) >> HSR_COND_SHIFT; + + return -1; +} + static inline unsigned long kvm_vcpu_get_hfar(struct kvm_vcpu *vcpu) { return vcpu->arch.fault.hxfar; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index de338d93d11b..2d19e02d03fd 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -39,7 +39,12 @@ #include <kvm/arm_vgic.h> + +#ifdef CONFIG_ARM_GIC_V3 +#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS +#else #define KVM_MAX_VCPUS VGIC_V2_MAX_CPUS +#endif #define KVM_REQ_VCPU_EXIT 8 @@ -183,15 +188,15 @@ struct kvm_vcpu_arch { }; struct kvm_vm_stat { - u32 remote_tlb_flush; + ulong remote_tlb_flush; }; struct kvm_vcpu_stat { - u32 halt_successful_poll; - u32 halt_attempted_poll; - u32 halt_poll_invalid; - u32 halt_wakeup; - u32 hvc_exit_stat; + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_poll_invalid; + u64 halt_wakeup; + u64 hvc_exit_stat; u64 wfe_exit_stat; u64 wfi_exit_stat; u64 mmio_exit_user; diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h index 6eaff28f2ff3..343135ede5fa 100644 --- a/arch/arm/include/asm/kvm_hyp.h +++ b/arch/arm/include/asm/kvm_hyp.h @@ -20,28 +20,15 @@ #include <linux/compiler.h> #include <linux/kvm_host.h> +#include <asm/cp15.h> #include <asm/kvm_mmu.h> #include <asm/vfp.h> #define __hyp_text __section(.hyp.text) notrace -#define __ACCESS_CP15(CRn, Op1, CRm, Op2) \ - "mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32 -#define __ACCESS_CP15_64(Op1, CRm) \ - "mrrc", "mcrr", __stringify(p15, Op1, %Q0, %R0, CRm), u64 #define __ACCESS_VFP(CRn) \ "mrc", "mcr", __stringify(p10, 7, %0, CRn, cr0, 0), u32 -#define __write_sysreg(v, r, w, c, t) asm volatile(w " " c : : "r" ((t)(v))) -#define write_sysreg(v, ...) __write_sysreg(v, __VA_ARGS__) - -#define __read_sysreg(r, w, c, t) ({ \ - t __val; \ - asm volatile(r " " c : "=r" (__val)); \ - __val; \ -}) -#define read_sysreg(...) __read_sysreg(__VA_ARGS__) - #define write_special(v, r) \ asm volatile("msr " __stringify(r) ", %0" : : "r" (v)) #define read_special(r) ({ \ @@ -119,6 +106,9 @@ void __vgic_v2_restore_state(struct kvm_vcpu *vcpu); void __sysreg_save_state(struct kvm_cpu_context *ctxt); void __sysreg_restore_state(struct kvm_cpu_context *ctxt); +void __vgic_v3_save_state(struct kvm_vcpu *vcpu); +void __vgic_v3_restore_state(struct kvm_vcpu *vcpu); + void asmlinkage __vfp_save_state(struct vfp_hard_struct *vfp); void asmlinkage __vfp_restore_state(struct vfp_hard_struct *vfp); static inline bool __vfp_enabled(void) diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 3bb803d6814b..74a44727f8e1 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -63,37 +63,13 @@ void kvm_clear_hyp_idmap(void); static inline void kvm_set_pmd(pmd_t *pmd, pmd_t new_pmd) { *pmd = new_pmd; - flush_pmd_entry(pmd); + dsb(ishst); } static inline void kvm_set_pte(pte_t *pte, pte_t new_pte) { *pte = new_pte; - /* - * flush_pmd_entry just takes a void pointer and cleans the necessary - * cache entries, so we can reuse the function for ptes. - */ - flush_pmd_entry(pte); -} - -static inline void kvm_clean_pgd(pgd_t *pgd) -{ - clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t)); -} - -static inline void kvm_clean_pmd(pmd_t *pmd) -{ - clean_dcache_area(pmd, PTRS_PER_PMD * sizeof(pmd_t)); -} - -static inline void kvm_clean_pmd_entry(pmd_t *pmd) -{ - clean_pmd_entry(pmd); -} - -static inline void kvm_clean_pte(pte_t *pte) -{ - clean_pte_table(pte); + dsb(ishst); } static inline pte_t kvm_s2pte_mkwrite(pte_t pte) diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 31c07a2cc100..76cbd9c674df 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -159,13 +159,8 @@ * PFNs are used to describe any physical page; this means * PFN 0 == physical address 0. */ -#if defined(__virt_to_phys) -#define PHYS_OFFSET PLAT_PHYS_OFFSET -#define PHYS_PFN_OFFSET ((unsigned long)(PHYS_OFFSET >> PAGE_SHIFT)) - -#define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT) -#elif defined(CONFIG_ARM_PATCH_PHYS_VIRT) +#if defined(CONFIG_ARM_PATCH_PHYS_VIRT) /* * Constants used to force the right instruction encodings and shifts @@ -182,10 +177,6 @@ extern const void *__pv_table_begin, *__pv_table_end; #define PHYS_OFFSET ((phys_addr_t)__pv_phys_pfn_offset << PAGE_SHIFT) #define PHYS_PFN_OFFSET (__pv_phys_pfn_offset) -#define virt_to_pfn(kaddr) \ - ((((unsigned long)(kaddr) - PAGE_OFFSET) >> PAGE_SHIFT) + \ - PHYS_PFN_OFFSET) - #define __pv_stub(from,to,instr,type) \ __asm__("@ __pv_stub\n" \ "1: " instr " %0, %1, %2\n" \ @@ -257,12 +248,12 @@ static inline unsigned long __phys_to_virt(phys_addr_t x) return x - PHYS_OFFSET + PAGE_OFFSET; } +#endif + #define virt_to_pfn(kaddr) \ ((((unsigned long)(kaddr) - PAGE_OFFSET) >> PAGE_SHIFT) + \ PHYS_PFN_OFFSET) -#endif - /* * These are *only* valid on the kernel direct mapped RAM memory. * Note: Drivers should NOT use these. They are the wrong diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h index e358b7966c06..464748b9fd7d 100644 --- a/arch/arm/include/asm/module.h +++ b/arch/arm/include/asm/module.h @@ -23,10 +23,8 @@ struct mod_arch_specific { struct unwind_table *unwind[ARM_SEC_MAX]; #endif #ifdef CONFIG_ARM_MODULE_PLTS - struct elf32_shdr *core_plt; - struct elf32_shdr *init_plt; - int core_plt_count; - int init_plt_count; + struct elf32_shdr *plt; + int plt_count; #endif }; diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h index d0131ee6f6af..3f82e9da7cec 100644 --- a/arch/arm/include/asm/pgtable-2level-hwdef.h +++ b/arch/arm/include/asm/pgtable-2level-hwdef.h @@ -47,6 +47,7 @@ #define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) #define PMD_SECT_MINICACHE (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE) #define PMD_SECT_WBWA (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) +#define PMD_SECT_CACHE_MASK (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) #define PMD_SECT_NONSHARED_DEV (PMD_SECT_TEX(2)) /* diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h index f8f1cff62065..4cd664abfcd3 100644 --- a/arch/arm/include/asm/pgtable-3level-hwdef.h +++ b/arch/arm/include/asm/pgtable-3level-hwdef.h @@ -62,6 +62,7 @@ #define PMD_SECT_WT (_AT(pmdval_t, 2) << 2) /* normal inner write-through */ #define PMD_SECT_WB (_AT(pmdval_t, 3) << 2) /* normal inner write-back */ #define PMD_SECT_WBWA (_AT(pmdval_t, 7) << 2) /* normal inner write-alloc */ +#define PMD_SECT_CACHE_MASK (_AT(pmdval_t, 7) << 2) /* * + Level 3 descriptor (PTE) diff --git a/arch/arm/include/asm/v7m.h b/arch/arm/include/asm/v7m.h index 615781c61627..1fd775c1bc5d 100644 --- a/arch/arm/include/asm/v7m.h +++ b/arch/arm/include/asm/v7m.h @@ -24,6 +24,9 @@ #define V7M_SCB_CCR 0x14 #define V7M_SCB_CCR_STKALIGN (1 << 9) +#define V7M_SCB_CCR_DC (1 << 16) +#define V7M_SCB_CCR_IC (1 << 17) +#define V7M_SCB_CCR_BP (1 << 18) #define V7M_SCB_SHPR2 0x1c #define V7M_SCB_SHPR3 0x20 @@ -47,6 +50,25 @@ #define EXC_RET_STACK_MASK 0x00000004 #define EXC_RET_THREADMODE_PROCESSSTACK 0xfffffffd +/* Cache related definitions */ + +#define V7M_SCB_CLIDR 0x78 /* Cache Level ID register */ +#define V7M_SCB_CTR 0x7c /* Cache Type register */ +#define V7M_SCB_CCSIDR 0x80 /* Cache size ID register */ +#define V7M_SCB_CSSELR 0x84 /* Cache size selection register */ + +/* Cache opeartions */ +#define V7M_SCB_ICIALLU 0x250 /* I-cache invalidate all to PoU */ +#define V7M_SCB_ICIMVAU 0x258 /* I-cache invalidate by MVA to PoU */ +#define V7M_SCB_DCIMVAC 0x25c /* D-cache invalidate by MVA to PoC */ +#define V7M_SCB_DCISW 0x260 /* D-cache invalidate by set-way */ +#define V7M_SCB_DCCMVAU 0x264 /* D-cache clean by MVA to PoU */ +#define V7M_SCB_DCCMVAC 0x268 /* D-cache clean by MVA to PoC */ +#define V7M_SCB_DCCSW 0x26c /* D-cache clean by set-way */ +#define V7M_SCB_DCCIMVAC 0x270 /* D-cache clean and invalidate by MVA to PoC */ +#define V7M_SCB_DCCISW 0x274 /* D-cache clean and invalidate by set-way */ +#define V7M_SCB_BPIALL 0x278 /* D-cache clean and invalidate by set-way */ + #ifndef __ASSEMBLY__ enum reboot_mode; diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index a2b3eb313a25..b38c10c73579 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -84,6 +84,13 @@ struct kvm_regs { #define KVM_VGIC_V2_DIST_SIZE 0x1000 #define KVM_VGIC_V2_CPU_SIZE 0x2000 +/* Supported VGICv3 address types */ +#define KVM_VGIC_V3_ADDR_TYPE_DIST 2 +#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3 + +#define KVM_VGIC_V3_DIST_SIZE SZ_64K +#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K) + #define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */ #define KVM_ARM_VCPU_PSCI_0_2 1 /* CPU uses PSCI v0.2 */ diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c index 7dccc964d75f..a3308ad1a024 100644 --- a/arch/arm/kernel/cpuidle.c +++ b/arch/arm/kernel/cpuidle.c @@ -19,7 +19,7 @@ extern struct of_cpuidle_method __cpuidle_method_of_table[]; static const struct of_cpuidle_method __cpuidle_method_of_table_sentinel __used __section(__cpuidle_method_of_table_end); -static struct cpuidle_ops cpuidle_ops[NR_CPUS]; +static struct cpuidle_ops cpuidle_ops[NR_CPUS] __ro_after_init; /** * arm_cpuidle_simple_enter() - a wrapper to cpu_do_idle() diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c index 40ecd5f514a2..f676febbb270 100644 --- a/arch/arm/kernel/devtree.c +++ b/arch/arm/kernel/devtree.c @@ -88,6 +88,8 @@ void __init arm_dt_init_cpu_maps(void) return; for_each_child_of_node(cpus, cpu) { + const __be32 *cell; + int prop_bytes; u32 hwid; if (of_node_cmp(cpu->type, "cpu")) @@ -99,7 +101,8 @@ void __init arm_dt_init_cpu_maps(void) * properties is considered invalid to build the * cpu_logical_map. */ - if (of_property_read_u32(cpu, "reg", &hwid)) { + cell = of_get_property(cpu, "reg", &prop_bytes); + if (!cell || prop_bytes < sizeof(*cell)) { pr_debug(" * %s missing reg property\n", cpu->full_name); of_node_put(cpu); @@ -107,10 +110,15 @@ void __init arm_dt_init_cpu_maps(void) } /* - * 8 MSBs must be set to 0 in the DT since the reg property + * Bits n:24 must be set to 0 in the DT since the reg property * defines the MPIDR[23:0]. */ - if (hwid & ~MPIDR_HWID_BITMASK) { + do { + hwid = be32_to_cpu(*cell++); + prop_bytes -= sizeof(*cell); + } while (!hwid && prop_bytes > 0); + + if (prop_bytes || (hwid & ~MPIDR_HWID_BITMASK)) { of_node_put(cpu); return; } diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index 709ee1d6d4df..3f1759411d51 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -218,7 +218,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, } err = ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer); + frame_pointer, NULL); if (err == -EBUSY) { *parent = old; return; diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index fb1a69eb49c1..6b4eb27b8758 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -158,7 +158,21 @@ __after_proc_init: bic r0, r0, #CR_V #endif mcr p15, 0, r0, c1, c0, 0 @ write control reg -#endif /* CONFIG_CPU_CP15 */ +#elif defined (CONFIG_CPU_V7M) + /* For V7M systems we want to modify the CCR similarly to the SCTLR */ +#ifdef CONFIG_CPU_DCACHE_DISABLE + bic r0, r0, #V7M_SCB_CCR_DC +#endif +#ifdef CONFIG_CPU_BPREDICT_DISABLE + bic r0, r0, #V7M_SCB_CCR_BP +#endif +#ifdef CONFIG_CPU_ICACHE_DISABLE + bic r0, r0, #V7M_SCB_CCR_IC +#endif + movw r3, #:lower16:(BASEADDR_V7M_SCB + V7M_SCB_CCR) + movt r3, #:upper16:(BASEADDR_V7M_SCB + V7M_SCB_CCR) + str r0, [r3] +#endif /* CONFIG_CPU_CP15 elif CONFIG_CPU_V7M */ ret lr ENDPROC(__after_proc_init) .ltorg diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S index 0b1e4a93d67e..15d073ae5da2 100644 --- a/arch/arm/kernel/hyp-stub.S +++ b/arch/arm/kernel/hyp-stub.S @@ -142,6 +142,19 @@ ARM_BE8(orr r7, r7, #(1 << 25)) @ HSCTLR.EE and r7, #0x1f @ Preserve HPMN mcr p15, 4, r7, c1, c1, 1 @ HDCR + @ Make sure NS-SVC is initialised appropriately + mrc p15, 0, r7, c1, c0, 0 @ SCTLR + orr r7, #(1 << 5) @ CP15 barriers enabled + bic r7, #(3 << 7) @ Clear SED/ITD for v8 (RES0 for v7) + bic r7, #(3 << 19) @ WXN and UWXN disabled + mcr p15, 0, r7, c1, c0, 0 @ SCTLR + + mrc p15, 0, r7, c0, c0, 0 @ MIDR + mcr p15, 4, r7, c0, c0, 0 @ VPIDR + + mrc p15, 0, r7, c0, c0, 5 @ MPIDR + mcr p15, 4, r7, c0, c0, 5 @ VMPIDR + #if !defined(ZIMAGE) && defined(CONFIG_ARM_ARCH_TIMER) @ make CNTP_* and CNTPCT accessible from PL1 mrc p15, 0, r7, c0, c1, 1 @ ID_PFR1 diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c index 0c7efc3446c0..3a5cba90c971 100644 --- a/arch/arm/kernel/module-plts.c +++ b/arch/arm/kernel/module-plts.c @@ -9,6 +9,7 @@ #include <linux/elf.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/sort.h> #include <asm/cache.h> #include <asm/opcodes.h> @@ -30,154 +31,198 @@ struct plt_entries { u32 lit[PLT_ENT_COUNT]; }; -static bool in_init(const struct module *mod, u32 addr) +u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val) { - return addr - (u32)mod->init_layout.base < mod->init_layout.size; + struct plt_entries *plt = (struct plt_entries *)mod->arch.plt->sh_addr; + int idx = 0; + + /* + * Look for an existing entry pointing to 'val'. Given that the + * relocations are sorted, this will be the last entry we allocated. + * (if one exists). + */ + if (mod->arch.plt_count > 0) { + plt += (mod->arch.plt_count - 1) / PLT_ENT_COUNT; + idx = (mod->arch.plt_count - 1) % PLT_ENT_COUNT; + + if (plt->lit[idx] == val) + return (u32)&plt->ldr[idx]; + + idx = (idx + 1) % PLT_ENT_COUNT; + if (!idx) + plt++; + } + + mod->arch.plt_count++; + BUG_ON(mod->arch.plt_count * PLT_ENT_SIZE > mod->arch.plt->sh_size); + + if (!idx) + /* Populate a new set of entries */ + *plt = (struct plt_entries){ + { [0 ... PLT_ENT_COUNT - 1] = PLT_ENT_LDR, }, + { val, } + }; + else + plt->lit[idx] = val; + + return (u32)&plt->ldr[idx]; } -u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val) +#define cmp_3way(a,b) ((a) < (b) ? -1 : (a) > (b)) + +static int cmp_rel(const void *a, const void *b) { - struct plt_entries *plt, *plt_end; - int c, *count; - - if (in_init(mod, loc)) { - plt = (void *)mod->arch.init_plt->sh_addr; - plt_end = (void *)plt + mod->arch.init_plt->sh_size; - count = &mod->arch.init_plt_count; - } else { - plt = (void *)mod->arch.core_plt->sh_addr; - plt_end = (void *)plt + mod->arch.core_plt->sh_size; - count = &mod->arch.core_plt_count; - } + const Elf32_Rel *x = a, *y = b; + int i; - /* Look for an existing entry pointing to 'val' */ - for (c = *count; plt < plt_end; c -= PLT_ENT_COUNT, plt++) { - int i; - - if (!c) { - /* Populate a new set of entries */ - *plt = (struct plt_entries){ - { [0 ... PLT_ENT_COUNT - 1] = PLT_ENT_LDR, }, - { val, } - }; - ++*count; - return (u32)plt->ldr; - } - for (i = 0; i < PLT_ENT_COUNT; i++) { - if (!plt->lit[i]) { - plt->lit[i] = val; - ++*count; - } - if (plt->lit[i] == val) - return (u32)&plt->ldr[i]; - } + /* sort by type and symbol index */ + i = cmp_3way(ELF32_R_TYPE(x->r_info), ELF32_R_TYPE(y->r_info)); + if (i == 0) + i = cmp_3way(ELF32_R_SYM(x->r_info), ELF32_R_SYM(y->r_info)); + return i; +} + +static bool is_zero_addend_relocation(Elf32_Addr base, const Elf32_Rel *rel) +{ + u32 *tval = (u32 *)(base + rel->r_offset); + + /* + * Do a bitwise compare on the raw addend rather than fully decoding + * the offset and doing an arithmetic comparison. + * Note that a zero-addend jump/call relocation is encoded taking the + * PC bias into account, i.e., -8 for ARM and -4 for Thumb2. + */ + switch (ELF32_R_TYPE(rel->r_info)) { + u16 upper, lower; + + case R_ARM_THM_CALL: + case R_ARM_THM_JUMP24: + upper = __mem_to_opcode_thumb16(((u16 *)tval)[0]); + lower = __mem_to_opcode_thumb16(((u16 *)tval)[1]); + + return (upper & 0x7ff) == 0x7ff && (lower & 0x2fff) == 0x2ffe; + + case R_ARM_CALL: + case R_ARM_PC24: + case R_ARM_JUMP24: + return (__mem_to_opcode_arm(*tval) & 0xffffff) == 0xfffffe; } BUG(); } -static int duplicate_rel(Elf32_Addr base, const Elf32_Rel *rel, int num, - u32 mask) +static bool duplicate_rel(Elf32_Addr base, const Elf32_Rel *rel, int num) { - u32 *loc1, *loc2; - int i; + const Elf32_Rel *prev; - for (i = 0; i < num; i++) { - if (rel[i].r_info != rel[num].r_info) - continue; + /* + * Entries are sorted by type and symbol index. That means that, + * if a duplicate entry exists, it must be in the preceding + * slot. + */ + if (!num) + return false; - /* - * Identical relocation types against identical symbols can - * still result in different PLT entries if the addend in the - * place is different. So resolve the target of the relocation - * to compare the values. - */ - loc1 = (u32 *)(base + rel[i].r_offset); - loc2 = (u32 *)(base + rel[num].r_offset); - if (((*loc1 ^ *loc2) & mask) == 0) - return 1; - } - return 0; + prev = rel + num - 1; + return cmp_rel(rel + num, prev) == 0 && + is_zero_addend_relocation(base, prev); } /* Count how many PLT entries we may need */ -static unsigned int count_plts(Elf32_Addr base, const Elf32_Rel *rel, int num) +static unsigned int count_plts(const Elf32_Sym *syms, Elf32_Addr base, + const Elf32_Rel *rel, int num) { unsigned int ret = 0; + const Elf32_Sym *s; int i; - /* - * Sure, this is order(n^2), but it's usually short, and not - * time critical - */ - for (i = 0; i < num; i++) + for (i = 0; i < num; i++) { switch (ELF32_R_TYPE(rel[i].r_info)) { case R_ARM_CALL: case R_ARM_PC24: case R_ARM_JUMP24: - if (!duplicate_rel(base, rel, i, - __opcode_to_mem_arm(0x00ffffff))) - ret++; - break; -#ifdef CONFIG_THUMB2_KERNEL case R_ARM_THM_CALL: case R_ARM_THM_JUMP24: - if (!duplicate_rel(base, rel, i, - __opcode_to_mem_thumb32(0x07ff2fff))) + /* + * We only have to consider branch targets that resolve + * to undefined symbols. This is not simply a heuristic, + * it is a fundamental limitation, since the PLT itself + * is part of the module, and needs to be within range + * as well, so modules can never grow beyond that limit. + */ + s = syms + ELF32_R_SYM(rel[i].r_info); + if (s->st_shndx != SHN_UNDEF) + break; + + /* + * Jump relocations with non-zero addends against + * undefined symbols are supported by the ELF spec, but + * do not occur in practice (e.g., 'jump n bytes past + * the entry point of undefined function symbol f'). + * So we need to support them, but there is no need to + * take them into consideration when trying to optimize + * this code. So let's only check for duplicates when + * the addend is zero. + */ + if (!is_zero_addend_relocation(base, rel + i) || + !duplicate_rel(base, rel, i)) ret++; -#endif } + } return ret; } int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings, struct module *mod) { - unsigned long core_plts = 0, init_plts = 0; + unsigned long plts = 0; Elf32_Shdr *s, *sechdrs_end = sechdrs + ehdr->e_shnum; + Elf32_Sym *syms = NULL; /* * To store the PLTs, we expand the .text section for core module code - * and the .init.text section for initialization code. + * and for initialization code. */ - for (s = sechdrs; s < sechdrs_end; ++s) - if (strcmp(".core.plt", secstrings + s->sh_name) == 0) - mod->arch.core_plt = s; - else if (strcmp(".init.plt", secstrings + s->sh_name) == 0) - mod->arch.init_plt = s; - - if (!mod->arch.core_plt || !mod->arch.init_plt) { - pr_err("%s: sections missing\n", mod->name); + for (s = sechdrs; s < sechdrs_end; ++s) { + if (strcmp(".plt", secstrings + s->sh_name) == 0) + mod->arch.plt = s; + else if (s->sh_type == SHT_SYMTAB) + syms = (Elf32_Sym *)s->sh_addr; + } + + if (!mod->arch.plt) { + pr_err("%s: module PLT section missing\n", mod->name); + return -ENOEXEC; + } + if (!syms) { + pr_err("%s: module symtab section missing\n", mod->name); return -ENOEXEC; } for (s = sechdrs + 1; s < sechdrs_end; ++s) { - const Elf32_Rel *rels = (void *)ehdr + s->sh_offset; + Elf32_Rel *rels = (void *)ehdr + s->sh_offset; int numrels = s->sh_size / sizeof(Elf32_Rel); Elf32_Shdr *dstsec = sechdrs + s->sh_info; if (s->sh_type != SHT_REL) continue; - if (strstr(secstrings + s->sh_name, ".init")) - init_plts += count_plts(dstsec->sh_addr, rels, numrels); - else - core_plts += count_plts(dstsec->sh_addr, rels, numrels); + /* ignore relocations that operate on non-exec sections */ + if (!(dstsec->sh_flags & SHF_EXECINSTR)) + continue; + + /* sort by type and symbol index */ + sort(rels, numrels, sizeof(Elf32_Rel), cmp_rel, NULL); + + plts += count_plts(syms, dstsec->sh_addr, rels, numrels); } - mod->arch.core_plt->sh_type = SHT_NOBITS; - mod->arch.core_plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC; - mod->arch.core_plt->sh_addralign = L1_CACHE_BYTES; - mod->arch.core_plt->sh_size = round_up(core_plts * PLT_ENT_SIZE, - sizeof(struct plt_entries)); - mod->arch.core_plt_count = 0; - - mod->arch.init_plt->sh_type = SHT_NOBITS; - mod->arch.init_plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC; - mod->arch.init_plt->sh_addralign = L1_CACHE_BYTES; - mod->arch.init_plt->sh_size = round_up(init_plts * PLT_ENT_SIZE, - sizeof(struct plt_entries)); - mod->arch.init_plt_count = 0; - pr_debug("%s: core.plt=%x, init.plt=%x\n", __func__, - mod->arch.core_plt->sh_size, mod->arch.init_plt->sh_size); + mod->arch.plt->sh_type = SHT_NOBITS; + mod->arch.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC; + mod->arch.plt->sh_addralign = L1_CACHE_BYTES; + mod->arch.plt->sh_size = round_up(plts * PLT_ENT_SIZE, + sizeof(struct plt_entries)); + mod->arch.plt_count = 0; + + pr_debug("%s: plt=%x\n", __func__, mod->arch.plt->sh_size); return 0; } diff --git a/arch/arm/kernel/module.lds b/arch/arm/kernel/module.lds index 3682fa107918..05881e2b414c 100644 --- a/arch/arm/kernel/module.lds +++ b/arch/arm/kernel/module.lds @@ -1,4 +1,3 @@ SECTIONS { - .core.plt : { BYTE(0) } - .init.plt : { BYTE(0) } + .plt : { BYTE(0) } } diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 15063851cd10..b9423491b9d7 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -596,12 +596,6 @@ static struct attribute_group armv7_pmuv1_events_attr_group = { .attrs = armv7_pmuv1_event_attrs, }; -static const struct attribute_group *armv7_pmuv1_attr_groups[] = { - &armv7_pmuv1_events_attr_group, - &armv7_pmu_format_attr_group, - NULL, -}; - ARMV7_EVENT_ATTR(mem_access, ARMV7_PERFCTR_MEM_ACCESS); ARMV7_EVENT_ATTR(l1i_cache, ARMV7_PERFCTR_L1_ICACHE_ACCESS); ARMV7_EVENT_ATTR(l1d_cache_wb, ARMV7_PERFCTR_L1_DCACHE_WB); @@ -653,12 +647,6 @@ static struct attribute_group armv7_pmuv2_events_attr_group = { .attrs = armv7_pmuv2_event_attrs, }; -static const struct attribute_group *armv7_pmuv2_attr_groups[] = { - &armv7_pmuv2_events_attr_group, - &armv7_pmu_format_attr_group, - NULL, -}; - /* * Perf Events' indices */ @@ -1208,7 +1196,10 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu) armv7pmu_init(cpu_pmu); cpu_pmu->name = "armv7_cortex_a8"; cpu_pmu->map_event = armv7_a8_map_event; - cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv1_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; return armv7_probe_num_events(cpu_pmu); } @@ -1217,7 +1208,10 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu) armv7pmu_init(cpu_pmu); cpu_pmu->name = "armv7_cortex_a9"; cpu_pmu->map_event = armv7_a9_map_event; - cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv1_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; return armv7_probe_num_events(cpu_pmu); } @@ -1226,7 +1220,10 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu) armv7pmu_init(cpu_pmu); cpu_pmu->name = "armv7_cortex_a5"; cpu_pmu->map_event = armv7_a5_map_event; - cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv1_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; return armv7_probe_num_events(cpu_pmu); } @@ -1236,7 +1233,10 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->name = "armv7_cortex_a15"; cpu_pmu->map_event = armv7_a15_map_event; cpu_pmu->set_event_filter = armv7pmu_set_event_filter; - cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv2_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; return armv7_probe_num_events(cpu_pmu); } @@ -1246,7 +1246,10 @@ static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->name = "armv7_cortex_a7"; cpu_pmu->map_event = armv7_a7_map_event; cpu_pmu->set_event_filter = armv7pmu_set_event_filter; - cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv2_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; return armv7_probe_num_events(cpu_pmu); } @@ -1256,7 +1259,10 @@ static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->name = "armv7_cortex_a12"; cpu_pmu->map_event = armv7_a12_map_event; cpu_pmu->set_event_filter = armv7pmu_set_event_filter; - cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv2_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; return armv7_probe_num_events(cpu_pmu); } @@ -1264,7 +1270,10 @@ static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu) { int ret = armv7_a12_pmu_init(cpu_pmu); cpu_pmu->name = "armv7_cortex_a17"; - cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv2_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; return ret; } diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index df7f2a75e769..34e3f3c45634 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -114,19 +114,19 @@ EXPORT_SYMBOL(elf_hwcap2); #ifdef MULTI_CPU -struct processor processor __read_mostly; +struct processor processor __ro_after_init; #endif #ifdef MULTI_TLB -struct cpu_tlb_fns cpu_tlb __read_mostly; +struct cpu_tlb_fns cpu_tlb __ro_after_init; #endif #ifdef MULTI_USER -struct cpu_user_fns cpu_user __read_mostly; +struct cpu_user_fns cpu_user __ro_after_init; #endif #ifdef MULTI_CACHE -struct cpu_cache_fns cpu_cache __read_mostly; +struct cpu_cache_fns cpu_cache __ro_after_init; #endif #ifdef CONFIG_OUTER_CACHE -struct outer_cache_fns outer_cache __read_mostly; +struct outer_cache_fns outer_cache __ro_after_init; EXPORT_SYMBOL(outer_cache); #endif @@ -290,12 +290,9 @@ static int cpu_has_aliasing_icache(unsigned int arch) /* arch specifies the register format */ switch (arch) { case CPU_ARCH_ARMv7: - asm("mcr p15, 2, %0, c0, c0, 0 @ set CSSELR" - : /* No output operands */ - : "r" (1)); + set_csselr(CSSELR_ICACHE | CSSELR_L1); isb(); - asm("mrc p15, 1, %0, c0, c0, 0 @ read CCSIDR" - : "=r" (id_reg)); + id_reg = read_ccsidr(); line_size = 4 << ((id_reg & 0x7) + 2); num_sets = ((id_reg >> 13) & 0x7fff) + 1; aliasing_icache = (line_size * num_sets) > PAGE_SIZE; @@ -315,11 +312,12 @@ static void __init cacheid_init(void) { unsigned int arch = cpu_architecture(); - if (arch == CPU_ARCH_ARMv7M) { - cacheid = 0; - } else if (arch >= CPU_ARCH_ARMv6) { + if (arch >= CPU_ARCH_ARMv6) { unsigned int cachetype = read_cpuid_cachetype(); - if ((cachetype & (7 << 29)) == 4 << 29) { + + if ((arch == CPU_ARCH_ARMv7M) && !cachetype) { + cacheid = 0; + } else if ((cachetype & (7 << 29)) == 4 << 29) { /* ARMv7 register format */ arch = CPU_ARCH_ARMv7; cacheid = CACHEID_VIPT_NONALIASING; diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 861521606c6d..937c8920d741 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -82,7 +82,7 @@ enum ipi_msg_type { static DECLARE_COMPLETION(cpu_running); -static struct smp_operations smp_ops; +static struct smp_operations smp_ops __ro_after_init; void __init smp_set_ops(const struct smp_operations *ops) { diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c index 994e971a8538..53cf86cf2d1a 100644 --- a/arch/arm/kernel/vdso.c +++ b/arch/arm/kernel/vdso.c @@ -17,6 +17,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/cache.h> #include <linux/elf.h> #include <linux/err.h> #include <linux/kernel.h> @@ -39,7 +40,7 @@ static struct page **vdso_text_pagelist; /* Total number of pages needed for the data and text portions of the VDSO. */ -unsigned int vdso_total_pages __read_mostly; +unsigned int vdso_total_pages __ro_after_init; /* * The VDSO data page. @@ -47,13 +48,13 @@ unsigned int vdso_total_pages __read_mostly; static union vdso_data_store vdso_data_store __page_aligned_data; static struct vdso_data *vdso_data = &vdso_data_store.data; -static struct page *vdso_data_page; -static struct vm_special_mapping vdso_data_mapping = { +static struct page *vdso_data_page __ro_after_init; +static const struct vm_special_mapping vdso_data_mapping = { .name = "[vvar]", .pages = &vdso_data_page, }; -static struct vm_special_mapping vdso_text_mapping = { +static struct vm_special_mapping vdso_text_mapping __ro_after_init = { .name = "[vdso]", }; @@ -67,7 +68,7 @@ struct elfinfo { /* Cached result of boot-time check for whether the arch timer exists, * and if so, whether the virtual counter is useable. */ -static bool cntvct_ok __read_mostly; +static bool cntvct_ok __ro_after_init; static bool __init cntvct_functional(void) { @@ -270,7 +271,7 @@ static bool tk_is_cntvct(const struct timekeeper *tk) if (!IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) return false; - if (strcmp(tk->tkr_mono.clock->name, "arch_sys_counter") != 0) + if (!tk->tkr_mono.clock->archdata.vdso_direct) return false; return true; diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index 10d77a66cad5..f19842ea5418 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -21,13 +21,16 @@ obj-$(CONFIG_KVM_ARM_HOST) += hyp/ obj-y += kvm-arm.o init.o interrupts.o obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o +obj-y += $(KVM)/arm/aarch32.o obj-y += $(KVM)/arm/vgic/vgic.o obj-y += $(KVM)/arm/vgic/vgic-init.o obj-y += $(KVM)/arm/vgic/vgic-irqfd.o obj-y += $(KVM)/arm/vgic/vgic-v2.o +obj-y += $(KVM)/arm/vgic/vgic-v3.o obj-y += $(KVM)/arm/vgic/vgic-mmio.o obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o +obj-y += $(KVM)/arm/vgic/vgic-mmio-v3.o obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o obj-y += $(KVM)/irqchip.o obj-y += $(KVM)/arm/arch_timer.o diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 75f130ef6504..03e9273f1876 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -144,6 +144,16 @@ out_fail_alloc: return ret; } +bool kvm_arch_has_vcpu_debugfs(void) +{ + return false; +} + +int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +{ + return 0; +} + int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) { return VM_FAULT_SIGBUS; @@ -158,8 +168,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm) { int i; - kvm_free_stage2_pgd(kvm); - for (i = 0; i < KVM_MAX_VCPUS; ++i) { if (kvm->vcpus[i]) { kvm_arch_vcpu_free(kvm->vcpus[i]); @@ -1178,6 +1186,10 @@ static int init_common_resources(void) return -ENOMEM; } + /* set size of VMID supported by CPU */ + kvm_vmid_bits = kvm_get_vmid_bits(); + kvm_info("%d-bit VMID\n", kvm_vmid_bits); + return 0; } @@ -1243,10 +1255,6 @@ static void teardown_hyp_mode(void) static int init_vhe_mode(void) { - /* set size of VMID supported by CPU */ - kvm_vmid_bits = kvm_get_vmid_bits(); - kvm_info("%d-bit VMID\n", kvm_vmid_bits); - kvm_info("VHE mode initialized successfully\n"); return 0; } @@ -1330,10 +1338,6 @@ static int init_hyp_mode(void) } } - /* set size of VMID supported by CPU */ - kvm_vmid_bits = kvm_get_vmid_bits(); - kvm_info("%d-bit VMID\n", kvm_vmid_bits); - kvm_info("Hyp mode initialized successfully\n"); return 0; diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 1bb2b79c01ff..3e5e4194ef86 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -228,6 +228,35 @@ bool access_vm_reg(struct kvm_vcpu *vcpu, return true; } +static bool access_gic_sgi(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + u64 reg; + + if (!p->is_write) + return read_from_write_only(vcpu, p); + + reg = (u64)*vcpu_reg(vcpu, p->Rt2) << 32; + reg |= *vcpu_reg(vcpu, p->Rt1) ; + + vgic_v3_dispatch_sgi(vcpu, reg); + + return true; +} + +static bool access_gic_sre(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + if (p->is_write) + return ignore_write(vcpu, p); + + *vcpu_reg(vcpu, p->Rt1) = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre; + + return true; +} + /* * We could trap ID_DFR0 and tell the guest we don't support performance * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was @@ -361,10 +390,16 @@ static const struct coproc_reg cp15_regs[] = { { CRn(10), CRm( 3), Op1( 0), Op2( 1), is32, access_vm_reg, reset_unknown, c10_AMAIR1}, + /* ICC_SGI1R */ + { CRm64(12), Op1( 0), is64, access_gic_sgi}, + /* VBAR: swapped by interrupt.S. */ { CRn(12), CRm( 0), Op1( 0), Op2( 0), is32, NULL, reset_val, c12_VBAR, 0x00000000 }, + /* ICC_SRE */ + { CRn(12), CRm(12), Op1( 0), Op2(5), is32, access_gic_sre }, + /* CONTEXTIDR/TPIDRURW/TPIDRURO/TPIDRPRW: swapped by interrupt.S. */ { CRn(13), CRm( 0), Op1( 0), Op2( 1), is32, access_vm_reg, reset_val, c13_CID, 0x00000000 }, diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c index af93e3ffc9f3..0064b86a2c87 100644 --- a/arch/arm/kvm/emulate.c +++ b/arch/arm/kvm/emulate.c @@ -161,105 +161,6 @@ unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu) } } -/* - * A conditional instruction is allowed to trap, even though it - * wouldn't be executed. So let's re-implement the hardware, in - * software! - */ -bool kvm_condition_valid(struct kvm_vcpu *vcpu) -{ - unsigned long cpsr, cond, insn; - - /* - * Exception Code 0 can only happen if we set HCR.TGE to 1, to - * catch undefined instructions, and then we won't get past - * the arm_exit_handlers test anyway. - */ - BUG_ON(!kvm_vcpu_trap_get_class(vcpu)); - - /* Top two bits non-zero? Unconditional. */ - if (kvm_vcpu_get_hsr(vcpu) >> 30) - return true; - - cpsr = *vcpu_cpsr(vcpu); - - /* Is condition field valid? */ - if ((kvm_vcpu_get_hsr(vcpu) & HSR_CV) >> HSR_CV_SHIFT) - cond = (kvm_vcpu_get_hsr(vcpu) & HSR_COND) >> HSR_COND_SHIFT; - else { - /* This can happen in Thumb mode: examine IT state. */ - unsigned long it; - - it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3); - - /* it == 0 => unconditional. */ - if (it == 0) - return true; - - /* The cond for this insn works out as the top 4 bits. */ - cond = (it >> 4); - } - - /* Shift makes it look like an ARM-mode instruction */ - insn = cond << 28; - return arm_check_condition(insn, cpsr) != ARM_OPCODE_CONDTEST_FAIL; -} - -/** - * adjust_itstate - adjust ITSTATE when emulating instructions in IT-block - * @vcpu: The VCPU pointer - * - * When exceptions occur while instructions are executed in Thumb IF-THEN - * blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have - * to do this little bit of work manually. The fields map like this: - * - * IT[7:0] -> CPSR[26:25],CPSR[15:10] - */ -static void kvm_adjust_itstate(struct kvm_vcpu *vcpu) -{ - unsigned long itbits, cond; - unsigned long cpsr = *vcpu_cpsr(vcpu); - bool is_arm = !(cpsr & PSR_T_BIT); - - BUG_ON(is_arm && (cpsr & PSR_IT_MASK)); - - if (!(cpsr & PSR_IT_MASK)) - return; - - cond = (cpsr & 0xe000) >> 13; - itbits = (cpsr & 0x1c00) >> (10 - 2); - itbits |= (cpsr & (0x3 << 25)) >> 25; - - /* Perform ITAdvance (see page A-52 in ARM DDI 0406C) */ - if ((itbits & 0x7) == 0) - itbits = cond = 0; - else - itbits = (itbits << 1) & 0x1f; - - cpsr &= ~PSR_IT_MASK; - cpsr |= cond << 13; - cpsr |= (itbits & 0x1c) << (10 - 2); - cpsr |= (itbits & 0x3) << 25; - *vcpu_cpsr(vcpu) = cpsr; -} - -/** - * kvm_skip_instr - skip a trapped instruction and proceed to the next - * @vcpu: The vcpu pointer - */ -void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) -{ - bool is_thumb; - - is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_T_BIT); - if (is_thumb && !is_wide_instr) - *vcpu_pc(vcpu) += 2; - else - *vcpu_pc(vcpu) += 4; - kvm_adjust_itstate(vcpu); -} - - /****************************************************************************** * Inject exceptions into the guest */ @@ -402,3 +303,15 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) { inject_abt(vcpu, true, addr); } + +/** + * kvm_inject_vabt - inject an async abort / SError into the guest + * @vcpu: The VCPU to receive the exception + * + * It is assumed that this code is called from the VCPU thread and that the + * VCPU therefore is not currently executing guest code. + */ +void kvm_inject_vabt(struct kvm_vcpu *vcpu) +{ + vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) | HCR_VA); +} diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index 3f1ef0dbc899..4e40d1955e35 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -28,14 +28,6 @@ typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *); -static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - /* SVC called from Hyp mode should never get here */ - kvm_debug("SVC called from Hyp mode shouldn't go here\n"); - BUG(); - return -EINVAL; /* Squash warning */ -} - static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) { int ret; @@ -59,22 +51,6 @@ static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) return 1; } -static int handle_pabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - /* The hypervisor should never cause aborts */ - kvm_err("Prefetch Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n", - kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu)); - return -EFAULT; -} - -static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - /* This is either an error in the ws. code or an external abort */ - kvm_err("Data Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n", - kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu)); - return -EFAULT; -} - /** * kvm_handle_wfx - handle a WFI or WFE instructions trapped in guests * @vcpu: the vcpu pointer @@ -112,13 +88,10 @@ static exit_handle_fn arm_exit_handlers[] = { [HSR_EC_CP14_64] = kvm_handle_cp14_access, [HSR_EC_CP_0_13] = kvm_handle_cp_0_13_access, [HSR_EC_CP10_ID] = kvm_handle_cp10_id, - [HSR_EC_SVC_HYP] = handle_svc_hyp, [HSR_EC_HVC] = handle_hvc, [HSR_EC_SMC] = handle_smc, [HSR_EC_IABT] = kvm_handle_guest_abort, - [HSR_EC_IABT_HYP] = handle_pabt_hyp, [HSR_EC_DABT] = kvm_handle_guest_abort, - [HSR_EC_DABT_HYP] = handle_dabt_hyp, }; static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) @@ -144,6 +117,25 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, { exit_handle_fn exit_handler; + if (ARM_ABORT_PENDING(exception_index)) { + u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu); + + /* + * HVC/SMC already have an adjusted PC, which we need + * to correct in order to return to after having + * injected the abort. + */ + if (hsr_ec == HSR_EC_HVC || hsr_ec == HSR_EC_SMC) { + u32 adj = kvm_vcpu_trap_il_is32bit(vcpu) ? 4 : 2; + *vcpu_pc(vcpu) -= adj; + } + + kvm_inject_vabt(vcpu); + return 1; + } + + exception_index = ARM_EXCEPTION_CODE(exception_index); + switch (exception_index) { case ARM_EXCEPTION_IRQ: return 1; @@ -160,6 +152,9 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, exit_handler = kvm_get_exit_handler(vcpu); return exit_handler(vcpu, run); + case ARM_EXCEPTION_DATA_ABORT: + kvm_inject_vabt(vcpu); + return 1; default: kvm_pr_unimpl("Unsupported exception type: %d", exception_index); diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile index 8dfa5f7f9290..3023bb530edf 100644 --- a/arch/arm/kvm/hyp/Makefile +++ b/arch/arm/kvm/hyp/Makefile @@ -5,6 +5,7 @@ KVM=../../../../virt/kvm obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o +obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o obj-$(CONFIG_KVM_ARM_HOST) += tlb.o diff --git a/arch/arm/kvm/hyp/entry.S b/arch/arm/kvm/hyp/entry.S index 21c238871c9e..60783f3b57cc 100644 --- a/arch/arm/kvm/hyp/entry.S +++ b/arch/arm/kvm/hyp/entry.S @@ -18,6 +18,7 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/kvm_arm.h> +#include <asm/kvm_asm.h> .arch_extension virt @@ -63,6 +64,36 @@ ENTRY(__guest_exit) ldr lr, [r0, #4] mov r0, r1 + mrs r1, SPSR + mrs r2, ELR_hyp + mrc p15, 4, r3, c5, c2, 0 @ HSR + + /* + * Force loads and stores to complete before unmasking aborts + * and forcing the delivery of the exception. This gives us a + * single instruction window, which the handler will try to + * match. + */ + dsb sy + cpsie a + + .global abort_guest_exit_start +abort_guest_exit_start: + + isb + + .global abort_guest_exit_end +abort_guest_exit_end: + + /* + * If we took an abort, r0[31] will be set, and cmp will set + * the N bit in PSTATE. + */ + cmp r0, #0 + msrmi SPSR_cxsf, r1 + msrmi ELR_hyp, r2 + mcrmi p15, 4, r3, c5, c2, 0 @ HSR + bx lr ENDPROC(__guest_exit) diff --git a/arch/arm/kvm/hyp/hyp-entry.S b/arch/arm/kvm/hyp/hyp-entry.S index 78091383a5d9..96beb53934c9 100644 --- a/arch/arm/kvm/hyp/hyp-entry.S +++ b/arch/arm/kvm/hyp/hyp-entry.S @@ -81,7 +81,6 @@ __kvm_hyp_vector: invalid_vector hyp_undef ARM_EXCEPTION_UNDEFINED invalid_vector hyp_svc ARM_EXCEPTION_SOFTWARE invalid_vector hyp_pabt ARM_EXCEPTION_PREF_ABORT - invalid_vector hyp_dabt ARM_EXCEPTION_DATA_ABORT invalid_vector hyp_fiq ARM_EXCEPTION_FIQ ENTRY(__hyp_do_panic) @@ -164,6 +163,21 @@ hyp_irq: load_vcpu r0 @ Load VCPU pointer to r0 b __guest_exit +hyp_dabt: + push {r0, r1} + mrs r0, ELR_hyp + ldr r1, =abort_guest_exit_start +THUMB( add r1, r1, #1) + cmp r0, r1 + ldrne r1, =abort_guest_exit_end +THUMB( addne r1, r1, #1) + cmpne r0, r1 + pop {r0, r1} + bne __hyp_panic + + orr r0, r0, #(1 << ARM_EXIT_WITH_ABORT_BIT) + eret + .ltorg .popsection diff --git a/arch/arm/kvm/hyp/switch.c b/arch/arm/kvm/hyp/switch.c index b13caa90cd44..92678b7bd046 100644 --- a/arch/arm/kvm/hyp/switch.c +++ b/arch/arm/kvm/hyp/switch.c @@ -14,6 +14,7 @@ * You should have received a copy of the GNU General Public License * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/jump_label.h> #include <asm/kvm_asm.h> #include <asm/kvm_hyp.h> @@ -54,6 +55,15 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu) { u32 val; + /* + * If we pended a virtual abort, preserve it until it gets + * cleared. See B1.9.9 (Virtual Abort exception) for details, + * but the crucial bit is the zeroing of HCR.VA in the + * pseudocode. + */ + if (vcpu->arch.hcr & HCR_VA) + vcpu->arch.hcr = read_sysreg(HCR); + write_sysreg(0, HCR); write_sysreg(0, HSTR); val = read_sysreg(HDCR); @@ -74,14 +84,21 @@ static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu) write_sysreg(read_sysreg(MIDR), VPIDR); } + static void __hyp_text __vgic_save_state(struct kvm_vcpu *vcpu) { - __vgic_v2_save_state(vcpu); + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + __vgic_v3_save_state(vcpu); + else + __vgic_v2_save_state(vcpu); } static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu) { - __vgic_v2_restore_state(vcpu); + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + __vgic_v3_restore_state(vcpu); + else + __vgic_v2_restore_state(vcpu); } static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) @@ -134,7 +151,7 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) return true; } -static int __hyp_text __guest_run(struct kvm_vcpu *vcpu) +int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; @@ -191,8 +208,6 @@ again: return exit_code; } -__alias(__guest_run) int __kvm_vcpu_run(struct kvm_vcpu *vcpu); - static const char * const __hyp_panic_string[] = { [ARM_EXCEPTION_RESET] = "\nHYP panic: RST PC:%08x CPSR:%08x", [ARM_EXCEPTION_UNDEFINED] = "\nHYP panic: UNDEF PC:%08x CPSR:%08x", diff --git a/arch/arm/kvm/hyp/tlb.c b/arch/arm/kvm/hyp/tlb.c index a2636001e616..729652854f90 100644 --- a/arch/arm/kvm/hyp/tlb.c +++ b/arch/arm/kvm/hyp/tlb.c @@ -34,7 +34,7 @@ * As v7 does not support flushing per IPA, just nuke the whole TLB * instead, ignoring the ipa value. */ -static void __hyp_text __tlb_flush_vmid(struct kvm *kvm) +void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) { dsb(ishst); @@ -50,21 +50,14 @@ static void __hyp_text __tlb_flush_vmid(struct kvm *kvm) write_sysreg(0, VTTBR); } -__alias(__tlb_flush_vmid) void __kvm_tlb_flush_vmid(struct kvm *kvm); - -static void __hyp_text __tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) +void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) { - __tlb_flush_vmid(kvm); + __kvm_tlb_flush_vmid(kvm); } -__alias(__tlb_flush_vmid_ipa) void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, - phys_addr_t ipa); - -static void __hyp_text __tlb_flush_vm_context(void) +void __hyp_text __kvm_flush_vm_context(void) { write_sysreg(0, TLBIALLNSNHIS); write_sysreg(0, ICIALLUIS); dsb(ish); } - -__alias(__tlb_flush_vm_context) void __kvm_flush_vm_context(void); diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 10f80a6c797a..b6e715fd3c90 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -126,12 +126,6 @@ static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len) int access_size; bool sign_extend; - if (kvm_vcpu_dabt_isextabt(vcpu)) { - /* cache operation on I/O addr, tell guest unsupported */ - kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); - return 1; - } - if (kvm_vcpu_dabt_iss1tw(vcpu)) { /* page table accesses IO mem: tell guest to fix its TTBR */ kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 29d0b23af2a9..a5265edbeeab 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -744,7 +744,6 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) if (!pgd) return -ENOMEM; - kvm_clean_pgd(pgd); kvm->arch.pgd = pgd; return 0; } @@ -936,7 +935,6 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, if (!cache) return 0; /* ignore calls from kvm_set_spte_hva */ pte = mmu_memory_cache_alloc(cache); - kvm_clean_pte(pte); pmd_populate_kernel(NULL, pmd, pte); get_page(virt_to_page(pmd)); } @@ -1434,6 +1432,11 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) int ret, idx; is_iabt = kvm_vcpu_trap_is_iabt(vcpu); + if (unlikely(!is_iabt && kvm_vcpu_dabt_isextabt(vcpu))) { + kvm_inject_vabt(vcpu); + return 1; + } + fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu), @@ -1714,7 +1717,8 @@ int kvm_mmu_init(void) kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL)); if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) && - hyp_idmap_start < kern_hyp_va(~0UL)) { + hyp_idmap_start < kern_hyp_va(~0UL) && + hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) { /* * The idmap page is intersecting with the VA space, * it is not safe to continue further. @@ -1893,6 +1897,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) void kvm_arch_flush_shadow_all(struct kvm *kvm) { + kvm_free_stage2_pgd(kvm); } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c index 8044591dca72..2cef11884857 100644 --- a/arch/arm/lib/delay.c +++ b/arch/arm/lib/delay.c @@ -29,7 +29,7 @@ /* * Default to the loop-based delay implementation. */ -struct arm_delay_ops arm_delay_ops = { +struct arm_delay_ops arm_delay_ops __ro_after_init = { .delay = __loop_delay, .const_udelay = __loop_const_udelay, .udelay = __loop_udelay, diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig index 5204395efda8..841e924143f9 100644 --- a/arch/arm/mach-at91/Kconfig +++ b/arch/arm/mach-at91/Kconfig @@ -55,7 +55,6 @@ config SOC_AT91RM9200 select ATMEL_ST select CPU_ARM920T select HAVE_AT91_USB_CLK - select MIGHT_HAVE_PCI select PINCTRL_AT91 select SOC_SAM_V4_V5 select SRAM if PM diff --git a/arch/arm/mach-axxia/Kconfig b/arch/arm/mach-axxia/Kconfig index 6c6d5e76565b..fe627cbcfdc5 100644 --- a/arch/arm/mach-axxia/Kconfig +++ b/arch/arm/mach-axxia/Kconfig @@ -7,8 +7,6 @@ config ARCH_AXXIA select ARM_TIMER_SP804 select HAVE_ARM_ARCH_TIMER select MFD_SYSCON - select MIGHT_HAVE_PCI - select PCI_DOMAINS if PCI select ZONE_DMA help This enables support for the LSI Axxia devices. diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig index 6a6302d1b40f..a0e66d8200c5 100644 --- a/arch/arm/mach-bcm/Kconfig +++ b/arch/arm/mach-bcm/Kconfig @@ -15,7 +15,6 @@ config ARCH_BCM_IPROC select HAVE_ARM_SCU if SMP select HAVE_ARM_TWD if SMP select ARM_GLOBAL_TIMER - select COMMON_CLK_IPROC select CLKSRC_MMIO select GPIOLIB select ARM_AMBA diff --git a/arch/arm/mach-clps711x/Makefile.boot b/arch/arm/mach-clps711x/Makefile.boot deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/arch/arm/mach-clps711x/Makefile.boot +++ /dev/null diff --git a/arch/arm/mach-clps711x/board-autcpu12.c b/arch/arm/mach-clps711x/board-autcpu12.c deleted file mode 100644 index ba3d7d1b28f8..000000000000 --- a/arch/arm/mach-clps711x/board-autcpu12.c +++ /dev/null @@ -1,275 +0,0 @@ -/* - * linux/arch/arm/mach-clps711x/autcpu12.c - * - * (c) 2001 Thomas Gleixner, autronix automation <gleixner@autronix.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/types.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/io.h> -#include <linux/gpio.h> -#include <linux/ioport.h> -#include <linux/interrupt.h> -#include <linux/mtd/physmap.h> -#include <linux/mtd/plat-ram.h> -#include <linux/mtd/partitions.h> -#include <linux/mtd/nand-gpio.h> -#include <linux/platform_device.h> -#include <linux/gpio/driver.h> - -#include <mach/hardware.h> -#include <asm/sizes.h> -#include <asm/setup.h> -#include <asm/mach-types.h> -#include <asm/mach/arch.h> -#include <asm/pgtable.h> -#include <asm/page.h> - -#include <asm/mach/map.h> - -#include "common.h" -#include "devices.h" - -/* NOR flash */ -#define AUTCPU12_FLASH_BASE (CS0_PHYS_BASE) - -/* Board specific hardware definitions */ -#define AUTCPU12_CHAR_LCD_BASE (CS1_PHYS_BASE + 0x00000000) -#define AUTCPU12_CSAUX1_BASE (CS1_PHYS_BASE + 0x04000000) -#define AUTCPU12_CAN_BASE (CS1_PHYS_BASE + 0x08000000) -#define AUTCPU12_TOUCH_BASE (CS1_PHYS_BASE + 0x0a000000) -#define AUTCPU12_IO_BASE (CS1_PHYS_BASE + 0x0c000000) -#define AUTCPU12_LPT_BASE (CS1_PHYS_BASE + 0x0e000000) - -/* NVRAM */ -#define AUTCPU12_NVRAM_BASE (CS1_PHYS_BASE + 0x02000000) - -/* SmartMedia flash */ -#define AUTCPU12_SMC_BASE (CS1_PHYS_BASE + 0x06000000) -#define AUTCPU12_SMC_SEL_BASE (AUTCPU12_SMC_BASE + 0x10) - -/* Ethernet */ -#define AUTCPU12_CS8900_BASE (CS2_PHYS_BASE + 0x300) -#define AUTCPU12_CS8900_IRQ (IRQ_EINT3) - -/* NAND flash */ -#define AUTCPU12_MMGPIO_BASE (CLPS711X_NR_GPIO) -#define AUTCPU12_SMC_NCE (AUTCPU12_MMGPIO_BASE + 0) /* Bit 0 */ -#define AUTCPU12_SMC_RDY CLPS711X_GPIO(1, 2) -#define AUTCPU12_SMC_ALE CLPS711X_GPIO(1, 3) -#define AUTCPU12_SMC_CLE CLPS711X_GPIO(1, 4) - -/* LCD contrast digital potentiometer */ -#define AUTCPU12_DPOT_CS CLPS711X_GPIO(4, 0) -#define AUTCPU12_DPOT_CLK CLPS711X_GPIO(4, 1) -#define AUTCPU12_DPOT_UD CLPS711X_GPIO(4, 2) - -static struct resource autcpu12_cs8900_resource[] __initdata = { - DEFINE_RES_MEM(AUTCPU12_CS8900_BASE, SZ_1K), - DEFINE_RES_IRQ(AUTCPU12_CS8900_IRQ), -}; - -static struct resource autcpu12_nand_resource[] __initdata = { - DEFINE_RES_MEM(AUTCPU12_SMC_BASE, SZ_16), -}; - -static struct mtd_partition autcpu12_nand_parts[] __initdata = { - { - .name = "Flash partition 1", - .offset = 0, - .size = SZ_8M, - }, - { - .name = "Flash partition 2", - .offset = MTDPART_OFS_APPEND, - .size = MTDPART_SIZ_FULL, - }, -}; - -static void __init autcpu12_adjust_parts(struct gpio_nand_platdata *pdata, - size_t sz) -{ - switch (sz) { - case SZ_16M: - case SZ_32M: - break; - case SZ_64M: - case SZ_128M: - pdata->parts[0].size = SZ_16M; - break; - default: - pr_warn("Unsupported SmartMedia device size %u\n", sz); - break; - } -} - -static struct gpio_nand_platdata autcpu12_nand_pdata __initdata = { - .gpio_rdy = AUTCPU12_SMC_RDY, - .gpio_nce = AUTCPU12_SMC_NCE, - .gpio_ale = AUTCPU12_SMC_ALE, - .gpio_cle = AUTCPU12_SMC_CLE, - .gpio_nwp = -1, - .chip_delay = 20, - .parts = autcpu12_nand_parts, - .num_parts = ARRAY_SIZE(autcpu12_nand_parts), - .adjust_parts = autcpu12_adjust_parts, -}; - -static struct platform_device autcpu12_nand_pdev __initdata = { - .name = "gpio-nand", - .id = -1, - .resource = autcpu12_nand_resource, - .num_resources = ARRAY_SIZE(autcpu12_nand_resource), - .dev = { - .platform_data = &autcpu12_nand_pdata, - }, -}; - -static struct resource autcpu12_mmgpio_resource[] __initdata = { - DEFINE_RES_MEM_NAMED(AUTCPU12_SMC_SEL_BASE, SZ_1, "dat"), -}; - -static struct bgpio_pdata autcpu12_mmgpio_pdata __initdata = { - .base = AUTCPU12_MMGPIO_BASE, - .ngpio = 8, -}; - -static struct platform_device autcpu12_mmgpio_pdev __initdata = { - .name = "basic-mmio-gpio", - .id = -1, - .resource = autcpu12_mmgpio_resource, - .num_resources = ARRAY_SIZE(autcpu12_mmgpio_resource), - .dev = { - .platform_data = &autcpu12_mmgpio_pdata, - }, -}; - -static const struct gpio const autcpu12_gpios[] __initconst = { - { AUTCPU12_DPOT_CS, GPIOF_OUT_INIT_HIGH, "DPOT CS" }, - { AUTCPU12_DPOT_CLK, GPIOF_OUT_INIT_LOW, "DPOT CLK" }, - { AUTCPU12_DPOT_UD, GPIOF_OUT_INIT_LOW, "DPOT UD" }, -}; - -static struct mtd_partition autcpu12_flash_partitions[] = { - { - .name = "NOR.0", - .offset = 0, - .size = MTDPART_SIZ_FULL, - }, -}; - -static struct physmap_flash_data autcpu12_flash_pdata = { - .width = 4, - .parts = autcpu12_flash_partitions, - .nr_parts = ARRAY_SIZE(autcpu12_flash_partitions), -}; - -static struct resource autcpu12_flash_resources[] __initdata = { - DEFINE_RES_MEM(AUTCPU12_FLASH_BASE, SZ_8M), -}; - -static struct platform_device autcpu12_flash_pdev __initdata = { - .name = "physmap-flash", - .id = 0, - .resource = autcpu12_flash_resources, - .num_resources = ARRAY_SIZE(autcpu12_flash_resources), - .dev = { - .platform_data = &autcpu12_flash_pdata, - }, -}; - -static struct resource autcpu12_nvram_resource[] __initdata = { - DEFINE_RES_MEM(AUTCPU12_NVRAM_BASE, 0), -}; - -static struct platdata_mtd_ram autcpu12_nvram_pdata = { - .bankwidth = 4, -}; - -static struct platform_device autcpu12_nvram_pdev __initdata = { - .name = "mtd-ram", - .id = 0, - .resource = autcpu12_nvram_resource, - .num_resources = ARRAY_SIZE(autcpu12_nvram_resource), - .dev = { - .platform_data = &autcpu12_nvram_pdata, - }, -}; - -static void __init autcpu12_nvram_init(void) -{ - void __iomem *nvram; - unsigned int save[2]; - resource_size_t nvram_size = SZ_128K; - - /* - * Check for 32K/128K - * Read ofs 0K - * Read ofs 64K - * Write complement to ofs 64K - * Read and check result on ofs 0K - * Restore contents - */ - nvram = ioremap(autcpu12_nvram_resource[0].start, SZ_128K); - if (nvram) { - save[0] = readl(nvram + 0); - save[1] = readl(nvram + SZ_64K); - writel(~save[0], nvram + SZ_64K); - if (readl(nvram + 0) != save[0]) { - writel(save[0], nvram + 0); - nvram_size = SZ_32K; - } else - writel(save[1], nvram + SZ_64K); - iounmap(nvram); - - autcpu12_nvram_resource[0].end = - autcpu12_nvram_resource[0].start + nvram_size - 1; - platform_device_register(&autcpu12_nvram_pdev); - } else - pr_err("Failed to remap NVRAM resource\n"); -} - -static void __init autcpu12_init(void) -{ - clps711x_devices_init(); - platform_device_register(&autcpu12_flash_pdev); - platform_device_register_simple("video-clps711x", 0, NULL, 0); - platform_device_register_simple("cs89x0", 0, autcpu12_cs8900_resource, - ARRAY_SIZE(autcpu12_cs8900_resource)); - platform_device_register(&autcpu12_mmgpio_pdev); - autcpu12_nvram_init(); -} - -static void __init autcpu12_init_late(void) -{ - gpio_request_array(autcpu12_gpios, ARRAY_SIZE(autcpu12_gpios)); - platform_device_register(&autcpu12_nand_pdev); -} - -MACHINE_START(AUTCPU12, "autronix autcpu12") - /* Maintainer: Thomas Gleixner */ - .atag_offset = 0x20000, - .map_io = clps711x_map_io, - .init_irq = clps711x_init_irq, - .init_time = clps711x_timer_init, - .init_machine = autcpu12_init, - .init_late = autcpu12_init_late, - .restart = clps711x_restart, -MACHINE_END - diff --git a/arch/arm/mach-clps711x/board-cdb89712.c b/arch/arm/mach-clps711x/board-cdb89712.c deleted file mode 100644 index 972abdb10028..000000000000 --- a/arch/arm/mach-clps711x/board-cdb89712.c +++ /dev/null @@ -1,147 +0,0 @@ -/* - * linux/arch/arm/mach-clps711x/cdb89712.c - * - * Copyright (C) 2000-2001 Deep Blue Solutions Ltd - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/types.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/io.h> -#include <linux/interrupt.h> -#include <linux/platform_device.h> - -#include <linux/mtd/physmap.h> -#include <linux/mtd/plat-ram.h> -#include <linux/mtd/partitions.h> - -#include <mach/hardware.h> -#include <asm/pgtable.h> -#include <asm/page.h> -#include <asm/setup.h> -#include <asm/mach-types.h> -#include <asm/mach/arch.h> -#include <asm/mach/map.h> - -#include "common.h" -#include "devices.h" - -#define CDB89712_CS8900_BASE (CS2_PHYS_BASE + 0x300) -#define CDB89712_CS8900_IRQ (IRQ_EINT3) - -static struct resource cdb89712_cs8900_resource[] __initdata = { - DEFINE_RES_MEM(CDB89712_CS8900_BASE, SZ_1K), - DEFINE_RES_IRQ(CDB89712_CS8900_IRQ), -}; - -static struct mtd_partition cdb89712_flash_partitions[] __initdata = { - { - .name = "Flash", - .offset = 0, - .size = MTDPART_SIZ_FULL, - }, -}; - -static struct physmap_flash_data cdb89712_flash_pdata __initdata = { - .width = 4, - .probe_type = "map_rom", - .parts = cdb89712_flash_partitions, - .nr_parts = ARRAY_SIZE(cdb89712_flash_partitions), -}; - -static struct resource cdb89712_flash_resources[] __initdata = { - DEFINE_RES_MEM(CS0_PHYS_BASE, SZ_8M), -}; - -static struct platform_device cdb89712_flash_pdev __initdata = { - .name = "physmap-flash", - .id = 0, - .resource = cdb89712_flash_resources, - .num_resources = ARRAY_SIZE(cdb89712_flash_resources), - .dev = { - .platform_data = &cdb89712_flash_pdata, - }, -}; - -static struct mtd_partition cdb89712_bootrom_partitions[] __initdata = { - { - .name = "BootROM", - .offset = 0, - .size = MTDPART_SIZ_FULL, - }, -}; - -static struct physmap_flash_data cdb89712_bootrom_pdata __initdata = { - .width = 4, - .probe_type = "map_rom", - .parts = cdb89712_bootrom_partitions, - .nr_parts = ARRAY_SIZE(cdb89712_bootrom_partitions), -}; - -static struct resource cdb89712_bootrom_resources[] __initdata = { - DEFINE_RES_NAMED(CS7_PHYS_BASE, SZ_128, "BOOTROM", IORESOURCE_MEM | - IORESOURCE_READONLY), -}; - -static struct platform_device cdb89712_bootrom_pdev __initdata = { - .name = "physmap-flash", - .id = 1, - .resource = cdb89712_bootrom_resources, - .num_resources = ARRAY_SIZE(cdb89712_bootrom_resources), - .dev = { - .platform_data = &cdb89712_bootrom_pdata, - }, -}; - -static struct platdata_mtd_ram cdb89712_sram_pdata __initdata = { - .bankwidth = 4, -}; - -static struct resource cdb89712_sram_resources[] __initdata = { - DEFINE_RES_MEM(CLPS711X_SRAM_BASE, CLPS711X_SRAM_SIZE), -}; - -static struct platform_device cdb89712_sram_pdev __initdata = { - .name = "mtd-ram", - .id = 0, - .resource = cdb89712_sram_resources, - .num_resources = ARRAY_SIZE(cdb89712_sram_resources), - .dev = { - .platform_data = &cdb89712_sram_pdata, - }, -}; - -static void __init cdb89712_init(void) -{ - clps711x_devices_init(); - platform_device_register(&cdb89712_flash_pdev); - platform_device_register(&cdb89712_bootrom_pdev); - platform_device_register(&cdb89712_sram_pdev); - platform_device_register_simple("cs89x0", 0, cdb89712_cs8900_resource, - ARRAY_SIZE(cdb89712_cs8900_resource)); -} - -MACHINE_START(CDB89712, "Cirrus-CDB89712") - /* Maintainer: Ray Lehtiniemi */ - .atag_offset = 0x100, - .map_io = clps711x_map_io, - .init_irq = clps711x_init_irq, - .init_time = clps711x_timer_init, - .init_machine = cdb89712_init, - .restart = clps711x_restart, -MACHINE_END diff --git a/arch/arm/mach-clps711x/board-clep7312.c b/arch/arm/mach-clps711x/board-clep7312.c deleted file mode 100644 index f9ca22b646bf..000000000000 --- a/arch/arm/mach-clps711x/board-clep7312.c +++ /dev/null @@ -1,45 +0,0 @@ -/* - * linux/arch/arm/mach-clps711x/clep7312.c - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -#include <linux/init.h> -#include <linux/types.h> -#include <linux/string.h> -#include <linux/memblock.h> - -#include <asm/setup.h> -#include <asm/mach-types.h> -#include <asm/mach/arch.h> - -#include "common.h" -#include "devices.h" - -static void __init -fixup_clep7312(struct tag *tags, char **cmdline) -{ - memblock_add(0xc0000000, 0x01000000); -} - -MACHINE_START(CLEP7212, "Cirrus Logic 7212/7312") - /* Maintainer: Nobody */ - .atag_offset = 0x0100, - .fixup = fixup_clep7312, - .map_io = clps711x_map_io, - .init_irq = clps711x_init_irq, - .init_time = clps711x_timer_init, - .init_machine = clps711x_devices_init, - .restart = clps711x_restart, -MACHINE_END diff --git a/arch/arm/mach-clps711x/board-edb7211.c b/arch/arm/mach-clps711x/board-edb7211.c deleted file mode 100644 index f33979784f38..000000000000 --- a/arch/arm/mach-clps711x/board-edb7211.c +++ /dev/null @@ -1,188 +0,0 @@ -/* - * Copyright (C) 2000, 2001 Blue Mug, Inc. All Rights Reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#include <linux/init.h> -#include <linux/gpio.h> -#include <linux/delay.h> -#include <linux/memblock.h> -#include <linux/types.h> -#include <linux/i2c-gpio.h> -#include <linux/interrupt.h> -#include <linux/platform_device.h> -#include <linux/pwm.h> -#include <linux/pwm_backlight.h> -#include <linux/memblock.h> - -#include <linux/mtd/physmap.h> -#include <linux/mtd/partitions.h> - -#include <asm/setup.h> -#include <asm/mach/map.h> -#include <asm/mach/arch.h> -#include <asm/mach-types.h> - -#include <video/platform_lcd.h> - -#include <mach/hardware.h> - -#include "common.h" -#include "devices.h" - -#define VIDEORAM_SIZE SZ_128K - -#define EDB7211_LCD_DC_DC_EN CLPS711X_GPIO(3, 1) -#define EDB7211_LCDEN CLPS711X_GPIO(3, 2) -#define EDB7211_LCDBL CLPS711X_GPIO(3, 3) - -#define EDB7211_I2C_SDA CLPS711X_GPIO(3, 4) -#define EDB7211_I2C_SCL CLPS711X_GPIO(3, 5) - -#define EDB7211_FLASH0_BASE (CS0_PHYS_BASE) -#define EDB7211_FLASH1_BASE (CS1_PHYS_BASE) - -#define EDB7211_CS8900_BASE (CS2_PHYS_BASE + 0x300) -#define EDB7211_CS8900_IRQ (IRQ_EINT3) - -/* The extra 8 lines of the keyboard matrix */ -#define EDB7211_EXTKBD_BASE (CS3_PHYS_BASE) - -static struct i2c_gpio_platform_data edb7211_i2c_pdata __initdata = { - .sda_pin = EDB7211_I2C_SDA, - .scl_pin = EDB7211_I2C_SCL, - .scl_is_output_only = 1, -}; - -static struct resource edb7211_cs8900_resource[] __initdata = { - DEFINE_RES_MEM(EDB7211_CS8900_BASE, SZ_1K), - DEFINE_RES_IRQ(EDB7211_CS8900_IRQ), -}; - -static struct mtd_partition edb7211_flash_partitions[] __initdata = { - { - .name = "Flash", - .offset = 0, - .size = MTDPART_SIZ_FULL, - }, -}; - -static struct physmap_flash_data edb7211_flash_pdata __initdata = { - .width = 4, - .parts = edb7211_flash_partitions, - .nr_parts = ARRAY_SIZE(edb7211_flash_partitions), -}; - -static struct resource edb7211_flash_resources[] __initdata = { - DEFINE_RES_MEM(EDB7211_FLASH0_BASE, SZ_8M), - DEFINE_RES_MEM(EDB7211_FLASH1_BASE, SZ_8M), -}; - -static struct platform_device edb7211_flash_pdev __initdata = { - .name = "physmap-flash", - .id = 0, - .resource = edb7211_flash_resources, - .num_resources = ARRAY_SIZE(edb7211_flash_resources), - .dev = { - .platform_data = &edb7211_flash_pdata, - }, -}; - -static void edb7211_lcd_power_set(struct plat_lcd_data *pd, unsigned int power) -{ - if (power) { - gpio_set_value(EDB7211_LCDEN, 1); - udelay(100); - gpio_set_value(EDB7211_LCD_DC_DC_EN, 1); - } else { - gpio_set_value(EDB7211_LCD_DC_DC_EN, 0); - udelay(100); - gpio_set_value(EDB7211_LCDEN, 0); - } -} - -static struct plat_lcd_data edb7211_lcd_power_pdata = { - .set_power = edb7211_lcd_power_set, -}; - -static struct pwm_lookup edb7211_pwm_lookup[] = { - PWM_LOOKUP("clps711x-pwm", 0, "pwm-backlight.0", NULL, - 0, PWM_POLARITY_NORMAL), -}; - -static struct platform_pwm_backlight_data pwm_bl_pdata = { - .dft_brightness = 0x01, - .max_brightness = 0x0f, - .enable_gpio = EDB7211_LCDBL, -}; - -static struct resource clps711x_pwm_res = - DEFINE_RES_MEM(CLPS711X_PHYS_BASE + PMPCON, SZ_4); - -static struct gpio edb7211_gpios[] __initconst = { - { EDB7211_LCD_DC_DC_EN, GPIOF_OUT_INIT_LOW, "LCD DC-DC" }, - { EDB7211_LCDEN, GPIOF_OUT_INIT_LOW, "LCD POWER" }, -}; - -/* Reserve screen memory region at the start of main system memory. */ -static void __init edb7211_reserve(void) -{ - memblock_reserve(PHYS_OFFSET, VIDEORAM_SIZE); -} - -static void __init -fixup_edb7211(struct tag *tags, char **cmdline) -{ - /* - * Bank start addresses are not present in the information - * passed in from the boot loader. We could potentially - * detect them, but instead we hard-code them. - * - * Banks sizes _are_ present in the param block, but we're - * not using that information yet. - */ - memblock_add(0xc0000000, SZ_8M); - memblock_add(0xc1000000, SZ_8M); -} - -static void __init edb7211_init_late(void) -{ - gpio_request_array(edb7211_gpios, ARRAY_SIZE(edb7211_gpios)); - - platform_device_register(&edb7211_flash_pdev); - - platform_device_register_data(NULL, "platform-lcd", 0, - &edb7211_lcd_power_pdata, - sizeof(edb7211_lcd_power_pdata)); - - platform_device_register_simple("clps711x-pwm", PLATFORM_DEVID_NONE, - &clps711x_pwm_res, 1); - pwm_add_table(edb7211_pwm_lookup, ARRAY_SIZE(edb7211_pwm_lookup)); - - platform_device_register_data(&platform_bus, "pwm-backlight", 0, - &pwm_bl_pdata, sizeof(pwm_bl_pdata)); - - platform_device_register_simple("video-clps711x", 0, NULL, 0); - platform_device_register_simple("cs89x0", 0, edb7211_cs8900_resource, - ARRAY_SIZE(edb7211_cs8900_resource)); - platform_device_register_data(NULL, "i2c-gpio", 0, - &edb7211_i2c_pdata, - sizeof(edb7211_i2c_pdata)); -} - -MACHINE_START(EDB7211, "CL-EDB7211 (EP7211 eval board)") - /* Maintainer: Jon McClintock */ - .atag_offset = VIDEORAM_SIZE + 0x100, - .fixup = fixup_edb7211, - .reserve = edb7211_reserve, - .map_io = clps711x_map_io, - .init_irq = clps711x_init_irq, - .init_time = clps711x_timer_init, - .init_machine = clps711x_devices_init, - .init_late = edb7211_init_late, - .restart = clps711x_restart, -MACHINE_END diff --git a/arch/arm/mach-clps711x/board-p720t.c b/arch/arm/mach-clps711x/board-p720t.c deleted file mode 100644 index 80a16a8b3776..000000000000 --- a/arch/arm/mach-clps711x/board-p720t.c +++ /dev/null @@ -1,373 +0,0 @@ -/* - * linux/arch/arm/mach-clps711x/p720t.c - * - * Copyright (C) 2000-2001 Deep Blue Solutions Ltd - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/types.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/io.h> -#include <linux/gpio.h> -#include <linux/slab.h> -#include <linux/leds.h> -#include <linux/sizes.h> -#include <linux/backlight.h> -#include <linux/gpio/driver.h> -#include <linux/platform_device.h> -#include <linux/mtd/partitions.h> -#include <linux/mtd/nand-gpio.h> - -#include <mach/hardware.h> -#include <asm/pgtable.h> -#include <asm/page.h> -#include <asm/setup.h> -#include <asm/mach-types.h> -#include <asm/mach/arch.h> -#include <asm/mach/map.h> - -#include <video/platform_lcd.h> - -#include "common.h" -#include "devices.h" - -#define P720T_USERLED CLPS711X_GPIO(3, 0) -#define P720T_NAND_CLE CLPS711X_GPIO(4, 0) -#define P720T_NAND_ALE CLPS711X_GPIO(4, 1) -#define P720T_NAND_NCE CLPS711X_GPIO(4, 2) - -#define P720T_NAND_BASE (CLPS711X_SDRAM1_BASE) - -#define P720T_MMGPIO_BASE (CLPS711X_NR_GPIO) - -#define SYSPLD_PHYS_BASE IOMEM(CS1_PHYS_BASE) - -#define PLD_INT (SYSPLD_PHYS_BASE + 0x000000) -#define PLD_INT_MMGPIO_BASE (P720T_MMGPIO_BASE + 0) -#define PLD_INT_PENIRQ (PLD_INT_MMGPIO_BASE + 5) -#define PLD_INT_UCB_IRQ (PLD_INT_MMGPIO_BASE + 1) -#define PLD_INT_KBD_ATN (PLD_INT_MMGPIO_BASE + 0) /* EINT1 */ - -#define PLD_PWR (SYSPLD_PHYS_BASE + 0x000004) -#define PLD_PWR_MMGPIO_BASE (P720T_MMGPIO_BASE + 8) -#define PLD_PWR_EXT (PLD_PWR_MMGPIO_BASE + 5) -#define PLD_PWR_MODE (PLD_PWR_MMGPIO_BASE + 4) /* 1 = PWM, 0 = PFM */ -#define PLD_S4_ON (PLD_PWR_MMGPIO_BASE + 3) /* LCD bias voltage enable */ -#define PLD_S3_ON (PLD_PWR_MMGPIO_BASE + 2) /* LCD backlight enable */ -#define PLD_S2_ON (PLD_PWR_MMGPIO_BASE + 1) /* LCD 3V3 supply enable */ -#define PLD_S1_ON (PLD_PWR_MMGPIO_BASE + 0) /* LCD 3V supply enable */ - -#define PLD_KBD (SYSPLD_PHYS_BASE + 0x000008) -#define PLD_KBD_MMGPIO_BASE (P720T_MMGPIO_BASE + 16) -#define PLD_KBD_WAKE (PLD_KBD_MMGPIO_BASE + 1) -#define PLD_KBD_EN (PLD_KBD_MMGPIO_BASE + 0) - -#define PLD_SPI (SYSPLD_PHYS_BASE + 0x00000c) -#define PLD_SPI_MMGPIO_BASE (P720T_MMGPIO_BASE + 24) -#define PLD_SPI_EN (PLD_SPI_MMGPIO_BASE + 0) - -#define PLD_IO (SYSPLD_PHYS_BASE + 0x000010) -#define PLD_IO_MMGPIO_BASE (P720T_MMGPIO_BASE + 32) -#define PLD_IO_BOOTSEL (PLD_IO_MMGPIO_BASE + 6) /* Boot sel switch */ -#define PLD_IO_USER (PLD_IO_MMGPIO_BASE + 5) /* User defined switch */ -#define PLD_IO_LED3 (PLD_IO_MMGPIO_BASE + 4) -#define PLD_IO_LED2 (PLD_IO_MMGPIO_BASE + 3) -#define PLD_IO_LED1 (PLD_IO_MMGPIO_BASE + 2) -#define PLD_IO_LED0 (PLD_IO_MMGPIO_BASE + 1) -#define PLD_IO_LEDEN (PLD_IO_MMGPIO_BASE + 0) - -#define PLD_IRDA (SYSPLD_PHYS_BASE + 0x000014) -#define PLD_IRDA_MMGPIO_BASE (P720T_MMGPIO_BASE + 40) -#define PLD_IRDA_EN (PLD_IRDA_MMGPIO_BASE + 0) - -#define PLD_COM2 (SYSPLD_PHYS_BASE + 0x000018) -#define PLD_COM2_MMGPIO_BASE (P720T_MMGPIO_BASE + 48) -#define PLD_COM2_EN (PLD_COM2_MMGPIO_BASE + 0) - -#define PLD_COM1 (SYSPLD_PHYS_BASE + 0x00001c) -#define PLD_COM1_MMGPIO_BASE (P720T_MMGPIO_BASE + 56) -#define PLD_COM1_EN (PLD_COM1_MMGPIO_BASE + 0) - -#define PLD_AUD (SYSPLD_PHYS_BASE + 0x000020) -#define PLD_AUD_MMGPIO_BASE (P720T_MMGPIO_BASE + 64) -#define PLD_AUD_DIV1 (PLD_AUD_MMGPIO_BASE + 6) -#define PLD_AUD_DIV0 (PLD_AUD_MMGPIO_BASE + 5) -#define PLD_AUD_CLK_SEL1 (PLD_AUD_MMGPIO_BASE + 4) -#define PLD_AUD_CLK_SEL0 (PLD_AUD_MMGPIO_BASE + 3) -#define PLD_AUD_MIC_PWR (PLD_AUD_MMGPIO_BASE + 2) -#define PLD_AUD_MIC_GAIN (PLD_AUD_MMGPIO_BASE + 1) -#define PLD_AUD_CODEC_EN (PLD_AUD_MMGPIO_BASE + 0) - -#define PLD_CF (SYSPLD_PHYS_BASE + 0x000024) -#define PLD_CF_MMGPIO_BASE (P720T_MMGPIO_BASE + 72) -#define PLD_CF2_SLEEP (PLD_CF_MMGPIO_BASE + 5) -#define PLD_CF1_SLEEP (PLD_CF_MMGPIO_BASE + 4) -#define PLD_CF2_nPDREQ (PLD_CF_MMGPIO_BASE + 3) -#define PLD_CF1_nPDREQ (PLD_CF_MMGPIO_BASE + 2) -#define PLD_CF2_nIRQ (PLD_CF_MMGPIO_BASE + 1) -#define PLD_CF1_nIRQ (PLD_CF_MMGPIO_BASE + 0) - -#define PLD_SDC (SYSPLD_PHYS_BASE + 0x000028) -#define PLD_SDC_MMGPIO_BASE (P720T_MMGPIO_BASE + 80) -#define PLD_SDC_INT_EN (PLD_SDC_MMGPIO_BASE + 2) -#define PLD_SDC_WP (PLD_SDC_MMGPIO_BASE + 1) -#define PLD_SDC_CD (PLD_SDC_MMGPIO_BASE + 0) - -#define PLD_CODEC (SYSPLD_PHYS_BASE + 0x400000) -#define PLD_CODEC_MMGPIO_BASE (P720T_MMGPIO_BASE + 88) -#define PLD_CODEC_IRQ3 (PLD_CODEC_MMGPIO_BASE + 4) -#define PLD_CODEC_IRQ2 (PLD_CODEC_MMGPIO_BASE + 3) -#define PLD_CODEC_IRQ1 (PLD_CODEC_MMGPIO_BASE + 2) -#define PLD_CODEC_EN (PLD_CODEC_MMGPIO_BASE + 0) - -#define PLD_BRITE (SYSPLD_PHYS_BASE + 0x400004) -#define PLD_BRITE_MMGPIO_BASE (P720T_MMGPIO_BASE + 96) -#define PLD_BRITE_UP (PLD_BRITE_MMGPIO_BASE + 1) -#define PLD_BRITE_DN (PLD_BRITE_MMGPIO_BASE + 0) - -#define PLD_LCDEN (SYSPLD_PHYS_BASE + 0x400008) -#define PLD_LCDEN_MMGPIO_BASE (P720T_MMGPIO_BASE + 104) -#define PLD_LCDEN_EN (PLD_LCDEN_MMGPIO_BASE + 0) - -#define PLD_TCH (SYSPLD_PHYS_BASE + 0x400010) -#define PLD_TCH_MMGPIO_BASE (P720T_MMGPIO_BASE + 112) -#define PLD_TCH_PENIRQ (PLD_TCH_MMGPIO_BASE + 1) -#define PLD_TCH_EN (PLD_TCH_MMGPIO_BASE + 0) - -#define PLD_GPIO (SYSPLD_PHYS_BASE + 0x400014) -#define PLD_GPIO_MMGPIO_BASE (P720T_MMGPIO_BASE + 120) -#define PLD_GPIO2 (PLD_GPIO_MMGPIO_BASE + 2) -#define PLD_GPIO1 (PLD_GPIO_MMGPIO_BASE + 1) -#define PLD_GPIO0 (PLD_GPIO_MMGPIO_BASE + 0) - -static struct gpio p720t_gpios[] __initconst = { - { PLD_S1_ON, GPIOF_OUT_INIT_LOW, "PLD_S1_ON" }, - { PLD_S2_ON, GPIOF_OUT_INIT_LOW, "PLD_S2_ON" }, - { PLD_S3_ON, GPIOF_OUT_INIT_LOW, "PLD_S3_ON" }, - { PLD_S4_ON, GPIOF_OUT_INIT_LOW, "PLD_S4_ON" }, - { PLD_KBD_EN, GPIOF_OUT_INIT_LOW, "PLD_KBD_EN" }, - { PLD_SPI_EN, GPIOF_OUT_INIT_LOW, "PLD_SPI_EN" }, - { PLD_IO_USER, GPIOF_OUT_INIT_LOW, "PLD_IO_USER" }, - { PLD_IO_LED0, GPIOF_OUT_INIT_LOW, "PLD_IO_LED0" }, - { PLD_IO_LED1, GPIOF_OUT_INIT_LOW, "PLD_IO_LED1" }, - { PLD_IO_LED2, GPIOF_OUT_INIT_LOW, "PLD_IO_LED2" }, - { PLD_IO_LED3, GPIOF_OUT_INIT_LOW, "PLD_IO_LED3" }, - { PLD_IO_LEDEN, GPIOF_OUT_INIT_LOW, "PLD_IO_LEDEN" }, - { PLD_IRDA_EN, GPIOF_OUT_INIT_LOW, "PLD_IRDA_EN" }, - { PLD_COM1_EN, GPIOF_OUT_INIT_HIGH, "PLD_COM1_EN" }, - { PLD_COM2_EN, GPIOF_OUT_INIT_HIGH, "PLD_COM2_EN" }, - { PLD_CODEC_EN, GPIOF_OUT_INIT_LOW, "PLD_CODEC_EN" }, - { PLD_LCDEN_EN, GPIOF_OUT_INIT_LOW, "PLD_LCDEN_EN" }, - { PLD_TCH_EN, GPIOF_OUT_INIT_LOW, "PLD_TCH_EN" }, - { P720T_USERLED,GPIOF_OUT_INIT_LOW, "USER_LED" }, -}; - -static struct resource p720t_mmgpio_resource[] __initdata = { - DEFINE_RES_MEM_NAMED(0, 4, "dat"), -}; - -static struct bgpio_pdata p720t_mmgpio_pdata = { - .ngpio = 8, -}; - -static struct platform_device p720t_mmgpio __initdata = { - .name = "basic-mmio-gpio", - .id = -1, - .resource = p720t_mmgpio_resource, - .num_resources = ARRAY_SIZE(p720t_mmgpio_resource), - .dev = { - .platform_data = &p720t_mmgpio_pdata, - }, -}; - -static void __init p720t_mmgpio_init(void __iomem *addrbase, int gpiobase) -{ - p720t_mmgpio_resource[0].start = (unsigned long)addrbase; - p720t_mmgpio_pdata.base = gpiobase; - - platform_device_register(&p720t_mmgpio); -} - -static struct { - void __iomem *addrbase; - int gpiobase; -} mmgpios[] __initconst = { - { PLD_INT, PLD_INT_MMGPIO_BASE }, - { PLD_PWR, PLD_PWR_MMGPIO_BASE }, - { PLD_KBD, PLD_KBD_MMGPIO_BASE }, - { PLD_SPI, PLD_SPI_MMGPIO_BASE }, - { PLD_IO, PLD_IO_MMGPIO_BASE }, - { PLD_IRDA, PLD_IRDA_MMGPIO_BASE }, - { PLD_COM2, PLD_COM2_MMGPIO_BASE }, - { PLD_COM1, PLD_COM1_MMGPIO_BASE }, - { PLD_AUD, PLD_AUD_MMGPIO_BASE }, - { PLD_CF, PLD_CF_MMGPIO_BASE }, - { PLD_SDC, PLD_SDC_MMGPIO_BASE }, - { PLD_CODEC, PLD_CODEC_MMGPIO_BASE }, - { PLD_BRITE, PLD_BRITE_MMGPIO_BASE }, - { PLD_LCDEN, PLD_LCDEN_MMGPIO_BASE }, - { PLD_TCH, PLD_TCH_MMGPIO_BASE }, - { PLD_GPIO, PLD_GPIO_MMGPIO_BASE }, -}; - -static struct resource p720t_nand_resource[] __initdata = { - DEFINE_RES_MEM(P720T_NAND_BASE, SZ_4), -}; - -static struct mtd_partition p720t_nand_parts[] __initdata = { - { - .name = "Flash partition 1", - .offset = 0, - .size = SZ_2M, - }, - { - .name = "Flash partition 2", - .offset = MTDPART_OFS_APPEND, - .size = MTDPART_SIZ_FULL, - }, -}; - -static struct gpio_nand_platdata p720t_nand_pdata __initdata = { - .gpio_rdy = -1, - .gpio_nce = P720T_NAND_NCE, - .gpio_ale = P720T_NAND_ALE, - .gpio_cle = P720T_NAND_CLE, - .gpio_nwp = -1, - .chip_delay = 15, - .parts = p720t_nand_parts, - .num_parts = ARRAY_SIZE(p720t_nand_parts), -}; - -static struct platform_device p720t_nand_pdev __initdata = { - .name = "gpio-nand", - .id = -1, - .resource = p720t_nand_resource, - .num_resources = ARRAY_SIZE(p720t_nand_resource), - .dev = { - .platform_data = &p720t_nand_pdata, - }, -}; - -static void p720t_lcd_power_set(struct plat_lcd_data *pd, unsigned int power) -{ - if (power) { - gpio_set_value(PLD_LCDEN_EN, 1); - gpio_set_value(PLD_S1_ON, 1); - gpio_set_value(PLD_S2_ON, 1); - gpio_set_value(PLD_S4_ON, 1); - } else { - gpio_set_value(PLD_S1_ON, 0); - gpio_set_value(PLD_S2_ON, 0); - gpio_set_value(PLD_S4_ON, 0); - gpio_set_value(PLD_LCDEN_EN, 0); - } -} - -static struct plat_lcd_data p720t_lcd_power_pdata = { - .set_power = p720t_lcd_power_set, -}; - -static void p720t_lcd_backlight_set_intensity(int intensity) -{ - gpio_set_value(PLD_S3_ON, intensity); -} - -static struct generic_bl_info p720t_lcd_backlight_pdata = { - .name = "lcd-backlight.0", - .default_intensity = 0x01, - .max_intensity = 0x01, - .set_bl_intensity = p720t_lcd_backlight_set_intensity, -}; - -static void __init -fixup_p720t(struct tag *tag, char **cmdline) -{ - /* - * Our bootloader doesn't setup any tags (yet). - */ - if (tag->hdr.tag != ATAG_CORE) { - tag->hdr.tag = ATAG_CORE; - tag->hdr.size = tag_size(tag_core); - tag->u.core.flags = 0; - tag->u.core.pagesize = PAGE_SIZE; - tag->u.core.rootdev = 0x0100; - - tag = tag_next(tag); - tag->hdr.tag = ATAG_MEM; - tag->hdr.size = tag_size(tag_mem32); - tag->u.mem.size = 4096; - tag->u.mem.start = PHYS_OFFSET; - - tag = tag_next(tag); - tag->hdr.tag = ATAG_NONE; - tag->hdr.size = 0; - } -} - -static struct gpio_led p720t_gpio_leds[] = { - { - .name = "User LED", - .default_trigger = "heartbeat", - .gpio = P720T_USERLED, - }, -}; - -static struct gpio_led_platform_data p720t_gpio_led_pdata __initdata = { - .leds = p720t_gpio_leds, - .num_leds = ARRAY_SIZE(p720t_gpio_leds), -}; - -static void __init p720t_init(void) -{ - int i; - - clps711x_devices_init(); - - for (i = 0; i < ARRAY_SIZE(mmgpios); i++) - p720t_mmgpio_init(mmgpios[i].addrbase, mmgpios[i].gpiobase); - - platform_device_register(&p720t_nand_pdev); -} - -static void __init p720t_init_late(void) -{ - WARN_ON(gpio_request_array(p720t_gpios, ARRAY_SIZE(p720t_gpios))); - - platform_device_register_data(NULL, "platform-lcd", 0, - &p720t_lcd_power_pdata, - sizeof(p720t_lcd_power_pdata)); - platform_device_register_data(NULL, "generic-bl", 0, - &p720t_lcd_backlight_pdata, - sizeof(p720t_lcd_backlight_pdata)); - platform_device_register_simple("video-clps711x", 0, NULL, 0); - platform_device_register_data(NULL, "leds-gpio", 0, - &p720t_gpio_led_pdata, - sizeof(p720t_gpio_led_pdata)); -} - -MACHINE_START(P720T, "ARM-Prospector720T") - /* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */ - .atag_offset = 0x100, - .fixup = fixup_p720t, - .map_io = clps711x_map_io, - .init_irq = clps711x_init_irq, - .init_time = clps711x_timer_init, - .init_machine = p720t_init, - .init_late = p720t_init_late, - .restart = clps711x_restart, -MACHINE_END diff --git a/arch/arm/mach-clps711x/common.c b/arch/arm/mach-clps711x/common.c deleted file mode 100644 index 6466da8f3c11..000000000000 --- a/arch/arm/mach-clps711x/common.c +++ /dev/null @@ -1,65 +0,0 @@ -/* - * linux/arch/arm/mach-clps711x/core.c - * - * Core support for the CLPS711x-based machines. - * - * Copyright (C) 2001,2011 Deep Blue Solutions Ltd - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/init.h> -#include <linux/sizes.h> - -#include <asm/mach/map.h> -#include <asm/system_misc.h> - -#include <mach/hardware.h> - -#include "common.h" - -/* - * This maps the generic CLPS711x registers - */ -static struct map_desc clps711x_io_desc[] __initdata = { - { - .virtual = (unsigned long)CLPS711X_VIRT_BASE, - .pfn = __phys_to_pfn(CLPS711X_PHYS_BASE), - .length = 48 * SZ_1K, - .type = MT_DEVICE, - } -}; - -void __init clps711x_map_io(void) -{ - iotable_init(clps711x_io_desc, ARRAY_SIZE(clps711x_io_desc)); -} - -void __init clps711x_init_irq(void) -{ - clps711x_intc_init(CLPS711X_PHYS_BASE, SZ_16K); -} - -void __init clps711x_timer_init(void) -{ - clps711x_clk_init(CLPS711X_VIRT_BASE); - clps711x_clksrc_init(CLPS711X_VIRT_BASE + TC1D, - CLPS711X_VIRT_BASE + TC2D, IRQ_TC2OI); -} - -void clps711x_restart(enum reboot_mode mode, const char *cmd) -{ - soft_restart(0); -} diff --git a/arch/arm/mach-clps711x/common.h b/arch/arm/mach-clps711x/common.h deleted file mode 100644 index 370200b26333..000000000000 --- a/arch/arm/mach-clps711x/common.h +++ /dev/null @@ -1,23 +0,0 @@ -/* - * linux/arch/arm/mach-clps711x/common.h - * - * Common bits. - */ - -#include <linux/reboot.h> - -#define CLPS711X_NR_GPIO (4 * 8 + 3) -#define CLPS711X_GPIO(prt, bit) ((prt) * 8 + (bit)) - -extern void clps711x_map_io(void); -extern void clps711x_init_irq(void); -extern void clps711x_timer_init(void); -extern void clps711x_restart(enum reboot_mode mode, const char *cmd); - -/* drivers/irqchip/irq-clps711x.c */ -void clps711x_intc_init(phys_addr_t, resource_size_t); -/* drivers/clk/clk-clps711x.c */ -void clps711x_clk_init(void __iomem *base); -/* drivers/clocksource/clps711x-timer.c */ -void clps711x_clksrc_init(void __iomem *tc1_base, void __iomem *tc2_base, - unsigned int irq); diff --git a/arch/arm/mach-clps711x/devices.c b/arch/arm/mach-clps711x/devices.c deleted file mode 100644 index 77a9617c216d..000000000000 --- a/arch/arm/mach-clps711x/devices.c +++ /dev/null @@ -1,149 +0,0 @@ -/* - * CLPS711X common devices definitions - * - * Author: Alexander Shiyan <shc_work@mail.ru>, 2013-2014 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#include <linux/io.h> -#include <linux/of_fdt.h> -#include <linux/platform_device.h> -#include <linux/random.h> -#include <linux/sizes.h> -#include <linux/slab.h> -#include <linux/sys_soc.h> - -#include <asm/system_info.h> - -#include <mach/hardware.h> - -static const struct resource clps711x_cpuidle_res __initconst = - DEFINE_RES_MEM(CLPS711X_PHYS_BASE + HALT, SZ_128); - -static void __init clps711x_add_cpuidle(void) -{ - platform_device_register_simple("clps711x-cpuidle", PLATFORM_DEVID_NONE, - &clps711x_cpuidle_res, 1); -} - -static const phys_addr_t clps711x_gpios[][2] __initconst = { - { PADR, PADDR }, - { PBDR, PBDDR }, - { PCDR, PCDDR }, - { PDDR, PDDDR }, - { PEDR, PEDDR }, -}; - -static void __init clps711x_add_gpio(void) -{ - unsigned i; - struct resource gpio_res[2]; - - memset(gpio_res, 0, sizeof(gpio_res)); - - gpio_res[0].flags = IORESOURCE_MEM; - gpio_res[1].flags = IORESOURCE_MEM; - - for (i = 0; i < ARRAY_SIZE(clps711x_gpios); i++) { - gpio_res[0].start = CLPS711X_PHYS_BASE + clps711x_gpios[i][0]; - gpio_res[0].end = gpio_res[0].start; - gpio_res[1].start = CLPS711X_PHYS_BASE + clps711x_gpios[i][1]; - gpio_res[1].end = gpio_res[1].start; - - platform_device_register_simple("clps711x-gpio", i, - gpio_res, ARRAY_SIZE(gpio_res)); - } -} - -const struct resource clps711x_syscon_res[] __initconst = { - /* SYSCON1, SYSFLG1 */ - DEFINE_RES_MEM(CLPS711X_PHYS_BASE + SYSCON1, SZ_128), - /* SYSCON2, SYSFLG2 */ - DEFINE_RES_MEM(CLPS711X_PHYS_BASE + SYSCON2, SZ_128), - /* SYSCON3 */ - DEFINE_RES_MEM(CLPS711X_PHYS_BASE + SYSCON3, SZ_64), -}; - -static void __init clps711x_add_syscon(void) -{ - unsigned i; - - for (i = 0; i < ARRAY_SIZE(clps711x_syscon_res); i++) - platform_device_register_simple("syscon", i + 1, - &clps711x_syscon_res[i], 1); -} - -static const struct resource clps711x_uart1_res[] __initconst = { - DEFINE_RES_MEM(CLPS711X_PHYS_BASE + UARTDR1, SZ_128), - DEFINE_RES_IRQ(IRQ_UTXINT1), - DEFINE_RES_IRQ(IRQ_URXINT1), -}; - -static const struct resource clps711x_uart2_res[] __initconst = { - DEFINE_RES_MEM(CLPS711X_PHYS_BASE + UARTDR2, SZ_128), - DEFINE_RES_IRQ(IRQ_UTXINT2), - DEFINE_RES_IRQ(IRQ_URXINT2), -}; - -static void __init clps711x_add_uart(void) -{ - platform_device_register_simple("clps711x-uart", 0, clps711x_uart1_res, - ARRAY_SIZE(clps711x_uart1_res)); - platform_device_register_simple("clps711x-uart", 1, clps711x_uart2_res, - ARRAY_SIZE(clps711x_uart2_res)); -}; - -static void __init clps711x_soc_init(void) -{ - struct soc_device_attribute *soc_dev_attr; - struct soc_device *soc_dev; - void __iomem *base; - u32 id[5]; - - base = ioremap(CLPS711X_PHYS_BASE, SZ_32K); - if (!base) - return; - - id[0] = readl(base + UNIQID); - id[1] = readl(base + RANDID0); - id[2] = readl(base + RANDID1); - id[3] = readl(base + RANDID2); - id[4] = readl(base + RANDID3); - system_rev = SYSFLG1_VERID(readl(base + SYSFLG1)); - - add_device_randomness(id, sizeof(id)); - - system_serial_low = id[0]; - - soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL); - if (!soc_dev_attr) - goto out_unmap; - - soc_dev_attr->machine = of_flat_dt_get_machine_name(); - soc_dev_attr->family = "Cirrus Logic CLPS711X"; - soc_dev_attr->revision = kasprintf(GFP_KERNEL, "%u", system_rev); - soc_dev_attr->soc_id = kasprintf(GFP_KERNEL, "%08x", id[0]); - - soc_dev = soc_device_register(soc_dev_attr); - if (IS_ERR(soc_dev)) { - kfree(soc_dev_attr->revision); - kfree(soc_dev_attr->soc_id); - kfree(soc_dev_attr); - } - -out_unmap: - iounmap(base); -} - -void __init clps711x_devices_init(void) -{ - clps711x_add_cpuidle(); - clps711x_add_gpio(); - clps711x_add_syscon(); - clps711x_add_uart(); - clps711x_soc_init(); -} diff --git a/arch/arm/mach-clps711x/devices.h b/arch/arm/mach-clps711x/devices.h deleted file mode 100644 index a5efc1744b84..000000000000 --- a/arch/arm/mach-clps711x/devices.h +++ /dev/null @@ -1,12 +0,0 @@ -/* - * CLPS711X common devices definitions - * - * Copyright (C) 2013 Alexander Shiyan <shc_work@mail.ru> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -void clps711x_devices_init(void); diff --git a/arch/arm/mach-cns3xxx/Kconfig b/arch/arm/mach-cns3xxx/Kconfig index eb14a0ff0093..5fd836be2701 100644 --- a/arch/arm/mach-cns3xxx/Kconfig +++ b/arch/arm/mach-cns3xxx/Kconfig @@ -2,7 +2,6 @@ menuconfig ARCH_CNS3XXX bool "Cavium Networks CNS3XXX family" depends on ARCH_MULTI_V6 select ARM_GIC - select PCI_DOMAINS if PCI help Support for Cavium Networks CNS3XXX platform. diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index b085855c1d0b..0bb63b8d21e7 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -127,8 +127,6 @@ config SOC_EXYNOS5440 select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE select HAVE_ARM_ARCH_TIMER select AUTO_ZRELADDR - select MIGHT_HAVE_PCI - select PCI_DOMAINS if PCI select PINCTRL_EXYNOS5440 select PM_OPP help diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c index 3750575c73c5..06332f626565 100644 --- a/arch/arm/mach-exynos/suspend.c +++ b/arch/arm/mach-exynos/suspend.c @@ -255,6 +255,12 @@ static int __init exynos_pmu_irq_init(struct device_node *node, return -ENOMEM; } + /* + * Clear the OF_POPULATED flag set in of_irq_init so that + * later the Exynos PMU platform device won't be skipped. + */ + of_node_clear_flag(node, OF_POPULATED); + return 0; } diff --git a/arch/arm/mach-footbridge/include/mach/hardware.h b/arch/arm/mach-footbridge/include/mach/hardware.h index 02f6d7a706b1..20d5ad781fe2 100644 --- a/arch/arm/mach-footbridge/include/mach/hardware.h +++ b/arch/arm/mach-footbridge/include/mach/hardware.h @@ -59,7 +59,7 @@ #define XBUS_SWITCH_J17_11 ((*XBUS_SWITCH) & (1 << 5)) #define XBUS_SWITCH_J17_9 ((*XBUS_SWITCH) & (1 << 6)) -#define UNCACHEABLE_ADDR (ARMCSR_BASE + 0x108) +#define UNCACHEABLE_ADDR (ARMCSR_BASE + 0x108) /* CSR_ROMBASEMASK */ /* PIC irq control */ diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig index ee9a318cab31..9155b639c9aa 100644 --- a/arch/arm/mach-imx/Kconfig +++ b/arch/arm/mach-imx/Kconfig @@ -64,13 +64,6 @@ config IMX_HAVE_IOMUX_V1 config ARCH_MXC_IOMUX_V3 bool -config SOC_IMX1 - bool - select CPU_ARM920T - select IMX_HAVE_IOMUX_V1 - select MXC_AVIC - select PINCTRL_IMX1 - config SOC_IMX21 bool select CPU_ARM926T @@ -88,7 +81,6 @@ config SOC_IMX31 bool select CPU_V6 select MXC_AVIC - select SMP_ON_UP if SMP config SOC_IMX35 bool @@ -96,35 +88,6 @@ config SOC_IMX35 select HAVE_EPIT select MXC_AVIC select PINCTRL_IMX35 - select SMP_ON_UP if SMP - -if ARCH_MULTI_V4T - -comment "MX1 platforms:" - -config MACH_SCB9328 - bool "Synertronixx scb9328" - select IMX_HAVE_PLATFORM_IMX_UART - select SOC_IMX1 - help - Say Y here if you are using a Synertronixx scb9328 board - -config MACH_APF9328 - bool "APF9328" - select IMX_HAVE_PLATFORM_IMX_I2C - select IMX_HAVE_PLATFORM_IMX_UART - select SOC_IMX1 - help - Say Yes here if you are using the Armadeus APF9328 development board - -config MACH_IMX1_DT - bool "Support i.MX1 platforms from device tree" - select SOC_IMX1 - help - Include support for Freescale i.MX1 based platforms - using the device tree for discovery. - -endif if ARCH_MULTI_V5 @@ -461,6 +424,18 @@ endif comment "Device tree only" +if ARCH_MULTI_V4T + +config SOC_IMX1 + bool "i.MX1 support" + select CPU_ARM920T + select MXC_AVIC + select PINCTRL_IMX1 + help + This enables support for Freescale i.MX1 processor + +endif + if ARCH_MULTI_V5 config SOC_IMX25 @@ -523,7 +498,6 @@ config SOC_IMX6Q select ARM_ERRATA_764369 if SMP select HAVE_ARM_SCU if SMP select HAVE_ARM_TWD - select PCI_DOMAINS if PCI select PINCTRL_IMX6Q select SOC_IMX6 @@ -569,7 +543,6 @@ config SOC_LS1021A bool "Freescale LS1021A support" select ARM_GIC select HAVE_ARM_ARCH_TIMER - select PCI_DOMAINS if PCI select ZONE_DMA if ARM_LPAE help This enables support for Freescale LS1021A processor. @@ -585,7 +558,6 @@ config SOC_VF610 select ARM_GIC if ARCH_MULTI_V7 select PINCTRL_VF610 select PL310_ERRATA_769419 if CACHE_L2X0 - select SMP_ON_UP if SMP help This enables support for Freescale Vybrid VF610 processor. diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile index 574e5b8c6a65..cab128913e72 100644 --- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -1,6 +1,5 @@ obj-y := cpu.o system.o irq-common.o -obj-$(CONFIG_SOC_IMX1) += mm-imx1.o obj-$(CONFIG_SOC_IMX21) += mm-imx21.o obj-$(CONFIG_SOC_IMX25) += cpu-imx25.o mach-imx25.o pm-imx25.o @@ -36,11 +35,6 @@ obj-y += ssi-fiq.o obj-y += ssi-fiq-ksym.o endif -# i.MX1 based machines -obj-$(CONFIG_MACH_SCB9328) += mach-scb9328.o -obj-$(CONFIG_MACH_APF9328) += mach-apf9328.o -obj-$(CONFIG_MACH_IMX1_DT) += imx1-dt.o - # i.MX21 based machines obj-$(CONFIG_MACH_MX21ADS) += mach-mx21ads.o @@ -94,6 +88,7 @@ obj-$(CONFIG_SOC_IMX53) += suspend-imx53.o endif obj-$(CONFIG_SOC_IMX6) += pm-imx6.o +obj-$(CONFIG_SOC_IMX1) += mach-imx1.o obj-$(CONFIG_SOC_IMX50) += mach-imx50.o obj-$(CONFIG_SOC_IMX51) += mach-imx51.o obj-$(CONFIG_SOC_IMX53) += mach-imx53.o diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h index fb644304446c..c4436d9c52ff 100644 --- a/arch/arm/mach-imx/common.h +++ b/arch/arm/mach-imx/common.h @@ -21,29 +21,24 @@ struct device_node; enum mxc_cpu_pwr_mode; struct of_device_id; -void mx1_map_io(void); void mx21_map_io(void); void mx27_map_io(void); void mx31_map_io(void); void mx35_map_io(void); -void imx1_init_early(void); void imx21_init_early(void); void imx27_init_early(void); void imx31_init_early(void); void imx35_init_early(void); void mxc_init_irq(void __iomem *); -void mx1_init_irq(void); void mx21_init_irq(void); void mx27_init_irq(void); void mx31_init_irq(void); void mx35_init_irq(void); -void imx1_soc_init(void); void imx21_soc_init(void); void imx27_soc_init(void); void imx31_soc_init(void); void imx35_soc_init(void); void epit_timer_init(void __iomem *base, int irq); -int mx1_clocks_init(unsigned long fref); int mx21_clocks_init(unsigned long lref, unsigned long fref); int mx27_clocks_init(unsigned long fref); int mx31_clocks_init(unsigned long fref); diff --git a/arch/arm/mach-imx/devices-imx1.h b/arch/arm/mach-imx/devices-imx1.h deleted file mode 100644 index f9b5afc6bcd1..000000000000 --- a/arch/arm/mach-imx/devices-imx1.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * Copyright (C) 2010 Pengutronix - * Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de> - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. - */ -#include "devices/devices-common.h" - -extern const struct imx_imx_fb_data imx1_imx_fb_data; -#define imx1_add_imx_fb(pdata) \ - imx_add_imx_fb(&imx1_imx_fb_data, pdata) - -extern const struct imx_imx_i2c_data imx1_imx_i2c_data; -#define imx1_add_imx_i2c(pdata) \ - imx_add_imx_i2c(&imx1_imx_i2c_data, pdata) - -extern const struct imx_imx_uart_3irq_data imx1_imx_uart_data[]; -#define imx1_add_imx_uart(id, pdata) \ - imx_add_imx_uart_3irq(&imx1_imx_uart_data[id], pdata) -#define imx1_add_imx_uart0(pdata) imx1_add_imx_uart(0, pdata) -#define imx1_add_imx_uart1(pdata) imx1_add_imx_uart(1, pdata) - -extern const struct imx_spi_imx_data imx1_cspi_data[]; -#define imx1_add_cspi(id, pdata) \ - imx_add_spi_imx(&imx1_cspi_data[id], pdata) - -#define imx1_add_spi_imx0(pdata) imx1_add_cspi(0, pdata) -#define imx1_add_spi_imx1(pdata) imx1_add_cspi(1, pdata) diff --git a/arch/arm/mach-imx/devices/Makefile b/arch/arm/mach-imx/devices/Makefile index e5cf587bc1a0..aa6cee870795 100644 --- a/arch/arm/mach-imx/devices/Makefile +++ b/arch/arm/mach-imx/devices/Makefile @@ -20,7 +20,6 @@ obj-$(CONFIG_IMX_HAVE_PLATFORM_MX2_CAMERA) += platform-mx2-camera.o obj-$(CONFIG_IMX_HAVE_PLATFORM_MXC_EHCI) += platform-mxc-ehci.o obj-$(CONFIG_IMX_HAVE_PLATFORM_MXC_MMC) += platform-mxc-mmc.o obj-$(CONFIG_IMX_HAVE_PLATFORM_MXC_NAND) += platform-mxc_nand.o -obj-$(CONFIG_IMX_HAVE_PLATFORM_MXC_RNGA) += platform-mxc_rnga.o obj-$(CONFIG_IMX_HAVE_PLATFORM_MXC_RTC) += platform-mxc_rtc.o obj-$(CONFIG_IMX_HAVE_PLATFORM_MXC_W1) += platform-mxc_w1.o obj-$(CONFIG_IMX_HAVE_PLATFORM_SDHCI_ESDHC_IMX) += platform-sdhci-esdhc-imx.o diff --git a/arch/arm/mach-imx/devices/devices-common.h b/arch/arm/mach-imx/devices/devices-common.h index 09cebd8cef2b..6920e356f4e5 100644 --- a/arch/arm/mach-imx/devices/devices-common.h +++ b/arch/arm/mach-imx/devices/devices-common.h @@ -154,18 +154,6 @@ struct platform_device *__init imx_add_imx_ssi( const struct imx_ssi_platform_data *pdata); #include <linux/platform_data/serial-imx.h> -struct imx_imx_uart_3irq_data { - int id; - resource_size_t iobase; - resource_size_t iosize; - resource_size_t irqrx; - resource_size_t irqtx; - resource_size_t irqrts; -}; -struct platform_device *__init imx_add_imx_uart_3irq( - const struct imx_imx_uart_3irq_data *data, - const struct imxuart_platform_data *pdata); - struct imx_imx_uart_1irq_data { int id; resource_size_t iobase; diff --git a/arch/arm/mach-imx/devices/platform-imx-fb.c b/arch/arm/mach-imx/devices/platform-imx-fb.c index 7df6328306f9..aa00272252e0 100644 --- a/arch/arm/mach-imx/devices/platform-imx-fb.c +++ b/arch/arm/mach-imx/devices/platform-imx-fb.c @@ -19,11 +19,6 @@ .irq = soc ## _INT_LCDC, \ } -#ifdef CONFIG_SOC_IMX1 -const struct imx_imx_fb_data imx1_imx_fb_data __initconst = - imx_imx_fb_data_entry_single(MX1, "imx1-fb", SZ_4K); -#endif /* ifdef CONFIG_SOC_IMX1 */ - #ifdef CONFIG_SOC_IMX21 const struct imx_imx_fb_data imx21_imx_fb_data __initconst = imx_imx_fb_data_entry_single(MX21, "imx21-fb", SZ_4K); diff --git a/arch/arm/mach-imx/devices/platform-imx-i2c.c b/arch/arm/mach-imx/devices/platform-imx-i2c.c index ae9791522fc8..9822bedb5d09 100644 --- a/arch/arm/mach-imx/devices/platform-imx-i2c.c +++ b/arch/arm/mach-imx/devices/platform-imx-i2c.c @@ -21,11 +21,6 @@ #define imx_imx_i2c_data_entry(soc, _devid, _id, _hwid, _size) \ [_id] = imx_imx_i2c_data_entry_single(soc, _devid, _id, _hwid, _size) -#ifdef CONFIG_SOC_IMX1 -const struct imx_imx_i2c_data imx1_imx_i2c_data __initconst = - imx_imx_i2c_data_entry_single(MX1, "imx1-i2c", 0, , SZ_4K); -#endif /* ifdef CONFIG_SOC_IMX1 */ - #ifdef CONFIG_SOC_IMX21 const struct imx_imx_i2c_data imx21_imx_i2c_data __initconst = imx_imx_i2c_data_entry_single(MX21, "imx21-i2c", 0, , SZ_4K); diff --git a/arch/arm/mach-imx/devices/platform-imx-uart.c b/arch/arm/mach-imx/devices/platform-imx-uart.c index 6962cff4a950..e3c89e9caf93 100644 --- a/arch/arm/mach-imx/devices/platform-imx-uart.c +++ b/arch/arm/mach-imx/devices/platform-imx-uart.c @@ -27,15 +27,6 @@ .irq = soc ## _INT_UART ## _hwid, \ } -#ifdef CONFIG_SOC_IMX1 -const struct imx_imx_uart_3irq_data imx1_imx_uart_data[] __initconst = { -#define imx1_imx_uart_data_entry(_id, _hwid) \ - imx_imx_uart_3irq_data_entry(MX1, _id, _hwid, 0xd0) - imx1_imx_uart_data_entry(0, 1), - imx1_imx_uart_data_entry(1, 2), -}; -#endif /* ifdef CONFIG_SOC_IMX1 */ - #ifdef CONFIG_SOC_IMX21 const struct imx_imx_uart_1irq_data imx21_imx_uart_data[] __initconst = { #define imx21_imx_uart_data_entry(_id, _hwid) \ @@ -82,34 +73,6 @@ const struct imx_imx_uart_1irq_data imx35_imx_uart_data[] __initconst = { }; #endif /* ifdef CONFIG_SOC_IMX35 */ -struct platform_device *__init imx_add_imx_uart_3irq( - const struct imx_imx_uart_3irq_data *data, - const struct imxuart_platform_data *pdata) -{ - struct resource res[] = { - { - .start = data->iobase, - .end = data->iobase + data->iosize - 1, - .flags = IORESOURCE_MEM, - }, { - .start = data->irqrx, - .end = data->irqrx, - .flags = IORESOURCE_IRQ, - }, { - .start = data->irqtx, - .end = data->irqtx, - .flags = IORESOURCE_IRQ, - }, { - .start = data->irqrts, - .end = data->irqrx, - .flags = IORESOURCE_IRQ, - }, - }; - - return imx_add_platform_device("imx1-uart", data->id, res, - ARRAY_SIZE(res), pdata, sizeof(*pdata)); -} - struct platform_device *__init imx_add_imx_uart_1irq( const struct imx_imx_uart_1irq_data *data, const struct imxuart_platform_data *pdata) diff --git a/arch/arm/mach-imx/devices/platform-spi_imx.c b/arch/arm/mach-imx/devices/platform-spi_imx.c index 5e9707b47f92..d93c446c9c02 100644 --- a/arch/arm/mach-imx/devices/platform-spi_imx.c +++ b/arch/arm/mach-imx/devices/platform-spi_imx.c @@ -21,15 +21,6 @@ #define imx_spi_imx_data_entry(soc, type, devid, id, hwid, size) \ [id] = imx_spi_imx_data_entry_single(soc, type, devid, id, hwid, size) -#ifdef CONFIG_SOC_IMX1 -const struct imx_spi_imx_data imx1_cspi_data[] __initconst = { -#define imx1_cspi_data_entry(_id, _hwid) \ - imx_spi_imx_data_entry(MX1, CSPI, "imx1-cspi", _id, _hwid, SZ_4K) - imx1_cspi_data_entry(0, 1), - imx1_cspi_data_entry(1, 2), -}; -#endif - #ifdef CONFIG_SOC_IMX21 const struct imx_spi_imx_data imx21_cspi_data[] __initconst = { #define imx21_cspi_data_entry(_id, _hwid) \ diff --git a/arch/arm/mach-imx/hardware.h b/arch/arm/mach-imx/hardware.h index d737f95ebb07..90e10cbd8fd1 100644 --- a/arch/arm/mach-imx/hardware.h +++ b/arch/arm/mach-imx/hardware.h @@ -112,7 +112,6 @@ #include "mx2x.h" #include "mx21.h" #include "mx27.h" -#include "mx1.h" #define imx_map_entry(soc, name, _type) { \ .virtual = soc ## _IO_P2V(soc ## _ ## name ## _BASE_ADDR), \ @@ -121,7 +120,7 @@ .type = _type, \ } -/* There's a off-by-one betweem the gpio bank number and the gpiochip */ +/* There's an off-by-one between the gpio bank number and the gpiochip */ /* range e.g. GPIO_1_5 is gpio 5 under linux */ #define IMX_GPIO_NR(bank, nr) (((bank) - 1) * 32 + (nr)) diff --git a/arch/arm/mach-imx/iomux-mx1.h b/arch/arm/mach-imx/iomux-mx1.h deleted file mode 100644 index 95f4681d85d7..000000000000 --- a/arch/arm/mach-imx/iomux-mx1.h +++ /dev/null @@ -1,155 +0,0 @@ -/* - * Copyright (C) 2008 by Sascha Hauer <kernel@pengutronix.de> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301, USA. - */ -#ifndef __MACH_IOMUX_MX1_H__ -#define __MACH_IOMUX_MX1_H__ - -#include "iomux-v1.h" - -#define PA0_AIN_SPI2_CLK (GPIO_PORTA | GPIO_AIN | GPIO_OUT | 0) -#define PA0_AF_ETMTRACESYNC (GPIO_PORTA | GPIO_AF | 0) -#define PA1_AOUT_SPI2_RXD (GPIO_PORTA | GPIO_AOUT | GPIO_IN | 1) -#define PA1_PF_TIN (GPIO_PORTA | GPIO_PF | 1) -#define PA2_PF_PWM0 (GPIO_PORTA | GPIO_PF | GPIO_OUT | 2) -#define PA3_PF_CSI_MCLK (GPIO_PORTA | GPIO_PF | 3) -#define PA4_PF_CSI_D0 (GPIO_PORTA | GPIO_PF | 4) -#define PA5_PF_CSI_D1 (GPIO_PORTA | GPIO_PF | 5) -#define PA6_PF_CSI_D2 (GPIO_PORTA | GPIO_PF | 6) -#define PA7_PF_CSI_D3 (GPIO_PORTA | GPIO_PF | 7) -#define PA8_PF_CSI_D4 (GPIO_PORTA | GPIO_PF | 8) -#define PA9_PF_CSI_D5 (GPIO_PORTA | GPIO_PF | 9) -#define PA10_PF_CSI_D6 (GPIO_PORTA | GPIO_PF | 10) -#define PA11_PF_CSI_D7 (GPIO_PORTA | GPIO_PF | 11) -#define PA12_PF_CSI_VSYNC (GPIO_PORTA | GPIO_PF | 12) -#define PA13_PF_CSI_HSYNC (GPIO_PORTA | GPIO_PF | 13) -#define PA14_PF_CSI_PIXCLK (GPIO_PORTA | GPIO_PF | 14) -#define PA15_PF_I2C_SDA (GPIO_PORTA | GPIO_PF | GPIO_OUT | 15) -#define PA16_PF_I2C_SCL (GPIO_PORTA | GPIO_PF | GPIO_OUT | 16) -#define PA17_AF_ETMTRACEPKT4 (GPIO_PORTA | GPIO_AF | 17) -#define PA17_AIN_SPI2_SS (GPIO_PORTA | GPIO_AIN | GPIO_OUT | 17) -#define PA18_AF_ETMTRACEPKT5 (GPIO_PORTA | GPIO_AF | 18) -#define PA19_AF_ETMTRACEPKT6 (GPIO_PORTA | GPIO_AF | 19) -#define PA20_AF_ETMTRACEPKT7 (GPIO_PORTA | GPIO_AF | 20) -#define PA21_PF_A0 (GPIO_PORTA | GPIO_PF | 21) -#define PA22_PF_CS4 (GPIO_PORTA | GPIO_PF | 22) -#define PA23_PF_CS5 (GPIO_PORTA | GPIO_PF | 23) -#define PA24_PF_A16 (GPIO_PORTA | GPIO_PF | 24) -#define PA24_AF_ETMTRACEPKT0 (GPIO_PORTA | GPIO_AF | 24) -#define PA25_PF_A17 (GPIO_PORTA | GPIO_PF | 25) -#define PA25_AF_ETMTRACEPKT1 (GPIO_PORTA | GPIO_AF | 25) -#define PA26_PF_A18 (GPIO_PORTA | GPIO_PF | 26) -#define PA26_AF_ETMTRACEPKT2 (GPIO_PORTA | GPIO_AF | 26) -#define PA27_PF_A19 (GPIO_PORTA | GPIO_PF | 27) -#define PA27_AF_ETMTRACEPKT3 (GPIO_PORTA | GPIO_AF | 27) -#define PA28_PF_A20 (GPIO_PORTA | GPIO_PF | 28) -#define PA28_AF_ETMPIPESTAT0 (GPIO_PORTA | GPIO_AF | 28) -#define PA29_PF_A21 (GPIO_PORTA | GPIO_PF | 29) -#define PA29_AF_ETMPIPESTAT1 (GPIO_PORTA | GPIO_AF | 29) -#define PA30_PF_A22 (GPIO_PORTA | GPIO_PF | 30) -#define PA30_AF_ETMPIPESTAT2 (GPIO_PORTA | GPIO_AF | 30) -#define PA31_PF_A23 (GPIO_PORTA | GPIO_PF | 31) -#define PA31_AF_ETMTRACECLK (GPIO_PORTA | GPIO_AF | 31) -#define PB8_PF_SD_DAT0 (GPIO_PORTB | GPIO_PF | GPIO_PUEN | 8) -#define PB8_AF_MS_PIO (GPIO_PORTB | GPIO_AF | 8) -#define PB9_PF_SD_DAT1 (GPIO_PORTB | GPIO_PF | GPIO_PUEN | 9) -#define PB9_AF_MS_PI1 (GPIO_PORTB | GPIO_AF | 9) -#define PB10_PF_SD_DAT2 (GPIO_PORTB | GPIO_PF | GPIO_PUEN | 10) -#define PB10_AF_MS_SCLKI (GPIO_PORTB | GPIO_AF | 10) -#define PB11_PF_SD_DAT3 (GPIO_PORTB | GPIO_PF | 11) -#define PB11_AF_MS_SDIO (GPIO_PORTB | GPIO_AF | 11) -#define PB12_PF_SD_CLK (GPIO_PORTB | GPIO_PF | 12) -#define PB12_AF_MS_SCLK0 (GPIO_PORTB | GPIO_AF | 12) -#define PB13_PF_SD_CMD (GPIO_PORTB | GPIO_PF | GPIO_PUEN | 13) -#define PB13_AF_MS_BS (GPIO_PORTB | GPIO_AF | 13) -#define PB14_AF_SSI_RXFS (GPIO_PORTB | GPIO_AF | 14) -#define PB15_AF_SSI_RXCLK (GPIO_PORTB | GPIO_AF | 15) -#define PB16_AF_SSI_RXDAT (GPIO_PORTB | GPIO_AF | GPIO_IN | 16) -#define PB17_AF_SSI_TXDAT (GPIO_PORTB | GPIO_AF | GPIO_OUT | 17) -#define PB18_AF_SSI_TXFS (GPIO_PORTB | GPIO_AF | 18) -#define PB19_AF_SSI_TXCLK (GPIO_PORTB | GPIO_AF | 19) -#define PB20_PF_USBD_AFE (GPIO_PORTB | GPIO_PF | 20) -#define PB21_PF_USBD_OE (GPIO_PORTB | GPIO_PF | 21) -#define PB22_PF_USBD_RCV (GPIO_PORTB | GPIO_PF | 22) -#define PB23_PF_USBD_SUSPND (GPIO_PORTB | GPIO_PF | 23) -#define PB24_PF_USBD_VP (GPIO_PORTB | GPIO_PF | 24) -#define PB25_PF_USBD_VM (GPIO_PORTB | GPIO_PF | 25) -#define PB26_PF_USBD_VPO (GPIO_PORTB | GPIO_PF | 26) -#define PB27_PF_USBD_VMO (GPIO_PORTB | GPIO_PF | 27) -#define PB28_PF_UART2_CTS (GPIO_PORTB | GPIO_PF | GPIO_OUT | 28) -#define PB29_PF_UART2_RTS (GPIO_PORTB | GPIO_PF | GPIO_IN | 29) -#define PB30_PF_UART2_TXD (GPIO_PORTB | GPIO_PF | GPIO_OUT | 30) -#define PB31_PF_UART2_RXD (GPIO_PORTB | GPIO_PF | GPIO_IN | 31) -#define PC3_PF_SSI_RXFS (GPIO_PORTC | GPIO_PF | 3) -#define PC4_PF_SSI_RXCLK (GPIO_PORTC | GPIO_PF | 4) -#define PC5_PF_SSI_RXDAT (GPIO_PORTC | GPIO_PF | GPIO_IN | 5) -#define PC6_PF_SSI_TXDAT (GPIO_PORTC | GPIO_PF | GPIO_OUT | 6) -#define PC7_PF_SSI_TXFS (GPIO_PORTC | GPIO_PF | 7) -#define PC8_PF_SSI_TXCLK (GPIO_PORTC | GPIO_PF | 8) -#define PC9_PF_UART1_CTS (GPIO_PORTC | GPIO_PF | GPIO_OUT | 9) -#define PC10_PF_UART1_RTS (GPIO_PORTC | GPIO_PF | GPIO_IN | 10) -#define PC11_PF_UART1_TXD (GPIO_PORTC | GPIO_PF | GPIO_OUT | 11) -#define PC12_PF_UART1_RXD (GPIO_PORTC | GPIO_PF | GPIO_IN | 12) -#define PC13_PF_SPI1_SPI_RDY (GPIO_PORTC | GPIO_PF | 13) -#define PC14_PF_SPI1_SCLK (GPIO_PORTC | GPIO_PF | 14) -#define PC15_PF_SPI1_SS (GPIO_PORTC | GPIO_PF | 15) -#define PC16_PF_SPI1_MISO (GPIO_PORTC | GPIO_PF | 16) -#define PC17_PF_SPI1_MOSI (GPIO_PORTC | GPIO_PF | 17) -#define PC24_BIN_UART3_RI (GPIO_PORTC | GPIO_BIN | GPIO_OUT | 24) -#define PC25_BIN_UART3_DSR (GPIO_PORTC | GPIO_BIN | GPIO_OUT | 25) -#define PC26_AOUT_UART3_DTR (GPIO_PORTC | GPIO_AOUT | GPIO_IN | 26) -#define PC27_BIN_UART3_DCD (GPIO_PORTC | GPIO_BIN | GPIO_OUT | 27) -#define PC28_BIN_UART3_CTS (GPIO_PORTC | GPIO_BIN | GPIO_OUT | 28) -#define PC29_AOUT_UART3_RTS (GPIO_PORTC | GPIO_AOUT | GPIO_IN | 29) -#define PC30_BIN_UART3_TX (GPIO_PORTC | GPIO_BIN | 30) -#define PC31_AOUT_UART3_RX (GPIO_PORTC | GPIO_AOUT | GPIO_IN | 31) -#define PD6_PF_LSCLK (GPIO_PORTD | GPIO_PF | GPIO_OUT | 6) -#define PD7_PF_REV (GPIO_PORTD | GPIO_PF | 7) -#define PD7_AF_UART2_DTR (GPIO_PORTD | GPIO_AF | GPIO_IN | 7) -#define PD7_AIN_SPI2_SCLK (GPIO_PORTD | GPIO_AIN | 7) -#define PD8_PF_CLS (GPIO_PORTD | GPIO_PF | 8) -#define PD8_AF_UART2_DCD (GPIO_PORTD | GPIO_AF | GPIO_OUT | 8) -#define PD8_AIN_SPI2_SS (GPIO_PORTD | GPIO_AIN | 8) -#define PD9_PF_PS (GPIO_PORTD | GPIO_PF | 9) -#define PD9_AF_UART2_RI (GPIO_PORTD | GPIO_AF | GPIO_OUT | 9) -#define PD9_AOUT_SPI2_RXD (GPIO_PORTD | GPIO_AOUT | GPIO_IN | 9) -#define PD10_PF_SPL_SPR (GPIO_PORTD | GPIO_PF | GPIO_OUT | 10) -#define PD10_AF_UART2_DSR (GPIO_PORTD | GPIO_AF | GPIO_OUT | 10) -#define PD10_AIN_SPI2_TXD (GPIO_PORTD | GPIO_AIN | GPIO_OUT | 10) -#define PD11_PF_CONTRAST (GPIO_PORTD | GPIO_PF | GPIO_OUT | 11) -#define PD12_PF_ACD_OE (GPIO_PORTD | GPIO_PF | GPIO_OUT | 12) -#define PD13_PF_LP_HSYNC (GPIO_PORTD | GPIO_PF | GPIO_OUT | 13) -#define PD14_PF_FLM_VSYNC (GPIO_PORTD | GPIO_PF | GPIO_OUT | 14) -#define PD15_PF_LD0 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 15) -#define PD16_PF_LD1 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 16) -#define PD17_PF_LD2 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 17) -#define PD18_PF_LD3 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 18) -#define PD19_PF_LD4 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 19) -#define PD20_PF_LD5 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 20) -#define PD21_PF_LD6 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 21) -#define PD22_PF_LD7 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 22) -#define PD23_PF_LD8 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 23) -#define PD24_PF_LD9 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 24) -#define PD25_PF_LD10 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 25) -#define PD26_PF_LD11 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 26) -#define PD27_PF_LD12 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 27) -#define PD28_PF_LD13 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 28) -#define PD29_PF_LD14 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 29) -#define PD30_PF_LD15 (GPIO_PORTD | GPIO_PF | GPIO_OUT | 30) -#define PD31_PF_TMR2OUT (GPIO_PORTD | GPIO_PF | 31) -#define PD31_BIN_SPI2_TXD (GPIO_PORTD | GPIO_BIN | 31) - -#endif /* ifndef __MACH_IOMUX_MX1_H__ */ diff --git a/arch/arm/mach-imx/iomux-mx3.h b/arch/arm/mach-imx/iomux-mx3.h index 2e4a0ddca76c..368667b32760 100644 --- a/arch/arm/mach-imx/iomux-mx3.h +++ b/arch/arm/mach-imx/iomux-mx3.h @@ -598,10 +598,7 @@ enum iomux_pins { #define MX31_PIN_CONTRAST__CONTRAST IOMUX_MODE(MX31_PIN_CONTRAST, IOMUX_CONFIG_FUNC) #define MX31_PIN_D3_SPL__D3_SPL IOMUX_MODE(MX31_PIN_D3_SPL, IOMUX_CONFIG_FUNC) #define MX31_PIN_D3_CLS__D3_CLS IOMUX_MODE(MX31_PIN_D3_CLS, IOMUX_CONFIG_FUNC) -#define MX31_PIN_LCS0__GPI03_23 IOMUX_MODE(MX31_PIN_LCS0, IOMUX_CONFIG_GPIO) #define MX31_PIN_GPIO1_1__GPIO IOMUX_MODE(MX31_PIN_GPIO1_1, IOMUX_CONFIG_GPIO) -#define MX31_PIN_I2C_CLK__SCL IOMUX_MODE(MX31_PIN_I2C_CLK, IOMUX_CONFIG_FUNC) -#define MX31_PIN_I2C_DAT__SDA IOMUX_MODE(MX31_PIN_I2C_DAT, IOMUX_CONFIG_FUNC) #define MX31_PIN_DCD_DTE1__I2C2_SDA IOMUX_MODE(MX31_PIN_DCD_DTE1, IOMUX_CONFIG_ALT2) #define MX31_PIN_RI_DTE1__I2C2_SCL IOMUX_MODE(MX31_PIN_RI_DTE1, IOMUX_CONFIG_ALT2) #define MX31_PIN_CSPI2_SS2__I2C3_SDA IOMUX_MODE(MX31_PIN_CSPI2_SS2, IOMUX_CONFIG_ALT1) @@ -665,37 +662,6 @@ enum iomux_pins { #define MX31_PIN_USB_OC__GPIO1_30 IOMUX_MODE(MX31_PIN_USB_OC, IOMUX_CONFIG_GPIO) #define MX31_PIN_I2C_DAT__I2C1_SDA IOMUX_MODE(MX31_PIN_I2C_DAT, IOMUX_CONFIG_FUNC) #define MX31_PIN_I2C_CLK__I2C1_SCL IOMUX_MODE(MX31_PIN_I2C_CLK, IOMUX_CONFIG_FUNC) -#define MX31_PIN_DCD_DTE1__I2C2_SDA IOMUX_MODE(MX31_PIN_DCD_DTE1, IOMUX_CONFIG_ALT2) -#define MX31_PIN_RI_DTE1__I2C2_SCL IOMUX_MODE(MX31_PIN_RI_DTE1, IOMUX_CONFIG_ALT2) -#define MX31_PIN_ATA_CS0__GPIO3_26 IOMUX_MODE(MX31_PIN_ATA_CS0, IOMUX_CONFIG_GPIO) -#define MX31_PIN_ATA_CS1__GPIO3_27 IOMUX_MODE(MX31_PIN_ATA_CS1, IOMUX_CONFIG_GPIO) -#define MX31_PIN_PC_PWRON__SD2_DATA3 IOMUX_MODE(MX31_PIN_PC_PWRON, IOMUX_CONFIG_ALT1) -#define MX31_PIN_PC_VS1__SD2_DATA2 IOMUX_MODE(MX31_PIN_PC_VS1, IOMUX_CONFIG_ALT1) -#define MX31_PIN_PC_READY__SD2_DATA1 IOMUX_MODE(MX31_PIN_PC_READY, IOMUX_CONFIG_ALT1) -#define MX31_PIN_PC_WAIT_B__SD2_DATA0 IOMUX_MODE(MX31_PIN_PC_WAIT_B, IOMUX_CONFIG_ALT1) -#define MX31_PIN_PC_CD2_B__SD2_CLK IOMUX_MODE(MX31_PIN_PC_CD2_B, IOMUX_CONFIG_ALT1) -#define MX31_PIN_PC_CD1_B__SD2_CMD IOMUX_MODE(MX31_PIN_PC_CD1_B, IOMUX_CONFIG_ALT1) -#define MX31_PIN_ATA_DIOR__GPIO3_28 IOMUX_MODE(MX31_PIN_ATA_DIOR, IOMUX_CONFIG_GPIO) -#define MX31_PIN_ATA_DIOW__GPIO3_29 IOMUX_MODE(MX31_PIN_ATA_DIOW, IOMUX_CONFIG_GPIO) -#define MX31_PIN_CSI_D4__CSI_D4 IOMUX_MODE(MX31_PIN_CSI_D4, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_D5__CSI_D5 IOMUX_MODE(MX31_PIN_CSI_D5, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_D6__CSI_D6 IOMUX_MODE(MX31_PIN_CSI_D6, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_D7__CSI_D7 IOMUX_MODE(MX31_PIN_CSI_D7, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_D8__CSI_D8 IOMUX_MODE(MX31_PIN_CSI_D8, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_D9__CSI_D9 IOMUX_MODE(MX31_PIN_CSI_D9, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_D10__CSI_D10 IOMUX_MODE(MX31_PIN_CSI_D10, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_D11__CSI_D11 IOMUX_MODE(MX31_PIN_CSI_D11, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_D12__CSI_D12 IOMUX_MODE(MX31_PIN_CSI_D12, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_D13__CSI_D13 IOMUX_MODE(MX31_PIN_CSI_D13, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_D14__CSI_D14 IOMUX_MODE(MX31_PIN_CSI_D14, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_D15__CSI_D15 IOMUX_MODE(MX31_PIN_CSI_D15, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_HSYNC__CSI_HSYNC IOMUX_MODE(MX31_PIN_CSI_HSYNC, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_MCLK__CSI_MCLK IOMUX_MODE(MX31_PIN_CSI_MCLK, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_PIXCLK__CSI_PIXCLK IOMUX_MODE(MX31_PIN_CSI_PIXCLK, IOMUX_CONFIG_FUNC) -#define MX31_PIN_CSI_VSYNC__CSI_VSYNC IOMUX_MODE(MX31_PIN_CSI_VSYNC, IOMUX_CONFIG_FUNC) -#define MX31_PIN_GPIO3_0__GPIO3_0 IOMUX_MODE(MX31_PIN_GPIO3_0, IOMUX_CONFIG_GPIO) -#define MX31_PIN_GPIO3_1__GPIO3_1 IOMUX_MODE(MX31_PIN_GPIO3_1, IOMUX_CONFIG_GPIO) -#define MX31_PIN_TXD2__GPIO1_28 IOMUX_MODE(MX31_PIN_TXD2, IOMUX_CONFIG_GPIO) #define MX31_PIN_GPIO1_0__GPIO1_0 IOMUX_MODE(MX31_PIN_GPIO1_0, IOMUX_CONFIG_GPIO) #define MX31_PIN_SVEN0__GPIO2_0 IOMUX_MODE(MX31_PIN_SVEN0, IOMUX_CONFIG_GPIO) #define MX31_PIN_STX0__GPIO2_1 IOMUX_MODE(MX31_PIN_STX0, IOMUX_CONFIG_GPIO) diff --git a/arch/arm/mach-imx/mach-apf9328.c b/arch/arm/mach-imx/mach-apf9328.c deleted file mode 100644 index ebbb5ab63529..000000000000 --- a/arch/arm/mach-imx/mach-apf9328.c +++ /dev/null @@ -1,148 +0,0 @@ -/* - * linux/arch/arm/mach-imx/mach-apf9328.c - * - * Copyright (c) 2005-2011 ARMadeus systems <support@armadeus.com> - * - * This work is based on mach-scb9328.c which is: - * Copyright (c) 2004 Sascha Hauer <saschahauer@web.de> - * Copyright (c) 2006-2008 Juergen Beisert <jbeisert@netscape.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - */ - -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/platform_device.h> -#include <linux/mtd/physmap.h> -#include <linux/dm9000.h> -#include <linux/gpio.h> -#include <linux/i2c.h> - -#include <asm/mach-types.h> -#include <asm/mach/arch.h> -#include <asm/mach/time.h> - -#include "common.h" -#include "devices-imx1.h" -#include "hardware.h" -#include "iomux-mx1.h" - -static const int apf9328_pins[] __initconst = { - /* UART1 */ - PC9_PF_UART1_CTS, - PC10_PF_UART1_RTS, - PC11_PF_UART1_TXD, - PC12_PF_UART1_RXD, - /* UART2 */ - PB28_PF_UART2_CTS, - PB29_PF_UART2_RTS, - PB30_PF_UART2_TXD, - PB31_PF_UART2_RXD, - /* I2C */ - PA15_PF_I2C_SDA, - PA16_PF_I2C_SCL, -}; - -/* - * The APF9328 can have up to 32MB NOR Flash - */ -static struct resource flash_resource = { - .start = MX1_CS0_PHYS, - .end = MX1_CS0_PHYS + SZ_32M - 1, - .flags = IORESOURCE_MEM, -}; - -static struct physmap_flash_data apf9328_flash_data = { - .width = 2, -}; - -static struct platform_device apf9328_flash_device = { - .name = "physmap-flash", - .id = 0, - .dev = { - .platform_data = &apf9328_flash_data, - }, - .resource = &flash_resource, - .num_resources = 1, -}; - -/* - * APF9328 has a DM9000 Ethernet controller - */ -static struct dm9000_plat_data dm9000_setup = { - .flags = DM9000_PLATF_16BITONLY -}; - -static struct resource dm9000_resources[] = { - { - .start = MX1_CS4_PHYS + 0x00C00000, - .end = MX1_CS4_PHYS + 0x00C00001, - .flags = IORESOURCE_MEM, - }, { - .start = MX1_CS4_PHYS + 0x00C00002, - .end = MX1_CS4_PHYS + 0x00C00003, - .flags = IORESOURCE_MEM, - }, { - /* irq number is run-time assigned */ - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_LOWLEVEL, - }, -}; - -static struct platform_device dm9000x_device = { - .name = "dm9000", - .id = 0, - .num_resources = ARRAY_SIZE(dm9000_resources), - .resource = dm9000_resources, - .dev = { - .platform_data = &dm9000_setup, - } -}; - -static const struct imxuart_platform_data uart1_pdata __initconst = { - .flags = IMXUART_HAVE_RTSCTS, -}; - -static const struct imxi2c_platform_data apf9328_i2c_data __initconst = { - .bitrate = 100000, -}; - -static struct platform_device *devices[] __initdata = { - &apf9328_flash_device, - &dm9000x_device, -}; - -static void __init apf9328_init(void) -{ - imx1_soc_init(); - - mxc_gpio_setup_multiple_pins(apf9328_pins, - ARRAY_SIZE(apf9328_pins), - "APF9328"); - - imx1_add_imx_uart0(NULL); - imx1_add_imx_uart1(&uart1_pdata); - - imx1_add_imx_i2c(&apf9328_i2c_data); - - dm9000_resources[2].start = gpio_to_irq(IMX_GPIO_NR(2, 14)); - dm9000_resources[2].end = gpio_to_irq(IMX_GPIO_NR(2, 14)); - platform_add_devices(devices, ARRAY_SIZE(devices)); -} - -static void __init apf9328_timer_init(void) -{ - mx1_clocks_init(32768); -} - -MACHINE_START(APF9328, "Armadeus APF9328") - /* Maintainer: Gwenhael Goavec-Merou, ARMadeus Systems */ - .map_io = mx1_map_io, - .init_early = imx1_init_early, - .init_irq = mx1_init_irq, - .init_time = apf9328_timer_init, - .init_machine = apf9328_init, - .restart = mxc_restart, -MACHINE_END diff --git a/arch/arm/mach-imx/imx1-dt.c b/arch/arm/mach-imx/mach-imx1.c index 6f915b0961c4..de5ab8d88549 100644 --- a/arch/arm/mach-imx/imx1-dt.c +++ b/arch/arm/mach-imx/mach-imx1.c @@ -9,8 +9,27 @@ #include <linux/of_platform.h> #include <asm/mach/arch.h> +#include <asm/mach/map.h> #include "common.h" +#include "hardware.h" + +#define MX1_AVIC_ADDR 0x00223000 + +static void __init imx1_init_early(void) +{ + mxc_set_cpu_type(MXC_CPU_MX1); +} + +static void __init imx1_init_irq(void) +{ + void __iomem *avic_addr; + + avic_addr = ioremap(MX1_AVIC_ADDR, SZ_4K); + WARN_ON(!avic_addr); + + mxc_init_irq(avic_addr); +} static const char * const imx1_dt_board_compat[] __initconst = { "fsl,imx1", @@ -18,9 +37,9 @@ static const char * const imx1_dt_board_compat[] __initconst = { }; DT_MACHINE_START(IMX1_DT, "Freescale i.MX1 (Device Tree Support)") - .map_io = mx1_map_io, + .map_io = debug_ll_io_init, .init_early = imx1_init_early, - .init_irq = mx1_init_irq, + .init_irq = imx1_init_irq, .dt_compat = imx1_dt_board_compat, .restart = mxc_restart, MACHINE_END diff --git a/arch/arm/mach-imx/mach-imx6ul.c b/arch/arm/mach-imx/mach-imx6ul.c index 08308a127ff7..58a2b88233e6 100644 --- a/arch/arm/mach-imx/mach-imx6ul.c +++ b/arch/arm/mach-imx/mach-imx6ul.c @@ -65,6 +65,7 @@ static void __init imx6ul_init_machine(void) if (parent == NULL) pr_warn("failed to initialize soc device\n"); + of_platform_default_populate(NULL, NULL, parent); imx6ul_enet_init(); imx_anatop_init(); imx6ul_pm_init(); diff --git a/arch/arm/mach-imx/mach-kzm_arm11_01.c b/arch/arm/mach-imx/mach-kzm_arm11_01.c index 8288acfe7221..ab847e2c822a 100644 --- a/arch/arm/mach-imx/mach-kzm_arm11_01.c +++ b/arch/arm/mach-imx/mach-kzm_arm11_01.c @@ -63,7 +63,7 @@ */ #define KZM_ARM11_16550 (MX31_CS4_BASE_ADDR + 0x1050) -#if defined(CONFIG_SERIAL_8250) || defined(CONFIG_SERIAL_8250_MODULE) +#if IS_ENABLED(CONFIG_SERIAL_8250) /* * KZM-ARM11-01 has an external UART on FPGA */ @@ -141,7 +141,7 @@ static inline int kzm_init_ext_uart(void) /* * SMSC LAN9118 */ -#if defined(CONFIG_SMSC911X) || defined(CONFIG_SMSC911X_MODULE) +#if IS_ENABLED(CONFIG_SMSC911X) static struct smsc911x_platform_config kzm_smsc9118_config = { .phy_interface = PHY_INTERFACE_MODE_MII, .irq_polarity = SMSC911X_IRQ_POLARITY_ACTIVE_HIGH, @@ -201,7 +201,7 @@ static inline int kzm_init_smsc9118(void) } #endif -#if defined(CONFIG_SERIAL_IMX) || defined(CONFIG_SERIAL_IMX_MODULE) +#if IS_ENABLED(CONFIG_SERIAL_IMX) static const struct imxuart_platform_data uart_pdata __initconst = { .flags = IMXUART_HAVE_RTSCTS, }; diff --git a/arch/arm/mach-imx/mach-pcm037.c b/arch/arm/mach-imx/mach-pcm037.c index d071ced7425d..9f0f55b0422c 100644 --- a/arch/arm/mach-imx/mach-pcm037.c +++ b/arch/arm/mach-imx/mach-pcm037.c @@ -149,7 +149,7 @@ static unsigned int pcm037_pins[] = { MX31_PIN_CONTRAST__CONTRAST, MX31_PIN_D3_SPL__D3_SPL, MX31_PIN_D3_CLS__D3_CLS, - MX31_PIN_LCS0__GPI03_23, + MX31_PIN_LCS0__GPIO3_23, /* CSI */ IOMUX_MODE(MX31_PIN_CSI_D5, IOMUX_CONFIG_GPIO), MX31_PIN_CSI_D6__CSI_D6, diff --git a/arch/arm/mach-imx/mach-scb9328.c b/arch/arm/mach-imx/mach-scb9328.c deleted file mode 100644 index 1f6bc3f7ae14..000000000000 --- a/arch/arm/mach-imx/mach-scb9328.c +++ /dev/null @@ -1,143 +0,0 @@ -/* - * linux/arch/arm/mach-mx1/mach-scb9328.c - * - * Copyright (c) 2004 Sascha Hauer <saschahauer@web.de> - * Copyright (c) 2006-2008 Juergen Beisert <jbeisert@netscape.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - */ - -#include <linux/platform_device.h> -#include <linux/mtd/physmap.h> -#include <linux/interrupt.h> -#include <linux/dm9000.h> -#include <linux/gpio.h> - -#include <asm/mach-types.h> -#include <asm/mach/arch.h> -#include <asm/mach/time.h> - -#include "common.h" -#include "devices-imx1.h" -#include "hardware.h" -#include "iomux-mx1.h" - -/* - * This scb9328 has a 32MiB flash - */ -static struct resource flash_resource = { - .start = MX1_CS0_PHYS, - .end = MX1_CS0_PHYS + (32 * 1024 * 1024) - 1, - .flags = IORESOURCE_MEM, -}; - -static struct physmap_flash_data scb_flash_data = { - .width = 2, -}; - -static struct platform_device scb_flash_device = { - .name = "physmap-flash", - .id = 0, - .dev = { - .platform_data = &scb_flash_data, - }, - .resource = &flash_resource, - .num_resources = 1, -}; - -/* - * scb9328 has a DM9000 network controller - * connected to CS5, with 16 bit data path - * and interrupt connected to GPIO 3 - */ - -/* - * internal datapath is fixed 16 bit - */ -static struct dm9000_plat_data dm9000_platdata = { - .flags = DM9000_PLATF_16BITONLY, -}; - -/* - * the DM9000 drivers wants two defined address spaces - * to gain access to address latch registers and the data path. - */ -static struct resource dm9000x_resources[] = { - { - .name = "address area", - .start = MX1_CS5_PHYS, - .end = MX1_CS5_PHYS + 1, - .flags = IORESOURCE_MEM, /* address access */ - }, { - .name = "data area", - .start = MX1_CS5_PHYS + 4, - .end = MX1_CS5_PHYS + 5, - .flags = IORESOURCE_MEM, /* data access */ - }, { - /* irq number is run-time assigned */ - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_LOWLEVEL, - }, -}; - -static struct platform_device dm9000x_device = { - .name = "dm9000", - .id = 0, - .num_resources = ARRAY_SIZE(dm9000x_resources), - .resource = dm9000x_resources, - .dev = { - .platform_data = &dm9000_platdata, - } -}; - -static const int mxc_uart1_pins[] = { - PC9_PF_UART1_CTS, - PC10_PF_UART1_RTS, - PC11_PF_UART1_TXD, - PC12_PF_UART1_RXD, -}; - -static const struct imxuart_platform_data uart_pdata __initconst = { - .flags = IMXUART_HAVE_RTSCTS, -}; - -static struct platform_device *devices[] __initdata = { - &scb_flash_device, - &dm9000x_device, -}; - -/* - * scb9328_init - Init the CPU card itself - */ -static void __init scb9328_init(void) -{ - imx1_soc_init(); - - mxc_gpio_setup_multiple_pins(mxc_uart1_pins, - ARRAY_SIZE(mxc_uart1_pins), "UART1"); - - imx1_add_imx_uart0(&uart_pdata); - - printk(KERN_INFO"Scb9328: Adding devices\n"); - dm9000x_resources[2].start = gpio_to_irq(IMX_GPIO_NR(3, 3)); - dm9000x_resources[2].end = gpio_to_irq(IMX_GPIO_NR(3, 3)); - platform_add_devices(devices, ARRAY_SIZE(devices)); -} - -static void __init scb9328_timer_init(void) -{ - mx1_clocks_init(32000); -} - -MACHINE_START(SCB9328, "Synertronixx scb9328") - /* Sascha Hauer */ - .atag_offset = 100, - .map_io = mx1_map_io, - .init_early = imx1_init_early, - .init_irq = mx1_init_irq, - .init_time = scb9328_timer_init, - .init_machine = scb9328_init, - .restart = mxc_restart, -MACHINE_END diff --git a/arch/arm/mach-imx/mm-imx1.c b/arch/arm/mach-imx/mm-imx1.c deleted file mode 100644 index 9a42f19be81e..000000000000 --- a/arch/arm/mach-imx/mm-imx1.c +++ /dev/null @@ -1,67 +0,0 @@ -/* - * author: Sascha Hauer - * Created: april 20th, 2004 - * Copyright: Synertronixx GmbH - * - * Common code for i.MX1 machines - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/io.h> -#include <linux/pinctrl/machine.h> - -#include <asm/mach/map.h> - -#include "common.h" -#include "devices/devices-common.h" -#include "hardware.h" -#include "iomux-v1.h" - -static struct map_desc imx_io_desc[] __initdata = { - imx_map_entry(MX1, IO, MT_DEVICE), -}; - -void __init mx1_map_io(void) -{ - iotable_init(imx_io_desc, ARRAY_SIZE(imx_io_desc)); -} - -void __init imx1_init_early(void) -{ - mxc_set_cpu_type(MXC_CPU_MX1); - imx_iomuxv1_init(MX1_IO_ADDRESS(MX1_GPIO_BASE_ADDR), - MX1_NUM_GPIO_PORT); -} - -void __init mx1_init_irq(void) -{ - mxc_init_irq(MX1_IO_ADDRESS(MX1_AVIC_BASE_ADDR)); -} - -void __init imx1_soc_init(void) -{ - imx1_reset_init(MX1_IO_ADDRESS(MX1_WDT_BASE_ADDR)); - mxc_device_init(); - - mxc_register_gpio("imx1-gpio", 0, MX1_GPIO1_BASE_ADDR, SZ_256, - MX1_GPIO_INT_PORTA, 0); - mxc_register_gpio("imx1-gpio", 1, MX1_GPIO2_BASE_ADDR, SZ_256, - MX1_GPIO_INT_PORTB, 0); - mxc_register_gpio("imx1-gpio", 2, MX1_GPIO3_BASE_ADDR, SZ_256, - MX1_GPIO_INT_PORTC, 0); - mxc_register_gpio("imx1-gpio", 3, MX1_GPIO4_BASE_ADDR, SZ_256, - MX1_GPIO_INT_PORTD, 0); - imx_add_imx_dma("imx1-dma", MX1_DMA_BASE_ADDR, - MX1_DMA_INT, MX1_DMA_ERR); - pinctrl_provide_dummies(); -} diff --git a/arch/arm/mach-imx/mx1.h b/arch/arm/mach-imx/mx1.h deleted file mode 100644 index 45bd31cc34d6..000000000000 --- a/arch/arm/mach-imx/mx1.h +++ /dev/null @@ -1,172 +0,0 @@ -/* - * Copyright (C) 1997,1998 Russell King - * Copyright (C) 1999 ARM Limited - * Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved. - * Copyright (c) 2008 Paulius Zaleckas <paulius.zaleckas@teltonika.lt> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef __MACH_MX1_H__ -#define __MACH_MX1_H__ - -/* - * Memory map - */ -#define MX1_IO_BASE_ADDR 0x00200000 -#define MX1_IO_SIZE SZ_1M - -#define MX1_CS0_PHYS 0x10000000 -#define MX1_CS0_SIZE 0x02000000 - -#define MX1_CS1_PHYS 0x12000000 -#define MX1_CS1_SIZE 0x01000000 - -#define MX1_CS2_PHYS 0x13000000 -#define MX1_CS2_SIZE 0x01000000 - -#define MX1_CS3_PHYS 0x14000000 -#define MX1_CS3_SIZE 0x01000000 - -#define MX1_CS4_PHYS 0x15000000 -#define MX1_CS4_SIZE 0x01000000 - -#define MX1_CS5_PHYS 0x16000000 -#define MX1_CS5_SIZE 0x01000000 - -/* - * Register BASEs, based on OFFSETs - */ -#define MX1_AIPI1_BASE_ADDR (0x00000 + MX1_IO_BASE_ADDR) -#define MX1_WDT_BASE_ADDR (0x01000 + MX1_IO_BASE_ADDR) -#define MX1_TIM1_BASE_ADDR (0x02000 + MX1_IO_BASE_ADDR) -#define MX1_TIM2_BASE_ADDR (0x03000 + MX1_IO_BASE_ADDR) -#define MX1_RTC_BASE_ADDR (0x04000 + MX1_IO_BASE_ADDR) -#define MX1_LCDC_BASE_ADDR (0x05000 + MX1_IO_BASE_ADDR) -#define MX1_UART1_BASE_ADDR (0x06000 + MX1_IO_BASE_ADDR) -#define MX1_UART2_BASE_ADDR (0x07000 + MX1_IO_BASE_ADDR) -#define MX1_PWM_BASE_ADDR (0x08000 + MX1_IO_BASE_ADDR) -#define MX1_DMA_BASE_ADDR (0x09000 + MX1_IO_BASE_ADDR) -#define MX1_AIPI2_BASE_ADDR (0x10000 + MX1_IO_BASE_ADDR) -#define MX1_SIM_BASE_ADDR (0x11000 + MX1_IO_BASE_ADDR) -#define MX1_USBD_BASE_ADDR (0x12000 + MX1_IO_BASE_ADDR) -#define MX1_CSPI1_BASE_ADDR (0x13000 + MX1_IO_BASE_ADDR) -#define MX1_MMC_BASE_ADDR (0x14000 + MX1_IO_BASE_ADDR) -#define MX1_ASP_BASE_ADDR (0x15000 + MX1_IO_BASE_ADDR) -#define MX1_BTA_BASE_ADDR (0x16000 + MX1_IO_BASE_ADDR) -#define MX1_I2C_BASE_ADDR (0x17000 + MX1_IO_BASE_ADDR) -#define MX1_SSI_BASE_ADDR (0x18000 + MX1_IO_BASE_ADDR) -#define MX1_CSPI2_BASE_ADDR (0x19000 + MX1_IO_BASE_ADDR) -#define MX1_MSHC_BASE_ADDR (0x1A000 + MX1_IO_BASE_ADDR) -#define MX1_CCM_BASE_ADDR (0x1B000 + MX1_IO_BASE_ADDR) -#define MX1_SCM_BASE_ADDR (0x1B804 + MX1_IO_BASE_ADDR) -#define MX1_GPIO_BASE_ADDR (0x1C000 + MX1_IO_BASE_ADDR) -#define MX1_GPIO1_BASE_ADDR (0x1C000 + MX1_IO_BASE_ADDR) -#define MX1_GPIO2_BASE_ADDR (0x1C100 + MX1_IO_BASE_ADDR) -#define MX1_GPIO3_BASE_ADDR (0x1C200 + MX1_IO_BASE_ADDR) -#define MX1_GPIO4_BASE_ADDR (0x1C300 + MX1_IO_BASE_ADDR) -#define MX1_EIM_BASE_ADDR (0x20000 + MX1_IO_BASE_ADDR) -#define MX1_SDRAMC_BASE_ADDR (0x21000 + MX1_IO_BASE_ADDR) -#define MX1_MMA_BASE_ADDR (0x22000 + MX1_IO_BASE_ADDR) -#define MX1_AVIC_BASE_ADDR (0x23000 + MX1_IO_BASE_ADDR) -#define MX1_CSI_BASE_ADDR (0x24000 + MX1_IO_BASE_ADDR) - -/* macro to get at IO space when running virtually */ -#define MX1_IO_P2V(x) IMX_IO_P2V(x) -#define MX1_IO_ADDRESS(x) IOMEM(MX1_IO_P2V(x)) - -/* fixed interrput numbers */ -#include <asm/irq.h> -#define MX1_INT_SOFTINT (NR_IRQS_LEGACY + 0) -#define MX1_INT_CSI (NR_IRQS_LEGACY + 6) -#define MX1_DSPA_MAC_INT (NR_IRQS_LEGACY + 7) -#define MX1_DSPA_INT (NR_IRQS_LEGACY + 8) -#define MX1_COMP_INT (NR_IRQS_LEGACY + 9) -#define MX1_MSHC_XINT (NR_IRQS_LEGACY + 10) -#define MX1_GPIO_INT_PORTA (NR_IRQS_LEGACY + 11) -#define MX1_GPIO_INT_PORTB (NR_IRQS_LEGACY + 12) -#define MX1_GPIO_INT_PORTC (NR_IRQS_LEGACY + 13) -#define MX1_INT_LCDC (NR_IRQS_LEGACY + 14) -#define MX1_SIM_INT (NR_IRQS_LEGACY + 15) -#define MX1_SIM_DATA_INT (NR_IRQS_LEGACY + 16) -#define MX1_RTC_INT (NR_IRQS_LEGACY + 17) -#define MX1_RTC_SAMINT (NR_IRQS_LEGACY + 18) -#define MX1_INT_UART2PFERR (NR_IRQS_LEGACY + 19) -#define MX1_INT_UART2RTS (NR_IRQS_LEGACY + 20) -#define MX1_INT_UART2DTR (NR_IRQS_LEGACY + 21) -#define MX1_INT_UART2UARTC (NR_IRQS_LEGACY + 22) -#define MX1_INT_UART2TX (NR_IRQS_LEGACY + 23) -#define MX1_INT_UART2RX (NR_IRQS_LEGACY + 24) -#define MX1_INT_UART1PFERR (NR_IRQS_LEGACY + 25) -#define MX1_INT_UART1RTS (NR_IRQS_LEGACY + 26) -#define MX1_INT_UART1DTR (NR_IRQS_LEGACY + 27) -#define MX1_INT_UART1UARTC (NR_IRQS_LEGACY + 28) -#define MX1_INT_UART1TX (NR_IRQS_LEGACY + 29) -#define MX1_INT_UART1RX (NR_IRQS_LEGACY + 30) -#define MX1_VOICE_DAC_INT (NR_IRQS_LEGACY + 31) -#define MX1_VOICE_ADC_INT (NR_IRQS_LEGACY + 32) -#define MX1_PEN_DATA_INT (NR_IRQS_LEGACY + 33) -#define MX1_PWM_INT (NR_IRQS_LEGACY + 34) -#define MX1_SDHC_INT (NR_IRQS_LEGACY + 35) -#define MX1_INT_I2C (NR_IRQS_LEGACY + 39) -#define MX1_INT_CSPI2 (NR_IRQS_LEGACY + 40) -#define MX1_INT_CSPI1 (NR_IRQS_LEGACY + 41) -#define MX1_SSI_TX_INT (NR_IRQS_LEGACY + 42) -#define MX1_SSI_TX_ERR_INT (NR_IRQS_LEGACY + 43) -#define MX1_SSI_RX_INT (NR_IRQS_LEGACY + 44) -#define MX1_SSI_RX_ERR_INT (NR_IRQS_LEGACY + 45) -#define MX1_TOUCH_INT (NR_IRQS_LEGACY + 46) -#define MX1_INT_USBD0 (NR_IRQS_LEGACY + 47) -#define MX1_INT_USBD1 (NR_IRQS_LEGACY + 48) -#define MX1_INT_USBD2 (NR_IRQS_LEGACY + 49) -#define MX1_INT_USBD3 (NR_IRQS_LEGACY + 50) -#define MX1_INT_USBD4 (NR_IRQS_LEGACY + 51) -#define MX1_INT_USBD5 (NR_IRQS_LEGACY + 52) -#define MX1_INT_USBD6 (NR_IRQS_LEGACY + 53) -#define MX1_BTSYS_INT (NR_IRQS_LEGACY + 55) -#define MX1_BTTIM_INT (NR_IRQS_LEGACY + 56) -#define MX1_BTWUI_INT (NR_IRQS_LEGACY + 57) -#define MX1_TIM2_INT (NR_IRQS_LEGACY + 58) -#define MX1_TIM1_INT (NR_IRQS_LEGACY + 59) -#define MX1_DMA_ERR (NR_IRQS_LEGACY + 60) -#define MX1_DMA_INT (NR_IRQS_LEGACY + 61) -#define MX1_GPIO_INT_PORTD (NR_IRQS_LEGACY + 62) -#define MX1_WDT_INT (NR_IRQS_LEGACY + 63) - -/* DMA */ -#define MX1_DMA_REQ_UART3_T 2 -#define MX1_DMA_REQ_UART3_R 3 -#define MX1_DMA_REQ_SSI2_T 4 -#define MX1_DMA_REQ_SSI2_R 5 -#define MX1_DMA_REQ_CSI_STAT 6 -#define MX1_DMA_REQ_CSI_R 7 -#define MX1_DMA_REQ_MSHC 8 -#define MX1_DMA_REQ_DSPA_DCT_DOUT 9 -#define MX1_DMA_REQ_DSPA_DCT_DIN 10 -#define MX1_DMA_REQ_DSPA_MAC 11 -#define MX1_DMA_REQ_EXT 12 -#define MX1_DMA_REQ_SDHC 13 -#define MX1_DMA_REQ_SPI1_R 14 -#define MX1_DMA_REQ_SPI1_T 15 -#define MX1_DMA_REQ_SSI_T 16 -#define MX1_DMA_REQ_SSI_R 17 -#define MX1_DMA_REQ_ASP_DAC 18 -#define MX1_DMA_REQ_ASP_ADC 19 -#define MX1_DMA_REQ_USP_EP(x) (20 + (x)) -#define MX1_DMA_REQ_SPI2_R 26 -#define MX1_DMA_REQ_SPI2_T 27 -#define MX1_DMA_REQ_UART2_T 28 -#define MX1_DMA_REQ_UART2_R 29 -#define MX1_DMA_REQ_UART1_T 30 -#define MX1_DMA_REQ_UART1_R 31 - -/* - * This doesn't depend on IMX_NEEDS_DEPRECATED_SYMBOLS - * to not break drivers/usb/gadget/imx_udc. Should go - * away after this driver uses the new name. - */ -#define USBD_INT0 MX1_INT_USBD0 - -#endif /* ifndef __MACH_MX1_H__ */ diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c index 549648309deb..1515e498d348 100644 --- a/arch/arm/mach-imx/pm-imx6.c +++ b/arch/arm/mach-imx/pm-imx6.c @@ -295,7 +295,7 @@ int imx6_set_lpm(enum mxc_cpu_pwr_mode mode) val &= ~BM_CLPCR_SBYOS; if (cpu_is_imx6sl()) val |= BM_CLPCR_BYPASS_PMIC_READY; - if (cpu_is_imx6sl() || cpu_is_imx6sx()) + if (cpu_is_imx6sl() || cpu_is_imx6sx() || cpu_is_imx6ul()) val |= BM_CLPCR_BYP_MMDC_CH0_LPM_HS; else val |= BM_CLPCR_BYP_MMDC_CH1_LPM_HS; @@ -310,7 +310,7 @@ int imx6_set_lpm(enum mxc_cpu_pwr_mode mode) val |= 0x3 << BP_CLPCR_STBY_COUNT; val |= BM_CLPCR_VSTBY; val |= BM_CLPCR_SBYOS; - if (cpu_is_imx6sl()) + if (cpu_is_imx6sl() || cpu_is_imx6sx()) val |= BM_CLPCR_BYPASS_PMIC_READY; if (cpu_is_imx6sl() || cpu_is_imx6sx() || cpu_is_imx6ul()) val |= BM_CLPCR_BYP_MMDC_CH0_LPM_HS; diff --git a/arch/arm/mach-integrator/Kconfig b/arch/arm/mach-integrator/Kconfig index 599f973e10d8..cefe44f6889b 100644 --- a/arch/arm/mach-integrator/Kconfig +++ b/arch/arm/mach-integrator/Kconfig @@ -21,7 +21,6 @@ if ARCH_INTEGRATOR config ARCH_INTEGRATOR_AP bool "Support Integrator/AP and Integrator/PP2 platforms" select INTEGRATOR_AP_TIMER - select MIGHT_HAVE_PCI select SERIAL_AMBA_PL010 if TTY select SERIAL_AMBA_PL010_CONSOLE if TTY select SOC_BUS diff --git a/arch/arm/mach-keystone/Kconfig b/arch/arm/mach-keystone/Kconfig index 8ff61be1a29f..24bd64dabdfc 100644 --- a/arch/arm/mach-keystone/Kconfig +++ b/arch/arm/mach-keystone/Kconfig @@ -8,8 +8,6 @@ config ARCH_KEYSTONE select COMMON_CLK_KEYSTONE select ARCH_SUPPORTS_BIG_ENDIAN select ZONE_DMA if ARM_LPAE - select MIGHT_HAVE_PCI - select PCI_DOMAINS if PCI select PINCTRL help Support for boards based on the Texas Instruments Keystone family of diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c index 0b7fe74ff46d..e4f21086b42b 100644 --- a/arch/arm/mach-mxs/mach-mxs.c +++ b/arch/arm/mach-mxs/mach-mxs.c @@ -268,80 +268,6 @@ static void __init apx4devkit_init(void) apx4devkit_phy_fixup); } -#define ENET0_MDC__GPIO_4_0 MXS_GPIO_NR(4, 0) -#define ENET0_MDIO__GPIO_4_1 MXS_GPIO_NR(4, 1) -#define ENET0_RX_EN__GPIO_4_2 MXS_GPIO_NR(4, 2) -#define ENET0_RXD0__GPIO_4_3 MXS_GPIO_NR(4, 3) -#define ENET0_RXD1__GPIO_4_4 MXS_GPIO_NR(4, 4) -#define ENET0_TX_EN__GPIO_4_6 MXS_GPIO_NR(4, 6) -#define ENET0_TXD0__GPIO_4_7 MXS_GPIO_NR(4, 7) -#define ENET0_TXD1__GPIO_4_8 MXS_GPIO_NR(4, 8) -#define ENET_CLK__GPIO_4_16 MXS_GPIO_NR(4, 16) - -#define TX28_FEC_PHY_POWER MXS_GPIO_NR(3, 29) -#define TX28_FEC_PHY_RESET MXS_GPIO_NR(4, 13) -#define TX28_FEC_nINT MXS_GPIO_NR(4, 5) - -static const struct gpio const tx28_gpios[] __initconst = { - { ENET0_MDC__GPIO_4_0, GPIOF_OUT_INIT_LOW, "GPIO_4_0" }, - { ENET0_MDIO__GPIO_4_1, GPIOF_OUT_INIT_LOW, "GPIO_4_1" }, - { ENET0_RX_EN__GPIO_4_2, GPIOF_OUT_INIT_LOW, "GPIO_4_2" }, - { ENET0_RXD0__GPIO_4_3, GPIOF_OUT_INIT_LOW, "GPIO_4_3" }, - { ENET0_RXD1__GPIO_4_4, GPIOF_OUT_INIT_LOW, "GPIO_4_4" }, - { ENET0_TX_EN__GPIO_4_6, GPIOF_OUT_INIT_LOW, "GPIO_4_6" }, - { ENET0_TXD0__GPIO_4_7, GPIOF_OUT_INIT_LOW, "GPIO_4_7" }, - { ENET0_TXD1__GPIO_4_8, GPIOF_OUT_INIT_LOW, "GPIO_4_8" }, - { ENET_CLK__GPIO_4_16, GPIOF_OUT_INIT_LOW, "GPIO_4_16" }, - { TX28_FEC_PHY_POWER, GPIOF_OUT_INIT_LOW, "fec-phy-power" }, - { TX28_FEC_PHY_RESET, GPIOF_OUT_INIT_LOW, "fec-phy-reset" }, - { TX28_FEC_nINT, GPIOF_DIR_IN, "fec-int" }, -}; - -static void __init tx28_post_init(void) -{ - struct device_node *np; - struct platform_device *pdev; - struct pinctrl *pctl; - int ret; - - enable_clk_enet_out(); - - np = of_find_compatible_node(NULL, NULL, "fsl,imx28-fec"); - pdev = of_find_device_by_node(np); - if (!pdev) { - pr_err("%s: failed to find fec device\n", __func__); - return; - } - - pctl = pinctrl_get_select(&pdev->dev, "gpio_mode"); - if (IS_ERR(pctl)) { - pr_err("%s: failed to get pinctrl state\n", __func__); - return; - } - - ret = gpio_request_array(tx28_gpios, ARRAY_SIZE(tx28_gpios)); - if (ret) { - pr_err("%s: failed to request gpios: %d\n", __func__, ret); - return; - } - - /* Power up fec phy */ - gpio_set_value(TX28_FEC_PHY_POWER, 1); - msleep(26); /* 25ms according to data sheet */ - - /* Mode strap pins */ - gpio_set_value(ENET0_RX_EN__GPIO_4_2, 1); - gpio_set_value(ENET0_RXD0__GPIO_4_3, 1); - gpio_set_value(ENET0_RXD1__GPIO_4_4, 1); - - udelay(100); /* minimum assertion time for nRST */ - - /* Deasserting FEC PHY RESET */ - gpio_set_value(TX28_FEC_PHY_RESET, 1); - - pinctrl_put(pctl); -} - static void __init crystalfontz_init(void) { update_fec_mac_prop(OUI_CRYSTALFONTZ); @@ -501,9 +427,6 @@ static void __init mxs_machine_init(void) of_platform_default_populate(NULL, NULL, parent); mxs_restart_init(); - - if (of_machine_is_compatible("karo,tx28")) - tx28_post_init(); } #define MXS_CLKCTRL_RESET_CHIP (1 << 1) diff --git a/arch/arm/mach-omap1/board-h2-mmc.c b/arch/arm/mach-omap1/board-h2-mmc.c index 7119ef28e0ad..357be2debc9d 100644 --- a/arch/arm/mach-omap1/board-h2-mmc.c +++ b/arch/arm/mach-omap1/board-h2-mmc.c @@ -19,7 +19,7 @@ #include "board-h2.h" #include "mmc.h" -#if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE) +#if IS_ENABLED(CONFIG_MMC_OMAP) static int mmc_set_power(struct device *dev, int slot, int power_on, int vdd) diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c index cd146ed0538d..675254ee4b1e 100644 --- a/arch/arm/mach-omap1/board-h2.c +++ b/arch/arm/mach-omap1/board-h2.c @@ -349,7 +349,7 @@ static struct omap_usb_config h2_usb_config __initdata = { #if IS_ENABLED(CONFIG_USB_OMAP) .hmc_mode = 19, /* 0:host(off) 1:dev|otg 2:disabled */ /* .hmc_mode = 21,*/ /* 0:host(off) 1:dev(loopback) 2:host(loopback) */ -#elif defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) +#elif IS_ENABLED(CONFIG_USB_OHCI_HCD) /* needs OTG cable, or NONSTANDARD (B-to-MiniB) */ .hmc_mode = 20, /* 1:dev|otg(off) 1:host 2:disabled */ #endif diff --git a/arch/arm/mach-omap1/board-h3-mmc.c b/arch/arm/mach-omap1/board-h3-mmc.c index 43aab63cbc39..4f58bfa5e754 100644 --- a/arch/arm/mach-omap1/board-h3-mmc.c +++ b/arch/arm/mach-omap1/board-h3-mmc.c @@ -20,7 +20,7 @@ #include "board-h3.h" #include "mmc.h" -#if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE) +#if IS_ENABLED(CONFIG_MMC_OMAP) static int mmc_set_power(struct device *dev, int slot, int power_on, int vdd) diff --git a/arch/arm/mach-omap1/board-h3.c b/arch/arm/mach-omap1/board-h3.c index f7c8c63dd532..e62f9d454f10 100644 --- a/arch/arm/mach-omap1/board-h3.c +++ b/arch/arm/mach-omap1/board-h3.c @@ -368,7 +368,7 @@ static struct omap_usb_config h3_usb_config __initdata = { #if IS_ENABLED(CONFIG_USB_OMAP) .hmc_mode = 19, /* 0:host(off) 1:dev|otg 2:disabled */ -#elif defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) +#elif IS_ENABLED(CONFIG_USB_OHCI_HCD) /* NONSTANDARD CABLE NEEDED (B-to-Mini-B) */ .hmc_mode = 20, /* 1:dev|otg(off) 1:host 2:disabled */ #endif diff --git a/arch/arm/mach-omap1/board-htcherald.c b/arch/arm/mach-omap1/board-htcherald.c index 9525ef9bc6c0..e424df901dbd 100644 --- a/arch/arm/mach-omap1/board-htcherald.c +++ b/arch/arm/mach-omap1/board-htcherald.c @@ -401,7 +401,7 @@ static struct platform_device lcd_device = { }; /* MMC Card */ -#if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE) +#if IS_ENABLED(CONFIG_MMC_OMAP) static struct omap_mmc_platform_data htc_mmc1_data = { .nr_slots = 1, .switch_slot = NULL, @@ -586,7 +586,7 @@ static void __init htcherald_init(void) omap_register_i2c_bus(1, 100, NULL, 0); -#if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE) +#if IS_ENABLED(CONFIG_MMC_OMAP) htc_mmc_data[0] = &htc_mmc1_data; omap1_init_mmc(htc_mmc_data, 1); #endif diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c index ae90bd02b3bf..67e188271643 100644 --- a/arch/arm/mach-omap1/board-innovator.c +++ b/arch/arm/mach-omap1/board-innovator.c @@ -315,7 +315,7 @@ static struct omap_usb_config h2_usb_config __initdata = { #if IS_ENABLED(CONFIG_USB_OMAP) .hmc_mode = 19, /* 0:host(off) 1:dev|otg 2:disabled */ /* .hmc_mode = 21,*/ /* 0:host(off) 1:dev(loopback) 2:host(loopback) */ -#elif defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) +#elif IS_ENABLED(CONFIG_USB_OHCI_HCD) /* NONSTANDARD CABLE NEEDED (B-to-Mini-B) */ .hmc_mode = 20, /* 1:dev|otg(off) 1:host 2:disabled */ #endif @@ -328,7 +328,7 @@ static struct omap_lcd_config innovator1610_lcd_config __initdata = { }; #endif -#if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE) +#if IS_ENABLED(CONFIG_MMC_OMAP) static int mmc_set_power(struct device *dev, int slot, int power_on, int vdd) diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c index dd3a3ad797ea..ee8d9f553db4 100644 --- a/arch/arm/mach-omap1/board-nokia770.c +++ b/arch/arm/mach-omap1/board-nokia770.c @@ -159,7 +159,7 @@ static struct omap_usb_config nokia770_usb_config __initdata = { .extcon = "tahvo-usb", }; -#if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE) +#if IS_ENABLED(CONFIG_MMC_OMAP) #define NOKIA770_GPIO_MMC_POWER 41 #define NOKIA770_GPIO_MMC_SWITCH 23 @@ -216,7 +216,7 @@ static inline void nokia770_mmc_init(void) } #endif -#if defined(CONFIG_I2C_CBUS_GPIO) || defined(CONFIG_I2C_CBUS_GPIO_MODULE) +#if IS_ENABLED(CONFIG_I2C_CBUS_GPIO) static struct i2c_cbus_platform_data nokia770_cbus_data = { .clk_gpio = OMAP_MPUIO(9), .dat_gpio = OMAP_MPUIO(10), diff --git a/arch/arm/mach-omap1/board-sx1-mmc.c b/arch/arm/mach-omap1/board-sx1-mmc.c index a9373570bbb1..79f0af8bfae0 100644 --- a/arch/arm/mach-omap1/board-sx1-mmc.c +++ b/arch/arm/mach-omap1/board-sx1-mmc.c @@ -20,7 +20,7 @@ #include "mmc.h" -#if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE) +#if IS_ENABLED(CONFIG_MMC_OMAP) static int mmc_set_power(struct device *dev, int slot, int power_on, int vdd) diff --git a/arch/arm/mach-omap1/devices.c b/arch/arm/mach-omap1/devices.c index 8c8be861fff2..baaf902b7016 100644 --- a/arch/arm/mach-omap1/devices.c +++ b/arch/arm/mach-omap1/devices.c @@ -33,7 +33,7 @@ #include "mmc.h" #include "sram.h" -#if defined(CONFIG_RTC_DRV_OMAP) || defined(CONFIG_RTC_DRV_OMAP_MODULE) +#if IS_ENABLED(CONFIG_RTC_DRV_OMAP) #define OMAP_RTC_BASE 0xfffb4800 @@ -72,7 +72,7 @@ static inline void omap_init_mbox(void) { } /*-------------------------------------------------------------------------*/ -#if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE) +#if IS_ENABLED(CONFIG_MMC_OMAP) static inline void omap1_mmc_mux(struct omap_mmc_platform_data *mmc_controller, int controller_nr) @@ -230,7 +230,7 @@ void __init omap1_init_mmc(struct omap_mmc_platform_data **mmc_data, /*-------------------------------------------------------------------------*/ /* OMAP7xx SPI support */ -#if defined(CONFIG_SPI_OMAP_100K) || defined(CONFIG_SPI_OMAP_100K_MODULE) +#if IS_ENABLED(CONFIG_SPI_OMAP_100K) struct platform_device omap_spi1 = { .name = "omap1_spi100k", @@ -312,7 +312,7 @@ static inline void omap_init_sti(void) {} * mcbsp1..3 = 5..7 */ -#if defined(CONFIG_SPI_OMAP_UWIRE) || defined(CONFIG_SPI_OMAP_UWIRE_MODULE) +#if IS_ENABLED(CONFIG_SPI_OMAP_UWIRE) #define OMAP_UWIRE_BASE 0xfffb3000 @@ -418,7 +418,7 @@ static int __init omap1_init_devices(void) } arch_initcall(omap1_init_devices); -#if defined(CONFIG_OMAP_WATCHDOG) || defined(CONFIG_OMAP_WATCHDOG_MODULE) +#if IS_ENABLED(CONFIG_OMAP_WATCHDOG) static struct resource wdt_resources[] = { { diff --git a/arch/arm/mach-omap1/fb.c b/arch/arm/mach-omap1/fb.c index c770d45c7226..ddab04087b7a 100644 --- a/arch/arm/mach-omap1/fb.c +++ b/arch/arm/mach-omap1/fb.c @@ -33,7 +33,7 @@ #include <asm/mach/map.h> -#if defined(CONFIG_FB_OMAP) || defined(CONFIG_FB_OMAP_MODULE) +#if IS_ENABLED(CONFIG_FB_OMAP) static bool omapfb_lcd_configured; static struct omapfb_platform_data omapfb_config; diff --git a/arch/arm/mach-omap1/include/mach/usb.h b/arch/arm/mach-omap1/include/mach/usb.h index 2c263051dc51..a7c5559caef2 100644 --- a/arch/arm/mach-omap1/include/mach/usb.h +++ b/arch/arm/mach-omap1/include/mach/usb.h @@ -12,7 +12,7 @@ void omap_otg_init(struct omap_usb_config *config); -#if defined(CONFIG_USB) || defined(CONFIG_USB_MODULE) +#if IS_ENABLED(CONFIG_USB) void omap1_usb_init(struct omap_usb_config *pdata); #else static inline void omap1_usb_init(struct omap_usb_config *pdata) diff --git a/arch/arm/mach-omap1/mmc.h b/arch/arm/mach-omap1/mmc.h index 39c2b13de884..d7b46880e4ca 100644 --- a/arch/arm/mach-omap1/mmc.h +++ b/arch/arm/mach-omap1/mmc.h @@ -7,7 +7,7 @@ #define OMAP1_MMC1_BASE 0xfffb7800 #define OMAP1_MMC2_BASE 0xfffb7c00 /* omap16xx only */ -#if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE) +#if IS_ENABLED(CONFIG_MMC_OMAP) void omap1_init_mmc(struct omap_mmc_platform_data **mmc_data, int nr_controllers); #else diff --git a/arch/arm/mach-omap1/usb.c b/arch/arm/mach-omap1/usb.c index 4118db50d5e8..2506e598a067 100644 --- a/arch/arm/mach-omap1/usb.c +++ b/arch/arm/mach-omap1/usb.c @@ -136,7 +136,7 @@ omap_otg_init(struct omap_usb_config *config) } #endif -#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) +#if IS_ENABLED(CONFIG_USB_OHCI_HCD) if (config->otg || config->register_host) { struct platform_device *ohci_device = config->ohci_device; int status; @@ -221,7 +221,7 @@ static inline void udc_device_init(struct omap_usb_config *pdata) #endif -#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) +#if IS_ENABLED(CONFIG_USB_OHCI_HCD) /* The dmamask must be set for OHCI to work */ static u64 ohci_dmamask = ~(u32)0; @@ -612,7 +612,7 @@ static void __init omap_1510_usb_init(struct omap_usb_config *config) } #endif -#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) +#if IS_ENABLED(CONFIG_USB_OHCI_HCD) if (config->register_host) { int status; diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 5a0b380a8166..a9afeebd59f2 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -192,12 +192,6 @@ config MACH_OMAP2_TUSB6010 depends on ARCH_OMAP2 && SOC_OMAP2420 default y if MACH_NOKIA_N8X0 -config MACH_OMAP_LDP - bool "OMAP3 LDP board" - depends on ARCH_OMAP3 - default y - select OMAP_PACKAGE_CBB - config MACH_OMAP3517EVM bool "OMAP3517/ AM3517 EVM board" depends on ARCH_OMAP3 @@ -222,12 +216,6 @@ config MACH_NOKIA_N8X0 select MACH_NOKIA_N810 select MACH_NOKIA_N810_WIMAX -config MACH_NOKIA_RX51 - bool "Nokia N900 (RX-51) phone" - depends on ARCH_OMAP3 - default y - select OMAP_PACKAGE_CBB - config OMAP3_SDRC_AC_TIMING bool "Enable SDRC AC timing register changes" depends on ARCH_OMAP3 diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile index a7f2d051f524..5b37ec29996e 100644 --- a/arch/arm/mach-omap2/Makefile +++ b/arch/arm/mach-omap2/Makefile @@ -231,11 +231,7 @@ obj-$(CONFIG_SOC_OMAP2420) += msdi.o # Specific board support obj-$(CONFIG_MACH_OMAP_GENERIC) += board-generic.o pdata-quirks.o -obj-$(CONFIG_MACH_OMAP_LDP) += board-ldp.o obj-$(CONFIG_MACH_NOKIA_N8X0) += board-n8x0.o -obj-$(CONFIG_MACH_NOKIA_RX51) += board-rx51.o sdram-nokia.o -obj-$(CONFIG_MACH_NOKIA_RX51) += board-rx51-peripherals.o -obj-$(CONFIG_MACH_NOKIA_RX51) += board-rx51-video.o # Platform specific device init code diff --git a/arch/arm/mach-omap2/board-flash.c b/arch/arm/mach-omap2/board-flash.c index 70b21cc279ba..2188dc30e232 100644 --- a/arch/arm/mach-omap2/board-flash.c +++ b/arch/arm/mach-omap2/board-flash.c @@ -81,8 +81,7 @@ __init board_nor_init(struct mtd_partition *nor_parts, u8 nr_parts, u8 cs) pr_err("Unable to register NOR device\n"); } -#if defined(CONFIG_MTD_ONENAND_OMAP2) || \ - defined(CONFIG_MTD_ONENAND_OMAP2_MODULE) +#if IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2) static struct omap_onenand_platform_data board_onenand_data = { .dma_channel = -1, /* disable DMA in OMAP OneNAND driver */ }; @@ -97,10 +96,9 @@ __init board_onenand_init(struct mtd_partition *onenand_parts, gpmc_onenand_init(&board_onenand_data); } -#endif /* CONFIG_MTD_ONENAND_OMAP2 || CONFIG_MTD_ONENAND_OMAP2_MODULE */ +#endif /* IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2) */ -#if defined(CONFIG_MTD_NAND_OMAP2) || \ - defined(CONFIG_MTD_NAND_OMAP2_MODULE) +#if IS_ENABLED(CONFIG_MTD_NAND_OMAP2) /* Note that all values in this struct are in nanoseconds */ struct gpmc_timings nand_default_timings[1] = { @@ -144,7 +142,7 @@ __init board_nand_init(struct mtd_partition *nand_parts, u8 nr_parts, u8 cs, board_nand_data.ecc_opt = OMAP_ECC_HAM1_CODE_SW; gpmc_nand_init(&board_nand_data, gpmc_t); } -#endif /* CONFIG_MTD_NAND_OMAP2 || CONFIG_MTD_NAND_OMAP2_MODULE */ +#endif /* IS_ENABLED(CONFIG_MTD_NAND_OMAP2) */ /** * get_gpmc0_type - Reads the FPGA DIP_SWITCH_INPUT_REGISTER2 to get diff --git a/arch/arm/mach-omap2/board-flash.h b/arch/arm/mach-omap2/board-flash.h index ea9aaebe11e7..8b39eec07318 100644 --- a/arch/arm/mach-omap2/board-flash.h +++ b/arch/arm/mach-omap2/board-flash.h @@ -23,10 +23,7 @@ struct flash_partitions { int nr_parts; }; -#if defined(CONFIG_MTD_NAND_OMAP2) || \ - defined(CONFIG_MTD_NAND_OMAP2_MODULE) || \ - defined(CONFIG_MTD_ONENAND_OMAP2) || \ - defined(CONFIG_MTD_ONENAND_OMAP2_MODULE) +#if IS_ENABLED(CONFIG_MTD_NAND_OMAP2) || IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2) extern void board_flash_init(struct flash_partitions [], char chip_sel[][GPMC_CS_NUM], int nand_type); #else @@ -36,8 +33,7 @@ static inline void board_flash_init(struct flash_partitions part[], } #endif -#if defined(CONFIG_MTD_NAND_OMAP2) || \ - defined(CONFIG_MTD_NAND_OMAP2_MODULE) +#if IS_ENABLED(CONFIG_MTD_NAND_OMAP2) extern void board_nand_init(struct mtd_partition *nand_parts, u8 nr_parts, u8 cs, int nand_type, struct gpmc_timings *gpmc_t); extern struct gpmc_timings nand_default_timings[]; @@ -49,8 +45,7 @@ static inline void board_nand_init(struct mtd_partition *nand_parts, #define nand_default_timings NULL #endif -#if defined(CONFIG_MTD_ONENAND_OMAP2) || \ - defined(CONFIG_MTD_ONENAND_OMAP2_MODULE) +#if IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2) extern void board_onenand_init(struct mtd_partition *nand_parts, u8 nr_parts, u8 cs); #else diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c deleted file mode 100644 index 390795b334c3..000000000000 --- a/arch/arm/mach-omap2/board-ldp.c +++ /dev/null @@ -1,430 +0,0 @@ -/* - * linux/arch/arm/mach-omap2/board-ldp.c - * - * Copyright (C) 2008 Texas Instruments Inc. - * Nishant Kamat <nskamat@ti.com> - * - * Modified from mach-omap2/board-3430sdp.c - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/gpio.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/platform_device.h> -#include <linux/delay.h> -#include <linux/input.h> -#include <linux/input/matrix_keypad.h> -#include <linux/gpio_keys.h> -#include <linux/workqueue.h> -#include <linux/err.h> -#include <linux/clk.h> -#include <linux/spi/spi.h> -#include <linux/regulator/fixed.h> -#include <linux/regulator/machine.h> -#include <linux/i2c/twl.h> -#include <linux/io.h> -#include <linux/smsc911x.h> -#include <linux/mmc/host.h> -#include <linux/usb/phy.h> -#include <linux/platform_data/spi-omap2-mcspi.h> - -#include <asm/mach-types.h> -#include <asm/mach/arch.h> -#include <asm/mach/map.h> - -#include "common.h" -#include "gpmc.h" -#include "gpmc-smsc911x.h" - -#include <linux/platform_data/omapdss.h> -#include <video/omap-panel-data.h> - -#include "board-flash.h" -#include "mux.h" -#include "hsmmc.h" -#include "control.h" -#include "common-board-devices.h" -#include "display.h" - -#define LDP_SMSC911X_CS 1 -#define LDP_SMSC911X_GPIO 152 -#define DEBUG_BASE 0x08000000 -#define LDP_ETHR_START DEBUG_BASE - -static uint32_t board_keymap[] = { - KEY(0, 0, KEY_1), - KEY(1, 0, KEY_2), - KEY(2, 0, KEY_3), - KEY(0, 1, KEY_4), - KEY(1, 1, KEY_5), - KEY(2, 1, KEY_6), - KEY(3, 1, KEY_F5), - KEY(0, 2, KEY_7), - KEY(1, 2, KEY_8), - KEY(2, 2, KEY_9), - KEY(3, 2, KEY_F6), - KEY(0, 3, KEY_F7), - KEY(1, 3, KEY_0), - KEY(2, 3, KEY_F8), - PERSISTENT_KEY(4, 5), - KEY(4, 4, KEY_VOLUMEUP), - KEY(5, 5, KEY_VOLUMEDOWN), - 0 -}; - -static struct matrix_keymap_data board_map_data = { - .keymap = board_keymap, - .keymap_size = ARRAY_SIZE(board_keymap), -}; - -static struct twl4030_keypad_data ldp_kp_twl4030_data = { - .keymap_data = &board_map_data, - .rows = 6, - .cols = 6, - .rep = 1, -}; - -static struct gpio_keys_button ldp_gpio_keys_buttons[] = { - [0] = { - .code = KEY_ENTER, - .gpio = 101, - .desc = "enter sw", - .active_low = 1, - .debounce_interval = 30, - }, - [1] = { - .code = KEY_F1, - .gpio = 102, - .desc = "func 1", - .active_low = 1, - .debounce_interval = 30, - }, - [2] = { - .code = KEY_F2, - .gpio = 103, - .desc = "func 2", - .active_low = 1, - .debounce_interval = 30, - }, - [3] = { - .code = KEY_F3, - .gpio = 104, - .desc = "func 3", - .active_low = 1, - .debounce_interval = 30, - }, - [4] = { - .code = KEY_F4, - .gpio = 105, - .desc = "func 4", - .active_low = 1, - .debounce_interval = 30, - }, - [5] = { - .code = KEY_LEFT, - .gpio = 106, - .desc = "left sw", - .active_low = 1, - .debounce_interval = 30, - }, - [6] = { - .code = KEY_RIGHT, - .gpio = 107, - .desc = "right sw", - .active_low = 1, - .debounce_interval = 30, - }, - [7] = { - .code = KEY_UP, - .gpio = 108, - .desc = "up sw", - .active_low = 1, - .debounce_interval = 30, - }, - [8] = { - .code = KEY_DOWN, - .gpio = 109, - .desc = "down sw", - .active_low = 1, - .debounce_interval = 30, - }, -}; - -static struct gpio_keys_platform_data ldp_gpio_keys = { - .buttons = ldp_gpio_keys_buttons, - .nbuttons = ARRAY_SIZE(ldp_gpio_keys_buttons), - .rep = 1, -}; - -static struct platform_device ldp_gpio_keys_device = { - .name = "gpio-keys", - .id = -1, - .dev = { - .platform_data = &ldp_gpio_keys, - }, -}; - -static struct omap_smsc911x_platform_data smsc911x_cfg = { - .cs = LDP_SMSC911X_CS, - .gpio_irq = LDP_SMSC911X_GPIO, - .gpio_reset = -EINVAL, - .flags = SMSC911X_USE_32BIT, -}; - -static inline void __init ldp_init_smsc911x(void) -{ - gpmc_smsc911x_init(&smsc911x_cfg); -} - -/* LCD */ - -#define LCD_PANEL_RESET_GPIO 55 -#define LCD_PANEL_QVGA_GPIO 56 - -static const struct display_timing ldp_lcd_videomode = { - .pixelclock = { 0, 5400000, 0 }, - - .hactive = { 0, 240, 0 }, - .hfront_porch = { 0, 3, 0 }, - .hback_porch = { 0, 39, 0 }, - .hsync_len = { 0, 3, 0 }, - - .vactive = { 0, 320, 0 }, - .vfront_porch = { 0, 2, 0 }, - .vback_porch = { 0, 7, 0 }, - .vsync_len = { 0, 1, 0 }, - - .flags = DISPLAY_FLAGS_HSYNC_LOW | DISPLAY_FLAGS_VSYNC_LOW | - DISPLAY_FLAGS_DE_HIGH | DISPLAY_FLAGS_PIXDATA_POSEDGE, -}; - -static struct panel_dpi_platform_data ldp_lcd_pdata = { - .name = "lcd", - .source = "dpi.0", - - .data_lines = 18, - - .display_timing = &ldp_lcd_videomode, - - .enable_gpio = -1, /* filled in code */ - .backlight_gpio = -1, /* filled in code */ -}; - -static struct platform_device ldp_lcd_device = { - .name = "panel-dpi", - .id = 0, - .dev.platform_data = &ldp_lcd_pdata, -}; - -static struct omap_dss_board_info ldp_dss_data = { - .default_display_name = "lcd", -}; - -static void __init ldp_display_init(void) -{ - int r; - - static struct gpio gpios[] __initdata = { - {LCD_PANEL_RESET_GPIO, GPIOF_OUT_INIT_HIGH, "LCD RESET"}, - {LCD_PANEL_QVGA_GPIO, GPIOF_OUT_INIT_HIGH, "LCD QVGA"}, - }; - - r = gpio_request_array(gpios, ARRAY_SIZE(gpios)); - if (r) { - pr_err("Cannot request LCD GPIOs, error %d\n", r); - return; - } - - omap_display_init(&ldp_dss_data); -} - -static int ldp_twl_gpio_setup(struct device *dev, unsigned gpio, unsigned ngpio) -{ - int res; - - /* LCD enable GPIO */ - ldp_lcd_pdata.enable_gpio = gpio + 7; - - /* Backlight enable GPIO */ - ldp_lcd_pdata.backlight_gpio = gpio + 15; - - res = platform_device_register(&ldp_lcd_device); - if (res) - pr_err("Unable to register LCD: %d\n", res); - - return 0; -} - -static struct twl4030_gpio_platform_data ldp_gpio_data = { - .setup = ldp_twl_gpio_setup, -}; - -static struct regulator_consumer_supply ldp_vmmc1_supply[] = { - REGULATOR_SUPPLY("vmmc", "omap_hsmmc.0"), -}; - -/* VMMC1 for MMC1 pins CMD, CLK, DAT0..DAT3 (20 mA, plus card == max 220 mA) */ -static struct regulator_init_data ldp_vmmc1 = { - .constraints = { - .min_uV = 1850000, - .max_uV = 3150000, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE - | REGULATOR_CHANGE_MODE - | REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(ldp_vmmc1_supply), - .consumer_supplies = ldp_vmmc1_supply, -}; - -/* ads7846 on SPI */ -static struct regulator_consumer_supply ldp_vaux1_supplies[] = { - REGULATOR_SUPPLY("vcc", "spi1.0"), -}; - -/* VAUX1 */ -static struct regulator_init_data ldp_vaux1 = { - .constraints = { - .min_uV = 3000000, - .max_uV = 3000000, - .apply_uV = true, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_MODE - | REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(ldp_vaux1_supplies), - .consumer_supplies = ldp_vaux1_supplies, -}; - -static struct regulator_consumer_supply ldp_vpll2_supplies[] = { - REGULATOR_SUPPLY("vdds_dsi", "omapdss"), - REGULATOR_SUPPLY("vdds_dsi", "omapdss_dpi.0"), - REGULATOR_SUPPLY("vdds_dsi", "omapdss_dsi.0"), -}; - -static struct regulator_init_data ldp_vpll2 = { - .constraints = { - .name = "VDVI", - .min_uV = 1800000, - .max_uV = 1800000, - .apply_uV = true, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_MODE - | REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(ldp_vpll2_supplies), - .consumer_supplies = ldp_vpll2_supplies, -}; - -static struct twl4030_platform_data ldp_twldata = { - /* platform_data for children goes here */ - .vmmc1 = &ldp_vmmc1, - .vaux1 = &ldp_vaux1, - .vpll2 = &ldp_vpll2, - .gpio = &ldp_gpio_data, - .keypad = &ldp_kp_twl4030_data, -}; - -static int __init omap_i2c_init(void) -{ - omap3_pmic_get_config(&ldp_twldata, - TWL_COMMON_PDATA_USB | TWL_COMMON_PDATA_MADC, 0); - omap3_pmic_init("twl4030", &ldp_twldata); - omap_register_i2c_bus(2, 400, NULL, 0); - omap_register_i2c_bus(3, 400, NULL, 0); - return 0; -} - -static struct omap2_hsmmc_info mmc[] __initdata = { - { - .mmc = 1, - .caps = MMC_CAP_4_BIT_DATA, - .gpio_cd = -EINVAL, - .gpio_wp = -EINVAL, - }, - {} /* Terminator */ -}; - -static struct platform_device *ldp_devices[] __initdata = { - &ldp_gpio_keys_device, -}; - -#ifdef CONFIG_OMAP_MUX -static struct omap_board_mux board_mux[] __initdata = { - { .reg_offset = OMAP_MUX_TERMINATOR }, -}; -#endif - -static struct mtd_partition ldp_nand_partitions[] = { - /* All the partition sizes are listed in terms of NAND block size */ - { - .name = "X-Loader-NAND", - .offset = 0, - .size = 4 * (64 * 2048), /* 512KB, 0x80000 */ - .mask_flags = MTD_WRITEABLE, /* force read-only */ - }, - { - .name = "U-Boot-NAND", - .offset = MTDPART_OFS_APPEND, /* Offset = 0x80000 */ - .size = 10 * (64 * 2048), /* 1.25MB, 0x140000 */ - .mask_flags = MTD_WRITEABLE, /* force read-only */ - }, - { - .name = "Boot Env-NAND", - .offset = MTDPART_OFS_APPEND, /* Offset = 0x1c0000 */ - .size = 2 * (64 * 2048), /* 256KB, 0x40000 */ - }, - { - .name = "Kernel-NAND", - .offset = MTDPART_OFS_APPEND, /* Offset = 0x0200000*/ - .size = 240 * (64 * 2048), /* 30M, 0x1E00000 */ - }, - { - .name = "File System - NAND", - .offset = MTDPART_OFS_APPEND, /* Offset = 0x2000000 */ - .size = MTDPART_SIZ_FULL, /* 96MB, 0x6000000 */ - }, - -}; - -static struct regulator_consumer_supply dummy_supplies[] = { - REGULATOR_SUPPLY("vddvario", "smsc911x.0"), - REGULATOR_SUPPLY("vdd33a", "smsc911x.0"), -}; - -static void __init omap_ldp_init(void) -{ - regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies)); - omap3_mux_init(board_mux, OMAP_PACKAGE_CBB); - ldp_init_smsc911x(); - omap_i2c_init(); - platform_add_devices(ldp_devices, ARRAY_SIZE(ldp_devices)); - omap_ads7846_init(1, 54, 310, NULL); - omap_serial_init(); - omap_sdrc_init(NULL, NULL); - usb_bind_phy("musb-hdrc.0.auto", 0, "twl4030_usb"); - usb_musb_init(NULL); - board_nand_init(ldp_nand_partitions, ARRAY_SIZE(ldp_nand_partitions), - 0, 0, nand_default_timings); - - omap_hsmmc_init(mmc); - ldp_display_init(); -} - -MACHINE_START(OMAP_LDP, "OMAP LDP board") - .atag_offset = 0x100, - .reserve = omap_reserve, - .map_io = omap3_map_io, - .init_early = omap3430_init_early, - .init_irq = omap3_init_irq, - .init_machine = omap_ldp_init, - .init_late = omap3430_init_late, - .init_time = omap_init_time, - .restart = omap3xxx_restart, -MACHINE_END diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c index b6443a4e0c78..6b6fda65fb3b 100644 --- a/arch/arm/mach-omap2/board-n8x0.c +++ b/arch/arm/mach-omap2/board-n8x0.c @@ -66,7 +66,7 @@ static void board_check_revision(void) pr_err("Unknown board\n"); } -#if defined(CONFIG_USB_MUSB_TUSB6010) || defined(CONFIG_USB_MUSB_TUSB6010_MODULE) +#if IS_ENABLED(CONFIG_USB_MUSB_TUSB6010) /* * Enable or disable power to TUSB6010. When enabling, turn on 3.3 V and * 1.5 V voltage regulators of PM companion chip. Companion chip will then @@ -163,8 +163,7 @@ static struct spi_board_info n800_spi_board_info[] __initdata = { }, }; -#if defined(CONFIG_MENELAUS) && \ - (defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE)) +#if defined(CONFIG_MENELAUS) && IS_ENABLED(CONFIG_MMC_OMAP) /* * On both N800 and N810, only the first of the two MMC controllers is in use. diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c deleted file mode 100644 index a5ab712c1a59..000000000000 --- a/arch/arm/mach-omap2/board-rx51-peripherals.c +++ /dev/null @@ -1,1312 +0,0 @@ -/* - * linux/arch/arm/mach-omap2/board-rx51-peripherals.c - * - * Copyright (C) 2008-2009 Nokia - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/platform_device.h> -#include <linux/input.h> -#include <linux/input/matrix_keypad.h> -#include <linux/spi/spi.h> -#include <linux/wl12xx.h> -#include <linux/spi/tsc2005.h> -#include <linux/i2c.h> -#include <linux/i2c/twl.h> -#include <linux/clk.h> -#include <linux/delay.h> -#include <linux/regulator/machine.h> -#include <linux/gpio.h> -#include <linux/gpio_keys.h> -#include <linux/gpio/machine.h> -#include <linux/omap-gpmc.h> -#include <linux/mmc/host.h> -#include <linux/power/isp1704_charger.h> -#include <linux/platform_data/spi-omap2-mcspi.h> -#include <linux/platform_data/mtd-onenand-omap2.h> - -#include <plat/dmtimer.h> - -#include <asm/system_info.h> - -#include "common.h" -#include <linux/omap-dma.h> - -#include "board-rx51.h" - -#include <sound/tlv320aic3x.h> -#include <sound/tpa6130a2-plat.h> -#include <linux/platform_data/media/si4713.h> -#include <linux/platform_data/leds-lp55xx.h> - -#include <linux/platform_data/tsl2563.h> -#include <linux/lis3lv02d.h> - -#include <video/omap-panel-data.h> - -#include <linux/platform_data/pwm_omap_dmtimer.h> -#include <linux/platform_data/media/ir-rx51.h> - -#include "mux.h" -#include "omap-pm.h" -#include "hsmmc.h" -#include "common-board-devices.h" -#include "soc.h" -#include "omap-secure.h" - -#define SYSTEM_REV_B_USES_VAUX3 0x1699 -#define SYSTEM_REV_S_USES_VAUX3 0x8 - -#define RX51_WL1251_POWER_GPIO 87 -#define RX51_WL1251_IRQ_GPIO 42 -#define RX51_FMTX_RESET_GPIO 163 -#define RX51_FMTX_IRQ 53 -#define RX51_LP5523_CHIP_EN_GPIO 41 - -#define RX51_USB_TRANSCEIVER_RST_GPIO 67 - -#define RX51_TSC2005_RESET_GPIO 104 -#define RX51_TSC2005_IRQ_GPIO 100 - -#define LIS302_IRQ1_GPIO 181 -#define LIS302_IRQ2_GPIO 180 /* Not yet in use */ - -/* List all SPI devices here. Note that the list/probe order seems to matter! */ -enum { - RX51_SPI_WL1251, - RX51_SPI_TSC2005, /* Touch Controller */ - RX51_SPI_MIPID, /* LCD panel */ -}; - -static struct wl1251_platform_data wl1251_pdata; -static struct tsc2005_platform_data tsc2005_pdata; - -#if defined(CONFIG_SENSORS_LIS3_I2C) || defined(CONFIG_SENSORS_LIS3_I2C_MODULE) -static int lis302_setup(void) -{ - int err; - int irq1 = LIS302_IRQ1_GPIO; - int irq2 = LIS302_IRQ2_GPIO; - - /* gpio for interrupt pin 1 */ - err = gpio_request(irq1, "lis3lv02dl_irq1"); - if (err) { - printk(KERN_ERR "lis3lv02dl: gpio request failed\n"); - goto out; - } - - /* gpio for interrupt pin 2 */ - err = gpio_request(irq2, "lis3lv02dl_irq2"); - if (err) { - gpio_free(irq1); - printk(KERN_ERR "lis3lv02dl: gpio request failed\n"); - goto out; - } - - gpio_direction_input(irq1); - gpio_direction_input(irq2); - -out: - return err; -} - -static int lis302_release(void) -{ - gpio_free(LIS302_IRQ1_GPIO); - gpio_free(LIS302_IRQ2_GPIO); - - return 0; -} - -static struct lis3lv02d_platform_data rx51_lis3lv02d_data = { - .click_flags = LIS3_CLICK_SINGLE_X | LIS3_CLICK_SINGLE_Y | - LIS3_CLICK_SINGLE_Z, - /* Limits are 0.5g * value */ - .click_thresh_x = 8, - .click_thresh_y = 8, - .click_thresh_z = 10, - /* Click must be longer than time limit */ - .click_time_limit = 9, - /* Kind of debounce filter */ - .click_latency = 50, - - /* Limits for all axis. millig-value / 18 to get HW values */ - .wakeup_flags = LIS3_WAKEUP_X_HI | LIS3_WAKEUP_Y_HI, - .wakeup_thresh = 800 / 18, - .wakeup_flags2 = LIS3_WAKEUP_Z_HI , - .wakeup_thresh2 = 900 / 18, - - .hipass_ctrl = LIS3_HIPASS1_DISABLE | LIS3_HIPASS2_DISABLE, - - /* Interrupt line 2 for click detection, line 1 for thresholds */ - .irq_cfg = LIS3_IRQ2_CLICK | LIS3_IRQ1_FF_WU_12, - - .axis_x = LIS3_DEV_X, - .axis_y = LIS3_INV_DEV_Y, - .axis_z = LIS3_INV_DEV_Z, - .setup_resources = lis302_setup, - .release_resources = lis302_release, - .st_min_limits = {-32, 3, 3}, - .st_max_limits = {-3, 32, 32}, -}; -#endif - -#if defined(CONFIG_SENSORS_TSL2563) || defined(CONFIG_SENSORS_TSL2563_MODULE) -static struct tsl2563_platform_data rx51_tsl2563_platform_data = { - .cover_comp_gain = 16, -}; -#endif - -#if defined(CONFIG_LEDS_LP5523) || defined(CONFIG_LEDS_LP5523_MODULE) -static struct lp55xx_led_config rx51_lp5523_led_config[] = { - { - .name = "lp5523:kb1", - .chan_nr = 0, - .led_current = 50, - .max_current = 100, - }, { - .name = "lp5523:kb2", - .chan_nr = 1, - .led_current = 50, - .max_current = 100, - }, { - .name = "lp5523:kb3", - .chan_nr = 2, - .led_current = 50, - .max_current = 100, - }, { - .name = "lp5523:kb4", - .chan_nr = 3, - .led_current = 50, - .max_current = 100, - }, { - .name = "lp5523:b", - .chan_nr = 4, - .led_current = 50, - .max_current = 100, - }, { - .name = "lp5523:g", - .chan_nr = 5, - .led_current = 50, - .max_current = 100, - }, { - .name = "lp5523:r", - .chan_nr = 6, - .led_current = 50, - .max_current = 100, - }, { - .name = "lp5523:kb5", - .chan_nr = 7, - .led_current = 50, - .max_current = 100, - }, { - .name = "lp5523:kb6", - .chan_nr = 8, - .led_current = 50, - .max_current = 100, - } -}; - -static struct lp55xx_platform_data rx51_lp5523_platform_data = { - .led_config = rx51_lp5523_led_config, - .num_channels = ARRAY_SIZE(rx51_lp5523_led_config), - .clock_mode = LP55XX_CLOCK_AUTO, - .enable_gpio = RX51_LP5523_CHIP_EN_GPIO, -}; -#endif - -#define RX51_LCD_RESET_GPIO 90 - -static struct panel_acx565akm_platform_data acx_pdata = { - .name = "lcd", - .source = "sdi.0", - .reset_gpio = RX51_LCD_RESET_GPIO, - .datapairs = 2, -}; - -static struct omap2_mcspi_device_config wl1251_mcspi_config = { - .turbo_mode = 0, -}; - -static struct omap2_mcspi_device_config mipid_mcspi_config = { - .turbo_mode = 0, -}; - -static struct omap2_mcspi_device_config tsc2005_mcspi_config = { - .turbo_mode = 0, -}; - -static struct spi_board_info rx51_peripherals_spi_board_info[] __initdata = { - [RX51_SPI_WL1251] = { - .modalias = "wl1251", - .bus_num = 4, - .chip_select = 0, - .max_speed_hz = 48000000, - .mode = SPI_MODE_3, - .controller_data = &wl1251_mcspi_config, - .platform_data = &wl1251_pdata, - }, - [RX51_SPI_MIPID] = { - .modalias = "acx565akm", - .bus_num = 1, - .chip_select = 2, - .max_speed_hz = 6000000, - .controller_data = &mipid_mcspi_config, - .platform_data = &acx_pdata, - }, - [RX51_SPI_TSC2005] = { - .modalias = "tsc2005", - .bus_num = 1, - .chip_select = 0, - .max_speed_hz = 6000000, - .controller_data = &tsc2005_mcspi_config, - .platform_data = &tsc2005_pdata, - }, -}; - -static struct platform_device rx51_battery_device = { - .name = "rx51-battery", - .id = -1, -}; - -static void rx51_charger_set_power(bool on) -{ - gpio_set_value(RX51_USB_TRANSCEIVER_RST_GPIO, on); -} - -static struct isp1704_charger_data rx51_charger_data = { - .set_power = rx51_charger_set_power, -}; - -static struct platform_device rx51_charger_device = { - .name = "isp1704_charger", - .dev = { - .platform_data = &rx51_charger_data, - }, -}; - -static void __init rx51_charger_init(void) -{ - WARN_ON(gpio_request_one(RX51_USB_TRANSCEIVER_RST_GPIO, - GPIOF_OUT_INIT_HIGH, "isp1704_reset")); - - platform_device_register(&rx51_battery_device); - platform_device_register(&rx51_charger_device); -} - -#if defined(CONFIG_KEYBOARD_GPIO) || defined(CONFIG_KEYBOARD_GPIO_MODULE) - -#define RX51_GPIO_CAMERA_LENS_COVER 110 -#define RX51_GPIO_CAMERA_FOCUS 68 -#define RX51_GPIO_CAMERA_CAPTURE 69 -#define RX51_GPIO_KEYPAD_SLIDE 71 -#define RX51_GPIO_LOCK_BUTTON 113 -#define RX51_GPIO_PROXIMITY 89 - -#define RX51_GPIO_DEBOUNCE_TIMEOUT 10 - -static struct gpio_keys_button rx51_gpio_keys[] = { - { - .desc = "Camera Lens Cover", - .type = EV_SW, - .code = SW_CAMERA_LENS_COVER, - .gpio = RX51_GPIO_CAMERA_LENS_COVER, - .active_low = 1, - .debounce_interval = RX51_GPIO_DEBOUNCE_TIMEOUT, - }, { - .desc = "Camera Focus", - .type = EV_KEY, - .code = KEY_CAMERA_FOCUS, - .gpio = RX51_GPIO_CAMERA_FOCUS, - .active_low = 1, - .debounce_interval = RX51_GPIO_DEBOUNCE_TIMEOUT, - }, { - .desc = "Camera Capture", - .type = EV_KEY, - .code = KEY_CAMERA, - .gpio = RX51_GPIO_CAMERA_CAPTURE, - .active_low = 1, - .debounce_interval = RX51_GPIO_DEBOUNCE_TIMEOUT, - }, { - .desc = "Lock Button", - .type = EV_KEY, - .code = KEY_SCREENLOCK, - .gpio = RX51_GPIO_LOCK_BUTTON, - .active_low = 1, - .debounce_interval = RX51_GPIO_DEBOUNCE_TIMEOUT, - }, { - .desc = "Keypad Slide", - .type = EV_SW, - .code = SW_KEYPAD_SLIDE, - .gpio = RX51_GPIO_KEYPAD_SLIDE, - .active_low = 1, - .debounce_interval = RX51_GPIO_DEBOUNCE_TIMEOUT, - }, { - .desc = "Proximity Sensor", - .type = EV_SW, - .code = SW_FRONT_PROXIMITY, - .gpio = RX51_GPIO_PROXIMITY, - .active_low = 0, - .debounce_interval = RX51_GPIO_DEBOUNCE_TIMEOUT, - } -}; - -static struct gpio_keys_platform_data rx51_gpio_keys_data = { - .buttons = rx51_gpio_keys, - .nbuttons = ARRAY_SIZE(rx51_gpio_keys), -}; - -static struct platform_device rx51_gpio_keys_device = { - .name = "gpio-keys", - .id = -1, - .dev = { - .platform_data = &rx51_gpio_keys_data, - }, -}; - -static void __init rx51_add_gpio_keys(void) -{ - platform_device_register(&rx51_gpio_keys_device); -} -#else -static void __init rx51_add_gpio_keys(void) -{ -} -#endif /* CONFIG_KEYBOARD_GPIO || CONFIG_KEYBOARD_GPIO_MODULE */ - -static uint32_t board_keymap[] = { - /* - * Note that KEY(x, 8, KEY_XXX) entries represent "entrire row - * connected to the ground" matrix state. - */ - KEY(0, 0, KEY_Q), - KEY(0, 1, KEY_O), - KEY(0, 2, KEY_P), - KEY(0, 3, KEY_COMMA), - KEY(0, 4, KEY_BACKSPACE), - KEY(0, 6, KEY_A), - KEY(0, 7, KEY_S), - - KEY(1, 0, KEY_W), - KEY(1, 1, KEY_D), - KEY(1, 2, KEY_F), - KEY(1, 3, KEY_G), - KEY(1, 4, KEY_H), - KEY(1, 5, KEY_J), - KEY(1, 6, KEY_K), - KEY(1, 7, KEY_L), - - KEY(2, 0, KEY_E), - KEY(2, 1, KEY_DOT), - KEY(2, 2, KEY_UP), - KEY(2, 3, KEY_ENTER), - KEY(2, 5, KEY_Z), - KEY(2, 6, KEY_X), - KEY(2, 7, KEY_C), - KEY(2, 8, KEY_F9), - - KEY(3, 0, KEY_R), - KEY(3, 1, KEY_V), - KEY(3, 2, KEY_B), - KEY(3, 3, KEY_N), - KEY(3, 4, KEY_M), - KEY(3, 5, KEY_SPACE), - KEY(3, 6, KEY_SPACE), - KEY(3, 7, KEY_LEFT), - - KEY(4, 0, KEY_T), - KEY(4, 1, KEY_DOWN), - KEY(4, 2, KEY_RIGHT), - KEY(4, 4, KEY_LEFTCTRL), - KEY(4, 5, KEY_RIGHTALT), - KEY(4, 6, KEY_LEFTSHIFT), - KEY(4, 8, KEY_F10), - - KEY(5, 0, KEY_Y), - KEY(5, 8, KEY_F11), - - KEY(6, 0, KEY_U), - - KEY(7, 0, KEY_I), - KEY(7, 1, KEY_F7), - KEY(7, 2, KEY_F8), -}; - -static struct matrix_keymap_data board_map_data = { - .keymap = board_keymap, - .keymap_size = ARRAY_SIZE(board_keymap), -}; - -static struct twl4030_keypad_data rx51_kp_data = { - .keymap_data = &board_map_data, - .rows = 8, - .cols = 8, - .rep = 1, -}; - -/* Enable input logic and pull all lines up when eMMC is on. */ -static struct omap_board_mux rx51_mmc2_on_mux[] = { - OMAP3_MUX(SDMMC2_CMD, OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT0, OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT1, OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT2, OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT3, OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT4, OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT5, OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT6, OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT7, OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0), - { .reg_offset = OMAP_MUX_TERMINATOR }, -}; - -/* Disable input logic and pull all lines down when eMMC is off. */ -static struct omap_board_mux rx51_mmc2_off_mux[] = { - OMAP3_MUX(SDMMC2_CMD, OMAP_PULL_ENA | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT0, OMAP_PULL_ENA | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT1, OMAP_PULL_ENA | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT2, OMAP_PULL_ENA | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT3, OMAP_PULL_ENA | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT4, OMAP_PULL_ENA | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT5, OMAP_PULL_ENA | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT6, OMAP_PULL_ENA | OMAP_MUX_MODE0), - OMAP3_MUX(SDMMC2_DAT7, OMAP_PULL_ENA | OMAP_MUX_MODE0), - { .reg_offset = OMAP_MUX_TERMINATOR }, -}; - -static struct omap_mux_partition *partition; - -/* - * Current flows to eMMC when eMMC is off and the data lines are pulled up, - * so pull them down. N.B. we pull 8 lines because we are using 8 lines. - */ -static void rx51_mmc2_remux(struct device *dev, int power_on) -{ - if (power_on) - omap_mux_write_array(partition, rx51_mmc2_on_mux); - else - omap_mux_write_array(partition, rx51_mmc2_off_mux); -} - -static struct omap2_hsmmc_info mmc[] __initdata = { - { - .name = "external", - .mmc = 1, - .caps = MMC_CAP_4_BIT_DATA, - .cover_only = true, - .gpio_cd = 160, - .gpio_wp = -EINVAL, - }, - { - .name = "internal", - .mmc = 2, - .caps = MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA, - /* See also rx51_mmc2_remux */ - .gpio_cd = -EINVAL, - .gpio_wp = -EINVAL, - .nonremovable = true, - .remux = rx51_mmc2_remux, - }, - {} /* Terminator */ -}; - -static struct regulator_consumer_supply rx51_vmmc1_supply[] = { - REGULATOR_SUPPLY("vmmc", "omap_hsmmc.0"), -}; - -static struct regulator_consumer_supply rx51_vaux2_supply[] = { - REGULATOR_SUPPLY("vdds_csib", "omap3isp"), -}; - -static struct regulator_consumer_supply rx51_vaux3_supply[] = { - REGULATOR_SUPPLY("vmmc", "omap_hsmmc.1"), -}; - -static struct regulator_consumer_supply rx51_vsim_supply[] = { - REGULATOR_SUPPLY("vmmc_aux", "omap_hsmmc.1"), -}; - -static struct regulator_consumer_supply rx51_vmmc2_supplies[] = { - /* tlv320aic3x analog supplies */ - REGULATOR_SUPPLY("AVDD", "2-0018"), - REGULATOR_SUPPLY("DRVDD", "2-0018"), - REGULATOR_SUPPLY("AVDD", "2-0019"), - REGULATOR_SUPPLY("DRVDD", "2-0019"), - /* tpa6130a2 */ - REGULATOR_SUPPLY("Vdd", "2-0060"), - /* Keep vmmc as last item. It is not iterated for newer boards */ - REGULATOR_SUPPLY("vmmc", "omap_hsmmc.1"), -}; - -static struct regulator_consumer_supply rx51_vio_supplies[] = { - /* tlv320aic3x digital supplies */ - REGULATOR_SUPPLY("IOVDD", "2-0018"), - REGULATOR_SUPPLY("DVDD", "2-0018"), - REGULATOR_SUPPLY("IOVDD", "2-0019"), - REGULATOR_SUPPLY("DVDD", "2-0019"), - /* Si4713 IO supply */ - REGULATOR_SUPPLY("vio", "2-0063"), - /* lis3lv02d */ - REGULATOR_SUPPLY("Vdd_IO", "3-001d"), -}; - -static struct regulator_consumer_supply rx51_vaux1_consumers[] = { - REGULATOR_SUPPLY("vdds_sdi", "omapdss"), - REGULATOR_SUPPLY("vdds_sdi", "omapdss_sdi.0"), - /* Si4713 supply */ - REGULATOR_SUPPLY("vdd", "2-0063"), - /* lis3lv02d */ - REGULATOR_SUPPLY("Vdd", "3-001d"), -}; - -static struct regulator_init_data rx51_vaux1 = { - .constraints = { - .name = "V28", - .min_uV = 2800000, - .max_uV = 2800000, - .always_on = true, /* due battery cover sensor */ - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_MODE - | REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(rx51_vaux1_consumers), - .consumer_supplies = rx51_vaux1_consumers, -}; - -static struct regulator_init_data rx51_vaux2 = { - .constraints = { - .name = "VCSI", - .min_uV = 1800000, - .max_uV = 1800000, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_MODE - | REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(rx51_vaux2_supply), - .consumer_supplies = rx51_vaux2_supply, -}; - -/* VAUX3 - adds more power to VIO_18 rail */ -static struct regulator_init_data rx51_vaux3_cam = { - .constraints = { - .name = "VCAM_DIG_18", - .min_uV = 1800000, - .max_uV = 1800000, - .apply_uV = true, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_MODE - | REGULATOR_CHANGE_STATUS, - }, -}; - -static struct regulator_init_data rx51_vaux3_mmc = { - .constraints = { - .name = "VMMC2_30", - .min_uV = 2800000, - .max_uV = 3000000, - .apply_uV = true, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE - | REGULATOR_CHANGE_MODE - | REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(rx51_vaux3_supply), - .consumer_supplies = rx51_vaux3_supply, -}; - -static struct regulator_init_data rx51_vaux4 = { - .constraints = { - .name = "VCAM_ANA_28", - .min_uV = 2800000, - .max_uV = 2800000, - .apply_uV = true, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_MODE - | REGULATOR_CHANGE_STATUS, - }, -}; - -static struct regulator_init_data rx51_vmmc1 = { - .constraints = { - .min_uV = 1850000, - .max_uV = 3150000, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE - | REGULATOR_CHANGE_MODE - | REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(rx51_vmmc1_supply), - .consumer_supplies = rx51_vmmc1_supply, -}; - -static struct regulator_init_data rx51_vmmc2 = { - .constraints = { - .name = "V28_A", - .min_uV = 2800000, - .max_uV = 3000000, - .always_on = true, /* due VIO leak to AIC34 VDDs */ - .apply_uV = true, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE - | REGULATOR_CHANGE_MODE - | REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(rx51_vmmc2_supplies), - .consumer_supplies = rx51_vmmc2_supplies, -}; - -static struct regulator_init_data rx51_vpll1 = { - .constraints = { - .name = "VPLL", - .min_uV = 1800000, - .max_uV = 1800000, - .apply_uV = true, - .always_on = true, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_MODE, - }, -}; - -static struct regulator_init_data rx51_vpll2 = { - .constraints = { - .name = "VSDI_CSI", - .min_uV = 1800000, - .max_uV = 1800000, - .apply_uV = true, - .always_on = true, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_MODE, - }, -}; - -static struct regulator_init_data rx51_vsim = { - .constraints = { - .name = "VMMC2_IO_18", - .min_uV = 1800000, - .max_uV = 1800000, - .apply_uV = true, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_MODE - | REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(rx51_vsim_supply), - .consumer_supplies = rx51_vsim_supply, -}; - -static struct regulator_init_data rx51_vio = { - .constraints = { - .min_uV = 1800000, - .max_uV = 1800000, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE - | REGULATOR_CHANGE_MODE - | REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(rx51_vio_supplies), - .consumer_supplies = rx51_vio_supplies, -}; - -static struct regulator_init_data rx51_vintana1 = { - .constraints = { - .name = "VINTANA1", - .min_uV = 1500000, - .max_uV = 1500000, - .always_on = true, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_MODE, - }, -}; - -static struct regulator_init_data rx51_vintana2 = { - .constraints = { - .name = "VINTANA2", - .min_uV = 2750000, - .max_uV = 2750000, - .apply_uV = true, - .always_on = true, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_MODE, - }, -}; - -static struct regulator_init_data rx51_vintdig = { - .constraints = { - .name = "VINTDIG", - .min_uV = 1500000, - .max_uV = 1500000, - .always_on = true, - .valid_modes_mask = REGULATOR_MODE_NORMAL - | REGULATOR_MODE_STANDBY, - .valid_ops_mask = REGULATOR_CHANGE_MODE, - }, -}; - -static struct gpiod_lookup_table rx51_fmtx_gpios_table = { - .dev_id = "2-0063", - .table = { - GPIO_LOOKUP("gpio.6", 3, "reset", GPIO_ACTIVE_HIGH), /* 163 */ - { }, - }, -}; - -static __init void rx51_gpio_init(void) -{ - gpiod_add_lookup_table(&rx51_fmtx_gpios_table); -} - -static int rx51_twlgpio_setup(struct device *dev, unsigned gpio, unsigned n) -{ - /* FIXME this gpio setup is just a placeholder for now */ - gpio_request_one(gpio + 6, GPIOF_OUT_INIT_LOW, "backlight_pwm"); - gpio_request_one(gpio + 7, GPIOF_OUT_INIT_LOW, "speaker_en"); - - return 0; -} - -static struct twl4030_gpio_platform_data rx51_gpio_data = { - .pulldowns = BIT(0) | BIT(1) | BIT(2) | BIT(3) - | BIT(4) | BIT(5) - | BIT(8) | BIT(9) | BIT(10) | BIT(11) - | BIT(12) | BIT(13) | BIT(14) | BIT(15) - | BIT(16) | BIT(17) , - .setup = rx51_twlgpio_setup, -}; - -static struct twl4030_ins sleep_on_seq[] __initdata = { -/* - * Turn off everything - */ - {MSG_BROADCAST(DEV_GRP_NULL, RES_GRP_ALL, 1, 0, RES_STATE_SLEEP), 2}, -}; - -static struct twl4030_script sleep_on_script __initdata = { - .script = sleep_on_seq, - .size = ARRAY_SIZE(sleep_on_seq), - .flags = TWL4030_SLEEP_SCRIPT, -}; - -static struct twl4030_ins wakeup_seq[] __initdata = { -/* - * Reenable everything - */ - {MSG_BROADCAST(DEV_GRP_NULL, RES_GRP_ALL, 1, 0, RES_STATE_ACTIVE), 2}, -}; - -static struct twl4030_script wakeup_script __initdata = { - .script = wakeup_seq, - .size = ARRAY_SIZE(wakeup_seq), - .flags = TWL4030_WAKEUP12_SCRIPT, -}; - -static struct twl4030_ins wakeup_p3_seq[] __initdata = { -/* - * Reenable everything - */ - {MSG_BROADCAST(DEV_GRP_NULL, RES_GRP_ALL, 1, 0, RES_STATE_ACTIVE), 2}, -}; - -static struct twl4030_script wakeup_p3_script __initdata = { - .script = wakeup_p3_seq, - .size = ARRAY_SIZE(wakeup_p3_seq), - .flags = TWL4030_WAKEUP3_SCRIPT, -}; - -static struct twl4030_ins wrst_seq[] __initdata = { -/* - * Reset twl4030. - * Reset VDD1 regulator. - * Reset VDD2 regulator. - * Reset VPLL1 regulator. - * Enable sysclk output. - * Reenable twl4030. - */ - {MSG_SINGULAR(DEV_GRP_NULL, RES_RESET, RES_STATE_OFF), 2}, - {MSG_BROADCAST(DEV_GRP_NULL, RES_GRP_ALL, 0, 1, RES_STATE_ACTIVE), - 0x13}, - {MSG_BROADCAST(DEV_GRP_NULL, RES_GRP_PP, 0, 3, RES_STATE_OFF), 0x13}, - {MSG_SINGULAR(DEV_GRP_NULL, RES_VDD1, RES_STATE_WRST), 0x13}, - {MSG_SINGULAR(DEV_GRP_NULL, RES_VDD2, RES_STATE_WRST), 0x13}, - {MSG_SINGULAR(DEV_GRP_NULL, RES_VPLL1, RES_STATE_WRST), 0x35}, - {MSG_SINGULAR(DEV_GRP_P3, RES_HFCLKOUT, RES_STATE_ACTIVE), 2}, - {MSG_SINGULAR(DEV_GRP_NULL, RES_RESET, RES_STATE_ACTIVE), 2}, -}; - -static struct twl4030_script wrst_script __initdata = { - .script = wrst_seq, - .size = ARRAY_SIZE(wrst_seq), - .flags = TWL4030_WRST_SCRIPT, -}; - -static struct twl4030_script *twl4030_scripts[] __initdata = { - /* wakeup12 script should be loaded before sleep script, otherwise a - board might hit retention before loading of wakeup script is - completed. This can cause boot failures depending on timing issues. - */ - &wakeup_script, - &sleep_on_script, - &wakeup_p3_script, - &wrst_script, -}; - -static struct twl4030_resconfig twl4030_rconfig[] __initdata = { - { .resource = RES_VDD1, .devgroup = -1, - .type = 1, .type2 = -1, .remap_off = RES_STATE_OFF, - .remap_sleep = RES_STATE_OFF - }, - { .resource = RES_VDD2, .devgroup = -1, - .type = 1, .type2 = -1, .remap_off = RES_STATE_OFF, - .remap_sleep = RES_STATE_OFF - }, - { .resource = RES_VPLL1, .devgroup = -1, - .type = 1, .type2 = -1, .remap_off = RES_STATE_OFF, - .remap_sleep = RES_STATE_OFF - }, - { .resource = RES_VPLL2, .devgroup = -1, - .type = -1, .type2 = 3, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_VAUX1, .devgroup = -1, - .type = -1, .type2 = 3, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_VAUX2, .devgroup = -1, - .type = -1, .type2 = 3, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_VAUX3, .devgroup = -1, - .type = -1, .type2 = 3, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_VAUX4, .devgroup = -1, - .type = -1, .type2 = 3, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_VMMC1, .devgroup = -1, - .type = -1, .type2 = 3, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_VMMC2, .devgroup = -1, - .type = -1, .type2 = 3, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_VDAC, .devgroup = -1, - .type = -1, .type2 = 3, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_VSIM, .devgroup = -1, - .type = -1, .type2 = 3, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_VINTANA1, .devgroup = DEV_GRP_P1 | DEV_GRP_P3, - .type = -1, .type2 = -1, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_VINTANA2, .devgroup = DEV_GRP_P1 | DEV_GRP_P3, - .type = 1, .type2 = -1, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_VINTDIG, .devgroup = DEV_GRP_P1 | DEV_GRP_P3, - .type = -1, .type2 = -1, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_VIO, .devgroup = DEV_GRP_P3, - .type = 1, .type2 = -1, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_CLKEN, .devgroup = DEV_GRP_P1 | DEV_GRP_P3, - .type = 1, .type2 = -1 , .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_REGEN, .devgroup = DEV_GRP_P1 | DEV_GRP_P3, - .type = 1, .type2 = -1, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_NRES_PWRON, .devgroup = DEV_GRP_P1 | DEV_GRP_P3, - .type = 1, .type2 = -1, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_SYSEN, .devgroup = DEV_GRP_P1 | DEV_GRP_P3, - .type = 1, .type2 = -1, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_HFCLKOUT, .devgroup = DEV_GRP_P3, - .type = 1, .type2 = -1, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_32KCLKOUT, .devgroup = -1, - .type = 1, .type2 = -1, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_RESET, .devgroup = -1, - .type = 1, .type2 = -1, .remap_off = -1, .remap_sleep = -1 - }, - { .resource = RES_MAIN_REF, .devgroup = -1, - .type = 1, .type2 = -1, .remap_off = -1, .remap_sleep = -1 - }, - { 0, 0}, -}; - -static struct twl4030_power_data rx51_t2scripts_data __initdata = { - .scripts = twl4030_scripts, - .num = ARRAY_SIZE(twl4030_scripts), - .resource_config = twl4030_rconfig, -}; - -static struct twl4030_vibra_data rx51_vibra_data __initdata = { - .coexist = 0, -}; - -static struct twl4030_audio_data rx51_audio_data __initdata = { - .audio_mclk = 26000000, - .vibra = &rx51_vibra_data, -}; - -static struct twl4030_platform_data rx51_twldata __initdata = { - /* platform_data for children goes here */ - .gpio = &rx51_gpio_data, - .keypad = &rx51_kp_data, - .power = &rx51_t2scripts_data, - .audio = &rx51_audio_data, - - .vaux1 = &rx51_vaux1, - .vaux2 = &rx51_vaux2, - .vaux4 = &rx51_vaux4, - .vmmc1 = &rx51_vmmc1, - .vpll1 = &rx51_vpll1, - .vpll2 = &rx51_vpll2, - .vsim = &rx51_vsim, - .vintana1 = &rx51_vintana1, - .vintana2 = &rx51_vintana2, - .vintdig = &rx51_vintdig, - .vio = &rx51_vio, -}; - -static struct tpa6130a2_platform_data rx51_tpa6130a2_data __initdata_or_module = { - .power_gpio = 98, -}; - -/* Audio setup data */ -static struct aic3x_setup_data rx51_aic34_setup = { - .gpio_func[0] = AIC3X_GPIO1_FUNC_DISABLED, - .gpio_func[1] = AIC3X_GPIO2_FUNC_DIGITAL_MIC_INPUT, -}; - -static struct aic3x_pdata rx51_aic3x_data = { - .setup = &rx51_aic34_setup, - .gpio_reset = 60, -}; - -static struct aic3x_pdata rx51_aic3x_data2 = { - .gpio_reset = 60, -}; - -#if IS_ENABLED(CONFIG_I2C_SI4713) && IS_ENABLED(CONFIG_PLATFORM_SI4713) -static struct si4713_platform_data rx51_si4713_platform_data = { - .is_platform_device = true -}; -#endif - -static struct i2c_board_info __initdata rx51_peripherals_i2c_board_info_2[] = { -#if IS_ENABLED(CONFIG_I2C_SI4713) && IS_ENABLED(CONFIG_PLATFORM_SI4713) - { - I2C_BOARD_INFO("si4713", 0x63), - .platform_data = &rx51_si4713_platform_data, - }, -#endif - { - I2C_BOARD_INFO("tlv320aic3x", 0x18), - .platform_data = &rx51_aic3x_data, - }, - { - I2C_BOARD_INFO("tlv320aic3x", 0x19), - .platform_data = &rx51_aic3x_data2, - }, -#if defined(CONFIG_SENSORS_TSL2563) || defined(CONFIG_SENSORS_TSL2563_MODULE) - { - I2C_BOARD_INFO("tsl2563", 0x29), - .platform_data = &rx51_tsl2563_platform_data, - }, -#endif -#if defined(CONFIG_LEDS_LP5523) || defined(CONFIG_LEDS_LP5523_MODULE) - { - I2C_BOARD_INFO("lp5523", 0x32), - .platform_data = &rx51_lp5523_platform_data, - }, -#endif - { - I2C_BOARD_INFO("bq27200", 0x55), - }, - { - I2C_BOARD_INFO("tpa6130a2", 0x60), - .platform_data = &rx51_tpa6130a2_data, - } -}; - -static struct i2c_board_info __initdata rx51_peripherals_i2c_board_info_3[] = { -#if defined(CONFIG_SENSORS_LIS3_I2C) || defined(CONFIG_SENSORS_LIS3_I2C_MODULE) - { - I2C_BOARD_INFO("lis3lv02d", 0x1d), - .platform_data = &rx51_lis3lv02d_data, - }, -#endif -}; - -static int __init rx51_i2c_init(void) -{ -#if IS_ENABLED(CONFIG_I2C_SI4713) && IS_ENABLED(CONFIG_PLATFORM_SI4713) - int err; -#endif - - if ((system_rev >= SYSTEM_REV_S_USES_VAUX3 && system_rev < 0x100) || - system_rev >= SYSTEM_REV_B_USES_VAUX3) { - rx51_twldata.vaux3 = &rx51_vaux3_mmc; - /* Only older boards use VMMC2 for internal MMC */ - rx51_vmmc2.num_consumer_supplies--; - } else { - rx51_twldata.vaux3 = &rx51_vaux3_cam; - } - rx51_twldata.vmmc2 = &rx51_vmmc2; - omap3_pmic_get_config(&rx51_twldata, - TWL_COMMON_PDATA_USB | TWL_COMMON_PDATA_MADC, - TWL_COMMON_REGULATOR_VDAC); - - rx51_twldata.vdac->constraints.apply_uV = true; - rx51_twldata.vdac->constraints.name = "VDAC"; - - omap_pmic_init(1, 2200, "twl5030", 7 + OMAP_INTC_START, &rx51_twldata); -#if IS_ENABLED(CONFIG_I2C_SI4713) && IS_ENABLED(CONFIG_PLATFORM_SI4713) - err = gpio_request_one(RX51_FMTX_IRQ, GPIOF_DIR_IN, "si4713 irq"); - if (err) { - printk(KERN_ERR "Cannot request si4713 irq gpio. %d\n", err); - return err; - } - rx51_peripherals_i2c_board_info_2[0].irq = gpio_to_irq(RX51_FMTX_IRQ); -#endif - omap_register_i2c_bus(2, 100, rx51_peripherals_i2c_board_info_2, - ARRAY_SIZE(rx51_peripherals_i2c_board_info_2)); -#if defined(CONFIG_SENSORS_LIS3_I2C) || defined(CONFIG_SENSORS_LIS3_I2C_MODULE) - rx51_lis3lv02d_data.irq2 = gpio_to_irq(LIS302_IRQ2_GPIO); - rx51_peripherals_i2c_board_info_3[0].irq = gpio_to_irq(LIS302_IRQ1_GPIO); -#endif - omap_register_i2c_bus(3, 400, rx51_peripherals_i2c_board_info_3, - ARRAY_SIZE(rx51_peripherals_i2c_board_info_3)); - return 0; -} - -#if defined(CONFIG_MTD_ONENAND_OMAP2) || \ - defined(CONFIG_MTD_ONENAND_OMAP2_MODULE) - -static struct mtd_partition onenand_partitions[] = { - { - .name = "bootloader", - .offset = 0, - .size = 0x20000, - .mask_flags = MTD_WRITEABLE, /* Force read-only */ - }, - { - .name = "config", - .offset = MTDPART_OFS_APPEND, - .size = 0x60000, - }, - { - .name = "log", - .offset = MTDPART_OFS_APPEND, - .size = 0x40000, - }, - { - .name = "kernel", - .offset = MTDPART_OFS_APPEND, - .size = 0x200000, - }, - { - .name = "initfs", - .offset = MTDPART_OFS_APPEND, - .size = 0x200000, - }, - { - .name = "rootfs", - .offset = MTDPART_OFS_APPEND, - .size = MTDPART_SIZ_FULL, - }, -}; - -static struct omap_onenand_platform_data board_onenand_data[] = { - { - .cs = 0, - .gpio_irq = 65, - .parts = onenand_partitions, - .nr_parts = ARRAY_SIZE(onenand_partitions), - .flags = ONENAND_SYNC_READWRITE, - } -}; -#endif - -static struct gpio rx51_wl1251_gpios[] __initdata = { - { RX51_WL1251_IRQ_GPIO, GPIOF_IN, "wl1251 irq" }, -}; - -static void __init rx51_init_wl1251(void) -{ - int irq, ret; - - ret = gpio_request_array(rx51_wl1251_gpios, - ARRAY_SIZE(rx51_wl1251_gpios)); - if (ret < 0) - goto error; - - irq = gpio_to_irq(RX51_WL1251_IRQ_GPIO); - if (irq < 0) - goto err_irq; - - wl1251_pdata.power_gpio = RX51_WL1251_POWER_GPIO; - rx51_peripherals_spi_board_info[RX51_SPI_WL1251].irq = irq; - - return; - -err_irq: - gpio_free(RX51_WL1251_IRQ_GPIO); -error: - printk(KERN_ERR "wl1251 board initialisation failed\n"); - wl1251_pdata.power_gpio = -1; - - /* - * Now rx51_peripherals_spi_board_info[1].irq is zero and - * set_power is null, and wl1251_probe() will fail. - */ -} - -static struct tsc2005_platform_data tsc2005_pdata = { - .ts_pressure_max = 2048, - .ts_pressure_fudge = 2, - .ts_x_max = 4096, - .ts_x_fudge = 4, - .ts_y_max = 4096, - .ts_y_fudge = 7, - .ts_x_plate_ohm = 280, - .esd_timeout_ms = 8000, -}; - -static struct gpio rx51_tsc2005_gpios[] __initdata = { - { RX51_TSC2005_IRQ_GPIO, GPIOF_IN, "tsc2005 IRQ" }, - { RX51_TSC2005_RESET_GPIO, GPIOF_OUT_INIT_HIGH, "tsc2005 reset" }, -}; - -static void rx51_tsc2005_set_reset(bool enable) -{ - gpio_set_value(RX51_TSC2005_RESET_GPIO, enable); -} - -static void __init rx51_init_tsc2005(void) -{ - int r; - - omap_mux_init_gpio(RX51_TSC2005_RESET_GPIO, OMAP_PIN_OUTPUT); - omap_mux_init_gpio(RX51_TSC2005_IRQ_GPIO, OMAP_PIN_INPUT_PULLUP); - - r = gpio_request_array(rx51_tsc2005_gpios, - ARRAY_SIZE(rx51_tsc2005_gpios)); - if (r < 0) { - printk(KERN_ERR "tsc2005 board initialization failed\n"); - tsc2005_pdata.esd_timeout_ms = 0; - return; - } - - tsc2005_pdata.set_reset = rx51_tsc2005_set_reset; - rx51_peripherals_spi_board_info[RX51_SPI_TSC2005].irq = - gpio_to_irq(RX51_TSC2005_IRQ_GPIO); -} - -#if IS_ENABLED(CONFIG_OMAP_DM_TIMER) -static struct pwm_omap_dmtimer_pdata __maybe_unused pwm_dmtimer_pdata = { - .request_by_node = omap_dm_timer_request_by_node, - .request_specific = omap_dm_timer_request_specific, - .request = omap_dm_timer_request, - .set_source = omap_dm_timer_set_source, - .get_irq = omap_dm_timer_get_irq, - .set_int_enable = omap_dm_timer_set_int_enable, - .set_int_disable = omap_dm_timer_set_int_disable, - .free = omap_dm_timer_free, - .enable = omap_dm_timer_enable, - .disable = omap_dm_timer_disable, - .get_fclk = omap_dm_timer_get_fclk, - .start = omap_dm_timer_start, - .stop = omap_dm_timer_stop, - .set_load = omap_dm_timer_set_load, - .set_match = omap_dm_timer_set_match, - .set_pwm = omap_dm_timer_set_pwm, - .set_prescaler = omap_dm_timer_set_prescaler, - .read_counter = omap_dm_timer_read_counter, - .write_counter = omap_dm_timer_write_counter, - .read_status = omap_dm_timer_read_status, - .write_status = omap_dm_timer_write_status, -}; -#endif - -#if defined(CONFIG_IR_RX51) || defined(CONFIG_IR_RX51_MODULE) -static struct lirc_rx51_platform_data rx51_lirc_data = { - .set_max_mpu_wakeup_lat = omap_pm_set_max_mpu_wakeup_lat, -}; - -static struct platform_device rx51_lirc_device = { - .name = "lirc_rx51", - .id = -1, - .dev = { - .platform_data = &rx51_lirc_data, - }, -}; - -static void __init rx51_init_lirc(void) -{ - platform_device_register(&rx51_lirc_device); -} -#else -static void __init rx51_init_lirc(void) -{ -} -#endif - -static struct platform_device madc_hwmon = { - .name = "twl4030_madc_hwmon", - .id = -1, -}; - -static void __init rx51_init_twl4030_hwmon(void) -{ - platform_device_register(&madc_hwmon); -} - -static struct platform_device omap3_rom_rng_device = { - .name = "omap3-rom-rng", - .id = -1, - .dev = { - .platform_data = rx51_secure_rng_call, - }, -}; - -static void __init rx51_init_omap3_rom_rng(void) -{ - if (omap_type() == OMAP2_DEVICE_TYPE_SEC) { - pr_info("RX-51: Registering OMAP3 HWRNG device\n"); - platform_device_register(&omap3_rom_rng_device); - } -} - -void __init rx51_peripherals_init(void) -{ - rx51_gpio_init(); - rx51_i2c_init(); - regulator_has_full_constraints(); - gpmc_onenand_init(board_onenand_data); - rx51_add_gpio_keys(); - rx51_init_wl1251(); - rx51_init_tsc2005(); - rx51_init_lirc(); - spi_register_board_info(rx51_peripherals_spi_board_info, - ARRAY_SIZE(rx51_peripherals_spi_board_info)); - - partition = omap_mux_get("core"); - if (partition) - omap_hsmmc_init(mmc); - - rx51_charger_init(); - rx51_init_twl4030_hwmon(); - rx51_init_omap3_rom_rng(); -} - diff --git a/arch/arm/mach-omap2/board-rx51-video.c b/arch/arm/mach-omap2/board-rx51-video.c deleted file mode 100644 index 180c6aa633bd..000000000000 --- a/arch/arm/mach-omap2/board-rx51-video.c +++ /dev/null @@ -1,67 +0,0 @@ -/* - * linux/arch/arm/mach-omap2/board-rx51-video.c - * - * Copyright (C) 2010 Nokia - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/platform_device.h> -#include <linux/gpio.h> -#include <linux/spi/spi.h> -#include <linux/mm.h> -#include <asm/mach-types.h> -#include <linux/platform_data/omapdss.h> -#include <video/omap-panel-data.h> - -#include <linux/platform_data/spi-omap2-mcspi.h> - -#include "soc.h" -#include "board-rx51.h" -#include "display.h" - -#include "mux.h" - -#define RX51_LCD_RESET_GPIO 90 - -#if defined(CONFIG_FB_OMAP2) || defined(CONFIG_FB_OMAP2_MODULE) - -static struct connector_atv_platform_data rx51_tv_pdata = { - .name = "tv", - .source = "venc.0", - .invert_polarity = false, -}; - -static struct platform_device rx51_tv_connector_device = { - .name = "connector-analog-tv", - .id = 0, - .dev.platform_data = &rx51_tv_pdata, -}; - -static struct omap_dss_board_info rx51_dss_board_info = { - .default_display_name = "lcd", -}; - -static int __init rx51_video_init(void) -{ - if (!machine_is_nokia_rx51()) - return 0; - - if (omap_mux_init_gpio(RX51_LCD_RESET_GPIO, OMAP_PIN_OUTPUT)) { - pr_err("%s cannot configure MUX for LCD RESET\n", __func__); - return 0; - } - - omap_display_init(&rx51_dss_board_info); - - platform_device_register(&rx51_tv_connector_device); - - return 0; -} - -omap_subsys_initcall(rx51_video_init); -#endif /* defined(CONFIG_FB_OMAP2) || defined(CONFIG_FB_OMAP2_MODULE) */ diff --git a/arch/arm/mach-omap2/board-rx51.c b/arch/arm/mach-omap2/board-rx51.c deleted file mode 100644 index 41161ca97d74..000000000000 --- a/arch/arm/mach-omap2/board-rx51.c +++ /dev/null @@ -1,141 +0,0 @@ -/* - * Board support file for Nokia N900 (aka RX-51). - * - * Copyright (C) 2007, 2008 Nokia - * Copyright (C) 2012 Ivaylo Dimitrov <freemangordon@abv.bg> - * Copyright (C) 2013 Pali Rohár <pali.rohar@gmail.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/platform_device.h> -#include <linux/delay.h> -#include <linux/err.h> -#include <linux/clk.h> -#include <linux/io.h> -#include <linux/gpio.h> -#include <linux/leds.h> -#include <linux/usb/phy.h> -#include <linux/usb/musb.h> -#include <linux/platform_data/spi-omap2-mcspi.h> - -#include <asm/mach-types.h> -#include <asm/mach/arch.h> -#include <asm/mach/map.h> - -#include <linux/omap-dma.h> - -#include "common.h" -#include "mux.h" -#include "gpmc.h" -#include "pm.h" -#include "soc.h" -#include "sdram-nokia.h" -#include "omap-secure.h" - -#define RX51_GPIO_SLEEP_IND 162 - -static struct gpio_led gpio_leds[] = { - { - .name = "sleep_ind", - .gpio = RX51_GPIO_SLEEP_IND, - }, -}; - -static struct gpio_led_platform_data gpio_led_info = { - .leds = gpio_leds, - .num_leds = ARRAY_SIZE(gpio_leds), -}; - -static struct platform_device leds_gpio = { - .name = "leds-gpio", - .id = -1, - .dev = { - .platform_data = &gpio_led_info, - }, -}; - -/* - * cpuidle C-states definition for rx51. - * - * The 'exit_latency' field is the sum of sleep - * and wake-up latencies. - - --------------------------------------------- - | state | exit_latency | target_residency | - --------------------------------------------- - | C1 | 110 + 162 | 5 | - | C2 | 106 + 180 | 309 | - | C3 | 107 + 410 | 46057 | - | C4 | 121 + 3374 | 46057 | - | C5 | 855 + 1146 | 46057 | - | C6 | 7580 + 4134 | 484329 | - | C7 | 7505 + 15274 | 484329 | - --------------------------------------------- - -*/ - -extern void __init rx51_peripherals_init(void); - -#ifdef CONFIG_OMAP_MUX -static struct omap_board_mux board_mux[] __initdata = { - { .reg_offset = OMAP_MUX_TERMINATOR }, -}; -#endif - -static struct omap_musb_board_data musb_board_data = { - .interface_type = MUSB_INTERFACE_ULPI, - .mode = MUSB_OTG, - .power = 0, -}; - -static void __init rx51_init(void) -{ - struct omap_sdrc_params *sdrc_params; - - omap3_mux_init(board_mux, OMAP_PACKAGE_CBB); - omap_serial_init(); - - sdrc_params = nokia_get_sdram_timings(); - omap_sdrc_init(sdrc_params, sdrc_params); - - usb_bind_phy("musb-hdrc.0.auto", 0, "twl4030_usb"); - usb_musb_init(&musb_board_data); - rx51_peripherals_init(); - - if (omap_type() == OMAP2_DEVICE_TYPE_SEC) { -#ifdef CONFIG_ARM_ERRATA_430973 - pr_info("RX-51: Enabling ARM errata 430973 workaround\n"); - /* set IBE to 1 */ - rx51_secure_update_aux_cr(BIT(6), 0); -#endif - } - - /* Ensure SDRC pins are mux'd for self-refresh */ - omap_mux_init_signal("sdrc_cke0", OMAP_PIN_OUTPUT); - omap_mux_init_signal("sdrc_cke1", OMAP_PIN_OUTPUT); - - platform_device_register(&leds_gpio); -} - -static void __init rx51_reserve(void) -{ - omap_reserve(); -} - -MACHINE_START(NOKIA_RX51, "Nokia RX-51 board") - /* Maintainer: Lauri Leukkunen <lauri.leukkunen@nokia.com> */ - .atag_offset = 0x100, - .reserve = rx51_reserve, - .map_io = omap3_map_io, - .init_early = omap3430_init_early, - .init_irq = omap3_init_irq, - .init_machine = rx51_init, - .init_late = omap3430_init_late, - .init_time = omap_init_time, - .restart = omap3xxx_restart, -MACHINE_END diff --git a/arch/arm/mach-omap2/board-rx51.h b/arch/arm/mach-omap2/board-rx51.h deleted file mode 100644 index b76f49e7eed5..000000000000 --- a/arch/arm/mach-omap2/board-rx51.h +++ /dev/null @@ -1,11 +0,0 @@ -/* - * Defines for rx51 boards - */ - -#ifndef _OMAP_BOARD_RX51_H -#define _OMAP_BOARD_RX51_H - -extern void __init rx51_peripherals_init(void); -extern void __init rx51_video_mem_init(void); - -#endif diff --git a/arch/arm/mach-omap2/cm33xx.c b/arch/arm/mach-omap2/cm33xx.c index c073fb57dd13..6f2d0aec0513 100644 --- a/arch/arm/mach-omap2/cm33xx.c +++ b/arch/arm/mach-omap2/cm33xx.c @@ -220,9 +220,6 @@ static int am33xx_cm_wait_module_ready(u8 part, s16 inst, u16 clkctrl_offs, { int i = 0; - if (!clkctrl_offs) - return 0; - omap_test_timeout(_is_module_ready(inst, clkctrl_offs), MAX_MODULE_READY_TIME, i); @@ -246,9 +243,6 @@ static int am33xx_cm_wait_module_idle(u8 part, s16 inst, u16 clkctrl_offs, { int i = 0; - if (!clkctrl_offs) - return 0; - omap_test_timeout((_clkctrl_idlest(inst, clkctrl_offs) == CLKCTRL_IDLEST_DISABLED), MAX_MODULE_READY_TIME, i); diff --git a/arch/arm/mach-omap2/cminst44xx.c b/arch/arm/mach-omap2/cminst44xx.c index 2c0e07ed6b99..2ab27ade136a 100644 --- a/arch/arm/mach-omap2/cminst44xx.c +++ b/arch/arm/mach-omap2/cminst44xx.c @@ -278,9 +278,6 @@ static int omap4_cminst_wait_module_ready(u8 part, s16 inst, u16 clkctrl_offs, { int i = 0; - if (!clkctrl_offs) - return 0; - omap_test_timeout(_is_module_ready(part, inst, clkctrl_offs), MAX_MODULE_READY_TIME, i); @@ -304,9 +301,6 @@ static int omap4_cminst_wait_module_idle(u8 part, s16 inst, u16 clkctrl_offs, { int i = 0; - if (!clkctrl_offs) - return 0; - omap_test_timeout((_clkctrl_idlest(part, inst, clkctrl_offs) == CLKCTRL_IDLEST_DISABLED), MAX_MODULE_DISABLE_TIME, i); diff --git a/arch/arm/mach-omap2/common-board-devices.c b/arch/arm/mach-omap2/common-board-devices.c index d246efd9f734..5388fcd3de72 100644 --- a/arch/arm/mach-omap2/common-board-devices.c +++ b/arch/arm/mach-omap2/common-board-devices.c @@ -29,8 +29,7 @@ #include "common.h" #include "common-board-devices.h" -#if defined(CONFIG_TOUCHSCREEN_ADS7846) || \ - defined(CONFIG_TOUCHSCREEN_ADS7846_MODULE) +#if IS_ENABLED(CONFIG_TOUCHSCREEN_ADS7846) static struct omap2_mcspi_device_config ads7846_mcspi_config = { .turbo_mode = 0, }; diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c index d7f1d69daf6d..60a20f3b44de 100644 --- a/arch/arm/mach-omap2/devices.c +++ b/arch/arm/mach-omap2/devices.c @@ -67,7 +67,7 @@ omap_postcore_initcall(omap3_l3_init); static inline void omap_init_sti(void) {} -#if defined(CONFIG_SPI_OMAP24XX) || defined(CONFIG_SPI_OMAP24XX_MODULE) +#if IS_ENABLED(CONFIG_SPI_OMAP24XX) #include <linux/platform_data/spi-omap2-mcspi.h> @@ -163,9 +163,8 @@ static void __init omap_init_aes(void) /*-------------------------------------------------------------------------*/ -#if defined(CONFIG_VIDEO_OMAP2_VOUT) || \ - defined(CONFIG_VIDEO_OMAP2_VOUT_MODULE) -#if defined(CONFIG_FB_OMAP2) || defined(CONFIG_FB_OMAP2_MODULE) +#if IS_ENABLED(CONFIG_VIDEO_OMAP2_VOUT) +#if IS_ENABLED(CONFIG_FB_OMAP2) static struct resource omap_vout_resource[3 - CONFIG_FB_OMAP2_NUM_FBS] = { }; #else diff --git a/arch/arm/mach-omap2/drm.c b/arch/arm/mach-omap2/drm.c index facd7406a03d..44fef961bb70 100644 --- a/arch/arm/mach-omap2/drm.c +++ b/arch/arm/mach-omap2/drm.c @@ -28,7 +28,7 @@ #include "soc.h" #include "display.h" -#if defined(CONFIG_DRM_OMAP) || defined(CONFIG_DRM_OMAP_MODULE) +#if IS_ENABLED(CONFIG_DRM_OMAP) static struct omap_drm_platform_data platform_data; diff --git a/arch/arm/mach-omap2/fb.c b/arch/arm/mach-omap2/fb.c index 1f1ecf8807eb..ecd00b63181e 100644 --- a/arch/arm/mach-omap2/fb.c +++ b/arch/arm/mach-omap2/fb.c @@ -90,7 +90,7 @@ int __init omap_init_vrfb(void) int __init omap_init_vrfb(void) { return 0; } #endif -#if defined(CONFIG_FB_OMAP2) || defined(CONFIG_FB_OMAP2_MODULE) +#if IS_ENABLED(CONFIG_FB_OMAP2) static u64 omap_fb_dma_mask = ~(u32)0; static struct omapfb_platform_data omapfb_config; diff --git a/arch/arm/mach-omap2/gpmc-smsc911x.h b/arch/arm/mach-omap2/gpmc-smsc911x.h index ea6c9c88c725..99a05b8412fa 100644 --- a/arch/arm/mach-omap2/gpmc-smsc911x.h +++ b/arch/arm/mach-omap2/gpmc-smsc911x.h @@ -21,7 +21,7 @@ struct omap_smsc911x_platform_data { u32 flags; }; -#if defined(CONFIG_SMSC911X) || defined(CONFIG_SMSC911X_MODULE) +#if IS_ENABLED(CONFIG_SMSC911X) extern void gpmc_smsc911x_init(struct omap_smsc911x_platform_data *d); diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c index cff079e563f4..478097741bce 100644 --- a/arch/arm/mach-omap2/hsmmc.c +++ b/arch/arm/mach-omap2/hsmmc.c @@ -26,7 +26,7 @@ #include "hsmmc.h" #include "control.h" -#if defined(CONFIG_MMC_OMAP_HS) || defined(CONFIG_MMC_OMAP_HS_MODULE) +#if IS_ENABLED(CONFIG_MMC_OMAP_HS) static u16 control_pbias_offset; static u16 control_devconf1_offset; diff --git a/arch/arm/mach-omap2/hsmmc.h b/arch/arm/mach-omap2/hsmmc.h index 148cd9b15499..69b619ddc765 100644 --- a/arch/arm/mach-omap2/hsmmc.h +++ b/arch/arm/mach-omap2/hsmmc.h @@ -28,7 +28,7 @@ struct omap2_hsmmc_info { void (*init_card)(struct mmc_card *card); }; -#if defined(CONFIG_MMC_OMAP_HS) || defined(CONFIG_MMC_OMAP_HS_MODULE) +#if IS_ENABLED(CONFIG_MMC_OMAP_HS) void omap_hsmmc_init(struct omap2_hsmmc_info *); void omap_hsmmc_late_init(struct omap2_hsmmc_info *); diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c index 0c4754386532..369f95a703ac 100644 --- a/arch/arm/mach-omap2/omap-wakeupgen.c +++ b/arch/arm/mach-omap2/omap-wakeupgen.c @@ -322,34 +322,25 @@ static void irq_save_secure_context(void) #endif #ifdef CONFIG_HOTPLUG_CPU -static int irq_cpu_hotplug_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +static int omap_wakeupgen_cpu_online(unsigned int cpu) { - unsigned int cpu = (unsigned int)hcpu; - - /* - * Corresponding FROZEN transitions do not have to be handled, - * they are handled by at a higher level - * (drivers/cpuidle/coupled.c). - */ - switch (action) { - case CPU_ONLINE: - wakeupgen_irqmask_all(cpu, 0); - break; - case CPU_DEAD: - wakeupgen_irqmask_all(cpu, 1); - break; - } - return NOTIFY_OK; + wakeupgen_irqmask_all(cpu, 0); + return 0; } -static struct notifier_block irq_hotplug_notifier = { - .notifier_call = irq_cpu_hotplug_notify, -}; +static int omap_wakeupgen_cpu_dead(unsigned int cpu) +{ + wakeupgen_irqmask_all(cpu, 1); + return 0; +} static void __init irq_hotplug_init(void) { - register_hotcpu_notifier(&irq_hotplug_notifier); + cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "arm/omap-wake:online", + omap_wakeupgen_cpu_online, NULL); + cpuhp_setup_state_nocalls(CPUHP_ARM_OMAP_WAKE_DEAD, + "arm/omap-wake:dead", NULL, + omap_wakeupgen_cpu_dead); } #else static void __init irq_hotplug_init(void) diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 5b709383381c..1052b29697b8 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -1053,6 +1053,10 @@ static int _omap4_wait_target_disable(struct omap_hwmod *oh) if (oh->flags & HWMOD_NO_IDLEST) return 0; + if (!oh->prcm.omap4.clkctrl_offs && + !(oh->prcm.omap4.flags & HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET)) + return 0; + return omap_cm_wait_module_idle(oh->clkdm->prcm_partition, oh->clkdm->cm_inst, oh->prcm.omap4.clkctrl_offs, 0); @@ -2971,6 +2975,10 @@ static int _omap4_wait_target_ready(struct omap_hwmod *oh) if (!_find_mpu_rt_port(oh)) return 0; + if (!oh->prcm.omap4.clkctrl_offs && + !(oh->prcm.omap4.flags & HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET)) + return 0; + /* XXX check module SIDLEMODE, hardreset status */ return omap_cm_wait_module_ready(oh->clkdm->prcm_partition, diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h index 4041bad79a9a..78904017f18c 100644 --- a/arch/arm/mach-omap2/omap_hwmod.h +++ b/arch/arm/mach-omap2/omap_hwmod.h @@ -443,8 +443,12 @@ struct omap_hwmod_omap2_prcm { * HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT: Some IP blocks don't have a PRCM * module-level context loss register associated with them; this * flag bit should be set in those cases + * HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET: Some IP blocks have a valid CLKCTRL + * offset of zero; this flag bit should be set in those cases to + * distinguish from hwmods that have no clkctrl offset. */ #define HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT (1 << 0) +#define HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET (1 << 1) /** * struct omap_hwmod_omap4_prcm - OMAP4-specific PRCM data diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c index 55c5878577f4..e2d84aa7f595 100644 --- a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c @@ -29,6 +29,7 @@ #define CLKCTRL(oh, clkctrl) ((oh).prcm.omap4.clkctrl_offs = (clkctrl)) #define RSTCTRL(oh, rstctrl) ((oh).prcm.omap4.rstctrl_offs = (rstctrl)) #define RSTST(oh, rstst) ((oh).prcm.omap4.rstst_offs = (rstst)) +#define PRCM_FLAGS(oh, flag) ((oh).prcm.omap4.flags = (flag)) /* * 'l3' class @@ -1296,6 +1297,7 @@ static void omap_hwmod_am33xx_clkctrl(void) CLKCTRL(am33xx_i2c1_hwmod, AM33XX_CM_WKUP_I2C0_CLKCTRL_OFFSET); CLKCTRL(am33xx_wd_timer1_hwmod, AM33XX_CM_WKUP_WDT1_CLKCTRL_OFFSET); CLKCTRL(am33xx_rtc_hwmod, AM33XX_CM_RTC_RTC_CLKCTRL_OFFSET); + PRCM_FLAGS(am33xx_rtc_hwmod, HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET); CLKCTRL(am33xx_mmc2_hwmod, AM33XX_CM_PER_MMC2_CLKCTRL_OFFSET); CLKCTRL(am33xx_gpmc_hwmod, AM33XX_CM_PER_GPMC_CLKCTRL_OFFSET); CLKCTRL(am33xx_l4_ls_hwmod, AM33XX_CM_PER_L4LS_CLKCTRL_OFFSET); diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c index d72ee6185d5e..1cc4a6f3954e 100644 --- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c @@ -722,8 +722,20 @@ static struct omap_hwmod omap3xxx_dss_dispc_hwmod = { * display serial interface controller */ +static struct omap_hwmod_class_sysconfig omap3xxx_dsi_sysc = { + .rev_offs = 0x0000, + .sysc_offs = 0x0010, + .syss_offs = 0x0014, + .sysc_flags = (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY | + SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE | + SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS), + .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART), + .sysc_fields = &omap_hwmod_sysc_type1, +}; + static struct omap_hwmod_class omap3xxx_dsi_hwmod_class = { .name = "dsi", + .sysc = &omap3xxx_dsi_sysc, }; static struct omap_hwmod_irq_info omap3xxx_dsi1_irqs[] = { diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c index 292eca0e78ed..a72738eab009 100644 --- a/arch/arm/mach-omap2/twl-common.c +++ b/arch/arm/mach-omap2/twl-common.c @@ -532,8 +532,7 @@ void __init omap4_pmic_get_config(struct twl4030_platform_data *pmic_data, } #endif /* CONFIG_ARCH_OMAP4 */ -#if defined(CONFIG_SND_OMAP_SOC_OMAP_TWL4030) || \ - defined(CONFIG_SND_OMAP_SOC_OMAP_TWL4030_MODULE) +#if IS_ENABLED(CONFIG_SND_OMAP_SOC_OMAP_TWL4030) #include <linux/platform_data/omap-twl4030.h> /* Commonly used configuration */ diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c index 4a2f9aba93ea..66184f5cbe40 100644 --- a/arch/arm/mach-pxa/hx4700.c +++ b/arch/arm/mach-pxa/hx4700.c @@ -24,10 +24,10 @@ #include <linux/input.h> #include <linux/input/navpoint.h> #include <linux/lcd.h> -#include <linux/mfd/htc-egpio.h> #include <linux/mfd/asic3.h> #include <linux/mtd/physmap.h> #include <linux/pda_power.h> +#include <linux/platform_data/gpio-htc-egpio.h> #include <linux/pwm.h> #include <linux/pwm_backlight.h> #include <linux/regulator/driver.h> diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c index c410d84b243d..66070acaa888 100644 --- a/arch/arm/mach-pxa/idp.c +++ b/arch/arm/mach-pxa/idp.c @@ -83,7 +83,8 @@ static struct resource smc91x_resources[] = { }; static struct smc91x_platdata smc91x_platdata = { - .flags = SMC91X_USE_32BIT | SMC91X_USE_DMA | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_USE_DMA | SMC91X_NOWAIT, }; static struct platform_device smc91x_device = { diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c index 7245f3359564..d6159f8ef0c2 100644 --- a/arch/arm/mach-pxa/lubbock.c +++ b/arch/arm/mach-pxa/lubbock.c @@ -137,6 +137,18 @@ static struct pxa2xx_udc_mach_info udc_info __initdata = { // no D+ pullup; lubbock can't connect/disconnect in software }; +static void lubbock_init_pcmcia(void) +{ + struct clk *clk; + + /* Add an alias for the SA1111 PCMCIA clock */ + clk = clk_get_sys("pxa2xx-pcmcia", NULL); + if (!IS_ERR(clk)) { + clkdev_create(clk, NULL, "1800"); + clk_put(clk); + } +} + static struct resource sa1111_resources[] = { [0] = { .start = 0x10000000, @@ -467,6 +479,8 @@ static void __init lubbock_init(void) pxa_set_btuart_info(NULL); pxa_set_stuart_info(NULL); + lubbock_init_pcmcia(); + clk_add_alias("SA1111_CLK", NULL, "GPIO11_CLK", NULL); pxa_set_udc_info(&udc_info); pxa_set_fb_info(NULL, &sharp_lm8v31); diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c index 6f8837ebbf91..b413e36506af 100644 --- a/arch/arm/mach-pxa/magician.c +++ b/arch/arm/mach-pxa/magician.c @@ -20,10 +20,10 @@ #include <linux/gpio.h> #include <linux/gpio_keys.h> #include <linux/input.h> -#include <linux/mfd/htc-egpio.h> #include <linux/mfd/htc-pasic3.h> #include <linux/mtd/physmap.h> #include <linux/pda_power.h> +#include <linux/platform_data/gpio-htc-egpio.h> #include <linux/pwm.h> #include <linux/pwm_backlight.h> #include <linux/regulator/driver.h> diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c index 3f06cd90567a..056369ef250e 100644 --- a/arch/arm/mach-pxa/xcep.c +++ b/arch/arm/mach-pxa/xcep.c @@ -120,7 +120,8 @@ static struct resource smc91x_resources[] = { }; static struct smc91x_platdata xcep_smc91x_info = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT | SMC91X_USE_DMA, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT | SMC91X_USE_DMA, }; static struct platform_device smc91x_device = { diff --git a/arch/arm/mach-realview/Kconfig b/arch/arm/mach-realview/Kconfig index 70ab4a25a5f8..1d7c83e73ffb 100644 --- a/arch/arm/mach-realview/Kconfig +++ b/arch/arm/mach-realview/Kconfig @@ -2,34 +2,29 @@ menuconfig ARCH_REALVIEW bool "ARM Ltd. RealView family" depends on ARCH_MULTI_V5 || ARCH_MULTI_V6 || ARCH_MULTI_V7 select ARM_AMBA + select ARM_GIC select ARM_TIMER_SP804 + select CLK_SP810 select COMMON_CLK_VERSATILE select GPIO_PL061 if GPIOLIB - select ICST - select PLAT_VERSATILE - select PLAT_VERSATILE_SCHED_CLOCK - help - This enables support for ARM Ltd RealView boards. - -if ARCH_REALVIEW - -config REALVIEW_DT - bool "Support RealView(R) Device Tree based boot" - select ARM_GIC - select CLK_SP810 - select HAVE_SMP + select HAVE_ARM_SCU if SMP + select HAVE_ARM_TWD if SMP + select HAVE_PATA_PLATFORM + select HAVE_TCM select ICST select MACH_REALVIEW_EB if ARCH_MULTI_V5 select MFD_SYSCON + select PLAT_VERSATILE + select PLAT_VERSATILE_SCHED_CLOCK select POWER_RESET select POWER_RESET_VERSATILE select POWER_SUPPLY - select SMP_ON_UP if SMP select SOC_REALVIEW select USE_OF help - Include support for booting the ARM(R) RealView(R) evaluation - boards using a device tree machine description. + This enables support for ARM Ltd RealView boards. + +if ARCH_REALVIEW config MACH_REALVIEW_EB bool "Support RealView(R) Emulation Baseboard" @@ -60,8 +55,6 @@ config REALVIEW_EB_ARM1176 config REALVIEW_EB_A9MP bool "Support Multicore Cortex-A9 Tile" depends on MACH_REALVIEW_EB && ARCH_MULTI_V7 - select HAVE_ARM_SCU if SMP - select HAVE_ARM_TWD if SMP select HAVE_SMP select MIGHT_HAVE_CACHE_L2X0 help @@ -71,30 +64,15 @@ config REALVIEW_EB_A9MP config REALVIEW_EB_ARM11MP bool "Support ARM11MPCore Tile" depends on MACH_REALVIEW_EB && ARCH_MULTI_V6 - select HAVE_ARM_SCU if SMP - select HAVE_ARM_TWD if SMP select HAVE_SMP select MIGHT_HAVE_CACHE_L2X0 help Enable support for the ARM11MPCore tile fitted to the Realview(R) Emulation Baseboard platform. -config REALVIEW_EB_ARM11MP_REVB - bool "Support ARM11MPCore RevB Tile" - depends on REALVIEW_EB_ARM11MP && ARCH_MULTI_V6 - help - Enable support for the ARM11MPCore Revision B tile on the - Realview(R) Emulation Baseboard platform. Since there are device - address differences, a kernel built with this option enabled is - not compatible with other revisions of the ARM11MPCore tile. - config MACH_REALVIEW_PB11MP bool "Support RealView(R) Platform Baseboard for ARM11MPCore" depends on ARCH_MULTI_V6 - select ARM_GIC - select HAVE_ARM_SCU if SMP - select HAVE_ARM_TWD if SMP - select HAVE_PATA_PLATFORM select HAVE_SMP select MIGHT_HAVE_CACHE_L2X0 help @@ -106,7 +84,6 @@ config MACH_REALVIEW_PB11MP config MACH_REALVIEW_PB1176 bool "Support RealView(R) Platform Baseboard for ARM1176JZF-S" depends on ARCH_MULTI_V6 - select ARM_GIC select CPU_V6 select HAVE_TCM select MIGHT_HAVE_CACHE_L2X0 @@ -114,20 +91,9 @@ config MACH_REALVIEW_PB1176 Include support for the ARM(R) RealView(R) Platform Baseboard for ARM1176JZF-S. -config REALVIEW_PB1176_SECURE_FLASH - bool "Allow access to the secure flash memory block" - depends on MACH_REALVIEW_PB1176 - default n - help - Select this option if Linux will only run in secure mode on the - RealView PB1176 platform and access to the secure flash memory - block (64MB @ 0x3c000000) is required. - config MACH_REALVIEW_PBA8 bool "Support RealView(R) Platform Baseboard for Cortex(tm)-A8 platform" depends on ARCH_MULTI_V7 - select ARM_GIC - select HAVE_PATA_PLATFORM help Include support for the ARM(R) RealView Platform Baseboard for Cortex(tm)-A8. This platform has an on-board Cortex-A8 and has @@ -136,10 +102,6 @@ config MACH_REALVIEW_PBA8 config MACH_REALVIEW_PBX bool "Support RealView(R) Platform Baseboard Explore for Cortex-A9" depends on ARCH_MULTI_V7 - select ARM_GIC - select HAVE_ARM_SCU if SMP - select HAVE_ARM_TWD if SMP - select HAVE_PATA_PLATFORM select HAVE_SMP select MIGHT_HAVE_CACHE_L2X0 select ZONE_DMA @@ -147,16 +109,4 @@ config MACH_REALVIEW_PBX Include support for the ARM(R) RealView(R) Platform Baseboard Explore. -config REALVIEW_HIGH_PHYS_OFFSET - bool "High physical base address for the RealView platform" - depends on MMU && !MACH_REALVIEW_PB1176 - default y - help - RealView boards other than PB1176 have the RAM available at - 0x70000000, 256MB of which being mirrored at 0x00000000. If - the board supports 512MB of RAM, this option allows the - memory to be accessed contiguously at the high physical - offset. On the PBX board, disabling this option allows 1GB of - RAM to be used with HIGHMEM. - endif diff --git a/arch/arm/mach-realview/Makefile b/arch/arm/mach-realview/Makefile index 404882130956..adf39ad71cc3 100644 --- a/arch/arm/mach-realview/Makefile +++ b/arch/arm/mach-realview/Makefile @@ -3,16 +3,6 @@ # ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-versatile/include -obj-y := core.o -obj-$(CONFIG_REALVIEW_DT) += realview-dt.o +obj-y += realview-dt.o obj-$(CONFIG_SMP) += platsmp-dt.o - -ifdef CONFIG_ATAGS -obj-$(CONFIG_MACH_REALVIEW_EB) += realview_eb.o -obj-$(CONFIG_MACH_REALVIEW_PB11MP) += realview_pb11mp.o -obj-$(CONFIG_MACH_REALVIEW_PB1176) += realview_pb1176.o -obj-$(CONFIG_MACH_REALVIEW_PBA8) += realview_pba8.o -obj-$(CONFIG_MACH_REALVIEW_PBX) += realview_pbx.o -obj-$(CONFIG_SMP) += platsmp.o -endif obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o diff --git a/arch/arm/mach-realview/board-eb.h b/arch/arm/mach-realview/board-eb.h deleted file mode 100644 index a850ae6945b0..000000000000 --- a/arch/arm/mach-realview/board-eb.h +++ /dev/null @@ -1,94 +0,0 @@ -/* - * Copyright (C) 2007 ARM Limited - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301, USA. - */ - -#ifndef __ASM_ARCH_BOARD_EB_H -#define __ASM_ARCH_BOARD_EB_H - -#include "platform.h" - -/* - * RealView EB + ARM11MPCore peripheral addresses - */ -#define REALVIEW_EB_UART0_BASE 0x10009000 /* UART 0 */ -#define REALVIEW_EB_UART1_BASE 0x1000A000 /* UART 1 */ -#define REALVIEW_EB_UART2_BASE 0x1000B000 /* UART 2 */ -#define REALVIEW_EB_UART3_BASE 0x1000C000 /* UART 3 */ -#define REALVIEW_EB_SSP_BASE 0x1000D000 /* Synchronous Serial Port */ -#define REALVIEW_EB_WATCHDOG_BASE 0x10010000 /* watchdog interface */ -#define REALVIEW_EB_TIMER0_1_BASE 0x10011000 /* Timer 0 and 1 */ -#define REALVIEW_EB_TIMER2_3_BASE 0x10012000 /* Timer 2 and 3 */ -#define REALVIEW_EB_GPIO0_BASE 0x10013000 /* GPIO port 0 */ -#define REALVIEW_EB_RTC_BASE 0x10017000 /* Real Time Clock */ -#define REALVIEW_EB_CLCD_BASE 0x10020000 /* CLCD */ -#define REALVIEW_EB_GIC_CPU_BASE 0x10040000 /* Generic interrupt controller CPU interface */ -#define REALVIEW_EB_GIC_DIST_BASE 0x10041000 /* Generic interrupt controller distributor */ -#define REALVIEW_EB_SMC_BASE 0x10080000 /* Static memory controller */ - -#define REALVIEW_EB_FLASH_BASE 0x40000000 -#define REALVIEW_EB_FLASH_SIZE SZ_64M -#define REALVIEW_EB_ETH_BASE 0x4E000000 /* Ethernet */ -#define REALVIEW_EB_USB_BASE 0x4F000000 /* USB */ - -#ifdef CONFIG_REALVIEW_EB_ARM11MP_REVB -#define REALVIEW_EB11MP_PRIV_MEM_BASE 0x10100000 -#define REALVIEW_EB11MP_L220_BASE 0x10102000 /* L220 registers */ -#define REALVIEW_EB11MP_SYS_PLD_CTRL1 0xD8 /* Register offset for MPCore sysctl */ -#else -#define REALVIEW_EB11MP_PRIV_MEM_BASE 0x1F000000 -#define REALVIEW_EB11MP_L220_BASE 0x1F002000 /* L220 registers */ -#define REALVIEW_EB11MP_SYS_PLD_CTRL1 0x74 /* Register offset for MPCore sysctl */ -#endif - -#define REALVIEW_EB11MP_PRIV_MEM_SIZE SZ_8K -#define REALVIEW_EB11MP_PRIV_MEM_OFF(x) (REALVIEW_EB11MP_PRIV_MEM_BASE + (x)) - -#define REALVIEW_EB11MP_SCU_BASE REALVIEW_EB11MP_PRIV_MEM_OFF(0) /* SCU registers */ -#define REALVIEW_EB11MP_GIC_CPU_BASE REALVIEW_EB11MP_PRIV_MEM_OFF(0x0100) /* Generic interrupt controller CPU interface */ -#define REALVIEW_EB11MP_TWD_BASE REALVIEW_EB11MP_PRIV_MEM_OFF(0x0600) -#define REALVIEW_EB11MP_GIC_DIST_BASE REALVIEW_EB11MP_PRIV_MEM_OFF(0x1000) /* Generic interrupt controller distributor */ - -/* - * Core tile identification (REALVIEW_SYS_PROCID) - */ -#define REALVIEW_EB_PROC_MASK 0xFF000000 -#define REALVIEW_EB_PROC_ARM7TDMI 0x00000000 -#define REALVIEW_EB_PROC_ARM9 0x02000000 -#define REALVIEW_EB_PROC_ARM11 0x04000000 -#define REALVIEW_EB_PROC_ARM11MP 0x06000000 -#define REALVIEW_EB_PROC_A9MP 0x0C000000 - -#define check_eb_proc(proc_type) \ - ((readl(__io_address(REALVIEW_SYS_PROCID)) & REALVIEW_EB_PROC_MASK) \ - == proc_type) - -#ifdef CONFIG_REALVIEW_EB_ARM11MP -#define core_tile_eb11mp() check_eb_proc(REALVIEW_EB_PROC_ARM11MP) -#else -#define core_tile_eb11mp() 0 -#endif - -#ifdef CONFIG_REALVIEW_EB_A9MP -#define core_tile_a9mp() check_eb_proc(REALVIEW_EB_PROC_A9MP) -#else -#define core_tile_a9mp() 0 -#endif - -#define machine_is_realview_eb_mp() \ - (machine_is_realview_eb() && (core_tile_eb11mp() || core_tile_a9mp())) - -#endif /* __ASM_ARCH_BOARD_EB_H */ diff --git a/arch/arm/mach-realview/board-pb1176.h b/arch/arm/mach-realview/board-pb1176.h deleted file mode 100644 index 29c04a9e1344..000000000000 --- a/arch/arm/mach-realview/board-pb1176.h +++ /dev/null @@ -1,81 +0,0 @@ -/* - * Copyright (C) 2008 ARM Limited - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301, USA. - */ - -#ifndef __ASM_ARCH_BOARD_PB1176_H -#define __ASM_ARCH_BOARD_PB1176_H - -#include "platform.h" - -/* - * Peripheral addresses - */ -#define REALVIEW_PB1176_UART4_BASE 0x10009000 /* UART 4 */ -#define REALVIEW_PB1176_SCTL_BASE 0x10100000 /* System controller */ -#define REALVIEW_PB1176_SMC_BASE 0x10111000 /* SMC */ -#define REALVIEW_PB1176_DMC_BASE 0x10109000 /* DMC configuration */ -#define REALVIEW_PB1176_SDRAM67_BASE 0x70000000 /* SDRAM banks 6 and 7 */ -#define REALVIEW_PB1176_FLASH_BASE 0x30000000 -#define REALVIEW_PB1176_FLASH_SIZE SZ_64M -#define REALVIEW_PB1176_SEC_FLASH_BASE 0x3C000000 /* Secure flash */ -#define REALVIEW_PB1176_SEC_FLASH_SIZE SZ_64M - -#define REALVIEW_PB1176_TIMER0_1_BASE 0x10104000 /* Timer 0 and 1 */ -#define REALVIEW_PB1176_TIMER2_3_BASE 0x10105000 /* Timer 2 and 3 */ -#define REALVIEW_PB1176_TIMER4_5_BASE 0x10106000 /* Timer 4 and 5 */ -#define REALVIEW_PB1176_WATCHDOG_BASE 0x10107000 /* watchdog interface */ -#define REALVIEW_PB1176_RTC_BASE 0x10108000 /* Real Time Clock */ -#define REALVIEW_PB1176_GPIO0_BASE 0x1010A000 /* GPIO port 0 */ -#define REALVIEW_PB1176_SSP_BASE 0x1010B000 /* Synchronous Serial Port */ -#define REALVIEW_PB1176_UART0_BASE 0x1010C000 /* UART 0 */ -#define REALVIEW_PB1176_UART1_BASE 0x1010D000 /* UART 1 */ -#define REALVIEW_PB1176_UART2_BASE 0x1010E000 /* UART 2 */ -#define REALVIEW_PB1176_UART3_BASE 0x1010F000 /* UART 3 */ -#define REALVIEW_PB1176_CLCD_BASE 0x10112000 /* CLCD */ -#define REALVIEW_PB1176_ETH_BASE 0x3A000000 /* Ethernet */ -#define REALVIEW_PB1176_USB_BASE 0x3B000000 /* USB */ - -/* - * PCI regions - */ -#define REALVIEW_PB1176_PCI_BASE 0x60000000 /* PCI self config */ -#define REALVIEW_PB1176_PCI_CFG_BASE 0x61000000 /* PCI config */ -#define REALVIEW_PB1176_PCI_IO_BASE0 0x62000000 /* PCI IO region */ -#define REALVIEW_PB1176_PCI_MEM_BASE0 0x63000000 /* Memory region 1 */ -#define REALVIEW_PB1176_PCI_MEM_BASE1 0x64000000 /* Memory region 2 */ -#define REALVIEW_PB1176_PCI_MEM_BASE2 0x68000000 /* Memory region 3 */ - -#define REALVIEW_PB1176_PCI_BASE_SIZE 0x01000000 /* 16MB */ -#define REALVIEW_PB1176_PCI_CFG_BASE_SIZE 0x01000000 /* 16MB */ -#define REALVIEW_PB1176_PCI_IO_BASE0_SIZE 0x01000000 /* 16MB */ -#define REALVIEW_PB1176_PCI_MEM_BASE0_SIZE 0x01000000 /* 16MB */ -#define REALVIEW_PB1176_PCI_MEM_BASE1_SIZE 0x04000000 /* 64MB */ -#define REALVIEW_PB1176_PCI_MEM_BASE2_SIZE 0x08000000 /* 128MB */ - -#define REALVIEW_DC1176_GIC_CPU_BASE 0x10120000 /* GIC CPU interface, on devchip */ -#define REALVIEW_DC1176_GIC_DIST_BASE 0x10121000 /* GIC distributor, on devchip */ -#define REALVIEW_DC1176_ROM_BASE 0x10200000 /* 16KiB NRAM preudo-ROM, on devchip */ -#define REALVIEW_PB1176_GIC_CPU_BASE 0x10040000 /* GIC CPU interface, on FPGA */ -#define REALVIEW_PB1176_GIC_DIST_BASE 0x10041000 /* GIC distributor, on FPGA */ -#define REALVIEW_PB1176_L220_BASE 0x10110000 /* L220 registers */ - -/* - * Control register SYS_RESETCTL Bit 8 is set to 1 to force a soft reset - */ -#define REALVIEW_PB1176_SYS_SOFT_RESET 0x0100 - -#endif /* __ASM_ARCH_BOARD_PB1176_H */ diff --git a/arch/arm/mach-realview/board-pb11mp.h b/arch/arm/mach-realview/board-pb11mp.h deleted file mode 100644 index b16e6e85e92d..000000000000 --- a/arch/arm/mach-realview/board-pb11mp.h +++ /dev/null @@ -1,96 +0,0 @@ -/* - * Copyright (C) 2008 ARM Limited - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301, USA. - */ - -#ifndef __ASM_ARCH_BOARD_PB11MP_H -#define __ASM_ARCH_BOARD_PB11MP_H - -#include "platform.h" - -/* - * Peripheral addresses - */ -#define REALVIEW_PB11MP_UART0_BASE 0x10009000 /* UART 0 */ -#define REALVIEW_PB11MP_UART1_BASE 0x1000A000 /* UART 1 */ -#define REALVIEW_PB11MP_UART2_BASE 0x1000B000 /* UART 2 */ -#define REALVIEW_PB11MP_UART3_BASE 0x1000C000 /* UART 3 */ -#define REALVIEW_PB11MP_SSP_BASE 0x1000D000 /* Synchronous Serial Port */ -#define REALVIEW_PB11MP_WATCHDOG0_BASE 0x1000F000 /* Watchdog 0 */ -#define REALVIEW_PB11MP_WATCHDOG_BASE 0x10010000 /* watchdog interface */ -#define REALVIEW_PB11MP_TIMER0_1_BASE 0x10011000 /* Timer 0 and 1 */ -#define REALVIEW_PB11MP_TIMER2_3_BASE 0x10012000 /* Timer 2 and 3 */ -#define REALVIEW_PB11MP_GPIO0_BASE 0x10013000 /* GPIO port 0 */ -#define REALVIEW_PB11MP_RTC_BASE 0x10017000 /* Real Time Clock */ -#define REALVIEW_PB11MP_TIMER4_5_BASE 0x10018000 /* Timer 4/5 */ -#define REALVIEW_PB11MP_TIMER6_7_BASE 0x10019000 /* Timer 6/7 */ -#define REALVIEW_PB11MP_SCTL_BASE 0x1001A000 /* System Controller */ -#define REALVIEW_PB11MP_CLCD_BASE 0x10020000 /* CLCD */ -#define REALVIEW_PB11MP_ONB_SRAM_BASE 0x10060000 /* On-board SRAM */ -#define REALVIEW_PB11MP_DMC_BASE 0x100E0000 /* DMC configuration */ -#define REALVIEW_PB11MP_SMC_BASE 0x100E1000 /* SMC configuration */ -#define REALVIEW_PB11MP_CAN_BASE 0x100E2000 /* CAN bus */ -#define REALVIEW_PB11MP_CF_BASE 0x18000000 /* Compact flash */ -#define REALVIEW_PB11MP_CF_MEM_BASE 0x18003000 /* SMC for Compact flash */ -#define REALVIEW_PB11MP_GIC_CPU_BASE 0x1E000000 /* Generic interrupt controller CPU interface */ -#define REALVIEW_PB11MP_FLASH0_BASE 0x40000000 -#define REALVIEW_PB11MP_FLASH0_SIZE SZ_64M -#define REALVIEW_PB11MP_FLASH1_BASE 0x44000000 -#define REALVIEW_PB11MP_FLASH1_SIZE SZ_64M -#define REALVIEW_PB11MP_ETH_BASE 0x4E000000 /* Ethernet */ -#define REALVIEW_PB11MP_USB_BASE 0x4F000000 /* USB */ -#define REALVIEW_PB11MP_GIC_DIST_BASE 0x1E001000 /* Generic interrupt controller distributor */ -#define REALVIEW_PB11MP_LT_BASE 0xC0000000 /* Logic Tile expansion */ -#define REALVIEW_PB11MP_SDRAM6_BASE 0x70000000 /* SDRAM bank 6 256MB */ -#define REALVIEW_PB11MP_SDRAM7_BASE 0x80000000 /* SDRAM bank 7 256MB */ - -#define REALVIEW_PB11MP_SYS_PLD_CTRL1 0x74 - -/* - * PB11MPCore PCI regions - */ -#define REALVIEW_PB11MP_PCI_BASE 0x90040000 /* PCI-X Unit base */ -#define REALVIEW_PB11MP_PCI_IO_BASE 0x90050000 /* IO Region on AHB */ -#define REALVIEW_PB11MP_PCI_MEM_BASE 0xA0000000 /* MEM Region on AHB */ - -#define REALVIEW_PB11MP_PCI_BASE_SIZE 0x10000 /* 16 Kb */ -#define REALVIEW_PB11MP_PCI_IO_SIZE 0x1000 /* 4 Kb */ -#define REALVIEW_PB11MP_PCI_MEM_SIZE 0x20000000 /* 512 MB */ - -/* - * Testchip peripheral and fpga gic regions - */ -#define REALVIEW_TC11MP_PRIV_MEM_BASE 0x1F000000 -#define REALVIEW_TC11MP_PRIV_MEM_SIZE SZ_8K -#define REALVIEW_TC11MP_SCU_BASE 0x1F000000 /* IRQ, Test chip */ -#define REALVIEW_TC11MP_GIC_CPU_BASE 0x1F000100 /* Test chip interrupt controller CPU interface */ -#define REALVIEW_TC11MP_TWD_BASE 0x1F000600 -#define REALVIEW_TC11MP_GIC_DIST_BASE 0x1F001000 /* Test chip interrupt controller distributor */ -#define REALVIEW_TC11MP_L220_BASE 0x1F002000 /* L220 registers */ - - /* - * Values for REALVIEW_SYS_RESET_CTRL - */ -#define REALVIEW_PB11MP_SYS_CTRL_RESET_CONFIGCLR 0x01 -#define REALVIEW_PB11MP_SYS_CTRL_RESET_CONFIGINIT 0x02 -#define REALVIEW_PB11MP_SYS_CTRL_RESET_DLLRESET 0x03 -#define REALVIEW_PB11MP_SYS_CTRL_RESET_PLLRESET 0x04 -#define REALVIEW_PB11MP_SYS_CTRL_RESET_POR 0x05 -#define REALVIEW_PB11MP_SYS_CTRL_RESET_DoC 0x06 - -#define REALVIEW_PB11MP_SYS_CTRL_LED (1 << 0) - -#endif /* __ASM_ARCH_BOARD_PB11MP_H */ diff --git a/arch/arm/mach-realview/board-pba8.h b/arch/arm/mach-realview/board-pba8.h deleted file mode 100644 index 6a1391f50373..000000000000 --- a/arch/arm/mach-realview/board-pba8.h +++ /dev/null @@ -1,71 +0,0 @@ -/* - * Copyright (C) 2008 ARM Limited - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301, USA. - */ - -#ifndef __ASM_ARCH_BOARD_PBA8_H -#define __ASM_ARCH_BOARD_PBA8_H - -#include "platform.h" - -/* - * Peripheral addresses - */ -#define REALVIEW_PBA8_UART0_BASE 0x10009000 /* UART 0 */ -#define REALVIEW_PBA8_UART1_BASE 0x1000A000 /* UART 1 */ -#define REALVIEW_PBA8_UART2_BASE 0x1000B000 /* UART 2 */ -#define REALVIEW_PBA8_UART3_BASE 0x1000C000 /* UART 3 */ -#define REALVIEW_PBA8_SSP_BASE 0x1000D000 /* Synchronous Serial Port */ -#define REALVIEW_PBA8_WATCHDOG0_BASE 0x1000F000 /* Watchdog 0 */ -#define REALVIEW_PBA8_WATCHDOG_BASE 0x10010000 /* watchdog interface */ -#define REALVIEW_PBA8_TIMER0_1_BASE 0x10011000 /* Timer 0 and 1 */ -#define REALVIEW_PBA8_TIMER2_3_BASE 0x10012000 /* Timer 2 and 3 */ -#define REALVIEW_PBA8_GPIO0_BASE 0x10013000 /* GPIO port 0 */ -#define REALVIEW_PBA8_RTC_BASE 0x10017000 /* Real Time Clock */ -#define REALVIEW_PBA8_TIMER4_5_BASE 0x10018000 /* Timer 4/5 */ -#define REALVIEW_PBA8_TIMER6_7_BASE 0x10019000 /* Timer 6/7 */ -#define REALVIEW_PBA8_SCTL_BASE 0x1001A000 /* System Controller */ -#define REALVIEW_PBA8_CLCD_BASE 0x10020000 /* CLCD */ -#define REALVIEW_PBA8_ONB_SRAM_BASE 0x10060000 /* On-board SRAM */ -#define REALVIEW_PBA8_DMC_BASE 0x100E0000 /* DMC configuration */ -#define REALVIEW_PBA8_SMC_BASE 0x100E1000 /* SMC configuration */ -#define REALVIEW_PBA8_CAN_BASE 0x100E2000 /* CAN bus */ -#define REALVIEW_PBA8_GIC_CPU_BASE 0x1E000000 /* Generic interrupt controller CPU interface */ -#define REALVIEW_PBA8_FLASH0_BASE 0x40000000 -#define REALVIEW_PBA8_FLASH0_SIZE SZ_64M -#define REALVIEW_PBA8_FLASH1_BASE 0x44000000 -#define REALVIEW_PBA8_FLASH1_SIZE SZ_64M -#define REALVIEW_PBA8_ETH_BASE 0x4E000000 /* Ethernet */ -#define REALVIEW_PBA8_USB_BASE 0x4F000000 /* USB */ -#define REALVIEW_PBA8_GIC_DIST_BASE 0x1E001000 /* Generic interrupt controller distributor */ -#define REALVIEW_PBA8_LT_BASE 0xC0000000 /* Logic Tile expansion */ -#define REALVIEW_PBA8_SDRAM6_BASE 0x70000000 /* SDRAM bank 6 256MB */ -#define REALVIEW_PBA8_SDRAM7_BASE 0x80000000 /* SDRAM bank 7 256MB */ - -#define REALVIEW_PBA8_SYS_PLD_CTRL1 0x74 - -/* - * PBA8 PCI regions - */ -#define REALVIEW_PBA8_PCI_BASE 0x90040000 /* PCI-X Unit base */ -#define REALVIEW_PBA8_PCI_IO_BASE 0x90050000 /* IO Region on AHB */ -#define REALVIEW_PBA8_PCI_MEM_BASE 0xA0000000 /* MEM Region on AHB */ - -#define REALVIEW_PBA8_PCI_BASE_SIZE 0x10000 /* 16 Kb */ -#define REALVIEW_PBA8_PCI_IO_SIZE 0x1000 /* 4 Kb */ -#define REALVIEW_PBA8_PCI_MEM_SIZE 0x20000000 /* 512 MB */ - -#endif /* __ASM_ARCH_BOARD_PBA8_H */ diff --git a/arch/arm/mach-realview/board-pbx.h b/arch/arm/mach-realview/board-pbx.h deleted file mode 100644 index 5cda480b12bb..000000000000 --- a/arch/arm/mach-realview/board-pbx.h +++ /dev/null @@ -1,106 +0,0 @@ -/* - * Copyright (C) 2009 ARM Limited - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef __ASM_ARCH_BOARD_PBX_H -#define __ASM_ARCH_BOARD_PBX_H - -#include "platform.h" - -/* - * Peripheral addresses - */ -#define REALVIEW_PBX_UART0_BASE 0x10009000 /* UART 0 */ -#define REALVIEW_PBX_UART1_BASE 0x1000A000 /* UART 1 */ -#define REALVIEW_PBX_UART2_BASE 0x1000B000 /* UART 2 */ -#define REALVIEW_PBX_UART3_BASE 0x1000C000 /* UART 3 */ -#define REALVIEW_PBX_SSP_BASE 0x1000D000 /* Synchronous Serial Port */ -#define REALVIEW_PBX_WATCHDOG0_BASE 0x1000F000 /* Watchdog 0 */ -#define REALVIEW_PBX_WATCHDOG_BASE 0x10010000 /* watchdog interface */ -#define REALVIEW_PBX_TIMER0_1_BASE 0x10011000 /* Timer 0 and 1 */ -#define REALVIEW_PBX_TIMER2_3_BASE 0x10012000 /* Timer 2 and 3 */ -#define REALVIEW_PBX_GPIO0_BASE 0x10013000 /* GPIO port 0 */ -#define REALVIEW_PBX_RTC_BASE 0x10017000 /* Real Time Clock */ -#define REALVIEW_PBX_TIMER4_5_BASE 0x10018000 /* Timer 4/5 */ -#define REALVIEW_PBX_TIMER6_7_BASE 0x10019000 /* Timer 6/7 */ -#define REALVIEW_PBX_SCTL_BASE 0x1001A000 /* System Controller */ -#define REALVIEW_PBX_CLCD_BASE 0x10020000 /* CLCD */ -#define REALVIEW_PBX_ONB_SRAM_BASE 0x10060000 /* On-board SRAM */ -#define REALVIEW_PBX_DMC_BASE 0x100E0000 /* DMC configuration */ -#define REALVIEW_PBX_SMC_BASE 0x100E1000 /* SMC configuration */ -#define REALVIEW_PBX_CAN_BASE 0x100E2000 /* CAN bus */ -#define REALVIEW_PBX_GIC_CPU_BASE 0x1E000000 /* Generic interrupt controller CPU interface */ -#define REALVIEW_PBX_FLASH0_BASE 0x40000000 -#define REALVIEW_PBX_FLASH0_SIZE SZ_64M -#define REALVIEW_PBX_FLASH1_BASE 0x44000000 -#define REALVIEW_PBX_FLASH1_SIZE SZ_64M -#define REALVIEW_PBX_ETH_BASE 0x4E000000 /* Ethernet */ -#define REALVIEW_PBX_USB_BASE 0x4F000000 /* USB */ -#define REALVIEW_PBX_GIC_DIST_BASE 0x1E001000 /* Generic interrupt controller distributor */ -#define REALVIEW_PBX_LT_BASE 0xC0000000 /* Logic Tile expansion */ -#define REALVIEW_PBX_SDRAM6_BASE 0x70000000 /* SDRAM bank 6 256MB */ -#define REALVIEW_PBX_SDRAM7_BASE 0x80000000 /* SDRAM bank 7 256MB */ - -/* - * Tile-specific addresses - */ -#define REALVIEW_PBX_TILE_SCU_BASE 0x1F000000 /* SCU registers */ -#define REALVIEW_PBX_TILE_GIC_CPU_BASE 0x1F000100 /* Private Generic interrupt controller CPU interface */ -#define REALVIEW_PBX_TILE_TWD_BASE 0x1F000600 -#define REALVIEW_PBX_TILE_TWD_PERCPU_BASE 0x1F000700 -#define REALVIEW_PBX_TILE_TWD_SIZE 0x00000100 -#define REALVIEW_PBX_TILE_GIC_DIST_BASE 0x1F001000 /* Private Generic interrupt controller distributor */ -#define REALVIEW_PBX_TILE_L220_BASE 0x1F002000 /* L220 registers */ - -#define REALVIEW_PBX_SYS_PLD_CTRL1 0x74 - -/* - * PBX PCI regions - */ -#define REALVIEW_PBX_PCI_BASE 0x90040000 /* PCI-X Unit base */ -#define REALVIEW_PBX_PCI_IO_BASE 0x90050000 /* IO Region on AHB */ -#define REALVIEW_PBX_PCI_MEM_BASE 0xA0000000 /* MEM Region on AHB */ - -#define REALVIEW_PBX_PCI_BASE_SIZE 0x10000 /* 16 Kb */ -#define REALVIEW_PBX_PCI_IO_SIZE 0x1000 /* 4 Kb */ -#define REALVIEW_PBX_PCI_MEM_SIZE 0x20000000 /* 512 MB */ - -/* - * Core tile identification (REALVIEW_SYS_PROCID) - */ -#define REALVIEW_PBX_PROC_MASK 0xFF000000 -#define REALVIEW_PBX_PROC_ARM7TDMI 0x00000000 -#define REALVIEW_PBX_PROC_ARM9 0x02000000 -#define REALVIEW_PBX_PROC_ARM11 0x04000000 -#define REALVIEW_PBX_PROC_ARM11MP 0x06000000 -#define REALVIEW_PBX_PROC_A9MP 0x0C000000 -#define REALVIEW_PBX_PROC_A8 0x0E000000 - -#define check_pbx_proc(proc_type) \ - ((readl(__io_address(REALVIEW_SYS_PROCID)) & REALVIEW_PBX_PROC_MASK) \ - == proc_type) - -#ifdef CONFIG_MACH_REALVIEW_PBX -#define core_tile_pbx11mp() check_pbx_proc(REALVIEW_PBX_PROC_ARM11MP) -#define core_tile_pbxa9mp() check_pbx_proc(REALVIEW_PBX_PROC_A9MP) -#define core_tile_pbxa8() check_pbx_proc(REALVIEW_PBX_PROC_A8) -#else -#define core_tile_pbx11mp() 0 -#define core_tile_pbxa9mp() 0 -#define core_tile_pbxa8() 0 -#endif - -#endif /* __ASM_ARCH_BOARD_PBX_H */ diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c deleted file mode 100644 index baf174542e36..000000000000 --- a/arch/arm/mach-realview/core.c +++ /dev/null @@ -1,404 +0,0 @@ -/* - * linux/arch/arm/mach-realview/core.c - * - * Copyright (C) 1999 - 2003 ARM Limited - * Copyright (C) 2000 Deep Blue Solutions Ltd - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -#include <linux/init.h> -#include <linux/platform_device.h> -#include <linux/dma-mapping.h> -#include <linux/device.h> -#include <linux/interrupt.h> -#include <linux/amba/bus.h> -#include <linux/amba/clcd.h> -#include <linux/platform_data/video-clcd-versatile.h> -#include <linux/io.h> -#include <linux/smsc911x.h> -#include <linux/smc91x.h> -#include <linux/ata_platform.h> -#include <linux/amba/mmci.h> -#include <linux/gfp.h> -#include <linux/mtd/physmap.h> -#include <linux/memblock.h> - -#include <clocksource/timer-sp804.h> -#include "hardware.h" -#include <asm/irq.h> -#include <asm/mach-types.h> -#include <asm/hardware/icst.h> - -#include <asm/mach/arch.h> -#include <asm/mach/irq.h> -#include <asm/mach/map.h> - -#include "platform.h" - -#include <plat/sched_clock.h> - -#include "core.h" - -#define REALVIEW_FLASHCTRL (__io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_FLASH_OFFSET) - -static void realview_flash_set_vpp(struct platform_device *pdev, int on) -{ - u32 val; - - val = __raw_readl(REALVIEW_FLASHCTRL); - if (on) - val |= REALVIEW_FLASHPROG_FLVPPEN; - else - val &= ~REALVIEW_FLASHPROG_FLVPPEN; - __raw_writel(val, REALVIEW_FLASHCTRL); -} - -static struct physmap_flash_data realview_flash_data = { - .width = 4, - .set_vpp = realview_flash_set_vpp, -}; - -struct platform_device realview_flash_device = { - .name = "physmap-flash", - .id = 0, - .dev = { - .platform_data = &realview_flash_data, - }, -}; - -int realview_flash_register(struct resource *res, u32 num) -{ - realview_flash_device.resource = res; - realview_flash_device.num_resources = num; - return platform_device_register(&realview_flash_device); -} - -static struct smsc911x_platform_config smsc911x_config = { - .flags = SMSC911X_USE_32BIT, - .irq_polarity = SMSC911X_IRQ_POLARITY_ACTIVE_HIGH, - .irq_type = SMSC911X_IRQ_TYPE_PUSH_PULL, - .phy_interface = PHY_INTERFACE_MODE_MII, -}; - -static struct smc91x_platdata smc91x_platdata = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT, -}; - -static struct platform_device realview_eth_device = { - .name = "smsc911x", - .id = 0, - .num_resources = 2, -}; - -int realview_eth_register(const char *name, struct resource *res) -{ - if (name) - realview_eth_device.name = name; - realview_eth_device.resource = res; - if (strcmp(realview_eth_device.name, "smsc911x") == 0) - realview_eth_device.dev.platform_data = &smsc911x_config; - else - realview_eth_device.dev.platform_data = &smc91x_platdata; - - return platform_device_register(&realview_eth_device); -} - -struct platform_device realview_usb_device = { - .name = "isp1760", - .num_resources = 2, -}; - -int realview_usb_register(struct resource *res) -{ - realview_usb_device.resource = res; - return platform_device_register(&realview_usb_device); -} - -static struct pata_platform_info pata_platform_data = { - .ioport_shift = 1, -}; - -static struct resource pata_resources[] = { - [0] = { - .start = REALVIEW_CF_BASE, - .end = REALVIEW_CF_BASE + 0xff, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = REALVIEW_CF_BASE + 0x100, - .end = REALVIEW_CF_BASE + SZ_4K - 1, - .flags = IORESOURCE_MEM, - }, -}; - -struct platform_device realview_cf_device = { - .name = "pata_platform", - .id = -1, - .num_resources = ARRAY_SIZE(pata_resources), - .resource = pata_resources, - .dev = { - .platform_data = &pata_platform_data, - }, -}; - -static struct resource realview_leds_resources[] = { - { - .start = REALVIEW_SYS_BASE + REALVIEW_SYS_LED_OFFSET, - .end = REALVIEW_SYS_BASE + REALVIEW_SYS_LED_OFFSET + 4, - .flags = IORESOURCE_MEM, - }, -}; - -struct platform_device realview_leds_device = { - .name = "versatile-leds", - .id = -1, - .num_resources = ARRAY_SIZE(realview_leds_resources), - .resource = realview_leds_resources, -}; - -static struct resource realview_i2c_resource = { - .start = REALVIEW_I2C_BASE, - .end = REALVIEW_I2C_BASE + SZ_4K - 1, - .flags = IORESOURCE_MEM, -}; - -struct platform_device realview_i2c_device = { - .name = "versatile-i2c", - .id = 0, - .num_resources = 1, - .resource = &realview_i2c_resource, -}; - -static struct i2c_board_info realview_i2c_board_info[] = { - { - I2C_BOARD_INFO("ds1338", 0xd0 >> 1), - }, -}; - -static int __init realview_i2c_init(void) -{ - return i2c_register_board_info(0, realview_i2c_board_info, - ARRAY_SIZE(realview_i2c_board_info)); -} -arch_initcall(realview_i2c_init); - -#define REALVIEW_SYSMCI (__io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_MCI_OFFSET) - -/* - * This is only used if GPIOLIB support is disabled - */ -static unsigned int realview_mmc_status(struct device *dev) -{ - struct amba_device *adev = container_of(dev, struct amba_device, dev); - u32 mask; - - if (machine_is_realview_pb1176()) { - static bool inserted = false; - - /* - * The PB1176 does not have the status register, - * assume it is inserted at startup, then invert - * for each call so card insertion/removal will - * be detected anyway. This will not be called if - * GPIO on PL061 is active, which is the proper - * way to do this on the PB1176. - */ - inserted = !inserted; - return inserted ? 0 : 1; - } - - if (adev->res.start == REALVIEW_MMCI0_BASE) - mask = 1; - else - mask = 2; - - return readl(REALVIEW_SYSMCI) & mask; -} - -struct mmci_platform_data realview_mmc0_plat_data = { - .ocr_mask = MMC_VDD_32_33|MMC_VDD_33_34, - .status = realview_mmc_status, - .gpio_wp = 17, - .gpio_cd = 16, - .cd_invert = true, -}; - -struct mmci_platform_data realview_mmc1_plat_data = { - .ocr_mask = MMC_VDD_32_33|MMC_VDD_33_34, - .status = realview_mmc_status, - .gpio_wp = 19, - .gpio_cd = 18, - .cd_invert = true, -}; - -void __init realview_init_early(void) -{ - void __iomem *sys = __io_address(REALVIEW_SYS_BASE); - - versatile_sched_clock_init(sys + REALVIEW_SYS_24MHz_OFFSET, 24000000); -} - -/* - * CLCD support. - */ -#define SYS_CLCD_NLCDIOON (1 << 2) -#define SYS_CLCD_VDDPOSSWITCH (1 << 3) -#define SYS_CLCD_PWR3V5SWITCH (1 << 4) -#define SYS_CLCD_ID_MASK (0x1f << 8) -#define SYS_CLCD_ID_SANYO_3_8 (0x00 << 8) -#define SYS_CLCD_ID_UNKNOWN_8_4 (0x01 << 8) -#define SYS_CLCD_ID_EPSON_2_2 (0x02 << 8) -#define SYS_CLCD_ID_SANYO_2_5 (0x07 << 8) -#define SYS_CLCD_ID_VGA (0x1f << 8) - -/* - * Disable all display connectors on the interface module. - */ -static void realview_clcd_disable(struct clcd_fb *fb) -{ - void __iomem *sys_clcd = __io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_CLCD_OFFSET; - u32 val; - - val = readl(sys_clcd); - val &= ~SYS_CLCD_NLCDIOON | SYS_CLCD_PWR3V5SWITCH; - writel(val, sys_clcd); -} - -/* - * Enable the relevant connector on the interface module. - */ -static void realview_clcd_enable(struct clcd_fb *fb) -{ - void __iomem *sys_clcd = __io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_CLCD_OFFSET; - u32 val; - - /* - * Enable the PSUs - */ - val = readl(sys_clcd); - val |= SYS_CLCD_NLCDIOON | SYS_CLCD_PWR3V5SWITCH; - writel(val, sys_clcd); -} - -/* - * Detect which LCD panel is connected, and return the appropriate - * clcd_panel structure. Note: we do not have any information on - * the required timings for the 8.4in panel, so we presently assume - * VGA timings. - */ -static int realview_clcd_setup(struct clcd_fb *fb) -{ - void __iomem *sys_clcd = __io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_CLCD_OFFSET; - const char *panel_name, *vga_panel_name; - unsigned long framesize; - u32 val; - - if (machine_is_realview_eb()) { - /* VGA, 16bpp */ - framesize = 640 * 480 * 2; - vga_panel_name = "VGA"; - } else { - /* XVGA, 16bpp */ - framesize = 1024 * 768 * 2; - vga_panel_name = "XVGA"; - } - - val = readl(sys_clcd) & SYS_CLCD_ID_MASK; - if (val == SYS_CLCD_ID_SANYO_3_8) - panel_name = "Sanyo TM38QV67A02A"; - else if (val == SYS_CLCD_ID_SANYO_2_5) - panel_name = "Sanyo QVGA Portrait"; - else if (val == SYS_CLCD_ID_EPSON_2_2) - panel_name = "Epson L2F50113T00"; - else if (val == SYS_CLCD_ID_VGA) - panel_name = vga_panel_name; - else { - pr_err("CLCD: unknown LCD panel ID 0x%08x, using VGA\n", val); - panel_name = vga_panel_name; - } - - fb->panel = versatile_clcd_get_panel(panel_name); - if (!fb->panel) - return -EINVAL; - - return versatile_clcd_setup_dma(fb, framesize); -} - -struct clcd_board clcd_plat_data = { - .name = "RealView", - .caps = CLCD_CAP_ALL, - .check = clcdfb_check, - .decode = clcdfb_decode, - .disable = realview_clcd_disable, - .enable = realview_clcd_enable, - .setup = realview_clcd_setup, - .mmap = versatile_clcd_mmap_dma, - .remove = versatile_clcd_remove_dma, -}; - -/* - * Where is the timer (VA)? - */ -void __iomem *timer0_va_base; -void __iomem *timer1_va_base; -void __iomem *timer2_va_base; -void __iomem *timer3_va_base; - -/* - * Set up the clock source and clock events devices - */ -void __init realview_timer_init(unsigned int timer_irq) -{ - u32 val; - - /* - * set clock frequency: - * REALVIEW_REFCLK is 32KHz - * REALVIEW_TIMCLK is 1MHz - */ - val = readl(__io_address(REALVIEW_SCTL_BASE)); - writel((REALVIEW_TIMCLK << REALVIEW_TIMER1_EnSel) | - (REALVIEW_TIMCLK << REALVIEW_TIMER2_EnSel) | - (REALVIEW_TIMCLK << REALVIEW_TIMER3_EnSel) | - (REALVIEW_TIMCLK << REALVIEW_TIMER4_EnSel) | val, - __io_address(REALVIEW_SCTL_BASE)); - - /* - * Initialise to a known state (all timers off) - */ - sp804_timer_disable(timer0_va_base); - sp804_timer_disable(timer1_va_base); - sp804_timer_disable(timer2_va_base); - sp804_timer_disable(timer3_va_base); - - sp804_clocksource_init(timer3_va_base, "timer3"); - sp804_clockevents_init(timer0_va_base, timer_irq, "timer0"); -} - -/* - * Setup the memory banks. - */ -void realview_fixup(struct tag *tags, char **from) -{ - /* - * Most RealView platforms have 512MB contiguous RAM at 0x70000000. - * Half of this is mirrored at 0. - */ -#ifdef CONFIG_REALVIEW_HIGH_PHYS_OFFSET - memblock_add(0x70000000, SZ_512M); -#else - memblock_add(0, SZ_256M); -#endif -} diff --git a/arch/arm/mach-realview/core.h b/arch/arm/mach-realview/core.h deleted file mode 100644 index 05a995ea16d3..000000000000 --- a/arch/arm/mach-realview/core.h +++ /dev/null @@ -1,58 +0,0 @@ -/* - * Copyright (C) 2004 ARM Limited - * Copyright (C) 2000 Deep Blue Solutions Ltd - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef __ASM_ARCH_REALVIEW_H -#define __ASM_ARCH_REALVIEW_H - -#include <linux/amba/bus.h> -#include <linux/io.h> - -#include <asm/setup.h> - -#define APB_DEVICE(name, busid, base, plat) \ -static AMBA_APB_DEVICE(name, busid, 0, REALVIEW_##base##_BASE, base##_IRQ, plat) - -#define AHB_DEVICE(name, busid, base, plat) \ -static AMBA_AHB_DEVICE(name, busid, 0, REALVIEW_##base##_BASE, base##_IRQ, plat) - -struct machine_desc; - -extern struct platform_device realview_flash_device; -extern struct platform_device realview_cf_device; -extern struct platform_device realview_leds_device; -extern struct platform_device realview_i2c_device; -extern struct mmci_platform_data realview_mmc0_plat_data; -extern struct mmci_platform_data realview_mmc1_plat_data; -extern struct clcd_board clcd_plat_data; -extern void __iomem *timer0_va_base; -extern void __iomem *timer1_va_base; -extern void __iomem *timer2_va_base; -extern void __iomem *timer3_va_base; - -extern void realview_timer_init(unsigned int timer_irq); -extern int realview_flash_register(struct resource *res, u32 num); -extern int realview_eth_register(const char *name, struct resource *res); -extern int realview_usb_register(struct resource *res); -extern void realview_init_early(void); -extern void realview_fixup(struct tag *tags, char **from); - -extern const struct smp_operations realview_smp_ops; -extern void realview_cpu_die(unsigned int cpu); - -#endif diff --git a/arch/arm/mach-realview/hardware.h b/arch/arm/mach-realview/hardware.h deleted file mode 100644 index 957a230aadf4..000000000000 --- a/arch/arm/mach-realview/hardware.h +++ /dev/null @@ -1,40 +0,0 @@ -/* - * This file contains the hardware definitions of the RealView boards. - * - * Copyright (C) 2003 ARM Limited. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -#ifndef __ASM_ARCH_HARDWARE_H -#define __ASM_ARCH_HARDWARE_H - -#include <asm/sizes.h> - -/* macro to get at IO space when running virtually */ -#ifdef CONFIG_MMU -/* - * Statically mapped addresses: - * - * 10xx xxxx -> fbxx xxxx - * 1exx xxxx -> fdxx xxxx - * 1fxx xxxx -> fexx xxxx - */ -#define IO_ADDRESS(x) (((x) & 0x03ffffff) + 0xfb000000) -#else -#define IO_ADDRESS(x) (x) -#endif -#define __io_address(n) IOMEM(IO_ADDRESS(n)) - -#endif diff --git a/arch/arm/mach-realview/hotplug.h b/arch/arm/mach-realview/hotplug.h new file mode 100644 index 000000000000..eacd7a4dad2f --- /dev/null +++ b/arch/arm/mach-realview/hotplug.h @@ -0,0 +1 @@ +void realview_cpu_die(unsigned int cpu); diff --git a/arch/arm/mach-realview/irqs-eb.h b/arch/arm/mach-realview/irqs-eb.h deleted file mode 100644 index 61e31680a749..000000000000 --- a/arch/arm/mach-realview/irqs-eb.h +++ /dev/null @@ -1,114 +0,0 @@ -/* - * Copyright (C) 2007 ARM Limited - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301, USA. - */ - -#ifndef __MACH_IRQS_EB_H -#define __MACH_IRQS_EB_H - -#define IRQ_LOCALTIMER 29 -#define IRQ_EB_GIC_START 32 - -/* - * RealView EB interrupt sources - */ -#define IRQ_EB_WDOG (IRQ_EB_GIC_START + 0) /* Watchdog timer */ -#define IRQ_EB_SOFT (IRQ_EB_GIC_START + 1) /* Software interrupt */ -#define IRQ_EB_COMMRx (IRQ_EB_GIC_START + 2) /* Debug Comm Rx interrupt */ -#define IRQ_EB_COMMTx (IRQ_EB_GIC_START + 3) /* Debug Comm Tx interrupt */ -#define IRQ_EB_TIMER0_1 (IRQ_EB_GIC_START + 4) /* Timer 0 and 1 */ -#define IRQ_EB_TIMER2_3 (IRQ_EB_GIC_START + 5) /* Timer 2 and 3 */ -#define IRQ_EB_GPIO0 (IRQ_EB_GIC_START + 6) /* GPIO 0 */ -#define IRQ_EB_GPIO1 (IRQ_EB_GIC_START + 7) /* GPIO 1 */ -#define IRQ_EB_GPIO2 (IRQ_EB_GIC_START + 8) /* GPIO 2 */ - /* 9 reserved */ -#define IRQ_EB_RTC (IRQ_EB_GIC_START + 10) /* Real Time Clock */ -#define IRQ_EB_SSP (IRQ_EB_GIC_START + 11) /* Synchronous Serial Port */ -#define IRQ_EB_UART0 (IRQ_EB_GIC_START + 12) /* UART 0 on development chip */ -#define IRQ_EB_UART1 (IRQ_EB_GIC_START + 13) /* UART 1 on development chip */ -#define IRQ_EB_UART2 (IRQ_EB_GIC_START + 14) /* UART 2 on development chip */ -#define IRQ_EB_UART3 (IRQ_EB_GIC_START + 15) /* UART 3 on development chip */ -#define IRQ_EB_SCI (IRQ_EB_GIC_START + 16) /* Smart Card Interface */ -#define IRQ_EB_MMCI0A (IRQ_EB_GIC_START + 17) /* Multimedia Card 0A */ -#define IRQ_EB_MMCI0B (IRQ_EB_GIC_START + 18) /* Multimedia Card 0B */ -#define IRQ_EB_AACI (IRQ_EB_GIC_START + 19) /* Audio Codec */ -#define IRQ_EB_KMI0 (IRQ_EB_GIC_START + 20) /* Keyboard/Mouse port 0 */ -#define IRQ_EB_KMI1 (IRQ_EB_GIC_START + 21) /* Keyboard/Mouse port 1 */ -#define IRQ_EB_CHARLCD (IRQ_EB_GIC_START + 22) /* Character LCD */ -#define IRQ_EB_CLCD (IRQ_EB_GIC_START + 23) /* CLCD controller */ -#define IRQ_EB_DMA (IRQ_EB_GIC_START + 24) /* DMA controller */ -#define IRQ_EB_PWRFAIL (IRQ_EB_GIC_START + 25) /* Power failure */ -#define IRQ_EB_PISMO (IRQ_EB_GIC_START + 26) /* PISMO interface */ -#define IRQ_EB_DoC (IRQ_EB_GIC_START + 27) /* Disk on Chip memory controller */ -#define IRQ_EB_ETH (IRQ_EB_GIC_START + 28) /* Ethernet controller */ -#define IRQ_EB_USB (IRQ_EB_GIC_START + 29) /* USB controller */ -#define IRQ_EB_TSPEN (IRQ_EB_GIC_START + 30) /* Touchscreen pen */ -#define IRQ_EB_TSKPAD (IRQ_EB_GIC_START + 31) /* Touchscreen keypad */ - -/* - * RealView EB + ARM11MPCore interrupt sources (primary GIC on the core tile) - */ -#define IRQ_EB11MP_AACI (IRQ_EB_GIC_START + 0) -#define IRQ_EB11MP_TIMER0_1 (IRQ_EB_GIC_START + 1) -#define IRQ_EB11MP_TIMER2_3 (IRQ_EB_GIC_START + 2) -#define IRQ_EB11MP_USB (IRQ_EB_GIC_START + 3) -#define IRQ_EB11MP_UART0 (IRQ_EB_GIC_START + 4) -#define IRQ_EB11MP_UART1 (IRQ_EB_GIC_START + 5) -#define IRQ_EB11MP_RTC (IRQ_EB_GIC_START + 6) -#define IRQ_EB11MP_KMI0 (IRQ_EB_GIC_START + 7) -#define IRQ_EB11MP_KMI1 (IRQ_EB_GIC_START + 8) -#define IRQ_EB11MP_ETH (IRQ_EB_GIC_START + 9) -#define IRQ_EB11MP_EB_IRQ1 (IRQ_EB_GIC_START + 10) /* main GIC */ -#define IRQ_EB11MP_EB_IRQ2 (IRQ_EB_GIC_START + 11) /* tile GIC */ -#define IRQ_EB11MP_EB_FIQ1 (IRQ_EB_GIC_START + 12) /* main GIC */ -#define IRQ_EB11MP_EB_FIQ2 (IRQ_EB_GIC_START + 13) /* tile GIC */ -#define IRQ_EB11MP_MMCI0A (IRQ_EB_GIC_START + 14) -#define IRQ_EB11MP_MMCI0B (IRQ_EB_GIC_START + 15) - -#define IRQ_EB11MP_PMU_CPU0 (IRQ_EB_GIC_START + 17) -#define IRQ_EB11MP_PMU_CPU1 (IRQ_EB_GIC_START + 18) -#define IRQ_EB11MP_PMU_CPU2 (IRQ_EB_GIC_START + 19) -#define IRQ_EB11MP_PMU_CPU3 (IRQ_EB_GIC_START + 20) -#define IRQ_EB11MP_PMU_SCU0 (IRQ_EB_GIC_START + 21) -#define IRQ_EB11MP_PMU_SCU1 (IRQ_EB_GIC_START + 22) -#define IRQ_EB11MP_PMU_SCU2 (IRQ_EB_GIC_START + 23) -#define IRQ_EB11MP_PMU_SCU3 (IRQ_EB_GIC_START + 24) -#define IRQ_EB11MP_PMU_SCU4 (IRQ_EB_GIC_START + 25) -#define IRQ_EB11MP_PMU_SCU5 (IRQ_EB_GIC_START + 26) -#define IRQ_EB11MP_PMU_SCU6 (IRQ_EB_GIC_START + 27) -#define IRQ_EB11MP_PMU_SCU7 (IRQ_EB_GIC_START + 28) - -#define IRQ_EB11MP_L220_EVENT (IRQ_EB_GIC_START + 29) -#define IRQ_EB11MP_L220_SLAVE (IRQ_EB_GIC_START + 30) -#define IRQ_EB11MP_L220_DECODE (IRQ_EB_GIC_START + 31) - -/* - * The 11MPcore tile leaves the following unconnected. - */ -#define IRQ_EB11MP_UART2 0 -#define IRQ_EB11MP_UART3 0 -#define IRQ_EB11MP_CLCD 0 -#define IRQ_EB11MP_DMA 0 -#define IRQ_EB11MP_WDOG 0 -#define IRQ_EB11MP_GPIO0 0 -#define IRQ_EB11MP_GPIO1 0 -#define IRQ_EB11MP_GPIO2 0 -#define IRQ_EB11MP_SCI 0 -#define IRQ_EB11MP_SSP 0 - -#define NR_GIC_EB11MP 2 - -#endif /* __MACH_IRQS_EB_H */ diff --git a/arch/arm/mach-realview/irqs-pb1176.h b/arch/arm/mach-realview/irqs-pb1176.h deleted file mode 100644 index 778edfd430e7..000000000000 --- a/arch/arm/mach-realview/irqs-pb1176.h +++ /dev/null @@ -1,77 +0,0 @@ -/* - * Copyright (C) 2008 ARM Limited - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301, USA. - */ - -#ifndef __MACH_IRQS_PB1176_H -#define __MACH_IRQS_PB1176_H - -#define IRQ_DC1176_GIC_START 32 -#define IRQ_PB1176_GIC_START 64 - -/* - * ARM1176 DevChip interrupt sources (primary GIC) - */ -#define IRQ_DC1176_WATCHDOG (IRQ_DC1176_GIC_START + 0) /* Watchdog timer */ -#define IRQ_DC1176_SOFTINT (IRQ_DC1176_GIC_START + 1) /* Software interrupt */ -#define IRQ_DC1176_COMMRx (IRQ_DC1176_GIC_START + 2) /* Debug Comm Rx interrupt */ -#define IRQ_DC1176_COMMTx (IRQ_DC1176_GIC_START + 3) /* Debug Comm Tx interrupt */ -#define IRQ_DC1176_CORE_PMU (IRQ_DC1176_GIC_START + 7) /* Core PMU interrupt */ -#define IRQ_DC1176_TIMER0 (IRQ_DC1176_GIC_START + 8) /* Timer 0 */ -#define IRQ_DC1176_TIMER1 (IRQ_DC1176_GIC_START + 9) /* Timer 1 */ -#define IRQ_DC1176_TIMER2 (IRQ_DC1176_GIC_START + 10) /* Timer 2 */ -#define IRQ_DC1176_APC (IRQ_DC1176_GIC_START + 11) -#define IRQ_DC1176_IEC (IRQ_DC1176_GIC_START + 12) -#define IRQ_DC1176_L2CC (IRQ_DC1176_GIC_START + 13) -#define IRQ_DC1176_RTC (IRQ_DC1176_GIC_START + 14) -#define IRQ_DC1176_CLCD (IRQ_DC1176_GIC_START + 15) /* CLCD controller */ -#define IRQ_DC1176_GPIO0 (IRQ_DC1176_GIC_START + 16) -#define IRQ_DC1176_SSP (IRQ_DC1176_GIC_START + 17) /* SSP port */ -#define IRQ_DC1176_UART0 (IRQ_DC1176_GIC_START + 18) /* UART 0 on development chip */ -#define IRQ_DC1176_UART1 (IRQ_DC1176_GIC_START + 19) /* UART 1 on development chip */ -#define IRQ_DC1176_UART2 (IRQ_DC1176_GIC_START + 20) /* UART 2 on development chip */ -#define IRQ_DC1176_UART3 (IRQ_DC1176_GIC_START + 21) /* UART 3 on development chip */ - -#define IRQ_DC1176_PB_IRQ2 (IRQ_DC1176_GIC_START + 30) /* tile GIC */ -#define IRQ_DC1176_PB_IRQ1 (IRQ_DC1176_GIC_START + 31) /* main GIC */ - -/* - * RealView PB1176 interrupt sources (secondary GIC) - */ -#define IRQ_PB1176_MMCI0A (IRQ_PB1176_GIC_START + 1) /* Multimedia Card 0A */ -#define IRQ_PB1176_MMCI0B (IRQ_PB1176_GIC_START + 2) /* Multimedia Card 0A */ -#define IRQ_PB1176_KMI0 (IRQ_PB1176_GIC_START + 3) /* Keyboard/Mouse port 0 */ -#define IRQ_PB1176_KMI1 (IRQ_PB1176_GIC_START + 4) /* Keyboard/Mouse port 1 */ -#define IRQ_PB1176_SCI (IRQ_PB1176_GIC_START + 5) -#define IRQ_PB1176_UART4 (IRQ_PB1176_GIC_START + 6) /* UART 4 on baseboard */ -#define IRQ_PB1176_CHARLCD (IRQ_PB1176_GIC_START + 7) /* Character LCD */ -#define IRQ_PB1176_GPIO1 (IRQ_PB1176_GIC_START + 8) -#define IRQ_PB1176_GPIO2 (IRQ_PB1176_GIC_START + 9) -#define IRQ_PB1176_ETH (IRQ_PB1176_GIC_START + 10) /* Ethernet controller */ -#define IRQ_PB1176_USB (IRQ_PB1176_GIC_START + 11) /* USB controller */ - -#define IRQ_PB1176_PISMO (IRQ_PB1176_GIC_START + 16) - -#define IRQ_PB1176_AACI (IRQ_PB1176_GIC_START + 19) /* Audio Codec */ - -#define IRQ_PB1176_TIMER0_1 (IRQ_PB1176_GIC_START + 22) -#define IRQ_PB1176_TIMER2_3 (IRQ_PB1176_GIC_START + 23) -#define IRQ_PB1176_DMAC (IRQ_PB1176_GIC_START + 24) /* DMA controller */ -#define IRQ_PB1176_RTC (IRQ_PB1176_GIC_START + 25) /* Real Time Clock */ - -#define IRQ_PB1176_SCTL -1 - -#endif /* __MACH_IRQS_PB1176_H */ diff --git a/arch/arm/mach-realview/irqs-pb11mp.h b/arch/arm/mach-realview/irqs-pb11mp.h deleted file mode 100644 index 938898a3df9f..000000000000 --- a/arch/arm/mach-realview/irqs-pb11mp.h +++ /dev/null @@ -1,97 +0,0 @@ -/* - * Copyright (C) 2008 ARM Limited - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301, USA. - */ - -#ifndef __MACH_IRQS_PB11MP_H -#define __MACH_IRQS_PB11MP_H - -#define IRQ_LOCALTIMER 29 -#define IRQ_TC11MP_GIC_START 32 -#define IRQ_PB11MP_GIC_START 64 - -/* - * ARM11MPCore test chip interrupt sources (primary GIC on the test chip) - */ -#define IRQ_TC11MP_AACI (IRQ_TC11MP_GIC_START + 0) -#define IRQ_TC11MP_TIMER0_1 (IRQ_TC11MP_GIC_START + 1) -#define IRQ_TC11MP_TIMER2_3 (IRQ_TC11MP_GIC_START + 2) -#define IRQ_TC11MP_USB (IRQ_TC11MP_GIC_START + 3) -#define IRQ_TC11MP_UART0 (IRQ_TC11MP_GIC_START + 4) -#define IRQ_TC11MP_UART1 (IRQ_TC11MP_GIC_START + 5) -#define IRQ_TC11MP_RTC (IRQ_TC11MP_GIC_START + 6) -#define IRQ_TC11MP_KMI0 (IRQ_TC11MP_GIC_START + 7) -#define IRQ_TC11MP_KMI1 (IRQ_TC11MP_GIC_START + 8) -#define IRQ_TC11MP_ETH (IRQ_TC11MP_GIC_START + 9) -#define IRQ_TC11MP_PB_IRQ1 (IRQ_TC11MP_GIC_START + 10) /* main GIC */ -#define IRQ_TC11MP_PB_IRQ2 (IRQ_TC11MP_GIC_START + 11) /* tile GIC */ -#define IRQ_TC11MP_PB_FIQ1 (IRQ_TC11MP_GIC_START + 12) /* main GIC */ -#define IRQ_TC11MP_PB_FIQ2 (IRQ_TC11MP_GIC_START + 13) /* tile GIC */ -#define IRQ_TC11MP_MMCI0A (IRQ_TC11MP_GIC_START + 14) -#define IRQ_TC11MP_MMCI0B (IRQ_TC11MP_GIC_START + 15) - -#define IRQ_TC11MP_PMU_CPU0 (IRQ_TC11MP_GIC_START + 17) -#define IRQ_TC11MP_PMU_CPU1 (IRQ_TC11MP_GIC_START + 18) -#define IRQ_TC11MP_PMU_CPU2 (IRQ_TC11MP_GIC_START + 19) -#define IRQ_TC11MP_PMU_CPU3 (IRQ_TC11MP_GIC_START + 20) -#define IRQ_TC11MP_PMU_SCU0 (IRQ_TC11MP_GIC_START + 21) -#define IRQ_TC11MP_PMU_SCU1 (IRQ_TC11MP_GIC_START + 22) -#define IRQ_TC11MP_PMU_SCU2 (IRQ_TC11MP_GIC_START + 23) -#define IRQ_TC11MP_PMU_SCU3 (IRQ_TC11MP_GIC_START + 24) -#define IRQ_TC11MP_PMU_SCU4 (IRQ_TC11MP_GIC_START + 25) -#define IRQ_TC11MP_PMU_SCU5 (IRQ_TC11MP_GIC_START + 26) -#define IRQ_TC11MP_PMU_SCU6 (IRQ_TC11MP_GIC_START + 27) -#define IRQ_TC11MP_PMU_SCU7 (IRQ_TC11MP_GIC_START + 28) - -#define IRQ_TC11MP_L220_EVENT (IRQ_TC11MP_GIC_START + 29) -#define IRQ_TC11MP_L220_SLAVE (IRQ_TC11MP_GIC_START + 30) -#define IRQ_TC11MP_L220_DECODE (IRQ_TC11MP_GIC_START + 31) - -/* - * RealView PB11MPCore GIC interrupt sources (secondary GIC on the board) - */ -#define IRQ_PB11MP_WATCHDOG (IRQ_PB11MP_GIC_START + 0) /* Watchdog timer */ -#define IRQ_PB11MP_SOFT (IRQ_PB11MP_GIC_START + 1) /* Software interrupt */ -#define IRQ_PB11MP_COMMRx (IRQ_PB11MP_GIC_START + 2) /* Debug Comm Rx interrupt */ -#define IRQ_PB11MP_COMMTx (IRQ_PB11MP_GIC_START + 3) /* Debug Comm Tx interrupt */ -#define IRQ_PB11MP_GPIO0 (IRQ_PB11MP_GIC_START + 6) /* GPIO 0 */ -#define IRQ_PB11MP_GPIO1 (IRQ_PB11MP_GIC_START + 7) /* GPIO 1 */ -#define IRQ_PB11MP_GPIO2 (IRQ_PB11MP_GIC_START + 8) /* GPIO 2 */ - /* 9 reserved */ -#define IRQ_PB11MP_RTC_GIC1 (IRQ_PB11MP_GIC_START + 10) /* Real Time Clock */ -#define IRQ_PB11MP_SSP (IRQ_PB11MP_GIC_START + 11) /* Synchronous Serial Port */ -#define IRQ_PB11MP_UART0_GIC1 (IRQ_PB11MP_GIC_START + 12) /* UART 0 on development chip */ -#define IRQ_PB11MP_UART1_GIC1 (IRQ_PB11MP_GIC_START + 13) /* UART 1 on development chip */ -#define IRQ_PB11MP_UART2 (IRQ_PB11MP_GIC_START + 14) /* UART 2 on development chip */ -#define IRQ_PB11MP_UART3 (IRQ_PB11MP_GIC_START + 15) /* UART 3 on development chip */ -#define IRQ_PB11MP_SCI (IRQ_PB11MP_GIC_START + 16) /* Smart Card Interface */ -#define IRQ_PB11MP_MMCI0A_GIC1 (IRQ_PB11MP_GIC_START + 17) /* Multimedia Card 0A */ -#define IRQ_PB11MP_MMCI0B_GIC1 (IRQ_PB11MP_GIC_START + 18) /* Multimedia Card 0B */ -#define IRQ_PB11MP_AACI_GIC1 (IRQ_PB11MP_GIC_START + 19) /* Audio Codec */ -#define IRQ_PB11MP_KMI0_GIC1 (IRQ_PB11MP_GIC_START + 20) /* Keyboard/Mouse port 0 */ -#define IRQ_PB11MP_KMI1_GIC1 (IRQ_PB11MP_GIC_START + 21) /* Keyboard/Mouse port 1 */ -#define IRQ_PB11MP_CHARLCD (IRQ_PB11MP_GIC_START + 22) /* Character LCD */ -#define IRQ_PB11MP_CLCD (IRQ_PB11MP_GIC_START + 23) /* CLCD controller */ -#define IRQ_PB11MP_DMAC (IRQ_PB11MP_GIC_START + 24) /* DMA controller */ -#define IRQ_PB11MP_PWRFAIL (IRQ_PB11MP_GIC_START + 25) /* Power failure */ -#define IRQ_PB11MP_PISMO (IRQ_PB11MP_GIC_START + 26) /* PISMO interface */ -#define IRQ_PB11MP_DoC (IRQ_PB11MP_GIC_START + 27) /* Disk on Chip memory controller */ -#define IRQ_PB11MP_ETH_GIC1 (IRQ_PB11MP_GIC_START + 28) /* Ethernet controller */ -#define IRQ_PB11MP_USB_GIC1 (IRQ_PB11MP_GIC_START + 29) /* USB controller */ -#define IRQ_PB11MP_TSPEN (IRQ_PB11MP_GIC_START + 30) /* Touchscreen pen */ -#define IRQ_PB11MP_TSKPAD (IRQ_PB11MP_GIC_START + 31) /* Touchscreen keypad */ - -#endif /* __MACH_IRQS_PB11MP_H */ diff --git a/arch/arm/mach-realview/irqs-pba8.h b/arch/arm/mach-realview/irqs-pba8.h deleted file mode 100644 index 262e321938b8..000000000000 --- a/arch/arm/mach-realview/irqs-pba8.h +++ /dev/null @@ -1,71 +0,0 @@ -/* - * Copyright (C) 2008 ARM Limited - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301, USA. - */ - -#ifndef __MACH_IRQS_PBA8_H -#define __MACH_IRQS_PBA8_H - -#define IRQ_PBA8_GIC_START 32 - -/* - * PB-A8 on-board gic irq sources - */ -#define IRQ_PBA8_WATCHDOG (IRQ_PBA8_GIC_START + 0) /* Watchdog timer */ -#define IRQ_PBA8_SOFT (IRQ_PBA8_GIC_START + 1) /* Software interrupt */ -#define IRQ_PBA8_COMMRx (IRQ_PBA8_GIC_START + 2) /* Debug Comm Rx interrupt */ -#define IRQ_PBA8_COMMTx (IRQ_PBA8_GIC_START + 3) /* Debug Comm Tx interrupt */ -#define IRQ_PBA8_TIMER0_1 (IRQ_PBA8_GIC_START + 4) /* Timer 0/1 (default timer) */ -#define IRQ_PBA8_TIMER2_3 (IRQ_PBA8_GIC_START + 5) /* Timer 2/3 */ -#define IRQ_PBA8_GPIO0 (IRQ_PBA8_GIC_START + 6) /* GPIO 0 */ -#define IRQ_PBA8_GPIO1 (IRQ_PBA8_GIC_START + 7) /* GPIO 1 */ -#define IRQ_PBA8_GPIO2 (IRQ_PBA8_GIC_START + 8) /* GPIO 2 */ - /* 9 reserved */ -#define IRQ_PBA8_RTC (IRQ_PBA8_GIC_START + 10) /* Real Time Clock */ -#define IRQ_PBA8_SSP (IRQ_PBA8_GIC_START + 11) /* Synchronous Serial Port */ -#define IRQ_PBA8_UART0 (IRQ_PBA8_GIC_START + 12) /* UART 0 on development chip */ -#define IRQ_PBA8_UART1 (IRQ_PBA8_GIC_START + 13) /* UART 1 on development chip */ -#define IRQ_PBA8_UART2 (IRQ_PBA8_GIC_START + 14) /* UART 2 on development chip */ -#define IRQ_PBA8_UART3 (IRQ_PBA8_GIC_START + 15) /* UART 3 on development chip */ -#define IRQ_PBA8_SCI (IRQ_PBA8_GIC_START + 16) /* Smart Card Interface */ -#define IRQ_PBA8_MMCI0A (IRQ_PBA8_GIC_START + 17) /* Multimedia Card 0A */ -#define IRQ_PBA8_MMCI0B (IRQ_PBA8_GIC_START + 18) /* Multimedia Card 0B */ -#define IRQ_PBA8_AACI (IRQ_PBA8_GIC_START + 19) /* Audio Codec */ -#define IRQ_PBA8_KMI0 (IRQ_PBA8_GIC_START + 20) /* Keyboard/Mouse port 0 */ -#define IRQ_PBA8_KMI1 (IRQ_PBA8_GIC_START + 21) /* Keyboard/Mouse port 1 */ -#define IRQ_PBA8_CHARLCD (IRQ_PBA8_GIC_START + 22) /* Character LCD */ -#define IRQ_PBA8_CLCD (IRQ_PBA8_GIC_START + 23) /* CLCD controller */ -#define IRQ_PBA8_DMAC (IRQ_PBA8_GIC_START + 24) /* DMA controller */ -#define IRQ_PBA8_PWRFAIL (IRQ_PBA8_GIC_START + 25) /* Power failure */ -#define IRQ_PBA8_PISMO (IRQ_PBA8_GIC_START + 26) /* PISMO interface */ -#define IRQ_PBA8_DoC (IRQ_PBA8_GIC_START + 27) /* Disk on Chip memory controller */ -#define IRQ_PBA8_ETH (IRQ_PBA8_GIC_START + 28) /* Ethernet controller */ -#define IRQ_PBA8_USB (IRQ_PBA8_GIC_START + 29) /* USB controller */ -#define IRQ_PBA8_TSPEN (IRQ_PBA8_GIC_START + 30) /* Touchscreen pen */ -#define IRQ_PBA8_TSKPAD (IRQ_PBA8_GIC_START + 31) /* Touchscreen keypad */ - -#define IRQ_PBA8_PMU (IRQ_PBA8_GIC_START + 47) /* Cortex-A8 PMU */ - -/* ... */ -#define IRQ_PBA8_PCI0 (IRQ_PBA8_GIC_START + 50) -#define IRQ_PBA8_PCI1 (IRQ_PBA8_GIC_START + 51) -#define IRQ_PBA8_PCI2 (IRQ_PBA8_GIC_START + 52) -#define IRQ_PBA8_PCI3 (IRQ_PBA8_GIC_START + 53) - -#define IRQ_PBA8_SMC -1 -#define IRQ_PBA8_SCTL -1 - -#endif /* __MACH_IRQS_PBA8_H */ diff --git a/arch/arm/mach-realview/irqs-pbx.h b/arch/arm/mach-realview/irqs-pbx.h deleted file mode 100644 index 4ef0567dec32..000000000000 --- a/arch/arm/mach-realview/irqs-pbx.h +++ /dev/null @@ -1,87 +0,0 @@ -/* - * Copyright (C) 2009 ARM Limited - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef __MACH_IRQS_PBX_H -#define __MACH_IRQS_PBX_H - -#define IRQ_LOCALTIMER 29 -#define IRQ_PBX_GIC_START 32 - -/* - * PBX on-board gic irq sources - */ -#define IRQ_PBX_WATCHDOG (IRQ_PBX_GIC_START + 0) /* Watchdog timer */ -#define IRQ_PBX_SOFT (IRQ_PBX_GIC_START + 1) /* Software interrupt */ -#define IRQ_PBX_COMMRx (IRQ_PBX_GIC_START + 2) /* Debug Comm Rx interrupt */ -#define IRQ_PBX_COMMTx (IRQ_PBX_GIC_START + 3) /* Debug Comm Tx interrupt */ -#define IRQ_PBX_TIMER0_1 (IRQ_PBX_GIC_START + 4) /* Timer 0/1 (default timer) */ -#define IRQ_PBX_TIMER2_3 (IRQ_PBX_GIC_START + 5) /* Timer 2/3 */ -#define IRQ_PBX_GPIO0 (IRQ_PBX_GIC_START + 6) /* GPIO 0 */ -#define IRQ_PBX_GPIO1 (IRQ_PBX_GIC_START + 7) /* GPIO 1 */ -#define IRQ_PBX_GPIO2 (IRQ_PBX_GIC_START + 8) /* GPIO 2 */ - /* 9 reserved */ -#define IRQ_PBX_RTC (IRQ_PBX_GIC_START + 10) /* Real Time Clock */ -#define IRQ_PBX_SSP (IRQ_PBX_GIC_START + 11) /* Synchronous Serial Port */ -#define IRQ_PBX_UART0 (IRQ_PBX_GIC_START + 12) /* UART 0 on development chip */ -#define IRQ_PBX_UART1 (IRQ_PBX_GIC_START + 13) /* UART 1 on development chip */ -#define IRQ_PBX_UART2 (IRQ_PBX_GIC_START + 14) /* UART 2 on development chip */ -#define IRQ_PBX_UART3 (IRQ_PBX_GIC_START + 15) /* UART 3 on development chip */ -#define IRQ_PBX_SCI (IRQ_PBX_GIC_START + 16) /* Smart Card Interface */ -#define IRQ_PBX_MMCI0A (IRQ_PBX_GIC_START + 17) /* Multimedia Card 0A */ -#define IRQ_PBX_MMCI0B (IRQ_PBX_GIC_START + 18) /* Multimedia Card 0B */ -#define IRQ_PBX_AACI (IRQ_PBX_GIC_START + 19) /* Audio Codec */ -#define IRQ_PBX_KMI0 (IRQ_PBX_GIC_START + 20) /* Keyboard/Mouse port 0 */ -#define IRQ_PBX_KMI1 (IRQ_PBX_GIC_START + 21) /* Keyboard/Mouse port 1 */ -#define IRQ_PBX_CHARLCD (IRQ_PBX_GIC_START + 22) /* Character LCD */ -#define IRQ_PBX_CLCD (IRQ_PBX_GIC_START + 23) /* CLCD controller */ -#define IRQ_PBX_DMAC (IRQ_PBX_GIC_START + 24) /* DMA controller */ -#define IRQ_PBX_PWRFAIL (IRQ_PBX_GIC_START + 25) /* Power failure */ -#define IRQ_PBX_PISMO (IRQ_PBX_GIC_START + 26) /* PISMO interface */ -#define IRQ_PBX_DoC (IRQ_PBX_GIC_START + 27) /* Disk on Chip memory controller */ -#define IRQ_PBX_ETH (IRQ_PBX_GIC_START + 28) /* Ethernet controller */ -#define IRQ_PBX_USB (IRQ_PBX_GIC_START + 29) /* USB controller */ -#define IRQ_PBX_TSPEN (IRQ_PBX_GIC_START + 30) /* Touchscreen pen */ -#define IRQ_PBX_TSKPAD (IRQ_PBX_GIC_START + 31) /* Touchscreen keypad */ - -#define IRQ_PBX_PMU_SCU0 (IRQ_PBX_GIC_START + 32) /* SCU PMU Interrupts (11mp) */ -#define IRQ_PBX_PMU_SCU1 (IRQ_PBX_GIC_START + 33) -#define IRQ_PBX_PMU_SCU2 (IRQ_PBX_GIC_START + 34) -#define IRQ_PBX_PMU_SCU3 (IRQ_PBX_GIC_START + 35) -#define IRQ_PBX_PMU_SCU4 (IRQ_PBX_GIC_START + 36) -#define IRQ_PBX_PMU_SCU5 (IRQ_PBX_GIC_START + 37) -#define IRQ_PBX_PMU_SCU6 (IRQ_PBX_GIC_START + 38) -#define IRQ_PBX_PMU_SCU7 (IRQ_PBX_GIC_START + 39) - -#define IRQ_PBX_WATCHDOG1 (IRQ_PBX_GIC_START + 40) /* Watchdog1 timer */ -#define IRQ_PBX_TIMER4_5 (IRQ_PBX_GIC_START + 41) /* Timer 0/1 (default timer) */ -#define IRQ_PBX_TIMER6_7 (IRQ_PBX_GIC_START + 42) /* Timer 2/3 */ -/* ... */ -#define IRQ_PBX_PMU_CPU0 (IRQ_PBX_GIC_START + 44) /* CPU PMU Interrupts */ -#define IRQ_PBX_PMU_CPU1 (IRQ_PBX_GIC_START + 45) -#define IRQ_PBX_PMU_CPU2 (IRQ_PBX_GIC_START + 46) -#define IRQ_PBX_PMU_CPU3 (IRQ_PBX_GIC_START + 47) - -/* ... */ -#define IRQ_PBX_PCI0 (IRQ_PBX_GIC_START + 50) -#define IRQ_PBX_PCI1 (IRQ_PBX_GIC_START + 51) -#define IRQ_PBX_PCI2 (IRQ_PBX_GIC_START + 52) -#define IRQ_PBX_PCI3 (IRQ_PBX_GIC_START + 53) - -#define IRQ_PBX_SMC -1 -#define IRQ_PBX_SCTL -1 - -#endif /* __MACH_IRQS_PBX_H */ diff --git a/arch/arm/mach-realview/platform.h b/arch/arm/mach-realview/platform.h deleted file mode 100644 index 11121739d371..000000000000 --- a/arch/arm/mach-realview/platform.h +++ /dev/null @@ -1,247 +0,0 @@ -/* - * Copyright (c) ARM Limited 2003. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef __ASM_ARCH_PLATFORM_H -#define __ASM_ARCH_PLATFORM_H - -/* - * Memory definitions - */ -#define REALVIEW_BOOT_ROM_LO 0x30000000 /* DoC Base (64Mb)...*/ -#define REALVIEW_BOOT_ROM_HI 0x30000000 -#define REALVIEW_BOOT_ROM_BASE REALVIEW_BOOT_ROM_HI /* Normal position */ -#define REALVIEW_BOOT_ROM_SIZE SZ_64M - -#define REALVIEW_SSRAM_BASE /* REALVIEW_SSMC_BASE ? */ -#define REALVIEW_SSRAM_SIZE SZ_2M - -/* - * SDRAM - */ -#define REALVIEW_SDRAM_BASE 0x00000000 - -/* - * Logic expansion modules - * - */ - - -/* ------------------------------------------------------------------------ - * RealView Registers - * ------------------------------------------------------------------------ - * - */ -#define REALVIEW_SYS_ID_OFFSET 0x00 -#define REALVIEW_SYS_SW_OFFSET 0x04 -#define REALVIEW_SYS_LED_OFFSET 0x08 -#define REALVIEW_SYS_OSC0_OFFSET 0x0C - -#define REALVIEW_SYS_OSC1_OFFSET 0x10 -#define REALVIEW_SYS_OSC2_OFFSET 0x14 -#define REALVIEW_SYS_OSC3_OFFSET 0x18 -#define REALVIEW_SYS_OSC4_OFFSET 0x1C /* OSC1 for RealView/AB */ - -#define REALVIEW_SYS_LOCK_OFFSET 0x20 -#define REALVIEW_SYS_100HZ_OFFSET 0x24 -#define REALVIEW_SYS_CFGDATA1_OFFSET 0x28 -#define REALVIEW_SYS_CFGDATA2_OFFSET 0x2C -#define REALVIEW_SYS_FLAGS_OFFSET 0x30 -#define REALVIEW_SYS_FLAGSSET_OFFSET 0x30 -#define REALVIEW_SYS_FLAGSCLR_OFFSET 0x34 -#define REALVIEW_SYS_NVFLAGS_OFFSET 0x38 -#define REALVIEW_SYS_NVFLAGSSET_OFFSET 0x38 -#define REALVIEW_SYS_NVFLAGSCLR_OFFSET 0x3C -#define REALVIEW_SYS_RESETCTL_OFFSET 0x40 -#define REALVIEW_SYS_PCICTL_OFFSET 0x44 -#define REALVIEW_SYS_MCI_OFFSET 0x48 -#define REALVIEW_SYS_FLASH_OFFSET 0x4C -#define REALVIEW_SYS_CLCD_OFFSET 0x50 -#define REALVIEW_SYS_CLCDSER_OFFSET 0x54 -#define REALVIEW_SYS_BOOTCS_OFFSET 0x58 -#define REALVIEW_SYS_24MHz_OFFSET 0x5C -#define REALVIEW_SYS_MISC_OFFSET 0x60 -#define REALVIEW_SYS_IOSEL_OFFSET 0x70 -#define REALVIEW_SYS_PROCID_OFFSET 0x84 -#define REALVIEW_SYS_TEST_OSC0_OFFSET 0xC0 -#define REALVIEW_SYS_TEST_OSC1_OFFSET 0xC4 -#define REALVIEW_SYS_TEST_OSC2_OFFSET 0xC8 -#define REALVIEW_SYS_TEST_OSC3_OFFSET 0xCC -#define REALVIEW_SYS_TEST_OSC4_OFFSET 0xD0 - -#define REALVIEW_SYS_BASE 0x10000000 -#define REALVIEW_SYS_ID (REALVIEW_SYS_BASE + REALVIEW_SYS_ID_OFFSET) -#define REALVIEW_SYS_SW (REALVIEW_SYS_BASE + REALVIEW_SYS_SW_OFFSET) -#define REALVIEW_SYS_LED (REALVIEW_SYS_BASE + REALVIEW_SYS_LED_OFFSET) -#define REALVIEW_SYS_OSC0 (REALVIEW_SYS_BASE + REALVIEW_SYS_OSC0_OFFSET) -#define REALVIEW_SYS_OSC1 (REALVIEW_SYS_BASE + REALVIEW_SYS_OSC1_OFFSET) - -#define REALVIEW_SYS_LOCK (REALVIEW_SYS_BASE + REALVIEW_SYS_LOCK_OFFSET) -#define REALVIEW_SYS_100HZ (REALVIEW_SYS_BASE + REALVIEW_SYS_100HZ_OFFSET) -#define REALVIEW_SYS_CFGDATA1 (REALVIEW_SYS_BASE + REALVIEW_SYS_CFGDATA1_OFFSET) -#define REALVIEW_SYS_CFGDATA2 (REALVIEW_SYS_BASE + REALVIEW_SYS_CFGDATA2_OFFSET) -#define REALVIEW_SYS_FLAGS (REALVIEW_SYS_BASE + REALVIEW_SYS_FLAGS_OFFSET) -#define REALVIEW_SYS_FLAGSSET (REALVIEW_SYS_BASE + REALVIEW_SYS_FLAGSSET_OFFSET) -#define REALVIEW_SYS_FLAGSCLR (REALVIEW_SYS_BASE + REALVIEW_SYS_FLAGSCLR_OFFSET) -#define REALVIEW_SYS_NVFLAGS (REALVIEW_SYS_BASE + REALVIEW_SYS_NVFLAGS_OFFSET) -#define REALVIEW_SYS_NVFLAGSSET (REALVIEW_SYS_BASE + REALVIEW_SYS_NVFLAGSSET_OFFSET) -#define REALVIEW_SYS_NVFLAGSCLR (REALVIEW_SYS_BASE + REALVIEW_SYS_NVFLAGSCLR_OFFSET) -#define REALVIEW_SYS_RESETCTL (REALVIEW_SYS_BASE + REALVIEW_SYS_RESETCTL_OFFSET) -#define REALVIEW_SYS_PCICTL (REALVIEW_SYS_BASE + REALVIEW_SYS_PCICTL_OFFSET) -#define REALVIEW_SYS_MCI (REALVIEW_SYS_BASE + REALVIEW_SYS_MCI_OFFSET) -#define REALVIEW_SYS_FLASH (REALVIEW_SYS_BASE + REALVIEW_SYS_FLASH_OFFSET) -#define REALVIEW_SYS_CLCD (REALVIEW_SYS_BASE + REALVIEW_SYS_CLCD_OFFSET) -#define REALVIEW_SYS_CLCDSER (REALVIEW_SYS_BASE + REALVIEW_SYS_CLCDSER_OFFSET) -#define REALVIEW_SYS_BOOTCS (REALVIEW_SYS_BASE + REALVIEW_SYS_BOOTCS_OFFSET) -#define REALVIEW_SYS_24MHz (REALVIEW_SYS_BASE + REALVIEW_SYS_24MHz_OFFSET) -#define REALVIEW_SYS_MISC (REALVIEW_SYS_BASE + REALVIEW_SYS_MISC_OFFSET) -#define REALVIEW_SYS_IOSEL (REALVIEW_SYS_BASE + REALVIEW_SYS_IOSEL_OFFSET) -#define REALVIEW_SYS_PROCID (REALVIEW_SYS_BASE + REALVIEW_SYS_PROCID_OFFSET) -#define REALVIEW_SYS_TEST_OSC0 (REALVIEW_SYS_BASE + REALVIEW_SYS_TEST_OSC0_OFFSET) -#define REALVIEW_SYS_TEST_OSC1 (REALVIEW_SYS_BASE + REALVIEW_SYS_TEST_OSC1_OFFSET) -#define REALVIEW_SYS_TEST_OSC2 (REALVIEW_SYS_BASE + REALVIEW_SYS_TEST_OSC2_OFFSET) -#define REALVIEW_SYS_TEST_OSC3 (REALVIEW_SYS_BASE + REALVIEW_SYS_TEST_OSC3_OFFSET) -#define REALVIEW_SYS_TEST_OSC4 (REALVIEW_SYS_BASE + REALVIEW_SYS_TEST_OSC4_OFFSET) - -/* ------------------------------------------------------------------------ - * RealView control registers - * ------------------------------------------------------------------------ - */ - -/* - * REALVIEW_IDFIELD - * - * 31:24 = manufacturer (0x41 = ARM) - * 23:16 = architecture (0x08 = AHB system bus, ASB processor bus) - * 15:12 = FPGA (0x3 = XVC600 or XVC600E) - * 11:4 = build value - * 3:0 = revision number (0x1 = rev B (AHB)) - */ - -/* - * REALVIEW_SYS_LOCK - * control access to SYS_OSCx, SYS_CFGDATAx, SYS_RESETCTL, - * SYS_CLD, SYS_BOOTCS - */ -#define REALVIEW_SYS_LOCK_LOCKED (1 << 16) -#define REALVIEW_SYS_LOCK_VAL 0xA05F /* Enable write access */ - -/* - * REALVIEW_SYS_FLASH - */ -#define REALVIEW_FLASHPROG_FLVPPEN (1 << 0) /* Enable writing to flash */ - -/* - * REALVIEW_INTREG - * - used to acknowledge and control MMCI and UART interrupts - */ -#define REALVIEW_INTREG_WPROT 0x00 /* MMC protection status (no interrupt generated) */ -#define REALVIEW_INTREG_RI0 0x01 /* Ring indicator UART0 is asserted, */ -#define REALVIEW_INTREG_CARDIN 0x08 /* MMCI card in detect */ - /* write 1 to acknowledge and clear */ -#define REALVIEW_INTREG_RI1 0x02 /* Ring indicator UART1 is asserted, */ -#define REALVIEW_INTREG_CARDINSERT 0x03 /* Signal insertion of MMC card */ - -/* - * RealView common peripheral addresses - */ -#define REALVIEW_SCTL_BASE 0x10001000 /* System controller */ -#define REALVIEW_I2C_BASE 0x10002000 /* I2C control */ -#define REALVIEW_AACI_BASE 0x10004000 /* Audio */ -#define REALVIEW_MMCI0_BASE 0x10005000 /* MMC interface */ -#define REALVIEW_KMI0_BASE 0x10006000 /* KMI interface */ -#define REALVIEW_KMI1_BASE 0x10007000 /* KMI 2nd interface */ -#define REALVIEW_CHAR_LCD_BASE 0x10008000 /* Character LCD */ -#define REALVIEW_SCI_BASE 0x1000E000 /* Smart card controller */ -#define REALVIEW_GPIO1_BASE 0x10014000 /* GPIO port 1 */ -#define REALVIEW_GPIO2_BASE 0x10015000 /* GPIO port 2 */ -#define REALVIEW_DMC_BASE 0x10018000 /* DMC configuration */ -#define REALVIEW_DMAC_BASE 0x10030000 /* DMA controller */ - -/* PCI space */ -#define REALVIEW_PCI_BASE 0x41000000 /* PCI Interface */ -#define REALVIEW_PCI_CFG_BASE 0x42000000 -#define REALVIEW_PCI_MEM_BASE0 0x44000000 -#define REALVIEW_PCI_MEM_BASE1 0x50000000 -#define REALVIEW_PCI_MEM_BASE2 0x60000000 -/* Sizes of above maps */ -#define REALVIEW_PCI_BASE_SIZE 0x01000000 -#define REALVIEW_PCI_CFG_BASE_SIZE 0x02000000 -#define REALVIEW_PCI_MEM_BASE0_SIZE 0x0c000000 /* 32Mb */ -#define REALVIEW_PCI_MEM_BASE1_SIZE 0x10000000 /* 256Mb */ -#define REALVIEW_PCI_MEM_BASE2_SIZE 0x10000000 /* 256Mb */ - -#define REALVIEW_SDRAM67_BASE 0x70000000 /* SDRAM banks 6 and 7 */ -#define REALVIEW_LT_BASE 0x80000000 /* Logic Tile expansion */ - -/* - * CompactFlash - */ -#define REALVIEW_CF_BASE 0x18000000 /* CompactFlash */ -#define REALVIEW_CF_MEM_BASE 0x18003000 /* SMC for CompactFlash */ - -/* - * Disk on Chip - */ -#define REALVIEW_DOC_BASE 0x2C000000 -#define REALVIEW_DOC_SIZE (16 << 20) -#define REALVIEW_DOC_PAGE_SIZE 512 -#define REALVIEW_DOC_TOTAL_PAGES (DOC_SIZE / PAGE_SIZE) - -#define ERASE_UNIT_PAGES 32 -#define START_PAGE 0x80 - -/* - * LED settings, bits [7:0] - */ -#define REALVIEW_SYS_LED0 (1 << 0) -#define REALVIEW_SYS_LED1 (1 << 1) -#define REALVIEW_SYS_LED2 (1 << 2) -#define REALVIEW_SYS_LED3 (1 << 3) -#define REALVIEW_SYS_LED4 (1 << 4) -#define REALVIEW_SYS_LED5 (1 << 5) -#define REALVIEW_SYS_LED6 (1 << 6) -#define REALVIEW_SYS_LED7 (1 << 7) - -#define ALL_LEDS 0xFF - -#define LED_BANK REALVIEW_SYS_LED - -/* - * Control registers - */ -#define REALVIEW_IDFIELD_OFFSET 0x0 /* RealView build information */ -#define REALVIEW_FLASHPROG_OFFSET 0x4 /* Flash devices */ -#define REALVIEW_INTREG_OFFSET 0x8 /* Interrupt control */ -#define REALVIEW_DECODE_OFFSET 0xC /* Fitted logic modules */ - -/* - * System controller bit assignment - */ -#define REALVIEW_REFCLK 0 -#define REALVIEW_TIMCLK 1 - -#define REALVIEW_TIMER1_EnSel 15 -#define REALVIEW_TIMER2_EnSel 17 -#define REALVIEW_TIMER3_EnSel 19 -#define REALVIEW_TIMER4_EnSel 21 - - -#define REALVIEW_CSR_BASE 0x10000000 -#define REALVIEW_CSR_SIZE 0x10000000 - -#endif /* __ASM_ARCH_PLATFORM_H */ diff --git a/arch/arm/mach-realview/platsmp-dt.c b/arch/arm/mach-realview/platsmp-dt.c index 6964e8876061..70ca99eb52c6 100644 --- a/arch/arm/mach-realview/platsmp-dt.c +++ b/arch/arm/mach-realview/platsmp-dt.c @@ -17,8 +17,7 @@ #include <asm/smp_scu.h> #include <plat/platsmp.h> - -#include "core.h" +#include "hotplug.h" #define REALVIEW_SYS_FLAGSSET_OFFSET 0x30 diff --git a/arch/arm/mach-realview/platsmp.c b/arch/arm/mach-realview/platsmp.c deleted file mode 100644 index e8ab69c7abfb..000000000000 --- a/arch/arm/mach-realview/platsmp.c +++ /dev/null @@ -1,86 +0,0 @@ -/* - * linux/arch/arm/mach-realview/platsmp.c - * - * Copyright (C) 2002 ARM Ltd. - * All Rights Reserved - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/init.h> -#include <linux/errno.h> -#include <linux/smp.h> -#include <linux/io.h> - -#include "hardware.h" -#include <asm/mach-types.h> -#include <asm/smp_scu.h> - -#include "board-eb.h" -#include "board-pb11mp.h" -#include "board-pbx.h" - -#include <plat/platsmp.h> - -#include "core.h" - -static void __iomem *scu_base_addr(void) -{ - if (machine_is_realview_eb_mp()) - return __io_address(REALVIEW_EB11MP_SCU_BASE); - else if (machine_is_realview_pb11mp()) - return __io_address(REALVIEW_TC11MP_SCU_BASE); - else if (machine_is_realview_pbx() && - (core_tile_pbx11mp() || core_tile_pbxa9mp())) - return __io_address(REALVIEW_PBX_TILE_SCU_BASE); - else - return (void __iomem *)0; -} - -/* - * Initialise the CPU possible map early - this describes the CPUs - * which may be present or become present in the system. - */ -static void __init realview_smp_init_cpus(void) -{ - void __iomem *scu_base = scu_base_addr(); - unsigned int i, ncores; - - ncores = scu_base ? scu_get_core_count(scu_base) : 1; - - /* sanity check */ - if (ncores > nr_cpu_ids) { - pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", - ncores, nr_cpu_ids); - ncores = nr_cpu_ids; - } - - for (i = 0; i < ncores; i++) - set_cpu_possible(i, true); -} - -static void __init realview_smp_prepare_cpus(unsigned int max_cpus) -{ - - scu_enable(scu_base_addr()); - - /* - * Write the address of secondary startup into the - * system-wide flags register. The BootMonitor waits - * until it receives a soft interrupt, and then the - * secondary CPU branches to this address. - */ - __raw_writel(virt_to_phys(versatile_secondary_startup), - __io_address(REALVIEW_SYS_FLAGSSET)); -} - -const struct smp_operations realview_smp_ops __initconst = { - .smp_init_cpus = realview_smp_init_cpus, - .smp_prepare_cpus = realview_smp_prepare_cpus, - .smp_secondary_init = versatile_secondary_init, - .smp_boot_secondary = versatile_boot_secondary, -#ifdef CONFIG_HOTPLUG_CPU - .cpu_die = realview_cpu_die, -#endif -}; diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c deleted file mode 100644 index b442fa61e943..000000000000 --- a/arch/arm/mach-realview/realview_eb.c +++ /dev/null @@ -1,492 +0,0 @@ -/* - * linux/arch/arm/mach-realview/realview_eb.c - * - * Copyright (C) 2004 ARM Limited - * Copyright (C) 2000 Deep Blue Solutions Ltd - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/init.h> -#include <linux/platform_device.h> -#include <linux/device.h> -#include <linux/amba/bus.h> -#include <linux/amba/pl061.h> -#include <linux/amba/mmci.h> -#include <linux/amba/pl022.h> -#include <linux/io.h> -#include <linux/irqchip/arm-gic.h> -#include <linux/platform_data/clk-realview.h> -#include <linux/reboot.h> - -#include "hardware.h" -#include <asm/irq.h> -#include <asm/mach-types.h> -#include <asm/pgtable.h> -#include <asm/hardware/cache-l2x0.h> -#include <asm/smp_twd.h> -#include <asm/system_info.h> -#include <asm/outercache.h> - -#include <asm/mach/arch.h> -#include <asm/mach/map.h> -#include <asm/mach/time.h> - -#include "board-eb.h" -#include "irqs-eb.h" - -#include "core.h" - -static struct map_desc realview_eb_io_desc[] __initdata = { - { - .virtual = IO_ADDRESS(REALVIEW_SYS_BASE), - .pfn = __phys_to_pfn(REALVIEW_SYS_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_EB_GIC_CPU_BASE), - .pfn = __phys_to_pfn(REALVIEW_EB_GIC_CPU_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_EB_GIC_DIST_BASE), - .pfn = __phys_to_pfn(REALVIEW_EB_GIC_DIST_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_SCTL_BASE), - .pfn = __phys_to_pfn(REALVIEW_SCTL_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_EB_TIMER0_1_BASE), - .pfn = __phys_to_pfn(REALVIEW_EB_TIMER0_1_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_EB_TIMER2_3_BASE), - .pfn = __phys_to_pfn(REALVIEW_EB_TIMER2_3_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, -#ifdef CONFIG_DEBUG_LL - { - .virtual = IO_ADDRESS(REALVIEW_EB_UART0_BASE), - .pfn = __phys_to_pfn(REALVIEW_EB_UART0_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - } -#endif -}; - -static struct map_desc realview_eb11mp_io_desc[] __initdata = { - { - .virtual = IO_ADDRESS(REALVIEW_EB11MP_PRIV_MEM_BASE), - .pfn = __phys_to_pfn(REALVIEW_EB11MP_PRIV_MEM_BASE), - .length = REALVIEW_EB11MP_PRIV_MEM_SIZE, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_EB11MP_L220_BASE), - .pfn = __phys_to_pfn(REALVIEW_EB11MP_L220_BASE), - .length = SZ_8K, - .type = MT_DEVICE, - } -}; - -static void __init realview_eb_map_io(void) -{ - iotable_init(realview_eb_io_desc, ARRAY_SIZE(realview_eb_io_desc)); - if (core_tile_eb11mp() || core_tile_a9mp()) - iotable_init(realview_eb11mp_io_desc, ARRAY_SIZE(realview_eb11mp_io_desc)); -} - -static struct pl061_platform_data gpio0_plat_data = { - .gpio_base = 0, -}; - -static struct pl061_platform_data gpio1_plat_data = { - .gpio_base = 8, -}; - -static struct pl061_platform_data gpio2_plat_data = { - .gpio_base = 16, -}; - -static struct pl022_ssp_controller ssp0_plat_data = { - .bus_id = 0, - .enable_dma = 0, - .num_chipselect = 1, -}; - -/* - * RealView EB AMBA devices - */ - -/* - * These devices are connected via the core APB bridge - */ -#define GPIO2_IRQ { IRQ_EB_GPIO2 } -#define GPIO3_IRQ { IRQ_EB_GPIO3 } - -#define AACI_IRQ { IRQ_EB_AACI } -#define MMCI0_IRQ { IRQ_EB_MMCI0A, IRQ_EB_MMCI0B } -#define KMI0_IRQ { IRQ_EB_KMI0 } -#define KMI1_IRQ { IRQ_EB_KMI1 } - -/* - * These devices are connected directly to the multi-layer AHB switch - */ -#define EB_SMC_IRQ { } -#define MPMC_IRQ { } -#define EB_CLCD_IRQ { IRQ_EB_CLCD } -#define DMAC_IRQ { IRQ_EB_DMA } - -/* - * These devices are connected via the core APB bridge - */ -#define SCTL_IRQ { } -#define EB_WATCHDOG_IRQ { IRQ_EB_WDOG } -#define EB_GPIO0_IRQ { IRQ_EB_GPIO0 } -#define GPIO1_IRQ { IRQ_EB_GPIO1 } -#define EB_RTC_IRQ { IRQ_EB_RTC } - -/* - * These devices are connected via the DMA APB bridge - */ -#define SCI_IRQ { IRQ_EB_SCI } -#define EB_UART0_IRQ { IRQ_EB_UART0 } -#define EB_UART1_IRQ { IRQ_EB_UART1 } -#define EB_UART2_IRQ { IRQ_EB_UART2 } -#define EB_UART3_IRQ { IRQ_EB_UART3 } -#define EB_SSP_IRQ { IRQ_EB_SSP } - -/* FPGA Primecells */ -APB_DEVICE(aaci, "fpga:aaci", AACI, NULL); -APB_DEVICE(mmc0, "fpga:mmc0", MMCI0, &realview_mmc0_plat_data); -APB_DEVICE(kmi0, "fpga:kmi0", KMI0, NULL); -APB_DEVICE(kmi1, "fpga:kmi1", KMI1, NULL); -APB_DEVICE(uart3, "fpga:uart3", EB_UART3, NULL); - -/* DevChip Primecells */ -AHB_DEVICE(smc, "dev:smc", EB_SMC, NULL); -AHB_DEVICE(clcd, "dev:clcd", EB_CLCD, &clcd_plat_data); -AHB_DEVICE(dmac, "dev:dmac", DMAC, NULL); -AHB_DEVICE(sctl, "dev:sctl", SCTL, NULL); -APB_DEVICE(wdog, "dev:wdog", EB_WATCHDOG, NULL); -APB_DEVICE(gpio0, "dev:gpio0", EB_GPIO0, &gpio0_plat_data); -APB_DEVICE(gpio1, "dev:gpio1", GPIO1, &gpio1_plat_data); -APB_DEVICE(gpio2, "dev:gpio2", GPIO2, &gpio2_plat_data); -APB_DEVICE(rtc, "dev:rtc", EB_RTC, NULL); -APB_DEVICE(sci0, "dev:sci0", SCI, NULL); -APB_DEVICE(uart0, "dev:uart0", EB_UART0, NULL); -APB_DEVICE(uart1, "dev:uart1", EB_UART1, NULL); -APB_DEVICE(uart2, "dev:uart2", EB_UART2, NULL); -APB_DEVICE(ssp0, "dev:ssp0", EB_SSP, &ssp0_plat_data); - -static struct amba_device *amba_devs[] __initdata = { - &dmac_device, - &uart0_device, - &uart1_device, - &uart2_device, - &uart3_device, - &smc_device, - &clcd_device, - &sctl_device, - &wdog_device, - &gpio0_device, - &gpio1_device, - &gpio2_device, - &rtc_device, - &sci0_device, - &ssp0_device, - &aaci_device, - &mmc0_device, - &kmi0_device, - &kmi1_device, -}; - -/* - * RealView EB platform devices - */ -static struct resource realview_eb_flash_resource = { - .start = REALVIEW_EB_FLASH_BASE, - .end = REALVIEW_EB_FLASH_BASE + REALVIEW_EB_FLASH_SIZE - 1, - .flags = IORESOURCE_MEM, -}; - -static struct resource realview_eb_eth_resources[] = { - [0] = { - .start = REALVIEW_EB_ETH_BASE, - .end = REALVIEW_EB_ETH_BASE + SZ_64K - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_EB_ETH, - .end = IRQ_EB_ETH, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE, - }, -}; - -/* - * Detect and register the correct Ethernet device. RealView/EB rev D - * platforms use the newer SMSC LAN9118 Ethernet chip - */ -static int eth_device_register(void) -{ - void __iomem *eth_addr = ioremap(REALVIEW_EB_ETH_BASE, SZ_4K); - const char *name = NULL; - u32 idrev; - - if (!eth_addr) - return -ENOMEM; - - idrev = readl(eth_addr + 0x50); - if ((idrev & 0xFFFF0000) != 0x01180000) - /* SMSC LAN9118 not present, use LAN91C111 instead */ - name = "smc91x"; - - iounmap(eth_addr); - return realview_eth_register(name, realview_eb_eth_resources); -} - -static struct resource realview_eb_isp1761_resources[] = { - [0] = { - .start = REALVIEW_EB_USB_BASE, - .end = REALVIEW_EB_USB_BASE + SZ_128K - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_EB_USB, - .end = IRQ_EB_USB, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource pmu_resources[] = { - [0] = { - .start = IRQ_EB11MP_PMU_CPU0, - .end = IRQ_EB11MP_PMU_CPU0, - .flags = IORESOURCE_IRQ, - }, - [1] = { - .start = IRQ_EB11MP_PMU_CPU1, - .end = IRQ_EB11MP_PMU_CPU1, - .flags = IORESOURCE_IRQ, - }, - [2] = { - .start = IRQ_EB11MP_PMU_CPU2, - .end = IRQ_EB11MP_PMU_CPU2, - .flags = IORESOURCE_IRQ, - }, - [3] = { - .start = IRQ_EB11MP_PMU_CPU3, - .end = IRQ_EB11MP_PMU_CPU3, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device pmu_device = { - .id = -1, - .num_resources = ARRAY_SIZE(pmu_resources), - .resource = pmu_resources, -}; - -static struct resource char_lcd_resources[] = { - { - .start = REALVIEW_CHAR_LCD_BASE, - .end = (REALVIEW_CHAR_LCD_BASE + SZ_4K - 1), - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_EB_CHARLCD, - .end = IRQ_EB_CHARLCD, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device char_lcd_device = { - .name = "arm-charlcd", - .id = -1, - .num_resources = ARRAY_SIZE(char_lcd_resources), - .resource = char_lcd_resources, -}; - -static void __init gic_init_irq(void) -{ - if (core_tile_eb11mp() || core_tile_a9mp()) { - unsigned int pldctrl; - - /* new irq mode */ - writel(0x0000a05f, __io_address(REALVIEW_SYS_LOCK)); - pldctrl = readl(__io_address(REALVIEW_SYS_BASE) + REALVIEW_EB11MP_SYS_PLD_CTRL1); - pldctrl |= 0x00800000; - writel(pldctrl, __io_address(REALVIEW_SYS_BASE) + REALVIEW_EB11MP_SYS_PLD_CTRL1); - writel(0x00000000, __io_address(REALVIEW_SYS_LOCK)); - - /* core tile GIC, primary */ - gic_init(0, 29, __io_address(REALVIEW_EB11MP_GIC_DIST_BASE), - __io_address(REALVIEW_EB11MP_GIC_CPU_BASE)); - -#ifndef CONFIG_REALVIEW_EB_ARM11MP_REVB - /* board GIC, secondary */ - gic_init(1, 96, __io_address(REALVIEW_EB_GIC_DIST_BASE), - __io_address(REALVIEW_EB_GIC_CPU_BASE)); - gic_cascade_irq(1, IRQ_EB11MP_EB_IRQ1); -#endif - } else { - /* board GIC, primary */ - gic_init(0, 29, __io_address(REALVIEW_EB_GIC_DIST_BASE), - __io_address(REALVIEW_EB_GIC_CPU_BASE)); - } -} - -/* - * Fix up the IRQ numbers for the RealView EB/ARM11MPCore tile - */ -static void realview_eb11mp_fixup(void) -{ - /* AMBA devices */ - dmac_device.irq[0] = IRQ_EB11MP_DMA; - uart0_device.irq[0] = IRQ_EB11MP_UART0; - uart1_device.irq[0] = IRQ_EB11MP_UART1; - uart2_device.irq[0] = IRQ_EB11MP_UART2; - uart3_device.irq[0] = IRQ_EB11MP_UART3; - clcd_device.irq[0] = IRQ_EB11MP_CLCD; - wdog_device.irq[0] = IRQ_EB11MP_WDOG; - gpio0_device.irq[0] = IRQ_EB11MP_GPIO0; - gpio1_device.irq[0] = IRQ_EB11MP_GPIO1; - gpio2_device.irq[0] = IRQ_EB11MP_GPIO2; - rtc_device.irq[0] = IRQ_EB11MP_RTC; - sci0_device.irq[0] = IRQ_EB11MP_SCI; - ssp0_device.irq[0] = IRQ_EB11MP_SSP; - aaci_device.irq[0] = IRQ_EB11MP_AACI; - mmc0_device.irq[0] = IRQ_EB11MP_MMCI0A; - mmc0_device.irq[1] = IRQ_EB11MP_MMCI0B; - kmi0_device.irq[0] = IRQ_EB11MP_KMI0; - kmi1_device.irq[0] = IRQ_EB11MP_KMI1; - - /* platform devices */ - realview_eb_eth_resources[1].start = IRQ_EB11MP_ETH; - realview_eb_eth_resources[1].end = IRQ_EB11MP_ETH; - realview_eb_isp1761_resources[1].start = IRQ_EB11MP_USB; - realview_eb_isp1761_resources[1].end = IRQ_EB11MP_USB; -} - -#ifdef CONFIG_HAVE_ARM_TWD -static DEFINE_TWD_LOCAL_TIMER(twd_local_timer, - REALVIEW_EB11MP_TWD_BASE, - IRQ_LOCALTIMER); - -static void __init realview_eb_twd_init(void) -{ - if (core_tile_eb11mp() || core_tile_a9mp()) { - int err = twd_local_timer_register(&twd_local_timer); - if (err) - pr_err("twd_local_timer_register failed %d\n", err); - } -} -#else -#define realview_eb_twd_init() do { } while(0) -#endif - -static void __init realview_eb_timer_init(void) -{ - unsigned int timer_irq; - - timer0_va_base = __io_address(REALVIEW_EB_TIMER0_1_BASE); - timer1_va_base = __io_address(REALVIEW_EB_TIMER0_1_BASE) + 0x20; - timer2_va_base = __io_address(REALVIEW_EB_TIMER2_3_BASE); - timer3_va_base = __io_address(REALVIEW_EB_TIMER2_3_BASE) + 0x20; - - if (core_tile_eb11mp() || core_tile_a9mp()) - timer_irq = IRQ_EB11MP_TIMER0_1; - else - timer_irq = IRQ_EB_TIMER0_1; - - realview_clk_init(__io_address(REALVIEW_SYS_BASE), false); - realview_timer_init(timer_irq); - realview_eb_twd_init(); -} - -static void realview_eb_restart(enum reboot_mode mode, const char *cmd) -{ - void __iomem *reset_ctrl = __io_address(REALVIEW_SYS_RESETCTL); - void __iomem *lock_ctrl = __io_address(REALVIEW_SYS_LOCK); - - /* - * To reset, we hit the on-board reset register - * in the system FPGA - */ - __raw_writel(REALVIEW_SYS_LOCK_VAL, lock_ctrl); - if (core_tile_eb11mp()) - __raw_writel(0x0008, reset_ctrl); - dsb(); -} - -static void __init realview_eb_init(void) -{ - int i; - - if (core_tile_eb11mp() || core_tile_a9mp()) { - realview_eb11mp_fixup(); - -#ifdef CONFIG_CACHE_L2X0 - /* - * The PL220 needs to be manually configured as the hardware - * doesn't report the correct sizes. - * 1MB (128KB/way), 8-way associativity, event monitor and - * parity enabled, ignore share bit, no force write allocate - * Bits: .... ...0 0111 1001 0000 .... .... .... - */ - l2x0_init(__io_address(REALVIEW_EB11MP_L220_BASE), 0x00790000, 0xfe000fff); - - /* - * due to a bug in the l220 cache controller, we must not call - * the sync function. stub it out here instead! - */ - outer_cache.sync = NULL; -#endif - pmu_device.name = core_tile_a9mp() ? "armv7-pmu" : "armv6-pmu"; - platform_device_register(&pmu_device); - } - - realview_flash_register(&realview_eb_flash_resource, 1); - platform_device_register(&realview_i2c_device); - platform_device_register(&char_lcd_device); - platform_device_register(&realview_leds_device); - eth_device_register(); - realview_usb_register(realview_eb_isp1761_resources); - - for (i = 0; i < ARRAY_SIZE(amba_devs); i++) { - struct amba_device *d = amba_devs[i]; - amba_device_register(d, &iomem_resource); - } -} - -MACHINE_START(REALVIEW_EB, "ARM-RealView EB") - /* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */ - .atag_offset = 0x100, - .smp = smp_ops(realview_smp_ops), - .fixup = realview_fixup, - .map_io = realview_eb_map_io, - .init_early = realview_init_early, - .init_irq = gic_init_irq, - .init_time = realview_eb_timer_init, - .init_machine = realview_eb_init, -#ifdef CONFIG_ZONE_DMA - .dma_zone_size = SZ_256M, -#endif - .restart = realview_eb_restart, -MACHINE_END diff --git a/arch/arm/mach-realview/realview_pb1176.c b/arch/arm/mach-realview/realview_pb1176.c deleted file mode 100644 index 537f3878d501..000000000000 --- a/arch/arm/mach-realview/realview_pb1176.c +++ /dev/null @@ -1,395 +0,0 @@ -/* - * linux/arch/arm/mach-realview/realview_pb1176.c - * - * Copyright (C) 2008 ARM Limited - * Copyright (C) 2000 Deep Blue Solutions Ltd - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/init.h> -#include <linux/platform_device.h> -#include <linux/device.h> -#include <linux/amba/bus.h> -#include <linux/amba/pl061.h> -#include <linux/amba/mmci.h> -#include <linux/amba/pl022.h> -#include <linux/mtd/physmap.h> -#include <linux/mtd/partitions.h> -#include <linux/io.h> -#include <linux/irqchip/arm-gic.h> -#include <linux/platform_data/clk-realview.h> -#include <linux/reboot.h> -#include <linux/memblock.h> - -#include "hardware.h" -#include <asm/irq.h> -#include <asm/mach-types.h> -#include <asm/pgtable.h> -#include <asm/hardware/cache-l2x0.h> - -#include <asm/mach/arch.h> -#include <asm/mach/flash.h> -#include <asm/mach/map.h> -#include <asm/mach/time.h> - -#include "board-pb1176.h" -#include "irqs-pb1176.h" - -#include "core.h" - -static struct map_desc realview_pb1176_io_desc[] __initdata = { - { - .virtual = IO_ADDRESS(REALVIEW_SYS_BASE), - .pfn = __phys_to_pfn(REALVIEW_SYS_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PB1176_GIC_CPU_BASE), - .pfn = __phys_to_pfn(REALVIEW_PB1176_GIC_CPU_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PB1176_GIC_DIST_BASE), - .pfn = __phys_to_pfn(REALVIEW_PB1176_GIC_DIST_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_DC1176_GIC_CPU_BASE), - .pfn = __phys_to_pfn(REALVIEW_DC1176_GIC_CPU_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_DC1176_GIC_DIST_BASE), - .pfn = __phys_to_pfn(REALVIEW_DC1176_GIC_DIST_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_SCTL_BASE), - .pfn = __phys_to_pfn(REALVIEW_SCTL_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PB1176_TIMER0_1_BASE), - .pfn = __phys_to_pfn(REALVIEW_PB1176_TIMER0_1_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PB1176_TIMER2_3_BASE), - .pfn = __phys_to_pfn(REALVIEW_PB1176_TIMER2_3_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PB1176_L220_BASE), - .pfn = __phys_to_pfn(REALVIEW_PB1176_L220_BASE), - .length = SZ_8K, - .type = MT_DEVICE, - }, -#ifdef CONFIG_DEBUG_LL - { - .virtual = IO_ADDRESS(REALVIEW_PB1176_UART0_BASE), - .pfn = __phys_to_pfn(REALVIEW_PB1176_UART0_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, -#endif -}; - -static void __init realview_pb1176_map_io(void) -{ - iotable_init(realview_pb1176_io_desc, ARRAY_SIZE(realview_pb1176_io_desc)); -} - -static struct pl061_platform_data gpio0_plat_data = { - .gpio_base = 0, -}; - -static struct pl061_platform_data gpio1_plat_data = { - .gpio_base = 8, -}; - -static struct pl061_platform_data gpio2_plat_data = { - .gpio_base = 16, -}; - -static struct pl022_ssp_controller ssp0_plat_data = { - .bus_id = 0, - .enable_dma = 0, - .num_chipselect = 1, -}; - -/* - * RealView PB1176 AMBA devices - */ -#define GPIO2_IRQ { IRQ_PB1176_GPIO2 } -#define GPIO3_IRQ { IRQ_PB1176_GPIO3 } -#define AACI_IRQ { IRQ_PB1176_AACI } -#define MMCI0_IRQ { IRQ_PB1176_MMCI0A, IRQ_PB1176_MMCI0B } -#define KMI0_IRQ { IRQ_PB1176_KMI0 } -#define KMI1_IRQ { IRQ_PB1176_KMI1 } -#define PB1176_SMC_IRQ { } -#define MPMC_IRQ { } -#define PB1176_CLCD_IRQ { IRQ_DC1176_CLCD } -#define SCTL_IRQ { } -#define PB1176_WATCHDOG_IRQ { IRQ_DC1176_WATCHDOG } -#define PB1176_GPIO0_IRQ { IRQ_DC1176_GPIO0 } -#define GPIO1_IRQ { IRQ_PB1176_GPIO1 } -#define PB1176_RTC_IRQ { IRQ_DC1176_RTC } -#define SCI_IRQ { IRQ_PB1176_SCI } -#define PB1176_UART0_IRQ { IRQ_DC1176_UART0 } -#define PB1176_UART1_IRQ { IRQ_DC1176_UART1 } -#define PB1176_UART2_IRQ { IRQ_DC1176_UART2 } -#define PB1176_UART3_IRQ { IRQ_DC1176_UART3 } -#define PB1176_UART4_IRQ { IRQ_PB1176_UART4 } -#define PB1176_SSP_IRQ { IRQ_DC1176_SSP } - -/* FPGA Primecells */ -APB_DEVICE(aaci, "fpga:aaci", AACI, NULL); -APB_DEVICE(mmc0, "fpga:mmc0", MMCI0, &realview_mmc0_plat_data); -APB_DEVICE(kmi0, "fpga:kmi0", KMI0, NULL); -APB_DEVICE(kmi1, "fpga:kmi1", KMI1, NULL); -APB_DEVICE(uart4, "fpga:uart4", PB1176_UART4, NULL); - -/* DevChip Primecells */ -AHB_DEVICE(smc, "dev:smc", PB1176_SMC, NULL); -AHB_DEVICE(sctl, "dev:sctl", SCTL, NULL); -APB_DEVICE(wdog, "dev:wdog", PB1176_WATCHDOG, NULL); -APB_DEVICE(gpio0, "dev:gpio0", PB1176_GPIO0, &gpio0_plat_data); -APB_DEVICE(gpio1, "dev:gpio1", GPIO1, &gpio1_plat_data); -APB_DEVICE(gpio2, "dev:gpio2", GPIO2, &gpio2_plat_data); -APB_DEVICE(rtc, "dev:rtc", PB1176_RTC, NULL); -APB_DEVICE(sci0, "dev:sci0", SCI, NULL); -APB_DEVICE(uart0, "dev:uart0", PB1176_UART0, NULL); -APB_DEVICE(uart1, "dev:uart1", PB1176_UART1, NULL); -APB_DEVICE(uart2, "dev:uart2", PB1176_UART2, NULL); -APB_DEVICE(uart3, "dev:uart3", PB1176_UART3, NULL); -APB_DEVICE(ssp0, "dev:ssp0", PB1176_SSP, &ssp0_plat_data); -AHB_DEVICE(clcd, "dev:clcd", PB1176_CLCD, &clcd_plat_data); - -static struct amba_device *amba_devs[] __initdata = { - &uart0_device, - &uart1_device, - &uart2_device, - &uart3_device, - &uart4_device, - &smc_device, - &clcd_device, - &sctl_device, - &wdog_device, - &gpio0_device, - &gpio1_device, - &gpio2_device, - &rtc_device, - &sci0_device, - &ssp0_device, - &aaci_device, - &mmc0_device, - &kmi0_device, - &kmi1_device, -}; - -/* - * RealView PB1176 platform devices - */ -static struct resource realview_pb1176_flash_resources[] = { - { - .start = REALVIEW_PB1176_FLASH_BASE, - .end = REALVIEW_PB1176_FLASH_BASE + REALVIEW_PB1176_FLASH_SIZE - 1, - .flags = IORESOURCE_MEM, - }, -#ifdef CONFIG_REALVIEW_PB1176_SECURE_FLASH - { - .start = REALVIEW_PB1176_SEC_FLASH_BASE, - .end = REALVIEW_PB1176_SEC_FLASH_BASE + REALVIEW_PB1176_SEC_FLASH_SIZE - 1, - .flags = IORESOURCE_MEM, - }, -#endif -}; - -static struct physmap_flash_data pb1176_rom_pdata = { - .probe_type = "map_rom", - .width = 4, - .nr_parts = 0, -}; - -static struct resource pb1176_rom_resources[] = { - /* - * This exposes the PB1176 DevChip ROM as an MTD ROM mapping. - * The reference manual states that this is actually a pseudo-ROM - * programmed in NVRAM. - */ - { - .start = REALVIEW_DC1176_ROM_BASE, - .end = REALVIEW_DC1176_ROM_BASE + SZ_16K - 1, - .flags = IORESOURCE_MEM, - } -}; - -static struct platform_device pb1176_rom_device = { - .name = "physmap-flash", - .id = -1, - .num_resources = ARRAY_SIZE(pb1176_rom_resources), - .resource = pb1176_rom_resources, - .dev = { - .platform_data = &pb1176_rom_pdata, - }, -}; - -static struct resource realview_pb1176_smsc911x_resources[] = { - [0] = { - .start = REALVIEW_PB1176_ETH_BASE, - .end = REALVIEW_PB1176_ETH_BASE + SZ_64K - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_PB1176_ETH, - .end = IRQ_PB1176_ETH, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource realview_pb1176_isp1761_resources[] = { - [0] = { - .start = REALVIEW_PB1176_USB_BASE, - .end = REALVIEW_PB1176_USB_BASE + SZ_128K - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_PB1176_USB, - .end = IRQ_PB1176_USB, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource pmu_resource = { - .start = IRQ_DC1176_CORE_PMU, - .end = IRQ_DC1176_CORE_PMU, - .flags = IORESOURCE_IRQ, -}; - -static struct platform_device pmu_device = { - .name = "armv6-pmu", - .id = -1, - .num_resources = 1, - .resource = &pmu_resource, -}; - -static struct resource char_lcd_resources[] = { - { - .start = REALVIEW_CHAR_LCD_BASE, - .end = (REALVIEW_CHAR_LCD_BASE + SZ_4K - 1), - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_PB1176_CHARLCD, - .end = IRQ_PB1176_CHARLCD, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device char_lcd_device = { - .name = "arm-charlcd", - .id = -1, - .num_resources = ARRAY_SIZE(char_lcd_resources), - .resource = char_lcd_resources, -}; - -static void __init gic_init_irq(void) -{ - /* ARM1176 DevChip GIC, primary */ - gic_init(0, IRQ_DC1176_GIC_START, - __io_address(REALVIEW_DC1176_GIC_DIST_BASE), - __io_address(REALVIEW_DC1176_GIC_CPU_BASE)); - - /* board GIC, secondary */ - gic_init(1, IRQ_PB1176_GIC_START, - __io_address(REALVIEW_PB1176_GIC_DIST_BASE), - __io_address(REALVIEW_PB1176_GIC_CPU_BASE)); - gic_cascade_irq(1, IRQ_DC1176_PB_IRQ1); -} - -static void __init realview_pb1176_timer_init(void) -{ - timer0_va_base = __io_address(REALVIEW_PB1176_TIMER0_1_BASE); - timer1_va_base = __io_address(REALVIEW_PB1176_TIMER0_1_BASE) + 0x20; - timer2_va_base = __io_address(REALVIEW_PB1176_TIMER2_3_BASE); - timer3_va_base = __io_address(REALVIEW_PB1176_TIMER2_3_BASE) + 0x20; - - realview_clk_init(__io_address(REALVIEW_SYS_BASE), true); - realview_timer_init(IRQ_DC1176_TIMER0); -} - -static void realview_pb1176_restart(enum reboot_mode mode, const char *cmd) -{ - void __iomem *reset_ctrl = __io_address(REALVIEW_SYS_RESETCTL); - void __iomem *lock_ctrl = __io_address(REALVIEW_SYS_LOCK); - __raw_writel(REALVIEW_SYS_LOCK_VAL, lock_ctrl); - __raw_writel(REALVIEW_PB1176_SYS_SOFT_RESET, reset_ctrl); - dsb(); -} - -static void realview_pb1176_fixup(struct tag *tags, char **from) -{ - /* - * RealView PB1176 only has 128MB of RAM mapped at 0. - */ - memblock_add(0, SZ_128M); -} - -static void __init realview_pb1176_init(void) -{ - int i; - -#ifdef CONFIG_CACHE_L2X0 - /* - * The PL220 needs to be manually configured as the hardware - * doesn't report the correct sizes. - * 128kB (16kB/way), 8-way associativity, event monitor and - * parity enabled, ignore share bit, no force write allocate - * Bits: .... ...0 0111 0011 0000 .... .... .... - */ - l2x0_init(__io_address(REALVIEW_PB1176_L220_BASE), 0x00730000, 0xfe000fff); -#endif - - realview_flash_register(realview_pb1176_flash_resources, - ARRAY_SIZE(realview_pb1176_flash_resources)); - platform_device_register(&pb1176_rom_device); - realview_eth_register(NULL, realview_pb1176_smsc911x_resources); - platform_device_register(&realview_i2c_device); - realview_usb_register(realview_pb1176_isp1761_resources); - platform_device_register(&pmu_device); - platform_device_register(&char_lcd_device); - platform_device_register(&realview_leds_device); - - for (i = 0; i < ARRAY_SIZE(amba_devs); i++) { - struct amba_device *d = amba_devs[i]; - amba_device_register(d, &iomem_resource); - } -} - -MACHINE_START(REALVIEW_PB1176, "ARM-RealView PB1176") - /* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */ - .atag_offset = 0x100, - .fixup = realview_pb1176_fixup, - .map_io = realview_pb1176_map_io, - .init_early = realview_init_early, - .init_irq = gic_init_irq, - .init_time = realview_pb1176_timer_init, - .init_machine = realview_pb1176_init, -#ifdef CONFIG_ZONE_DMA - .dma_zone_size = SZ_256M, -#endif - .restart = realview_pb1176_restart, -MACHINE_END diff --git a/arch/arm/mach-realview/realview_pb11mp.c b/arch/arm/mach-realview/realview_pb11mp.c deleted file mode 100644 index a90a0752f157..000000000000 --- a/arch/arm/mach-realview/realview_pb11mp.c +++ /dev/null @@ -1,385 +0,0 @@ -/* - * linux/arch/arm/mach-realview/realview_pb11mp.c - * - * Copyright (C) 2008 ARM Limited - * Copyright (C) 2000 Deep Blue Solutions Ltd - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/init.h> -#include <linux/platform_device.h> -#include <linux/device.h> -#include <linux/amba/bus.h> -#include <linux/amba/pl061.h> -#include <linux/amba/mmci.h> -#include <linux/amba/pl022.h> -#include <linux/io.h> -#include <linux/irqchip/arm-gic.h> -#include <linux/platform_data/clk-realview.h> -#include <linux/reboot.h> - -#include "hardware.h" -#include <asm/irq.h> -#include <asm/mach-types.h> -#include <asm/pgtable.h> -#include <asm/hardware/cache-l2x0.h> -#include <asm/smp_twd.h> - -#include <asm/mach/arch.h> -#include <asm/mach/flash.h> -#include <asm/mach/map.h> -#include <asm/mach/time.h> -#include <asm/outercache.h> - -#include "board-pb11mp.h" -#include "irqs-pb11mp.h" - -#include "core.h" - -static struct map_desc realview_pb11mp_io_desc[] __initdata = { - { - .virtual = IO_ADDRESS(REALVIEW_SYS_BASE), - .pfn = __phys_to_pfn(REALVIEW_SYS_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PB11MP_GIC_CPU_BASE), - .pfn = __phys_to_pfn(REALVIEW_PB11MP_GIC_CPU_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PB11MP_GIC_DIST_BASE), - .pfn = __phys_to_pfn(REALVIEW_PB11MP_GIC_DIST_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { /* Maps the SCU, GIC CPU interface, TWD, GIC DIST */ - .virtual = IO_ADDRESS(REALVIEW_TC11MP_PRIV_MEM_BASE), - .pfn = __phys_to_pfn(REALVIEW_TC11MP_PRIV_MEM_BASE), - .length = REALVIEW_TC11MP_PRIV_MEM_SIZE, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_SCTL_BASE), - .pfn = __phys_to_pfn(REALVIEW_SCTL_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PB11MP_TIMER0_1_BASE), - .pfn = __phys_to_pfn(REALVIEW_PB11MP_TIMER0_1_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PB11MP_TIMER2_3_BASE), - .pfn = __phys_to_pfn(REALVIEW_PB11MP_TIMER2_3_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_TC11MP_L220_BASE), - .pfn = __phys_to_pfn(REALVIEW_TC11MP_L220_BASE), - .length = SZ_8K, - .type = MT_DEVICE, - }, -#ifdef CONFIG_DEBUG_LL - { - .virtual = IO_ADDRESS(REALVIEW_PB11MP_UART0_BASE), - .pfn = __phys_to_pfn(REALVIEW_PB11MP_UART0_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, -#endif -}; - -static void __init realview_pb11mp_map_io(void) -{ - iotable_init(realview_pb11mp_io_desc, ARRAY_SIZE(realview_pb11mp_io_desc)); -} - -static struct pl061_platform_data gpio0_plat_data = { - .gpio_base = 0, -}; - -static struct pl061_platform_data gpio1_plat_data = { - .gpio_base = 8, -}; - -static struct pl061_platform_data gpio2_plat_data = { - .gpio_base = 16, -}; - -static struct pl022_ssp_controller ssp0_plat_data = { - .bus_id = 0, - .enable_dma = 0, - .num_chipselect = 1, -}; - -/* - * RealView PB11MPCore AMBA devices - */ - -#define GPIO2_IRQ { IRQ_PB11MP_GPIO2 } -#define GPIO3_IRQ { IRQ_PB11MP_GPIO3 } -#define AACI_IRQ { IRQ_TC11MP_AACI } -#define MMCI0_IRQ { IRQ_TC11MP_MMCI0A, IRQ_TC11MP_MMCI0B } -#define KMI0_IRQ { IRQ_TC11MP_KMI0 } -#define KMI1_IRQ { IRQ_TC11MP_KMI1 } -#define PB11MP_SMC_IRQ { } -#define MPMC_IRQ { } -#define PB11MP_CLCD_IRQ { IRQ_PB11MP_CLCD } -#define DMAC_IRQ { IRQ_PB11MP_DMAC } -#define SCTL_IRQ { } -#define PB11MP_WATCHDOG_IRQ { IRQ_PB11MP_WATCHDOG } -#define PB11MP_GPIO0_IRQ { IRQ_PB11MP_GPIO0 } -#define GPIO1_IRQ { IRQ_PB11MP_GPIO1 } -#define PB11MP_RTC_IRQ { IRQ_TC11MP_RTC } -#define SCI_IRQ { IRQ_PB11MP_SCI } -#define PB11MP_UART0_IRQ { IRQ_TC11MP_UART0 } -#define PB11MP_UART1_IRQ { IRQ_TC11MP_UART1 } -#define PB11MP_UART2_IRQ { IRQ_PB11MP_UART2 } -#define PB11MP_UART3_IRQ { IRQ_PB11MP_UART3 } -#define PB11MP_SSP_IRQ { IRQ_PB11MP_SSP } - -/* FPGA Primecells */ -APB_DEVICE(aaci, "fpga:aaci", AACI, NULL); -APB_DEVICE(mmc0, "fpga:mmc0", MMCI0, &realview_mmc0_plat_data); -APB_DEVICE(kmi0, "fpga:kmi0", KMI0, NULL); -APB_DEVICE(kmi1, "fpga:kmi1", KMI1, NULL); -APB_DEVICE(uart3, "fpga:uart3", PB11MP_UART3, NULL); - -/* DevChip Primecells */ -AHB_DEVICE(smc, "dev:smc", PB11MP_SMC, NULL); -AHB_DEVICE(sctl, "dev:sctl", SCTL, NULL); -APB_DEVICE(wdog, "dev:wdog", PB11MP_WATCHDOG, NULL); -APB_DEVICE(gpio0, "dev:gpio0", PB11MP_GPIO0, &gpio0_plat_data); -APB_DEVICE(gpio1, "dev:gpio1", GPIO1, &gpio1_plat_data); -APB_DEVICE(gpio2, "dev:gpio2", GPIO2, &gpio2_plat_data); -APB_DEVICE(rtc, "dev:rtc", PB11MP_RTC, NULL); -APB_DEVICE(sci0, "dev:sci0", SCI, NULL); -APB_DEVICE(uart0, "dev:uart0", PB11MP_UART0, NULL); -APB_DEVICE(uart1, "dev:uart1", PB11MP_UART1, NULL); -APB_DEVICE(uart2, "dev:uart2", PB11MP_UART2, NULL); -APB_DEVICE(ssp0, "dev:ssp0", PB11MP_SSP, &ssp0_plat_data); - -/* Primecells on the NEC ISSP chip */ -AHB_DEVICE(clcd, "issp:clcd", PB11MP_CLCD, &clcd_plat_data); -AHB_DEVICE(dmac, "issp:dmac", DMAC, NULL); - -static struct amba_device *amba_devs[] __initdata = { - &dmac_device, - &uart0_device, - &uart1_device, - &uart2_device, - &uart3_device, - &smc_device, - &clcd_device, - &sctl_device, - &wdog_device, - &gpio0_device, - &gpio1_device, - &gpio2_device, - &rtc_device, - &sci0_device, - &ssp0_device, - &aaci_device, - &mmc0_device, - &kmi0_device, - &kmi1_device, -}; - -/* - * RealView PB11MPCore platform devices - */ -static struct resource realview_pb11mp_flash_resource[] = { - [0] = { - .start = REALVIEW_PB11MP_FLASH0_BASE, - .end = REALVIEW_PB11MP_FLASH0_BASE + REALVIEW_PB11MP_FLASH0_SIZE - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = REALVIEW_PB11MP_FLASH1_BASE, - .end = REALVIEW_PB11MP_FLASH1_BASE + REALVIEW_PB11MP_FLASH1_SIZE - 1, - .flags = IORESOURCE_MEM, - }, -}; - -static struct resource realview_pb11mp_smsc911x_resources[] = { - [0] = { - .start = REALVIEW_PB11MP_ETH_BASE, - .end = REALVIEW_PB11MP_ETH_BASE + SZ_64K - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_TC11MP_ETH, - .end = IRQ_TC11MP_ETH, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource realview_pb11mp_isp1761_resources[] = { - [0] = { - .start = REALVIEW_PB11MP_USB_BASE, - .end = REALVIEW_PB11MP_USB_BASE + SZ_128K - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_TC11MP_USB, - .end = IRQ_TC11MP_USB, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource pmu_resources[] = { - [0] = { - .start = IRQ_TC11MP_PMU_CPU0, - .end = IRQ_TC11MP_PMU_CPU0, - .flags = IORESOURCE_IRQ, - }, - [1] = { - .start = IRQ_TC11MP_PMU_CPU1, - .end = IRQ_TC11MP_PMU_CPU1, - .flags = IORESOURCE_IRQ, - }, - [2] = { - .start = IRQ_TC11MP_PMU_CPU2, - .end = IRQ_TC11MP_PMU_CPU2, - .flags = IORESOURCE_IRQ, - }, - [3] = { - .start = IRQ_TC11MP_PMU_CPU3, - .end = IRQ_TC11MP_PMU_CPU3, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device pmu_device = { - .name = "armv6-pmu", - .id = -1, - .num_resources = ARRAY_SIZE(pmu_resources), - .resource = pmu_resources, -}; - -static void __init gic_init_irq(void) -{ - unsigned int pldctrl; - - /* new irq mode with no DCC */ - writel(0x0000a05f, __io_address(REALVIEW_SYS_LOCK)); - pldctrl = readl(__io_address(REALVIEW_SYS_BASE) + REALVIEW_PB11MP_SYS_PLD_CTRL1); - pldctrl |= 2 << 22; - writel(pldctrl, __io_address(REALVIEW_SYS_BASE) + REALVIEW_PB11MP_SYS_PLD_CTRL1); - writel(0x00000000, __io_address(REALVIEW_SYS_LOCK)); - - /* ARM11MPCore test chip GIC, primary */ - gic_init(0, 29, __io_address(REALVIEW_TC11MP_GIC_DIST_BASE), - __io_address(REALVIEW_TC11MP_GIC_CPU_BASE)); - - /* board GIC, secondary */ - gic_init(1, IRQ_PB11MP_GIC_START, - __io_address(REALVIEW_PB11MP_GIC_DIST_BASE), - __io_address(REALVIEW_PB11MP_GIC_CPU_BASE)); - gic_cascade_irq(1, IRQ_TC11MP_PB_IRQ1); -} - -#ifdef CONFIG_HAVE_ARM_TWD -static DEFINE_TWD_LOCAL_TIMER(twd_local_timer, - REALVIEW_TC11MP_TWD_BASE, - IRQ_LOCALTIMER); - -static void __init realview_pb11mp_twd_init(void) -{ - int err = twd_local_timer_register(&twd_local_timer); - if (err) - pr_err("twd_local_timer_register failed %d\n", err); -} -#else -#define realview_pb11mp_twd_init() do {} while(0) -#endif - -static void __init realview_pb11mp_timer_init(void) -{ - timer0_va_base = __io_address(REALVIEW_PB11MP_TIMER0_1_BASE); - timer1_va_base = __io_address(REALVIEW_PB11MP_TIMER0_1_BASE) + 0x20; - timer2_va_base = __io_address(REALVIEW_PB11MP_TIMER2_3_BASE); - timer3_va_base = __io_address(REALVIEW_PB11MP_TIMER2_3_BASE) + 0x20; - - realview_clk_init(__io_address(REALVIEW_SYS_BASE), false); - realview_timer_init(IRQ_TC11MP_TIMER0_1); - realview_pb11mp_twd_init(); -} - -static void realview_pb11mp_restart(enum reboot_mode mode, const char *cmd) -{ - void __iomem *reset_ctrl = __io_address(REALVIEW_SYS_RESETCTL); - void __iomem *lock_ctrl = __io_address(REALVIEW_SYS_LOCK); - - /* - * To reset, we hit the on-board reset register - * in the system FPGA - */ - __raw_writel(REALVIEW_SYS_LOCK_VAL, lock_ctrl); - __raw_writel(0x0000, reset_ctrl); - __raw_writel(0x0004, reset_ctrl); - dsb(); -} - -static void __init realview_pb11mp_init(void) -{ - int i; - -#ifdef CONFIG_CACHE_L2X0 - /* - * The PL220 needs to be manually configured as the hardware - * doesn't report the correct sizes. - * 1MB (128KB/way), 8-way associativity, event monitor and - * parity enabled, ignore share bit, no force write allocate - * Bits: .... ...0 0111 1001 0000 .... .... .... - */ - l2x0_init(__io_address(REALVIEW_TC11MP_L220_BASE), 0x00790000, 0xfe000fff); - /* - * due to a bug in the l220 cache controller, we must not call - * the sync function. stub it out here instead! - */ - outer_cache.sync = NULL; -#endif - - realview_flash_register(realview_pb11mp_flash_resource, - ARRAY_SIZE(realview_pb11mp_flash_resource)); - realview_eth_register(NULL, realview_pb11mp_smsc911x_resources); - platform_device_register(&realview_i2c_device); - platform_device_register(&realview_cf_device); - platform_device_register(&realview_leds_device); - realview_usb_register(realview_pb11mp_isp1761_resources); - platform_device_register(&pmu_device); - - for (i = 0; i < ARRAY_SIZE(amba_devs); i++) { - struct amba_device *d = amba_devs[i]; - amba_device_register(d, &iomem_resource); - } -} - -MACHINE_START(REALVIEW_PB11MP, "ARM-RealView PB11MPCore") - /* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */ - .atag_offset = 0x100, - .smp = smp_ops(realview_smp_ops), - .fixup = realview_fixup, - .map_io = realview_pb11mp_map_io, - .init_early = realview_init_early, - .init_irq = gic_init_irq, - .init_time = realview_pb11mp_timer_init, - .init_machine = realview_pb11mp_init, -#ifdef CONFIG_ZONE_DMA - .dma_zone_size = SZ_256M, -#endif - .restart = realview_pb11mp_restart, -MACHINE_END diff --git a/arch/arm/mach-realview/realview_pba8.c b/arch/arm/mach-realview/realview_pba8.c deleted file mode 100644 index ddafb67c2b6f..000000000000 --- a/arch/arm/mach-realview/realview_pba8.c +++ /dev/null @@ -1,307 +0,0 @@ -/* - * linux/arch/arm/mach-realview/realview_pba8.c - * - * Copyright (C) 2008 ARM Limited - * Copyright (C) 2000 Deep Blue Solutions Ltd - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/init.h> -#include <linux/platform_device.h> -#include <linux/device.h> -#include <linux/amba/bus.h> -#include <linux/amba/pl061.h> -#include <linux/amba/mmci.h> -#include <linux/amba/pl022.h> -#include <linux/io.h> -#include <linux/irqchip/arm-gic.h> -#include <linux/platform_data/clk-realview.h> -#include <linux/reboot.h> - -#include <asm/irq.h> -#include <asm/mach-types.h> -#include <asm/pgtable.h> - -#include <asm/mach/arch.h> -#include <asm/mach/map.h> -#include <asm/mach/time.h> - -#include "hardware.h" -#include "board-pba8.h" -#include "irqs-pba8.h" - -#include "core.h" - -static struct map_desc realview_pba8_io_desc[] __initdata = { - { - .virtual = IO_ADDRESS(REALVIEW_SYS_BASE), - .pfn = __phys_to_pfn(REALVIEW_SYS_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PBA8_GIC_CPU_BASE), - .pfn = __phys_to_pfn(REALVIEW_PBA8_GIC_CPU_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PBA8_GIC_DIST_BASE), - .pfn = __phys_to_pfn(REALVIEW_PBA8_GIC_DIST_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_SCTL_BASE), - .pfn = __phys_to_pfn(REALVIEW_SCTL_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PBA8_TIMER0_1_BASE), - .pfn = __phys_to_pfn(REALVIEW_PBA8_TIMER0_1_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PBA8_TIMER2_3_BASE), - .pfn = __phys_to_pfn(REALVIEW_PBA8_TIMER2_3_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, -#ifdef CONFIG_DEBUG_LL - { - .virtual = IO_ADDRESS(REALVIEW_PBA8_UART0_BASE), - .pfn = __phys_to_pfn(REALVIEW_PBA8_UART0_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, -#endif -}; - -static void __init realview_pba8_map_io(void) -{ - iotable_init(realview_pba8_io_desc, ARRAY_SIZE(realview_pba8_io_desc)); -} - -static struct pl061_platform_data gpio0_plat_data = { - .gpio_base = 0, -}; - -static struct pl061_platform_data gpio1_plat_data = { - .gpio_base = 8, -}; - -static struct pl061_platform_data gpio2_plat_data = { - .gpio_base = 16, -}; - -static struct pl022_ssp_controller ssp0_plat_data = { - .bus_id = 0, - .enable_dma = 0, - .num_chipselect = 1, -}; - -/* - * RealView PBA8Core AMBA devices - */ - -#define GPIO2_IRQ { IRQ_PBA8_GPIO2 } -#define GPIO3_IRQ { IRQ_PBA8_GPIO3 } -#define AACI_IRQ { IRQ_PBA8_AACI } -#define MMCI0_IRQ { IRQ_PBA8_MMCI0A, IRQ_PBA8_MMCI0B } -#define KMI0_IRQ { IRQ_PBA8_KMI0 } -#define KMI1_IRQ { IRQ_PBA8_KMI1 } -#define PBA8_SMC_IRQ { } -#define MPMC_IRQ { } -#define PBA8_CLCD_IRQ { IRQ_PBA8_CLCD } -#define DMAC_IRQ { IRQ_PBA8_DMAC } -#define SCTL_IRQ { } -#define PBA8_WATCHDOG_IRQ { IRQ_PBA8_WATCHDOG } -#define PBA8_GPIO0_IRQ { IRQ_PBA8_GPIO0 } -#define GPIO1_IRQ { IRQ_PBA8_GPIO1 } -#define PBA8_RTC_IRQ { IRQ_PBA8_RTC } -#define SCI_IRQ { IRQ_PBA8_SCI } -#define PBA8_UART0_IRQ { IRQ_PBA8_UART0 } -#define PBA8_UART1_IRQ { IRQ_PBA8_UART1 } -#define PBA8_UART2_IRQ { IRQ_PBA8_UART2 } -#define PBA8_UART3_IRQ { IRQ_PBA8_UART3 } -#define PBA8_SSP_IRQ { IRQ_PBA8_SSP } - -/* FPGA Primecells */ -APB_DEVICE(aaci, "fpga:aaci", AACI, NULL); -APB_DEVICE(mmc0, "fpga:mmc0", MMCI0, &realview_mmc0_plat_data); -APB_DEVICE(kmi0, "fpga:kmi0", KMI0, NULL); -APB_DEVICE(kmi1, "fpga:kmi1", KMI1, NULL); -APB_DEVICE(uart3, "fpga:uart3", PBA8_UART3, NULL); - -/* DevChip Primecells */ -AHB_DEVICE(smc, "dev:smc", PBA8_SMC, NULL); -AHB_DEVICE(sctl, "dev:sctl", SCTL, NULL); -APB_DEVICE(wdog, "dev:wdog", PBA8_WATCHDOG, NULL); -APB_DEVICE(gpio0, "dev:gpio0", PBA8_GPIO0, &gpio0_plat_data); -APB_DEVICE(gpio1, "dev:gpio1", GPIO1, &gpio1_plat_data); -APB_DEVICE(gpio2, "dev:gpio2", GPIO2, &gpio2_plat_data); -APB_DEVICE(rtc, "dev:rtc", PBA8_RTC, NULL); -APB_DEVICE(sci0, "dev:sci0", SCI, NULL); -APB_DEVICE(uart0, "dev:uart0", PBA8_UART0, NULL); -APB_DEVICE(uart1, "dev:uart1", PBA8_UART1, NULL); -APB_DEVICE(uart2, "dev:uart2", PBA8_UART2, NULL); -APB_DEVICE(ssp0, "dev:ssp0", PBA8_SSP, &ssp0_plat_data); - -/* Primecells on the NEC ISSP chip */ -AHB_DEVICE(clcd, "issp:clcd", PBA8_CLCD, &clcd_plat_data); -AHB_DEVICE(dmac, "issp:dmac", DMAC, NULL); - -static struct amba_device *amba_devs[] __initdata = { - &dmac_device, - &uart0_device, - &uart1_device, - &uart2_device, - &uart3_device, - &smc_device, - &clcd_device, - &sctl_device, - &wdog_device, - &gpio0_device, - &gpio1_device, - &gpio2_device, - &rtc_device, - &sci0_device, - &ssp0_device, - &aaci_device, - &mmc0_device, - &kmi0_device, - &kmi1_device, -}; - -/* - * RealView PB-A8 platform devices - */ -static struct resource realview_pba8_flash_resource[] = { - [0] = { - .start = REALVIEW_PBA8_FLASH0_BASE, - .end = REALVIEW_PBA8_FLASH0_BASE + REALVIEW_PBA8_FLASH0_SIZE - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = REALVIEW_PBA8_FLASH1_BASE, - .end = REALVIEW_PBA8_FLASH1_BASE + REALVIEW_PBA8_FLASH1_SIZE - 1, - .flags = IORESOURCE_MEM, - }, -}; - -static struct resource realview_pba8_smsc911x_resources[] = { - [0] = { - .start = REALVIEW_PBA8_ETH_BASE, - .end = REALVIEW_PBA8_ETH_BASE + SZ_64K - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_PBA8_ETH, - .end = IRQ_PBA8_ETH, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource realview_pba8_isp1761_resources[] = { - [0] = { - .start = REALVIEW_PBA8_USB_BASE, - .end = REALVIEW_PBA8_USB_BASE + SZ_128K - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_PBA8_USB, - .end = IRQ_PBA8_USB, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource pmu_resource = { - .start = IRQ_PBA8_PMU, - .end = IRQ_PBA8_PMU, - .flags = IORESOURCE_IRQ, -}; - -static struct platform_device pmu_device = { - .name = "armv7-pmu", - .id = -1, - .num_resources = 1, - .resource = &pmu_resource, -}; - -static void __init gic_init_irq(void) -{ - /* ARM PB-A8 on-board GIC */ - gic_init(0, IRQ_PBA8_GIC_START, - __io_address(REALVIEW_PBA8_GIC_DIST_BASE), - __io_address(REALVIEW_PBA8_GIC_CPU_BASE)); -} - -static void __init realview_pba8_timer_init(void) -{ - timer0_va_base = __io_address(REALVIEW_PBA8_TIMER0_1_BASE); - timer1_va_base = __io_address(REALVIEW_PBA8_TIMER0_1_BASE) + 0x20; - timer2_va_base = __io_address(REALVIEW_PBA8_TIMER2_3_BASE); - timer3_va_base = __io_address(REALVIEW_PBA8_TIMER2_3_BASE) + 0x20; - - realview_clk_init(__io_address(REALVIEW_SYS_BASE), false); - realview_timer_init(IRQ_PBA8_TIMER0_1); -} - -static void realview_pba8_restart(enum reboot_mode mode, const char *cmd) -{ - void __iomem *reset_ctrl = __io_address(REALVIEW_SYS_RESETCTL); - void __iomem *lock_ctrl = __io_address(REALVIEW_SYS_LOCK); - - /* - * To reset, we hit the on-board reset register - * in the system FPGA - */ - __raw_writel(REALVIEW_SYS_LOCK_VAL, lock_ctrl); - __raw_writel(0x0000, reset_ctrl); - __raw_writel(0x0004, reset_ctrl); - dsb(); -} - -static void __init realview_pba8_init(void) -{ - int i; - - realview_flash_register(realview_pba8_flash_resource, - ARRAY_SIZE(realview_pba8_flash_resource)); - realview_eth_register(NULL, realview_pba8_smsc911x_resources); - platform_device_register(&realview_i2c_device); - platform_device_register(&realview_cf_device); - platform_device_register(&realview_leds_device); - realview_usb_register(realview_pba8_isp1761_resources); - platform_device_register(&pmu_device); - - for (i = 0; i < ARRAY_SIZE(amba_devs); i++) { - struct amba_device *d = amba_devs[i]; - amba_device_register(d, &iomem_resource); - } -} - -MACHINE_START(REALVIEW_PBA8, "ARM-RealView PB-A8") - /* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */ - .atag_offset = 0x100, - .fixup = realview_fixup, - .map_io = realview_pba8_map_io, - .init_early = realview_init_early, - .init_irq = gic_init_irq, - .init_time = realview_pba8_timer_init, - .init_machine = realview_pba8_init, -#ifdef CONFIG_ZONE_DMA - .dma_zone_size = SZ_256M, -#endif - .restart = realview_pba8_restart, -MACHINE_END diff --git a/arch/arm/mach-realview/realview_pbx.c b/arch/arm/mach-realview/realview_pbx.c deleted file mode 100644 index be1cec5fe3ad..000000000000 --- a/arch/arm/mach-realview/realview_pbx.c +++ /dev/null @@ -1,402 +0,0 @@ -/* - * arch/arm/mach-realview/realview_pbx.c - * - * Copyright (C) 2009 ARM Limited - * Copyright (C) 2000 Deep Blue Solutions Ltd - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/init.h> -#include <linux/platform_device.h> -#include <linux/device.h> -#include <linux/amba/bus.h> -#include <linux/amba/pl061.h> -#include <linux/amba/mmci.h> -#include <linux/amba/pl022.h> -#include <linux/io.h> -#include <linux/irqchip/arm-gic.h> -#include <linux/platform_data/clk-realview.h> -#include <linux/reboot.h> -#include <linux/memblock.h> - -#include <asm/irq.h> -#include <asm/mach-types.h> -#include <asm/smp_twd.h> -#include <asm/pgtable.h> -#include <asm/hardware/cache-l2x0.h> - -#include <asm/mach/arch.h> -#include <asm/mach/map.h> -#include <asm/mach/time.h> - -#include "hardware.h" -#include "board-pbx.h" -#include "irqs-pbx.h" - -#include "core.h" - -static struct map_desc realview_pbx_io_desc[] __initdata = { - { - .virtual = IO_ADDRESS(REALVIEW_SYS_BASE), - .pfn = __phys_to_pfn(REALVIEW_SYS_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PBX_GIC_CPU_BASE), - .pfn = __phys_to_pfn(REALVIEW_PBX_GIC_CPU_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PBX_GIC_DIST_BASE), - .pfn = __phys_to_pfn(REALVIEW_PBX_GIC_DIST_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_SCTL_BASE), - .pfn = __phys_to_pfn(REALVIEW_SCTL_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PBX_TIMER0_1_BASE), - .pfn = __phys_to_pfn(REALVIEW_PBX_TIMER0_1_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PBX_TIMER2_3_BASE), - .pfn = __phys_to_pfn(REALVIEW_PBX_TIMER2_3_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, -#ifdef CONFIG_DEBUG_LL - { - .virtual = IO_ADDRESS(REALVIEW_PBX_UART0_BASE), - .pfn = __phys_to_pfn(REALVIEW_PBX_UART0_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, -#endif -}; - -static struct map_desc realview_local_io_desc[] __initdata = { - { - .virtual = IO_ADDRESS(REALVIEW_PBX_TILE_SCU_BASE), - .pfn = __phys_to_pfn(REALVIEW_PBX_TILE_SCU_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PBX_TILE_GIC_DIST_BASE), - .pfn = __phys_to_pfn(REALVIEW_PBX_TILE_GIC_DIST_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = IO_ADDRESS(REALVIEW_PBX_TILE_L220_BASE), - .pfn = __phys_to_pfn(REALVIEW_PBX_TILE_L220_BASE), - .length = SZ_8K, - .type = MT_DEVICE, - } -}; - -static void __init realview_pbx_map_io(void) -{ - iotable_init(realview_pbx_io_desc, ARRAY_SIZE(realview_pbx_io_desc)); - if (core_tile_pbx11mp() || core_tile_pbxa9mp()) - iotable_init(realview_local_io_desc, ARRAY_SIZE(realview_local_io_desc)); -} - -static struct pl061_platform_data gpio0_plat_data = { - .gpio_base = 0, -}; - -static struct pl061_platform_data gpio1_plat_data = { - .gpio_base = 8, -}; - -static struct pl061_platform_data gpio2_plat_data = { - .gpio_base = 16, -}; - -static struct pl022_ssp_controller ssp0_plat_data = { - .bus_id = 0, - .enable_dma = 0, - .num_chipselect = 1, -}; - -/* - * RealView PBXCore AMBA devices - */ - -#define GPIO2_IRQ { IRQ_PBX_GPIO2 } -#define GPIO3_IRQ { IRQ_PBX_GPIO3 } -#define AACI_IRQ { IRQ_PBX_AACI } -#define MMCI0_IRQ { IRQ_PBX_MMCI0A, IRQ_PBX_MMCI0B } -#define KMI0_IRQ { IRQ_PBX_KMI0 } -#define KMI1_IRQ { IRQ_PBX_KMI1 } -#define PBX_SMC_IRQ { } -#define MPMC_IRQ { } -#define PBX_CLCD_IRQ { IRQ_PBX_CLCD } -#define DMAC_IRQ { IRQ_PBX_DMAC } -#define SCTL_IRQ { } -#define PBX_WATCHDOG_IRQ { IRQ_PBX_WATCHDOG } -#define PBX_GPIO0_IRQ { IRQ_PBX_GPIO0 } -#define GPIO1_IRQ { IRQ_PBX_GPIO1 } -#define PBX_RTC_IRQ { IRQ_PBX_RTC } -#define SCI_IRQ { IRQ_PBX_SCI } -#define PBX_UART0_IRQ { IRQ_PBX_UART0 } -#define PBX_UART1_IRQ { IRQ_PBX_UART1 } -#define PBX_UART2_IRQ { IRQ_PBX_UART2 } -#define PBX_UART3_IRQ { IRQ_PBX_UART3 } -#define PBX_SSP_IRQ { IRQ_PBX_SSP } - -/* FPGA Primecells */ -APB_DEVICE(aaci, "fpga:aaci", AACI, NULL); -APB_DEVICE(mmc0, "fpga:mmc0", MMCI0, &realview_mmc0_plat_data); -APB_DEVICE(kmi0, "fpga:kmi0", KMI0, NULL); -APB_DEVICE(kmi1, "fpga:kmi1", KMI1, NULL); -APB_DEVICE(uart3, "fpga:uart3", PBX_UART3, NULL); - -/* DevChip Primecells */ -AHB_DEVICE(smc, "dev:smc", PBX_SMC, NULL); -AHB_DEVICE(sctl, "dev:sctl", SCTL, NULL); -APB_DEVICE(wdog, "dev:wdog", PBX_WATCHDOG, NULL); -APB_DEVICE(gpio0, "dev:gpio0", PBX_GPIO0, &gpio0_plat_data); -APB_DEVICE(gpio1, "dev:gpio1", GPIO1, &gpio1_plat_data); -APB_DEVICE(gpio2, "dev:gpio2", GPIO2, &gpio2_plat_data); -APB_DEVICE(rtc, "dev:rtc", PBX_RTC, NULL); -APB_DEVICE(sci0, "dev:sci0", SCI, NULL); -APB_DEVICE(uart0, "dev:uart0", PBX_UART0, NULL); -APB_DEVICE(uart1, "dev:uart1", PBX_UART1, NULL); -APB_DEVICE(uart2, "dev:uart2", PBX_UART2, NULL); -APB_DEVICE(ssp0, "dev:ssp0", PBX_SSP, &ssp0_plat_data); - -/* Primecells on the NEC ISSP chip */ -AHB_DEVICE(clcd, "issp:clcd", PBX_CLCD, &clcd_plat_data); -AHB_DEVICE(dmac, "issp:dmac", DMAC, NULL); - -static struct amba_device *amba_devs[] __initdata = { - &dmac_device, - &uart0_device, - &uart1_device, - &uart2_device, - &uart3_device, - &smc_device, - &clcd_device, - &sctl_device, - &wdog_device, - &gpio0_device, - &gpio1_device, - &gpio2_device, - &rtc_device, - &sci0_device, - &ssp0_device, - &aaci_device, - &mmc0_device, - &kmi0_device, - &kmi1_device, -}; - -/* - * RealView PB-X platform devices - */ -static struct resource realview_pbx_flash_resources[] = { - [0] = { - .start = REALVIEW_PBX_FLASH0_BASE, - .end = REALVIEW_PBX_FLASH0_BASE + REALVIEW_PBX_FLASH0_SIZE - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = REALVIEW_PBX_FLASH1_BASE, - .end = REALVIEW_PBX_FLASH1_BASE + REALVIEW_PBX_FLASH1_SIZE - 1, - .flags = IORESOURCE_MEM, - }, -}; - -static struct resource realview_pbx_smsc911x_resources[] = { - [0] = { - .start = REALVIEW_PBX_ETH_BASE, - .end = REALVIEW_PBX_ETH_BASE + SZ_64K - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_PBX_ETH, - .end = IRQ_PBX_ETH, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource realview_pbx_isp1761_resources[] = { - [0] = { - .start = REALVIEW_PBX_USB_BASE, - .end = REALVIEW_PBX_USB_BASE + SZ_128K - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_PBX_USB, - .end = IRQ_PBX_USB, - .flags = IORESOURCE_IRQ, - }, -}; - -#ifdef CONFIG_CACHE_L2X0 -static struct resource pmu_resources[] = { - [0] = { - .start = IRQ_PBX_PMU_CPU0, - .end = IRQ_PBX_PMU_CPU0, - .flags = IORESOURCE_IRQ, - }, - [1] = { - .start = IRQ_PBX_PMU_CPU1, - .end = IRQ_PBX_PMU_CPU1, - .flags = IORESOURCE_IRQ, - }, - [2] = { - .start = IRQ_PBX_PMU_CPU2, - .end = IRQ_PBX_PMU_CPU2, - .flags = IORESOURCE_IRQ, - }, - [3] = { - .start = IRQ_PBX_PMU_CPU3, - .end = IRQ_PBX_PMU_CPU3, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device pmu_device = { - .name = "armv7-pmu", - .id = -1, - .num_resources = ARRAY_SIZE(pmu_resources), - .resource = pmu_resources, -}; -#endif - -static void __init gic_init_irq(void) -{ - /* ARM PBX on-board GIC */ - if (core_tile_pbx11mp() || core_tile_pbxa9mp()) { - gic_init(0, 29, __io_address(REALVIEW_PBX_TILE_GIC_DIST_BASE), - __io_address(REALVIEW_PBX_TILE_GIC_CPU_BASE)); - } else { - gic_init(0, IRQ_PBX_GIC_START, - __io_address(REALVIEW_PBX_GIC_DIST_BASE), - __io_address(REALVIEW_PBX_GIC_CPU_BASE)); - } -} - -#ifdef CONFIG_HAVE_ARM_TWD -static DEFINE_TWD_LOCAL_TIMER(twd_local_timer, - REALVIEW_PBX_TILE_TWD_BASE, - IRQ_LOCALTIMER); - -static void __init realview_pbx_twd_init(void) -{ - int err = twd_local_timer_register(&twd_local_timer); - if (err) - pr_err("twd_local_timer_register failed %d\n", err); -} -#else -#define realview_pbx_twd_init() do { } while(0) -#endif - -static void __init realview_pbx_timer_init(void) -{ - timer0_va_base = __io_address(REALVIEW_PBX_TIMER0_1_BASE); - timer1_va_base = __io_address(REALVIEW_PBX_TIMER0_1_BASE) + 0x20; - timer2_va_base = __io_address(REALVIEW_PBX_TIMER2_3_BASE); - timer3_va_base = __io_address(REALVIEW_PBX_TIMER2_3_BASE) + 0x20; - - realview_clk_init(__io_address(REALVIEW_SYS_BASE), false); - realview_timer_init(IRQ_PBX_TIMER0_1); - realview_pbx_twd_init(); -} - -static void realview_pbx_fixup(struct tag *tags, char **from) -{ -#ifdef CONFIG_SPARSEMEM - /* - * Memory configuration with SPARSEMEM enabled on RealView PBX (see - * asm/mach/memory.h for more information). - */ - - memblock_add(0, SZ_256M); - memblock_add(0x20000000, SZ_512M); - memblock_add(0x80000000, SZ_256M); -#else - realview_fixup(tags, from); -#endif -} - -static void realview_pbx_restart(enum reboot_mode mode, const char *cmd) -{ - void __iomem *reset_ctrl = __io_address(REALVIEW_SYS_RESETCTL); - void __iomem *lock_ctrl = __io_address(REALVIEW_SYS_LOCK); - - /* - * To reset, we hit the on-board reset register - * in the system FPGA - */ - __raw_writel(REALVIEW_SYS_LOCK_VAL, lock_ctrl); - __raw_writel(0x00F0, reset_ctrl); - __raw_writel(0x00F4, reset_ctrl); - dsb(); -} - -static void __init realview_pbx_init(void) -{ - int i; - -#ifdef CONFIG_CACHE_L2X0 - if (core_tile_pbxa9mp()) { - void __iomem *l2x0_base = - __io_address(REALVIEW_PBX_TILE_L220_BASE); - - /* set RAM latencies to 1 cycle for eASIC */ - writel(0, l2x0_base + L310_TAG_LATENCY_CTRL); - writel(0, l2x0_base + L310_DATA_LATENCY_CTRL); - - /* 16KB way size, 8-way associativity, parity disabled - * Bits: .. 0 0 0 0 1 00 1 0 1 001 0 000 0 .... .... .... */ - l2x0_init(l2x0_base, 0x02520000, 0xc0000fff); - platform_device_register(&pmu_device); - } -#endif - - realview_flash_register(realview_pbx_flash_resources, - ARRAY_SIZE(realview_pbx_flash_resources)); - realview_eth_register(NULL, realview_pbx_smsc911x_resources); - platform_device_register(&realview_i2c_device); - platform_device_register(&realview_cf_device); - platform_device_register(&realview_leds_device); - realview_usb_register(realview_pbx_isp1761_resources); - - for (i = 0; i < ARRAY_SIZE(amba_devs); i++) { - struct amba_device *d = amba_devs[i]; - amba_device_register(d, &iomem_resource); - } -} - -MACHINE_START(REALVIEW_PBX, "ARM-RealView PBX") - /* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */ - .atag_offset = 0x100, - .smp = smp_ops(realview_smp_ops), - .fixup = realview_pbx_fixup, - .map_io = realview_pbx_map_io, - .init_early = realview_init_early, - .init_irq = gic_init_irq, - .init_time = realview_pbx_timer_init, - .init_machine = realview_pbx_init, -#ifdef CONFIG_ZONE_DMA - .dma_zone_size = SZ_256M, -#endif - .restart = realview_pbx_restart, -MACHINE_END diff --git a/arch/arm/mach-rpc/include/mach/hardware.h b/arch/arm/mach-rpc/include/mach/hardware.h index 257166b21f3d..aa79fa47373a 100644 --- a/arch/arm/mach-rpc/include/mach/hardware.h +++ b/arch/arm/mach-rpc/include/mach/hardware.h @@ -40,7 +40,7 @@ #define SCREEN_END 0xdfc00000 #define SCREEN_BASE 0xdf800000 -#define UNCACHEABLE_ADDR 0xdf010000 +#define UNCACHEABLE_ADDR (FLUSH_BASE + 0x10000) /* * IO Addresses diff --git a/arch/arm/mach-s3c24xx/common.c b/arch/arm/mach-s3c24xx/common.c index fe7485dc7fb5..f6c3f151d0d4 100644 --- a/arch/arm/mach-s3c24xx/common.c +++ b/arch/arm/mach-s3c24xx/common.c @@ -33,6 +33,7 @@ #include <linux/delay.h> #include <linux/io.h> #include <linux/platform_data/dma-s3c24xx.h> +#include <linux/dmaengine.h> #include <mach/hardware.h> #include <mach/regs-clock.h> @@ -445,10 +446,44 @@ static struct s3c24xx_dma_channel s3c2440_dma_channels[DMACH_MAX] = { [DMACH_USB_EP4] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 3), }, }; +static const struct dma_slave_map s3c2440_dma_slave_map[] = { + /* TODO: DMACH_XD0 */ + /* TODO: DMACH_XD1 */ + { "s3c2440-sdi", "rx-tx", (void *)DMACH_SDI }, + { "s3c2410-spi.0", "rx", (void *)DMACH_SPI0 }, + { "s3c2410-spi.0", "tx", (void *)DMACH_SPI0 }, + { "s3c2410-spi.1", "rx", (void *)DMACH_SPI1 }, + { "s3c2410-spi.1", "tx", (void *)DMACH_SPI1 }, + { "s3c2440-uart.0", "rx", (void *)DMACH_UART0 }, + { "s3c2440-uart.0", "tx", (void *)DMACH_UART0 }, + { "s3c2440-uart.1", "rx", (void *)DMACH_UART1 }, + { "s3c2440-uart.1", "tx", (void *)DMACH_UART1 }, + { "s3c2440-uart.2", "rx", (void *)DMACH_UART2 }, + { "s3c2440-uart.2", "tx", (void *)DMACH_UART2 }, + { "s3c2440-uart.3", "rx", (void *)DMACH_UART3 }, + { "s3c2440-uart.3", "tx", (void *)DMACH_UART3 }, + /* TODO: DMACH_TIMER */ + { "s3c24xx-iis", "rx", (void *)DMACH_I2S_IN }, + { "s3c24xx-iis", "tx", (void *)DMACH_I2S_OUT }, + { "samsung-ac97", "rx", (void *)DMACH_PCM_IN }, + { "samsung-ac97", "tx", (void *)DMACH_PCM_OUT }, + { "samsung-ac97", "rx", (void *)DMACH_MIC_IN }, + { "s3c-hsudc", "rx0", (void *)DMACH_USB_EP1 }, + { "s3c-hsudc", "rx1", (void *)DMACH_USB_EP2 }, + { "s3c-hsudc", "rx2", (void *)DMACH_USB_EP3 }, + { "s3c-hsudc", "rx3", (void *)DMACH_USB_EP4 }, + { "s3c-hsudc", "tx0", (void *)DMACH_USB_EP1 }, + { "s3c-hsudc", "tx1", (void *)DMACH_USB_EP2 }, + { "s3c-hsudc", "tx2", (void *)DMACH_USB_EP3 }, + { "s3c-hsudc", "tx3", (void *)DMACH_USB_EP4 } +}; + static struct s3c24xx_dma_platdata s3c2440_dma_platdata = { .num_phy_channels = 4, .channels = s3c2440_dma_channels, .num_channels = DMACH_MAX, + .slave_map = s3c2440_dma_slave_map, + .slavecnt = ARRAY_SIZE(s3c2440_dma_slave_map), }; struct platform_device s3c2440_device_dma = { diff --git a/arch/arm/mach-s3c24xx/mach-mini2440.c b/arch/arm/mach-s3c24xx/mach-mini2440.c index bbf41322d726..ec60bd4a1646 100644 --- a/arch/arm/mach-s3c24xx/mach-mini2440.c +++ b/arch/arm/mach-s3c24xx/mach-mini2440.c @@ -497,9 +497,28 @@ static struct i2c_board_info mini2440_i2c_devs[] __initdata = { }, }; +static struct uda134x_platform_data s3c24xx_uda134x = { + .l3 = { + .gpio_clk = S3C2410_GPB(4), + .gpio_data = S3C2410_GPB(3), + .gpio_mode = S3C2410_GPB(2), + .use_gpios = 1, + .data_hold = 1, + .data_setup = 1, + .clock_high = 1, + .mode_hold = 1, + .mode = 1, + .mode_setup = 1, + }, + .model = UDA134X_UDA1341, +}; + static struct platform_device uda1340_codec = { .name = "uda134x-codec", .id = -1, + .dev = { + .platform_data = &s3c24xx_uda134x, + }, }; static struct platform_device *mini2440_devices[] __initdata = { diff --git a/arch/arm/mach-sa1100/clock.c b/arch/arm/mach-sa1100/clock.c index cbf53bb9c814..0db46895c82a 100644 --- a/arch/arm/mach-sa1100/clock.c +++ b/arch/arm/mach-sa1100/clock.c @@ -125,6 +125,8 @@ static unsigned long clk_36864_get_rate(struct clk *clk) } static struct clkops clk_36864_ops = { + .enable = clk_cpu_enable, + .disable = clk_cpu_disable, .get_rate = clk_36864_get_rate, }; @@ -140,9 +142,8 @@ static struct clk_lookup sa11xx_clkregs[] = { CLKDEV_INIT(NULL, "OSTIMER0", &clk_36864), }; -static int __init sa11xx_clk_init(void) +int __init sa11xx_clk_init(void) { clkdev_add_table(sa11xx_clkregs, ARRAY_SIZE(sa11xx_clkregs)); return 0; } -core_initcall(sa11xx_clk_init); diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c index 345e63f4eb71..3e09beddb6e8 100644 --- a/arch/arm/mach-sa1100/generic.c +++ b/arch/arm/mach-sa1100/generic.c @@ -34,6 +34,7 @@ #include <mach/hardware.h> #include <mach/irqs.h> +#include <mach/reset.h> #include "generic.h" #include <clocksource/pxa.h> @@ -95,6 +96,8 @@ static void sa1100_power_off(void) void sa11x0_restart(enum reboot_mode mode, const char *cmd) { + clear_reset_status(RESET_STATUS_ALL); + if (mode == REBOOT_SOFT) { /* Jump into ROM at address 0 */ soft_restart(0); @@ -388,6 +391,7 @@ void __init sa1100_init_irq(void) sa11x0_init_irq_nodt(IRQ_GPIO0_SC, irq_resource.start); sa1100_init_gpio(); + sa11xx_clk_init(); } /* diff --git a/arch/arm/mach-sa1100/generic.h b/arch/arm/mach-sa1100/generic.h index 0d92e119b36b..68199b603ff7 100644 --- a/arch/arm/mach-sa1100/generic.h +++ b/arch/arm/mach-sa1100/generic.h @@ -44,3 +44,5 @@ int sa11x0_pm_init(void); #else static inline int sa11x0_pm_init(void) { return 0; } #endif + +int sa11xx_clk_init(void); diff --git a/arch/arm/mach-sa1100/h3xxx.c b/arch/arm/mach-sa1100/h3xxx.c index b1d4faa12f9a..b69e76614d5b 100644 --- a/arch/arm/mach-sa1100/h3xxx.c +++ b/arch/arm/mach-sa1100/h3xxx.c @@ -14,9 +14,9 @@ #include <linux/gpio.h> #include <linux/gpio_keys.h> #include <linux/input.h> -#include <linux/mfd/htc-egpio.h> #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> +#include <linux/platform_data/gpio-htc-egpio.h> #include <linux/platform_data/sa11x0-serial.h> #include <linux/platform_device.h> #include <linux/serial_core.h> diff --git a/arch/arm/mach-sa1100/include/mach/hardware.h b/arch/arm/mach-sa1100/include/mach/hardware.h index cbedd75a9d65..d944fd7e464f 100644 --- a/arch/arm/mach-sa1100/include/mach/hardware.h +++ b/arch/arm/mach-sa1100/include/mach/hardware.h @@ -13,7 +13,7 @@ #define __ASM_ARCH_HARDWARE_H -#define UNCACHEABLE_ADDR 0xfa050000 +#define UNCACHEABLE_ADDR 0xfa050000 /* ICIP */ /* @@ -36,28 +36,10 @@ #define io_v2p( x ) \ ( (((x)&0x00ffffff) | (((x)&(0x30000000>>VIO_SHIFT))<<VIO_SHIFT)) + PIO_START ) -#define CPU_SA1110_A0 (0) -#define CPU_SA1110_B0 (4) -#define CPU_SA1110_B1 (5) -#define CPU_SA1110_B2 (6) -#define CPU_SA1110_B4 (8) - -#define CPU_SA1100_ID (0x4401a110) -#define CPU_SA1100_MASK (0xfffffff0) -#define CPU_SA1110_ID (0x6901b110) -#define CPU_SA1110_MASK (0xfffffff0) - #define __MREG(x) IOMEM(io_p2v(x)) #ifndef __ASSEMBLY__ -#include <asm/cputype.h> - -#define CPU_REVISION (read_cpuid_id() & 15) - -#define cpu_is_sa1100() ((read_cpuid_id() & CPU_SA1100_MASK) == CPU_SA1100_ID) -#define cpu_is_sa1110() ((read_cpuid_id() & CPU_SA1110_MASK) == CPU_SA1110_ID) - # define __REG(x) (*((volatile unsigned long __iomem *)io_p2v(x))) # define __PREG(x) (io_v2p((unsigned long)&(x))) diff --git a/arch/arm/mach-sa1100/jornada720.c b/arch/arm/mach-sa1100/jornada720.c index c0b1f5bafae4..0a2ca9be00e6 100644 --- a/arch/arm/mach-sa1100/jornada720.c +++ b/arch/arm/mach-sa1100/jornada720.c @@ -17,6 +17,7 @@ #include <linux/kernel.h> #include <linux/tty.h> #include <linux/delay.h> +#include <linux/gpio/machine.h> #include <linux/platform_data/sa11x0-serial.h> #include <linux/platform_device.h> #include <linux/ioport.h> @@ -217,9 +218,22 @@ static struct platform_device jornada_ssp_device = { .id = -1, }; +static struct resource jornada_kbd_resources[] = { + DEFINE_RES_IRQ(IRQ_GPIO0), +}; + static struct platform_device jornada_kbd_device = { .name = "jornada720_kbd", .id = -1, + .num_resources = ARRAY_SIZE(jornada_kbd_resources), + .resource = jornada_kbd_resources, +}; + +static struct gpiod_lookup_table jornada_ts_gpiod_table = { + .dev_id = "jornada_ts", + .table = { + GPIO_LOOKUP("gpio", 9, "penup", GPIO_ACTIVE_HIGH), + }, }; static struct platform_device jornada_ts_device = { @@ -250,6 +264,8 @@ static int __init jornada720_init(void) GPSR = GPIO_GPIO20; /* restart gpio20 */ udelay(20); /* give it some time to restart */ + gpiod_add_lookup_table(&jornada_ts_gpiod_table); + ret = platform_add_devices(devices, ARRAY_SIZE(devices)); } diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c index 1525d7b5f1b7..88149f85bc49 100644 --- a/arch/arm/mach-sa1100/pleb.c +++ b/arch/arm/mach-sa1100/pleb.c @@ -45,7 +45,7 @@ static struct resource smc91x_resources[] = { }; static struct smc91x_platdata smc91x_platdata = { - .flags = SMC91X_USE_16BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_16BIT | SMC91X_USE_8BIT | SMC91X_NOWAIT, }; static struct platform_device smc91x_device = { diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig index 4a48c9f5f725..09817bae4558 100644 --- a/arch/arm/mach-shmobile/Kconfig +++ b/arch/arm/mach-shmobile/Kconfig @@ -22,7 +22,6 @@ config ARCH_RCAR_GEN2 select PM_GENERIC_DOMAINS select RENESAS_IRQC select SYS_SUPPORTS_SH_CMT - select PCI_DOMAINS if PCI config ARCH_RMOBILE bool diff --git a/arch/arm/mach-shmobile/platsmp-scu.c b/arch/arm/mach-shmobile/platsmp-scu.c index 8d478f1da265..d1ecaf37d142 100644 --- a/arch/arm/mach-shmobile/platsmp-scu.c +++ b/arch/arm/mach-shmobile/platsmp-scu.c @@ -21,26 +21,14 @@ static phys_addr_t shmobile_scu_base_phys; static void __iomem *shmobile_scu_base; -static int shmobile_smp_scu_notifier_call(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int shmobile_scu_cpu_prepare(unsigned int cpu) { - unsigned int cpu = (long)hcpu; - - switch (action) { - case CPU_UP_PREPARE: - /* For this particular CPU register SCU SMP boot vector */ - shmobile_smp_hook(cpu, virt_to_phys(shmobile_boot_scu), - shmobile_scu_base_phys); - break; - }; - - return NOTIFY_OK; + /* For this particular CPU register SCU SMP boot vector */ + shmobile_smp_hook(cpu, virt_to_phys(shmobile_boot_scu), + shmobile_scu_base_phys); + return 0; } -static struct notifier_block shmobile_smp_scu_notifier = { - .notifier_call = shmobile_smp_scu_notifier_call, -}; - void __init shmobile_smp_scu_prepare_cpus(phys_addr_t scu_base_phys, unsigned int max_cpus) { @@ -54,7 +42,9 @@ void __init shmobile_smp_scu_prepare_cpus(phys_addr_t scu_base_phys, scu_power_mode(shmobile_scu_base, SCU_PM_NORMAL); /* Use CPU notifier for reset vector control */ - register_cpu_notifier(&shmobile_smp_scu_notifier); + cpuhp_setup_state_nocalls(CPUHP_ARM_SHMOBILE_SCU_PREPARE, + "arm/shmobile-scu:prepare", + shmobile_scu_cpu_prepare, NULL); } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c index 62437b57813e..73e3adbc1330 100644 --- a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c +++ b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c @@ -41,39 +41,26 @@ #define REGULATOR_IRQ_MASK BIT(2) /* IRQ2, active low */ -static void __iomem *irqc; - -static const u8 da9063_mask_regs[] = { - DA9063_REG_IRQ_MASK_A, - DA9063_REG_IRQ_MASK_B, - DA9063_REG_IRQ_MASK_C, - DA9063_REG_IRQ_MASK_D, -}; - -/* DA9210 System Control and Event Registers */ +/* start of DA9210 System Control and Event Registers */ #define DA9210_REG_MASK_A 0x54 -#define DA9210_REG_MASK_B 0x55 - -static const u8 da9210_mask_regs[] = { - DA9210_REG_MASK_A, - DA9210_REG_MASK_B, -}; - -static void da9xxx_mask_irqs(struct i2c_client *client, const u8 regs[], - unsigned int nregs) -{ - unsigned int i; - dev_info(&client->dev, "Masking %s interrupt sources\n", client->name); +static void __iomem *irqc; - for (i = 0; i < nregs; i++) { - int error = i2c_smbus_write_byte_data(client, regs[i], ~0); - if (error) { - dev_err(&client->dev, "i2c error %d\n", error); - return; - } - } -} +/* first byte sets the memory pointer, following are consecutive reg values */ +static u8 da9063_irq_clr[] = { DA9063_REG_IRQ_MASK_A, 0xff, 0xff, 0xff, 0xff }; +static u8 da9210_irq_clr[] = { DA9210_REG_MASK_A, 0xff, 0xff }; + +static struct i2c_msg da9xxx_msgs[2] = { + { + .addr = 0x58, + .len = ARRAY_SIZE(da9063_irq_clr), + .buf = da9063_irq_clr, + }, { + .addr = 0x68, + .len = ARRAY_SIZE(da9210_irq_clr), + .buf = da9210_irq_clr, + }, +}; static int regulator_quirk_notify(struct notifier_block *nb, unsigned long action, void *data) @@ -93,12 +80,15 @@ static int regulator_quirk_notify(struct notifier_block *nb, client = to_i2c_client(dev); dev_dbg(dev, "Detected %s\n", client->name); - if ((client->addr == 0x58 && !strcmp(client->name, "da9063"))) - da9xxx_mask_irqs(client, da9063_mask_regs, - ARRAY_SIZE(da9063_mask_regs)); - else if (client->addr == 0x68 && !strcmp(client->name, "da9210")) - da9xxx_mask_irqs(client, da9210_mask_regs, - ARRAY_SIZE(da9210_mask_regs)); + if ((client->addr == 0x58 && !strcmp(client->name, "da9063")) || + (client->addr == 0x68 && !strcmp(client->name, "da9210"))) { + int ret; + + dev_info(&client->dev, "clearing da9063/da9210 interrupts\n"); + ret = i2c_transfer(client->adapter, da9xxx_msgs, ARRAY_SIZE(da9xxx_msgs)); + if (ret != ARRAY_SIZE(da9xxx_msgs)) + dev_err(&client->dev, "i2c error %d\n", ret); + } mon = ioread32(irqc + IRQC_MONITOR); if (mon & REGULATOR_IRQ_MASK) diff --git a/arch/arm/mach-spear/Kconfig b/arch/arm/mach-spear/Kconfig index b7260c2b510c..1b6cae5e78f4 100644 --- a/arch/arm/mach-spear/Kconfig +++ b/arch/arm/mach-spear/Kconfig @@ -20,7 +20,6 @@ config ARCH_SPEAR13XX select HAVE_ARM_TWD if SMP select PINCTRL select MFD_SYSCON - select MIGHT_HAVE_PCI help Supports for ARM's SPEAR13XX family diff --git a/arch/arm/mach-versatile/Kconfig b/arch/arm/mach-versatile/Kconfig index b0cc26284fc9..c257d40ca51d 100644 --- a/arch/arm/mach-versatile/Kconfig +++ b/arch/arm/mach-versatile/Kconfig @@ -9,7 +9,6 @@ config ARCH_VERSATILE select CPU_ARM926T select ICST select MFD_SYSCON - select MIGHT_HAVE_PCI select PLAT_VERSATILE select POWER_RESET select POWER_RESET_VERSATILE diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index d15a7fe51618..c1799dd1d0d9 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -403,6 +403,7 @@ config CPU_V7M bool select CPU_32v7M select CPU_ABRT_NOMMU + select CPU_CACHE_V7M select CPU_CACHE_NOP select CPU_PABRT_LEGACY select CPU_THUMBONLY @@ -518,6 +519,9 @@ config CPU_CACHE_VIPT config CPU_CACHE_FA bool +config CPU_CACHE_V7M + bool + if MMU # The copy-page model config CPU_COPY_V4WT @@ -750,14 +754,14 @@ config CPU_HIGH_VECTOR config CPU_ICACHE_DISABLE bool "Disable I-Cache (I-bit)" - depends on CPU_CP15 && !(CPU_ARM720T || CPU_ARM740T || CPU_XSCALE || CPU_XSC3) + depends on (CPU_CP15 && !(CPU_ARM720T || CPU_ARM740T || CPU_XSCALE || CPU_XSC3)) || CPU_V7M help Say Y here to disable the processor instruction cache. Unless you have a reason not to or are unsure, say N. config CPU_DCACHE_DISABLE bool "Disable D-Cache (C-bit)" - depends on CPU_CP15 && !SMP + depends on (CPU_CP15 && !SMP) || CPU_V7M help Say Y here to disable the processor data cache. Unless you have a reason not to or are unsure, say N. @@ -792,7 +796,7 @@ config CPU_CACHE_ROUND_ROBIN config CPU_BPREDICT_DISABLE bool "Disable branch prediction" - depends on CPU_ARM1020 || CPU_V6 || CPU_V6K || CPU_MOHAWK || CPU_XSC3 || CPU_V7 || CPU_FA526 + depends on CPU_ARM1020 || CPU_V6 || CPU_V6K || CPU_MOHAWK || CPU_XSC3 || CPU_V7 || CPU_FA526 || CPU_V7M help Say Y here to disable branch prediction. If unsure, say N. @@ -916,6 +920,13 @@ config CACHE_L2X0 help This option enables the L2x0 PrimeCell. +config CACHE_L2X0_PMU + bool "L2x0 performance monitor support" if CACHE_L2X0 + depends on PERF_EVENTS + help + This option enables support for the performance monitoring features + of the L220 and PL310 outer cache controllers. + if CACHE_L2X0 config PL310_ERRATA_588369 diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index 7f76d96ce546..e8698241ece9 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -43,9 +43,11 @@ obj-$(CONFIG_CPU_CACHE_V6) += cache-v6.o obj-$(CONFIG_CPU_CACHE_V7) += cache-v7.o obj-$(CONFIG_CPU_CACHE_FA) += cache-fa.o obj-$(CONFIG_CPU_CACHE_NOP) += cache-nop.o +obj-$(CONFIG_CPU_CACHE_V7M) += cache-v7m.o AFLAGS_cache-v6.o :=-Wa,-march=armv6 AFLAGS_cache-v7.o :=-Wa,-march=armv7-a +AFLAGS_cache-v7m.o :=-Wa,-march=armv7-m obj-$(CONFIG_CPU_COPY_V4WT) += copypage-v4wt.o obj-$(CONFIG_CPU_COPY_V4WB) += copypage-v4wb.o @@ -101,6 +103,7 @@ AFLAGS_proc-v7.o :=-Wa,-march=armv7-a obj-$(CONFIG_OUTER_CACHE) += l2c-common.o obj-$(CONFIG_CACHE_FEROCEON_L2) += cache-feroceon-l2.o obj-$(CONFIG_CACHE_L2X0) += cache-l2x0.o l2c-l2x0-resume.o +obj-$(CONFIG_CACHE_L2X0_PMU) += cache-l2x0-pmu.o obj-$(CONFIG_CACHE_XSC3L2) += cache-xsc3l2.o obj-$(CONFIG_CACHE_TAUROS2) += cache-tauros2.o obj-$(CONFIG_CACHE_UNIPHIER) += cache-uniphier.o diff --git a/arch/arm/mm/cache-l2x0-pmu.c b/arch/arm/mm/cache-l2x0-pmu.c new file mode 100644 index 000000000000..976d3057272e --- /dev/null +++ b/arch/arm/mm/cache-l2x0-pmu.c @@ -0,0 +1,584 @@ +/* + * L220/L310 cache controller support + * + * Copyright (C) 2016 ARM Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +#include <linux/errno.h> +#include <linux/hrtimer.h> +#include <linux/io.h> +#include <linux/list.h> +#include <linux/perf_event.h> +#include <linux/printk.h> +#include <linux/slab.h> +#include <linux/types.h> + +#include <asm/hardware/cache-l2x0.h> + +#define PMU_NR_COUNTERS 2 + +static void __iomem *l2x0_base; +static struct pmu *l2x0_pmu; +static cpumask_t pmu_cpu; + +static const char *l2x0_name; + +static ktime_t l2x0_pmu_poll_period; +static struct hrtimer l2x0_pmu_hrtimer; + +/* + * The L220/PL310 PMU has two equivalent counters, Counter1 and Counter0. + * Registers controlling these are laid out in pairs, in descending order, i.e. + * the register for Counter1 comes first, followed by the register for + * Counter0. + * We ensure that idx 0 -> Counter0, and idx1 -> Counter1. + */ +static struct perf_event *events[PMU_NR_COUNTERS]; + +/* Find an unused counter */ +static int l2x0_pmu_find_idx(void) +{ + int i; + + for (i = 0; i < PMU_NR_COUNTERS; i++) { + if (!events[i]) + return i; + } + + return -1; +} + +/* How many counters are allocated? */ +static int l2x0_pmu_num_active_counters(void) +{ + int i, cnt = 0; + + for (i = 0; i < PMU_NR_COUNTERS; i++) { + if (events[i]) + cnt++; + } + + return cnt; +} + +static void l2x0_pmu_counter_config_write(int idx, u32 val) +{ + writel_relaxed(val, l2x0_base + L2X0_EVENT_CNT0_CFG - 4 * idx); +} + +static u32 l2x0_pmu_counter_read(int idx) +{ + return readl_relaxed(l2x0_base + L2X0_EVENT_CNT0_VAL - 4 * idx); +} + +static void l2x0_pmu_counter_write(int idx, u32 val) +{ + writel_relaxed(val, l2x0_base + L2X0_EVENT_CNT0_VAL - 4 * idx); +} + +static void __l2x0_pmu_enable(void) +{ + u32 val = readl_relaxed(l2x0_base + L2X0_EVENT_CNT_CTRL); + val |= L2X0_EVENT_CNT_CTRL_ENABLE; + writel_relaxed(val, l2x0_base + L2X0_EVENT_CNT_CTRL); +} + +static void __l2x0_pmu_disable(void) +{ + u32 val = readl_relaxed(l2x0_base + L2X0_EVENT_CNT_CTRL); + val &= ~L2X0_EVENT_CNT_CTRL_ENABLE; + writel_relaxed(val, l2x0_base + L2X0_EVENT_CNT_CTRL); +} + +static void l2x0_pmu_enable(struct pmu *pmu) +{ + if (l2x0_pmu_num_active_counters() == 0) + return; + + __l2x0_pmu_enable(); +} + +static void l2x0_pmu_disable(struct pmu *pmu) +{ + if (l2x0_pmu_num_active_counters() == 0) + return; + + __l2x0_pmu_disable(); +} + +static void warn_if_saturated(u32 count) +{ + if (count != 0xffffffff) + return; + + pr_warn_ratelimited("L2X0 counter saturated. Poll period too long\n"); +} + +static void l2x0_pmu_event_read(struct perf_event *event) +{ + struct hw_perf_event *hw = &event->hw; + u64 prev_count, new_count, mask; + + do { + prev_count = local64_read(&hw->prev_count); + new_count = l2x0_pmu_counter_read(hw->idx); + } while (local64_xchg(&hw->prev_count, new_count) != prev_count); + + mask = GENMASK_ULL(31, 0); + local64_add((new_count - prev_count) & mask, &event->count); + + warn_if_saturated(new_count); +} + +static void l2x0_pmu_event_configure(struct perf_event *event) +{ + struct hw_perf_event *hw = &event->hw; + + /* + * The L2X0 counters saturate at 0xffffffff rather than wrapping, so we + * will *always* lose some number of events when a counter saturates, + * and have no way of detecting how many were lost. + * + * To minimize the impact of this, we try to maximize the period by + * always starting counters at zero. To ensure that group ratios are + * representative, we poll periodically to avoid counters saturating. + * See l2x0_pmu_poll(). + */ + local64_set(&hw->prev_count, 0); + l2x0_pmu_counter_write(hw->idx, 0); +} + +static enum hrtimer_restart l2x0_pmu_poll(struct hrtimer *hrtimer) +{ + unsigned long flags; + int i; + + local_irq_save(flags); + __l2x0_pmu_disable(); + + for (i = 0; i < PMU_NR_COUNTERS; i++) { + struct perf_event *event = events[i]; + + if (!event) + continue; + + l2x0_pmu_event_read(event); + l2x0_pmu_event_configure(event); + } + + __l2x0_pmu_enable(); + local_irq_restore(flags); + + hrtimer_forward_now(hrtimer, l2x0_pmu_poll_period); + return HRTIMER_RESTART; +} + + +static void __l2x0_pmu_event_enable(int idx, u32 event) +{ + u32 val; + + val = event << L2X0_EVENT_CNT_CFG_SRC_SHIFT; + val |= L2X0_EVENT_CNT_CFG_INT_DISABLED; + l2x0_pmu_counter_config_write(idx, val); +} + +static void l2x0_pmu_event_start(struct perf_event *event, int flags) +{ + struct hw_perf_event *hw = &event->hw; + + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + if (flags & PERF_EF_RELOAD) { + WARN_ON_ONCE(!(hw->state & PERF_HES_UPTODATE)); + l2x0_pmu_event_configure(event); + } + + hw->state = 0; + + __l2x0_pmu_event_enable(hw->idx, hw->config_base); +} + +static void __l2x0_pmu_event_disable(int idx) +{ + u32 val; + + val = L2X0_EVENT_CNT_CFG_SRC_DISABLED << L2X0_EVENT_CNT_CFG_SRC_SHIFT; + val |= L2X0_EVENT_CNT_CFG_INT_DISABLED; + l2x0_pmu_counter_config_write(idx, val); +} + +static void l2x0_pmu_event_stop(struct perf_event *event, int flags) +{ + struct hw_perf_event *hw = &event->hw; + + if (WARN_ON_ONCE(event->hw.state & PERF_HES_STOPPED)) + return; + + __l2x0_pmu_event_disable(hw->idx); + + hw->state |= PERF_HES_STOPPED; + + if (flags & PERF_EF_UPDATE) { + l2x0_pmu_event_read(event); + hw->state |= PERF_HES_UPTODATE; + } +} + +static int l2x0_pmu_event_add(struct perf_event *event, int flags) +{ + struct hw_perf_event *hw = &event->hw; + int idx = l2x0_pmu_find_idx(); + + if (idx == -1) + return -EAGAIN; + + /* + * Pin the timer, so that the overflows are handled by the chosen + * event->cpu (this is the same one as presented in "cpumask" + * attribute). + */ + if (l2x0_pmu_num_active_counters() == 0) + hrtimer_start(&l2x0_pmu_hrtimer, l2x0_pmu_poll_period, + HRTIMER_MODE_REL_PINNED); + + events[idx] = event; + hw->idx = idx; + + l2x0_pmu_event_configure(event); + + hw->state = PERF_HES_STOPPED | PERF_HES_UPTODATE; + + if (flags & PERF_EF_START) + l2x0_pmu_event_start(event, 0); + + return 0; +} + +static void l2x0_pmu_event_del(struct perf_event *event, int flags) +{ + struct hw_perf_event *hw = &event->hw; + + l2x0_pmu_event_stop(event, PERF_EF_UPDATE); + + events[hw->idx] = NULL; + hw->idx = -1; + + if (l2x0_pmu_num_active_counters() == 0) + hrtimer_cancel(&l2x0_pmu_hrtimer); +} + +static bool l2x0_pmu_group_is_valid(struct perf_event *event) +{ + struct pmu *pmu = event->pmu; + struct perf_event *leader = event->group_leader; + struct perf_event *sibling; + int num_hw = 0; + + if (leader->pmu == pmu) + num_hw++; + else if (!is_software_event(leader)) + return false; + + list_for_each_entry(sibling, &leader->sibling_list, group_entry) { + if (sibling->pmu == pmu) + num_hw++; + else if (!is_software_event(sibling)) + return false; + } + + return num_hw <= PMU_NR_COUNTERS; +} + +static int l2x0_pmu_event_init(struct perf_event *event) +{ + struct hw_perf_event *hw = &event->hw; + + if (event->attr.type != l2x0_pmu->type) + return -ENOENT; + + if (is_sampling_event(event) || + event->attach_state & PERF_ATTACH_TASK) + return -EINVAL; + + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest) + return -EINVAL; + + if (event->cpu < 0) + return -EINVAL; + + if (event->attr.config & ~L2X0_EVENT_CNT_CFG_SRC_MASK) + return -EINVAL; + + hw->config_base = event->attr.config; + + if (!l2x0_pmu_group_is_valid(event)) + return -EINVAL; + + event->cpu = cpumask_first(&pmu_cpu); + + return 0; +} + +struct l2x0_event_attribute { + struct device_attribute attr; + unsigned int config; + bool pl310_only; +}; + +#define L2X0_EVENT_ATTR(_name, _config, _pl310_only) \ + (&((struct l2x0_event_attribute[]) {{ \ + .attr = __ATTR(_name, S_IRUGO, l2x0_pmu_event_show, NULL), \ + .config = _config, \ + .pl310_only = _pl310_only, \ + }})[0].attr.attr) + +#define L220_PLUS_EVENT_ATTR(_name, _config) \ + L2X0_EVENT_ATTR(_name, _config, false) + +#define PL310_EVENT_ATTR(_name, _config) \ + L2X0_EVENT_ATTR(_name, _config, true) + +static ssize_t l2x0_pmu_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct l2x0_event_attribute *lattr; + + lattr = container_of(attr, typeof(*lattr), attr); + return snprintf(buf, PAGE_SIZE, "config=0x%x\n", lattr->config); +} + +static umode_t l2x0_pmu_event_attr_is_visible(struct kobject *kobj, + struct attribute *attr, + int unused) +{ + struct device *dev = kobj_to_dev(kobj); + struct pmu *pmu = dev_get_drvdata(dev); + struct l2x0_event_attribute *lattr; + + lattr = container_of(attr, typeof(*lattr), attr.attr); + + if (!lattr->pl310_only || strcmp("l2c_310", pmu->name) == 0) + return attr->mode; + + return 0; +} + +static struct attribute *l2x0_pmu_event_attrs[] = { + L220_PLUS_EVENT_ATTR(co, 0x1), + L220_PLUS_EVENT_ATTR(drhit, 0x2), + L220_PLUS_EVENT_ATTR(drreq, 0x3), + L220_PLUS_EVENT_ATTR(dwhit, 0x4), + L220_PLUS_EVENT_ATTR(dwreq, 0x5), + L220_PLUS_EVENT_ATTR(dwtreq, 0x6), + L220_PLUS_EVENT_ATTR(irhit, 0x7), + L220_PLUS_EVENT_ATTR(irreq, 0x8), + L220_PLUS_EVENT_ATTR(wa, 0x9), + PL310_EVENT_ATTR(ipfalloc, 0xa), + PL310_EVENT_ATTR(epfhit, 0xb), + PL310_EVENT_ATTR(epfalloc, 0xc), + PL310_EVENT_ATTR(srrcvd, 0xd), + PL310_EVENT_ATTR(srconf, 0xe), + PL310_EVENT_ATTR(epfrcvd, 0xf), + NULL +}; + +static struct attribute_group l2x0_pmu_event_attrs_group = { + .name = "events", + .attrs = l2x0_pmu_event_attrs, + .is_visible = l2x0_pmu_event_attr_is_visible, +}; + +static ssize_t l2x0_pmu_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return cpumap_print_to_pagebuf(true, buf, &pmu_cpu); +} + +static struct device_attribute l2x0_pmu_cpumask_attr = + __ATTR(cpumask, S_IRUGO, l2x0_pmu_cpumask_show, NULL); + +static struct attribute *l2x0_pmu_cpumask_attrs[] = { + &l2x0_pmu_cpumask_attr.attr, + NULL, +}; + +static struct attribute_group l2x0_pmu_cpumask_attr_group = { + .attrs = l2x0_pmu_cpumask_attrs, +}; + +static const struct attribute_group *l2x0_pmu_attr_groups[] = { + &l2x0_pmu_event_attrs_group, + &l2x0_pmu_cpumask_attr_group, + NULL, +}; + +static void l2x0_pmu_reset(void) +{ + int i; + + __l2x0_pmu_disable(); + + for (i = 0; i < PMU_NR_COUNTERS; i++) + __l2x0_pmu_event_disable(i); +} + +static int l2x0_pmu_offline_cpu(unsigned int cpu) +{ + unsigned int target; + + if (!cpumask_test_and_clear_cpu(cpu, &pmu_cpu)) + return 0; + + target = cpumask_any_but(cpu_online_mask, cpu); + if (target >= nr_cpu_ids) + return 0; + + perf_pmu_migrate_context(l2x0_pmu, cpu, target); + cpumask_set_cpu(target, &pmu_cpu); + + return 0; +} + +void l2x0_pmu_suspend(void) +{ + int i; + + if (!l2x0_pmu) + return; + + l2x0_pmu_disable(l2x0_pmu); + + for (i = 0; i < PMU_NR_COUNTERS; i++) { + if (events[i]) + l2x0_pmu_event_stop(events[i], PERF_EF_UPDATE); + } + +} + +void l2x0_pmu_resume(void) +{ + int i; + + if (!l2x0_pmu) + return; + + l2x0_pmu_reset(); + + for (i = 0; i < PMU_NR_COUNTERS; i++) { + if (events[i]) + l2x0_pmu_event_start(events[i], PERF_EF_RELOAD); + } + + l2x0_pmu_enable(l2x0_pmu); +} + +void __init l2x0_pmu_register(void __iomem *base, u32 part) +{ + /* + * Determine whether we support the PMU, and choose the name for sysfs. + * This is also used by l2x0_pmu_event_attr_is_visible to determine + * which events to display, as the PL310 PMU supports a superset of + * L220 events. + * + * The L210 PMU has a different programmer's interface, and is not + * supported by this driver. + * + * We must defer registering the PMU until the perf subsystem is up and + * running, so just stash the name and base, and leave that to another + * initcall. + */ + switch (part & L2X0_CACHE_ID_PART_MASK) { + case L2X0_CACHE_ID_PART_L220: + l2x0_name = "l2c_220"; + break; + case L2X0_CACHE_ID_PART_L310: + l2x0_name = "l2c_310"; + break; + default: + return; + } + + l2x0_base = base; +} + +static __init int l2x0_pmu_init(void) +{ + int ret; + + if (!l2x0_base) + return 0; + + l2x0_pmu = kzalloc(sizeof(*l2x0_pmu), GFP_KERNEL); + if (!l2x0_pmu) { + pr_warn("Unable to allocate L2x0 PMU\n"); + return -ENOMEM; + } + + *l2x0_pmu = (struct pmu) { + .task_ctx_nr = perf_invalid_context, + .pmu_enable = l2x0_pmu_enable, + .pmu_disable = l2x0_pmu_disable, + .read = l2x0_pmu_event_read, + .start = l2x0_pmu_event_start, + .stop = l2x0_pmu_event_stop, + .add = l2x0_pmu_event_add, + .del = l2x0_pmu_event_del, + .event_init = l2x0_pmu_event_init, + .attr_groups = l2x0_pmu_attr_groups, + }; + + l2x0_pmu_reset(); + + /* + * We always use a hrtimer rather than an interrupt. + * See comments in l2x0_pmu_event_configure and l2x0_pmu_poll. + * + * Polling once a second allows the counters to fill up to 1/128th on a + * quad-core test chip with cores clocked at 400MHz. Hopefully this + * leaves sufficient headroom to avoid overflow on production silicon + * at higher frequencies. + */ + l2x0_pmu_poll_period = ms_to_ktime(1000); + hrtimer_init(&l2x0_pmu_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + l2x0_pmu_hrtimer.function = l2x0_pmu_poll; + + cpumask_set_cpu(0, &pmu_cpu); + ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_L2X0_ONLINE, + "AP_PERF_ARM_L2X0_ONLINE", NULL, + l2x0_pmu_offline_cpu); + if (ret) + goto out_pmu; + + ret = perf_pmu_register(l2x0_pmu, l2x0_name, -1); + if (ret) + goto out_cpuhp; + + return 0; + +out_cpuhp: + cpuhp_remove_state_nocalls(CPUHP_AP_PERF_ARM_L2X0_ONLINE); +out_pmu: + kfree(l2x0_pmu); + l2x0_pmu = NULL; + return ret; +} +device_initcall(l2x0_pmu_init); diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index cc12905ae6f8..d1870c777c6e 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -142,6 +142,8 @@ static void l2c_disable(void) { void __iomem *base = l2x0_base; + l2x0_pmu_suspend(); + outer_cache.flush_all(); l2c_write_sec(0, base, L2X0_CTRL); dsb(st); @@ -159,6 +161,8 @@ static void l2c_resume(void) /* Do not touch the controller if already enabled. */ if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)) l2c_enable(base, l2x0_data->num_lock); + + l2x0_pmu_resume(); } /* @@ -709,9 +713,8 @@ static void __init l2c310_fixup(void __iomem *base, u32 cache_id, if (revision >= L310_CACHE_ID_RTL_R3P0 && revision < L310_CACHE_ID_RTL_R3P2) { u32 val = l2x0_saved_regs.prefetch_ctrl; - /* I don't think bit23 is required here... but iMX6 does so */ - if (val & (BIT(30) | BIT(23))) { - val &= ~(BIT(30) | BIT(23)); + if (val & L310_PREFETCH_CTRL_DBL_LINEFILL) { + val &= ~L310_PREFETCH_CTRL_DBL_LINEFILL; l2x0_saved_regs.prefetch_ctrl = val; errata[n++] = "752271"; } @@ -892,6 +895,8 @@ static int __init __l2c_init(const struct l2c_init_data *data, pr_info("%s: CACHE_ID 0x%08x, AUX_CTRL 0x%08x\n", data->type, cache_id, aux); + l2x0_pmu_register(l2x0_base, cache_id); + return 0; } diff --git a/arch/arm/mm/cache-v7m.S b/arch/arm/mm/cache-v7m.S new file mode 100644 index 000000000000..816a7e44e6f1 --- /dev/null +++ b/arch/arm/mm/cache-v7m.S @@ -0,0 +1,453 @@ +/* + * linux/arch/arm/mm/cache-v7m.S + * + * Based on linux/arch/arm/mm/cache-v7.S + * + * Copyright (C) 2001 Deep Blue Solutions Ltd. + * Copyright (C) 2005 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This is the "shell" of the ARMv7M processor support. + */ +#include <linux/linkage.h> +#include <linux/init.h> +#include <asm/assembler.h> +#include <asm/errno.h> +#include <asm/unwind.h> +#include <asm/v7m.h> + +#include "proc-macros.S" + +/* Generic V7M read/write macros for memory mapped cache operations */ +.macro v7m_cache_read, rt, reg + movw \rt, #:lower16:BASEADDR_V7M_SCB + \reg + movt \rt, #:upper16:BASEADDR_V7M_SCB + \reg + ldr \rt, [\rt] +.endm + +.macro v7m_cacheop, rt, tmp, op, c = al + movw\c \tmp, #:lower16:BASEADDR_V7M_SCB + \op + movt\c \tmp, #:upper16:BASEADDR_V7M_SCB + \op + str\c \rt, [\tmp] +.endm + + +.macro read_ccsidr, rt + v7m_cache_read \rt, V7M_SCB_CCSIDR +.endm + +.macro read_clidr, rt + v7m_cache_read \rt, V7M_SCB_CLIDR +.endm + +.macro write_csselr, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_CSSELR +.endm + +/* + * dcisw: Invalidate data cache by set/way + */ +.macro dcisw, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_DCISW +.endm + +/* + * dccisw: Clean and invalidate data cache by set/way + */ +.macro dccisw, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_DCCISW +.endm + +/* + * dccimvac: Clean and invalidate data cache line by MVA to PoC. + */ +.irp c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo +.macro dccimvac\c, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_DCCIMVAC, \c +.endm +.endr + +/* + * dcimvac: Invalidate data cache line by MVA to PoC + */ +.macro dcimvac, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_DCIMVAC +.endm + +/* + * dccmvau: Clean data cache line by MVA to PoU + */ +.macro dccmvau, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_DCCMVAU +.endm + +/* + * dccmvac: Clean data cache line by MVA to PoC + */ +.macro dccmvac, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_DCCMVAC +.endm + +/* + * icimvau: Invalidate instruction caches by MVA to PoU + */ +.macro icimvau, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_ICIMVAU +.endm + +/* + * Invalidate the icache, inner shareable if SMP, invalidate BTB for UP. + * rt data ignored by ICIALLU(IS), so can be used for the address + */ +.macro invalidate_icache, rt + v7m_cacheop \rt, \rt, V7M_SCB_ICIALLU + mov \rt, #0 +.endm + +/* + * Invalidate the BTB, inner shareable if SMP. + * rt data ignored by BPIALL, so it can be used for the address + */ +.macro invalidate_bp, rt + v7m_cacheop \rt, \rt, V7M_SCB_BPIALL + mov \rt, #0 +.endm + +ENTRY(v7m_invalidate_l1) + mov r0, #0 + + write_csselr r0, r1 + read_ccsidr r0 + + movw r1, #0x7fff + and r2, r1, r0, lsr #13 + + movw r1, #0x3ff + + and r3, r1, r0, lsr #3 @ NumWays - 1 + add r2, r2, #1 @ NumSets + + and r0, r0, #0x7 + add r0, r0, #4 @ SetShift + + clz r1, r3 @ WayShift + add r4, r3, #1 @ NumWays +1: sub r2, r2, #1 @ NumSets-- + mov r3, r4 @ Temp = NumWays +2: subs r3, r3, #1 @ Temp-- + mov r5, r3, lsl r1 + mov r6, r2, lsl r0 + orr r5, r5, r6 @ Reg = (Temp<<WayShift)|(NumSets<<SetShift) + dcisw r5, r6 + bgt 2b + cmp r2, #0 + bgt 1b + dsb st + isb + ret lr +ENDPROC(v7m_invalidate_l1) + +/* + * v7m_flush_icache_all() + * + * Flush the whole I-cache. + * + * Registers: + * r0 - set to 0 + */ +ENTRY(v7m_flush_icache_all) + invalidate_icache r0 + ret lr +ENDPROC(v7m_flush_icache_all) + +/* + * v7m_flush_dcache_all() + * + * Flush the whole D-cache. + * + * Corrupted registers: r0-r7, r9-r11 + */ +ENTRY(v7m_flush_dcache_all) + dmb @ ensure ordering with previous memory accesses + read_clidr r0 + mov r3, r0, lsr #23 @ move LoC into position + ands r3, r3, #7 << 1 @ extract LoC*2 from clidr + beq finished @ if loc is 0, then no need to clean +start_flush_levels: + mov r10, #0 @ start clean at cache level 0 +flush_levels: + add r2, r10, r10, lsr #1 @ work out 3x current cache level + mov r1, r0, lsr r2 @ extract cache type bits from clidr + and r1, r1, #7 @ mask of the bits for current cache only + cmp r1, #2 @ see what cache we have at this level + blt skip @ skip if no cache, or just i-cache +#ifdef CONFIG_PREEMPT + save_and_disable_irqs_notrace r9 @ make cssr&csidr read atomic +#endif + write_csselr r10, r1 @ set current cache level + isb @ isb to sych the new cssr&csidr + read_ccsidr r1 @ read the new csidr +#ifdef CONFIG_PREEMPT + restore_irqs_notrace r9 +#endif + and r2, r1, #7 @ extract the length of the cache lines + add r2, r2, #4 @ add 4 (line length offset) + movw r4, #0x3ff + ands r4, r4, r1, lsr #3 @ find maximum number on the way size + clz r5, r4 @ find bit position of way size increment + movw r7, #0x7fff + ands r7, r7, r1, lsr #13 @ extract max number of the index size +loop1: + mov r9, r7 @ create working copy of max index +loop2: + lsl r6, r4, r5 + orr r11, r10, r6 @ factor way and cache number into r11 + lsl r6, r9, r2 + orr r11, r11, r6 @ factor index number into r11 + dccisw r11, r6 @ clean/invalidate by set/way + subs r9, r9, #1 @ decrement the index + bge loop2 + subs r4, r4, #1 @ decrement the way + bge loop1 +skip: + add r10, r10, #2 @ increment cache number + cmp r3, r10 + bgt flush_levels +finished: + mov r10, #0 @ swith back to cache level 0 + write_csselr r10, r3 @ select current cache level in cssr + dsb st + isb + ret lr +ENDPROC(v7m_flush_dcache_all) + +/* + * v7m_flush_cache_all() + * + * Flush the entire cache system. + * The data cache flush is now achieved using atomic clean / invalidates + * working outwards from L1 cache. This is done using Set/Way based cache + * maintenance instructions. + * The instruction cache can still be invalidated back to the point of + * unification in a single instruction. + * + */ +ENTRY(v7m_flush_kern_cache_all) + stmfd sp!, {r4-r7, r9-r11, lr} + bl v7m_flush_dcache_all + invalidate_icache r0 + ldmfd sp!, {r4-r7, r9-r11, lr} + ret lr +ENDPROC(v7m_flush_kern_cache_all) + +/* + * v7m_flush_cache_all() + * + * Flush all TLB entries in a particular address space + * + * - mm - mm_struct describing address space + */ +ENTRY(v7m_flush_user_cache_all) + /*FALLTHROUGH*/ + +/* + * v7m_flush_cache_range(start, end, flags) + * + * Flush a range of TLB entries in the specified address space. + * + * - start - start address (may not be aligned) + * - end - end address (exclusive, may not be aligned) + * - flags - vm_area_struct flags describing address space + * + * It is assumed that: + * - we have a VIPT cache. + */ +ENTRY(v7m_flush_user_cache_range) + ret lr +ENDPROC(v7m_flush_user_cache_all) +ENDPROC(v7m_flush_user_cache_range) + +/* + * v7m_coherent_kern_range(start,end) + * + * Ensure that the I and D caches are coherent within specified + * region. This is typically used when code has been written to + * a memory region, and will be executed. + * + * - start - virtual start address of region + * - end - virtual end address of region + * + * It is assumed that: + * - the Icache does not read data from the write buffer + */ +ENTRY(v7m_coherent_kern_range) + /* FALLTHROUGH */ + +/* + * v7m_coherent_user_range(start,end) + * + * Ensure that the I and D caches are coherent within specified + * region. This is typically used when code has been written to + * a memory region, and will be executed. + * + * - start - virtual start address of region + * - end - virtual end address of region + * + * It is assumed that: + * - the Icache does not read data from the write buffer + */ +ENTRY(v7m_coherent_user_range) + UNWIND(.fnstart ) + dcache_line_size r2, r3 + sub r3, r2, #1 + bic r12, r0, r3 +1: +/* + * We use open coded version of dccmvau otherwise USER() would + * point at movw instruction. + */ + dccmvau r12, r3 + add r12, r12, r2 + cmp r12, r1 + blo 1b + dsb ishst + icache_line_size r2, r3 + sub r3, r2, #1 + bic r12, r0, r3 +2: + icimvau r12, r3 + add r12, r12, r2 + cmp r12, r1 + blo 2b + invalidate_bp r0 + dsb ishst + isb + ret lr + UNWIND(.fnend ) +ENDPROC(v7m_coherent_kern_range) +ENDPROC(v7m_coherent_user_range) + +/* + * v7m_flush_kern_dcache_area(void *addr, size_t size) + * + * Ensure that the data held in the page kaddr is written back + * to the page in question. + * + * - addr - kernel address + * - size - region size + */ +ENTRY(v7m_flush_kern_dcache_area) + dcache_line_size r2, r3 + add r1, r0, r1 + sub r3, r2, #1 + bic r0, r0, r3 +1: + dccimvac r0, r3 @ clean & invalidate D line / unified line + add r0, r0, r2 + cmp r0, r1 + blo 1b + dsb st + ret lr +ENDPROC(v7m_flush_kern_dcache_area) + +/* + * v7m_dma_inv_range(start,end) + * + * Invalidate the data cache within the specified region; we will + * be performing a DMA operation in this region and we want to + * purge old data in the cache. + * + * - start - virtual start address of region + * - end - virtual end address of region + */ +v7m_dma_inv_range: + dcache_line_size r2, r3 + sub r3, r2, #1 + tst r0, r3 + bic r0, r0, r3 + dccimvacne r0, r3 + subne r3, r2, #1 @ restore r3, corrupted by v7m's dccimvac + tst r1, r3 + bic r1, r1, r3 + dccimvacne r1, r3 +1: + dcimvac r0, r3 + add r0, r0, r2 + cmp r0, r1 + blo 1b + dsb st + ret lr +ENDPROC(v7m_dma_inv_range) + +/* + * v7m_dma_clean_range(start,end) + * - start - virtual start address of region + * - end - virtual end address of region + */ +v7m_dma_clean_range: + dcache_line_size r2, r3 + sub r3, r2, #1 + bic r0, r0, r3 +1: + dccmvac r0, r3 @ clean D / U line + add r0, r0, r2 + cmp r0, r1 + blo 1b + dsb st + ret lr +ENDPROC(v7m_dma_clean_range) + +/* + * v7m_dma_flush_range(start,end) + * - start - virtual start address of region + * - end - virtual end address of region + */ +ENTRY(v7m_dma_flush_range) + dcache_line_size r2, r3 + sub r3, r2, #1 + bic r0, r0, r3 +1: + dccimvac r0, r3 @ clean & invalidate D / U line + add r0, r0, r2 + cmp r0, r1 + blo 1b + dsb st + ret lr +ENDPROC(v7m_dma_flush_range) + +/* + * dma_map_area(start, size, dir) + * - start - kernel virtual start address + * - size - size of region + * - dir - DMA direction + */ +ENTRY(v7m_dma_map_area) + add r1, r1, r0 + teq r2, #DMA_FROM_DEVICE + beq v7m_dma_inv_range + b v7m_dma_clean_range +ENDPROC(v7m_dma_map_area) + +/* + * dma_unmap_area(start, size, dir) + * - start - kernel virtual start address + * - size - size of region + * - dir - DMA direction + */ +ENTRY(v7m_dma_unmap_area) + add r1, r1, r0 + teq r2, #DMA_TO_DEVICE + bne v7m_dma_inv_range + ret lr +ENDPROC(v7m_dma_unmap_area) + + .globl v7m_flush_kern_cache_louis + .equ v7m_flush_kern_cache_louis, v7m_flush_kern_cache_all + + __INITDATA + + @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S) + define_cache_functions v7m diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index c6834c0cfd1c..ab4f74536057 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -436,7 +436,7 @@ static int __init atomic_pool_init(void) gen_pool_set_algo(atomic_pool, gen_pool_first_fit_order_align, (void *)PAGE_SHIFT); - pr_info("DMA: preallocated %zd KiB pool for atomic coherent allocations\n", + pr_info("DMA: preallocated %zu KiB pool for atomic coherent allocations\n", atomic_pool_size / 1024); return 0; } @@ -445,7 +445,7 @@ destroy_genpool: gen_pool_destroy(atomic_pool); atomic_pool = NULL; out: - pr_err("DMA: failed to allocate %zx KiB pool for atomic coherent allocation\n", + pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n", atomic_pool_size / 1024); return -ENOMEM; } @@ -2014,6 +2014,63 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle, __free_iova(mapping, iova, len); } +/** + * arm_iommu_map_resource - map a device resource for DMA + * @dev: valid struct device pointer + * @phys_addr: physical address of resource + * @size: size of resource to map + * @dir: DMA transfer direction + */ +static dma_addr_t arm_iommu_map_resource(struct device *dev, + phys_addr_t phys_addr, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); + dma_addr_t dma_addr; + int ret, prot; + phys_addr_t addr = phys_addr & PAGE_MASK; + unsigned int offset = phys_addr & ~PAGE_MASK; + size_t len = PAGE_ALIGN(size + offset); + + dma_addr = __alloc_iova(mapping, len); + if (dma_addr == DMA_ERROR_CODE) + return dma_addr; + + prot = __dma_direction_to_prot(dir) | IOMMU_MMIO; + + ret = iommu_map(mapping->domain, dma_addr, addr, len, prot); + if (ret < 0) + goto fail; + + return dma_addr + offset; +fail: + __free_iova(mapping, dma_addr, len); + return DMA_ERROR_CODE; +} + +/** + * arm_iommu_unmap_resource - unmap a device DMA resource + * @dev: valid struct device pointer + * @dma_handle: DMA address to resource + * @size: size of resource to map + * @dir: DMA transfer direction + */ +static void arm_iommu_unmap_resource(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); + dma_addr_t iova = dma_handle & PAGE_MASK; + unsigned int offset = dma_handle & ~PAGE_MASK; + size_t len = PAGE_ALIGN(size + offset); + + if (!iova) + return; + + iommu_unmap(mapping->domain, iova, len); + __free_iova(mapping, iova, len); +} + static void arm_iommu_sync_single_for_cpu(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir) { @@ -2057,6 +2114,9 @@ struct dma_map_ops iommu_ops = { .unmap_sg = arm_iommu_unmap_sg, .sync_sg_for_cpu = arm_iommu_sync_sg_for_cpu, .sync_sg_for_device = arm_iommu_sync_sg_for_device, + + .map_resource = arm_iommu_map_resource, + .unmap_resource = arm_iommu_unmap_resource, }; struct dma_map_ops iommu_coherent_ops = { @@ -2070,6 +2130,9 @@ struct dma_map_ops iommu_coherent_ops = { .map_sg = arm_coherent_iommu_map_sg, .unmap_sg = arm_coherent_iommu_unmap_sg, + + .map_resource = arm_iommu_map_resource, + .unmap_resource = arm_iommu_unmap_resource, }; /** diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 6344913f0804..4001dd15818d 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -137,7 +137,7 @@ void __init init_default_cache_policy(unsigned long pmd) initial_pmd_value = pmd; - pmd &= PMD_SECT_TEX(1) | PMD_SECT_BUFFERABLE | PMD_SECT_CACHEABLE; + pmd &= PMD_SECT_CACHE_MASK; for (i = 0; i < ARRAY_SIZE(cache_policies); i++) if (cache_policies[i].pmd == pmd) { @@ -243,7 +243,7 @@ __setup("noalign", noalign_setup); #define PROT_PTE_S2_DEVICE PROT_PTE_DEVICE #define PROT_SECT_DEVICE PMD_TYPE_SECT|PMD_SECT_AP_WRITE -static struct mem_type mem_types[] = { +static struct mem_type mem_types[] __ro_after_init = { [MT_DEVICE] = { /* Strongly ordered / ARMv6 shared device */ .prot_pte = PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED | L_PTE_SHARED, diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index c671f345266a..0d40c285bd86 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -7,6 +7,10 @@ #include <asm/asm-offsets.h> #include <asm/thread_info.h> +#ifdef CONFIG_CPU_V7M +#include <asm/v7m.h> +#endif + /* * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm) */ @@ -70,7 +74,13 @@ * on ARMv7. */ .macro dcache_line_size, reg, tmp +#ifdef CONFIG_CPU_V7M + movw \tmp, #:lower16:BASEADDR_V7M_SCB + V7M_SCB_CTR + movt \tmp, #:upper16:BASEADDR_V7M_SCB + V7M_SCB_CTR + ldr \tmp, [\tmp] +#else mrc p15, 0, \tmp, c0, c0, 1 @ read ctr +#endif lsr \tmp, \tmp, #16 and \tmp, \tmp, #0xf @ cache line size encoding mov \reg, #4 @ bytes per word @@ -82,7 +92,13 @@ * on ARMv7. */ .macro icache_line_size, reg, tmp +#ifdef CONFIG_CPU_V7M + movw \tmp, #:lower16:BASEADDR_V7M_SCB + V7M_SCB_CTR + movt \tmp, #:upper16:BASEADDR_V7M_SCB + V7M_SCB_CTR + ldr \tmp, [\tmp] +#else mrc p15, 0, \tmp, c0, c0, 1 @ read ctr +#endif and \tmp, \tmp, #0xf @ cache line size encoding mov \reg, #4 @ bytes per word mov \reg, \reg, lsl \tmp @ actual cache line size diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index a7123b4e129d..d00d52c9de3e 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -16,6 +16,7 @@ #include <asm/hwcap.h> #include <asm/pgtable-hwdef.h> #include <asm/pgtable.h> +#include <asm/memory.h> #include "proc-macros.S" diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S index 7229d8d0be1a..f6d333f09bfe 100644 --- a/arch/arm/mm/proc-v7m.S +++ b/arch/arm/mm/proc-v7m.S @@ -74,14 +74,42 @@ ENTRY(cpu_v7m_do_resume) ENDPROC(cpu_v7m_do_resume) #endif +ENTRY(cpu_cm7_dcache_clean_area) + dcache_line_size r2, r3 + movw r3, #:lower16:BASEADDR_V7M_SCB + V7M_SCB_DCCMVAC + movt r3, #:upper16:BASEADDR_V7M_SCB + V7M_SCB_DCCMVAC + +1: str r0, [r3] @ clean D entry + add r0, r0, r2 + subs r1, r1, r2 + bhi 1b + dsb + ret lr +ENDPROC(cpu_cm7_dcache_clean_area) + +ENTRY(cpu_cm7_proc_fin) + movw r2, #:lower16:(BASEADDR_V7M_SCB + V7M_SCB_CCR) + movt r2, #:upper16:(BASEADDR_V7M_SCB + V7M_SCB_CCR) + ldr r0, [r2] + bic r0, r0, #(V7M_SCB_CCR_DC | V7M_SCB_CCR_IC) + str r0, [r2] + ret lr +ENDPROC(cpu_cm7_proc_fin) + .section ".text.init", #alloc, #execinstr +__v7m_cm7_setup: + mov r8, #(V7M_SCB_CCR_DC | V7M_SCB_CCR_IC| V7M_SCB_CCR_BP) + b __v7m_setup_cont /* * __v7m_setup * * This should be able to cover all ARMv7-M cores. */ __v7m_setup: + mov r8, 0 + +__v7m_setup_cont: @ Configure the vector table base address ldr r0, =BASEADDR_V7M_SCB ldr r12, =vector_table @@ -104,6 +132,7 @@ __v7m_setup: badr r1, 1f ldr r5, [r12, #11 * 4] @ read the SVC vector entry str r1, [r12, #11 * 4] @ write the temporary SVC vector entry + dsb mov r6, lr @ save LR ldr sp, =init_thread_union + THREAD_START_SP cpsie i @@ -116,15 +145,32 @@ __v7m_setup: mov r1, #1 msr control, r1 @ Thread mode has unpriviledged access + @ Configure caches (if implemented) + teq r8, #0 + stmneia r12, {r0-r6, lr} @ v7m_invalidate_l1 touches r0-r6 + blne v7m_invalidate_l1 + teq r8, #0 @ re-evalutae condition + ldmneia r12, {r0-r6, lr} + @ Configure the System Control Register to ensure 8-byte stack alignment @ Note the STKALIGN bit is either RW or RAO. - ldr r12, [r0, V7M_SCB_CCR] @ system control register - orr r12, #V7M_SCB_CCR_STKALIGN - str r12, [r0, V7M_SCB_CCR] + ldr r0, [r0, V7M_SCB_CCR] @ system control register + orr r0, #V7M_SCB_CCR_STKALIGN + orr r0, r0, r8 + ret lr ENDPROC(__v7m_setup) +/* + * Cortex-M7 processor functions + */ + globl_equ cpu_cm7_proc_init, cpu_v7m_proc_init + globl_equ cpu_cm7_reset, cpu_v7m_reset + globl_equ cpu_cm7_do_idle, cpu_v7m_do_idle + globl_equ cpu_cm7_switch_mm, cpu_v7m_switch_mm + define_processor_functions v7m, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1 + define_processor_functions cm7, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1 .section ".rodata" string cpu_arch_name, "armv7m" @@ -133,6 +179,50 @@ ENDPROC(__v7m_setup) .section ".proc.info.init", #alloc +.macro __v7m_proc name, initfunc, cache_fns = nop_cache_fns, hwcaps = 0, proc_fns = v7m_processor_functions + .long 0 /* proc_info_list.__cpu_mm_mmu_flags */ + .long 0 /* proc_info_list.__cpu_io_mmu_flags */ + initfn \initfunc, \name + .long cpu_arch_name + .long cpu_elf_name + .long HWCAP_HALF | HWCAP_THUMB | HWCAP_FAST_MULT | \hwcaps + .long cpu_v7m_name + .long \proc_fns + .long 0 /* proc_info_list.tlb */ + .long 0 /* proc_info_list.user */ + .long \cache_fns +.endm + + /* + * Match ARM Cortex-M7 processor. + */ + .type __v7m_cm7_proc_info, #object +__v7m_cm7_proc_info: + .long 0x410fc270 /* ARM Cortex-M7 0xC27 */ + .long 0xff0ffff0 /* Mask off revision, patch release */ + __v7m_proc __v7m_cm7_proc_info, __v7m_cm7_setup, hwcaps = HWCAP_EDSP, cache_fns = v7m_cache_fns, proc_fns = cm7_processor_functions + .size __v7m_cm7_proc_info, . - __v7m_cm7_proc_info + + /* + * Match ARM Cortex-M4 processor. + */ + .type __v7m_cm4_proc_info, #object +__v7m_cm4_proc_info: + .long 0x410fc240 /* ARM Cortex-M4 0xC24 */ + .long 0xff0ffff0 /* Mask off revision, patch release */ + __v7m_proc __v7m_cm4_proc_info, __v7m_setup, hwcaps = HWCAP_EDSP + .size __v7m_cm4_proc_info, . - __v7m_cm4_proc_info + + /* + * Match ARM Cortex-M3 processor. + */ + .type __v7m_cm3_proc_info, #object +__v7m_cm3_proc_info: + .long 0x410fc230 /* ARM Cortex-M3 0xC23 */ + .long 0xff0ffff0 /* Mask off revision, patch release */ + __v7m_proc __v7m_cm3_proc_info, __v7m_setup + .size __v7m_cm3_proc_info, . - __v7m_cm3_proc_info + /* * Match any ARMv7-M processor core. */ @@ -140,16 +230,6 @@ ENDPROC(__v7m_setup) __v7m_proc_info: .long 0x000f0000 @ Required ID value .long 0x000f0000 @ Mask for ID - .long 0 @ proc_info_list.__cpu_mm_mmu_flags - .long 0 @ proc_info_list.__cpu_io_mmu_flags - initfn __v7m_setup, __v7m_proc_info @ proc_info_list.__cpu_flush - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT - .long cpu_v7m_name - .long v7m_processor_functions @ proc_info_list.proc - .long 0 @ proc_info_list.tlb - .long 0 @ proc_info_list.user - .long nop_cache_fns @ proc_info_list.cache + __v7m_proc __v7m_proc_info, __v7m_setup .size __v7m_proc_info, . - __v7m_proc_info diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 3d2cef6488ea..f193414d0f6f 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -170,9 +170,6 @@ static int xen_starting_cpu(unsigned int cpu) pr_info("Xen: initializing cpu%d\n", cpu); vcpup = per_cpu_ptr(xen_vcpu_info, cpu); - /* Direct vCPU id mapping for ARM guests. */ - per_cpu(xen_vcpu_id, cpu) = cpu; - info.mfn = virt_to_gfn(vcpup); info.offset = xen_offset_in_page(vcpup); @@ -330,6 +327,7 @@ static int __init xen_guest_init(void) { struct xen_add_to_physmap xatp; struct shared_info *shared_info_page = NULL; + int cpu; if (!xen_domain()) return 0; @@ -380,7 +378,8 @@ static int __init xen_guest_init(void) return -ENOMEM; /* Direct vCPU id mapping for ARM guests. */ - per_cpu(xen_vcpu_id, 0) = 0; + for_each_possible_cpu(cpu) + per_cpu(xen_vcpu_id, cpu) = cpu; xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames(); if (xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn, diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index bc3f00f586f1..01600401a53e 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -4,6 +4,8 @@ config ARM64 select ACPI_GENERIC_GSI if ACPI select ACPI_REDUCED_HARDWARE_ONLY if ACPI select ACPI_MCFG if ACPI + select ACPI_SPCR_TABLE if ACPI + select ARCH_CLOCKSOURCE_DATA select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE @@ -15,7 +17,6 @@ config ARM64 select ARCH_USE_CMPXCHG_LOCKREF select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_NUMA_BALANCING - select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_COMPAT_IPC_PARSE_VERSION select ARCH_WANT_FRAME_POINTERS select ARCH_HAS_UBSAN_SANITIZE_ALL @@ -102,10 +103,8 @@ config ARM64 select NO_BOOTMEM select OF select OF_EARLY_FLATTREE - select OF_NUMA if NUMA && OF select OF_RESERVED_MEM select PCI_ECAM if ACPI - select PERF_USE_VMALLOC select POWER_RESET select POWER_SUPPLY select SPARSE_IRQ @@ -122,6 +121,9 @@ config ARCH_PHYS_ADDR_T_64BIT config MMU def_bool y +config DEBUG_RODATA + def_bool y + config ARM64_PAGE_SHIFT int default 16 if ARM64_64K_PAGES @@ -415,18 +417,13 @@ config ARM64_ERRATUM_845719 config ARM64_ERRATUM_843419 bool "Cortex-A53: 843419: A load or store might access an incorrect address" - depends on MODULES default y - select ARM64_MODULE_CMODEL_LARGE + select ARM64_MODULE_CMODEL_LARGE if MODULES help - This option builds kernel modules using the large memory model in - order to avoid the use of the ADRP instruction, which can cause - a subsequent memory access to use an incorrect address on Cortex-A53 - parts up to r0p4. - - Note that the kernel itself must be linked with a version of ld - which fixes potentially affected ADRP instructions through the - use of veneers. + This option links the kernel with '--fix-cortex-a53-843419' and + builds modules using the large memory model in order to avoid the use + of the ADRP instruction, which can cause a subsequent memory access + to use an incorrect address on Cortex-A53 parts up to r0p4. If unsure, say Y. @@ -582,7 +579,8 @@ config HOTPLUG_CPU # Common NUMA Features config NUMA bool "Numa Memory Allocation and Scheduler Support" - depends on SMP + select ACPI_NUMA if ACPI + select OF_NUMA help Enable NUMA (Non Uniform Memory Access) support. @@ -603,11 +601,18 @@ config USE_PERCPU_NUMA_NODE_ID def_bool y depends on NUMA +config HAVE_SETUP_PER_CPU_AREA + def_bool y + depends on NUMA + +config NEED_PER_CPU_EMBED_FIRST_CHUNK + def_bool y + depends on NUMA + source kernel/Kconfig.preempt source kernel/Kconfig.hz config ARCH_SUPPORTS_DEBUG_PAGEALLOC - depends on !HIBERNATION def_bool y config ARCH_HAS_HOLES_MEMORYMODEL diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index 0cc758cdd0dc..b661fe742615 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -49,16 +49,6 @@ config DEBUG_SET_MODULE_RONX If in doubt, say Y. -config DEBUG_RODATA - bool "Make kernel text and rodata read-only" - default y - help - If this is set, kernel text and rodata will be made read-only. This - is to help catch accidental or malicious attempts to change the - kernel's executable code. - - If in doubt, say Y. - config DEBUG_ALIGN_RODATA depends on DEBUG_RODATA bool "Align linker sections up to SECTION_SIZE" diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index be5d824ebdba..b6b36570b1c0 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -15,8 +15,8 @@ config ARCH_ALPINE config ARCH_BCM2835 bool "Broadcom BCM2835 family" - select ARCH_REQUIRE_GPIOLIB select CLKSRC_OF + select GPIOLIB select PINCTRL select PINCTRL_BCM2835 select ARM_AMBA @@ -29,15 +29,15 @@ config ARCH_BCM2835 config ARCH_BCM_IPROC bool "Broadcom iProc SoC Family" select COMMON_CLK_IPROC + select GPIOLIB select PINCTRL - select ARCH_REQUIRE_GPIOLIB help This enables support for Broadcom iProc based SoCs config ARCH_BERLIN bool "Marvell Berlin SoC Family" - select ARCH_REQUIRE_GPIOLIB select DW_APB_ICTL + select GPIOLIB select PINCTRL help This enables support for Marvell Berlin SoC Family @@ -55,6 +55,7 @@ config ARCH_EXYNOS config ARCH_LAYERSCAPE bool "ARMv8 based Freescale Layerscape SoC family" + select EDAC_SUPPORT help This enables support for the Freescale Layerscape SoC family. @@ -93,6 +94,7 @@ config ARCH_MVEBU select ARMADA_CP110_SYSCON select ARMADA_37XX_CLK select MVEBU_ODMI + select MVEBU_PIC help This enables support for Marvell EBU familly, including: - Armada 3700 SoC Family @@ -108,7 +110,7 @@ config ARCH_QCOM config ARCH_ROCKCHIP bool "Rockchip Platforms" select ARCH_HAS_RESET_CONTROLLER - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB select PINCTRL select PINCTRL_ROCKCHIP select ROCKCHIP_TIMER @@ -154,12 +156,11 @@ config ARCH_STRATIX10 config ARCH_TEGRA bool "NVIDIA Tegra SoC Family" select ARCH_HAS_RESET_CONTROLLER - select ARCH_REQUIRE_GPIOLIB select CLKDEV_LOOKUP select CLKSRC_MMIO select CLKSRC_OF select GENERIC_CLOCKEVENTS - select HAVE_CLK + select GPIOLIB select PINCTRL select RESET_CONTROLLER help @@ -183,8 +184,8 @@ config ARCH_UNIPHIER config ARCH_VEXPRESS bool "ARMv8 software model (Versatile Express)" - select ARCH_REQUIRE_GPIOLIB select COMMON_CLK_VERSATILE + select GPIOLIB select PM select PM_GENERIC_DOMAINS select POWER_RESET_VEXPRESS diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 5b54f8c021d8..ab51aed6b6c1 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -18,6 +18,14 @@ ifneq ($(CONFIG_RELOCATABLE),) LDFLAGS_vmlinux += -pie -Bsymbolic endif +ifeq ($(CONFIG_ARM64_ERRATUM_843419),y) + ifeq ($(call ld-option, --fix-cortex-a53-843419),) +$(warning ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum) + else +LDFLAGS_vmlinux += --fix-cortex-a53-843419 + endif +endif + KBUILD_DEFCONFIG := defconfig # Check for binutils support for specific extensions @@ -38,10 +46,12 @@ ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) KBUILD_CPPFLAGS += -mbig-endian AS += -EB LD += -EB +UTS_MACHINE := aarch64_be else KBUILD_CPPFLAGS += -mlittle-endian AS += -EL LD += -EL +UTS_MACHINE := aarch64 endif CHECKFLAGS += -D__aarch64__ diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi index 445aa678f914..c2b9bcb0ef61 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi @@ -255,10 +255,10 @@ /* Local timer */ timer { compatible = "arm,armv8-timer"; - interrupts = <1 13 0xf01>, - <1 14 0xf01>, - <1 11 0xf01>, - <1 10 0xf01>; + interrupts = <1 13 0xf08>, + <1 14 0xf08>, + <1 11 0xf08>, + <1 10 0xf08>; }; timer0: timer0@ffc03000 { diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi index e502c24b0ac7..bf6c8d051002 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi @@ -102,13 +102,13 @@ timer { compatible = "arm,armv8-timer"; interrupts = <GIC_PPI 13 - (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>, + (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>, <GIC_PPI 14 - (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>, + (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>, <GIC_PPI 11 - (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>, + (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>, <GIC_PPI 10 - (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>; + (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>; }; xtal: xtal-clk { diff --git a/arch/arm64/boot/dts/apm/apm-mustang.dts b/arch/arm64/boot/dts/apm/apm-mustang.dts index b7fb5d9295c2..32a961c5e98a 100644 --- a/arch/arm64/boot/dts/apm/apm-mustang.dts +++ b/arch/arm64/boot/dts/apm/apm-mustang.dts @@ -74,6 +74,7 @@ &xgenet { status = "ok"; + rxlos-gpios = <&sbgpio 12 1>; }; &mmc0 { diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi index f1c2c713f9b0..31ea70a5a3ff 100644 --- a/arch/arm64/boot/dts/apm/apm-storm.dtsi +++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi @@ -110,10 +110,10 @@ timer { compatible = "arm,armv8-timer"; - interrupts = <1 0 0xff01>, /* Secure Phys IRQ */ - <1 13 0xff01>, /* Non-secure Phys IRQ */ - <1 14 0xff01>, /* Virt IRQ */ - <1 15 0xff01>; /* Hyp IRQ */ + interrupts = <1 0 0xff08>, /* Secure Phys IRQ */ + <1 13 0xff08>, /* Non-secure Phys IRQ */ + <1 14 0xff08>, /* Virt IRQ */ + <1 15 0xff08>; /* Hyp IRQ */ clock-frequency = <50000000>; }; @@ -923,7 +923,7 @@ /* mac address will be overwritten by the bootloader */ local-mac-address = [00 00 00 00 00 00]; phy-connection-type = "rgmii"; - phy-handle = <&menet0phy>,<&menetphy>; + phy-handle = <&menetphy>,<&menet0phy>; mdio { compatible = "apm,xgene-mdio"; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/broadcom/bcm2835-rpi.dtsi b/arch/arm64/boot/dts/broadcom/bcm2835-rpi.dtsi new file mode 120000 index 000000000000..3937b77cb310 --- /dev/null +++ b/arch/arm64/boot/dts/broadcom/bcm2835-rpi.dtsi @@ -0,0 +1 @@ +../../../../arm/boot/dts/bcm2835-rpi.dtsi
\ No newline at end of file diff --git a/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts b/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts index 6f47dd2bb1db..7841b724e340 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts +++ b/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts @@ -1,7 +1,7 @@ /dts-v1/; #include "bcm2837.dtsi" -#include "../../../../arm/boot/dts/bcm2835-rpi.dtsi" -#include "../../../../arm/boot/dts/bcm283x-rpi-smsc9514.dtsi" +#include "bcm2835-rpi.dtsi" +#include "bcm283x-rpi-smsc9514.dtsi" / { compatible = "raspberrypi,3-model-b", "brcm,bcm2837"; diff --git a/arch/arm64/boot/dts/broadcom/bcm2837.dtsi b/arch/arm64/boot/dts/broadcom/bcm2837.dtsi index f2a31d06845d..8216bbb29fe0 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2837.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcm2837.dtsi @@ -1,4 +1,4 @@ -#include "../../../../arm/boot/dts/bcm283x.dtsi" +#include "bcm283x.dtsi" / { compatible = "brcm,bcm2836"; diff --git a/arch/arm64/boot/dts/broadcom/bcm283x-rpi-smsc9514.dtsi b/arch/arm64/boot/dts/broadcom/bcm283x-rpi-smsc9514.dtsi new file mode 120000 index 000000000000..dca7c057d5a5 --- /dev/null +++ b/arch/arm64/boot/dts/broadcom/bcm283x-rpi-smsc9514.dtsi @@ -0,0 +1 @@ +../../../../arm/boot/dts/bcm283x-rpi-smsc9514.dtsi
\ No newline at end of file diff --git a/arch/arm64/boot/dts/broadcom/bcm283x.dtsi b/arch/arm64/boot/dts/broadcom/bcm283x.dtsi new file mode 120000 index 000000000000..5f54e4cab99b --- /dev/null +++ b/arch/arm64/boot/dts/broadcom/bcm283x.dtsi @@ -0,0 +1 @@ +../../../../arm/boot/dts/bcm283x.dtsi
\ No newline at end of file diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi index f53b0955bfd3..d4a12fad8afd 100644 --- a/arch/arm64/boot/dts/broadcom/ns2.dtsi +++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi @@ -88,13 +88,13 @@ timer { compatible = "arm,armv8-timer"; interrupts = <GIC_PPI 13 (GIC_CPU_MASK_RAW(0xff) | - IRQ_TYPE_EDGE_RISING)>, + IRQ_TYPE_LEVEL_LOW)>, <GIC_PPI 14 (GIC_CPU_MASK_RAW(0xff) | - IRQ_TYPE_EDGE_RISING)>, + IRQ_TYPE_LEVEL_LOW)>, <GIC_PPI 11 (GIC_CPU_MASK_RAW(0xff) | - IRQ_TYPE_EDGE_RISING)>, + IRQ_TYPE_LEVEL_LOW)>, <GIC_PPI 10 (GIC_CPU_MASK_RAW(0xff) | - IRQ_TYPE_EDGE_RISING)>; + IRQ_TYPE_LEVEL_LOW)>; }; pmu { diff --git a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi index 2eb9b225f0bc..04dc8a8d1539 100644 --- a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi +++ b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi @@ -354,10 +354,10 @@ timer { compatible = "arm,armv8-timer"; - interrupts = <1 13 0xff01>, - <1 14 0xff01>, - <1 11 0xff01>, - <1 10 0xff01>; + interrupts = <1 13 4>, + <1 14 4>, + <1 11 4>, + <1 10 4>; }; pmu { diff --git a/arch/arm64/boot/dts/exynos/exynos7.dtsi b/arch/arm64/boot/dts/exynos/exynos7.dtsi index ca663dfe5189..162831546e18 100644 --- a/arch/arm64/boot/dts/exynos/exynos7.dtsi +++ b/arch/arm64/boot/dts/exynos/exynos7.dtsi @@ -473,10 +473,10 @@ timer { compatible = "arm,armv8-timer"; - interrupts = <1 13 0xff01>, - <1 14 0xff01>, - <1 11 0xff01>, - <1 10 0xff01>; + interrupts = <1 13 0xff08>, + <1 14 0xff08>, + <1 11 0xff08>, + <1 10 0xff08>; }; pmu_system_controller: system-controller@105c0000 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi index e669fbd7f9c3..a67e210e2019 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi @@ -119,10 +119,10 @@ timer { compatible = "arm,armv8-timer"; - interrupts = <1 13 0x1>, /* Physical Secure PPI */ - <1 14 0x1>, /* Physical Non-Secure PPI */ - <1 11 0x1>, /* Virtual PPI */ - <1 10 0x1>; /* Hypervisor PPI */ + interrupts = <1 13 0xf08>, /* Physical Secure PPI */ + <1 14 0xf08>, /* Physical Non-Secure PPI */ + <1 11 0xf08>, /* Virtual PPI */ + <1 10 0xf08>; /* Hypervisor PPI */ }; pmu { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi index 21023a388c29..e3b6034ea5d9 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi @@ -191,10 +191,10 @@ timer { compatible = "arm,armv8-timer"; - interrupts = <1 13 0x8>, /* Physical Secure PPI, active-low */ - <1 14 0x8>, /* Physical Non-Secure PPI, active-low */ - <1 11 0x8>, /* Virtual PPI, active-low */ - <1 10 0x8>; /* Hypervisor PPI, active-low */ + interrupts = <1 13 4>, /* Physical Secure PPI, active-low */ + <1 14 4>, /* Physical Non-Secure PPI, active-low */ + <1 11 4>, /* Virtual PPI, active-low */ + <1 10 4>; /* Hypervisor PPI, active-low */ }; pmu { diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi index eab1a42fb934..c2a6745f168c 100644 --- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi @@ -122,10 +122,10 @@ timer { compatible = "arm,armv8-timer"; - interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>, - <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>, - <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>, - <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; + interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>, + <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>, + <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>, + <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>; }; odmi: odmi@300000 { diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index d02a900378e1..4f44d1191bfd 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -270,6 +270,8 @@ #io-channel-cells = <1>; clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>; clock-names = "saradc", "apb_pclk"; + resets = <&cru SRST_SARADC>; + reset-names = "saradc-apb"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi index c223915f0907..d73bdc8c9115 100644 --- a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi +++ b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi @@ -129,10 +129,10 @@ timer { compatible = "arm,armv8-timer"; - interrupts = <1 13 0xf01>, - <1 14 0xf01>, - <1 11 0xf01>, - <1 10 0xf01>; + interrupts = <1 13 4>, + <1 14 4>, + <1 11 4>, + <1 10 4>; }; soc { diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi index e595f22e7e4b..3e2e51fbd2bc 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi +++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi @@ -65,10 +65,10 @@ timer { compatible = "arm,armv8-timer"; interrupt-parent = <&gic>; - interrupts = <1 13 0xf01>, - <1 14 0xf01>, - <1 11 0xf01>, - <1 10 0xf01>; + interrupts = <1 13 0xf08>, + <1 14 0xf08>, + <1 11 0xf08>, + <1 10 0xf08>; }; amba_apu { diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c index 5c888049d061..6b2aa0fd6cd0 100644 --- a/arch/arm64/crypto/aes-glue.c +++ b/arch/arm64/crypto/aes-glue.c @@ -216,7 +216,7 @@ static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE); } - if (nbytes) { + if (walk.nbytes % AES_BLOCK_SIZE) { u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE; u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE; u8 __aligned(8) tail[AES_BLOCK_SIZE]; diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index f43d2c44c765..44e1d7f10add 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -1,4 +1,3 @@ -generic-y += bug.h generic-y += bugs.h generic-y += clkdev.h generic-y += cputime.h @@ -10,7 +9,6 @@ generic-y += dma-contiguous.h generic-y += early_ioremap.h generic-y += emergency-restart.h generic-y += errno.h -generic-y += ftrace.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ioctls.h @@ -27,12 +25,10 @@ generic-y += mman.h generic-y += msgbuf.h generic-y += msi.h generic-y += mutex.h -generic-y += pci.h generic-y += poll.h generic-y += preempt.h generic-y += resource.h generic-y += rwsem.h -generic-y += sections.h generic-y += segment.h generic-y += sembuf.h generic-y += serial.h @@ -45,7 +41,6 @@ generic-y += swab.h generic-y += switch_to.h generic-y += termbits.h generic-y += termios.h -generic-y += topology.h generic-y += trace_clock.h generic-y += types.h generic-y += unaligned.h diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index 5420cb0fcb3e..e517088d635f 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -12,7 +12,7 @@ #ifndef _ASM_ACPI_H #define _ASM_ACPI_H -#include <linux/mm.h> +#include <linux/memblock.h> #include <linux/psci.h> #include <asm/cputype.h> @@ -32,7 +32,11 @@ static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) { - if (!page_is_ram(phys >> PAGE_SHIFT)) + /* + * EFI's reserve_regions() call adds memory with the WB attribute + * to memblock via early_init_dt_add_memory_arch(). + */ + if (!memblock_is_memory(phys)) return ioremap(phys, size); return ioremap_cache(phys, size); diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 8746ff6abd77..55101bd86b98 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -2,6 +2,7 @@ #define __ASM_ALTERNATIVE_H #include <asm/cpufeature.h> +#include <asm/insn.h> #ifndef __ASSEMBLY__ @@ -90,34 +91,55 @@ void apply_alternatives(void *start, size_t length); .endm /* - * Begin an alternative code sequence. + * Alternative sequences + * + * The code for the case where the capability is not present will be + * assembled and linked as normal. There are no restrictions on this + * code. + * + * The code for the case where the capability is present will be + * assembled into a special section to be used for dynamic patching. + * Code for that case must: + * + * 1. Be exactly the same length (in bytes) as the default code + * sequence. * - * The code that follows this macro will be assembled and linked as - * normal. There are no restrictions on this code. + * 2. Not contain a branch target that is used outside of the + * alternative sequence it is defined in (branches into an + * alternative sequence are not fixed up). + */ + +/* + * Begin an alternative code sequence. */ .macro alternative_if_not cap + .set .Lasm_alt_mode, 0 .pushsection .altinstructions, "a" altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f .popsection 661: .endm +.macro alternative_if cap + .set .Lasm_alt_mode, 1 + .pushsection .altinstructions, "a" + altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f + .popsection + .pushsection .altinstr_replacement, "ax" + .align 2 /* So GAS knows label 661 is suitably aligned */ +661: +.endm + /* - * Provide the alternative code sequence. - * - * The code that follows this macro is assembled into a special - * section to be used for dynamic patching. Code that follows this - * macro must: - * - * 1. Be exactly the same length (in bytes) as the default code - * sequence. - * - * 2. Not contain a branch target that is used outside of the - * alternative sequence it is defined in (branches into an - * alternative sequence are not fixed up). + * Provide the other half of the alternative code sequence. */ .macro alternative_else -662: .pushsection .altinstr_replacement, "ax" +662: + .if .Lasm_alt_mode==0 + .pushsection .altinstr_replacement, "ax" + .else + .popsection + .endif 663: .endm @@ -125,11 +147,25 @@ void apply_alternatives(void *start, size_t length); * Complete an alternative code sequence. */ .macro alternative_endif -664: .popsection +664: + .if .Lasm_alt_mode==0 + .popsection + .endif .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) .endm +/* + * Provides a trivial alternative or default sequence consisting solely + * of NOPs. The number of NOPs is chosen automatically to match the + * previous case. + */ +.macro alternative_else_nop_endif +alternative_else + nops (662b-661b) / AARCH64_INSN_SIZE +alternative_endif +.endm + #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \ alternative_insn insn1, insn2, cap, IS_ENABLED(cfg) diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 8ec88e5b290f..f8ae6d6e4767 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -28,6 +28,7 @@ #define ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4) #define ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5) #define ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7) +#define ICC_BPR1_EL1 sys_reg(3, 0, 12, 12, 3) #define ICC_SRE_EL2 sys_reg(3, 4, 12, 9, 5) @@ -79,6 +80,19 @@ #include <linux/stringify.h> #include <asm/barrier.h> +#define read_gicreg(r) \ + ({ \ + u64 reg; \ + asm volatile("mrs_s %0, " __stringify(r) : "=r" (reg)); \ + reg; \ + }) + +#define write_gicreg(v,r) \ + do { \ + u64 __val = (v); \ + asm volatile("msr_s " __stringify(r) ", %0" : : "r" (__val));\ + } while (0) + /* * Low-level accessors * @@ -165,6 +179,11 @@ static inline void gic_write_sre(u32 val) isb(); } +static inline void gic_write_bpr1(u32 val) +{ + asm volatile("msr_s " __stringify(ICC_BPR1_EL1) ", %0" : : "r" (val)); +} + #define gic_read_typer(c) readq_relaxed(c) #define gic_write_irouter(v, c) writeq_relaxed(v, c) diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h index fbe0ca31a99c..eaa5bbe3fa87 100644 --- a/arch/arm64/include/asm/arch_timer.h +++ b/arch/arm64/include/asm/arch_timer.h @@ -20,13 +20,55 @@ #define __ASM_ARCH_TIMER_H #include <asm/barrier.h> +#include <asm/sysreg.h> #include <linux/bug.h> #include <linux/init.h> +#include <linux/jump_label.h> #include <linux/types.h> #include <clocksource/arm_arch_timer.h> +#if IS_ENABLED(CONFIG_FSL_ERRATUM_A008585) +extern struct static_key_false arch_timer_read_ool_enabled; +#define needs_fsl_a008585_workaround() \ + static_branch_unlikely(&arch_timer_read_ool_enabled) +#else +#define needs_fsl_a008585_workaround() false +#endif + +u32 __fsl_a008585_read_cntp_tval_el0(void); +u32 __fsl_a008585_read_cntv_tval_el0(void); +u64 __fsl_a008585_read_cntvct_el0(void); + +/* + * The number of retries is an arbitrary value well beyond the highest number + * of iterations the loop has been observed to take. + */ +#define __fsl_a008585_read_reg(reg) ({ \ + u64 _old, _new; \ + int _retries = 200; \ + \ + do { \ + _old = read_sysreg(reg); \ + _new = read_sysreg(reg); \ + _retries--; \ + } while (unlikely(_old != _new) && _retries); \ + \ + WARN_ON_ONCE(!_retries); \ + _new; \ +}) + +#define arch_timer_reg_read_stable(reg) \ +({ \ + u64 _val; \ + if (needs_fsl_a008585_workaround()) \ + _val = __fsl_a008585_read_##reg(); \ + else \ + _val = read_sysreg(reg); \ + _val; \ +}) + /* * These register accessors are marked inline so the compiler can * nicely work out which register we want, and chuck away the rest of @@ -38,19 +80,19 @@ void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val) if (access == ARCH_TIMER_PHYS_ACCESS) { switch (reg) { case ARCH_TIMER_REG_CTRL: - asm volatile("msr cntp_ctl_el0, %0" : : "r" (val)); + write_sysreg(val, cntp_ctl_el0); break; case ARCH_TIMER_REG_TVAL: - asm volatile("msr cntp_tval_el0, %0" : : "r" (val)); + write_sysreg(val, cntp_tval_el0); break; } } else if (access == ARCH_TIMER_VIRT_ACCESS) { switch (reg) { case ARCH_TIMER_REG_CTRL: - asm volatile("msr cntv_ctl_el0, %0" : : "r" (val)); + write_sysreg(val, cntv_ctl_el0); break; case ARCH_TIMER_REG_TVAL: - asm volatile("msr cntv_tval_el0, %0" : : "r" (val)); + write_sysreg(val, cntv_tval_el0); break; } } @@ -61,48 +103,38 @@ void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val) static __always_inline u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg) { - u32 val; - if (access == ARCH_TIMER_PHYS_ACCESS) { switch (reg) { case ARCH_TIMER_REG_CTRL: - asm volatile("mrs %0, cntp_ctl_el0" : "=r" (val)); - break; + return read_sysreg(cntp_ctl_el0); case ARCH_TIMER_REG_TVAL: - asm volatile("mrs %0, cntp_tval_el0" : "=r" (val)); - break; + return arch_timer_reg_read_stable(cntp_tval_el0); } } else if (access == ARCH_TIMER_VIRT_ACCESS) { switch (reg) { case ARCH_TIMER_REG_CTRL: - asm volatile("mrs %0, cntv_ctl_el0" : "=r" (val)); - break; + return read_sysreg(cntv_ctl_el0); case ARCH_TIMER_REG_TVAL: - asm volatile("mrs %0, cntv_tval_el0" : "=r" (val)); - break; + return arch_timer_reg_read_stable(cntv_tval_el0); } } - return val; + BUG(); } static inline u32 arch_timer_get_cntfrq(void) { - u32 val; - asm volatile("mrs %0, cntfrq_el0" : "=r" (val)); - return val; + return read_sysreg(cntfrq_el0); } static inline u32 arch_timer_get_cntkctl(void) { - u32 cntkctl; - asm volatile("mrs %0, cntkctl_el1" : "=r" (cntkctl)); - return cntkctl; + return read_sysreg(cntkctl_el1); } static inline void arch_timer_set_cntkctl(u32 cntkctl) { - asm volatile("msr cntkctl_el1, %0" : : "r" (cntkctl)); + write_sysreg(cntkctl, cntkctl_el1); } static inline u64 arch_counter_get_cntpct(void) @@ -116,12 +148,8 @@ static inline u64 arch_counter_get_cntpct(void) static inline u64 arch_counter_get_cntvct(void) { - u64 cval; - isb(); - asm volatile("mrs %0, cntvct_el0" : "=r" (cval)); - - return cval; + return arch_timer_reg_read_stable(cntvct_el0); } static inline int arch_timer_arch_init(void) diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index d5025c69ca81..28bfe6132eb6 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -87,6 +87,15 @@ .endm /* + * NOP sequence + */ + .macro nops, num + .rept \num + nop + .endr + .endm + +/* * Emit an entry into the exception table */ .macro _asm_extable, from, to @@ -216,11 +225,26 @@ lr .req x30 // link register .macro mmid, rd, rn ldr \rd, [\rn, #MM_CONTEXT_ID] .endm +/* + * read_ctr - read CTR_EL0. If the system has mismatched + * cache line sizes, provide the system wide safe value + * from arm64_ftr_reg_ctrel0.sys_val + */ + .macro read_ctr, reg +alternative_if_not ARM64_MISMATCHED_CACHE_LINE_SIZE + mrs \reg, ctr_el0 // read CTR + nop +alternative_else + ldr_l \reg, arm64_ftr_reg_ctrel0 + ARM64_FTR_SYSVAL +alternative_endif + .endm + /* - * dcache_line_size - get the minimum D-cache line size from the CTR register. + * raw_dcache_line_size - get the minimum D-cache line size on this CPU + * from the CTR register. */ - .macro dcache_line_size, reg, tmp + .macro raw_dcache_line_size, reg, tmp mrs \tmp, ctr_el0 // read CTR ubfm \tmp, \tmp, #16, #19 // cache line size encoding mov \reg, #4 // bytes per word @@ -228,9 +252,20 @@ lr .req x30 // link register .endm /* - * icache_line_size - get the minimum I-cache line size from the CTR register. + * dcache_line_size - get the safe D-cache line size across all CPUs */ - .macro icache_line_size, reg, tmp + .macro dcache_line_size, reg, tmp + read_ctr \tmp + ubfm \tmp, \tmp, #16, #19 // cache line size encoding + mov \reg, #4 // bytes per word + lsl \reg, \reg, \tmp // actual cache line size + .endm + +/* + * raw_icache_line_size - get the minimum I-cache line size on this CPU + * from the CTR register. + */ + .macro raw_icache_line_size, reg, tmp mrs \tmp, ctr_el0 // read CTR and \tmp, \tmp, #0xf // cache line size encoding mov \reg, #4 // bytes per word @@ -238,6 +273,16 @@ lr .req x30 // link register .endm /* + * icache_line_size - get the safe I-cache line size across all CPUs + */ + .macro icache_line_size, reg, tmp + read_ctr \tmp + and \tmp, \tmp, #0xf // cache line size encoding + mov \reg, #4 // bytes per word + lsl \reg, \reg, \tmp // actual cache line size + .endm + +/* * tcr_set_idmap_t0sz - update TCR.T0SZ so that we can load the ID map */ .macro tcr_set_idmap_t0sz, valreg, tmpreg diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index b5890be8f257..7457ce082b5f 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -86,8 +86,8 @@ static inline int atomic_add_return##name(int i, atomic_t *v) \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - " nop\n" \ - __LL_SC_ATOMIC(add_return##name), \ + __LL_SC_ATOMIC(add_return##name) \ + __nops(1), \ /* LSE atomics */ \ " ldadd" #mb " %w[i], w30, %[v]\n" \ " add %w[i], %w[i], w30") \ @@ -112,8 +112,8 @@ static inline void atomic_and(int i, atomic_t *v) asm volatile(ARM64_LSE_ATOMIC_INSN( /* LL/SC */ - " nop\n" - __LL_SC_ATOMIC(and), + __LL_SC_ATOMIC(and) + __nops(1), /* LSE atomics */ " mvn %w[i], %w[i]\n" " stclr %w[i], %[v]") @@ -130,8 +130,8 @@ static inline int atomic_fetch_and##name(int i, atomic_t *v) \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - " nop\n" \ - __LL_SC_ATOMIC(fetch_and##name), \ + __LL_SC_ATOMIC(fetch_and##name) \ + __nops(1), \ /* LSE atomics */ \ " mvn %w[i], %w[i]\n" \ " ldclr" #mb " %w[i], %w[i], %[v]") \ @@ -156,8 +156,8 @@ static inline void atomic_sub(int i, atomic_t *v) asm volatile(ARM64_LSE_ATOMIC_INSN( /* LL/SC */ - " nop\n" - __LL_SC_ATOMIC(sub), + __LL_SC_ATOMIC(sub) + __nops(1), /* LSE atomics */ " neg %w[i], %w[i]\n" " stadd %w[i], %[v]") @@ -174,9 +174,8 @@ static inline int atomic_sub_return##name(int i, atomic_t *v) \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - " nop\n" \ __LL_SC_ATOMIC(sub_return##name) \ - " nop", \ + __nops(2), \ /* LSE atomics */ \ " neg %w[i], %w[i]\n" \ " ldadd" #mb " %w[i], w30, %[v]\n" \ @@ -203,8 +202,8 @@ static inline int atomic_fetch_sub##name(int i, atomic_t *v) \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - " nop\n" \ - __LL_SC_ATOMIC(fetch_sub##name), \ + __LL_SC_ATOMIC(fetch_sub##name) \ + __nops(1), \ /* LSE atomics */ \ " neg %w[i], %w[i]\n" \ " ldadd" #mb " %w[i], %w[i], %[v]") \ @@ -284,8 +283,8 @@ static inline long atomic64_add_return##name(long i, atomic64_t *v) \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - " nop\n" \ - __LL_SC_ATOMIC64(add_return##name), \ + __LL_SC_ATOMIC64(add_return##name) \ + __nops(1), \ /* LSE atomics */ \ " ldadd" #mb " %[i], x30, %[v]\n" \ " add %[i], %[i], x30") \ @@ -310,8 +309,8 @@ static inline void atomic64_and(long i, atomic64_t *v) asm volatile(ARM64_LSE_ATOMIC_INSN( /* LL/SC */ - " nop\n" - __LL_SC_ATOMIC64(and), + __LL_SC_ATOMIC64(and) + __nops(1), /* LSE atomics */ " mvn %[i], %[i]\n" " stclr %[i], %[v]") @@ -328,8 +327,8 @@ static inline long atomic64_fetch_and##name(long i, atomic64_t *v) \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - " nop\n" \ - __LL_SC_ATOMIC64(fetch_and##name), \ + __LL_SC_ATOMIC64(fetch_and##name) \ + __nops(1), \ /* LSE atomics */ \ " mvn %[i], %[i]\n" \ " ldclr" #mb " %[i], %[i], %[v]") \ @@ -354,8 +353,8 @@ static inline void atomic64_sub(long i, atomic64_t *v) asm volatile(ARM64_LSE_ATOMIC_INSN( /* LL/SC */ - " nop\n" - __LL_SC_ATOMIC64(sub), + __LL_SC_ATOMIC64(sub) + __nops(1), /* LSE atomics */ " neg %[i], %[i]\n" " stadd %[i], %[v]") @@ -372,9 +371,8 @@ static inline long atomic64_sub_return##name(long i, atomic64_t *v) \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - " nop\n" \ __LL_SC_ATOMIC64(sub_return##name) \ - " nop", \ + __nops(2), \ /* LSE atomics */ \ " neg %[i], %[i]\n" \ " ldadd" #mb " %[i], x30, %[v]\n" \ @@ -401,8 +399,8 @@ static inline long atomic64_fetch_sub##name(long i, atomic64_t *v) \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - " nop\n" \ - __LL_SC_ATOMIC64(fetch_sub##name), \ + __LL_SC_ATOMIC64(fetch_sub##name) \ + __nops(1), \ /* LSE atomics */ \ " neg %[i], %[i]\n" \ " ldadd" #mb " %[i], %[i], %[v]") \ @@ -426,13 +424,8 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) asm volatile(ARM64_LSE_ATOMIC_INSN( /* LL/SC */ - " nop\n" __LL_SC_ATOMIC64(dec_if_positive) - " nop\n" - " nop\n" - " nop\n" - " nop\n" - " nop", + __nops(6), /* LSE atomics */ "1: ldr x30, %[v]\n" " subs %[ret], x30, #1\n" @@ -464,9 +457,8 @@ static inline unsigned long __cmpxchg_case_##name(volatile void *ptr, \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - " nop\n" \ - __LL_SC_CMPXCHG(name) \ - " nop", \ + __LL_SC_CMPXCHG(name) \ + __nops(2), \ /* LSE atomics */ \ " mov " #w "30, %" #w "[old]\n" \ " cas" #mb #sz "\t" #w "30, %" #w "[new], %[v]\n" \ @@ -517,10 +509,8 @@ static inline long __cmpxchg_double##name(unsigned long old1, \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - " nop\n" \ - " nop\n" \ - " nop\n" \ - __LL_SC_CMPXCHG_DBL(name), \ + __LL_SC_CMPXCHG_DBL(name) \ + __nops(3), \ /* LSE atomics */ \ " casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\ " eor %[old1], %[old1], %[oldval1]\n" \ diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 4eea7f618dce..4e0497f581a0 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -20,6 +20,9 @@ #ifndef __ASSEMBLY__ +#define __nops(n) ".rept " #n "\nnop\n.endr\n" +#define nops(n) asm volatile(__nops(n)) + #define sev() asm volatile("sev" : : : "memory") #define wfe() asm volatile("wfe" : : : "memory") #define wfi() asm volatile("wfi" : : : "memory") diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index c64268dbff64..2e5fb976a572 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -68,6 +68,7 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_icache_range(unsigned long start, unsigned long end); extern void __flush_dcache_area(void *addr, size_t len); +extern void __clean_dcache_area_poc(void *addr, size_t len); extern void __clean_dcache_area_pou(void *addr, size_t len); extern long __flush_cache_user_range(unsigned long start, unsigned long end); @@ -85,7 +86,7 @@ static inline void flush_cache_page(struct vm_area_struct *vma, */ extern void __dma_map_area(const void *, size_t, int); extern void __dma_unmap_area(const void *, size_t, int); -extern void __dma_flush_range(const void *, const void *); +extern void __dma_flush_area(const void *, size_t); /* * Copy user data from/to a page which is mapped into a different diff --git a/arch/arm64/include/asm/clocksource.h b/arch/arm64/include/asm/clocksource.h new file mode 100644 index 000000000000..0b350a7e26f3 --- /dev/null +++ b/arch/arm64/include/asm/clocksource.h @@ -0,0 +1,8 @@ +#ifndef _ASM_CLOCKSOURCE_H +#define _ASM_CLOCKSOURCE_H + +struct arch_clocksource_data { + bool vdso_direct; /* Usable for direct VDSO access? */ +}; + +#endif diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index bd86a79491bc..91b26d26af8a 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -43,10 +43,8 @@ static inline unsigned long __xchg_case_##name(unsigned long x, \ " cbnz %w1, 1b\n" \ " " #mb, \ /* LSE atomics */ \ - " nop\n" \ - " nop\n" \ " swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n" \ - " nop\n" \ + __nops(3) \ " " #nop_lse) \ : "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr) \ : "r" (x) \ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 7099f26e3702..758d74fedfad 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -9,6 +9,8 @@ #ifndef __ASM_CPUFEATURE_H #define __ASM_CPUFEATURE_H +#include <linux/jump_label.h> + #include <asm/hwcap.h> #include <asm/sysreg.h> @@ -37,8 +39,9 @@ #define ARM64_WORKAROUND_CAVIUM_27456 12 #define ARM64_HAS_32BIT_EL0 13 #define ARM64_HYP_OFFSET_LOW 14 +#define ARM64_MISMATCHED_CACHE_LINE_SIZE 15 -#define ARM64_NCAPS 15 +#define ARM64_NCAPS 16 #ifndef __ASSEMBLY__ @@ -63,7 +66,7 @@ struct arm64_ftr_bits { enum ftr_type type; u8 shift; u8 width; - s64 safe_val; /* safe value for discrete features */ + s64 safe_val; /* safe value for FTR_EXACT features */ }; /* @@ -72,13 +75,14 @@ struct arm64_ftr_bits { * @sys_val Safe value across the CPUs (system view) */ struct arm64_ftr_reg { - u32 sys_id; - const char *name; - u64 strict_mask; - u64 sys_val; - struct arm64_ftr_bits *ftr_bits; + const char *name; + u64 strict_mask; + u64 sys_val; + const struct arm64_ftr_bits *ftr_bits; }; +extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; + /* scope of capability check */ enum { SCOPE_SYSTEM, @@ -109,6 +113,7 @@ struct arm64_cpu_capabilities { }; extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); +extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS]; bool this_cpu_has_cap(unsigned int cap); @@ -121,16 +126,21 @@ static inline bool cpus_have_cap(unsigned int num) { if (num >= ARM64_NCAPS) return false; - return test_bit(num, cpu_hwcaps); + if (__builtin_constant_p(num)) + return static_branch_unlikely(&cpu_hwcap_keys[num]); + else + return test_bit(num, cpu_hwcaps); } static inline void cpus_set_cap(unsigned int num) { - if (num >= ARM64_NCAPS) + if (num >= ARM64_NCAPS) { pr_warn("Attempt to set an illegal CPU capability (%d >= %d)\n", num, ARM64_NCAPS); - else + } else { __set_bit(num, cpu_hwcaps); + static_branch_enable(&cpu_hwcap_keys[num]); + } } static inline int __attribute_const__ @@ -157,7 +167,7 @@ cpuid_feature_extract_unsigned_field(u64 features, int field) return cpuid_feature_extract_unsigned_field_width(features, field, 4); } -static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp) +static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp) { return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift); } @@ -170,7 +180,7 @@ cpuid_feature_extract_field(u64 features, int field, bool sign) cpuid_feature_extract_unsigned_field(features, field); } -static inline s64 arm64_ftr_value(struct arm64_ftr_bits *ftrp, u64 val) +static inline s64 arm64_ftr_value(const struct arm64_ftr_bits *ftrp, u64 val) { return (s64)cpuid_feature_extract_field(val, ftrp->shift, ftrp->sign); } @@ -193,11 +203,11 @@ void __init setup_cpu_features(void); void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, const char *info); void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps); -void check_local_cpu_errata(void); -void __init enable_errata_workarounds(void); +void check_local_cpu_capabilities(void); -void verify_local_cpu_errata(void); -void verify_local_cpu_capabilities(void); +void update_cpu_errata_workarounds(void); +void __init enable_errata_workarounds(void); +void verify_local_cpu_errata_workarounds(void); u64 read_system_reg(u32 id); diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 9d9fd4b9a72e..26a68ddb11c1 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -93,11 +93,7 @@ #include <asm/sysreg.h> -#define read_cpuid(reg) ({ \ - u64 __val; \ - asm("mrs_s %0, " __stringify(SYS_ ## reg) : "=r" (__val)); \ - __val; \ -}) +#define read_cpuid(reg) read_sysreg_s(SYS_ ## reg) /* * The CPU ID never changes at run time, so we might as well tell the diff --git a/arch/arm64/include/asm/dcc.h b/arch/arm64/include/asm/dcc.h index 65e0190e97c8..836b05630003 100644 --- a/arch/arm64/include/asm/dcc.h +++ b/arch/arm64/include/asm/dcc.h @@ -21,21 +21,16 @@ #define __ASM_DCC_H #include <asm/barrier.h> +#include <asm/sysreg.h> static inline u32 __dcc_getstatus(void) { - u32 ret; - - asm volatile("mrs %0, mdccsr_el0" : "=r" (ret)); - - return ret; + return read_sysreg(mdccsr_el0); } static inline char __dcc_getchar(void) { - char c; - - asm volatile("mrs %0, dbgdtrrx_el0" : "=r" (c)); + char c = read_sysreg(dbgdtrrx_el0); isb(); return c; @@ -47,8 +42,7 @@ static inline void __dcc_putchar(char c) * The typecast is to make absolutely certain that 'c' is * zero-extended. */ - asm volatile("msr dbgdtrtx_el0, %0" - : : "r" ((unsigned long)(unsigned char)c)); + write_sysreg((unsigned char)c, dbgdtrtx_el0); isb(); } diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index 4b6b3f72a215..b71420a12f26 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -61,8 +61,6 @@ #define AARCH64_BREAK_KGDB_DYN_DBG \ (AARCH64_BREAK_MON | (KGDB_DYN_DBG_BRK_IMM << 5)) -#define KGDB_DYN_BRK_INS_BYTE(x) \ - ((AARCH64_BREAK_KGDB_DYN_DBG >> (8 * (x))) & 0xff) #define CACHE_FLUSH_IS_SAFE 1 diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index f772e15c4766..d14c478976d0 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -78,6 +78,23 @@ #define ESR_ELx_IL (UL(1) << 25) #define ESR_ELx_ISS_MASK (ESR_ELx_IL - 1) + +/* ISS field definitions shared by different classes */ +#define ESR_ELx_WNR (UL(1) << 6) + +/* Shared ISS field definitions for Data/Instruction aborts */ +#define ESR_ELx_EA (UL(1) << 9) +#define ESR_ELx_S1PTW (UL(1) << 7) + +/* Shared ISS fault status code(IFSC/DFSC) for Data/Instruction aborts */ +#define ESR_ELx_FSC (0x3F) +#define ESR_ELx_FSC_TYPE (0x3C) +#define ESR_ELx_FSC_EXTABT (0x10) +#define ESR_ELx_FSC_ACCESS (0x08) +#define ESR_ELx_FSC_FAULT (0x04) +#define ESR_ELx_FSC_PERM (0x0C) + +/* ISS field definitions for Data Aborts */ #define ESR_ELx_ISV (UL(1) << 24) #define ESR_ELx_SAS_SHIFT (22) #define ESR_ELx_SAS (UL(3) << ESR_ELx_SAS_SHIFT) @@ -86,16 +103,9 @@ #define ESR_ELx_SRT_MASK (UL(0x1F) << ESR_ELx_SRT_SHIFT) #define ESR_ELx_SF (UL(1) << 15) #define ESR_ELx_AR (UL(1) << 14) -#define ESR_ELx_EA (UL(1) << 9) #define ESR_ELx_CM (UL(1) << 8) -#define ESR_ELx_S1PTW (UL(1) << 7) -#define ESR_ELx_WNR (UL(1) << 6) -#define ESR_ELx_FSC (0x3F) -#define ESR_ELx_FSC_TYPE (0x3C) -#define ESR_ELx_FSC_EXTABT (0x10) -#define ESR_ELx_FSC_ACCESS (0x08) -#define ESR_ELx_FSC_FAULT (0x04) -#define ESR_ELx_FSC_PERM (0x0C) + +/* ISS field definitions for exceptions taken in to Hyp */ #define ESR_ELx_CV (UL(1) << 24) #define ESR_ELx_COND_SHIFT (20) #define ESR_ELx_COND_MASK (UL(0xF) << ESR_ELx_COND_SHIFT) @@ -109,6 +119,62 @@ ((ESR_ELx_EC_BRK64 << ESR_ELx_EC_SHIFT) | ESR_ELx_IL | \ ((imm) & 0xffff)) +/* ISS field definitions for System instruction traps */ +#define ESR_ELx_SYS64_ISS_RES0_SHIFT 22 +#define ESR_ELx_SYS64_ISS_RES0_MASK (UL(0x7) << ESR_ELx_SYS64_ISS_RES0_SHIFT) +#define ESR_ELx_SYS64_ISS_DIR_MASK 0x1 +#define ESR_ELx_SYS64_ISS_DIR_READ 0x1 +#define ESR_ELx_SYS64_ISS_DIR_WRITE 0x0 + +#define ESR_ELx_SYS64_ISS_RT_SHIFT 5 +#define ESR_ELx_SYS64_ISS_RT_MASK (UL(0x1f) << ESR_ELx_SYS64_ISS_RT_SHIFT) +#define ESR_ELx_SYS64_ISS_CRM_SHIFT 1 +#define ESR_ELx_SYS64_ISS_CRM_MASK (UL(0xf) << ESR_ELx_SYS64_ISS_CRM_SHIFT) +#define ESR_ELx_SYS64_ISS_CRN_SHIFT 10 +#define ESR_ELx_SYS64_ISS_CRN_MASK (UL(0xf) << ESR_ELx_SYS64_ISS_CRN_SHIFT) +#define ESR_ELx_SYS64_ISS_OP1_SHIFT 14 +#define ESR_ELx_SYS64_ISS_OP1_MASK (UL(0x7) << ESR_ELx_SYS64_ISS_OP1_SHIFT) +#define ESR_ELx_SYS64_ISS_OP2_SHIFT 17 +#define ESR_ELx_SYS64_ISS_OP2_MASK (UL(0x7) << ESR_ELx_SYS64_ISS_OP2_SHIFT) +#define ESR_ELx_SYS64_ISS_OP0_SHIFT 20 +#define ESR_ELx_SYS64_ISS_OP0_MASK (UL(0x3) << ESR_ELx_SYS64_ISS_OP0_SHIFT) +#define ESR_ELx_SYS64_ISS_SYS_MASK (ESR_ELx_SYS64_ISS_OP0_MASK | \ + ESR_ELx_SYS64_ISS_OP1_MASK | \ + ESR_ELx_SYS64_ISS_OP2_MASK | \ + ESR_ELx_SYS64_ISS_CRN_MASK | \ + ESR_ELx_SYS64_ISS_CRM_MASK) +#define ESR_ELx_SYS64_ISS_SYS_VAL(op0, op1, op2, crn, crm) \ + (((op0) << ESR_ELx_SYS64_ISS_OP0_SHIFT) | \ + ((op1) << ESR_ELx_SYS64_ISS_OP1_SHIFT) | \ + ((op2) << ESR_ELx_SYS64_ISS_OP2_SHIFT) | \ + ((crn) << ESR_ELx_SYS64_ISS_CRN_SHIFT) | \ + ((crm) << ESR_ELx_SYS64_ISS_CRM_SHIFT)) + +#define ESR_ELx_SYS64_ISS_SYS_OP_MASK (ESR_ELx_SYS64_ISS_SYS_MASK | \ + ESR_ELx_SYS64_ISS_DIR_MASK) +/* + * User space cache operations have the following sysreg encoding + * in System instructions. + * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 14 }, WRITE (L=0) + */ +#define ESR_ELx_SYS64_ISS_CRM_DC_CIVAC 14 +#define ESR_ELx_SYS64_ISS_CRM_DC_CVAU 11 +#define ESR_ELx_SYS64_ISS_CRM_DC_CVAC 10 +#define ESR_ELx_SYS64_ISS_CRM_IC_IVAU 5 + +#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK (ESR_ELx_SYS64_ISS_OP0_MASK | \ + ESR_ELx_SYS64_ISS_OP1_MASK | \ + ESR_ELx_SYS64_ISS_OP2_MASK | \ + ESR_ELx_SYS64_ISS_CRN_MASK | \ + ESR_ELx_SYS64_ISS_DIR_MASK) +#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL \ + (ESR_ELx_SYS64_ISS_SYS_VAL(1, 3, 1, 7, 0) | \ + ESR_ELx_SYS64_ISS_DIR_WRITE) + +#define ESR_ELx_SYS64_ISS_SYS_CTR ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 1, 0, 0) +#define ESR_ELx_SYS64_ISS_SYS_CTR_READ (ESR_ELx_SYS64_ISS_SYS_CTR | \ + ESR_ELx_SYS64_ISS_DIR_READ) + #ifndef __ASSEMBLY__ #include <asm/types.h> diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index 115ea2a64520..9510ace570e2 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -18,6 +18,7 @@ #include <asm/cputype.h> #include <asm/cpufeature.h> +#include <asm/sysreg.h> #include <asm/virt.h> #ifdef __KERNEL__ @@ -98,18 +99,18 @@ static inline void decode_ctrl_reg(u32 reg, #define AARCH64_DBG_REG_WCR (AARCH64_DBG_REG_WVR + ARM_MAX_WRP) /* Debug register names. */ -#define AARCH64_DBG_REG_NAME_BVR "bvr" -#define AARCH64_DBG_REG_NAME_BCR "bcr" -#define AARCH64_DBG_REG_NAME_WVR "wvr" -#define AARCH64_DBG_REG_NAME_WCR "wcr" +#define AARCH64_DBG_REG_NAME_BVR bvr +#define AARCH64_DBG_REG_NAME_BCR bcr +#define AARCH64_DBG_REG_NAME_WVR wvr +#define AARCH64_DBG_REG_NAME_WCR wcr /* Accessor macros for the debug registers. */ #define AARCH64_DBG_READ(N, REG, VAL) do {\ - asm volatile("mrs %0, dbg" REG #N "_el1" : "=r" (VAL));\ + VAL = read_sysreg(dbg##REG##N##_el1);\ } while (0) #define AARCH64_DBG_WRITE(N, REG, VAL) do {\ - asm volatile("msr dbg" REG #N "_el1, %0" :: "r" (VAL));\ + write_sysreg(VAL, dbg##REG##N##_el1);\ } while (0) struct task_struct; @@ -141,8 +142,6 @@ static inline void ptrace_hw_copy_thread(struct task_struct *task) } #endif -extern struct pmu perf_ops_bp; - /* Determine number of BRP registers available. */ static inline int get_num_brps(void) { diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 1dbaa901d7e5..bc853663dd51 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -246,7 +246,8 @@ static __always_inline bool aarch64_insn_is_##abbr(u32 code) \ static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \ { return (val); } -__AARCH64_INSN_FUNCS(adr_adrp, 0x1F000000, 0x10000000) +__AARCH64_INSN_FUNCS(adr, 0x9F000000, 0x10000000) +__AARCH64_INSN_FUNCS(adrp, 0x9F000000, 0x90000000) __AARCH64_INSN_FUNCS(prfm_lit, 0xFF000000, 0xD8000000) __AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800) __AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800) @@ -318,6 +319,11 @@ __AARCH64_INSN_FUNCS(msr_reg, 0xFFF00000, 0xD5100000) bool aarch64_insn_is_nop(u32 insn); bool aarch64_insn_is_branch_imm(u32 insn); +static inline bool aarch64_insn_is_adr_adrp(u32 insn) +{ + return aarch64_insn_is_adr(insn) || aarch64_insn_is_adrp(insn); +} + int aarch64_insn_read(void *addr, u32 *insnp); int aarch64_insn_write(void *addr, u32 insn); enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn); @@ -398,6 +404,9 @@ int aarch64_insn_patch_text_nosync(void *addr, u32 insn); int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt); int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt); +s32 aarch64_insn_adrp_get_offset(u32 insn); +u32 aarch64_insn_adrp_set_offset(u32 insn, s32 offset); + bool aarch32_insn_is_wide(u32 insn); #define A32_RN_OFFSET 16 diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 9b6e408cfa51..0bba427bb4c2 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -40,25 +40,25 @@ #define __raw_writeb __raw_writeb static inline void __raw_writeb(u8 val, volatile void __iomem *addr) { - asm volatile("strb %w0, [%1]" : : "r" (val), "r" (addr)); + asm volatile("strb %w0, [%1]" : : "rZ" (val), "r" (addr)); } #define __raw_writew __raw_writew static inline void __raw_writew(u16 val, volatile void __iomem *addr) { - asm volatile("strh %w0, [%1]" : : "r" (val), "r" (addr)); + asm volatile("strh %w0, [%1]" : : "rZ" (val), "r" (addr)); } #define __raw_writel __raw_writel static inline void __raw_writel(u32 val, volatile void __iomem *addr) { - asm volatile("str %w0, [%1]" : : "r" (val), "r" (addr)); + asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr)); } #define __raw_writeq __raw_writeq static inline void __raw_writeq(u64 val, volatile void __iomem *addr) { - asm volatile("str %0, [%1]" : : "r" (val), "r" (addr)); + asm volatile("str %x0, [%1]" : : "rZ" (val), "r" (addr)); } #define __raw_readb __raw_readb @@ -184,17 +184,6 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); #define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); }) #define iowrite64be(v,p) ({ __iowmb(); __raw_writeq((__force __u64)cpu_to_be64(v), p); }) -/* - * Convert a physical pointer to a virtual kernel pointer for /dev/mem - * access - */ -#define xlate_dev_mem_ptr(p) __va(p) - -/* - * Convert a virtual cached pointer to an uncached pointer - */ -#define xlate_dev_kmem_ptr(p) p - #include <asm-generic/io.h> /* diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 4b5c977af465..2a2752b5b6aa 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -50,7 +50,7 @@ #define HCR_BSU (3 << 10) #define HCR_BSU_IS (UL(1) << 10) #define HCR_FB (UL(1) << 9) -#define HCR_VA (UL(1) << 8) +#define HCR_VSE (UL(1) << 8) #define HCR_VI (UL(1) << 7) #define HCR_VF (UL(1) << 6) #define HCR_AMO (UL(1) << 5) @@ -80,7 +80,7 @@ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW) -#define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF) +#define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) #define HCR_INT_OVERRIDE (HCR_FMO | HCR_IMO) #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 7561f63f1c28..18f746551bf6 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -20,10 +20,15 @@ #include <asm/virt.h> +#define ARM_EXIT_WITH_SERROR_BIT 31 +#define ARM_EXCEPTION_CODE(x) ((x) & ~(1U << ARM_EXIT_WITH_SERROR_BIT)) +#define ARM_SERROR_PENDING(x) !!((x) & (1U << ARM_EXIT_WITH_SERROR_BIT)) + #define ARM_EXCEPTION_IRQ 0 -#define ARM_EXCEPTION_TRAP 1 +#define ARM_EXCEPTION_EL1_SERROR 1 +#define ARM_EXCEPTION_TRAP 2 /* The hyp-stub will return this for any kvm_call_hyp() call */ -#define ARM_EXCEPTION_HYP_GONE 2 +#define ARM_EXCEPTION_HYP_GONE 3 #define KVM_ARM64_DEBUG_DIRTY_SHIFT 0 #define KVM_ARM64_DEBUG_DIRTY (1 << KVM_ARM64_DEBUG_DIRTY_SHIFT) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 4cdeae3b17c6..fd9d5fd788f5 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -38,6 +38,7 @@ bool kvm_condition_valid32(const struct kvm_vcpu *vcpu); void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr); void kvm_inject_undefined(struct kvm_vcpu *vcpu); +void kvm_inject_vabt(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); @@ -147,6 +148,16 @@ static inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu) return vcpu->arch.fault.esr_el2; } +static inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) +{ + u32 esr = kvm_vcpu_get_hsr(vcpu); + + if (esr & ESR_ELx_CV) + return (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT; + + return -1; +} + static inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vcpu) { return vcpu->arch.fault.far_el2; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 3eda975837d0..bd94e6766759 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -290,15 +290,15 @@ struct kvm_vcpu_arch { #endif struct kvm_vm_stat { - u32 remote_tlb_flush; + ulong remote_tlb_flush; }; struct kvm_vcpu_stat { - u32 halt_successful_poll; - u32 halt_attempted_poll; - u32 halt_poll_invalid; - u32 halt_wakeup; - u32 hvc_exit_stat; + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_poll_invalid; + u64 halt_wakeup; + u64 hvc_exit_stat; u64 wfe_exit_stat; u64 wfi_exit_stat; u64 mmio_exit_user; diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index cff510574fae..b18e852d27e8 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -123,6 +123,7 @@ typeof(orig) * __hyp_text fname(void) \ void __vgic_v2_save_state(struct kvm_vcpu *vcpu); void __vgic_v2_restore_state(struct kvm_vcpu *vcpu); +int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu); void __vgic_v3_save_state(struct kvm_vcpu *vcpu); void __vgic_v3_restore_state(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index b6bb83400cd8..a79b969c26fc 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -99,14 +99,10 @@ .macro kern_hyp_va reg alternative_if_not ARM64_HAS_VIRT_HOST_EXTN and \reg, \reg, #HYP_PAGE_OFFSET_HIGH_MASK -alternative_else - nop -alternative_endif -alternative_if_not ARM64_HYP_OFFSET_LOW - nop -alternative_else +alternative_else_nop_endif +alternative_if ARM64_HYP_OFFSET_LOW and \reg, \reg, #HYP_PAGE_OFFSET_LOW_MASK -alternative_endif +alternative_else_nop_endif .endm #else @@ -166,12 +162,6 @@ void kvm_clear_hyp_idmap(void); #define kvm_set_pte(ptep, pte) set_pte(ptep, pte) #define kvm_set_pmd(pmdp, pmd) set_pmd(pmdp, pmd) -static inline void kvm_clean_pgd(pgd_t *pgd) {} -static inline void kvm_clean_pmd(pmd_t *pmd) {} -static inline void kvm_clean_pmd_entry(pmd_t *pmd) {} -static inline void kvm_clean_pte(pte_t *pte) {} -static inline void kvm_clean_pte_entry(pte_t *pte) {} - static inline pte_t kvm_s2pte_mkwrite(pte_t pte) { pte_val(pte) |= PTE_S2_RDWR; diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 31b73227b41f..ba62df8c6e35 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -214,7 +214,7 @@ static inline void *phys_to_virt(phys_addr_t x) #ifndef CONFIG_SPARSEMEM_VMEMMAP #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) -#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) +#define _virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) #else #define __virt_to_pgoff(kaddr) (((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page)) #define __page_to_voff(kaddr) (((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page)) @@ -222,11 +222,15 @@ static inline void *phys_to_virt(phys_addr_t x) #define page_to_virt(page) ((void *)((__page_to_voff(page)) | PAGE_OFFSET)) #define virt_to_page(vaddr) ((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START)) -#define virt_addr_valid(kaddr) pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \ +#define _virt_addr_valid(kaddr) pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \ + PHYS_OFFSET) >> PAGE_SHIFT) #endif #endif +#define _virt_addr_is_linear(kaddr) (((u64)(kaddr)) >= PAGE_OFFSET) +#define virt_addr_valid(kaddr) (_virt_addr_is_linear(kaddr) && \ + _virt_addr_valid(kaddr)) + #include <asm-generic/memory_model.h> #endif diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index b1892a0dbcb0..a50185375f09 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -27,22 +27,17 @@ #include <asm-generic/mm_hooks.h> #include <asm/cputype.h> #include <asm/pgtable.h> +#include <asm/sysreg.h> #include <asm/tlbflush.h> -#ifdef CONFIG_PID_IN_CONTEXTIDR -static inline void contextidr_thread_switch(struct task_struct *next) -{ - asm( - " msr contextidr_el1, %0\n" - " isb" - : - : "r" (task_pid_nr(next))); -} -#else static inline void contextidr_thread_switch(struct task_struct *next) { + if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR)) + return; + + write_sysreg(task_pid_nr(next), contextidr_el1); + isb(); } -#endif /* * Set TTBR0 to empty_zero_page. No translations will be possible via TTBR0. @@ -51,11 +46,8 @@ static inline void cpu_set_reserved_ttbr0(void) { unsigned long ttbr = virt_to_phys(empty_zero_page); - asm( - " msr ttbr0_el1, %0 // set TTBR0\n" - " isb" - : - : "r" (ttbr)); + write_sysreg(ttbr, ttbr0_el1); + isb(); } /* @@ -81,13 +73,11 @@ static inline void __cpu_set_tcr_t0sz(unsigned long t0sz) if (!__cpu_uses_extended_idmap()) return; - asm volatile ( - " mrs %0, tcr_el1 ;" - " bfi %0, %1, %2, %3 ;" - " msr tcr_el1, %0 ;" - " isb" - : "=&r" (tcr) - : "r"(t0sz), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH)); + tcr = read_sysreg(tcr_el1); + tcr &= ~TCR_T0SZ_MASK; + tcr |= t0sz << TCR_T0SZ_OFFSET; + write_sysreg(tcr, tcr_el1); + isb(); } #define cpu_set_default_tcr_t0sz() __cpu_set_tcr_t0sz(TCR_T0SZ(VA_BITS)) diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 0a456bef8c79..2fee2f59288c 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -199,19 +199,19 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val, #define _percpu_read(pcp) \ ({ \ typeof(pcp) __retval; \ - preempt_disable(); \ + preempt_disable_notrace(); \ __retval = (typeof(pcp))__percpu_read(raw_cpu_ptr(&(pcp)), \ sizeof(pcp)); \ - preempt_enable(); \ + preempt_enable_notrace(); \ __retval; \ }) #define _percpu_write(pcp, val) \ do { \ - preempt_disable(); \ + preempt_disable_notrace(); \ __percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), \ sizeof(pcp)); \ - preempt_enable(); \ + preempt_enable_notrace(); \ } while(0) \ #define _pcp_protect(operation, pcp, val) \ diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index c3ae239db3ee..eb0c2bd90de9 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -208,6 +208,7 @@ #define TCR_T1SZ(x) ((UL(64) - (x)) << TCR_T1SZ_OFFSET) #define TCR_TxSZ(x) (TCR_T0SZ(x) | TCR_T1SZ(x)) #define TCR_TxSZ_WIDTH 6 +#define TCR_T0SZ_MASK (((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET) #define TCR_IRGN0_SHIFT 8 #define TCR_IRGN0_MASK (UL(3) << TCR_IRGN0_SHIFT) diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 39f5252673f7..2142c7726e76 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -70,12 +70,13 @@ #define PAGE_COPY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN) #define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) #define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN) +#define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_NG | PTE_PXN) #define __P000 PAGE_NONE #define __P001 PAGE_READONLY #define __P010 PAGE_COPY #define __P011 PAGE_COPY -#define __P100 PAGE_READONLY_EXEC +#define __P100 PAGE_EXECONLY #define __P101 PAGE_READONLY_EXEC #define __P110 PAGE_COPY_EXEC #define __P111 PAGE_COPY_EXEC @@ -84,7 +85,7 @@ #define __S001 PAGE_READONLY #define __S010 PAGE_SHARED #define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY_EXEC +#define __S100 PAGE_EXECONLY #define __S101 PAGE_READONLY_EXEC #define __S110 PAGE_SHARED_EXEC #define __S111 PAGE_SHARED_EXEC diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index e20bd431184a..ffbb9a520563 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -73,7 +73,7 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) -#define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) +#define pte_ng(pte) (!!(pte_val(pte) & PTE_NG)) #ifdef CONFIG_ARM64_HW_AFDBM #define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY)) @@ -84,8 +84,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) -#define pte_valid_not_user(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) +#define pte_valid_global(pte) \ + ((pte_val(pte) & (PTE_VALID | PTE_NG)) == PTE_VALID) #define pte_valid_young(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) @@ -155,6 +155,16 @@ static inline pte_t pte_mknoncont(pte_t pte) return clear_pte_bit(pte, __pgprot(PTE_CONT)); } +static inline pte_t pte_clear_rdonly(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(PTE_RDONLY)); +} + +static inline pte_t pte_mkpresent(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(PTE_VALID)); +} + static inline pmd_t pmd_mkcont(pmd_t pmd) { return __pmd(pmd_val(pmd) | PMD_SECT_CONT); @@ -168,7 +178,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte) * Only if the new pte is valid and kernel, otherwise TLB maintenance * or update_mmu_cache() have the necessary barriers. */ - if (pte_valid_not_user(pte)) { + if (pte_valid_global(pte)) { dsb(ishst); isb(); } @@ -202,7 +212,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_val(pte) &= ~PTE_RDONLY; else pte_val(pte) |= PTE_RDONLY; - if (pte_user(pte) && pte_exec(pte) && !pte_special(pte)) + if (pte_ng(pte) && pte_exec(pte) && !pte_special(pte)) __sync_icache_dcache(pte, addr); } diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index ace0a96e7d6e..df2e53d3a969 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -37,7 +37,6 @@ #include <asm/ptrace.h> #include <asm/types.h> -#ifdef __KERNEL__ #define STACK_TOP_MAX TASK_SIZE_64 #ifdef CONFIG_COMPAT #define AARCH32_VECTORS_BASE 0xffff0000 @@ -49,7 +48,6 @@ extern phys_addr_t arm64_dma_phys_limit; #define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1) -#endif /* __KERNEL__ */ struct debug_info { /* Have we suspended stepping by a debugger? */ diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h new file mode 100644 index 000000000000..4e7e7067afdb --- /dev/null +++ b/arch/arm64/include/asm/sections.h @@ -0,0 +1,30 @@ +/* + * Copyright (C) 2016 ARM Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ +#ifndef __ASM_SECTIONS_H +#define __ASM_SECTIONS_H + +#include <asm-generic/sections.h> + +extern char __alt_instructions[], __alt_instructions_end[]; +extern char __exception_text_start[], __exception_text_end[]; +extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[]; +extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[]; +extern char __hyp_text_start[], __hyp_text_end[]; +extern char __idmap_text_start[], __idmap_text_end[]; +extern char __irqentry_text_start[], __irqentry_text_end[]; +extern char __mmuoff_data_start[], __mmuoff_data_end[]; + +#endif /* __ASM_SECTIONS_H */ diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index e875a5a551d7..cae331d553f8 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -66,8 +66,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) ARM64_LSE_ATOMIC_INSN( /* LL/SC */ " stxr %w1, %w0, %2\n" -" nop\n" -" nop\n", + __nops(2), /* LSE atomics */ " mov %w1, %w0\n" " cas %w0, %w0, %2\n" @@ -99,9 +98,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) /* LSE atomics */ " mov %w2, %w5\n" " ldadda %w2, %w0, %3\n" -" nop\n" -" nop\n" -" nop\n" + __nops(3) ) /* Did we get the lock? */ @@ -165,8 +162,8 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) " stlrh %w1, %0", /* LSE atomics */ " mov %w1, #1\n" - " nop\n" - " staddlh %w1, %0") + " staddlh %w1, %0\n" + __nops(1)) : "=Q" (lock->owner), "=&r" (tmp) : : "memory"); @@ -212,7 +209,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw) " cbnz %w0, 1b\n" " stxr %w0, %w2, %1\n" " cbnz %w0, 2b\n" - " nop", + __nops(1), /* LSE atomics */ "1: mov %w0, wzr\n" "2: casa %w0, %w2, %1\n" @@ -241,8 +238,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw) /* LSE atomics */ " mov %w0, wzr\n" " casa %w0, %w2, %1\n" - " nop\n" - " nop") + __nops(2)) : "=&r" (tmp), "+Q" (rw->lock) : "r" (0x80000000) : "memory"); @@ -290,8 +286,8 @@ static inline void arch_read_lock(arch_rwlock_t *rw) " add %w0, %w0, #1\n" " tbnz %w0, #31, 1b\n" " stxr %w1, %w0, %2\n" - " nop\n" - " cbnz %w1, 2b", + " cbnz %w1, 2b\n" + __nops(1), /* LSE atomics */ "1: wfe\n" "2: ldxr %w0, %2\n" @@ -317,9 +313,8 @@ static inline void arch_read_unlock(arch_rwlock_t *rw) " cbnz %w1, 1b", /* LSE atomics */ " movn %w0, #0\n" - " nop\n" - " nop\n" - " staddl %w0, %2") + " staddl %w0, %2\n" + __nops(2)) : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock) : : "memory"); @@ -344,7 +339,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) " tbnz %w1, #31, 1f\n" " casa %w0, %w1, %2\n" " sbc %w1, %w1, %w0\n" - " nop\n" + __nops(1) "1:") : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock) : @@ -363,4 +358,14 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) #define arch_read_relax(lock) cpu_relax() #define arch_write_relax(lock) cpu_relax() +/* + * Accesses appearing in program order before a spin_lock() operation + * can be reordered with accesses inside the critical section, by virtue + * of arch_spin_lock being constructed using acquire semantics. + * + * In cases where this is problematic (e.g. try_to_wake_up), an + * smp_mb__before_spinlock() can restore the required ordering. + */ +#define smp_mb__before_spinlock() smp_mb() + #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h index 024d623f662e..b8a313fd7a09 100644 --- a/arch/arm64/include/asm/suspend.h +++ b/arch/arm64/include/asm/suspend.h @@ -47,4 +47,7 @@ int swsusp_arch_resume(void); int arch_hibernation_header_save(void *addr, unsigned int max_size); int arch_hibernation_header_restore(void *addr); +/* Used to resume on the CPU we hibernated on */ +int hibernate_resume_nonboot_cpu_disable(void); + #endif diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index cc06794b7346..e8d46e8e6079 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -100,6 +100,7 @@ /* SCTLR_EL1 specific flags. */ #define SCTLR_EL1_UCI (1 << 26) #define SCTLR_EL1_SPAN (1 << 23) +#define SCTLR_EL1_UCT (1 << 15) #define SCTLR_EL1_SED (1 << 8) #define SCTLR_EL1_CP15BEN (1 << 5) @@ -253,16 +254,6 @@ asm( " .endm\n" ); -static inline void config_sctlr_el1(u32 clear, u32 set) -{ - u32 val; - - asm volatile("mrs %0, sctlr_el1" : "=r" (val)); - val &= ~clear; - val |= set; - asm volatile("msr sctlr_el1, %0" : : "r" (val)); -} - /* * Unlike read_cpuid, calls to read_sysreg are never expected to be * optimized away or replaced with synthetic values. @@ -273,12 +264,41 @@ static inline void config_sctlr_el1(u32 clear, u32 set) __val; \ }) +/* + * The "Z" constraint normally means a zero immediate, but when combined with + * the "%x0" template means XZR. + */ #define write_sysreg(v, r) do { \ u64 __val = (u64)v; \ - asm volatile("msr " __stringify(r) ", %0" \ - : : "r" (__val)); \ + asm volatile("msr " __stringify(r) ", %x0" \ + : : "rZ" (__val)); \ +} while (0) + +/* + * For registers without architectural names, or simply unsupported by + * GAS. + */ +#define read_sysreg_s(r) ({ \ + u64 __val; \ + asm volatile("mrs_s %0, " __stringify(r) : "=r" (__val)); \ + __val; \ +}) + +#define write_sysreg_s(v, r) do { \ + u64 __val = (u64)v; \ + asm volatile("msr_s " __stringify(r) ", %0" : : "rZ" (__val)); \ } while (0) +static inline void config_sctlr_el1(u32 clear, u32 set) +{ + u32 val; + + val = read_sysreg(sctlr_el1); + val &= ~clear; + val |= set; + write_sysreg(val, sctlr_el1); +} + #endif #endif /* __ASM_SYSREG_H */ diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h index 57f110bea6a8..bc812435bc76 100644 --- a/arch/arm64/include/asm/system_misc.h +++ b/arch/arm64/include/asm/system_misc.h @@ -56,12 +56,6 @@ extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd); __show_ratelimited; \ }) -#define UDBG_UNDEFINED (1 << 0) -#define UDBG_SYSCALL (1 << 1) -#define UDBG_BADABORT (1 << 2) -#define UDBG_SEGV (1 << 3) -#define UDBG_BUS (1 << 4) - #endif /* __ASSEMBLY__ */ #endif /* __ASM_SYSTEM_MISC_H */ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index abd64bd1f6d9..e9ea5a6bd449 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -75,6 +75,9 @@ static inline struct thread_info *current_thread_info(void) __attribute_const__; /* * struct thread_info can be accessed directly via sp_el0. + * + * We don't use read_sysreg() as we want the compiler to cache the value where + * possible. */ static inline struct thread_info *current_thread_info(void) { diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index b460ae28e346..deab52374119 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -25,6 +25,24 @@ #include <asm/cputype.h> /* + * Raw TLBI operations. + * + * Where necessary, use the __tlbi() macro to avoid asm() + * boilerplate. Drivers and most kernel code should use the TLB + * management routines in preference to the macro below. + * + * The macro can be used as __tlbi(op) or __tlbi(op, arg), depending + * on whether a particular TLBI operation takes an argument or + * not. The macros handles invoking the asm with or without the + * register argument as appropriate. + */ +#define __TLBI_0(op, arg) asm ("tlbi " #op) +#define __TLBI_1(op, arg) asm ("tlbi " #op ", %0" : : "r" (arg)) +#define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg) + +#define __tlbi(op, ...) __TLBI_N(op, ##__VA_ARGS__, 1, 0) + +/* * TLB Management * ============== * @@ -66,7 +84,7 @@ static inline void local_flush_tlb_all(void) { dsb(nshst); - asm("tlbi vmalle1"); + __tlbi(vmalle1); dsb(nsh); isb(); } @@ -74,7 +92,7 @@ static inline void local_flush_tlb_all(void) static inline void flush_tlb_all(void) { dsb(ishst); - asm("tlbi vmalle1is"); + __tlbi(vmalle1is); dsb(ish); isb(); } @@ -84,7 +102,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm) unsigned long asid = ASID(mm) << 48; dsb(ishst); - asm("tlbi aside1is, %0" : : "r" (asid)); + __tlbi(aside1is, asid); dsb(ish); } @@ -94,7 +112,7 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr = uaddr >> 12 | (ASID(vma->vm_mm) << 48); dsb(ishst); - asm("tlbi vale1is, %0" : : "r" (addr)); + __tlbi(vale1is, addr); dsb(ish); } @@ -122,9 +140,9 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, dsb(ishst); for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) { if (last_level) - asm("tlbi vale1is, %0" : : "r"(addr)); + __tlbi(vale1is, addr); else - asm("tlbi vae1is, %0" : : "r"(addr)); + __tlbi(vae1is, addr); } dsb(ish); } @@ -149,7 +167,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end dsb(ishst); for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) - asm("tlbi vaae1is, %0" : : "r"(addr)); + __tlbi(vaae1is, addr); dsb(ish); isb(); } @@ -163,7 +181,7 @@ static inline void __flush_tlb_pgtable(struct mm_struct *mm, { unsigned long addr = uaddr >> 12 | (ASID(mm) << 48); - asm("tlbi vae1is, %0" : : "r" (addr)); + __tlbi(vae1is, addr); dsb(ish); } diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h index 9cd03f3e812f..02e9035b0685 100644 --- a/arch/arm64/include/asm/traps.h +++ b/arch/arm64/include/asm/traps.h @@ -19,6 +19,7 @@ #define __ASM_TRAP_H #include <linux/list.h> +#include <asm/sections.h> struct pt_regs; @@ -39,9 +40,6 @@ void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr); #ifdef CONFIG_FUNCTION_GRAPH_TRACER static inline int __in_irqentry_text(unsigned long ptr) { - extern char __irqentry_text_start[]; - extern char __irqentry_text_end[]; - return ptr >= (unsigned long)&__irqentry_text_start && ptr < (unsigned long)&__irqentry_text_end; } @@ -54,8 +52,6 @@ static inline int __in_irqentry_text(unsigned long ptr) static inline int in_exception_text(unsigned long ptr) { - extern char __exception_text_start[]; - extern char __exception_text_end[]; int in; in = ptr >= (unsigned long)&__exception_text_start && diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 1788545f25bc..fea10736b11f 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -45,6 +45,8 @@ #ifndef __ASSEMBLY__ #include <asm/ptrace.h> +#include <asm/sections.h> +#include <asm/sysreg.h> /* * __boot_cpu_mode records what mode CPUs were booted in. @@ -75,10 +77,7 @@ static inline bool is_hyp_mode_mismatched(void) static inline bool is_kernel_in_hyp_mode(void) { - u64 el; - - asm("mrs %0, CurrentEL" : "=r" (el)); - return el == CurrentEL_EL2; + return read_sysreg(CurrentEL) == CurrentEL_EL2; } #ifdef CONFIG_ARM64_VHE @@ -87,14 +86,6 @@ extern void verify_cpu_run_el(void); static inline void verify_cpu_run_el(void) {} #endif -/* The section containing the hypervisor idmap text */ -extern char __hyp_idmap_text_start[]; -extern char __hyp_idmap_text_end[]; - -/* The section containing the hypervisor text */ -extern char __hyp_text_start[]; -extern char __hyp_text_end[]; - #endif /* __ASSEMBLY__ */ #endif /* ! __ASM__VIRT_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 14f7b651c787..7d66bbaafc0c 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -10,6 +10,8 @@ CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_insn.o = -pg CFLAGS_REMOVE_return_address.o = -pg +CFLAGS_setup.o = -DUTS_MACHINE='"$(UTS_MACHINE)"' + # Object file lists. arm64-obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ entry-fpsimd.o process.o ptrace.o setup.o signal.o \ diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 3e4f1a45b125..252a6d9c1da5 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -24,6 +24,7 @@ #include <linux/memblock.h> #include <linux/of_fdt.h> #include <linux/smp.h> +#include <linux/serial_core.h> #include <asm/cputype.h> #include <asm/cpu_ops.h> @@ -206,7 +207,7 @@ void __init acpi_boot_table_init(void) if (param_acpi_off || (!param_acpi_on && !param_acpi_force && of_scan_flat_dt(dt_scan_depth1_nodes, NULL))) - return; + goto done; /* * ACPI is disabled at this point. Enable it in order to parse @@ -226,6 +227,14 @@ void __init acpi_boot_table_init(void) if (!param_acpi_force) disable_acpi(); } + +done: + if (acpi_disabled) { + if (earlycon_init_is_deferred) + early_init_dt_scan_chosen_stdout(); + } else { + parse_spcr(earlycon_init_is_deferred); + } } #ifdef CONFIG_ACPI_APEI diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c index f85149cc7c71..f01fab637dab 100644 --- a/arch/arm64/kernel/acpi_numa.c +++ b/arch/arm64/kernel/acpi_numa.c @@ -105,8 +105,10 @@ int __init arm64_acpi_numa_init(void) int ret; ret = acpi_numa_init(); - if (ret) + if (ret) { + pr_info("Failed to initialise from firmware\n"); return ret; + } return srat_disabled() ? -EINVAL : 0; } diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index d2ee1b21a10d..06d650f61da7 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -25,14 +25,13 @@ #include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/insn.h> +#include <asm/sections.h> #include <linux/stop_machine.h> #define __ALT_PTR(a,f) (u32 *)((void *)&(a)->f + (a)->f) #define ALT_ORIG_PTR(a) __ALT_PTR(a, orig_offset) #define ALT_REPL_PTR(a) __ALT_PTR(a, alt_offset) -extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; - struct alt_region { struct alt_instr *begin; struct alt_instr *end; @@ -59,6 +58,8 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) BUG(); } +#define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1)) + static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr) { u32 insn; @@ -80,6 +81,25 @@ static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr) offset = target - (unsigned long)insnptr; insn = aarch64_set_branch_offset(insn, offset); } + } else if (aarch64_insn_is_adrp(insn)) { + s32 orig_offset, new_offset; + unsigned long target; + + /* + * If we're replacing an adrp instruction, which uses PC-relative + * immediate addressing, adjust the offset to reflect the new + * PC. adrp operates on 4K aligned addresses. + */ + orig_offset = aarch64_insn_adrp_get_offset(insn); + target = align_down(altinsnptr, SZ_4K) + orig_offset; + new_offset = target - align_down(insnptr, SZ_4K); + insn = aarch64_insn_adrp_set_offset(insn, new_offset); + } else if (aarch64_insn_uses_literal(insn)) { + /* + * Disallow patching unhandled instructions using PC relative + * literal addresses + */ + BUG(); } return insn; @@ -124,8 +144,8 @@ static int __apply_alternatives_multi_stop(void *unused) { static int patched = 0; struct alt_region region = { - .begin = __alt_instructions, - .end = __alt_instructions_end, + .begin = (struct alt_instr *)__alt_instructions, + .end = (struct alt_instr *)__alt_instructions_end, }; /* We always have a CPU 0 at this point (__init) */ diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 05070b72fc28..4a2f0f0fef32 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -23,6 +23,7 @@ #include <linux/dma-mapping.h> #include <linux/kvm_host.h> #include <linux/suspend.h> +#include <asm/cpufeature.h> #include <asm/thread_info.h> #include <asm/memory.h> #include <asm/smp_plat.h> @@ -145,5 +146,6 @@ int main(void) DEFINE(HIBERN_PBE_ORIG, offsetof(struct pbe, orig_address)); DEFINE(HIBERN_PBE_ADDR, offsetof(struct pbe, address)); DEFINE(HIBERN_PBE_NEXT, offsetof(struct pbe, next)); + DEFINE(ARM64_FTR_SYSVAL, offsetof(struct arm64_ftr_reg, sys_val)); return 0; } diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c index b8629d52fba9..9617301f76b5 100644 --- a/arch/arm64/kernel/cacheinfo.c +++ b/arch/arm64/kernel/cacheinfo.c @@ -39,7 +39,7 @@ static inline enum cache_type get_cache_type(int level) if (level > MAX_CACHE_LEVEL) return CACHE_TYPE_NOCACHE; - asm volatile ("mrs %x0, clidr_el1" : "=r" (clidr)); + clidr = read_sysreg(clidr_el1); return CLIDR_CTYPE(clidr, level); } @@ -55,11 +55,9 @@ u64 __attribute_const__ cache_get_ccsidr(u64 csselr) WARN_ON(preemptible()); - /* Put value into CSSELR */ - asm volatile("msr csselr_el1, %x0" : : "r" (csselr)); + write_sysreg(csselr, csselr_el1); isb(); - /* Read result out of CCSIDR */ - asm volatile("mrs %x0, ccsidr_el1" : "=r" (ccsidr)); + ccsidr = read_sysreg(ccsidr_el1); return ccsidr; } diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 82b0fc2e637b..0150394f4cab 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -30,6 +30,21 @@ is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope) entry->midr_range_max); } +static bool +has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry, + int scope) +{ + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + return (read_cpuid_cachetype() & arm64_ftr_reg_ctrel0.strict_mask) != + (arm64_ftr_reg_ctrel0.sys_val & arm64_ftr_reg_ctrel0.strict_mask); +} + +static void cpu_enable_trap_ctr_access(void *__unused) +{ + /* Clear SCTLR_EL1.UCT */ + config_sctlr_el1(SCTLR_EL1_UCT, 0); +} + #define MIDR_RANGE(model, min, max) \ .def_scope = SCOPE_LOCAL_CPU, \ .matches = is_affected_midr_range, \ @@ -108,6 +123,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { }, #endif { + .desc = "Mismatched cache line size", + .capability = ARM64_MISMATCHED_CACHE_LINE_SIZE, + .matches = has_mismatched_cache_line_size, + .def_scope = SCOPE_LOCAL_CPU, + .enable = cpu_enable_trap_ctr_access, + }, + { } }; @@ -116,7 +138,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { * and the related information is freed soon after. If the new CPU requires * an errata not detected at boot, fail this CPU. */ -void verify_local_cpu_errata(void) +void verify_local_cpu_errata_workarounds(void) { const struct arm64_cpu_capabilities *caps = arm64_errata; @@ -131,7 +153,7 @@ void verify_local_cpu_errata(void) } } -void check_local_cpu_errata(void) +void update_cpu_errata_workarounds(void) { update_cpu_capabilities(arm64_errata, "enabling workaround for"); } diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c index c7cfb8fe06f9..e137ceaf5016 100644 --- a/arch/arm64/kernel/cpu_ops.c +++ b/arch/arm64/kernel/cpu_ops.c @@ -17,6 +17,7 @@ */ #include <linux/acpi.h> +#include <linux/cache.h> #include <linux/errno.h> #include <linux/of.h> #include <linux/string.h> @@ -28,7 +29,7 @@ extern const struct cpu_operations smp_spin_table_ops; extern const struct cpu_operations acpi_parking_protocol_ops; extern const struct cpu_operations cpu_psci_ops; -const struct cpu_operations *cpu_ops[NR_CPUS]; +const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init; static const struct cpu_operations *dt_supported_cpu_ops[] __initconst = { &smp_spin_table_ops, diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 62272eac1352..d577f263cc4a 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -46,6 +46,9 @@ unsigned int compat_elf_hwcap2 __read_mostly; DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); +DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS); +EXPORT_SYMBOL(cpu_hwcap_keys); + #define __ARM64_FTR_BITS(SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ { \ .sign = SIGNED, \ @@ -74,7 +77,7 @@ static bool __maybe_unused cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused); -static struct arm64_ftr_bits ftr_id_aa64isar0[] = { +static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_RDM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0), @@ -87,7 +90,7 @@ static struct arm64_ftr_bits ftr_id_aa64isar0[] = { ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_id_aa64pfr0[] = { +static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 4, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_GIC_SHIFT, 4, 0), @@ -101,7 +104,7 @@ static struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { +static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI), S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI), @@ -119,7 +122,7 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { +static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_LOR_SHIFT, 4, 0), @@ -130,7 +133,7 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { +static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LVA_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_IESB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LSM_SHIFT, 4, 0), @@ -139,7 +142,7 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_ctr[] = { +static const struct arm64_ftr_bits ftr_ctr[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RAO */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 3, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0), /* CWG */ @@ -147,15 +150,21 @@ static struct arm64_ftr_bits ftr_ctr[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1), /* DminLine */ /* * Linux can handle differing I-cache policies. Userspace JITs will - * make use of *minLine + * make use of *minLine. + * If we have differing I-cache policies, report it as the weakest - AIVIVT. */ - ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0), /* L1Ip */ + ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, ICACHE_POLICY_AIVIVT), /* L1Ip */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 10, 0), /* RAZ */ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* IminLine */ ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_id_mmfr0[] = { +struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = { + .name = "SYS_CTR_EL0", + .ftr_bits = ftr_ctr +}; + +static const struct arm64_ftr_bits ftr_id_mmfr0[] = { S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 4, 0xf), /* InnerShr */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0), /* FCSE */ ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, 20, 4, 0), /* AuxReg */ @@ -167,7 +176,7 @@ static struct arm64_ftr_bits ftr_id_mmfr0[] = { ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_id_aa64dfr0[] = { +static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0), @@ -178,14 +187,14 @@ static struct arm64_ftr_bits ftr_id_aa64dfr0[] = { ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_mvfr2[] = { +static const struct arm64_ftr_bits ftr_mvfr2[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 24, 0), /* RAZ */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* FPMisc */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* SIMDMisc */ ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_dczid[] = { +static const struct arm64_ftr_bits ftr_dczid[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 5, 27, 0), /* RAZ */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 1, 1), /* DZP */ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* BS */ @@ -193,7 +202,7 @@ static struct arm64_ftr_bits ftr_dczid[] = { }; -static struct arm64_ftr_bits ftr_id_isar5[] = { +static const struct arm64_ftr_bits ftr_id_isar5[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_RDM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 20, 4, 0), /* RAZ */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_CRC32_SHIFT, 4, 0), @@ -204,14 +213,14 @@ static struct arm64_ftr_bits ftr_id_isar5[] = { ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_id_mmfr4[] = { +static const struct arm64_ftr_bits ftr_id_mmfr4[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 24, 0), /* RAZ */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* ac2 */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* RAZ */ ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_id_pfr0[] = { +static const struct arm64_ftr_bits ftr_id_pfr0[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 16, 16, 0), /* RAZ */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 12, 4, 0), /* State3 */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 4, 0), /* State2 */ @@ -220,7 +229,7 @@ static struct arm64_ftr_bits ftr_id_pfr0[] = { ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_id_dfr0[] = { +static const struct arm64_ftr_bits ftr_id_dfr0[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), S_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf), /* PerfMon */ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), @@ -238,7 +247,7 @@ static struct arm64_ftr_bits ftr_id_dfr0[] = { * 0. Covers the following 32bit registers: * id_isar[0-4], id_mmfr[1-3], id_pfr1, mvfr[0-1] */ -static struct arm64_ftr_bits ftr_generic_32bits[] = { +static const struct arm64_ftr_bits ftr_generic_32bits[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), @@ -250,29 +259,32 @@ static struct arm64_ftr_bits ftr_generic_32bits[] = { ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_generic[] = { +static const struct arm64_ftr_bits ftr_generic[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 64, 0), ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_generic32[] = { +static const struct arm64_ftr_bits ftr_generic32[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 32, 0), ARM64_FTR_END, }; -static struct arm64_ftr_bits ftr_aa64raz[] = { +static const struct arm64_ftr_bits ftr_aa64raz[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 64, 0), ARM64_FTR_END, }; -#define ARM64_FTR_REG(id, table) \ - { \ - .sys_id = id, \ +#define ARM64_FTR_REG(id, table) { \ + .sys_id = id, \ + .reg = &(struct arm64_ftr_reg){ \ .name = #id, \ .ftr_bits = &((table)[0]), \ - } + }} -static struct arm64_ftr_reg arm64_ftr_regs[] = { +static const struct __ftr_reg_entry { + u32 sys_id; + struct arm64_ftr_reg *reg; +} arm64_ftr_regs[] = { /* Op1 = 0, CRn = 0, CRm = 1 */ ARM64_FTR_REG(SYS_ID_PFR0_EL1, ftr_id_pfr0), @@ -315,7 +327,7 @@ static struct arm64_ftr_reg arm64_ftr_regs[] = { ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2), /* Op1 = 3, CRn = 0, CRm = 0 */ - ARM64_FTR_REG(SYS_CTR_EL0, ftr_ctr), + { SYS_CTR_EL0, &arm64_ftr_reg_ctrel0 }, ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid), /* Op1 = 3, CRn = 14, CRm = 0 */ @@ -324,7 +336,7 @@ static struct arm64_ftr_reg arm64_ftr_regs[] = { static int search_cmp_ftr_reg(const void *id, const void *regp) { - return (int)(unsigned long)id - (int)((const struct arm64_ftr_reg *)regp)->sys_id; + return (int)(unsigned long)id - (int)((const struct __ftr_reg_entry *)regp)->sys_id; } /* @@ -339,14 +351,20 @@ static int search_cmp_ftr_reg(const void *id, const void *regp) */ static struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id) { - return bsearch((const void *)(unsigned long)sys_id, + const struct __ftr_reg_entry *ret; + + ret = bsearch((const void *)(unsigned long)sys_id, arm64_ftr_regs, ARRAY_SIZE(arm64_ftr_regs), sizeof(arm64_ftr_regs[0]), search_cmp_ftr_reg); + if (ret) + return ret->reg; + return NULL; } -static u64 arm64_ftr_set_value(struct arm64_ftr_bits *ftrp, s64 reg, s64 ftr_val) +static u64 arm64_ftr_set_value(const struct arm64_ftr_bits *ftrp, s64 reg, + s64 ftr_val) { u64 mask = arm64_ftr_mask(ftrp); @@ -355,7 +373,8 @@ static u64 arm64_ftr_set_value(struct arm64_ftr_bits *ftrp, s64 reg, s64 ftr_val return reg; } -static s64 arm64_ftr_safe_value(struct arm64_ftr_bits *ftrp, s64 new, s64 cur) +static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, + s64 cur) { s64 ret = 0; @@ -376,27 +395,13 @@ static s64 arm64_ftr_safe_value(struct arm64_ftr_bits *ftrp, s64 new, s64 cur) return ret; } -static int __init sort_cmp_ftr_regs(const void *a, const void *b) -{ - return ((const struct arm64_ftr_reg *)a)->sys_id - - ((const struct arm64_ftr_reg *)b)->sys_id; -} - -static void __init swap_ftr_regs(void *a, void *b, int size) -{ - struct arm64_ftr_reg tmp = *(struct arm64_ftr_reg *)a; - *(struct arm64_ftr_reg *)a = *(struct arm64_ftr_reg *)b; - *(struct arm64_ftr_reg *)b = tmp; -} - static void __init sort_ftr_regs(void) { - /* Keep the array sorted so that we can do the binary search */ - sort(arm64_ftr_regs, - ARRAY_SIZE(arm64_ftr_regs), - sizeof(arm64_ftr_regs[0]), - sort_cmp_ftr_regs, - swap_ftr_regs); + int i; + + /* Check that the array is sorted so that we can do the binary search */ + for (i = 1; i < ARRAY_SIZE(arm64_ftr_regs); i++) + BUG_ON(arm64_ftr_regs[i].sys_id < arm64_ftr_regs[i - 1].sys_id); } /* @@ -407,7 +412,7 @@ static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new) { u64 val = 0; u64 strict_mask = ~0x0ULL; - struct arm64_ftr_bits *ftrp; + const struct arm64_ftr_bits *ftrp; struct arm64_ftr_reg *reg = get_arm64_ftr_reg(sys_reg); BUG_ON(!reg); @@ -464,7 +469,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new) { - struct arm64_ftr_bits *ftrp; + const struct arm64_ftr_bits *ftrp; for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) { s64 ftr_cur = arm64_ftr_value(ftrp, reg->sys_val); @@ -1004,23 +1009,33 @@ verify_local_cpu_features(const struct arm64_cpu_capabilities *caps) * cannot do anything to fix it up and could cause unexpected failures. So * we park the CPU. */ -void verify_local_cpu_capabilities(void) +static void verify_local_cpu_capabilities(void) { + verify_local_cpu_errata_workarounds(); + verify_local_cpu_features(arm64_features); + verify_local_elf_hwcaps(arm64_elf_hwcaps); + if (system_supports_32bit_el0()) + verify_local_elf_hwcaps(compat_elf_hwcaps); +} +void check_local_cpu_capabilities(void) +{ + /* + * All secondary CPUs should conform to the early CPU features + * in use by the kernel based on boot CPU. + */ check_early_cpu_features(); /* - * If we haven't computed the system capabilities, there is nothing - * to verify. + * If we haven't finalised the system capabilities, this CPU gets + * a chance to update the errata work arounds. + * Otherwise, this CPU should verify that it has all the system + * advertised capabilities. */ if (!sys_caps_initialised) - return; - - verify_local_cpu_errata(); - verify_local_cpu_features(arm64_features); - verify_local_elf_hwcaps(arm64_elf_hwcaps); - if (system_supports_32bit_el0()) - verify_local_elf_hwcaps(compat_elf_hwcaps); + update_cpu_errata_workarounds(); + else + verify_local_cpu_capabilities(); } static void __init setup_feature_capabilities(void) diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index ed1b84fe6925..b3d5b3e8fbcb 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -363,8 +363,6 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) } cpuinfo_detect_icache_policy(info); - - check_local_cpu_errata(); } void cpuinfo_store_cpu(void) diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 91fff48d0f57..73ae90ef434c 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -46,16 +46,14 @@ static void mdscr_write(u32 mdscr) { unsigned long flags; local_dbg_save(flags); - asm volatile("msr mdscr_el1, %0" :: "r" (mdscr)); + write_sysreg(mdscr, mdscr_el1); local_dbg_restore(flags); } NOKPROBE_SYMBOL(mdscr_write); static u32 mdscr_read(void) { - u32 mdscr; - asm volatile("mrs %0, mdscr_el1" : "=r" (mdscr)); - return mdscr; + return read_sysreg(mdscr_el1); } NOKPROBE_SYMBOL(mdscr_read); @@ -132,36 +130,18 @@ NOKPROBE_SYMBOL(disable_debug_monitors); /* * OS lock clearing. */ -static void clear_os_lock(void *unused) +static int clear_os_lock(unsigned int cpu) { - asm volatile("msr oslar_el1, %0" : : "r" (0)); -} - -static int os_lock_notify(struct notifier_block *self, - unsigned long action, void *data) -{ - if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE) - clear_os_lock(NULL); - return NOTIFY_OK; + write_sysreg(0, oslar_el1); + isb(); + return 0; } -static struct notifier_block os_lock_nb = { - .notifier_call = os_lock_notify, -}; - static int debug_monitors_init(void) { - cpu_notifier_register_begin(); - - /* Clear the OS lock. */ - on_each_cpu(clear_os_lock, NULL, 1); - isb(); - - /* Register hotplug handler. */ - __register_cpu_notifier(&os_lock_nb); - - cpu_notifier_register_done(); - return 0; + return cpuhp_setup_state(CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING, + "CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING", + clear_os_lock, NULL); } postcore_initcall(debug_monitors_init); @@ -254,7 +234,7 @@ static int single_step_handler(unsigned long addr, unsigned int esr, return 0; if (user_mode(regs)) { - send_user_sigtrap(TRAP_HWBKPT); + send_user_sigtrap(TRAP_TRACE); /* * ptrace will disable single step unless explicitly @@ -382,7 +362,7 @@ NOKPROBE_SYMBOL(aarch32_break_handler); static int __init debug_traps_init(void) { hook_debug_fault_code(DBG_ESR_EVT_HWSS, single_step_handler, SIGTRAP, - TRAP_HWBKPT, "single-step handler"); + TRAP_TRACE, "single-step handler"); hook_debug_fault_code(DBG_ESR_EVT_BRK, brk_handler, SIGTRAP, TRAP_BRKPT, "ptrace BRK handler"); return 0; @@ -435,8 +415,10 @@ NOKPROBE_SYMBOL(kernel_active_single_step); /* ptrace API */ void user_enable_single_step(struct task_struct *task) { - set_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP); - set_regs_spsr_ss(task_pt_regs(task)); + struct thread_info *ti = task_thread_info(task); + + if (!test_and_set_ti_thread_flag(ti, TIF_SINGLESTEP)) + set_regs_spsr_ss(task_pt_regs(task)); } NOKPROBE_SYMBOL(user_enable_single_step); diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 0f03a8fe2314..aef02d2af3b5 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -219,7 +219,7 @@ ENDPROC(ftrace_graph_caller) * * Run ftrace_return_to_handler() before going back to parent. * @fp is checked against the value passed by ftrace_graph_caller() - * only when CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST is enabled. + * only when HAVE_FUNCTION_GRAPH_FP_TEST is enabled. */ ENTRY(return_to_handler) save_return_regs diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 441420ca7d08..223d54a4d66b 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -104,7 +104,7 @@ str x20, [sp, #S_ORIG_ADDR_LIMIT] mov x20, #TASK_SIZE_64 str x20, [tsk, #TI_ADDR_LIMIT] - ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO) + /* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */ .endif /* \el == 0 */ mrs x22, elr_el1 mrs x23, spsr_el1 @@ -150,13 +150,7 @@ ldr x23, [sp, #S_SP] // load return stack pointer msr sp_el0, x23 #ifdef CONFIG_ARM64_ERRATUM_845719 -alternative_if_not ARM64_WORKAROUND_845719 - nop - nop -#ifdef CONFIG_PID_IN_CONTEXTIDR - nop -#endif -alternative_else +alternative_if ARM64_WORKAROUND_845719 tbz x22, #4, 1f #ifdef CONFIG_PID_IN_CONTEXTIDR mrs x29, contextidr_el1 @@ -165,7 +159,7 @@ alternative_else msr contextidr_el1, xzr #endif 1: -alternative_endif +alternative_else_nop_endif #endif .endif msr elr_el1, x21 // set up the return data @@ -707,18 +701,13 @@ ret_fast_syscall_trace: * Ok, we need to do extra processing, enter the slow path. */ work_pending: - tbnz x1, #TIF_NEED_RESCHED, work_resched - /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */ mov x0, sp // 'regs' - enable_irq // enable interrupts for do_notify_resume() bl do_notify_resume - b ret_to_user -work_resched: #ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off // the IRQs are off here, inform the tracing code + bl trace_hardirqs_on // enabled while in userspace #endif - bl schedule - + ldr x1, [tsk, #TI_FLAGS] // re-check for single-step + b finish_ret_to_user /* * "slow" syscall return path. */ @@ -727,6 +716,7 @@ ret_to_user: ldr x1, [tsk, #TI_FLAGS] and x2, x1, #_TIF_WORK_MASK cbnz x2, work_pending +finish_ret_to_user: enable_step_tsk x1, x2 kernel_exit 0 ENDPROC(ret_to_user) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 975b274ee7b5..394c61db5566 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -299,28 +299,16 @@ static inline void fpsimd_pm_init(void) { } #endif /* CONFIG_CPU_PM */ #ifdef CONFIG_HOTPLUG_CPU -static int fpsimd_cpu_hotplug_notifier(struct notifier_block *nfb, - unsigned long action, - void *hcpu) +static int fpsimd_cpu_dead(unsigned int cpu) { - unsigned int cpu = (long)hcpu; - - switch (action) { - case CPU_DEAD: - case CPU_DEAD_FROZEN: - per_cpu(fpsimd_last_state, cpu) = NULL; - break; - } - return NOTIFY_OK; + per_cpu(fpsimd_last_state, cpu) = NULL; + return 0; } -static struct notifier_block fpsimd_cpu_hotplug_notifier_block = { - .notifier_call = fpsimd_cpu_hotplug_notifier, -}; - static inline void fpsimd_hotplug_init(void) { - register_cpu_notifier(&fpsimd_cpu_hotplug_notifier_block); + cpuhp_setup_state_nocalls(CPUHP_ARM64_FPSIMD_DEAD, "arm64/fpsimd:dead", + NULL, fpsimd_cpu_dead); } #else diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index ebecf9aa33d1..40ad08ac569a 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -138,7 +138,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, return; err = ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer); + frame_pointer, NULL); if (err == -EBUSY) return; else diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 3e7b050e99dc..427f6d3f084c 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -208,13 +208,23 @@ efi_header_end: __INIT + /* + * The following callee saved general purpose registers are used on the + * primary lowlevel boot path: + * + * Register Scope Purpose + * x21 stext() .. start_kernel() FDT pointer passed at boot in x0 + * x23 stext() .. start_kernel() physical misalignment/KASLR offset + * x28 __create_page_tables() callee preserved temp register + * x19/x20 __primary_switch() callee preserved temp registers + */ ENTRY(stext) bl preserve_boot_args - bl el2_setup // Drop to EL1, w20=cpu_boot_mode - adrp x24, __PHYS_OFFSET - and x23, x24, MIN_KIMG_ALIGN - 1 // KASLR offset, defaults to 0 + bl el2_setup // Drop to EL1, w0=cpu_boot_mode + adrp x23, __PHYS_OFFSET + and x23, x23, MIN_KIMG_ALIGN - 1 // KASLR offset, defaults to 0 bl set_cpu_boot_mode_flag - bl __create_page_tables // x25=TTBR0, x26=TTBR1 + bl __create_page_tables /* * The following calls CPU setup code, see arch/arm64/mm/proc.S for * details. @@ -222,9 +232,7 @@ ENTRY(stext) * the TCR will have been set. */ bl __cpu_setup // initialise processor - adr_l x27, __primary_switch // address to jump to after - // MMU has been enabled - b __enable_mmu + b __primary_switch ENDPROC(stext) /* @@ -311,23 +319,21 @@ ENDPROC(preserve_boot_args) * been enabled */ __create_page_tables: - adrp x25, idmap_pg_dir - adrp x26, swapper_pg_dir mov x28, lr /* * Invalidate the idmap and swapper page tables to avoid potential * dirty cache lines being evicted. */ - mov x0, x25 - add x1, x26, #SWAPPER_DIR_SIZE + adrp x0, idmap_pg_dir + adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE bl __inval_cache_range /* * Clear the idmap and swapper page tables. */ - mov x0, x25 - add x6, x26, #SWAPPER_DIR_SIZE + adrp x0, idmap_pg_dir + adrp x6, swapper_pg_dir + SWAPPER_DIR_SIZE 1: stp xzr, xzr, [x0], #16 stp xzr, xzr, [x0], #16 stp xzr, xzr, [x0], #16 @@ -340,7 +346,7 @@ __create_page_tables: /* * Create the identity mapping. */ - mov x0, x25 // idmap_pg_dir + adrp x0, idmap_pg_dir adrp x3, __idmap_text_start // __pa(__idmap_text_start) #ifndef CONFIG_ARM64_VA_BITS_48 @@ -390,7 +396,7 @@ __create_page_tables: /* * Map the kernel image (starting with PHYS_OFFSET). */ - mov x0, x26 // swapper_pg_dir + adrp x0, swapper_pg_dir mov_q x5, KIMAGE_VADDR + TEXT_OFFSET // compile time __va(_text) add x5, x5, x23 // add KASLR displacement create_pgd_entry x0, x5, x3, x6 @@ -405,8 +411,8 @@ __create_page_tables: * accesses (MMU disabled), invalidate the idmap and swapper page * tables again to remove any speculatively loaded cache lines. */ - mov x0, x25 - add x1, x26, #SWAPPER_DIR_SIZE + adrp x0, idmap_pg_dir + adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE dmb sy bl __inval_cache_range @@ -416,14 +422,27 @@ ENDPROC(__create_page_tables) /* * The following fragment of code is executed with the MMU enabled. + * + * x0 = __PHYS_OFFSET */ - .set initial_sp, init_thread_union + THREAD_START_SP __primary_switched: - mov x28, lr // preserve LR + adrp x4, init_thread_union + add sp, x4, #THREAD_SIZE + msr sp_el0, x4 // Save thread_info + adr_l x8, vectors // load VBAR_EL1 with virtual msr vbar_el1, x8 // vector table address isb + stp xzr, x30, [sp, #-16]! + mov x29, sp + + str_l x21, __fdt_pointer, x5 // Save FDT pointer + + ldr_l x4, kimage_vaddr // Save the offset between + sub x4, x4, x0 // the kernel virtual and + str_l x4, kimage_voffset, x5 // physical mappings + // Clear BSS adr_l x0, __bss_start mov x1, xzr @@ -432,17 +451,6 @@ __primary_switched: bl __pi_memset dsb ishst // Make zero page visible to PTW - adr_l sp, initial_sp, x4 - mov x4, sp - and x4, x4, #~(THREAD_SIZE - 1) - msr sp_el0, x4 // Save thread_info - str_l x21, __fdt_pointer, x5 // Save FDT pointer - - ldr_l x4, kimage_vaddr // Save the offset between - sub x4, x4, x24 // the kernel virtual and - str_l x4, kimage_voffset, x5 // physical mappings - - mov x29, #0 #ifdef CONFIG_KASAN bl kasan_early_init #endif @@ -454,8 +462,8 @@ __primary_switched: bl kaslr_early_init // parse FDT for KASLR options cbz x0, 0f // KASLR disabled? just proceed orr x23, x23, x0 // record KASLR offset - ret x28 // we must enable KASLR, return - // to __enable_mmu() + ldp x29, x30, [sp], #16 // we must enable KASLR, return + ret // to __primary_switch() 0: #endif b start_kernel @@ -465,7 +473,7 @@ ENDPROC(__primary_switched) * end early head section, begin head code that is also used for * hotplug and needs to have the same protections as the text region */ - .section ".text","ax" + .section ".idmap.text","ax" ENTRY(kimage_vaddr) .quad _text - TEXT_OFFSET @@ -490,7 +498,7 @@ CPU_LE( bic x0, x0, #(1 << 25) ) // Clear the EE bit for EL2 CPU_BE( orr x0, x0, #(3 << 24) ) // Set the EE and E0E bits for EL1 CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1 msr sctlr_el1, x0 - mov w20, #BOOT_CPU_MODE_EL1 // This cpu booted in EL1 + mov w0, #BOOT_CPU_MODE_EL1 // This cpu booted in EL1 isb ret @@ -586,7 +594,7 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems cbz x2, install_el2_stub - mov w20, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2 + mov w0, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2 isb ret @@ -601,7 +609,7 @@ install_el2_stub: PSR_MODE_EL1h) msr spsr_el2, x0 msr elr_el2, lr - mov w20, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2 + mov w0, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2 eret ENDPROC(el2_setup) @@ -611,27 +619,39 @@ ENDPROC(el2_setup) */ set_cpu_boot_mode_flag: adr_l x1, __boot_cpu_mode - cmp w20, #BOOT_CPU_MODE_EL2 + cmp w0, #BOOT_CPU_MODE_EL2 b.ne 1f add x1, x1, #4 -1: str w20, [x1] // This CPU has booted in EL1 +1: str w0, [x1] // This CPU has booted in EL1 dmb sy dc ivac, x1 // Invalidate potentially stale cache line ret ENDPROC(set_cpu_boot_mode_flag) /* + * These values are written with the MMU off, but read with the MMU on. + * Writers will invalidate the corresponding address, discarding up to a + * 'Cache Writeback Granule' (CWG) worth of data. The linker script ensures + * sufficient alignment that the CWG doesn't overlap another section. + */ + .pushsection ".mmuoff.data.write", "aw" +/* * We need to find out the CPU boot mode long after boot, so we need to * store it in a writable variable. * * This is not in .bss, because we set it sufficiently early that the boot-time * zeroing of .bss would clobber it. */ - .pushsection .data..cacheline_aligned - .align L1_CACHE_SHIFT ENTRY(__boot_cpu_mode) .long BOOT_CPU_MODE_EL2 .long BOOT_CPU_MODE_EL1 +/* + * The booting CPU updates the failed status @__early_cpu_boot_status, + * with MMU turned off. + */ +ENTRY(__early_cpu_boot_status) + .long 0 + .popsection /* @@ -639,7 +659,7 @@ ENTRY(__boot_cpu_mode) * cores are held until we're ready for them to initialise. */ ENTRY(secondary_holding_pen) - bl el2_setup // Drop to EL1, w20=cpu_boot_mode + bl el2_setup // Drop to EL1, w0=cpu_boot_mode bl set_cpu_boot_mode_flag mrs x0, mpidr_el1 mov_q x1, MPIDR_HWID_BITMASK @@ -666,12 +686,10 @@ secondary_startup: /* * Common entry point for secondary CPUs. */ - adrp x25, idmap_pg_dir - adrp x26, swapper_pg_dir bl __cpu_setup // initialise processor - - adr_l x27, __secondary_switch // address to jump to after enabling the MMU - b __enable_mmu + bl __enable_mmu + ldr x8, =__secondary_switched + br x8 ENDPROC(secondary_startup) __secondary_switched: @@ -706,33 +724,27 @@ ENDPROC(__secondary_switched) dc ivac, \tmp1 // Invalidate potentially stale cache line .endm - .pushsection .data..cacheline_aligned - .align L1_CACHE_SHIFT -ENTRY(__early_cpu_boot_status) - .long 0 - .popsection - /* * Enable the MMU. * * x0 = SCTLR_EL1 value for turning on the MMU. - * x27 = *virtual* address to jump to upon completion * - * Other registers depend on the function called upon completion. + * Returns to the caller via x30/lr. This requires the caller to be covered + * by the .idmap.text section. * * Checks if the selected granule size is supported by the CPU. * If it isn't, park the CPU */ - .section ".idmap.text", "ax" ENTRY(__enable_mmu) - mrs x22, sctlr_el1 // preserve old SCTLR_EL1 value mrs x1, ID_AA64MMFR0_EL1 ubfx x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4 cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED b.ne __no_granule_support update_early_cpu_boot_status 0, x1, x2 - msr ttbr0_el1, x25 // load TTBR0 - msr ttbr1_el1, x26 // load TTBR1 + adrp x1, idmap_pg_dir + adrp x2, swapper_pg_dir + msr ttbr0_el1, x1 // load TTBR0 + msr ttbr1_el1, x2 // load TTBR1 isb msr sctlr_el1, x0 isb @@ -744,29 +756,7 @@ ENTRY(__enable_mmu) ic iallu dsb nsh isb -#ifdef CONFIG_RANDOMIZE_BASE - mov x19, x0 // preserve new SCTLR_EL1 value - blr x27 - - /* - * If we return here, we have a KASLR displacement in x23 which we need - * to take into account by discarding the current kernel mapping and - * creating a new one. - */ - msr sctlr_el1, x22 // disable the MMU - isb - bl __create_page_tables // recreate kernel mapping - - tlbi vmalle1 // Remove any stale TLB entries - dsb nsh - - msr sctlr_el1, x19 // re-enable the MMU - isb - ic iallu // flush instructions fetched - dsb nsh // via old mapping - isb -#endif - br x27 + ret ENDPROC(__enable_mmu) __no_granule_support: @@ -775,11 +765,11 @@ __no_granule_support: 1: wfe wfi - b 1b + b 1b ENDPROC(__no_granule_support) -__primary_switch: #ifdef CONFIG_RELOCATABLE +__relocate_kernel: /* * Iterate over each entry in the relocation table, and apply the * relocations in place. @@ -801,14 +791,46 @@ __primary_switch: add x13, x13, x23 // relocate str x13, [x11, x23] b 0b +1: ret +ENDPROC(__relocate_kernel) +#endif -1: +__primary_switch: +#ifdef CONFIG_RANDOMIZE_BASE + mov x19, x0 // preserve new SCTLR_EL1 value + mrs x20, sctlr_el1 // preserve old SCTLR_EL1 value #endif + + bl __enable_mmu +#ifdef CONFIG_RELOCATABLE + bl __relocate_kernel +#ifdef CONFIG_RANDOMIZE_BASE ldr x8, =__primary_switched - br x8 -ENDPROC(__primary_switch) + adrp x0, __PHYS_OFFSET + blr x8 -__secondary_switch: - ldr x8, =__secondary_switched + /* + * If we return here, we have a KASLR displacement in x23 which we need + * to take into account by discarding the current kernel mapping and + * creating a new one. + */ + msr sctlr_el1, x20 // disable the MMU + isb + bl __create_page_tables // recreate kernel mapping + + tlbi vmalle1 // Remove any stale TLB entries + dsb nsh + + msr sctlr_el1, x19 // re-enable the MMU + isb + ic iallu // flush instructions fetched + dsb nsh // via old mapping + isb + + bl __relocate_kernel +#endif +#endif + ldr x8, =__primary_switched + adrp x0, __PHYS_OFFSET br x8 -ENDPROC(__secondary_switch) +ENDPROC(__primary_switch) diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S index 46f29b6560ec..e56d848b6466 100644 --- a/arch/arm64/kernel/hibernate-asm.S +++ b/arch/arm64/kernel/hibernate-asm.S @@ -36,8 +36,8 @@ .macro break_before_make_ttbr_switch zero_page, page_table msr ttbr1_el1, \zero_page isb - tlbi vmalle1is - dsb ish + tlbi vmalle1 + dsb nsh msr ttbr1_el1, \page_table isb .endm @@ -96,7 +96,7 @@ ENTRY(swsusp_arch_suspend_exit) add x1, x10, #PAGE_SIZE /* Clean the copied page to PoU - based on flush_icache_range() */ - dcache_line_size x2, x3 + raw_dcache_line_size x2, x3 sub x3, x2, #1 bic x4, x10, x3 2: dc cvau, x4 /* clean D line / unified line */ diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 65d81f965e74..d55a7b09959b 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -15,9 +15,9 @@ * License terms: GNU General Public License (GPL) version 2 */ #define pr_fmt(x) "hibernate: " x +#include <linux/cpu.h> #include <linux/kvm_host.h> #include <linux/mm.h> -#include <linux/notifier.h> #include <linux/pm.h> #include <linux/sched.h> #include <linux/suspend.h> @@ -26,6 +26,7 @@ #include <asm/barrier.h> #include <asm/cacheflush.h> +#include <asm/cputype.h> #include <asm/irqflags.h> #include <asm/memory.h> #include <asm/mmu_context.h> @@ -34,6 +35,7 @@ #include <asm/pgtable-hwdef.h> #include <asm/sections.h> #include <asm/smp.h> +#include <asm/smp_plat.h> #include <asm/suspend.h> #include <asm/sysreg.h> #include <asm/virt.h> @@ -54,12 +56,6 @@ extern int in_suspend; /* Do we need to reset el2? */ #define el2_reset_needed() (is_hyp_mode_available() && !is_kernel_in_hyp_mode()) -/* - * Start/end of the hibernate exit code, this must be copied to a 'safe' - * location in memory, and executed from there. - */ -extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[]; - /* temporary el2 vectors in the __hibernate_exit_text section. */ extern char hibernate_el2_vectors[]; @@ -67,6 +63,12 @@ extern char hibernate_el2_vectors[]; extern char __hyp_stub_vectors[]; /* + * The logical cpu number we should resume on, initialised to a non-cpu + * number. + */ +static int sleep_cpu = -EINVAL; + +/* * Values that may not change over hibernate/resume. We put the build number * and date in here so that we guarantee not to resume with a different * kernel. @@ -88,6 +90,8 @@ static struct arch_hibernate_hdr { * re-configure el2. */ phys_addr_t __hyp_stub_vectors; + + u64 sleep_cpu_mpidr; } resume_hdr; static inline void arch_hdr_invariants(struct arch_hibernate_hdr_invariants *i) @@ -130,12 +134,22 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size) else hdr->__hyp_stub_vectors = 0; + /* Save the mpidr of the cpu we called cpu_suspend() on... */ + if (sleep_cpu < 0) { + pr_err("Failing to hibernate on an unkown CPU.\n"); + return -ENODEV; + } + hdr->sleep_cpu_mpidr = cpu_logical_map(sleep_cpu); + pr_info("Hibernating on CPU %d [mpidr:0x%llx]\n", sleep_cpu, + hdr->sleep_cpu_mpidr); + return 0; } EXPORT_SYMBOL(arch_hibernation_header_save); int arch_hibernation_header_restore(void *addr) { + int ret; struct arch_hibernate_hdr_invariants invariants; struct arch_hibernate_hdr *hdr = addr; @@ -145,6 +159,24 @@ int arch_hibernation_header_restore(void *addr) return -EINVAL; } + sleep_cpu = get_logical_index(hdr->sleep_cpu_mpidr); + pr_info("Hibernated on CPU %d [mpidr:0x%llx]\n", sleep_cpu, + hdr->sleep_cpu_mpidr); + if (sleep_cpu < 0) { + pr_crit("Hibernated on a CPU not known to this kernel!\n"); + sleep_cpu = -EINVAL; + return -EINVAL; + } + if (!cpu_online(sleep_cpu)) { + pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n"); + ret = cpu_up(sleep_cpu); + if (ret) { + pr_err("Failed to bring hibernate-CPU up!\n"); + sleep_cpu = -EINVAL; + return ret; + } + } + resume_hdr = *hdr; return 0; @@ -241,6 +273,7 @@ out: return rc; } +#define dcache_clean_range(start, end) __flush_dcache_area(start, (end - start)) int swsusp_arch_suspend(void) { @@ -256,10 +289,16 @@ int swsusp_arch_suspend(void) local_dbg_save(flags); if (__cpu_suspend_enter(&state)) { + sleep_cpu = smp_processor_id(); ret = swsusp_save(); } else { - /* Clean kernel to PoC for secondary core startup */ - __flush_dcache_area(LMADDR(KERNEL_START), KERNEL_END - KERNEL_START); + /* Clean kernel core startup/idle code to PoC*/ + dcache_clean_range(__mmuoff_data_start, __mmuoff_data_end); + dcache_clean_range(__idmap_text_start, __idmap_text_end); + + /* Clean kvm setup code to PoC? */ + if (el2_reset_needed()) + dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end); /* * Tell the hibernation core that we've just restored @@ -267,6 +306,7 @@ int swsusp_arch_suspend(void) */ in_suspend = 0; + sleep_cpu = -EINVAL; __cpu_suspend_exit(); } @@ -275,6 +315,33 @@ int swsusp_arch_suspend(void) return ret; } +static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr) +{ + pte_t pte = *src_pte; + + if (pte_valid(pte)) { + /* + * Resume will overwrite areas that may be marked + * read only (code, rodata). Clear the RDONLY bit from + * the temporary mappings we use during restore. + */ + set_pte(dst_pte, pte_clear_rdonly(pte)); + } else if (debug_pagealloc_enabled() && !pte_none(pte)) { + /* + * debug_pagealloc will removed the PTE_VALID bit if + * the page isn't in use by the resume kernel. It may have + * been in use by the original kernel, in which case we need + * to put it back in our copy to do the restore. + * + * Before marking this entry valid, check the pfn should + * be mapped. + */ + BUG_ON(!pfn_valid(pte_pfn(pte))); + + set_pte(dst_pte, pte_mkpresent(pte_clear_rdonly(pte))); + } +} + static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start, unsigned long end) { @@ -290,13 +357,7 @@ static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start, src_pte = pte_offset_kernel(src_pmd, start); do { - if (!pte_none(*src_pte)) - /* - * Resume will overwrite areas that may be marked - * read only (code, rodata). Clear the RDONLY bit from - * the temporary mappings we use during restore. - */ - set_pte(dst_pte, __pte(pte_val(*src_pte) & ~PTE_RDONLY)); + _copy_pte(dst_pte, src_pte, addr); } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); return 0; @@ -483,27 +544,12 @@ out: return rc; } -static int check_boot_cpu_online_pm_callback(struct notifier_block *nb, - unsigned long action, void *ptr) +int hibernate_resume_nonboot_cpu_disable(void) { - if (action == PM_HIBERNATION_PREPARE && - cpumask_first(cpu_online_mask) != 0) { - pr_warn("CPU0 is offline.\n"); - return notifier_from_errno(-ENODEV); + if (sleep_cpu < 0) { + pr_err("Failing to resume from hibernate on an unkown CPU.\n"); + return -ENODEV; } - return NOTIFY_OK; -} - -static int __init check_boot_cpu_online_init(void) -{ - /* - * Set this pm_notifier callback with a lower priority than - * cpu_hotplug_pm_callback, so that cpu_hotplug_pm_callback will be - * called earlier to disable cpu hotplug before the cpu online check. - */ - pm_notifier(check_boot_cpu_online_pm_callback, -INT_MAX); - - return 0; + return freeze_secondary_cpus(sleep_cpu); } -core_initcall(check_boot_cpu_online_init); diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 26a6bf77d272..948b73148d56 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -857,7 +857,7 @@ void hw_breakpoint_thread_switch(struct task_struct *next) /* * CPU initialisation. */ -static void hw_breakpoint_reset(void *unused) +static int hw_breakpoint_reset(unsigned int cpu) { int i; struct perf_event **slots; @@ -888,28 +888,14 @@ static void hw_breakpoint_reset(void *unused) write_wb_reg(AARCH64_DBG_REG_WVR, i, 0UL); } } -} -static int hw_breakpoint_reset_notify(struct notifier_block *self, - unsigned long action, - void *hcpu) -{ - if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE) { - local_irq_disable(); - hw_breakpoint_reset(NULL); - local_irq_enable(); - } - return NOTIFY_OK; + return 0; } -static struct notifier_block hw_breakpoint_reset_nb = { - .notifier_call = hw_breakpoint_reset_notify, -}; - #ifdef CONFIG_CPU_PM -extern void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)); +extern void cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int)); #else -static inline void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)) +static inline void cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int)) { } #endif @@ -919,36 +905,34 @@ static inline void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)) */ static int __init arch_hw_breakpoint_init(void) { + int ret; + core_num_brps = get_num_brps(); core_num_wrps = get_num_wrps(); pr_info("found %d breakpoint and %d watchpoint registers.\n", core_num_brps, core_num_wrps); - cpu_notifier_register_begin(); - - /* - * Reset the breakpoint resources. We assume that a halting - * debugger will leave the world in a nice state for us. - */ - smp_call_function(hw_breakpoint_reset, NULL, 1); - hw_breakpoint_reset(NULL); - /* Register debug fault handlers. */ hook_debug_fault_code(DBG_ESR_EVT_HWBP, breakpoint_handler, SIGTRAP, TRAP_HWBKPT, "hw-breakpoint handler"); hook_debug_fault_code(DBG_ESR_EVT_HWWP, watchpoint_handler, SIGTRAP, TRAP_HWBKPT, "hw-watchpoint handler"); - /* Register hotplug notifier. */ - __register_cpu_notifier(&hw_breakpoint_reset_nb); - - cpu_notifier_register_done(); + /* + * Reset the breakpoint resources. We assume that a halting + * debugger will leave the world in a nice state for us. + */ + ret = cpuhp_setup_state(CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING, + "CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING", + hw_breakpoint_reset, NULL); + if (ret) + pr_err("failed to register CPU hotplug notifier: %d\n", ret); /* Register cpu_suspend hw breakpoint restore hook */ cpu_suspend_set_dbg_restorer(hw_breakpoint_reset); - return 0; + return ret; } arch_initcall(arch_hw_breakpoint_init); diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 63f9432d05e8..6f2ac4fc66ca 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -96,7 +96,7 @@ static void __kprobes *patch_map(void *addr, int fixmap) if (module && IS_ENABLED(CONFIG_DEBUG_SET_MODULE_RONX)) page = vmalloc_to_page(addr); - else if (!module && IS_ENABLED(CONFIG_DEBUG_RODATA)) + else if (!module) page = pfn_to_page(PHYS_PFN(__pa(addr))); else return addr; @@ -1202,6 +1202,19 @@ u32 aarch64_set_branch_offset(u32 insn, s32 offset) BUG(); } +s32 aarch64_insn_adrp_get_offset(u32 insn) +{ + BUG_ON(!aarch64_insn_is_adrp(insn)); + return aarch64_insn_decode_immediate(AARCH64_INSN_IMM_ADR, insn) << 12; +} + +u32 aarch64_insn_adrp_set_offset(u32 insn, s32 offset) +{ + BUG_ON(!aarch64_insn_is_adrp(insn)); + return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_ADR, insn, + offset >> 12); +} + /* * Extract the Op/CR data from a msr/mrs instruction. */ diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index b05469173ba5..769f24ef628c 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -6,6 +6,7 @@ * published by the Free Software Foundation. */ +#include <linux/cache.h> #include <linux/crc32.h> #include <linux/init.h> #include <linux/libfdt.h> @@ -20,7 +21,7 @@ #include <asm/pgtable.h> #include <asm/sections.h> -u64 __read_mostly module_alloc_base; +u64 __ro_after_init module_alloc_base; u16 __initdata memstart_offset_seed; static __init u64 get_kaslr_seed(void *fdt) diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c index 8c57f6496e56..e017a9493b92 100644 --- a/arch/arm64/kernel/kgdb.c +++ b/arch/arm64/kernel/kgdb.c @@ -19,10 +19,13 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/bug.h> #include <linux/irq.h> #include <linux/kdebug.h> #include <linux/kgdb.h> #include <linux/kprobes.h> +#include <asm/debug-monitors.h> +#include <asm/insn.h> #include <asm/traps.h> struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { @@ -338,15 +341,24 @@ void kgdb_arch_exit(void) unregister_die_notifier(&kgdb_notifier); } -/* - * ARM instructions are always in LE. - * Break instruction is encoded in LE format - */ -struct kgdb_arch arch_kgdb_ops = { - .gdb_bpt_instr = { - KGDB_DYN_BRK_INS_BYTE(0), - KGDB_DYN_BRK_INS_BYTE(1), - KGDB_DYN_BRK_INS_BYTE(2), - KGDB_DYN_BRK_INS_BYTE(3), - } -}; +struct kgdb_arch arch_kgdb_ops; + +int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) +{ + int err; + + BUILD_BUG_ON(AARCH64_INSN_SIZE != BREAK_INSTR_SIZE); + + err = aarch64_insn_read((void *)bpt->bpt_addr, (u32 *)bpt->saved_instr); + if (err) + return err; + + return aarch64_insn_write((void *)bpt->bpt_addr, + (u32)AARCH64_BREAK_KGDB_DYN_DBG); +} + +int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) +{ + return aarch64_insn_write((void *)bpt->bpt_addr, + *(u32 *)bpt->saved_instr); +} diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 838ccf123307..a9310a69fffd 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -24,6 +24,7 @@ #include <asm/sysreg.h> #include <asm/virt.h> +#include <linux/acpi.h> #include <linux/of.h> #include <linux/perf/arm_pmu.h> #include <linux/platform_device.h> @@ -190,13 +191,23 @@ #define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS 0xED /* PMUv3 HW events mapping. */ + +/* + * ARMv8 Architectural defined events, not all of these may + * be supported on any given implementation. Undefined events will + * be disabled at run-time. + */ static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = { PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INST_RETIRED, [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE, [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED, + [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV8_PMUV3_PERFCTR_STALL_FRONTEND, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV8_PMUV3_PERFCTR_STALL_BACKEND, }; /* ARM Cortex-A53 HW events mapping. */ @@ -258,6 +269,15 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE, [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL, + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL, + [C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_TLB, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL, + [C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB, + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED, [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED, [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED, @@ -523,12 +543,6 @@ static struct attribute_group armv8_pmuv3_format_attr_group = { .attrs = armv8_pmuv3_format_attrs, }; -static const struct attribute_group *armv8_pmuv3_attr_groups[] = { - &armv8_pmuv3_events_attr_group, - &armv8_pmuv3_format_attr_group, - NULL, -}; - /* * Perf Events' indices */ @@ -905,9 +919,22 @@ static void armv8pmu_reset(void *info) static int armv8_pmuv3_map_event(struct perf_event *event) { - return armpmu_map_event(event, &armv8_pmuv3_perf_map, - &armv8_pmuv3_perf_cache_map, - ARMV8_PMU_EVTYPE_EVENT); + int hw_event_id; + struct arm_pmu *armpmu = to_arm_pmu(event->pmu); + + hw_event_id = armpmu_map_event(event, &armv8_pmuv3_perf_map, + &armv8_pmuv3_perf_cache_map, + ARMV8_PMU_EVTYPE_EVENT); + if (hw_event_id < 0) + return hw_event_id; + + /* disable micro/arch events not supported by this PMU */ + if ((hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS) && + !test_bit(hw_event_id, armpmu->pmceid_bitmap)) { + return -EOPNOTSUPP; + } + + return hw_event_id; } static int armv8_a53_map_event(struct perf_event *event) @@ -985,7 +1012,10 @@ static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu) armv8_pmu_init(cpu_pmu); cpu_pmu->name = "armv8_pmuv3"; cpu_pmu->map_event = armv8_pmuv3_map_event; - cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv8_pmuv3_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv8_pmuv3_format_attr_group; return armv8pmu_probe_pmu(cpu_pmu); } @@ -994,7 +1024,10 @@ static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu) armv8_pmu_init(cpu_pmu); cpu_pmu->name = "armv8_cortex_a53"; cpu_pmu->map_event = armv8_a53_map_event; - cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv8_pmuv3_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv8_pmuv3_format_attr_group; return armv8pmu_probe_pmu(cpu_pmu); } @@ -1003,7 +1036,10 @@ static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu) armv8_pmu_init(cpu_pmu); cpu_pmu->name = "armv8_cortex_a57"; cpu_pmu->map_event = armv8_a57_map_event; - cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv8_pmuv3_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv8_pmuv3_format_attr_group; return armv8pmu_probe_pmu(cpu_pmu); } @@ -1012,7 +1048,10 @@ static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu) armv8_pmu_init(cpu_pmu); cpu_pmu->name = "armv8_cortex_a72"; cpu_pmu->map_event = armv8_a57_map_event; - cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv8_pmuv3_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv8_pmuv3_format_attr_group; return armv8pmu_probe_pmu(cpu_pmu); } @@ -1021,7 +1060,10 @@ static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu) armv8_pmu_init(cpu_pmu); cpu_pmu->name = "armv8_cavium_thunder"; cpu_pmu->map_event = armv8_thunder_map_event; - cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv8_pmuv3_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv8_pmuv3_format_attr_group; return armv8pmu_probe_pmu(cpu_pmu); } @@ -1030,7 +1072,10 @@ static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu) armv8_pmu_init(cpu_pmu); cpu_pmu->name = "armv8_brcm_vulcan"; cpu_pmu->map_event = armv8_vulcan_map_event; - cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv8_pmuv3_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv8_pmuv3_format_attr_group; return armv8pmu_probe_pmu(cpu_pmu); } @@ -1044,21 +1089,32 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = { {}, }; +/* + * Non DT systems have their micro/arch events probed at run-time. + * A fairly complete list of generic events are provided and ones that + * aren't supported by the current PMU are disabled. + */ +static const struct pmu_probe_info armv8_pmu_probe_table[] = { + PMU_PROBE(0, 0, armv8_pmuv3_init), /* enable all defined counters */ + { /* sentinel value */ } +}; + static int armv8_pmu_device_probe(struct platform_device *pdev) { - return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, NULL); + if (acpi_disabled) + return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, + NULL); + + return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, + armv8_pmu_probe_table); } static struct platform_driver armv8_pmu_driver = { .driver = { - .name = "armv8-pmu", + .name = ARMV8_PMU_PDEV_NAME, .of_match_table = armv8_pmu_of_device_ids, }, .probe = armv8_pmu_device_probe, }; -static int __init register_armv8_pmu_driver(void) -{ - return platform_driver_register(&armv8_pmu_driver); -} -device_initcall(register_armv8_pmu_driver); +builtin_platform_driver(armv8_pmu_driver); diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c index 37e47a9d617e..d1731bf977ef 100644 --- a/arch/arm64/kernel/probes/decode-insn.c +++ b/arch/arm64/kernel/probes/decode-insn.c @@ -16,6 +16,7 @@ #include <linux/kernel.h> #include <linux/kprobes.h> #include <linux/module.h> +#include <linux/kallsyms.h> #include <asm/kprobes.h> #include <asm/insn.h> #include <asm/sections.h> @@ -122,7 +123,7 @@ arm_probe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) static bool __kprobes is_probed_address_atomic(kprobe_opcode_t *scan_start, kprobe_opcode_t *scan_end) { - while (scan_start > scan_end) { + while (scan_start >= scan_end) { /* * atomic region starts from exclusive load and ends with * exclusive store. @@ -142,33 +143,30 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi) { enum kprobe_insn decoded; kprobe_opcode_t insn = le32_to_cpu(*addr); - kprobe_opcode_t *scan_start = addr - 1; - kprobe_opcode_t *scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE; -#if defined(CONFIG_MODULES) && defined(MODULES_VADDR) - struct module *mod; -#endif - - if (addr >= (kprobe_opcode_t *)_text && - scan_end < (kprobe_opcode_t *)_text) - scan_end = (kprobe_opcode_t *)_text; -#if defined(CONFIG_MODULES) && defined(MODULES_VADDR) - else { - preempt_disable(); - mod = __module_address((unsigned long)addr); - if (mod && within_module_init((unsigned long)addr, mod) && - !within_module_init((unsigned long)scan_end, mod)) - scan_end = (kprobe_opcode_t *)mod->init_layout.base; - else if (mod && within_module_core((unsigned long)addr, mod) && - !within_module_core((unsigned long)scan_end, mod)) - scan_end = (kprobe_opcode_t *)mod->core_layout.base; - preempt_enable(); + kprobe_opcode_t *scan_end = NULL; + unsigned long size = 0, offset = 0; + + /* + * If there's a symbol defined in front of and near enough to + * the probe address assume it is the entry point to this + * code and use it to further limit how far back we search + * when determining if we're in an atomic sequence. If we could + * not find any symbol skip the atomic test altogether as we + * could otherwise end up searching irrelevant text/literals. + * KPROBES depends on KALLSYMS so this last case should never + * happen. + */ + if (kallsyms_lookup_size_offset((unsigned long) addr, &size, &offset)) { + if (offset < (MAX_ATOMIC_CONTEXT_SIZE*sizeof(kprobe_opcode_t))) + scan_end = addr - (offset / sizeof(kprobe_opcode_t)); + else + scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE; } -#endif decoded = arm_probe_decode_insn(insn, asi); - if (decoded == INSN_REJECTED || - is_probed_address_atomic(scan_start, scan_end)) - return INSN_REJECTED; + if (decoded != INSN_REJECTED && scan_end) + if (is_probed_address_atomic(addr - 1, scan_end)) + return INSN_REJECTED; return decoded; } diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index c6b0f40620d8..f5077ea7af6d 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -19,7 +19,7 @@ #include <linux/kasan.h> #include <linux/kernel.h> #include <linux/kprobes.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/slab.h> #include <linux/stop_machine.h> #include <linux/stringify.h> @@ -31,7 +31,7 @@ #include <asm/insn.h> #include <asm/uaccess.h> #include <asm/irq.h> -#include <asm-generic/sections.h> +#include <asm/sections.h> #include "decode-insn.h" @@ -166,13 +166,18 @@ static void __kprobes set_current_kprobe(struct kprobe *p) } /* - * The D-flag (Debug mask) is set (masked) upon debug exception entry. - * Kprobes needs to clear (unmask) D-flag -ONLY- in case of recursive - * probe i.e. when probe hit from kprobe handler context upon - * executing the pre/post handlers. In this case we return with - * D-flag clear so that single-stepping can be carried-out. - * - * Leave D-flag set in all other cases. + * When PSTATE.D is set (masked), then software step exceptions can not be + * generated. + * SPSR's D bit shows the value of PSTATE.D immediately before the + * exception was taken. PSTATE.D is set while entering into any exception + * mode, however software clears it for any normal (none-debug-exception) + * mode in the exception entry. Therefore, when we are entering into kprobe + * breakpoint handler from any normal mode then SPSR.D bit is already + * cleared, however it is set when we are entering from any debug exception + * mode. + * Since we always need to generate single step exception after a kprobe + * breakpoint exception therefore we need to clear it unconditionally, when + * we become sure that the current breakpoint exception is for kprobe. */ static void __kprobes spsr_set_debug_flag(struct pt_regs *regs, int mask) @@ -245,10 +250,7 @@ static void __kprobes setup_singlestep(struct kprobe *p, set_ss_context(kcb, slot); /* mark pending ss */ - if (kcb->kprobe_status == KPROBE_REENTER) - spsr_set_debug_flag(regs, 0); - else - WARN_ON(regs->pstate & PSR_D_BIT); + spsr_set_debug_flag(regs, 0); /* IRQs and single stepping do not mix well. */ kprobes_save_local_irqflag(kcb, regs); @@ -333,8 +335,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr) BUG(); kernel_disable_single_step(); - if (kcb->kprobe_status == KPROBE_REENTER) - spsr_set_debug_flag(regs, 1); if (kcb->kprobe_status == KPROBE_REENTER) restore_previous_kprobe(kcb); @@ -457,9 +457,6 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr) kprobes_restore_local_irqflag(kcb, regs); kernel_disable_single_step(); - if (kcb->kprobe_status == KPROBE_REENTER) - spsr_set_debug_flag(regs, 1); - post_kprobe_handler(kcb, regs); } @@ -543,9 +540,6 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) bool arch_within_kprobe_blacklist(unsigned long addr) { - extern char __idmap_text_start[], __idmap_text_end[]; - extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[]; - if ((addr >= (unsigned long)__kprobes_text_start && addr < (unsigned long)__kprobes_text_end) || (addr >= (unsigned long)__entry_text_start && diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 6cd2612236dc..a4f5f766af08 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -202,7 +202,7 @@ void show_regs(struct pt_regs * regs) static void tls_thread_flush(void) { - asm ("msr tpidr_el0, xzr"); + write_sysreg(0, tpidr_el0); if (is_compat_task()) { current->thread.tp_value = 0; @@ -213,7 +213,7 @@ static void tls_thread_flush(void) * with a stale shadow state during context switch. */ barrier(); - asm ("msr tpidrro_el0, xzr"); + write_sysreg(0, tpidrro_el0); } } @@ -253,7 +253,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, * Read the current TLS pointer from tpidr_el0 as it may be * out-of-sync with the saved value. */ - asm("mrs %0, tpidr_el0" : "=r" (*task_user_tls(p))); + *task_user_tls(p) = read_sysreg(tpidr_el0); if (stack_start) { if (is_compat_thread(task_thread_info(p))) @@ -289,17 +289,15 @@ static void tls_thread_switch(struct task_struct *next) { unsigned long tpidr, tpidrro; - asm("mrs %0, tpidr_el0" : "=r" (tpidr)); + tpidr = read_sysreg(tpidr_el0); *task_user_tls(current) = tpidr; tpidr = *task_user_tls(next); tpidrro = is_compat_thread(task_thread_info(next)) ? next->thread.tp_value : 0; - asm( - " msr tpidr_el0, %0\n" - " msr tpidrro_el0, %1" - : : "r" (tpidr), "r" (tpidrro)); + write_sysreg(tpidr, tpidr_el0); + write_sysreg(tpidrro, tpidrro_el0); } /* Restore the UAO state depending on next's addr_limit */ diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S index 51b73cdde287..ce704a4aeadd 100644 --- a/arch/arm64/kernel/relocate_kernel.S +++ b/arch/arm64/kernel/relocate_kernel.S @@ -34,7 +34,7 @@ ENTRY(arm64_relocate_new_kernel) /* Setup the list loop variables. */ mov x17, x1 /* x17 = kimage_start */ mov x16, x0 /* x16 = kimage_head */ - dcache_line_size x15, x0 /* x15 = dcache line size */ + raw_dcache_line_size x15, x0 /* x15 = dcache line size */ mov x14, xzr /* x14 = entry ptr */ mov x13, xzr /* x13 = copy dest */ diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 536dce22fe76..f534f492a268 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -206,10 +206,15 @@ static void __init request_standard_resources(void) for_each_memblock(memory, region) { res = alloc_bootmem_low(sizeof(*res)); - res->name = "System RAM"; + if (memblock_is_nomap(region)) { + res->name = "reserved"; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + } else { + res->name = "System RAM"; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + } res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region)); res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1; - res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); @@ -228,7 +233,7 @@ void __init setup_arch(char **cmdline_p) { pr_info("Boot CPU: AArch64 Processor [%08x]\n", read_cpuid_id()); - sprintf(init_utsname()->machine, ELF_PLATFORM); + sprintf(init_utsname()->machine, UTS_MACHINE); init_mm.start_code = (unsigned long) _text; init_mm.end_code = (unsigned long) _etext; init_mm.end_data = (unsigned long) _edata; diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index a8eafdbc7cb8..404dd67080b9 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -402,15 +402,31 @@ static void do_signal(struct pt_regs *regs) asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned int thread_flags) { - if (thread_flags & _TIF_SIGPENDING) - do_signal(regs); - - if (thread_flags & _TIF_NOTIFY_RESUME) { - clear_thread_flag(TIF_NOTIFY_RESUME); - tracehook_notify_resume(regs); - } - - if (thread_flags & _TIF_FOREIGN_FPSTATE) - fpsimd_restore_current_state(); + /* + * The assembly code enters us with IRQs off, but it hasn't + * informed the tracing code of that for efficiency reasons. + * Update the trace code with the current status. + */ + trace_hardirqs_off(); + do { + if (thread_flags & _TIF_NEED_RESCHED) { + schedule(); + } else { + local_irq_enable(); + + if (thread_flags & _TIF_SIGPENDING) + do_signal(regs); + + if (thread_flags & _TIF_NOTIFY_RESUME) { + clear_thread_flag(TIF_NOTIFY_RESUME); + tracehook_notify_resume(regs); + } + + if (thread_flags & _TIF_FOREIGN_FPSTATE) + fpsimd_restore_current_state(); + } + local_irq_disable(); + thread_flags = READ_ONCE(current_thread_info()->flags); + } while (thread_flags & _TIF_WORK_MASK); } diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index ccf79d849e0a..b8799e7c79de 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -73,10 +73,9 @@ ENTRY(__cpu_suspend_enter) str x2, [x0, #SLEEP_STACK_DATA_SYSTEM_REGS + CPU_CTX_SP] /* find the mpidr_hash */ - ldr x1, =sleep_save_stash - ldr x1, [x1] + ldr_l x1, sleep_save_stash mrs x7, mpidr_el1 - ldr x9, =mpidr_hash + adr_l x9, mpidr_hash ldr x10, [x9, #MPIDR_HASH_MASK] /* * Following code relies on the struct mpidr_hash @@ -95,36 +94,30 @@ ENTRY(__cpu_suspend_enter) mov x0, #1 ret ENDPROC(__cpu_suspend_enter) - .ltorg + .pushsection ".idmap.text", "ax" ENTRY(cpu_resume) bl el2_setup // if in EL2 drop to EL1 cleanly + bl __cpu_setup /* enable the MMU early - so we can access sleep_save_stash by va */ - adr_l lr, __enable_mmu /* __cpu_setup will return here */ - adr_l x27, _resume_switched /* __enable_mmu will branch here */ - adrp x25, idmap_pg_dir - adrp x26, swapper_pg_dir - b __cpu_setup -ENDPROC(cpu_resume) - - .pushsection ".idmap.text", "ax" -_resume_switched: + bl __enable_mmu ldr x8, =_cpu_resume br x8 -ENDPROC(_resume_switched) +ENDPROC(cpu_resume) .ltorg .popsection ENTRY(_cpu_resume) mrs x1, mpidr_el1 - adrp x8, mpidr_hash - add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address - /* retrieve mpidr_hash members to compute the hash */ + adr_l x8, mpidr_hash // x8 = struct mpidr_hash virt address + + /* retrieve mpidr_hash members to compute the hash */ ldr x2, [x8, #MPIDR_HASH_MASK] ldp w3, w4, [x8, #MPIDR_HASH_SHIFTS] ldp w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)] compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2 - /* x7 contains hash index, let's use it to grab context pointer */ + + /* x7 contains hash index, let's use it to grab context pointer */ ldr_l x0, sleep_save_stash ldr x0, [x0, x7, lsl #3] add x29, x0, #SLEEP_STACK_DATA_CALLEE_REGS diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index d93d43352504..d3f151cfd4a1 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -201,12 +201,6 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) return ret; } -static void smp_store_cpu_info(unsigned int cpuid) -{ - store_cpu_topology(cpuid); - numa_store_cpu_info(cpuid); -} - /* * This is the secondary CPU boot entry. We're using this CPUs * idle thread stack, but a set of temporary page tables. @@ -239,7 +233,7 @@ asmlinkage void secondary_start_kernel(void) * this CPU ticks all of those. If it doesn't, the CPU will * fail to come online. */ - verify_local_cpu_capabilities(); + check_local_cpu_capabilities(); if (cpu_ops[cpu]->cpu_postboot) cpu_ops[cpu]->cpu_postboot(); @@ -254,7 +248,7 @@ asmlinkage void secondary_start_kernel(void) */ notify_cpu_starting(cpu); - smp_store_cpu_info(cpu); + store_cpu_topology(cpu); /* * OK, now it's safe to let the boot CPU continue. Wait for @@ -437,8 +431,19 @@ void __init smp_cpus_done(unsigned int max_cpus) void __init smp_prepare_boot_cpu(void) { set_my_cpu_offset(per_cpu_offset(smp_processor_id())); + /* + * Initialise the static keys early as they may be enabled by the + * cpufeature code. + */ + jump_label_init(); cpuinfo_store_boot_cpu(); save_boot_cpu_run_el(); + /* + * Run the errata work around checks on the boot CPU, once we have + * initialised the cpu feature infrastructure from + * cpuinfo_store_boot_cpu() above. + */ + update_cpu_errata_workarounds(); } static u64 __init of_get_cpu_mpidr(struct device_node *dn) @@ -619,6 +624,7 @@ static void __init of_parse_and_init_cpus(void) } bootcpu_valid = true; + early_map_cpu_to_node(0, of_node_to_nid(dn)); /* * cpu_logical_map has already been @@ -689,10 +695,13 @@ void __init smp_prepare_cpus(unsigned int max_cpus) { int err; unsigned int cpu; + unsigned int this_cpu; init_cpu_topology(); - smp_store_cpu_info(smp_processor_id()); + this_cpu = smp_processor_id(); + store_cpu_topology(this_cpu); + numa_store_cpu_info(this_cpu); /* * If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set @@ -719,6 +728,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) continue; set_cpu_present(cpu, true); + numa_store_cpu_info(cpu); } } diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c index 18a71bcd26ee..9a00eee9acc8 100644 --- a/arch/arm64/kernel/smp_spin_table.c +++ b/arch/arm64/kernel/smp_spin_table.c @@ -29,7 +29,8 @@ #include <asm/smp_plat.h> extern void secondary_holding_pen(void); -volatile unsigned long secondary_holding_pen_release = INVALID_HWID; +volatile unsigned long __section(".mmuoff.data.read") +secondary_holding_pen_release = INVALID_HWID; static phys_addr_t cpu_release_addr[NR_CPUS]; diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index d9751a4769e7..c2efddfca18c 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -43,6 +43,9 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) unsigned long fp = frame->fp; unsigned long irq_stack_ptr; + if (!tsk) + tsk = current; + /* * Switching between stacks is valid when tracing current and in * non-preemptible context. @@ -67,7 +70,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8)); #ifdef CONFIG_FUNCTION_GRAPH_TRACER - if (tsk && tsk->ret_stack && + if (tsk->ret_stack && (frame->pc == (unsigned long)return_to_handler)) { /* * This is a case where function graph tracer has @@ -152,6 +155,27 @@ static int save_trace(struct stackframe *frame, void *d) return trace->nr_entries >= trace->max_entries; } +void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) +{ + struct stack_trace_data data; + struct stackframe frame; + + data.trace = trace; + data.skip = trace->skip; + data.no_sched_functions = 0; + + frame.fp = regs->regs[29]; + frame.sp = regs->sp; + frame.pc = regs->pc; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = current->curr_ret_stack; +#endif + + walk_stackframe(current, &frame, save_trace, &data); + if (trace->nr_entries < trace->max_entries) + trace->entries[trace->nr_entries++] = ULONG_MAX; +} + void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { struct stack_trace_data data; diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index b616e365cee3..ad734142070d 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -23,8 +23,8 @@ unsigned long *sleep_save_stash; * time the notifier runs debug exceptions might have been enabled already, * with HW breakpoints registers content still in an unknown state. */ -static void (*hw_breakpoint_restore)(void *); -void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)) +static int (*hw_breakpoint_restore)(unsigned int); +void __init cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int)) { /* Prevent multiple restore hook initializations */ if (WARN_ON(hw_breakpoint_restore)) @@ -34,6 +34,8 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)) void notrace __cpu_suspend_exit(void) { + unsigned int cpu = smp_processor_id(); + /* * We are resuming from reset with the idmap active in TTBR0_EL1. * We must uninstall the idmap and restore the expected MMU @@ -45,7 +47,7 @@ void notrace __cpu_suspend_exit(void) * Restore per-cpu offset before any kernel * subsystem relying on it has a chance to run. */ - set_my_cpu_offset(per_cpu_offset(smp_processor_id())); + set_my_cpu_offset(per_cpu_offset(cpu)); /* * Restore HW breakpoint registers to sane values @@ -53,7 +55,7 @@ void notrace __cpu_suspend_exit(void) * through local_dbg_restore. */ if (hw_breakpoint_restore) - hw_breakpoint_restore(NULL); + hw_breakpoint_restore(cpu); } /* diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index 28c511b06edf..abaf582fc7a8 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -94,7 +94,7 @@ long compat_arm_syscall(struct pt_regs *regs) * See comment in tls_thread_flush. */ barrier(); - asm ("msr tpidrro_el0, %0" : : "r" (regs->regs[0])); + write_sysreg(regs->regs[0], tpidrro_el0); return 0; default: diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index e04f83873af7..5ff020f8fb7f 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -142,6 +142,11 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) unsigned long irq_stack_ptr; int skip; + pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); + + if (!tsk) + tsk = current; + /* * Switching between stacks is valid when tracing current and in * non-preemptible context. @@ -151,11 +156,6 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) else irq_stack_ptr = 0; - pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); - - if (!tsk) - tsk = current; - if (tsk == current) { frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_stack_pointer; @@ -447,36 +447,29 @@ void cpu_enable_cache_maint_trap(void *__unused) : "=r" (res) \ : "r" (address), "i" (-EFAULT) ) -asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) +static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs) { unsigned long address; - int ret; - - /* if this is a write with: Op0=1, Op2=1, Op1=3, CRn=7 */ - if ((esr & 0x01fffc01) == 0x0012dc00) { - int rt = (esr >> 5) & 0x1f; - int crm = (esr >> 1) & 0x0f; + int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT; + int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT; + int ret = 0; - address = (rt == 31) ? 0 : regs->regs[rt]; + address = (rt == 31) ? 0 : regs->regs[rt]; - switch (crm) { - case 11: /* DC CVAU, gets promoted */ - __user_cache_maint("dc civac", address, ret); - break; - case 10: /* DC CVAC, gets promoted */ - __user_cache_maint("dc civac", address, ret); - break; - case 14: /* DC CIVAC */ - __user_cache_maint("dc civac", address, ret); - break; - case 5: /* IC IVAU */ - __user_cache_maint("ic ivau", address, ret); - break; - default: - force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0); - return; - } - } else { + switch (crm) { + case ESR_ELx_SYS64_ISS_CRM_DC_CVAU: /* DC CVAU, gets promoted */ + __user_cache_maint("dc civac", address, ret); + break; + case ESR_ELx_SYS64_ISS_CRM_DC_CVAC: /* DC CVAC, gets promoted */ + __user_cache_maint("dc civac", address, ret); + break; + case ESR_ELx_SYS64_ISS_CRM_DC_CIVAC: /* DC CIVAC */ + __user_cache_maint("dc civac", address, ret); + break; + case ESR_ELx_SYS64_ISS_CRM_IC_IVAU: /* IC IVAU */ + __user_cache_maint("ic ivau", address, ret); + break; + default: force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0); return; } @@ -487,6 +480,48 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) regs->pc += 4; } +static void ctr_read_handler(unsigned int esr, struct pt_regs *regs) +{ + int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT; + + regs->regs[rt] = arm64_ftr_reg_ctrel0.sys_val; + regs->pc += 4; +} + +struct sys64_hook { + unsigned int esr_mask; + unsigned int esr_val; + void (*handler)(unsigned int esr, struct pt_regs *regs); +}; + +static struct sys64_hook sys64_hooks[] = { + { + .esr_mask = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK, + .esr_val = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL, + .handler = user_cache_maint_handler, + }, + { + /* Trap read access to CTR_EL0 */ + .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK, + .esr_val = ESR_ELx_SYS64_ISS_SYS_CTR_READ, + .handler = ctr_read_handler, + }, + {}, +}; + +asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) +{ + struct sys64_hook *hook; + + for (hook = sys64_hooks; hook->handler; hook++) + if ((hook->esr_mask & esr) == hook->esr_val) { + hook->handler(esr, regs); + return; + } + + force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0); +} + long compat_arm_syscall(struct pt_regs *regs); asmlinkage long do_ni_syscall(struct pt_regs *regs) diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 076312b17d4f..a2c2478e7d78 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -18,12 +18,13 @@ * Author: Will Deacon <will.deacon@arm.com> */ -#include <linux/kernel.h> +#include <linux/cache.h> #include <linux/clocksource.h> #include <linux/elf.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/gfp.h> +#include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/signal.h> @@ -37,8 +38,7 @@ #include <asm/vdso_datapage.h> extern char vdso_start, vdso_end; -static unsigned long vdso_pages; -static struct page **vdso_pagelist; +static unsigned long vdso_pages __ro_after_init; /* * The vDSO data page. @@ -53,9 +53,9 @@ struct vdso_data *vdso_data = &vdso_data_store.data; /* * Create and map the vectors page for AArch32 tasks. */ -static struct page *vectors_page[1]; +static struct page *vectors_page[1] __ro_after_init; -static int alloc_vectors_page(void) +static int __init alloc_vectors_page(void) { extern char __kuser_helper_start[], __kuser_helper_end[]; extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[]; @@ -88,7 +88,7 @@ int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; unsigned long addr = AARCH32_VECTORS_BASE; - static struct vm_special_mapping spec = { + static const struct vm_special_mapping spec = { .name = "[vectors]", .pages = vectors_page, @@ -110,11 +110,19 @@ int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp) } #endif /* CONFIG_COMPAT */ -static struct vm_special_mapping vdso_spec[2]; +static struct vm_special_mapping vdso_spec[2] __ro_after_init = { + { + .name = "[vvar]", + }, + { + .name = "[vdso]", + }, +}; static int __init vdso_init(void) { int i; + struct page **vdso_pagelist; if (memcmp(&vdso_start, "\177ELF", 4)) { pr_err("vDSO is not a valid ELF object!\n"); @@ -138,16 +146,8 @@ static int __init vdso_init(void) for (i = 0; i < vdso_pages; i++) vdso_pagelist[i + 1] = pfn_to_page(PHYS_PFN(__pa(&vdso_start)) + i); - /* Populate the special mapping structures */ - vdso_spec[0] = (struct vm_special_mapping) { - .name = "[vvar]", - .pages = vdso_pagelist, - }; - - vdso_spec[1] = (struct vm_special_mapping) { - .name = "[vdso]", - .pages = &vdso_pagelist[1], - }; + vdso_spec[0].pages = &vdso_pagelist[0]; + vdso_spec[1].pages = &vdso_pagelist[1]; return 0; } @@ -201,7 +201,7 @@ up_fail: */ void update_vsyscall(struct timekeeper *tk) { - u32 use_syscall = strcmp(tk->tkr_mono.clock->name, "arch_sys_counter"); + u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct; ++vdso_data->tb_seq_count; smp_wmb(); diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 659963d40bb4..5ce9b2929e0d 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -185,6 +185,25 @@ SECTIONS _data = .; _sdata = .; RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) + + /* + * Data written with the MMU off but read with the MMU on requires + * cache lines to be invalidated, discarding up to a Cache Writeback + * Granule (CWG) of data from the cache. Keep the section that + * requires this type of maintenance to be in its own Cache Writeback + * Granule (CWG) area so the cache maintenance operations don't + * interfere with adjacent data. + */ + .mmuoff.data.write : ALIGN(SZ_2K) { + __mmuoff_data_start = .; + *(.mmuoff.data.write) + } + . = ALIGN(SZ_2K); + .mmuoff.data.read : { + *(.mmuoff.data.read) + __mmuoff_data_end = .; + } + PECOFF_EDATA_PADDING _edata = .; diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 9c9edc98d271..6eaf12c1d627 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -16,7 +16,7 @@ menuconfig VIRTUALIZATION if VIRTUALIZATION -config KVM_ARM_VGIC_V3 +config KVM_ARM_VGIC_V3_ITS bool config KVM @@ -34,7 +34,7 @@ config KVM select KVM_VFIO select HAVE_KVM_EVENTFD select HAVE_KVM_IRQFD - select KVM_ARM_VGIC_V3 + select KVM_ARM_VGIC_V3_ITS select KVM_ARM_PMU if HW_PERF_EVENTS select HAVE_KVM_MSI select HAVE_KVM_IRQCHIP diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 695eb3c7ef41..d50a82a16ff6 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -16,9 +16,10 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/e kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o -kvm-$(CONFIG_KVM_ARM_HOST) += emulate.o inject_fault.o regmap.o +kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/aarch32.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-init.o diff --git a/arch/arm64/kvm/emulate.c b/arch/arm64/kvm/emulate.c deleted file mode 100644 index f87d8fbaa48d..000000000000 --- a/arch/arm64/kvm/emulate.c +++ /dev/null @@ -1,159 +0,0 @@ -/* - * (not much of an) Emulation layer for 32bit guests. - * - * Copyright (C) 2012,2013 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * based on arch/arm/kvm/emulate.c - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - * - * This program is free software: you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#include <linux/kvm_host.h> -#include <asm/esr.h> -#include <asm/kvm_emulate.h> - -/* - * stolen from arch/arm/kernel/opcodes.c - * - * condition code lookup table - * index into the table is test code: EQ, NE, ... LT, GT, AL, NV - * - * bit position in short is condition code: NZCV - */ -static const unsigned short cc_map[16] = { - 0xF0F0, /* EQ == Z set */ - 0x0F0F, /* NE */ - 0xCCCC, /* CS == C set */ - 0x3333, /* CC */ - 0xFF00, /* MI == N set */ - 0x00FF, /* PL */ - 0xAAAA, /* VS == V set */ - 0x5555, /* VC */ - 0x0C0C, /* HI == C set && Z clear */ - 0xF3F3, /* LS == C clear || Z set */ - 0xAA55, /* GE == (N==V) */ - 0x55AA, /* LT == (N!=V) */ - 0x0A05, /* GT == (!Z && (N==V)) */ - 0xF5FA, /* LE == (Z || (N!=V)) */ - 0xFFFF, /* AL always */ - 0 /* NV */ -}; - -static int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) -{ - u32 esr = kvm_vcpu_get_hsr(vcpu); - - if (esr & ESR_ELx_CV) - return (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT; - - return -1; -} - -/* - * Check if a trapped instruction should have been executed or not. - */ -bool kvm_condition_valid32(const struct kvm_vcpu *vcpu) -{ - unsigned long cpsr; - u32 cpsr_cond; - int cond; - - /* Top two bits non-zero? Unconditional. */ - if (kvm_vcpu_get_hsr(vcpu) >> 30) - return true; - - /* Is condition field valid? */ - cond = kvm_vcpu_get_condition(vcpu); - if (cond == 0xE) - return true; - - cpsr = *vcpu_cpsr(vcpu); - - if (cond < 0) { - /* This can happen in Thumb mode: examine IT state. */ - unsigned long it; - - it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3); - - /* it == 0 => unconditional. */ - if (it == 0) - return true; - - /* The cond for this insn works out as the top 4 bits. */ - cond = (it >> 4); - } - - cpsr_cond = cpsr >> 28; - - if (!((cc_map[cond] >> cpsr_cond) & 1)) - return false; - - return true; -} - -/** - * adjust_itstate - adjust ITSTATE when emulating instructions in IT-block - * @vcpu: The VCPU pointer - * - * When exceptions occur while instructions are executed in Thumb IF-THEN - * blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have - * to do this little bit of work manually. The fields map like this: - * - * IT[7:0] -> CPSR[26:25],CPSR[15:10] - */ -static void kvm_adjust_itstate(struct kvm_vcpu *vcpu) -{ - unsigned long itbits, cond; - unsigned long cpsr = *vcpu_cpsr(vcpu); - bool is_arm = !(cpsr & COMPAT_PSR_T_BIT); - - BUG_ON(is_arm && (cpsr & COMPAT_PSR_IT_MASK)); - - if (!(cpsr & COMPAT_PSR_IT_MASK)) - return; - - cond = (cpsr & 0xe000) >> 13; - itbits = (cpsr & 0x1c00) >> (10 - 2); - itbits |= (cpsr & (0x3 << 25)) >> 25; - - /* Perform ITAdvance (see page A2-52 in ARM DDI 0406C) */ - if ((itbits & 0x7) == 0) - itbits = cond = 0; - else - itbits = (itbits << 1) & 0x1f; - - cpsr &= ~COMPAT_PSR_IT_MASK; - cpsr |= cond << 13; - cpsr |= (itbits & 0x1c) << (10 - 2); - cpsr |= (itbits & 0x3) << 25; - *vcpu_cpsr(vcpu) = cpsr; -} - -/** - * kvm_skip_instr - skip a trapped instruction and proceed to the next - * @vcpu: The vcpu pointer - */ -void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr) -{ - bool is_thumb; - - is_thumb = !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_T_BIT); - if (is_thumb && !is_wide_instr) - *vcpu_pc(vcpu) += 2; - else - *vcpu_pc(vcpu) += 4; - kvm_adjust_itstate(vcpu); -} diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index fa96fe2bd469..a204adf29f0a 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -170,9 +170,32 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, { exit_handle_fn exit_handler; + if (ARM_SERROR_PENDING(exception_index)) { + u8 hsr_ec = ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu)); + + /* + * HVC/SMC already have an adjusted PC, which we need + * to correct in order to return to after having + * injected the SError. + */ + if (hsr_ec == ESR_ELx_EC_HVC32 || hsr_ec == ESR_ELx_EC_HVC64 || + hsr_ec == ESR_ELx_EC_SMC32 || hsr_ec == ESR_ELx_EC_SMC64) { + u32 adj = kvm_vcpu_trap_il_is32bit(vcpu) ? 4 : 2; + *vcpu_pc(vcpu) -= adj; + } + + kvm_inject_vabt(vcpu); + return 1; + } + + exception_index = ARM_EXCEPTION_CODE(exception_index); + switch (exception_index) { case ARM_EXCEPTION_IRQ: return 1; + case ARM_EXCEPTION_EL1_SERROR: + kvm_inject_vabt(vcpu); + return 1; case ARM_EXCEPTION_TRAP: /* * See ARM ARM B1.14.1: "Hyp traps on instructions diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 7ce931565151..2726635dceba 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -46,10 +46,6 @@ alternative_if_not ARM64_HAS_VIRT_HOST_EXTN hvc #0 ldr lr, [sp], #16 ret -alternative_else +alternative_else_nop_endif b __vhe_hyp_call - nop - nop - nop -alternative_endif ENDPROC(__kvm_call_hyp) diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile index 0c85febcc1eb..aaf42ae8d8c3 100644 --- a/arch/arm64/kvm/hyp/Makefile +++ b/arch/arm64/kvm/hyp/Makefile @@ -5,9 +5,9 @@ KVM=../../../../virt/kvm obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o +obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o -obj-$(CONFIG_KVM_ARM_HOST) += vgic-v3-sr.o obj-$(CONFIG_KVM_ARM_HOST) += sysreg-sr.o obj-$(CONFIG_KVM_ARM_HOST) += debug-sr.o obj-$(CONFIG_KVM_ARM_HOST) += entry.o diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c index 33342a776ec7..4ba5c9095d03 100644 --- a/arch/arm64/kvm/hyp/debug-sr.c +++ b/arch/arm64/kvm/hyp/debug-sr.c @@ -131,9 +131,7 @@ void __hyp_text __debug_cond_restore_host_state(struct kvm_vcpu *vcpu) vcpu->arch.debug_flags &= ~KVM_ARM64_DEBUG_DIRTY; } -static u32 __hyp_text __debug_read_mdcr_el2(void) +u32 __hyp_text __kvm_get_mdcr_el2(void) { return read_sysreg(mdcr_el2); } - -__alias(__debug_read_mdcr_el2) u32 __kvm_get_mdcr_el2(void); diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index ce9e5e5f28cf..12ee62d6d410 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -55,79 +55,111 @@ */ ENTRY(__guest_enter) // x0: vcpu - // x1: host/guest context - // x2-x18: clobbered by macros + // x1: host context + // x2-x17: clobbered by macros + // x18: guest context // Store the host regs save_callee_saved_regs x1 - // Preserve vcpu & host_ctxt for use at exit time - stp x0, x1, [sp, #-16]! + // Store the host_ctxt for use at exit time + str x1, [sp, #-16]! - add x1, x0, #VCPU_CONTEXT + add x18, x0, #VCPU_CONTEXT - // Prepare x0-x1 for later restore by pushing them onto the stack - ldp x2, x3, [x1, #CPU_XREG_OFFSET(0)] - stp x2, x3, [sp, #-16]! + // Restore guest regs x0-x17 + ldp x0, x1, [x18, #CPU_XREG_OFFSET(0)] + ldp x2, x3, [x18, #CPU_XREG_OFFSET(2)] + ldp x4, x5, [x18, #CPU_XREG_OFFSET(4)] + ldp x6, x7, [x18, #CPU_XREG_OFFSET(6)] + ldp x8, x9, [x18, #CPU_XREG_OFFSET(8)] + ldp x10, x11, [x18, #CPU_XREG_OFFSET(10)] + ldp x12, x13, [x18, #CPU_XREG_OFFSET(12)] + ldp x14, x15, [x18, #CPU_XREG_OFFSET(14)] + ldp x16, x17, [x18, #CPU_XREG_OFFSET(16)] - // x2-x18 - ldp x2, x3, [x1, #CPU_XREG_OFFSET(2)] - ldp x4, x5, [x1, #CPU_XREG_OFFSET(4)] - ldp x6, x7, [x1, #CPU_XREG_OFFSET(6)] - ldp x8, x9, [x1, #CPU_XREG_OFFSET(8)] - ldp x10, x11, [x1, #CPU_XREG_OFFSET(10)] - ldp x12, x13, [x1, #CPU_XREG_OFFSET(12)] - ldp x14, x15, [x1, #CPU_XREG_OFFSET(14)] - ldp x16, x17, [x1, #CPU_XREG_OFFSET(16)] - ldr x18, [x1, #CPU_XREG_OFFSET(18)] - - // x19-x29, lr - restore_callee_saved_regs x1 - - // Last bits of the 64bit state - ldp x0, x1, [sp], #16 + // Restore guest regs x19-x29, lr + restore_callee_saved_regs x18 + + // Restore guest reg x18 + ldr x18, [x18, #CPU_XREG_OFFSET(18)] // Do not touch any register after this! eret ENDPROC(__guest_enter) ENTRY(__guest_exit) - // x0: vcpu - // x1: return code - // x2-x3: free - // x4-x29,lr: vcpu regs - // vcpu x0-x3 on the stack + // x0: return code + // x1: vcpu + // x2-x29,lr: vcpu regs + // vcpu x0-x1 on the stack - add x2, x0, #VCPU_CONTEXT + add x1, x1, #VCPU_CONTEXT - stp x4, x5, [x2, #CPU_XREG_OFFSET(4)] - stp x6, x7, [x2, #CPU_XREG_OFFSET(6)] - stp x8, x9, [x2, #CPU_XREG_OFFSET(8)] - stp x10, x11, [x2, #CPU_XREG_OFFSET(10)] - stp x12, x13, [x2, #CPU_XREG_OFFSET(12)] - stp x14, x15, [x2, #CPU_XREG_OFFSET(14)] - stp x16, x17, [x2, #CPU_XREG_OFFSET(16)] - str x18, [x2, #CPU_XREG_OFFSET(18)] + ALTERNATIVE(nop, SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN) - ldp x6, x7, [sp], #16 // x2, x3 - ldp x4, x5, [sp], #16 // x0, x1 + // Store the guest regs x2 and x3 + stp x2, x3, [x1, #CPU_XREG_OFFSET(2)] - stp x4, x5, [x2, #CPU_XREG_OFFSET(0)] - stp x6, x7, [x2, #CPU_XREG_OFFSET(2)] + // Retrieve the guest regs x0-x1 from the stack + ldp x2, x3, [sp], #16 // x0, x1 + + // Store the guest regs x0-x1 and x4-x18 + stp x2, x3, [x1, #CPU_XREG_OFFSET(0)] + stp x4, x5, [x1, #CPU_XREG_OFFSET(4)] + stp x6, x7, [x1, #CPU_XREG_OFFSET(6)] + stp x8, x9, [x1, #CPU_XREG_OFFSET(8)] + stp x10, x11, [x1, #CPU_XREG_OFFSET(10)] + stp x12, x13, [x1, #CPU_XREG_OFFSET(12)] + stp x14, x15, [x1, #CPU_XREG_OFFSET(14)] + stp x16, x17, [x1, #CPU_XREG_OFFSET(16)] + str x18, [x1, #CPU_XREG_OFFSET(18)] + + // Store the guest regs x19-x29, lr + save_callee_saved_regs x1 - save_callee_saved_regs x2 + // Restore the host_ctxt from the stack + ldr x2, [sp], #16 - // Restore vcpu & host_ctxt from the stack - // (preserving return code in x1) - ldp x0, x2, [sp], #16 // Now restore the host regs restore_callee_saved_regs x2 - mov x0, x1 - ret + // If we have a pending asynchronous abort, now is the + // time to find out. From your VAXorcist book, page 666: + // "Threaten me not, oh Evil one! For I speak with + // the power of DEC, and I command thee to show thyself!" + mrs x2, elr_el2 + mrs x3, esr_el2 + mrs x4, spsr_el2 + mov x5, x0 + + dsb sy // Synchronize against in-flight ld/st + msr daifclr, #4 // Unmask aborts + + // This is our single instruction exception window. A pending + // SError is guaranteed to occur at the earliest when we unmask + // it, and at the latest just after the ISB. + .global abort_guest_exit_start +abort_guest_exit_start: + + isb + + .global abort_guest_exit_end +abort_guest_exit_end: + + // If the exception took place, restore the EL1 exception + // context so that we can report some information. + // Merge the exception code with the SError pending bit. + tbz x0, #ARM_EXIT_WITH_SERROR_BIT, 1f + msr elr_el2, x2 + msr esr_el2, x3 + msr spsr_el2, x4 + orr x0, x0, x5 +1: ret ENDPROC(__guest_exit) ENTRY(__fpsimd_guest_restore) + stp x2, x3, [sp, #-16]! stp x4, lr, [sp, #-16]! alternative_if_not ARM64_HAS_VIRT_HOST_EXTN diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index f6d9694ae3b1..4e92399f7105 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -27,16 +27,6 @@ .text .pushsection .hyp.text, "ax" -.macro save_x0_to_x3 - stp x0, x1, [sp, #-16]! - stp x2, x3, [sp, #-16]! -.endm - -.macro restore_x0_to_x3 - ldp x2, x3, [sp], #16 - ldp x0, x1, [sp], #16 -.endm - .macro do_el2_call /* * Shuffle the parameters before calling the function @@ -79,23 +69,23 @@ ENTRY(__kvm_hyp_teardown) ENDPROC(__kvm_hyp_teardown) el1_sync: // Guest trapped into EL2 - save_x0_to_x3 + stp x0, x1, [sp, #-16]! alternative_if_not ARM64_HAS_VIRT_HOST_EXTN mrs x1, esr_el2 alternative_else mrs x1, esr_el1 alternative_endif - lsr x2, x1, #ESR_ELx_EC_SHIFT + lsr x0, x1, #ESR_ELx_EC_SHIFT - cmp x2, #ESR_ELx_EC_HVC64 + cmp x0, #ESR_ELx_EC_HVC64 b.ne el1_trap - mrs x3, vttbr_el2 // If vttbr is valid, the 64bit guest - cbnz x3, el1_trap // called HVC + mrs x1, vttbr_el2 // If vttbr is valid, the 64bit guest + cbnz x1, el1_trap // called HVC /* Here, we're pretty sure the host called HVC. */ - restore_x0_to_x3 + ldp x0, x1, [sp], #16 cmp x0, #HVC_GET_VECTORS b.ne 1f @@ -113,24 +103,51 @@ alternative_endif el1_trap: /* - * x1: ESR - * x2: ESR_EC + * x0: ESR_EC */ /* Guest accessed VFP/SIMD registers, save host, restore Guest */ - cmp x2, #ESR_ELx_EC_FP_ASIMD + cmp x0, #ESR_ELx_EC_FP_ASIMD b.eq __fpsimd_guest_restore - mrs x0, tpidr_el2 - mov x1, #ARM_EXCEPTION_TRAP + mrs x1, tpidr_el2 + mov x0, #ARM_EXCEPTION_TRAP b __guest_exit el1_irq: - save_x0_to_x3 - mrs x0, tpidr_el2 - mov x1, #ARM_EXCEPTION_IRQ + stp x0, x1, [sp, #-16]! + mrs x1, tpidr_el2 + mov x0, #ARM_EXCEPTION_IRQ + b __guest_exit + +el1_error: + stp x0, x1, [sp, #-16]! + mrs x1, tpidr_el2 + mov x0, #ARM_EXCEPTION_EL1_SERROR b __guest_exit +el2_error: + /* + * Only two possibilities: + * 1) Either we come from the exit path, having just unmasked + * PSTATE.A: change the return code to an EL2 fault, and + * carry on, as we're already in a sane state to handle it. + * 2) Or we come from anywhere else, and that's a bug: we panic. + * + * For (1), x0 contains the original return code and x1 doesn't + * contain anything meaningful at that stage. We can reuse them + * as temp registers. + * For (2), who cares? + */ + mrs x0, elr_el2 + adr x1, abort_guest_exit_start + cmp x0, x1 + adr x1, abort_guest_exit_end + ccmp x0, x1, #4, ne + b.ne __hyp_panic + mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) + eret + ENTRY(__hyp_do_panic) mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ PSR_MODE_EL1h) @@ -155,11 +172,9 @@ ENDPROC(\label) invalid_vector el2h_sync_invalid invalid_vector el2h_irq_invalid invalid_vector el2h_fiq_invalid - invalid_vector el2h_error_invalid invalid_vector el1_sync_invalid invalid_vector el1_irq_invalid invalid_vector el1_fiq_invalid - invalid_vector el1_error_invalid .ltorg @@ -174,15 +189,15 @@ ENTRY(__kvm_hyp_vector) ventry el2h_sync_invalid // Synchronous EL2h ventry el2h_irq_invalid // IRQ EL2h ventry el2h_fiq_invalid // FIQ EL2h - ventry el2h_error_invalid // Error EL2h + ventry el2_error // Error EL2h ventry el1_sync // Synchronous 64-bit EL1 ventry el1_irq // IRQ 64-bit EL1 ventry el1_fiq_invalid // FIQ 64-bit EL1 - ventry el1_error_invalid // Error 64-bit EL1 + ventry el1_error // Error 64-bit EL1 ventry el1_sync // Synchronous 32-bit EL1 ventry el1_irq // IRQ 32-bit EL1 ventry el1_fiq_invalid // FIQ 32-bit EL1 - ventry el1_error_invalid // Error 32-bit EL1 + ventry el1_error // Error 32-bit EL1 ENDPROC(__kvm_hyp_vector) diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 5a84b4562603..83037cd62d01 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -16,7 +16,10 @@ */ #include <linux/types.h> +#include <linux/jump_label.h> + #include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> static bool __hyp_text __fpsimd_enabled_nvhe(void) @@ -109,6 +112,15 @@ static hyp_alternate_select(__deactivate_traps_arch, static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu) { + /* + * If we pended a virtual abort, preserve it until it gets + * cleared. See D1.14.3 (Virtual Interrupts) for details, but + * the crucial bit is "On taking a vSError interrupt, + * HCR_EL2.VSE is cleared to 0." + */ + if (vcpu->arch.hcr_el2 & HCR_VSE) + vcpu->arch.hcr_el2 = read_sysreg(hcr_el2); + __deactivate_traps_arch()(); write_sysreg(0, hstr_el2); write_sysreg(read_sysreg(mdcr_el2) & MDCR_EL2_HPMN_MASK, mdcr_el2); @@ -126,17 +138,13 @@ static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu) write_sysreg(0, vttbr_el2); } -static hyp_alternate_select(__vgic_call_save_state, - __vgic_v2_save_state, __vgic_v3_save_state, - ARM64_HAS_SYSREG_GIC_CPUIF); - -static hyp_alternate_select(__vgic_call_restore_state, - __vgic_v2_restore_state, __vgic_v3_restore_state, - ARM64_HAS_SYSREG_GIC_CPUIF); - static void __hyp_text __vgic_save_state(struct kvm_vcpu *vcpu) { - __vgic_call_save_state()(vcpu); + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + __vgic_v3_save_state(vcpu); + else + __vgic_v2_save_state(vcpu); + write_sysreg(read_sysreg(hcr_el2) & ~HCR_INT_OVERRIDE, hcr_el2); } @@ -149,7 +157,10 @@ static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu) val |= vcpu->arch.irq_lines; write_sysreg(val, hcr_el2); - __vgic_call_restore_state()(vcpu); + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + __vgic_v3_restore_state(vcpu); + else + __vgic_v2_restore_state(vcpu); } static bool __hyp_text __true_value(void) @@ -232,7 +243,22 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) return true; } -static int __hyp_text __guest_run(struct kvm_vcpu *vcpu) +static void __hyp_text __skip_instr(struct kvm_vcpu *vcpu) +{ + *vcpu_pc(vcpu) = read_sysreg_el2(elr); + + if (vcpu_mode_is_32bit(vcpu)) { + vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(spsr); + kvm_skip_instr32(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, spsr); + } else { + *vcpu_pc(vcpu) += 4; + } + + write_sysreg_el2(*vcpu_pc(vcpu), elr); +} + +int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; @@ -267,9 +293,43 @@ again: exit_code = __guest_enter(vcpu, host_ctxt); /* And we're baaack! */ + /* + * We're using the raw exception code in order to only process + * the trap if no SError is pending. We will come back to the + * same PC once the SError has been injected, and replay the + * trapping instruction. + */ if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu)) goto again; + if (static_branch_unlikely(&vgic_v2_cpuif_trap) && + exit_code == ARM_EXCEPTION_TRAP) { + bool valid; + + valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW && + kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT && + kvm_vcpu_dabt_isvalid(vcpu) && + !kvm_vcpu_dabt_isextabt(vcpu) && + !kvm_vcpu_dabt_iss1tw(vcpu); + + if (valid) { + int ret = __vgic_v2_perform_cpuif_access(vcpu); + + if (ret == 1) { + __skip_instr(vcpu); + goto again; + } + + if (ret == -1) { + /* Promote an illegal access to an SError */ + __skip_instr(vcpu); + exit_code = ARM_EXCEPTION_EL1_SERROR; + } + + /* 0 falls through to be handler out of EL2 */ + } + } + fp_enabled = __fpsimd_enabled(); __sysreg_save_guest_state(guest_ctxt); @@ -293,8 +353,6 @@ again: return exit_code; } -__alias(__guest_run) int __kvm_vcpu_run(struct kvm_vcpu *vcpu); - static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n"; static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par) diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index be8177cdd3bf..9cc0ea784ae6 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -17,7 +17,7 @@ #include <asm/kvm_hyp.h> -static void __hyp_text __tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) +void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) { dsb(ishst); @@ -48,10 +48,7 @@ static void __hyp_text __tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) write_sysreg(0, vttbr_el2); } -__alias(__tlb_flush_vmid_ipa) void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, - phys_addr_t ipa); - -static void __hyp_text __tlb_flush_vmid(struct kvm *kvm) +void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) { dsb(ishst); @@ -67,14 +64,10 @@ static void __hyp_text __tlb_flush_vmid(struct kvm *kvm) write_sysreg(0, vttbr_el2); } -__alias(__tlb_flush_vmid) void __kvm_tlb_flush_vmid(struct kvm *kvm); - -static void __hyp_text __tlb_flush_vm_context(void) +void __hyp_text __kvm_flush_vm_context(void) { dsb(ishst); asm volatile("tlbi alle1is \n" "ic ialluis ": : ); dsb(ish); } - -__alias(__tlb_flush_vm_context) void __kvm_flush_vm_context(void); diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c deleted file mode 100644 index 5f8f80b4a224..000000000000 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ /dev/null @@ -1,343 +0,0 @@ -/* - * Copyright (C) 2012-2015 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#include <linux/compiler.h> -#include <linux/irqchip/arm-gic-v3.h> -#include <linux/kvm_host.h> - -#include <asm/kvm_hyp.h> - -#define vtr_to_max_lr_idx(v) ((v) & 0xf) -#define vtr_to_nr_pri_bits(v) (((u32)(v) >> 29) + 1) - -#define read_gicreg(r) \ - ({ \ - u64 reg; \ - asm volatile("mrs_s %0, " __stringify(r) : "=r" (reg)); \ - reg; \ - }) - -#define write_gicreg(v,r) \ - do { \ - u64 __val = (v); \ - asm volatile("msr_s " __stringify(r) ", %0" : : "r" (__val));\ - } while (0) - -static u64 __hyp_text __gic_v3_get_lr(unsigned int lr) -{ - switch (lr & 0xf) { - case 0: - return read_gicreg(ICH_LR0_EL2); - case 1: - return read_gicreg(ICH_LR1_EL2); - case 2: - return read_gicreg(ICH_LR2_EL2); - case 3: - return read_gicreg(ICH_LR3_EL2); - case 4: - return read_gicreg(ICH_LR4_EL2); - case 5: - return read_gicreg(ICH_LR5_EL2); - case 6: - return read_gicreg(ICH_LR6_EL2); - case 7: - return read_gicreg(ICH_LR7_EL2); - case 8: - return read_gicreg(ICH_LR8_EL2); - case 9: - return read_gicreg(ICH_LR9_EL2); - case 10: - return read_gicreg(ICH_LR10_EL2); - case 11: - return read_gicreg(ICH_LR11_EL2); - case 12: - return read_gicreg(ICH_LR12_EL2); - case 13: - return read_gicreg(ICH_LR13_EL2); - case 14: - return read_gicreg(ICH_LR14_EL2); - case 15: - return read_gicreg(ICH_LR15_EL2); - } - - unreachable(); -} - -static void __hyp_text __gic_v3_set_lr(u64 val, int lr) -{ - switch (lr & 0xf) { - case 0: - write_gicreg(val, ICH_LR0_EL2); - break; - case 1: - write_gicreg(val, ICH_LR1_EL2); - break; - case 2: - write_gicreg(val, ICH_LR2_EL2); - break; - case 3: - write_gicreg(val, ICH_LR3_EL2); - break; - case 4: - write_gicreg(val, ICH_LR4_EL2); - break; - case 5: - write_gicreg(val, ICH_LR5_EL2); - break; - case 6: - write_gicreg(val, ICH_LR6_EL2); - break; - case 7: - write_gicreg(val, ICH_LR7_EL2); - break; - case 8: - write_gicreg(val, ICH_LR8_EL2); - break; - case 9: - write_gicreg(val, ICH_LR9_EL2); - break; - case 10: - write_gicreg(val, ICH_LR10_EL2); - break; - case 11: - write_gicreg(val, ICH_LR11_EL2); - break; - case 12: - write_gicreg(val, ICH_LR12_EL2); - break; - case 13: - write_gicreg(val, ICH_LR13_EL2); - break; - case 14: - write_gicreg(val, ICH_LR14_EL2); - break; - case 15: - write_gicreg(val, ICH_LR15_EL2); - break; - } -} - -static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu, int nr_lr) -{ - struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; - int i; - bool expect_mi; - - expect_mi = !!(cpu_if->vgic_hcr & ICH_HCR_UIE); - - for (i = 0; i < nr_lr; i++) { - if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i))) - continue; - - expect_mi |= (!(cpu_if->vgic_lr[i] & ICH_LR_HW) && - (cpu_if->vgic_lr[i] & ICH_LR_EOI)); - } - - if (expect_mi) { - cpu_if->vgic_misr = read_gicreg(ICH_MISR_EL2); - - if (cpu_if->vgic_misr & ICH_MISR_EOI) - cpu_if->vgic_eisr = read_gicreg(ICH_EISR_EL2); - else - cpu_if->vgic_eisr = 0; - } else { - cpu_if->vgic_misr = 0; - cpu_if->vgic_eisr = 0; - } -} - -void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu) -{ - struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; - u64 val; - - /* - * Make sure stores to the GIC via the memory mapped interface - * are now visible to the system register interface. - */ - if (!cpu_if->vgic_sre) - dsb(st); - - cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2); - - if (vcpu->arch.vgic_cpu.live_lrs) { - int i; - u32 max_lr_idx, nr_pri_bits; - - cpu_if->vgic_elrsr = read_gicreg(ICH_ELSR_EL2); - - write_gicreg(0, ICH_HCR_EL2); - val = read_gicreg(ICH_VTR_EL2); - max_lr_idx = vtr_to_max_lr_idx(val); - nr_pri_bits = vtr_to_nr_pri_bits(val); - - save_maint_int_state(vcpu, max_lr_idx + 1); - - for (i = 0; i <= max_lr_idx; i++) { - if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i))) - continue; - - if (cpu_if->vgic_elrsr & (1 << i)) - cpu_if->vgic_lr[i] &= ~ICH_LR_STATE; - else - cpu_if->vgic_lr[i] = __gic_v3_get_lr(i); - - __gic_v3_set_lr(0, i); - } - - switch (nr_pri_bits) { - case 7: - cpu_if->vgic_ap0r[3] = read_gicreg(ICH_AP0R3_EL2); - cpu_if->vgic_ap0r[2] = read_gicreg(ICH_AP0R2_EL2); - case 6: - cpu_if->vgic_ap0r[1] = read_gicreg(ICH_AP0R1_EL2); - default: - cpu_if->vgic_ap0r[0] = read_gicreg(ICH_AP0R0_EL2); - } - - switch (nr_pri_bits) { - case 7: - cpu_if->vgic_ap1r[3] = read_gicreg(ICH_AP1R3_EL2); - cpu_if->vgic_ap1r[2] = read_gicreg(ICH_AP1R2_EL2); - case 6: - cpu_if->vgic_ap1r[1] = read_gicreg(ICH_AP1R1_EL2); - default: - cpu_if->vgic_ap1r[0] = read_gicreg(ICH_AP1R0_EL2); - } - - vcpu->arch.vgic_cpu.live_lrs = 0; - } else { - cpu_if->vgic_misr = 0; - cpu_if->vgic_eisr = 0; - cpu_if->vgic_elrsr = 0xffff; - cpu_if->vgic_ap0r[0] = 0; - cpu_if->vgic_ap0r[1] = 0; - cpu_if->vgic_ap0r[2] = 0; - cpu_if->vgic_ap0r[3] = 0; - cpu_if->vgic_ap1r[0] = 0; - cpu_if->vgic_ap1r[1] = 0; - cpu_if->vgic_ap1r[2] = 0; - cpu_if->vgic_ap1r[3] = 0; - } - - val = read_gicreg(ICC_SRE_EL2); - write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2); - - if (!cpu_if->vgic_sre) { - /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */ - isb(); - write_gicreg(1, ICC_SRE_EL1); - } -} - -void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu) -{ - struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; - u64 val; - u32 max_lr_idx, nr_pri_bits; - u16 live_lrs = 0; - int i; - - /* - * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a - * Group0 interrupt (as generated in GICv2 mode) to be - * delivered as a FIQ to the guest, with potentially fatal - * consequences. So we must make sure that ICC_SRE_EL1 has - * been actually programmed with the value we want before - * starting to mess with the rest of the GIC. - */ - if (!cpu_if->vgic_sre) { - write_gicreg(0, ICC_SRE_EL1); - isb(); - } - - val = read_gicreg(ICH_VTR_EL2); - max_lr_idx = vtr_to_max_lr_idx(val); - nr_pri_bits = vtr_to_nr_pri_bits(val); - - for (i = 0; i <= max_lr_idx; i++) { - if (cpu_if->vgic_lr[i] & ICH_LR_STATE) - live_lrs |= (1 << i); - } - - write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2); - - if (live_lrs) { - write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2); - - switch (nr_pri_bits) { - case 7: - write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2); - write_gicreg(cpu_if->vgic_ap0r[2], ICH_AP0R2_EL2); - case 6: - write_gicreg(cpu_if->vgic_ap0r[1], ICH_AP0R1_EL2); - default: - write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2); - } - - switch (nr_pri_bits) { - case 7: - write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2); - write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2); - case 6: - write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2); - default: - write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2); - } - - for (i = 0; i <= max_lr_idx; i++) { - if (!(live_lrs & (1 << i))) - continue; - - __gic_v3_set_lr(cpu_if->vgic_lr[i], i); - } - } - - /* - * Ensures that the above will have reached the - * (re)distributors. This ensure the guest will read the - * correct values from the memory-mapped interface. - */ - if (!cpu_if->vgic_sre) { - isb(); - dsb(sy); - } - vcpu->arch.vgic_cpu.live_lrs = live_lrs; - - /* - * Prevent the guest from touching the GIC system registers if - * SRE isn't enabled for GICv3 emulation. - */ - write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE, - ICC_SRE_EL2); -} - -void __hyp_text __vgic_v3_init_lrs(void) -{ - int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2)); - int i; - - for (i = 0; i <= max_lr_idx; i++) - __gic_v3_set_lr(0, i); -} - -static u64 __hyp_text __vgic_v3_read_ich_vtr_el2(void) -{ - return read_gicreg(ICH_VTR_EL2); -} - -__alias(__vgic_v3_read_ich_vtr_el2) u64 __vgic_v3_get_ich_vtr_el2(void); diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 898c0e6aedd4..da6a8cfa54a0 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -231,3 +231,15 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu) else inject_undef64(vcpu); } + +/** + * kvm_inject_vabt - inject an async abort / SError into the guest + * @vcpu: The VCPU to receive the exception + * + * It is assumed that this code is called from the VCPU thread and that the + * VCPU therefore is not currently executing guest code. + */ +void kvm_inject_vabt(struct kvm_vcpu *vcpu) +{ + vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) | HCR_VSE); +} diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index e51367d159d0..f302fdb3a030 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -36,6 +36,7 @@ #include <asm/kvm_host.h> #include <asm/kvm_mmu.h> #include <asm/perf_event.h> +#include <asm/sysreg.h> #include <trace/events/kvm.h> @@ -67,11 +68,9 @@ static u32 get_ccsidr(u32 csselr) /* Make sure noone else changes CSSELR during this! */ local_irq_disable(); - /* Put value into CSSELR */ - asm volatile("msr csselr_el1, %x0" : : "r" (csselr)); + write_sysreg(csselr, csselr_el1); isb(); - /* Read result out of CCSIDR */ - asm volatile("mrs %0, ccsidr_el1" : "=r" (ccsidr)); + ccsidr = read_sysreg(ccsidr_el1); local_irq_enable(); return ccsidr; @@ -174,9 +173,7 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu, if (p->is_write) { return ignore_write(vcpu, p); } else { - u32 val; - asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val)); - p->regval = val; + p->regval = read_sysreg(dbgauthstatus_el1); return true; } } @@ -429,10 +426,7 @@ static void reset_wcr(struct kvm_vcpu *vcpu, static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { - u64 amair; - - asm volatile("mrs %0, amair_el1\n" : "=r" (amair)); - vcpu_sys_reg(vcpu, AMAIR_EL1) = amair; + vcpu_sys_reg(vcpu, AMAIR_EL1) = read_sysreg(amair_el1); } static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) @@ -456,8 +450,9 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 pmcr, val; - asm volatile("mrs %0, pmcr_el0\n" : "=r" (pmcr)); - /* Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) is reset to UNKNOWN + pmcr = read_sysreg(pmcr_el0); + /* + * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN * except PMCR.E resetting to zero. */ val = ((pmcr & ~ARMV8_PMU_PMCR_MASK) @@ -557,9 +552,9 @@ static bool access_pmceid(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return false; if (!(p->Op2 & 1)) - asm volatile("mrs %0, pmceid0_el0\n" : "=r" (pmceid)); + pmceid = read_sysreg(pmceid0_el0); else - asm volatile("mrs %0, pmceid1_el0\n" : "=r" (pmceid)); + pmceid = read_sysreg(pmceid1_el0); p->regval = pmceid; @@ -1833,11 +1828,7 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu, static void get_##reg(struct kvm_vcpu *v, \ const struct sys_reg_desc *r) \ { \ - u64 val; \ - \ - asm volatile("mrs %0, " __stringify(reg) "\n" \ - : "=r" (val)); \ - ((struct sys_reg_desc *)r)->val = val; \ + ((struct sys_reg_desc *)r)->val = read_sysreg(reg); \ } FUNCTION_INVARIANT(midr_el1) diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c index ed90578fa120..46af7186bca6 100644 --- a/arch/arm64/kvm/sys_regs_generic_v8.c +++ b/arch/arm64/kvm/sys_regs_generic_v8.c @@ -26,6 +26,7 @@ #include <asm/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_coproc.h> +#include <asm/sysreg.h> #include <linux/init.h> #include "sys_regs.h" @@ -43,10 +44,7 @@ static bool access_actlr(struct kvm_vcpu *vcpu, static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { - u64 actlr; - - asm volatile("mrs %0, actlr_el1\n" : "=r" (actlr)); - vcpu_sys_reg(vcpu, ACTLR_EL1) = actlr; + vcpu_sys_reg(vcpu, ACTLR_EL1) = read_sysreg(actlr_el1); } /* diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S index 4c1e700840b6..c3cd65e31814 100644 --- a/arch/arm64/lib/copy_page.S +++ b/arch/arm64/lib/copy_page.S @@ -29,14 +29,11 @@ * x1 - src */ ENTRY(copy_page) -alternative_if_not ARM64_HAS_NO_HW_PREFETCH - nop - nop -alternative_else +alternative_if ARM64_HAS_NO_HW_PREFETCH # Prefetch two cache lines ahead. prfm pldl1strm, [x1, #128] prfm pldl1strm, [x1, #256] -alternative_endif +alternative_else_nop_endif ldp x2, x3, [x1] ldp x4, x5, [x1, #16] @@ -52,11 +49,9 @@ alternative_endif 1: subs x18, x18, #128 -alternative_if_not ARM64_HAS_NO_HW_PREFETCH - nop -alternative_else +alternative_if ARM64_HAS_NO_HW_PREFETCH prfm pldl1strm, [x1, #384] -alternative_endif +alternative_else_nop_endif stnp x2, x3, [x0] ldp x2, x3, [x1] diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index 07d7352d7c38..58b5a906ff78 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -105,19 +105,20 @@ ENTRY(__clean_dcache_area_pou) ENDPROC(__clean_dcache_area_pou) /* - * __inval_cache_range(start, end) - * - start - start address of region - * - end - end address of region + * __dma_inv_area(start, size) + * - start - virtual start address of region + * - size - size in question */ -ENTRY(__inval_cache_range) +__dma_inv_area: + add x1, x1, x0 /* FALLTHROUGH */ /* - * __dma_inv_range(start, end) - * - start - virtual start address of region - * - end - virtual end address of region + * __inval_cache_range(start, end) + * - start - start address of region + * - end - end address of region */ -__dma_inv_range: +ENTRY(__inval_cache_range) dcache_line_size x2, x3 sub x3, x2, #1 tst x1, x3 // end cache line aligned? @@ -136,46 +137,43 @@ __dma_inv_range: dsb sy ret ENDPIPROC(__inval_cache_range) -ENDPROC(__dma_inv_range) +ENDPROC(__dma_inv_area) + +/* + * __clean_dcache_area_poc(kaddr, size) + * + * Ensure that any D-cache lines for the interval [kaddr, kaddr+size) + * are cleaned to the PoC. + * + * - kaddr - kernel address + * - size - size in question + */ +ENTRY(__clean_dcache_area_poc) + /* FALLTHROUGH */ /* - * __dma_clean_range(start, end) + * __dma_clean_area(start, size) * - start - virtual start address of region - * - end - virtual end address of region + * - size - size in question */ -__dma_clean_range: - dcache_line_size x2, x3 - sub x3, x2, #1 - bic x0, x0, x3 -1: -alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE - dc cvac, x0 -alternative_else - dc civac, x0 -alternative_endif - add x0, x0, x2 - cmp x0, x1 - b.lo 1b - dsb sy +__dma_clean_area: + dcache_by_line_op cvac, sy, x0, x1, x2, x3 ret -ENDPROC(__dma_clean_range) +ENDPIPROC(__clean_dcache_area_poc) +ENDPROC(__dma_clean_area) /* - * __dma_flush_range(start, end) + * __dma_flush_area(start, size) + * + * clean & invalidate D / U line + * * - start - virtual start address of region - * - end - virtual end address of region + * - size - size in question */ -ENTRY(__dma_flush_range) - dcache_line_size x2, x3 - sub x3, x2, #1 - bic x0, x0, x3 -1: dc civac, x0 // clean & invalidate D / U line - add x0, x0, x2 - cmp x0, x1 - b.lo 1b - dsb sy +ENTRY(__dma_flush_area) + dcache_by_line_op civac, sy, x0, x1, x2, x3 ret -ENDPIPROC(__dma_flush_range) +ENDPIPROC(__dma_flush_area) /* * __dma_map_area(start, size, dir) @@ -184,10 +182,9 @@ ENDPIPROC(__dma_flush_range) * - dir - DMA direction */ ENTRY(__dma_map_area) - add x1, x1, x0 cmp w2, #DMA_FROM_DEVICE - b.eq __dma_inv_range - b __dma_clean_range + b.eq __dma_inv_area + b __dma_clean_area ENDPIPROC(__dma_map_area) /* @@ -197,8 +194,7 @@ ENDPIPROC(__dma_map_area) * - dir - DMA direction */ ENTRY(__dma_unmap_area) - add x1, x1, x0 cmp w2, #DMA_TO_DEVICE - b.ne __dma_inv_range + b.ne __dma_inv_area ret ENDPIPROC(__dma_unmap_area) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index c4284c432ae8..bdacead5b802 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -20,6 +20,7 @@ #include <linux/gfp.h> #include <linux/acpi.h> #include <linux/bootmem.h> +#include <linux/cache.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/genalloc.h> @@ -30,7 +31,7 @@ #include <asm/cacheflush.h> -static int swiotlb __read_mostly; +static int swiotlb __ro_after_init; static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot, bool coherent) @@ -168,7 +169,7 @@ static void *__dma_alloc(struct device *dev, size_t size, return ptr; /* remove any dirty cache lines on the kernel alias */ - __dma_flush_range(ptr, ptr + size); + __dma_flush_area(ptr, size); /* create a coherent mapping */ page = virt_to_page(ptr); @@ -387,7 +388,7 @@ static int __init atomic_pool_init(void) void *page_addr = page_address(page); memset(page_addr, 0, atomic_pool_size); - __dma_flush_range(page_addr, page_addr + atomic_pool_size); + __dma_flush_area(page_addr, atomic_pool_size); atomic_pool = gen_pool_create(PAGE_SHIFT, -1); if (!atomic_pool) @@ -548,7 +549,7 @@ fs_initcall(dma_debug_do_init); /* Thankfully, all cache ops are by VA so we can ignore phys here */ static void flush_page(struct device *dev, const void *virt, phys_addr_t phys) { - __dma_flush_range(virt, virt + PAGE_SIZE); + __dma_flush_area(virt, PAGE_SIZE); } static void *__iommu_alloc_attrs(struct device *dev, size_t size, diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c index 81acd4706878..c9f118cd812b 100644 --- a/arch/arm64/mm/extable.c +++ b/arch/arm64/mm/extable.c @@ -2,7 +2,7 @@ * Based on arch/arm/mm/extable.c */ -#include <linux/module.h> +#include <linux/extable.h> #include <linux/uaccess.h> int fixup_exception(struct pt_regs *regs) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 05d2bd776c69..53d9159662fe 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -18,7 +18,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ -#include <linux/module.h> +#include <linux/extable.h> #include <linux/signal.h> #include <linux/mm.h> #include <linux/hardirq.h> @@ -251,8 +251,7 @@ static int __do_page_fault(struct mm_struct *mm, unsigned long addr, good_area: /* * Check that the permissions on the VMA allow for the fault which - * occurred. If we encountered a write or exec fault, we must have - * appropriate permissions, otherwise we allow any permission. + * occurred. */ if (!(vma->vm_flags & vm_flags)) { fault = VM_FAULT_BADACCESS; @@ -288,7 +287,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, struct task_struct *tsk; struct mm_struct *mm; int fault, sig, code; - unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC; + unsigned long vm_flags = VM_READ | VM_WRITE; unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; if (notify_page_fault(regs, esr)) diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index 43a76b07eb32..8377329d8c97 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -25,8 +25,6 @@ #include <asm/cachetype.h> #include <asm/tlbflush.h> -#include "mm.h" - void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index bbb7ee76e319..21c489bdeb4e 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -23,6 +23,7 @@ #include <linux/swap.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/cache.h> #include <linux/mman.h> #include <linux/nodemask.h> #include <linux/initrd.h> @@ -34,6 +35,7 @@ #include <linux/dma-contiguous.h> #include <linux/efi.h> #include <linux/swiotlb.h> +#include <linux/vmalloc.h> #include <asm/boot.h> #include <asm/fixmap.h> @@ -47,16 +49,14 @@ #include <asm/tlb.h> #include <asm/alternative.h> -#include "mm.h" - /* * We need to be able to catch inadvertent references to memstart_addr * that occur (potentially in generic code) before arm64_memblock_init() * executes, which assigns it its actual value. So use a default value * that cannot be mistaken for a real physical address. */ -s64 memstart_addr __read_mostly = -1; -phys_addr_t arm64_dma_phys_limit __read_mostly; +s64 memstart_addr __ro_after_init = -1; +phys_addr_t arm64_dma_phys_limit __ro_after_init; #ifdef CONFIG_BLK_DEV_INITRD static int __init early_initrd(char *p) @@ -485,7 +485,12 @@ void free_initmem(void) { free_reserved_area(__va(__pa(__init_begin)), __va(__pa(__init_end)), 0, "unused kernel"); - fixup_init(); + /* + * Unmap the __init region but leave the VM area in place. This + * prevents the region from being reused for kernel modules, which + * is not supported by kallsyms. + */ + unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin)); } #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/arm64/mm/mm.h b/arch/arm64/mm/mm.h deleted file mode 100644 index 71fe98985455..000000000000 --- a/arch/arm64/mm/mm.h +++ /dev/null @@ -1,2 +0,0 @@ - -void fixup_init(void); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 4989948d1feb..05615a3fdc6f 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -17,6 +17,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/cache.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/errno.h> @@ -42,11 +43,9 @@ #include <asm/memblock.h> #include <asm/mmu_context.h> -#include "mm.h" - u64 idmap_t0sz = TCR_T0SZ(VA_BITS); -u64 kimage_voffset __read_mostly; +u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); /* @@ -399,16 +398,6 @@ void mark_rodata_ro(void) section_size, PAGE_KERNEL_RO); } -void fixup_init(void) -{ - /* - * Unmap the __init region but leave the VM area in place. This - * prevents the region from being reused for kernel modules, which - * is not supported by kallsyms. - */ - unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin)); -} - static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, pgprot_t prot, struct vm_struct *vma) { diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index 5bb15eab6f00..778a985c8a70 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -17,6 +17,8 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#define pr_fmt(fmt) "NUMA: " fmt + #include <linux/acpi.h> #include <linux/bootmem.h> #include <linux/memblock.h> @@ -24,6 +26,7 @@ #include <linux/of.h> #include <asm/acpi.h> +#include <asm/sections.h> struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); @@ -38,10 +41,9 @@ static __init int numa_parse_early_param(char *opt) { if (!opt) return -EINVAL; - if (!strncmp(opt, "off", 3)) { - pr_info("%s\n", "NUMA turned off"); + if (!strncmp(opt, "off", 3)) numa_off = true; - } + return 0; } early_param("numa", numa_parse_early_param); @@ -93,7 +95,6 @@ void numa_clear_node(unsigned int cpu) */ static void __init setup_node_to_cpumask_map(void) { - unsigned int cpu; int node; /* setup nr_node_ids if not done yet */ @@ -106,11 +107,8 @@ static void __init setup_node_to_cpumask_map(void) cpumask_clear(node_to_cpumask_map[node]); } - for_each_possible_cpu(cpu) - set_cpu_numa_node(cpu, NUMA_NO_NODE); - /* cpumask_of_node() will now work */ - pr_debug("NUMA: Node to cpumask map for %d nodes\n", nr_node_ids); + pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids); } /* @@ -118,18 +116,77 @@ static void __init setup_node_to_cpumask_map(void) */ void numa_store_cpu_info(unsigned int cpu) { - map_cpu_to_node(cpu, numa_off ? 0 : cpu_to_node_map[cpu]); + map_cpu_to_node(cpu, cpu_to_node_map[cpu]); } void __init early_map_cpu_to_node(unsigned int cpu, int nid) { /* fallback to node 0 */ - if (nid < 0 || nid >= MAX_NUMNODES) + if (nid < 0 || nid >= MAX_NUMNODES || numa_off) nid = 0; cpu_to_node_map[cpu] = nid; + + /* + * We should set the numa node of cpu0 as soon as possible, because it + * has already been set up online before. cpu_to_node(0) will soon be + * called. + */ + if (!cpu) + set_cpu_numa_node(cpu, nid); +} + +#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA +unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; +EXPORT_SYMBOL(__per_cpu_offset); + +static int __init early_cpu_to_node(int cpu) +{ + return cpu_to_node_map[cpu]; +} + +static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) +{ + return node_distance(from, to); } +static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, + size_t align) +{ + int nid = early_cpu_to_node(cpu); + + return memblock_virt_alloc_try_nid(size, align, + __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); +} + +static void __init pcpu_fc_free(void *ptr, size_t size) +{ + memblock_free_early(__pa(ptr), size); +} + +void __init setup_per_cpu_areas(void) +{ + unsigned long delta; + unsigned int cpu; + int rc; + + /* + * Always reserve area for module percpu variables. That's + * what the legacy allocator did. + */ + rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, + PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, + pcpu_cpu_distance, + pcpu_fc_alloc, pcpu_fc_free); + if (rc < 0) + panic("Failed to initialize percpu areas."); + + delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; + for_each_possible_cpu(cpu) + __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; +} +#endif + /** * numa_add_memblk - Set node id to memblk * @nid: NUMA node ID of the new memblk @@ -145,13 +202,13 @@ int __init numa_add_memblk(int nid, u64 start, u64 end) ret = memblock_set_node(start, (end - start), &memblock.memory, nid); if (ret < 0) { - pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n", + pr_err("memblock [0x%llx - 0x%llx] failed to add on node %d\n", start, (end - 1), nid); return ret; } node_set(nid, numa_nodes_parsed); - pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n", + pr_info("Adding memblock [0x%llx - 0x%llx] on node %d\n", start, (end - 1), nid); return ret; } @@ -166,19 +223,18 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) void *nd; int tnid; - pr_info("NUMA: Initmem setup node %d [mem %#010Lx-%#010Lx]\n", - nid, start_pfn << PAGE_SHIFT, - (end_pfn << PAGE_SHIFT) - 1); + pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n", + nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1); nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); nd = __va(nd_pa); /* report and initialize */ - pr_info("NUMA: NODE_DATA [mem %#010Lx-%#010Lx]\n", + pr_info("NODE_DATA [mem %#010Lx-%#010Lx]\n", nd_pa, nd_pa + nd_size - 1); tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); if (tnid != nid) - pr_info("NUMA: NODE_DATA(%d) on node %d\n", nid, tnid); + pr_info("NODE_DATA(%d) on node %d\n", nid, tnid); node_data[nid] = nd; memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); @@ -235,8 +291,7 @@ static int __init numa_alloc_distance(void) numa_distance[i * numa_distance_cnt + j] = i == j ? LOCAL_DISTANCE : REMOTE_DISTANCE; - pr_debug("NUMA: Initialized distance table, cnt=%d\n", - numa_distance_cnt); + pr_debug("Initialized distance table, cnt=%d\n", numa_distance_cnt); return 0; } @@ -257,20 +312,20 @@ static int __init numa_alloc_distance(void) void __init numa_set_distance(int from, int to, int distance) { if (!numa_distance) { - pr_warn_once("NUMA: Warning: distance table not allocated yet\n"); + pr_warn_once("Warning: distance table not allocated yet\n"); return; } if (from >= numa_distance_cnt || to >= numa_distance_cnt || from < 0 || to < 0) { - pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n", + pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n", from, to, distance); return; } if ((u8)distance != distance || (from == to && distance != LOCAL_DISTANCE)) { - pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n", + pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n", from, to, distance); return; } @@ -297,7 +352,7 @@ static int __init numa_register_nodes(void) /* Check that valid nid is set to memblks */ for_each_memblock(memory, mblk) if (mblk->nid == NUMA_NO_NODE || mblk->nid >= MAX_NUMNODES) { - pr_warn("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n", + pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n", mblk->nid, mblk->base, mblk->base + mblk->size - 1); return -EINVAL; @@ -335,8 +390,10 @@ static int __init numa_init(int (*init_func)(void)) if (ret < 0) return ret; - if (nodes_empty(numa_nodes_parsed)) + if (nodes_empty(numa_nodes_parsed)) { + pr_info("No NUMA configuration found\n"); return -EINVAL; + } ret = numa_register_nodes(); if (ret < 0) @@ -344,10 +401,6 @@ static int __init numa_init(int (*init_func)(void)) setup_node_to_cpumask_map(); - /* init boot processor */ - cpu_to_node_map[0] = 0; - map_cpu_to_node(0, 0); - return 0; } @@ -367,10 +420,8 @@ static int __init dummy_numa_init(void) if (numa_off) pr_info("NUMA disabled\n"); /* Forced off on command line. */ - else - pr_info("No NUMA configuration found\n"); - pr_info("NUMA: Faking a node at [mem %#018Lx-%#018Lx]\n", - 0LLU, PFN_PHYS(max_pfn) - 1); + pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n", + 0LLU, PFN_PHYS(max_pfn) - 1); for_each_memblock(memory, mblk) { ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size); diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index ca6d268e3313..8def55e7249b 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -139,4 +139,43 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) __pgprot(0), __pgprot(PTE_VALID)); } -#endif +#ifdef CONFIG_HIBERNATION +/* + * When built with CONFIG_DEBUG_PAGEALLOC and CONFIG_HIBERNATION, this function + * is used to determine if a linear map page has been marked as not-valid by + * CONFIG_DEBUG_PAGEALLOC. Walk the page table and check the PTE_VALID bit. + * This is based on kern_addr_valid(), which almost does what we need. + * + * Because this is only called on the kernel linear map, p?d_sect() implies + * p?d_present(). When debug_pagealloc is enabled, sections mappings are + * disabled. + */ +bool kernel_page_present(struct page *page) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + unsigned long addr = (unsigned long)page_address(page); + + pgd = pgd_offset_k(addr); + if (pgd_none(*pgd)) + return false; + + pud = pud_offset(pgd, addr); + if (pud_none(*pud)) + return false; + if (pud_sect(*pud)) + return true; + + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return false; + if (pmd_sect(*pmd)) + return true; + + pte = pte_offset_kernel(pmd, addr); + return pte_valid(*pte); +} +#endif /* CONFIG_HIBERNATION */ +#endif /* CONFIG_DEBUG_PAGEALLOC */ diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index ae11d4e03d0e..371c5f03a170 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -26,8 +26,6 @@ #include <asm/page.h> #include <asm/tlbflush.h> -#include "mm.h" - static struct kmem_cache *pgd_cache; pgd_t *pgd_alloc(struct mm_struct *mm) diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 5bb61de23201..352c73b6a59e 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -83,6 +83,7 @@ ENDPROC(cpu_do_suspend) * * x0: Address of context pointer */ + .pushsection ".idmap.text", "ax" ENTRY(cpu_do_resume) ldp x2, x3, [x0] ldp x4, x5, [x0, #16] @@ -100,7 +101,16 @@ ENTRY(cpu_do_resume) msr tcr_el1, x8 msr vbar_el1, x9 + + /* + * __cpu_setup() cleared MDSCR_EL1.MDE and friends, before unmasking + * debug exceptions. By restoring MDSCR_EL1 here, we may take a debug + * exception. Mask them until local_dbg_restore() in cpu_suspend() + * resets them. + */ + disable_dbg msr mdscr_el1, x10 + msr sctlr_el1, x12 /* * Restore oslsr_el1 by writing oslar_el1 @@ -111,6 +121,7 @@ ENTRY(cpu_do_resume) isb ret ENDPROC(cpu_do_resume) + .popsection #endif /* @@ -125,17 +136,12 @@ ENTRY(cpu_do_switch_mm) bfi x0, x1, #48, #16 // set the ASID msr ttbr0_el1, x0 // set TTBR0 isb -alternative_if_not ARM64_WORKAROUND_CAVIUM_27456 - ret - nop - nop - nop -alternative_else +alternative_if ARM64_WORKAROUND_CAVIUM_27456 ic iallu dsb nsh isb +alternative_else_nop_endif ret -alternative_endif ENDPROC(cpu_do_switch_mm) .pushsection ".idmap.text", "ax" @@ -172,6 +178,7 @@ ENDPROC(idmap_cpu_replace_ttbr1) * Initialise the processor for turning the MMU on. Return in x0 the * value of the SCTLR_EL1 register. */ + .pushsection ".idmap.text", "ax" ENTRY(__cpu_setup) tlbi vmalle1 // Invalidate local TLB dsb nsh @@ -257,3 +264,4 @@ ENDPROC(__cpu_setup) crval: .word 0xfcffffff // clear .word 0x34d5d91d // set + .popsection diff --git a/arch/avr32/include/asm/uaccess.h b/arch/avr32/include/asm/uaccess.h index 68cf638faf48..b1ec1fa06463 100644 --- a/arch/avr32/include/asm/uaccess.h +++ b/arch/avr32/include/asm/uaccess.h @@ -74,7 +74,7 @@ extern __kernel_size_t __copy_user(void *to, const void *from, extern __kernel_size_t copy_to_user(void __user *to, const void *from, __kernel_size_t n); -extern __kernel_size_t copy_from_user(void *to, const void __user *from, +extern __kernel_size_t ___copy_from_user(void *to, const void __user *from, __kernel_size_t n); static inline __kernel_size_t __copy_to_user(void __user *to, const void *from, @@ -88,6 +88,15 @@ static inline __kernel_size_t __copy_from_user(void *to, { return __copy_user(to, (const void __force *)from, n); } +static inline __kernel_size_t copy_from_user(void *to, + const void __user *from, + __kernel_size_t n) +{ + size_t res = ___copy_from_user(to, from, n); + if (unlikely(res)) + memset(to + (n - res), 0, res); + return res; +} #define __copy_to_user_inatomic __copy_to_user #define __copy_from_user_inatomic __copy_from_user diff --git a/arch/avr32/kernel/avr32_ksyms.c b/arch/avr32/kernel/avr32_ksyms.c index d93ead02daed..7c6cf14f0985 100644 --- a/arch/avr32/kernel/avr32_ksyms.c +++ b/arch/avr32/kernel/avr32_ksyms.c @@ -36,7 +36,7 @@ EXPORT_SYMBOL(copy_page); /* * Userspace access stuff. */ -EXPORT_SYMBOL(copy_from_user); +EXPORT_SYMBOL(___copy_from_user); EXPORT_SYMBOL(copy_to_user); EXPORT_SYMBOL(__copy_user); EXPORT_SYMBOL(strncpy_from_user); diff --git a/arch/avr32/kernel/traps.c b/arch/avr32/kernel/traps.c index 682b2478691a..eb4a3fcfbaff 100644 --- a/arch/avr32/kernel/traps.c +++ b/arch/avr32/kernel/traps.c @@ -11,7 +11,8 @@ #include <linux/init.h> #include <linux/kallsyms.h> #include <linux/kdebug.h> -#include <linux/module.h> +#include <linux/extable.h> +#include <linux/module.h> /* print_modules */ #include <linux/notifier.h> #include <linux/sched.h> #include <linux/uaccess.h> diff --git a/arch/avr32/lib/copy_user.S b/arch/avr32/lib/copy_user.S index ea59c04b07de..075373471da1 100644 --- a/arch/avr32/lib/copy_user.S +++ b/arch/avr32/lib/copy_user.S @@ -23,13 +23,13 @@ */ .text .align 1 - .global copy_from_user - .type copy_from_user, @function -copy_from_user: + .global ___copy_from_user + .type ___copy_from_user, @function +___copy_from_user: branch_if_kernel r8, __copy_user ret_if_privileged r8, r11, r10, r10 rjmp __copy_user - .size copy_from_user, . - copy_from_user + .size ___copy_from_user, . - ___copy_from_user .global copy_to_user .type copy_to_user, @function diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c index a4b7edac8f10..b3977e9208a3 100644 --- a/arch/avr32/mm/fault.c +++ b/arch/avr32/mm/fault.c @@ -10,7 +10,7 @@ */ #include <linux/mm.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/pagemap.h> #include <linux/kdebug.h> #include <linux/kprobes.h> diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index 28c63fea786d..3c1bd640042a 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -26,7 +26,7 @@ config BLACKFIN select HAVE_OPROFILE select HAVE_PERF_EVENTS select ARCH_HAVE_CUSTOM_GPIO_H - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB select HAVE_UID16 select HAVE_UNDERSCORE_SYMBOL_PREFIX select VIRT_TO_BUS diff --git a/arch/blackfin/include/asm/uaccess.h b/arch/blackfin/include/asm/uaccess.h index 12f5d6851bbc..0a2a70096d8b 100644 --- a/arch/blackfin/include/asm/uaccess.h +++ b/arch/blackfin/include/asm/uaccess.h @@ -171,11 +171,12 @@ static inline int bad_user_access_length(void) static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { - if (access_ok(VERIFY_READ, from, n)) + if (likely(access_ok(VERIFY_READ, from, n))) { memcpy(to, (const void __force *)from, n); - else - return n; - return 0; + return 0; + } + memset(to, 0, n); + return n; } static inline unsigned long __must_check diff --git a/arch/blackfin/kernel/ftrace-entry.S b/arch/blackfin/kernel/ftrace-entry.S index 28d059540424..3b8bdcbb7da3 100644 --- a/arch/blackfin/kernel/ftrace-entry.S +++ b/arch/blackfin/kernel/ftrace-entry.S @@ -169,7 +169,7 @@ ENTRY(_ftrace_graph_caller) r0 = sp; /* unsigned long *parent */ r1 = [sp]; /* unsigned long self_addr */ # endif -# ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST +# ifdef HAVE_FUNCTION_GRAPH_FP_TEST r2 = fp; /* unsigned long frame_pointer */ # endif r0 += 16; /* skip the 4 local regs on stack */ @@ -190,7 +190,7 @@ ENTRY(_return_to_handler) [--sp] = r1; /* get original return address */ -# ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST +# ifdef HAVE_FUNCTION_GRAPH_FP_TEST r0 = fp; /* Blackfin is sane, so omit this */ # endif call _ftrace_return_to_handler; diff --git a/arch/blackfin/kernel/ftrace.c b/arch/blackfin/kernel/ftrace.c index 095de0fa044d..8dad7589b843 100644 --- a/arch/blackfin/kernel/ftrace.c +++ b/arch/blackfin/kernel/ftrace.c @@ -107,7 +107,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, return; if (ftrace_push_return_trace(*parent, self_addr, &trace.depth, - frame_pointer) == -EBUSY) + frame_pointer, NULL) == -EBUSY) return; trace.func = self_addr; diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c index c6db52ba3a06..10c57771822d 100644 --- a/arch/blackfin/mach-bf561/boards/cm_bf561.c +++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c @@ -146,7 +146,8 @@ static struct platform_device hitachi_fb_device = { #include <linux/smc91x.h> static struct smc91x_platdata smc91x_info = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT, .leda = RPC_LED_100_10, .ledb = RPC_LED_TX_RX, }; diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c index f35525b55819..57d1c43726d9 100644 --- a/arch/blackfin/mach-bf561/boards/ezkit.c +++ b/arch/blackfin/mach-bf561/boards/ezkit.c @@ -134,7 +134,8 @@ static struct platform_device net2272_bfin_device = { #include <linux/smc91x.h> static struct smc91x_platdata smc91x_info = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT, .leda = RPC_LED_100_10, .ledb = RPC_LED_TX_RX, }; diff --git a/arch/blackfin/mach-bf561/coreb.c b/arch/blackfin/mach-bf561/coreb.c index 78ecb50bafc8..8a2543c654b3 100644 --- a/arch/blackfin/mach-bf561/coreb.c +++ b/arch/blackfin/mach-bf561/coreb.c @@ -59,18 +59,7 @@ static struct miscdevice coreb_dev = { .name = "coreb", .fops = &coreb_fops, }; - -static int __init bf561_coreb_init(void) -{ - return misc_register(&coreb_dev); -} -module_init(bf561_coreb_init); - -static void __exit bf561_coreb_exit(void) -{ - misc_deregister(&coreb_dev); -} -module_exit(bf561_coreb_exit); +module_misc_device(coreb_dev); MODULE_AUTHOR("Bas Vermeulen <bvermeul@blackstar.xs4all.nl>"); MODULE_DESCRIPTION("BF561 Core B Support"); diff --git a/arch/cris/include/asm/uaccess.h b/arch/cris/include/asm/uaccess.h index e3530d0f13ee..56c7d5750abd 100644 --- a/arch/cris/include/asm/uaccess.h +++ b/arch/cris/include/asm/uaccess.h @@ -194,30 +194,6 @@ extern unsigned long __copy_user(void __user *to, const void *from, unsigned lon extern unsigned long __copy_user_zeroing(void *to, const void __user *from, unsigned long n); extern unsigned long __do_clear_user(void __user *to, unsigned long n); -static inline unsigned long -__generic_copy_to_user(void __user *to, const void *from, unsigned long n) -{ - if (access_ok(VERIFY_WRITE, to, n)) - return __copy_user(to, from, n); - return n; -} - -static inline unsigned long -__generic_copy_from_user(void *to, const void __user *from, unsigned long n) -{ - if (access_ok(VERIFY_READ, from, n)) - return __copy_user_zeroing(to, from, n); - return n; -} - -static inline unsigned long -__generic_clear_user(void __user *to, unsigned long n) -{ - if (access_ok(VERIFY_WRITE, to, n)) - return __do_clear_user(to, n); - return n; -} - static inline long __strncpy_from_user(char *dst, const char __user *src, long count) { @@ -282,7 +258,7 @@ __constant_copy_from_user(void *to, const void __user *from, unsigned long n) else if (n == 24) __asm_copy_from_user_24(to, from, ret); else - ret = __generic_copy_from_user(to, from, n); + ret = __copy_user_zeroing(to, from, n); return ret; } @@ -333,7 +309,7 @@ __constant_copy_to_user(void __user *to, const void *from, unsigned long n) else if (n == 24) __asm_copy_to_user_24(to, from, ret); else - ret = __generic_copy_to_user(to, from, n); + ret = __copy_user(to, from, n); return ret; } @@ -366,26 +342,43 @@ __constant_clear_user(void __user *to, unsigned long n) else if (n == 24) __asm_clear_24(to, ret); else - ret = __generic_clear_user(to, n); + ret = __do_clear_user(to, n); return ret; } -#define clear_user(to, n) \ - (__builtin_constant_p(n) ? \ - __constant_clear_user(to, n) : \ - __generic_clear_user(to, n)) +static inline size_t clear_user(void __user *to, size_t n) +{ + if (unlikely(!access_ok(VERIFY_WRITE, to, n))) + return n; + if (__builtin_constant_p(n)) + return __constant_clear_user(to, n); + else + return __do_clear_user(to, n); +} -#define copy_from_user(to, from, n) \ - (__builtin_constant_p(n) ? \ - __constant_copy_from_user(to, from, n) : \ - __generic_copy_from_user(to, from, n)) +static inline size_t copy_from_user(void *to, const void __user *from, size_t n) +{ + if (unlikely(!access_ok(VERIFY_READ, from, n))) { + memset(to, 0, n); + return n; + } + if (__builtin_constant_p(n)) + return __constant_copy_from_user(to, from, n); + else + return __copy_user_zeroing(to, from, n); +} -#define copy_to_user(to, from, n) \ - (__builtin_constant_p(n) ? \ - __constant_copy_to_user(to, from, n) : \ - __generic_copy_to_user(to, from, n)) +static inline size_t copy_to_user(void __user *to, const void *from, size_t n) +{ + if (unlikely(!access_ok(VERIFY_WRITE, to, n))) + return n; + if (__builtin_constant_p(n)) + return __constant_copy_to_user(to, from, n); + else + return __copy_user(to, from, n); +} /* We let the __ versions of copy_from/to_user inline, because they're often * used in fast paths and have only a small space overhead. diff --git a/arch/frv/include/asm/uaccess.h b/arch/frv/include/asm/uaccess.h index 3ac9a59d65d4..87d9e34c5df8 100644 --- a/arch/frv/include/asm/uaccess.h +++ b/arch/frv/include/asm/uaccess.h @@ -263,19 +263,25 @@ do { \ extern long __memset_user(void *dst, unsigned long count); extern long __memcpy_user(void *dst, const void *src, unsigned long count); -#define clear_user(dst,count) __memset_user(____force(dst), (count)) +#define __clear_user(dst,count) __memset_user(____force(dst), (count)) #define __copy_from_user_inatomic(to, from, n) __memcpy_user((to), ____force(from), (n)) #define __copy_to_user_inatomic(to, from, n) __memcpy_user(____force(to), (from), (n)) #else -#define clear_user(dst,count) (memset(____force(dst), 0, (count)), 0) +#define __clear_user(dst,count) (memset(____force(dst), 0, (count)), 0) #define __copy_from_user_inatomic(to, from, n) (memcpy((to), ____force(from), (n)), 0) #define __copy_to_user_inatomic(to, from, n) (memcpy(____force(to), (from), (n)), 0) #endif -#define __clear_user clear_user +static inline unsigned long __must_check +clear_user(void __user *to, unsigned long n) +{ + if (likely(__access_ok(to, n))) + n = __clear_user(to, n); + return n; +} static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n) diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h index f000a382bc7f..f61cfb28e9f2 100644 --- a/arch/hexagon/include/asm/uaccess.h +++ b/arch/hexagon/include/asm/uaccess.h @@ -103,7 +103,8 @@ static inline long hexagon_strncpy_from_user(char *dst, const char __user *src, { long res = __strnlen_user(src, n); - /* return from strnlen can't be zero -- that would be rubbish. */ + if (unlikely(!res)) + return -EFAULT; if (res > n) { copy_from_user(dst, src, n); diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index 29bd59790d6c..c7026429816b 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -56,7 +56,7 @@ struct thread_info { #define alloc_thread_stack_node(tsk, node) ((unsigned long *) 0) #define task_thread_info(tsk) ((struct thread_info *) 0) #endif -#define free_thread_stack(ti) /* nothing */ +#define free_thread_stack(tsk) /* nothing */ #define task_stack_page(tsk) ((void *)(tsk)) #define __HAVE_THREAD_FUNCTIONS diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h index 465c70982f40..bfe13196f770 100644 --- a/arch/ia64/include/asm/uaccess.h +++ b/arch/ia64/include/asm/uaccess.h @@ -241,8 +241,7 @@ extern unsigned long __must_check __copy_user (void __user *to, const void __use static inline unsigned long __copy_to_user (void __user *to, const void *from, unsigned long count) { - if (!__builtin_constant_p(count)) - check_object_size(from, count, true); + check_object_size(from, count, true); return __copy_user(to, (__force void __user *) from, count); } @@ -250,8 +249,7 @@ __copy_to_user (void __user *to, const void *from, unsigned long count) static inline unsigned long __copy_from_user (void *to, const void __user *from, unsigned long count) { - if (!__builtin_constant_p(count)) - check_object_size(to, count, false); + check_object_size(to, count, false); return __copy_user((__force void __user *) to, from, count); } @@ -265,27 +263,22 @@ __copy_from_user (void *to, const void __user *from, unsigned long count) long __cu_len = (n); \ \ if (__access_ok(__cu_to, __cu_len, get_fs())) { \ - if (!__builtin_constant_p(n)) \ - check_object_size(__cu_from, __cu_len, true); \ + check_object_size(__cu_from, __cu_len, true); \ __cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len); \ } \ __cu_len; \ }) -#define copy_from_user(to, from, n) \ -({ \ - void *__cu_to = (to); \ - const void __user *__cu_from = (from); \ - long __cu_len = (n); \ - \ - __chk_user_ptr(__cu_from); \ - if (__access_ok(__cu_from, __cu_len, get_fs())) { \ - if (!__builtin_constant_p(n)) \ - check_object_size(__cu_to, __cu_len, false); \ - __cu_len = __copy_user((__force void __user *) __cu_to, __cu_from, __cu_len); \ - } \ - __cu_len; \ -}) +static inline unsigned long +copy_from_user(void *to, const void __user *from, unsigned long n) +{ + check_object_size(to, n, false); + if (likely(__access_ok(from, n, get_fs()))) + n = __copy_user((__force void __user *) to, from, n); + else + memset(to, 0, n); + return n; +} #define __copy_in_user(to, from, size) __copy_user((to), (from), (size)) diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 92b7bc956795..9273e034b730 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -796,7 +796,7 @@ int acpi_isa_irq_to_gsi(unsigned isa_irq, u32 *gsi) * ACPI based hotplug CPU support */ #ifdef CONFIG_ACPI_HOTPLUG_CPU -static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) +int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) { #ifdef CONFIG_ACPI_NUMA /* diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index eb9220cde76c..9509cc73b9c6 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -986,7 +986,7 @@ ia64_mca_modify_original_stack(struct pt_regs *regs, int cpu = smp_processor_id(); previous_current = curr_task(cpu); - set_curr_task(cpu, current); + ia64_set_curr_task(cpu, current); if ((p = strchr(current->comm, ' '))) *p = '\0'; @@ -1360,14 +1360,14 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw, cpumask_clear_cpu(i, &mca_cpu); /* wake next cpu */ while (monarch_cpu != -1) cpu_relax(); /* spin until last cpu leaves */ - set_curr_task(cpu, previous_current); + ia64_set_curr_task(cpu, previous_current); ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE; return; } } } - set_curr_task(cpu, previous_current); + ia64_set_curr_task(cpu, previous_current); ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE; monarch_cpu = -1; /* This frees the slaves and previous monarchs */ } @@ -1729,7 +1729,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw, NOTIFY_INIT(DIE_INIT_SLAVE_LEAVE, regs, (long)&nd, 1); mprintk("Slave on cpu %d returning to normal service.\n", cpu); - set_curr_task(cpu, previous_current); + ia64_set_curr_task(cpu, previous_current); ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE; atomic_dec(&slaves); return; @@ -1756,7 +1756,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw, mprintk("\nINIT dump complete. Monarch on cpu %d returning to normal service.\n", cpu); atomic_dec(&monarchs); - set_curr_task(cpu, previous_current); + ia64_set_curr_task(cpu, previous_current); monarch_cpu = -1; return; } @@ -1890,7 +1890,7 @@ ia64_mca_cpu_init(void *cpu_data) PAGE_KERNEL))); } -static void ia64_mca_cmc_vector_adjust(void *dummy) +static int ia64_mca_cpu_online(unsigned int cpu) { unsigned long flags; @@ -1898,25 +1898,9 @@ static void ia64_mca_cmc_vector_adjust(void *dummy) if (!cmc_polling_enabled) ia64_mca_cmc_vector_enable(NULL); local_irq_restore(flags); + return 0; } -static int mca_cpu_callback(struct notifier_block *nfb, - unsigned long action, - void *hcpu) -{ - switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - ia64_mca_cmc_vector_adjust(NULL); - break; - } - return NOTIFY_OK; -} - -static struct notifier_block mca_cpu_notifier = { - .notifier_call = mca_cpu_callback -}; - /* * ia64_mca_init * @@ -2111,15 +2095,13 @@ ia64_mca_late_init(void) if (!mca_init) return 0; - register_hotcpu_notifier(&mca_cpu_notifier); - /* Setup the CMCI/P vector and handler */ setup_timer(&cmc_poll_timer, ia64_mca_cmc_poll, 0UL); /* Unmask/enable the vector */ cmc_polling_enabled = 0; - schedule_work(&cmc_enable_work); - + cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "ia64/mca:online", + ia64_mca_cpu_online, NULL); IA64_MCA_DEBUG("%s: CMCI/P setup and enabled.\n", __func__); #ifdef CONFIG_ACPI diff --git a/arch/m32r/include/asm/uaccess.h b/arch/m32r/include/asm/uaccess.h index cac7014daef3..6f8982157a75 100644 --- a/arch/m32r/include/asm/uaccess.h +++ b/arch/m32r/include/asm/uaccess.h @@ -219,7 +219,7 @@ extern int fixup_exception(struct pt_regs *regs); #define __get_user_nocheck(x, ptr, size) \ ({ \ long __gu_err = 0; \ - unsigned long __gu_val; \ + unsigned long __gu_val = 0; \ might_fault(); \ __get_user_size(__gu_val, (ptr), (size), __gu_err); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 498b567f007b..d140206d5d29 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -14,7 +14,6 @@ config M68K select GENERIC_IOMAP select GENERIC_STRNCPY_FROM_USER if MMU select GENERIC_STRNLEN_USER if MMU - select FPU if MMU select ARCH_WANT_IPC_PARSE_VERSION select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE select HAVE_FUTEX_CMPXCHG if MMU && FUTEX diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu index 967260f2eb1c..d2219f30b78f 100644 --- a/arch/m68k/Kconfig.cpu +++ b/arch/m68k/Kconfig.cpu @@ -62,6 +62,7 @@ config MCPU32 config M68020 bool "68020 support" depends on MMU + select FPU select CPU_HAS_ADDRESS_SPACES help If you anticipate running this kernel on a computer with a MC68020 @@ -72,6 +73,7 @@ config M68020 config M68030 bool "68030 support" depends on MMU && !MMU_SUN3 + select FPU select CPU_HAS_ADDRESS_SPACES help If you anticipate running this kernel on a computer with a MC68030 @@ -81,6 +83,7 @@ config M68030 config M68040 bool "68040 support" depends on MMU && !MMU_SUN3 + select FPU select CPU_HAS_ADDRESS_SPACES help If you anticipate running this kernel on a computer with a MC68LC040 @@ -91,6 +94,7 @@ config M68040 config M68060 bool "68060 support" depends on MMU && !MMU_SUN3 + select FPU select CPU_HAS_ADDRESS_SPACES help If you anticipate running this kernel on a computer with a MC68060 @@ -259,6 +263,7 @@ config M547x bool "MCF547x" select M54xx select MMU_COLDFIRE if MMU + select FPU if MMU select HAVE_CACHE_CB select HAVE_MBAR select CPU_NO_EFFICIENT_FFS @@ -268,6 +273,7 @@ config M547x config M548x bool "MCF548x" select MMU_COLDFIRE if MMU + select FPU if MMU select M54xx select HAVE_CACHE_CB select HAVE_MBAR diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c index ec9cc1fdd237..ddb8192a3661 100644 --- a/arch/m68k/amiga/config.c +++ b/arch/m68k/amiga/config.c @@ -396,7 +396,7 @@ void __init config_amiga(void) mach_max_dma_address = 0xffffffff; mach_reset = amiga_reset; -#if defined(CONFIG_INPUT_M68K_BEEP) || defined(CONFIG_INPUT_M68K_BEEP_MODULE) +#if IS_ENABLED(CONFIG_INPUT_M68K_BEEP) mach_beep = amiga_mksound; #endif diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c index cbd5991fd49a..97a3c38cd1f5 100644 --- a/arch/m68k/atari/config.c +++ b/arch/m68k/atari/config.c @@ -211,7 +211,7 @@ void __init config_atari(void) arch_gettimeoffset = atari_gettimeoffset; mach_reset = atari_reset; mach_max_dma_address = 0xffffff; -#if defined(CONFIG_INPUT_M68K_BEEP) || defined(CONFIG_INPUT_M68K_BEEP_MODULE) +#if IS_ENABLED(CONFIG_INPUT_M68K_BEEP) mach_beep = atari_mksound; #endif #ifdef CONFIG_HEARTBEAT diff --git a/arch/m68k/coldfire/clk.c b/arch/m68k/coldfire/clk.c index fddfdccae63b..1e3c7e9193d1 100644 --- a/arch/m68k/coldfire/clk.c +++ b/arch/m68k/coldfire/clk.c @@ -101,6 +101,10 @@ EXPORT_SYMBOL(clk_enable); void clk_disable(struct clk *clk) { unsigned long flags; + + if (!clk) + return; + spin_lock_irqsave(&clk_lock, flags); if ((--clk->enabled == 0) && clk->clk_ops) clk->clk_ops->disable(clk); diff --git a/arch/m68k/coldfire/head.S b/arch/m68k/coldfire/head.S index 73d92ea0ce65..bdb472c48401 100644 --- a/arch/m68k/coldfire/head.S +++ b/arch/m68k/coldfire/head.S @@ -280,10 +280,10 @@ _clear_bss: movel %d0,m68k_cputype /* Mark us as a ColdFire */ movel #MMU_COLDFIRE,%d0 movel %d0,m68k_mmutype - movel #FPU_COLDFIRE,%d0 - movel %d0,m68k_fputype - movel #MACH_M54XX,%d0 - movel %d0,m68k_machtype /* Mark us as a 54xx machine */ + movel #FPUTYPE,%d0 + movel %d0,m68k_fputype /* Mark FPU type */ + movel #MACHINE,%d0 + movel %d0,m68k_machtype /* Mark machine type */ lea init_task,%a2 /* Set "current" init task */ #endif diff --git a/arch/m68k/coldfire/m528x.c b/arch/m68k/coldfire/m528x.c index 45e947aeade4..12f9e370d8dd 100644 --- a/arch/m68k/coldfire/m528x.c +++ b/arch/m68k/coldfire/m528x.c @@ -102,14 +102,14 @@ void wildfiremod_halt(void) printk(KERN_INFO "WildFireMod hibernating...\n"); /* Set portE.5 to Digital IO */ - MCF5282_GPIO_PEPAR &= ~(1 << (5 * 2)); + writew(readw(MCFGPIO_PEPAR) & ~(1 << (5 * 2)), MCFGPIO_PEPAR); /* Make portE.5 an output */ - MCF5282_GPIO_DDRE |= (1 << 5); + writeb(readb(MCFGPIO_PDDR_E) | (1 << 5), MCFGPIO_PDDR_E); /* Now toggle portE.5 from low to high */ - MCF5282_GPIO_PORTE &= ~(1 << 5); - MCF5282_GPIO_PORTE |= (1 << 5); + writeb(readb(MCFGPIO_PODR_E) & ~(1 << 5), MCFGPIO_PODR_E); + writeb(readb(MCFGPIO_PODR_E) | (1 << 5), MCFGPIO_PODR_E); printk(KERN_EMERG "Failed to hibernate. Halting!\n"); } diff --git a/arch/m68k/coldfire/m53xx.c b/arch/m68k/coldfire/m53xx.c index 80879a7fe3d5..2502f63960bc 100644 --- a/arch/m68k/coldfire/m53xx.c +++ b/arch/m68k/coldfire/m53xx.c @@ -271,9 +271,6 @@ void __init config_BSP(char *commandp, int size) #define NAND_FLASH_ADDRESS (0xD0000000) -int sys_clk_khz = 0; -int sys_clk_mhz = 0; - void wtm_init(void); void scm_init(void); void gpio_init(void); @@ -286,9 +283,8 @@ int get_sys_clock (void); asmlinkage void __init sysinit(void) { - sys_clk_khz = clock_pll(0, 0); - sys_clk_mhz = sys_clk_khz/1000; - + clock_pll(0, 0); + wtm_init(); scm_init(); gpio_init(); diff --git a/arch/m68k/coldfire/m54xx.c b/arch/m68k/coldfire/m54xx.c index c32f76791f48..386df3b68cdf 100644 --- a/arch/m68k/coldfire/m54xx.c +++ b/arch/m68k/coldfire/m54xx.c @@ -25,7 +25,6 @@ #include <asm/m54xxgpt.h> #ifdef CONFIG_MMU #include <asm/mmu_context.h> -#include <linux/pfn.h> #endif /***************************************************************************/ @@ -78,47 +77,10 @@ static void mcf54xx_reset(void) /***************************************************************************/ -#ifdef CONFIG_MMU - -unsigned long num_pages; - -static void __init mcf54xx_bootmem_alloc(void) -{ - unsigned long start_pfn; - unsigned long memstart; - - /* _rambase and _ramend will be naturally page aligned */ - m68k_memory[0].addr = _rambase; - m68k_memory[0].size = _ramend - _rambase; - - /* compute total pages in system */ - num_pages = PFN_DOWN(_ramend - _rambase); - - /* page numbers */ - memstart = PAGE_ALIGN(_ramstart); - min_low_pfn = PFN_DOWN(_rambase); - start_pfn = PFN_DOWN(memstart); - max_pfn = max_low_pfn = PFN_DOWN(_ramend); - high_memory = (void *)_ramend; - - m68k_virt_to_node_shift = fls(_ramend - _rambase - 1) - 6; - module_fixup(NULL, __start_fixup, __stop_fixup); - - /* setup bootmem data */ - m68k_setup_node(0); - memstart += init_bootmem_node(NODE_DATA(0), start_pfn, - min_low_pfn, max_low_pfn); - free_bootmem_node(NODE_DATA(0), memstart, _ramend - memstart); -} - -#endif /* CONFIG_MMU */ - -/***************************************************************************/ - void __init config_BSP(char *commandp, int size) { #ifdef CONFIG_MMU - mcf54xx_bootmem_alloc(); + cf_bootmem_alloc(); mmu_context_init(); #endif mach_reset = mcf54xx_reset; diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 8f5b6f7dd136..55be7e3ff109 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -566,6 +566,8 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_CRYPTO_RSA=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m @@ -584,6 +586,7 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 31bded9c83d4..365dda66b0e6 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -525,6 +525,8 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_CRYPTO_RSA=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m @@ -543,6 +545,7 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 0d7739e04ae2..ce3cbfd16fcd 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -546,6 +546,8 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_CRYPTO_RSA=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m @@ -564,6 +566,7 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 2cbb5c465fec..8db496a9797d 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -517,6 +517,8 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_CRYPTO_RSA=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m @@ -535,6 +537,7 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index 96102a42c156..8314156f7149 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -527,6 +527,8 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_CRYPTO_RSA=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m @@ -545,6 +547,7 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 97d88f7dc5a7..6600270b9622 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -549,6 +549,8 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_CRYPTO_RSA=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m @@ -567,6 +569,7 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index be25ef208f0f..90abfe9eabba 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -629,6 +629,8 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_CRYPTO_RSA=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m @@ -647,6 +649,7 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index a008344360c9..0d502c2f73d5 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -517,6 +517,8 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_CRYPTO_RSA=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m @@ -535,6 +537,7 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 6735a25f36d4..5930e91fc710 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -517,6 +517,8 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_CRYPTO_RSA=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m @@ -535,6 +537,7 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 780c6e9f6cf9..74e3ad82eca9 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -540,6 +540,8 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_CRYPTO_RSA=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m @@ -558,6 +560,7 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 44693cf361e5..4ba8606a4e69 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -518,6 +518,8 @@ CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_CRYPTO_RSA=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m @@ -536,6 +538,7 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index ef0071d61158..c6f49726a6c9 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -519,6 +519,8 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_CRYPTO_RSA=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m @@ -537,6 +539,7 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/m68k/include/asm/bootinfo.h b/arch/m68k/include/asm/bootinfo.h index 8e213267f8e7..81c91af8ec6c 100644 --- a/arch/m68k/include/asm/bootinfo.h +++ b/arch/m68k/include/asm/bootinfo.h @@ -22,6 +22,12 @@ extern void save_bootinfo(const struct bi_record *bi); static inline void save_bootinfo(const struct bi_record *bi) {} #endif +#ifdef CONFIG_UBOOT +void process_uboot_commandline(char *commandp, int size); +#else +static inline void process_uboot_commandline(char *commandp, int size) {} +#endif + #endif /* __ASSEMBLY__ */ diff --git a/arch/m68k/include/asm/m5441xsim.h b/arch/m68k/include/asm/m5441xsim.h index cc798ab9524b..64f60be47066 100644 --- a/arch/m68k/include/asm/m5441xsim.h +++ b/arch/m68k/include/asm/m5441xsim.h @@ -10,6 +10,10 @@ #define CPU_NAME "COLDFIRE(m5441x)" #define CPU_INSTR_PER_JIFFY 2 #define MCF_BUSCLK (MCF_CLK / 2) +#define MACHINE MACH_M5441X +#define FPUTYPE 0 +#define IOMEMBASE 0xe0000000 +#define IOMEMSIZE 0x20000000 #include <asm/m54xxacr.h> diff --git a/arch/m68k/include/asm/m54xxacr.h b/arch/m68k/include/asm/m54xxacr.h index 59e171063c2f..c6ac05cda282 100644 --- a/arch/m68k/include/asm/m54xxacr.h +++ b/arch/m68k/include/asm/m54xxacr.h @@ -94,7 +94,7 @@ * register region as non-cacheable. And then we map all our RAM as * cacheable and supervisor access only. */ -#define ACR0_MODE (ACR_BA(CONFIG_MBAR)+ACR_ADMSK(0x1000000)+ \ +#define ACR0_MODE (ACR_BA(IOMEMBASE)+ACR_ADMSK(IOMEMSIZE)+ \ ACR_ENABLE+ACR_SUPER+ACR_CM_OFF_PRE+ACR_SP) #if defined(CONFIG_CACHE_COPYBACK) #define ACR1_MODE (ACR_BA(CONFIG_RAMBASE)+ACR_ADMSK(CONFIG_RAMSIZE)+ \ diff --git a/arch/m68k/include/asm/m54xxsim.h b/arch/m68k/include/asm/m54xxsim.h index a5fbd17ab0a5..73d937ff36eb 100644 --- a/arch/m68k/include/asm/m54xxsim.h +++ b/arch/m68k/include/asm/m54xxsim.h @@ -8,6 +8,10 @@ #define CPU_NAME "COLDFIRE(m54xx)" #define CPU_INSTR_PER_JIFFY 2 #define MCF_BUSCLK (MCF_CLK / 2) +#define MACHINE MACH_M54XX +#define FPUTYPE FPU_COLDFIRE +#define IOMEMBASE MCF_MBAR +#define IOMEMSIZE 0x01000000 #include <asm/m54xxacr.h> diff --git a/arch/m68k/include/asm/mcfmmu.h b/arch/m68k/include/asm/mcfmmu.h index 8824236e303f..10f9930ec49a 100644 --- a/arch/m68k/include/asm/mcfmmu.h +++ b/arch/m68k/include/asm/mcfmmu.h @@ -105,6 +105,7 @@ static inline void mmu_write(u32 a, u32 v) __asm__ __volatile__ ("nop"); } +void cf_bootmem_alloc(void); int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word); #endif diff --git a/arch/m68k/include/asm/nettel.h b/arch/m68k/include/asm/nettel.h index 2a7a7667d807..926375d538ec 100644 --- a/arch/m68k/include/asm/nettel.h +++ b/arch/m68k/include/asm/nettel.h @@ -92,7 +92,7 @@ static __inline__ unsigned int mcf_getppdata(void) static __inline__ void mcf_setppdata(unsigned int mask, unsigned int bits) { - write((readw(MCFSIM_PBDAT) & ~mask) | bits, MCFSIM_PBDAT); + writew((readw(MCFSIM_PBDAT) & ~mask) | bits, MCFSIM_PBDAT); } #endif diff --git a/arch/m68k/include/uapi/asm/bootinfo.h b/arch/m68k/include/uapi/asm/bootinfo.h index cdeb26a015b0..a48cf544c762 100644 --- a/arch/m68k/include/uapi/asm/bootinfo.h +++ b/arch/m68k/include/uapi/asm/bootinfo.h @@ -81,6 +81,7 @@ struct mem_info { #define MACH_Q40 10 #define MACH_SUN3X 11 #define MACH_M54XX 12 +#define MACH_M5441X 13 /* diff --git a/arch/m68k/kernel/Makefile b/arch/m68k/kernel/Makefile index e47778f8588d..8a1c4d3f91c8 100644 --- a/arch/m68k/kernel/Makefile +++ b/arch/m68k/kernel/Makefile @@ -24,6 +24,7 @@ obj-$(CONFIG_HAS_DMA) += dma.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_BOOTINFO_PROC) += bootinfo_proc.o +obj-$(CONFIG_UBOOT) += uboot.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index c55ff719fa72..4ba1ae7345c3 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -203,11 +203,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, } /* Fill in the fpu structure for a core dump. */ -#ifdef CONFIG_FPU int dump_fpu (struct pt_regs *regs, struct user_m68kfp_struct *fpu) { - char fpustate[216]; - if (FPU_IS_EMU) { int i; @@ -222,37 +219,40 @@ int dump_fpu (struct pt_regs *regs, struct user_m68kfp_struct *fpu) return 1; } - /* First dump the fpu context to avoid protocol violation. */ - asm volatile ("fsave %0" :: "m" (fpustate[0]) : "memory"); - if (!CPU_IS_060 ? !fpustate[0] : !fpustate[2]) - return 0; + if (IS_ENABLED(CONFIG_FPU)) { + char fpustate[216]; - if (CPU_IS_COLDFIRE) { - asm volatile ("fmovel %/fpiar,%0\n\t" - "fmovel %/fpcr,%1\n\t" - "fmovel %/fpsr,%2\n\t" - "fmovemd %/fp0-%/fp7,%3" - : - : "m" (fpu->fpcntl[0]), - "m" (fpu->fpcntl[1]), - "m" (fpu->fpcntl[2]), - "m" (fpu->fpregs[0]) - : "memory"); - } else { - asm volatile ("fmovem %/fpiar/%/fpcr/%/fpsr,%0" - : - : "m" (fpu->fpcntl[0]) - : "memory"); - asm volatile ("fmovemx %/fp0-%/fp7,%0" - : - : "m" (fpu->fpregs[0]) - : "memory"); + /* First dump the fpu context to avoid protocol violation. */ + asm volatile ("fsave %0" :: "m" (fpustate[0]) : "memory"); + if (!CPU_IS_060 ? !fpustate[0] : !fpustate[2]) + return 0; + + if (CPU_IS_COLDFIRE) { + asm volatile ("fmovel %/fpiar,%0\n\t" + "fmovel %/fpcr,%1\n\t" + "fmovel %/fpsr,%2\n\t" + "fmovemd %/fp0-%/fp7,%3" + : + : "m" (fpu->fpcntl[0]), + "m" (fpu->fpcntl[1]), + "m" (fpu->fpcntl[2]), + "m" (fpu->fpregs[0]) + : "memory"); + } else { + asm volatile ("fmovem %/fpiar/%/fpcr/%/fpsr,%0" + : + : "m" (fpu->fpcntl[0]) + : "memory"); + asm volatile ("fmovemx %/fp0-%/fp7,%0" + : + : "m" (fpu->fpregs[0]) + : "memory"); + } } return 1; } EXPORT_SYMBOL(dump_fpu); -#endif /* CONFIG_FPU */ unsigned long get_wchan(struct task_struct *p) { diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index 5b8ec4d5f8e8..7a2c21212820 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -105,7 +105,7 @@ EXPORT_SYMBOL(mach_heartbeat); #ifdef CONFIG_M68K_L2_CACHE void (*mach_l2_flush) (int); #endif -#if defined(CONFIG_INPUT_M68K_BEEP) || defined(CONFIG_INPUT_M68K_BEEP_MODULE) +#if IS_ENABLED(CONFIG_INPUT_M68K_BEEP) void (*mach_beep)(unsigned int, unsigned int); EXPORT_SYMBOL(mach_beep); #endif @@ -245,7 +245,7 @@ void __init setup_arch(char **cmdline_p) * We should really do our own FPU check at startup. * [what do we do with buggy 68LC040s? if we have problems * with them, we should add a test to check_bugs() below] */ -#ifndef CONFIG_M68KFPU_EMU_ONLY +#if defined(CONFIG_FPU) && !defined(CONFIG_M68KFPU_EMU_ONLY) /* clear the fpu if we have one */ if (m68k_fputype & (FPU_68881|FPU_68882|FPU_68040|FPU_68060|FPU_COLDFIRE)) { volatile int zero = 0; @@ -274,6 +274,7 @@ void __init setup_arch(char **cmdline_p) strncpy(m68k_command_line, CONFIG_BOOTPARAM_STRING, CL_SIZE); m68k_command_line[CL_SIZE - 1] = 0; #endif /* CONFIG_BOOTPARAM */ + process_uboot_commandline(&m68k_command_line[0], CL_SIZE); *cmdline_p = m68k_command_line; memcpy(boot_command_line, *cmdline_p, CL_SIZE); @@ -341,6 +342,7 @@ void __init setup_arch(char **cmdline_p) #endif #ifdef CONFIG_COLDFIRE case MACH_M54XX: + case MACH_M5441X: config_BSP(NULL, 0); break; #endif @@ -548,7 +550,7 @@ module_init(proc_hardware_init); void check_bugs(void) { -#ifndef CONFIG_M68KFPU_EMU +#if defined(CONFIG_FPU) && !defined(CONFIG_M68KFPU_EMU) if (m68k_fputype == 0) { pr_emerg("*** YOU DO NOT HAVE A FLOATING POINT UNIT, " "WHICH IS REQUIRED BY LINUX/M68K ***\n"); diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c index 9309789215a8..8afe6f651c1c 100644 --- a/arch/m68k/kernel/setup_no.c +++ b/arch/m68k/kernel/setup_no.c @@ -34,6 +34,7 @@ #include <linux/rtc.h> #include <asm/setup.h> +#include <asm/bootinfo.h> #include <asm/irq.h> #include <asm/machdep.h> #include <asm/pgtable.h> @@ -82,69 +83,6 @@ void (*mach_power_off)(void); #define CPU_INSTR_PER_JIFFY 16 #endif -#if defined(CONFIG_UBOOT) -/* - * parse_uboot_commandline - * - * Copies u-boot commandline arguments and store them in the proper linux - * variables. - * - * Assumes: - * _init_sp global contains the address in the stack pointer when the - * kernel starts (see head.S::_start) - * - * U-Boot calling convention: - * (*kernel) (kbd, initrd_start, initrd_end, cmd_start, cmd_end); - * - * _init_sp can be parsed as such - * - * _init_sp+00 = u-boot cmd after jsr into kernel (skip) - * _init_sp+04 = &kernel board_info (residual data) - * _init_sp+08 = &initrd_start - * _init_sp+12 = &initrd_end - * _init_sp+16 = &cmd_start - * _init_sp+20 = &cmd_end - * - * This also assumes that the memory locations pointed to are still - * unmodified. U-boot places them near the end of external SDRAM. - * - * Argument(s): - * commandp = the linux commandline arg container to fill. - * size = the sizeof commandp. - * - * Returns: - */ -static void __init parse_uboot_commandline(char *commandp, int size) -{ - extern unsigned long _init_sp; - unsigned long *sp; - unsigned long uboot_kbd; - unsigned long uboot_initrd_start, uboot_initrd_end; - unsigned long uboot_cmd_start, uboot_cmd_end; - - - sp = (unsigned long *)_init_sp; - uboot_kbd = sp[1]; - uboot_initrd_start = sp[2]; - uboot_initrd_end = sp[3]; - uboot_cmd_start = sp[4]; - uboot_cmd_end = sp[5]; - - if (uboot_cmd_start && uboot_cmd_end) - strncpy(commandp, (const char *)uboot_cmd_start, size); -#if defined(CONFIG_BLK_DEV_INITRD) - if (uboot_initrd_start && uboot_initrd_end && - (uboot_initrd_end > uboot_initrd_start)) { - initrd_start = uboot_initrd_start; - initrd_end = uboot_initrd_end; - ROOT_DEV = Root_RAM0; - printk(KERN_INFO "initrd at 0x%lx:0x%lx\n", - initrd_start, initrd_end); - } -#endif /* if defined(CONFIG_BLK_DEV_INITRD) */ -} -#endif /* #if defined(CONFIG_UBOOT) */ - void __init setup_arch(char **cmdline_p) { int bootmap_size; @@ -164,53 +102,38 @@ void __init setup_arch(char **cmdline_p) command_line[sizeof(command_line) - 1] = 0; #endif /* CONFIG_BOOTPARAM */ -#if defined(CONFIG_UBOOT) - /* CONFIG_UBOOT and CONFIG_BOOTPARAM defined, concatenate cmdline */ - #if defined(CONFIG_BOOTPARAM) - /* Add the whitespace separator */ - command_line[strlen(CONFIG_BOOTPARAM_STRING)] = ' '; - /* Parse uboot command line into the rest of the buffer */ - parse_uboot_commandline( - &command_line[(strlen(CONFIG_BOOTPARAM_STRING)+1)], - (sizeof(command_line) - - (strlen(CONFIG_BOOTPARAM_STRING)+1))); - /* Only CONFIG_UBOOT defined, create cmdline */ - #else - parse_uboot_commandline(&command_line[0], sizeof(command_line)); - #endif /* CONFIG_BOOTPARAM */ - command_line[sizeof(command_line) - 1] = 0; -#endif /* CONFIG_UBOOT */ + process_uboot_commandline(&command_line[0], sizeof(command_line)); - printk(KERN_INFO "\x0F\r\n\nuClinux/" CPU_NAME "\n"); + pr_info("uClinux with CPU " CPU_NAME "\n"); #ifdef CONFIG_UCDIMM - printk(KERN_INFO "uCdimm by Lineo, Inc. <www.lineo.com>\n"); + pr_info("uCdimm by Lineo, Inc. <www.lineo.com>\n"); #endif #ifdef CONFIG_M68VZ328 - printk(KERN_INFO "M68VZ328 support by Evan Stawnyczy <e@lineo.ca>\n"); + pr_info("M68VZ328 support by Evan Stawnyczy <e@lineo.ca>\n"); #endif #ifdef CONFIG_COLDFIRE - printk(KERN_INFO "COLDFIRE port done by Greg Ungerer, gerg@snapgear.com\n"); + pr_info("COLDFIRE port done by Greg Ungerer, gerg@snapgear.com\n"); #ifdef CONFIG_M5307 - printk(KERN_INFO "Modified for M5307 by Dave Miller, dmiller@intellistor.com\n"); + pr_info("Modified for M5307 by Dave Miller, dmiller@intellistor.com\n"); #endif #ifdef CONFIG_ELITE - printk(KERN_INFO "Modified for M5206eLITE by Rob Scott, rscott@mtrob.fdns.net\n"); + pr_info("Modified for M5206eLITE by Rob Scott, rscott@mtrob.fdns.net\n"); #endif #endif - printk(KERN_INFO "Flat model support (C) 1998,1999 Kenneth Albanowski, D. Jeff Dionne\n"); + pr_info("Flat model support (C) 1998,1999 Kenneth Albanowski, D. Jeff Dionne\n"); #if defined( CONFIG_PILOT ) && defined( CONFIG_M68328 ) - printk(KERN_INFO "TRG SuperPilot FLASH card support <info@trgnet.com>\n"); + pr_info("TRG SuperPilot FLASH card support <info@trgnet.com>\n"); #endif #if defined( CONFIG_PILOT ) && defined( CONFIG_M68EZ328 ) - printk(KERN_INFO "PalmV support by Lineo Inc. <jeff@uclinux.com>\n"); + pr_info("PalmV support by Lineo Inc. <jeff@uclinux.com>\n"); #endif #ifdef CONFIG_DRAGEN2 - printk(KERN_INFO "DragonEngine II board support by Georges Menie\n"); + pr_info("DragonEngine II board support by Georges Menie\n"); #endif #ifdef CONFIG_M5235EVB - printk(KERN_INFO "Motorola M5235EVB support (C)2005 Syn-tech Systems, Inc. (Jate Sujjavanich)\n"); + pr_info("Motorola M5235EVB support (C)2005 Syn-tech Systems, Inc. (Jate Sujjavanich)\n"); #endif pr_debug("KERNEL -> TEXT=0x%p-0x%p DATA=0x%p-0x%p BSS=0x%p-0x%p\n", diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index 9202f82dfce6..58507edbdf1d 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -42,7 +42,7 @@ #include <linux/personality.h> #include <linux/tty.h> #include <linux/binfmts.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/tracehook.h> #include <asm/setup.h> diff --git a/arch/m68k/kernel/uboot.c b/arch/m68k/kernel/uboot.c new file mode 100644 index 000000000000..b3536a82a262 --- /dev/null +++ b/arch/m68k/kernel/uboot.c @@ -0,0 +1,107 @@ +/* + * uboot.c -- uboot arguments support + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/fb.h> +#include <linux/module.h> +#include <linux/mm.h> +#include <linux/console.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/bootmem.h> +#include <linux/seq_file.h> +#include <linux/init.h> +#include <linux/initrd.h> +#include <linux/root_dev.h> +#include <linux/rtc.h> + +#include <asm/setup.h> +#include <asm/irq.h> +#include <asm/machdep.h> +#include <asm/pgtable.h> +#include <asm/sections.h> + +/* + * parse_uboot_commandline + * + * Copies u-boot commandline arguments and store them in the proper linux + * variables. + * + * Assumes: + * _init_sp global contains the address in the stack pointer when the + * kernel starts (see head.S::_start) + * + * U-Boot calling convention: + * (*kernel) (kbd, initrd_start, initrd_end, cmd_start, cmd_end); + * + * _init_sp can be parsed as such + * + * _init_sp+00 = u-boot cmd after jsr into kernel (skip) + * _init_sp+04 = &kernel board_info (residual data) + * _init_sp+08 = &initrd_start + * _init_sp+12 = &initrd_end + * _init_sp+16 = &cmd_start + * _init_sp+20 = &cmd_end + * + * This also assumes that the memory locations pointed to are still + * unmodified. U-boot places them near the end of external SDRAM. + * + * Argument(s): + * commandp = the linux commandline arg container to fill. + * size = the sizeof commandp. + * + * Returns: + */ +static void __init parse_uboot_commandline(char *commandp, int size) +{ + extern unsigned long _init_sp; + unsigned long *sp; + unsigned long uboot_kbd; + unsigned long uboot_initrd_start, uboot_initrd_end; + unsigned long uboot_cmd_start, uboot_cmd_end; + + sp = (unsigned long *)_init_sp; + uboot_kbd = sp[1]; + uboot_initrd_start = sp[2]; + uboot_initrd_end = sp[3]; + uboot_cmd_start = sp[4]; + uboot_cmd_end = sp[5]; + + if (uboot_cmd_start && uboot_cmd_end) + strncpy(commandp, (const char *)uboot_cmd_start, size); +#if defined(CONFIG_BLK_DEV_INITRD) + if (uboot_initrd_start && uboot_initrd_end && + (uboot_initrd_end > uboot_initrd_start)) { + initrd_start = uboot_initrd_start; + initrd_end = uboot_initrd_end; + ROOT_DEV = Root_RAM0; + printk(KERN_INFO "initrd at 0x%lx:0x%lx\n", + initrd_start, initrd_end); + } +#endif /* if defined(CONFIG_BLK_DEV_INITRD) */ +} + +__init void process_uboot_commandline(char *commandp, int size) +{ + int len, n; + + n = strnlen(commandp, size); + commandp += n; + len = size - n; + if (len) { + /* Add the whitespace separator */ + *commandp++ = ' '; + len--; + } + + parse_uboot_commandline(commandp, len); + commandp[size - 1] = 0; +} diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index 2f33a33001e5..e46895316eb0 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -162,7 +162,7 @@ void __init config_mac(void) mach_halt = mac_poweroff; mach_power_off = mac_poweroff; mach_max_dma_address = 0xffffffff; -#if defined(CONFIG_INPUT_M68K_BEEP) || defined(CONFIG_INPUT_M68K_BEEP_MODULE) +#if IS_ENABLED(CONFIG_INPUT_M68K_BEEP) mach_beep = mac_mksound; #endif diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index f58fafe7e4c9..87131cd3bc8f 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -27,7 +27,7 @@ mm_context_t next_mmu_context; unsigned long context_map[LAST_CONTEXT / BITS_PER_LONG + 1]; atomic_t nr_free_contexts; struct mm_struct *context_mm[LAST_CONTEXT+1]; -extern unsigned long num_pages; +unsigned long num_pages; /* * ColdFire paging_init derived from sun3. @@ -150,6 +150,35 @@ int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word) return 0; } +void __init cf_bootmem_alloc(void) +{ + unsigned long start_pfn; + unsigned long memstart; + + /* _rambase and _ramend will be naturally page aligned */ + m68k_memory[0].addr = _rambase; + m68k_memory[0].size = _ramend - _rambase; + + /* compute total pages in system */ + num_pages = PFN_DOWN(_ramend - _rambase); + + /* page numbers */ + memstart = PAGE_ALIGN(_ramstart); + min_low_pfn = PFN_DOWN(_rambase); + start_pfn = PFN_DOWN(memstart); + max_pfn = max_low_pfn = PFN_DOWN(_ramend); + high_memory = (void *)_ramend; + + m68k_virt_to_node_shift = fls(_ramend - _rambase - 1) - 6; + module_fixup(NULL, __start_fixup, __stop_fixup); + + /* setup bootmem data */ + m68k_setup_node(0); + memstart += init_bootmem_node(NODE_DATA(0), start_pfn, + min_low_pfn, max_low_pfn); + free_bootmem_node(NODE_DATA(0), memstart, _ramend - memstart); +} + /* * Initialize the context management stuff. * The following was taken from arch/ppc/mmu_context.c diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c index fcb7f05b60b6..ea89a24f4600 100644 --- a/arch/m68k/q40/config.c +++ b/arch/m68k/q40/config.c @@ -180,7 +180,7 @@ void __init config_q40(void) mach_reset = q40_reset; mach_get_model = q40_get_model; -#if defined(CONFIG_INPUT_M68K_BEEP) || defined(CONFIG_INPUT_M68K_BEEP_MODULE) +#if IS_ENABLED(CONFIG_INPUT_M68K_BEEP) mach_beep = q40_mksound; #endif #ifdef CONFIG_HEARTBEAT diff --git a/arch/metag/include/asm/uaccess.h b/arch/metag/include/asm/uaccess.h index 8282cbce7e39..273e61225c27 100644 --- a/arch/metag/include/asm/uaccess.h +++ b/arch/metag/include/asm/uaccess.h @@ -204,8 +204,9 @@ extern unsigned long __must_check __copy_user_zeroing(void *to, static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n) { - if (access_ok(VERIFY_READ, from, n)) + if (likely(access_ok(VERIFY_READ, from, n))) return __copy_user_zeroing(to, from, n); + memset(to, 0, n); return n; } diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h index 331b0d35f89c..826676778094 100644 --- a/arch/microblaze/include/asm/uaccess.h +++ b/arch/microblaze/include/asm/uaccess.h @@ -227,7 +227,7 @@ extern long __user_bad(void); #define __get_user(x, ptr) \ ({ \ - unsigned long __gu_val; \ + unsigned long __gu_val = 0; \ /*unsigned long __gu_ptr = (unsigned long)(ptr);*/ \ long __gu_err; \ switch (sizeof(*(ptr))) { \ @@ -373,10 +373,13 @@ extern long __user_bad(void); static inline long copy_from_user(void *to, const void __user *from, unsigned long n) { + unsigned long res = n; might_fault(); - if (access_ok(VERIFY_READ, from, n)) - return __copy_from_user(to, from, n); - return n; + if (likely(access_ok(VERIFY_READ, from, n))) + res = __copy_from_user(to, from, n); + if (unlikely(res)) + memset(to + (n - res), 0, res); + return res; } #define __copy_to_user(to, from, n) \ diff --git a/arch/microblaze/kernel/ftrace.c b/arch/microblaze/kernel/ftrace.c index fc7b48a52cd5..d57563c58a26 100644 --- a/arch/microblaze/kernel/ftrace.c +++ b/arch/microblaze/kernel/ftrace.c @@ -63,7 +63,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0); + err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0, NULL); if (err == -EBUSY) { *parent = old; return; diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c index 81556b843a8e..7f696f97f9dd 100644 --- a/arch/microblaze/pci/pci-common.c +++ b/arch/microblaze/pci/pci-common.c @@ -632,10 +632,10 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, } } -/* Decide whether to display the domain number in /proc */ +/* Display the domain number in /proc */ int pci_proc_domain(struct pci_bus *bus) { - return 0; + return pci_domain_nr(bus); } /* This header fixup will do the resource fixup for all devices as they are diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 26388562e300..212ff92920d2 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -65,6 +65,7 @@ config MIPS select ARCH_CLOCKSOURCE_DATA select HANDLE_DOMAIN_IRQ select HAVE_EXIT_THREAD + select HAVE_REGS_AND_STACK_ACCESS_API menu "Machine selection" diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug index f0e314ceb8ba..7f975b20b20c 100644 --- a/arch/mips/Kconfig.debug +++ b/arch/mips/Kconfig.debug @@ -113,42 +113,6 @@ config SPINLOCK_TEST help Add several files to the debugfs to test spinlock speed. -if CPU_MIPSR6 - -choice - prompt "Compact branch policy" - default MIPS_COMPACT_BRANCHES_OPTIMAL - -config MIPS_COMPACT_BRANCHES_NEVER - bool "Never (force delay slot branches)" - help - Pass the -mcompact-branches=never flag to the compiler in order to - force it to always emit branches with delay slots, and make no use - of the compact branch instructions introduced by MIPSr6. This is - useful if you suspect there may be an issue with compact branches in - either the compiler or the CPU. - -config MIPS_COMPACT_BRANCHES_OPTIMAL - bool "Optimal (use where beneficial)" - help - Pass the -mcompact-branches=optimal flag to the compiler in order for - it to make use of compact branch instructions where it deems them - beneficial, and use branches with delay slots elsewhere. This is the - default compiler behaviour, and should be used unless you have a - reason to choose otherwise. - -config MIPS_COMPACT_BRANCHES_ALWAYS - bool "Always (force compact branches)" - help - Pass the -mcompact-branches=always flag to the compiler in order to - force it to always emit compact branches, making no use of branch - instructions with delay slots. This can result in more compact code - which may be beneficial in some scenarios. - -endchoice - -endif # CPU_MIPSR6 - config SCACHE_DEBUGFS bool "L2 cache debugfs entries" depends on DEBUG_FS diff --git a/arch/mips/Makefile b/arch/mips/Makefile index efd7a9dc93c4..598ab2930fce 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -203,10 +203,6 @@ endif toolchain-virt := $(call cc-option-yn,$(mips-cflags) -mvirt) cflags-$(toolchain-virt) += -DTOOLCHAIN_SUPPORTS_VIRT -cflags-$(CONFIG_MIPS_COMPACT_BRANCHES_NEVER) += -mcompact-branches=never -cflags-$(CONFIG_MIPS_COMPACT_BRANCHES_OPTIMAL) += -mcompact-branches=optimal -cflags-$(CONFIG_MIPS_COMPACT_BRANCHES_ALWAYS) += -mcompact-branches=always - # # Firmware support # diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c index 2e7378467c5c..cc3a1e33a600 100644 --- a/arch/mips/ath79/clock.c +++ b/arch/mips/ath79/clock.c @@ -96,7 +96,7 @@ static struct clk * __init ath79_reg_ffclk(const char *name, struct clk *clk; clk = clk_register_fixed_factor(NULL, name, parent_name, 0, mult, div); - if (!clk) + if (IS_ERR(clk)) panic("failed to allocate %s clock structure", name); return clk; diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 5a9b87b7993e..c1eb1ff7c800 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -1619,6 +1619,12 @@ static int __init octeon_irq_init_gpio( return -ENOMEM; } + /* + * Clear the OF_POPULATED flag that was set by of_irq_init() + * so that all GPIO devices will be probed. + */ + of_node_clear_flag(gpio_node, OF_POPULATED); + return 0; } /* diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c index b31fbc9d6eae..37a932d9148c 100644 --- a/arch/mips/cavium-octeon/octeon-platform.c +++ b/arch/mips/cavium-octeon/octeon-platform.c @@ -1059,7 +1059,7 @@ static int __init octeon_publish_devices(void) { return of_platform_bus_probe(NULL, octeon_ids, NULL); } -device_initcall(octeon_publish_devices); +arch_initcall(octeon_publish_devices); MODULE_AUTHOR("David Daney <ddaney@caviumnetworks.com>"); MODULE_LICENSE("GPL"); diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 4d457d602d3b..256fe6f65cf2 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -380,29 +380,11 @@ static int octeon_update_boot_vector(unsigned int cpu) return 0; } -static int octeon_cpu_callback(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - unsigned int cpu = (unsigned long)hcpu; - - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - octeon_update_boot_vector(cpu); - break; - case CPU_ONLINE: - pr_info("Cpu %d online\n", cpu); - break; - case CPU_DEAD: - break; - } - - return NOTIFY_OK; -} - static int register_cavium_notifier(void) { - hotcpu_notifier(octeon_cpu_callback, 0); - return 0; + return cpuhp_setup_state_nocalls(CPUHP_MIPS_SOC_PREPARE, + "mips/cavium:prepare", + octeon_update_boot_vector, NULL); } late_initcall(register_cavium_notifier); diff --git a/arch/mips/dec/int-handler.S b/arch/mips/dec/int-handler.S index d7b99180c6e1..1910223a9c02 100644 --- a/arch/mips/dec/int-handler.S +++ b/arch/mips/dec/int-handler.S @@ -146,7 +146,25 @@ /* * Find irq with highest priority */ - PTR_LA t1,cpu_mask_nr_tbl + # open coded PTR_LA t1, cpu_mask_nr_tbl +#if (_MIPS_SZPTR == 32) + # open coded la t1, cpu_mask_nr_tbl + lui t1, %hi(cpu_mask_nr_tbl) + addiu t1, %lo(cpu_mask_nr_tbl) + +#endif +#if (_MIPS_SZPTR == 64) + # open coded dla t1, cpu_mask_nr_tbl + .set push + .set noat + lui t1, %highest(cpu_mask_nr_tbl) + lui AT, %hi(cpu_mask_nr_tbl) + daddiu t1, t1, %higher(cpu_mask_nr_tbl) + daddiu AT, AT, %lo(cpu_mask_nr_tbl) + dsll t1, 32 + daddu t1, t1, AT + .set pop +#endif 1: lw t2,(t1) nop and t2,t0 @@ -195,7 +213,25 @@ /* * Find irq with highest priority */ - PTR_LA t1,asic_mask_nr_tbl + # open coded PTR_LA t1,asic_mask_nr_tbl +#if (_MIPS_SZPTR == 32) + # open coded la t1, asic_mask_nr_tbl + lui t1, %hi(asic_mask_nr_tbl) + addiu t1, %lo(asic_mask_nr_tbl) + +#endif +#if (_MIPS_SZPTR == 64) + # open coded dla t1, asic_mask_nr_tbl + .set push + .set noat + lui t1, %highest(asic_mask_nr_tbl) + lui AT, %hi(asic_mask_nr_tbl) + daddiu t1, t1, %higher(asic_mask_nr_tbl) + daddiu AT, AT, %lo(asic_mask_nr_tbl) + dsll t1, 32 + daddu t1, t1, AT + .set pop +#endif 2: lw t2,(t1) nop and t2,t0 diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h index 56584a659183..83054f79f72a 100644 --- a/arch/mips/include/asm/asmmacro.h +++ b/arch/mips/include/asm/asmmacro.h @@ -157,6 +157,7 @@ ldc1 $f28, THREAD_FPR28(\thread) ldc1 $f30, THREAD_FPR30(\thread) ctc1 \tmp, fcr31 + .set pop .endm .macro fpu_restore_16odd thread diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index b54bcadd8aec..07f58cfc1ab9 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -107,35 +107,49 @@ #define KVM_INVALID_INST 0xdeadbeef #define KVM_INVALID_ADDR 0xdeadbeef +/* + * EVA has overlapping user & kernel address spaces, so user VAs may be > + * PAGE_OFFSET. For this reason we can't use the default KVM_HVA_ERR_BAD of + * PAGE_OFFSET. + */ + +#define KVM_HVA_ERR_BAD (-1UL) +#define KVM_HVA_ERR_RO_BAD (-2UL) + +static inline bool kvm_is_error_hva(unsigned long addr) +{ + return IS_ERR_VALUE(addr); +} + extern atomic_t kvm_mips_instance; struct kvm_vm_stat { - u32 remote_tlb_flush; + ulong remote_tlb_flush; }; struct kvm_vcpu_stat { - u32 wait_exits; - u32 cache_exits; - u32 signal_exits; - u32 int_exits; - u32 cop_unusable_exits; - u32 tlbmod_exits; - u32 tlbmiss_ld_exits; - u32 tlbmiss_st_exits; - u32 addrerr_st_exits; - u32 addrerr_ld_exits; - u32 syscall_exits; - u32 resvd_inst_exits; - u32 break_inst_exits; - u32 trap_inst_exits; - u32 msa_fpe_exits; - u32 fpe_exits; - u32 msa_disabled_exits; - u32 flush_dcache_exits; - u32 halt_successful_poll; - u32 halt_attempted_poll; - u32 halt_poll_invalid; - u32 halt_wakeup; + u64 wait_exits; + u64 cache_exits; + u64 signal_exits; + u64 int_exits; + u64 cop_unusable_exits; + u64 tlbmod_exits; + u64 tlbmiss_ld_exits; + u64 tlbmiss_st_exits; + u64 addrerr_st_exits; + u64 addrerr_ld_exits; + u64 syscall_exits; + u64 resvd_inst_exits; + u64 break_inst_exits; + u64 trap_inst_exits; + u64 msa_fpe_exits; + u64 fpe_exits; + u64 msa_disabled_exits; + u64 flush_dcache_exits; + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_poll_invalid; + u64 halt_wakeup; }; struct kvm_arch_memory_slot { @@ -314,6 +328,9 @@ struct kvm_vcpu_arch { u32 guest_kernel_asid[NR_CPUS]; struct mm_struct guest_kernel_mm, guest_user_mm; + /* Guest ASID of last user mode execution */ + unsigned int last_user_gasid; + int last_sched_cpu; /* WAIT executed */ diff --git a/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h b/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h index 0cf5ac1f7245..8ff2cbdf2c3e 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h +++ b/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h @@ -15,8 +15,8 @@ static inline bool __should_swizzle_bits(volatile void *a) { extern const bool octeon_should_swizzle_table[]; + u64 did = ((u64)(uintptr_t)a >> 40) & 0xff; - unsigned long did = ((unsigned long)a >> 40) & 0xff; return octeon_should_swizzle_table[did]; } @@ -29,7 +29,7 @@ static inline bool __should_swizzle_bits(volatile void *a) #define __should_swizzle_bits(a) false -static inline bool __should_swizzle_addr(unsigned long p) +static inline bool __should_swizzle_addr(u64 p) { /* boot bus? */ return ((p >> 40) & 0xff) == 0; diff --git a/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h b/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h index 2f82bfa3a773..c9f5769dfc8f 100644 --- a/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h +++ b/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h @@ -11,11 +11,13 @@ #define CP0_EBASE $15, 1 .macro kernel_entry_setup +#ifdef CONFIG_SMP mfc0 t0, CP0_EBASE andi t0, t0, 0x3ff # CPUNum beqz t0, 1f # CPUs other than zero goto smp_bootstrap j smp_bootstrap +#endif /* CONFIG_SMP */ 1: .endm diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h index 58e7874e9347..4fafeefe65c2 100644 --- a/arch/mips/include/asm/mips-cm.h +++ b/arch/mips/include/asm/mips-cm.h @@ -458,10 +458,21 @@ static inline int mips_cm_revision(void) static inline unsigned int mips_cm_max_vp_width(void) { extern int smp_num_siblings; + uint32_t cfg; if (mips_cm_revision() >= CM_REV_CM3) return read_gcr_sys_config2() & CM_GCR_SYS_CONFIG2_MAXVPW_MSK; + if (mips_cm_present()) { + /* + * We presume that all cores in the system will have the same + * number of VP(E)s, and if that ever changes then this will + * need revisiting. + */ + cfg = read_gcr_cl_config() & CM_GCR_Cx_CONFIG_PVPE_MSK; + return (cfg >> CM_GCR_Cx_CONFIG_PVPE_SHF) + 1; + } + if (IS_ENABLED(CONFIG_SMP)) return smp_num_siblings; diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index def9d8d13f6e..7dd2dd47909a 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -660,8 +660,6 @@ #define MIPS_CONF7_IAR (_ULCAST_(1) << 10) #define MIPS_CONF7_AR (_ULCAST_(1) << 16) -/* FTLB probability bits for R6 */ -#define MIPS_CONF7_FTLBP_SHIFT (18) /* WatchLo* register definitions */ #define MIPS_WATCHLO_IRW (_ULCAST_(0x7) << 0) diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h index 11b965f98d95..21a2aaba20d5 100644 --- a/arch/mips/include/asm/uaccess.h +++ b/arch/mips/include/asm/uaccess.h @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/thread_info.h> +#include <linux/string.h> #include <asm/asm-eva.h> /* @@ -1170,6 +1171,8 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n); __cu_len = __invoke_copy_from_user(__cu_to, \ __cu_from, \ __cu_len); \ + } else { \ + memset(__cu_to, 0, __cu_len); \ } \ } \ __cu_len; \ diff --git a/arch/mips/include/asm/uprobes.h b/arch/mips/include/asm/uprobes.h index 34c325c674c4..70a4a2f173ff 100644 --- a/arch/mips/include/asm/uprobes.h +++ b/arch/mips/include/asm/uprobes.h @@ -36,7 +36,6 @@ struct arch_uprobe { unsigned long resume_epc; u32 insn[2]; u32 ixol[2]; - union mips_instruction orig_inst[MAX_UINSN_BYTES / 4]; }; struct arch_uprobe_task { diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index a88d44247cc8..dd3175442c9e 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -352,7 +352,12 @@ __setup("nohtw", htw_disable); static int mips_ftlb_disabled; static int mips_has_ftlb_configured; -static int set_ftlb_enable(struct cpuinfo_mips *c, int enable); +enum ftlb_flags { + FTLB_EN = 1 << 0, + FTLB_SET_PROB = 1 << 1, +}; + +static int set_ftlb_enable(struct cpuinfo_mips *c, enum ftlb_flags flags); static int __init ftlb_disable(char *s) { @@ -371,8 +376,6 @@ static int __init ftlb_disable(char *s) return 1; } - back_to_back_c0_hazard(); - config4 = read_c0_config4(); /* Check that FTLB has been disabled */ @@ -531,7 +534,7 @@ static unsigned int calculate_ftlb_probability(struct cpuinfo_mips *c) return 3; } -static int set_ftlb_enable(struct cpuinfo_mips *c, int enable) +static int set_ftlb_enable(struct cpuinfo_mips *c, enum ftlb_flags flags) { unsigned int config; @@ -542,33 +545,33 @@ static int set_ftlb_enable(struct cpuinfo_mips *c, int enable) case CPU_P6600: /* proAptiv & related cores use Config6 to enable the FTLB */ config = read_c0_config6(); - /* Clear the old probability value */ - config &= ~(3 << MIPS_CONF6_FTLBP_SHIFT); - if (enable) - /* Enable FTLB */ - write_c0_config6(config | - (calculate_ftlb_probability(c) - << MIPS_CONF6_FTLBP_SHIFT) - | MIPS_CONF6_FTLBEN); + + if (flags & FTLB_EN) + config |= MIPS_CONF6_FTLBEN; else - /* Disable FTLB */ - write_c0_config6(config & ~MIPS_CONF6_FTLBEN); + config &= ~MIPS_CONF6_FTLBEN; + + if (flags & FTLB_SET_PROB) { + config &= ~(3 << MIPS_CONF6_FTLBP_SHIFT); + config |= calculate_ftlb_probability(c) + << MIPS_CONF6_FTLBP_SHIFT; + } + + write_c0_config6(config); + back_to_back_c0_hazard(); break; case CPU_I6400: - /* I6400 & related cores use Config7 to configure FTLB */ - config = read_c0_config7(); - /* Clear the old probability value */ - config &= ~(3 << MIPS_CONF7_FTLBP_SHIFT); - write_c0_config7(config | (calculate_ftlb_probability(c) - << MIPS_CONF7_FTLBP_SHIFT)); - break; + /* There's no way to disable the FTLB */ + if (!(flags & FTLB_EN)) + return 1; + return 0; case CPU_LOONGSON3: /* Flush ITLB, DTLB, VTLB and FTLB */ write_c0_diag(LOONGSON_DIAG_ITLB | LOONGSON_DIAG_DTLB | LOONGSON_DIAG_VTLB | LOONGSON_DIAG_FTLB); /* Loongson-3 cores use Config6 to enable the FTLB */ config = read_c0_config6(); - if (enable) + if (flags & FTLB_EN) /* Enable FTLB */ write_c0_config6(config & ~MIPS_CONF6_FTLBDIS); else @@ -788,6 +791,7 @@ static inline unsigned int decode_config4(struct cpuinfo_mips *c) PAGE_SIZE, config4); /* Switch FTLB off */ set_ftlb_enable(c, 0); + mips_ftlb_disabled = 1; break; } c->tlbsizeftlbsets = 1 << @@ -852,7 +856,7 @@ static void decode_configs(struct cpuinfo_mips *c) c->scache.flags = MIPS_CACHE_NOT_PRESENT; /* Enable FTLB if present and not disabled */ - set_ftlb_enable(c, !mips_ftlb_disabled); + set_ftlb_enable(c, mips_ftlb_disabled ? 0 : FTLB_EN); ok = decode_config0(c); /* Read Config registers. */ BUG_ON(!ok); /* Arch spec violation! */ @@ -902,6 +906,9 @@ static void decode_configs(struct cpuinfo_mips *c) } } + /* configure the FTLB write probability */ + set_ftlb_enable(c, (mips_ftlb_disabled ? 0 : FTLB_EN) | FTLB_SET_PROB); + mips_probe_watch_registers(c); #ifndef CONFIG_MIPS_CPS diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index 937c54bc8ccc..30a3b75e88eb 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -382,8 +382,8 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra, if (unlikely(faulted)) goto out; - if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp) - == -EBUSY) { + if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp, + NULL) == -EBUSY) { *parent_ra_addr = old_parent_ra; return; } diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index 17326a90d53c..dc0b29612891 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -142,9 +142,8 @@ LEAF(__r4k_wait) PTR_LA k1, __r4k_wait ori k0, 0x1f /* 32 byte rollback region */ xori k0, 0x1f - bne k0, k1, 9f + bne k0, k1, \handler MTC0 k0, CP0_EPC -9: .set pop .endm diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c index c3372cac6db2..0a7e10b5f9e3 100644 --- a/arch/mips/kernel/mips-r2-to-r6-emul.c +++ b/arch/mips/kernel/mips-r2-to-r6-emul.c @@ -1164,7 +1164,9 @@ fpu_emul: regs->regs[31] = r31; regs->cp0_epc = epc; if (!used_math()) { /* First time FPU user. */ + preempt_disable(); err = init_fpu(); + preempt_enable(); set_used_math(); } lose_fpu(1); /* Save FPU state for the emulator. */ diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 7429ad09fbe3..d2d061520a23 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -605,14 +605,14 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value) return -EOPNOTSUPP; /* Avoid inadvertently triggering emulation */ - if ((value & PR_FP_MODE_FR) && cpu_has_fpu && - !(current_cpu_data.fpu_id & MIPS_FPIR_F64)) + if ((value & PR_FP_MODE_FR) && raw_cpu_has_fpu && + !(raw_current_cpu_data.fpu_id & MIPS_FPIR_F64)) return -EOPNOTSUPP; - if ((value & PR_FP_MODE_FRE) && cpu_has_fpu && !cpu_has_fre) + if ((value & PR_FP_MODE_FRE) && raw_cpu_has_fpu && !cpu_has_fre) return -EOPNOTSUPP; /* FR = 0 not supported in MIPS R6 */ - if (!(value & PR_FP_MODE_FR) && cpu_has_fpu && cpu_has_mips_r6) + if (!(value & PR_FP_MODE_FR) && raw_cpu_has_fpu && cpu_has_mips_r6) return -EOPNOTSUPP; /* Proceed with the mode switch */ diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 36cf8d65c47d..0d57909d9026 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -87,6 +87,13 @@ void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type) int x = boot_mem_map.nr_map; int i; + /* + * If the region reaches the top of the physical address space, adjust + * the size slightly so that (start + size) doesn't overflow + */ + if (start + size - 1 == (phys_addr_t)ULLONG_MAX) + --size; + /* Sanity check */ if (start + size < start) { pr_warn("Trying to add an invalid memory region, skipped\n"); @@ -757,7 +764,6 @@ static void __init arch_mem_init(char **cmdline_p) device_tree_init(); sparse_init(); plat_swiotlb_setup(); - paging_init(); dma_contiguous_reserve(PFN_PHYS(max_low_pfn)); /* Tell bootmem about cma reserved memblock section */ @@ -870,6 +876,7 @@ void __init setup_arch(char **cmdline_p) prefill_possible_map(); cpu_cache_init(); + paging_init(); } unsigned long kernelsp[NR_CPUS]; diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index e9d9fc6c754c..6183ad84cc73 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -513,7 +513,7 @@ static void cps_cpu_die(unsigned int cpu) * in which case the CPC will refuse to power down the core. */ do { - mips_cm_lock_other(core, vpe_id); + mips_cm_lock_other(core, 0); mips_cpc_lock_other(core); stat = read_cpc_co_stat_conf(); stat &= CPC_Cx_STAT_CONF_SEQSTATE_MSK; diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index f95f094f36e4..b0baf48951fa 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -322,6 +322,9 @@ asmlinkage void start_secondary(void) cpumask_set_cpu(cpu, &cpu_coherent_mask); notify_cpu_starting(cpu); + cpumask_set_cpu(cpu, &cpu_callin_map); + synchronise_count_slave(cpu); + set_cpu_online(cpu, true); set_cpu_sibling_map(cpu); @@ -329,10 +332,6 @@ asmlinkage void start_secondary(void) calculate_cpu_foreign_map(); - cpumask_set_cpu(cpu, &cpu_callin_map); - - synchronise_count_slave(cpu); - /* * irq will be enabled in ->smp_finish(), enabling it too early * is dangerous. diff --git a/arch/mips/kernel/uprobes.c b/arch/mips/kernel/uprobes.c index 8452d933a645..4c7c1558944a 100644 --- a/arch/mips/kernel/uprobes.c +++ b/arch/mips/kernel/uprobes.c @@ -157,7 +157,6 @@ bool is_trap_insn(uprobe_opcode_t *insn) int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs) { struct uprobe_task *utask = current->utask; - union mips_instruction insn; /* * Now find the EPC where to resume after the breakpoint has been @@ -168,10 +167,10 @@ int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs) unsigned long epc; epc = regs->cp0_epc; - __compute_return_epc_for_insn(regs, insn); + __compute_return_epc_for_insn(regs, + (union mips_instruction) aup->insn[0]); aup->resume_epc = regs->cp0_epc; } - utask->autask.saved_trap_nr = current->thread.trap_nr; current->thread.trap_nr = UPROBE_TRAP_NR; regs->cp0_epc = current->utask->xol_vaddr; @@ -222,7 +221,7 @@ int arch_uprobe_exception_notify(struct notifier_block *self, return NOTIFY_DONE; switch (val) { - case DIE_BREAK: + case DIE_UPROBE: if (uprobe_pre_sstep_notifier(regs)) return NOTIFY_STOP; break; @@ -257,7 +256,7 @@ unsigned long arch_uretprobe_hijack_return_addr( ra = regs->regs[31]; /* Replace the return address with the trampoline address */ - regs->regs[31] = ra; + regs->regs[31] = trampoline_vaddr; return ra; } @@ -280,24 +279,6 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, return uprobe_write_opcode(mm, vaddr, UPROBE_SWBP_INSN); } -/** - * set_orig_insn - Restore the original instruction. - * @mm: the probed process address space. - * @auprobe: arch specific probepoint information. - * @vaddr: the virtual address to insert the opcode. - * - * For mm @mm, restore the original opcode (opcode) at @vaddr. - * Return 0 (success) or a negative errno. - * - * This overrides the weak version in kernel/events/uprobes.c. - */ -int set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, - unsigned long vaddr) -{ - return uprobe_write_opcode(mm, vaddr, - *(uprobe_opcode_t *)&auprobe->orig_inst[0].word); -} - void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, void *src, unsigned long len) { diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index 9abe447a4b48..f9dbfb14af33 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -39,16 +39,16 @@ static struct vm_special_mapping vdso_vvar_mapping = { static void __init init_vdso_image(struct mips_vdso_image *image) { unsigned long num_pages, i; + unsigned long data_pfn; BUG_ON(!PAGE_ALIGNED(image->data)); BUG_ON(!PAGE_ALIGNED(image->size)); num_pages = image->size / PAGE_SIZE; - for (i = 0; i < num_pages; i++) { - image->mapping.pages[i] = - virt_to_page(image->data + (i * PAGE_SIZE)); - } + data_pfn = __phys_to_pfn(__pa_symbol(image->data)); + for (i = 0; i < num_pages; i++) + image->mapping.pages[i] = pfn_to_page(data_pfn + i); } static int __init init_vdso(void) diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index e788515f766b..4db4c0370859 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -846,6 +846,47 @@ enum emulation_result kvm_mips_emul_tlbr(struct kvm_vcpu *vcpu) return EMULATE_FAIL; } +/** + * kvm_mips_invalidate_guest_tlb() - Indicates a change in guest MMU map. + * @vcpu: VCPU with changed mappings. + * @tlb: TLB entry being removed. + * + * This is called to indicate a single change in guest MMU mappings, so that we + * can arrange TLB flushes on this and other CPUs. + */ +static void kvm_mips_invalidate_guest_tlb(struct kvm_vcpu *vcpu, + struct kvm_mips_tlb *tlb) +{ + int cpu, i; + bool user; + + /* No need to flush for entries which are already invalid */ + if (!((tlb->tlb_lo[0] | tlb->tlb_lo[1]) & ENTRYLO_V)) + return; + /* User address space doesn't need flushing for KSeg2/3 changes */ + user = tlb->tlb_hi < KVM_GUEST_KSEG0; + + preempt_disable(); + + /* + * Probe the shadow host TLB for the entry being overwritten, if one + * matches, invalidate it + */ + kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi); + + /* Invalidate the whole ASID on other CPUs */ + cpu = smp_processor_id(); + for_each_possible_cpu(i) { + if (i == cpu) + continue; + if (user) + vcpu->arch.guest_user_asid[i] = 0; + vcpu->arch.guest_kernel_asid[i] = 0; + } + + preempt_enable(); +} + /* Write Guest TLB Entry @ Index */ enum emulation_result kvm_mips_emul_tlbwi(struct kvm_vcpu *vcpu) { @@ -865,11 +906,8 @@ enum emulation_result kvm_mips_emul_tlbwi(struct kvm_vcpu *vcpu) } tlb = &vcpu->arch.guest_tlb[index]; - /* - * Probe the shadow host TLB for the entry being overwritten, if one - * matches, invalidate it - */ - kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi); + + kvm_mips_invalidate_guest_tlb(vcpu, tlb); tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0); tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0); @@ -898,11 +936,7 @@ enum emulation_result kvm_mips_emul_tlbwr(struct kvm_vcpu *vcpu) tlb = &vcpu->arch.guest_tlb[index]; - /* - * Probe the shadow host TLB for the entry being overwritten, if one - * matches, invalidate it - */ - kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi); + kvm_mips_invalidate_guest_tlb(vcpu, tlb); tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0); tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0); @@ -1026,6 +1060,7 @@ enum emulation_result kvm_mips_emulate_CP0(union mips_instruction inst, enum emulation_result er = EMULATE_DONE; u32 rt, rd, sel; unsigned long curr_pc; + int cpu, i; /* * Update PC and hold onto current PC in case there is @@ -1127,16 +1162,31 @@ enum emulation_result kvm_mips_emulate_CP0(union mips_instruction inst, } else if (rd == MIPS_CP0_TLB_HI && sel == 0) { u32 nasid = vcpu->arch.gprs[rt] & KVM_ENTRYHI_ASID; - if ((KSEGX(vcpu->arch.gprs[rt]) != CKSEG0) && - ((kvm_read_c0_guest_entryhi(cop0) & + if (((kvm_read_c0_guest_entryhi(cop0) & KVM_ENTRYHI_ASID) != nasid)) { trace_kvm_asid_change(vcpu, kvm_read_c0_guest_entryhi(cop0) & KVM_ENTRYHI_ASID, nasid); - /* Blow away the shadow host TLBs */ - kvm_mips_flush_host_tlb(1); + /* + * Regenerate/invalidate kernel MMU + * context. + * The user MMU context will be + * regenerated lazily on re-entry to + * guest user if the guest ASID actually + * changes. + */ + preempt_disable(); + cpu = smp_processor_id(); + kvm_get_new_mmu_context(&vcpu->arch.guest_kernel_mm, + cpu, vcpu); + vcpu->arch.guest_kernel_asid[cpu] = + vcpu->arch.guest_kernel_mm.context.asid[cpu]; + for_each_possible_cpu(i) + if (i != cpu) + vcpu->arch.guest_kernel_asid[i] = 0; + preempt_enable(); } kvm_write_c0_guest_entryhi(cop0, vcpu->arch.gprs[rt]); diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index a6ea084b4d9d..ce961495b5e1 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -140,6 +140,16 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return 0; } +bool kvm_arch_has_vcpu_debugfs(void) +{ + return false; +} + +int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +{ + return 0; +} + void kvm_mips_free_vcpus(struct kvm *kvm) { unsigned int i; @@ -411,6 +421,31 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, return -ENOIOCTLCMD; } +/* Must be called with preemption disabled, just before entering guest */ +static void kvm_mips_check_asids(struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + int cpu = smp_processor_id(); + unsigned int gasid; + + /* + * Lazy host ASID regeneration for guest user mode. + * If the guest ASID has changed since the last guest usermode + * execution, regenerate the host ASID so as to invalidate stale TLB + * entries. + */ + if (!KVM_GUEST_KERNEL_MODE(vcpu)) { + gasid = kvm_read_c0_guest_entryhi(cop0) & KVM_ENTRYHI_ASID; + if (gasid != vcpu->arch.last_user_gasid) { + kvm_get_new_mmu_context(&vcpu->arch.guest_user_mm, cpu, + vcpu); + vcpu->arch.guest_user_asid[cpu] = + vcpu->arch.guest_user_mm.context.asid[cpu]; + vcpu->arch.last_user_gasid = gasid; + } + } +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) { int r = 0; @@ -438,6 +473,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) htw_stop(); trace_kvm_enter(vcpu); + + kvm_mips_check_asids(vcpu); + r = vcpu->arch.vcpu_run(run, vcpu); trace_kvm_out(vcpu); @@ -1551,6 +1589,8 @@ skip_emul: if (ret == RESUME_GUEST) { trace_kvm_reenter(vcpu); + kvm_mips_check_asids(vcpu); + /* * If FPU / MSA are enabled (i.e. the guest's FPU / MSA context * is live), restore FCR31 / MSACSR. diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 121008c0fcc9..03883ba806e2 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -250,15 +250,27 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_get_new_mmu_context(&vcpu->arch.guest_kernel_mm, cpu, vcpu); vcpu->arch.guest_kernel_asid[cpu] = vcpu->arch.guest_kernel_mm.context.asid[cpu]; + newasid++; + + kvm_debug("[%d]: cpu_context: %#lx\n", cpu, + cpu_context(cpu, current->mm)); + kvm_debug("[%d]: Allocated new ASID for Guest Kernel: %#x\n", + cpu, vcpu->arch.guest_kernel_asid[cpu]); + } + + if ((vcpu->arch.guest_user_asid[cpu] ^ asid_cache(cpu)) & + asid_version_mask(cpu)) { + u32 gasid = kvm_read_c0_guest_entryhi(vcpu->arch.cop0) & + KVM_ENTRYHI_ASID; + kvm_get_new_mmu_context(&vcpu->arch.guest_user_mm, cpu, vcpu); vcpu->arch.guest_user_asid[cpu] = vcpu->arch.guest_user_mm.context.asid[cpu]; + vcpu->arch.last_user_gasid = gasid; newasid++; kvm_debug("[%d]: cpu_context: %#lx\n", cpu, cpu_context(cpu, current->mm)); - kvm_debug("[%d]: Allocated new ASID for Guest Kernel: %#x\n", - cpu, vcpu->arch.guest_kernel_asid[cpu]); kvm_debug("[%d]: Allocated new ASID for Guest User: %#x\n", cpu, vcpu->arch.guest_user_asid[cpu]); } diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c index 091553942bcb..3a5484f9aa50 100644 --- a/arch/mips/kvm/trap_emul.c +++ b/arch/mips/kvm/trap_emul.c @@ -175,6 +175,24 @@ static int kvm_trap_emul_handle_tlb_miss(struct kvm_vcpu *vcpu, bool store) run->exit_reason = KVM_EXIT_INTERNAL_ERROR; ret = RESUME_HOST; } + } else if (KVM_GUEST_KERNEL_MODE(vcpu) + && (KSEGX(badvaddr) == CKSEG0 || KSEGX(badvaddr) == CKSEG1)) { + /* + * With EVA we may get a TLB exception instead of an address + * error when the guest performs MMIO to KSeg1 addresses. + */ + kvm_debug("Emulate %s MMIO space\n", + store ? "Store to" : "Load from"); + er = kvm_mips_emulate_inst(cause, opc, run, vcpu); + if (er == EMULATE_FAIL) { + kvm_err("Emulate %s MMIO space failed\n", + store ? "Store to" : "Load from"); + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + } else { + run->exit_reason = KVM_EXIT_MMIO; + ret = RESUME_HOST; + } } else { kvm_err("Illegal TLB %s fault address , cause %#x, PC: %p, BadVaddr: %#lx\n", store ? "ST" : "LD", cause, opc, badvaddr); diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c index 2fec6f753a35..99aab9f85904 100644 --- a/arch/mips/loongson64/loongson-3/smp.c +++ b/arch/mips/loongson64/loongson-3/smp.c @@ -677,7 +677,7 @@ void play_dead(void) play_dead_at_ckseg1(state_addr); } -void loongson3_disable_clock(int cpu) +static int loongson3_disable_clock(unsigned int cpu) { uint64_t core_id = cpu_data[cpu].core; uint64_t package_id = cpu_data[cpu].package; @@ -688,9 +688,10 @@ void loongson3_disable_clock(int cpu) if (!(loongson_sysconf.workarounds & WORKAROUND_CPUHOTPLUG)) LOONGSON_FREQCTRL(package_id) &= ~(1 << (core_id * 4 + 3)); } + return 0; } -void loongson3_enable_clock(int cpu) +static int loongson3_enable_clock(unsigned int cpu) { uint64_t core_id = cpu_data[cpu].core; uint64_t package_id = cpu_data[cpu].package; @@ -701,34 +702,15 @@ void loongson3_enable_clock(int cpu) if (!(loongson_sysconf.workarounds & WORKAROUND_CPUHOTPLUG)) LOONGSON_FREQCTRL(package_id) |= 1 << (core_id * 4 + 3); } -} - -#define CPU_POST_DEAD_FROZEN (CPU_POST_DEAD | CPU_TASKS_FROZEN) -static int loongson3_cpu_callback(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - unsigned int cpu = (unsigned long)hcpu; - - switch (action) { - case CPU_POST_DEAD: - case CPU_POST_DEAD_FROZEN: - pr_info("Disable clock for CPU#%d\n", cpu); - loongson3_disable_clock(cpu); - break; - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - pr_info("Enable clock for CPU#%d\n", cpu); - loongson3_enable_clock(cpu); - break; - } - - return NOTIFY_OK; + return 0; } static int register_loongson3_notifier(void) { - hotcpu_notifier(loongson3_cpu_callback, 0); - return 0; + return cpuhp_setup_state_nocalls(CPUHP_MIPS_SOC_PREPARE, + "mips/loongson:prepare", + loongson3_enable_clock, + loongson3_disable_clock); } early_initcall(register_loongson3_notifier); diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c index 72a4642eee2c..4a094f7acb3d 100644 --- a/arch/mips/math-emu/dsemul.c +++ b/arch/mips/math-emu/dsemul.c @@ -298,5 +298,6 @@ bool do_dsemulret(struct pt_regs *xcp) /* Set EPC to return to post-branch instruction */ xcp->cp0_epc = current->thread.bd_emu_cont_pc; pr_debug("dsemulret to 0x%08lx\n", xcp->cp0_epc); + MIPS_FPU_EMU_INC_STATS(ds_emul); return true; } diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index cd72805b64a7..fa7d8d3790bf 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -800,7 +800,7 @@ static void r4k_flush_icache_range(unsigned long start, unsigned long end) * If address-based cache ops don't require an SMP call, then * use them exclusively for small flushes. */ - size = start - end; + size = end - start; cache_size = icache_size; if (!cpu_has_ic_fills_f_dc) { size *= 2; diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index a5509e7dcad2..72f7478ee068 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -261,7 +261,6 @@ unsigned __weak platform_maar_init(unsigned num_pairs) { struct maar_config cfg[BOOT_MEM_MAP_MAX]; unsigned i, num_configured, num_cfg = 0; - phys_addr_t skip; for (i = 0; i < boot_mem_map.nr_map; i++) { switch (boot_mem_map.map[i].type) { @@ -272,14 +271,14 @@ unsigned __weak platform_maar_init(unsigned num_pairs) continue; } - skip = 0x10000 - (boot_mem_map.map[i].addr & 0xffff); - + /* Round lower up */ cfg[num_cfg].lower = boot_mem_map.map[i].addr; - cfg[num_cfg].lower += skip; + cfg[num_cfg].lower = (cfg[num_cfg].lower + 0xffff) & ~0xffff; - cfg[num_cfg].upper = cfg[num_cfg].lower; - cfg[num_cfg].upper += boot_mem_map.map[i].size - 1; - cfg[num_cfg].upper -= skip; + /* Round upper down */ + cfg[num_cfg].upper = boot_mem_map.map[i].addr + + boot_mem_map.map[i].size; + cfg[num_cfg].upper = (cfg[num_cfg].upper & ~0xffff) - 1; cfg[num_cfg].attrs = MIPS_MAAR_S; num_cfg++; @@ -441,6 +440,9 @@ static inline void mem_init_free_highmem(void) #ifdef CONFIG_HIGHMEM unsigned long tmp; + if (cpu_has_dc_aliases) + return; + for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) { struct page *page = pfn_to_page(tmp); diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c index ec5b21678fad..7e7364b0501e 100644 --- a/arch/mips/mti-malta/malta-setup.c +++ b/arch/mips/mti-malta/malta-setup.c @@ -39,6 +39,9 @@ #include <linux/console.h> #endif +#define ROCIT_CONFIG_GEN0 0x1f403000 +#define ROCIT_CONFIG_GEN0_PCI_IOCU BIT(7) + extern void malta_be_init(void); extern int malta_be_handler(struct pt_regs *regs, int is_fixup); @@ -107,6 +110,8 @@ static void __init fd_activate(void) static int __init plat_enable_iocoherency(void) { int supported = 0; + u32 cfg; + if (mips_revision_sconid == MIPS_REVISION_SCON_BONITO) { if (BONITO_PCICACHECTRL & BONITO_PCICACHECTRL_CPUCOH_PRES) { BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_CPUCOH_EN; @@ -129,7 +134,8 @@ static int __init plat_enable_iocoherency(void) } else if (mips_cm_numiocu() != 0) { /* Nothing special needs to be done to enable coherency */ pr_info("CMP IOCU detected\n"); - if ((*(unsigned int *)0xbf403000 & 0x81) != 0x81) { + cfg = __raw_readl((u32 *)CKSEG1ADDR(ROCIT_CONFIG_GEN0)); + if (!(cfg & ROCIT_CONFIG_GEN0_PCI_IOCU)) { pr_crit("IOCU OPERATION DISABLED BY SWITCH - DEFAULTING TO SW IO COHERENCY\n"); return 0; } diff --git a/arch/mn10300/include/asm/uaccess.h b/arch/mn10300/include/asm/uaccess.h index 20f7bf6de384..d012e877a95a 100644 --- a/arch/mn10300/include/asm/uaccess.h +++ b/arch/mn10300/include/asm/uaccess.h @@ -166,6 +166,7 @@ struct __large_struct { unsigned long buf[100]; }; "2:\n" \ " .section .fixup,\"ax\"\n" \ "3:\n\t" \ + " mov 0,%1\n" \ " mov %3,%0\n" \ " jmp 2b\n" \ " .previous\n" \ diff --git a/arch/mn10300/lib/usercopy.c b/arch/mn10300/lib/usercopy.c index 7826e6c364e7..ce8899e5e171 100644 --- a/arch/mn10300/lib/usercopy.c +++ b/arch/mn10300/lib/usercopy.c @@ -9,7 +9,7 @@ * as published by the Free Software Foundation; either version * 2 of the Licence, or (at your option) any later version. */ -#include <asm/uaccess.h> +#include <linux/uaccess.h> unsigned long __generic_copy_to_user(void *to, const void *from, unsigned long n) @@ -24,6 +24,8 @@ __generic_copy_from_user(void *to, const void *from, unsigned long n) { if (access_ok(VERIFY_READ, from, n)) __copy_user_zeroing(to, from, n); + else + memset(to, 0, n); return n; } diff --git a/arch/nios2/boot/dts/10m50_devboard.dts b/arch/nios2/boot/dts/10m50_devboard.dts index 3e411c644824..f362b2224ee7 100755 --- a/arch/nios2/boot/dts/10m50_devboard.dts +++ b/arch/nios2/boot/dts/10m50_devboard.dts @@ -83,6 +83,7 @@ fifo-size = <32>; reg-io-width = <4>; reg-shift = <2>; + tx-threshold = <16>; }; sysid: sysid@18001528 { diff --git a/arch/nios2/include/asm/uaccess.h b/arch/nios2/include/asm/uaccess.h index caa51ff85a3c..0ab82324c817 100644 --- a/arch/nios2/include/asm/uaccess.h +++ b/arch/nios2/include/asm/uaccess.h @@ -102,9 +102,12 @@ extern long __copy_to_user(void __user *to, const void *from, unsigned long n); static inline long copy_from_user(void *to, const void __user *from, unsigned long n) { - if (!access_ok(VERIFY_READ, from, n)) - return n; - return __copy_from_user(to, from, n); + unsigned long res = n; + if (access_ok(VERIFY_READ, from, n)) + res = __copy_from_user(to, from, n); + if (unlikely(res)) + memset(to + (n - res), 0, res); + return res; } static inline long copy_to_user(void __user *to, const void *from, @@ -139,7 +142,7 @@ extern long strnlen_user(const char __user *s, long n); #define __get_user_unknown(val, size, ptr, err) do { \ err = 0; \ - if (copy_from_user(&(val), ptr, size)) { \ + if (__copy_from_user(&(val), ptr, size)) { \ err = -EFAULT; \ } \ } while (0) @@ -166,7 +169,7 @@ do { \ ({ \ long __gu_err = -EFAULT; \ const __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \ - unsigned long __gu_val; \ + unsigned long __gu_val = 0; \ __get_user_common(__gu_val, sizeof(*(ptr)), __gu_ptr, __gu_err);\ (x) = (__force __typeof__(x))__gu_val; \ __gu_err; \ diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h index a6bd07ca3d6c..5cc6b4f1b795 100644 --- a/arch/openrisc/include/asm/uaccess.h +++ b/arch/openrisc/include/asm/uaccess.h @@ -273,28 +273,20 @@ __copy_tofrom_user(void *to, const void *from, unsigned long size); static inline unsigned long copy_from_user(void *to, const void *from, unsigned long n) { - unsigned long over; - - if (access_ok(VERIFY_READ, from, n)) - return __copy_tofrom_user(to, from, n); - if ((unsigned long)from < TASK_SIZE) { - over = (unsigned long)from + n - TASK_SIZE; - return __copy_tofrom_user(to, from, n - over) + over; - } - return n; + unsigned long res = n; + + if (likely(access_ok(VERIFY_READ, from, n))) + res = __copy_tofrom_user(to, from, n); + if (unlikely(res)) + memset(to + (n - res), 0, res); + return res; } static inline unsigned long copy_to_user(void *to, const void *from, unsigned long n) { - unsigned long over; - - if (access_ok(VERIFY_WRITE, to, n)) - return __copy_tofrom_user(to, from, n); - if ((unsigned long)to < TASK_SIZE) { - over = (unsigned long)to + n - TASK_SIZE; - return __copy_tofrom_user(to, from, n - over) + over; - } + if (likely(access_ok(VERIFY_WRITE, to, n))) + n = __copy_tofrom_user(to, from, n); return n; } @@ -303,13 +295,8 @@ extern unsigned long __clear_user(void *addr, unsigned long size); static inline __must_check unsigned long clear_user(void *addr, unsigned long size) { - - if (access_ok(VERIFY_WRITE, addr, size)) - return __clear_user(addr, size); - if ((unsigned long)addr < TASK_SIZE) { - unsigned long over = (unsigned long)addr + size - TASK_SIZE; - return __clear_user(addr, size - over) + over; - } + if (likely(access_ok(VERIFY_WRITE, addr, size))) + size = __clear_user(addr, size); return size; } diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index cd8778103165..2a0339a68894 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -1,6 +1,5 @@ config PARISC def_bool y - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_MIGHT_HAVE_PC_PARPORT select HAVE_IDE select HAVE_OPROFILE @@ -11,12 +10,13 @@ config PARISC select RTC_CLASS select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE + select HAVE_MEMBLOCK + select NO_BOOTMEM select BUG select BUILDTIME_EXTABLE_SORT select HAVE_PERF_EVENTS select GENERIC_ATOMIC64 if !64BIT select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select BROKEN_RODATA select GENERIC_IRQ_PROBE select GENERIC_PCI_IOMAP select ARCH_HAVE_NMI_SAFE_CMPXCHG @@ -25,6 +25,7 @@ config PARISC select SYSCTL_ARCH_UNALIGN_ALLOW select SYSCTL_EXCEPTION_TRACE select HAVE_MOD_ARCH_SPECIFIC + select HAVE_ARCH_HARDENED_USERCOPY select VIRT_TO_BUS select MODULES_USE_ELF_RELA select CLONE_BACKWARDS diff --git a/arch/parisc/configs/c8000_defconfig b/arch/parisc/configs/c8000_defconfig index 1a8f6f95689e..f6a4c016304b 100644 --- a/arch/parisc/configs/c8000_defconfig +++ b/arch/parisc/configs/c8000_defconfig @@ -245,7 +245,6 @@ CONFIG_DEBUG_RT_MUTEXES=y CONFIG_PROVE_RCU_DELAY=y CONFIG_DEBUG_BLOCK_EXT_DEVT=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_KEYS=y # CONFIG_CRYPTO_HW is not set CONFIG_FONTS=y diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index 7e0792658952..c564e6e1fa23 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -291,7 +291,6 @@ CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y # CONFIG_SCHED_DEBUG is not set CONFIG_TIMER_STATS=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m diff --git a/arch/parisc/include/asm/dwarf.h b/arch/parisc/include/asm/dwarf.h new file mode 100644 index 000000000000..8fe7d6b2cc42 --- /dev/null +++ b/arch/parisc/include/asm/dwarf.h @@ -0,0 +1,23 @@ +/* + * Copyright (C) 2016 Helge Deller <deller@gmx.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _ASM_PARISC_DWARF_H +#define _ASM_PARISC_DWARF_H + +#ifdef __ASSEMBLY__ + +#define CFI_STARTPROC .cfi_startproc +#define CFI_ENDPROC .cfi_endproc +#define CFI_DEF_CFA .cfi_def_cfa +#define CFI_REGISTER .cfi_register +#define CFI_REL_OFFSET .cfi_rel_offset +#define CFI_UNDEFINED .cfi_undefined + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_PARISC_DWARF_H */ diff --git a/arch/parisc/include/asm/linkage.h b/arch/parisc/include/asm/linkage.h index 0b19a7242d0c..67e6b433d399 100644 --- a/arch/parisc/include/asm/linkage.h +++ b/arch/parisc/include/asm/linkage.h @@ -1,6 +1,8 @@ #ifndef __ASM_PARISC_LINKAGE_H #define __ASM_PARISC_LINKAGE_H +#include <asm/dwarf.h> + #ifndef __ALIGN #define __ALIGN .align 4 #define __ALIGN_STR ".align 4" @@ -10,6 +12,8 @@ * In parisc assembly a semicolon marks a comment while a * exclamation mark is used to separate independent lines. */ +#define ASM_NL ! + #ifdef __ASSEMBLY__ #define ENTRY(name) \ @@ -26,6 +30,14 @@ name: END(name) #endif +#define ENTRY_CFI(name) \ + ENTRY(name) ASM_NL\ + CFI_STARTPROC + +#define ENDPROC_CFI(name) \ + ENDPROC(name) ASM_NL\ + CFI_ENDPROC + #endif /* __ASSEMBLY__ */ #endif /* __ASM_PARISC_LINKAGE_H */ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 291cee28ccb6..e44bdb9078a5 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -83,7 +83,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e)) /* This is the size of the initially mapped kernel memory */ -#ifdef CONFIG_64BIT +#if defined(CONFIG_64BIT) || defined(CONFIG_SMP) #define KERNEL_INITIAL_ORDER 25 /* 1<<25 = 32MB */ #else #define KERNEL_INITIAL_ORDER 24 /* 1<<24 = 16MB */ diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 0f59fd9ca205..9a2aee1b90fc 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -10,6 +10,8 @@ #include <asm-generic/uaccess-unaligned.h> #include <linux/bug.h> +#include <linux/string.h> +#include <linux/thread_info.h> #define VERIFY_READ 0 #define VERIFY_WRITE 1 @@ -200,35 +202,58 @@ extern long lstrnlen_user(const char __user *, long); #define clear_user lclear_user #define __clear_user lclear_user -unsigned long copy_to_user(void __user *dst, const void *src, unsigned long len); -#define __copy_to_user copy_to_user -unsigned long __copy_from_user(void *dst, const void __user *src, unsigned long len); -unsigned long copy_in_user(void __user *dst, const void __user *src, unsigned long len); +unsigned long __must_check __copy_to_user(void __user *dst, const void *src, + unsigned long len); +unsigned long __must_check __copy_from_user(void *dst, const void __user *src, + unsigned long len); +unsigned long copy_in_user(void __user *dst, const void __user *src, + unsigned long len); #define __copy_in_user copy_in_user #define __copy_to_user_inatomic __copy_to_user #define __copy_from_user_inatomic __copy_from_user -extern void copy_from_user_overflow(void) -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS - __compiletime_error("copy_from_user() buffer size is not provably correct") -#else - __compiletime_warning("copy_from_user() buffer size is not provably correct") -#endif -; +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} + +static __always_inline unsigned long __must_check +copy_from_user(void *to, const void __user *from, unsigned long n) +{ + int sz = __compiletime_object_size(to); + unsigned long ret = n; + + if (likely(sz < 0 || sz >= n)) { + check_object_size(to, n, false); + ret = __copy_from_user(to, from, n); + } else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); + else + __bad_copy_user(); + + if (unlikely(ret)) + memset(to + (n - ret), 0, ret); + + return ret; +} -static inline unsigned long __must_check copy_from_user(void *to, - const void __user *from, - unsigned long n) +static __always_inline unsigned long __must_check +copy_to_user(void __user *to, const void *from, unsigned long n) { - int sz = __compiletime_object_size(to); - int ret = -EFAULT; + int sz = __compiletime_object_size(from); - if (likely(sz == -1 || !__builtin_constant_p(n) || sz >= n)) - ret = __copy_from_user(to, from, n); - else - copy_from_user_overflow(); + if (likely(sz < 0 || sz >= n)) { + check_object_size(from, n, true); + n = __copy_to_user(to, from, n); + } else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); + else + __bad_copy_user(); - return ret; + return n; } struct pt_regs; diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index baa3d9d6e971..4fcff2dcc9c3 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -766,7 +766,7 @@ ENTRY(end_fault_vector) * copy_thread moved args into task save area. */ -ENTRY(ret_from_kernel_thread) +ENTRY_CFI(ret_from_kernel_thread) /* Call schedule_tail first though */ BL schedule_tail, %r2 @@ -782,7 +782,7 @@ ENTRY(ret_from_kernel_thread) copy %r31, %r2 b finish_child_return nop -ENDPROC(ret_from_kernel_thread) +ENDPROC_CFI(ret_from_kernel_thread) /* @@ -790,7 +790,7 @@ ENDPROC(ret_from_kernel_thread) * struct task_struct *next) * * switch kernel stacks and return prev */ -ENTRY(_switch_to) +ENTRY_CFI(_switch_to) STREG %r2, -RP_OFFSET(%r30) callee_save_float @@ -815,7 +815,7 @@ _switch_to_ret: LDREG -RP_OFFSET(%r30), %r2 bv %r0(%r2) copy %r26, %r28 -ENDPROC(_switch_to) +ENDPROC_CFI(_switch_to) /* * Common rfi return path for interruptions, kernel execve, and @@ -833,7 +833,7 @@ ENDPROC(_switch_to) .align PAGE_SIZE -ENTRY(syscall_exit_rfi) +ENTRY_CFI(syscall_exit_rfi) mfctl %cr30,%r16 LDREG TI_TASK(%r16), %r16 /* thread_info -> task_struct */ ldo TASK_REGS(%r16),%r16 @@ -1037,12 +1037,12 @@ intr_extint: b do_cpu_irq_mask ldo R%intr_return(%r2), %r2 /* return to intr_return, not here */ -ENDPROC(syscall_exit_rfi) +ENDPROC_CFI(syscall_exit_rfi) /* Generic interruptions (illegal insn, unaligned, page fault, etc) */ -ENTRY(intr_save) /* for os_hpmc */ +ENTRY_CFI(intr_save) /* for os_hpmc */ mfsp %sr7,%r16 cmpib,COND(=),n 0,%r16,1f get_stack_use_cr30 @@ -1117,7 +1117,7 @@ skip_save_ior: b handle_interruption ldo R%intr_check_sig(%r2), %r2 -ENDPROC(intr_save) +ENDPROC_CFI(intr_save) /* @@ -1720,7 +1720,7 @@ dtlb_fault: .endm .macro fork_like name -ENTRY(sys_\name\()_wrapper) +ENTRY_CFI(sys_\name\()_wrapper) LDREG TI_TASK-THREAD_SZ_ALGN-FRAME_SIZE(%r30), %r1 ldo TASK_REGS(%r1),%r1 reg_save %r1 @@ -1728,7 +1728,7 @@ ENTRY(sys_\name\()_wrapper) ldil L%sys_\name, %r31 be R%sys_\name(%sr4,%r31) STREG %r28, PT_CR27(%r1) -ENDPROC(sys_\name\()_wrapper) +ENDPROC_CFI(sys_\name\()_wrapper) .endm fork_like clone @@ -1736,7 +1736,7 @@ fork_like fork fork_like vfork /* Set the return value for the child */ -ENTRY(child_return) +ENTRY_CFI(child_return) BL schedule_tail, %r2 nop finish_child_return: @@ -1748,9 +1748,9 @@ finish_child_return: reg_restore %r1 b syscall_exit copy %r0,%r28 -ENDPROC(child_return) +ENDPROC_CFI(child_return) -ENTRY(sys_rt_sigreturn_wrapper) +ENTRY_CFI(sys_rt_sigreturn_wrapper) LDREG TI_TASK-THREAD_SZ_ALGN-FRAME_SIZE(%r30),%r26 ldo TASK_REGS(%r26),%r26 /* get pt regs */ /* Don't save regs, we are going to restore them from sigcontext. */ @@ -1778,9 +1778,9 @@ ENTRY(sys_rt_sigreturn_wrapper) */ bv %r0(%r2) LDREG PT_GR28(%r1),%r28 /* reload original r28 for syscall_exit */ -ENDPROC(sys_rt_sigreturn_wrapper) +ENDPROC_CFI(sys_rt_sigreturn_wrapper) -ENTRY(syscall_exit) +ENTRY_CFI(syscall_exit) /* NOTE: Not all syscalls exit this way. rt_sigreturn will exit * via syscall_exit_rfi if the signal was received while the process * was running. @@ -1979,7 +1979,7 @@ syscall_do_resched: #else nop #endif -ENDPROC(syscall_exit) +ENDPROC_CFI(syscall_exit) #ifdef CONFIG_FUNCTION_TRACER @@ -2023,7 +2023,7 @@ ENDPROC(mcount) .align 8 .globl return_to_handler .type return_to_handler, @function -ENTRY(return_to_handler) +ENTRY_CFI(return_to_handler) .proc .callinfo caller,frame=FRAME_SIZE .entry @@ -2067,7 +2067,7 @@ parisc_return_to_handler: LDREGM -FRAME_SIZE(%sp),%r3 .exit .procend -ENDPROC(return_to_handler) +ENDPROC_CFI(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ @@ -2076,7 +2076,7 @@ ENDPROC(return_to_handler) #ifdef CONFIG_IRQSTACKS /* void call_on_stack(unsigned long param1, void *func, unsigned long new_stack) */ -ENTRY(call_on_stack) +ENTRY_CFI(call_on_stack) copy %sp, %r1 /* Regarding the HPPA calling conventions for function pointers, @@ -2112,10 +2112,10 @@ ENTRY(call_on_stack) bv (%rp) LDREG -68(%sp), %sp # endif /* CONFIG_64BIT */ -ENDPROC(call_on_stack) +ENDPROC_CFI(call_on_stack) #endif /* CONFIG_IRQSTACKS */ -get_register: +ENTRY_CFI(get_register) /* * get_register is used by the non access tlb miss handlers to * copy the value of the general register specified in r8 into @@ -2192,9 +2192,10 @@ get_register: copy %r30,%r1 bv %r0(%r25) /* r31 */ copy %r31,%r1 +ENDPROC_CFI(get_register) -set_register: +ENTRY_CFI(set_register) /* * set_register is used by the non access tlb miss handlers to * copy the value of r1 into the general register specified in @@ -2266,4 +2267,5 @@ set_register: copy %r1,%r30 bv %r0(%r25) /* r31 */ copy %r1,%r31 +ENDPROC_CFI(set_register) diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index a828a0adf52c..5a5506a35395 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -48,7 +48,7 @@ static void __hot prepare_ftrace_return(unsigned long *parent, return; if (ftrace_push_return_trace(old, self_addr, &trace.depth, - 0 ) == -EBUSY) + 0, NULL) == -EBUSY) return; /* activate parisc_return_to_handler() as return point */ diff --git a/arch/parisc/kernel/hpmc.S b/arch/parisc/kernel/hpmc.S index e158b6fbf1b4..0fbd0a0e1cda 100644 --- a/arch/parisc/kernel/hpmc.S +++ b/arch/parisc/kernel/hpmc.S @@ -41,12 +41,12 @@ */ .level 1.1 - .data #include <asm/assembly.h> #include <asm/pdc.h> #include <linux/linkage.h> +#include <linux/init.h> /* * stack for os_hpmc, the HPMC handler. @@ -55,22 +55,26 @@ * IODC requires 7K byte stack. That leaves 1K byte for os_hpmc. */ + __PAGE_ALIGNED_BSS .align 4096 hpmc_stack: .block 16384 #define HPMC_IODC_BUF_SIZE 0x8000 + __PAGE_ALIGNED_BSS .align 4096 hpmc_iodc_buf: .block HPMC_IODC_BUF_SIZE + .section .bss .align 8 hpmc_raddr: .block 128 #define HPMC_PIM_DATA_SIZE 896 /* Enough to hold all architected 2.0 state */ + .section .bss .align 8 ENTRY(hpmc_pim_data) .block HPMC_PIM_DATA_SIZE @@ -79,7 +83,7 @@ END(hpmc_pim_data) .text .import intr_save, code -ENTRY(os_hpmc) +ENTRY_CFI(os_hpmc) .os_hpmc: /* @@ -295,11 +299,11 @@ os_hpmc_6: b . nop -ENDPROC(os_hpmc) +ENDPROC_CFI(os_hpmc) .os_hpmc_end: - nop -.data -.align 4 + + + __INITRODATA .export os_hpmc_size os_hpmc_size: .word .os_hpmc_end-.os_hpmc diff --git a/arch/parisc/kernel/inventory.c b/arch/parisc/kernel/inventory.c index f0b6722fc706..545f9d2fe711 100644 --- a/arch/parisc/kernel/inventory.c +++ b/arch/parisc/kernel/inventory.c @@ -506,7 +506,7 @@ add_system_map_addresses(struct parisc_device *dev, int num_addrs, long status; struct pdc_system_map_addr_info addr_result; - dev->addr = kmalloc(num_addrs * sizeof(unsigned long), GFP_KERNEL); + dev->addr = kmalloc_array(num_addrs, sizeof(*dev->addr), GFP_KERNEL); if(!dev->addr) { printk(KERN_ERR "%s %s(): memory allocation failure\n", __FILE__, __func__); diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index b743a80eaba0..985e06da37f5 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -41,7 +41,7 @@ .text .align 128 -ENTRY(flush_tlb_all_local) +ENTRY_CFI(flush_tlb_all_local) .proc .callinfo NO_CALLS .entry @@ -190,11 +190,11 @@ fdtdone: .exit .procend -ENDPROC(flush_tlb_all_local) +ENDPROC_CFI(flush_tlb_all_local) .import cache_info,data -ENTRY(flush_instruction_cache_local) +ENTRY_CFI(flush_instruction_cache_local) .proc .callinfo NO_CALLS .entry @@ -257,11 +257,11 @@ fisync: .exit .procend -ENDPROC(flush_instruction_cache_local) +ENDPROC_CFI(flush_instruction_cache_local) .import cache_info, data -ENTRY(flush_data_cache_local) +ENTRY_CFI(flush_data_cache_local) .proc .callinfo NO_CALLS .entry @@ -325,7 +325,7 @@ fdsync: .exit .procend -ENDPROC(flush_data_cache_local) +ENDPROC_CFI(flush_data_cache_local) .align 16 @@ -356,7 +356,7 @@ ENDPROC(flush_data_cache_local) /* Clear page using kernel mapping. */ -ENTRY(clear_page_asm) +ENTRY_CFI(clear_page_asm) .proc .callinfo NO_CALLS .entry @@ -422,11 +422,11 @@ ENTRY(clear_page_asm) .exit .procend -ENDPROC(clear_page_asm) +ENDPROC_CFI(clear_page_asm) /* Copy page using kernel mapping. */ -ENTRY(copy_page_asm) +ENTRY_CFI(copy_page_asm) .proc .callinfo NO_CALLS .entry @@ -540,7 +540,7 @@ ENTRY(copy_page_asm) .exit .procend -ENDPROC(copy_page_asm) +ENDPROC_CFI(copy_page_asm) /* * NOTE: Code in clear_user_page has a hard coded dependency on the @@ -573,11 +573,17 @@ ENDPROC(copy_page_asm) .endm /* - * We can't do this since copy_user_page is used to bring in - * file data that might have instructions. Since the data would - * then need to be flushed out so the i-fetch can see it, it - * makes more sense to just copy through the kernel translation - * and flush it. + * copy_user_page_asm() performs a page copy using mappings + * equivalent to the user page mappings. It can be used to + * implement copy_user_page() but unfortunately both the `from' + * and `to' pages need to be flushed through mappings equivalent + * to the user mappings after the copy because the kernel accesses + * the `from' page through the kmap kernel mapping and the `to' + * page needs to be flushed since code can be copied. As a + * result, this implementation is less efficient than the simpler + * copy using the kernel mapping. It only needs the `from' page + * to flushed via the user mapping. The kunmap routines handle + * the flushes needed for the kernel mapping. * * I'm still keeping this around because it may be possible to * use it if more information is passed into copy_user_page(). @@ -586,7 +592,7 @@ ENDPROC(copy_page_asm) * */ -ENTRY(copy_user_page_asm) +ENTRY_CFI(copy_user_page_asm) .proc .callinfo NO_CALLS .entry @@ -742,9 +748,9 @@ ENTRY(copy_user_page_asm) .exit .procend -ENDPROC(copy_user_page_asm) +ENDPROC_CFI(copy_user_page_asm) -ENTRY(clear_user_page_asm) +ENTRY_CFI(clear_user_page_asm) .proc .callinfo NO_CALLS .entry @@ -828,9 +834,9 @@ ENTRY(clear_user_page_asm) .exit .procend -ENDPROC(clear_user_page_asm) +ENDPROC_CFI(clear_user_page_asm) -ENTRY(flush_dcache_page_asm) +ENTRY_CFI(flush_dcache_page_asm) .proc .callinfo NO_CALLS .entry @@ -904,9 +910,9 @@ ENTRY(flush_dcache_page_asm) .exit .procend -ENDPROC(flush_dcache_page_asm) +ENDPROC_CFI(flush_dcache_page_asm) -ENTRY(flush_icache_page_asm) +ENTRY_CFI(flush_icache_page_asm) .proc .callinfo NO_CALLS .entry @@ -982,9 +988,9 @@ ENTRY(flush_icache_page_asm) .exit .procend -ENDPROC(flush_icache_page_asm) +ENDPROC_CFI(flush_icache_page_asm) -ENTRY(flush_kernel_dcache_page_asm) +ENTRY_CFI(flush_kernel_dcache_page_asm) .proc .callinfo NO_CALLS .entry @@ -1025,9 +1031,9 @@ ENTRY(flush_kernel_dcache_page_asm) .exit .procend -ENDPROC(flush_kernel_dcache_page_asm) +ENDPROC_CFI(flush_kernel_dcache_page_asm) -ENTRY(purge_kernel_dcache_page_asm) +ENTRY_CFI(purge_kernel_dcache_page_asm) .proc .callinfo NO_CALLS .entry @@ -1067,9 +1073,9 @@ ENTRY(purge_kernel_dcache_page_asm) .exit .procend -ENDPROC(purge_kernel_dcache_page_asm) +ENDPROC_CFI(purge_kernel_dcache_page_asm) -ENTRY(flush_user_dcache_range_asm) +ENTRY_CFI(flush_user_dcache_range_asm) .proc .callinfo NO_CALLS .entry @@ -1088,9 +1094,9 @@ ENTRY(flush_user_dcache_range_asm) .exit .procend -ENDPROC(flush_user_dcache_range_asm) +ENDPROC_CFI(flush_user_dcache_range_asm) -ENTRY(flush_kernel_dcache_range_asm) +ENTRY_CFI(flush_kernel_dcache_range_asm) .proc .callinfo NO_CALLS .entry @@ -1110,9 +1116,9 @@ ENTRY(flush_kernel_dcache_range_asm) .exit .procend -ENDPROC(flush_kernel_dcache_range_asm) +ENDPROC_CFI(flush_kernel_dcache_range_asm) -ENTRY(flush_user_icache_range_asm) +ENTRY_CFI(flush_user_icache_range_asm) .proc .callinfo NO_CALLS .entry @@ -1131,9 +1137,9 @@ ENTRY(flush_user_icache_range_asm) .exit .procend -ENDPROC(flush_user_icache_range_asm) +ENDPROC_CFI(flush_user_icache_range_asm) -ENTRY(flush_kernel_icache_page) +ENTRY_CFI(flush_kernel_icache_page) .proc .callinfo NO_CALLS .entry @@ -1174,9 +1180,9 @@ ENTRY(flush_kernel_icache_page) .exit .procend -ENDPROC(flush_kernel_icache_page) +ENDPROC_CFI(flush_kernel_icache_page) -ENTRY(flush_kernel_icache_range_asm) +ENTRY_CFI(flush_kernel_icache_range_asm) .proc .callinfo NO_CALLS .entry @@ -1194,13 +1200,13 @@ ENTRY(flush_kernel_icache_range_asm) nop .exit .procend -ENDPROC(flush_kernel_icache_range_asm) +ENDPROC_CFI(flush_kernel_icache_range_asm) /* align should cover use of rfi in disable_sr_hashing_asm and * srdis_done. */ .align 256 -ENTRY(disable_sr_hashing_asm) +ENTRY_CFI(disable_sr_hashing_asm) .proc .callinfo NO_CALLS .entry @@ -1289,6 +1295,6 @@ srdis_done: .exit .procend -ENDPROC(disable_sr_hashing_asm) +ENDPROC_CFI(disable_sr_hashing_asm) .end diff --git a/arch/parisc/kernel/real2.S b/arch/parisc/kernel/real2.S index 5f3d3a1f9037..1db58e546230 100644 --- a/arch/parisc/kernel/real2.S +++ b/arch/parisc/kernel/real2.S @@ -61,7 +61,7 @@ save_cr_end: * iodc_fn is the IODC function to call */ -ENTRY(real32_call_asm) +ENTRY_CFI(real32_call_asm) STREG %rp, -RP_OFFSET(%sp) /* save RP */ #ifdef CONFIG_64BIT callee_save @@ -119,14 +119,14 @@ ric_ret: LDREG -RP_OFFSET(%sp), %rp /* restore RP */ bv 0(%rp) nop -ENDPROC(real32_call_asm) +ENDPROC_CFI(real32_call_asm) # define PUSH_CR(r, where) mfctl r, %r1 ! STREG,ma %r1, REG_SZ(where) # define POP_CR(r, where) LDREG,mb -REG_SZ(where), %r1 ! mtctl %r1, r .text -save_control_regs: +ENTRY_CFI(save_control_regs) load32 PA(save_cr_space), %r28 PUSH_CR(%cr24, %r28) PUSH_CR(%cr25, %r28) @@ -139,8 +139,9 @@ save_control_regs: PUSH_CR(%cr15, %r28) bv 0(%r2) nop +ENDPROC_CFI(save_control_regs) -restore_control_regs: +ENTRY_CFI(restore_control_regs) load32 PA(save_cr_end), %r26 POP_CR(%cr15, %r26) POP_CR(%cr31, %r26) @@ -153,13 +154,14 @@ restore_control_regs: POP_CR(%cr24, %r26) bv 0(%r2) nop +ENDPROC_CFI(restore_control_regs) /* rfi_virt2real() and rfi_real2virt() could perhaps be adapted for * more general-purpose use by the several places which need RFIs */ .text .align 128 -rfi_virt2real: +ENTRY_CFI(rfi_virt2real) /* switch to real mode... */ rsm PSW_SM_I,%r0 load32 PA(rfi_v2r_1), %r1 @@ -191,10 +193,11 @@ rfi_v2r_1: tophys_r1 %r2 bv 0(%r2) nop +ENDPROC_CFI(rfi_virt2real) .text .align 128 -rfi_real2virt: +ENTRY_CFI(rfi_real2virt) rsm PSW_SM_I,%r0 load32 (rfi_r2v_1), %r1 nop @@ -225,6 +228,7 @@ rfi_r2v_1: tovirt_r1 %r2 bv 0(%r2) nop +ENDPROC_CFI(rfi_real2virt) #ifdef CONFIG_64BIT @@ -238,7 +242,7 @@ rfi_r2v_1: * arg0p points to where saved arg values may be found * iodc_fn is the IODC function to call */ -ENTRY(real64_call_asm) +ENTRY_CFI(real64_call_asm) std %rp, -0x10(%sp) /* save RP */ std %sp, -8(%arg0) /* save SP on real-mode stack */ copy %arg0, %sp /* adopt the real-mode SP */ @@ -284,7 +288,7 @@ r64_ret: ldd -0x10(%sp), %rp /* restore RP */ bv 0(%rp) nop -ENDPROC(real64_call_asm) +ENDPROC_CFI(real64_call_asm) #endif @@ -293,12 +297,12 @@ ENDPROC(real64_call_asm) ** GCC 3.3 and later has a new function in libgcc.a for ** comparing function pointers. */ -ENTRY(__canonicalize_funcptr_for_compare) +ENTRY_CFI(__canonicalize_funcptr_for_compare) #ifdef CONFIG_64BIT bve (%r2) #else bv %r0(%r2) #endif copy %r26,%r28 -ENDPROC(__canonicalize_funcptr_for_compare) +ENDPROC_CFI(__canonicalize_funcptr_for_compare) diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index f7ea626e29c9..81d6f6391944 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -38,6 +38,7 @@ #include <linux/export.h> #include <asm/processor.h> +#include <asm/sections.h> #include <asm/pdc.h> #include <asm/led.h> #include <asm/machdep.h> /* for pa7300lc_init() proto */ @@ -140,6 +141,13 @@ void __init setup_arch(char **cmdline_p) #endif printk(KERN_CONT ".\n"); + /* + * Check if initial kernel page mappings are sufficient. + * panic early if not, else we may access kernel functions + * and variables which can't be reached. + */ + if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE) + panic("KERNEL_INITIAL_ORDER too small!"); pdc_console_init(); diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index c2a9cc55a62f..75dab2871346 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -412,8 +412,8 @@ void smp_cpus_done(unsigned int cpu_max) int __cpu_up(unsigned int cpu, struct task_struct *tidle) { - if (cpu != 0 && cpu < parisc_max_cpus) - smp_boot_one_cpu(cpu, tidle); + if (cpu != 0 && cpu < parisc_max_cpus && smp_boot_one_cpu(cpu, tidle)) + return -ENOSYS; return cpu_online(cpu) ? 0 : -ENOSYS; } diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 4b0b963d52a7..9b63b876a13a 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -226,12 +226,6 @@ void __init start_cpu_itimer(void) unsigned int cpu = smp_processor_id(); unsigned long next_tick = mfctl(16) + clocktick; -#if defined(CONFIG_HAVE_UNSTABLE_SCHED_CLOCK) && defined(CONFIG_64BIT) - /* With multiple 64bit CPUs online, the cr16's are not syncronized. */ - if (cpu != 0) - clear_sched_clock_stable(); -#endif - mtctl(next_tick, 16); /* kick off Interval Timer (CR16) */ per_cpu(cpu_data, cpu).it_value = next_tick; diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index f3ead0b6ce46..5b8fae8d4d12 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -138,8 +138,6 @@ SECTIONS /* BSS */ BSS_SECTION(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE) - /* bootmap is allocated in setup_bootmem() directly behind bss. */ - . = ALIGN(HUGEPAGE_SIZE); _end = . ; diff --git a/arch/parisc/lib/fixup.S b/arch/parisc/lib/fixup.S index 1052b747e011..a5b72f22c7a6 100644 --- a/arch/parisc/lib/fixup.S +++ b/arch/parisc/lib/fixup.S @@ -65,34 +65,34 @@ .section .fixup, "ax" /* get_user() fixups, store -EFAULT in r8, and 0 in r9 */ -ENTRY(fixup_get_user_skip_1) +ENTRY_CFI(fixup_get_user_skip_1) get_fault_ip %r1,%r8 ldo 4(%r1), %r1 ldi -EFAULT, %r8 bv %r0(%r1) copy %r0, %r9 -ENDPROC(fixup_get_user_skip_1) +ENDPROC_CFI(fixup_get_user_skip_1) -ENTRY(fixup_get_user_skip_2) +ENTRY_CFI(fixup_get_user_skip_2) get_fault_ip %r1,%r8 ldo 8(%r1), %r1 ldi -EFAULT, %r8 bv %r0(%r1) copy %r0, %r9 -ENDPROC(fixup_get_user_skip_2) +ENDPROC_CFI(fixup_get_user_skip_2) /* put_user() fixups, store -EFAULT in r8 */ -ENTRY(fixup_put_user_skip_1) +ENTRY_CFI(fixup_put_user_skip_1) get_fault_ip %r1,%r8 ldo 4(%r1), %r1 bv %r0(%r1) ldi -EFAULT, %r8 -ENDPROC(fixup_put_user_skip_1) +ENDPROC_CFI(fixup_put_user_skip_1) -ENTRY(fixup_put_user_skip_2) +ENTRY_CFI(fixup_put_user_skip_2) get_fault_ip %r1,%r8 ldo 8(%r1), %r1 bv %r0(%r1) ldi -EFAULT, %r8 -ENDPROC(fixup_put_user_skip_2) +ENDPROC_CFI(fixup_put_user_skip_2) diff --git a/arch/parisc/lib/lusercopy.S b/arch/parisc/lib/lusercopy.S index a512f07d4feb..56845de6b5df 100644 --- a/arch/parisc/lib/lusercopy.S +++ b/arch/parisc/lib/lusercopy.S @@ -67,7 +67,7 @@ * otherwise, returns number of bytes not transferred. */ -ENTRY(lclear_user) +ENTRY_CFI(lclear_user) .proc .callinfo NO_CALLS .entry @@ -81,7 +81,7 @@ $lclu_done: bv %r0(%r2) copy %r25,%r28 .exit -ENDPROC(lclear_user) +ENDPROC_CFI(lclear_user) .section .fixup,"ax" 2: fixup_branch $lclu_done @@ -100,7 +100,7 @@ ENDPROC(lclear_user) * else strlen + 1 (i.e. includes zero byte). */ -ENTRY(lstrnlen_user) +ENTRY_CFI(lstrnlen_user) .proc .callinfo NO_CALLS .entry @@ -120,7 +120,7 @@ $lslen_done: $lslen_nzero: b $lslen_done ldo 1(%r26),%r26 /* special case for N == 0 */ -ENDPROC(lstrnlen_user) +ENDPROC_CFI(lstrnlen_user) .section .fixup,"ax" 3: fixup_branch $lslen_done diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c index b2b441b32341..f82ff10ed974 100644 --- a/arch/parisc/lib/memcpy.c +++ b/arch/parisc/lib/memcpy.c @@ -489,20 +489,23 @@ static unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len) } #ifdef __KERNEL__ -unsigned long copy_to_user(void __user *dst, const void *src, unsigned long len) +unsigned long __copy_to_user(void __user *dst, const void *src, + unsigned long len) { mtsp(get_kernel_space(), 1); mtsp(get_user_space(), 2); return pa_memcpy((void __force *)dst, src, len); } +EXPORT_SYMBOL(__copy_to_user); -EXPORT_SYMBOL(__copy_from_user); -unsigned long __copy_from_user(void *dst, const void __user *src, unsigned long len) +unsigned long __copy_from_user(void *dst, const void __user *src, + unsigned long len) { mtsp(get_user_space(), 1); mtsp(get_kernel_space(), 2); return pa_memcpy(dst, (void __force *)src, len); } +EXPORT_SYMBOL(__copy_from_user); unsigned long copy_in_user(void __user *dst, const void __user *src, unsigned long len) { @@ -520,8 +523,6 @@ void * memcpy(void * dst,const void *src, size_t count) return dst; } -EXPORT_SYMBOL(copy_to_user); -EXPORT_SYMBOL(copy_from_user); EXPORT_SYMBOL(copy_in_user); EXPORT_SYMBOL(memcpy); diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 163af2c31d76..47a6ca4c9e40 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -168,6 +168,43 @@ int fixup_exception(struct pt_regs *regs) } /* + * parisc hardware trap list + * + * Documented in section 3 "Addressing and Access Control" of the + * "PA-RISC 1.1 Architecture and Instruction Set Reference Manual" + * https://parisc.wiki.kernel.org/index.php/File:Pa11_acd.pdf + * + * For implementation see handle_interruption() in traps.c + */ +static const char * const trap_description[] = { + [1] "High-priority machine check (HPMC)", + [2] "Power failure interrupt", + [3] "Recovery counter trap", + [5] "Low-priority machine check", + [6] "Instruction TLB miss fault", + [7] "Instruction access rights / protection trap", + [8] "Illegal instruction trap", + [9] "Break instruction trap", + [10] "Privileged operation trap", + [11] "Privileged register trap", + [12] "Overflow trap", + [13] "Conditional trap", + [14] "FP Assist Exception trap", + [15] "Data TLB miss fault", + [16] "Non-access ITLB miss fault", + [17] "Non-access DTLB miss fault", + [18] "Data memory protection/unaligned access trap", + [19] "Data memory break trap", + [20] "TLB dirty bit trap", + [21] "Page reference trap", + [22] "Assist emulation trap", + [25] "Taken branch trap", + [26] "Data memory access rights trap", + [27] "Data memory protection ID trap", + [28] "Unaligned data reference trap", +}; + +/* * Print out info about fatal segfaults, if the show_unhandled_signals * sysctl is set: */ @@ -176,6 +213,8 @@ show_signal_msg(struct pt_regs *regs, unsigned long code, unsigned long address, struct task_struct *tsk, struct vm_area_struct *vma) { + const char *trap_name = NULL; + if (!unhandled_signal(tsk, SIGSEGV)) return; @@ -186,8 +225,15 @@ show_signal_msg(struct pt_regs *regs, unsigned long code, pr_warn("do_page_fault() command='%s' type=%lu address=0x%08lx", tsk->comm, code, address); print_vma_addr(KERN_CONT " in ", regs->iaoq[0]); + + if (code < ARRAY_SIZE(trap_description)) + trap_name = trap_description[code]; + pr_warn(KERN_CONT " trap #%lu: %s%c", code, + trap_name ? trap_name : "unknown", + vma ? ',':'\n'); + if (vma) - pr_warn(" vm_start = 0x%08lx, vm_end = 0x%08lx\n", + pr_warn(KERN_CONT " vm_start = 0x%08lx, vm_end = 0x%08lx\n", vma->vm_start, vma->vm_end); show_regs(regs); diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 6b3e7c6ee096..356f38473b5d 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/mm.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/gfp.h> #include <linux/delay.h> #include <linux/init.h> @@ -79,6 +80,34 @@ static struct resource sysram_resources[MAX_PHYSMEM_RANGES] __read_mostly; physmem_range_t pmem_ranges[MAX_PHYSMEM_RANGES] __read_mostly; int npmem_ranges __read_mostly; +/* + * get_memblock() allocates pages via memblock. + * We can't use memblock_find_in_range(0, KERNEL_INITIAL_SIZE) here since it + * doesn't allocate from bottom to top which is needed because we only created + * the initial mapping up to KERNEL_INITIAL_SIZE in the assembly bootup code. + */ +static void * __init get_memblock(unsigned long size) +{ + static phys_addr_t search_addr __initdata; + phys_addr_t phys; + + if (!search_addr) + search_addr = PAGE_ALIGN(__pa((unsigned long) &_end)); + search_addr = ALIGN(search_addr, size); + while (!memblock_is_region_memory(search_addr, size) || + memblock_is_region_reserved(search_addr, size)) { + search_addr += size; + } + phys = search_addr; + + if (phys) + memblock_reserve(phys, size); + else + panic("get_memblock() failed.\n"); + + return __va(phys); +} + #ifdef CONFIG_64BIT #define MAX_MEM (~0UL) #else /* !CONFIG_64BIT */ @@ -118,11 +147,7 @@ static void __init mem_limit_func(void) static void __init setup_bootmem(void) { - unsigned long bootmap_size; unsigned long mem_max; - unsigned long bootmap_pages; - unsigned long bootmap_start_pfn; - unsigned long bootmap_pfn; #ifndef CONFIG_DISCONTIGMEM physmem_range_t pmem_holes[MAX_PHYSMEM_RANGES - 1]; int npmem_holes; @@ -178,33 +203,29 @@ static void __init setup_bootmem(void) } #endif - if (npmem_ranges > 1) { - - /* Print the memory ranges */ + /* Print the memory ranges */ + pr_info("Memory Ranges:\n"); - printk(KERN_INFO "Memory Ranges:\n"); + for (i = 0; i < npmem_ranges; i++) { + struct resource *res = &sysram_resources[i]; + unsigned long start; + unsigned long size; - for (i = 0; i < npmem_ranges; i++) { - unsigned long start; - unsigned long size; + size = (pmem_ranges[i].pages << PAGE_SHIFT); + start = (pmem_ranges[i].start_pfn << PAGE_SHIFT); + pr_info("%2d) Start 0x%016lx End 0x%016lx Size %6ld MB\n", + i, start, start + (size - 1), size >> 20); - size = (pmem_ranges[i].pages << PAGE_SHIFT); - start = (pmem_ranges[i].start_pfn << PAGE_SHIFT); - printk(KERN_INFO "%2d) Start 0x%016lx End 0x%016lx Size %6ld MB\n", - i,start, start + (size - 1), size >> 20); - } - } - - sysram_resource_count = npmem_ranges; - for (i = 0; i < sysram_resource_count; i++) { - struct resource *res = &sysram_resources[i]; + /* request memory resource */ res->name = "System RAM"; - res->start = pmem_ranges[i].start_pfn << PAGE_SHIFT; - res->end = res->start + (pmem_ranges[i].pages << PAGE_SHIFT)-1; + res->start = start; + res->end = start + size - 1; res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); } + sysram_resource_count = npmem_ranges; + /* * For 32 bit kernels we limit the amount of memory we can * support, in order to preserve enough kernel address space @@ -263,16 +284,9 @@ static void __init setup_bootmem(void) } #endif - bootmap_pages = 0; - for (i = 0; i < npmem_ranges; i++) - bootmap_pages += bootmem_bootmap_pages(pmem_ranges[i].pages); - - bootmap_start_pfn = PAGE_ALIGN(__pa((unsigned long) &_end)) >> PAGE_SHIFT; - #ifdef CONFIG_DISCONTIGMEM for (i = 0; i < MAX_PHYSMEM_RANGES; i++) { memset(NODE_DATA(i), 0, sizeof(pg_data_t)); - NODE_DATA(i)->bdata = &bootmem_node_data[i]; } memset(pfnnid_map, 0xff, sizeof(pfnnid_map)); @@ -284,28 +298,24 @@ static void __init setup_bootmem(void) /* * Initialize and free the full range of memory in each range. - * Note that the only writing these routines do are to the bootmap, - * and we've made sure to locate the bootmap properly so that they - * won't be writing over anything important. */ - bootmap_pfn = bootmap_start_pfn; max_pfn = 0; for (i = 0; i < npmem_ranges; i++) { unsigned long start_pfn; unsigned long npages; + unsigned long start; + unsigned long size; start_pfn = pmem_ranges[i].start_pfn; npages = pmem_ranges[i].pages; - bootmap_size = init_bootmem_node(NODE_DATA(i), - bootmap_pfn, - start_pfn, - (start_pfn + npages) ); - free_bootmem_node(NODE_DATA(i), - (start_pfn << PAGE_SHIFT), - (npages << PAGE_SHIFT) ); - bootmap_pfn += (bootmap_size + PAGE_SIZE - 1) >> PAGE_SHIFT; + start = start_pfn << PAGE_SHIFT; + size = npages << PAGE_SHIFT; + + /* add system RAM memblock */ + memblock_add(start, size); + if ((start_pfn + npages) > max_pfn) max_pfn = start_pfn + npages; } @@ -317,32 +327,22 @@ static void __init setup_bootmem(void) */ max_low_pfn = max_pfn; - /* bootmap sizing messed up? */ - BUG_ON((bootmap_pfn - bootmap_start_pfn) != bootmap_pages); - /* reserve PAGE0 pdc memory, kernel text/data/bss & bootmap */ #define PDC_CONSOLE_IO_IODC_SIZE 32768 - reserve_bootmem_node(NODE_DATA(0), 0UL, - (unsigned long)(PAGE0->mem_free + - PDC_CONSOLE_IO_IODC_SIZE), BOOTMEM_DEFAULT); - reserve_bootmem_node(NODE_DATA(0), __pa(KERNEL_BINARY_TEXT_START), - (unsigned long)(_end - KERNEL_BINARY_TEXT_START), - BOOTMEM_DEFAULT); - reserve_bootmem_node(NODE_DATA(0), (bootmap_start_pfn << PAGE_SHIFT), - ((bootmap_pfn - bootmap_start_pfn) << PAGE_SHIFT), - BOOTMEM_DEFAULT); + memblock_reserve(0UL, (unsigned long)(PAGE0->mem_free + + PDC_CONSOLE_IO_IODC_SIZE)); + memblock_reserve(__pa(KERNEL_BINARY_TEXT_START), + (unsigned long)(_end - KERNEL_BINARY_TEXT_START)); #ifndef CONFIG_DISCONTIGMEM /* reserve the holes */ for (i = 0; i < npmem_holes; i++) { - reserve_bootmem_node(NODE_DATA(0), - (pmem_holes[i].start_pfn << PAGE_SHIFT), - (pmem_holes[i].pages << PAGE_SHIFT), - BOOTMEM_DEFAULT); + memblock_reserve((pmem_holes[i].start_pfn << PAGE_SHIFT), + (pmem_holes[i].pages << PAGE_SHIFT)); } #endif @@ -360,8 +360,7 @@ static void __init setup_bootmem(void) initrd_below_start_ok = 1; printk(KERN_INFO "initrd: reserving %08lx-%08lx (mem_max %08lx)\n", __pa(initrd_start), __pa(initrd_start) + initrd_reserve, mem_max); - reserve_bootmem_node(NODE_DATA(0), __pa(initrd_start), - initrd_reserve, BOOTMEM_DEFAULT); + memblock_reserve(__pa(initrd_start), initrd_reserve); } } #endif @@ -439,7 +438,7 @@ static void __init map_pages(unsigned long start_vaddr, */ if (!pmd) { - pmd = (pmd_t *) alloc_bootmem_low_pages_node(NODE_DATA(0), PAGE_SIZE << PMD_ORDER); + pmd = (pmd_t *) get_memblock(PAGE_SIZE << PMD_ORDER); pmd = (pmd_t *) __pa(pmd); } @@ -458,8 +457,7 @@ static void __init map_pages(unsigned long start_vaddr, pg_table = (pte_t *)pmd_address(*pmd); if (!pg_table) { - pg_table = (pte_t *) - alloc_bootmem_low_pages_node(NODE_DATA(0), PAGE_SIZE); + pg_table = (pte_t *) get_memblock(PAGE_SIZE); pg_table = (pte_t *) __pa(pg_table); } @@ -737,7 +735,7 @@ static void __init pagetable_init(void) } #endif - empty_zero_page = alloc_bootmem_pages(PAGE_SIZE); + empty_zero_page = get_memblock(PAGE_SIZE); } static void __init gateway_init(void) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 927d2ab2ce08..569b4f9271a4 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -12,11 +12,6 @@ config 64BIT bool default y if PPC64 -config WORD_SIZE - int - default 64 if PPC64 - default 32 if !PPC64 - config ARCH_PHYS_ADDR_T_64BIT def_bool PPC64 || PHYS_64BIT @@ -101,7 +96,7 @@ config PPC select VIRT_TO_BUS if !PPC64 select HAVE_IDE select HAVE_IOREMAP_PROT - select HAVE_EFFICIENT_UNALIGNED_ACCESS if !CPU_LITTLE_ENDIAN + select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU) select HAVE_KPROBES select HAVE_ARCH_KGDB select HAVE_KRETPROBES @@ -167,6 +162,7 @@ config PPC select GENERIC_CPU_AUTOPROBE select HAVE_VIRT_CPU_ACCOUNTING select HAVE_ARCH_HARDENED_USERCOPY + select HAVE_KERNEL_GZIP config GENERIC_CSUM def_bool CPU_LITTLE_ENDIAN @@ -637,7 +633,7 @@ config FORCE_MAX_ZONEORDER int "Maximum zone order" range 8 9 if PPC64 && PPC_64K_PAGES default "9" if PPC64 && PPC_64K_PAGES - range 9 13 if PPC64 && !PPC_64K_PAGES + range 13 13 if PPC64 && !PPC_64K_PAGES default "13" if PPC64 && !PPC_64K_PAGES range 9 64 if PPC32 && PPC_16K_PAGES default "9" if PPC32 && PPC_16K_PAGES diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 1934707bf321..50d020ac0f48 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -43,31 +43,24 @@ NM := $(NM) --synthetic endif endif -ifeq ($(CONFIG_PPC64),y) -ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) -OLDARCH := ppc64le -else -OLDARCH := ppc64 -endif -else -ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) -OLDARCH := ppcle -else -OLDARCH := ppc -endif -endif +# BITS is used as extension for files which are available in a 32 bit +# and a 64 bit version to simplify shared Makefiles. +# e.g.: obj-y += foo_$(BITS).o +export BITS -# It seems there are times we use this Makefile without -# including the config file, but this replicates the old behaviour -ifeq ($(CONFIG_WORD_SIZE),) -CONFIG_WORD_SIZE := 32 +ifdef CONFIG_PPC64 + BITS := 64 +else + BITS := 32 endif -UTS_MACHINE := $(OLDARCH) +machine-y = ppc +machine-$(CONFIG_PPC64) += 64 +machine-$(CONFIG_CPU_LITTLE_ENDIAN) += le +UTS_MACHINE := $(subst $(space),,$(machine-y)) ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) override LD += -EL -override CROSS32AS += -mlittle-endian LDEMULATION := lppc GNUTARGET := powerpcle MULTIPLEWORD := -mno-multiple @@ -89,10 +82,10 @@ aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian) aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian ifeq ($(HAS_BIARCH),y) -override AS += -a$(CONFIG_WORD_SIZE) -override LD += -m elf$(CONFIG_WORD_SIZE)$(LDEMULATION) -override CC += -m$(CONFIG_WORD_SIZE) -override AR := GNUTARGET=elf$(CONFIG_WORD_SIZE)-$(GNUTARGET) $(AR) +override AS += -a$(BITS) +override LD += -m elf$(BITS)$(LDEMULATION) +override CC += -m$(BITS) +override AR := GNUTARGET=elf$(BITS)-$(GNUTARGET) $(AR) endif LDFLAGS_vmlinux-y := -Bstatic @@ -179,7 +172,7 @@ KBUILD_CFLAGS += $(call cc-option,-msoft-float) KBUILD_CFLAGS += -pipe -Iarch/$(ARCH) $(CFLAGS-y) CPP = $(CC) -E $(KBUILD_CFLAGS) -CHECKFLAGS += -m$(CONFIG_WORD_SIZE) -D__powerpc__ -D__powerpc$(CONFIG_WORD_SIZE)__ +CHECKFLAGS += -m$(BITS) -D__powerpc__ -D__powerpc$(BITS)__ ifdef CONFIG_CPU_BIG_ENDIAN CHECKFLAGS += -D__BIG_ENDIAN__ else @@ -234,7 +227,7 @@ KBUILD_CFLAGS += $(cpu-as-y) KBUILD_AFLAGS += $(aflags-y) KBUILD_CFLAGS += $(cflags-y) -head-y := arch/powerpc/kernel/head_$(CONFIG_WORD_SIZE).o +head-y := arch/powerpc/kernel/head_$(BITS).o head-$(CONFIG_8xx) := arch/powerpc/kernel/head_8xx.o head-$(CONFIG_40x) := arch/powerpc/kernel/head_40x.o head-$(CONFIG_44x) := arch/powerpc/kernel/head_44x.o diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 1a2a6e8dc40d..eae2dc8bc218 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -19,10 +19,15 @@ all: $(obj)/zImage +compress-$(CONFIG_KERNEL_GZIP) := CONFIG_KERNEL_GZIP +compress-$(CONFIG_KERNEL_XZ) := CONFIG_KERNEL_XZ + BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -Os -msoft-float -pipe \ -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ - -isystem $(shell $(CROSS32CC) -print-file-name=include) + -isystem $(shell $(CROSS32CC) -print-file-name=include) \ + -D$(compress-y) + ifdef CONFIG_PPC64_BOOT_WRAPPER BOOTCFLAGS += -m64 endif @@ -59,13 +64,30 @@ $(obj)/treeboot-currituck.o: BOOTCFLAGS += -mcpu=405 $(obj)/treeboot-akebono.o: BOOTCFLAGS += -mcpu=405 $(obj)/virtex405-head.o: BOOTAFLAGS += -mcpu=405 +# The pre-boot decompressors pull in a lot of kernel headers and other source +# files. This creates a bit of a dependency headache since we need to copy +# these files into the build dir, fix up any includes and ensure that dependent +# files are copied in the right order. + +# these need to be seperate variables because they are copied out of different +# directories in the kernel tree. Sure you COULd merge them, but it's a +# cure-is-worse-than-disease situation. +zlib-decomp-$(CONFIG_KERNEL_GZIP) := decompress_inflate.c +zlib-$(CONFIG_KERNEL_GZIP) := inffast.c inflate.c inftrees.c +zlibheader-$(CONFIG_KERNEL_GZIP) := inffast.h inffixed.h inflate.h inftrees.h infutil.h +zliblinuxheader-$(CONFIG_KERNEL_GZIP) := zlib.h zconf.h zutil.h -zlib := inffast.c inflate.c inftrees.c -zlibheader := inffast.h inffixed.h inflate.h inftrees.h infutil.h -zliblinuxheader := zlib.h zconf.h zutil.h +$(addprefix $(obj)/, decompress.o): \ + $(addprefix $(obj)/,$(zlib-decomp-y)) -$(addprefix $(obj)/,$(zlib) cuboot-c2k.o gunzip_util.o main.o): \ - $(addprefix $(obj)/,$(zliblinuxheader)) $(addprefix $(obj)/,$(zlibheader)) +$(addprefix $(obj)/, $(zlib-decomp-y)): \ + $(addprefix $(obj)/,$(zliblinuxheader-y)) \ + $(addprefix $(obj)/,$(zlibheader-y)) \ + $(addprefix $(obj)/,$(zlib-y)) + +$(addprefix $(obj)/,$(zlib-y)): \ + $(addprefix $(obj)/,$(zliblinuxheader-y)) \ + $(addprefix $(obj)/,$(zlibheader-y)) libfdt := fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c libfdtheader := fdt.h libfdt.h libfdt_internal.h @@ -73,10 +95,10 @@ libfdtheader := fdt.h libfdt.h libfdt_internal.h $(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o): \ $(addprefix $(obj)/,$(libfdtheader)) -src-wlib-y := string.S crt0.S crtsavres.S stdio.c main.c \ +src-wlib-y := string.S crt0.S crtsavres.S stdio.c decompress.c main.c \ $(libfdt) libfdt-wrapper.c \ ns16550.c serial.c simple_alloc.c div64.S util.S \ - gunzip_util.c elf_util.c $(zlib) devtree.c stdlib.c \ + elf_util.c $(zlib-y) devtree.c stdlib.c \ oflib.c ofconsole.c cuboot.c mpsc.c cpm-serial.c \ uartlite.c mpc52xx-psc.c opal.c opal-calls.S src-wlib-$(CONFIG_40x) += 4xx.c planetcore.c @@ -125,23 +147,20 @@ obj-wlib := $(addsuffix .o, $(basename $(addprefix $(obj)/, $(src-wlib)))) obj-plat := $(addsuffix .o, $(basename $(addprefix $(obj)/, $(src-plat)))) obj-plat: $(libfdt) -quiet_cmd_copy_zlib = COPY $@ - cmd_copy_zlib = sed "s@__used@@;s@<linux/\([^>]*\).*@\"\1\"@" $< > $@ +quiet_cmd_copy_kern_src = COPY $@ + cmd_copy_kern_src = sed -f $(srctree)/arch/powerpc/boot/fixup-headers.sed $< > $@ -quiet_cmd_copy_zlibheader = COPY $@ - cmd_copy_zlibheader = sed "s@<linux/\([^>]*\).*@\"\1\"@" $< > $@ -# stddef.h for NULL -quiet_cmd_copy_zliblinuxheader = COPY $@ - cmd_copy_zliblinuxheader = sed "s@<linux/string.h>@\"string.h\"@;s@<linux/kernel.h>@<stddef.h>@;s@<linux/\([^>]*\).*@\"\1\"@" $< > $@ +$(addprefix $(obj)/,$(zlib-y)): $(obj)/%: $(srctree)/lib/zlib_inflate/% + $(call cmd,copy_kern_src) -$(addprefix $(obj)/,$(zlib)): $(obj)/%: $(srctree)/lib/zlib_inflate/% - $(call cmd,copy_zlib) +$(addprefix $(obj)/,$(zlibheader-y)): $(obj)/%: $(srctree)/lib/zlib_inflate/% + $(call cmd,copy_kern_src) -$(addprefix $(obj)/,$(zlibheader)): $(obj)/%: $(srctree)/lib/zlib_inflate/% - $(call cmd,copy_zlibheader) +$(addprefix $(obj)/,$(zliblinuxheader-y)): $(obj)/%: $(srctree)/include/linux/% + $(call cmd,copy_kern_src) -$(addprefix $(obj)/,$(zliblinuxheader)): $(obj)/%: $(srctree)/include/linux/% - $(call cmd,copy_zliblinuxheader) +$(addprefix $(obj)/,$(zlib-decomp-y)): $(obj)/%: $(srctree)/lib/% + $(call cmd,copy_kern_src) quiet_cmd_copy_libfdt = COPY $@ cmd_copy_libfdt = cp $< $@ @@ -150,17 +169,17 @@ $(addprefix $(obj)/,$(libfdt) $(libfdtheader)): $(obj)/%: $(srctree)/scripts/dtc $(call cmd,copy_libfdt) $(obj)/empty.c: - @touch $@ + $(Q)touch $@ $(obj)/zImage.lds: $(obj)/%: $(srctree)/$(src)/%.S $(CROSS32CC) $(cpp_flags) -E -Wp,-MD,$(depfile) -P -Upowerpc \ -D__ASSEMBLY__ -DLINKER_SCRIPT -o $@ $< $(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds : $(obj)/%: $(srctree)/$(src)/%.S - @cp $< $@ + $(Q)cp $< $@ -clean-files := $(zlib) $(zlibheader) $(zliblinuxheader) \ - $(libfdt) $(libfdtheader) \ +clean-files := $(zlib-) $(zlibheader-) $(zliblinuxheader-) \ + $(zlib-decomp-) $(libfdt) $(libfdtheader) \ empty.c zImage.coff.lds zImage.ps3.lds zImage.lds quiet_cmd_bootcc = BOOTCC $@ @@ -207,10 +226,14 @@ CROSSWRAP := -C "$(CROSS_COMPILE)" endif endif +compressor-$(CONFIG_KERNEL_GZIP) := gz +compressor-$(CONFIG_KERNEL_XZ) := xz + # args (to if_changed): 1 = (this rule), 2 = platform, 3 = dts 4=dtb 5=initrd quiet_cmd_wrap = WRAP $@ - cmd_wrap =$(CONFIG_SHELL) $(wrapper) -c -o $@ -p $2 $(CROSSWRAP) \ - $(if $3, -s $3)$(if $4, -d $4)$(if $5, -i $5) vmlinux + cmd_wrap =$(CONFIG_SHELL) $(wrapper) -Z $(compressor-y) -c -o $@ -p $2 \ + $(CROSSWRAP) $(if $3, -s $3)$(if $4, -d $4)$(if $5, -i $5) \ + vmlinux image-$(CONFIG_PPC_PSERIES) += zImage.pseries image-$(CONFIG_PPC_POWERNV) += zImage.pseries @@ -391,9 +414,9 @@ image-y := vmlinux.strip endif $(obj)/zImage: $(addprefix $(obj)/, $(image-y)) - @rm -f $@; ln $< $@ + $(Q)rm -f $@; ln $< $@ $(obj)/zImage.initrd: $(addprefix $(obj)/, $(initrd-y)) - @rm -f $@; ln $< $@ + $(Q)rm -f $@; ln $< $@ # Only install the vmlinux install: $(CONFIGURE) $(addprefix $(obj)/, $(image-y)) @@ -410,8 +433,9 @@ clean-files += $(image-) $(initrd-) cuImage.* dtbImage.* treeImage.* \ zImage.maple simpleImage.* otheros.bld *.dtb # clean up files cached by wrapper -clean-kernel := vmlinux.strip vmlinux.bin -clean-kernel += $(addsuffix .gz,$(clean-kernel)) +clean-kernel-base := vmlinux.strip vmlinux.bin +clean-kernel := $(addsuffix .gz,$(clean-kernel-base)) +clean-kernel += $(addsuffix .xz,$(clean-kernel-base)) # If not absolute clean-files are relative to $(obj). clean-files += $(addprefix $(objtree)/, $(clean-kernel)) diff --git a/arch/powerpc/boot/cuboot-c2k.c b/arch/powerpc/boot/cuboot-c2k.c index e43594950ba3..9309c51f1d65 100644 --- a/arch/powerpc/boot/cuboot-c2k.c +++ b/arch/powerpc/boot/cuboot-c2k.c @@ -18,7 +18,6 @@ #include "io.h" #include "ops.h" #include "elf.h" -#include "gunzip_util.h" #include "mv64x60.h" #include "cuboot.h" #include "ppcboot.h" diff --git a/arch/powerpc/boot/decompress.c b/arch/powerpc/boot/decompress.c new file mode 100644 index 000000000000..3aff4423ad01 --- /dev/null +++ b/arch/powerpc/boot/decompress.c @@ -0,0 +1,148 @@ +/* + * Wrapper around the kernel's pre-boot decompression library. + * + * Copyright (C) IBM Corporation 2016. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include "elf.h" +#include "page.h" +#include "string.h" +#include "stdio.h" +#include "ops.h" +#include "reg.h" +#include "types.h" + +/* + * The decompressor_*.c files play #ifdef games so they can be used in both + * pre-boot and regular kernel code. We need these definitions to make the + * includes work. + */ + +#define STATIC static +#define INIT +#define __always_inline inline + +/* + * The build process will copy the required zlib source files and headers + * out of lib/ and "fix" the includes so they do not pull in other kernel + * headers. + */ + +#ifdef CONFIG_KERNEL_GZIP +# include "decompress_inflate.c" +#endif + +#ifdef CONFIG_KERNEL_XZ +# include "xz_config.h" +# include "../../../lib/decompress_unxz.c" +#endif + +/* globals for tracking the state of the decompression */ +static unsigned long decompressed_bytes; +static unsigned long limit; +static unsigned long skip; +static char *output_buffer; + +/* + * flush() is called by __decompress() when the decompressor's scratch buffer is + * full. + */ +static long flush(void *v, unsigned long buffer_size) +{ + unsigned long end = decompressed_bytes + buffer_size; + unsigned long size = buffer_size; + unsigned long offset = 0; + char *in = v; + char *out; + + /* + * if we hit our decompression limit, we need to fake an error to abort + * the in-progress decompression. + */ + if (decompressed_bytes >= limit) + return -1; + + /* skip this entire block */ + if (end <= skip) { + decompressed_bytes += buffer_size; + return buffer_size; + } + + /* skip some data at the start, but keep the rest of the block */ + if (decompressed_bytes < skip && end > skip) { + offset = skip - decompressed_bytes; + + in += offset; + size -= offset; + decompressed_bytes += offset; + } + + out = &output_buffer[decompressed_bytes - skip]; + size = min(decompressed_bytes + size, limit) - decompressed_bytes; + + memcpy(out, in, size); + decompressed_bytes += size; + + return buffer_size; +} + +static void print_err(char *s) +{ + /* suppress the "error" when we terminate the decompressor */ + if (decompressed_bytes >= limit) + return; + + printf("Decompression error: '%s'\n\r", s); +} + +/** + * partial_decompress - decompresses part or all of a compressed buffer + * @inbuf: input buffer + * @input_size: length of the input buffer + * @outbuf: input buffer + * @output_size: length of the input buffer + * @skip number of output bytes to ignore + * + * This function takes compressed data from inbuf, decompresses and write it to + * outbuf. Once output_size bytes are written to the output buffer, or the + * stream is exhausted the function will return the number of bytes that were + * decompressed. Otherwise it will return whatever error code the decompressor + * reported (NB: This is specific to each decompressor type). + * + * The skip functionality is mainly there so the program and discover + * the size of the compressed image so that it can ask firmware (if present) + * for an appropriately sized buffer. + */ +long partial_decompress(void *inbuf, unsigned long input_size, + void *outbuf, unsigned long output_size, unsigned long _skip) +{ + int ret; + + /* + * The skipped bytes needs to be included in the size of data we want + * to decompress. + */ + output_size += _skip; + + decompressed_bytes = 0; + output_buffer = outbuf; + limit = output_size; + skip = _skip; + + ret = __decompress(inbuf, input_size, NULL, flush, outbuf, + output_size, NULL, print_err); + + /* + * If decompression was aborted due to an actual error rather than + * a fake error that we used to abort, then we should report it. + */ + if (decompressed_bytes < limit) + return ret; + + return decompressed_bytes - skip; +} diff --git a/arch/powerpc/boot/fixup-headers.sed b/arch/powerpc/boot/fixup-headers.sed new file mode 100644 index 000000000000..96362428eb37 --- /dev/null +++ b/arch/powerpc/boot/fixup-headers.sed @@ -0,0 +1,12 @@ +# Copyright 2016 IBM Corporation. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of the GNU General Public License version 2 or later as +# published by the Free Software Foundation. + +s@#include <linux/decompress/mm\.h>@@; +s@\"zlib_inflate/\([^\"]*\).*@"\1"@; +s@<linux/kernel.h>@<stddef.h>@; + +s@__used@@; +s@<linux/\([^>]*\).*@"\1"@; diff --git a/arch/powerpc/boot/gunzip_util.c b/arch/powerpc/boot/gunzip_util.c deleted file mode 100644 index 9dc52501de83..000000000000 --- a/arch/powerpc/boot/gunzip_util.c +++ /dev/null @@ -1,204 +0,0 @@ -/* - * Copyright 2007 David Gibson, IBM Corporation. - * Based on earlier work, Copyright (C) Paul Mackerras 1997. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <stddef.h> -#include "string.h" -#include "stdio.h" -#include "ops.h" -#include "gunzip_util.h" - -#define HEAD_CRC 2 -#define EXTRA_FIELD 4 -#define ORIG_NAME 8 -#define COMMENT 0x10 -#define RESERVED 0xe0 - -/** - * gunzip_start - prepare to decompress gzip data - * @state: decompressor state structure to be initialized - * @src: buffer containing gzip compressed or uncompressed data - * @srclen: size in bytes of the buffer at src - * - * If the buffer at @src contains a gzip header, this function - * initializes zlib to decompress the data, storing the decompression - * state in @state. The other functions in this file can then be used - * to decompress data from the gzipped stream. - * - * If the buffer at @src does not contain a gzip header, it is assumed - * to contain uncompressed data. The buffer information is recorded - * in @state and the other functions in this file will simply copy - * data from the uncompressed data stream at @src. - * - * Any errors, such as bad compressed data, cause an error to be - * printed an the platform's exit() function to be called. - */ -void gunzip_start(struct gunzip_state *state, void *src, int srclen) -{ - char *hdr = src; - int hdrlen = 0; - - memset(state, 0, sizeof(*state)); - - /* Check for gzip magic number */ - if ((hdr[0] == 0x1f) && (hdr[1] == 0x8b)) { - /* gzip data, initialize zlib parameters */ - int r, flags; - - state->s.workspace = state->scratch; - if (zlib_inflate_workspacesize() > sizeof(state->scratch)) - fatal("insufficient scratch space for gunzip\n\r"); - - /* skip header */ - hdrlen = 10; - flags = hdr[3]; - if (hdr[2] != Z_DEFLATED || (flags & RESERVED) != 0) - fatal("bad gzipped data\n\r"); - if ((flags & EXTRA_FIELD) != 0) - hdrlen = 12 + hdr[10] + (hdr[11] << 8); - if ((flags & ORIG_NAME) != 0) - while (hdr[hdrlen++] != 0) - ; - if ((flags & COMMENT) != 0) - while (hdr[hdrlen++] != 0) - ; - if ((flags & HEAD_CRC) != 0) - hdrlen += 2; - if (hdrlen >= srclen) - fatal("gunzip_start: ran out of data in header\n\r"); - - r = zlib_inflateInit2(&state->s, -MAX_WBITS); - if (r != Z_OK) - fatal("inflateInit2 returned %d\n\r", r); - } - - state->s.total_in = hdrlen; - state->s.next_in = src + hdrlen; - state->s.avail_in = srclen - hdrlen; -} - -/** - * gunzip_partial - extract bytes from a gzip data stream - * @state: gzip state structure previously initialized by gunzip_start() - * @dst: buffer to store extracted data - * @dstlen: maximum number of bytes to extract - * - * This function extracts at most @dstlen bytes from the data stream - * previously associated with @state by gunzip_start(), decompressing - * if necessary. Exactly @dstlen bytes are extracted unless the data - * stream doesn't contain enough bytes, in which case the entire - * remainder of the stream is decompressed. - * - * Returns the actual number of bytes extracted. If any errors occur, - * such as a corrupted compressed stream, an error is printed an the - * platform's exit() function is called. - */ -int gunzip_partial(struct gunzip_state *state, void *dst, int dstlen) -{ - int len; - - if (state->s.workspace) { - /* gunzipping */ - int r; - - state->s.next_out = dst; - state->s.avail_out = dstlen; - r = zlib_inflate(&state->s, Z_FULL_FLUSH); - if (r != Z_OK && r != Z_STREAM_END) - fatal("inflate returned %d msg: %s\n\r", r, state->s.msg); - len = state->s.next_out - (Byte *)dst; - } else { - /* uncompressed image */ - len = min(state->s.avail_in, (uLong)dstlen); - memcpy(dst, state->s.next_in, len); - state->s.next_in += len; - state->s.avail_in -= len; - } - return len; -} - -/** - * gunzip_exactly - extract a fixed number of bytes from a gzip data stream - * @state: gzip state structure previously initialized by gunzip_start() - * @dst: buffer to store extracted data - * @dstlen: number of bytes to extract - * - * This function extracts exactly @dstlen bytes from the data stream - * previously associated with @state by gunzip_start(), decompressing - * if necessary. - * - * If there are less @dstlen bytes available in the data stream, or if - * any other errors occur, such as a corrupted compressed stream, an - * error is printed an the platform's exit() function is called. - */ -void gunzip_exactly(struct gunzip_state *state, void *dst, int dstlen) -{ - int len; - - len = gunzip_partial(state, dst, dstlen); - if (len < dstlen) - fatal("\n\rgunzip_exactly: ran out of data!" - " Wanted %d, got %d.\n\r", dstlen, len); -} - -/** - * gunzip_discard - discard bytes from a gzip data stream - * @state: gzip state structure previously initialized by gunzip_start() - * @len: number of bytes to discard - * - * This function extracts, then discards exactly @len bytes from the - * data stream previously associated with @state by gunzip_start(). - * Subsequent gunzip_partial(), gunzip_exactly() or gunzip_finish() - * calls will extract the data following the discarded bytes in the - * data stream. - * - * If there are less @len bytes available in the data stream, or if - * any other errors occur, such as a corrupted compressed stream, an - * error is printed an the platform's exit() function is called. - */ -void gunzip_discard(struct gunzip_state *state, int len) -{ - static char discard_buf[128]; - - while (len > sizeof(discard_buf)) { - gunzip_exactly(state, discard_buf, sizeof(discard_buf)); - len -= sizeof(discard_buf); - } - - if (len > 0) - gunzip_exactly(state, discard_buf, len); -} - -/** - * gunzip_finish - extract all remaining bytes from a gzip data stream - * @state: gzip state structure previously initialized by gunzip_start() - * @dst: buffer to store extracted data - * @dstlen: maximum number of bytes to extract - * - * This function extracts all remaining data, or at most @dstlen - * bytes, from the stream previously associated with @state by - * gunzip_start(). zlib is then shut down, so it is an error to use - * any of the functions in this file on @state until it is - * re-initialized with another call to gunzip_start(). - * - * If any errors occur, such as a corrupted compressed stream, an - * error is printed an the platform's exit() function is called. - */ -int gunzip_finish(struct gunzip_state *state, void *dst, int dstlen) -{ - int len; - - len = gunzip_partial(state, dst, dstlen); - - if (state->s.workspace) { - zlib_inflateEnd(&state->s); - } - - return len; -} diff --git a/arch/powerpc/boot/gunzip_util.h b/arch/powerpc/boot/gunzip_util.h deleted file mode 100644 index b3dfa6e87b3a..000000000000 --- a/arch/powerpc/boot/gunzip_util.h +++ /dev/null @@ -1,45 +0,0 @@ -/* - * Decompression convenience functions - * - * Copyright 2007 David Gibson, IBM Corporation. - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. - */ -#ifndef _PPC_BOOT_GUNZIP_UTIL_H_ -#define _PPC_BOOT_GUNZIP_UTIL_H_ - -#include "zlib.h" - -/* - * These functions are designed to make life easy for decompressing - * kernel images, initrd images or any other gzip compressed image, - * particularly if its useful to decompress part of the image (e.g. to - * examine headers) before decompressing the remainder. - * - * To use: - * - declare a gunzip_state structure - * - use gunzip_start() to initialize the state, associating it - * with a stream of compressed data - * - use gunzip_partial(), gunzip_exactly() and gunzip_discard() - * in any combination to extract pieces of data from the stream - * - Finally use gunzip_finish() to extract the tail of the - * compressed stream and wind up zlib - */ - -/* scratch space for gunzip; 46912 is from zlib_inflate_workspacesize() */ -#define GUNZIP_SCRATCH_SIZE 46912 - -struct gunzip_state { - z_stream s; - char scratch[46912]; -}; - -void gunzip_start(struct gunzip_state *state, void *src, int srclen); -int gunzip_partial(struct gunzip_state *state, void *dst, int dstlen); -void gunzip_exactly(struct gunzip_state *state, void *dst, int len); -void gunzip_discard(struct gunzip_state *state, int len); -int gunzip_finish(struct gunzip_state *state, void *dst, int len); - -#endif /* _PPC_BOOT_GUNZIP_UTIL_H_ */ diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c index d80161b633f4..f7a184b6c35b 100644 --- a/arch/powerpc/boot/main.c +++ b/arch/powerpc/boot/main.c @@ -15,11 +15,8 @@ #include "string.h" #include "stdio.h" #include "ops.h" -#include "gunzip_util.h" #include "reg.h" -static struct gunzip_state gzstate; - struct addr_range { void *addr; unsigned long size; @@ -30,15 +27,14 @@ struct addr_range { static struct addr_range prep_kernel(void) { char elfheader[256]; - void *vmlinuz_addr = _vmlinux_start; + unsigned char *vmlinuz_addr = (unsigned char *)_vmlinux_start; unsigned long vmlinuz_size = _vmlinux_end - _vmlinux_start; void *addr = 0; struct elf_info ei; - int len; + long len; - /* gunzip the ELF header of the kernel */ - gunzip_start(&gzstate, vmlinuz_addr, vmlinuz_size); - gunzip_exactly(&gzstate, elfheader, sizeof(elfheader)); + partial_decompress(vmlinuz_addr, vmlinuz_size, + elfheader, sizeof(elfheader), 0); if (!parse_elf64(elfheader, &ei) && !parse_elf32(elfheader, &ei)) fatal("Error: not a valid PPC32 or PPC64 ELF file!\n\r"); @@ -51,7 +47,7 @@ static struct addr_range prep_kernel(void) * the kernel bss must be claimed (it will be zero'd by the * kernel itself) */ - printf("Allocating 0x%lx bytes for kernel ...\n\r", ei.memsize); + printf("Allocating 0x%lx bytes for kernel...\n\r", ei.memsize); if (platform_ops.vmlinux_alloc) { addr = platform_ops.vmlinux_alloc(ei.memsize); @@ -71,16 +67,21 @@ static struct addr_range prep_kernel(void) "device tree\n\r"); } - /* Finally, gunzip the kernel */ - printf("gunzipping (0x%p <- 0x%p:0x%p)...", addr, + /* Finally, decompress the kernel */ + printf("Decompressing (0x%p <- 0x%p:0x%p)...\n\r", addr, vmlinuz_addr, vmlinuz_addr+vmlinuz_size); - /* discard up to the actual load data */ - gunzip_discard(&gzstate, ei.elfoffset - sizeof(elfheader)); - len = gunzip_finish(&gzstate, addr, ei.loadsize); + + len = partial_decompress(vmlinuz_addr, vmlinuz_size, + addr, ei.loadsize, ei.elfoffset); + + if (len < 0) + fatal("Decompression failed with error code %ld\n\r", len); + if (len != ei.loadsize) - fatal("ran out of data! only got 0x%x of 0x%lx bytes.\n\r", - len, ei.loadsize); - printf("done 0x%x bytes\n\r", len); + fatal("Decompression error: got 0x%lx bytes, expected 0x%lx.\n\r", + len, ei.loadsize); + + printf("Done! Decompressed 0x%lx bytes\n\r", len); flush_cache(addr, ei.loadsize); diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h index e19b64ef977a..309d1b127e96 100644 --- a/arch/powerpc/boot/ops.h +++ b/arch/powerpc/boot/ops.h @@ -260,4 +260,7 @@ int __ilog2_u32(u32 n) return 31 - bit; } +long partial_decompress(void *inbuf, unsigned long input_size, void *outbuf, + unsigned long output_size, unsigned long skip); + #endif /* _PPC_BOOT_OPS_H_ */ diff --git a/arch/powerpc/boot/stdbool.h b/arch/powerpc/boot/stdbool.h new file mode 100644 index 000000000000..f818efb08891 --- /dev/null +++ b/arch/powerpc/boot/stdbool.h @@ -0,0 +1,14 @@ +/* + * Copyright (C) IBM Corporation 2016. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * This file is only necessary because some of the pre-boot decompressors + * expect stdbool.h to be available. + * + */ + +#include "types.h" diff --git a/arch/powerpc/boot/stdint.h b/arch/powerpc/boot/stdint.h new file mode 100644 index 000000000000..c1c853be7490 --- /dev/null +++ b/arch/powerpc/boot/stdint.h @@ -0,0 +1,13 @@ +/* + * Copyright (C) IBM Corporation 2016. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * This file is only necessary because some of the pre-boot decompressors + * expect stdint.h to be available. + */ + +#include "types.h" diff --git a/arch/powerpc/boot/types.h b/arch/powerpc/boot/types.h index 85565a89bcc2..af6b66b842c4 100644 --- a/arch/powerpc/boot/types.h +++ b/arch/powerpc/boot/types.h @@ -1,6 +1,8 @@ #ifndef _TYPES_H_ #define _TYPES_H_ +#include <stdbool.h> + #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) typedef unsigned char u8; @@ -34,4 +36,16 @@ typedef s64 int64_t; (void) (&_x == &_y); \ _x > _y ? _x : _y; }) +#define min_t(type, a, b) min(((type) a), ((type) b)) +#define max_t(type, a, b) max(((type) a), ((type) b)) + +typedef int bool; + +#ifndef true +#define true 1 +#endif + +#ifndef false +#define false 0 +#endif #endif /* _TYPES_H_ */ diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index 6681ec3625c9..404b3aabdb4d 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -20,6 +20,8 @@ # -D dir specify directory containing data files used by script # (default ./arch/powerpc/boot) # -W dir specify working directory for temporary files (default .) +# -z use gzip (legacy) +# -Z zsuffix compression to use (gz, xz or none) # Stop execution if any command fails set -e @@ -38,7 +40,7 @@ dtb= dts= cacheit= binary= -gzip=.gz +compression=.gz pie= format= @@ -59,7 +61,8 @@ tmpdir=. usage() { echo 'Usage: wrapper [-o output] [-p platform] [-i initrd]' >&2 echo ' [-d devtree] [-s tree.dts] [-c] [-C cross-prefix]' >&2 - echo ' [-D datadir] [-W workingdir] [--no-gzip] [vmlinux]' >&2 + echo ' [-D datadir] [-W workingdir] [-Z (gz|xz|none)]' >&2 + echo ' [--no-compression] [vmlinux]' >&2 exit 1 } @@ -126,8 +129,24 @@ while [ "$#" -gt 0 ]; do [ "$#" -gt 0 ] || usage tmpdir="$1" ;; + -z) + compression=.gz + ;; + -Z) + shift + [ "$#" -gt 0 ] || usage + [ "$1" != "gz" -o "$1" != "xz" -o "$1" != "none" ] || usage + + compression=".$1" + + if [ $compression = ".none" ]; then + compression= + fi + ;; --no-gzip) - gzip= + # a "feature" of the the wrapper script is that it can be used outside + # the kernel tree. So keeping this around for backwards compatibility. + compression= ;; -?) usage @@ -140,6 +159,7 @@ while [ "$#" -gt 0 ]; do shift done + if [ -n "$dts" ]; then if [ ! -r "$dts" -a -r "$object/dts/$dts" ]; then dts="$object/dts/$dts" @@ -212,7 +232,7 @@ miboot|uboot*) ;; cuboot*) binary=y - gzip= + compression= case "$platform" in *-mpc866ads|*-mpc885ads|*-adder875*|*-ep88xc) platformo=$object/cuboot-8xx.o @@ -243,7 +263,7 @@ cuboot*) ps3) platformo="$object/ps3-head.o $object/ps3-hvcall.o $object/ps3.o" lds=$object/zImage.ps3.lds - gzip= + compression= ext=bin objflags="-O binary --set-section-flags=.bss=contents,alloc,load,data" ksection=.kernel:vmlinux.bin @@ -310,27 +330,37 @@ mvme7100) esac vmz="$tmpdir/`basename \"$kernel\"`.$ext" -if [ -z "$cacheit" -o ! -f "$vmz$gzip" -o "$vmz$gzip" -ot "$kernel" ]; then - ${CROSS}objcopy $objflags "$kernel" "$vmz.$$" - strip_size=$(stat -c %s $vmz.$$) +# Calculate the vmlinux.strip size +${CROSS}objcopy $objflags "$kernel" "$vmz.$$" +strip_size=$(stat -c %s $vmz.$$) - if [ -n "$gzip" ]; then +if [ -z "$cacheit" -o ! -f "$vmz$compression" -o "$vmz$compression" -ot "$kernel" ]; then + # recompress the image if we need to + case $compression in + .xz) + xz --check=crc32 -f -6 "$vmz.$$" + ;; + .gz) gzip -n -f -9 "$vmz.$$" - fi + ;; + *) + # drop the compression suffix so the stripped vmlinux is used + compression= + ;; + esac if [ -n "$cacheit" ]; then - mv -f "$vmz.$$$gzip" "$vmz$gzip" + mv -f "$vmz.$$$compression" "$vmz$compression" else vmz="$vmz.$$" fi else - # Calculate the vmlinux.strip size - ${CROSS}objcopy $objflags "$kernel" "$vmz.$$" - strip_size=$(stat -c %s $vmz.$$) rm -f $vmz.$$ fi +vmz="$vmz$compression" + if [ "$make_space" = "y" ]; then # Round the size to next higher MB limit round_size=$(((strip_size + 0xfffff) & 0xfff00000)) @@ -346,8 +376,6 @@ if [ "$make_space" = "y" ]; then fi fi -vmz="$vmz$gzip" - # Extract kernel version information, some platforms want to include # it in the image header version=`${CROSS}strings "$kernel" | grep '^Linux version [-0-9.]' | \ @@ -417,6 +445,7 @@ if [ "$platform" != "miboot" ]; then if [ -n "$link_address" ] ; then text_start="-Ttext $link_address" fi +#link everything ${CROSS}ld -m $format -T $lds $text_start $pie -o "$ofile" \ $platformo $tmp $object/wrapper.a rm $tmp diff --git a/arch/powerpc/boot/xz_config.h b/arch/powerpc/boot/xz_config.h new file mode 100644 index 000000000000..5c6afdbca642 --- /dev/null +++ b/arch/powerpc/boot/xz_config.h @@ -0,0 +1,39 @@ +#ifndef __XZ_CONFIG_H__ +#define __XZ_CONFIG_H__ + +/* + * most of this is copied from lib/xz/xz_private.h, we can't use their defines + * since the boot wrapper is not built in the same environment as the rest of + * the kernel. + */ + +#include "types.h" +#include "swab.h" + +static inline uint32_t swab32p(void *p) +{ + uint32_t *q = p; + + return swab32(*q); +} + +#ifdef __LITTLE_ENDIAN__ +#define get_le32(p) (*((uint32_t *) (p))) +#else +#define get_le32(p) swab32p(p) +#endif + +#define memeq(a, b, size) (memcmp(a, b, size) == 0) +#define memzero(buf, size) memset(buf, 0, size) + +/* prevent the inclusion of the xz-preboot MM headers */ +#define DECOMPR_MM_H +#define memmove memmove +#define XZ_EXTERN static + +/* xz.h needs to be included directly since we need enum xz_mode */ +#include "../../../include/linux/xz.h" + +#undef XZ_EXTERN + +#endif diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index dce352e9153b..d98b6eb3254f 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -15,6 +15,8 @@ CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=18 +CONFIG_LOG_CPU_MAX_BUF_SHIFT=13 CONFIG_NUMA_BALANCING=y CONFIG_CGROUPS=y CONFIG_MEMCG=y @@ -95,7 +97,7 @@ CONFIG_BLK_DEV_IDECD=y CONFIG_BLK_DEV_GENERIC=y CONFIG_BLK_DEV_AMD74XX=y CONFIG_BLK_DEV_SD=y -CONFIG_CHR_DEV_ST=y +CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y @@ -107,7 +109,7 @@ CONFIG_SCSI_CXGB4_ISCSI=m CONFIG_SCSI_BNX2_ISCSI=m CONFIG_BE2ISCSI=m CONFIG_SCSI_MPT2SAS=m -CONFIG_SCSI_SYM53C8XX_2=y +CONFIG_SCSI_SYM53C8XX_2=m CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0 CONFIG_SCSI_IPR=y CONFIG_SCSI_QLA_FC=m @@ -149,10 +151,10 @@ CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m CONFIG_VHOST_NET=m -CONFIG_VORTEX=y +CONFIG_VORTEX=m CONFIG_ACENIC=m CONFIG_ACENIC_OMIT_TIGON_I=y -CONFIG_PCNET32=y +CONFIG_PCNET32=m CONFIG_TIGON3=y CONFIG_BNX2X=m CONFIG_CHELSIO_T1=m @@ -163,6 +165,7 @@ CONFIG_E1000=y CONFIG_E1000E=y CONFIG_IXGB=m CONFIG_IXGBE=m +CONFIG_I40E=m CONFIG_MLX4_EN=m CONFIG_MYRI10GE=m CONFIG_QLGE=m @@ -238,7 +241,7 @@ CONFIG_EXT2_FS_SECURITY=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -CONFIG_REISERFS_FS=y +CONFIG_REISERFS_FS=m CONFIG_REISERFS_FS_XATTR=y CONFIG_REISERFS_FS_POSIX_ACL=y CONFIG_REISERFS_FS_SECURITY=y @@ -253,10 +256,10 @@ CONFIG_NILFS2_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_OVERLAY_FS=m -CONFIG_ISO9660_FS=y +CONFIG_ISO9660_FS=m CONFIG_UDF_FS=m CONFIG_MSDOS_FS=y -CONFIG_VFAT_FS=y +CONFIG_VFAT_FS=m CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y @@ -310,6 +313,8 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_DEV_NX=y +CONFIG_CRYPTO_DEV_VMX=y +CONFIG_CRYPTO_DEV_VMX_ENCRYPT=m CONFIG_VIRTUALIZATION=y CONFIG_KVM_BOOK3S_64=m CONFIG_KVM_BOOK3S_64_HV=m diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 0a8d250cb97e..58a98d40086f 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -10,6 +10,8 @@ CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=18 +CONFIG_LOG_CPU_MAX_BUF_SHIFT=13 CONFIG_CGROUPS=y CONFIG_CPUSETS=y CONFIG_BLK_DEV_INITRD=y @@ -90,7 +92,7 @@ CONFIG_BLK_DEV_AMD74XX=y CONFIG_BLK_DEV_IDE_PMAC=y CONFIG_BLK_DEV_IDE_PMAC_ATA100FIRST=y CONFIG_BLK_DEV_SD=y -CONFIG_CHR_DEV_ST=y +CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y @@ -103,7 +105,7 @@ CONFIG_BE2ISCSI=m CONFIG_SCSI_MPT2SAS=m CONFIG_SCSI_IBMVSCSI=y CONFIG_SCSI_IBMVFC=m -CONFIG_SCSI_SYM53C8XX_2=y +CONFIG_SCSI_SYM53C8XX_2=m CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0 CONFIG_SCSI_IPR=y CONFIG_SCSI_QLA_FC=m @@ -149,10 +151,10 @@ CONFIG_NETCONSOLE=y CONFIG_TUN=m CONFIG_VIRTIO_NET=m CONFIG_VHOST_NET=m -CONFIG_VORTEX=y +CONFIG_VORTEX=m CONFIG_ACENIC=m CONFIG_ACENIC_OMIT_TIGON_I=y -CONFIG_PCNET32=y +CONFIG_PCNET32=m CONFIG_TIGON3=y CONFIG_BNX2X=m CONFIG_CHELSIO_T1=m @@ -165,6 +167,7 @@ CONFIG_E1000=y CONFIG_E1000E=y CONFIG_IXGB=m CONFIG_IXGBE=m +CONFIG_I40E=m CONFIG_MLX4_EN=m CONFIG_MYRI10GE=m CONFIG_PASEMI_MAC=y @@ -269,7 +272,7 @@ CONFIG_EXT2_FS_SECURITY=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -CONFIG_REISERFS_FS=y +CONFIG_REISERFS_FS=m CONFIG_REISERFS_FS_XATTR=y CONFIG_REISERFS_FS_POSIX_ACL=y CONFIG_REISERFS_FS_SECURITY=y @@ -284,10 +287,10 @@ CONFIG_NILFS2_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_OVERLAY_FS=m -CONFIG_ISO9660_FS=y +CONFIG_ISO9660_FS=m CONFIG_UDF_FS=m CONFIG_MSDOS_FS=y -CONFIG_VFAT_FS=y +CONFIG_VFAT_FS=m CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y @@ -347,6 +350,8 @@ CONFIG_CRYPTO_LZO=m # CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRYPTO_DEV_NX=y CONFIG_CRYPTO_DEV_NX_ENCRYPT=m +CONFIG_CRYPTO_DEV_VMX=y +CONFIG_CRYPTO_DEV_VMX_ENCRYPT=m CONFIG_VIRTUALIZATION=y CONFIG_KVM_BOOK3S_64=m CONFIG_KVM_BOOK3S_64_HV=m diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 654aeffc57ef..8a3bc016b732 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -15,6 +15,8 @@ CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=18 +CONFIG_LOG_CPU_MAX_BUF_SHIFT=13 CONFIG_NUMA_BALANCING=y CONFIG_NUMA_BALANCING_DEFAULT_ENABLED=y CONFIG_CGROUPS=y @@ -95,7 +97,7 @@ CONFIG_BLK_DEV_IDECD=y CONFIG_BLK_DEV_GENERIC=y CONFIG_BLK_DEV_AMD74XX=y CONFIG_BLK_DEV_SD=y -CONFIG_CHR_DEV_ST=y +CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y @@ -108,7 +110,7 @@ CONFIG_BE2ISCSI=m CONFIG_SCSI_MPT2SAS=m CONFIG_SCSI_IBMVSCSI=y CONFIG_SCSI_IBMVFC=m -CONFIG_SCSI_SYM53C8XX_2=y +CONFIG_SCSI_SYM53C8XX_2=m CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0 CONFIG_SCSI_IPR=y CONFIG_SCSI_QLA_FC=m @@ -150,10 +152,10 @@ CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m CONFIG_VHOST_NET=m -CONFIG_VORTEX=y +CONFIG_VORTEX=m CONFIG_ACENIC=m CONFIG_ACENIC_OMIT_TIGON_I=y -CONFIG_PCNET32=y +CONFIG_PCNET32=m CONFIG_TIGON3=y CONFIG_BNX2X=m CONFIG_CHELSIO_T1=m @@ -166,6 +168,7 @@ CONFIG_E1000=y CONFIG_E1000E=y CONFIG_IXGB=m CONFIG_IXGBE=m +CONFIG_I40E=m CONFIG_MLX4_EN=m CONFIG_MYRI10GE=m CONFIG_QLGE=m @@ -241,7 +244,7 @@ CONFIG_EXT2_FS_SECURITY=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -CONFIG_REISERFS_FS=y +CONFIG_REISERFS_FS=m CONFIG_REISERFS_FS_XATTR=y CONFIG_REISERFS_FS_POSIX_ACL=y CONFIG_REISERFS_FS_SECURITY=y @@ -256,10 +259,10 @@ CONFIG_NILFS2_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_OVERLAY_FS=m -CONFIG_ISO9660_FS=y +CONFIG_ISO9660_FS=m CONFIG_UDF_FS=m CONFIG_MSDOS_FS=y -CONFIG_VFAT_FS=y +CONFIG_VFAT_FS=m CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y @@ -314,6 +317,8 @@ CONFIG_CRYPTO_LZO=m # CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRYPTO_DEV_NX=y CONFIG_CRYPTO_DEV_NX_ENCRYPT=m +CONFIG_CRYPTO_DEV_VMX=y +CONFIG_CRYPTO_DEV_VMX_ENCRYPT=m CONFIG_VIRTUALIZATION=y CONFIG_KVM_BOOK3S_64=m CONFIG_KVM_BOOK3S_64_HV=m diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index e71b9097594c..d1492736d852 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -15,6 +15,8 @@ #include <linux/threads.h> #include <linux/kprobes.h> +#include <uapi/asm/ucontext.h> + /* SMP */ extern struct thread_info *current_set[NR_CPUS]; extern struct thread_info *secondary_ti; @@ -52,8 +54,8 @@ void SMIException(struct pt_regs *regs); void handle_hmi_exception(struct pt_regs *regs); void instruction_breakpoint_exception(struct pt_regs *regs); void RunModeException(struct pt_regs *regs); -void __kprobes single_step_exception(struct pt_regs *regs); -void __kprobes program_check_exception(struct pt_regs *regs); +void single_step_exception(struct pt_regs *regs); +void program_check_exception(struct pt_regs *regs); void alignment_exception(struct pt_regs *regs); void StackOverflow(struct pt_regs *regs); void nonrecoverable_exception(struct pt_regs *regs); @@ -70,6 +72,41 @@ void unrecoverable_exception(struct pt_regs *regs); void kernel_bad_stack(struct pt_regs *regs); void system_reset_exception(struct pt_regs *regs); void machine_check_exception(struct pt_regs *regs); -void __kprobes emulation_assist_interrupt(struct pt_regs *regs); +void emulation_assist_interrupt(struct pt_regs *regs); + +/* signals, syscalls and interrupts */ +#ifdef CONFIG_PPC64 +int sys_swapcontext(struct ucontext __user *old_ctx, + struct ucontext __user *new_ctx, + long ctx_size, long r6, long r7, long r8, struct pt_regs *regs); +#else +long sys_swapcontext(struct ucontext __user *old_ctx, + struct ucontext __user *new_ctx, + int ctx_size, int r6, int r7, int r8, struct pt_regs *regs); +#endif +long sys_switch_endian(void); +notrace unsigned int __check_irq_replay(void); +void notrace restore_interrupts(void); + +/* ptrace */ +long do_syscall_trace_enter(struct pt_regs *regs); +void do_syscall_trace_leave(struct pt_regs *regs); + +/* process */ +void restore_math(struct pt_regs *regs); +void restore_tm_state(struct pt_regs *regs); + +/* prom_init (OpenFirmware) */ +unsigned long __init prom_init(unsigned long r3, unsigned long r4, + unsigned long pp, + unsigned long r6, unsigned long r7, + unsigned long kbase); + +/* setup */ +void __init early_setup(unsigned long dt_ptr); +void early_setup_secondary(void); + +/* time */ +void accumulate_stolen_time(void); #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */ diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index f08d567e0ca4..2b90335194a7 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -233,7 +233,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %0,0,%1 # __atomic_add_unless\n\ cmpw 0,%0,%3 \n\ - beq- 2f \n\ + beq 2f \n\ add %0,%2,%0 \n" PPC405_ERR77(0,%2) " stwcx. %0,0,%1 \n\ @@ -539,7 +539,7 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) PPC_ATOMIC_ENTRY_BARRIER "1: ldarx %0,0,%1 # __atomic_add_unless\n\ cmpd 0,%0,%3 \n\ - beq- 2f \n\ + beq 2f \n\ add %0,%2,%0 \n" " stdcx. %0,0,%1 \n\ bne- 1b \n" diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 38b33dcfcc9d..6b8b2d57fdc8 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -223,7 +223,8 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, } -static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry) +static inline void __ptep_set_access_flags(struct mm_struct *mm, + pte_t *ptep, pte_t entry) { unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 287a656ceb57..e407af2b7333 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -245,6 +245,43 @@ static inline int segment_shift(int ssize) } /* + * This array is indexed by the LP field of the HPTE second dword. + * Since this field may contain some RPN bits, some entries are + * replicated so that we get the same value irrespective of RPN. + * The top 4 bits are the page size index (MMU_PAGE_*) for the + * actual page size, the bottom 4 bits are the base page size. + */ +extern u8 hpte_page_sizes[1 << LP_BITS]; + +static inline unsigned long __hpte_page_size(unsigned long h, unsigned long l, + bool is_base_size) +{ + unsigned int i, lp; + + if (!(h & HPTE_V_LARGE)) + return 1ul << 12; + + /* Look at the 8 bit LP value */ + lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1); + i = hpte_page_sizes[lp]; + if (!i) + return 0; + if (!is_base_size) + i >>= 4; + return 1ul << mmu_psize_defs[i & 0xf].shift; +} + +static inline unsigned long hpte_page_size(unsigned long h, unsigned long l) +{ + return __hpte_page_size(h, l, 0); +} + +static inline unsigned long hpte_base_page_size(unsigned long h, unsigned long l) +{ + return __hpte_page_size(h, l, 1); +} + +/* * The current system page and segment sizes */ extern int mmu_kernel_ssize; diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 263bf39ced40..9fd77f8794a0 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -6,6 +6,8 @@ */ #define _PAGE_BIT_SWAP_TYPE 0 +#define _PAGE_RO 0 + #define _PAGE_EXEC 0x00001 /* execute permission */ #define _PAGE_WRITE 0x00002 /* write access allowed */ #define _PAGE_READ 0x00004 /* read access allowed */ @@ -565,10 +567,11 @@ static inline bool check_pte_access(unsigned long access, unsigned long ptev) * Generic functions with hash/radix callbacks */ -static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry) +static inline void __ptep_set_access_flags(struct mm_struct *mm, + pte_t *ptep, pte_t entry) { if (radix_enabled()) - return radix__ptep_set_access_flags(ptep, entry); + return radix__ptep_set_access_flags(mm, ptep, entry); return hash__ptep_set_access_flags(ptep, entry); } diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index df294224e280..2a46dea8e1b1 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -11,6 +11,11 @@ #include <asm/book3s/64/radix-4k.h> #endif +#ifndef __ASSEMBLY__ +#include <asm/book3s/64/tlbflush-radix.h> +#include <asm/cpu_has_feature.h> +#endif + /* An empty PTE can still have a R or C writeback */ #define RADIX_PTE_NONE_MASK (_PAGE_DIRTY | _PAGE_ACCESSED) @@ -105,11 +110,8 @@ #define RADIX_PUD_TABLE_SIZE (sizeof(pud_t) << RADIX_PUD_INDEX_SIZE) #define RADIX_PGD_TABLE_SIZE (sizeof(pgd_t) << RADIX_PGD_INDEX_SIZE) -static inline unsigned long radix__pte_update(struct mm_struct *mm, - unsigned long addr, - pte_t *ptep, unsigned long clr, - unsigned long set, - int huge) +static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr, + unsigned long set) { pte_t pte; unsigned long old_pte, new_pte; @@ -121,9 +123,39 @@ static inline unsigned long radix__pte_update(struct mm_struct *mm, } while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); - /* We already do a sync in cmpxchg, is ptesync needed ?*/ + return old_pte; +} + + +static inline unsigned long radix__pte_update(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, unsigned long clr, + unsigned long set, + int huge) +{ + unsigned long old_pte; + + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) { + + unsigned long new_pte; + + old_pte = __radix_pte_update(ptep, ~0, 0); + asm volatile("ptesync" : : : "memory"); + /* + * new value of pte + */ + new_pte = (old_pte | set) & ~clr; + + /* + * For now let's do heavy pid flush + * radix__flush_tlb_page_psize(mm, addr, mmu_virtual_psize); + */ + radix__flush_tlb_mm(mm); + + __radix_pte_update(ptep, 0, new_pte); + } else + old_pte = __radix_pte_update(ptep, clr, set); asm volatile("ptesync" : : : "memory"); - /* huge pages use the old page table lock */ if (!huge) assert_pte_locked(mm, addr); @@ -134,20 +166,33 @@ static inline unsigned long radix__pte_update(struct mm_struct *mm, * Set the dirty and/or accessed bits atomically in a linux PTE, this * function doesn't need to invalidate tlb. */ -static inline void radix__ptep_set_access_flags(pte_t *ptep, pte_t entry) +static inline void radix__ptep_set_access_flags(struct mm_struct *mm, + pte_t *ptep, pte_t entry) { - pte_t pte; - unsigned long old_pte, new_pte; + unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); - do { - pte = READ_ONCE(*ptep); - old_pte = pte_val(pte); + + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) { + + unsigned long old_pte, new_pte; + + old_pte = __radix_pte_update(ptep, ~0, 0); + asm volatile("ptesync" : : : "memory"); + /* + * new value of pte + */ new_pte = old_pte | set; - } while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); + /* + * For now let's do heavy pid flush + * radix__flush_tlb_page_psize(mm, addr, mmu_virtual_psize); + */ + radix__flush_tlb_mm(mm); - /* We already do a sync in cmpxchg, is ptesync needed ?*/ + __radix_pte_update(ptep, 0, new_pte); + } else + __radix_pte_update(ptep, 0, set); asm volatile("ptesync" : : : "memory"); } @@ -233,14 +278,19 @@ static inline unsigned long radix__get_tree_size(void) { unsigned long rts_field; /* - * we support 52 bits, hence 52-31 = 21, 0b10101 + * We support 52 bits, hence: + * DD1 52-28 = 24, 0b11000 + * Others 52-31 = 21, 0b10101 * RTS encoding details * bits 0 - 3 of rts -> bits 6 - 8 unsigned long * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long */ - rts_field = (0x5UL << 5); /* 6 - 8 bits */ - rts_field |= (0x2UL << 61); - + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + rts_field = (0x3UL << 61); + else { + rts_field = (0x5UL << 5); /* 6 - 8 bits */ + rts_field |= (0x2UL << 61); + } return rts_field; } #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 65037762b120..a9e19cb2f7c5 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -41,4 +41,5 @@ extern void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmad extern void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa, unsigned long page_size); extern void radix__flush_tlb_lpid(unsigned long lpid); +extern void radix__flush_tlb_all(void); #endif diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h index 2ef55f8968a2..b312b152461b 100644 --- a/arch/powerpc/include/asm/cpu_has_feature.h +++ b/arch/powerpc/include/asm/cpu_has_feature.h @@ -15,7 +15,7 @@ static inline bool early_cpu_has_feature(unsigned long feature) #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS #include <linux/jump_label.h> -#define NUM_CPU_FTR_KEYS 64 +#define NUM_CPU_FTR_KEYS BITS_PER_LONG extern struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS]; diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 82026b419341..f752e6f7cfbe 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -212,6 +212,7 @@ enum { #define CPU_FTR_DABRX LONG_ASM_CONST(0x0800000000000000) #define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x1000000000000000) #define CPU_FTR_SUBCORE LONG_ASM_CONST(0x2000000000000000) +#define CPU_FTR_POWER9_DD1 LONG_ASM_CONST(0x4000000000000000) #ifndef __ASSEMBLY__ @@ -472,6 +473,7 @@ enum { CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300) +#define CPU_FTRS_POWER9_DD1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) #define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ @@ -490,7 +492,7 @@ enum { (CPU_FTRS_POWER4 | CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \ CPU_FTRS_POWER6 | CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | \ CPU_FTRS_POWER8 | CPU_FTRS_POWER8_DD1 | CPU_FTRS_CELL | \ - CPU_FTRS_PA6T | CPU_FTR_VSX | CPU_FTRS_POWER9) + CPU_FTRS_PA6T | CPU_FTR_VSX | CPU_FTRS_POWER9 | CPU_FTRS_POWER9_DD1) #endif #else enum { diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index 666bef4ebfae..9377bdf42eb8 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -3,6 +3,7 @@ #ifndef __ASSEMBLY__ #include <linux/cpumask.h> +#include <asm/cpu_has_feature.h> /* * Mapping of threads to cores diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index bed66e5743b3..2e4e7d878c8e 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -34,6 +34,7 @@ * exception handlers (including pSeries LPAR) and iSeries LPAR * implementations as possible. */ +#include <asm/head-64.h> #define EX_R9 0 #define EX_R10 8 @@ -52,7 +53,6 @@ #ifdef CONFIG_RELOCATABLE #define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) \ - ld r12,PACAKBASE(r13); /* get high part of &label */ \ mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ LOAD_HANDLER(r12,label); \ mtctr r12; \ @@ -84,13 +84,14 @@ /* * We're short on space and time in the exception prolog, so we can't - * use the normal SET_REG_IMMEDIATE macro. Normally we just need the - * low halfword of the address, but for Kdump we need the whole low - * word. + * use the normal LOAD_REG_IMMEDIATE macro to load the address of label. + * Instead we get the base of the kernel from paca->kernelbase and or in the low + * part of label. This requires that the label be within 64KB of kernelbase, and + * that kernelbase be 64K aligned. */ #define LOAD_HANDLER(reg, label) \ - /* Handlers must be within 64K of kbase, which must be 64k aligned */ \ - ori reg,reg,(label)-_stext; /* virt addr of handler ... */ + ld reg,PACAKBASE(r13); /* get high part of &label */ \ + ori reg,reg,(FIXED_SYMBOL_ABS_ADDR(label))@l; /* Exception register prefixes */ #define EXC_HV H @@ -175,7 +176,6 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) __EXCEPTION_PROLOG_1(area, extra, vec) #define __EXCEPTION_PROLOG_PSERIES_1(label, h) \ - ld r12,PACAKBASE(r13); /* get high part of &label */ \ ld r10,PACAKMSR(r13); /* get MSR value for kernel */ \ mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ LOAD_HANDLER(r12,label) \ @@ -192,10 +192,10 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) EXCEPTION_PROLOG_1(area, extra, vec); \ EXCEPTION_PROLOG_PSERIES_1(label, h); -#define __KVMTEST(n) \ - lbz r10,HSTATE_IN_GUEST(r13); \ +#define __KVMTEST(h, n) \ + lbz r10,HSTATE_IN_GUEST(r13); \ cmpwi r10,0; \ - bne do_kvm_##n + bne do_kvm_##h##n #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE /* @@ -208,8 +208,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define kvmppc_interrupt kvmppc_interrupt_pr #endif -#define __KVM_HANDLER(area, h, n) \ -do_kvm_##n: \ +#define __KVM_HANDLER_PROLOG(area, n) \ BEGIN_FTR_SECTION_NESTED(947) \ ld r10,area+EX_CFAR(r13); \ std r10,HSTATE_CFAR(r13); \ @@ -222,21 +221,23 @@ do_kvm_##n: \ stw r9,HSTATE_SCRATCH1(r13); \ ld r9,area+EX_R9(r13); \ std r12,HSTATE_SCRATCH0(r13); \ + +#define __KVM_HANDLER(area, h, n) \ + __KVM_HANDLER_PROLOG(area, n) \ li r12,n; \ b kvmppc_interrupt #define __KVM_HANDLER_SKIP(area, h, n) \ -do_kvm_##n: \ cmpwi r10,KVM_GUEST_MODE_SKIP; \ ld r10,area+EX_R10(r13); \ beq 89f; \ - stw r9,HSTATE_SCRATCH1(r13); \ + stw r9,HSTATE_SCRATCH1(r13); \ BEGIN_FTR_SECTION_NESTED(948) \ ld r9,area+EX_PPR(r13); \ std r9,HSTATE_PPR(r13); \ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948); \ ld r9,area+EX_R9(r13); \ - std r12,HSTATE_SCRATCH0(r13); \ + std r12,HSTATE_SCRATCH0(r13); \ li r12,n; \ b kvmppc_interrupt; \ 89: mtocrf 0x80,r9; \ @@ -244,12 +245,12 @@ do_kvm_##n: \ b kvmppc_skip_##h##interrupt #ifdef CONFIG_KVM_BOOK3S_64_HANDLER -#define KVMTEST(n) __KVMTEST(n) +#define KVMTEST(h, n) __KVMTEST(h, n) #define KVM_HANDLER(area, h, n) __KVM_HANDLER(area, h, n) #define KVM_HANDLER_SKIP(area, h, n) __KVM_HANDLER_SKIP(area, h, n) #else -#define KVMTEST(n) +#define KVMTEST(h, n) #define KVM_HANDLER(area, h, n) #define KVM_HANDLER_SKIP(area, h, n) #endif @@ -333,94 +334,79 @@ do_kvm_##n: \ /* * Exception vectors. */ -#define STD_EXCEPTION_PSERIES(vec, label) \ - . = vec; \ - .globl label##_pSeries; \ -label##_pSeries: \ +#define STD_EXCEPTION_PSERIES(vec, label) \ SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, \ - EXC_STD, KVMTEST, vec) + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label, \ + EXC_STD, KVMTEST_PR, vec); \ /* Version of above for when we have to branch out-of-line */ +#define __OOL_EXCEPTION(vec, label, hdlr) \ + SET_SCRATCH0(r13) \ + EXCEPTION_PROLOG_0(PACA_EXGEN) \ + b hdlr; + #define STD_EXCEPTION_PSERIES_OOL(vec, label) \ - .globl label##_pSeries; \ -label##_pSeries: \ - EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, vec); \ - EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_STD) - -#define STD_EXCEPTION_HV(loc, vec, label) \ - . = loc; \ - .globl label##_hv; \ -label##_hv: \ + EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, vec); \ + EXCEPTION_PROLOG_PSERIES_1(label, EXC_STD) + +#define STD_EXCEPTION_HV(loc, vec, label) \ SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, \ - EXC_HV, KVMTEST, vec) + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label, \ + EXC_HV, KVMTEST_HV, vec); -/* Version of above for when we have to branch out-of-line */ -#define STD_EXCEPTION_HV_OOL(vec, label) \ - .globl label##_hv; \ -label##_hv: \ - EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, vec); \ - EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_HV) +#define STD_EXCEPTION_HV_OOL(vec, label) \ + EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, vec); \ + EXCEPTION_PROLOG_PSERIES_1(label, EXC_HV) #define STD_RELON_EXCEPTION_PSERIES(loc, vec, label) \ - . = loc; \ - .globl label##_relon_pSeries; \ -label##_relon_pSeries: \ /* No guest interrupts come through here */ \ SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \ - EXC_STD, NOTEST, vec) + EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label, EXC_STD, NOTEST, vec); #define STD_RELON_EXCEPTION_PSERIES_OOL(vec, label) \ - .globl label##_relon_pSeries; \ -label##_relon_pSeries: \ EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec); \ - EXCEPTION_RELON_PROLOG_PSERIES_1(label##_common, EXC_STD) + EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_STD) #define STD_RELON_EXCEPTION_HV(loc, vec, label) \ - . = loc; \ - .globl label##_relon_hv; \ -label##_relon_hv: \ /* No guest interrupts come through here */ \ SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \ - EXC_HV, NOTEST, vec) + EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label, EXC_HV, NOTEST, vec); #define STD_RELON_EXCEPTION_HV_OOL(vec, label) \ - .globl label##_relon_hv; \ -label##_relon_hv: \ EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec); \ - EXCEPTION_RELON_PROLOG_PSERIES_1(label##_common, EXC_HV) + EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV) /* This associate vector numbers with bits in paca->irq_happened */ #define SOFTEN_VALUE_0x500 PACA_IRQ_EE -#define SOFTEN_VALUE_0x502 PACA_IRQ_EE #define SOFTEN_VALUE_0x900 PACA_IRQ_DEC -#define SOFTEN_VALUE_0x982 PACA_IRQ_DEC +#define SOFTEN_VALUE_0x980 PACA_IRQ_DEC #define SOFTEN_VALUE_0xa00 PACA_IRQ_DBELL #define SOFTEN_VALUE_0xe80 PACA_IRQ_DBELL -#define SOFTEN_VALUE_0xe82 PACA_IRQ_DBELL #define SOFTEN_VALUE_0xe60 PACA_IRQ_HMI -#define SOFTEN_VALUE_0xe62 PACA_IRQ_HMI #define SOFTEN_VALUE_0xea0 PACA_IRQ_EE -#define SOFTEN_VALUE_0xea2 PACA_IRQ_EE #define __SOFTEN_TEST(h, vec) \ lbz r10,PACASOFTIRQEN(r13); \ cmpwi r10,0; \ li r10,SOFTEN_VALUE_##vec; \ beq masked_##h##interrupt + #define _SOFTEN_TEST(h, vec) __SOFTEN_TEST(h, vec) #define SOFTEN_TEST_PR(vec) \ - KVMTEST(vec); \ + KVMTEST(EXC_STD, vec); \ _SOFTEN_TEST(EXC_STD, vec) #define SOFTEN_TEST_HV(vec) \ - KVMTEST(vec); \ + KVMTEST(EXC_HV, vec); \ _SOFTEN_TEST(EXC_HV, vec) +#define KVMTEST_PR(vec) \ + KVMTEST(EXC_STD, vec) + +#define KVMTEST_HV(vec) \ + KVMTEST(EXC_HV, vec) + #define SOFTEN_NOTEST_PR(vec) _SOFTEN_TEST(EXC_STD, vec) #define SOFTEN_NOTEST_HV(vec) _SOFTEN_TEST(EXC_HV, vec) @@ -428,58 +414,47 @@ label##_relon_hv: \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_PROLOG_0(PACA_EXGEN); \ __EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec); \ - EXCEPTION_PROLOG_PSERIES_1(label##_common, h); + EXCEPTION_PROLOG_PSERIES_1(label, h); #define _MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra) \ __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra) #define MASKABLE_EXCEPTION_PSERIES(loc, vec, label) \ - . = loc; \ - .globl label##_pSeries; \ -label##_pSeries: \ _MASKABLE_EXCEPTION_PSERIES(vec, label, \ EXC_STD, SOFTEN_TEST_PR) +#define MASKABLE_EXCEPTION_PSERIES_OOL(vec, label) \ + EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_PR, vec); \ + EXCEPTION_PROLOG_PSERIES_1(label, EXC_STD) + #define MASKABLE_EXCEPTION_HV(loc, vec, label) \ - . = loc; \ - .globl label##_hv; \ -label##_hv: \ _MASKABLE_EXCEPTION_PSERIES(vec, label, \ EXC_HV, SOFTEN_TEST_HV) #define MASKABLE_EXCEPTION_HV_OOL(vec, label) \ - .globl label##_hv; \ -label##_hv: \ EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec); \ - EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_HV); + EXCEPTION_PROLOG_PSERIES_1(label, EXC_HV) #define __MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra) \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_PROLOG_0(PACA_EXGEN); \ - __EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec); \ - EXCEPTION_RELON_PROLOG_PSERIES_1(label##_common, h); -#define _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra) \ + __EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec); \ + EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) + +#define _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra) \ __MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra) #define MASKABLE_RELON_EXCEPTION_PSERIES(loc, vec, label) \ - . = loc; \ - .globl label##_relon_pSeries; \ -label##_relon_pSeries: \ _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, \ EXC_STD, SOFTEN_NOTEST_PR) #define MASKABLE_RELON_EXCEPTION_HV(loc, vec, label) \ - . = loc; \ - .globl label##_relon_hv; \ -label##_relon_hv: \ _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, \ EXC_HV, SOFTEN_NOTEST_HV) #define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label) \ - .globl label##_relon_hv; \ -label##_relon_hv: \ EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_HV, vec); \ - EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_HV); + EXCEPTION_PROLOG_PSERIES_1(label, EXC_HV) /* * Our exception common code can be passed various "additions" @@ -505,9 +480,6 @@ BEGIN_FTR_SECTION \ END_FTR_SECTION_IFSET(CPU_FTR_CTRL) #define EXCEPTION_COMMON(trap, label, hdlr, ret, additions) \ - .align 7; \ - .globl label##_common; \ -label##_common: \ EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN); \ /* Volatile regs are potentially clobbered here */ \ additions; \ diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h index b4407d0add27..0031806475f0 100644 --- a/arch/powerpc/include/asm/fadump.h +++ b/arch/powerpc/include/asm/fadump.h @@ -45,10 +45,6 @@ #define memblock_num_regions(memblock_type) (memblock.memblock_type.cnt) -#ifndef ELF_CORE_EFLAGS -#define ELF_CORE_EFLAGS 0 -#endif - /* Firmware provided dump sections */ #define FADUMP_CPU_STATE_DATA 0x0001 #define FADUMP_HPTE_REGION 0x0002 diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h new file mode 100644 index 000000000000..ab90c2fa1ea6 --- /dev/null +++ b/arch/powerpc/include/asm/head-64.h @@ -0,0 +1,393 @@ +#ifndef _ASM_POWERPC_HEAD_64_H +#define _ASM_POWERPC_HEAD_64_H + +#include <asm/cache.h> + +/* + * We can't do CPP stringification and concatination directly into the section + * name for some reason, so these macros can do it for us. + */ +.macro define_ftsec name + .section ".head.text.\name\()","ax",@progbits +.endm +.macro define_data_ftsec name + .section ".head.data.\name\()","a",@progbits +.endm +.macro use_ftsec name + .section ".head.text.\name\()" +.endm + +/* + * Fixed (location) sections are used by opening fixed sections and emitting + * fixed section entries into them before closing them. Multiple fixed sections + * can be open at any time. + * + * Each fixed section created in a .S file must have corresponding linkage + * directives including location, added to arch/powerpc/kernel/vmlinux.lds.S + * + * For each fixed section, code is generated into it in the order which it + * appears in the source. Fixed section entries can be placed at a fixed + * location within the section using _LOCATION postifx variants. These must + * be ordered according to their relative placements within the section. + * + * OPEN_FIXED_SECTION(section_name, start_address, end_address) + * FIXED_SECTION_ENTRY_BEGIN(section_name, label1) + * + * USE_FIXED_SECTION(section_name) + * label3: + * li r10,128 + * mv r11,r10 + + * FIXED_SECTION_ENTRY_BEGIN_LOCATION(section_name, label2, start_address) + * FIXED_SECTION_ENTRY_END_LOCATION(section_name, label2, end_address) + * CLOSE_FIXED_SECTION(section_name) + * + * ZERO_FIXED_SECTION can be used to emit zeroed data. + * + * Troubleshooting: + * - If the build dies with "Error: attempt to move .org backwards" at + * CLOSE_FIXED_SECTION() or elsewhere, there may be something + * unexpected being added there. Remove the '. = x_len' line, rebuild, and + * check what is pushing the section down. + * - If the build dies in linking, check arch/powerpc/kernel/vmlinux.lds.S + * for instructions. + * - If the kernel crashes or hangs in very early boot, it could be linker + * stubs at the start of the main text. + */ + +#define OPEN_FIXED_SECTION(sname, start, end) \ + sname##_start = (start); \ + sname##_end = (end); \ + sname##_len = (end) - (start); \ + define_ftsec sname; \ + . = 0x0; \ +start_##sname: + +#define OPEN_TEXT_SECTION(start) \ + text_start = (start); \ + .section ".text","ax",@progbits; \ + . = 0x0; \ +start_text: + +#define ZERO_FIXED_SECTION(sname, start, end) \ + sname##_start = (start); \ + sname##_end = (end); \ + sname##_len = (end) - (start); \ + define_data_ftsec sname; \ + . = 0x0; \ + . = sname##_len; + +#define USE_FIXED_SECTION(sname) \ + fs_label = start_##sname; \ + fs_start = sname##_start; \ + use_ftsec sname; + +#define USE_TEXT_SECTION() \ + fs_label = start_text; \ + fs_start = text_start; \ + .text + +#define CLOSE_FIXED_SECTION(sname) \ + USE_FIXED_SECTION(sname); \ + . = sname##_len; \ +end_##sname: + + +#define __FIXED_SECTION_ENTRY_BEGIN(sname, name, __align) \ + USE_FIXED_SECTION(sname); \ + .align __align; \ + .global name; \ +name: + +#define FIXED_SECTION_ENTRY_BEGIN(sname, name) \ + __FIXED_SECTION_ENTRY_BEGIN(sname, name, 0) + +#define FIXED_SECTION_ENTRY_BEGIN_LOCATION(sname, name, start) \ + USE_FIXED_SECTION(sname); \ + name##_start = (start); \ + .if (start) < sname##_start; \ + .error "Fixed section underflow"; \ + .abort; \ + .endif; \ + . = (start) - sname##_start; \ + .global name; \ +name: + +#define FIXED_SECTION_ENTRY_END_LOCATION(sname, name, end) \ + .if (end) > sname##_end; \ + .error "Fixed section overflow"; \ + .abort; \ + .endif; \ + .if (. - name > end - name##_start); \ + .error "Fixed entry overflow"; \ + .abort; \ + .endif; \ + . = ((end) - sname##_start); \ + + +/* + * These macros are used to change symbols in other fixed sections to be + * absolute or related to our current fixed section. + * + * - DEFINE_FIXED_SYMBOL / FIXED_SYMBOL_ABS_ADDR is used to find the + * absolute address of a symbol within a fixed section, from any section. + * + * - ABS_ADDR is used to find the absolute address of any symbol, from within + * a fixed section. + */ +#define DEFINE_FIXED_SYMBOL(label) \ + label##_absolute = (label - fs_label + fs_start) + +#define FIXED_SYMBOL_ABS_ADDR(label) \ + (label##_absolute) + +#define ABS_ADDR(label) (label - fs_label + fs_start) + +/* + * Following are the BOOK3S exception handler helper macros. + * Handlers come in a number of types, and each type has a number of varieties. + * + * EXC_REAL_* - real, unrelocated exception vectors + * EXC_VIRT_* - virt (AIL), unrelocated exception vectors + * TRAMP_REAL_* - real, unrelocated helpers (virt can call these) + * TRAMP_VIRT_* - virt, unreloc helpers (in practice, real can use) + * TRAMP_KVM - KVM handlers that get put into real, unrelocated + * EXC_COMMON_* - virt, relocated common handlers + * + * The EXC handlers are given a name, and branch to name_common, or the + * appropriate KVM or masking function. Vector handler verieties are as + * follows: + * + * EXC_{REAL|VIRT}_BEGIN/END - used to open-code the exception + * + * EXC_{REAL|VIRT} - standard exception + * + * EXC_{REAL|VIRT}_suffix + * where _suffix is: + * - _MASKABLE - maskable exception + * - _OOL - out of line with trampoline to common handler + * - _HV - HV exception + * + * There can be combinations, e.g., EXC_VIRT_OOL_MASKABLE_HV + * + * The one unusual case is __EXC_REAL_OOL_HV_DIRECT, which is + * an OOL vector that branches to a specified handler rather than the usual + * trampoline that goes to common. It, and other underscore macros, should + * be used with care. + * + * KVM handlers come in the following verieties: + * TRAMP_KVM + * TRAMP_KVM_SKIP + * TRAMP_KVM_HV + * TRAMP_KVM_HV_SKIP + * + * COMMON handlers come in the following verieties: + * EXC_COMMON_BEGIN/END - used to open-code the handler + * EXC_COMMON + * EXC_COMMON_ASYNC + * EXC_COMMON_HV + * + * TRAMP_REAL and TRAMP_VIRT can be used with BEGIN/END. KVM + * and OOL handlers are implemented as types of TRAMP and TRAMP_VIRT handlers. + */ + +#define EXC_REAL_BEGIN(name, start, end) \ + FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##name, start) + +#define EXC_REAL_END(name, start, end) \ + FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##name, end) + +#define EXC_VIRT_BEGIN(name, start, end) \ + FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##name, start) + +#define EXC_VIRT_END(name, start, end) \ + FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##name, end) + +#define EXC_COMMON_BEGIN(name) \ + USE_TEXT_SECTION(); \ + .align 7; \ + .global name; \ + DEFINE_FIXED_SYMBOL(name); \ +name: + +#define TRAMP_REAL_BEGIN(name) \ + FIXED_SECTION_ENTRY_BEGIN(real_trampolines, name) + +#define TRAMP_VIRT_BEGIN(name) \ + FIXED_SECTION_ENTRY_BEGIN(virt_trampolines, name) + +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +#define TRAMP_KVM_BEGIN(name) \ + TRAMP_REAL_BEGIN(name) +#else +#define TRAMP_KVM_BEGIN(name) +#endif + +#define EXC_REAL_NONE(start, end) \ + FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##unused, start); \ + FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##unused, end) + +#define EXC_VIRT_NONE(start, end) \ + FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##unused, start); \ + FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##unused, end); + + +#define EXC_REAL(name, start, end) \ + EXC_REAL_BEGIN(name, start, end); \ + STD_EXCEPTION_PSERIES(start, name##_common); \ + EXC_REAL_END(name, start, end); + +#define EXC_VIRT(name, start, end, realvec) \ + EXC_VIRT_BEGIN(name, start, end); \ + STD_RELON_EXCEPTION_PSERIES(start, realvec, name##_common); \ + EXC_VIRT_END(name, start, end); + +#define EXC_REAL_MASKABLE(name, start, end) \ + EXC_REAL_BEGIN(name, start, end); \ + MASKABLE_EXCEPTION_PSERIES(start, start, name##_common); \ + EXC_REAL_END(name, start, end); + +#define EXC_VIRT_MASKABLE(name, start, end, realvec) \ + EXC_VIRT_BEGIN(name, start, end); \ + MASKABLE_RELON_EXCEPTION_PSERIES(start, realvec, name##_common); \ + EXC_VIRT_END(name, start, end); + +#define EXC_REAL_HV(name, start, end) \ + EXC_REAL_BEGIN(name, start, end); \ + STD_EXCEPTION_HV(start, start, name##_common); \ + EXC_REAL_END(name, start, end); + +#define EXC_VIRT_HV(name, start, end, realvec) \ + EXC_VIRT_BEGIN(name, start, end); \ + STD_RELON_EXCEPTION_HV(start, realvec, name##_common); \ + EXC_VIRT_END(name, start, end); + +#define __EXC_REAL_OOL(name, start, end) \ + EXC_REAL_BEGIN(name, start, end); \ + __OOL_EXCEPTION(start, label, tramp_real_##name); \ + EXC_REAL_END(name, start, end); + +#define __TRAMP_REAL_REAL_OOL(name, vec) \ + TRAMP_REAL_BEGIN(tramp_real_##name); \ + STD_EXCEPTION_PSERIES_OOL(vec, name##_common); \ + +#define EXC_REAL_OOL(name, start, end) \ + __EXC_REAL_OOL(name, start, end); \ + __TRAMP_REAL_REAL_OOL(name, start); + +#define __EXC_REAL_OOL_MASKABLE(name, start, end) \ + __EXC_REAL_OOL(name, start, end); + +#define __TRAMP_REAL_REAL_OOL_MASKABLE(name, vec) \ + TRAMP_REAL_BEGIN(tramp_real_##name); \ + MASKABLE_EXCEPTION_PSERIES_OOL(vec, name##_common); \ + +#define EXC_REAL_OOL_MASKABLE(name, start, end) \ + __EXC_REAL_OOL_MASKABLE(name, start, end); \ + __TRAMP_REAL_REAL_OOL_MASKABLE(name, start); + +#define __EXC_REAL_OOL_HV_DIRECT(name, start, end, handler) \ + EXC_REAL_BEGIN(name, start, end); \ + __OOL_EXCEPTION(start, label, handler); \ + EXC_REAL_END(name, start, end); + +#define __EXC_REAL_OOL_HV(name, start, end) \ + __EXC_REAL_OOL(name, start, end); + +#define __TRAMP_REAL_REAL_OOL_HV(name, vec) \ + TRAMP_REAL_BEGIN(tramp_real_##name); \ + STD_EXCEPTION_HV_OOL(vec, name##_common); \ + +#define EXC_REAL_OOL_HV(name, start, end) \ + __EXC_REAL_OOL_HV(name, start, end); \ + __TRAMP_REAL_REAL_OOL_HV(name, start); + +#define __EXC_REAL_OOL_MASKABLE_HV(name, start, end) \ + __EXC_REAL_OOL(name, start, end); + +#define __TRAMP_REAL_REAL_OOL_MASKABLE_HV(name, vec) \ + TRAMP_REAL_BEGIN(tramp_real_##name); \ + MASKABLE_EXCEPTION_HV_OOL(vec, name##_common); \ + +#define EXC_REAL_OOL_MASKABLE_HV(name, start, end) \ + __EXC_REAL_OOL_MASKABLE_HV(name, start, end); \ + __TRAMP_REAL_REAL_OOL_MASKABLE_HV(name, start); + +#define __EXC_VIRT_OOL(name, start, end) \ + EXC_VIRT_BEGIN(name, start, end); \ + __OOL_EXCEPTION(start, label, tramp_virt_##name); \ + EXC_VIRT_END(name, start, end); + +#define __TRAMP_REAL_VIRT_OOL(name, realvec) \ + TRAMP_VIRT_BEGIN(tramp_virt_##name); \ + STD_RELON_EXCEPTION_PSERIES_OOL(realvec, name##_common); \ + +#define EXC_VIRT_OOL(name, start, end, realvec) \ + __EXC_VIRT_OOL(name, start, end); \ + __TRAMP_REAL_VIRT_OOL(name, realvec); + +#define __EXC_VIRT_OOL_MASKABLE(name, start, end) \ + __EXC_VIRT_OOL(name, start, end); + +#define __TRAMP_REAL_VIRT_OOL_MASKABLE(name, realvec) \ + TRAMP_VIRT_BEGIN(tramp_virt_##name); \ + MASKABLE_RELON_EXCEPTION_PSERIES_OOL(realvec, name##_common); \ + +#define EXC_VIRT_OOL_MASKABLE(name, start, end, realvec) \ + __EXC_VIRT_OOL_MASKABLE(name, start, end); \ + __TRAMP_REAL_VIRT_OOL_MASKABLE(name, realvec); + +#define __EXC_VIRT_OOL_HV(name, start, end) \ + __EXC_VIRT_OOL(name, start, end); + +#define __TRAMP_REAL_VIRT_OOL_HV(name, realvec) \ + TRAMP_VIRT_BEGIN(tramp_virt_##name); \ + STD_RELON_EXCEPTION_HV_OOL(realvec, name##_common); \ + +#define EXC_VIRT_OOL_HV(name, start, end, realvec) \ + __EXC_VIRT_OOL_HV(name, start, end); \ + __TRAMP_REAL_VIRT_OOL_HV(name, realvec); + +#define __EXC_VIRT_OOL_MASKABLE_HV(name, start, end) \ + __EXC_VIRT_OOL(name, start, end); + +#define __TRAMP_REAL_VIRT_OOL_MASKABLE_HV(name, realvec) \ + TRAMP_VIRT_BEGIN(tramp_virt_##name); \ + MASKABLE_RELON_EXCEPTION_HV_OOL(realvec, name##_common); \ + +#define EXC_VIRT_OOL_MASKABLE_HV(name, start, end, realvec) \ + __EXC_VIRT_OOL_MASKABLE_HV(name, start, end); \ + __TRAMP_REAL_VIRT_OOL_MASKABLE_HV(name, realvec); + +#define TRAMP_KVM(area, n) \ + TRAMP_KVM_BEGIN(do_kvm_##n); \ + KVM_HANDLER(area, EXC_STD, n); \ + +#define TRAMP_KVM_SKIP(area, n) \ + TRAMP_KVM_BEGIN(do_kvm_##n); \ + KVM_HANDLER_SKIP(area, EXC_STD, n); \ + +/* + * HV variant exceptions get the 0x2 bit added to their trap number. + */ +#define TRAMP_KVM_HV(area, n) \ + TRAMP_KVM_BEGIN(do_kvm_H##n); \ + KVM_HANDLER(area, EXC_HV, n + 0x2); \ + +#define TRAMP_KVM_HV_SKIP(area, n) \ + TRAMP_KVM_BEGIN(do_kvm_H##n); \ + KVM_HANDLER_SKIP(area, EXC_HV, n + 0x2); \ + +#define EXC_COMMON(name, realvec, hdlr) \ + EXC_COMMON_BEGIN(name); \ + STD_EXCEPTION_COMMON(realvec, name, hdlr); \ + +#define EXC_COMMON_ASYNC(name, realvec, hdlr) \ + EXC_COMMON_BEGIN(name); \ + STD_EXCEPTION_COMMON_ASYNC(realvec, name, hdlr); \ + +#define EXC_COMMON_HV(name, realvec, hdlr) \ + EXC_COMMON_BEGIN(name); \ + STD_EXCEPTION_COMMON(realvec + 0x2, name, hdlr); \ + +#endif /* _ASM_POWERPC_HEAD_64_H */ diff --git a/arch/powerpc/include/asm/hmi.h b/arch/powerpc/include/asm/hmi.h index 88b4901ac4ee..85b7a1a21e22 100644 --- a/arch/powerpc/include/asm/hmi.h +++ b/arch/powerpc/include/asm/hmi.h @@ -21,7 +21,7 @@ #ifndef __ASM_PPC64_HMI_H__ #define __ASM_PPC64_HMI_H__ -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE #define CORE_TB_RESYNC_REQ_BIT 63 #define MAX_SUBCORE_PER_CORE 4 diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 2fd1690b79d2..f6fda8482f60 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -241,6 +241,35 @@ static inline void out_be64(volatile u64 __iomem *addr, u64 val) #endif #endif /* __powerpc64__ */ + +/* + * Simple Cache inhibited accessors + * Unlike the DEF_MMIO_* macros, these don't include any h/w memory + * barriers, callers need to manage memory barriers on their own. + * These can only be used in hypervisor real mode. + */ + +static inline u32 _lwzcix(unsigned long addr) +{ + u32 ret; + + __asm__ __volatile__("lwzcix %0,0, %1" + : "=r" (ret) : "r" (addr) : "memory"); + return ret; +} + +static inline void _stbcix(u64 addr, u8 val) +{ + __asm__ __volatile__("stbcix %0,0,%1" + : : "r" (val), "r" (addr) : "memory"); +} + +static inline void _stwcix(u64 addr, u32 val) +{ + __asm__ __volatile__("stwcix %0,0,%1" + : : "r" (val), "r" (addr) : "memory"); +} + /* * Low level IO stream instructions are defined out of line for now */ diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 5bca220bbb60..05cabed3d1bd 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -105,6 +105,15 @@ #define BOOK3S_INTERRUPT_FAC_UNAVAIL 0xf60 #define BOOK3S_INTERRUPT_H_FAC_UNAVAIL 0xf80 +/* book3s_hv */ + +/* + * Special trap used to indicate to host that this is a + * passthrough interrupt that could not be handled + * completely in the guest. + */ +#define BOOK3S_INTERRUPT_HV_RM_HARD 0x5555 + #define BOOK3S_IRQPRIO_SYSTEM_RESET 0 #define BOOK3S_IRQPRIO_DATA_SEGMENT 1 #define BOOK3S_IRQPRIO_INST_SEGMENT 2 @@ -136,6 +145,7 @@ #define RESUME_FLAG_NV (1<<0) /* Reload guest nonvolatile state? */ #define RESUME_FLAG_HOST (1<<1) /* Resume host? */ #define RESUME_FLAG_ARCH1 (1<<2) +#define RESUME_FLAG_ARCH2 (1<<3) #define RESUME_GUEST 0 #define RESUME_GUEST_NV RESUME_FLAG_NV diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 8f39796c9da8..5cf306ae0ac3 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -69,6 +69,43 @@ struct hpte_cache { int pagesize; }; +/* + * Struct for a virtual core. + * Note: entry_exit_map combines a bitmap of threads that have entered + * in the bottom 8 bits and a bitmap of threads that have exited in the + * next 8 bits. This is so that we can atomically set the entry bit + * iff the exit map is 0 without taking a lock. + */ +struct kvmppc_vcore { + int n_runnable; + int num_threads; + int entry_exit_map; + int napping_threads; + int first_vcpuid; + u16 pcpu; + u16 last_cpu; + u8 vcore_state; + u8 in_guest; + struct kvmppc_vcore *master_vcore; + struct kvm_vcpu *runnable_threads[MAX_SMT_THREADS]; + struct list_head preempt_list; + spinlock_t lock; + struct swait_queue_head wq; + spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */ + u64 stolen_tb; + u64 preempt_tb; + struct kvm_vcpu *runner; + struct kvm *kvm; + u64 tb_offset; /* guest timebase - host timebase */ + ulong lpcr; + u32 arch_compat; + ulong pcr; + ulong dpdes; /* doorbell state (POWER8) */ + ulong vtb; /* virtual timebase */ + ulong conferring_threads; + unsigned int halt_poll_ns; +}; + struct kvmppc_vcpu_book3s { struct kvmppc_sid_map sid_map[SID_MAP_NUM]; struct { @@ -83,6 +120,7 @@ struct kvmppc_vcpu_book3s { u64 sdr1; u64 hior; u64 msr_mask; + u64 vtb; #ifdef CONFIG_PPC_BOOK3S_32 u32 vsid_pool[VSID_POOL_SIZE]; u32 vsid_next; @@ -191,6 +229,7 @@ extern void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu, struct kvm_vcpu *vcpu); extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu, struct kvmppc_book3s_shadow_vcpu *svcpu); +extern int kvm_irq_bypass; static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) { diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 88d17b4ea9c8..848292176908 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -20,6 +20,8 @@ #ifndef __ASM_KVM_BOOK3S_64_H__ #define __ASM_KVM_BOOK3S_64_H__ +#include <asm/book3s/64/mmu-hash.h> + #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu) { @@ -97,56 +99,20 @@ static inline void __unlock_hpte(__be64 *hpte, unsigned long hpte_v) hpte[0] = cpu_to_be64(hpte_v); } -static inline int __hpte_actual_psize(unsigned int lp, int psize) -{ - int i, shift; - unsigned int mask; - - /* start from 1 ignoring MMU_PAGE_4K */ - for (i = 1; i < MMU_PAGE_COUNT; i++) { - - /* invalid penc */ - if (mmu_psize_defs[psize].penc[i] == -1) - continue; - /* - * encoding bits per actual page size - * PTE LP actual page size - * rrrr rrrz >=8KB - * rrrr rrzz >=16KB - * rrrr rzzz >=32KB - * rrrr zzzz >=64KB - * ....... - */ - shift = mmu_psize_defs[i].shift - LP_SHIFT; - if (shift > LP_BITS) - shift = LP_BITS; - mask = (1 << shift) - 1; - if ((lp & mask) == mmu_psize_defs[psize].penc[i]) - return i; - } - return -1; -} - static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, unsigned long pte_index) { - int b_psize = MMU_PAGE_4K, a_psize = MMU_PAGE_4K; + int i, b_psize = MMU_PAGE_4K, a_psize = MMU_PAGE_4K; unsigned int penc; unsigned long rb = 0, va_low, sllp; unsigned int lp = (r >> LP_SHIFT) & ((1 << LP_BITS) - 1); if (v & HPTE_V_LARGE) { - for (b_psize = 0; b_psize < MMU_PAGE_COUNT; b_psize++) { - - /* valid entries have a shift value */ - if (!mmu_psize_defs[b_psize].shift) - continue; - - a_psize = __hpte_actual_psize(lp, b_psize); - if (a_psize != -1) - break; - } + i = hpte_page_sizes[lp]; + b_psize = i & 0xf; + a_psize = i >> 4; } + /* * Ignore the top 14 bits of va * v have top two bits covering segment size, hence move @@ -159,7 +125,6 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, /* This covers 14..54 bits of va*/ rb = (v & ~0x7fUL) << 16; /* AVA field */ - rb |= (v >> HPTE_V_SSIZE_SHIFT) << 8; /* B field */ /* * AVA in v had cleared lower 23 bits. We need to derive * that from pteg index @@ -211,49 +176,10 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, break; } } - rb |= (v >> 54) & 0x300; /* B field */ + rb |= (v >> HPTE_V_SSIZE_SHIFT) << 8; /* B field */ return rb; } -static inline unsigned long __hpte_page_size(unsigned long h, unsigned long l, - bool is_base_size) -{ - - int size, a_psize; - /* Look at the 8 bit LP value */ - unsigned int lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1); - - /* only handle 4k, 64k and 16M pages for now */ - if (!(h & HPTE_V_LARGE)) - return 1ul << 12; - else { - for (size = 0; size < MMU_PAGE_COUNT; size++) { - /* valid entries have a shift value */ - if (!mmu_psize_defs[size].shift) - continue; - - a_psize = __hpte_actual_psize(lp, size); - if (a_psize != -1) { - if (is_base_size) - return 1ul << mmu_psize_defs[size].shift; - return 1ul << mmu_psize_defs[a_psize].shift; - } - } - - } - return 0; -} - -static inline unsigned long hpte_page_size(unsigned long h, unsigned long l) -{ - return __hpte_page_size(h, l, 0); -} - -static inline unsigned long hpte_base_page_size(unsigned long h, unsigned long l) -{ - return __hpte_page_size(h, l, 1); -} - static inline unsigned long hpte_rpn(unsigned long ptel, unsigned long psize) { return ((ptel & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index ec35af34a3fb..28350a294b1e 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -43,6 +43,8 @@ #include <asm/cputhreads.h> #define KVM_MAX_VCPU_ID (threads_per_subcore * KVM_MAX_VCORES) +#define __KVM_HAVE_ARCH_INTC_INITIALIZED + #ifdef CONFIG_KVM_MMIO #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 #endif @@ -95,42 +97,49 @@ struct kvmppc_vcpu_book3s; struct kvmppc_book3s_shadow_vcpu; struct kvm_vm_stat { - u32 remote_tlb_flush; + ulong remote_tlb_flush; }; struct kvm_vcpu_stat { - u32 sum_exits; - u32 mmio_exits; - u32 signal_exits; - u32 light_exits; + u64 sum_exits; + u64 mmio_exits; + u64 signal_exits; + u64 light_exits; /* Account for special types of light exits: */ - u32 itlb_real_miss_exits; - u32 itlb_virt_miss_exits; - u32 dtlb_real_miss_exits; - u32 dtlb_virt_miss_exits; - u32 syscall_exits; - u32 isi_exits; - u32 dsi_exits; - u32 emulated_inst_exits; - u32 dec_exits; - u32 ext_intr_exits; - u32 halt_successful_poll; - u32 halt_attempted_poll; - u32 halt_poll_invalid; - u32 halt_wakeup; - u32 dbell_exits; - u32 gdbell_exits; - u32 ld; - u32 st; + u64 itlb_real_miss_exits; + u64 itlb_virt_miss_exits; + u64 dtlb_real_miss_exits; + u64 dtlb_virt_miss_exits; + u64 syscall_exits; + u64 isi_exits; + u64 dsi_exits; + u64 emulated_inst_exits; + u64 dec_exits; + u64 ext_intr_exits; + u64 halt_poll_success_ns; + u64 halt_poll_fail_ns; + u64 halt_wait_ns; + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_successful_wait; + u64 halt_poll_invalid; + u64 halt_wakeup; + u64 dbell_exits; + u64 gdbell_exits; + u64 ld; + u64 st; #ifdef CONFIG_PPC_BOOK3S - u32 pf_storage; - u32 pf_instruc; - u32 sp_storage; - u32 sp_instruc; - u32 queue_intr; - u32 ld_slow; - u32 st_slow; + u64 pf_storage; + u64 pf_instruc; + u64 sp_storage; + u64 sp_instruc; + u64 queue_intr; + u64 ld_slow; + u64 st_slow; #endif + u64 pthru_all; + u64 pthru_host; + u64 pthru_bad_aff; }; enum kvm_exit_types { @@ -197,6 +206,8 @@ struct kvmppc_spapr_tce_table { struct kvmppc_xics; struct kvmppc_icp; +struct kvmppc_passthru_irqmap; + /* * The reverse mapping array has one entry for each HPTE, * which stores the guest's view of the second word of the HPTE @@ -267,6 +278,7 @@ struct kvm_arch { #endif #ifdef CONFIG_KVM_XICS struct kvmppc_xics *xics; + struct kvmppc_passthru_irqmap *pimap; #endif struct kvmppc_ops *kvm_ops; #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -275,41 +287,6 @@ struct kvm_arch { #endif }; -/* - * Struct for a virtual core. - * Note: entry_exit_map combines a bitmap of threads that have entered - * in the bottom 8 bits and a bitmap of threads that have exited in the - * next 8 bits. This is so that we can atomically set the entry bit - * iff the exit map is 0 without taking a lock. - */ -struct kvmppc_vcore { - int n_runnable; - int num_threads; - int entry_exit_map; - int napping_threads; - int first_vcpuid; - u16 pcpu; - u16 last_cpu; - u8 vcore_state; - u8 in_guest; - struct kvmppc_vcore *master_vcore; - struct list_head runnable_threads; - struct list_head preempt_list; - spinlock_t lock; - struct swait_queue_head wq; - spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */ - u64 stolen_tb; - u64 preempt_tb; - struct kvm_vcpu *runner; - struct kvm *kvm; - u64 tb_offset; /* guest timebase - host timebase */ - ulong lpcr; - u32 arch_compat; - ulong pcr; - ulong dpdes; /* doorbell state (POWER8) */ - ulong conferring_threads; -}; - #define VCORE_ENTRY_MAP(vc) ((vc)->entry_exit_map & 0xff) #define VCORE_EXIT_MAP(vc) ((vc)->entry_exit_map >> 8) #define VCORE_IS_EXITING(vc) (VCORE_EXIT_MAP(vc) != 0) @@ -329,6 +306,7 @@ struct kvmppc_vcore { #define VCORE_SLEEPING 3 #define VCORE_RUNNING 4 #define VCORE_EXITING 5 +#define VCORE_POLLING 6 /* * Struct used to manage memory for a virtual processor area @@ -397,6 +375,20 @@ struct kvmhv_tb_accumulator { u64 tb_max; /* max time */ }; +#ifdef CONFIG_PPC_BOOK3S_64 +struct kvmppc_irq_map { + u32 r_hwirq; + u32 v_hwirq; + struct irq_desc *desc; +}; + +#define KVMPPC_PIRQ_MAPPED 1024 +struct kvmppc_passthru_irqmap { + int n_mapped; + struct kvmppc_irq_map mapped[KVMPPC_PIRQ_MAPPED]; +}; +#endif + # ifdef CONFIG_PPC_FSL_BOOK3E #define KVMPPC_BOOKE_IAC_NUM 2 #define KVMPPC_BOOKE_DAC_NUM 2 @@ -483,7 +475,6 @@ struct kvm_vcpu_arch { ulong purr; ulong spurr; ulong ic; - ulong vtb; ulong dscr; ulong amr; ulong uamor; @@ -668,7 +659,6 @@ struct kvm_vcpu_arch { long pgfault_index; unsigned long pgfault_hpte[2]; - struct list_head run_list; struct task_struct *run_task; struct kvm_run *kvm_run; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 2544edabe7f3..f6e49640dbe1 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -287,6 +287,10 @@ struct kvmppc_ops { long (*arch_vm_ioctl)(struct file *filp, unsigned int ioctl, unsigned long arg); int (*hcall_implemented)(unsigned long hcall); + int (*irq_bypass_add_producer)(struct irq_bypass_consumer *, + struct irq_bypass_producer *); + void (*irq_bypass_del_producer)(struct irq_bypass_consumer *, + struct irq_bypass_producer *); }; extern struct kvmppc_ops *kvmppc_hv_ops; @@ -453,8 +457,19 @@ static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) { return vcpu->arch.irq_type == KVMPPC_IRQ_XICS; } + +static inline struct kvmppc_passthru_irqmap *kvmppc_get_passthru_irqmap( + struct kvm *kvm) +{ + if (kvm && kvm_irq_bypass) + return kvm->arch.pimap; + return NULL; +} + extern void kvmppc_alloc_host_rm_ops(void); extern void kvmppc_free_host_rm_ops(void); +extern void kvmppc_free_pimap(struct kvm *kvm); +extern int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall); extern void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu); extern int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server); extern int kvm_vm_ioctl_xics_irq(struct kvm *kvm, struct kvm_irq_level *args); @@ -464,10 +479,23 @@ extern int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval); extern int kvmppc_xics_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, u32 cpu); extern void kvmppc_xics_ipi_action(void); +extern void kvmppc_xics_set_mapped(struct kvm *kvm, unsigned long guest_irq, + unsigned long host_irq); +extern void kvmppc_xics_clr_mapped(struct kvm *kvm, unsigned long guest_irq, + unsigned long host_irq); +extern long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu, u32 xirr, + struct kvmppc_irq_map *irq_map, + struct kvmppc_passthru_irqmap *pimap); extern int h_ipi_redirect; #else +static inline struct kvmppc_passthru_irqmap *kvmppc_get_passthru_irqmap( + struct kvm *kvm) + { return NULL; } static inline void kvmppc_alloc_host_rm_ops(void) {}; static inline void kvmppc_free_host_rm_ops(void) {}; +static inline void kvmppc_free_pimap(struct kvm *kvm) {}; +static inline int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall) + { return 0; } static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) { return 0; } static inline void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu) { } diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 0420b388dd83..e02cbc6a6c70 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -61,7 +61,7 @@ struct machdep_calls { void (*init_IRQ)(void); - /* Return an irq, or NO_IRQ to indicate there are none pending. */ + /* Return an irq, or 0 to indicate there are none pending. */ unsigned int (*get_irq)(void); /* PCI stuff */ diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h index cd4f04a74802..b62a8d43a06c 100644 --- a/arch/powerpc/include/asm/mmu-book3e.h +++ b/arch/powerpc/include/asm/mmu-book3e.h @@ -313,6 +313,9 @@ extern int book3e_htw_mode; * return 1, indicating that the tlb requires preloading. */ #define HUGETLB_NEED_PRELOAD + +#define mmu_cleanup_all NULL + #endif #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index e2fb408f8398..e88368354e49 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -204,6 +204,10 @@ extern unsigned int __start___mmu_ftr_fixup, __stop___mmu_ftr_fixup; * make it match the size our of bolted TLB area */ extern u64 ppc64_rma_size; + +/* Cleanup function used by kexec */ +extern void mmu_cleanup_all(void); +extern void radix__mmu_cleanup_all(void); #endif /* CONFIG_PPC64 */ struct mm_struct; @@ -271,6 +275,7 @@ static inline bool early_radix_enabled(void) #define MMU_PAGE_16G 13 #define MMU_PAGE_64G 14 +/* N.B. we need to change the type of hpte_page_sizes if this gets to be > 16 */ #define MMU_PAGE_COUNT 15 #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 9d2cd0c36ec2..5c451140660a 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -18,6 +18,7 @@ extern void destroy_context(struct mm_struct *mm); #ifdef CONFIG_SPAPR_TCE_IOMMU struct mm_iommu_table_group_mem_t; +extern int isolate_lru_page(struct page *page); /* from internal.h */ extern bool mm_iommu_preregistered(void); extern long mm_iommu_get(unsigned long ua, unsigned long entries, struct mm_iommu_table_group_mem_t **pmem); @@ -71,7 +72,8 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { /* Mark this context has been used on the new CPU */ - cpumask_set_cpu(smp_processor_id(), mm_cpumask(next)); + if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) + cpumask_set_cpu(smp_processor_id(), mm_cpumask(next)); /* 32-bit keeps track of the current PGDIR in the thread struct */ #ifdef CONFIG_PPC32 diff --git a/arch/powerpc/include/asm/mpic_msgr.h b/arch/powerpc/include/asm/mpic_msgr.h index d4f471fb1031..088420d8aa59 100644 --- a/arch/powerpc/include/asm/mpic_msgr.h +++ b/arch/powerpc/include/asm/mpic_msgr.h @@ -122,9 +122,9 @@ static inline void mpic_msgr_set_destination(struct mpic_msgr *msgr, * @msgr: the message register whose IRQ is to be returned * * Returns the IRQ number associated with the given message register. - * NO_IRQ is returned if this message register is not capable of - * receiving interrupts. What message register can and cannot receive - * interrupts is specified in the device tree for the system. + * 0 is returned if this message register is not capable of receiving + * interrupts. What message register can and cannot receive interrupts is + * specified in the device tree for the system. */ static inline int mpic_msgr_get_irq(struct mpic_msgr *msgr) { diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 780847597514..c219ef7be53b 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -267,7 +267,8 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, } -static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry) +static inline void __ptep_set_access_flags(struct mm_struct *mm, + pte_t *ptep, pte_t entry) { unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index d4d808cf905e..653a1838469d 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -300,7 +300,8 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, /* Set the dirty and/or accessed bits atomically in a linux PTE, this * function doesn't need to flush the hash entry */ -static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry) +static inline void __ptep_set_access_flags(struct mm_struct *mm, + pte_t *ptep, pte_t entry) { unsigned long bits = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index ee05bd203630..e958b7096f19 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -67,6 +67,7 @@ int64_t opal_pci_config_write_half_word(uint64_t phb_id, uint64_t bus_dev_func, int64_t opal_pci_config_write_word(uint64_t phb_id, uint64_t bus_dev_func, uint64_t offset, uint32_t data); int64_t opal_set_xive(uint32_t isn, uint16_t server, uint8_t priority); +int64_t opal_rm_set_xive(uint32_t isn, uint16_t server, uint8_t priority); int64_t opal_get_xive(uint32_t isn, __be16 *server, uint8_t *priority); int64_t opal_register_exception_handler(uint64_t opal_exception, uint64_t handler_address, diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 148303e7771f..6a6792bb39fb 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -183,11 +183,6 @@ struct paca_struct { */ u16 in_mce; u8 hmi_event_available; /* HMI event is available */ - /* - * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for - * more details - */ - struct sibling_subcore_state *sibling_subcore_state; #endif /* Stuff for accurate time accounting */ @@ -202,6 +197,13 @@ struct paca_struct { struct kvmppc_book3s_shadow_vcpu shadow_vcpu; #endif struct kvmppc_host_state kvm_hstate; +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* + * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for + * more details + */ + struct sibling_subcore_state *sibling_subcore_state; +#endif #endif }; diff --git a/arch/powerpc/include/asm/parport.h b/arch/powerpc/include/asm/parport.h index a452968b29ea..6595ad1d18cc 100644 --- a/arch/powerpc/include/asm/parport.h +++ b/arch/powerpc/include/asm/parport.h @@ -28,7 +28,7 @@ static int parport_pc_find_nonpci_ports (int autoirq, int autodma) io1 = prop[1]; io2 = prop[2]; virq = irq_of_parse_and_map(np, 0); - if (virq == NO_IRQ) + if (!virq) continue; if (parport_pc_probe_port(io1, io2, virq, autodma, NULL, 0) diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index b5e88e4a171a..c0309c59bed8 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -301,6 +301,7 @@ extern void pci_process_bridge_OF_ranges(struct pci_controller *hose, /* Allocate & free a PCI host bridge structure */ extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev); extern void pcibios_free_controller(struct pci_controller *phb); +extern void pcibios_free_controller_deferred(struct pci_host_bridge *bridge); #ifdef CONFIG_PCI extern int pcibios_vaddr_is_ioport(void __iomem *address); diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h index 0cbd8134ce81..696438f09aea 100644 --- a/arch/powerpc/include/asm/pnv-pci.h +++ b/arch/powerpc/include/asm/pnv-pci.h @@ -12,10 +12,11 @@ #include <linux/pci.h> #include <linux/pci_hotplug.h> +#include <linux/irq.h> #include <misc/cxl-base.h> #include <asm/opal-api.h> -#define PCI_SLOT_ID_PREFIX 0x8000000000000000 +#define PCI_SLOT_ID_PREFIX (1UL << 63) #define PCI_SLOT_ID(phb_id, bdfn) \ (PCI_SLOT_ID_PREFIX | ((uint64_t)(bdfn) << 16) | (phb_id)) @@ -33,6 +34,8 @@ int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num); void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num); int pnv_cxl_get_irq_count(struct pci_dev *dev); struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev); +int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq); +bool is_pnv_opal_msi(struct irq_chip *chip); #ifdef CONFIG_CXL_BASE int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs, @@ -60,6 +63,8 @@ struct pnv_php_slot { #define PNV_PHP_STATE_POPULATED 2 #define PNV_PHP_STATE_OFFLINE 3 int state; + int irq; + struct workqueue_struct *wq; struct device_node *dn; struct pci_dev *pdev; struct pci_bus *bus; diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 127ebf5862b4..54ff8ce7fa96 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -236,6 +236,7 @@ #define PPC_INST_STWU 0x94000000 #define PPC_INST_MFLR 0x7c0802a6 #define PPC_INST_MTLR 0x7c0803a6 +#define PPC_INST_MTCTR 0x7c0903a6 #define PPC_INST_CMPWI 0x2c000000 #define PPC_INST_CMPDI 0x2c200000 #define PPC_INST_CMPW 0x7c000000 @@ -250,6 +251,7 @@ #define PPC_INST_SUB 0x7c000050 #define PPC_INST_BLR 0x4e800020 #define PPC_INST_BLRL 0x4e800021 +#define PPC_INST_BCTR 0x4e800420 #define PPC_INST_MULLD 0x7c0001d2 #define PPC_INST_MULLW 0x7c0001d6 #define PPC_INST_MULHWU 0x7c000016 diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index d5d5b5e348f2..c73750b0d9fa 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -201,14 +201,12 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #ifdef PPC64_ELF_ABI_v2 #define _GLOBAL(name) \ - .section ".text"; \ .align 2 ; \ .type name,@function; \ .globl name; \ name: #define _GLOBAL_TOC(name) \ - .section ".text"; \ .align 2 ; \ .type name,@function; \ .globl name; \ @@ -217,13 +215,6 @@ name: \ addi r2,r2,(.TOC.-0b)@l; \ .localentry name,.-name -#define _KPROBE(name) \ - .section ".kprobes.text","a"; \ - .align 2 ; \ - .type name,@function; \ - .globl name; \ -name: - #define DOTSYM(a) a #else @@ -232,35 +223,20 @@ name: #define GLUE(a,b) XGLUE(a,b) #define _GLOBAL(name) \ - .section ".text"; \ .align 2 ; \ .globl name; \ .globl GLUE(.,name); \ - .section ".opd","aw"; \ + .pushsection ".opd","aw"; \ name: \ .quad GLUE(.,name); \ .quad .TOC.@tocbase; \ .quad 0; \ - .previous; \ + .popsection; \ .type GLUE(.,name),@function; \ GLUE(.,name): #define _GLOBAL_TOC(name) _GLOBAL(name) -#define _KPROBE(name) \ - .section ".kprobes.text","a"; \ - .align 2 ; \ - .globl name; \ - .globl GLUE(.,name); \ - .section ".opd","aw"; \ -name: \ - .quad GLUE(.,name); \ - .quad .TOC.@tocbase; \ - .quad 0; \ - .previous; \ - .type GLUE(.,name),@function; \ -GLUE(.,name): - #define DOTSYM(a) GLUE(.,a) #endif @@ -272,20 +248,28 @@ GLUE(.,name): n: #define _GLOBAL(n) \ - .text; \ .stabs __stringify(n:F-1),N_FUN,0,0,n;\ .globl n; \ n: #define _GLOBAL_TOC(name) _GLOBAL(name) -#define _KPROBE(n) \ - .section ".kprobes.text","a"; \ - .globl n; \ -n: - #endif +/* + * __kprobes (the C annotation) puts the symbol into the .kprobes.text + * section, which gets emitted at the end of regular text. + * + * _ASM_NOKPROBE_SYMBOL and NOKPROBE_SYMBOL just adds the symbol to + * a blacklist. The former is for core kprobe functions/data, the + * latter is for those that incdentially must be excluded from probing + * and allows them to be linked at more optimal location within text. + */ +#define _ASM_NOKPROBE_SYMBOL(entry) \ + .pushsection "_kprobe_blacklist","aw"; \ + PPC_LONG (entry) ; \ + .popsection + #define FUNC_START(name) _GLOBAL(name) #define FUNC_END(name) @@ -527,7 +511,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) #endif #define MTMSRD(r) mtmsr r #define MTMSR_EERI(reg) mtmsr reg -#define CLR_TOP32(r) #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 68e3bf57b027..c07c31b0e89e 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -147,7 +147,7 @@ typedef struct { } mm_segment_t; #define TS_FPR(i) fp_state.fpr[i][TS_FPROFFSET] -#define TS_TRANS_FPR(i) transact_fp.fpr[i][TS_FPROFFSET] +#define TS_CKFPR(i) ckfp_state.fpr[i][TS_FPROFFSET] /* FP and VSX 0-31 register set */ struct thread_fp_state { @@ -257,6 +257,7 @@ struct thread_struct { int used_spe; /* set if process has used spe */ #endif /* CONFIG_SPE */ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM + u8 load_tm; u64 tm_tfhar; /* Transaction fail handler addr */ u64 tm_texasr; /* Transaction exception & summary */ u64 tm_tfiar; /* Transaction fail instr address reg */ @@ -267,20 +268,17 @@ struct thread_struct { unsigned long tm_dscr; /* - * Transactional FP and VSX 0-31 register set. - * NOTE: the sense of these is the opposite of the integer ckpt_regs! + * Checkpointed FP and VSX 0-31 register set. * * When a transaction is active/signalled/scheduled etc., *regs is the * most recent set of/speculated GPRs with ckpt_regs being the older * checkpointed regs to which we roll back if transaction aborts. * - * However, fpr[] is the checkpointed 'base state' of FP regs, and - * transact_fpr[] is the new set of transactional values. - * VRs work the same way. + * These are analogous to how ckpt_regs and pt_regs work */ - struct thread_fp_state transact_fp; - struct thread_vr_state transact_vr; - unsigned long transact_vrsave; + struct thread_fp_state ckfp_state; /* Checkpointed FP state */ + struct thread_vr_state ckvr_state; /* Checkpointed VR state */ + unsigned long ckvrsave; /* Checkpointed VRSAVE */ #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ #ifdef CONFIG_KVM_BOOK3S_32_HANDLER void* kvm_shadow_vcpu; /* KVM internal data */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index f69f40f1519a..2a620789954b 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -475,6 +475,9 @@ #define HID0_POWER8_1TO4LPAR __MASK(51) #define HID0_POWER8_DYNLPARDIS __MASK(48) +/* POWER9 HID0 bits */ +#define HID0_POWER9_RADIX __MASK(63 - 8) + #define SPRN_HID1 0x3F1 /* Hardware Implementation Register 1 */ #ifdef CONFIG_6xx #define HID1_EMCP (1<<31) /* 7450 Machine Check Pin Enable */ @@ -737,6 +740,7 @@ #define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */ #define SPRN_MMCR1 798 #define SPRN_MMCR2 785 +#define SPRN_UMMCR2 769 #define SPRN_MMCRA 0x312 #define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ #define MMCRA_SDAR_DCACHE_MISS 0x40000000UL @@ -1247,7 +1251,7 @@ static inline void mtmsr_isync(unsigned long val) : "memory") #endif -extern void msr_check_and_set(unsigned long bits); +extern unsigned long msr_check_and_set(unsigned long bits); extern bool strict_msr_control; extern void __msr_check_and_clear(unsigned long bits); static inline void msr_check_and_clear(unsigned long bits) diff --git a/arch/powerpc/include/asm/signal.h b/arch/powerpc/include/asm/signal.h index 9322c28aebd2..5ff77722a52d 100644 --- a/arch/powerpc/include/asm/signal.h +++ b/arch/powerpc/include/asm/signal.h @@ -5,6 +5,4 @@ #include <uapi/asm/signal.h> #include <uapi/asm/ptrace.h> -extern unsigned long get_tm_stackpointer(struct pt_regs *regs); - #endif /* _ASM_POWERPC_SIGNAL_H */ diff --git a/arch/powerpc/include/asm/tm.h b/arch/powerpc/include/asm/tm.h index c22d704b6d41..82e06ca3a49b 100644 --- a/arch/powerpc/include/asm/tm.h +++ b/arch/powerpc/include/asm/tm.h @@ -9,11 +9,6 @@ #ifndef __ASSEMBLY__ -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -extern void do_load_up_transact_fpu(struct thread_struct *thread); -extern void do_load_up_transact_altivec(struct thread_struct *thread); -#endif - extern void tm_enable(void); extern void tm_reclaim(struct thread_struct *thread, unsigned long orig_msr, uint8_t cause); diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index c1dc6c14deb8..c266227fdd5b 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -308,40 +308,21 @@ extern unsigned long __copy_tofrom_user(void __user *to, static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n) { - unsigned long over; - - if (access_ok(VERIFY_READ, from, n)) { - if (!__builtin_constant_p(n)) - check_object_size(to, n, false); + if (likely(access_ok(VERIFY_READ, from, n))) { + check_object_size(to, n, false); return __copy_tofrom_user((__force void __user *)to, from, n); } - if ((unsigned long)from < TASK_SIZE) { - over = (unsigned long)from + n - TASK_SIZE; - if (!__builtin_constant_p(n - over)) - check_object_size(to, n - over, false); - return __copy_tofrom_user((__force void __user *)to, from, - n - over) + over; - } + memset(to, 0, n); return n; } static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n) { - unsigned long over; - if (access_ok(VERIFY_WRITE, to, n)) { - if (!__builtin_constant_p(n)) - check_object_size(from, n, true); + check_object_size(from, n, true); return __copy_tofrom_user(to, (__force void __user *)from, n); } - if ((unsigned long)to < TASK_SIZE) { - over = (unsigned long)to + n - TASK_SIZE; - if (!__builtin_constant_p(n)) - check_object_size(from, n - over, true); - return __copy_tofrom_user(to, (__force void __user *)from, - n - over) + over; - } return n; } @@ -383,8 +364,7 @@ static inline unsigned long __copy_from_user_inatomic(void *to, return 0; } - if (!__builtin_constant_p(n)) - check_object_size(to, n, false); + check_object_size(to, n, false); return __copy_tofrom_user((__force void __user *)to, from, n); } @@ -412,8 +392,8 @@ static inline unsigned long __copy_to_user_inatomic(void __user *to, if (ret == 0) return 0; } - if (!__builtin_constant_p(n)) - check_object_size(from, n, true); + + check_object_size(from, n, true); return __copy_tofrom_user(to, (__force const void __user *)from, n); } @@ -439,10 +419,6 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size) might_fault(); if (likely(access_ok(VERIFY_WRITE, addr, size))) return __clear_user(addr, size); - if ((unsigned long)addr < TASK_SIZE) { - unsigned long over = (unsigned long)addr + size - TASK_SIZE; - return __clear_user(addr, size - over) + over; - } return size; } diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index b2027a5cf508..aded29ad2e8f 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -31,8 +31,7 @@ obj-y := cputable.o ptrace.o syscalls.o \ process.o systbl.o idle.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ - udbg.o misc.o io.o dma.o \ - misc_$(CONFIG_WORD_SIZE).o \ + udbg.o misc.o io.o dma.o misc_$(BITS).o \ of_platform.o prom_parse.o obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ @@ -41,7 +40,7 @@ obj-$(CONFIG_VDSO32) += vdso32/ obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o -obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o hmi.o +obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o @@ -70,23 +69,23 @@ obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o ifeq ($(CONFIG_FSL_BOOKE),y) obj-$(CONFIG_HIBERNATION) += swsusp_booke.o else -obj-$(CONFIG_HIBERNATION) += swsusp_$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_HIBERNATION) += swsusp_$(BITS).o endif obj64-$(CONFIG_HIBERNATION) += swsusp_asm64.o -obj-$(CONFIG_MODULES) += module.o module_$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_MODULES) += module.o module_$(BITS).o obj-$(CONFIG_44x) += cpu_setup_44x.o obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o obj-$(CONFIG_PPC_DOORBELL) += dbell.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o -extra-y := head_$(CONFIG_WORD_SIZE).o +extra-y := head_$(BITS).o extra-$(CONFIG_40x) := head_40x.o extra-$(CONFIG_44x) := head_44x.o extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o extra-$(CONFIG_8xx) := head_8xx.o extra-y += vmlinux.lds -obj-$(CONFIG_RELOCATABLE) += reloc_$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_RELOCATABLE) += reloc_$(BITS).o obj-$(CONFIG_PPC32) += entry_32.o setup_32.o obj-$(CONFIG_PPC64) += dma-iommu.o iommu.o @@ -104,11 +103,11 @@ obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o pci64-$(CONFIG_PPC64) += pci_dn.o pci-hotplug.o isa-bridge.o -obj-$(CONFIG_PCI) += pci_$(CONFIG_WORD_SIZE).o $(pci64-y) \ +obj-$(CONFIG_PCI) += pci_$(BITS).o $(pci64-y) \ pci-common.o pci_of_scan.o obj-$(CONFIG_PCI_MSI) += msi.o obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o \ - machine_kexec_$(CONFIG_WORD_SIZE).o + machine_kexec_$(BITS).o obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index b89d14c0352c..caec7bf3b99a 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -142,12 +142,12 @@ int main(void) DEFINE(THREAD_TM_PPR, offsetof(struct thread_struct, tm_ppr)); DEFINE(THREAD_TM_DSCR, offsetof(struct thread_struct, tm_dscr)); DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs)); - DEFINE(THREAD_TRANSACT_VRSTATE, offsetof(struct thread_struct, - transact_vr)); - DEFINE(THREAD_TRANSACT_VRSAVE, offsetof(struct thread_struct, - transact_vrsave)); - DEFINE(THREAD_TRANSACT_FPSTATE, offsetof(struct thread_struct, - transact_fp)); + DEFINE(THREAD_CKVRSTATE, offsetof(struct thread_struct, + ckvr_state)); + DEFINE(THREAD_CKVRSAVE, offsetof(struct thread_struct, + ckvrsave)); + DEFINE(THREAD_CKFPSTATE, offsetof(struct thread_struct, + ckfp_state)); /* Local pt_regs on stack for Transactional Memory funcs. */ DEFINE(TM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); @@ -506,7 +506,6 @@ int main(void) DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr)); DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr)); DEFINE(VCPU_IC, offsetof(struct kvm_vcpu, arch.ic)); - DEFINE(VCPU_VTB, offsetof(struct kvm_vcpu, arch.vtb)); DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr)); DEFINE(VCPU_AMR, offsetof(struct kvm_vcpu, arch.amr)); DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor)); @@ -557,6 +556,7 @@ int main(void) DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr)); DEFINE(VCORE_PCR, offsetof(struct kvmppc_vcore, pcr)); DEFINE(VCORE_DPDES, offsetof(struct kvmppc_vcore, dpdes)); + DEFINE(VCORE_VTB, offsetof(struct kvmppc_vcore, vtb)); DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige)); DEFINE(VCPU_SLB_V, offsetof(struct kvmppc_slb, origv)); DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb)); diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 74248ab18e98..6c4646ac9234 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -506,6 +506,25 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, + { /* Power9 DD1*/ + .pvr_mask = 0xffffff00, + .pvr_value = 0x004e0100, + .cpu_name = "POWER9 (raw)", + .cpu_features = CPU_FTRS_POWER9_DD1, + .cpu_user_features = COMMON_USER_POWER9, + .cpu_user_features2 = COMMON_USER2_POWER9, + .mmu_features = MMU_FTRS_POWER9, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .oprofile_cpu_type = "ppc64/power9", + .oprofile_type = PPC_OPROFILE_INVALID, + .cpu_setup = __setup_cpu_power9, + .cpu_restore = __restore_cpu_power9, + .flush_tlb = __flush_tlb_power9, + .platform = "power9", + }, { /* Power9 */ .pvr_mask = 0xffff0000, .pvr_value = 0x004e0000, diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 7429556eb8df..f25731627d7f 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -116,6 +116,7 @@ struct eeh_ops *eeh_ops = NULL; /* Lock to avoid races due to multiple reports of an error */ DEFINE_RAW_SPINLOCK(confirm_error_lock); +EXPORT_SYMBOL_GPL(confirm_error_lock); /* Lock to protect passed flags */ static DEFINE_MUTEX(eeh_dev_mutex); @@ -1044,7 +1045,7 @@ int eeh_init(void) if (eeh_enabled()) pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n"); else - pr_warn("EEH: No capable adapters found\n"); + pr_info("EEH: No capable adapters found\n"); return ret; } @@ -1502,6 +1503,7 @@ int eeh_pe_set_option(struct eeh_pe *pe, int option) break; case EEH_OPT_THAW_MMIO: case EEH_OPT_THAW_DMA: + case EEH_OPT_FREEZE_PE: if (!eeh_ops || !eeh_ops->set_option) { ret = -ENOENT; break; diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 5f36e8a70daa..a62be72da274 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -993,9 +993,17 @@ static void eeh_handle_special_event(void) /* Notify all devices to be down */ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); - bus = eeh_pe_bus_get(phb_pe); eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); + bus = eeh_pe_bus_get(phb_pe); + if (!bus) { + pr_err("%s: Cannot find PCI bus for " + "PHB#%d-PE#%x\n", + __func__, + pe->phb->global_number, + pe->addr); + break; + } pci_hp_remove_devices(bus); } pci_unlock_rescan_remove(); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index f0520da85759..de7d091c4c31 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -581,6 +581,7 @@ void eeh_pe_state_mark(struct eeh_pe *pe, int state) { eeh_pe_traverse(pe, __eeh_pe_state_mark, &state); } +EXPORT_SYMBOL_GPL(eeh_pe_state_mark); static void *__eeh_pe_dev_mode_mark(void *data, void *flag) { diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 9899032230b4..83428a283fa0 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -654,7 +654,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPE) #endif /* CONFIG_SMP */ tophys(r0,r4) - CLR_TOP32(r0) mtspr SPRN_SPRG_THREAD,r0 /* Update current THREAD phys addr */ lwz r1,KSP(r4) /* Load new stack pointer */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 6b8bc0dd09d4..51df82b61084 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -139,7 +139,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #ifdef CONFIG_PPC_BOOK3E wrteei 1 #else - ld r11,PACAKMSR(r13) + li r11,MSR_RI ori r11,r11,MSR_EE mtmsrd r11,1 #endif /* CONFIG_PPC_BOOK3E */ @@ -195,7 +195,6 @@ system_call: /* label this so stack traces look sane */ #ifdef CONFIG_PPC_BOOK3E wrteei 0 #else - ld r10,PACAKMSR(r13) /* * For performance reasons we clear RI the same time that we * clear EE. We only need to clear RI just before we restore r13 @@ -203,8 +202,7 @@ system_call: /* label this so stack traces look sane */ * We have to be careful to restore RI if we branch anywhere from * here (eg syscall_exit_work). */ - li r9,MSR_RI - andc r11,r10,r9 + li r11,0 mtmsrd r11,1 #endif /* CONFIG_PPC_BOOK3E */ @@ -221,13 +219,12 @@ system_call: /* label this so stack traces look sane */ #endif 2: addi r3,r1,STACK_FRAME_OVERHEAD #ifdef CONFIG_PPC_BOOK3S + li r10,MSR_RI mtmsrd r10,1 /* Restore RI */ #endif bl restore_math #ifdef CONFIG_PPC_BOOK3S - ld r10,PACAKMSR(r13) - li r9,MSR_RI - andc r11,r10,r9 /* Re-clear RI */ + li r11,0 mtmsrd r11,1 #endif ld r8,_MSR(r1) @@ -308,6 +305,7 @@ syscall_enosys: syscall_exit_work: #ifdef CONFIG_PPC_BOOK3S + li r10,MSR_RI mtmsrd r10,1 /* Restore RI */ #endif /* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr. @@ -354,7 +352,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) #ifdef CONFIG_PPC_BOOK3E wrteei 1 #else - ld r10,PACAKMSR(r13) + li r10,MSR_RI ori r10,r10,MSR_EE mtmsrd r10,1 #endif /* CONFIG_PPC_BOOK3E */ @@ -368,13 +366,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) tabort_syscall: /* Firstly we need to enable TM in the kernel */ mfmsr r10 - li r13, 1 - rldimi r10, r13, MSR_TM_LG, 63-MSR_TM_LG + li r9, 1 + rldimi r10, r9, MSR_TM_LG, 63-MSR_TM_LG mtmsrd r10, 0 /* tabort, this dooms the transaction, nothing else */ - li r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) - TABORT(R13) + li r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) + TABORT(R9) /* * Return directly to userspace. We have corrupted user register state, @@ -382,8 +380,8 @@ tabort_syscall: * resume after the tbegin of the aborted transaction with the * checkpointed register state. */ - li r13, MSR_RI - andc r10, r10, r13 + li r9, MSR_RI + andc r10, r10, r9 mtmsrd r10, 1 mtspr SPRN_SRR0, r11 mtspr SPRN_SRR1, r12 @@ -619,7 +617,7 @@ _GLOBAL(ret_from_except_lite) #ifdef CONFIG_PPC_BOOK3E wrteei 0 #else - ld r10,PACAKMSR(r13) /* Get kernel MSR without EE */ + li r10,MSR_RI mtmsrd r10,1 /* Update machine state */ #endif /* CONFIG_PPC_BOOK3E */ @@ -751,7 +749,7 @@ resume_kernel: #ifdef CONFIG_PPC_BOOK3E wrteei 0 #else - ld r10,PACAKMSR(r13) /* Get kernel MSR without EE */ + li r10,MSR_RI mtmsrd r10,1 /* Update machine state */ #endif /* CONFIG_PPC_BOOK3E */ #endif /* CONFIG_PREEMPT */ @@ -841,8 +839,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) * userspace and we take an exception after restoring r13, * we end up corrupting the userspace r13 value. */ - ld r4,PACAKMSR(r13) /* Get kernel MSR without EE */ - andc r4,r4,r0 /* r0 contains MSR_RI here */ + li r4,0 mtmsrd r4,1 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index df6d45eb4115..08992f8f5036 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -16,72 +16,71 @@ #include <asm/exception-64s.h> #include <asm/ptrace.h> #include <asm/cpuidle.h> +#include <asm/head-64.h> /* + * There are a few constraints to be concerned with. + * - Real mode exceptions code/data must be located at their physical location. + * - Virtual mode exceptions must be mapped at their 0xc000... location. + * - Fixed location code must not call directly beyond the __end_interrupts + * area when built with CONFIG_RELOCATABLE. LOAD_HANDLER / bctr sequence + * must be used. + * - LOAD_HANDLER targets must be within first 64K of physical 0 / + * virtual 0xc00... + * - Conditional branch targets must be within +/-32K of caller. + * + * "Virtual exceptions" run with relocation on (MSR_IR=1, MSR_DR=1), and + * therefore don't have to run in physically located code or rfid to + * virtual mode kernel code. However on relocatable kernels they do have + * to branch to KERNELBASE offset because the rest of the kernel (outside + * the exception vectors) may be located elsewhere. + * + * Virtual exceptions correspond with physical, except their entry points + * are offset by 0xc000000000000000 and also tend to get an added 0x4000 + * offset applied. Virtual exceptions are enabled with the Alternate + * Interrupt Location (AIL) bit set in the LPCR. However this does not + * guarantee they will be delivered virtually. Some conditions (see the ISA) + * cause exceptions to be delivered in real mode. + * + * It's impossible to receive interrupts below 0x300 via AIL. + * + * KVM: None of the virtual exceptions are from the guest. Anything that + * escalated to HV=1 from HV=0 is delivered via real mode handlers. + * + * * We layout physical memory as follows: * 0x0000 - 0x00ff : Secondary processor spin code - * 0x0100 - 0x17ff : pSeries Interrupt prologs - * 0x1800 - 0x4000 : interrupt support common interrupt prologs - * 0x4000 - 0x5fff : pSeries interrupts with IR=1,DR=1 - * 0x6000 - 0x6fff : more interrupt support including for IR=1,DR=1 + * 0x0100 - 0x18ff : Real mode pSeries interrupt vectors + * 0x1900 - 0x3fff : Real mode trampolines + * 0x4000 - 0x58ff : Relon (IR=1,DR=1) mode pSeries interrupt vectors + * 0x5900 - 0x6fff : Relon mode trampolines * 0x7000 - 0x7fff : FWNMI data area - * 0x8000 - 0x8fff : Initial (CPU0) segment table - * 0x9000 - : Early init and support code + * 0x8000 - .... : Common interrupt handlers, remaining early + * setup code, rest of kernel. + * + * We could reclaim 0x4000-0x42ff for real mode trampolines if the space + * is necessary. Until then it's more consistent to explicitly put VIRT_NONE + * vectors there. */ - /* Syscall routine is used twice, in reloc-off and reloc-on paths */ -#define SYSCALL_PSERIES_1 \ -BEGIN_FTR_SECTION \ - cmpdi r0,0x1ebe ; \ - beq- 1f ; \ -END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ - mr r9,r13 ; \ - GET_PACA(r13) ; \ - mfspr r11,SPRN_SRR0 ; \ -0: - -#define SYSCALL_PSERIES_2_RFID \ - mfspr r12,SPRN_SRR1 ; \ - ld r10,PACAKBASE(r13) ; \ - LOAD_HANDLER(r10, system_call_entry) ; \ - mtspr SPRN_SRR0,r10 ; \ - ld r10,PACAKMSR(r13) ; \ - mtspr SPRN_SRR1,r10 ; \ - rfid ; \ - b . ; /* prevent speculative execution */ - -#define SYSCALL_PSERIES_3 \ - /* Fast LE/BE switch system call */ \ -1: mfspr r12,SPRN_SRR1 ; \ - xori r12,r12,MSR_LE ; \ - mtspr SPRN_SRR1,r12 ; \ - rfid ; /* return to userspace */ \ - b . ; /* prevent speculative execution */ - -#if defined(CONFIG_RELOCATABLE) - /* - * We can't branch directly so we do it via the CTR which - * is volatile across system calls. - */ -#define SYSCALL_PSERIES_2_DIRECT \ - mflr r10 ; \ - ld r12,PACAKBASE(r13) ; \ - LOAD_HANDLER(r12, system_call_entry) ; \ - mtctr r12 ; \ - mfspr r12,SPRN_SRR1 ; \ - /* Re-use of r13... No spare regs to do this */ \ - li r13,MSR_RI ; \ - mtmsrd r13,1 ; \ - GET_PACA(r13) ; /* get r13 back */ \ - bctr ; +OPEN_FIXED_SECTION(real_vectors, 0x0100, 0x1900) +OPEN_FIXED_SECTION(real_trampolines, 0x1900, 0x4000) +OPEN_FIXED_SECTION(virt_vectors, 0x4000, 0x5900) +OPEN_FIXED_SECTION(virt_trampolines, 0x5900, 0x7000) +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) +/* + * Data area reserved for FWNMI option. + * This address (0x7000) is fixed by the RPA. + * pseries and powernv need to keep the whole page from + * 0x7000 to 0x8000 free for use by the firmware + */ +ZERO_FIXED_SECTION(fwnmi_page, 0x7000, 0x8000) +OPEN_TEXT_SECTION(0x8000) #else - /* We can branch directly */ -#define SYSCALL_PSERIES_2_DIRECT \ - mfspr r12,SPRN_SRR1 ; \ - li r10,MSR_RI ; \ - mtmsrd r10,1 ; /* Set RI (EE=0) */ \ - b system_call_common ; +OPEN_TEXT_SECTION(0x7000) #endif +USE_FIXED_SECTION(real_vectors) + /* * This is the start of the interrupt handlers for pSeries * This code runs with relocation off. @@ -90,12 +89,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ * Therefore any relative branches in this section must only * branch to labels in this section. */ - . = 0x100 .globl __start_interrupts __start_interrupts: - .globl system_reset_pSeries; -system_reset_pSeries: +/* No virt vectors corresponding with 0x0..0x100 */ +EXC_VIRT_NONE(0x4000, 0x4100) + +EXC_REAL_BEGIN(system_reset, 0x100, 0x200) SET_SCRATCH0(r13) #ifdef CONFIG_PPC_P7_NAP BEGIN_FTR_SECTION @@ -136,9 +136,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) #endif /* CONFIG_PPC_P7_NAP */ EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, NOTEST, 0x100) +EXC_REAL_END(system_reset, 0x100, 0x200) +EXC_VIRT_NONE(0x4100, 0x4200) +EXC_COMMON(system_reset_common, 0x100, system_reset_exception) + +#ifdef CONFIG_PPC_PSERIES +/* + * Vectors for the FWNMI option. Share common code. + */ +TRAMP_REAL_BEGIN(system_reset_fwnmi) + SET_SCRATCH0(r13) /* save r13 */ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, + NOTEST, 0x100) +#endif /* CONFIG_PPC_PSERIES */ + - . = 0x200 -machine_check_pSeries_1: +EXC_REAL_BEGIN(machine_check, 0x200, 0x300) /* This is moved out of line as it can be patched by FW, but * some code path might still want to branch into the original * vector @@ -158,253 +171,9 @@ BEGIN_FTR_SECTION FTR_SECTION_ELSE b machine_check_pSeries_0 ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) - - . = 0x300 - .globl data_access_pSeries -data_access_pSeries: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD, - KVMTEST, 0x300) - - . = 0x380 - .globl data_access_slb_pSeries -data_access_slb_pSeries: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXSLB) - EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380) - std r3,PACA_EXSLB+EX_R3(r13) - mfspr r3,SPRN_DAR - mfspr r12,SPRN_SRR1 -#ifndef CONFIG_RELOCATABLE - b slb_miss_realmode -#else - /* - * We can't just use a direct branch to slb_miss_realmode - * because the distance from here to there depends on where - * the kernel ends up being put. - */ - mfctr r11 - ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, slb_miss_realmode) - mtctr r10 - bctr -#endif - - STD_EXCEPTION_PSERIES(0x400, instruction_access) - - . = 0x480 - .globl instruction_access_slb_pSeries -instruction_access_slb_pSeries: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXSLB) - EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x480) - std r3,PACA_EXSLB+EX_R3(r13) - mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ - mfspr r12,SPRN_SRR1 -#ifndef CONFIG_RELOCATABLE - b slb_miss_realmode -#else - mfctr r11 - ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, slb_miss_realmode) - mtctr r10 - bctr -#endif - - /* We open code these as we can't have a ". = x" (even with - * x = "." within a feature section - */ - . = 0x500; - .globl hardware_interrupt_pSeries; - .globl hardware_interrupt_hv; -hardware_interrupt_pSeries: -hardware_interrupt_hv: - BEGIN_FTR_SECTION - _MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, - EXC_HV, SOFTEN_TEST_HV) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502) - FTR_SECTION_ELSE - _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, - EXC_STD, SOFTEN_TEST_PR) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500) - ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) - - STD_EXCEPTION_PSERIES(0x600, alignment) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x600) - - STD_EXCEPTION_PSERIES(0x700, program_check) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x700) - - STD_EXCEPTION_PSERIES(0x800, fp_unavailable) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x800) - - . = 0x900 - .globl decrementer_pSeries -decrementer_pSeries: - _MASKABLE_EXCEPTION_PSERIES(0x900, decrementer, EXC_STD, SOFTEN_TEST_PR) - - STD_EXCEPTION_HV(0x980, 0x982, hdecrementer) - - MASKABLE_EXCEPTION_PSERIES(0xa00, 0xa00, doorbell_super) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xa00) - - STD_EXCEPTION_PSERIES(0xb00, trap_0b) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xb00) - - . = 0xc00 - .globl system_call_pSeries -system_call_pSeries: - /* - * If CONFIG_KVM_BOOK3S_64_HANDLER is set, save the PPR (on systems - * that support it) before changing to HMT_MEDIUM. That allows the KVM - * code to save that value into the guest state (it is the guest's PPR - * value). Otherwise just change to HMT_MEDIUM as userspace has - * already saved the PPR. - */ -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER - SET_SCRATCH0(r13) - GET_PACA(r13) - std r9,PACA_EXGEN+EX_R9(r13) - OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR); - HMT_MEDIUM; - std r10,PACA_EXGEN+EX_R10(r13) - OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r9, CPU_FTR_HAS_PPR); - mfcr r9 - KVMTEST(0xc00) - GET_SCRATCH0(r13) -#else - HMT_MEDIUM; -#endif - SYSCALL_PSERIES_1 - SYSCALL_PSERIES_2_RFID - SYSCALL_PSERIES_3 - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xc00) - - STD_EXCEPTION_PSERIES(0xd00, single_step) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xd00) - - /* At 0xe??? we have a bunch of hypervisor exceptions, we branch - * out of line to handle them - */ - . = 0xe00 -hv_data_storage_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_data_storage_hv - - . = 0xe20 -hv_instr_storage_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_instr_storage_hv - - . = 0xe40 -emulation_assist_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b emulation_assist_hv - - . = 0xe60 -hv_exception_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b hmi_exception_early - - . = 0xe80 -hv_doorbell_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_doorbell_hv - - . = 0xea0 -hv_virt_irq_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_virt_irq_hv - - /* We need to deal with the Altivec unavailable exception - * here which is at 0xf20, thus in the middle of the - * prolog code of the PerformanceMonitor one. A little - * trickery is thus necessary - */ - . = 0xf00 -performance_monitor_pseries_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b performance_monitor_pSeries - - . = 0xf20 -altivec_unavailable_pseries_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b altivec_unavailable_pSeries - - . = 0xf40 -vsx_unavailable_pseries_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b vsx_unavailable_pSeries - - . = 0xf60 -facility_unavailable_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b facility_unavailable_pSeries - - . = 0xf80 -hv_facility_unavailable_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b facility_unavailable_hv - -#ifdef CONFIG_CBE_RAS - STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202) -#endif /* CONFIG_CBE_RAS */ - - STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1300) - - . = 0x1500 - .global denorm_exception_hv -denorm_exception_hv: - mtspr SPRN_SPRG_HSCRATCH0,r13 - EXCEPTION_PROLOG_0(PACA_EXGEN) - EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500) - -#ifdef CONFIG_PPC_DENORMALISATION - mfspr r10,SPRN_HSRR1 - mfspr r11,SPRN_HSRR0 /* save HSRR0 */ - andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */ - addi r11,r11,-4 /* HSRR0 is next instruction */ - bne+ denorm_assist -#endif - - KVMTEST(0x1500) - EXCEPTION_PROLOG_PSERIES_1(denorm_common, EXC_HV) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1500) - -#ifdef CONFIG_CBE_RAS - STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602) -#endif /* CONFIG_CBE_RAS */ - - STD_EXCEPTION_PSERIES(0x1700, altivec_assist) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x1700) - -#ifdef CONFIG_CBE_RAS - STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1802) -#else - . = 0x1800 -#endif /* CONFIG_CBE_RAS */ - - -/*** Out of line interrupts support ***/ - - .align 7 - /* moved from 0x200 */ -machine_check_powernv_early: +EXC_REAL_END(machine_check, 0x200, 0x300) +EXC_VIRT_NONE(0x4200, 0x4300) +TRAMP_REAL_BEGIN(machine_check_powernv_early) BEGIN_FTR_SECTION EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200) /* @@ -457,7 +226,6 @@ BEGIN_FTR_SECTION mfmsr r11 /* get MSR value */ ori r11,r11,MSR_ME /* turn on ME bit */ ori r11,r11,MSR_RI /* turn on RI bit */ - ld r12,PACAKBASE(r13) /* get high part of &label */ LOAD_HANDLER(r12, machine_check_handle_early) 1: mtspr SPRN_SRR0,r12 mtspr SPRN_SRR1,r11 @@ -470,7 +238,6 @@ BEGIN_FTR_SECTION */ addi r1,r1,INT_FRAME_SIZE /* go back to previous stack frame */ ld r11,PACAKMSR(r13) - ld r12,PACAKBASE(r13) LOAD_HANDLER(r12, unrecover_mce) li r10,MSR_ME andc r11,r11,r10 /* Turn off MSR_ME */ @@ -478,505 +245,48 @@ BEGIN_FTR_SECTION b . /* prevent speculative execution */ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) -machine_check_pSeries: +TRAMP_REAL_BEGIN(machine_check_pSeries) .globl machine_check_fwnmi machine_check_fwnmi: SET_SCRATCH0(r13) /* save r13 */ EXCEPTION_PROLOG_0(PACA_EXMC) machine_check_pSeries_0: - EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST, 0x200) - EXCEPTION_PROLOG_PSERIES_1(machine_check_common, EXC_STD) - KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300) - KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x400) - KVM_HANDLER(PACA_EXSLB, EXC_STD, 0x480) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x900) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982) - -#ifdef CONFIG_PPC_DENORMALISATION -denorm_assist: -BEGIN_FTR_SECTION -/* - * To denormalise we need to move a copy of the register to itself. - * For POWER6 do that here for all FP regs. - */ - mfmsr r10 - ori r10,r10,(MSR_FP|MSR_FE0|MSR_FE1) - xori r10,r10,(MSR_FE0|MSR_FE1) - mtmsrd r10 - sync - -#define FMR2(n) fmr (n), (n) ; fmr n+1, n+1 -#define FMR4(n) FMR2(n) ; FMR2(n+2) -#define FMR8(n) FMR4(n) ; FMR4(n+4) -#define FMR16(n) FMR8(n) ; FMR8(n+8) -#define FMR32(n) FMR16(n) ; FMR16(n+16) - FMR32(0) - -FTR_SECTION_ELSE -/* - * To denormalise we need to move a copy of the register to itself. - * For POWER7 do that here for the first 32 VSX registers only. - */ - mfmsr r10 - oris r10,r10,MSR_VSX@h - mtmsrd r10 - sync - -#define XVCPSGNDP2(n) XVCPSGNDP(n,n,n) ; XVCPSGNDP(n+1,n+1,n+1) -#define XVCPSGNDP4(n) XVCPSGNDP2(n) ; XVCPSGNDP2(n+2) -#define XVCPSGNDP8(n) XVCPSGNDP4(n) ; XVCPSGNDP4(n+4) -#define XVCPSGNDP16(n) XVCPSGNDP8(n) ; XVCPSGNDP8(n+8) -#define XVCPSGNDP32(n) XVCPSGNDP16(n) ; XVCPSGNDP16(n+16) - XVCPSGNDP32(0) - -ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206) - -BEGIN_FTR_SECTION - b denorm_done -END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) -/* - * To denormalise we need to move a copy of the register to itself. - * For POWER8 we need to do that for all 64 VSX registers - */ - XVCPSGNDP32(32) -denorm_done: - mtspr SPRN_HSRR0,r11 - mtcrf 0x80,r9 - ld r9,PACA_EXGEN+EX_R9(r13) - RESTORE_PPR_PACA(PACA_EXGEN, r10) -BEGIN_FTR_SECTION - ld r10,PACA_EXGEN+EX_CFAR(r13) - mtspr SPRN_CFAR,r10 -END_FTR_SECTION_IFSET(CPU_FTR_CFAR) - ld r10,PACA_EXGEN+EX_R10(r13) - ld r11,PACA_EXGEN+EX_R11(r13) - ld r12,PACA_EXGEN+EX_R12(r13) - ld r13,PACA_EXGEN+EX_R13(r13) - HRFID - b . -#endif - - .align 7 - /* moved from 0xe00 */ - STD_EXCEPTION_HV_OOL(0xe02, h_data_storage) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0xe02) - STD_EXCEPTION_HV_OOL(0xe22, h_instr_storage) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe22) - STD_EXCEPTION_HV_OOL(0xe42, emulation_assist) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe42) - MASKABLE_EXCEPTION_HV_OOL(0xe62, hmi_exception) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe62) - - MASKABLE_EXCEPTION_HV_OOL(0xe82, h_doorbell) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe82) - - MASKABLE_EXCEPTION_HV_OOL(0xea2, h_virt_irq) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xea2) - - /* moved from 0xf00 */ - STD_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf00) - STD_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf20) - STD_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf40) - STD_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf60) - STD_EXCEPTION_HV_OOL(0xf82, facility_unavailable) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xf82) - -/* - * An interrupt came in while soft-disabled. We set paca->irq_happened, then: - * - If it was a decrementer interrupt, we bump the dec to max and and return. - * - If it was a doorbell we return immediately since doorbells are edge - * triggered and won't automatically refire. - * - If it was a HMI we return immediately since we handled it in realmode - * and it won't refire. - * - else we hard disable and return. - * This is called with r10 containing the value to OR to the paca field. - */ -#define MASKED_INTERRUPT(_H) \ -masked_##_H##interrupt: \ - std r11,PACA_EXGEN+EX_R11(r13); \ - lbz r11,PACAIRQHAPPENED(r13); \ - or r11,r11,r10; \ - stb r11,PACAIRQHAPPENED(r13); \ - cmpwi r10,PACA_IRQ_DEC; \ - bne 1f; \ - lis r10,0x7fff; \ - ori r10,r10,0xffff; \ - mtspr SPRN_DEC,r10; \ - b 2f; \ -1: cmpwi r10,PACA_IRQ_DBELL; \ - beq 2f; \ - cmpwi r10,PACA_IRQ_HMI; \ - beq 2f; \ - mfspr r10,SPRN_##_H##SRR1; \ - rldicl r10,r10,48,1; /* clear MSR_EE */ \ - rotldi r10,r10,16; \ - mtspr SPRN_##_H##SRR1,r10; \ -2: mtcrf 0x80,r9; \ - ld r9,PACA_EXGEN+EX_R9(r13); \ - ld r10,PACA_EXGEN+EX_R10(r13); \ - ld r11,PACA_EXGEN+EX_R11(r13); \ - GET_SCRATCH0(r13); \ - ##_H##rfid; \ - b . - - MASKED_INTERRUPT() - MASKED_INTERRUPT(H) - -/* - * Called from arch_local_irq_enable when an interrupt needs - * to be resent. r3 contains 0x500, 0x900, 0xa00 or 0xe80 to indicate - * which kind of interrupt. MSR:EE is already off. We generate a - * stackframe like if a real interrupt had happened. - * - * Note: While MSR:EE is off, we need to make sure that _MSR - * in the generated frame has EE set to 1 or the exception - * handler will not properly re-enable them. - */ -_GLOBAL(__replay_interrupt) - /* We are going to jump to the exception common code which - * will retrieve various register values from the PACA which - * we don't give a damn about, so we don't bother storing them. - */ - mfmsr r12 - mflr r11 - mfcr r9 - ori r12,r12,MSR_EE - cmpwi r3,0x900 - beq decrementer_common - cmpwi r3,0x500 - beq hardware_interrupt_common -BEGIN_FTR_SECTION - cmpwi r3,0xe80 - beq h_doorbell_common - cmpwi r3,0xea0 - beq h_virt_irq_common - cmpwi r3,0xe60 - beq hmi_exception_common -FTR_SECTION_ELSE - cmpwi r3,0xa00 - beq doorbell_super_common -ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) - blr - -#ifdef CONFIG_PPC_PSERIES -/* - * Vectors for the FWNMI option. Share common code. - */ - .globl system_reset_fwnmi - .align 7 -system_reset_fwnmi: - SET_SCRATCH0(r13) /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, - NOTEST, 0x100) - -#endif /* CONFIG_PPC_PSERIES */ - -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER -kvmppc_skip_interrupt: + EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST_PR, 0x200) /* - * Here all GPRs are unchanged from when the interrupt happened - * except for r13, which is saved in SPRG_SCRATCH0. + * The following is essentially EXCEPTION_PROLOG_PSERIES_1 with the + * difference that MSR_RI is not enabled, because PACA_EXMC is being + * used, so nested machine check corrupts it. machine_check_common + * enables MSR_RI. */ - mfspr r13, SPRN_SRR0 - addi r13, r13, 4 - mtspr SPRN_SRR0, r13 - GET_SCRATCH0(r13) - rfid - b . - -kvmppc_skip_Hinterrupt: - /* - * Here all GPRs are unchanged from when the interrupt happened - * except for r13, which is saved in SPRG_SCRATCH0. - */ - mfspr r13, SPRN_HSRR0 - addi r13, r13, 4 - mtspr SPRN_HSRR0, r13 - GET_SCRATCH0(r13) - hrfid - b . -#endif - -/* - * Ensure that any handlers that get invoked from the exception prologs - * above are below the first 64KB (0x10000) of the kernel image because - * the prologs assemble the addresses of these handlers using the - * LOAD_HANDLER macro, which uses an ori instruction. - */ - -/*** Common interrupt handlers ***/ - - STD_EXCEPTION_COMMON(0x100, system_reset, system_reset_exception) - - STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ) - STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, timer_interrupt) - STD_EXCEPTION_COMMON(0x980, hdecrementer, hdec_interrupt) -#ifdef CONFIG_PPC_DOORBELL - STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, doorbell_exception) -#else - STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, unknown_exception) -#endif - STD_EXCEPTION_COMMON(0xb00, trap_0b, unknown_exception) - STD_EXCEPTION_COMMON(0xd00, single_step, single_step_exception) - STD_EXCEPTION_COMMON(0xe00, trap_0e, unknown_exception) - STD_EXCEPTION_COMMON(0xe40, emulation_assist, emulation_assist_interrupt) - STD_EXCEPTION_COMMON_ASYNC(0xe60, hmi_exception, handle_hmi_exception) -#ifdef CONFIG_PPC_DOORBELL - STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, doorbell_exception) -#else - STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, unknown_exception) -#endif - STD_EXCEPTION_COMMON_ASYNC(0xea0, h_virt_irq, do_IRQ) - STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, performance_monitor_exception) - STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, instruction_breakpoint_exception) - STD_EXCEPTION_COMMON(0x1502, denorm, unknown_exception) -#ifdef CONFIG_ALTIVEC - STD_EXCEPTION_COMMON(0x1700, altivec_assist, altivec_assist_exception) -#else - STD_EXCEPTION_COMMON(0x1700, altivec_assist, unknown_exception) -#endif - - /* - * Relocation-on interrupts: A subset of the interrupts can be delivered - * with IR=1/DR=1, if AIL==2 and MSR.HV won't be changed by delivering - * it. Addresses are the same as the original interrupt addresses, but - * offset by 0xc000000000004000. - * It's impossible to receive interrupts below 0x300 via this mechanism. - * KVM: None of these traps are from the guest ; anything that escalated - * to HV=1 from HV=0 is delivered via real mode handlers. - */ - - /* - * This uses the standard macro, since the original 0x300 vector - * only has extra guff for STAB-based processors -- which never - * come here. - */ - STD_RELON_EXCEPTION_PSERIES(0x4300, 0x300, data_access) - . = 0x4380 - .globl data_access_slb_relon_pSeries -data_access_slb_relon_pSeries: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXSLB) - EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x380) - std r3,PACA_EXSLB+EX_R3(r13) - mfspr r3,SPRN_DAR - mfspr r12,SPRN_SRR1 -#ifndef CONFIG_RELOCATABLE - b slb_miss_realmode -#else - /* - * We can't just use a direct branch to slb_miss_realmode - * because the distance from here to there depends on where - * the kernel ends up being put. - */ - mfctr r11 - ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, slb_miss_realmode) - mtctr r10 - bctr -#endif - - STD_RELON_EXCEPTION_PSERIES(0x4400, 0x400, instruction_access) - . = 0x4480 - .globl instruction_access_slb_relon_pSeries -instruction_access_slb_relon_pSeries: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXSLB) - EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x480) - std r3,PACA_EXSLB+EX_R3(r13) - mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ + ld r10,PACAKMSR(r13) + xori r10,r10,MSR_RI + mfspr r11,SPRN_SRR0 + LOAD_HANDLER(r12, machine_check_common) + mtspr SPRN_SRR0,r12 mfspr r12,SPRN_SRR1 -#ifndef CONFIG_RELOCATABLE - b slb_miss_realmode -#else - mfctr r11 - ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, slb_miss_realmode) - mtctr r10 - bctr -#endif - - . = 0x4500 - .globl hardware_interrupt_relon_pSeries; - .globl hardware_interrupt_relon_hv; -hardware_interrupt_relon_pSeries: -hardware_interrupt_relon_hv: - BEGIN_FTR_SECTION - _MASKABLE_RELON_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV, SOFTEN_TEST_HV) - FTR_SECTION_ELSE - _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD, SOFTEN_TEST_PR) - ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) - STD_RELON_EXCEPTION_PSERIES(0x4600, 0x600, alignment) - STD_RELON_EXCEPTION_PSERIES(0x4700, 0x700, program_check) - STD_RELON_EXCEPTION_PSERIES(0x4800, 0x800, fp_unavailable) - MASKABLE_RELON_EXCEPTION_PSERIES(0x4900, 0x900, decrementer) - STD_RELON_EXCEPTION_HV(0x4980, 0x982, hdecrementer) - MASKABLE_RELON_EXCEPTION_PSERIES(0x4a00, 0xa00, doorbell_super) - STD_RELON_EXCEPTION_PSERIES(0x4b00, 0xb00, trap_0b) - - . = 0x4c00 - .globl system_call_relon_pSeries -system_call_relon_pSeries: - HMT_MEDIUM - SYSCALL_PSERIES_1 - SYSCALL_PSERIES_2_DIRECT - SYSCALL_PSERIES_3 - - STD_RELON_EXCEPTION_PSERIES(0x4d00, 0xd00, single_step) - - . = 0x4e00 - b . /* Can't happen, see v2.07 Book III-S section 6.5 */ - - . = 0x4e20 - b . /* Can't happen, see v2.07 Book III-S section 6.5 */ - - . = 0x4e40 -emulation_assist_relon_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b emulation_assist_relon_hv - - . = 0x4e60 - b . /* Can't happen, see v2.07 Book III-S section 6.5 */ - - . = 0x4e80 -h_doorbell_relon_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_doorbell_relon_hv - - . = 0x4ea0 -h_virt_irq_relon_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_virt_irq_relon_hv - - . = 0x4f00 -performance_monitor_relon_pseries_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b performance_monitor_relon_pSeries - - . = 0x4f20 -altivec_unavailable_relon_pseries_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b altivec_unavailable_relon_pSeries - - . = 0x4f40 -vsx_unavailable_relon_pseries_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b vsx_unavailable_relon_pSeries - - . = 0x4f60 -facility_unavailable_relon_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b facility_unavailable_relon_pSeries - - . = 0x4f80 -hv_facility_unavailable_relon_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b hv_facility_unavailable_relon_hv - - STD_RELON_EXCEPTION_PSERIES(0x5300, 0x1300, instruction_breakpoint) -#ifdef CONFIG_PPC_DENORMALISATION - . = 0x5500 - b denorm_exception_hv -#endif - STD_RELON_EXCEPTION_PSERIES(0x5700, 0x1700, altivec_assist) - - .align 7 -system_call_entry: - b system_call_common - -ppc64_runlatch_on_trampoline: - b __ppc64_runlatch_on - -/* - * Here r13 points to the paca, r9 contains the saved CR, - * SRR0 and SRR1 are saved in r11 and r12, - * r9 - r13 are saved in paca->exgen. - */ - .align 7 - .globl data_access_common -data_access_common: - mfspr r10,SPRN_DAR - std r10,PACA_EXGEN+EX_DAR(r13) - mfspr r10,SPRN_DSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) - EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN) - RECONCILE_IRQ_STATE(r10, r11) - ld r12,_MSR(r1) - ld r3,PACA_EXGEN+EX_DAR(r13) - lwz r4,PACA_EXGEN+EX_DSISR(r13) - li r5,0x300 - std r3,_DAR(r1) - std r4,_DSISR(r1) -BEGIN_MMU_FTR_SECTION - b do_hash_page /* Try to handle as hpte fault */ -MMU_FTR_SECTION_ELSE - b handle_page_fault -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) - - .align 7 - .globl h_data_storage_common -h_data_storage_common: - mfspr r10,SPRN_HDAR - std r10,PACA_EXGEN+EX_DAR(r13) - mfspr r10,SPRN_HDSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) - EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN) - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl unknown_exception - b ret_from_except - - .align 7 - .globl instruction_access_common -instruction_access_common: - EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN) - RECONCILE_IRQ_STATE(r10, r11) - ld r12,_MSR(r1) - ld r3,_NIP(r1) - andis. r4,r12,0x5820 - li r5,0x400 - std r3,_DAR(r1) - std r4,_DSISR(r1) -BEGIN_MMU_FTR_SECTION - b do_hash_page /* Try to handle as hpte fault */ -MMU_FTR_SECTION_ELSE - b handle_page_fault -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) + mtspr SPRN_SRR1,r10 + rfid + b . /* prevent speculative execution */ - STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception) +TRAMP_KVM_SKIP(PACA_EXMC, 0x200) +EXC_COMMON_BEGIN(machine_check_common) /* * Machine check is different because we use a different * save area: PACA_EXMC instead of PACA_EXGEN. */ - .align 7 - .globl machine_check_common -machine_check_common: - mfspr r10,SPRN_DAR - std r10,PACA_EXGEN+EX_DAR(r13) + std r10,PACA_EXMC+EX_DAR(r13) mfspr r10,SPRN_DSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) + stw r10,PACA_EXMC+EX_DSISR(r13) EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) FINISH_NAP RECONCILE_IRQ_STATE(r10, r11) - ld r3,PACA_EXGEN+EX_DAR(r13) - lwz r4,PACA_EXGEN+EX_DSISR(r13) + ld r3,PACA_EXMC+EX_DAR(r13) + lwz r4,PACA_EXMC+EX_DSISR(r13) + /* Enable MSR_RI when finished with PACA_EXMC */ + li r10,MSR_RI + mtmsrd r10,1 std r3,_DAR(r1) std r4,_DSISR(r1) bl save_nvgprs @@ -984,230 +294,6 @@ machine_check_common: bl machine_check_exception b ret_from_except - .align 7 - .globl alignment_common -alignment_common: - mfspr r10,SPRN_DAR - std r10,PACA_EXGEN+EX_DAR(r13) - mfspr r10,SPRN_DSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) - EXCEPTION_PROLOG_COMMON(0x600, PACA_EXGEN) - ld r3,PACA_EXGEN+EX_DAR(r13) - lwz r4,PACA_EXGEN+EX_DSISR(r13) - std r3,_DAR(r1) - std r4,_DSISR(r1) - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl alignment_exception - b ret_from_except - - .align 7 - .globl program_check_common -program_check_common: - EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl program_check_exception - b ret_from_except - - .align 7 - .globl fp_unavailable_common -fp_unavailable_common: - EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN) - bne 1f /* if from user, just load it up */ - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl kernel_fp_unavailable_exception - BUG_OPCODE -1: -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -BEGIN_FTR_SECTION - /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in - * transaction), go do TM stuff - */ - rldicl. r0, r12, (64-MSR_TS_LG), (64-2) - bne- 2f -END_FTR_SECTION_IFSET(CPU_FTR_TM) -#endif - bl load_up_fpu - b fast_exception_return -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -2: /* User process was in a transaction */ - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl fp_unavailable_tm - b ret_from_except -#endif - .align 7 - .globl altivec_unavailable_common -altivec_unavailable_common: - EXCEPTION_PROLOG_COMMON(0xf20, PACA_EXGEN) -#ifdef CONFIG_ALTIVEC -BEGIN_FTR_SECTION - beq 1f -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - BEGIN_FTR_SECTION_NESTED(69) - /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in - * transaction), go do TM stuff - */ - rldicl. r0, r12, (64-MSR_TS_LG), (64-2) - bne- 2f - END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) -#endif - bl load_up_altivec - b fast_exception_return -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -2: /* User process was in a transaction */ - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl altivec_unavailable_tm - b ret_from_except -#endif -1: -END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) -#endif - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl altivec_unavailable_exception - b ret_from_except - - .align 7 - .globl vsx_unavailable_common -vsx_unavailable_common: - EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN) -#ifdef CONFIG_VSX -BEGIN_FTR_SECTION - beq 1f -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - BEGIN_FTR_SECTION_NESTED(69) - /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in - * transaction), go do TM stuff - */ - rldicl. r0, r12, (64-MSR_TS_LG), (64-2) - bne- 2f - END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) -#endif - b load_up_vsx -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -2: /* User process was in a transaction */ - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl vsx_unavailable_tm - b ret_from_except -#endif -1: -END_FTR_SECTION_IFSET(CPU_FTR_VSX) -#endif - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl vsx_unavailable_exception - b ret_from_except - - /* Equivalents to the above handlers for relocation-on interrupt vectors */ - STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist) - MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell) - MASKABLE_RELON_EXCEPTION_HV_OOL(0xea0, h_virt_irq) - - STD_RELON_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor) - STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable) - STD_RELON_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable) - STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable) - STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable) - - /* - * The __end_interrupts marker must be past the out-of-line (OOL) - * handlers, so that they are copied to real address 0x100 when running - * a relocatable kernel. This ensures they can be reached from the short - * trampoline handlers (like 0x4f00, 0x4f20, etc.) which branch - * directly, without using LOAD_HANDLER(). - */ - .align 7 - .globl __end_interrupts -__end_interrupts: - -#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) -/* - * Data area reserved for FWNMI option. - * This address (0x7000) is fixed by the RPA. - */ - .= 0x7000 - .globl fwnmi_data_area -fwnmi_data_area: - - /* pseries and powernv need to keep the whole page from - * 0x7000 to 0x8000 free for use by the firmware - */ - . = 0x8000 -#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */ - - STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception) - STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception) - -#ifdef CONFIG_CBE_RAS - STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception) - STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception) - STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception) -#endif /* CONFIG_CBE_RAS */ - - .globl hmi_exception_early -hmi_exception_early: - EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, 0xe62) - mr r10,r1 /* Save r1 */ - ld r1,PACAEMERGSP(r13) /* Use emergency stack */ - subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ - std r9,_CCR(r1) /* save CR in stackframe */ - mfspr r11,SPRN_HSRR0 /* Save HSRR0 */ - std r11,_NIP(r1) /* save HSRR0 in stackframe */ - mfspr r12,SPRN_HSRR1 /* Save SRR1 */ - std r12,_MSR(r1) /* save SRR1 in stackframe */ - std r10,0(r1) /* make stack chain pointer */ - std r0,GPR0(r1) /* save r0 in stackframe */ - std r10,GPR1(r1) /* save r1 in stackframe */ - EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN) - EXCEPTION_PROLOG_COMMON_3(0xe60) - addi r3,r1,STACK_FRAME_OVERHEAD - bl hmi_exception_realmode - /* Windup the stack. */ - /* Move original HSRR0 and HSRR1 into the respective regs */ - ld r9,_MSR(r1) - mtspr SPRN_HSRR1,r9 - ld r3,_NIP(r1) - mtspr SPRN_HSRR0,r3 - ld r9,_CTR(r1) - mtctr r9 - ld r9,_XER(r1) - mtxer r9 - ld r9,_LINK(r1) - mtlr r9 - REST_GPR(0, r1) - REST_8GPRS(2, r1) - REST_GPR(10, r1) - ld r11,_CCR(r1) - mtcr r11 - REST_GPR(11, r1) - REST_2GPRS(12, r1) - /* restore original r1. */ - ld r1,GPR1(r1) - - /* - * Go to virtual mode and pull the HMI event information from - * firmware. - */ - .globl hmi_exception_after_realmode -hmi_exception_after_realmode: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b hmi_exception_hv - - #define MACHINE_CHECK_HANDLER_WINDUP \ /* Clear MSR_RI before setting SRR0 and SRR1. */\ li r0,MSR_RI; \ @@ -1243,9 +329,7 @@ hmi_exception_after_realmode: * Handle machine check early in real mode. We come here with * ME=1, MMU (IR=0 and DR=0) off and using MC emergency stack. */ - .align 7 - .globl machine_check_handle_early -machine_check_handle_early: +EXC_COMMON_BEGIN(machine_check_handle_early) std r0,GPR0(r1) /* Save r0 */ EXCEPTION_PROLOG_COMMON_3(0x200) bl save_nvgprs @@ -1334,7 +418,6 @@ machine_check_handle_early: andi. r11,r12,MSR_RI bne 2f 1: mfspr r11,SPRN_SRR0 - ld r10,PACAKBASE(r13) LOAD_HANDLER(r10,unrecover_mce) mtspr SPRN_SRR0,r10 ld r10,PACAKMSR(r13) @@ -1372,7 +455,7 @@ machine_check_handle_early: MACHINE_CHECK_HANDLER_WINDUP b machine_check_pSeries -unrecover_mce: +EXC_COMMON_BEGIN(unrecover_mce) /* Invoke machine_check_exception to print MCE event and panic. */ addi r3,r1,STACK_FRAME_OVERHEAD bl machine_check_exception @@ -1383,15 +466,155 @@ unrecover_mce: 1: addi r3,r1,STACK_FRAME_OVERHEAD bl unrecoverable_exception b 1b -/* - * r13 points to the PACA, r9 contains the saved CR, - * r12 contain the saved SRR1, SRR0 is still ready for return - * r3 has the faulting address - * r9 - r13 are saved in paca->exslb. - * r3 is saved in paca->slb_r3 - * We assume we aren't going to take any exceptions during this procedure. - */ -slb_miss_realmode: + + +EXC_REAL(data_access, 0x300, 0x380) +EXC_VIRT(data_access, 0x4300, 0x4380, 0x300) +TRAMP_KVM_SKIP(PACA_EXGEN, 0x300) + +EXC_COMMON_BEGIN(data_access_common) + /* + * Here r13 points to the paca, r9 contains the saved CR, + * SRR0 and SRR1 are saved in r11 and r12, + * r9 - r13 are saved in paca->exgen. + */ + mfspr r10,SPRN_DAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_DSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN) + RECONCILE_IRQ_STATE(r10, r11) + ld r12,_MSR(r1) + ld r3,PACA_EXGEN+EX_DAR(r13) + lwz r4,PACA_EXGEN+EX_DSISR(r13) + li r5,0x300 + std r3,_DAR(r1) + std r4,_DSISR(r1) +BEGIN_MMU_FTR_SECTION + b do_hash_page /* Try to handle as hpte fault */ +MMU_FTR_SECTION_ELSE + b handle_page_fault +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) + + +EXC_REAL_BEGIN(data_access_slb, 0x380, 0x400) + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXSLB) + EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380) + std r3,PACA_EXSLB+EX_R3(r13) + mfspr r3,SPRN_DAR + mfspr r12,SPRN_SRR1 + crset 4*cr6+eq +#ifndef CONFIG_RELOCATABLE + b slb_miss_realmode +#else + /* + * We can't just use a direct branch to slb_miss_realmode + * because the distance from here to there depends on where + * the kernel ends up being put. + */ + mfctr r11 + LOAD_HANDLER(r10, slb_miss_realmode) + mtctr r10 + bctr +#endif +EXC_REAL_END(data_access_slb, 0x380, 0x400) + +EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x4400) + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXSLB) + EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x380) + std r3,PACA_EXSLB+EX_R3(r13) + mfspr r3,SPRN_DAR + mfspr r12,SPRN_SRR1 + crset 4*cr6+eq +#ifndef CONFIG_RELOCATABLE + b slb_miss_realmode +#else + /* + * We can't just use a direct branch to slb_miss_realmode + * because the distance from here to there depends on where + * the kernel ends up being put. + */ + mfctr r11 + LOAD_HANDLER(r10, slb_miss_realmode) + mtctr r10 + bctr +#endif +EXC_VIRT_END(data_access_slb, 0x4380, 0x4400) +TRAMP_KVM_SKIP(PACA_EXSLB, 0x380) + + +EXC_REAL(instruction_access, 0x400, 0x480) +EXC_VIRT(instruction_access, 0x4400, 0x4480, 0x400) +TRAMP_KVM(PACA_EXGEN, 0x400) + +EXC_COMMON_BEGIN(instruction_access_common) + EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN) + RECONCILE_IRQ_STATE(r10, r11) + ld r12,_MSR(r1) + ld r3,_NIP(r1) + andis. r4,r12,0x5820 + li r5,0x400 + std r3,_DAR(r1) + std r4,_DSISR(r1) +BEGIN_MMU_FTR_SECTION + b do_hash_page /* Try to handle as hpte fault */ +MMU_FTR_SECTION_ELSE + b handle_page_fault +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) + + +EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x500) + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXSLB) + EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480) + std r3,PACA_EXSLB+EX_R3(r13) + mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ + mfspr r12,SPRN_SRR1 + crclr 4*cr6+eq +#ifndef CONFIG_RELOCATABLE + b slb_miss_realmode +#else + mfctr r11 + LOAD_HANDLER(r10, slb_miss_realmode) + mtctr r10 + bctr +#endif +EXC_REAL_END(instruction_access_slb, 0x480, 0x500) + +EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x4500) + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXSLB) + EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x480) + std r3,PACA_EXSLB+EX_R3(r13) + mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ + mfspr r12,SPRN_SRR1 + crclr 4*cr6+eq +#ifndef CONFIG_RELOCATABLE + b slb_miss_realmode +#else + mfctr r11 + LOAD_HANDLER(r10, slb_miss_realmode) + mtctr r10 + bctr +#endif +EXC_VIRT_END(instruction_access_slb, 0x4480, 0x4500) +TRAMP_KVM(PACA_EXSLB, 0x480) + + +/* This handler is used by both 0x380 and 0x480 slb miss interrupts */ +EXC_COMMON_BEGIN(slb_miss_realmode) + /* + * r13 points to the PACA, r9 contains the saved CR, + * r12 contain the saved SRR1, SRR0 is still ready for return + * r3 has the faulting address + * r9 - r13 are saved in paca->exslb. + * r3 is saved in paca->slb_r3 + * cr6.eq is set for a D-SLB miss, clear for a I-SLB miss + * We assume we aren't going to take any exceptions during this + * procedure. + */ mflr r10 #ifdef CONFIG_RELOCATABLE mtctr r11 @@ -1399,29 +622,31 @@ slb_miss_realmode: stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ + std r3,PACA_EXSLB+EX_DAR(r13) + crset 4*cr0+eq #ifdef CONFIG_PPC_STD_MMU_64 BEGIN_MMU_FTR_SECTION bl slb_allocate_realmode END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) #endif - /* All done -- return from exception. */ ld r10,PACA_EXSLB+EX_LR(r13) ld r3,PACA_EXSLB+EX_R3(r13) lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ - mtlr r10 + + beq 8f /* if bad address, make full stack frame */ + andi. r10,r12,MSR_RI /* check for unrecoverable exception */ -BEGIN_MMU_FTR_SECTION beq- 2f -FTR_SECTION_ELSE - b 2f -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) + + /* All done -- return from exception. */ .machine push .machine "power4" mtcrf 0x80,r9 + mtcrf 0x02,r9 /* I/D indication is in cr6 */ mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ .machine pop @@ -1435,7 +660,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) b . /* prevent speculative execution */ 2: mfspr r11,SPRN_SRR0 - ld r10,PACAKBASE(r13) LOAD_HANDLER(r10,unrecov_slb) mtspr SPRN_SRR0,r10 ld r10,PACAKMSR(r13) @@ -1443,7 +667,15 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) rfid b . -unrecov_slb: +8: mfspr r11,SPRN_SRR0 + LOAD_HANDLER(r10,bad_addr_slb) + mtspr SPRN_SRR0,r10 + ld r10,PACAKMSR(r13) + mtspr SPRN_SRR1,r10 + rfid + b . + +EXC_COMMON_BEGIN(unrecov_slb) EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB) RECONCILE_IRQ_STATE(r10, r11) bl save_nvgprs @@ -1451,9 +683,701 @@ unrecov_slb: bl unrecoverable_exception b 1b +EXC_COMMON_BEGIN(bad_addr_slb) + EXCEPTION_PROLOG_COMMON(0x380, PACA_EXSLB) + RECONCILE_IRQ_STATE(r10, r11) + ld r3, PACA_EXSLB+EX_DAR(r13) + std r3, _DAR(r1) + beq cr6, 2f + li r10, 0x480 /* fix trap number for I-SLB miss */ + std r10, _TRAP(r1) +2: bl save_nvgprs + addi r3, r1, STACK_FRAME_OVERHEAD + bl slb_miss_bad_addr + b ret_from_except + +EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x600) + .globl hardware_interrupt_hv; +hardware_interrupt_hv: + BEGIN_FTR_SECTION + _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, + EXC_HV, SOFTEN_TEST_HV) +do_kvm_H0x500: + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502) + FTR_SECTION_ELSE + _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, + EXC_STD, SOFTEN_TEST_PR) +do_kvm_0x500: + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500) + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) +EXC_REAL_END(hardware_interrupt, 0x500, 0x600) + +EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x4600) + .globl hardware_interrupt_relon_hv; +hardware_interrupt_relon_hv: + BEGIN_FTR_SECTION + _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, EXC_HV, SOFTEN_TEST_HV) + FTR_SECTION_ELSE + _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, EXC_STD, SOFTEN_TEST_PR) + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) +EXC_VIRT_END(hardware_interrupt, 0x4500, 0x4600) + +EXC_COMMON_ASYNC(hardware_interrupt_common, 0x500, do_IRQ) + + +EXC_REAL(alignment, 0x600, 0x700) +EXC_VIRT(alignment, 0x4600, 0x4700, 0x600) +TRAMP_KVM(PACA_EXGEN, 0x600) +EXC_COMMON_BEGIN(alignment_common) + mfspr r10,SPRN_DAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_DSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0x600, PACA_EXGEN) + ld r3,PACA_EXGEN+EX_DAR(r13) + lwz r4,PACA_EXGEN+EX_DSISR(r13) + std r3,_DAR(r1) + std r4,_DSISR(r1) + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl alignment_exception + b ret_from_except + + +EXC_REAL(program_check, 0x700, 0x800) +EXC_VIRT(program_check, 0x4700, 0x4800, 0x700) +TRAMP_KVM(PACA_EXGEN, 0x700) +EXC_COMMON_BEGIN(program_check_common) + EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl program_check_exception + b ret_from_except + + +EXC_REAL(fp_unavailable, 0x800, 0x900) +EXC_VIRT(fp_unavailable, 0x4800, 0x4900, 0x800) +TRAMP_KVM(PACA_EXGEN, 0x800) +EXC_COMMON_BEGIN(fp_unavailable_common) + EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN) + bne 1f /* if from user, just load it up */ + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl kernel_fp_unavailable_exception + BUG_OPCODE +1: +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +BEGIN_FTR_SECTION + /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in + * transaction), go do TM stuff + */ + rldicl. r0, r12, (64-MSR_TS_LG), (64-2) + bne- 2f +END_FTR_SECTION_IFSET(CPU_FTR_TM) +#endif + bl load_up_fpu + b fast_exception_return +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +2: /* User process was in a transaction */ + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl fp_unavailable_tm + b ret_from_except +#endif + + +EXC_REAL_MASKABLE(decrementer, 0x900, 0x980) +EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x4980, 0x900) +TRAMP_KVM(PACA_EXGEN, 0x900) +EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt) + + +EXC_REAL_HV(hdecrementer, 0x980, 0xa00) +EXC_VIRT_HV(hdecrementer, 0x4980, 0x4a00, 0x980) +TRAMP_KVM_HV(PACA_EXGEN, 0x980) +EXC_COMMON(hdecrementer_common, 0x980, hdec_interrupt) + + +EXC_REAL_MASKABLE(doorbell_super, 0xa00, 0xb00) +EXC_VIRT_MASKABLE(doorbell_super, 0x4a00, 0x4b00, 0xa00) +TRAMP_KVM(PACA_EXGEN, 0xa00) +#ifdef CONFIG_PPC_DOORBELL +EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, doorbell_exception) +#else +EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, unknown_exception) +#endif + + +EXC_REAL(trap_0b, 0xb00, 0xc00) +EXC_VIRT(trap_0b, 0x4b00, 0x4c00, 0xb00) +TRAMP_KVM(PACA_EXGEN, 0xb00) +EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) + + +#define LOAD_SYSCALL_HANDLER(reg) \ + ld reg,PACAKBASE(r13); \ + ori reg,reg,(ABS_ADDR(system_call_common))@l; + +/* Syscall routine is used twice, in reloc-off and reloc-on paths */ +#define SYSCALL_PSERIES_1 \ +BEGIN_FTR_SECTION \ + cmpdi r0,0x1ebe ; \ + beq- 1f ; \ +END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ + mr r9,r13 ; \ + GET_PACA(r13) ; \ + mfspr r11,SPRN_SRR0 ; \ +0: + +#define SYSCALL_PSERIES_2_RFID \ + mfspr r12,SPRN_SRR1 ; \ + LOAD_SYSCALL_HANDLER(r10) ; \ + mtspr SPRN_SRR0,r10 ; \ + ld r10,PACAKMSR(r13) ; \ + mtspr SPRN_SRR1,r10 ; \ + rfid ; \ + b . ; /* prevent speculative execution */ + +#define SYSCALL_PSERIES_3 \ + /* Fast LE/BE switch system call */ \ +1: mfspr r12,SPRN_SRR1 ; \ + xori r12,r12,MSR_LE ; \ + mtspr SPRN_SRR1,r12 ; \ + rfid ; /* return to userspace */ \ + b . ; /* prevent speculative execution */ + +#if defined(CONFIG_RELOCATABLE) + /* + * We can't branch directly so we do it via the CTR which + * is volatile across system calls. + */ +#define SYSCALL_PSERIES_2_DIRECT \ + LOAD_SYSCALL_HANDLER(r12) ; \ + mtctr r12 ; \ + mfspr r12,SPRN_SRR1 ; \ + li r10,MSR_RI ; \ + mtmsrd r10,1 ; \ + bctr ; +#else + /* We can branch directly */ +#define SYSCALL_PSERIES_2_DIRECT \ + mfspr r12,SPRN_SRR1 ; \ + li r10,MSR_RI ; \ + mtmsrd r10,1 ; /* Set RI (EE=0) */ \ + b system_call_common ; +#endif + +EXC_REAL_BEGIN(system_call, 0xc00, 0xd00) + /* + * If CONFIG_KVM_BOOK3S_64_HANDLER is set, save the PPR (on systems + * that support it) before changing to HMT_MEDIUM. That allows the KVM + * code to save that value into the guest state (it is the guest's PPR + * value). Otherwise just change to HMT_MEDIUM as userspace has + * already saved the PPR. + */ +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER + SET_SCRATCH0(r13) + GET_PACA(r13) + std r9,PACA_EXGEN+EX_R9(r13) + OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR); + HMT_MEDIUM; + std r10,PACA_EXGEN+EX_R10(r13) + OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r9, CPU_FTR_HAS_PPR); + mfcr r9 + KVMTEST_PR(0xc00) + GET_SCRATCH0(r13) +#else + HMT_MEDIUM; +#endif + SYSCALL_PSERIES_1 + SYSCALL_PSERIES_2_RFID + SYSCALL_PSERIES_3 +EXC_REAL_END(system_call, 0xc00, 0xd00) + +EXC_VIRT_BEGIN(system_call, 0x4c00, 0x4d00) + HMT_MEDIUM + SYSCALL_PSERIES_1 + SYSCALL_PSERIES_2_DIRECT + SYSCALL_PSERIES_3 +EXC_VIRT_END(system_call, 0x4c00, 0x4d00) + +TRAMP_KVM(PACA_EXGEN, 0xc00) + + +EXC_REAL(single_step, 0xd00, 0xe00) +EXC_VIRT(single_step, 0x4d00, 0x4e00, 0xd00) +TRAMP_KVM(PACA_EXGEN, 0xd00) +EXC_COMMON(single_step_common, 0xd00, single_step_exception) + +EXC_REAL_OOL_HV(h_data_storage, 0xe00, 0xe20) +EXC_VIRT_NONE(0x4e00, 0x4e20) +TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0xe00) +EXC_COMMON_BEGIN(h_data_storage_common) + mfspr r10,SPRN_HDAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_HDSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN) + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl unknown_exception + b ret_from_except + + +EXC_REAL_OOL_HV(h_instr_storage, 0xe20, 0xe40) +EXC_VIRT_NONE(0x4e20, 0x4e40) +TRAMP_KVM_HV(PACA_EXGEN, 0xe20) +EXC_COMMON(h_instr_storage_common, 0xe20, unknown_exception) + + +EXC_REAL_OOL_HV(emulation_assist, 0xe40, 0xe60) +EXC_VIRT_OOL_HV(emulation_assist, 0x4e40, 0x4e60, 0xe40) +TRAMP_KVM_HV(PACA_EXGEN, 0xe40) +EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt) + + +/* + * hmi_exception trampoline is a special case. It jumps to hmi_exception_early + * first, and then eventaully from there to the trampoline to get into virtual + * mode. + */ +__EXC_REAL_OOL_HV_DIRECT(hmi_exception, 0xe60, 0xe80, hmi_exception_early) +__TRAMP_REAL_REAL_OOL_MASKABLE_HV(hmi_exception, 0xe60) +EXC_VIRT_NONE(0x4e60, 0x4e80) +TRAMP_KVM_HV(PACA_EXGEN, 0xe60) +TRAMP_REAL_BEGIN(hmi_exception_early) + EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, 0xe60) + mr r10,r1 /* Save r1 */ + ld r1,PACAEMERGSP(r13) /* Use emergency stack */ + subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ + std r9,_CCR(r1) /* save CR in stackframe */ + mfspr r11,SPRN_HSRR0 /* Save HSRR0 */ + std r11,_NIP(r1) /* save HSRR0 in stackframe */ + mfspr r12,SPRN_HSRR1 /* Save SRR1 */ + std r12,_MSR(r1) /* save SRR1 in stackframe */ + std r10,0(r1) /* make stack chain pointer */ + std r0,GPR0(r1) /* save r0 in stackframe */ + std r10,GPR1(r1) /* save r1 in stackframe */ + EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN) + EXCEPTION_PROLOG_COMMON_3(0xe60) + addi r3,r1,STACK_FRAME_OVERHEAD + bl hmi_exception_realmode + /* Windup the stack. */ + /* Move original HSRR0 and HSRR1 into the respective regs */ + ld r9,_MSR(r1) + mtspr SPRN_HSRR1,r9 + ld r3,_NIP(r1) + mtspr SPRN_HSRR0,r3 + ld r9,_CTR(r1) + mtctr r9 + ld r9,_XER(r1) + mtxer r9 + ld r9,_LINK(r1) + mtlr r9 + REST_GPR(0, r1) + REST_8GPRS(2, r1) + REST_GPR(10, r1) + ld r11,_CCR(r1) + mtcr r11 + REST_GPR(11, r1) + REST_2GPRS(12, r1) + /* restore original r1. */ + ld r1,GPR1(r1) + + /* + * Go to virtual mode and pull the HMI event information from + * firmware. + */ + .globl hmi_exception_after_realmode +hmi_exception_after_realmode: + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXGEN) + b tramp_real_hmi_exception + +EXC_COMMON_ASYNC(hmi_exception_common, 0xe60, handle_hmi_exception) + + +EXC_REAL_OOL_MASKABLE_HV(h_doorbell, 0xe80, 0xea0) +EXC_VIRT_OOL_MASKABLE_HV(h_doorbell, 0x4e80, 0x4ea0, 0xe80) +TRAMP_KVM_HV(PACA_EXGEN, 0xe80) +#ifdef CONFIG_PPC_DOORBELL +EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, doorbell_exception) +#else +EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, unknown_exception) +#endif + + +EXC_REAL_OOL_MASKABLE_HV(h_virt_irq, 0xea0, 0xec0) +EXC_VIRT_OOL_MASKABLE_HV(h_virt_irq, 0x4ea0, 0x4ec0, 0xea0) +TRAMP_KVM_HV(PACA_EXGEN, 0xea0) +EXC_COMMON_ASYNC(h_virt_irq_common, 0xea0, do_IRQ) + + +EXC_REAL_NONE(0xec0, 0xf00) +EXC_VIRT_NONE(0x4ec0, 0x4f00) + + +EXC_REAL_OOL(performance_monitor, 0xf00, 0xf20) +EXC_VIRT_OOL(performance_monitor, 0x4f00, 0x4f20, 0xf00) +TRAMP_KVM(PACA_EXGEN, 0xf00) +EXC_COMMON_ASYNC(performance_monitor_common, 0xf00, performance_monitor_exception) + + +EXC_REAL_OOL(altivec_unavailable, 0xf20, 0xf40) +EXC_VIRT_OOL(altivec_unavailable, 0x4f20, 0x4f40, 0xf20) +TRAMP_KVM(PACA_EXGEN, 0xf20) +EXC_COMMON_BEGIN(altivec_unavailable_common) + EXCEPTION_PROLOG_COMMON(0xf20, PACA_EXGEN) +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + beq 1f +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + BEGIN_FTR_SECTION_NESTED(69) + /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in + * transaction), go do TM stuff + */ + rldicl. r0, r12, (64-MSR_TS_LG), (64-2) + bne- 2f + END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) +#endif + bl load_up_altivec + b fast_exception_return +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +2: /* User process was in a transaction */ + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl altivec_unavailable_tm + b ret_from_except +#endif +1: +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#endif + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl altivec_unavailable_exception + b ret_from_except + + +EXC_REAL_OOL(vsx_unavailable, 0xf40, 0xf60) +EXC_VIRT_OOL(vsx_unavailable, 0x4f40, 0x4f60, 0xf40) +TRAMP_KVM(PACA_EXGEN, 0xf40) +EXC_COMMON_BEGIN(vsx_unavailable_common) + EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN) +#ifdef CONFIG_VSX +BEGIN_FTR_SECTION + beq 1f +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + BEGIN_FTR_SECTION_NESTED(69) + /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in + * transaction), go do TM stuff + */ + rldicl. r0, r12, (64-MSR_TS_LG), (64-2) + bne- 2f + END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) +#endif + b load_up_vsx +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +2: /* User process was in a transaction */ + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl vsx_unavailable_tm + b ret_from_except +#endif +1: +END_FTR_SECTION_IFSET(CPU_FTR_VSX) +#endif + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl vsx_unavailable_exception + b ret_from_except + + +EXC_REAL_OOL(facility_unavailable, 0xf60, 0xf80) +EXC_VIRT_OOL(facility_unavailable, 0x4f60, 0x4f80, 0xf60) +TRAMP_KVM(PACA_EXGEN, 0xf60) +EXC_COMMON(facility_unavailable_common, 0xf60, facility_unavailable_exception) + + +EXC_REAL_OOL_HV(h_facility_unavailable, 0xf80, 0xfa0) +EXC_VIRT_OOL_HV(h_facility_unavailable, 0x4f80, 0x4fa0, 0xf80) +TRAMP_KVM_HV(PACA_EXGEN, 0xf80) +EXC_COMMON(h_facility_unavailable_common, 0xf80, facility_unavailable_exception) + + +EXC_REAL_NONE(0xfa0, 0x1200) +EXC_VIRT_NONE(0x4fa0, 0x5200) + +#ifdef CONFIG_CBE_RAS +EXC_REAL_HV(cbe_system_error, 0x1200, 0x1300) +EXC_VIRT_NONE(0x5200, 0x5300) +TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1200) +EXC_COMMON(cbe_system_error_common, 0x1200, cbe_system_error_exception) +#else /* CONFIG_CBE_RAS */ +EXC_REAL_NONE(0x1200, 0x1300) +EXC_VIRT_NONE(0x5200, 0x5300) +#endif + + +EXC_REAL(instruction_breakpoint, 0x1300, 0x1400) +EXC_VIRT(instruction_breakpoint, 0x5300, 0x5400, 0x1300) +TRAMP_KVM_SKIP(PACA_EXGEN, 0x1300) +EXC_COMMON(instruction_breakpoint_common, 0x1300, instruction_breakpoint_exception) + +EXC_REAL_NONE(0x1400, 0x1500) +EXC_VIRT_NONE(0x5400, 0x5500) + +EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x1600) + mtspr SPRN_SPRG_HSCRATCH0,r13 + EXCEPTION_PROLOG_0(PACA_EXGEN) + EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500) + +#ifdef CONFIG_PPC_DENORMALISATION + mfspr r10,SPRN_HSRR1 + mfspr r11,SPRN_HSRR0 /* save HSRR0 */ + andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */ + addi r11,r11,-4 /* HSRR0 is next instruction */ + bne+ denorm_assist +#endif + + KVMTEST_PR(0x1500) + EXCEPTION_PROLOG_PSERIES_1(denorm_common, EXC_HV) +EXC_REAL_END(denorm_exception_hv, 0x1500, 0x1600) + +#ifdef CONFIG_PPC_DENORMALISATION +EXC_VIRT_BEGIN(denorm_exception, 0x5500, 0x5600) + b exc_real_0x1500_denorm_exception_hv +EXC_VIRT_END(denorm_exception, 0x5500, 0x5600) +#else +EXC_VIRT_NONE(0x5500, 0x5600) +#endif + +TRAMP_KVM_SKIP(PACA_EXGEN, 0x1500) + +#ifdef CONFIG_PPC_DENORMALISATION +TRAMP_REAL_BEGIN(denorm_assist) +BEGIN_FTR_SECTION +/* + * To denormalise we need to move a copy of the register to itself. + * For POWER6 do that here for all FP regs. + */ + mfmsr r10 + ori r10,r10,(MSR_FP|MSR_FE0|MSR_FE1) + xori r10,r10,(MSR_FE0|MSR_FE1) + mtmsrd r10 + sync + +#define FMR2(n) fmr (n), (n) ; fmr n+1, n+1 +#define FMR4(n) FMR2(n) ; FMR2(n+2) +#define FMR8(n) FMR4(n) ; FMR4(n+4) +#define FMR16(n) FMR8(n) ; FMR8(n+8) +#define FMR32(n) FMR16(n) ; FMR16(n+16) + FMR32(0) + +FTR_SECTION_ELSE +/* + * To denormalise we need to move a copy of the register to itself. + * For POWER7 do that here for the first 32 VSX registers only. + */ + mfmsr r10 + oris r10,r10,MSR_VSX@h + mtmsrd r10 + sync + +#define XVCPSGNDP2(n) XVCPSGNDP(n,n,n) ; XVCPSGNDP(n+1,n+1,n+1) +#define XVCPSGNDP4(n) XVCPSGNDP2(n) ; XVCPSGNDP2(n+2) +#define XVCPSGNDP8(n) XVCPSGNDP4(n) ; XVCPSGNDP4(n+4) +#define XVCPSGNDP16(n) XVCPSGNDP8(n) ; XVCPSGNDP8(n+8) +#define XVCPSGNDP32(n) XVCPSGNDP16(n) ; XVCPSGNDP16(n+16) + XVCPSGNDP32(0) + +ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206) + +BEGIN_FTR_SECTION + b denorm_done +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) +/* + * To denormalise we need to move a copy of the register to itself. + * For POWER8 we need to do that for all 64 VSX registers + */ + XVCPSGNDP32(32) +denorm_done: + mtspr SPRN_HSRR0,r11 + mtcrf 0x80,r9 + ld r9,PACA_EXGEN+EX_R9(r13) + RESTORE_PPR_PACA(PACA_EXGEN, r10) +BEGIN_FTR_SECTION + ld r10,PACA_EXGEN+EX_CFAR(r13) + mtspr SPRN_CFAR,r10 +END_FTR_SECTION_IFSET(CPU_FTR_CFAR) + ld r10,PACA_EXGEN+EX_R10(r13) + ld r11,PACA_EXGEN+EX_R11(r13) + ld r12,PACA_EXGEN+EX_R12(r13) + ld r13,PACA_EXGEN+EX_R13(r13) + HRFID + b . +#endif + +EXC_COMMON_HV(denorm_common, 0x1500, unknown_exception) + + +#ifdef CONFIG_CBE_RAS +EXC_REAL_HV(cbe_maintenance, 0x1600, 0x1700) +EXC_VIRT_NONE(0x5600, 0x5700) +TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1600) +EXC_COMMON(cbe_maintenance_common, 0x1600, cbe_maintenance_exception) +#else /* CONFIG_CBE_RAS */ +EXC_REAL_NONE(0x1600, 0x1700) +EXC_VIRT_NONE(0x5600, 0x5700) +#endif + + +EXC_REAL(altivec_assist, 0x1700, 0x1800) +EXC_VIRT(altivec_assist, 0x5700, 0x5800, 0x1700) +TRAMP_KVM(PACA_EXGEN, 0x1700) +#ifdef CONFIG_ALTIVEC +EXC_COMMON(altivec_assist_common, 0x1700, altivec_assist_exception) +#else +EXC_COMMON(altivec_assist_common, 0x1700, unknown_exception) +#endif + + +#ifdef CONFIG_CBE_RAS +EXC_REAL_HV(cbe_thermal, 0x1800, 0x1900) +EXC_VIRT_NONE(0x5800, 0x5900) +TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1800) +EXC_COMMON(cbe_thermal_common, 0x1800, cbe_thermal_exception) +#else /* CONFIG_CBE_RAS */ +EXC_REAL_NONE(0x1800, 0x1900) +EXC_VIRT_NONE(0x5800, 0x5900) +#endif + + +/* + * An interrupt came in while soft-disabled. We set paca->irq_happened, then: + * - If it was a decrementer interrupt, we bump the dec to max and and return. + * - If it was a doorbell we return immediately since doorbells are edge + * triggered and won't automatically refire. + * - If it was a HMI we return immediately since we handled it in realmode + * and it won't refire. + * - else we hard disable and return. + * This is called with r10 containing the value to OR to the paca field. + */ +#define MASKED_INTERRUPT(_H) \ +masked_##_H##interrupt: \ + std r11,PACA_EXGEN+EX_R11(r13); \ + lbz r11,PACAIRQHAPPENED(r13); \ + or r11,r11,r10; \ + stb r11,PACAIRQHAPPENED(r13); \ + cmpwi r10,PACA_IRQ_DEC; \ + bne 1f; \ + lis r10,0x7fff; \ + ori r10,r10,0xffff; \ + mtspr SPRN_DEC,r10; \ + b 2f; \ +1: cmpwi r10,PACA_IRQ_DBELL; \ + beq 2f; \ + cmpwi r10,PACA_IRQ_HMI; \ + beq 2f; \ + mfspr r10,SPRN_##_H##SRR1; \ + rldicl r10,r10,48,1; /* clear MSR_EE */ \ + rotldi r10,r10,16; \ + mtspr SPRN_##_H##SRR1,r10; \ +2: mtcrf 0x80,r9; \ + ld r9,PACA_EXGEN+EX_R9(r13); \ + ld r10,PACA_EXGEN+EX_R10(r13); \ + ld r11,PACA_EXGEN+EX_R11(r13); \ + GET_SCRATCH0(r13); \ + ##_H##rfid; \ + b . + +/* + * Real mode exceptions actually use this too, but alternate + * instruction code patches (which end up in the common .text area) + * cannot reach these if they are put there. + */ +USE_FIXED_SECTION(virt_trampolines) + MASKED_INTERRUPT() + MASKED_INTERRUPT(H) + +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +TRAMP_REAL_BEGIN(kvmppc_skip_interrupt) + /* + * Here all GPRs are unchanged from when the interrupt happened + * except for r13, which is saved in SPRG_SCRATCH0. + */ + mfspr r13, SPRN_SRR0 + addi r13, r13, 4 + mtspr SPRN_SRR0, r13 + GET_SCRATCH0(r13) + rfid + b . + +TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt) + /* + * Here all GPRs are unchanged from when the interrupt happened + * except for r13, which is saved in SPRG_SCRATCH0. + */ + mfspr r13, SPRN_HSRR0 + addi r13, r13, 4 + mtspr SPRN_HSRR0, r13 + GET_SCRATCH0(r13) + hrfid + b . +#endif + +/* + * Ensure that any handlers that get invoked from the exception prologs + * above are below the first 64KB (0x10000) of the kernel image because + * the prologs assemble the addresses of these handlers using the + * LOAD_HANDLER macro, which uses an ori instruction. + */ + +/*** Common interrupt handlers ***/ + + + /* + * Relocation-on interrupts: A subset of the interrupts can be delivered + * with IR=1/DR=1, if AIL==2 and MSR.HV won't be changed by delivering + * it. Addresses are the same as the original interrupt addresses, but + * offset by 0xc000000000004000. + * It's impossible to receive interrupts below 0x300 via this mechanism. + * KVM: None of these traps are from the guest ; anything that escalated + * to HV=1 from HV=0 is delivered via real mode handlers. + */ + + /* + * This uses the standard macro, since the original 0x300 vector + * only has extra guff for STAB-based processors -- which never + * come here. + */ + +EXC_COMMON_BEGIN(ppc64_runlatch_on_trampoline) + b __ppc64_runlatch_on + +USE_FIXED_SECTION(virt_trampolines) + /* + * The __end_interrupts marker must be past the out-of-line (OOL) + * handlers, so that they are copied to real address 0x100 when running + * a relocatable kernel. This ensures they can be reached from the short + * trampoline handlers (like 0x4f00, 0x4f20, etc.) which branch + * directly, without using LOAD_HANDLER(). + */ + .align 7 + .globl __end_interrupts +__end_interrupts: +DEFINE_FIXED_SYMBOL(__end_interrupts) #ifdef CONFIG_PPC_970_NAP -power4_fixup_nap: +TRAMP_REAL_BEGIN(power4_fixup_nap) andc r9,r9,r10 std r9,TI_LOCAL_FLAGS(r11) ld r10,_LINK(r1) /* make idle task do the */ @@ -1461,6 +1385,13 @@ power4_fixup_nap: blr #endif +CLOSE_FIXED_SECTION(real_vectors); +CLOSE_FIXED_SECTION(real_trampolines); +CLOSE_FIXED_SECTION(virt_vectors); +CLOSE_FIXED_SECTION(virt_trampolines); + +USE_TEXT_SECTION() + /* * Hash table stuff */ @@ -1606,3 +1537,39 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) 1: addi r3,r1,STACK_FRAME_OVERHEAD bl kernel_bad_stack b 1b + +/* + * Called from arch_local_irq_enable when an interrupt needs + * to be resent. r3 contains 0x500, 0x900, 0xa00 or 0xe80 to indicate + * which kind of interrupt. MSR:EE is already off. We generate a + * stackframe like if a real interrupt had happened. + * + * Note: While MSR:EE is off, we need to make sure that _MSR + * in the generated frame has EE set to 1 or the exception + * handler will not properly re-enable them. + */ +_GLOBAL(__replay_interrupt) + /* We are going to jump to the exception common code which + * will retrieve various register values from the PACA which + * we don't give a damn about, so we don't bother storing them. + */ + mfmsr r12 + mflr r11 + mfcr r9 + ori r12,r12,MSR_EE + cmpwi r3,0x900 + beq decrementer_common + cmpwi r3,0x500 + beq hardware_interrupt_common +BEGIN_FTR_SECTION + cmpwi r3,0xe80 + beq h_doorbell_common + cmpwi r3,0xea0 + beq h_virt_irq_common + cmpwi r3,0xe60 + beq hmi_exception_common +FTR_SECTION_ELSE + cmpwi r3,0xa00 + beq doorbell_super_common +ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) + blr diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index b3a663333d36..963918e0974a 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -778,7 +778,11 @@ static int fadump_init_elfcore_header(char *bufp) elf->e_entry = 0; elf->e_phoff = sizeof(struct elfhdr); elf->e_shoff = 0; - elf->e_flags = ELF_CORE_EFLAGS; +#if defined(_CALL_ELF) + elf->e_flags = _CALL_ELF; +#else + elf->e_flags = 0; +#endif elf->e_ehsize = sizeof(struct elfhdr); elf->e_phentsize = sizeof(struct elf_phdr); elf->e_phnum = 0; @@ -1104,7 +1108,9 @@ static ssize_t fadump_release_memory_store(struct kobject *kobj, * Take away the '/proc/vmcore'. We are releasing the dump * memory, hence it will not be valid anymore. */ +#ifdef CONFIG_PROC_VMCORE vmcore_cleanup(); +#endif fadump_invalidate_release_mem(); } else diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 15da2b5df85e..08d14b096eb9 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -50,32 +50,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ #define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base) #define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base) -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -/* void do_load_up_transact_fpu(struct thread_struct *thread) - * - * This is similar to load_up_fpu but for the transactional version of the FP - * register set. It doesn't mess with the task MSR or valid flags. - * Furthermore, we don't do lazy FP with TM currently. - */ -_GLOBAL(do_load_up_transact_fpu) - mfmsr r6 - ori r5,r6,MSR_FP -#ifdef CONFIG_VSX -BEGIN_FTR_SECTION - oris r5,r5,MSR_VSX@h -END_FTR_SECTION_IFSET(CPU_FTR_VSX) -#endif - SYNC - MTMSRD(r5) - - addi r7,r3,THREAD_TRANSACT_FPSTATE - lfd fr0,FPSTATE_FPSCR(r7) - MTFSF_L(fr0) - REST_32FPVSRS(0, R4, R7) - - blr -#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ - /* * Load state from memory into FP registers including FPSCR. * Assumes the caller has enabled FP in the MSR. diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index cc52d9795f88..a95639b8d4ac 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -593,7 +593,8 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) if (!ftrace_graph_entry(&trace)) goto out; - if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) + if (ftrace_push_return_trace(parent, ip, &trace.depth, 0, + NULL) == -EBUSY) goto out; parent = return_hooker; diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index dc0488b6f6e1..a3f821eb7e9a 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -266,7 +266,6 @@ __secondary_hold_acknowledge: #define EXCEPTION_PROLOG_2 \ - CLR_TOP32(r11); \ stw r10,_CCR(r11); /* save registers */ \ stw r12,GPR12(r11); \ stw r9,GPR9(r11); \ @@ -862,7 +861,6 @@ __secondary_start: /* ptr to phys current thread */ tophys(r4,r2) addi r4,r4,THREAD /* phys address of our thread_struct */ - CLR_TOP32(r4) mtspr SPRN_SPRG_THREAD,r4 li r3,0 mtspr SPRN_SPRG_RTAS,r3 /* 0 => not in RTAS */ @@ -949,7 +947,6 @@ start_here: /* ptr to phys current thread */ tophys(r4,r2) addi r4,r4,THREAD /* init task's THREAD */ - CLR_TOP32(r4) mtspr SPRN_SPRG_THREAD,r4 li r3,0 mtspr SPRN_SPRG_RTAS,r3 /* 0 => not in RTAS */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index f765b0434731..79da0641bae2 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -28,6 +28,7 @@ #include <asm/page.h> #include <asm/mmu.h> #include <asm/ppc_asm.h> +#include <asm/head-64.h> #include <asm/asm-offsets.h> #include <asm/bug.h> #include <asm/cputable.h> @@ -65,9 +66,14 @@ * 2. The kernel is entered at __start */ - .text - .globl _stext -_stext: +OPEN_FIXED_SECTION(first_256B, 0x0, 0x100) +USE_FIXED_SECTION(first_256B) + /* + * Offsets are relative from the start of fixed section, and + * first_256B starts at 0. Offsets are a bit easier to use here + * than the fixed section entry macros. + */ + . = 0x0 _GLOBAL(__start) /* NOP this out unconditionally */ BEGIN_FTR_SECTION @@ -104,6 +110,7 @@ __secondary_hold_acknowledge: . = 0x5c .globl __run_at_load __run_at_load: +DEFINE_FIXED_SYMBOL(__run_at_load) .long 0x72756e30 /* "run0" -- relocate to 0 by default */ #endif @@ -133,7 +140,7 @@ __secondary_hold: /* Tell the master cpu we're here */ /* Relocation is off & we are located at an address less */ /* than 0x100, so only need to grab low order offset. */ - std r24,__secondary_hold_acknowledge-_stext(0) + std r24,(ABS_ADDR(__secondary_hold_acknowledge))(0) sync li r26,0 @@ -141,7 +148,7 @@ __secondary_hold: tovirt(r26,r26) #endif /* All secondary cpus wait here until told to start. */ -100: ld r12,__secondary_hold_spinloop-_stext(r26) +100: ld r12,(ABS_ADDR(__secondary_hold_spinloop))(r26) cmpdi 0,r12,0 beq 100b @@ -166,12 +173,13 @@ __secondary_hold: #else BUG_OPCODE #endif +CLOSE_FIXED_SECTION(first_256B) /* This value is used to mark exception frames on the stack. */ .section ".toc","aw" exception_marker: .tc ID_72656773_68657265[TC],0x7265677368657265 - .text + .previous /* * On server, we include the exception vectors code here as it @@ -180,8 +188,12 @@ exception_marker: */ #ifdef CONFIG_PPC_BOOK3S #include "exceptions-64s.S" +#else +OPEN_TEXT_SECTION(0x100) #endif +USE_TEXT_SECTION() + #ifdef CONFIG_PPC_BOOK3E /* * The booting_thread_hwid holds the thread id we want to boot in cpu @@ -558,7 +570,7 @@ __after_prom_start: #if defined(CONFIG_PPC_BOOK3E) tovirt(r26,r26) /* on booke, we already run at PAGE_OFFSET */ #endif - lwz r7,__run_at_load-_stext(r26) + lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26) #if defined(CONFIG_PPC_BOOK3E) tophys(r26,r26) #endif @@ -601,7 +613,7 @@ __after_prom_start: #if defined(CONFIG_PPC_BOOK3E) tovirt(r26,r26) /* on booke, we already run at PAGE_OFFSET */ #endif - lwz r7,__run_at_load-_stext(r26) + lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26) cmplwi cr0,r7,1 bne 3f @@ -611,28 +623,35 @@ __after_prom_start: sub r5,r5,r11 #else /* just copy interrupts */ - LOAD_REG_IMMEDIATE(r5, __end_interrupts - _stext) + LOAD_REG_IMMEDIATE(r5, FIXED_SYMBOL_ABS_ADDR(__end_interrupts)) #endif b 5f 3: #endif - lis r5,(copy_to_here - _stext)@ha - addi r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */ + /* # bytes of memory to copy */ + lis r5,(ABS_ADDR(copy_to_here))@ha + addi r5,r5,(ABS_ADDR(copy_to_here))@l bl copy_and_flush /* copy the first n bytes */ /* this includes the code being */ /* executed here. */ - addis r8,r3,(4f - _stext)@ha /* Jump to the copy of this code */ - addi r12,r8,(4f - _stext)@l /* that we just made */ + /* Jump to the copy of this code that we just made */ + addis r8,r3,(ABS_ADDR(4f))@ha + addi r12,r8,(ABS_ADDR(4f))@l mtctr r12 bctr .balign 8 -p_end: .llong _end - _stext +p_end: .llong _end - copy_to_here -4: /* Now copy the rest of the kernel up to _end */ - addis r5,r26,(p_end - _stext)@ha - ld r5,(p_end - _stext)@l(r5) /* get _end */ +4: + /* + * Now copy the rest of the kernel up to _end, add + * _end - copy_to_here to the copy limit and run again. + */ + addis r8,r26,(ABS_ADDR(p_end))@ha + ld r8,(ABS_ADDR(p_end))@l(r8) + add r5,r5,r8 5: bl copy_and_flush /* copy the rest */ 9: b start_here_multiplatform diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 43ddaae42baf..3a185c51ce8f 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -151,7 +151,6 @@ turn_on_mmu: #define EXCEPTION_PROLOG_2 \ - CLR_TOP32(r11); \ stw r10,_CCR(r11); /* save registers */ \ stw r12,GPR12(r11); \ stw r9,GPR9(r11); \ diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index aec9a1b1d25b..9781c69eae57 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -206,7 +206,7 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) /* * Handle debug exception notifications. */ -int __kprobes hw_breakpoint_handler(struct die_args *args) +int hw_breakpoint_handler(struct die_args *args) { int rc = NOTIFY_STOP; struct perf_event *bp; @@ -290,11 +290,12 @@ out: rcu_read_unlock(); return rc; } +NOKPROBE_SYMBOL(hw_breakpoint_handler); /* * Handle single-step exceptions following a DABR hit. */ -static int __kprobes single_step_dabr_instruction(struct die_args *args) +static int single_step_dabr_instruction(struct die_args *args) { struct pt_regs *regs = args->regs; struct perf_event *bp = NULL; @@ -329,11 +330,12 @@ static int __kprobes single_step_dabr_instruction(struct die_args *args) return NOTIFY_STOP; } +NOKPROBE_SYMBOL(single_step_dabr_instruction); /* * Handle debug exception notifications. */ -int __kprobes hw_breakpoint_exceptions_notify( +int hw_breakpoint_exceptions_notify( struct notifier_block *unused, unsigned long val, void *data) { int ret = NOTIFY_DONE; @@ -349,6 +351,7 @@ int __kprobes hw_breakpoint_exceptions_notify( return ret; } +NOKPROBE_SYMBOL(hw_breakpoint_exceptions_notify); /* * Release the user breakpoints used by ptrace diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index c1ca9282f4a0..6ca9a2ffaac7 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -227,7 +227,7 @@ int ibmebus_request_irq(u32 ist, irq_handler_t handler, { unsigned int irq = irq_create_mapping(NULL, ist); - if (irq == NO_IRQ) + if (!irq) return -EINVAL; return request_irq(irq, handler, irq_flags, devname, dev_id); diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 2265c6398a17..bd739fed26e3 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -411,7 +411,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) * * r13 - PACA * cr3 - gt if waking up with partial/complete hypervisor state loss - * cr4 - eq if waking up from complete hypervisor state loss. + * cr4 - gt or eq if waking up from complete hypervisor state loss. */ _GLOBAL(pnv_wakeup_tb_loss) ld r1,PACAR1(r13) @@ -453,7 +453,7 @@ lwarx_loop2: * At this stage * cr2 - eq if first thread to wakeup in core * cr3- gt if waking up with partial/complete hypervisor state loss - * cr4 - eq if waking up from complete hypervisor state loss. + * cr4 - gt or eq if waking up from complete hypervisor state loss. */ ori r15,r15,PNV_CORE_IDLE_LOCK_BIT @@ -481,7 +481,7 @@ first_thread_in_subcore: * If waking up from sleep, subcore state is not lost. Hence * skip subcore state restore */ - bne cr4,subcore_state_restored + blt cr4,subcore_state_restored /* Restore per-subcore state */ ld r4,_SDR1(r1) @@ -526,7 +526,7 @@ timebase_resync: * If waking up from sleep, per core state is not lost, skip to * clear_lock. */ - bne cr4,clear_lock + blt cr4,clear_lock /* * First thread in the core to wake up and its waking up with @@ -557,7 +557,7 @@ common_exit: * If waking up from sleep, hypervisor state is not lost. Hence * skip hypervisor state restore. */ - bne cr4,hypervisor_state_restored + blt cr4,hypervisor_state_restored /* Waking up from winkle */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 08887cf2b20e..3c05c311e35e 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -67,6 +67,7 @@ #include <asm/smp.h> #include <asm/debug.h> #include <asm/livepatch.h> +#include <asm/asm-prototypes.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> @@ -156,6 +157,15 @@ notrace unsigned int __check_irq_replay(void) } /* + * Check if an hypervisor Maintenance interrupt happened. + * This is a higher priority interrupt than the others, so + * replay it first. + */ + local_paca->irq_happened &= ~PACA_IRQ_HMI; + if (happened & PACA_IRQ_HMI) + return 0xe60; + + /* * We may have missed a decrementer interrupt. We check the * decrementer itself rather than the paca irq_happened field * in case we also had a rollover while hard disabled @@ -190,11 +200,6 @@ notrace unsigned int __check_irq_replay(void) } #endif /* CONFIG_PPC_BOOK3E */ - /* Check if an hypervisor Maintenance interrupt happened */ - local_paca->irq_happened &= ~PACA_IRQ_HMI; - if (happened & PACA_IRQ_HMI) - return 0xe60; - /* There should be nothing left ! */ BUG_ON(local_paca->irq_happened != 0); @@ -514,7 +519,7 @@ void __do_irq(struct pt_regs *regs) may_hard_irq_enable(); /* And finally process it */ - if (unlikely(irq == NO_IRQ)) + if (unlikely(!irq)) __this_cpu_inc(irq_stat.spurious_irqs); else generic_handle_irq(irq); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 3ed8ec09b5c9..e785cc9e1ecd 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -29,7 +29,7 @@ #include <linux/kprobes.h> #include <linux/ptrace.h> #include <linux/preempt.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/kdebug.h> #include <linux/slab.h> #include <asm/code-patching.h> diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 7b750c4ed5c7..bc525ea0dc09 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -193,10 +193,10 @@ static int __init add_legacy_soc_port(struct device_node *np, */ if (tsi && !strcmp(tsi->type, "tsi-bridge")) return add_legacy_port(np, -1, UPIO_TSI, addr, addr, - NO_IRQ, legacy_port_flags, 0); + 0, legacy_port_flags, 0); else return add_legacy_port(np, -1, UPIO_MEM, addr, addr, - NO_IRQ, legacy_port_flags, 0); + 0, legacy_port_flags, 0); } static int __init add_legacy_isa_port(struct device_node *np, @@ -242,7 +242,7 @@ static int __init add_legacy_isa_port(struct device_node *np, /* Add port, irq will be dealt with later */ return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]), - taddr, NO_IRQ, legacy_port_flags, 0); + taddr, 0, legacy_port_flags, 0); } @@ -314,7 +314,7 @@ static int __init add_legacy_pci_port(struct device_node *np, /* Add port, irq will be dealt with later. We passed a translated * IO port value. It will be fixed up later along with the irq */ - return add_legacy_port(np, index, iotype, base, addr, NO_IRQ, + return add_legacy_port(np, index, iotype, base, addr, 0, legacy_port_flags, np != pci_dev); } #endif @@ -462,14 +462,14 @@ static void __init fixup_port_irq(int index, DBG("fixup_port_irq(%d)\n", index); virq = irq_of_parse_and_map(np, 0); - if (virq == NO_IRQ && legacy_serial_infos[index].irq_check_parent) { + if (!virq && legacy_serial_infos[index].irq_check_parent) { np = of_get_parent(np); if (np == NULL) return; virq = irq_of_parse_and_map(np, 0); of_node_put(np); } - if (virq == NO_IRQ) + if (!virq) return; port->irq = virq; @@ -543,7 +543,7 @@ static int __init serial_dev_init(void) struct plat_serial8250_port *port = &legacy_serial_ports[i]; struct device_node *np = legacy_serial_infos[i].np; - if (port->irq == NO_IRQ) + if (!port->irq) fixup_port_irq(i, np, port); if (port->iotype == UPIO_PORT) fixup_port_pio(i, np, port); diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 4c780a342282..a205fa3d9bf3 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -23,6 +23,7 @@ #include <asm/current.h> #include <asm/machdep.h> #include <asm/cacheflush.h> +#include <asm/firmware.h> #include <asm/paca.h> #include <asm/mmu.h> #include <asm/sections.h> /* _end */ @@ -31,21 +32,6 @@ #include <asm/hw_breakpoint.h> #include <asm/asm-prototypes.h> -#ifdef CONFIG_PPC_BOOK3E -int default_machine_kexec_prepare(struct kimage *image) -{ - int i; - /* - * Since we use the kernel fault handlers and paging code to - * handle the virtual mode, we must make sure no destination - * overlaps kernel static data or bss. - */ - for (i = 0; i < image->nr_segments; i++) - if (image->segment[i].mem < __pa(_end)) - return -ETXTBSY; - return 0; -} -#else int default_machine_kexec_prepare(struct kimage *image) { int i; @@ -55,9 +41,6 @@ int default_machine_kexec_prepare(struct kimage *image) const unsigned long *basep; const unsigned int *sizep; - if (!mmu_hash_ops.hpte_clear_all) - return -ENOENT; - /* * Since we use the kernel fault handlers and paging code to * handle the virtual mode, we must make sure no destination @@ -67,31 +50,6 @@ int default_machine_kexec_prepare(struct kimage *image) if (image->segment[i].mem < __pa(_end)) return -ETXTBSY; - /* - * For non-LPAR, we absolutely can not overwrite the mmu hash - * table, since we are still using the bolted entries in it to - * do the copy. Check that here. - * - * It is safe if the end is below the start of the blocked - * region (end <= low), or if the beginning is after the - * end of the blocked region (begin >= high). Use the - * boolean identity !(a || b) === (!a && !b). - */ -#ifdef CONFIG_PPC_STD_MMU_64 - if (htab_address) { - low = __pa(htab_address); - high = low + htab_size_bytes; - - for (i = 0; i < image->nr_segments; i++) { - begin = image->segment[i].mem; - end = begin + image->segment[i].memsz; - - if ((begin < high) && (end > low)) - return -ETXTBSY; - } - } -#endif /* CONFIG_PPC_STD_MMU_64 */ - /* We also should not overwrite the tce tables */ for_each_node_by_type(node, "pci") { basep = of_get_property(node, "linux,tce-base", NULL); @@ -113,7 +71,6 @@ int default_machine_kexec_prepare(struct kimage *image) return 0; } -#endif /* !CONFIG_PPC_BOOK3E */ static void copy_segments(unsigned long ind) { @@ -332,11 +289,14 @@ struct paca_struct kexec_paca; /* Our assembly helper, in misc_64.S */ extern void kexec_sequence(void *newstack, unsigned long start, void *image, void *control, - void (*clear_all)(void)) __noreturn; + void (*clear_all)(void), + bool copy_with_mmu_off) __noreturn; /* too late to fail here */ void default_machine_kexec(struct kimage *image) { + bool copy_with_mmu_off; + /* prepare control code if any */ /* @@ -374,18 +334,29 @@ void default_machine_kexec(struct kimage *image) /* XXX: If anyone does 'dynamic lppacas' this will also need to be * switched to a static version! */ + /* + * On Book3S, the copy must happen with the MMU off if we are either + * using Radix page tables or we are not in an LPAR since we can + * overwrite the page tables while copying. + * + * In an LPAR, we keep the MMU on otherwise we can't access beyond + * the RMA. On BookE there is no real MMU off mode, so we have to + * keep it enabled as well (but then we have bolted TLB entries). + */ +#ifdef CONFIG_PPC_BOOK3E + copy_with_mmu_off = false; +#else + copy_with_mmu_off = radix_enabled() || + !(firmware_has_feature(FW_FEATURE_LPAR) || + firmware_has_feature(FW_FEATURE_PS3_LV1)); +#endif /* Some things are best done in assembly. Finding globals with * a toc is easier in C, so pass in what we can. */ kexec_sequence(&kexec_stack, image->start, image, - page_address(image->control_code_page), -#ifdef CONFIG_PPC_STD_MMU - mmu_hash_ops.hpte_clear_all -#else - NULL -#endif - ); + page_address(image->control_code_page), + mmu_cleanup_all, copy_with_mmu_off); /* NOTREACHED */ } diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index d9c912b6e632..03756ffdcd71 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -328,7 +328,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_UNIFIED_ID_CACHE) * * flush_icache_range(unsigned long start, unsigned long stop) */ -_KPROBE(flush_icache_range) +_GLOBAL(flush_icache_range) BEGIN_FTR_SECTION PURGE_PREFETCHED_INS blr /* for 601, do nothing */ @@ -358,6 +358,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) sync /* additional sync needed on g4 */ isync blr +_ASM_NOKPROBE_SYMBOL(flush_icache_range) + /* * Flush a particular page from the data cache to RAM. * Note: this is necessary because the instruction cache does *not* diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index cb195157b318..9f0bed214bcb 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -66,7 +66,7 @@ PPC64_CACHES: * flush all bytes from start through stop-1 inclusive */ -_KPROBE(flush_icache_range) +_GLOBAL(flush_icache_range) BEGIN_FTR_SECTION PURGE_PREFETCHED_INS blr @@ -109,7 +109,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) bdnz 2b isync blr - .previous .text +_ASM_NOKPROBE_SYMBOL(flush_icache_range) + /* * Like above, but only do the D-cache. * @@ -591,7 +592,8 @@ real_mode: /* assume normal blr return */ #endif /* - * kexec_sequence(newstack, start, image, control, clear_all()) + * kexec_sequence(newstack, start, image, control, clear_all(), + copy_with_mmu_off) * * does the grungy work with stack switching and real mode switches * also does simple calls to other code @@ -627,7 +629,7 @@ _GLOBAL(kexec_sequence) mr r29,r5 /* image (virt) */ mr r28,r6 /* control, unused */ mr r27,r7 /* clear_all() fn desc */ - mr r26,r8 /* spare */ + mr r26,r8 /* copy_with_mmu_off */ lhz r25,PACAHWCPUID(r13) /* get our phys cpu from paca */ /* disable interrupts, we are overwriting kernel data next */ @@ -639,15 +641,24 @@ _GLOBAL(kexec_sequence) mtmsrd r3,1 #endif + /* We need to turn the MMU off unless we are in hash mode + * under a hypervisor + */ + cmpdi r26,0 + beq 1f + bl real_mode +1: /* copy dest pages, flush whole dest image */ mr r3,r29 bl kexec_copy_flush /* (image) */ - /* turn off mmu */ + /* turn off mmu now if not done earlier */ + cmpdi r26,0 + bne 1f bl real_mode /* copy 0x100 bytes starting at start to 0 */ - li r3,0 +1: li r3,0 mr r4,r30 /* start, aka phys mem offset */ li r5,0x100 li r6,0 @@ -659,7 +670,9 @@ _GLOBAL(kexec_sequence) li r6,1 stw r6,kexec_flag-1b(5) -#ifndef CONFIG_PPC_BOOK3E + cmpdi r27,0 + beq 1f + /* clear out hardware hash page table and tlb */ #ifdef PPC64_ELF_ABI_v1 ld r12,0(r27) /* deref function descriptor */ @@ -668,7 +681,6 @@ _GLOBAL(kexec_sequence) #endif mtctr r12 bctrl /* mmu_hash_ops.hpte_clear_all(void); */ -#endif /* !CONFIG_PPC_BOOK3E */ /* * kexec image calling is: @@ -695,7 +707,7 @@ _GLOBAL(kexec_sequence) * are the boot cpu ????? * other device tree differences (prop sizes, va vs pa, etc)... */ - mr r3,r25 # my phys cpu +1: mr r3,r25 # my phys cpu mr r4,r30 # start, aka phys mem offset mtlr 4 li r5,0 diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index d1f1b35bf0c7..30b89d5cbb03 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -27,7 +27,7 @@ #include <linux/sort.h> #include <asm/setup.h> -LIST_HEAD(module_bug_list); +static LIST_HEAD(module_bug_list); static const Elf_Shdr *find_section(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 64174bf95611..34d2c595de23 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -542,9 +542,9 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, time->tv_nsec = 0; } *buf = kmemdup(buff + hdr_size, length, GFP_KERNEL); + kfree(buff); if (*buf == NULL) return -ENOMEM; - kfree(buff); *ecc_notice_size = 0; if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) @@ -851,7 +851,7 @@ static long dev_nvram_ioctl(struct file *file, unsigned int cmd, } } -const struct file_operations nvram_fops = { +static const struct file_operations nvram_fops = { .owner = THIS_MODULE, .llseek = dev_nvram_llseek, .read = dev_nvram_read, @@ -956,7 +956,7 @@ int __init nvram_remove_partition(const char *name, int sig, /* Make partition a free partition */ part->header.signature = NVRAM_SIG_FREE; - strncpy(part->header.name, "wwwwwwwwwwww", 12); + memset(part->header.name, 'w', 12); part->header.checksum = nvram_checksum(&part->header); rc = nvram_write_header(part); if (rc <= 0) { @@ -974,8 +974,8 @@ int __init nvram_remove_partition(const char *name, int sig, } if (prev) { prev->header.length += part->header.length; - prev->header.checksum = nvram_checksum(&part->header); - rc = nvram_write_header(part); + prev->header.checksum = nvram_checksum(&prev->header); + rc = nvram_write_header(prev); if (rc <= 0) { printk(KERN_ERR "nvram_remove_partition: nvram_write failed (%d)\n", rc); return rc; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 7fdf324d5b51..95d3769a2e26 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -154,6 +154,42 @@ void pcibios_free_controller(struct pci_controller *phb) EXPORT_SYMBOL_GPL(pcibios_free_controller); /* + * This function is used to call pcibios_free_controller() + * in a deferred manner: a callback from the PCI subsystem. + * + * _*DO NOT*_ call pcibios_free_controller() explicitly if + * this is used (or it may access an invalid *phb pointer). + * + * The callback occurs when all references to the root bus + * are dropped (e.g., child buses/devices and their users). + * + * It's called as .release_fn() of 'struct pci_host_bridge' + * which is associated with the 'struct pci_controller.bus' + * (root bus) - it expects .release_data to hold a pointer + * to 'struct pci_controller'. + * + * In order to use it, register .release_fn()/release_data + * like this: + * + * pci_set_host_bridge_release(bridge, + * pcibios_free_controller_deferred + * (void *) phb); + * + * e.g. in the pcibios_root_bridge_prepare() callback from + * pci_create_root_bus(). + */ +void pcibios_free_controller_deferred(struct pci_host_bridge *bridge) +{ + struct pci_controller *phb = (struct pci_controller *) + bridge->release_data; + + pr_debug("domain %d, dynamic %d\n", phb->global_number, phb->is_dynamic); + + pcibios_free_controller(phb); +} +EXPORT_SYMBOL_GPL(pcibios_free_controller_deferred); + +/* * The function is used to return the minimal alignment * for memory or I/O windows of the associated P2P bridge. * By default, 4KiB alignment for I/O windows and 1MiB for @@ -324,7 +360,7 @@ static int pci_read_irq_line(struct pci_dev *pci_dev) line, pin); virq = irq_create_mapping(NULL, line); - if (virq != NO_IRQ) + if (virq) irq_set_irq_type(virq, IRQ_TYPE_LEVEL_LOW); } else { pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %s\n", @@ -333,7 +369,8 @@ static int pci_read_irq_line(struct pci_dev *pci_dev) virq = irq_create_of_mapping(&oirq); } - if(virq == NO_IRQ) { + + if (!virq) { pr_debug(" Failed to map !\n"); return -1; } diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 526ac6750e4d..ea3d98115b88 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -178,7 +178,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, dev->hdr_type = PCI_HEADER_TYPE_NORMAL; dev->rom_base_reg = PCI_ROM_ADDRESS; /* Maybe do a default OF mapping here */ - dev->irq = NO_IRQ; + dev->irq = 0; } of_pci_parse_addrs(node, dev); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 9ee2623e0f67..9e7c10fe205f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -59,6 +59,7 @@ #include <asm/exec.h> #include <asm/livepatch.h> #include <asm/cpu_has_feature.h> +#include <asm/asm-prototypes.h> #include <linux/kprobes.h> #include <linux/kdebug.h> @@ -88,7 +89,13 @@ static void check_if_tm_restore_required(struct task_struct *tsk) set_thread_flag(TIF_RESTORE_TM); } } + +static inline bool msr_tm_active(unsigned long msr) +{ + return MSR_TM_ACTIVE(msr); +} #else +static inline bool msr_tm_active(unsigned long msr) { return false; } static inline void check_if_tm_restore_required(struct task_struct *tsk) { } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ @@ -104,7 +111,7 @@ static int __init enable_strict_msr_control(char *str) } early_param("ppc_strict_facility_enable", enable_strict_msr_control); -void msr_check_and_set(unsigned long bits) +unsigned long msr_check_and_set(unsigned long bits) { unsigned long oldmsr = mfmsr(); unsigned long newmsr; @@ -118,6 +125,8 @@ void msr_check_and_set(unsigned long bits) if (oldmsr != newmsr) mtmsr_isync(newmsr); + + return newmsr; } void __msr_check_and_clear(unsigned long bits) @@ -196,19 +205,30 @@ EXPORT_SYMBOL_GPL(flush_fp_to_thread); void enable_kernel_fp(void) { + unsigned long cpumsr; + WARN_ON(preemptible()); - msr_check_and_set(MSR_FP); + cpumsr = msr_check_and_set(MSR_FP); if (current->thread.regs && (current->thread.regs->msr & MSR_FP)) { check_if_tm_restore_required(current); + /* + * If a thread has already been reclaimed then the + * checkpointed registers are on the CPU but have definitely + * been saved by the reclaim code. Don't need to and *cannot* + * giveup as this would save to the 'live' structure not the + * checkpointed structure. + */ + if(!msr_tm_active(cpumsr) && msr_tm_active(current->thread.regs->msr)) + return; __giveup_fpu(current); } } EXPORT_SYMBOL(enable_kernel_fp); static int restore_fp(struct task_struct *tsk) { - if (tsk->thread.load_fp) { + if (tsk->thread.load_fp || msr_tm_active(tsk->thread.regs->msr)) { load_fp_state(¤t->thread.fp_state); current->thread.load_fp++; return 1; @@ -248,12 +268,23 @@ EXPORT_SYMBOL(giveup_altivec); void enable_kernel_altivec(void) { + unsigned long cpumsr; + WARN_ON(preemptible()); - msr_check_and_set(MSR_VEC); + cpumsr = msr_check_and_set(MSR_VEC); if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) { check_if_tm_restore_required(current); + /* + * If a thread has already been reclaimed then the + * checkpointed registers are on the CPU but have definitely + * been saved by the reclaim code. Don't need to and *cannot* + * giveup as this would save to the 'live' structure not the + * checkpointed structure. + */ + if(!msr_tm_active(cpumsr) && msr_tm_active(current->thread.regs->msr)) + return; __giveup_altivec(current); } } @@ -278,7 +309,8 @@ EXPORT_SYMBOL_GPL(flush_altivec_to_thread); static int restore_altivec(struct task_struct *tsk) { - if (cpu_has_feature(CPU_FTR_ALTIVEC) && tsk->thread.load_vec) { + if (cpu_has_feature(CPU_FTR_ALTIVEC) && + (tsk->thread.load_vec || msr_tm_active(tsk->thread.regs->msr))) { load_vr_state(&tsk->thread.vr_state); tsk->thread.used_vr = 1; tsk->thread.load_vec++; @@ -321,12 +353,23 @@ static void save_vsx(struct task_struct *tsk) void enable_kernel_vsx(void) { + unsigned long cpumsr; + WARN_ON(preemptible()); - msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX); + cpumsr = msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX); if (current->thread.regs && (current->thread.regs->msr & MSR_VSX)) { check_if_tm_restore_required(current); + /* + * If a thread has already been reclaimed then the + * checkpointed registers are on the CPU but have definitely + * been saved by the reclaim code. Don't need to and *cannot* + * giveup as this would save to the 'live' structure not the + * checkpointed structure. + */ + if(!msr_tm_active(cpumsr) && msr_tm_active(current->thread.regs->msr)) + return; if (current->thread.regs->msr & MSR_FP) __giveup_fpu(current); if (current->thread.regs->msr & MSR_VEC) @@ -438,6 +481,7 @@ void giveup_all(struct task_struct *tsk) return; msr_check_and_set(msr_all_available); + check_if_tm_restore_required(tsk); #ifdef CONFIG_PPC_FPU if (usermsr & MSR_FP) @@ -464,7 +508,8 @@ void restore_math(struct pt_regs *regs) { unsigned long msr; - if (!current->thread.load_fp && !loadvec(current->thread)) + if (!msr_tm_active(regs->msr) && + !current->thread.load_fp && !loadvec(current->thread)) return; msr = regs->msr; @@ -767,29 +812,15 @@ static inline bool hw_brk_match(struct arch_hw_breakpoint *a, } #ifdef CONFIG_PPC_TRANSACTIONAL_MEM + +static inline bool tm_enabled(struct task_struct *tsk) +{ + return tsk && tsk->thread.regs && (tsk->thread.regs->msr & MSR_TM); +} + static void tm_reclaim_thread(struct thread_struct *thr, struct thread_info *ti, uint8_t cause) { - unsigned long msr_diff = 0; - - /* - * If FP/VSX registers have been already saved to the - * thread_struct, move them to the transact_fp array. - * We clear the TIF_RESTORE_TM bit since after the reclaim - * the thread will no longer be transactional. - */ - if (test_ti_thread_flag(ti, TIF_RESTORE_TM)) { - msr_diff = thr->ckpt_regs.msr & ~thr->regs->msr; - if (msr_diff & MSR_FP) - memcpy(&thr->transact_fp, &thr->fp_state, - sizeof(struct thread_fp_state)); - if (msr_diff & MSR_VEC) - memcpy(&thr->transact_vr, &thr->vr_state, - sizeof(struct thread_vr_state)); - clear_ti_thread_flag(ti, TIF_RESTORE_TM); - msr_diff &= MSR_FP | MSR_VEC | MSR_VSX | MSR_FE0 | MSR_FE1; - } - /* * Use the current MSR TM suspended bit to track if we have * checkpointed state outstanding. @@ -808,15 +839,9 @@ static void tm_reclaim_thread(struct thread_struct *thr, if (!MSR_TM_SUSPENDED(mfmsr())) return; - tm_reclaim(thr, thr->regs->msr, cause); + giveup_all(container_of(thr, struct task_struct, thread)); - /* Having done the reclaim, we now have the checkpointed - * FP/VSX values in the registers. These might be valid - * even if we have previously called enable_kernel_fp() or - * flush_fp_to_thread(), so update thr->regs->msr to - * indicate their current validity. - */ - thr->regs->msr |= msr_diff; + tm_reclaim(thr, thr->ckpt_regs.msr, cause); } void tm_reclaim_current(uint8_t cause) @@ -832,8 +857,8 @@ static inline void tm_reclaim_task(struct task_struct *tsk) * * In switching we need to maintain a 2nd register state as * oldtask->thread.ckpt_regs. We tm_reclaim(oldproc); this saves the - * checkpointed (tbegin) state in ckpt_regs and saves the transactional - * (current) FPRs into oldtask->thread.transact_fpr[]. + * checkpointed (tbegin) state in ckpt_regs, ckfp_state and + * ckvr_state * * We also context switch (save) TFHAR/TEXASR/TFIAR in here. */ @@ -845,14 +870,6 @@ static inline void tm_reclaim_task(struct task_struct *tsk) if (!MSR_TM_ACTIVE(thr->regs->msr)) goto out_and_saveregs; - /* Stash the original thread MSR, as giveup_fpu et al will - * modify it. We hold onto it to see whether the task used - * FP & vector regs. If the TIF_RESTORE_TM flag is set, - * ckpt_regs.msr is already set. - */ - if (!test_ti_thread_flag(task_thread_info(tsk), TIF_RESTORE_TM)) - thr->ckpt_regs.msr = thr->regs->msr; - TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, " "ccr=%lx, msr=%lx, trap=%lx)\n", tsk->pid, thr->regs->nip, @@ -881,6 +898,9 @@ void tm_recheckpoint(struct thread_struct *thread, { unsigned long flags; + if (!(thread->regs->msr & MSR_TM)) + return; + /* We really can't be interrupted here as the TEXASR registers can't * change and later in the trecheckpoint code, we have a userspace R1. * So let's hard disable over this region. @@ -910,10 +930,10 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new) * If the task was using FP, we non-lazily reload both the original and * the speculative FP register states. This is because the kernel * doesn't see if/when a TM rollback occurs, so if we take an FP - * unavoidable later, we are unable to determine which set of FP regs + * unavailable later, we are unable to determine which set of FP regs * need to be restored. */ - if (!new->thread.regs) + if (!tm_enabled(new)) return; if (!MSR_TM_ACTIVE(new->thread.regs->msr)){ @@ -926,35 +946,35 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new) "(new->msr 0x%lx, new->origmsr 0x%lx)\n", new->pid, new->thread.regs->msr, msr); - /* This loads the checkpointed FP/VEC state, if used */ tm_recheckpoint(&new->thread, msr); - /* This loads the speculative FP/VEC state, if used */ - if (msr & MSR_FP) { - do_load_up_transact_fpu(&new->thread); - new->thread.regs->msr |= - (MSR_FP | new->thread.fpexc_mode); - } -#ifdef CONFIG_ALTIVEC - if (msr & MSR_VEC) { - do_load_up_transact_altivec(&new->thread); - new->thread.regs->msr |= MSR_VEC; - } -#endif - /* We may as well turn on VSX too since all the state is restored now */ - if (msr & MSR_VSX) - new->thread.regs->msr |= MSR_VSX; + /* + * The checkpointed state has been restored but the live state has + * not, ensure all the math functionality is turned off to trigger + * restore_math() to reload. + */ + new->thread.regs->msr &= ~(MSR_FP | MSR_VEC | MSR_VSX); TM_DEBUG("*** tm_recheckpoint of pid %d complete " "(kernel msr 0x%lx)\n", new->pid, mfmsr()); } -static inline void __switch_to_tm(struct task_struct *prev) +static inline void __switch_to_tm(struct task_struct *prev, + struct task_struct *new) { if (cpu_has_feature(CPU_FTR_TM)) { - tm_enable(); - tm_reclaim_task(prev); + if (tm_enabled(prev) || tm_enabled(new)) + tm_enable(); + + if (tm_enabled(prev)) { + prev->thread.load_tm++; + tm_reclaim_task(prev); + if (!MSR_TM_ACTIVE(prev->thread.regs->msr) && prev->thread.load_tm == 0) + prev->thread.regs->msr &= ~MSR_TM; + } + + tm_recheckpoint_new_task(new); } } @@ -976,6 +996,12 @@ void restore_tm_state(struct pt_regs *regs) { unsigned long msr_diff; + /* + * This is the only moment we should clear TIF_RESTORE_TM as + * it is here that ckpt_regs.msr and pt_regs.msr become the same + * again, anything else could lead to an incorrect ckpt_msr being + * saved and therefore incorrect signal contexts. + */ clear_thread_flag(TIF_RESTORE_TM); if (!MSR_TM_ACTIVE(regs->msr)) return; @@ -983,6 +1009,13 @@ void restore_tm_state(struct pt_regs *regs) msr_diff = current->thread.ckpt_regs.msr & ~regs->msr; msr_diff &= MSR_FP | MSR_VEC | MSR_VSX; + /* Ensure that restore_math() will restore */ + if (msr_diff & MSR_FP) + current->thread.load_fp = 1; +#ifdef CONFIG_ALIVEC + if (cpu_has_feature(CPU_FTR_ALTIVEC) && msr_diff & MSR_VEC) + current->thread.load_vec = 1; +#endif restore_math(regs); regs->msr |= msr_diff; @@ -990,7 +1023,7 @@ void restore_tm_state(struct pt_regs *regs) #else #define tm_recheckpoint_new_task(new) -#define __switch_to_tm(prev) +#define __switch_to_tm(prev, new) #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ static inline void save_sprs(struct thread_struct *t) @@ -1131,11 +1164,11 @@ struct task_struct *__switch_to(struct task_struct *prev, */ save_sprs(&prev->thread); - __switch_to_tm(prev); - /* Save FPU, Altivec, VSX and SPE state */ giveup_all(prev); + __switch_to_tm(prev, new); + /* * We can't take a PMU exception inside _switch() since there is a * window where the kernel stack SLB and the kernel stack are out @@ -1143,8 +1176,6 @@ struct task_struct *__switch_to(struct task_struct *prev, */ hard_irq_disable(); - tm_recheckpoint_new_task(new); - /* * Call restore_sprs() before calling _switch(). If we move it after * _switch() then we miss out on calling it for new tasks. The reason @@ -1379,9 +1410,11 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) * transitions the CPU out of TM mode. Hence we need to call * tm_recheckpoint_new_task() (on the same task) to restore the * checkpointed state back and the TM mode. + * + * Can't pass dst because it isn't ready. Doesn't matter, passing + * dst is only important for __switch_to() */ - __switch_to_tm(src); - tm_recheckpoint_new_task(src); + __switch_to_tm(src, src); *dst = *src; @@ -1623,8 +1656,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.used_spe = 0; #endif /* CONFIG_SPE */ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (cpu_has_feature(CPU_FTR_TM)) - regs->msr |= MSR_TM; current->thread.tm_tfhar = 0; current->thread.tm_texasr = 0; current->thread.tm_tfiar = 0; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 4e74fc588a3f..88ac964f4858 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -42,6 +42,7 @@ #include <asm/sections.h> #include <asm/machdep.h> #include <asm/opal.h> +#include <asm/asm-prototypes.h> #include <linux/linux_logo.h> @@ -695,7 +696,7 @@ unsigned char ibm_architecture_vec[] = { OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */ /* option vector 5: PAPR/OF options */ - VECTOR_LENGTH(18), /* length */ + VECTOR_LENGTH(21), /* length */ 0, /* don't ignore, don't halt */ OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) | OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) | @@ -726,8 +727,11 @@ unsigned char ibm_architecture_vec[] = { 0, 0, OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) | - OV5_FEAT(OV5_PFO_HW_842), - OV5_FEAT(OV5_SUB_PROCESSORS), + OV5_FEAT(OV5_PFO_HW_842), /* Byte 17 */ + 0, /* Byte 18 */ + 0, /* Byte 19 */ + 0, /* Byte 20 */ + OV5_FEAT(OV5_SUB_PROCESSORS), /* Byte 21 */ /* option vector 6: IBM PAPR hints */ VECTOR_LENGTH(3), /* length */ @@ -2640,6 +2644,86 @@ static void __init fixup_device_tree_efika(void) #define fixup_device_tree_efika() #endif +#ifdef CONFIG_PPC_PASEMI_NEMO +/* + * CFE supplied on Nemo is broken in several ways, biggest + * problem is that it reassigns ISA interrupts to unused mpic ints. + * Add an interrupt-controller property for the io-bridge to use + * and correct the ints so we can attach them to an irq_domain + */ +static void __init fixup_device_tree_pasemi(void) +{ + u32 interrupts[2], parent, rval, val = 0; + char *name, *pci_name; + phandle iob, node; + + /* Find the root pci node */ + name = "/pxp@0,e0000000"; + iob = call_prom("finddevice", 1, 1, ADDR(name)); + if (!PHANDLE_VALID(iob)) + return; + + /* check if interrupt-controller node set yet */ + if (prom_getproplen(iob, "interrupt-controller") !=PROM_ERROR) + return; + + prom_printf("adding interrupt-controller property for SB600...\n"); + + prom_setprop(iob, name, "interrupt-controller", &val, 0); + + pci_name = "/pxp@0,e0000000/pci@11"; + node = call_prom("finddevice", 1, 1, ADDR(pci_name)); + parent = ADDR(iob); + + for( ; prom_next_node(&node); ) { + /* scan each node for one with an interrupt */ + if (!PHANDLE_VALID(node)) + continue; + + rval = prom_getproplen(node, "interrupts"); + if (rval == 0 || rval == PROM_ERROR) + continue; + + prom_getprop(node, "interrupts", &interrupts, sizeof(interrupts)); + if ((interrupts[0] < 212) || (interrupts[0] > 222)) + continue; + + /* found a node, update both interrupts and interrupt-parent */ + if ((interrupts[0] >= 212) && (interrupts[0] <= 215)) + interrupts[0] -= 203; + if ((interrupts[0] >= 216) && (interrupts[0] <= 220)) + interrupts[0] -= 213; + if (interrupts[0] == 221) + interrupts[0] = 14; + if (interrupts[0] == 222) + interrupts[0] = 8; + + prom_setprop(node, pci_name, "interrupts", interrupts, + sizeof(interrupts)); + prom_setprop(node, pci_name, "interrupt-parent", &parent, + sizeof(parent)); + } + + /* + * The io-bridge has device_type set to 'io-bridge' change it to 'isa' + * so that generic isa-bridge code can add the SB600 and its on-board + * peripherals. + */ + name = "/pxp@0,e0000000/io-bridge@0"; + iob = call_prom("finddevice", 1, 1, ADDR(name)); + if (!PHANDLE_VALID(iob)) + return; + + /* device_type is already set, just change it. */ + + prom_printf("Changing device_type of SB600 node...\n"); + + prom_setprop(iob, name, "device_type", "isa", sizeof("isa")); +} +#else /* !CONFIG_PPC_PASEMI_NEMO */ +static inline void fixup_device_tree_pasemi(void) { } +#endif + static void __init fixup_device_tree(void) { fixup_device_tree_maple(); @@ -2647,6 +2731,7 @@ static void __init fixup_device_tree(void) fixup_device_tree_chrp(); fixup_device_tree_pmac(); fixup_device_tree_efika(); + fixup_device_tree_pasemi(); } static void __init prom_find_boot_cpu(void) diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index bf91658a8a40..b1ec62f2cc31 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -39,6 +39,7 @@ #include <asm/pgtable.h> #include <asm/switch_to.h> #include <asm/tm.h> +#include <asm/asm-prototypes.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> @@ -402,13 +403,9 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, } /* - * When the transaction is active, 'transact_fp' holds the current running - * value of all FPR registers and 'fp_state' holds the last checkpointed - * value of all FPR registers for the current transaction. When transaction - * is not active 'fp_state' holds the current running state of all the FPR - * registers. So this function which returns the current running values of - * all the FPR registers, needs to know whether any transaction is active - * or not. + * Regardless of transactions, 'fp_state' holds the current running + * value of all FPR registers and 'ckfp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. * * Userspace interface buffer layout: * @@ -416,13 +413,6 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, * u64 fpr[32]; * u64 fpscr; * }; - * - * There are two config options CONFIG_VSX and CONFIG_PPC_TRANSACTIONAL_MEM - * which determines the final code in this function. All the combinations of - * these two config options are possible except the one below as transactional - * memory config pulls in CONFIG_VSX automatically. - * - * !defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) */ static int fpr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, @@ -431,50 +421,29 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, #ifdef CONFIG_VSX u64 buf[33]; int i; -#endif - flush_fp_to_thread(target); -#if defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) - /* copy to local buffer then write that out */ - if (MSR_TM_ACTIVE(target->thread.regs->msr)) { - flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); - for (i = 0; i < 32 ; i++) - buf[i] = target->thread.TS_TRANS_FPR(i); - buf[32] = target->thread.transact_fp.fpscr; - } else { - for (i = 0; i < 32 ; i++) - buf[i] = target->thread.TS_FPR(i); - buf[32] = target->thread.fp_state.fpscr; - } - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); -#endif + flush_fp_to_thread(target); -#if defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) /* copy to local buffer then write that out */ for (i = 0; i < 32 ; i++) buf[i] = target->thread.TS_FPR(i); buf[32] = target->thread.fp_state.fpscr; return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); -#endif - -#if !defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) +#else BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != offsetof(struct thread_fp_state, fpr[32])); + flush_fp_to_thread(target); + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.fp_state, 0, -1); #endif } /* - * When the transaction is active, 'transact_fp' holds the current running - * value of all FPR registers and 'fp_state' holds the last checkpointed - * value of all FPR registers for the current transaction. When transaction - * is not active 'fp_state' holds the current running state of all the FPR - * registers. So this function which setss the current running values of - * all the FPR registers, needs to know whether any transaction is active - * or not. + * Regardless of transactions, 'fp_state' holds the current running + * value of all FPR registers and 'ckfp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. * * Userspace interface buffer layout: * @@ -483,12 +452,6 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, * u64 fpscr; * }; * - * There are two config options CONFIG_VSX and CONFIG_PPC_TRANSACTIONAL_MEM - * which determines the final code in this function. All the combinations of - * these two config options are possible except the one below as transactional - * memory config pulls in CONFIG_VSX automatically. - * - * !defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) */ static int fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, @@ -497,44 +460,24 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, #ifdef CONFIG_VSX u64 buf[33]; int i; -#endif + flush_fp_to_thread(target); -#if defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) /* copy to local buffer then write that out */ i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); if (i) return i; - if (MSR_TM_ACTIVE(target->thread.regs->msr)) { - flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); - for (i = 0; i < 32 ; i++) - target->thread.TS_TRANS_FPR(i) = buf[i]; - target->thread.transact_fp.fpscr = buf[32]; - } else { - for (i = 0; i < 32 ; i++) - target->thread.TS_FPR(i) = buf[i]; - target->thread.fp_state.fpscr = buf[32]; - } - return 0; -#endif - -#if defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) - /* copy to local buffer then write that out */ - i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); - if (i) - return i; for (i = 0; i < 32 ; i++) target->thread.TS_FPR(i) = buf[i]; target->thread.fp_state.fpscr = buf[32]; return 0; -#endif - -#if !defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) +#else BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != offsetof(struct thread_fp_state, fpr[32])); + flush_fp_to_thread(target); + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.fp_state, 0, -1); #endif @@ -562,13 +505,10 @@ static int vr_active(struct task_struct *target, } /* - * When the transaction is active, 'transact_vr' holds the current running - * value of all the VMX registers and 'vr_state' holds the last checkpointed - * value of all the VMX registers for the current transaction to fall back - * on in case it aborts. When transaction is not active 'vr_state' holds - * the current running state of all the VMX registers. So this function which - * gets the current running values of all the VMX registers, needs to know - * whether any transaction is active or not. + * Regardless of transactions, 'vr_state' holds the current running + * value of all the VMX registers and 'ckvr_state' holds the last + * checkpointed value of all the VMX registers for the current + * transaction to fall back on in case it aborts. * * Userspace interface buffer layout: * @@ -582,7 +522,6 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - struct thread_vr_state *addr; int ret; flush_altivec_to_thread(target); @@ -590,19 +529,8 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) != offsetof(struct thread_vr_state, vr[32])); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) { - flush_fp_to_thread(target); - flush_tmregs_to_thread(target); - addr = &target->thread.transact_vr; - } else { - addr = &target->thread.vr_state; - } -#else - addr = &target->thread.vr_state; -#endif ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - addr, 0, + &target->thread.vr_state, 0, 33 * sizeof(vector128)); if (!ret) { /* @@ -614,14 +542,7 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, } vrsave; memset(&vrsave, 0, sizeof(vrsave)); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) - vrsave.word = target->thread.transact_vrsave; - else - vrsave.word = target->thread.vrsave; -#else vrsave.word = target->thread.vrsave; -#endif ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); @@ -631,13 +552,10 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, } /* - * When the transaction is active, 'transact_vr' holds the current running - * value of all the VMX registers and 'vr_state' holds the last checkpointed - * value of all the VMX registers for the current transaction to fall back - * on in case it aborts. When transaction is not active 'vr_state' holds - * the current running state of all the VMX registers. So this function which - * sets the current running values of all the VMX registers, needs to know - * whether any transaction is active or not. + * Regardless of transactions, 'vr_state' holds the current running + * value of all the VMX registers and 'ckvr_state' holds the last + * checkpointed value of all the VMX registers for the current + * transaction to fall back on in case it aborts. * * Userspace interface buffer layout: * @@ -651,7 +569,6 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct thread_vr_state *addr; int ret; flush_altivec_to_thread(target); @@ -659,19 +576,8 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) != offsetof(struct thread_vr_state, vr[32])); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) { - flush_fp_to_thread(target); - flush_tmregs_to_thread(target); - addr = &target->thread.transact_vr; - } else { - addr = &target->thread.vr_state; - } -#else - addr = &target->thread.vr_state; -#endif ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - addr, 0, + &target->thread.vr_state, 0, 33 * sizeof(vector128)); if (!ret && count > 0) { /* @@ -683,27 +589,12 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, } vrsave; memset(&vrsave, 0, sizeof(vrsave)); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) - vrsave.word = target->thread.transact_vrsave; - else - vrsave.word = target->thread.vrsave; -#else vrsave.word = target->thread.vrsave; -#endif + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); - if (!ret) { - -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) - target->thread.transact_vrsave = vrsave.word; - else - target->thread.vrsave = vrsave.word; -#else + if (!ret) target->thread.vrsave = vrsave.word; -#endif - } } return ret; @@ -725,13 +616,10 @@ static int vsr_active(struct task_struct *target, } /* - * When the transaction is active, 'transact_fp' holds the current running - * value of all FPR registers and 'fp_state' holds the last checkpointed - * value of all FPR registers for the current transaction. When transaction - * is not active 'fp_state' holds the current running state of all the FPR - * registers. So this function which returns the current running values of - * all the FPR registers, needs to know whether any transaction is active - * or not. + * Regardless of transactions, 'fp_state' holds the current running + * value of all FPR registers and 'ckfp_state' holds the last + * checkpointed value of all FPR registers for the current + * transaction. * * Userspace interface buffer layout: * @@ -746,27 +634,14 @@ static int vsr_get(struct task_struct *target, const struct user_regset *regset, u64 buf[32]; int ret, i; -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); -#endif flush_vsx_to_thread(target); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) { - for (i = 0; i < 32 ; i++) - buf[i] = target->thread. - transact_fp.fpr[i][TS_VSRLOWOFFSET]; - } else { - for (i = 0; i < 32 ; i++) - buf[i] = target->thread. - fp_state.fpr[i][TS_VSRLOWOFFSET]; - } -#else for (i = 0; i < 32 ; i++) buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET]; -#endif + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); @@ -774,12 +649,10 @@ static int vsr_get(struct task_struct *target, const struct user_regset *regset, } /* - * When the transaction is active, 'transact_fp' holds the current running - * value of all FPR registers and 'fp_state' holds the last checkpointed - * value of all FPR registers for the current transaction. When transaction - * is not active 'fp_state' holds the current running state of all the FPR - * registers. So this function which sets the current running values of all - * the FPR registers, needs to know whether any transaction is active or not. + * Regardless of transactions, 'fp_state' holds the current running + * value of all FPR registers and 'ckfp_state' holds the last + * checkpointed value of all FPR registers for the current + * transaction. * * Userspace interface buffer layout: * @@ -794,31 +667,16 @@ static int vsr_set(struct task_struct *target, const struct user_regset *regset, u64 buf[32]; int ret,i; -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); -#endif flush_vsx_to_thread(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); - -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) { - for (i = 0; i < 32 ; i++) - target->thread.transact_fp. - fpr[i][TS_VSRLOWOFFSET] = buf[i]; - } else { + if (!ret) for (i = 0; i < 32 ; i++) - target->thread.fp_state. - fpr[i][TS_VSRLOWOFFSET] = buf[i]; - } -#else - for (i = 0; i < 32 ; i++) - target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; -#endif - + target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; return ret; } @@ -944,9 +802,9 @@ static int tm_cgpr_get(struct task_struct *target, if (!MSR_TM_ACTIVE(target->thread.regs->msr)) return -ENODATA; + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.ckpt_regs, @@ -1009,9 +867,9 @@ static int tm_cgpr_set(struct task_struct *target, if (!MSR_TM_ACTIVE(target->thread.regs->msr)) return -ENODATA; + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.ckpt_regs, @@ -1087,7 +945,7 @@ static int tm_cfpr_active(struct task_struct *target, * * This function gets in transaction checkpointed FPR registers. * - * When the transaction is active 'fp_state' holds the checkpointed + * When the transaction is active 'ckfp_state' holds the checkpointed * values for the current transaction to fall back on if it aborts * in between. This function gets those checkpointed FPR registers. * The userspace interface buffer layout is as follows. @@ -1111,14 +969,14 @@ static int tm_cfpr_get(struct task_struct *target, if (!MSR_TM_ACTIVE(target->thread.regs->msr)) return -ENODATA; + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); /* copy to local buffer then write that out */ for (i = 0; i < 32 ; i++) - buf[i] = target->thread.TS_FPR(i); - buf[32] = target->thread.fp_state.fpscr; + buf[i] = target->thread.TS_CKFPR(i); + buf[32] = target->thread.ckfp_state.fpscr; return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); } @@ -1133,7 +991,7 @@ static int tm_cfpr_get(struct task_struct *target, * * This function sets in transaction checkpointed FPR registers. * - * When the transaction is active 'fp_state' holds the checkpointed + * When the transaction is active 'ckfp_state' holds the checkpointed * FPR register values for the current transaction to fall back on * if it aborts in between. This function sets these checkpointed * FPR registers. The userspace interface buffer layout is as follows. @@ -1157,17 +1015,17 @@ static int tm_cfpr_set(struct task_struct *target, if (!MSR_TM_ACTIVE(target->thread.regs->msr)) return -ENODATA; + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); /* copy to local buffer then write that out */ i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); if (i) return i; for (i = 0; i < 32 ; i++) - target->thread.TS_FPR(i) = buf[i]; - target->thread.fp_state.fpscr = buf[32]; + target->thread.TS_CKFPR(i) = buf[i]; + target->thread.ckfp_state.fpscr = buf[32]; return 0; } @@ -1202,7 +1060,7 @@ static int tm_cvmx_active(struct task_struct *target, * * This function gets in transaction checkpointed VMX registers. * - * When the transaction is active 'vr_state' and 'vr_save' hold + * When the transaction is active 'ckvr_state' and 'ckvrsave' hold * the checkpointed values for the current transaction to fall * back on if it aborts in between. The userspace interface buffer * layout is as follows. @@ -1229,12 +1087,12 @@ static int tm_cvmx_get(struct task_struct *target, return -ENODATA; /* Flush the state */ + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.vr_state, 0, + &target->thread.ckvr_state, 0, 33 * sizeof(vector128)); if (!ret) { /* @@ -1245,7 +1103,7 @@ static int tm_cvmx_get(struct task_struct *target, u32 word; } vrsave; memset(&vrsave, 0, sizeof(vrsave)); - vrsave.word = target->thread.vrsave; + vrsave.word = target->thread.ckvrsave; ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); } @@ -1264,7 +1122,7 @@ static int tm_cvmx_get(struct task_struct *target, * * This function sets in transaction checkpointed VMX registers. * - * When the transaction is active 'vr_state' and 'vr_save' hold + * When the transaction is active 'ckvr_state' and 'ckvrsave' hold * the checkpointed values for the current transaction to fall * back on if it aborts in between. The userspace interface buffer * layout is as follows. @@ -1290,12 +1148,12 @@ static int tm_cvmx_set(struct task_struct *target, if (!MSR_TM_ACTIVE(target->thread.regs->msr)) return -ENODATA; + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.vr_state, 0, + &target->thread.ckvr_state, 0, 33 * sizeof(vector128)); if (!ret && count > 0) { /* @@ -1306,11 +1164,11 @@ static int tm_cvmx_set(struct task_struct *target, u32 word; } vrsave; memset(&vrsave, 0, sizeof(vrsave)); - vrsave.word = target->thread.vrsave; + vrsave.word = target->thread.ckvrsave; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); if (!ret) - target->thread.vrsave = vrsave.word; + target->thread.ckvrsave = vrsave.word; } return ret; @@ -1348,7 +1206,7 @@ static int tm_cvsx_active(struct task_struct *target, * * This function gets in transaction checkpointed VSX registers. * - * When the transaction is active 'fp_state' holds the checkpointed + * When the transaction is active 'ckfp_state' holds the checkpointed * values for the current transaction to fall back on if it aborts * in between. This function gets those checkpointed VSX registers. * The userspace interface buffer layout is as follows. @@ -1372,13 +1230,13 @@ static int tm_cvsx_get(struct task_struct *target, return -ENODATA; /* Flush the state */ + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); flush_vsx_to_thread(target); for (i = 0; i < 32 ; i++) - buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET]; + buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET]; ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); @@ -1396,7 +1254,7 @@ static int tm_cvsx_get(struct task_struct *target, * * This function sets in transaction checkpointed VSX registers. * - * When the transaction is active 'fp_state' holds the checkpointed + * When the transaction is active 'ckfp_state' holds the checkpointed * VSX register values for the current transaction to fall back on * if it aborts in between. This function sets these checkpointed * FPR registers. The userspace interface buffer layout is as follows. @@ -1420,15 +1278,16 @@ static int tm_cvsx_set(struct task_struct *target, return -ENODATA; /* Flush the state */ + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); flush_vsx_to_thread(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); - for (i = 0; i < 32 ; i++) - target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; + if (!ret) + for (i = 0; i < 32 ; i++) + target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; return ret; } @@ -1484,9 +1343,9 @@ static int tm_spr_get(struct task_struct *target, return -ENODEV; /* Flush the states */ + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); /* TFHAR register */ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, @@ -1540,9 +1399,9 @@ static int tm_spr_set(struct task_struct *target, return -ENODEV; /* Flush the states */ + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); /* TFHAR register */ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, @@ -2065,33 +1924,12 @@ static const struct user_regset_view user_ppc_native_view = { static int gpr32_get_common(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf, bool tm_active) + void *kbuf, void __user *ubuf, + unsigned long *regs) { - const unsigned long *regs = &target->thread.regs->gpr[0]; - const unsigned long *ckpt_regs; compat_ulong_t *k = kbuf; compat_ulong_t __user *u = ubuf; compat_ulong_t reg; - int i; - -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - ckpt_regs = &target->thread.ckpt_regs.gpr[0]; -#endif - if (tm_active) { - regs = ckpt_regs; - } else { - if (target->thread.regs == NULL) - return -EIO; - - if (!FULL_REGS(target->thread.regs)) { - /* - * We have a partial register set. - * Fill 14-31 with bogus values. - */ - for (i = 14; i < 32; i++) - target->thread.regs->gpr[i] = NV_REG_POISON; - } - } pos /= sizeof(reg); count /= sizeof(reg); @@ -2133,29 +1971,13 @@ static int gpr32_get_common(struct task_struct *target, static int gpr32_set_common(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf, bool tm_active) + const void *kbuf, const void __user *ubuf, + unsigned long *regs) { - unsigned long *regs = &target->thread.regs->gpr[0]; - unsigned long *ckpt_regs; const compat_ulong_t *k = kbuf; const compat_ulong_t __user *u = ubuf; compat_ulong_t reg; -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - ckpt_regs = &target->thread.ckpt_regs.gpr[0]; -#endif - - if (tm_active) { - regs = ckpt_regs; - } else { - regs = &target->thread.regs->gpr[0]; - - if (target->thread.regs == NULL) - return -EIO; - - CHECK_FULL_REGS(target->thread.regs); - } - pos /= sizeof(reg); count /= sizeof(reg); @@ -2220,7 +2042,8 @@ static int tm_cgpr32_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, 1); + return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, + &target->thread.ckpt_regs.gpr[0]); } static int tm_cgpr32_set(struct task_struct *target, @@ -2228,7 +2051,8 @@ static int tm_cgpr32_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, 1); + return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, + &target->thread.ckpt_regs.gpr[0]); } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ @@ -2237,7 +2061,21 @@ static int gpr32_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, 0); + int i; + + if (target->thread.regs == NULL) + return -EIO; + + if (!FULL_REGS(target->thread.regs)) { + /* + * We have a partial register set. + * Fill 14-31 with bogus values. + */ + for (i = 14; i < 32; i++) + target->thread.regs->gpr[i] = NV_REG_POISON; + } + return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, + &target->thread.regs->gpr[0]); } static int gpr32_set(struct task_struct *target, @@ -2245,7 +2083,12 @@ static int gpr32_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, 0); + if (target->thread.regs == NULL) + return -EIO; + + CHECK_FULL_REGS(target->thread.regs); + return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, + &target->thread.regs->gpr[0]); } /* diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index cb64d6feb45a..bbe77aed198d 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -99,22 +99,24 @@ static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, } } -static void do_signal(struct pt_regs *regs) +static void do_signal(struct task_struct *tsk) { sigset_t *oldset = sigmask_to_save(); struct ksignal ksig; int ret; int is32 = is_32bit_task(); + BUG_ON(tsk != current); + get_signal(&ksig); /* Is there any syscall restart business here ? */ - check_syscall_restart(regs, &ksig.ka, ksig.sig > 0); + check_syscall_restart(tsk->thread.regs, &ksig.ka, ksig.sig > 0); if (ksig.sig <= 0) { /* No signal to deliver -- put the saved sigmask back */ restore_saved_sigmask(); - regs->trap = 0; + tsk->thread.regs->trap = 0; return; /* no signals delivered */ } @@ -124,23 +126,22 @@ static void do_signal(struct pt_regs *regs) * user space. The DABR will have been cleared if it * triggered inside the kernel. */ - if (current->thread.hw_brk.address && - current->thread.hw_brk.type) - __set_breakpoint(¤t->thread.hw_brk); + if (tsk->thread.hw_brk.address && tsk->thread.hw_brk.type) + __set_breakpoint(&tsk->thread.hw_brk); #endif /* Re-enable the breakpoints for the signal stack */ - thread_change_pc(current, regs); + thread_change_pc(tsk, tsk->thread.regs); if (is32) { if (ksig.ka.sa.sa_flags & SA_SIGINFO) - ret = handle_rt_signal32(&ksig, oldset, regs); + ret = handle_rt_signal32(&ksig, oldset, tsk); else - ret = handle_signal32(&ksig, oldset, regs); + ret = handle_signal32(&ksig, oldset, tsk); } else { - ret = handle_rt_signal64(&ksig, oldset, regs); + ret = handle_rt_signal64(&ksig, oldset, tsk); } - regs->trap = 0; + tsk->thread.regs->trap = 0; signal_setup_done(ret, &ksig, test_thread_flag(TIF_SINGLESTEP)); } @@ -151,8 +152,10 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) if (thread_info_flags & _TIF_UPROBE) uprobe_notify_resume(regs); - if (thread_info_flags & _TIF_SIGPENDING) - do_signal(regs); + if (thread_info_flags & _TIF_SIGPENDING) { + BUG_ON(regs != current->thread.regs); + do_signal(current); + } if (thread_info_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); @@ -162,7 +165,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) user_enter(); } -unsigned long get_tm_stackpointer(struct pt_regs *regs) +unsigned long get_tm_stackpointer(struct task_struct *tsk) { /* When in an active transaction that takes a signal, we need to be * careful with the stack. It's possible that the stack has moved back @@ -187,11 +190,13 @@ unsigned long get_tm_stackpointer(struct pt_regs *regs) */ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(regs->msr)) { + BUG_ON(tsk != current); + + if (MSR_TM_ACTIVE(tsk->thread.regs->msr)) { tm_reclaim_current(TM_CAUSE_SIGNAL); - if (MSR_TM_TRANSACTIONAL(regs->msr)) - return current->thread.ckpt_regs.gpr[1]; + if (MSR_TM_TRANSACTIONAL(tsk->thread.regs->msr)) + return tsk->thread.ckpt_regs.gpr[1]; } #endif - return regs->gpr[1]; + return tsk->thread.regs->gpr[1]; } diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index be305c858e51..7c59d88b9d86 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -16,39 +16,41 @@ extern void __user *get_sigframe(struct ksignal *ksig, unsigned long sp, size_t frame_size, int is_32); extern int handle_signal32(struct ksignal *ksig, sigset_t *oldset, - struct pt_regs *regs); + struct task_struct *tsk); extern int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, - struct pt_regs *regs); + struct task_struct *tsk); extern unsigned long copy_fpr_to_user(void __user *to, struct task_struct *task); -extern unsigned long copy_transact_fpr_to_user(void __user *to, +extern unsigned long copy_ckfpr_to_user(void __user *to, struct task_struct *task); extern unsigned long copy_fpr_from_user(struct task_struct *task, void __user *from); -extern unsigned long copy_transact_fpr_from_user(struct task_struct *task, +extern unsigned long copy_ckfpr_from_user(struct task_struct *task, void __user *from); +extern unsigned long get_tm_stackpointer(struct task_struct *tsk); + #ifdef CONFIG_VSX extern unsigned long copy_vsx_to_user(void __user *to, struct task_struct *task); -extern unsigned long copy_transact_vsx_to_user(void __user *to, +extern unsigned long copy_ckvsx_to_user(void __user *to, struct task_struct *task); extern unsigned long copy_vsx_from_user(struct task_struct *task, void __user *from); -extern unsigned long copy_transact_vsx_from_user(struct task_struct *task, +extern unsigned long copy_ckvsx_from_user(struct task_struct *task, void __user *from); #endif #ifdef CONFIG_PPC64 extern int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, - struct pt_regs *regs); + struct task_struct *tsk); #else /* CONFIG_PPC64 */ static inline int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, - struct pt_regs *regs) + struct task_struct *tsk) { return -EFAULT; } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index b6aa378aff63..27aa913ac91d 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -44,6 +44,7 @@ #include <asm/vdso.h> #include <asm/switch_to.h> #include <asm/tm.h> +#include <asm/asm-prototypes.h> #ifdef CONFIG_PPC64 #include "ppc32.h" #include <asm/unistd.h> @@ -315,7 +316,7 @@ unsigned long copy_vsx_from_user(struct task_struct *task, } #ifdef CONFIG_PPC_TRANSACTIONAL_MEM -unsigned long copy_transact_fpr_to_user(void __user *to, +unsigned long copy_ckfpr_to_user(void __user *to, struct task_struct *task) { u64 buf[ELF_NFPREG]; @@ -323,12 +324,12 @@ unsigned long copy_transact_fpr_to_user(void __user *to, /* save FPR copy to local buffer then write to the thread_struct */ for (i = 0; i < (ELF_NFPREG - 1) ; i++) - buf[i] = task->thread.TS_TRANS_FPR(i); - buf[i] = task->thread.transact_fp.fpscr; + buf[i] = task->thread.TS_CKFPR(i); + buf[i] = task->thread.ckfp_state.fpscr; return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double)); } -unsigned long copy_transact_fpr_from_user(struct task_struct *task, +unsigned long copy_ckfpr_from_user(struct task_struct *task, void __user *from) { u64 buf[ELF_NFPREG]; @@ -337,13 +338,13 @@ unsigned long copy_transact_fpr_from_user(struct task_struct *task, if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double))) return 1; for (i = 0; i < (ELF_NFPREG - 1) ; i++) - task->thread.TS_TRANS_FPR(i) = buf[i]; - task->thread.transact_fp.fpscr = buf[i]; + task->thread.TS_CKFPR(i) = buf[i]; + task->thread.ckfp_state.fpscr = buf[i]; return 0; } -unsigned long copy_transact_vsx_to_user(void __user *to, +unsigned long copy_ckvsx_to_user(void __user *to, struct task_struct *task) { u64 buf[ELF_NVSRHALFREG]; @@ -351,11 +352,11 @@ unsigned long copy_transact_vsx_to_user(void __user *to, /* save FPR copy to local buffer then write to the thread_struct */ for (i = 0; i < ELF_NVSRHALFREG; i++) - buf[i] = task->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET]; + buf[i] = task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET]; return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double)); } -unsigned long copy_transact_vsx_from_user(struct task_struct *task, +unsigned long copy_ckvsx_from_user(struct task_struct *task, void __user *from) { u64 buf[ELF_NVSRHALFREG]; @@ -364,7 +365,7 @@ unsigned long copy_transact_vsx_from_user(struct task_struct *task, if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double))) return 1; for (i = 0; i < ELF_NVSRHALFREG ; i++) - task->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET] = buf[i]; + task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; return 0; } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ @@ -384,17 +385,17 @@ inline unsigned long copy_fpr_from_user(struct task_struct *task, } #ifdef CONFIG_PPC_TRANSACTIONAL_MEM -inline unsigned long copy_transact_fpr_to_user(void __user *to, +inline unsigned long copy_ckfpr_to_user(void __user *to, struct task_struct *task) { - return __copy_to_user(to, task->thread.transact_fp.fpr, + return __copy_to_user(to, task->thread.ckfp_state.fpr, ELF_NFPREG * sizeof(double)); } -inline unsigned long copy_transact_fpr_from_user(struct task_struct *task, +inline unsigned long copy_ckfpr_from_user(struct task_struct *task, void __user *from) { - return __copy_from_user(task->thread.transact_fp.fpr, from, + return __copy_from_user(task->thread.ckfp_state.fpr, from, ELF_NFPREG * sizeof(double)); } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ @@ -525,9 +526,6 @@ static int save_tm_user_regs(struct pt_regs *regs, */ regs->msr &= ~MSR_TS_MASK; - /* Make sure floating point registers are stored in regs */ - flush_fp_to_thread(current); - /* Save both sets of general registers */ if (save_general_regs(¤t->thread.ckpt_regs, frame) || save_general_regs(regs, tm_frame)) @@ -545,18 +543,17 @@ static int save_tm_user_regs(struct pt_regs *regs, #ifdef CONFIG_ALTIVEC /* save altivec registers */ if (current->thread.used_vr) { - flush_altivec_to_thread(current); - if (__copy_to_user(&frame->mc_vregs, ¤t->thread.vr_state, + if (__copy_to_user(&frame->mc_vregs, ¤t->thread.ckvr_state, ELF_NVRREG * sizeof(vector128))) return 1; if (msr & MSR_VEC) { if (__copy_to_user(&tm_frame->mc_vregs, - ¤t->thread.transact_vr, + ¤t->thread.vr_state, ELF_NVRREG * sizeof(vector128))) return 1; } else { if (__copy_to_user(&tm_frame->mc_vregs, - ¤t->thread.vr_state, + ¤t->thread.ckvr_state, ELF_NVRREG * sizeof(vector128))) return 1; } @@ -573,28 +570,28 @@ static int save_tm_user_regs(struct pt_regs *regs, * most significant bits of that same vector. --BenH */ if (cpu_has_feature(CPU_FTR_ALTIVEC)) - current->thread.vrsave = mfspr(SPRN_VRSAVE); - if (__put_user(current->thread.vrsave, + current->thread.ckvrsave = mfspr(SPRN_VRSAVE); + if (__put_user(current->thread.ckvrsave, (u32 __user *)&frame->mc_vregs[32])) return 1; if (msr & MSR_VEC) { - if (__put_user(current->thread.transact_vrsave, + if (__put_user(current->thread.vrsave, (u32 __user *)&tm_frame->mc_vregs[32])) return 1; } else { - if (__put_user(current->thread.vrsave, + if (__put_user(current->thread.ckvrsave, (u32 __user *)&tm_frame->mc_vregs[32])) return 1; } #endif /* CONFIG_ALTIVEC */ - if (copy_fpr_to_user(&frame->mc_fregs, current)) + if (copy_ckfpr_to_user(&frame->mc_fregs, current)) return 1; if (msr & MSR_FP) { - if (copy_transact_fpr_to_user(&tm_frame->mc_fregs, current)) + if (copy_fpr_to_user(&tm_frame->mc_fregs, current)) return 1; } else { - if (copy_fpr_to_user(&tm_frame->mc_fregs, current)) + if (copy_ckfpr_to_user(&tm_frame->mc_fregs, current)) return 1; } @@ -606,15 +603,14 @@ static int save_tm_user_regs(struct pt_regs *regs, * contains valid data */ if (current->thread.used_vsr) { - flush_vsx_to_thread(current); - if (copy_vsx_to_user(&frame->mc_vsregs, current)) + if (copy_ckvsx_to_user(&frame->mc_vsregs, current)) return 1; if (msr & MSR_VSX) { - if (copy_transact_vsx_to_user(&tm_frame->mc_vsregs, + if (copy_vsx_to_user(&tm_frame->mc_vsregs, current)) return 1; } else { - if (copy_vsx_to_user(&tm_frame->mc_vsregs, current)) + if (copy_ckvsx_to_user(&tm_frame->mc_vsregs, current)) return 1; } @@ -698,6 +694,7 @@ static long restore_user_regs(struct pt_regs *regs, if (__copy_from_user(¤t->thread.vr_state, &sr->mc_vregs, sizeof(sr->mc_vregs))) return 1; + current->thread.used_vr = true; } else if (current->thread.used_vr) memset(¤t->thread.vr_state, 0, ELF_NVRREG * sizeof(vector128)); @@ -724,6 +721,7 @@ static long restore_user_regs(struct pt_regs *regs, */ if (copy_vsx_from_user(current, &sr->mc_vsregs)) return 1; + current->thread.used_vsr = true; } else if (current->thread.used_vsr) for (i = 0; i < 32 ; i++) current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0; @@ -743,6 +741,7 @@ static long restore_user_regs(struct pt_regs *regs, if (__copy_from_user(current->thread.evr, &sr->mc_vregs, ELF_NEVRREG * sizeof(u32))) return 1; + current->thread.used_spe = true; } else if (current->thread.used_spe) memset(current->thread.evr, 0, ELF_NEVRREG * sizeof(u32)); @@ -793,33 +792,34 @@ static long restore_tm_user_regs(struct pt_regs *regs, regs->msr &= ~MSR_VEC; if (msr & MSR_VEC) { /* restore altivec registers from the stack */ - if (__copy_from_user(¤t->thread.vr_state, &sr->mc_vregs, + if (__copy_from_user(¤t->thread.ckvr_state, &sr->mc_vregs, sizeof(sr->mc_vregs)) || - __copy_from_user(¤t->thread.transact_vr, + __copy_from_user(¤t->thread.vr_state, &tm_sr->mc_vregs, sizeof(sr->mc_vregs))) return 1; + current->thread.used_vr = true; } else if (current->thread.used_vr) { memset(¤t->thread.vr_state, 0, ELF_NVRREG * sizeof(vector128)); - memset(¤t->thread.transact_vr, 0, + memset(¤t->thread.ckvr_state, 0, ELF_NVRREG * sizeof(vector128)); } /* Always get VRSAVE back */ - if (__get_user(current->thread.vrsave, + if (__get_user(current->thread.ckvrsave, (u32 __user *)&sr->mc_vregs[32]) || - __get_user(current->thread.transact_vrsave, + __get_user(current->thread.vrsave, (u32 __user *)&tm_sr->mc_vregs[32])) return 1; if (cpu_has_feature(CPU_FTR_ALTIVEC)) - mtspr(SPRN_VRSAVE, current->thread.vrsave); + mtspr(SPRN_VRSAVE, current->thread.ckvrsave); #endif /* CONFIG_ALTIVEC */ regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1); if (copy_fpr_from_user(current, &sr->mc_fregs) || - copy_transact_fpr_from_user(current, &tm_sr->mc_fregs)) + copy_ckfpr_from_user(current, &tm_sr->mc_fregs)) return 1; #ifdef CONFIG_VSX @@ -829,13 +829,14 @@ static long restore_tm_user_regs(struct pt_regs *regs, * Restore altivec registers from the stack to a local * buffer, then write this out to the thread_struct */ - if (copy_vsx_from_user(current, &sr->mc_vsregs) || - copy_transact_vsx_from_user(current, &tm_sr->mc_vsregs)) + if (copy_vsx_from_user(current, &tm_sr->mc_vsregs) || + copy_ckvsx_from_user(current, &sr->mc_vsregs)) return 1; + current->thread.used_vsr = true; } else if (current->thread.used_vsr) for (i = 0; i < 32 ; i++) { current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0; - current->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET] = 0; + current->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = 0; } #endif /* CONFIG_VSX */ @@ -848,6 +849,7 @@ static long restore_tm_user_regs(struct pt_regs *regs, if (__copy_from_user(current->thread.evr, &sr->mc_vregs, ELF_NEVRREG * sizeof(u32))) return 1; + current->thread.used_spe = true; } else if (current->thread.used_spe) memset(current->thread.evr, 0, ELF_NEVRREG * sizeof(u32)); @@ -877,13 +879,14 @@ static long restore_tm_user_regs(struct pt_regs *regs, tm_recheckpoint(¤t->thread, msr); /* This loads the speculative FP/VEC state, if used */ + msr_check_and_set(msr & (MSR_FP | MSR_VEC)); if (msr & MSR_FP) { - do_load_up_transact_fpu(¤t->thread); + load_fp_state(¤t->thread.fp_state); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } #ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { - do_load_up_transact_altivec(¤t->thread); + load_vr_state(¤t->thread.vr_state); regs->msr |= MSR_VEC; } #endif @@ -971,7 +974,7 @@ int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from) * (one which gets siginfo). */ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, - struct pt_regs *regs) + struct task_struct *tsk) { struct rt_sigframe __user *rt_sf; struct mcontext __user *frame; @@ -980,10 +983,13 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, unsigned long newsp = 0; int sigret; unsigned long tramp; + struct pt_regs *regs = tsk->thread.regs; + + BUG_ON(tsk != current); /* Set up Signal Frame */ /* Put a Real Time Context onto stack */ - rt_sf = get_sigframe(ksig, get_tm_stackpointer(regs), sizeof(*rt_sf), 1); + rt_sf = get_sigframe(ksig, get_tm_stackpointer(tsk), sizeof(*rt_sf), 1); addr = rt_sf; if (unlikely(rt_sf == NULL)) goto badframe; @@ -1000,9 +1006,9 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, /* Save user registers on the stack */ frame = &rt_sf->uc.uc_mcontext; addr = frame; - if (vdso32_rt_sigtramp && current->mm->context.vdso_base) { + if (vdso32_rt_sigtramp && tsk->mm->context.vdso_base) { sigret = 0; - tramp = current->mm->context.vdso_base + vdso32_rt_sigtramp; + tramp = tsk->mm->context.vdso_base + vdso32_rt_sigtramp; } else { sigret = __NR_rt_sigreturn; tramp = (unsigned long) frame->tramp; @@ -1029,7 +1035,7 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, } regs->link = tramp; - current->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */ + tsk->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */ /* create a stack frame for the caller of the handler */ newsp = ((unsigned long)rt_sf) - (__SIGNAL_FRAMESIZE + 16); @@ -1054,7 +1060,7 @@ badframe: printk_ratelimited(KERN_INFO "%s[%d]: bad frame in handle_rt_signal32: " "%p nip %08lx lr %08lx\n", - current->comm, current->pid, + tsk->comm, tsk->pid, addr, regs->nip, regs->link); return 1; @@ -1226,7 +1232,21 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, (regs->gpr[1] + __SIGNAL_FRAMESIZE + 16); if (!access_ok(VERIFY_READ, rt_sf, sizeof(*rt_sf))) goto bad; + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * If there is a transactional state then throw it away. + * The purpose of a sigreturn is to destroy all traces of the + * signal frame, this includes any transactional state created + * within in. We only check for suspended as we can never be + * active in the kernel, we are active, there is nothing better to + * do than go ahead and Bad Thing later. + * The cause is not important as there will never be a + * recheckpoint so it's not user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); + if (__get_user(tmp, &rt_sf->uc.uc_link)) goto bad; uc_transact = (struct ucontext __user *)(uintptr_t)tmp; @@ -1396,7 +1416,8 @@ int sys_debug_setcontext(struct ucontext __user *ctx, /* * OK, we're invoking a handler */ -int handle_signal32(struct ksignal *ksig, sigset_t *oldset, struct pt_regs *regs) +int handle_signal32(struct ksignal *ksig, sigset_t *oldset, + struct task_struct *tsk) { struct sigcontext __user *sc; struct sigframe __user *frame; @@ -1404,9 +1425,12 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, struct pt_regs *regs unsigned long newsp = 0; int sigret; unsigned long tramp; + struct pt_regs *regs = tsk->thread.regs; + + BUG_ON(tsk != current); /* Set up Signal Frame */ - frame = get_sigframe(ksig, get_tm_stackpointer(regs), sizeof(*frame), 1); + frame = get_sigframe(ksig, get_tm_stackpointer(tsk), sizeof(*frame), 1); if (unlikely(frame == NULL)) goto badframe; sc = (struct sigcontext __user *) &frame->sctx; @@ -1425,9 +1449,9 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, struct pt_regs *regs || __put_user(ksig->sig, &sc->signal)) goto badframe; - if (vdso32_sigtramp && current->mm->context.vdso_base) { + if (vdso32_sigtramp && tsk->mm->context.vdso_base) { sigret = 0; - tramp = current->mm->context.vdso_base + vdso32_sigtramp; + tramp = tsk->mm->context.vdso_base + vdso32_sigtramp; } else { sigret = __NR_sigreturn; tramp = (unsigned long) frame->mctx.tramp; @@ -1449,7 +1473,7 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, struct pt_regs *regs regs->link = tramp; - current->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */ + tsk->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */ /* create a stack frame for the caller of the handler */ newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE; @@ -1469,7 +1493,7 @@ badframe: printk_ratelimited(KERN_INFO "%s[%d]: bad frame in handle_signal32: " "%p nip %08lx lr %08lx\n", - current->comm, current->pid, + tsk->comm, tsk->pid, frame, regs->nip, regs->link); return 1; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 7e49984d4331..96698fdf93b4 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -35,6 +35,7 @@ #include <asm/vdso.h> #include <asm/switch_to.h> #include <asm/tm.h> +#include <asm/asm-prototypes.h> #include "signal.h" @@ -90,9 +91,9 @@ static elf_vrreg_t __user *sigcontext_vmx_regs(struct sigcontext __user *sc) * Set up the sigcontext for the signal frame. */ -static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, - int signr, sigset_t *set, unsigned long handler, - int ctx_has_vsx_region) +static long setup_sigcontext(struct sigcontext __user *sc, + struct task_struct *tsk, int signr, sigset_t *set, + unsigned long handler, int ctx_has_vsx_region) { /* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the * process never used altivec yet (MSR_VEC is zero in pt_regs of @@ -106,17 +107,20 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc); unsigned long vrsave; #endif + struct pt_regs *regs = tsk->thread.regs; unsigned long msr = regs->msr; long err = 0; + BUG_ON(tsk != current); + #ifdef CONFIG_ALTIVEC err |= __put_user(v_regs, &sc->v_regs); /* save altivec registers */ - if (current->thread.used_vr) { - flush_altivec_to_thread(current); + if (tsk->thread.used_vr) { + flush_altivec_to_thread(tsk); /* Copy 33 vec registers (vr0..31 and vscr) to the stack */ - err |= __copy_to_user(v_regs, ¤t->thread.vr_state, + err |= __copy_to_user(v_regs, &tsk->thread.vr_state, 33 * sizeof(vector128)); /* set MSR_VEC in the MSR value in the frame to indicate that sc->v_reg) * contains valid data. @@ -129,16 +133,16 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, vrsave = 0; if (cpu_has_feature(CPU_FTR_ALTIVEC)) { vrsave = mfspr(SPRN_VRSAVE); - current->thread.vrsave = vrsave; + tsk->thread.vrsave = vrsave; } err |= __put_user(vrsave, (u32 __user *)&v_regs[33]); #else /* CONFIG_ALTIVEC */ err |= __put_user(0, &sc->v_regs); #endif /* CONFIG_ALTIVEC */ - flush_fp_to_thread(current); + flush_fp_to_thread(tsk); /* copy fpr regs and fpscr */ - err |= copy_fpr_to_user(&sc->fp_regs, current); + err |= copy_fpr_to_user(&sc->fp_regs, tsk); /* * Clear the MSR VSX bit to indicate there is no valid state attached @@ -151,10 +155,10 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, * then out to userspace. Update v_regs to point after the * VMX data. */ - if (current->thread.used_vsr && ctx_has_vsx_region) { - flush_vsx_to_thread(current); + if (tsk->thread.used_vsr && ctx_has_vsx_region) { + flush_vsx_to_thread(tsk); v_regs += ELF_NVRREG; - err |= copy_vsx_to_user(v_regs, current); + err |= copy_vsx_to_user(v_regs, tsk); /* set MSR_VSX in the MSR value in the frame to * indicate that sc->vs_reg) contains valid data. */ @@ -187,7 +191,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, */ static long setup_tm_sigcontexts(struct sigcontext __user *sc, struct sigcontext __user *tm_sc, - struct pt_regs *regs, + struct task_struct *tsk, int signr, sigset_t *set, unsigned long handler) { /* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the @@ -202,9 +206,12 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc); elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc); #endif - unsigned long msr = regs->msr; + struct pt_regs *regs = tsk->thread.regs; + unsigned long msr = tsk->thread.ckpt_regs.msr; long err = 0; + BUG_ON(tsk != current); + BUG_ON(!MSR_TM_ACTIVE(regs->msr)); /* Remove TM bits from thread's MSR. The MSR in the sigcontext @@ -214,28 +221,25 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, */ regs->msr &= ~MSR_TS_MASK; - flush_fp_to_thread(current); - #ifdef CONFIG_ALTIVEC err |= __put_user(v_regs, &sc->v_regs); err |= __put_user(tm_v_regs, &tm_sc->v_regs); /* save altivec registers */ - if (current->thread.used_vr) { - flush_altivec_to_thread(current); + if (tsk->thread.used_vr) { /* Copy 33 vec registers (vr0..31 and vscr) to the stack */ - err |= __copy_to_user(v_regs, ¤t->thread.vr_state, + err |= __copy_to_user(v_regs, &tsk->thread.ckvr_state, 33 * sizeof(vector128)); /* If VEC was enabled there are transactional VRs valid too, * else they're a copy of the checkpointed VRs. */ if (msr & MSR_VEC) err |= __copy_to_user(tm_v_regs, - ¤t->thread.transact_vr, + &tsk->thread.vr_state, 33 * sizeof(vector128)); else err |= __copy_to_user(tm_v_regs, - ¤t->thread.vr_state, + &tsk->thread.ckvr_state, 33 * sizeof(vector128)); /* set MSR_VEC in the MSR value in the frame to indicate @@ -247,13 +251,13 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, * use altivec. */ if (cpu_has_feature(CPU_FTR_ALTIVEC)) - current->thread.vrsave = mfspr(SPRN_VRSAVE); - err |= __put_user(current->thread.vrsave, (u32 __user *)&v_regs[33]); + tsk->thread.ckvrsave = mfspr(SPRN_VRSAVE); + err |= __put_user(tsk->thread.ckvrsave, (u32 __user *)&v_regs[33]); if (msr & MSR_VEC) - err |= __put_user(current->thread.transact_vrsave, + err |= __put_user(tsk->thread.vrsave, (u32 __user *)&tm_v_regs[33]); else - err |= __put_user(current->thread.vrsave, + err |= __put_user(tsk->thread.ckvrsave, (u32 __user *)&tm_v_regs[33]); #else /* CONFIG_ALTIVEC */ @@ -262,11 +266,11 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, #endif /* CONFIG_ALTIVEC */ /* copy fpr regs and fpscr */ - err |= copy_fpr_to_user(&sc->fp_regs, current); + err |= copy_ckfpr_to_user(&sc->fp_regs, tsk); if (msr & MSR_FP) - err |= copy_transact_fpr_to_user(&tm_sc->fp_regs, current); + err |= copy_fpr_to_user(&tm_sc->fp_regs, tsk); else - err |= copy_fpr_to_user(&tm_sc->fp_regs, current); + err |= copy_ckfpr_to_user(&tm_sc->fp_regs, tsk); #ifdef CONFIG_VSX /* @@ -274,17 +278,16 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, * then out to userspace. Update v_regs to point after the * VMX data. */ - if (current->thread.used_vsr) { - flush_vsx_to_thread(current); + if (tsk->thread.used_vsr) { v_regs += ELF_NVRREG; tm_v_regs += ELF_NVRREG; - err |= copy_vsx_to_user(v_regs, current); + err |= copy_ckvsx_to_user(v_regs, tsk); if (msr & MSR_VSX) - err |= copy_transact_vsx_to_user(tm_v_regs, current); + err |= copy_vsx_to_user(tm_v_regs, tsk); else - err |= copy_vsx_to_user(tm_v_regs, current); + err |= copy_ckvsx_to_user(tm_v_regs, tsk); /* set MSR_VSX in the MSR value in the frame to * indicate that sc->vs_reg) contains valid data. @@ -298,7 +301,7 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, WARN_ON(!FULL_REGS(regs)); err |= __copy_to_user(&tm_sc->gp_regs, regs, GP_REGS_SIZE); err |= __copy_to_user(&sc->gp_regs, - ¤t->thread.ckpt_regs, GP_REGS_SIZE); + &tsk->thread.ckpt_regs, GP_REGS_SIZE); err |= __put_user(msr, &tm_sc->gp_regs[PT_MSR]); err |= __put_user(msr, &sc->gp_regs[PT_MSR]); err |= __put_user(signr, &sc->signal); @@ -314,7 +317,7 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, * Restore the sigcontext from the signal frame. */ -static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, +static long restore_sigcontext(struct task_struct *tsk, sigset_t *set, int sig, struct sigcontext __user *sc) { #ifdef CONFIG_ALTIVEC @@ -323,10 +326,13 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, unsigned long err = 0; unsigned long save_r13 = 0; unsigned long msr; + struct pt_regs *regs = tsk->thread.regs; #ifdef CONFIG_VSX int i; #endif + BUG_ON(tsk != current); + /* If this is not a signal return, we preserve the TLS in r13 */ if (!sig) save_r13 = regs->gpr[13]; @@ -356,7 +362,7 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, /* * Force reload of FP/VEC. - * This has to be done before copying stuff into current->thread.fpr/vr + * This has to be done before copying stuff into tsk->thread.fpr/vr * for the reasons explained in the previous comment. */ regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC | MSR_VSX); @@ -368,21 +374,23 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, if (v_regs && !access_ok(VERIFY_READ, v_regs, 34 * sizeof(vector128))) return -EFAULT; /* Copy 33 vec registers (vr0..31 and vscr) from the stack */ - if (v_regs != NULL && (msr & MSR_VEC) != 0) - err |= __copy_from_user(¤t->thread.vr_state, v_regs, + if (v_regs != NULL && (msr & MSR_VEC) != 0) { + err |= __copy_from_user(&tsk->thread.vr_state, v_regs, 33 * sizeof(vector128)); - else if (current->thread.used_vr) - memset(¤t->thread.vr_state, 0, 33 * sizeof(vector128)); + tsk->thread.used_vr = true; + } else if (tsk->thread.used_vr) { + memset(&tsk->thread.vr_state, 0, 33 * sizeof(vector128)); + } /* Always get VRSAVE back */ if (v_regs != NULL) - err |= __get_user(current->thread.vrsave, (u32 __user *)&v_regs[33]); + err |= __get_user(tsk->thread.vrsave, (u32 __user *)&v_regs[33]); else - current->thread.vrsave = 0; + tsk->thread.vrsave = 0; if (cpu_has_feature(CPU_FTR_ALTIVEC)) - mtspr(SPRN_VRSAVE, current->thread.vrsave); + mtspr(SPRN_VRSAVE, tsk->thread.vrsave); #endif /* CONFIG_ALTIVEC */ /* restore floating point */ - err |= copy_fpr_from_user(current, &sc->fp_regs); + err |= copy_fpr_from_user(tsk, &sc->fp_regs); #ifdef CONFIG_VSX /* * Get additional VSX data. Update v_regs to point after the @@ -390,11 +398,13 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, * buffer for formatting, then into the taskstruct. */ v_regs += ELF_NVRREG; - if ((msr & MSR_VSX) != 0) - err |= copy_vsx_from_user(current, v_regs); - else + if ((msr & MSR_VSX) != 0) { + err |= copy_vsx_from_user(tsk, v_regs); + tsk->thread.used_vsr = true; + } else { for (i = 0; i < 32 ; i++) - current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0; + tsk->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0; + } #endif return err; } @@ -404,7 +414,7 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, * Restore the two sigcontexts from the frame of a transactional processes. */ -static long restore_tm_sigcontexts(struct pt_regs *regs, +static long restore_tm_sigcontexts(struct task_struct *tsk, struct sigcontext __user *sc, struct sigcontext __user *tm_sc) { @@ -413,12 +423,16 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, #endif unsigned long err = 0; unsigned long msr; + struct pt_regs *regs = tsk->thread.regs; #ifdef CONFIG_VSX int i; #endif + + BUG_ON(tsk != current); + /* copy the GPRs */ err |= __copy_from_user(regs->gpr, tm_sc->gp_regs, sizeof(regs->gpr)); - err |= __copy_from_user(¤t->thread.ckpt_regs, sc->gp_regs, + err |= __copy_from_user(&tsk->thread.ckpt_regs, sc->gp_regs, sizeof(regs->gpr)); /* @@ -430,7 +444,7 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, * we don't need to re-copy them here. */ err |= __get_user(regs->nip, &tm_sc->gp_regs[PT_NIP]); - err |= __get_user(current->thread.tm_tfhar, &sc->gp_regs[PT_NIP]); + err |= __get_user(tsk->thread.tm_tfhar, &sc->gp_regs[PT_NIP]); /* get MSR separately, transfer the LE bit if doing signal return */ err |= __get_user(msr, &sc->gp_regs[PT_MSR]); @@ -449,13 +463,13 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, err |= __get_user(regs->link, &tm_sc->gp_regs[PT_LNK]); err |= __get_user(regs->xer, &tm_sc->gp_regs[PT_XER]); err |= __get_user(regs->ccr, &tm_sc->gp_regs[PT_CCR]); - err |= __get_user(current->thread.ckpt_regs.ctr, + err |= __get_user(tsk->thread.ckpt_regs.ctr, &sc->gp_regs[PT_CTR]); - err |= __get_user(current->thread.ckpt_regs.link, + err |= __get_user(tsk->thread.ckpt_regs.link, &sc->gp_regs[PT_LNK]); - err |= __get_user(current->thread.ckpt_regs.xer, + err |= __get_user(tsk->thread.ckpt_regs.xer, &sc->gp_regs[PT_XER]); - err |= __get_user(current->thread.ckpt_regs.ccr, + err |= __get_user(tsk->thread.ckpt_regs.ccr, &sc->gp_regs[PT_CCR]); /* These regs are not checkpointed; they can go in 'regs'. */ @@ -466,7 +480,7 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, /* * Force reload of FP/VEC. - * This has to be done before copying stuff into current->thread.fpr/vr + * This has to be done before copying stuff into tsk->thread.fpr/vr * for the reasons explained in the previous comment. */ regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC | MSR_VSX); @@ -483,32 +497,33 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, return -EFAULT; /* Copy 33 vec registers (vr0..31 and vscr) from the stack */ if (v_regs != NULL && tm_v_regs != NULL && (msr & MSR_VEC) != 0) { - err |= __copy_from_user(¤t->thread.vr_state, v_regs, + err |= __copy_from_user(&tsk->thread.ckvr_state, v_regs, 33 * sizeof(vector128)); - err |= __copy_from_user(¤t->thread.transact_vr, tm_v_regs, + err |= __copy_from_user(&tsk->thread.vr_state, tm_v_regs, 33 * sizeof(vector128)); + current->thread.used_vr = true; } - else if (current->thread.used_vr) { - memset(¤t->thread.vr_state, 0, 33 * sizeof(vector128)); - memset(¤t->thread.transact_vr, 0, 33 * sizeof(vector128)); + else if (tsk->thread.used_vr) { + memset(&tsk->thread.vr_state, 0, 33 * sizeof(vector128)); + memset(&tsk->thread.ckvr_state, 0, 33 * sizeof(vector128)); } /* Always get VRSAVE back */ if (v_regs != NULL && tm_v_regs != NULL) { - err |= __get_user(current->thread.vrsave, + err |= __get_user(tsk->thread.ckvrsave, (u32 __user *)&v_regs[33]); - err |= __get_user(current->thread.transact_vrsave, + err |= __get_user(tsk->thread.vrsave, (u32 __user *)&tm_v_regs[33]); } else { - current->thread.vrsave = 0; - current->thread.transact_vrsave = 0; + tsk->thread.vrsave = 0; + tsk->thread.ckvrsave = 0; } if (cpu_has_feature(CPU_FTR_ALTIVEC)) - mtspr(SPRN_VRSAVE, current->thread.vrsave); + mtspr(SPRN_VRSAVE, tsk->thread.vrsave); #endif /* CONFIG_ALTIVEC */ /* restore floating point */ - err |= copy_fpr_from_user(current, &sc->fp_regs); - err |= copy_transact_fpr_from_user(current, &tm_sc->fp_regs); + err |= copy_fpr_from_user(tsk, &tm_sc->fp_regs); + err |= copy_ckfpr_from_user(tsk, &sc->fp_regs); #ifdef CONFIG_VSX /* * Get additional VSX data. Update v_regs to point after the @@ -518,32 +533,31 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, if (v_regs && ((msr & MSR_VSX) != 0)) { v_regs += ELF_NVRREG; tm_v_regs += ELF_NVRREG; - err |= copy_vsx_from_user(current, v_regs); - err |= copy_transact_vsx_from_user(current, tm_v_regs); + err |= copy_vsx_from_user(tsk, tm_v_regs); + err |= copy_ckvsx_from_user(tsk, v_regs); + tsk->thread.used_vsr = true; } else { for (i = 0; i < 32 ; i++) { - current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0; - current->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET] = 0; + tsk->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0; + tsk->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = 0; } } #endif tm_enable(); /* Make sure the transaction is marked as failed */ - current->thread.tm_texasr |= TEXASR_FS; + tsk->thread.tm_texasr |= TEXASR_FS; /* This loads the checkpointed FP/VEC state, if used */ - tm_recheckpoint(¤t->thread, msr); + tm_recheckpoint(&tsk->thread, msr); - /* This loads the speculative FP/VEC state, if used */ + msr_check_and_set(msr & (MSR_FP | MSR_VEC)); if (msr & MSR_FP) { - do_load_up_transact_fpu(¤t->thread); - regs->msr |= (MSR_FP | current->thread.fpexc_mode); + load_fp_state(&tsk->thread.fp_state); + regs->msr |= (MSR_FP | tsk->thread.fpexc_mode); } -#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { - do_load_up_transact_altivec(¤t->thread); + load_vr_state(&tsk->thread.vr_state); regs->msr |= MSR_VEC; } -#endif return err; } @@ -594,6 +608,8 @@ int sys_swapcontext(struct ucontext __user *old_ctx, unsigned long new_msr = 0; int ctx_has_vsx_region = 0; + BUG_ON(regs != current->thread.regs); + if (new_ctx && get_user(new_msr, &new_ctx->uc_mcontext.gp_regs[PT_MSR])) return -EFAULT; @@ -616,7 +632,7 @@ int sys_swapcontext(struct ucontext __user *old_ctx, if (old_ctx != NULL) { if (!access_ok(VERIFY_WRITE, old_ctx, ctx_size) - || setup_sigcontext(&old_ctx->uc_mcontext, regs, 0, NULL, 0, + || setup_sigcontext(&old_ctx->uc_mcontext, current, 0, NULL, 0, ctx_has_vsx_region) || __copy_to_user(&old_ctx->uc_sigmask, ¤t->blocked, sizeof(sigset_t))) @@ -644,7 +660,7 @@ int sys_swapcontext(struct ucontext __user *old_ctx, if (__copy_from_user(&set, &new_ctx->uc_sigmask, sizeof(set))) do_exit(SIGSEGV); set_current_blocked(&set); - if (restore_sigcontext(regs, NULL, 0, &new_ctx->uc_mcontext)) + if (restore_sigcontext(current, NULL, 0, &new_ctx->uc_mcontext)) do_exit(SIGSEGV); /* This returns like rt_sigreturn */ @@ -667,6 +683,8 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, unsigned long msr; #endif + BUG_ON(current->thread.regs != regs); + /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; @@ -676,7 +694,21 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, if (__copy_from_user(&set, &uc->uc_sigmask, sizeof(set))) goto badframe; set_current_blocked(&set); + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * If there is a transactional state then throw it away. + * The purpose of a sigreturn is to destroy all traces of the + * signal frame, this includes any transactional state created + * within in. We only check for suspended as we can never be + * active in the kernel, we are active, there is nothing better to + * do than go ahead and Bad Thing later. + * The cause is not important as there will never be a + * recheckpoint so it's not user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); + if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR])) goto badframe; if (MSR_TM_ACTIVE(msr)) { @@ -684,14 +716,14 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, struct ucontext __user *uc_transact; if (__get_user(uc_transact, &uc->uc_link)) goto badframe; - if (restore_tm_sigcontexts(regs, &uc->uc_mcontext, + if (restore_tm_sigcontexts(current, &uc->uc_mcontext, &uc_transact->uc_mcontext)) goto badframe; } else /* Fall through, for non-TM restore */ #endif - if (restore_sigcontext(regs, NULL, 1, &uc->uc_mcontext)) + if (restore_sigcontext(current, NULL, 1, &uc->uc_mcontext)) goto badframe; if (restore_altstack(&uc->uc_stack)) @@ -710,13 +742,17 @@ badframe: return 0; } -int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) +int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, + struct task_struct *tsk) { struct rt_sigframe __user *frame; unsigned long newsp = 0; long err = 0; + struct pt_regs *regs = tsk->thread.regs; + + BUG_ON(tsk != current); - frame = get_sigframe(ksig, get_tm_stackpointer(regs), sizeof(*frame), 0); + frame = get_sigframe(ksig, get_tm_stackpointer(tsk), sizeof(*frame), 0); if (unlikely(frame == NULL)) goto badframe; @@ -737,14 +773,13 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs err |= __put_user(&frame->uc_transact, &frame->uc.uc_link); err |= setup_tm_sigcontexts(&frame->uc.uc_mcontext, &frame->uc_transact.uc_mcontext, - regs, ksig->sig, - NULL, + tsk, ksig->sig, NULL, (unsigned long)ksig->ka.sa.sa_handler); } else #endif { err |= __put_user(0, &frame->uc.uc_link); - err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, ksig->sig, + err |= setup_sigcontext(&frame->uc.uc_mcontext, tsk, ksig->sig, NULL, (unsigned long)ksig->ka.sa.sa_handler, 1); } @@ -753,11 +788,11 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs goto badframe; /* Make sure signal handler doesn't get spurious FP exceptions */ - current->thread.fp_state.fpscr = 0; + tsk->thread.fp_state.fpscr = 0; /* Set up to return from userspace. */ - if (vdso64_rt_sigtramp && current->mm->context.vdso_base) { - regs->link = current->mm->context.vdso_base + vdso64_rt_sigtramp; + if (vdso64_rt_sigtramp && tsk->mm->context.vdso_base) { + regs->link = tsk->mm->context.vdso_base + vdso64_rt_sigtramp; } else { err |= setup_trampoline(__NR_rt_sigreturn, &frame->tramp[0]); if (err) @@ -807,7 +842,7 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs badframe: if (show_unhandled_signals) printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, - current->comm, current->pid, "setup_rt_frame", + tsk->comm, tsk->pid, "setup_rt_frame", (long)frame, regs->nip, regs->link); return 1; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 25a39052bf6b..9c6f3fd58059 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -830,7 +830,7 @@ int __cpu_disable(void) /* Update sibling maps */ base = cpu_first_thread_sibling(cpu); - for (i = 0; i < threads_per_core; i++) { + for (i = 0; i < threads_per_core && base + i < nr_cpu_ids; i++) { cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i)); cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu)); cpumask_clear_cpu(cpu, cpu_core_mask(base + i)); diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 5fa92706444b..644cce3d8dce 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -40,6 +40,7 @@ #include <asm/syscalls.h> #include <asm/time.h> #include <asm/unistd.h> +#include <asm/asm-prototypes.h> static inline unsigned long do_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 3efbedefba6a..67859b7d1c97 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -73,6 +73,7 @@ #include <asm/vdso_datapage.h> #include <asm/firmware.h> #include <asm/cputime.h> +#include <asm/asm-prototypes.h> /* powerpc clocksource/clockevent code */ diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 298afcf3bf2a..3a2d04134da9 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -108,6 +108,7 @@ _GLOBAL(tm_reclaim) /* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. */ std r3, STK_PARAM(R3)(r1) + std r4, STK_PARAM(R4)(r1) SAVE_NVGPRS(r1) /* We need to setup MSR for VSX register save instructions. */ @@ -126,43 +127,6 @@ _GLOBAL(tm_reclaim) mtmsrd r15 std r14, TM_FRAME_L0(r1) - /* Stash the stack pointer away for use after reclaim */ - std r1, PACAR1(r13) - - /* ******************** FPR/VR/VSRs ************ - * Before reclaiming, capture the current/transactional FPR/VR - * versions /if used/. - * - * (If VSX used, FP and VMX are implied. Or, we don't need to look - * at MSR.VSX as copying FP regs if .FP, vector regs if .VMX covers it.) - * - * We're passed the thread's MSR as parameter 2. - * - * We enabled VEC/FP/VSX in the msr above, so we can execute these - * instructions! - */ - andis. r0, r4, MSR_VEC@h - beq dont_backup_vec - - addi r7, r3, THREAD_TRANSACT_VRSTATE - SAVE_32VRS(0, r6, r7) /* r6 scratch, r7 transact vr state */ - mfvscr v0 - li r6, VRSTATE_VSCR - stvx v0, r7, r6 -dont_backup_vec: - mfspr r0, SPRN_VRSAVE - std r0, THREAD_TRANSACT_VRSAVE(r3) - - andi. r0, r4, MSR_FP - beq dont_backup_fp - - addi r7, r3, THREAD_TRANSACT_FPSTATE - SAVE_32FPRS_VSRS(0, R6, R7) /* r6 scratch, r7 transact fp state */ - - mffs fr0 - stfd fr0,FPSTATE_FPSCR(r7) - -dont_backup_fp: /* Do sanity check on MSR to make sure we are suspended */ li r7, (MSR_TS_S)@higher srdi r6, r14, 32 @@ -170,6 +134,9 @@ dont_backup_fp: 1: tdeqi r6, 0 EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 + /* Stash the stack pointer away for use after reclaim */ + std r1, PACAR1(r13) + /* Clear MSR RI since we are about to change r1, EE is already off. */ li r4, 0 mtmsrd r4, 1 @@ -273,6 +240,43 @@ dont_backup_fp: * MSR. */ + + /* ******************** FPR/VR/VSRs ************ + * After reclaiming, capture the checkpointed FPRs/VRs /if used/. + * + * (If VSX used, FP and VMX are implied. Or, we don't need to look + * at MSR.VSX as copying FP regs if .FP, vector regs if .VMX covers it.) + * + * We're passed the thread's MSR as the second parameter + * + * We enabled VEC/FP/VSX in the msr above, so we can execute these + * instructions! + */ + ld r4, STK_PARAM(R4)(r1) /* Second parameter, MSR * */ + mr r3, r12 + andis. r0, r4, MSR_VEC@h + beq dont_backup_vec + + addi r7, r3, THREAD_CKVRSTATE + SAVE_32VRS(0, r6, r7) /* r6 scratch, r7 transact vr state */ + mfvscr v0 + li r6, VRSTATE_VSCR + stvx v0, r7, r6 +dont_backup_vec: + mfspr r0, SPRN_VRSAVE + std r0, THREAD_CKVRSAVE(r3) + + andi. r0, r4, MSR_FP + beq dont_backup_fp + + addi r7, r3, THREAD_CKFPSTATE + SAVE_32FPRS_VSRS(0, R6, R7) /* r6 scratch, r7 transact fp state */ + + mffs fr0 + stfd fr0,FPSTATE_FPSCR(r7) + +dont_backup_fp: + /* TM regs, incl TEXASR -- these live in thread_struct. Note they've * been updated by the treclaim, to explain to userland the failure * cause (aborted). @@ -288,6 +292,7 @@ dont_backup_fp: /* Restore original MSR/IRQ state & clear TM mode */ ld r14, TM_FRAME_L0(r1) /* Orig MSR */ + li r15, 0 rldimi r14, r15, MSR_TS_LG, (63-MSR_TS_LG)-1 mtmsrd r14 @@ -356,28 +361,29 @@ _GLOBAL(__tm_recheckpoint) mtmsr r5 #ifdef CONFIG_ALTIVEC - /* FP and VEC registers: These are recheckpointed from thread.fpr[] - * and thread.vr[] respectively. The thread.transact_fpr[] version - * is more modern, and will be loaded subsequently by any FPUnavailable - * trap. + /* + * FP and VEC registers: These are recheckpointed from + * thread.ckfp_state and thread.ckvr_state respectively. The + * thread.fp_state[] version holds the 'live' (transactional) + * and will be loaded subsequently by any FPUnavailable trap. */ andis. r0, r4, MSR_VEC@h beq dont_restore_vec - addi r8, r3, THREAD_VRSTATE + addi r8, r3, THREAD_CKVRSTATE li r5, VRSTATE_VSCR lvx v0, r8, r5 mtvscr v0 REST_32VRS(0, r5, r8) /* r5 scratch, r8 ptr */ dont_restore_vec: - ld r5, THREAD_VRSAVE(r3) + ld r5, THREAD_CKVRSAVE(r3) mtspr SPRN_VRSAVE, r5 #endif andi. r0, r4, MSR_FP beq dont_restore_fp - addi r8, r3, THREAD_FPSTATE + addi r8, r3, THREAD_CKFPSTATE lfd fr0, FPSTATE_FPSCR(r8) MTFSF_L(fr0) REST_32FPRS_VSRS(0, R4, R8) diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 2cb589264cb7..a1f8f5641e9e 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -25,7 +25,8 @@ #include <linux/user.h> #include <linux/interrupt.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/extable.h> +#include <linux/module.h> /* print_modules */ #include <linux/prctl.h> #include <linux/delay.h> #include <linux/kprobes.h> @@ -116,7 +117,7 @@ static int die_owner = -1; static unsigned int die_nest_count; static int die_counter; -static unsigned __kprobes long oops_begin(struct pt_regs *regs) +static unsigned long oops_begin(struct pt_regs *regs) { int cpu; unsigned long flags; @@ -143,8 +144,9 @@ static unsigned __kprobes long oops_begin(struct pt_regs *regs) pmac_backlight_unblank(); return flags; } +NOKPROBE_SYMBOL(oops_begin); -static void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, +static void oops_end(unsigned long flags, struct pt_regs *regs, int signr) { bust_spinlocks(0); @@ -195,8 +197,9 @@ static void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, panic("Fatal exception"); do_exit(signr); } +NOKPROBE_SYMBOL(oops_end); -static int __kprobes __die(const char *str, struct pt_regs *regs, long err) +static int __die(const char *str, struct pt_regs *regs, long err) { printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); #ifdef CONFIG_PREEMPT @@ -220,6 +223,7 @@ static int __kprobes __die(const char *str, struct pt_regs *regs, long err) return 0; } +NOKPROBE_SYMBOL(__die); void die(const char *str, struct pt_regs *regs, long err) { @@ -801,7 +805,7 @@ void RunModeException(struct pt_regs *regs) _exception(SIGTRAP, regs, 0, 0); } -void __kprobes single_step_exception(struct pt_regs *regs) +void single_step_exception(struct pt_regs *regs) { enum ctx_state prev_state = exception_enter(); @@ -818,6 +822,7 @@ void __kprobes single_step_exception(struct pt_regs *regs) bail: exception_exit(prev_state); } +NOKPROBE_SYMBOL(single_step_exception); /* * After we have successfully emulated an instruction, we have to @@ -1139,7 +1144,7 @@ static int emulate_math(struct pt_regs *regs) static inline int emulate_math(struct pt_regs *regs) { return -1; } #endif -void __kprobes program_check_exception(struct pt_regs *regs) +void program_check_exception(struct pt_regs *regs) { enum ctx_state prev_state = exception_enter(); unsigned int reason = get_reason(regs); @@ -1259,16 +1264,18 @@ sigill: bail: exception_exit(prev_state); } +NOKPROBE_SYMBOL(program_check_exception); /* * This occurs when running in hypervisor mode on POWER6 or later * and an illegal instruction is encountered. */ -void __kprobes emulation_assist_interrupt(struct pt_regs *regs) +void emulation_assist_interrupt(struct pt_regs *regs) { regs->msr |= REASON_ILLEGAL; program_check_exception(regs); } +NOKPROBE_SYMBOL(emulation_assist_interrupt); void alignment_exception(struct pt_regs *regs) { @@ -1309,6 +1316,18 @@ bail: exception_exit(prev_state); } +void slb_miss_bad_addr(struct pt_regs *regs) +{ + enum ctx_state prev_state = exception_enter(); + + if (user_mode(regs)) + _exception(SIGSEGV, regs, SEGV_BNDERR, regs->dar); + else + bad_page_fault(regs, regs->dar, SIGSEGV); + + exception_exit(prev_state); +} + void StackOverflow(struct pt_regs *regs) { printk(KERN_CRIT "Kernel stack overflow in process %p, r1=%lx\n", @@ -1371,6 +1390,22 @@ void vsx_unavailable_exception(struct pt_regs *regs) } #ifdef CONFIG_PPC64 +static void tm_unavailable(struct pt_regs *regs) +{ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (user_mode(regs)) { + current->thread.load_tm++; + regs->msr |= MSR_TM; + tm_enable(); + tm_restore_sprs(¤t->thread); + return; + } +#endif + pr_emerg("Unrecoverable TM Unavailable Exception " + "%lx at %lx\n", regs->trap, regs->nip); + die("Unrecoverable TM Unavailable Exception", regs, SIGABRT); +} + void facility_unavailable_exception(struct pt_regs *regs) { static char *facility_strings[] = { @@ -1450,6 +1485,27 @@ void facility_unavailable_exception(struct pt_regs *regs) return; } + if (status == FSCR_TM_LG) { + /* + * If we're here then the hardware is TM aware because it + * generated an exception with FSRM_TM set. + * + * If cpu_has_feature(CPU_FTR_TM) is false, then either firmware + * told us not to do TM, or the kernel is not built with TM + * support. + * + * If both of those things are true, then userspace can spam the + * console by triggering the printk() below just by continually + * doing tbegin (or any TM instruction). So in that case just + * send the process a SIGILL immediately. + */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto out; + + tm_unavailable(regs); + return; + } + if ((status < ARRAY_SIZE(facility_strings)) && facility_strings[status]) facility = facility_strings[status]; @@ -1462,6 +1518,7 @@ void facility_unavailable_exception(struct pt_regs *regs) "%sFacility '%s' unavailable, exception at 0x%lx, MSR=%lx\n", hv ? "Hypervisor " : "", facility, regs->nip, regs->msr); +out: if (user_mode(regs)) { _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); return; @@ -1503,7 +1560,8 @@ void fp_unavailable_tm(struct pt_regs *regs) /* If VMX is in use, get the transactional values back */ if (regs->msr & MSR_VEC) { - do_load_up_transact_altivec(¤t->thread); + msr_check_and_set(MSR_VEC); + load_vr_state(¤t->thread.vr_state); /* At this point all the VSX state is loaded, so enable it */ regs->msr |= MSR_VSX; } @@ -1524,7 +1582,8 @@ void altivec_unavailable_tm(struct pt_regs *regs) current->thread.used_vr = 1; if (regs->msr & MSR_FP) { - do_load_up_transact_fpu(¤t->thread); + msr_check_and_set(MSR_FP); + load_fp_state(¤t->thread.fp_state); regs->msr |= MSR_VSX; } } @@ -1563,10 +1622,12 @@ void vsx_unavailable_tm(struct pt_regs *regs) */ tm_recheckpoint(¤t->thread, regs->msr & ~orig_msr); + msr_check_and_set(orig_msr & (MSR_FP | MSR_VEC)); + if (orig_msr & MSR_FP) - do_load_up_transact_fpu(¤t->thread); + load_fp_state(¤t->thread.fp_state); if (orig_msr & MSR_VEC) - do_load_up_transact_altivec(¤t->thread); + load_vr_state(¤t->thread.vr_state); } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ @@ -1655,7 +1716,7 @@ static void handle_debug(struct pt_regs *regs, unsigned long debug_status) mtspr(SPRN_DBCR0, current->thread.debug.dbcr0); } -void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status) +void DebugException(struct pt_regs *regs, unsigned long debug_status) { current->thread.debug.dbsr = debug_status; @@ -1716,6 +1777,7 @@ void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status) } else handle_debug(regs, debug_status); } +NOKPROBE_SYMBOL(DebugException); #endif /* CONFIG_PPC_ADV_DEBUG_REGS */ #if !defined(CONFIG_TAU_INT) diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index 366ae09b14c1..31107bf5a61f 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -31,15 +31,9 @@ $(obj)/%.so: OBJCOPYFLAGS := -S $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) -# assembly rules for the .S files -$(obj-vdso64): %.o: %.S FORCE - $(call if_changed_dep,vdso64as) - # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) -quiet_cmd_vdso64as = VDSO64A $@ - cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< # install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S index 184a6ba7f283..abf17feffe40 100644 --- a/arch/powerpc/kernel/vdso64/datapage.S +++ b/arch/powerpc/kernel/vdso64/datapage.S @@ -59,7 +59,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) bl V_LOCAL_FUNC(__get_datapage) mtlr r12 addi r3,r3,CFG_SYSCALL_MAP64 - cmpli cr0,r4,0 + cmpldi cr0,r4,0 crclr cr0*4+so beqlr li r0,NR_syscalls diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index a76b4af37ef2..382021324883 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -145,7 +145,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) bne cr0,99f li r3,0 - cmpli cr0,r4,0 + cmpldi cr0,r4,0 crclr cr0*4+so beqlr lis r5,CLOCK_REALTIME_RES@h diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 616a6d854638..bc85bdff4e01 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -7,31 +7,6 @@ #include <asm/page.h> #include <asm/ptrace.h> -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -/* void do_load_up_transact_altivec(struct thread_struct *thread) - * - * This is similar to load_up_altivec but for the transactional version of the - * vector regs. It doesn't mess with the task MSR or valid flags. - * Furthermore, VEC laziness is not supported with TM currently. - */ -_GLOBAL(do_load_up_transact_altivec) - mfmsr r6 - oris r5,r6,MSR_VEC@h - MTMSRD(r5) - isync - - li r4,1 - stw r4,THREAD_USED_VR(r3) - - li r10,THREAD_TRANSACT_VRSTATE+VRSTATE_VSCR - lvx v0,r10,r3 - mtvscr v0 - addi r10,r3,THREAD_TRANSACT_VRSTATE - REST_32VRS(0,r4,r10) - - blr -#endif - /* * Load state from memory into VMX registers including VSCR. * Assumes the caller has enabled VMX in the MSR. diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index b5fba689fca6..2d1cfafd1404 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -44,11 +44,58 @@ SECTIONS * Text, read only data and other permanent read-only sections */ - /* Text and gots */ + _text = .; + _stext = .; + + /* + * Head text. + * This needs to be in its own output section to avoid ld placing + * branch trampoline stubs randomly throughout the fixed sections, + * which it will do (even if the branch comes from another section) + * in order to optimize stub generation. + */ + .head.text : AT(ADDR(.head.text) - LOAD_OFFSET) { +#ifdef CONFIG_PPC64 + KEEP(*(.head.text.first_256B)); +#ifdef CONFIG_PPC_BOOK3E +# define END_FIXED 0x100 +#else + KEEP(*(.head.text.real_vectors)); + *(.head.text.real_trampolines); + KEEP(*(.head.text.virt_vectors)); + *(.head.text.virt_trampolines); +# if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) + KEEP(*(.head.data.fwnmi_page)); +# define END_FIXED 0x8000 +# else +# define END_FIXED 0x7000 +# endif +#endif + ASSERT((. == END_FIXED), "vmlinux.lds.S: fixed section overflow error"); +#else /* !CONFIG_PPC64 */ + HEAD_TEXT +#endif + } :kernel + + /* + * If the build dies here, it's likely code in head_64.S is referencing + * labels it can't reach, and the linker inserting stubs without the + * assembler's knowledge. To debug, remove the above assert and + * rebuild. Look for branch stubs in the fixed section region. + * + * Linker stub generation could be allowed in "trampoline" + * sections if absolutely necessary, but this would require + * some rework of the fixed sections. Before resorting to this, + * consider references that have sufficient addressing range, + * (e.g., hand coded trampolines) so the linker does not have + * to add stubs. + * + * Linker stubs at the top of the main text section are currently not + * detected, and will result in a crash at boot due to offsets being + * wrong. + */ .text : AT(ADDR(.text) - LOAD_OFFSET) { ALIGN_FUNCTION(); - HEAD_TEXT - _text = .; /* careful! __ftr_alt_* sections need to be close to .text */ *(.text .fixup __ftr_alt_* .ref.text) SCHED_TEXT @@ -56,6 +103,8 @@ SECTIONS KPROBES_TEXT IRQENTRY_TEXT SOFTIRQENTRY_TEXT + MEM_KEEP(init.text) + MEM_KEEP(exit.text) #ifdef CONFIG_PPC32 *(.got1) diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index c2024ac9d4e8..029be26b5a17 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -22,6 +22,9 @@ config KVM select ANON_INODES select HAVE_KVM_EVENTFD select SRCU + select KVM_VFIO + select IRQ_BYPASS_MANAGER + select HAVE_KVM_IRQ_BYPASS config KVM_BOOK3S_HANDLER bool diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 1f9e5529e692..7dd89b79d038 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -7,16 +7,16 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm KVM := ../../../virt/kvm -common-objs-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ - $(KVM)/eventfd.o +common-objs-y = $(KVM)/kvm_main.o $(KVM)/eventfd.o common-objs-$(CONFIG_KVM_VFIO) += $(KVM)/vfio.o +common-objs-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o CFLAGS_e500_mmu.o := -I. CFLAGS_e500_mmu_host.o := -I. CFLAGS_emulate.o := -I. CFLAGS_emulate_loadstore.o := -I. -common-objs-y += powerpc.o emulate.o emulate_loadstore.o +common-objs-y += powerpc.o emulate_loadstore.o obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o obj-$(CONFIG_KVM_BOOK3S_HANDLER) += book3s_exports.o @@ -24,6 +24,7 @@ AFLAGS_booke_interrupts.o := -I$(objtree)/$(obj) kvm-e500-objs := \ $(common-objs-y) \ + emulate.o \ booke.o \ booke_emulate.o \ booke_interrupts.o \ @@ -35,6 +36,7 @@ kvm-objs-$(CONFIG_KVM_E500V2) := $(kvm-e500-objs) kvm-e500mc-objs := \ $(common-objs-y) \ + emulate.o \ booke.o \ booke_emulate.o \ bookehv_interrupts.o \ @@ -61,9 +63,6 @@ kvm-pr-y := \ book3s_32_mmu.o ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE -kvm-book3s_64-module-objs := \ - $(KVM)/coalesced_mmio.o - kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \ book3s_rmhandlers.o endif @@ -78,6 +77,7 @@ kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \ ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \ + book3s_hv_hmi.o \ book3s_hv_rmhandlers.o \ book3s_hv_rm_mmu.o \ book3s_hv_ras.o \ @@ -88,11 +88,8 @@ endif kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \ book3s_xics.o -kvm-book3s_64-module-objs += \ - $(KVM)/kvm_main.o \ - $(KVM)/eventfd.o \ - powerpc.o \ - emulate_loadstore.o \ +kvm-book3s_64-module-objs := \ + $(common-objs-y) \ book3s.o \ book3s_64_vio.o \ book3s_rtas.o \ @@ -102,6 +99,7 @@ kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-module-objs) kvm-book3s_32-objs := \ $(common-objs-y) \ + emulate.o \ fpu.o \ book3s_paired_singles.o \ book3s.o \ diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 47018fcbf7d6..b6952dd23152 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -52,8 +52,12 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "dec", VCPU_STAT(dec_exits) }, { "ext_intr", VCPU_STAT(ext_intr_exits) }, { "queue_intr", VCPU_STAT(queue_intr) }, + { "halt_poll_success_ns", VCPU_STAT(halt_poll_success_ns) }, + { "halt_poll_fail_ns", VCPU_STAT(halt_poll_fail_ns) }, + { "halt_wait_ns", VCPU_STAT(halt_wait_ns) }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll), }, { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll), }, + { "halt_successful_wait", VCPU_STAT(halt_successful_wait) }, { "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) }, { "halt_wakeup", VCPU_STAT(halt_wakeup) }, { "pf_storage", VCPU_STAT(pf_storage) }, @@ -64,6 +68,9 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "ld_slow", VCPU_STAT(ld_slow) }, { "st", VCPU_STAT(st) }, { "st_slow", VCPU_STAT(st_slow) }, + { "pthru_all", VCPU_STAT(pthru_all) }, + { "pthru_host", VCPU_STAT(pthru_host) }, + { "pthru_bad_aff", VCPU_STAT(pthru_bad_aff) }, { NULL } }; @@ -592,9 +599,6 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_BESCR: *val = get_reg_val(id, vcpu->arch.bescr); break; - case KVM_REG_PPC_VTB: - *val = get_reg_val(id, vcpu->arch.vtb); - break; case KVM_REG_PPC_IC: *val = get_reg_val(id, vcpu->arch.ic); break; @@ -666,9 +670,6 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_BESCR: vcpu->arch.bescr = set_reg_val(id, *val); break; - case KVM_REG_PPC_VTB: - vcpu->arch.vtb = set_reg_val(id, *val); - break; case KVM_REG_PPC_IC: vcpu->arch.ic = set_reg_val(id, *val); break; diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c index 2afdb9c0937d..8359752b3efc 100644 --- a/arch/powerpc/kvm/book3s_emulate.c +++ b/arch/powerpc/kvm/book3s_emulate.c @@ -498,6 +498,7 @@ int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) case SPRN_MMCR0: case SPRN_MMCR1: case SPRN_MMCR2: + case SPRN_UMMCR2: #endif break; unprivileged: @@ -579,7 +580,7 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val *spr_val = vcpu->arch.spurr; break; case SPRN_VTB: - *spr_val = vcpu->arch.vtb; + *spr_val = to_book3s(vcpu)->vtb; break; case SPRN_IC: *spr_val = vcpu->arch.ic; @@ -640,6 +641,7 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val case SPRN_MMCR0: case SPRN_MMCR1: case SPRN_MMCR2: + case SPRN_UMMCR2: case SPRN_TIR: #endif *spr_val = 0; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 2fd5580c8f6e..3686471be32b 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -53,11 +53,15 @@ #include <asm/smp.h> #include <asm/dbell.h> #include <asm/hmi.h> +#include <asm/pnv-pci.h> #include <linux/gfp.h> #include <linux/vmalloc.h> #include <linux/highmem.h> #include <linux/hugetlb.h> +#include <linux/kvm_irqfd.h> +#include <linux/irqbypass.h> #include <linux/module.h> +#include <linux/compiler.h> #include "book3s.h" @@ -70,6 +74,8 @@ /* Used to indicate that a guest page fault needs to be handled */ #define RESUME_PAGE_FAULT (RESUME_GUEST | RESUME_FLAG_ARCH1) +/* Used to indicate that a guest passthrough interrupt needs to be handled */ +#define RESUME_PASSTHROUGH (RESUME_GUEST | RESUME_FLAG_ARCH2) /* Used as a "null" value for timebase values */ #define TB_NIL (~(u64)0) @@ -89,14 +95,55 @@ static struct kernel_param_ops module_param_ops = { .get = param_get_int, }; +module_param_cb(kvm_irq_bypass, &module_param_ops, &kvm_irq_bypass, + S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(kvm_irq_bypass, "Bypass passthrough interrupt optimization"); + module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core"); #endif +/* Maximum halt poll interval defaults to KVM_HALT_POLL_NS_DEFAULT */ +static unsigned int halt_poll_max_ns = KVM_HALT_POLL_NS_DEFAULT; +module_param(halt_poll_max_ns, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(halt_poll_max_ns, "Maximum halt poll time in ns"); + +/* Factor by which the vcore halt poll interval is grown, default is to double + */ +static unsigned int halt_poll_ns_grow = 2; +module_param(halt_poll_ns_grow, int, S_IRUGO); +MODULE_PARM_DESC(halt_poll_ns_grow, "Factor halt poll time is grown by"); + +/* Factor by which the vcore halt poll interval is shrunk, default is to reset + */ +static unsigned int halt_poll_ns_shrink; +module_param(halt_poll_ns_shrink, int, S_IRUGO); +MODULE_PARM_DESC(halt_poll_ns_shrink, "Factor halt poll time is shrunk by"); + static void kvmppc_end_cede(struct kvm_vcpu *vcpu); static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); +static inline struct kvm_vcpu *next_runnable_thread(struct kvmppc_vcore *vc, + int *ip) +{ + int i = *ip; + struct kvm_vcpu *vcpu; + + while (++i < MAX_SMT_THREADS) { + vcpu = READ_ONCE(vc->runnable_threads[i]); + if (vcpu) { + *ip = i; + return vcpu; + } + } + return NULL; +} + +/* Used to traverse the list of runnable threads for a given vcore */ +#define for_each_runnable_thread(i, vcpu, vc) \ + for (i = -1; (vcpu = next_runnable_thread(vc, &i)); ) + static bool kvmppc_ipi_thread(int cpu) { /* On POWER8 for IPIs to threads in the same core, use msgsnd */ @@ -991,6 +1038,9 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, kvmppc_core_queue_program(vcpu, SRR1_PROGILL); r = RESUME_GUEST; break; + case BOOK3S_INTERRUPT_HV_RM_HARD: + r = RESUME_PASSTHROUGH; + break; default: kvmppc_dump_regs(vcpu); printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n", @@ -1149,6 +1199,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_DPDES: *val = get_reg_val(id, vcpu->arch.vcore->dpdes); break; + case KVM_REG_PPC_VTB: + *val = get_reg_val(id, vcpu->arch.vcore->vtb); + break; case KVM_REG_PPC_DAWR: *val = get_reg_val(id, vcpu->arch.dawr); break; @@ -1341,6 +1394,9 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_DPDES: vcpu->arch.vcore->dpdes = set_reg_val(id, *val); break; + case KVM_REG_PPC_VTB: + vcpu->arch.vcore->vtb = set_reg_val(id, *val); + break; case KVM_REG_PPC_DAWR: vcpu->arch.dawr = set_reg_val(id, *val); break; @@ -1493,7 +1549,6 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core) if (vcore == NULL) return NULL; - INIT_LIST_HEAD(&vcore->runnable_threads); spin_lock_init(&vcore->lock); spin_lock_init(&vcore->stoltb_lock); init_swait_queue_head(&vcore->wq); @@ -1802,7 +1857,7 @@ static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; spin_unlock_irq(&vcpu->arch.tbacct_lock); --vc->n_runnable; - list_del(&vcpu->arch.run_list); + WRITE_ONCE(vc->runnable_threads[vcpu->arch.ptid], NULL); } static int kvmppc_grab_hwthread(int cpu) @@ -2048,66 +2103,6 @@ static void init_master_vcore(struct kvmppc_vcore *vc) vc->conferring_threads = 0; } -/* - * See if the existing subcores can be split into 3 (or fewer) subcores - * of at most two threads each, so we can fit in another vcore. This - * assumes there are at most two subcores and at most 6 threads in total. - */ -static bool can_split_piggybacked_subcores(struct core_info *cip) -{ - int sub, new_sub; - int large_sub = -1; - int thr; - int n_subcores = cip->n_subcores; - struct kvmppc_vcore *vc, *vcnext; - struct kvmppc_vcore *master_vc = NULL; - - for (sub = 0; sub < cip->n_subcores; ++sub) { - if (cip->subcore_threads[sub] <= 2) - continue; - if (large_sub >= 0) - return false; - large_sub = sub; - vc = list_first_entry(&cip->vcs[sub], struct kvmppc_vcore, - preempt_list); - if (vc->num_threads > 2) - return false; - n_subcores += (cip->subcore_threads[sub] - 1) >> 1; - } - if (large_sub < 0 || !subcore_config_ok(n_subcores + 1, 2)) - return false; - - /* - * Seems feasible, so go through and move vcores to new subcores. - * Note that when we have two or more vcores in one subcore, - * all those vcores must have only one thread each. - */ - new_sub = cip->n_subcores; - thr = 0; - sub = large_sub; - list_for_each_entry_safe(vc, vcnext, &cip->vcs[sub], preempt_list) { - if (thr >= 2) { - list_del(&vc->preempt_list); - list_add_tail(&vc->preempt_list, &cip->vcs[new_sub]); - /* vc->num_threads must be 1 */ - if (++cip->subcore_threads[new_sub] == 1) { - cip->subcore_vm[new_sub] = vc->kvm; - init_master_vcore(vc); - master_vc = vc; - ++cip->n_subcores; - } else { - vc->master_vcore = master_vc; - ++new_sub; - } - } - thr += vc->num_threads; - } - cip->subcore_threads[large_sub] = 2; - cip->max_subcore_threads = 2; - - return true; -} - static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip) { int n_threads = vc->num_threads; @@ -2118,23 +2113,9 @@ static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip) if (n_threads < cip->max_subcore_threads) n_threads = cip->max_subcore_threads; - if (subcore_config_ok(cip->n_subcores + 1, n_threads)) { - cip->max_subcore_threads = n_threads; - } else if (cip->n_subcores <= 2 && cip->total_threads <= 6 && - vc->num_threads <= 2) { - /* - * We may be able to fit another subcore in by - * splitting an existing subcore with 3 or 4 - * threads into two 2-thread subcores, or one - * with 5 or 6 threads into three subcores. - * We can only do this if those subcores have - * piggybacked virtual cores. - */ - if (!can_split_piggybacked_subcores(cip)) - return false; - } else { + if (!subcore_config_ok(cip->n_subcores + 1, n_threads)) return false; - } + cip->max_subcore_threads = n_threads; sub = cip->n_subcores; ++cip->n_subcores; @@ -2148,43 +2129,6 @@ static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip) return true; } -static bool can_piggyback_subcore(struct kvmppc_vcore *pvc, - struct core_info *cip, int sub) -{ - struct kvmppc_vcore *vc; - int n_thr; - - vc = list_first_entry(&cip->vcs[sub], struct kvmppc_vcore, - preempt_list); - - /* require same VM and same per-core reg values */ - if (pvc->kvm != vc->kvm || - pvc->tb_offset != vc->tb_offset || - pvc->pcr != vc->pcr || - pvc->lpcr != vc->lpcr) - return false; - - /* P8 guest with > 1 thread per core would see wrong TIR value */ - if (cpu_has_feature(CPU_FTR_ARCH_207S) && - (vc->num_threads > 1 || pvc->num_threads > 1)) - return false; - - n_thr = cip->subcore_threads[sub] + pvc->num_threads; - if (n_thr > cip->max_subcore_threads) { - if (!subcore_config_ok(cip->n_subcores, n_thr)) - return false; - cip->max_subcore_threads = n_thr; - } - - cip->total_threads += pvc->num_threads; - cip->subcore_threads[sub] = n_thr; - pvc->master_vcore = vc; - list_del(&pvc->preempt_list); - list_add_tail(&pvc->preempt_list, &cip->vcs[sub]); - - return true; -} - /* * Work out whether it is possible to piggyback the execution of * vcore *pvc onto the execution of the other vcores described in *cip. @@ -2192,27 +2136,18 @@ static bool can_piggyback_subcore(struct kvmppc_vcore *pvc, static bool can_piggyback(struct kvmppc_vcore *pvc, struct core_info *cip, int target_threads) { - int sub; - if (cip->total_threads + pvc->num_threads > target_threads) return false; - for (sub = 0; sub < cip->n_subcores; ++sub) - if (cip->subcore_threads[sub] && - can_piggyback_subcore(pvc, cip, sub)) - return true; - - if (can_dynamic_split(pvc, cip)) - return true; - return false; + return can_dynamic_split(pvc, cip); } static void prepare_threads(struct kvmppc_vcore *vc) { - struct kvm_vcpu *vcpu, *vnext; + int i; + struct kvm_vcpu *vcpu; - list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads, - arch.run_list) { + for_each_runnable_thread(i, vcpu, vc) { if (signal_pending(vcpu->arch.run_task)) vcpu->arch.ret = -EINTR; else if (vcpu->arch.vpa.update_pending || @@ -2259,15 +2194,14 @@ static void collect_piggybacks(struct core_info *cip, int target_threads) static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) { - int still_running = 0; + int still_running = 0, i; u64 now; long ret; - struct kvm_vcpu *vcpu, *vnext; + struct kvm_vcpu *vcpu; spin_lock(&vc->lock); now = get_tb(); - list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads, - arch.run_list) { + for_each_runnable_thread(i, vcpu, vc) { /* cancel pending dec exception if dec is positive */ if (now < vcpu->arch.dec_expires && kvmppc_core_pending_dec(vcpu)) @@ -2307,8 +2241,8 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) } if (vc->n_runnable > 0 && vc->runner == NULL) { /* make sure there's a candidate runner awake */ - vcpu = list_first_entry(&vc->runnable_threads, - struct kvm_vcpu, arch.run_list); + i = -1; + vcpu = next_runnable_thread(vc, &i); wake_up(&vcpu->arch.cpu_run); } } @@ -2361,7 +2295,7 @@ static inline void kvmppc_set_host_core(int cpu) */ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) { - struct kvm_vcpu *vcpu, *vnext; + struct kvm_vcpu *vcpu; int i; int srcu_idx; struct core_info core_info; @@ -2397,8 +2331,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) */ if ((threads_per_core > 1) && ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) { - list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads, - arch.run_list) { + for_each_runnable_thread(i, vcpu, vc) { vcpu->arch.ret = -EBUSY; kvmppc_remove_runnable(vc, vcpu); wake_up(&vcpu->arch.cpu_run); @@ -2477,8 +2410,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) active |= 1 << thr; list_for_each_entry(pvc, &core_info.vcs[sub], preempt_list) { pvc->pcpu = pcpu + thr; - list_for_each_entry(vcpu, &pvc->runnable_threads, - arch.run_list) { + for_each_runnable_thread(i, vcpu, pvc) { kvmppc_start_thread(vcpu, pvc); kvmppc_create_dtl_entry(vcpu, pvc); trace_kvm_guest_enter(vcpu); @@ -2604,34 +2536,92 @@ static void kvmppc_wait_for_exec(struct kvmppc_vcore *vc, finish_wait(&vcpu->arch.cpu_run, &wait); } +static void grow_halt_poll_ns(struct kvmppc_vcore *vc) +{ + /* 10us base */ + if (vc->halt_poll_ns == 0 && halt_poll_ns_grow) + vc->halt_poll_ns = 10000; + else + vc->halt_poll_ns *= halt_poll_ns_grow; + + if (vc->halt_poll_ns > halt_poll_max_ns) + vc->halt_poll_ns = halt_poll_max_ns; +} + +static void shrink_halt_poll_ns(struct kvmppc_vcore *vc) +{ + if (halt_poll_ns_shrink == 0) + vc->halt_poll_ns = 0; + else + vc->halt_poll_ns /= halt_poll_ns_shrink; +} + +/* Check to see if any of the runnable vcpus on the vcore have pending + * exceptions or are no longer ceded + */ +static int kvmppc_vcore_check_block(struct kvmppc_vcore *vc) +{ + struct kvm_vcpu *vcpu; + int i; + + for_each_runnable_thread(i, vcpu, vc) { + if (vcpu->arch.pending_exceptions || !vcpu->arch.ceded) + return 1; + } + + return 0; +} + /* * All the vcpus in this vcore are idle, so wait for a decrementer * or external interrupt to one of the vcpus. vc->lock is held. */ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) { - struct kvm_vcpu *vcpu; + ktime_t cur, start_poll, start_wait; int do_sleep = 1; + u64 block_ns; DECLARE_SWAITQUEUE(wait); - prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE); + /* Poll for pending exceptions and ceded state */ + cur = start_poll = ktime_get(); + if (vc->halt_poll_ns) { + ktime_t stop = ktime_add_ns(start_poll, vc->halt_poll_ns); + ++vc->runner->stat.halt_attempted_poll; - /* - * Check one last time for pending exceptions and ceded state after - * we put ourselves on the wait queue - */ - list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { - if (vcpu->arch.pending_exceptions || !vcpu->arch.ceded) { - do_sleep = 0; - break; + vc->vcore_state = VCORE_POLLING; + spin_unlock(&vc->lock); + + do { + if (kvmppc_vcore_check_block(vc)) { + do_sleep = 0; + break; + } + cur = ktime_get(); + } while (single_task_running() && ktime_before(cur, stop)); + + spin_lock(&vc->lock); + vc->vcore_state = VCORE_INACTIVE; + + if (!do_sleep) { + ++vc->runner->stat.halt_successful_poll; + goto out; } } - if (!do_sleep) { + prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE); + + if (kvmppc_vcore_check_block(vc)) { finish_swait(&vc->wq, &wait); - return; + do_sleep = 0; + /* If we polled, count this as a successful poll */ + if (vc->halt_poll_ns) + ++vc->runner->stat.halt_successful_poll; + goto out; } + start_wait = ktime_get(); + vc->vcore_state = VCORE_SLEEPING; trace_kvmppc_vcore_blocked(vc, 0); spin_unlock(&vc->lock); @@ -2640,13 +2630,52 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; trace_kvmppc_vcore_blocked(vc, 1); + ++vc->runner->stat.halt_successful_wait; + + cur = ktime_get(); + +out: + block_ns = ktime_to_ns(cur) - ktime_to_ns(start_poll); + + /* Attribute wait time */ + if (do_sleep) { + vc->runner->stat.halt_wait_ns += + ktime_to_ns(cur) - ktime_to_ns(start_wait); + /* Attribute failed poll time */ + if (vc->halt_poll_ns) + vc->runner->stat.halt_poll_fail_ns += + ktime_to_ns(start_wait) - + ktime_to_ns(start_poll); + } else { + /* Attribute successful poll time */ + if (vc->halt_poll_ns) + vc->runner->stat.halt_poll_success_ns += + ktime_to_ns(cur) - + ktime_to_ns(start_poll); + } + + /* Adjust poll time */ + if (halt_poll_max_ns) { + if (block_ns <= vc->halt_poll_ns) + ; + /* We slept and blocked for longer than the max halt time */ + else if (vc->halt_poll_ns && block_ns > halt_poll_max_ns) + shrink_halt_poll_ns(vc); + /* We slept and our poll time is too small */ + else if (vc->halt_poll_ns < halt_poll_max_ns && + block_ns < halt_poll_max_ns) + grow_halt_poll_ns(vc); + } else + vc->halt_poll_ns = 0; + + trace_kvmppc_vcore_wakeup(do_sleep, block_ns); } static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) { - int n_ceded; + int n_ceded, i; struct kvmppc_vcore *vc; - struct kvm_vcpu *v, *vn; + struct kvm_vcpu *v; trace_kvmppc_run_vcpu_enter(vcpu); @@ -2666,7 +2695,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb()); vcpu->arch.state = KVMPPC_VCPU_RUNNABLE; vcpu->arch.busy_preempt = TB_NIL; - list_add_tail(&vcpu->arch.run_list, &vc->runnable_threads); + WRITE_ONCE(vc->runnable_threads[vcpu->arch.ptid], vcpu); ++vc->n_runnable; /* @@ -2706,8 +2735,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_wait_for_exec(vc, vcpu, TASK_INTERRUPTIBLE); continue; } - list_for_each_entry_safe(v, vn, &vc->runnable_threads, - arch.run_list) { + for_each_runnable_thread(i, v, vc) { kvmppc_core_prepare_to_enter(v); if (signal_pending(v->arch.run_task)) { kvmppc_remove_runnable(vc, v); @@ -2720,7 +2748,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) if (!vc->n_runnable || vcpu->arch.state != KVMPPC_VCPU_RUNNABLE) break; n_ceded = 0; - list_for_each_entry(v, &vc->runnable_threads, arch.run_list) { + for_each_runnable_thread(i, v, vc) { if (!v->arch.pending_exceptions) n_ceded += v->arch.ceded; else @@ -2759,8 +2787,8 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) if (vc->n_runnable && vc->vcore_state == VCORE_INACTIVE) { /* Wake up some vcpu to run the core */ - v = list_first_entry(&vc->runnable_threads, - struct kvm_vcpu, arch.run_list); + i = -1; + v = next_runnable_thread(vc, &i); wake_up(&v->arch.cpu_run); } @@ -2818,7 +2846,8 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) r = kvmppc_book3s_hv_page_fault(run, vcpu, vcpu->arch.fault_dar, vcpu->arch.fault_dsisr); srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); - } + } else if (r == RESUME_PASSTHROUGH) + r = kvmppc_xics_rm_complete(vcpu, 0); } while (is_kvmppc_resume_guest(r)); out: @@ -3247,6 +3276,8 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) kvmppc_free_vcores(kvm); kvmppc_free_hpt(kvm); + + kvmppc_free_pimap(kvm); } /* We don't need to emulate any privileged instructions or dcbz */ @@ -3282,6 +3313,184 @@ static int kvmppc_core_check_processor_compat_hv(void) return 0; } +#ifdef CONFIG_KVM_XICS + +void kvmppc_free_pimap(struct kvm *kvm) +{ + kfree(kvm->arch.pimap); +} + +static struct kvmppc_passthru_irqmap *kvmppc_alloc_pimap(void) +{ + return kzalloc(sizeof(struct kvmppc_passthru_irqmap), GFP_KERNEL); +} + +static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) +{ + struct irq_desc *desc; + struct kvmppc_irq_map *irq_map; + struct kvmppc_passthru_irqmap *pimap; + struct irq_chip *chip; + int i; + + if (!kvm_irq_bypass) + return 1; + + desc = irq_to_desc(host_irq); + if (!desc) + return -EIO; + + mutex_lock(&kvm->lock); + + pimap = kvm->arch.pimap; + if (pimap == NULL) { + /* First call, allocate structure to hold IRQ map */ + pimap = kvmppc_alloc_pimap(); + if (pimap == NULL) { + mutex_unlock(&kvm->lock); + return -ENOMEM; + } + kvm->arch.pimap = pimap; + } + + /* + * For now, we only support interrupts for which the EOI operation + * is an OPAL call followed by a write to XIRR, since that's + * what our real-mode EOI code does. + */ + chip = irq_data_get_irq_chip(&desc->irq_data); + if (!chip || !is_pnv_opal_msi(chip)) { + pr_warn("kvmppc_set_passthru_irq_hv: Could not assign IRQ map for (%d,%d)\n", + host_irq, guest_gsi); + mutex_unlock(&kvm->lock); + return -ENOENT; + } + + /* + * See if we already have an entry for this guest IRQ number. + * If it's mapped to a hardware IRQ number, that's an error, + * otherwise re-use this entry. + */ + for (i = 0; i < pimap->n_mapped; i++) { + if (guest_gsi == pimap->mapped[i].v_hwirq) { + if (pimap->mapped[i].r_hwirq) { + mutex_unlock(&kvm->lock); + return -EINVAL; + } + break; + } + } + + if (i == KVMPPC_PIRQ_MAPPED) { + mutex_unlock(&kvm->lock); + return -EAGAIN; /* table is full */ + } + + irq_map = &pimap->mapped[i]; + + irq_map->v_hwirq = guest_gsi; + irq_map->desc = desc; + + /* + * Order the above two stores before the next to serialize with + * the KVM real mode handler. + */ + smp_wmb(); + irq_map->r_hwirq = desc->irq_data.hwirq; + + if (i == pimap->n_mapped) + pimap->n_mapped++; + + kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq); + + mutex_unlock(&kvm->lock); + + return 0; +} + +static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) +{ + struct irq_desc *desc; + struct kvmppc_passthru_irqmap *pimap; + int i; + + if (!kvm_irq_bypass) + return 0; + + desc = irq_to_desc(host_irq); + if (!desc) + return -EIO; + + mutex_lock(&kvm->lock); + + if (kvm->arch.pimap == NULL) { + mutex_unlock(&kvm->lock); + return 0; + } + pimap = kvm->arch.pimap; + + for (i = 0; i < pimap->n_mapped; i++) { + if (guest_gsi == pimap->mapped[i].v_hwirq) + break; + } + + if (i == pimap->n_mapped) { + mutex_unlock(&kvm->lock); + return -ENODEV; + } + + kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq); + + /* invalidate the entry */ + pimap->mapped[i].r_hwirq = 0; + + /* + * We don't free this structure even when the count goes to + * zero. The structure is freed when we destroy the VM. + */ + + mutex_unlock(&kvm->lock); + return 0; +} + +static int kvmppc_irq_bypass_add_producer_hv(struct irq_bypass_consumer *cons, + struct irq_bypass_producer *prod) +{ + int ret = 0; + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + + irqfd->producer = prod; + + ret = kvmppc_set_passthru_irq(irqfd->kvm, prod->irq, irqfd->gsi); + if (ret) + pr_info("kvmppc_set_passthru_irq (irq %d, gsi %d) fails: %d\n", + prod->irq, irqfd->gsi, ret); + + return ret; +} + +static void kvmppc_irq_bypass_del_producer_hv(struct irq_bypass_consumer *cons, + struct irq_bypass_producer *prod) +{ + int ret; + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + + irqfd->producer = NULL; + + /* + * When producer of consumer is unregistered, we change back to + * default external interrupt handling mode - KVM real mode + * will switch back to host. + */ + ret = kvmppc_clr_passthru_irq(irqfd->kvm, prod->irq, irqfd->gsi); + if (ret) + pr_warn("kvmppc_clr_passthru_irq (irq %d, gsi %d) fails: %d\n", + prod->irq, irqfd->gsi, ret); +} +#endif + static long kvm_arch_vm_ioctl_hv(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -3400,6 +3609,10 @@ static struct kvmppc_ops kvm_ops_hv = { .fast_vcpu_kick = kvmppc_fast_vcpu_kick_hv, .arch_vm_ioctl = kvm_arch_vm_ioctl_hv, .hcall_implemented = kvmppc_hcall_impl_hv, +#ifdef CONFIG_KVM_XICS + .irq_bypass_add_producer = kvmppc_irq_bypass_add_producer_hv, + .irq_bypass_del_producer = kvmppc_irq_bypass_del_producer_hv, +#endif }; static int kvm_init_subcore_bitmap(void) diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 5f0380db3eab..0c84d6bc8356 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -25,6 +25,7 @@ #include <asm/xics.h> #include <asm/dbell.h> #include <asm/cputhreads.h> +#include <asm/io.h> #define KVM_CMA_CHUNK_ORDER 18 @@ -286,3 +287,158 @@ void kvmhv_commence_exit(int trap) struct kvmppc_host_rm_ops *kvmppc_host_rm_ops_hv; EXPORT_SYMBOL_GPL(kvmppc_host_rm_ops_hv); + +#ifdef CONFIG_KVM_XICS +static struct kvmppc_irq_map *get_irqmap(struct kvmppc_passthru_irqmap *pimap, + u32 xisr) +{ + int i; + + /* + * We access the mapped array here without a lock. That + * is safe because we never reduce the number of entries + * in the array and we never change the v_hwirq field of + * an entry once it is set. + * + * We have also carefully ordered the stores in the writer + * and the loads here in the reader, so that if we find a matching + * hwirq here, the associated GSI and irq_desc fields are valid. + */ + for (i = 0; i < pimap->n_mapped; i++) { + if (xisr == pimap->mapped[i].r_hwirq) { + /* + * Order subsequent reads in the caller to serialize + * with the writer. + */ + smp_rmb(); + return &pimap->mapped[i]; + } + } + return NULL; +} + +/* + * If we have an interrupt that's not an IPI, check if we have a + * passthrough adapter and if so, check if this external interrupt + * is for the adapter. + * We will attempt to deliver the IRQ directly to the target VCPU's + * ICP, the virtual ICP (based on affinity - the xive value in ICS). + * + * If the delivery fails or if this is not for a passthrough adapter, + * return to the host to handle this interrupt. We earlier + * saved a copy of the XIRR in the PACA, it will be picked up by + * the host ICP driver. + */ +static int kvmppc_check_passthru(u32 xisr, __be32 xirr) +{ + struct kvmppc_passthru_irqmap *pimap; + struct kvmppc_irq_map *irq_map; + struct kvm_vcpu *vcpu; + + vcpu = local_paca->kvm_hstate.kvm_vcpu; + if (!vcpu) + return 1; + pimap = kvmppc_get_passthru_irqmap(vcpu->kvm); + if (!pimap) + return 1; + irq_map = get_irqmap(pimap, xisr); + if (!irq_map) + return 1; + + /* We're handling this interrupt, generic code doesn't need to */ + local_paca->kvm_hstate.saved_xirr = 0; + + return kvmppc_deliver_irq_passthru(vcpu, xirr, irq_map, pimap); +} + +#else +static inline int kvmppc_check_passthru(u32 xisr, __be32 xirr) +{ + return 1; +} +#endif + +/* + * Determine what sort of external interrupt is pending (if any). + * Returns: + * 0 if no interrupt is pending + * 1 if an interrupt is pending that needs to be handled by the host + * 2 Passthrough that needs completion in the host + * -1 if there was a guest wakeup IPI (which has now been cleared) + * -2 if there is PCI passthrough external interrupt that was handled + */ + +long kvmppc_read_intr(void) +{ + unsigned long xics_phys; + u32 h_xirr; + __be32 xirr; + u32 xisr; + u8 host_ipi; + + /* see if a host IPI is pending */ + host_ipi = local_paca->kvm_hstate.host_ipi; + if (host_ipi) + return 1; + + /* Now read the interrupt from the ICP */ + xics_phys = local_paca->kvm_hstate.xics_phys; + if (unlikely(!xics_phys)) + return 1; + + /* + * Save XIRR for later. Since we get control in reverse endian + * on LE systems, save it byte reversed and fetch it back in + * host endian. Note that xirr is the value read from the + * XIRR register, while h_xirr is the host endian version. + */ + xirr = _lwzcix(xics_phys + XICS_XIRR); + h_xirr = be32_to_cpu(xirr); + local_paca->kvm_hstate.saved_xirr = h_xirr; + xisr = h_xirr & 0xffffff; + /* + * Ensure that the store/load complete to guarantee all side + * effects of loading from XIRR has completed + */ + smp_mb(); + + /* if nothing pending in the ICP */ + if (!xisr) + return 0; + + /* We found something in the ICP... + * + * If it is an IPI, clear the MFRR and EOI it. + */ + if (xisr == XICS_IPI) { + _stbcix(xics_phys + XICS_MFRR, 0xff); + _stwcix(xics_phys + XICS_XIRR, xirr); + /* + * Need to ensure side effects of above stores + * complete before proceeding. + */ + smp_mb(); + + /* + * We need to re-check host IPI now in case it got set in the + * meantime. If it's clear, we bounce the interrupt to the + * guest + */ + host_ipi = local_paca->kvm_hstate.host_ipi; + if (unlikely(host_ipi != 0)) { + /* We raced with the host, + * we need to resend that IPI, bummer + */ + _stbcix(xics_phys + XICS_MFRR, IPI_PRIORITY); + /* Let side effects complete */ + smp_mb(); + return 1; + } + + /* OK, it's an IPI for us */ + local_paca->kvm_hstate.saved_xirr = 0; + return -1; + } + + return kvmppc_check_passthru(xisr, xirr); +} diff --git a/arch/powerpc/kernel/hmi.c b/arch/powerpc/kvm/book3s_hv_hmi.c index e3f738eb1cac..e3f738eb1cac 100644 --- a/arch/powerpc/kernel/hmi.c +++ b/arch/powerpc/kvm/book3s_hv_hmi.c diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index 980d8a6f7284..82ff5de8b1e7 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -10,6 +10,7 @@ #include <linux/kernel.h> #include <linux/kvm_host.h> #include <linux/err.h> +#include <linux/kernel_stat.h> #include <asm/kvm_book3s.h> #include <asm/kvm_ppc.h> @@ -18,7 +19,10 @@ #include <asm/debug.h> #include <asm/synch.h> #include <asm/cputhreads.h> +#include <asm/pgtable.h> #include <asm/ppc-opcode.h> +#include <asm/pnv-pci.h> +#include <asm/opal.h> #include "book3s_xics.h" @@ -26,9 +30,12 @@ int h_ipi_redirect = 1; EXPORT_SYMBOL(h_ipi_redirect); +int kvm_irq_bypass = 1; +EXPORT_SYMBOL(kvm_irq_bypass); static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, u32 new_irq); +static int xics_opal_rm_set_server(unsigned int hw_irq, int server_cpu); /* -- ICS routines -- */ static void ics_rm_check_resend(struct kvmppc_xics *xics, @@ -708,10 +715,123 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) icp->rm_action |= XICS_RM_NOTIFY_EOI; icp->rm_eoied_irq = irq; } + + if (state->host_irq) { + ++vcpu->stat.pthru_all; + if (state->intr_cpu != -1) { + int pcpu = raw_smp_processor_id(); + + pcpu = cpu_first_thread_sibling(pcpu); + ++vcpu->stat.pthru_host; + if (state->intr_cpu != pcpu) { + ++vcpu->stat.pthru_bad_aff; + xics_opal_rm_set_server(state->host_irq, pcpu); + } + state->intr_cpu = -1; + } + } bail: return check_too_hard(xics, icp); } +unsigned long eoi_rc; + +static void icp_eoi(struct irq_chip *c, u32 hwirq, u32 xirr) +{ + unsigned long xics_phys; + int64_t rc; + + rc = pnv_opal_pci_msi_eoi(c, hwirq); + + if (rc) + eoi_rc = rc; + + iosync(); + + /* EOI it */ + xics_phys = local_paca->kvm_hstate.xics_phys; + _stwcix(xics_phys + XICS_XIRR, xirr); +} + +static int xics_opal_rm_set_server(unsigned int hw_irq, int server_cpu) +{ + unsigned int mangle_cpu = get_hard_smp_processor_id(server_cpu) << 2; + + return opal_rm_set_xive(hw_irq, mangle_cpu, DEFAULT_PRIORITY); +} + +/* + * Increment a per-CPU 32-bit unsigned integer variable. + * Safe to call in real-mode. Handles vmalloc'ed addresses + * + * ToDo: Make this work for any integral type + */ + +static inline void this_cpu_inc_rm(unsigned int __percpu *addr) +{ + unsigned long l; + unsigned int *raddr; + int cpu = smp_processor_id(); + + raddr = per_cpu_ptr(addr, cpu); + l = (unsigned long)raddr; + + if (REGION_ID(l) == VMALLOC_REGION_ID) { + l = vmalloc_to_phys(raddr); + raddr = (unsigned int *)l; + } + ++*raddr; +} + +/* + * We don't try to update the flags in the irq_desc 'istate' field in + * here as would happen in the normal IRQ handling path for several reasons: + * - state flags represent internal IRQ state and are not expected to be + * updated outside the IRQ subsystem + * - more importantly, these are useful for edge triggered interrupts, + * IRQ probing, etc., but we are only handling MSI/MSIx interrupts here + * and these states shouldn't apply to us. + * + * However, we do update irq_stats - we somewhat duplicate the code in + * kstat_incr_irqs_this_cpu() for this since this function is defined + * in irq/internal.h which we don't want to include here. + * The only difference is that desc->kstat_irqs is an allocated per CPU + * variable and could have been vmalloc'ed, so we can't directly + * call __this_cpu_inc() on it. The kstat structure is a static + * per CPU variable and it should be accessible by real-mode KVM. + * + */ +static void kvmppc_rm_handle_irq_desc(struct irq_desc *desc) +{ + this_cpu_inc_rm(desc->kstat_irqs); + __this_cpu_inc(kstat.irqs_sum); +} + +long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu, + u32 xirr, + struct kvmppc_irq_map *irq_map, + struct kvmppc_passthru_irqmap *pimap) +{ + struct kvmppc_xics *xics; + struct kvmppc_icp *icp; + u32 irq; + + irq = irq_map->v_hwirq; + xics = vcpu->kvm->arch.xics; + icp = vcpu->arch.icp; + + kvmppc_rm_handle_irq_desc(irq_map->desc); + icp_rm_deliver_irq(xics, icp, irq); + + /* EOI the interrupt */ + icp_eoi(irq_desc_get_chip(irq_map->desc), irq_map->r_hwirq, xirr); + + if (check_too_hard(xics, icp) == H_TOO_HARD) + return 2; + else + return -2; +} + /* --- Non-real mode XICS-related built-in routines --- */ /** diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 975655573844..c3c1d1bcfc67 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -221,6 +221,13 @@ kvmppc_primary_no_guest: li r3, 0 /* Don't wake on privileged (OS) doorbell */ b kvm_do_nap +/* + * kvm_novcpu_wakeup + * Entered from kvm_start_guest if kvm_hstate.napping is set + * to NAPPING_NOVCPU + * r2 = kernel TOC + * r13 = paca + */ kvm_novcpu_wakeup: ld r1, HSTATE_HOST_R1(r13) ld r5, HSTATE_KVM_VCORE(r13) @@ -230,6 +237,13 @@ kvm_novcpu_wakeup: /* check the wake reason */ bl kvmppc_check_wake_reason + /* + * Restore volatile registers since we could have called + * a C routine in kvmppc_check_wake_reason. + * r5 = VCORE + */ + ld r5, HSTATE_KVM_VCORE(r13) + /* see if any other thread is already exiting */ lwz r0, VCORE_ENTRY_EXIT(r5) cmpwi r0, 0x100 @@ -322,6 +336,11 @@ kvm_start_guest: /* Check the wake reason in SRR1 to see why we got here */ bl kvmppc_check_wake_reason + /* + * kvmppc_check_wake_reason could invoke a C routine, but we + * have no volatile registers to restore when we return. + */ + cmpdi r3, 0 bge kvm_no_guest @@ -625,9 +644,11 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S) 38: BEGIN_FTR_SECTION - /* DPDES is shared between threads */ + /* DPDES and VTB are shared between threads */ ld r8, VCORE_DPDES(r5) + ld r7, VCORE_VTB(r5) mtspr SPRN_DPDES, r8 + mtspr SPRN_VTB, r7 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* Mark the subcore state as inside guest */ @@ -787,10 +808,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) mtspr SPRN_CIABR, r7 mtspr SPRN_TAR, r8 ld r5, VCPU_IC(r4) - ld r6, VCPU_VTB(r4) - mtspr SPRN_IC, r5 - mtspr SPRN_VTB, r6 ld r8, VCPU_EBBHR(r4) + mtspr SPRN_IC, r5 mtspr SPRN_EBBHR, r8 ld r5, VCPU_EBBRR(r4) ld r6, VCPU_BESCR(r4) @@ -881,6 +900,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) cmpwi r3, 512 /* 1 microsecond */ blt hdec_soon +deliver_guest_interrupt: ld r6, VCPU_CTR(r4) ld r7, VCPU_XER(r4) @@ -895,7 +915,6 @@ kvmppc_cede_reentry: /* r4 = vcpu, r13 = paca */ mtspr SPRN_SRR0, r6 mtspr SPRN_SRR1, r7 -deliver_guest_interrupt: /* r11 = vcpu->arch.msr & ~MSR_HV */ rldicl r11, r11, 63 - MSR_HV_LG, 1 rotldi r11, r11, 1 + MSR_HV_LG @@ -1155,10 +1174,54 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) * set, we know the host wants us out so let's do it now */ bl kvmppc_read_intr + + /* + * Restore the active volatile registers after returning from + * a C function. + */ + ld r9, HSTATE_KVM_VCPU(r13) + li r12, BOOK3S_INTERRUPT_EXTERNAL + + /* + * kvmppc_read_intr return codes: + * + * Exit to host (r3 > 0) + * 1 An interrupt is pending that needs to be handled by the host + * Exit guest and return to host by branching to guest_exit_cont + * + * 2 Passthrough that needs completion in the host + * Exit guest and return to host by branching to guest_exit_cont + * However, we also set r12 to BOOK3S_INTERRUPT_HV_RM_HARD + * to indicate to the host to complete handling the interrupt + * + * Before returning to guest, we check if any CPU is heading out + * to the host and if so, we head out also. If no CPUs are heading + * check return values <= 0. + * + * Return to guest (r3 <= 0) + * 0 No external interrupt is pending + * -1 A guest wakeup IPI (which has now been cleared) + * In either case, we return to guest to deliver any pending + * guest interrupts. + * + * -2 A PCI passthrough external interrupt was handled + * (interrupt was delivered directly to guest) + * Return to guest to deliver any pending guest interrupts. + */ + + cmpdi r3, 1 + ble 1f + + /* Return code = 2 */ + li r12, BOOK3S_INTERRUPT_HV_RM_HARD + stw r12, VCPU_TRAP(r9) + b guest_exit_cont + +1: /* Return code <= 1 */ cmpdi r3, 0 bgt guest_exit_cont - /* Check if any CPU is heading out to the host, if so head out too */ + /* Return code <= 0 */ 4: ld r5, HSTATE_KVM_VCORE(r13) lwz r0, VCORE_ENTRY_EXIT(r5) cmpwi r0, 0x100 @@ -1271,10 +1334,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) stw r6, VCPU_PSPB(r9) std r7, VCPU_FSCR(r9) mfspr r5, SPRN_IC - mfspr r6, SPRN_VTB mfspr r7, SPRN_TAR std r5, VCPU_IC(r9) - std r6, VCPU_VTB(r9) std r7, VCPU_TAR(r9) mfspr r8, SPRN_EBBHR std r8, VCPU_EBBHR(r9) @@ -1501,9 +1562,11 @@ kvmhv_switch_to_host: isync BEGIN_FTR_SECTION - /* DPDES is shared between threads */ + /* DPDES and VTB are shared between threads */ mfspr r7, SPRN_DPDES + mfspr r8, SPRN_VTB std r7, VCORE_DPDES(r5) + std r8, VCORE_VTB(r5) /* clear DPDES so we don't get guest doorbells in the host */ li r8, 0 mtspr SPRN_DPDES, r8 @@ -2213,10 +2276,20 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) ld r29, VCPU_GPR(R29)(r4) ld r30, VCPU_GPR(R30)(r4) ld r31, VCPU_GPR(R31)(r4) - + /* Check the wake reason in SRR1 to see why we got here */ bl kvmppc_check_wake_reason + /* + * Restore volatile registers since we could have called a + * C routine in kvmppc_check_wake_reason + * r4 = VCPU + * r3 tells us whether we need to return to host or not + * WARNING: it gets checked further down: + * should not modify r3 until this check is done. + */ + ld r4, HSTATE_KVM_VCPU(r13) + /* clear our bit in vcore->napping_threads */ 34: ld r5,HSTATE_KVM_VCORE(r13) lbz r7,HSTATE_PTID(r13) @@ -2230,7 +2303,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) li r0,0 stb r0,HSTATE_NAPPING(r13) - /* See if the wake reason means we need to exit */ + /* See if the wake reason saved in r3 means we need to exit */ stw r12, VCPU_TRAP(r4) mr r9, r4 cmpdi r3, 0 @@ -2297,10 +2370,14 @@ machine_check_realmode: * 0 if nothing needs to be done * 1 if something happened that needs to be handled by the host * -1 if there was a guest wakeup (IPI or msgsnd) + * -2 if we handled a PCI passthrough interrupt (returned by + * kvmppc_read_intr only) * * Also sets r12 to the interrupt vector for any interrupt that needs * to be handled now by the host (0x500 for external interrupt), or zero. - * Modifies r0, r6, r7, r8. + * Modifies all volatile registers (since it may call a C function). + * This routine calls kvmppc_read_intr, a C function, if an external + * interrupt is pending. */ kvmppc_check_wake_reason: mfspr r6, SPRN_SRR1 @@ -2310,8 +2387,7 @@ FTR_SECTION_ELSE rlwinm r6, r6, 45-31, 0xe /* P7 wake reason field is 3 bits */ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S) cmpwi r6, 8 /* was it an external interrupt? */ - li r12, BOOK3S_INTERRUPT_EXTERNAL - beq kvmppc_read_intr /* if so, see what it was */ + beq 7f /* if so, see what it was */ li r3, 0 li r12, 0 cmpwi r6, 6 /* was it the decrementer? */ @@ -2350,83 +2426,28 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) li r3, 1 blr -/* - * Determine what sort of external interrupt is pending (if any). - * Returns: - * 0 if no interrupt is pending - * 1 if an interrupt is pending that needs to be handled by the host - * -1 if there was a guest wakeup IPI (which has now been cleared) - * Modifies r0, r6, r7, r8, returns value in r3. - */ -kvmppc_read_intr: - /* see if a host IPI is pending */ - li r3, 1 - lbz r0, HSTATE_HOST_IPI(r13) - cmpwi r0, 0 - bne 1f + /* external interrupt - create a stack frame so we can call C */ +7: mflr r0 + std r0, PPC_LR_STKOFF(r1) + stdu r1, -PPC_MIN_STKFRM(r1) + bl kvmppc_read_intr + nop + li r12, BOOK3S_INTERRUPT_EXTERNAL + cmpdi r3, 1 + ble 1f - /* Now read the interrupt from the ICP */ - ld r6, HSTATE_XICS_PHYS(r13) - li r7, XICS_XIRR - cmpdi r6, 0 - beq- 1f - lwzcix r0, r6, r7 /* - * Save XIRR for later. Since we get in in reverse endian on LE - * systems, save it byte reversed and fetch it back in host endian. - */ - li r3, HSTATE_SAVED_XIRR - STWX_BE r0, r3, r13 -#ifdef __LITTLE_ENDIAN__ - lwz r3, HSTATE_SAVED_XIRR(r13) -#else - mr r3, r0 -#endif - rlwinm. r3, r3, 0, 0xffffff - sync - beq 1f /* if nothing pending in the ICP */ - - /* We found something in the ICP... - * - * If it's not an IPI, stash it in the PACA and return to - * the host, we don't (yet) handle directing real external - * interrupts directly to the guest + * Return code of 2 means PCI passthrough interrupt, but + * we need to return back to host to complete handling the + * interrupt. Trap reason is expected in r12 by guest + * exit code. */ - cmpwi r3, XICS_IPI /* if there is, is it an IPI? */ - bne 42f - - /* It's an IPI, clear the MFRR and EOI it */ - li r3, 0xff - li r8, XICS_MFRR - stbcix r3, r6, r8 /* clear the IPI */ - stwcix r0, r6, r7 /* EOI it */ - sync - - /* We need to re-check host IPI now in case it got set in the - * meantime. If it's clear, we bounce the interrupt to the - * guest - */ - lbz r0, HSTATE_HOST_IPI(r13) - cmpwi r0, 0 - bne- 43f - - /* OK, it's an IPI for us */ - li r12, 0 - li r3, -1 -1: blr - -42: /* It's not an IPI and it's for the host. We saved a copy of XIRR in - * the PACA earlier, it will be picked up by the host ICP driver - */ - li r3, 1 - b 1b - -43: /* We raced with the host, we need to resend that IPI, bummer */ - li r0, IPI_PRIORITY - stbcix r0, r6, r8 /* set the IPI */ - sync - li r3, 1 - b 1b + li r12, BOOK3S_INTERRUPT_HV_RM_HARD +1: + ld r0, PPC_MIN_STKFRM+PPC_LR_STKOFF(r1) + addi r1, r1, PPC_MIN_STKFRM + mtlr r0 + blr /* * Save away FP, VMX and VSX registers. diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index e76f79a45988..826c541a12af 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -226,7 +226,7 @@ void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu, */ vcpu->arch.purr += get_tb() - vcpu->arch.entry_tb; vcpu->arch.spurr += get_tb() - vcpu->arch.entry_tb; - vcpu->arch.vtb += get_vtb() - vcpu->arch.entry_vtb; + to_book3s(vcpu)->vtb += get_vtb() - vcpu->arch.entry_vtb; if (cpu_has_feature(CPU_FTR_ARCH_207S)) vcpu->arch.ic += mfspr(SPRN_IC) - vcpu->arch.entry_ic; svcpu->in_use = false; @@ -448,6 +448,8 @@ void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr) case PVR_POWER7: case PVR_POWER7p: case PVR_POWER8: + case PVR_POWER8E: + case PVR_POWER8NVL: vcpu->arch.hflags |= BOOK3S_HFLAG_MULTI_PGSIZE | BOOK3S_HFLAG_NEW_TLBIE; break; @@ -1361,6 +1363,9 @@ static int kvmppc_get_one_reg_pr(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_HIOR: *val = get_reg_val(id, to_book3s(vcpu)->hior); break; + case KVM_REG_PPC_VTB: + *val = get_reg_val(id, to_book3s(vcpu)->vtb); + break; case KVM_REG_PPC_LPCR: case KVM_REG_PPC_LPCR_64: /* @@ -1397,6 +1402,9 @@ static int kvmppc_set_one_reg_pr(struct kvm_vcpu *vcpu, u64 id, to_book3s(vcpu)->hior = set_reg_val(id, *val); to_book3s(vcpu)->hior_explicit = true; break; + case KVM_REG_PPC_VTB: + to_book3s(vcpu)->vtb = set_reg_val(id, *val); + break; case KVM_REG_PPC_LPCR: case KVM_REG_PPC_LPCR_64: kvmppc_set_lpcr_pr(vcpu, set_reg_val(id, *val)); diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index 05aa11399a78..3bdc639157c1 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -99,6 +99,10 @@ static int ics_deliver_irq(struct kvmppc_xics *xics, u32 irq, u32 level) return 0; } + /* Record which CPU this arrived on for passed-through interrupts */ + if (state->host_irq) + state->intr_cpu = raw_smp_processor_id(); + /* Attempt delivery */ icp_deliver_irq(xics, NULL, irq); @@ -812,7 +816,7 @@ static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) return H_SUCCESS; } -static noinline int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall) +int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall) { struct kvmppc_xics *xics = vcpu->kvm->arch.xics; struct kvmppc_icp *icp = vcpu->arch.icp; @@ -841,6 +845,7 @@ static noinline int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall) return H_SUCCESS; } +EXPORT_SYMBOL_GPL(kvmppc_xics_rm_complete); int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req) { @@ -892,6 +897,21 @@ EXPORT_SYMBOL_GPL(kvmppc_xics_hcall); /* -- Initialisation code etc. -- */ +static void xics_debugfs_irqmap(struct seq_file *m, + struct kvmppc_passthru_irqmap *pimap) +{ + int i; + + if (!pimap) + return; + seq_printf(m, "========\nPIRQ mappings: %d maps\n===========\n", + pimap->n_mapped); + for (i = 0; i < pimap->n_mapped; i++) { + seq_printf(m, "r_hwirq=%x, v_hwirq=%x\n", + pimap->mapped[i].r_hwirq, pimap->mapped[i].v_hwirq); + } +} + static int xics_debug_show(struct seq_file *m, void *private) { struct kvmppc_xics *xics = m->private; @@ -913,6 +933,8 @@ static int xics_debug_show(struct seq_file *m, void *private) t_check_resend = 0; t_reject = 0; + xics_debugfs_irqmap(m, kvm->arch.pimap); + seq_printf(m, "=========\nICP state\n=========\n"); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -1252,6 +1274,8 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, { struct kvmppc_xics *xics = kvm->arch.xics; + if (!xics) + return -ENODEV; return ics_deliver_irq(xics, irq, level); } @@ -1418,3 +1442,34 @@ int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin) { return pin; } + +void kvmppc_xics_set_mapped(struct kvm *kvm, unsigned long irq, + unsigned long host_irq) +{ + struct kvmppc_xics *xics = kvm->arch.xics; + struct kvmppc_ics *ics; + u16 idx; + + ics = kvmppc_xics_find_ics(xics, irq, &idx); + if (!ics) + return; + + ics->irq_state[idx].host_irq = host_irq; + ics->irq_state[idx].intr_cpu = -1; +} +EXPORT_SYMBOL_GPL(kvmppc_xics_set_mapped); + +void kvmppc_xics_clr_mapped(struct kvm *kvm, unsigned long irq, + unsigned long host_irq) +{ + struct kvmppc_xics *xics = kvm->arch.xics; + struct kvmppc_ics *ics; + u16 idx; + + ics = kvmppc_xics_find_ics(xics, irq, &idx); + if (!ics) + return; + + ics->irq_state[idx].host_irq = 0; +} +EXPORT_SYMBOL_GPL(kvmppc_xics_clr_mapped); diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h index a46b954055c4..2a50320b55ca 100644 --- a/arch/powerpc/kvm/book3s_xics.h +++ b/arch/powerpc/kvm/book3s_xics.h @@ -42,6 +42,8 @@ struct ics_irq_state { u8 lsi; /* level-sensitive interrupt */ u8 asserted; /* Only for LSI */ u8 exists; + int intr_cpu; + u32 host_irq; }; /* Atomic ICP state, updated with a single compare & swap */ diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 02b4672f7347..df3f2706d3e5 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -2038,7 +2038,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, if (type == KVMPPC_DEBUG_NONE) continue; - if (type & !(KVMPPC_DEBUG_WATCH_READ | + if (type & ~(KVMPPC_DEBUG_WATCH_READ | KVMPPC_DEBUG_WATCH_WRITE | KVMPPC_DEBUG_BREAKPOINT)) return -EINVAL; diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c index 29911a07bcdb..ddbf8f0284c0 100644 --- a/arch/powerpc/kvm/e500_mmu.c +++ b/arch/powerpc/kvm/e500_mmu.c @@ -743,7 +743,7 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu, char *virt; struct page **pages; struct tlbe_priv *privs[2] = {}; - u64 *g2h_bitmap = NULL; + u64 *g2h_bitmap; size_t array_len; u32 sets; int num_pages, ret, i; @@ -779,41 +779,44 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu, num_pages = DIV_ROUND_UP(cfg->array + array_len - 1, PAGE_SIZE) - cfg->array / PAGE_SIZE; - pages = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL); + pages = kmalloc_array(num_pages, sizeof(*pages), GFP_KERNEL); if (!pages) return -ENOMEM; ret = get_user_pages_fast(cfg->array, num_pages, 1, pages); if (ret < 0) - goto err_pages; + goto free_pages; if (ret != num_pages) { num_pages = ret; ret = -EFAULT; - goto err_put_page; + goto put_pages; } virt = vmap(pages, num_pages, VM_MAP, PAGE_KERNEL); if (!virt) { ret = -ENOMEM; - goto err_put_page; + goto put_pages; } - privs[0] = kzalloc(sizeof(struct tlbe_priv) * params.tlb_sizes[0], - GFP_KERNEL); - privs[1] = kzalloc(sizeof(struct tlbe_priv) * params.tlb_sizes[1], - GFP_KERNEL); + privs[0] = kcalloc(params.tlb_sizes[0], sizeof(*privs[0]), GFP_KERNEL); + if (!privs[0]) { + ret = -ENOMEM; + goto put_pages; + } - if (!privs[0] || !privs[1]) { + privs[1] = kcalloc(params.tlb_sizes[1], sizeof(*privs[1]), GFP_KERNEL); + if (!privs[1]) { ret = -ENOMEM; - goto err_privs; + goto free_privs_first; } - g2h_bitmap = kzalloc(sizeof(u64) * params.tlb_sizes[1], - GFP_KERNEL); + g2h_bitmap = kcalloc(params.tlb_sizes[1], + sizeof(*g2h_bitmap), + GFP_KERNEL); if (!g2h_bitmap) { ret = -ENOMEM; - goto err_privs; + goto free_privs_second; } free_gtlb(vcpu_e500); @@ -845,16 +848,14 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu, kvmppc_recalc_tlb1map_range(vcpu_e500); return 0; - -err_privs: - kfree(privs[0]); + free_privs_second: kfree(privs[1]); - -err_put_page: + free_privs_first: + kfree(privs[0]); + put_pages: for (i = 0; i < num_pages; i++) put_page(pages[i]); - -err_pages: + free_pages: kfree(pages); return ret; } @@ -904,11 +905,9 @@ static int vcpu_mmu_init(struct kvm_vcpu *vcpu, int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500) { struct kvm_vcpu *vcpu = &vcpu_e500->vcpu; - int entry_size = sizeof(struct kvm_book3e_206_tlb_entry); - int entries = KVM_E500_TLB0_SIZE + KVM_E500_TLB1_SIZE; if (e500_mmu_host_init(vcpu_e500)) - goto err; + goto free_vcpu; vcpu_e500->gtlb_params[0].entries = KVM_E500_TLB0_SIZE; vcpu_e500->gtlb_params[1].entries = KVM_E500_TLB1_SIZE; @@ -920,37 +919,39 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500) vcpu_e500->gtlb_params[1].ways = KVM_E500_TLB1_SIZE; vcpu_e500->gtlb_params[1].sets = 1; - vcpu_e500->gtlb_arch = kmalloc(entries * entry_size, GFP_KERNEL); + vcpu_e500->gtlb_arch = kmalloc_array(KVM_E500_TLB0_SIZE + + KVM_E500_TLB1_SIZE, + sizeof(*vcpu_e500->gtlb_arch), + GFP_KERNEL); if (!vcpu_e500->gtlb_arch) return -ENOMEM; vcpu_e500->gtlb_offset[0] = 0; vcpu_e500->gtlb_offset[1] = KVM_E500_TLB0_SIZE; - vcpu_e500->gtlb_priv[0] = kzalloc(sizeof(struct tlbe_ref) * - vcpu_e500->gtlb_params[0].entries, + vcpu_e500->gtlb_priv[0] = kcalloc(vcpu_e500->gtlb_params[0].entries, + sizeof(struct tlbe_ref), GFP_KERNEL); if (!vcpu_e500->gtlb_priv[0]) - goto err; + goto free_vcpu; - vcpu_e500->gtlb_priv[1] = kzalloc(sizeof(struct tlbe_ref) * - vcpu_e500->gtlb_params[1].entries, + vcpu_e500->gtlb_priv[1] = kcalloc(vcpu_e500->gtlb_params[1].entries, + sizeof(struct tlbe_ref), GFP_KERNEL); if (!vcpu_e500->gtlb_priv[1]) - goto err; + goto free_vcpu; - vcpu_e500->g2h_tlb1_map = kzalloc(sizeof(u64) * - vcpu_e500->gtlb_params[1].entries, + vcpu_e500->g2h_tlb1_map = kcalloc(vcpu_e500->gtlb_params[1].entries, + sizeof(*vcpu_e500->g2h_tlb1_map), GFP_KERNEL); if (!vcpu_e500->g2h_tlb1_map) - goto err; + goto free_vcpu; vcpu_mmu_init(vcpu, vcpu_e500->gtlb_params); kvmppc_recalc_tlb1map_range(vcpu_e500); return 0; - -err: + free_vcpu: free_gtlb(vcpu_e500); return -1; } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 6ce40dd6fe51..70963c845e96 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -27,6 +27,8 @@ #include <linux/slab.h> #include <linux/file.h> #include <linux/module.h> +#include <linux/irqbypass.h> +#include <linux/kvm_irqfd.h> #include <asm/cputable.h> #include <asm/uaccess.h> #include <asm/kvm_ppc.h> @@ -436,6 +438,16 @@ err_out: return -EINVAL; } +bool kvm_arch_has_vcpu_debugfs(void) +{ + return false; +} + +int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +{ + return 0; +} + void kvm_arch_destroy_vm(struct kvm *kvm) { unsigned int i; @@ -739,6 +751,42 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) #endif } +/* + * irq_bypass_add_producer and irq_bypass_del_producer are only + * useful if the architecture supports PCI passthrough. + * irq_bypass_stop and irq_bypass_start are not needed and so + * kvm_ops are not defined for them. + */ +bool kvm_arch_has_irq_bypass(void) +{ + return ((kvmppc_hv_ops && kvmppc_hv_ops->irq_bypass_add_producer) || + (kvmppc_pr_ops && kvmppc_pr_ops->irq_bypass_add_producer)); +} + +int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, + struct irq_bypass_producer *prod) +{ + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + struct kvm *kvm = irqfd->kvm; + + if (kvm->arch.kvm_ops->irq_bypass_add_producer) + return kvm->arch.kvm_ops->irq_bypass_add_producer(cons, prod); + + return 0; +} + +void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, + struct irq_bypass_producer *prod) +{ + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + struct kvm *kvm = irqfd->kvm; + + if (kvm->arch.kvm_ops->irq_bypass_del_producer) + kvm->arch.kvm_ops->irq_bypass_del_producer(cons, prod); +} + static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run) { @@ -1167,6 +1215,19 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return r; } +bool kvm_arch_intc_initialized(struct kvm *kvm) +{ +#ifdef CONFIG_KVM_MPIC + if (kvm->arch.mpic) + return true; +#endif +#ifdef CONFIG_KVM_XICS + if (kvm->arch.xics) + return true; +#endif + return false; +} + int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h index 33d9daff5783..fb21990c0fb4 100644 --- a/arch/powerpc/kvm/trace_hv.h +++ b/arch/powerpc/kvm/trace_hv.h @@ -432,6 +432,28 @@ TRACE_EVENT(kvmppc_vcore_blocked, __entry->runner_vcpu, __entry->n_runnable, __entry->tgid) ); +TRACE_EVENT(kvmppc_vcore_wakeup, + TP_PROTO(int do_sleep, __u64 ns), + + TP_ARGS(do_sleep, ns), + + TP_STRUCT__entry( + __field(__u64, ns) + __field(int, waited) + __field(pid_t, tgid) + ), + + TP_fast_assign( + __entry->ns = ns; + __entry->waited = do_sleep; + __entry->tgid = current->tgid; + ), + + TP_printk("%s time %lld ns, tgid=%d", + __entry->waited ? "wait" : "poll", + __entry->ns, __entry->tgid) +); + TRACE_EVENT(kvmppc_run_vcpu_enter, TP_PROTO(struct kvm_vcpu *vcpu), diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index ba21be15310f..ad5290005ca4 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -22,7 +22,7 @@ obj64-$(CONFIG_SMP) += locks.o obj64-$(CONFIG_ALTIVEC) += vmx-helper.o ifeq ($(CONFIG_GENERIC_CSUM),) -obj-y += checksum_$(CONFIG_WORD_SIZE).o checksum_wrappers.o +obj-y += checksum_$(BITS).o checksum_wrappers.o endif obj-$(CONFIG_PPC_EMULATE_SSTEP) += sstep.o ldstfp.o diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S index 0a57fe6d49cc..aa8214f30c92 100644 --- a/arch/powerpc/lib/checksum_32.S +++ b/arch/powerpc/lib/checksum_32.S @@ -127,18 +127,19 @@ _GLOBAL(csum_partial_copy_generic) stw r7,12(r1) stw r8,8(r1) - rlwinm r0,r4,3,0x8 - rlwnm r6,r6,r0,0,31 /* odd destination address: rotate one byte */ - cmplwi cr7,r0,0 /* is destination address even ? */ addic r12,r6,0 addi r6,r4,-4 neg r0,r4 addi r4,r3,-4 andi. r0,r0,CACHELINE_MASK /* # bytes to start of cache line */ + crset 4*cr7+eq beq 58f cmplw 0,r5,r0 /* is this more than total to do? */ blt 63f /* if not much to do */ + rlwinm r7,r6,3,0x8 + rlwnm r12,r12,r7,0,31 /* odd destination address: rotate one byte */ + cmplwi cr7,r7,0 /* is destination address even ? */ andi. r8,r0,3 /* get it word-aligned first */ mtctr r8 beq+ 61f diff --git a/arch/powerpc/lib/mem_64.S b/arch/powerpc/lib/mem_64.S index 43435c6892fb..eda7a96161ab 100644 --- a/arch/powerpc/lib/mem_64.S +++ b/arch/powerpc/lib/mem_64.S @@ -37,6 +37,7 @@ _GLOBAL(memset) clrldi r5,r5,58 mtctr r0 beq 5f + .balign 16 4: std r4,0(r6) std r4,8(r6) std r4,16(r6) @@ -90,6 +91,7 @@ _GLOBAL(backwards_memcpy) andi. r0,r6,3 mtctr r7 bne 5f + .balign 16 1: lwz r7,-4(r4) lwzu r8,-8(r4) stw r7,-4(r6) diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index f2cea6d5e764..1a4e570f7894 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -7,17 +7,16 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) obj-y := fault.o mem.o pgtable.o mmap.o \ - init_$(CONFIG_WORD_SIZE).o \ - pgtable_$(CONFIG_WORD_SIZE).o + init_$(BITS).o pgtable_$(BITS).o obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \ tlb_nohash_low.o -obj-$(CONFIG_PPC_BOOK3E) += tlb_low_$(CONFIG_WORD_SIZE)e.o +obj-$(CONFIG_PPC_BOOK3E) += tlb_low_$(BITS)e.o hash64-$(CONFIG_PPC_NATIVE) := hash_native_64.o obj-$(CONFIG_PPC_BOOK3E_64) += pgtable-book3e.o obj-$(CONFIG_PPC_STD_MMU_64) += pgtable-hash64.o hash_utils_64.o slb_low.o slb.o $(hash64-y) mmu_context_book3s64.o pgtable-book3s64.o obj-$(CONFIG_PPC_RADIX_MMU) += pgtable-radix.o tlb-radix.o obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o mmu_context_hash32.o -obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(BITS).o ifeq ($(CONFIG_PPC_STD_MMU_64),y) obj-$(CONFIG_PPC_4K_PAGES) += hash64_4k.o obj-$(CONFIG_PPC_64K_PAGES) += hash64_64k.o diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index a4db22f65021..d0b137d96df1 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -26,7 +26,7 @@ #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/highmem.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/kprobes.h> #include <linux/kdebug.h> #include <linux/perf_event.h> @@ -205,7 +205,7 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault) * The return value is 0 if the fault was handled, or the signal * number if this is a kernel fault that can't be handled here. */ -int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, +int do_page_fault(struct pt_regs *regs, unsigned long address, unsigned long error_code) { enum ctx_state prev_state = exception_enter(); @@ -498,8 +498,8 @@ bad_area_nosemaphore: bail: exception_exit(prev_state); return rc; - } +NOKPROBE_SYMBOL(do_page_fault); /* * bad_page_fault is called when we have a bad access from the kernel. diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 0e4e9654bd2c..83ddc0e171b0 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -493,36 +493,6 @@ static void native_hugepage_invalidate(unsigned long vsid, } #endif -static inline int __hpte_actual_psize(unsigned int lp, int psize) -{ - int i, shift; - unsigned int mask; - - /* start from 1 ignoring MMU_PAGE_4K */ - for (i = 1; i < MMU_PAGE_COUNT; i++) { - - /* invalid penc */ - if (mmu_psize_defs[psize].penc[i] == -1) - continue; - /* - * encoding bits per actual page size - * PTE LP actual page size - * rrrr rrrz >=8KB - * rrrr rrzz >=16KB - * rrrr rzzz >=32KB - * rrrr zzzz >=64KB - * ....... - */ - shift = mmu_psize_defs[i].shift - LP_SHIFT; - if (shift > LP_BITS) - shift = LP_BITS; - mask = (1 << shift) - 1; - if ((lp & mask) == mmu_psize_defs[psize].penc[i]) - return i; - } - return -1; -} - static void hpte_decode(struct hash_pte *hpte, unsigned long slot, int *psize, int *apsize, int *ssize, unsigned long *vpn) { @@ -538,16 +508,8 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot, size = MMU_PAGE_4K; a_size = MMU_PAGE_4K; } else { - for (size = 0; size < MMU_PAGE_COUNT; size++) { - - /* valid entries have a shift value */ - if (!mmu_psize_defs[size].shift) - continue; - - a_size = __hpte_actual_psize(lp, size); - if (a_size != -1) - break; - } + size = hpte_page_sizes[lp] & 0xf; + a_size = hpte_page_sizes[lp] >> 4; } /* This works for all page sizes, and for 256M and 1T segments */ if (cpu_has_feature(CPU_FTR_ARCH_300)) diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 0821556e16f4..90480e23fd2c 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -93,6 +93,9 @@ static unsigned long _SDR1; struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; EXPORT_SYMBOL_GPL(mmu_psize_defs); +u8 hpte_page_sizes[1 << LP_BITS]; +EXPORT_SYMBOL_GPL(hpte_page_sizes); + struct hash_pte *htab_address; unsigned long htab_size_bytes; unsigned long htab_hash_mask; @@ -564,8 +567,60 @@ static void __init htab_scan_page_sizes(void) #endif /* CONFIG_HUGETLB_PAGE */ } +/* + * Fill in the hpte_page_sizes[] array. + * We go through the mmu_psize_defs[] array looking for all the + * supported base/actual page size combinations. Each combination + * has a unique pagesize encoding (penc) value in the low bits of + * the LP field of the HPTE. For actual page sizes less than 1MB, + * some of the upper LP bits are used for RPN bits, meaning that + * we need to fill in several entries in hpte_page_sizes[]. + * + * In diagrammatic form, with r = RPN bits and z = page size bits: + * PTE LP actual page size + * rrrr rrrz >=8KB + * rrrr rrzz >=16KB + * rrrr rzzz >=32KB + * rrrr zzzz >=64KB + * ... + * + * The zzzz bits are implementation-specific but are chosen so that + * no encoding for a larger page size uses the same value in its + * low-order N bits as the encoding for the 2^(12+N) byte page size + * (if it exists). + */ +static void init_hpte_page_sizes(void) +{ + long int ap, bp; + long int shift, penc; + + for (bp = 0; bp < MMU_PAGE_COUNT; ++bp) { + if (!mmu_psize_defs[bp].shift) + continue; /* not a supported page size */ + for (ap = bp; ap < MMU_PAGE_COUNT; ++ap) { + penc = mmu_psize_defs[bp].penc[ap]; + if (penc == -1) + continue; + shift = mmu_psize_defs[ap].shift - LP_SHIFT; + if (shift <= 0) + continue; /* should never happen */ + /* + * For page sizes less than 1MB, this loop + * replicates the entry for all possible values + * of the rrrr bits. + */ + while (penc < (1 << LP_BITS)) { + hpte_page_sizes[penc] = (ap << 4) | bp; + penc += 1 << shift; + } + } + } +} + static void __init htab_init_page_sizes(void) { + init_hpte_page_sizes(); + if (!debug_pagealloc_enabled()) { /* * Pick a size for the linear mapping. Currently, we only @@ -711,6 +766,29 @@ int remove_section_mapping(unsigned long start, unsigned long end) } #endif /* CONFIG_MEMORY_HOTPLUG */ +static void update_hid_for_hash(void) +{ + unsigned long hid0; + unsigned long rb = 3UL << PPC_BITLSHIFT(53); /* IS = 3 */ + + asm volatile("ptesync": : :"memory"); + /* prs = 0, ric = 2, rs = 0, r = 1 is = 3 */ + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(0), "i"(0), "i"(2), "r"(0) : "memory"); + asm volatile("eieio; tlbsync; ptesync; isync; slbia": : :"memory"); + /* + * now switch the HID + */ + hid0 = mfspr(SPRN_HID0); + hid0 &= ~HID0_POWER9_RADIX; + mtspr(SPRN_HID0, hid0); + asm volatile("isync": : :"memory"); + + /* Wait for it to happen */ + while ((mfspr(SPRN_HID0) & HID0_POWER9_RADIX)) + cpu_relax(); +} + static void __init hash_init_partition_table(phys_addr_t hash_table, unsigned long htab_size) { @@ -737,6 +815,8 @@ static void __init hash_init_partition_table(phys_addr_t hash_table, */ partition_tb->patb1 = 0; pr_info("Partition table %p\n", partition_tb); + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + update_hid_for_hash(); /* * update partition table control register, * 64 K size. @@ -1460,6 +1540,29 @@ out_exit: local_irq_restore(flags); } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static inline void tm_flush_hash_page(int local) +{ + /* + * Transactions are not aborted by tlbiel, only tlbie. Without, syncing a + * page back to a block device w/PIO could pick up transactional data + * (bad!) so we force an abort here. Before the sync the page will be + * made read-only, which will flush_hash_page. BIG ISSUE here: if the + * kernel uses a page from userspace without unmapping it first, it may + * see the speculated version. + */ + if (local && cpu_has_feature(CPU_FTR_TM) && current->thread.regs && + MSR_TM_ACTIVE(current->thread.regs->msr)) { + tm_enable(); + tm_abort(TM_CAUSE_TLBI); + } +} +#else +static inline void tm_flush_hash_page(int local) +{ +} +#endif + /* WARNING: This is called from hash_low_64.S, if you change this prototype, * do not forget to update the assembly call site ! */ @@ -1486,21 +1589,7 @@ void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize, ssize, local); } pte_iterate_hashed_end(); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - /* Transactions are not aborted by tlbiel, only tlbie. - * Without, syncing a page back to a block device w/ PIO could pick up - * transactional data (bad!) so we force an abort here. Before the - * sync the page will be made read-only, which will flush_hash_page. - * BIG ISSUE here: if the kernel uses a page from userspace without - * unmapping it first, it may see the speculated version. - */ - if (local && cpu_has_feature(CPU_FTR_TM) && - current->thread.regs && - MSR_TM_ACTIVE(current->thread.regs->msr)) { - tm_enable(); - tm_abort(TM_CAUSE_TLBI); - } -#endif + tm_flush_hash_page(local); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -1557,22 +1646,7 @@ void flush_hash_hugepage(unsigned long vsid, unsigned long addr, MMU_PAGE_16M, ssize, local); } tm_abort: -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - /* Transactions are not aborted by tlbiel, only tlbie. - * Without, syncing a page back to a block device w/ PIO could pick up - * transactional data (bad!) so we force an abort here. Before the - * sync the page will be made read-only, which will flush_hash_page. - * BIG ISSUE here: if the kernel uses a page from userspace without - * unmapping it first, it may see the speculated version. - */ - if (local && cpu_has_feature(CPU_FTR_TM) && - current->thread.regs && - MSR_TM_ACTIVE(current->thread.regs->msr)) { - tm_enable(); - tm_abort(TM_CAUSE_TLBI); - } -#endif - return; + tm_flush_hash_page(local); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 7372ee13eb1e..a5d3ecdabc44 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -1019,8 +1019,15 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, pte = READ_ONCE(*ptep); mask = _PAGE_PRESENT | _PAGE_READ; + + /* + * On some CPUs like the 8xx, _PAGE_RW hence _PAGE_WRITE is defined + * as 0 and _PAGE_RO has to be set when a page is not writable + */ if (write) mask |= _PAGE_WRITE; + else + mask |= _PAGE_RO; if ((pte_val(pte) & mask) != mask) return 0; diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 448685fbf27c..8a7c38b8d335 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -137,7 +137,7 @@ void __init MMU_init(void) if (memblock.memory.cnt > 1) { #ifndef CONFIG_WII memblock_enforce_memory_limit(memblock.memory.regions[0].size); - printk(KERN_WARNING "Only using first contiguous memory region"); + pr_warn("Only using first contiguous memory region\n"); #else wii_memory_fixups(); #endif diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index da6a2168ae9e..e0f1c33601dd 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -15,6 +15,9 @@ #include <linux/rculist.h> #include <linux/vmalloc.h> #include <linux/mutex.h> +#include <linux/migrate.h> +#include <linux/hugetlb.h> +#include <linux/swap.h> #include <asm/mmu_context.h> static DEFINE_MUTEX(mem_list_mutex); @@ -72,6 +75,55 @@ bool mm_iommu_preregistered(void) } EXPORT_SYMBOL_GPL(mm_iommu_preregistered); +/* + * Taken from alloc_migrate_target with changes to remove CMA allocations + */ +struct page *new_iommu_non_cma_page(struct page *page, unsigned long private, + int **resultp) +{ + gfp_t gfp_mask = GFP_USER; + struct page *new_page; + + if (PageHuge(page) || PageTransHuge(page) || PageCompound(page)) + return NULL; + + if (PageHighMem(page)) + gfp_mask |= __GFP_HIGHMEM; + + /* + * We don't want the allocation to force an OOM if possibe + */ + new_page = alloc_page(gfp_mask | __GFP_NORETRY | __GFP_NOWARN); + return new_page; +} + +static int mm_iommu_move_page_from_cma(struct page *page) +{ + int ret = 0; + LIST_HEAD(cma_migrate_pages); + + /* Ignore huge pages for now */ + if (PageHuge(page) || PageTransHuge(page) || PageCompound(page)) + return -EBUSY; + + lru_add_drain(); + ret = isolate_lru_page(page); + if (ret) + return ret; + + list_add(&page->lru, &cma_migrate_pages); + put_page(page); /* Drop the gup reference */ + + ret = migrate_pages(&cma_migrate_pages, new_iommu_non_cma_page, + NULL, 0, MIGRATE_SYNC, MR_CMA); + if (ret) { + if (!list_empty(&cma_migrate_pages)) + putback_movable_pages(&cma_migrate_pages); + } + + return 0; +} + long mm_iommu_get(unsigned long ua, unsigned long entries, struct mm_iommu_table_group_mem_t **pmem) { @@ -124,15 +176,36 @@ long mm_iommu_get(unsigned long ua, unsigned long entries, for (i = 0; i < entries; ++i) { if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT), 1/* pages */, 1/* iswrite */, &page)) { + ret = -EFAULT; for (j = 0; j < i; ++j) - put_page(pfn_to_page( - mem->hpas[j] >> PAGE_SHIFT)); + put_page(pfn_to_page(mem->hpas[j] >> + PAGE_SHIFT)); vfree(mem->hpas); kfree(mem); - ret = -EFAULT; goto unlock_exit; } - + /* + * If we get a page from the CMA zone, since we are going to + * be pinning these entries, we might as well move them out + * of the CMA zone if possible. NOTE: faulting in + migration + * can be expensive. Batching can be considered later + */ + if (get_pageblock_migratetype(page) == MIGRATE_CMA) { + if (mm_iommu_move_page_from_cma(page)) + goto populate; + if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT), + 1/* pages */, 1/* iswrite */, + &page)) { + ret = -EFAULT; + for (j = 0; j < i; ++j) + put_page(pfn_to_page(mem->hpas[j] >> + PAGE_SHIFT)); + vfree(mem->hpas); + kfree(mem); + goto unlock_exit; + } + } +populate: mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; } diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 7d95bc402dba..c491f2c8f2b9 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -369,44 +369,34 @@ void destroy_context(struct mm_struct *mm) } #ifdef CONFIG_SMP - -static int mmu_context_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +static int mmu_ctx_cpu_prepare(unsigned int cpu) { - unsigned int cpu = (unsigned int)(long)hcpu; - /* We don't touch CPU 0 map, it's allocated at aboot and kept * around forever */ if (cpu == boot_cpuid) - return NOTIFY_OK; - - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - pr_devel("MMU: Allocating stale context map for CPU %d\n", cpu); - stale_map[cpu] = kzalloc(CTX_MAP_SIZE, GFP_KERNEL); - break; -#ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - case CPU_DEAD: - case CPU_DEAD_FROZEN: - pr_devel("MMU: Freeing stale context map for CPU %d\n", cpu); - kfree(stale_map[cpu]); - stale_map[cpu] = NULL; - - /* We also clear the cpu_vm_mask bits of CPUs going away */ - clear_tasks_mm_cpumask(cpu); - break; -#endif /* CONFIG_HOTPLUG_CPU */ - } - return NOTIFY_OK; + return 0; + + pr_devel("MMU: Allocating stale context map for CPU %d\n", cpu); + stale_map[cpu] = kzalloc(CTX_MAP_SIZE, GFP_KERNEL); + return 0; } -static struct notifier_block mmu_context_cpu_nb = { - .notifier_call = mmu_context_cpu_notify, -}; +static int mmu_ctx_cpu_dead(unsigned int cpu) +{ +#ifdef CONFIG_HOTPLUG_CPU + if (cpu == boot_cpuid) + return 0; + + pr_devel("MMU: Freeing stale context map for CPU %d\n", cpu); + kfree(stale_map[cpu]); + stale_map[cpu] = NULL; + + /* We also clear the cpu_vm_mask bits of CPUs going away */ + clear_tasks_mm_cpumask(cpu); +#endif + return 0; +} #endif /* CONFIG_SMP */ @@ -469,7 +459,9 @@ void __init mmu_context_init(void) #else stale_map[boot_cpuid] = memblock_virt_alloc(CTX_MAP_SIZE, 0); - register_cpu_notifier(&mmu_context_cpu_nb); + cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE, + "powerpc/mmu/ctx:prepare", + mmu_ctx_cpu_prepare, mmu_ctx_cpu_dead); #endif printk(KERN_INFO diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 34079302cc17..f4f437cbabf1 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -35,7 +35,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, #endif changed = !pmd_same(*(pmdp), entry); if (changed) { - __ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry)); + __ptep_set_access_flags(vma->vm_mm, pmdp_ptep(pmdp), pmd_pte(entry)); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } return changed; @@ -116,3 +116,12 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, return; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +/* For use by kexec */ +void mmu_cleanup_all(void) +{ + if (radix_enabled()) + radix__mmu_cleanup_all(); + else if (mmu_hash_ops.hpte_clear_all) + mmu_hash_ops.hpte_clear_all(); +} diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index af897d91d09f..ed7bddc456b7 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -294,6 +294,32 @@ found: return; } +static void update_hid_for_radix(void) +{ + unsigned long hid0; + unsigned long rb = 3UL << PPC_BITLSHIFT(53); /* IS = 3 */ + + asm volatile("ptesync": : :"memory"); + /* prs = 0, ric = 2, rs = 0, r = 1 is = 3 */ + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(1), "i"(0), "i"(2), "r"(0) : "memory"); + /* prs = 1, ric = 2, rs = 0, r = 1 is = 3 */ + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(1), "i"(1), "i"(2), "r"(0) : "memory"); + asm volatile("eieio; tlbsync; ptesync; isync; slbia": : :"memory"); + /* + * now switch the HID + */ + hid0 = mfspr(SPRN_HID0); + hid0 |= HID0_POWER9_RADIX; + mtspr(SPRN_HID0, hid0); + asm volatile("isync": : :"memory"); + + /* Wait for it to happen */ + while (!(mfspr(SPRN_HID0) & HID0_POWER9_RADIX)) + cpu_relax(); +} + void __init radix__early_init_mmu(void) { unsigned long lpcr; @@ -345,6 +371,8 @@ void __init radix__early_init_mmu(void) if (!firmware_has_feature(FW_FEATURE_LPAR)) { radix_init_native(); + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + update_hid_for_radix(); lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR); radix_init_partition_table(); @@ -368,6 +396,18 @@ void radix__early_init_mmu_secondary(void) } } +void radix__mmu_cleanup_all(void) +{ + unsigned long lpcr; + + if (!firmware_has_feature(FW_FEATURE_LPAR)) { + lpcr = mfspr(SPRN_LPCR); + mtspr(SPRN_LPCR, lpcr & ~LPCR_UPRT); + mtspr(SPRN_PTCR, 0); + radix__flush_tlb_all(); + } +} + void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size) { diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 0b6fb244d0a1..911fdfb63ec1 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -224,7 +224,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, if (changed) { if (!is_vm_hugetlb_page(vma)) assert_pte_locked(vma->vm_mm, address); - __ptep_set_access_flags(ptep, entry); + __ptep_set_access_flags(vma->vm_mm, ptep, entry); flush_tlb_page(vma, address); } return changed; diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index dfdb90cb4403..e2974fcd20f1 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -113,7 +113,12 @@ BEGIN_FTR_SECTION END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) b slb_finish_load_1T -0: +0: /* + * For userspace addresses, make sure this is region 0. + */ + cmpdi r9, 0 + bne 8f + /* when using slices, we extract the psize off the slice bitmaps * and then we need to get the sllp encoding off the mmu_psize_defs * array. @@ -173,11 +178,9 @@ BEGIN_FTR_SECTION END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) b slb_finish_load -8: /* invalid EA */ - li r10,0 /* BAD_VSID */ - li r9,0 /* BAD_VSID */ - li r11,SLB_VSID_USER /* flags don't much matter */ - b slb_finish_load +8: /* invalid EA - return an error indication */ + crset 4*cr0+eq /* indicate failure */ + blr /* * Finish loading of an SLB entry and return diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 48df05ef5231..0e49ec541ab5 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -400,3 +400,27 @@ void radix__flush_pmd_tlb_range(struct vm_area_struct *vma, radix__flush_tlb_range_psize(vma->vm_mm, start, end, MMU_PAGE_2M); } EXPORT_SYMBOL(radix__flush_pmd_tlb_range); + +void radix__flush_tlb_all(void) +{ + unsigned long rb,prs,r,rs; + unsigned long ric = RIC_FLUSH_ALL; + + rb = 0x3 << PPC_BITLSHIFT(53); /* IS = 3 */ + prs = 0; /* partition scoped */ + r = 1; /* raidx format */ + rs = 1 & ((1UL << 32) - 1); /* any LPID value to flush guest mappings */ + + asm volatile("ptesync": : :"memory"); + /* + * now flush guest entries by passing PRS = 1 and LPID != 0 + */ + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(1), "i"(ric), "r"(rs) : "memory"); + /* + * now flush host entires by passing PRS = 0 and LPID == 0 + */ + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(0) : "memory"); + asm volatile("eieio; tlbsync; ptesync": : :"memory"); +} diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index d5301b6f20d0..89f70073dec8 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -40,6 +40,8 @@ #define PPC_BLR() EMIT(PPC_INST_BLR) #define PPC_BLRL() EMIT(PPC_INST_BLRL) #define PPC_MTLR(r) EMIT(PPC_INST_MTLR | ___PPC_RT(r)) +#define PPC_BCTR() EMIT(PPC_INST_BCTR) +#define PPC_MTCTR(r) EMIT(PPC_INST_MTCTR | ___PPC_RT(r)) #define PPC_ADDI(d, a, i) EMIT(PPC_INST_ADDI | ___PPC_RT(d) | \ ___PPC_RA(a) | IMM_L(i)) #define PPC_MR(d, a) PPC_OR(d, a, a) diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h index 5046d6f65c02..62fa7589db2b 100644 --- a/arch/powerpc/net/bpf_jit64.h +++ b/arch/powerpc/net/bpf_jit64.h @@ -16,30 +16,33 @@ /* * Stack layout: + * Ensure the top half (upto local_tmp_var) stays consistent + * with our redzone usage. * * [ prev sp ] <------------- * [ nv gpr save area ] 8*8 | + * [ tail_call_cnt ] 8 | + * [ local_tmp_var ] 8 | * fp (r31) --> [ ebpf stack space ] 512 | - * [ local/tmp var space ] 16 | * [ frame header ] 32/112 | * sp (r1) ---> [ stack pointer ] -------------- */ -/* for bpf JIT code internal usage */ -#define BPF_PPC_STACK_LOCALS 16 /* for gpr non volatile registers BPG_REG_6 to 10, plus skb cache registers */ #define BPF_PPC_STACK_SAVE (8*8) +/* for bpf JIT code internal usage */ +#define BPF_PPC_STACK_LOCALS 16 /* Ensure this is quadword aligned */ -#define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS + \ - MAX_BPF_STACK + BPF_PPC_STACK_SAVE) +#define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + MAX_BPF_STACK + \ + BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE) #ifndef __ASSEMBLY__ /* BPF register usage */ -#define SKB_HLEN_REG (MAX_BPF_REG + 0) -#define SKB_DATA_REG (MAX_BPF_REG + 1) -#define TMP_REG_1 (MAX_BPF_REG + 2) -#define TMP_REG_2 (MAX_BPF_REG + 3) +#define SKB_HLEN_REG (MAX_BPF_JIT_REG + 0) +#define SKB_DATA_REG (MAX_BPF_JIT_REG + 1) +#define TMP_REG_1 (MAX_BPF_JIT_REG + 2) +#define TMP_REG_2 (MAX_BPF_JIT_REG + 3) /* BPF to ppc register mappings */ static const int b2p[] = { @@ -59,12 +62,16 @@ static const int b2p[] = { /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = 31, /* eBPF jit internal registers */ + [BPF_REG_AX] = 2, [SKB_HLEN_REG] = 25, [SKB_DATA_REG] = 26, [TMP_REG_1] = 9, [TMP_REG_2] = 10 }; +/* PPC NVR range -- update this if we ever use NVRs below r24 */ +#define BPF_PPC_NVR_MIN 24 + /* Assembly helpers */ #define DECLARE_LOAD_FUNC(func) u64 func(u64 r3, u64 r4); \ u64 func##_negative_offset(u64 r3, u64 r4); \ @@ -82,6 +89,7 @@ DECLARE_LOAD_FUNC(sk_load_byte); #define SEEN_FUNC 0x1000 /* might call external helpers */ #define SEEN_STACK 0x2000 /* uses BPF stack */ #define SEEN_SKB 0x4000 /* uses sk_buff */ +#define SEEN_TAILCALL 0x8000 /* uses tail calls */ struct codegen_context { /* diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 6073b78516f6..0fe98a567125 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -17,6 +17,7 @@ #include <linux/filter.h> #include <linux/if_vlan.h> #include <asm/kprobes.h> +#include <linux/bpf.h> #include "bpf_jit64.h" @@ -58,6 +59,40 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx) return ctx->seen & SEEN_FUNC || bpf_is_seen_register(ctx, BPF_REG_FP); } +/* + * When not setting up our own stackframe, the redzone usage is: + * + * [ prev sp ] <------------- + * [ ... ] | + * sp (r1) ---> [ stack pointer ] -------------- + * [ nv gpr save area ] 8*8 + * [ tail_call_cnt ] 8 + * [ local_tmp_var ] 8 + * [ unused red zone ] 208 bytes protected + */ +static int bpf_jit_stack_local(struct codegen_context *ctx) +{ + if (bpf_has_stack_frame(ctx)) + return STACK_FRAME_MIN_SIZE + MAX_BPF_STACK; + else + return -(BPF_PPC_STACK_SAVE + 16); +} + +static int bpf_jit_stack_tailcallcnt(struct codegen_context *ctx) +{ + return bpf_jit_stack_local(ctx) + 8; +} + +static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg) +{ + if (reg >= BPF_PPC_NVR_MIN && reg < 32) + return (bpf_has_stack_frame(ctx) ? BPF_PPC_STACKFRAME : 0) + - (8 * (32 - reg)); + + pr_err("BPF JIT is asking about unknown registers"); + BUG(); +} + static void bpf_jit_emit_skb_loads(u32 *image, struct codegen_context *ctx) { /* @@ -73,36 +108,27 @@ static void bpf_jit_emit_skb_loads(u32 *image, struct codegen_context *ctx) PPC_BPF_LL(b2p[SKB_DATA_REG], 3, offsetof(struct sk_buff, data)); } -static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func) +static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) { -#ifdef PPC64_ELF_ABI_v1 - /* func points to the function descriptor */ - PPC_LI64(b2p[TMP_REG_2], func); - /* Load actual entry point from function descriptor */ - PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0); - /* ... and move it to LR */ - PPC_MTLR(b2p[TMP_REG_1]); + int i; + /* - * Load TOC from function descriptor at offset 8. - * We can clobber r2 since we get called through a - * function pointer (so caller will save/restore r2) - * and since we don't use a TOC ourself. + * Initialize tail_call_cnt if we do tail calls. + * Otherwise, put in NOPs so that it can be skipped when we are + * invoked through a tail call. */ - PPC_BPF_LL(2, b2p[TMP_REG_2], 8); -#else - /* We can clobber r12 */ - PPC_FUNC_ADDR(12, func); - PPC_MTLR(12); -#endif - PPC_BLRL(); -} + if (ctx->seen & SEEN_TAILCALL) { + PPC_LI(b2p[TMP_REG_1], 0); + /* this goes in the redzone */ + PPC_BPF_STL(b2p[TMP_REG_1], 1, -(BPF_PPC_STACK_SAVE + 8)); + } else { + PPC_NOP(); + PPC_NOP(); + } -static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) -{ - int i; - bool new_stack_frame = bpf_has_stack_frame(ctx); +#define BPF_TAILCALL_PROLOGUE_SIZE 8 - if (new_stack_frame) { + if (bpf_has_stack_frame(ctx)) { /* * We need a stack frame, but we don't necessarily need to * save/restore LR unless we call other functions @@ -122,9 +148,7 @@ static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) */ for (i = BPF_REG_6; i <= BPF_REG_10; i++) if (bpf_is_seen_register(ctx, i)) - PPC_BPF_STL(b2p[i], 1, - (new_stack_frame ? BPF_PPC_STACKFRAME : 0) - - (8 * (32 - b2p[i]))); + PPC_BPF_STL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i])); /* * Save additional non-volatile regs if we cache skb @@ -132,53 +156,142 @@ static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) */ if (ctx->seen & SEEN_SKB) { PPC_BPF_STL(b2p[SKB_HLEN_REG], 1, - BPF_PPC_STACKFRAME - (8 * (32 - b2p[SKB_HLEN_REG]))); + bpf_jit_stack_offsetof(ctx, b2p[SKB_HLEN_REG])); PPC_BPF_STL(b2p[SKB_DATA_REG], 1, - BPF_PPC_STACKFRAME - (8 * (32 - b2p[SKB_DATA_REG]))); + bpf_jit_stack_offsetof(ctx, b2p[SKB_DATA_REG])); bpf_jit_emit_skb_loads(image, ctx); } /* Setup frame pointer to point to the bpf stack area */ if (bpf_is_seen_register(ctx, BPF_REG_FP)) PPC_ADDI(b2p[BPF_REG_FP], 1, - BPF_PPC_STACKFRAME - BPF_PPC_STACK_SAVE); + STACK_FRAME_MIN_SIZE + MAX_BPF_STACK); } -static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) +static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx) { int i; - bool new_stack_frame = bpf_has_stack_frame(ctx); - - /* Move result to r3 */ - PPC_MR(3, b2p[BPF_REG_0]); /* Restore NVRs */ for (i = BPF_REG_6; i <= BPF_REG_10; i++) if (bpf_is_seen_register(ctx, i)) - PPC_BPF_LL(b2p[i], 1, - (new_stack_frame ? BPF_PPC_STACKFRAME : 0) - - (8 * (32 - b2p[i]))); + PPC_BPF_LL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i])); /* Restore non-volatile registers used for skb cache */ if (ctx->seen & SEEN_SKB) { PPC_BPF_LL(b2p[SKB_HLEN_REG], 1, - BPF_PPC_STACKFRAME - (8 * (32 - b2p[SKB_HLEN_REG]))); + bpf_jit_stack_offsetof(ctx, b2p[SKB_HLEN_REG])); PPC_BPF_LL(b2p[SKB_DATA_REG], 1, - BPF_PPC_STACKFRAME - (8 * (32 - b2p[SKB_DATA_REG]))); + bpf_jit_stack_offsetof(ctx, b2p[SKB_DATA_REG])); } /* Tear down our stack frame */ - if (new_stack_frame) { + if (bpf_has_stack_frame(ctx)) { PPC_ADDI(1, 1, BPF_PPC_STACKFRAME); if (ctx->seen & SEEN_FUNC) { PPC_BPF_LL(0, 1, PPC_LR_STKOFF); PPC_MTLR(0); } } +} + +static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) +{ + bpf_jit_emit_common_epilogue(image, ctx); + + /* Move result to r3 */ + PPC_MR(3, b2p[BPF_REG_0]); PPC_BLR(); } +static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func) +{ +#ifdef PPC64_ELF_ABI_v1 + /* func points to the function descriptor */ + PPC_LI64(b2p[TMP_REG_2], func); + /* Load actual entry point from function descriptor */ + PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0); + /* ... and move it to LR */ + PPC_MTLR(b2p[TMP_REG_1]); + /* + * Load TOC from function descriptor at offset 8. + * We can clobber r2 since we get called through a + * function pointer (so caller will save/restore r2) + * and since we don't use a TOC ourself. + */ + PPC_BPF_LL(2, b2p[TMP_REG_2], 8); +#else + /* We can clobber r12 */ + PPC_FUNC_ADDR(12, func); + PPC_MTLR(12); +#endif + PPC_BLRL(); +} + +static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) +{ + /* + * By now, the eBPF program has already setup parameters in r3, r4 and r5 + * r3/BPF_REG_1 - pointer to ctx -- passed as is to the next bpf program + * r4/BPF_REG_2 - pointer to bpf_array + * r5/BPF_REG_3 - index in bpf_array + */ + int b2p_bpf_array = b2p[BPF_REG_2]; + int b2p_index = b2p[BPF_REG_3]; + + /* + * if (index >= array->map.max_entries) + * goto out; + */ + PPC_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries)); + PPC_CMPLW(b2p_index, b2p[TMP_REG_1]); + PPC_BCC(COND_GE, out); + + /* + * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * goto out; + */ + PPC_LD(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); + PPC_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT); + PPC_BCC(COND_GT, out); + + /* + * tail_call_cnt++; + */ + PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], 1); + PPC_BPF_STL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); + + /* prog = array->ptrs[index]; */ + PPC_MULI(b2p[TMP_REG_1], b2p_index, 8); + PPC_ADD(b2p[TMP_REG_1], b2p[TMP_REG_1], b2p_bpf_array); + PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs)); + + /* + * if (prog == NULL) + * goto out; + */ + PPC_CMPLDI(b2p[TMP_REG_1], 0); + PPC_BCC(COND_EQ, out); + + /* goto *(prog->bpf_func + prologue_size); */ + PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func)); +#ifdef PPC64_ELF_ABI_v1 + /* skip past the function descriptor */ + PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], + FUNCTION_DESCR_SIZE + BPF_TAILCALL_PROLOGUE_SIZE); +#else + PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], BPF_TAILCALL_PROLOGUE_SIZE); +#endif + PPC_MTCTR(b2p[TMP_REG_1]); + + /* tear down stack, restore NVRs, ... */ + bpf_jit_emit_common_epilogue(image, ctx); + + PPC_BCTR(); + /* out: */ +} + /* Assemble the body code between the prologue & epilogue */ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx, @@ -200,7 +313,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u64 imm64; u8 *func; u32 true_cond; - int stack_local_off; /* * addrs[] maps a BPF bytecode address into a real offset from @@ -219,9 +331,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, * optimization but everything else should work without * any issues. */ - if (dst_reg >= 24 && dst_reg <= 31) + if (dst_reg >= BPF_PPC_NVR_MIN && dst_reg < 32) bpf_set_seen_register(ctx, insn[i].dst_reg); - if (src_reg >= 24 && src_reg <= 31) + if (src_reg >= BPF_PPC_NVR_MIN && src_reg < 32) bpf_set_seen_register(ctx, insn[i].src_reg); switch (code) { @@ -490,25 +602,12 @@ bpf_alu32_trunc: * Way easier and faster(?) to store the value * into stack and then use ldbrx * - * First, determine where in stack we can store - * this: - * - if we have allotted a stack frame, then we - * will utilize the area set aside by - * BPF_PPC_STACK_LOCALS - * - else, we use the area beneath the NV GPR - * save area - * * ctx->seen will be reliable in pass2, but * the instructions generated will remain the * same across all passes */ - if (bpf_has_stack_frame(ctx)) - stack_local_off = STACK_FRAME_MIN_SIZE; - else - stack_local_off = -(BPF_PPC_STACK_SAVE + 8); - - PPC_STD(dst_reg, 1, stack_local_off); - PPC_ADDI(b2p[TMP_REG_1], 1, stack_local_off); + PPC_STD(dst_reg, 1, bpf_jit_stack_local(ctx)); + PPC_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx)); PPC_LDBRX(dst_reg, 0, b2p[TMP_REG_1]); break; } @@ -668,7 +767,7 @@ emit_clear: /* Save skb pointer if we need to re-cache skb data */ if (bpf_helper_changes_skb_data(func)) - PPC_BPF_STL(3, 1, STACK_FRAME_MIN_SIZE); + PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx)); bpf_jit_emit_func_call(image, ctx, (u64)func); @@ -678,7 +777,7 @@ emit_clear: /* refresh skb cache */ if (bpf_helper_changes_skb_data(func)) { /* reload skb pointer to r3 */ - PPC_BPF_LL(3, 1, STACK_FRAME_MIN_SIZE); + PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx)); bpf_jit_emit_skb_loads(image, ctx); } break; @@ -837,9 +936,12 @@ common_load: break; /* - * TODO: Tail call + * Tail call */ case BPF_JMP | BPF_CALL | BPF_X: + ctx->seen |= SEEN_TAILCALL; + bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); + break; default: /* @@ -872,21 +974,37 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) int pass; int flen; struct bpf_binary_header *bpf_hdr; + struct bpf_prog *org_fp = fp; + struct bpf_prog *tmp_fp; + bool bpf_blinded = false; if (!bpf_jit_enable) - return fp; + return org_fp; + + tmp_fp = bpf_jit_blind_constants(org_fp); + if (IS_ERR(tmp_fp)) + return org_fp; + + if (tmp_fp != org_fp) { + bpf_blinded = true; + fp = tmp_fp; + } flen = fp->len; addrs = kzalloc((flen+1) * sizeof(*addrs), GFP_KERNEL); - if (addrs == NULL) - return fp; + if (addrs == NULL) { + fp = org_fp; + goto out; + } + + memset(&cgctx, 0, sizeof(struct codegen_context)); - cgctx.idx = 0; - cgctx.seen = 0; /* Scouting faux-generate pass 0 */ - if (bpf_jit_build_body(fp, 0, &cgctx, addrs)) + if (bpf_jit_build_body(fp, 0, &cgctx, addrs)) { /* We hit something illegal or unsupported. */ + fp = org_fp; goto out; + } /* * Pretend to build prologue, given the features we've seen. This will @@ -901,8 +1019,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) bpf_hdr = bpf_jit_binary_alloc(alloclen, &image, 4, bpf_jit_fill_ill_insns); - if (!bpf_hdr) + if (!bpf_hdr) { + fp = org_fp; goto out; + } code_base = (u32 *)(image + FUNCTION_DESCR_SIZE); @@ -939,6 +1059,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) out: kfree(addrs); + + if (bpf_blinded) + bpf_jit_prog_release_other(fp, fp == org_fp ? tmp_fp : org_fp); + return fp; } diff --git a/arch/powerpc/oprofile/cell/spu_profiler.c b/arch/powerpc/oprofile/cell/spu_profiler.c index b129d007e7fe..b19265de9178 100644 --- a/arch/powerpc/oprofile/cell/spu_profiler.c +++ b/arch/powerpc/oprofile/cell/spu_profiler.c @@ -43,7 +43,7 @@ static unsigned int profiling_interval; #define SPU_PC_MASK 0xFFFF DEFINE_SPINLOCK(oprof_spu_smpl_arry_lck); -unsigned long oprof_spu_smpl_arry_lck_flags; +static unsigned long oprof_spu_smpl_arry_lck_flags; void set_spu_profiling_frequency(unsigned int freq_khz, unsigned int cycles_reset) { diff --git a/arch/powerpc/oprofile/cell/spu_task_sync.c b/arch/powerpc/oprofile/cell/spu_task_sync.c index ef2142ff7dbd..83d2b4ef7f0d 100644 --- a/arch/powerpc/oprofile/cell/spu_task_sync.c +++ b/arch/powerpc/oprofile/cell/spu_task_sync.c @@ -36,7 +36,7 @@ static DEFINE_SPINLOCK(buffer_lock); static DEFINE_SPINLOCK(cache_lock); static int num_spu_nodes; -int spu_prof_num_nodes; +static int spu_prof_num_nodes; struct spu_buffer spu_buff[MAX_NUMNODES * SPUS_PER_NODE]; struct delayed_work spu_work; @@ -88,7 +88,7 @@ static void spu_buff_add(unsigned long int value, int spu) /* This function copies the per SPU buffers to the * OProfile kernel buffer. */ -void sync_spu_buff(void) +static void sync_spu_buff(void) { int spu; unsigned long flags; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 4ed377f0f7b2..72c27b8d2cf3 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2158,7 +2158,7 @@ static void perf_event_interrupt(struct pt_regs *regs) irq_exit(); } -int power_pmu_prepare_cpu(unsigned int cpu) +static int power_pmu_prepare_cpu(unsigned int cpu) { struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 7aa37236bb70..43fabb3cae0f 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -131,7 +131,7 @@ static const struct attribute_group *attr_groups[] = { #define HGPCI_MAX_DATA_BYTES \ (HGPCI_REQ_BUFFER_SIZE - sizeof(struct hv_get_perf_counter_info_params)) -DEFINE_PER_CPU(char, hv_gpci_reqb[HGPCI_REQ_BUFFER_SIZE]) __aligned(sizeof(uint64_t)); +static DEFINE_PER_CPU(char, hv_gpci_reqb[HGPCI_REQ_BUFFER_SIZE]) __aligned(sizeof(uint64_t)); struct hv_gpci_request_buffer { struct hv_get_perf_counter_info_params params; diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c index a383c23a9070..7963658dbc22 100644 --- a/arch/powerpc/perf/power7-pmu.c +++ b/arch/powerpc/perf/power7-pmu.c @@ -416,7 +416,7 @@ static struct attribute *power7_pmu_format_attr[] = { NULL, }; -struct attribute_group power7_pmu_format_group = { +static struct attribute_group power7_pmu_format_group = { .name = "format", .attrs = power7_pmu_format_attr, }; diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index 5fde2b192fec..ab830d106ec5 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -204,7 +204,7 @@ static struct attribute *power8_pmu_format_attr[] = { NULL, }; -struct attribute_group power8_pmu_format_group = { +static struct attribute_group power8_pmu_format_group = { .name = "format", .attrs = power8_pmu_format_attr, }; diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 788346303852..8e9a81967ff8 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -119,7 +119,7 @@ static struct attribute *power9_pmu_format_attr[] = { NULL, }; -struct attribute_group power9_pmu_format_group = { +static struct attribute_group power9_pmu_format_group = { .name = "format", .attrs = power9_pmu_format_attr, }; diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c index 5ecce543103e..a886c2c22097 100644 --- a/arch/powerpc/platforms/44x/warp.c +++ b/arch/powerpc/platforms/44x/warp.c @@ -204,7 +204,7 @@ static void pika_setup_critical_temp(struct device_node *np, i2c_smbus_write_byte_data(client, 3, 0); /* Tlow */ irq = irq_of_parse_and_map(np, 0); - if (irq == NO_IRQ) { + if (!irq) { printk(KERN_ERR __FILE__ ": Unable to get ad7414 irq\n"); return; } diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c index 0035d146df73..fe4d4eac7427 100644 --- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c +++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c @@ -97,7 +97,7 @@ cpld_pic_get_irq(int offset, u8 ignore, u8 __iomem *statusp, status |= (ignore | mask); if (status == 0xff) - return NO_IRQ; + return 0; cpld_irq = ffz(status) + offset; @@ -110,14 +110,14 @@ static void cpld_pic_cascade(struct irq_desc *desc) irq = cpld_pic_get_irq(0, PCI_IGNORE, &cpld_regs->pci_status, &cpld_regs->pci_mask); - if (irq != NO_IRQ) { + if (irq) { generic_handle_irq(irq); return; } irq = cpld_pic_get_irq(8, MISC_IGNORE, &cpld_regs->misc_status, &cpld_regs->misc_mask); - if (irq != NO_IRQ) { + if (irq) { generic_handle_irq(irq); return; } @@ -177,7 +177,7 @@ mpc5121_ads_cpld_pic_init(void) goto end; cascade_irq = irq_of_parse_and_map(np, 0); - if (cascade_irq == NO_IRQ) + if (!cascade_irq) goto end; /* diff --git a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c index 8eb82b043dd8..cec3f88f153d 100644 --- a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c +++ b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c @@ -473,7 +473,7 @@ static int mpc512x_lpbfifo_probe(struct platform_device *pdev) } lpbfifo.irq = irq_of_parse_and_map(pdev->dev.of_node, 0); - if (lpbfifo.irq == NO_IRQ) { + if (!lpbfifo.irq) { dev_err(&pdev->dev, "mapping irq failed\n"); ret = -ENODEV; goto err0; @@ -528,7 +528,6 @@ static struct platform_driver mpc512x_lpbfifo_driver = { .remove = mpc512x_lpbfifo_remove, .driver = { .name = DRV_NAME, - .owner = THIS_MODULE, .of_match_table = mpc512x_lpbfifo_match, }, }; diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c index 4fe2074c88cb..fc98912f42cf 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c @@ -511,7 +511,7 @@ unsigned int mpc52xx_get_irq(void) irq |= (MPC52xx_IRQ_L1_PERP << MPC52xx_IRQ_L1_OFFSET); } } else { - return NO_IRQ; + return 0; } return irq_linear_revmap(mpc52xx_irqhost, irq); diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c index 60e89fc9c753..8b065bdf7412 100644 --- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c +++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c @@ -131,7 +131,7 @@ int __init pq2ads_pci_init_irq(void) } irq = irq_of_parse_and_map(np, 0); - if (irq == NO_IRQ) { + if (!irq) { printk(KERN_ERR "No interrupt in pci pic node.\n"); of_node_put(np); goto out; diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index dbcd0303afed..63c5ab6489c9 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -222,7 +222,6 @@ static const struct of_device_id mcu_of_match_table[] = { static struct i2c_driver mcu_driver = { .driver = { .name = "mcu-mpc8349emitx", - .owner = THIS_MODULE, .of_match_table = mcu_of_match_table, }, .probe = mcu_probe, diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c index 2ef03e7d248c..0d6a62fc5864 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c @@ -89,7 +89,7 @@ static int __init of_fsl_spi_probe(char *type, char *compatible, u32 sysclk, goto err; ret = of_irq_to_resource(np, 0, &res[1]); - if (ret == NO_IRQ) + if (!ret) goto err; pdev = platform_device_alloc("mpc83xx_spi", i); diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c index fcbea4b51a78..24717d060008 100644 --- a/arch/powerpc/platforms/83xx/suspend.c +++ b/arch/powerpc/platforms/83xx/suspend.c @@ -352,7 +352,7 @@ static int pmc_probe(struct platform_device *ofdev) return -ENODEV; pmc_irq = irq_of_parse_and_map(np, 0); - if (pmc_irq != NO_IRQ) { + if (pmc_irq) { ret = request_irq(pmc_irq, pmc_irq_handler, IRQF_SHARED, "pmc", ofdev); @@ -400,7 +400,7 @@ out_syscr: out_pmc: iounmap(pmc_regs); out: - if (pmc_irq != NO_IRQ) + if (pmc_irq) free_irq(pmc_irq, ofdev); return ret; diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c index 28720a4ded7b..954e5e8b14ef 100644 --- a/arch/powerpc/platforms/85xx/common.c +++ b/arch/powerpc/platforms/85xx/common.c @@ -76,7 +76,7 @@ void __init mpc85xx_cpm2_pic_init(void) return; } irq = irq_of_parse_and_map(np, 0); - if (irq == NO_IRQ) { + if (!irq) { of_node_put(np); printk(KERN_ERR "PIC init: got no IRQ for cpm cascade\n"); return; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c index 62f171c71c4c..86f20156178e 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c @@ -196,7 +196,7 @@ static void mpc85xx_8259_cascade_handler(struct irq_desc *desc) { unsigned int cascade_irq = i8259_irq(); - if (cascade_irq != NO_IRQ) + if (cascade_irq) /* handle an interrupt from the 8259 */ generic_handle_irq(cascade_irq); @@ -247,7 +247,7 @@ static int mpc85xx_cds_8259_attach(void) } cascade_irq = irq_of_parse_and_map(cascade_node, 0); - if (cascade_irq == NO_IRQ) { + if (!cascade_irq) { printk(KERN_ERR "Failed to map cascade interrupt\n"); return -ENXIO; } diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index 6bc07d837b1c..ed69c7ee1829 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -51,7 +51,7 @@ static void mpc85xx_8259_cascade(struct irq_desc *desc) struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq = i8259_irq(); - if (cascade_irq != NO_IRQ) { + if (cascade_irq) { generic_handle_irq(cascade_irq); } chip->irq_eoi(&desc->irq_data); @@ -96,7 +96,7 @@ void __init mpc85xx_ds_pic_init(void) } cascade_irq = irq_of_parse_and_map(cascade_node, 0); - if (cascade_irq == NO_IRQ) { + if (!cascade_irq) { printk(KERN_ERR "Failed to map cascade interrupt\n"); return; } diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c index b02d6a5bb035..82f8490b5aa7 100644 --- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c +++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c @@ -78,7 +78,7 @@ static inline unsigned int socrates_fpga_pic_get_irq(unsigned int irq) break; } if (i == 3) - return NO_IRQ; + return 0; raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); cause = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(i)); @@ -103,7 +103,7 @@ static void socrates_fpga_pic_cascade(struct irq_desc *desc) */ cascade_irq = socrates_fpga_pic_get_irq(irq); - if (cascade_irq != NO_IRQ) + if (cascade_irq) generic_handle_irq(cascade_irq); chip->irq_eoi(&desc->irq_data); } @@ -292,7 +292,7 @@ void socrates_fpga_pic_init(struct device_node *pic) for (i = 0; i < 3; i++) { socrates_fpga_irqs[i] = irq_of_parse_and_map(pic, i); - if (socrates_fpga_irqs[i] == NO_IRQ) { + if (!socrates_fpga_irqs[i]) { pr_warning("FPGA PIC: can't get irq%d.\n", i); continue; } diff --git a/arch/powerpc/platforms/86xx/pic.c b/arch/powerpc/platforms/86xx/pic.c index 845defa1fd19..a6c695fa4da0 100644 --- a/arch/powerpc/platforms/86xx/pic.c +++ b/arch/powerpc/platforms/86xx/pic.c @@ -22,7 +22,7 @@ static void mpc86xx_8259_cascade(struct irq_desc *desc) struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq = i8259_irq(); - if (cascade_irq != NO_IRQ) + if (cascade_irq) generic_handle_irq(cascade_irq); chip->irq_eoi(&desc->irq_data); @@ -58,7 +58,7 @@ void __init mpc86xx_init_irq(void) } cascade_irq = irq_of_parse_and_map(cascade_node, 0); - if (cascade_irq == NO_IRQ) { + if (!cascade_irq) { printk(KERN_ERR "Failed to map cascade interrupt\n"); return; } diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c index b1ab6e96cb31..f81069f79a94 100644 --- a/arch/powerpc/platforms/8xx/m8xx_setup.c +++ b/arch/powerpc/platforms/8xx/m8xx_setup.c @@ -241,6 +241,6 @@ void __init mpc8xx_pics_init(void) } irq = cpm_pic_init(); - if (irq != NO_IRQ) + if (irq) irq_set_chained_handler(irq, cpm_cascade); } diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index f32edec13fd1..ca2da30ad2ab 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -74,6 +74,7 @@ config PPC_BOOK3S_64 select HAVE_ARCH_TRANSPARENT_HUGEPAGE select ARCH_SUPPORTS_NUMA_BALANCING select IRQ_WORK + select HAVE_KERNEL_XZ config PPC_BOOK3E_64 bool "Embedded processors" @@ -86,6 +87,7 @@ endchoice choice prompt "CPU selection" depends on PPC64 + default POWER8_CPU if CPU_LITTLE_ENDIAN default GENERIC_CPU help This will create a kernel which is optimised for a particular CPU. diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index aed7714495c1..8b55c5f19d4c 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -271,7 +271,7 @@ static int axon_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) for_each_pci_msi_entry(entry, dev) { virq = irq_create_direct_mapping(msic->irq_domain); - if (virq == NO_IRQ) { + if (!virq) { dev_warn(&dev->dev, "axon_msi: virq allocation failed!\n"); return -1; @@ -293,7 +293,7 @@ static void axon_msi_teardown_msi_irqs(struct pci_dev *dev) dev_dbg(&dev->dev, "axon_msi: tearing down msi irqs\n"); for_each_pci_msi_entry(entry, dev) { - if (entry->irq == NO_IRQ) + if (!entry->irq) continue; irq_set_msi_desc(entry->irq, NULL); @@ -375,7 +375,7 @@ static int axon_msi_probe(struct platform_device *device) } virq = irq_of_parse_and_map(dn, 0); - if (virq == NO_IRQ) { + if (!virq) { printk(KERN_ERR "axon_msi: irq parse and map failed for %s\n", dn->full_name); goto out_free_fifo; diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c index 1428d583c238..b926438d73af 100644 --- a/arch/powerpc/platforms/cell/cbe_regs.c +++ b/arch/powerpc/platforms/cell/cbe_regs.c @@ -189,7 +189,7 @@ static struct device_node *cbe_get_be_node(int cpu_id) return NULL; } -void __init cbe_fill_regs_map(struct cbe_regs_map *map) +static void __init cbe_fill_regs_map(struct cbe_regs_map *map) { if(map->be_node) { struct device_node *be, *np; diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c index 9f609fc8d331..a6bbbaba14a3 100644 --- a/arch/powerpc/platforms/cell/interrupt.c +++ b/arch/powerpc/platforms/cell/interrupt.c @@ -123,7 +123,7 @@ static void iic_ioexc_cascade(struct irq_desc *desc) unsigned int cirq = irq_linear_revmap(iic_host, base | cascade); - if (cirq != NO_IRQ) + if (cirq) generic_handle_irq(cirq); } /* post-ack level interrupts */ @@ -153,10 +153,10 @@ static unsigned int iic_get_irq(void) *(unsigned long *) &pending = in_be64((u64 __iomem *) &iic->regs->pending_destr); if (!(pending.flags & CBE_IIC_IRQ_VALID)) - return NO_IRQ; + return 0; virq = irq_linear_revmap(iic_host, iic_pending_to_hwnum(pending)); - if (virq == NO_IRQ) - return NO_IRQ; + if (!virq) + return 0; iic->eoi_stack[++iic->eoi_ptr] = pending.prio; BUG_ON(iic->eoi_ptr > 15); return virq; @@ -187,18 +187,12 @@ void iic_message_pass(int cpu, int msg) out_be64(&per_cpu(cpu_iic, cpu).regs->generate, (0xf - msg) << 4); } -struct irq_domain *iic_get_irq_host(int node) -{ - return iic_host; -} -EXPORT_SYMBOL_GPL(iic_get_irq_host); - static void iic_request_ipi(int msg) { int virq; virq = irq_create_mapping(iic_host, iic_msg_to_irq(msg)); - if (virq == NO_IRQ) { + if (!virq) { printk(KERN_ERR "iic: failed to map IPI %s\n", smp_ipi_name[msg]); return; @@ -353,7 +347,7 @@ static int __init setup_iic(void) cascade |= 1 << IIC_IRQ_CLASS_SHIFT; cascade |= IIC_UNIT_IIC; cascade = irq_create_mapping(iic_host, cascade); - if (cascade == NO_IRQ) + if (!cascade) continue; /* * irq_data is a generic pointer that gets passed back diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index f7d1a4953ea0..7ff51f96a00e 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -411,7 +411,7 @@ static void cell_iommu_enable_hardware(struct cbe_iommu *iommu) virq = irq_create_mapping(NULL, IIC_IRQ_IOEX_ATI | (iommu->nid << IIC_IRQ_NODE_SHIFT)); - BUG_ON(virq == NO_IRQ); + BUG_ON(!virq); ret = request_irq(virq, ioc_interrupt, 0, iommu->name, iommu); BUG_ON(ret); @@ -651,7 +651,7 @@ static int dma_fixed_dma_supported(struct device *dev, u64 mask) static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask); -struct dma_map_ops dma_iommu_fixed_ops = { +static struct dma_map_ops dma_iommu_fixed_ops = { .alloc = dma_fixed_alloc_coherent, .free = dma_fixed_free_coherent, .map_sg = dma_fixed_map_sg, diff --git a/arch/powerpc/platforms/cell/pmu.c b/arch/powerpc/platforms/cell/pmu.c index 348a27b12512..e3ad0c38f017 100644 --- a/arch/powerpc/platforms/cell/pmu.c +++ b/arch/powerpc/platforms/cell/pmu.c @@ -385,7 +385,7 @@ static int __init cbe_init_pm_irq(void) for_each_online_node(node) { irq = irq_create_mapping(NULL, IIC_IRQ_IOEX_PMI | (node << IIC_IRQ_NODE_SHIFT)); - if (irq == NO_IRQ) { + if (!irq) { printk("ERROR: Unable to allocate irq for node %d\n", node); return -EINVAL; @@ -412,7 +412,7 @@ void cbe_sync_irq(int node) IIC_IRQ_IOEX_PMI | (node << IIC_IRQ_NODE_SHIFT)); - if (irq == NO_IRQ) { + if (!irq) { printk(KERN_WARNING "ERROR, unable to get existing irq %d " \ "for node %d\n", irq, node); return; diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c index 2d4f60c0119a..460ab392f0e7 100644 --- a/arch/powerpc/platforms/cell/ras.c +++ b/arch/powerpc/platforms/cell/ras.c @@ -298,7 +298,7 @@ int cbe_sysreset_hack(void) } #endif /* CONFIG_PPC_IBM_CELL_RESETBUTTON */ -int __init cbe_ptcal_init(void) +static int __init cbe_ptcal_init(void) { int ret; ptcal_start_tok = rtas_token("ibm,cbe-start-ptcal"); diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c index d06dcac66fcb..ff924af00e78 100644 --- a/arch/powerpc/platforms/cell/spider-pic.c +++ b/arch/powerpc/platforms/cell/spider-pic.c @@ -207,11 +207,11 @@ static void spider_irq_cascade(struct irq_desc *desc) cs = in_be32(pic->regs + TIR_CS) >> 24; if (cs == SPIDER_IRQ_INVALID) - virq = NO_IRQ; + virq = 0; else virq = irq_linear_revmap(pic->host, cs); - if (virq != NO_IRQ) + if (virq) generic_handle_irq(virq); chip->irq_eoi(&desc->irq_data); @@ -245,19 +245,19 @@ static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic) /* Now do the horrible hacks */ tmp = of_get_property(of_node, "#interrupt-cells", NULL); if (tmp == NULL) - return NO_IRQ; + return 0; intsize = *tmp; imap = of_get_property(of_node, "interrupt-map", &imaplen); if (imap == NULL || imaplen < (intsize + 1)) - return NO_IRQ; + return 0; iic = of_find_node_by_phandle(imap[intsize]); if (iic == NULL) - return NO_IRQ; + return 0; imap += intsize + 1; tmp = of_get_property(iic, "#interrupt-cells", NULL); if (tmp == NULL) { of_node_put(iic); - return NO_IRQ; + return 0; } intsize = *tmp; /* Assume unit is last entry of interrupt specifier */ @@ -266,7 +266,7 @@ static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic) tmp = of_get_property(iic, "ibm,interrupt-server-ranges", NULL); if (tmp == NULL) { of_node_put(iic); - return NO_IRQ; + return 0; } /* ugly as hell but works for now */ pic->node_id = (*tmp) >> 1; @@ -281,7 +281,7 @@ static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic) (pic->node_id << IIC_IRQ_NODE_SHIFT) | (2 << IIC_IRQ_CLASS_SHIFT) | unit); - if (virq == NO_IRQ) + if (!virq) printk(KERN_ERR "spider_pic: failed to map cascade !"); return virq; } @@ -318,7 +318,7 @@ static void __init spider_init_one(struct device_node *of_node, int chip, /* Hook up the cascade interrupt to the iic and nodeid */ virq = spider_find_cascade_and_node(pic); - if (virq == NO_IRQ) + if (!virq) return; irq_set_handler_data(virq, pic); irq_set_chained_handler(virq, spider_irq_cascade); diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c index bb4a8e07c229..e84d8fbc2e21 100644 --- a/arch/powerpc/platforms/cell/spu_base.c +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -402,7 +402,7 @@ static int spu_request_irqs(struct spu *spu) { int ret = 0; - if (spu->irqs[0] != NO_IRQ) { + if (spu->irqs[0]) { snprintf(spu->irq_c0, sizeof (spu->irq_c0), "spe%02d.0", spu->number); ret = request_irq(spu->irqs[0], spu_irq_class_0, @@ -410,7 +410,7 @@ static int spu_request_irqs(struct spu *spu) if (ret) goto bail0; } - if (spu->irqs[1] != NO_IRQ) { + if (spu->irqs[1]) { snprintf(spu->irq_c1, sizeof (spu->irq_c1), "spe%02d.1", spu->number); ret = request_irq(spu->irqs[1], spu_irq_class_1, @@ -418,7 +418,7 @@ static int spu_request_irqs(struct spu *spu) if (ret) goto bail1; } - if (spu->irqs[2] != NO_IRQ) { + if (spu->irqs[2]) { snprintf(spu->irq_c2, sizeof (spu->irq_c2), "spe%02d.2", spu->number); ret = request_irq(spu->irqs[2], spu_irq_class_2, @@ -429,10 +429,10 @@ static int spu_request_irqs(struct spu *spu) return 0; bail2: - if (spu->irqs[1] != NO_IRQ) + if (spu->irqs[1]) free_irq(spu->irqs[1], spu); bail1: - if (spu->irqs[0] != NO_IRQ) + if (spu->irqs[0]) free_irq(spu->irqs[0], spu); bail0: return ret; @@ -440,11 +440,11 @@ bail0: static void spu_free_irqs(struct spu *spu) { - if (spu->irqs[0] != NO_IRQ) + if (spu->irqs[0]) free_irq(spu->irqs[0], spu); - if (spu->irqs[1] != NO_IRQ) + if (spu->irqs[1]) free_irq(spu->irqs[1], spu); - if (spu->irqs[2] != NO_IRQ) + if (spu->irqs[2]) free_irq(spu->irqs[2], spu); } diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c index 21b4bfb97200..672d310dcf14 100644 --- a/arch/powerpc/platforms/cell/spu_manage.c +++ b/arch/powerpc/platforms/cell/spu_manage.c @@ -105,7 +105,10 @@ static int __init spu_map_interrupts_old(struct spu *spu, spu->irqs[2] = irq_create_mapping(NULL, IIC_IRQ_CLASS_2 | isrc); /* Right now, we only fail if class 2 failed */ - return spu->irqs[2] == NO_IRQ ? -EINVAL : 0; + if (!spu->irqs[2]) + return -EINVAL; + + return 0; } static void __iomem * __init spu_map_prop_old(struct spu *spu, @@ -191,7 +194,7 @@ static int __init spu_map_interrupts(struct spu *spu, struct device_node *np) pr_debug(" irq %d no 0x%x on %s\n", i, oirq.args[0], oirq.np->full_name); spu->irqs[i] = irq_create_of_mapping(&oirq); - if (spu->irqs[i] == NO_IRQ) { + if (!spu->irqs[i]) { pr_debug("spu_new: failed to map it !\n"); goto err; } @@ -202,7 +205,7 @@ err: pr_debug("failed to map irq %x for spu %s\n", *oirq.args, spu->name); for (; i >= 0; i--) { - if (spu->irqs[i] != NO_IRQ) + if (spu->irqs[i]) irq_dispose_mapping(spu->irqs[i]); } return ret; diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index bfb300633dfe..0ce1b45f02a8 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -368,7 +368,7 @@ static void chrp_8259_cascade(struct irq_desc *desc) struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq = i8259_irq(); - if (cascade_irq != NO_IRQ) + if (cascade_irq) generic_handle_irq(cascade_irq); chip->irq_eoi(&desc->irq_data); @@ -514,7 +514,7 @@ static void __init chrp_find_8259(void) } if (chrp_mpic != NULL) { cascade_irq = irq_of_parse_and_map(pic, 0); - if (cascade_irq == NO_IRQ) + if (!cascade_irq) printk(KERN_ERR "i8259: failed to map cascade irq\n"); else irq_set_chained_handler(cascade_irq, diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c index b7866e01483d..ade83829d5e8 100644 --- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c +++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c @@ -181,7 +181,7 @@ unsigned int flipper_pic_get_irq(void) irq_status = in_be32(io_base + FLIPPER_ICR) & in_be32(io_base + FLIPPER_IMR); if (irq_status == 0) - return NO_IRQ; /* no more IRQs pending */ + return 0; /* no more IRQs pending */ irq = __ffs(irq_status); return irq_linear_revmap(flipper_irq_host, irq); diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c index 9b7975706bfc..89c54de88b7a 100644 --- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c +++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c @@ -114,7 +114,7 @@ static unsigned int __hlwd_pic_get_irq(struct irq_domain *h) irq_status = in_be32(io_base + HW_BROADWAY_ICR) & in_be32(io_base + HW_BROADWAY_IMR); if (irq_status == 0) - return NO_IRQ; /* no more IRQs pending */ + return 0; /* no more IRQs pending */ irq = __ffs(irq_status); return irq_linear_revmap(h, irq); @@ -131,7 +131,7 @@ static void hlwd_pic_irq_cascade(struct irq_desc *desc) raw_spin_unlock(&desc->lock); virq = __hlwd_pic_get_irq(irq_domain); - if (virq != NO_IRQ) + if (virq) generic_handle_irq(virq); else pr_err("spurious interrupt!\n"); diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c index dafba1057a47..dfd310031549 100644 --- a/arch/powerpc/platforms/embedded6xx/holly.c +++ b/arch/powerpc/platforms/embedded6xx/holly.c @@ -26,7 +26,7 @@ #include <linux/tty.h> #include <linux/serial_core.h> #include <linux/of_platform.h> -#include <linux/module.h> +#include <linux/extable.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c index 80804f9916ee..f97bab8e37a2 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c +++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c @@ -23,7 +23,7 @@ #include <linux/pci.h> #include <linux/kdev_t.h> #include <linux/console.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/delay.h> #include <linux/irq.h> #include <linux/seq_file.h> diff --git a/arch/powerpc/platforms/embedded6xx/mvme5100.c b/arch/powerpc/platforms/embedded6xx/mvme5100.c index ed7321d6772e..8e3590941960 100644 --- a/arch/powerpc/platforms/embedded6xx/mvme5100.c +++ b/arch/powerpc/platforms/embedded6xx/mvme5100.c @@ -47,7 +47,7 @@ static void mvme5100_8259_cascade(struct irq_desc *desc) struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq = i8259_irq(); - if (cascade_irq != NO_IRQ) + if (cascade_irq) generic_handle_irq(cascade_irq); chip->irq_eoi(&desc->irq_data); @@ -84,7 +84,7 @@ static void __init mvme5100_pic_init(void) } cirq = irq_of_parse_and_map(cp, 0); - if (cirq == NO_IRQ) { + if (!cirq) { pr_warn("mvme5100_pic_init: no cascade interrupt?\n"); return; } diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c index a2f89e6326ce..a0589aac4163 100644 --- a/arch/powerpc/platforms/maple/pci.c +++ b/arch/powerpc/platforms/maple/pci.c @@ -552,7 +552,7 @@ void maple_pci_irq_fixup(struct pci_dev *dev) pci_bus_to_host(dev->bus) == u4_pcie) { printk(KERN_DEBUG "Fixup U4 PCIe IRQ\n"); dev->irq = irq_create_mapping(NULL, 1); - if (dev->irq != NO_IRQ) + if (dev->irq) irq_set_irq_type(dev->irq, IRQ_TYPE_LEVEL_LOW); } @@ -562,7 +562,7 @@ void maple_pci_irq_fixup(struct pci_dev *dev) if (dev->vendor == PCI_VENDOR_ID_AMD && dev->device == PCI_DEVICE_ID_AMD_8111_IDE && (dev->class & 5) != 5) { - dev->irq = NO_IRQ; + dev->irq = 0; } DBG(" <- maple_pci_irq_fixup\n"); @@ -648,7 +648,7 @@ int maple_pci_get_legacy_ide_irq(struct pci_dev *pdev, int channel) return defirq; } irq = irq_of_parse_and_map(np, channel & 0x1); - if (irq == NO_IRQ) { + if (!irq) { printk("Failed to map onboard IDE interrupt for channel %d\n", channel); return defirq; diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c index 3c30c7a4534d..b7f937563827 100644 --- a/arch/powerpc/platforms/maple/setup.c +++ b/arch/powerpc/platforms/maple/setup.c @@ -156,7 +156,7 @@ static void __noreturn maple_halt(void) } #ifdef CONFIG_SMP -struct smp_ops_t maple_smp_ops = { +static struct smp_ops_t maple_smp_ops = { .probe = smp_mpic_probe, .message_pass = smp_mpic_message_pass, .kick_cpu = smp_generic_kick_cpu, @@ -176,7 +176,7 @@ static void __init maple_use_rtas_reboot_and_halt_if_present(void) } } -void __init maple_setup_arch(void) +static void __init maple_setup_arch(void) { /* init to some ~sane value until calibrate_delay() runs */ loops_per_jiffy = 50000000; diff --git a/arch/powerpc/platforms/pasemi/Kconfig b/arch/powerpc/platforms/pasemi/Kconfig index 00d4b28cbb60..c7f1dbe94de7 100644 --- a/arch/powerpc/platforms/pasemi/Kconfig +++ b/arch/powerpc/platforms/pasemi/Kconfig @@ -14,6 +14,16 @@ config PPC_PASEMI menu "PA Semi PWRficient options" depends on PPC_PASEMI +config PPC_PASEMI_NEMO + bool "Nemo motherboard Support" + depends on PPC_PASEMI + select PPC_I8259 + help + This option enables support for the 'Nemo' motherboard + used in A-Eons's Amigaone X1000. This consists of some + device tree patches and workarounds for the SB600 South + Bridge that provides SATA/USB/Audio. + config PPC_PASEMI_IOMMU bool "PA Semi IOMMU support" depends on PPC_PASEMI diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c index ddf635000c6b..c23e60959aa8 100644 --- a/arch/powerpc/platforms/pasemi/gpio_mdio.c +++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c @@ -306,7 +306,7 @@ static struct platform_driver gpio_mdio_driver = }, }; -int gpio_mdio_init(void) +static int gpio_mdio_init(void) { struct device_node *np; @@ -326,7 +326,7 @@ int gpio_mdio_init(void) } module_init(gpio_mdio_init); -void gpio_mdio_exit(void) +static void gpio_mdio_exit(void) { platform_driver_unregister(&gpio_mdio_driver); if (gpio_regs) diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index c61667e8bb06..e74adc4e7fd8 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -199,7 +199,7 @@ static void pci_dma_dev_setup_pasemi(struct pci_dev *dev) set_iommu_table_base(&dev->dev, &iommu_table_iobmap); } -int __init iob_init(struct device_node *dn) +static int __init iob_init(struct device_node *dn) { unsigned long tmp; u32 regword; diff --git a/arch/powerpc/platforms/pasemi/misc.c b/arch/powerpc/platforms/pasemi/misc.c index e0ab299763c1..8571e7bf78b6 100644 --- a/arch/powerpc/platforms/pasemi/misc.c +++ b/arch/powerpc/platforms/pasemi/misc.c @@ -76,7 +76,7 @@ static int __init pasemi_register_i2c_devices(void) } info.irq = irq_of_parse_and_map(node, 0); - if (info.irq == NO_IRQ) + if (!info.irq) info.irq = -1; if (find_i2c_driver(node, &info) < 0) diff --git a/arch/powerpc/platforms/pasemi/msi.c b/arch/powerpc/platforms/pasemi/msi.c index d9af76342d99..d9cd510c8865 100644 --- a/arch/powerpc/platforms/pasemi/msi.c +++ b/arch/powerpc/platforms/pasemi/msi.c @@ -68,7 +68,7 @@ static void pasemi_msi_teardown_msi_irqs(struct pci_dev *pdev) pr_debug("pasemi_msi_teardown_msi_irqs, pdev %p\n", pdev); for_each_pci_msi_entry(entry, pdev) { - if (entry->irq == NO_IRQ) + if (!entry->irq) continue; hwirq = virq_to_hw(entry->irq); @@ -109,7 +109,7 @@ static int pasemi_msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) } virq = irq_create_mapping(msi_mpic->irqhost, hwirq); - if (virq == NO_IRQ) { + if (!virq) { pr_debug("pasemi_msi: failed mapping hwirq 0x%x\n", hwirq); msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap, hwirq, diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c index e86c1bd08f1f..3182400cf48f 100644 --- a/arch/powerpc/platforms/pasemi/setup.c +++ b/arch/powerpc/platforms/pasemi/setup.c @@ -59,7 +59,7 @@ struct mce_regs { static struct mce_regs mce_regs[MAX_MCE_REGS]; static int num_mce_regs; -static int nmi_virq = NO_IRQ; +static int nmi_virq = 0; static void __noreturn pas_restart(char *cmd) @@ -105,7 +105,7 @@ static void pas_take_timebase(void) arch_spin_unlock(&timebase_lock); } -struct smp_ops_t pas_smp_ops = { +static struct smp_ops_t pas_smp_ops = { .probe = smp_mpic_probe, .message_pass = smp_mpic_message_pass, .kick_cpu = smp_generic_kick_cpu, @@ -115,7 +115,7 @@ struct smp_ops_t pas_smp_ops = { }; #endif /* CONFIG_SMP */ -void __init pas_setup_arch(void) +static void __init pas_setup_arch(void) { #ifdef CONFIG_SMP /* Setup SMP callback */ @@ -264,7 +264,7 @@ static int pas_machine_check_handler(struct pt_regs *regs) srr0 = regs->nip; srr1 = regs->msr; - if (nmi_virq != NO_IRQ && mpic_get_mcirq() == nmi_virq) { + if (nmi_virq && mpic_get_mcirq() == nmi_virq) { printk(KERN_ERR "NMI delivered\n"); debugger(regs); mpic_end_irq(irq_get_irq_data(nmi_virq)); diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c index 6d6f277477aa..c8c217b7dd33 100644 --- a/arch/powerpc/platforms/powermac/low_i2c.c +++ b/arch/powerpc/platforms/powermac/low_i2c.c @@ -401,7 +401,7 @@ static int kw_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize, { struct pmac_i2c_host_kw *host = bus->hostdata; u8 mode_reg = host->speed; - int use_irq = host->irq != NO_IRQ && !bus->polled; + int use_irq = host->irq && !bus->polled; /* Setup mode & subaddress if any */ switch(bus->mode) { @@ -535,7 +535,7 @@ static struct pmac_i2c_host_kw *__init kw_i2c_host_init(struct device_node *np) break; } host->irq = irq_of_parse_and_map(np, 0); - if (host->irq == NO_IRQ) + if (!host->irq) printk(KERN_WARNING "low_i2c: Failed to map interrupt for %s\n", np->full_name); @@ -557,7 +557,7 @@ static struct pmac_i2c_host_kw *__init kw_i2c_host_init(struct device_node *np) */ if (request_irq(host->irq, kw_i2c_irq, IRQF_NO_SUSPEND, "keywest i2c", host)) - host->irq = NO_IRQ; + host->irq = 0; printk(KERN_INFO "KeyWest i2c @0x%08x irq %d %s\n", *addrp, host->irq, np->full_name); diff --git a/arch/powerpc/platforms/powermac/pfunc_base.c b/arch/powerpc/platforms/powermac/pfunc_base.c index e49d07f3d542..459138ed4571 100644 --- a/arch/powerpc/platforms/powermac/pfunc_base.c +++ b/arch/powerpc/platforms/powermac/pfunc_base.c @@ -26,7 +26,7 @@ static irqreturn_t macio_gpio_irq(int irq, void *data) static int macio_do_gpio_irq_enable(struct pmf_function *func) { unsigned int irq = irq_of_parse_and_map(func->node, 0); - if (irq == NO_IRQ) + if (!irq) return -EINVAL; return request_irq(irq, macio_gpio_irq, 0, func->node->name, func); } @@ -34,7 +34,7 @@ static int macio_do_gpio_irq_enable(struct pmf_function *func) static int macio_do_gpio_irq_disable(struct pmf_function *func) { unsigned int irq = irq_of_parse_and_map(func->node, 0); - if (irq == NO_IRQ) + if (!irq) return -EINVAL; free_irq(irq, func); return 0; diff --git a/arch/powerpc/platforms/powermac/pfunc_core.c b/arch/powerpc/platforms/powermac/pfunc_core.c index 43075081721f..695e8c4d4224 100644 --- a/arch/powerpc/platforms/powermac/pfunc_core.c +++ b/arch/powerpc/platforms/powermac/pfunc_core.c @@ -804,7 +804,7 @@ void pmf_unregister_driver(struct device_node *np) } EXPORT_SYMBOL_GPL(pmf_unregister_driver); -struct pmf_function *__pmf_find_function(struct device_node *target, +static struct pmf_function *__pmf_find_function(struct device_node *target, const char *name, u32 flags) { struct device_node *actor = of_node_get(target); diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 981546345033..f5f9ad7c3398 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -251,7 +251,7 @@ static unsigned int pmac_pic_get_irq(void) } raw_spin_unlock_irqrestore(&pmac_pic_lock, flags); if (unlikely(irq < 0)) - return NO_IRQ; + return 0; return irq_linear_revmap(pmac_pic_host, irq); } @@ -389,7 +389,7 @@ static void __init pmac_pic_probe_oldstyle(void) out_le32(&pmac_irq_hw[i]->enable, 0); /* Hookup cascade irq */ - if (slave && pmac_irq_cascade != NO_IRQ) + if (slave && pmac_irq_cascade) setup_irq(pmac_irq_cascade, &gatwick_cascade_action); printk(KERN_INFO "irq: System has %d possible interrupts\n", max_irqs); @@ -444,7 +444,7 @@ static void __init pmac_pic_setup_mpic_nmi(struct mpic *mpic) pswitch = of_find_node_by_name(NULL, "programmer-switch"); if (pswitch) { nmi_irq = irq_of_parse_and_map(pswitch, 0); - if (nmi_irq != NO_IRQ) { + if (nmi_irq) { mpic_irq_set_priority(nmi_irq, 9); setup_irq(nmi_irq, &xmon_action); } diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index 834868b9fdc9..c9eb7d6540ea 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -852,37 +852,33 @@ static void smp_core99_setup_cpu(int cpu_nr) #ifdef CONFIG_PPC64 #ifdef CONFIG_HOTPLUG_CPU -static int smp_core99_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +static unsigned int smp_core99_host_open; + +static int smp_core99_cpu_prepare(unsigned int cpu) { int rc; - switch(action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - /* Open i2c bus if it was used for tb sync */ - if (pmac_tb_clock_chip_host) { - rc = pmac_i2c_open(pmac_tb_clock_chip_host, 1); - if (rc) { - pr_err("Failed to open i2c bus for time sync\n"); - return notifier_from_errno(rc); - } + /* Open i2c bus if it was used for tb sync */ + if (pmac_tb_clock_chip_host && !smp_core99_host_open) { + rc = pmac_i2c_open(pmac_tb_clock_chip_host, 1); + if (rc) { + pr_err("Failed to open i2c bus for time sync\n"); + return notifier_from_errno(rc); } - break; - case CPU_ONLINE: - case CPU_UP_CANCELED: - /* Close i2c bus if it was used for tb sync */ - if (pmac_tb_clock_chip_host) - pmac_i2c_close(pmac_tb_clock_chip_host); - break; - default: - break; + smp_core99_host_open = 1; } - return NOTIFY_OK; + return 0; } -static struct notifier_block smp_core99_cpu_nb = { - .notifier_call = smp_core99_cpu_notify, -}; +static int smp_core99_cpu_online(unsigned int cpu) +{ + /* Close i2c bus if it was used for tb sync */ + if (pmac_tb_clock_chip_host && smp_core99_host_open) { + pmac_i2c_close(pmac_tb_clock_chip_host); + smp_core99_host_open = 0; + } + return 0; +} #endif /* CONFIG_HOTPLUG_CPU */ static void __init smp_core99_bringup_done(void) @@ -902,7 +898,11 @@ static void __init smp_core99_bringup_done(void) g5_phy_disable_cpu1(); } #ifdef CONFIG_HOTPLUG_CPU - register_cpu_notifier(&smp_core99_cpu_nb); + cpuhp_setup_state_nocalls(CPUHP_POWERPC_PMAC_PREPARE, + "powerpc/pmac:prepare", smp_core99_cpu_prepare, + NULL); + cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "powerpc/pmac:online", + smp_core99_cpu_online, NULL); #endif if (ppc_md.progress) @@ -979,7 +979,7 @@ static void pmac_cpu_die(void) #endif /* CONFIG_HOTPLUG_CPU */ /* Core99 Macs (dual G4s and G5s) */ -struct smp_ops_t core99_smp_ops = { +static struct smp_ops_t core99_smp_ops = { .message_pass = smp_mpic_message_pass, .probe = smp_core99_probe, #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 86544ea85dc3..2354ea51e871 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -763,7 +763,8 @@ int pnv_eeh_phb_reset(struct pci_controller *hose, int option) * reset followed by hot reset on root bus. So we also * need the PCI bus settlement delay. */ - rc = pnv_eeh_poll(phb->opal_id); + if (rc > 0) + rc = pnv_eeh_poll(phb->opal_id); if (option == EEH_RESET_DEACTIVATE) { if (system_state < SYSTEM_RUNNING) udelay(1000 * EEH_PE_RST_SETTLE_TIME); @@ -806,7 +807,8 @@ static int pnv_eeh_root_reset(struct pci_controller *hose, int option) goto out; /* Poll state of the PHB until the request is done */ - rc = pnv_eeh_poll(phb->opal_id); + if (rc > 0) + rc = pnv_eeh_poll(phb->opal_id); if (option == EEH_RESET_DEACTIVATE) msleep(EEH_PE_RST_SETTLE_TIME); out: @@ -1090,10 +1092,16 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option) } } - bus = eeh_pe_bus_get(pe); if (pe->type & EEH_PE_VF) return pnv_eeh_reset_vf_pe(pe, option); + bus = eeh_pe_bus_get(pe); + if (!bus) { + pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n", + __func__, pe->phb->global_number, pe->addr); + return -EIO; + } + if (pci_is_root_bus(bus) || pci_is_root_bus(bus->parent)) return pnv_eeh_root_reset(hose, option); @@ -1306,7 +1314,7 @@ static void pnv_eeh_get_and_dump_hub_diag(struct pci_controller *hose) return; } - switch (data->type) { + switch (be16_to_cpu(data->type)) { case OPAL_P7IOC_DIAG_TYPE_RGC: pr_info("P7IOC diag-data for RGC\n\n"); pnv_eeh_dump_hub_diag_common(data); @@ -1538,7 +1546,7 @@ static int pnv_eeh_next_error(struct eeh_pe **pe) /* Try best to clear it */ opal_pci_eeh_freeze_clear(phb->opal_id, - frozen_pe_no, + be64_to_cpu(frozen_pe_no), OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); ret = EEH_NEXT_ERR_NONE; } else if ((*pe)->state & EEH_PE_ISOLATED || diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index 00e1a0195c78..aec85e778028 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -115,7 +115,7 @@ static u64 dma_npu_get_required_mask(struct device *dev) return 0; } -struct dma_map_ops dma_npu_ops = { +static struct dma_map_ops dma_npu_ops = { .map_page = dma_npu_map_page, .map_sg = dma_npu_map_sg, .alloc = dma_npu_alloc, diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 2ee96431f736..4c827826c05e 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -370,6 +370,7 @@ static irqreturn_t process_dump(int irq, void *data) uint32_t dump_id, dump_size, dump_type; struct dump_obj *dump; char name[22]; + struct kobject *kobj; rc = dump_read_info(&dump_id, &dump_size, &dump_type); if (rc != OPAL_SUCCESS) @@ -381,8 +382,12 @@ static irqreturn_t process_dump(int irq, void *data) * that gracefully and not create two conflicting * entries. */ - if (kset_find_obj(dump_kset, name)) + kobj = kset_find_obj(dump_kset, name); + if (kobj) { + /* Drop reference added by kset_find_obj() */ + kobject_put(kobj); return 0; + } dump = create_dump_obj(dump_id, dump_size, dump_type); if (!dump) diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index 37f959bf392e..f2344cbd2f46 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -247,6 +247,7 @@ static irqreturn_t elog_event(int irq, void *data) uint64_t elog_type; int rc; char name[2+16+1]; + struct kobject *kobj; rc = opal_get_elog_size(&id, &size, &type); if (rc != OPAL_SUCCESS) { @@ -269,8 +270,12 @@ static irqreturn_t elog_event(int irq, void *data) * that gracefully and not create two conflicting * entries. */ - if (kset_find_obj(elog_kset, name)) + kobj = kset_find_obj(elog_kset, name); + if (kobj) { + /* Drop reference added by kset_find_obj() */ + kobject_put(kobj); return IRQ_HANDLED; + } create_elog_obj(log_id, elog_size, elog_type); diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c index ed8bba68a162..998316bf2dad 100644 --- a/arch/powerpc/platforms/powernv/opal-irqchip.c +++ b/arch/powerpc/platforms/powernv/opal-irqchip.c @@ -222,7 +222,7 @@ int __init opal_event_init(void) /* Get hardware and virtual IRQ */ irq = be32_to_cpup(irqs); virq = irq_create_mapping(NULL, irq); - if (virq == NO_IRQ) { + if (!virq) { pr_warn("Failed to map irq 0x%x\n", irq); continue; } @@ -260,7 +260,7 @@ machine_arch_initcall(powernv, opal_event_init); int opal_event_request(unsigned int opal_event_nr) { if (WARN_ON_ONCE(!opal_event_irqchip.domain)) - return NO_IRQ; + return 0; return irq_create_mapping(opal_event_irqchip.domain, opal_event_nr); } diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 3d29d40eb0e9..44d2d842cee7 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -208,6 +208,7 @@ OPAL_CALL(opal_pci_config_write_byte, OPAL_PCI_CONFIG_WRITE_BYTE); OPAL_CALL(opal_pci_config_write_half_word, OPAL_PCI_CONFIG_WRITE_HALF_WORD); OPAL_CALL(opal_pci_config_write_word, OPAL_PCI_CONFIG_WRITE_WORD); OPAL_CALL(opal_set_xive, OPAL_SET_XIVE); +OPAL_CALL_REAL(opal_rm_set_xive, OPAL_SET_XIVE); OPAL_CALL(opal_get_xive, OPAL_GET_XIVE); OPAL_CALL(opal_register_exception_handler, OPAL_REGISTER_OPAL_EXCEPTION_HANDLER); OPAL_CALL(opal_pci_eeh_freeze_status, OPAL_PCI_EEH_FREEZE_STATUS); diff --git a/arch/powerpc/platforms/powernv/pci-cxl.c b/arch/powerpc/platforms/powernv/pci-cxl.c index 1349a099c74c..94498a04558b 100644 --- a/arch/powerpc/platforms/powernv/pci-cxl.c +++ b/arch/powerpc/platforms/powernv/pci-cxl.c @@ -344,7 +344,7 @@ int pnv_cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) return (hwirq ? hwirq : -ENOMEM); virq = irq_create_mapping(NULL, hwirq); - if (virq == NO_IRQ) { + if (!virq) { pr_warn("%s: Failed to map cxl mode MSI to linux irq\n", pci_name(pdev)); return -ENOMEM; @@ -374,7 +374,7 @@ void pnv_cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev) return; for_each_pci_msi_entry(entry, pdev) { - if (entry->irq == NO_IRQ) + if (!entry->irq) continue; hwirq = virq_to_hw(entry->irq); irq_set_msi_desc(entry->irq, NULL); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index fd9444f9fb0c..d4b33dd2d9e7 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -124,11 +124,31 @@ static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r) r->start < (phb->ioda.m64_base + phb->ioda.m64_size)); } +static inline bool pnv_pci_is_m64_flags(unsigned long resource_flags) +{ + unsigned long flags = (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH); + + return (resource_flags & flags) == flags; +} + static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no) { + s64 rc; + phb->ioda.pe_array[pe_no].phb = phb; phb->ioda.pe_array[pe_no].pe_number = pe_no; + /* + * Clear the PE frozen state as it might be put into frozen state + * in the last PCI remove path. It's not harmful to do so when the + * PE is already in unfrozen state. + */ + rc = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no, + OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); + if (rc != OPAL_SUCCESS) + pr_warn("%s: Error %lld unfreezing PHB#%d-PE#%d\n", + __func__, rc, phb->hose->global_number, pe_no); + return &phb->ioda.pe_array[pe_no]; } @@ -149,7 +169,7 @@ static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no) static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb) { - unsigned long pe = phb->ioda.total_pe_num - 1; + long pe; for (pe = phb->ioda.total_pe_num - 1; pe >= 0; pe--) { if (!test_and_set_bit(pe, phb->ioda.pe_alloc)) @@ -162,11 +182,12 @@ static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb) static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe) { struct pnv_phb *phb = pe->phb; + unsigned int pe_num = pe->pe_number; WARN_ON(pe->pdev); memset(pe, 0, sizeof(struct pnv_ioda_pe)); - clear_bit(pe->pe_number, phb->ioda.pe_alloc); + clear_bit(pe_num, phb->ioda.pe_alloc); } /* The default M64 BAR is shared by all PEs */ @@ -409,7 +430,7 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb) struct device_node *dn = hose->dn; struct resource *res; u32 m64_range[2], i; - const u32 *r; + const __be32 *r; u64 pci_addr; if (phb->type != PNV_PHB_IODA1 && phb->type != PNV_PHB_IODA2) { @@ -2216,7 +2237,7 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group, pnv_pci_link_table_and_group(phb->hose->node, num, tbl, &pe->table_group); - pnv_pci_phb3_tce_invalidate_pe(pe); + pnv_pci_ioda2_tce_invalidate_pe(pe); return 0; } @@ -2354,7 +2375,7 @@ static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group, if (ret) pe_warn(pe, "Unmapping failed, ret = %ld\n", ret); else - pnv_pci_phb3_tce_invalidate_pe(pe); + pnv_pci_ioda2_tce_invalidate_pe(pe); pnv_pci_unlink_table_and_group(table_group->tables[num], table_group); @@ -2710,15 +2731,21 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, } #ifdef CONFIG_PCI_MSI -static void pnv_ioda2_msi_eoi(struct irq_data *d) +int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq) { - unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); - struct irq_chip *chip = irq_data_get_irq_chip(d); struct pnv_phb *phb = container_of(chip, struct pnv_phb, ioda.irq_chip); + + return opal_pci_msi_eoi(phb->opal_id, hw_irq); +} + +static void pnv_ioda2_msi_eoi(struct irq_data *d) +{ int64_t rc; + unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + struct irq_chip *chip = irq_data_get_irq_chip(d); - rc = opal_pci_msi_eoi(phb->opal_id, hw_irq); + rc = pnv_opal_pci_msi_eoi(chip, hw_irq); WARN_ON_ONCE(rc); icp_native_eoi(d); @@ -2748,6 +2775,16 @@ void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq) irq_set_chip(virq, &phb->ioda.irq_chip); } +/* + * Returns true iff chip is something that we could call + * pnv_opal_pci_msi_eoi for. + */ +bool is_pnv_opal_msi(struct irq_chip *chip) +{ + return chip->irq_eoi == pnv_ioda2_msi_eoi; +} +EXPORT_SYMBOL_GPL(is_pnv_opal_msi); + static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, unsigned int hwirq, unsigned int virq, unsigned int is_64, struct msi_msg *msg) @@ -2870,7 +2907,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) res = &pdev->resource[i + PCI_IOV_RESOURCES]; if (!res->flags || res->parent) continue; - if (!pnv_pci_is_m64(phb, res)) { + if (!pnv_pci_is_m64_flags(res->flags)) { dev_warn(&pdev->dev, "Don't support SR-IOV with" " non M64 VF BAR%d: %pR. \n", i, res); @@ -3025,6 +3062,38 @@ static void pnv_ioda_setup_pe_seg(struct pnv_ioda_pe *pe) } } +#ifdef CONFIG_DEBUG_FS +static int pnv_pci_diag_data_set(void *data, u64 val) +{ + struct pci_controller *hose; + struct pnv_phb *phb; + s64 ret; + + if (val != 1ULL) + return -EINVAL; + + hose = (struct pci_controller *)data; + if (!hose || !hose->private_data) + return -ENODEV; + + phb = hose->private_data; + + /* Retrieve the diag data from firmware */ + ret = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob, + PNV_PCI_DIAG_BUF_SIZE); + if (ret != OPAL_SUCCESS) + return -EIO; + + /* Print the diag data to the kernel log */ + pnv_pci_dump_phb_diag_data(phb->hose, phb->diag.blob); + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(pnv_pci_diag_data_fops, NULL, + pnv_pci_diag_data_set, "%llu\n"); + +#endif /* CONFIG_DEBUG_FS */ + static void pnv_pci_ioda_create_dbgfs(void) { #ifdef CONFIG_DEBUG_FS @@ -3040,9 +3109,14 @@ static void pnv_pci_ioda_create_dbgfs(void) sprintf(name, "PCI%04x", hose->global_number); phb->dbgfs = debugfs_create_dir(name, powerpc_debugfs_root); - if (!phb->dbgfs) + if (!phb->dbgfs) { pr_warning("%s: Error on creating debugfs on PHB#%x\n", __func__, hose->global_number); + continue; + } + + debugfs_create_file("dump_diag_regs", 0200, phb->dbgfs, hose, + &pnv_pci_diag_data_fops); } #endif /* CONFIG_DEBUG_FS */ } @@ -3095,7 +3169,7 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus, * alignment for any 64-bit resource, PCIe doesn't care and * bridges only do 64-bit prefetchable anyway. */ - if (phb->ioda.m64_segsize && (type & IORESOURCE_MEM_64)) + if (phb->ioda.m64_segsize && pnv_pci_is_m64_flags(type)) return phb->ioda.m64_segsize; if (type & IORESOURCE_MEM) return phb->ioda.m32_segsize; @@ -3402,12 +3476,6 @@ static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe) struct pnv_phb *phb = pe->phb; struct pnv_ioda_pe *slave, *tmp; - /* Release slave PEs in compound PE */ - if (pe->flags & PNV_IODA_PE_MASTER) { - list_for_each_entry_safe(slave, tmp, &pe->slaves, list) - pnv_ioda_release_pe(slave); - } - list_del(&pe->list); switch (phb->type) { case PNV_PHB_IODA1: @@ -3422,7 +3490,26 @@ static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe) pnv_ioda_release_pe_seg(pe); pnv_ioda_deconfigure_pe(pe->phb, pe); - pnv_ioda_free_pe(pe); + + /* Release slave PEs in the compound PE */ + if (pe->flags & PNV_IODA_PE_MASTER) { + list_for_each_entry_safe(slave, tmp, &pe->slaves, list) { + list_del(&slave->list); + pnv_ioda_free_pe(slave); + } + } + + /* + * The PE for root bus can be removed because of hotplug in EEH + * recovery for fenced PHB error. We need to mark the PE dead so + * that it can be populated again in PCI hot add path. The PE + * shouldn't be destroyed as it's the global reserved resource. + */ + if (phb->ioda.root_pe_populated && + phb->ioda.root_pe_idx == pe->pe_number) + phb->ioda.root_pe_populated = false; + else + pnv_ioda_free_pe(pe); } static void pnv_pci_release_device(struct pci_dev *pdev) @@ -3438,7 +3525,17 @@ static void pnv_pci_release_device(struct pci_dev *pdev) if (!pdn || pdn->pe_number == IODA_INVALID_PE) return; + /* + * PCI hotplug can happen as part of EEH error recovery. The @pdn + * isn't removed and added afterwards in this scenario. We should + * set the PE number in @pdn to an invalid one. Otherwise, the PE's + * device count is decreased on removing devices while failing to + * be increased on adding devices. It leads to unbalanced PE's device + * count and eventually make normal PCI hotplug path broken. + */ pe = &phb->ioda.pe_array[pdn->pe_number]; + pdn->pe_number = IODA_INVALID_PE; + WARN_ON(--pe->device_count < 0); if (pe->device_count == 0) pnv_ioda_release_pe(pe); @@ -3732,10 +3829,11 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, if (rc) pr_warning(" OPAL Error %ld performing IODA table reset !\n", rc); - /* If we're running in kdump kerenl, the previous kerenl never + /* + * If we're running in kdump kernel, the previous kernel never * shutdown PCI devices correctly. We already got IODA table * cleaned out. So we have to issue PHB reset to stop all PCI - * transactions from previous kerenl. + * transactions from previous kernel. */ if (is_kdump_kernel()) { pr_info(" Issue PHB reset ...\n"); diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index a21d831c1114..db7b8020f68e 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -186,7 +186,7 @@ int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) return -ENOSPC; } virq = irq_create_mapping(NULL, phb->msi_base + hwirq); - if (virq == NO_IRQ) { + if (!virq) { pr_warn("%s: Failed to map MSI to linux irq\n", pci_name(pdev)); msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, 1); @@ -217,7 +217,7 @@ void pnv_teardown_msi_irqs(struct pci_dev *pdev) return; for_each_pci_msi_entry(entry, pdev) { - if (entry->irq == NO_IRQ) + if (!entry->irq) continue; hwirq = virq_to_hw(entry->irq); irq_set_msi_desc(entry->irq, NULL); @@ -309,8 +309,8 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose, be64_to_cpu(data->dma1ErrorLog1)); for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) { - if ((data->pestA[i] >> 63) == 0 && - (data->pestB[i] >> 63) == 0) + if ((be64_to_cpu(data->pestA[i]) >> 63) == 0 && + (be64_to_cpu(data->pestB[i]) >> 63) == 0) continue; pr_info("PE[%3d] A/B: %016llx %016llx\n", diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c index 57caaf11a83f..e48462447ff0 100644 --- a/arch/powerpc/platforms/ps3/device-init.c +++ b/arch/powerpc/platforms/ps3/device-init.c @@ -62,7 +62,7 @@ static int __init ps3_register_lpm_devices(void) &dev->lpm.rights); if (result) { - pr_debug("%s:%d: ps3_repository_read_lpm_privleges failed \n", + pr_debug("%s:%d: ps3_repository_read_lpm_privileges failed\n", __func__, __LINE__); goto fail_read_repo; } diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c index b831638e6f4a..98f8c3611133 100644 --- a/arch/powerpc/platforms/ps3/interrupt.c +++ b/arch/powerpc/platforms/ps3/interrupt.c @@ -192,7 +192,7 @@ static int ps3_virq_setup(enum ps3_cpu_binding cpu, unsigned long outlet, *virq = irq_create_mapping(NULL, outlet); - if (*virq == NO_IRQ) { + if (!*virq) { FAIL("%s:%d: irq_create_mapping failed: outlet %lu\n", __func__, __LINE__, outlet); result = -ENOMEM; @@ -339,7 +339,7 @@ int ps3_event_receive_port_setup(enum ps3_cpu_binding cpu, unsigned int *virq) if (result) { FAIL("%s:%d: lv1_construct_event_receive_port failed: %s\n", __func__, __LINE__, ps3_result(result)); - *virq = NO_IRQ; + *virq = 0; return result; } @@ -418,7 +418,7 @@ int ps3_sb_event_receive_port_setup(struct ps3_system_bus_device *dev, " failed: %s\n", __func__, __LINE__, ps3_result(result)); ps3_event_receive_port_destroy(*virq); - *virq = NO_IRQ; + *virq = 0; return result; } @@ -724,12 +724,12 @@ static unsigned int ps3_get_irq(void) asm volatile("cntlzd %0,%1" : "=r" (plug) : "r" (x)); plug &= 0x3f; - if (unlikely(plug == NO_IRQ)) { + if (unlikely(!plug)) { DBG("%s:%d: no plug found: thread_id %llu\n", __func__, __LINE__, pd->thread_id); dump_bmp(&per_cpu(ps3_private, 0)); dump_bmp(&per_cpu(ps3_private, 1)); - return NO_IRQ; + return 0; } #if defined(DEBUG) diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c index 3c7707af3384..60154d08debf 100644 --- a/arch/powerpc/platforms/ps3/smp.c +++ b/arch/powerpc/platforms/ps3/smp.c @@ -91,7 +91,7 @@ static void __init ps3_smp_probe(void) result = smp_request_message_ipi(virqs[i], i); if (result) - virqs[i] = NO_IRQ; + virqs[i] = 0; else ps3_register_ipi_irq(cpu, virqs[i]); } @@ -112,7 +112,7 @@ void ps3_smp_cleanup_cpu(int cpu) for (i = 0; i < MSG_COUNT; i++) { /* Can't call free_irq from interrupt context. */ ps3_event_receive_port_destroy(virqs[i]); - virqs[i] = NO_IRQ; + virqs[i] = 0; } DBG(" <- %s:%d: (%d)\n", __func__, __LINE__, cpu); diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c index 492b2575e0d2..b54850845466 100644 --- a/arch/powerpc/platforms/ps3/spu.c +++ b/arch/powerpc/platforms/ps3/spu.c @@ -284,7 +284,7 @@ fail_alloc_2: fail_alloc_1: ps3_spe_irq_destroy(spu->irqs[0]); fail_alloc_0: - spu->irqs[0] = spu->irqs[1] = spu->irqs[2] = NO_IRQ; + spu->irqs[0] = spu->irqs[1] = spu->irqs[2] = 0; return result; } @@ -334,7 +334,7 @@ static int ps3_destroy_spu(struct spu *spu) ps3_spe_irq_destroy(spu->irqs[1]); ps3_spe_irq_destroy(spu->irqs[0]); - spu->irqs[0] = spu->irqs[1] = spu->irqs[2] = NO_IRQ; + spu->irqs[0] = spu->irqs[1] = spu->irqs[2] = 0; spu_unmap(spu); diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index 4748124faa10..423e450efe07 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -27,7 +27,7 @@ #include <asm/uaccess.h> #include <asm/rtas.h> -struct workqueue_struct *pseries_hp_wq; +static struct workqueue_struct *pseries_hp_wq; struct pseries_hp_work { struct work_struct work; @@ -377,7 +377,7 @@ static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog) return rc; } -void pseries_hp_work_fn(struct work_struct *work) +static void pseries_hp_work_fn(struct work_struct *work) { struct pseries_hp_work *hp_work = container_of(work, struct pseries_hp_work, work); @@ -413,6 +413,7 @@ void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog, queue_work(pseries_hp_wq, (struct work_struct *)work); } else { *rc = -ENOMEM; + kfree(hp_errlog_copy); complete(hotplug_done); } } diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c index a6ddca833119..32187dc76730 100644 --- a/arch/powerpc/platforms/pseries/event_sources.c +++ b/arch/powerpc/platforms/pseries/event_sources.c @@ -34,7 +34,7 @@ void request_event_sources_irqs(struct device_node *np, if (count > 15) break; virqs[count] = irq_create_of_mapping(&oirq); - if (virqs[count] == NO_IRQ) { + if (!virqs[count]) { pr_err("event-sources: Unable to allocate " "interrupt number for %s\n", np->full_name); diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 543a6386f3eb..326ef0dd6038 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -119,7 +119,7 @@ static void rtas_teardown_msi_irqs(struct pci_dev *pdev) struct msi_desc *entry; for_each_pci_msi_entry(entry, pdev) { - if (entry->irq == NO_IRQ) + if (!entry->irq) continue; irq_set_msi_desc(entry->irq, NULL); @@ -471,7 +471,7 @@ again: virq = irq_create_mapping(NULL, hwirq); - if (virq == NO_IRQ) { + if (!virq) { pr_debug("rtas_msi: Failed mapping hwirq %d\n", hwirq); return -ENOSPC; } @@ -490,7 +490,7 @@ again: static void rtas_msi_pci_irq_fixup(struct pci_dev *pdev) { /* No LSI -> leave MSIs (if any) configured */ - if (pdev->irq == NO_IRQ) { + if (!pdev->irq) { dev_dbg(&pdev->dev, "rtas_msi: no LSI, nothing to do.\n"); return; } diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index fe16a50700de..09eba5a9929a 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -119,6 +119,10 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) bus = bridge->bus; + /* Rely on the pcibios_free_controller_deferred() callback. */ + pci_set_host_bridge_release(bridge, pcibios_free_controller_deferred, + (void *) pci_bus_to_host(bus)); + dn = pcibios_get_phb_of_node(bus); if (!dn) return 0; diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 906dbaa97fe2..547fd13e4f8e 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -106,8 +106,11 @@ int remove_phb_dynamic(struct pci_controller *phb) release_resource(res); } - /* Free pci_controller data structure */ - pcibios_free_controller(phb); + /* + * The pci_controller data structure is freed by + * the pcibios_free_controller_deferred() callback; + * see pseries_root_bridge_prepare(). + */ return 0; } diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c index b502ab61aafa..7d28cabf1206 100644 --- a/arch/powerpc/platforms/pseries/scanlog.c +++ b/arch/powerpc/platforms/pseries/scanlog.c @@ -156,7 +156,7 @@ static int scanlog_release(struct inode * inode, struct file * file) return 0; } -const struct file_operations scanlog_fops = { +static const struct file_operations scanlog_fops = { .owner = THIS_MODULE, .read = scanlog_read, .write = scanlog_write, diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 4ffcaa6f8670..97aa3f332f24 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -41,7 +41,6 @@ #include <linux/root_dev.h> #include <linux/of.h> #include <linux/of_pci.h> -#include <linux/kexec.h> #include <asm/mmu.h> #include <asm/processor.h> @@ -66,6 +65,7 @@ #include <asm/eeh.h> #include <asm/reg.h> #include <asm/plpar_wrappers.h> +#include <asm/kexec.h> #include "pseries.h" @@ -114,7 +114,7 @@ static void pseries_8259_cascade(struct irq_desc *desc) struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq = i8259_irq(); - if (cascade_irq != NO_IRQ) + if (cascade_irq) generic_handle_irq(cascade_irq); chip->irq_eoi(&desc->irq_data); @@ -141,7 +141,7 @@ static void __init pseries_setup_i8259_cascade(void) } cascade = irq_of_parse_and_map(found, 0); - if (cascade == NO_IRQ) { + if (!cascade) { printk(KERN_ERR "pic: failed to map cascade interrupt"); return; } diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index 9144204442eb..ada29eaed6e2 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -240,7 +240,7 @@ static int axon_ram_probe(struct platform_device *device) device_add_disk(&device->dev, bank->disk); bank->irq_id = irq_of_parse_and_map(device->dev.of_node, 0); - if (bank->irq_id == NO_IRQ) { + if (!bank->irq_id) { dev_err(&device->dev, "Cannot access ECC interrupt ID\n"); rc = -EFAULT; goto failed; @@ -250,7 +250,7 @@ static int axon_ram_probe(struct platform_device *device) AXON_RAM_IRQ_FLAGS, bank->disk->disk_name, device); if (rc != 0) { dev_err(&device->dev, "Cannot register ECC interrupt handler\n"); - bank->irq_id = NO_IRQ; + bank->irq_id = 0; rc = -EFAULT; goto failed; } @@ -268,7 +268,7 @@ static int axon_ram_probe(struct platform_device *device) failed: if (bank != NULL) { - if (bank->irq_id != NO_IRQ) + if (bank->irq_id) free_irq(bank->irq_id, device); if (bank->disk != NULL) { if (bank->disk->major > 0) diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c index 6c110994d902..3c0eb9b25535 100644 --- a/arch/powerpc/sysdev/cpm1.c +++ b/arch/powerpc/sysdev/cpm1.c @@ -132,7 +132,7 @@ unsigned int cpm_pic_init(void) { struct device_node *np = NULL; struct resource res; - unsigned int sirq = NO_IRQ, hwirq, eirq; + unsigned int sirq = 0, hwirq, eirq; int ret; pr_debug("cpm_pic_init\n"); @@ -154,7 +154,7 @@ unsigned int cpm_pic_init(void) goto end; sirq = irq_of_parse_and_map(np, 0); - if (sirq == NO_IRQ) + if (!sirq) goto end; /* Initialize the CPM interrupt controller. */ @@ -168,7 +168,7 @@ unsigned int cpm_pic_init(void) cpm_pic_host = irq_domain_add_linear(np, 64, &cpm_pic_host_ops, NULL); if (cpm_pic_host == NULL) { printk(KERN_ERR "CPM2 PIC: failed to allocate irq host!\n"); - sirq = NO_IRQ; + sirq = 0; goto end; } @@ -182,7 +182,7 @@ unsigned int cpm_pic_init(void) } eirq = irq_of_parse_and_map(np, 0); - if (eirq == NO_IRQ) + if (!eirq) goto end; if (setup_irq(eirq, &cpm_error_irqaction)) @@ -534,7 +534,8 @@ struct cpm1_gpio16_chip { static void cpm1_gpio16_save_regs(struct of_mm_gpio_chip *mm_gc) { - struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm1_gpio16_chip *cpm1_gc = + container_of(mm_gc, struct cpm1_gpio16_chip, mm_gc); struct cpm_ioport16 __iomem *iop = mm_gc->regs; cpm1_gc->cpdata = in_be16(&iop->dat); @@ -649,7 +650,8 @@ struct cpm1_gpio32_chip { static void cpm1_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc) { - struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm1_gpio32_chip *cpm1_gc = + container_of(mm_gc, struct cpm1_gpio32_chip, mm_gc); struct cpm_ioport32b __iomem *iop = mm_gc->regs; cpm1_gc->cpdata = in_be32(&iop->dat); diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c index 911456d17713..947f42007734 100644 --- a/arch/powerpc/sysdev/cpm_common.c +++ b/arch/powerpc/sysdev/cpm_common.c @@ -94,7 +94,8 @@ struct cpm2_gpio32_chip { static void cpm2_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc) { - struct cpm2_gpio32_chip *cpm2_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm2_gpio32_chip *cpm2_gc = + container_of(mm_gc, struct cpm2_gpio32_chip, mm_gc); struct cpm2_ioports __iomem *iop = mm_gc->regs; cpm2_gc->cpdata = in_be32(&iop->dat); diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c index bffcc7a486a1..48866e6c1efb 100644 --- a/arch/powerpc/sysdev/ehv_pic.c +++ b/arch/powerpc/sysdev/ehv_pic.c @@ -155,7 +155,7 @@ static struct irq_chip ehv_pic_direct_eoi_irq_chip = { .irq_set_type = ehv_pic_set_irq_type, }; -/* Return an interrupt vector or NO_IRQ if no interrupt is pending. */ +/* Return an interrupt vector or 0 if no interrupt is pending. */ unsigned int ehv_pic_get_irq(void) { int irq; @@ -168,7 +168,7 @@ unsigned int ehv_pic_get_irq(void) ev_int_iack(0, &irq); /* legacy mode */ if (irq == 0xFFFF) /* 0xFFFF --> no irq is pending */ - return NO_IRQ; + return 0; /* * this will also setup revmap[] in the slow path for the first diff --git a/arch/powerpc/sysdev/fsl_gtm.c b/arch/powerpc/sysdev/fsl_gtm.c index 06ac3c61b3d0..a6f0b96ce2c9 100644 --- a/arch/powerpc/sysdev/fsl_gtm.c +++ b/arch/powerpc/sysdev/fsl_gtm.c @@ -406,7 +406,7 @@ static int __init fsl_gtm_init(void) unsigned int irq; irq = irq_of_parse_and_map(np, i); - if (irq == NO_IRQ) { + if (!irq) { pr_err("%s: not enough interrupts specified\n", np->full_name); goto err; diff --git a/arch/powerpc/sysdev/fsl_mpic_err.c b/arch/powerpc/sysdev/fsl_mpic_err.c index b83f32562a37..488ec453038a 100644 --- a/arch/powerpc/sysdev/fsl_mpic_err.c +++ b/arch/powerpc/sysdev/fsl_mpic_err.c @@ -115,8 +115,8 @@ static irqreturn_t fsl_error_int_handler(int irq, void *data) errint = __builtin_clz(eisr); cascade_irq = irq_linear_revmap(mpic->irqhost, mpic->err_int_vecs[errint]); - WARN_ON(cascade_irq == NO_IRQ); - if (cascade_irq != NO_IRQ) { + WARN_ON(!cascade_irq); + if (cascade_irq) { generic_handle_irq(cascade_irq); } else { eimr |= 1 << (31 - errint); @@ -134,7 +134,7 @@ void mpic_err_int_init(struct mpic *mpic, irq_hw_number_t irqnum) int ret; virq = irq_create_mapping(mpic->irqhost, irqnum); - if (virq == NO_IRQ) { + if (!virq) { pr_err("Error interrupt setup failed\n"); return; } diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 3a2be3676f43..8a244828782e 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -131,7 +131,7 @@ static void fsl_teardown_msi_irqs(struct pci_dev *pdev) irq_hw_number_t hwirq; for_each_pci_msi_entry(entry, pdev) { - if (entry->irq == NO_IRQ) + if (!entry->irq) continue; hwirq = virq_to_hw(entry->irq); msi_data = irq_get_chip_data(entry->irq); @@ -250,7 +250,7 @@ static int fsl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) virq = irq_create_mapping(msi_data->irqhost, hwirq); - if (virq == NO_IRQ) { + if (!virq) { dev_err(&pdev->dev, "fail mapping hwirq %i\n", hwirq); msi_bitmap_free_hwirqs(&msi_data->bitmap, hwirq, 1); rc = -ENOSPC; @@ -285,7 +285,7 @@ static irqreturn_t fsl_msi_cascade(int irq, void *data) msir_index = cascade_data->index; if (msir_index >= NR_MSI_REG_MAX) - cascade_irq = NO_IRQ; + cascade_irq = 0; switch (msi_data->feature & FSL_PIC_IP_MASK) { case FSL_PIC_IP_MPIC: @@ -315,7 +315,7 @@ static irqreturn_t fsl_msi_cascade(int irq, void *data) cascade_irq = irq_linear_revmap(msi_data->irqhost, msi_hwirq(msi_data, msir_index, intr_index + have_shift)); - if (cascade_irq != NO_IRQ) { + if (cascade_irq) { generic_handle_irq(cascade_irq); ret = IRQ_HANDLED; } @@ -337,7 +337,7 @@ static int fsl_of_msi_remove(struct platform_device *ofdev) if (msi->cascade_array[i]) { virq = msi->cascade_array[i]->virq; - BUG_ON(virq == NO_IRQ); + BUG_ON(!virq); free_irq(virq, msi->cascade_array[i]); kfree(msi->cascade_array[i]); @@ -362,7 +362,7 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev, int virt_msir, i, ret; virt_msir = irq_of_parse_and_map(dev->dev.of_node, irq_index); - if (virt_msir == NO_IRQ) { + if (!virt_msir) { dev_err(&dev->dev, "%s: Cannot translate IRQ index %d\n", __func__, irq_index); return 0; diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 68e7c0dd2e45..3cc7cace194a 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -23,7 +23,7 @@ */ #include <linux/init.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/types.h> #include <linux/dma-mapping.h> #include <linux/interrupt.h> diff --git a/arch/powerpc/sysdev/ge/ge_pic.c b/arch/powerpc/sysdev/ge/ge_pic.c index d57b77573068..02553a8ce191 100644 --- a/arch/powerpc/sysdev/ge/ge_pic.c +++ b/arch/powerpc/sysdev/ge/ge_pic.c @@ -102,7 +102,7 @@ static void gef_pic_cascade(struct irq_desc *desc) */ cascade_irq = gef_pic_get_irq(); - if (cascade_irq != NO_IRQ) + if (cascade_irq) generic_handle_irq(cascade_irq); chip->irq_eoi(&desc->irq_data); @@ -206,7 +206,7 @@ void __init gef_pic_init(struct device_node *np) /* Map controller */ gef_pic_cascade_irq = irq_of_parse_and_map(np, 0); - if (gef_pic_cascade_irq == NO_IRQ) { + if (!gef_pic_cascade_irq) { printk(KERN_ERR "SBC610: failed to map cascade interrupt"); return; } @@ -223,12 +223,12 @@ void __init gef_pic_init(struct device_node *np) /* * This is called when we receive an interrupt with apparently comes from this - * chip - check, returning the highest interrupt generated or return NO_IRQ + * chip - check, returning the highest interrupt generated or return 0. */ unsigned int gef_pic_get_irq(void) { u32 cause, mask, active; - unsigned int virq = NO_IRQ; + unsigned int virq = 0; int hwirq; cause = in_be32(gef_pic_irq_reg_base + GEF_PIC_INTR_STATUS); diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c index aa2c186d3115..bafb014e1a7e 100644 --- a/arch/powerpc/sysdev/i8259.c +++ b/arch/powerpc/sysdev/i8259.c @@ -68,9 +68,9 @@ unsigned int i8259_irq(void) if (!pci_intack) outb(0x0B, 0x20); /* ISR register */ if(~inb(0x20) & 0x80) - irq = NO_IRQ; + irq = 0; } else if (irq == 0xff) - irq = NO_IRQ; + irq = 0; if (lock) raw_spin_unlock(&i8259_lock); diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c index f76ee39cb337..f267ee0afc08 100644 --- a/arch/powerpc/sysdev/ipic.c +++ b/arch/powerpc/sysdev/ipic.c @@ -853,7 +853,7 @@ void ipic_clear_mcp_status(u32 mask) ipic_write(primary_ipic->regs, IPIC_SERMR, mask); } -/* Return an interrupt vector or NO_IRQ if no interrupt is pending. */ +/* Return an interrupt vector or 0 if no interrupt is pending. */ unsigned int ipic_get_irq(void) { int irq; @@ -864,7 +864,7 @@ unsigned int ipic_get_irq(void) irq = ipic_read(primary_ipic->regs, IPIC_SIVCR) & IPIC_SIVCR_VECTOR_MASK; if (irq == 0) /* 0 --> no irq is pending */ - return NO_IRQ; + return 0; return irq_linear_revmap(primary_ipic->irqhost, irq); } diff --git a/arch/powerpc/sysdev/mmio_nvram.c b/arch/powerpc/sysdev/mmio_nvram.c index 69f5814ae6d4..c31f634f1973 100644 --- a/arch/powerpc/sysdev/mmio_nvram.c +++ b/arch/powerpc/sysdev/mmio_nvram.c @@ -89,7 +89,7 @@ static ssize_t mmio_nvram_write(char *buf, size_t count, loff_t *index) return count; } -void mmio_nvram_write_val(int addr, unsigned char val) +static void mmio_nvram_write_val(int addr, unsigned char val) { unsigned long flags; diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c index b7cf7abff2eb..3e828b20c21e 100644 --- a/arch/powerpc/sysdev/mpc8xx_pic.c +++ b/arch/powerpc/sysdev/mpc8xx_pic.c @@ -79,7 +79,7 @@ unsigned int mpc8xx_get_irq(void) irq = in_be32(&siu_reg->sc_sivec) >> 26; if (irq == PIC_VEC_SPURRIOUS) - irq = NO_IRQ; + irq = 0; return irq_linear_revmap(mpc8xx_pic_host, irq); diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 7de45b2df366..4d48cecfedd1 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -1649,7 +1649,7 @@ void __init mpic_init(struct mpic *mpic) /* Check if this MPIC is chained from a parent interrupt controller */ if (mpic->flags & MPIC_SECONDARY) { int virq = irq_of_parse_and_map(mpic->node, 0); - if (virq != NO_IRQ) { + if (virq) { printk(KERN_INFO "%s: hooking up to IRQ %d\n", mpic->node->full_name, virq); irq_set_handler_data(virq, mpic); @@ -1778,13 +1778,13 @@ static unsigned int _mpic_get_one_irq(struct mpic *mpic, int reg) if (unlikely(src == mpic->spurious_vec)) { if (mpic->flags & MPIC_SPV_EOI) mpic_eoi(mpic); - return NO_IRQ; + return 0; } if (unlikely(mpic->protected && test_bit(src, mpic->protected))) { printk_ratelimited(KERN_WARNING "%s: Got protected source %d !\n", mpic->name, (int)src); mpic_eoi(mpic); - return NO_IRQ; + return 0; } return irq_linear_revmap(mpic->irqhost, src); @@ -1817,17 +1817,17 @@ unsigned int mpic_get_coreint_irq(void) if (unlikely(src == mpic->spurious_vec)) { if (mpic->flags & MPIC_SPV_EOI) mpic_eoi(mpic); - return NO_IRQ; + return 0; } if (unlikely(mpic->protected && test_bit(src, mpic->protected))) { printk_ratelimited(KERN_WARNING "%s: Got protected source %d !\n", mpic->name, (int)src); - return NO_IRQ; + return 0; } return irq_linear_revmap(mpic->irqhost, src); #else - return NO_IRQ; + return 0; #endif } @@ -1852,7 +1852,7 @@ void mpic_request_ipis(void) for (i = 0; i < 4; i++) { unsigned int vipi = irq_create_mapping(mpic->irqhost, mpic->ipi_vecs[0] + i); - if (vipi == NO_IRQ) { + if (!vipi) { printk(KERN_ERR "Failed to map %s\n", smp_ipi_name[i]); continue; } diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c index 3f165d972a0e..db2286be5d9a 100644 --- a/arch/powerpc/sysdev/mpic_msgr.c +++ b/arch/powerpc/sysdev/mpic_msgr.c @@ -238,7 +238,7 @@ static int mpic_msgr_probe(struct platform_device *dev) if (receive_mask & (1 << i)) { msgr->irq = irq_of_parse_and_map(np, irq_index); - if (msgr->irq == NO_IRQ) { + if (!msgr->irq) { dev_err(&dev->dev, "Missing interrupt specifier"); kfree(msgr); @@ -246,7 +246,7 @@ static int mpic_msgr_probe(struct platform_device *dev) } irq_index += 1; } else { - msgr->irq = NO_IRQ; + msgr->irq = 0; } mpic_msgrs[reg_number] = msgr; diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c index 2cbc7e29b85f..cfc1c57d760f 100644 --- a/arch/powerpc/sysdev/mpic_u3msi.c +++ b/arch/powerpc/sysdev/mpic_u3msi.c @@ -110,7 +110,7 @@ static void u3msi_teardown_msi_irqs(struct pci_dev *pdev) irq_hw_number_t hwirq; for_each_pci_msi_entry(entry, pdev) { - if (entry->irq == NO_IRQ) + if (!entry->irq) continue; hwirq = virq_to_hw(entry->irq); @@ -155,7 +155,7 @@ static int u3msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) msg.address_hi = addr >> 32; virq = irq_create_mapping(msi_mpic->irqhost, hwirq); - if (virq == NO_IRQ) { + if (!virq) { pr_debug("u3msi: failed mapping hwirq 0x%x\n", hwirq); msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap, hwirq, 1); return -ENOSPC; diff --git a/arch/powerpc/sysdev/mv64x60_pic.c b/arch/powerpc/sysdev/mv64x60_pic.c index 0f842dd16bcd..a79953deb489 100644 --- a/arch/powerpc/sysdev/mv64x60_pic.c +++ b/arch/powerpc/sysdev/mv64x60_pic.c @@ -272,7 +272,7 @@ unsigned int mv64x60_get_irq(void) u32 cause; int level1; irq_hw_number_t hwirq; - int virq = NO_IRQ; + int virq = 0; cause = in_le32(mv64x60_irq_reg_base + MV64X60_IC_CPU0_SELECT_CAUSE); if (cause & MV64X60_SELECT_CAUSE_HIGH) { diff --git a/arch/powerpc/sysdev/pmi.c b/arch/powerpc/sysdev/pmi.c index 8a0b77a3ec0c..9ea6a221d9d5 100644 --- a/arch/powerpc/sysdev/pmi.c +++ b/arch/powerpc/sysdev/pmi.c @@ -158,7 +158,7 @@ static int pmi_of_probe(struct platform_device *dev) data->dev = dev; data->irq = irq_of_parse_and_map(np, 0); - if (data->irq == NO_IRQ) { + if (!data->irq) { printk(KERN_ERR "pmi: invalid interrupt.\n"); rc = -EFAULT; goto error_cleanup_iomap; diff --git a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c index 52a93dcae262..9926ad67af76 100644 --- a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c +++ b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c @@ -60,7 +60,7 @@ static int hsta_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) } hwirq = ppc4xx_hsta_msi.irq_map[irq]; - if (hwirq == NO_IRQ) { + if (!hwirq) { pr_err("%s: Failed mapping irq %d\n", __func__, irq); return -EINVAL; } @@ -110,7 +110,7 @@ static void hsta_teardown_msi_irqs(struct pci_dev *dev) int irq; for_each_pci_msi_entry(entry, dev) { - if (entry->irq == NO_IRQ) + if (!entry->irq) continue; irq = hsta_find_hwirq_offset(entry->irq); @@ -166,7 +166,7 @@ static int hsta_msi_probe(struct platform_device *pdev) for (irq = 0; irq < irq_count; irq++) { ppc4xx_hsta_msi.irq_map[irq] = irq_of_parse_and_map(dev->of_node, irq); - if (ppc4xx_hsta_msi.irq_map[irq] == NO_IRQ) { + if (!ppc4xx_hsta_msi.irq_map[irq]) { dev_err(dev, "Unable to map IRQ\n"); ret = -EINVAL; goto out2; diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c index 8fb806135043..590dab4f47d6 100644 --- a/arch/powerpc/sysdev/ppc4xx_msi.c +++ b/arch/powerpc/sysdev/ppc4xx_msi.c @@ -102,7 +102,7 @@ static int ppc4xx_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) __func__); } virq = irq_of_parse_and_map(msi_data->msi_dev, int_no); - if (virq == NO_IRQ) { + if (!virq) { dev_err(&dev->dev, "%s: fail mapping irq\n", __func__); msi_bitmap_free_hwirqs(&msi_data->bitmap, int_no, 1); return -ENOSPC; @@ -129,7 +129,7 @@ void ppc4xx_teardown_msi_irqs(struct pci_dev *dev) dev_dbg(&dev->dev, "PCIE-MSI: tearing down msi irqs\n"); for_each_pci_msi_entry(entry, dev) { - if (entry->irq == NO_IRQ) + if (!entry->irq) continue; hwirq = virq_to_hw(entry->irq); irq_set_msi_desc(entry->irq, NULL); @@ -201,7 +201,7 @@ static int ppc4xx_of_msi_remove(struct platform_device *dev) for (i = 0; i < msi_irqs; i++) { virq = msi->msi_virqs[i]; - if (virq != NO_IRQ) + if (virq) irq_dispose_mapping(virq); } diff --git a/arch/powerpc/sysdev/ppc4xx_soc.c b/arch/powerpc/sysdev/ppc4xx_soc.c index 5c77c9ba33aa..d41134d2f786 100644 --- a/arch/powerpc/sysdev/ppc4xx_soc.c +++ b/arch/powerpc/sysdev/ppc4xx_soc.c @@ -109,7 +109,7 @@ static int __init ppc4xx_l2c_probe(void) /* Get and map irq number from device tree */ irq = irq_of_parse_and_map(np, 0); - if (irq == NO_IRQ) { + if (!irq) { printk(KERN_ERR "irq_of_parse_and_map failed\n"); of_node_put(np); return -ENODEV; diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c index 379de955aae3..57c971b7839c 100644 --- a/arch/powerpc/sysdev/tsi108_pci.c +++ b/arch/powerpc/sysdev/tsi108_pci.c @@ -433,7 +433,7 @@ void tsi108_irq_cascade(struct irq_desc *desc) struct irq_chip *chip = irq_desc_get_chip(desc); unsigned int cascade_irq = get_pci_source(); - if (cascade_irq != NO_IRQ) + if (cascade_irq) generic_handle_irq(cascade_irq); chip->irq_eoi(&desc->irq_data); diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c index 6893d8f236df..a00949f3e378 100644 --- a/arch/powerpc/sysdev/uic.c +++ b/arch/powerpc/sysdev/uic.c @@ -319,7 +319,7 @@ void __init uic_init_tree(void) } } -/* Return an interrupt vector or NO_IRQ if no interrupt is pending. */ +/* Return an interrupt vector or 0 if no interrupt is pending. */ unsigned int uic_get_irq(void) { u32 msr; diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c index c1917cf67c3d..e7fa26c4ff73 100644 --- a/arch/powerpc/sysdev/xics/icp-hv.c +++ b/arch/powerpc/sysdev/xics/icp-hv.c @@ -112,10 +112,10 @@ static unsigned int icp_hv_get_irq(void) unsigned int irq; if (vec == XICS_IRQ_SPURIOUS) - return NO_IRQ; + return 0; irq = irq_find_mapping(xics_host, vec); - if (likely(irq != NO_IRQ)) { + if (likely(irq)) { xics_push_cppr(vec); return irq; } @@ -126,7 +126,7 @@ static unsigned int icp_hv_get_irq(void) /* We might learn about it later, so EOI it */ icp_hv_set_xirr(xirr); - return NO_IRQ; + return 0; } static void icp_hv_set_cpu_priority(unsigned char cppr) diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c index afdf62f2a695..8a6a043e239b 100644 --- a/arch/powerpc/sysdev/xics/icp-native.c +++ b/arch/powerpc/sysdev/xics/icp-native.c @@ -124,10 +124,10 @@ static unsigned int icp_native_get_irq(void) unsigned int irq; if (vec == XICS_IRQ_SPURIOUS) - return NO_IRQ; + return 0; irq = irq_find_mapping(xics_host, vec); - if (likely(irq != NO_IRQ)) { + if (likely(irq)) { xics_push_cppr(vec); return irq; } @@ -138,7 +138,7 @@ static unsigned int icp_native_get_irq(void) /* We might learn about it later, so EOI it */ icp_native_set_xirr(xirr); - return NO_IRQ; + return 0; } #ifdef CONFIG_SMP diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c index 57d72f10a97f..d38e86fd5720 100644 --- a/arch/powerpc/sysdev/xics/icp-opal.c +++ b/arch/powerpc/sysdev/xics/icp-opal.c @@ -23,10 +23,10 @@ static void icp_opal_teardown_cpu(void) { - int cpu = smp_processor_id(); + int hw_cpu = hard_smp_processor_id(); /* Clear any pending IPI */ - opal_int_set_mfrr(cpu, 0xff); + opal_int_set_mfrr(hw_cpu, 0xff); } static void icp_opal_flush_ipi(void) @@ -51,14 +51,14 @@ static unsigned int icp_opal_get_irq(void) rc = opal_int_get_xirr(&xirr, false); if (rc < 0) - return NO_IRQ; + return 0; xirr = be32_to_cpu(xirr); vec = xirr & 0x00ffffff; if (vec == XICS_IRQ_SPURIOUS) - return NO_IRQ; + return 0; irq = irq_find_mapping(xics_host, vec); - if (likely(irq != NO_IRQ)) { + if (likely(irq)) { xics_push_cppr(vec); return irq; } @@ -69,7 +69,7 @@ static unsigned int icp_opal_get_irq(void) /* We might learn about it later, so EOI it */ opal_int_eoi(xirr); - return NO_IRQ; + return 0; } static void icp_opal_set_cpu_priority(unsigned char cppr) @@ -101,14 +101,16 @@ static void icp_opal_eoi(struct irq_data *d) static void icp_opal_cause_ipi(int cpu, unsigned long data) { - opal_int_set_mfrr(cpu, IPI_PRIORITY); + int hw_cpu = get_hard_smp_processor_id(cpu); + + opal_int_set_mfrr(hw_cpu, IPI_PRIORITY); } static irqreturn_t icp_opal_ipi_action(int irq, void *dev_id) { - int cpu = smp_processor_id(); + int hw_cpu = hard_smp_processor_id(); - opal_int_set_mfrr(cpu, 0xff); + opal_int_set_mfrr(hw_cpu, 0xff); return smp_ipi_demux(); } diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index 9d530f479588..69d858e51ac7 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -131,7 +131,7 @@ static void xics_request_ipi(void) unsigned int ipi; ipi = irq_create_mapping(xics_host, XICS_IPI); - BUG_ON(ipi == NO_IRQ); + BUG_ON(!ipi); /* * IPIs are marked IRQF_PERCPU. The handler was set in map. diff --git a/arch/powerpc/xmon/spr_access.S b/arch/powerpc/xmon/spr_access.S index 84ad74213c83..7d8b0e8ed6d9 100644 --- a/arch/powerpc/xmon/spr_access.S +++ b/arch/powerpc/xmon/spr_access.S @@ -2,12 +2,12 @@ /* unsigned long xmon_mfspr(sprn, default_value) */ _GLOBAL(xmon_mfspr) - ld r5, .Lmfspr_table@got(r2) + PPC_LL r5, .Lmfspr_table@got(r2) b xmon_mxspr /* void xmon_mtspr(sprn, new_value) */ _GLOBAL(xmon_mtspr) - ld r5, .Lmtspr_table@got(r2) + PPC_LL r5, .Lmtspr_table@got(r2) b xmon_mxspr /* diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index e751fe25d6ab..deeadfa291ba 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -68,12 +68,12 @@ config DEBUG_RODATA config S390 def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV select ARCH_HAS_SG_CHAIN + select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK select ARCH_INLINE_READ_LOCK_BH @@ -110,6 +110,7 @@ config S390 select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANTS_PROT_NUMA_PROT_NONE + select ARCH_WANTS_UBSAN_NO_NULL select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS2 @@ -137,6 +138,7 @@ config S390 select HAVE_DMA_API_DEBUG select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS + select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_EXIT_THREAD select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 224b42734f0d..54e00526b8df 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -46,6 +46,8 @@ cflags-$(CONFIG_MARCH_Z196_TUNE) += -mtune=z196 cflags-$(CONFIG_MARCH_ZEC12_TUNE) += -mtune=zEC12 cflags-$(CONFIG_MARCH_Z13_TUNE) += -mtune=z13 +cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include + #KBUILD_IMAGE is necessary for make rpm KBUILD_IMAGE :=arch/s390/boot/image diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 15c94246b600..f587c4811faf 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -542,7 +542,7 @@ static int __init appldata_init(void) rc = PTR_ERR(appldata_pdev); goto out_driver; } - appldata_wq = create_singlethread_workqueue("appldata"); + appldata_wq = alloc_ordered_workqueue("appldata", 0); if (!appldata_wq) { rc = -ENOMEM; goto out_device; diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile index 33ba697c782d..0daa070d6c9d 100644 --- a/arch/s390/boot/compressed/Makefile +++ b/arch/s390/boot/compressed/Makefile @@ -17,6 +17,7 @@ KBUILD_CFLAGS += $(call cc-option,-mpacked-stack) KBUILD_CFLAGS += $(call cc-option,-ffreestanding) GCOV_PROFILE := n +UBSAN_SANITIZE := n OBJECTS := $(addprefix $(objtree)/arch/s390/kernel/, head.o sclp.o ebcdic.o als.o) OBJECTS += $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig index 26e0c7f08814..45968686f918 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/default_defconfig @@ -260,7 +260,6 @@ CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NF_TABLES_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NF_TABLES_ARP=m -CONFIG_NF_NAT_IPV4=m CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m @@ -269,6 +268,8 @@ CONFIG_IP_NF_MATCH_RPFILTER=m CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_CLUSTERIP=m CONFIG_IP_NF_TARGET_ECN=m @@ -281,7 +282,6 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NF_TABLES_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m -CONFIG_NF_NAT_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m @@ -299,6 +299,8 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m CONFIG_IP6_NF_SECURITY=m +CONFIG_IP6_NF_NAT=m +CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_NF_TABLES_BRIDGE=m CONFIG_NET_SCTPPROBE=m CONFIG_RDS=m @@ -359,6 +361,7 @@ CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_DNS_RESOLVER=y +CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m CONFIG_NET_TCPPROBE=m @@ -409,6 +412,7 @@ CONFIG_MD_FAULTY=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m +CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -428,6 +432,7 @@ CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_TUN=m CONFIG_VETH=m @@ -453,7 +458,6 @@ CONFIG_PPP_SYNC_TTY=m # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set -CONFIG_DEVPTS_MULTIPLE_INSTANCES=y CONFIG_LEGACY_PTY_COUNT=0 CONFIG_HW_RANDOM_VIRTIO=m CONFIG_RAW_DRIVER=m @@ -495,6 +499,7 @@ CONFIG_QFMT_V2=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_FSCACHE=m CONFIG_CACHEFILES=m CONFIG_ISO9660_FS=y @@ -602,7 +607,6 @@ CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_IRQSOFF_TRACER=y CONFIG_PREEMPT_TRACER=y CONFIG_SCHED_TRACER=y diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig index 24879dab47bc..1dd05e345c4d 100644 --- a/arch/s390/configs/gcov_defconfig +++ b/arch/s390/configs/gcov_defconfig @@ -15,6 +15,8 @@ CONFIG_NUMA_BALANCING=y CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y CONFIG_BLK_CGROUP=y +CONFIG_CFS_BANDWIDTH=y +CONFIG_RT_GROUP_SCHED=y CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_HUGETLB=y @@ -255,7 +257,6 @@ CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NF_TABLES_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NF_TABLES_ARP=m -CONFIG_NF_NAT_IPV4=m CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m @@ -264,6 +265,8 @@ CONFIG_IP_NF_MATCH_RPFILTER=m CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_CLUSTERIP=m CONFIG_IP_NF_TARGET_ECN=m @@ -276,7 +279,6 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NF_TABLES_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m -CONFIG_NF_NAT_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m @@ -294,6 +296,8 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m CONFIG_IP6_NF_SECURITY=m +CONFIG_IP6_NF_NAT=m +CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_NF_TABLES_BRIDGE=m CONFIG_NET_SCTPPROBE=m CONFIG_RDS=m @@ -353,6 +357,7 @@ CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_DNS_RESOLVER=y +CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m CONFIG_NET_TCPPROBE=m @@ -403,6 +408,7 @@ CONFIG_MD_FAULTY=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m +CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -422,6 +428,7 @@ CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_TUN=m CONFIG_VETH=m @@ -447,7 +454,6 @@ CONFIG_PPP_SYNC_TTY=m # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set -CONFIG_DEVPTS_MULTIPLE_INSTANCES=y CONFIG_LEGACY_PTY_COUNT=0 CONFIG_HW_RANDOM_VIRTIO=m CONFIG_RAW_DRIVER=m @@ -487,6 +493,7 @@ CONFIG_QFMT_V2=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_FSCACHE=m CONFIG_CACHEFILES=m CONFIG_ISO9660_FS=y @@ -552,7 +559,6 @@ CONFIG_NOTIFIER_ERROR_INJECTION=m CONFIG_CPU_NOTIFIER_ERROR_INJECT=m CONFIG_PM_NOTIFIER_ERROR_INJECT=m CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_BLK_DEV_IO_TRACE=y # CONFIG_KPROBE_EVENT is not set CONFIG_TRACE_ENUM_MAP_FILE=y diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index a5c1e5f2a0ca..29d1178666f0 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -16,6 +16,8 @@ CONFIG_NUMA_BALANCING=y CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y CONFIG_BLK_CGROUP=y +CONFIG_CFS_BANDWIDTH=y +CONFIG_RT_GROUP_SCHED=y CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_HUGETLB=y @@ -255,7 +257,6 @@ CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NF_TABLES_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NF_TABLES_ARP=m -CONFIG_NF_NAT_IPV4=m CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m @@ -264,6 +265,8 @@ CONFIG_IP_NF_MATCH_RPFILTER=m CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_CLUSTERIP=m CONFIG_IP_NF_TARGET_ECN=m @@ -276,7 +279,6 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NF_TABLES_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m -CONFIG_NF_NAT_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m @@ -294,6 +296,8 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m CONFIG_IP6_NF_SECURITY=m +CONFIG_IP6_NF_NAT=m +CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_NF_TABLES_BRIDGE=m CONFIG_NET_SCTPPROBE=m CONFIG_RDS=m @@ -353,6 +357,7 @@ CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_DNS_RESOLVER=y +CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m CONFIG_NET_TCPPROBE=m @@ -403,6 +408,7 @@ CONFIG_MD_FAULTY=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m +CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -422,6 +428,7 @@ CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_TUN=m CONFIG_VETH=m @@ -447,7 +454,6 @@ CONFIG_PPP_SYNC_TTY=m # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set -CONFIG_DEVPTS_MULTIPLE_INSTANCES=y CONFIG_LEGACY_PTY_COUNT=0 CONFIG_HW_RANDOM_VIRTIO=m CONFIG_RAW_DRIVER=m @@ -488,6 +494,7 @@ CONFIG_QFMT_V2=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_FSCACHE=m CONFIG_CACHEFILES=m CONFIG_ISO9660_FS=y @@ -549,7 +556,6 @@ CONFIG_TIMER_STATS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_STACK_TRACER=y diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 2ea18b050309..303d28eb03a2 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -31,69 +31,29 @@ #include <crypto/xts.h> #include <asm/cpacf.h> -#define AES_KEYLEN_128 1 -#define AES_KEYLEN_192 2 -#define AES_KEYLEN_256 4 - static u8 *ctrblk; static DEFINE_SPINLOCK(ctrblk_lock); -static char keylen_flag; + +static cpacf_mask_t km_functions, kmc_functions, kmctr_functions; struct s390_aes_ctx { u8 key[AES_MAX_KEY_SIZE]; - long enc; - long dec; int key_len; + unsigned long fc; union { struct crypto_skcipher *blk; struct crypto_cipher *cip; } fallback; }; -struct pcc_param { - u8 key[32]; - u8 tweak[16]; - u8 block[16]; - u8 bit[16]; - u8 xts[16]; -}; - struct s390_xts_ctx { u8 key[32]; u8 pcc_key[32]; - long enc; - long dec; int key_len; + unsigned long fc; struct crypto_skcipher *fallback; }; -/* - * Check if the key_len is supported by the HW. - * Returns 0 if it is, a positive number if it is not and software fallback is - * required or a negative number in case the key size is not valid - */ -static int need_fallback(unsigned int key_len) -{ - switch (key_len) { - case 16: - if (!(keylen_flag & AES_KEYLEN_128)) - return 1; - break; - case 24: - if (!(keylen_flag & AES_KEYLEN_192)) - return 1; - break; - case 32: - if (!(keylen_flag & AES_KEYLEN_256)) - return 1; - break; - default: - return -1; - break; - } - return 0; -} - static int setkey_fallback_cip(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len) { @@ -117,72 +77,44 @@ static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len) { struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); - u32 *flags = &tfm->crt_flags; - int ret; + unsigned long fc; - ret = need_fallback(key_len); - if (ret < 0) { - *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; - return -EINVAL; - } + /* Pick the correct function code based on the key length */ + fc = (key_len == 16) ? CPACF_KM_AES_128 : + (key_len == 24) ? CPACF_KM_AES_192 : + (key_len == 32) ? CPACF_KM_AES_256 : 0; - sctx->key_len = key_len; - if (!ret) { - memcpy(sctx->key, in_key, key_len); - return 0; - } + /* Check if the function code is available */ + sctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0; + if (!sctx->fc) + return setkey_fallback_cip(tfm, in_key, key_len); - return setkey_fallback_cip(tfm, in_key, key_len); + sctx->key_len = key_len; + memcpy(sctx->key, in_key, key_len); + return 0; } static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); - if (unlikely(need_fallback(sctx->key_len))) { + if (unlikely(!sctx->fc)) { crypto_cipher_encrypt_one(sctx->fallback.cip, out, in); return; } - - switch (sctx->key_len) { - case 16: - cpacf_km(CPACF_KM_AES_128_ENC, &sctx->key, out, in, - AES_BLOCK_SIZE); - break; - case 24: - cpacf_km(CPACF_KM_AES_192_ENC, &sctx->key, out, in, - AES_BLOCK_SIZE); - break; - case 32: - cpacf_km(CPACF_KM_AES_256_ENC, &sctx->key, out, in, - AES_BLOCK_SIZE); - break; - } + cpacf_km(sctx->fc, &sctx->key, out, in, AES_BLOCK_SIZE); } static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); - if (unlikely(need_fallback(sctx->key_len))) { + if (unlikely(!sctx->fc)) { crypto_cipher_decrypt_one(sctx->fallback.cip, out, in); return; } - - switch (sctx->key_len) { - case 16: - cpacf_km(CPACF_KM_AES_128_DEC, &sctx->key, out, in, - AES_BLOCK_SIZE); - break; - case 24: - cpacf_km(CPACF_KM_AES_192_DEC, &sctx->key, out, in, - AES_BLOCK_SIZE); - break; - case 32: - cpacf_km(CPACF_KM_AES_256_DEC, &sctx->key, out, in, - AES_BLOCK_SIZE); - break; - } + cpacf_km(sctx->fc | CPACF_DECRYPT, + &sctx->key, out, in, AES_BLOCK_SIZE); } static int fallback_init_cip(struct crypto_tfm *tfm) @@ -291,50 +223,37 @@ static int ecb_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len) { struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); - int ret; + unsigned long fc; - ret = need_fallback(key_len); - if (ret > 0) { - sctx->key_len = key_len; - return setkey_fallback_blk(tfm, in_key, key_len); - } + /* Pick the correct function code based on the key length */ + fc = (key_len == 16) ? CPACF_KM_AES_128 : + (key_len == 24) ? CPACF_KM_AES_192 : + (key_len == 32) ? CPACF_KM_AES_256 : 0; - switch (key_len) { - case 16: - sctx->enc = CPACF_KM_AES_128_ENC; - sctx->dec = CPACF_KM_AES_128_DEC; - break; - case 24: - sctx->enc = CPACF_KM_AES_192_ENC; - sctx->dec = CPACF_KM_AES_192_DEC; - break; - case 32: - sctx->enc = CPACF_KM_AES_256_ENC; - sctx->dec = CPACF_KM_AES_256_DEC; - break; - } + /* Check if the function code is available */ + sctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0; + if (!sctx->fc) + return setkey_fallback_blk(tfm, in_key, key_len); - return aes_set_key(tfm, in_key, key_len); + sctx->key_len = key_len; + memcpy(sctx->key, in_key, key_len); + return 0; } -static int ecb_aes_crypt(struct blkcipher_desc *desc, long func, void *param, +static int ecb_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier, struct blkcipher_walk *walk) { - int ret = blkcipher_walk_virt(desc, walk); - unsigned int nbytes; + struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int nbytes, n; + int ret; - while ((nbytes = walk->nbytes)) { + ret = blkcipher_walk_virt(desc, walk); + while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { /* only use complete blocks */ - unsigned int n = nbytes & ~(AES_BLOCK_SIZE - 1); - u8 *out = walk->dst.virt.addr; - u8 *in = walk->src.virt.addr; - - ret = cpacf_km(func, param, out, in, n); - if (ret < 0 || ret != n) - return -EIO; - - nbytes &= AES_BLOCK_SIZE - 1; - ret = blkcipher_walk_done(desc, walk, nbytes); + n = nbytes & ~(AES_BLOCK_SIZE - 1); + cpacf_km(sctx->fc | modifier, sctx->key, + walk->dst.virt.addr, walk->src.virt.addr, n); + ret = blkcipher_walk_done(desc, walk, nbytes - n); } return ret; @@ -347,11 +266,11 @@ static int ecb_aes_encrypt(struct blkcipher_desc *desc, struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; - if (unlikely(need_fallback(sctx->key_len))) + if (unlikely(!sctx->fc)) return fallback_blk_enc(desc, dst, src, nbytes); blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_aes_crypt(desc, sctx->enc, sctx->key, &walk); + return ecb_aes_crypt(desc, 0, &walk); } static int ecb_aes_decrypt(struct blkcipher_desc *desc, @@ -361,11 +280,11 @@ static int ecb_aes_decrypt(struct blkcipher_desc *desc, struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; - if (unlikely(need_fallback(sctx->key_len))) + if (unlikely(!sctx->fc)) return fallback_blk_dec(desc, dst, src, nbytes); blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_aes_crypt(desc, sctx->dec, sctx->key, &walk); + return ecb_aes_crypt(desc, CPACF_DECRYPT, &walk); } static int fallback_init_blk(struct crypto_tfm *tfm) @@ -420,64 +339,45 @@ static int cbc_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len) { struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); - int ret; + unsigned long fc; - ret = need_fallback(key_len); - if (ret > 0) { - sctx->key_len = key_len; - return setkey_fallback_blk(tfm, in_key, key_len); - } + /* Pick the correct function code based on the key length */ + fc = (key_len == 16) ? CPACF_KMC_AES_128 : + (key_len == 24) ? CPACF_KMC_AES_192 : + (key_len == 32) ? CPACF_KMC_AES_256 : 0; - switch (key_len) { - case 16: - sctx->enc = CPACF_KMC_AES_128_ENC; - sctx->dec = CPACF_KMC_AES_128_DEC; - break; - case 24: - sctx->enc = CPACF_KMC_AES_192_ENC; - sctx->dec = CPACF_KMC_AES_192_DEC; - break; - case 32: - sctx->enc = CPACF_KMC_AES_256_ENC; - sctx->dec = CPACF_KMC_AES_256_DEC; - break; - } + /* Check if the function code is available */ + sctx->fc = (fc && cpacf_test_func(&kmc_functions, fc)) ? fc : 0; + if (!sctx->fc) + return setkey_fallback_blk(tfm, in_key, key_len); - return aes_set_key(tfm, in_key, key_len); + sctx->key_len = key_len; + memcpy(sctx->key, in_key, key_len); + return 0; } -static int cbc_aes_crypt(struct blkcipher_desc *desc, long func, +static int cbc_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier, struct blkcipher_walk *walk) { struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); - int ret = blkcipher_walk_virt(desc, walk); - unsigned int nbytes = walk->nbytes; + unsigned int nbytes, n; + int ret; struct { u8 iv[AES_BLOCK_SIZE]; u8 key[AES_MAX_KEY_SIZE]; } param; - if (!nbytes) - goto out; - + ret = blkcipher_walk_virt(desc, walk); memcpy(param.iv, walk->iv, AES_BLOCK_SIZE); memcpy(param.key, sctx->key, sctx->key_len); - do { + while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { /* only use complete blocks */ - unsigned int n = nbytes & ~(AES_BLOCK_SIZE - 1); - u8 *out = walk->dst.virt.addr; - u8 *in = walk->src.virt.addr; - - ret = cpacf_kmc(func, ¶m, out, in, n); - if (ret < 0 || ret != n) - return -EIO; - - nbytes &= AES_BLOCK_SIZE - 1; - ret = blkcipher_walk_done(desc, walk, nbytes); - } while ((nbytes = walk->nbytes)); + n = nbytes & ~(AES_BLOCK_SIZE - 1); + cpacf_kmc(sctx->fc | modifier, ¶m, + walk->dst.virt.addr, walk->src.virt.addr, n); + ret = blkcipher_walk_done(desc, walk, nbytes - n); + } memcpy(walk->iv, param.iv, AES_BLOCK_SIZE); - -out: return ret; } @@ -488,11 +388,11 @@ static int cbc_aes_encrypt(struct blkcipher_desc *desc, struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; - if (unlikely(need_fallback(sctx->key_len))) + if (unlikely(!sctx->fc)) return fallback_blk_enc(desc, dst, src, nbytes); blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_aes_crypt(desc, sctx->enc, &walk); + return cbc_aes_crypt(desc, 0, &walk); } static int cbc_aes_decrypt(struct blkcipher_desc *desc, @@ -502,11 +402,11 @@ static int cbc_aes_decrypt(struct blkcipher_desc *desc, struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; - if (unlikely(need_fallback(sctx->key_len))) + if (unlikely(!sctx->fc)) return fallback_blk_dec(desc, dst, src, nbytes); blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_aes_crypt(desc, sctx->dec, &walk); + return cbc_aes_crypt(desc, CPACF_DECRYPT, &walk); } static struct crypto_alg cbc_aes_alg = { @@ -594,83 +494,67 @@ static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len) { struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm); - u32 *flags = &tfm->crt_flags; + unsigned long fc; int err; err = xts_check_key(tfm, in_key, key_len); if (err) return err; - switch (key_len) { - case 32: - xts_ctx->enc = CPACF_KM_XTS_128_ENC; - xts_ctx->dec = CPACF_KM_XTS_128_DEC; - memcpy(xts_ctx->key + 16, in_key, 16); - memcpy(xts_ctx->pcc_key + 16, in_key + 16, 16); - break; - case 48: - xts_ctx->enc = 0; - xts_ctx->dec = 0; - xts_fallback_setkey(tfm, in_key, key_len); - break; - case 64: - xts_ctx->enc = CPACF_KM_XTS_256_ENC; - xts_ctx->dec = CPACF_KM_XTS_256_DEC; - memcpy(xts_ctx->key, in_key, 32); - memcpy(xts_ctx->pcc_key, in_key + 32, 32); - break; - default: - *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; - return -EINVAL; - } + /* Pick the correct function code based on the key length */ + fc = (key_len == 32) ? CPACF_KM_XTS_128 : + (key_len == 64) ? CPACF_KM_XTS_256 : 0; + + /* Check if the function code is available */ + xts_ctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0; + if (!xts_ctx->fc) + return xts_fallback_setkey(tfm, in_key, key_len); + + /* Split the XTS key into the two subkeys */ + key_len = key_len / 2; xts_ctx->key_len = key_len; + memcpy(xts_ctx->key, in_key, key_len); + memcpy(xts_ctx->pcc_key, in_key + key_len, key_len); return 0; } -static int xts_aes_crypt(struct blkcipher_desc *desc, long func, - struct s390_xts_ctx *xts_ctx, +static int xts_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier, struct blkcipher_walk *walk) { - unsigned int offset = (xts_ctx->key_len >> 1) & 0x10; - int ret = blkcipher_walk_virt(desc, walk); - unsigned int nbytes = walk->nbytes; - unsigned int n; - u8 *in, *out; - struct pcc_param pcc_param; + struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int offset, nbytes, n; + int ret; + struct { + u8 key[32]; + u8 tweak[16]; + u8 block[16]; + u8 bit[16]; + u8 xts[16]; + } pcc_param; struct { u8 key[32]; u8 init[16]; } xts_param; - if (!nbytes) - goto out; - + ret = blkcipher_walk_virt(desc, walk); + offset = xts_ctx->key_len & 0x10; memset(pcc_param.block, 0, sizeof(pcc_param.block)); memset(pcc_param.bit, 0, sizeof(pcc_param.bit)); memset(pcc_param.xts, 0, sizeof(pcc_param.xts)); memcpy(pcc_param.tweak, walk->iv, sizeof(pcc_param.tweak)); - memcpy(pcc_param.key, xts_ctx->pcc_key, 32); - /* remove decipher modifier bit from 'func' and call PCC */ - ret = cpacf_pcc(func & 0x7f, &pcc_param.key[offset]); - if (ret < 0) - return -EIO; + memcpy(pcc_param.key + offset, xts_ctx->pcc_key, xts_ctx->key_len); + cpacf_pcc(xts_ctx->fc, pcc_param.key + offset); - memcpy(xts_param.key, xts_ctx->key, 32); + memcpy(xts_param.key + offset, xts_ctx->key, xts_ctx->key_len); memcpy(xts_param.init, pcc_param.xts, 16); - do { + + while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); - out = walk->dst.virt.addr; - in = walk->src.virt.addr; - - ret = cpacf_km(func, &xts_param.key[offset], out, in, n); - if (ret < 0 || ret != n) - return -EIO; - - nbytes &= AES_BLOCK_SIZE - 1; - ret = blkcipher_walk_done(desc, walk, nbytes); - } while ((nbytes = walk->nbytes)); -out: + cpacf_km(xts_ctx->fc | modifier, xts_param.key + offset, + walk->dst.virt.addr, walk->src.virt.addr, n); + ret = blkcipher_walk_done(desc, walk, nbytes - n); + } return ret; } @@ -681,11 +565,11 @@ static int xts_aes_encrypt(struct blkcipher_desc *desc, struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; - if (unlikely(xts_ctx->key_len == 48)) + if (unlikely(!xts_ctx->fc)) return xts_fallback_encrypt(desc, dst, src, nbytes); blkcipher_walk_init(&walk, dst, src, nbytes); - return xts_aes_crypt(desc, xts_ctx->enc, xts_ctx, &walk); + return xts_aes_crypt(desc, 0, &walk); } static int xts_aes_decrypt(struct blkcipher_desc *desc, @@ -695,11 +579,11 @@ static int xts_aes_decrypt(struct blkcipher_desc *desc, struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; - if (unlikely(xts_ctx->key_len == 48)) + if (unlikely(!xts_ctx->fc)) return xts_fallback_decrypt(desc, dst, src, nbytes); blkcipher_walk_init(&walk, dst, src, nbytes); - return xts_aes_crypt(desc, xts_ctx->dec, xts_ctx, &walk); + return xts_aes_crypt(desc, CPACF_DECRYPT, &walk); } static int xts_fallback_init(struct crypto_tfm *tfm) @@ -750,108 +634,79 @@ static struct crypto_alg xts_aes_alg = { } }; -static int xts_aes_alg_reg; - static int ctr_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len) { struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); + unsigned long fc; - switch (key_len) { - case 16: - sctx->enc = CPACF_KMCTR_AES_128_ENC; - sctx->dec = CPACF_KMCTR_AES_128_DEC; - break; - case 24: - sctx->enc = CPACF_KMCTR_AES_192_ENC; - sctx->dec = CPACF_KMCTR_AES_192_DEC; - break; - case 32: - sctx->enc = CPACF_KMCTR_AES_256_ENC; - sctx->dec = CPACF_KMCTR_AES_256_DEC; - break; - } + /* Pick the correct function code based on the key length */ + fc = (key_len == 16) ? CPACF_KMCTR_AES_128 : + (key_len == 24) ? CPACF_KMCTR_AES_192 : + (key_len == 32) ? CPACF_KMCTR_AES_256 : 0; + + /* Check if the function code is available */ + sctx->fc = (fc && cpacf_test_func(&kmctr_functions, fc)) ? fc : 0; + if (!sctx->fc) + return setkey_fallback_blk(tfm, in_key, key_len); - return aes_set_key(tfm, in_key, key_len); + sctx->key_len = key_len; + memcpy(sctx->key, in_key, key_len); + return 0; } -static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes) +static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes) { unsigned int i, n; /* only use complete blocks, max. PAGE_SIZE */ + memcpy(ctrptr, iv, AES_BLOCK_SIZE); n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(AES_BLOCK_SIZE - 1); - for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) { - memcpy(ctrptr + i, ctrptr + i - AES_BLOCK_SIZE, - AES_BLOCK_SIZE); - crypto_inc(ctrptr + i, AES_BLOCK_SIZE); + for (i = (n / AES_BLOCK_SIZE) - 1; i > 0; i--) { + memcpy(ctrptr + AES_BLOCK_SIZE, ctrptr, AES_BLOCK_SIZE); + crypto_inc(ctrptr + AES_BLOCK_SIZE, AES_BLOCK_SIZE); + ctrptr += AES_BLOCK_SIZE; } return n; } -static int ctr_aes_crypt(struct blkcipher_desc *desc, long func, - struct s390_aes_ctx *sctx, struct blkcipher_walk *walk) +static int ctr_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier, + struct blkcipher_walk *walk) { - int ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE); + struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); + u8 buf[AES_BLOCK_SIZE], *ctrptr; unsigned int n, nbytes; - u8 buf[AES_BLOCK_SIZE], ctrbuf[AES_BLOCK_SIZE]; - u8 *out, *in, *ctrptr = ctrbuf; - - if (!walk->nbytes) - return ret; + int ret, locked; - if (spin_trylock(&ctrblk_lock)) - ctrptr = ctrblk; + locked = spin_trylock(&ctrblk_lock); - memcpy(ctrptr, walk->iv, AES_BLOCK_SIZE); + ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE); while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { - out = walk->dst.virt.addr; - in = walk->src.virt.addr; - while (nbytes >= AES_BLOCK_SIZE) { - if (ctrptr == ctrblk) - n = __ctrblk_init(ctrptr, nbytes); - else - n = AES_BLOCK_SIZE; - ret = cpacf_kmctr(func, sctx->key, out, in, n, ctrptr); - if (ret < 0 || ret != n) { - if (ctrptr == ctrblk) - spin_unlock(&ctrblk_lock); - return -EIO; - } - if (n > AES_BLOCK_SIZE) - memcpy(ctrptr, ctrptr + n - AES_BLOCK_SIZE, - AES_BLOCK_SIZE); - crypto_inc(ctrptr, AES_BLOCK_SIZE); - out += n; - in += n; - nbytes -= n; - } - ret = blkcipher_walk_done(desc, walk, nbytes); + n = AES_BLOCK_SIZE; + if (nbytes >= 2*AES_BLOCK_SIZE && locked) + n = __ctrblk_init(ctrblk, walk->iv, nbytes); + ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk->iv; + cpacf_kmctr(sctx->fc | modifier, sctx->key, + walk->dst.virt.addr, walk->src.virt.addr, + n, ctrptr); + if (ctrptr == ctrblk) + memcpy(walk->iv, ctrptr + n - AES_BLOCK_SIZE, + AES_BLOCK_SIZE); + crypto_inc(walk->iv, AES_BLOCK_SIZE); + ret = blkcipher_walk_done(desc, walk, nbytes - n); } - if (ctrptr == ctrblk) { - if (nbytes) - memcpy(ctrbuf, ctrptr, AES_BLOCK_SIZE); - else - memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE); + if (locked) spin_unlock(&ctrblk_lock); - } else { - if (!nbytes) - memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE); - } /* * final block may be < AES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { - out = walk->dst.virt.addr; - in = walk->src.virt.addr; - ret = cpacf_kmctr(func, sctx->key, buf, in, - AES_BLOCK_SIZE, ctrbuf); - if (ret < 0 || ret != AES_BLOCK_SIZE) - return -EIO; - memcpy(out, buf, nbytes); - crypto_inc(ctrbuf, AES_BLOCK_SIZE); + cpacf_kmctr(sctx->fc | modifier, sctx->key, + buf, walk->src.virt.addr, + AES_BLOCK_SIZE, walk->iv); + memcpy(walk->dst.virt.addr, buf, nbytes); + crypto_inc(walk->iv, AES_BLOCK_SIZE); ret = blkcipher_walk_done(desc, walk, 0); - memcpy(walk->iv, ctrbuf, AES_BLOCK_SIZE); } return ret; @@ -864,8 +719,11 @@ static int ctr_aes_encrypt(struct blkcipher_desc *desc, struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; + if (unlikely(!sctx->fc)) + return fallback_blk_enc(desc, dst, src, nbytes); + blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_aes_crypt(desc, sctx->enc, sctx, &walk); + return ctr_aes_crypt(desc, 0, &walk); } static int ctr_aes_decrypt(struct blkcipher_desc *desc, @@ -875,19 +733,25 @@ static int ctr_aes_decrypt(struct blkcipher_desc *desc, struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; + if (unlikely(!sctx->fc)) + return fallback_blk_dec(desc, dst, src, nbytes); + blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_aes_crypt(desc, sctx->dec, sctx, &walk); + return ctr_aes_crypt(desc, CPACF_DECRYPT, &walk); } static struct crypto_alg ctr_aes_alg = { .cra_name = "ctr(aes)", .cra_driver_name = "ctr-aes-s390", .cra_priority = 400, /* combo: aes + ctr */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_NEED_FALLBACK, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct s390_aes_ctx), .cra_type = &crypto_blkcipher_type, .cra_module = THIS_MODULE, + .cra_init = fallback_init_blk, + .cra_exit = fallback_exit_blk, .cra_u = { .blkcipher = { .min_keysize = AES_MIN_KEY_SIZE, @@ -900,89 +764,79 @@ static struct crypto_alg ctr_aes_alg = { } }; -static int ctr_aes_alg_reg; +static struct crypto_alg *aes_s390_algs_ptr[5]; +static int aes_s390_algs_num; -static int __init aes_s390_init(void) +static int aes_s390_register_alg(struct crypto_alg *alg) { int ret; - if (cpacf_query(CPACF_KM, CPACF_KM_AES_128_ENC)) - keylen_flag |= AES_KEYLEN_128; - if (cpacf_query(CPACF_KM, CPACF_KM_AES_192_ENC)) - keylen_flag |= AES_KEYLEN_192; - if (cpacf_query(CPACF_KM, CPACF_KM_AES_256_ENC)) - keylen_flag |= AES_KEYLEN_256; + ret = crypto_register_alg(alg); + if (!ret) + aes_s390_algs_ptr[aes_s390_algs_num++] = alg; + return ret; +} - if (!keylen_flag) - return -EOPNOTSUPP; +static void aes_s390_fini(void) +{ + while (aes_s390_algs_num--) + crypto_unregister_alg(aes_s390_algs_ptr[aes_s390_algs_num]); + if (ctrblk) + free_page((unsigned long) ctrblk); +} - /* z9 109 and z9 BC/EC only support 128 bit key length */ - if (keylen_flag == AES_KEYLEN_128) - pr_info("AES hardware acceleration is only available for" - " 128-bit keys\n"); +static int __init aes_s390_init(void) +{ + int ret; - ret = crypto_register_alg(&aes_alg); - if (ret) - goto aes_err; + /* Query available functions for KM, KMC and KMCTR */ + cpacf_query(CPACF_KM, &km_functions); + cpacf_query(CPACF_KMC, &kmc_functions); + cpacf_query(CPACF_KMCTR, &kmctr_functions); - ret = crypto_register_alg(&ecb_aes_alg); - if (ret) - goto ecb_aes_err; + if (cpacf_test_func(&km_functions, CPACF_KM_AES_128) || + cpacf_test_func(&km_functions, CPACF_KM_AES_192) || + cpacf_test_func(&km_functions, CPACF_KM_AES_256)) { + ret = aes_s390_register_alg(&aes_alg); + if (ret) + goto out_err; + ret = aes_s390_register_alg(&ecb_aes_alg); + if (ret) + goto out_err; + } - ret = crypto_register_alg(&cbc_aes_alg); - if (ret) - goto cbc_aes_err; + if (cpacf_test_func(&kmc_functions, CPACF_KMC_AES_128) || + cpacf_test_func(&kmc_functions, CPACF_KMC_AES_192) || + cpacf_test_func(&kmc_functions, CPACF_KMC_AES_256)) { + ret = aes_s390_register_alg(&cbc_aes_alg); + if (ret) + goto out_err; + } - if (cpacf_query(CPACF_KM, CPACF_KM_XTS_128_ENC) && - cpacf_query(CPACF_KM, CPACF_KM_XTS_256_ENC)) { - ret = crypto_register_alg(&xts_aes_alg); + if (cpacf_test_func(&km_functions, CPACF_KM_XTS_128) || + cpacf_test_func(&km_functions, CPACF_KM_XTS_256)) { + ret = aes_s390_register_alg(&xts_aes_alg); if (ret) - goto xts_aes_err; - xts_aes_alg_reg = 1; + goto out_err; } - if (cpacf_query(CPACF_KMCTR, CPACF_KMCTR_AES_128_ENC) && - cpacf_query(CPACF_KMCTR, CPACF_KMCTR_AES_192_ENC) && - cpacf_query(CPACF_KMCTR, CPACF_KMCTR_AES_256_ENC)) { + if (cpacf_test_func(&kmctr_functions, CPACF_KMCTR_AES_128) || + cpacf_test_func(&kmctr_functions, CPACF_KMCTR_AES_192) || + cpacf_test_func(&kmctr_functions, CPACF_KMCTR_AES_256)) { ctrblk = (u8 *) __get_free_page(GFP_KERNEL); if (!ctrblk) { ret = -ENOMEM; - goto ctr_aes_err; + goto out_err; } - ret = crypto_register_alg(&ctr_aes_alg); - if (ret) { - free_page((unsigned long) ctrblk); - goto ctr_aes_err; - } - ctr_aes_alg_reg = 1; + ret = aes_s390_register_alg(&ctr_aes_alg); + if (ret) + goto out_err; } -out: + return 0; +out_err: + aes_s390_fini(); return ret; - -ctr_aes_err: - crypto_unregister_alg(&xts_aes_alg); -xts_aes_err: - crypto_unregister_alg(&cbc_aes_alg); -cbc_aes_err: - crypto_unregister_alg(&ecb_aes_alg); -ecb_aes_err: - crypto_unregister_alg(&aes_alg); -aes_err: - goto out; -} - -static void __exit aes_s390_fini(void) -{ - if (ctr_aes_alg_reg) { - crypto_unregister_alg(&ctr_aes_alg); - free_page((unsigned long) ctrblk); - } - if (xts_aes_alg_reg) - crypto_unregister_alg(&xts_aes_alg); - crypto_unregister_alg(&cbc_aes_alg); - crypto_unregister_alg(&ecb_aes_alg); - crypto_unregister_alg(&aes_alg); } module_cpu_feature_match(MSA, aes_s390_init); diff --git a/arch/s390/crypto/crc32-vx.c b/arch/s390/crypto/crc32-vx.c index 2bad9d837029..992e630c227b 100644 --- a/arch/s390/crypto/crc32-vx.c +++ b/arch/s390/crypto/crc32-vx.c @@ -67,7 +67,7 @@ u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size); \ kernel_fpu_begin(&vxstate, KERNEL_VXR_LOW); \ crc = ___crc32_vx(crc, data, aligned); \ - kernel_fpu_end(&vxstate); \ + kernel_fpu_end(&vxstate, KERNEL_VXR_LOW); \ \ if (remaining) \ crc = ___crc32_sw(crc, data + aligned, remaining); \ diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index 697e71a75fc2..8b83144206eb 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -27,6 +27,8 @@ static u8 *ctrblk; static DEFINE_SPINLOCK(ctrblk_lock); +static cpacf_mask_t km_functions, kmc_functions, kmctr_functions; + struct s390_des_ctx { u8 iv[DES_BLOCK_SIZE]; u8 key[DES3_KEY_SIZE]; @@ -36,12 +38,12 @@ static int des_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int key_len) { struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm); - u32 *flags = &tfm->crt_flags; u32 tmp[DES_EXPKEY_WORDS]; /* check for weak keys */ - if (!des_ekey(tmp, key) && (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) { - *flags |= CRYPTO_TFM_RES_WEAK_KEY; + if (!des_ekey(tmp, key) && + (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } @@ -53,14 +55,15 @@ static void des_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm); - cpacf_km(CPACF_KM_DEA_ENC, ctx->key, out, in, DES_BLOCK_SIZE); + cpacf_km(CPACF_KM_DEA, ctx->key, out, in, DES_BLOCK_SIZE); } static void des_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm); - cpacf_km(CPACF_KM_DEA_DEC, ctx->key, out, in, DES_BLOCK_SIZE); + cpacf_km(CPACF_KM_DEA | CPACF_DECRYPT, + ctx->key, out, in, DES_BLOCK_SIZE); } static struct crypto_alg des_alg = { @@ -82,61 +85,46 @@ static struct crypto_alg des_alg = { } }; -static int ecb_desall_crypt(struct blkcipher_desc *desc, long func, - u8 *key, struct blkcipher_walk *walk) +static int ecb_desall_crypt(struct blkcipher_desc *desc, unsigned long fc, + struct blkcipher_walk *walk) { - int ret = blkcipher_walk_virt(desc, walk); - unsigned int nbytes; + struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int nbytes, n; + int ret; - while ((nbytes = walk->nbytes)) { + ret = blkcipher_walk_virt(desc, walk); + while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) { /* only use complete blocks */ - unsigned int n = nbytes & ~(DES_BLOCK_SIZE - 1); - u8 *out = walk->dst.virt.addr; - u8 *in = walk->src.virt.addr; - - ret = cpacf_km(func, key, out, in, n); - if (ret < 0 || ret != n) - return -EIO; - - nbytes &= DES_BLOCK_SIZE - 1; - ret = blkcipher_walk_done(desc, walk, nbytes); + n = nbytes & ~(DES_BLOCK_SIZE - 1); + cpacf_km(fc, ctx->key, walk->dst.virt.addr, + walk->src.virt.addr, n); + ret = blkcipher_walk_done(desc, walk, nbytes - n); } - return ret; } -static int cbc_desall_crypt(struct blkcipher_desc *desc, long func, +static int cbc_desall_crypt(struct blkcipher_desc *desc, unsigned long fc, struct blkcipher_walk *walk) { struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); - int ret = blkcipher_walk_virt(desc, walk); - unsigned int nbytes = walk->nbytes; + unsigned int nbytes, n; + int ret; struct { u8 iv[DES_BLOCK_SIZE]; u8 key[DES3_KEY_SIZE]; } param; - if (!nbytes) - goto out; - + ret = blkcipher_walk_virt(desc, walk); memcpy(param.iv, walk->iv, DES_BLOCK_SIZE); memcpy(param.key, ctx->key, DES3_KEY_SIZE); - do { + while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) { /* only use complete blocks */ - unsigned int n = nbytes & ~(DES_BLOCK_SIZE - 1); - u8 *out = walk->dst.virt.addr; - u8 *in = walk->src.virt.addr; - - ret = cpacf_kmc(func, ¶m, out, in, n); - if (ret < 0 || ret != n) - return -EIO; - - nbytes &= DES_BLOCK_SIZE - 1; - ret = blkcipher_walk_done(desc, walk, nbytes); - } while ((nbytes = walk->nbytes)); + n = nbytes & ~(DES_BLOCK_SIZE - 1); + cpacf_kmc(fc, ¶m, walk->dst.virt.addr, + walk->src.virt.addr, n); + ret = blkcipher_walk_done(desc, walk, nbytes - n); + } memcpy(walk->iv, param.iv, DES_BLOCK_SIZE); - -out: return ret; } @@ -144,22 +132,20 @@ static int ecb_des_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_desall_crypt(desc, CPACF_KM_DEA_ENC, ctx->key, &walk); + return ecb_desall_crypt(desc, CPACF_KM_DEA, &walk); } static int ecb_des_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_desall_crypt(desc, CPACF_KM_DEA_DEC, ctx->key, &walk); + return ecb_desall_crypt(desc, CPACF_KM_DEA | CPACF_DECRYPT, &walk); } static struct crypto_alg ecb_des_alg = { @@ -189,7 +175,7 @@ static int cbc_des_encrypt(struct blkcipher_desc *desc, struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, CPACF_KMC_DEA_ENC, &walk); + return cbc_desall_crypt(desc, CPACF_KMC_DEA, &walk); } static int cbc_des_decrypt(struct blkcipher_desc *desc, @@ -199,7 +185,7 @@ static int cbc_des_decrypt(struct blkcipher_desc *desc, struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, CPACF_KMC_DEA_DEC, &walk); + return cbc_desall_crypt(desc, CPACF_KMC_DEA | CPACF_DECRYPT, &walk); } static struct crypto_alg cbc_des_alg = { @@ -240,13 +226,12 @@ static int des3_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int key_len) { struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm); - u32 *flags = &tfm->crt_flags; if (!(crypto_memneq(key, &key[DES_KEY_SIZE], DES_KEY_SIZE) && crypto_memneq(&key[DES_KEY_SIZE], &key[DES_KEY_SIZE * 2], DES_KEY_SIZE)) && - (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) { - *flags |= CRYPTO_TFM_RES_WEAK_KEY; + (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } memcpy(ctx->key, key, key_len); @@ -257,14 +242,15 @@ static void des3_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm); - cpacf_km(CPACF_KM_TDEA_192_ENC, ctx->key, dst, src, DES_BLOCK_SIZE); + cpacf_km(CPACF_KM_TDEA_192, ctx->key, dst, src, DES_BLOCK_SIZE); } static void des3_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm); - cpacf_km(CPACF_KM_TDEA_192_DEC, ctx->key, dst, src, DES_BLOCK_SIZE); + cpacf_km(CPACF_KM_TDEA_192 | CPACF_DECRYPT, + ctx->key, dst, src, DES_BLOCK_SIZE); } static struct crypto_alg des3_alg = { @@ -290,22 +276,21 @@ static int ecb_des3_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_desall_crypt(desc, CPACF_KM_TDEA_192_ENC, ctx->key, &walk); + return ecb_desall_crypt(desc, CPACF_KM_TDEA_192, &walk); } static int ecb_des3_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_desall_crypt(desc, CPACF_KM_TDEA_192_DEC, ctx->key, &walk); + return ecb_desall_crypt(desc, CPACF_KM_TDEA_192 | CPACF_DECRYPT, + &walk); } static struct crypto_alg ecb_des3_alg = { @@ -335,7 +320,7 @@ static int cbc_des3_encrypt(struct blkcipher_desc *desc, struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, CPACF_KMC_TDEA_192_ENC, &walk); + return cbc_desall_crypt(desc, CPACF_KMC_TDEA_192, &walk); } static int cbc_des3_decrypt(struct blkcipher_desc *desc, @@ -345,7 +330,8 @@ static int cbc_des3_decrypt(struct blkcipher_desc *desc, struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, CPACF_KMC_TDEA_192_DEC, &walk); + return cbc_desall_crypt(desc, CPACF_KMC_TDEA_192 | CPACF_DECRYPT, + &walk); } static struct crypto_alg cbc_des3_alg = { @@ -369,81 +355,54 @@ static struct crypto_alg cbc_des3_alg = { } }; -static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes) +static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes) { unsigned int i, n; /* align to block size, max. PAGE_SIZE */ n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(DES_BLOCK_SIZE - 1); - for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) { - memcpy(ctrptr + i, ctrptr + i - DES_BLOCK_SIZE, DES_BLOCK_SIZE); - crypto_inc(ctrptr + i, DES_BLOCK_SIZE); + memcpy(ctrptr, iv, DES_BLOCK_SIZE); + for (i = (n / DES_BLOCK_SIZE) - 1; i > 0; i--) { + memcpy(ctrptr + DES_BLOCK_SIZE, ctrptr, DES_BLOCK_SIZE); + crypto_inc(ctrptr + DES_BLOCK_SIZE, DES_BLOCK_SIZE); + ctrptr += DES_BLOCK_SIZE; } return n; } -static int ctr_desall_crypt(struct blkcipher_desc *desc, long func, - struct s390_des_ctx *ctx, +static int ctr_desall_crypt(struct blkcipher_desc *desc, unsigned long fc, struct blkcipher_walk *walk) { - int ret = blkcipher_walk_virt_block(desc, walk, DES_BLOCK_SIZE); + struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + u8 buf[DES_BLOCK_SIZE], *ctrptr; unsigned int n, nbytes; - u8 buf[DES_BLOCK_SIZE], ctrbuf[DES_BLOCK_SIZE]; - u8 *out, *in, *ctrptr = ctrbuf; - - if (!walk->nbytes) - return ret; + int ret, locked; - if (spin_trylock(&ctrblk_lock)) - ctrptr = ctrblk; + locked = spin_trylock(&ctrblk_lock); - memcpy(ctrptr, walk->iv, DES_BLOCK_SIZE); + ret = blkcipher_walk_virt_block(desc, walk, DES_BLOCK_SIZE); while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) { - out = walk->dst.virt.addr; - in = walk->src.virt.addr; - while (nbytes >= DES_BLOCK_SIZE) { - if (ctrptr == ctrblk) - n = __ctrblk_init(ctrptr, nbytes); - else - n = DES_BLOCK_SIZE; - ret = cpacf_kmctr(func, ctx->key, out, in, n, ctrptr); - if (ret < 0 || ret != n) { - if (ctrptr == ctrblk) - spin_unlock(&ctrblk_lock); - return -EIO; - } - if (n > DES_BLOCK_SIZE) - memcpy(ctrptr, ctrptr + n - DES_BLOCK_SIZE, - DES_BLOCK_SIZE); - crypto_inc(ctrptr, DES_BLOCK_SIZE); - out += n; - in += n; - nbytes -= n; - } - ret = blkcipher_walk_done(desc, walk, nbytes); + n = DES_BLOCK_SIZE; + if (nbytes >= 2*DES_BLOCK_SIZE && locked) + n = __ctrblk_init(ctrblk, walk->iv, nbytes); + ctrptr = (n > DES_BLOCK_SIZE) ? ctrblk : walk->iv; + cpacf_kmctr(fc, ctx->key, walk->dst.virt.addr, + walk->src.virt.addr, n, ctrptr); + if (ctrptr == ctrblk) + memcpy(walk->iv, ctrptr + n - DES_BLOCK_SIZE, + DES_BLOCK_SIZE); + crypto_inc(walk->iv, DES_BLOCK_SIZE); + ret = blkcipher_walk_done(desc, walk, nbytes - n); } - if (ctrptr == ctrblk) { - if (nbytes) - memcpy(ctrbuf, ctrptr, DES_BLOCK_SIZE); - else - memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE); + if (locked) spin_unlock(&ctrblk_lock); - } else { - if (!nbytes) - memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE); - } /* final block may be < DES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { - out = walk->dst.virt.addr; - in = walk->src.virt.addr; - ret = cpacf_kmctr(func, ctx->key, buf, in, - DES_BLOCK_SIZE, ctrbuf); - if (ret < 0 || ret != DES_BLOCK_SIZE) - return -EIO; - memcpy(out, buf, nbytes); - crypto_inc(ctrbuf, DES_BLOCK_SIZE); + cpacf_kmctr(fc, ctx->key, buf, walk->src.virt.addr, + DES_BLOCK_SIZE, walk->iv); + memcpy(walk->dst.virt.addr, buf, nbytes); + crypto_inc(walk->iv, DES_BLOCK_SIZE); ret = blkcipher_walk_done(desc, walk, 0); - memcpy(walk->iv, ctrbuf, DES_BLOCK_SIZE); } return ret; } @@ -452,22 +411,20 @@ static int ctr_des_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_desall_crypt(desc, CPACF_KMCTR_DEA_ENC, ctx, &walk); + return ctr_desall_crypt(desc, CPACF_KMCTR_DEA, &walk); } static int ctr_des_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_desall_crypt(desc, CPACF_KMCTR_DEA_DEC, ctx, &walk); + return ctr_desall_crypt(desc, CPACF_KMCTR_DEA | CPACF_DECRYPT, &walk); } static struct crypto_alg ctr_des_alg = { @@ -495,22 +452,21 @@ static int ctr_des3_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_desall_crypt(desc, CPACF_KMCTR_TDEA_192_ENC, ctx, &walk); + return ctr_desall_crypt(desc, CPACF_KMCTR_TDEA_192, &walk); } static int ctr_des3_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_desall_crypt(desc, CPACF_KMCTR_TDEA_192_DEC, ctx, &walk); + return ctr_desall_crypt(desc, CPACF_KMCTR_TDEA_192 | CPACF_DECRYPT, + &walk); } static struct crypto_alg ctr_des3_alg = { @@ -534,83 +490,87 @@ static struct crypto_alg ctr_des3_alg = { } }; +static struct crypto_alg *des_s390_algs_ptr[8]; +static int des_s390_algs_num; + +static int des_s390_register_alg(struct crypto_alg *alg) +{ + int ret; + + ret = crypto_register_alg(alg); + if (!ret) + des_s390_algs_ptr[des_s390_algs_num++] = alg; + return ret; +} + +static void des_s390_exit(void) +{ + while (des_s390_algs_num--) + crypto_unregister_alg(des_s390_algs_ptr[des_s390_algs_num]); + if (ctrblk) + free_page((unsigned long) ctrblk); +} + static int __init des_s390_init(void) { int ret; - if (!cpacf_query(CPACF_KM, CPACF_KM_DEA_ENC) || - !cpacf_query(CPACF_KM, CPACF_KM_TDEA_192_ENC)) - return -EOPNOTSUPP; - - ret = crypto_register_alg(&des_alg); - if (ret) - goto des_err; - ret = crypto_register_alg(&ecb_des_alg); - if (ret) - goto ecb_des_err; - ret = crypto_register_alg(&cbc_des_alg); - if (ret) - goto cbc_des_err; - ret = crypto_register_alg(&des3_alg); - if (ret) - goto des3_err; - ret = crypto_register_alg(&ecb_des3_alg); - if (ret) - goto ecb_des3_err; - ret = crypto_register_alg(&cbc_des3_alg); - if (ret) - goto cbc_des3_err; - - if (cpacf_query(CPACF_KMCTR, CPACF_KMCTR_DEA_ENC) && - cpacf_query(CPACF_KMCTR, CPACF_KMCTR_TDEA_192_ENC)) { - ret = crypto_register_alg(&ctr_des_alg); + /* Query available functions for KM, KMC and KMCTR */ + cpacf_query(CPACF_KM, &km_functions); + cpacf_query(CPACF_KMC, &kmc_functions); + cpacf_query(CPACF_KMCTR, &kmctr_functions); + + if (cpacf_test_func(&km_functions, CPACF_KM_DEA)) { + ret = des_s390_register_alg(&des_alg); + if (ret) + goto out_err; + ret = des_s390_register_alg(&ecb_des_alg); if (ret) - goto ctr_des_err; - ret = crypto_register_alg(&ctr_des3_alg); + goto out_err; + } + if (cpacf_test_func(&kmc_functions, CPACF_KMC_DEA)) { + ret = des_s390_register_alg(&cbc_des_alg); if (ret) - goto ctr_des3_err; + goto out_err; + } + if (cpacf_test_func(&km_functions, CPACF_KM_TDEA_192)) { + ret = des_s390_register_alg(&des3_alg); + if (ret) + goto out_err; + ret = des_s390_register_alg(&ecb_des3_alg); + if (ret) + goto out_err; + } + if (cpacf_test_func(&kmc_functions, CPACF_KMC_TDEA_192)) { + ret = des_s390_register_alg(&cbc_des3_alg); + if (ret) + goto out_err; + } + + if (cpacf_test_func(&kmctr_functions, CPACF_KMCTR_DEA) || + cpacf_test_func(&kmctr_functions, CPACF_KMCTR_TDEA_192)) { ctrblk = (u8 *) __get_free_page(GFP_KERNEL); if (!ctrblk) { ret = -ENOMEM; - goto ctr_mem_err; + goto out_err; } } -out: - return ret; -ctr_mem_err: - crypto_unregister_alg(&ctr_des3_alg); -ctr_des3_err: - crypto_unregister_alg(&ctr_des_alg); -ctr_des_err: - crypto_unregister_alg(&cbc_des3_alg); -cbc_des3_err: - crypto_unregister_alg(&ecb_des3_alg); -ecb_des3_err: - crypto_unregister_alg(&des3_alg); -des3_err: - crypto_unregister_alg(&cbc_des_alg); -cbc_des_err: - crypto_unregister_alg(&ecb_des_alg); -ecb_des_err: - crypto_unregister_alg(&des_alg); -des_err: - goto out; -} - -static void __exit des_s390_exit(void) -{ - if (ctrblk) { - crypto_unregister_alg(&ctr_des_alg); - crypto_unregister_alg(&ctr_des3_alg); - free_page((unsigned long) ctrblk); + if (cpacf_test_func(&kmctr_functions, CPACF_KMCTR_DEA)) { + ret = des_s390_register_alg(&ctr_des_alg); + if (ret) + goto out_err; + } + if (cpacf_test_func(&kmctr_functions, CPACF_KMCTR_TDEA_192)) { + ret = des_s390_register_alg(&ctr_des3_alg); + if (ret) + goto out_err; } - crypto_unregister_alg(&cbc_des3_alg); - crypto_unregister_alg(&ecb_des3_alg); - crypto_unregister_alg(&des3_alg); - crypto_unregister_alg(&cbc_des_alg); - crypto_unregister_alg(&ecb_des_alg); - crypto_unregister_alg(&des_alg); + + return 0; +out_err: + des_s390_exit(); + return ret; } module_cpu_feature_match(MSA, des_s390_init); diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c index ab68de72e795..564616d48d8b 100644 --- a/arch/s390/crypto/ghash_s390.c +++ b/arch/s390/crypto/ghash_s390.c @@ -58,7 +58,6 @@ static int ghash_update(struct shash_desc *desc, struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); unsigned int n; u8 *buf = dctx->buffer; - int ret; if (dctx->bytes) { u8 *pos = buf + (GHASH_BLOCK_SIZE - dctx->bytes); @@ -71,18 +70,14 @@ static int ghash_update(struct shash_desc *desc, src += n; if (!dctx->bytes) { - ret = cpacf_kimd(CPACF_KIMD_GHASH, dctx, buf, - GHASH_BLOCK_SIZE); - if (ret != GHASH_BLOCK_SIZE) - return -EIO; + cpacf_kimd(CPACF_KIMD_GHASH, dctx, buf, + GHASH_BLOCK_SIZE); } } n = srclen & ~(GHASH_BLOCK_SIZE - 1); if (n) { - ret = cpacf_kimd(CPACF_KIMD_GHASH, dctx, src, n); - if (ret != n) - return -EIO; + cpacf_kimd(CPACF_KIMD_GHASH, dctx, src, n); src += n; srclen -= n; } @@ -98,17 +93,12 @@ static int ghash_update(struct shash_desc *desc, static int ghash_flush(struct ghash_desc_ctx *dctx) { u8 *buf = dctx->buffer; - int ret; if (dctx->bytes) { u8 *pos = buf + (GHASH_BLOCK_SIZE - dctx->bytes); memset(pos, 0, dctx->bytes); - - ret = cpacf_kimd(CPACF_KIMD_GHASH, dctx, buf, GHASH_BLOCK_SIZE); - if (ret != GHASH_BLOCK_SIZE) - return -EIO; - + cpacf_kimd(CPACF_KIMD_GHASH, dctx, buf, GHASH_BLOCK_SIZE); dctx->bytes = 0; } @@ -146,7 +136,7 @@ static struct shash_alg ghash_alg = { static int __init ghash_mod_init(void) { - if (!cpacf_query(CPACF_KIMD, CPACF_KIMD_GHASH)) + if (!cpacf_query_func(CPACF_KIMD, CPACF_KIMD_GHASH)) return -EOPNOTSUPP; return crypto_register_shash(&ghash_alg); diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c index 41527b113f5a..9cc050f9536c 100644 --- a/arch/s390/crypto/prng.c +++ b/arch/s390/crypto/prng.c @@ -135,12 +135,7 @@ static int generate_entropy(u8 *ebuf, size_t nbytes) else h = ebuf; /* generate sha256 from this page */ - if (cpacf_kimd(CPACF_KIMD_SHA_256, h, - pg, PAGE_SIZE) != PAGE_SIZE) { - prng_errorflag = PRNG_GEN_ENTROPY_FAILED; - ret = -EIO; - goto out; - } + cpacf_kimd(CPACF_KIMD_SHA_256, h, pg, PAGE_SIZE); if (n < sizeof(hash)) memcpy(ebuf, hash, n); ret += n; @@ -148,7 +143,6 @@ static int generate_entropy(u8 *ebuf, size_t nbytes) nbytes -= n; } -out: free_page((unsigned long)pg); return ret; } @@ -160,13 +154,11 @@ static void prng_tdes_add_entropy(void) { __u64 entropy[4]; unsigned int i; - int ret; for (i = 0; i < 16; i++) { - ret = cpacf_kmc(CPACF_KMC_PRNG, prng_data->prngws.parm_block, - (char *)entropy, (char *)entropy, - sizeof(entropy)); - BUG_ON(ret < 0 || ret != sizeof(entropy)); + cpacf_kmc(CPACF_KMC_PRNG, prng_data->prngws.parm_block, + (char *) entropy, (char *) entropy, + sizeof(entropy)); memcpy(prng_data->prngws.parm_block, entropy, sizeof(entropy)); } } @@ -303,21 +295,14 @@ static int __init prng_sha512_selftest(void) 0x21, 0xe4, 0xb0, 0x86, 0x44, 0xf6, 0x72, 0x7c, 0x36, 0x8c, 0x5a, 0x9f, 0x7a, 0x4b, 0x3e, 0xe2 }; - int ret = 0; u8 buf[sizeof(random)]; struct ppno_ws_s ws; memset(&ws, 0, sizeof(ws)); /* initial seed */ - ret = cpacf_ppno(CPACF_PPNO_SHA512_DRNG_SEED, &ws, NULL, 0, - seed, sizeof(seed)); - if (ret < 0) { - pr_err("The prng self test seed operation for the " - "SHA-512 mode failed with rc=%d\n", ret); - prng_errorflag = PRNG_SELFTEST_FAILED; - return -EIO; - } + cpacf_ppno(CPACF_PPNO_SHA512_DRNG_SEED, + &ws, NULL, 0, seed, sizeof(seed)); /* check working states V and C */ if (memcmp(ws.V, V0, sizeof(V0)) != 0 @@ -329,22 +314,10 @@ static int __init prng_sha512_selftest(void) } /* generate random bytes */ - ret = cpacf_ppno(CPACF_PPNO_SHA512_DRNG_GEN, - &ws, buf, sizeof(buf), NULL, 0); - if (ret < 0) { - pr_err("The prng self test generate operation for " - "the SHA-512 mode failed with rc=%d\n", ret); - prng_errorflag = PRNG_SELFTEST_FAILED; - return -EIO; - } - ret = cpacf_ppno(CPACF_PPNO_SHA512_DRNG_GEN, - &ws, buf, sizeof(buf), NULL, 0); - if (ret < 0) { - pr_err("The prng self test generate operation for " - "the SHA-512 mode failed with rc=%d\n", ret); - prng_errorflag = PRNG_SELFTEST_FAILED; - return -EIO; - } + cpacf_ppno(CPACF_PPNO_SHA512_DRNG_GEN, + &ws, buf, sizeof(buf), NULL, 0); + cpacf_ppno(CPACF_PPNO_SHA512_DRNG_GEN, + &ws, buf, sizeof(buf), NULL, 0); /* check against expected data */ if (memcmp(buf, random, sizeof(random)) != 0) { @@ -392,26 +365,16 @@ static int __init prng_sha512_instantiate(void) get_tod_clock_ext(seed + 48); /* initial seed of the ppno drng */ - ret = cpacf_ppno(CPACF_PPNO_SHA512_DRNG_SEED, - &prng_data->ppnows, NULL, 0, seed, sizeof(seed)); - if (ret < 0) { - prng_errorflag = PRNG_SEED_FAILED; - ret = -EIO; - goto outfree; - } + cpacf_ppno(CPACF_PPNO_SHA512_DRNG_SEED, + &prng_data->ppnows, NULL, 0, seed, sizeof(seed)); /* if fips mode is enabled, generate a first block of random bytes for the FIPS 140-2 Conditional Self Test */ if (fips_enabled) { prng_data->prev = prng_data->buf + prng_chunk_size; - ret = cpacf_ppno(CPACF_PPNO_SHA512_DRNG_GEN, - &prng_data->ppnows, - prng_data->prev, prng_chunk_size, NULL, 0); - if (ret < 0 || ret != prng_chunk_size) { - prng_errorflag = PRNG_GEN_FAILED; - ret = -EIO; - goto outfree; - } + cpacf_ppno(CPACF_PPNO_SHA512_DRNG_GEN, + &prng_data->ppnows, + prng_data->prev, prng_chunk_size, NULL, 0); } return 0; @@ -440,12 +403,8 @@ static int prng_sha512_reseed(void) return ret; /* do a reseed of the ppno drng with this bytestring */ - ret = cpacf_ppno(CPACF_PPNO_SHA512_DRNG_SEED, - &prng_data->ppnows, NULL, 0, seed, sizeof(seed)); - if (ret) { - prng_errorflag = PRNG_RESEED_FAILED; - return -EIO; - } + cpacf_ppno(CPACF_PPNO_SHA512_DRNG_SEED, + &prng_data->ppnows, NULL, 0, seed, sizeof(seed)); return 0; } @@ -463,12 +422,8 @@ static int prng_sha512_generate(u8 *buf, size_t nbytes) } /* PPNO generate */ - ret = cpacf_ppno(CPACF_PPNO_SHA512_DRNG_GEN, - &prng_data->ppnows, buf, nbytes, NULL, 0); - if (ret < 0 || ret != nbytes) { - prng_errorflag = PRNG_GEN_FAILED; - return -EIO; - } + cpacf_ppno(CPACF_PPNO_SHA512_DRNG_GEN, + &prng_data->ppnows, buf, nbytes, NULL, 0); /* FIPS 140-2 Conditional Self Test */ if (fips_enabled) { @@ -479,7 +434,7 @@ static int prng_sha512_generate(u8 *buf, size_t nbytes) memcpy(prng_data->prev, buf, nbytes); } - return ret; + return nbytes; } @@ -494,7 +449,7 @@ static int prng_open(struct inode *inode, struct file *file) static ssize_t prng_tdes_read(struct file *file, char __user *ubuf, size_t nbytes, loff_t *ppos) { - int chunk, n, tmp, ret = 0; + int chunk, n, ret = 0; /* lock prng_data struct */ if (mutex_lock_interruptible(&prng_data->mutex)) @@ -545,13 +500,9 @@ static ssize_t prng_tdes_read(struct file *file, char __user *ubuf, * * Note: you can still get strict X9.17 conformity by setting * prng_chunk_size to 8 bytes. - */ - tmp = cpacf_kmc(CPACF_KMC_PRNG, prng_data->prngws.parm_block, - prng_data->buf, prng_data->buf, n); - if (tmp < 0 || tmp != n) { - ret = -EIO; - break; - } + */ + cpacf_kmc(CPACF_KMC_PRNG, prng_data->prngws.parm_block, + prng_data->buf, prng_data->buf, n); prng_data->prngws.byte_counter += n; prng_data->prngws.reseed_counter += n; @@ -806,13 +757,13 @@ static int __init prng_init(void) int ret; /* check if the CPU has a PRNG */ - if (!cpacf_query(CPACF_KMC, CPACF_KMC_PRNG)) + if (!cpacf_query_func(CPACF_KMC, CPACF_KMC_PRNG)) return -EOPNOTSUPP; /* choose prng mode */ if (prng_mode != PRNG_MODE_TDES) { /* check for MSA5 support for PPNO operations */ - if (!cpacf_query(CPACF_PPNO, CPACF_PPNO_SHA512_DRNG_GEN)) { + if (!cpacf_query_func(CPACF_PPNO, CPACF_PPNO_SHA512_DRNG_GEN)) { if (prng_mode == PRNG_MODE_SHA512) { pr_err("The prng module cannot " "start in SHA-512 mode\n"); diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c index 5fbf91bbb478..c7de53d8da75 100644 --- a/arch/s390/crypto/sha1_s390.c +++ b/arch/s390/crypto/sha1_s390.c @@ -91,7 +91,7 @@ static struct shash_alg alg = { static int __init sha1_s390_init(void) { - if (!cpacf_query(CPACF_KIMD, CPACF_KIMD_SHA_1)) + if (!cpacf_query_func(CPACF_KIMD, CPACF_KIMD_SHA_1)) return -EOPNOTSUPP; return crypto_register_shash(&alg); } diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c index 10aac0b11988..53c277999a28 100644 --- a/arch/s390/crypto/sha256_s390.c +++ b/arch/s390/crypto/sha256_s390.c @@ -123,7 +123,7 @@ static int __init sha256_s390_init(void) { int ret; - if (!cpacf_query(CPACF_KIMD, CPACF_KIMD_SHA_256)) + if (!cpacf_query_func(CPACF_KIMD, CPACF_KIMD_SHA_256)) return -EOPNOTSUPP; ret = crypto_register_shash(&sha256_alg); if (ret < 0) diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c index ea85757be407..2f4caa1ef123 100644 --- a/arch/s390/crypto/sha512_s390.c +++ b/arch/s390/crypto/sha512_s390.c @@ -133,7 +133,7 @@ static int __init init(void) { int ret; - if (!cpacf_query(CPACF_KIMD, CPACF_KIMD_SHA_512)) + if (!cpacf_query_func(CPACF_KIMD, CPACF_KIMD_SHA_512)) return -EOPNOTSUPP; if ((ret = crypto_register_shash(&sha512_alg)) < 0) goto out; diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c index 8e908166c3ee..c740f77285b2 100644 --- a/arch/s390/crypto/sha_common.c +++ b/arch/s390/crypto/sha_common.c @@ -22,8 +22,7 @@ int s390_sha_update(struct shash_desc *desc, const u8 *data, unsigned int len) { struct s390_sha_ctx *ctx = shash_desc_ctx(desc); unsigned int bsize = crypto_shash_blocksize(desc->tfm); - unsigned int index; - int ret; + unsigned int index, n; /* how much is already in the buffer? */ index = ctx->count & (bsize - 1); @@ -35,9 +34,7 @@ int s390_sha_update(struct shash_desc *desc, const u8 *data, unsigned int len) /* process one stored block */ if (index) { memcpy(ctx->buf + index, data, bsize - index); - ret = cpacf_kimd(ctx->func, ctx->state, ctx->buf, bsize); - if (ret != bsize) - return -EIO; + cpacf_kimd(ctx->func, ctx->state, ctx->buf, bsize); data += bsize - index; len -= bsize - index; index = 0; @@ -45,12 +42,10 @@ int s390_sha_update(struct shash_desc *desc, const u8 *data, unsigned int len) /* process as many blocks as possible */ if (len >= bsize) { - ret = cpacf_kimd(ctx->func, ctx->state, data, - len & ~(bsize - 1)); - if (ret != (len & ~(bsize - 1))) - return -EIO; - data += ret; - len -= ret; + n = len & ~(bsize - 1); + cpacf_kimd(ctx->func, ctx->state, data, n); + data += n; + len -= n; } store: if (len) @@ -66,7 +61,6 @@ int s390_sha_final(struct shash_desc *desc, u8 *out) unsigned int bsize = crypto_shash_blocksize(desc->tfm); u64 bits; unsigned int index, end, plen; - int ret; /* SHA-512 uses 128 bit padding length */ plen = (bsize > SHA256_BLOCK_SIZE) ? 16 : 8; @@ -88,10 +82,7 @@ int s390_sha_final(struct shash_desc *desc, u8 *out) */ bits = ctx->count * 8; memcpy(ctx->buf + end - 8, &bits, sizeof(bits)); - - ret = cpacf_kimd(ctx->func, ctx->state, ctx->buf, end); - if (ret != end) - return -EIO; + cpacf_kimd(ctx->func, ctx->state, ctx->buf, end); /* copy digest to out */ memcpy(out, ctx->state, crypto_shash_digestsize(desc->tfm)); diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 73610f2e3b4f..2d40ef0a6295 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -172,7 +172,6 @@ CONFIG_DEBUG_NOTIFIERS=y CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_RCU_TRACE=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h index d28621de8e0b..2c680db7e5c1 100644 --- a/arch/s390/include/asm/cpacf.h +++ b/arch/s390/include/asm/cpacf.h @@ -28,67 +28,51 @@ #define CPACF_PPNO 0xb93c /* MSA5 */ /* - * Function codes for the KM (CIPHER MESSAGE) - * instruction (0x80 is the decipher modifier bit) + * Decryption modifier bit + */ +#define CPACF_DECRYPT 0x80 + +/* + * Function codes for the KM (CIPHER MESSAGE) instruction */ #define CPACF_KM_QUERY 0x00 -#define CPACF_KM_DEA_ENC 0x01 -#define CPACF_KM_DEA_DEC 0x81 -#define CPACF_KM_TDEA_128_ENC 0x02 -#define CPACF_KM_TDEA_128_DEC 0x82 -#define CPACF_KM_TDEA_192_ENC 0x03 -#define CPACF_KM_TDEA_192_DEC 0x83 -#define CPACF_KM_AES_128_ENC 0x12 -#define CPACF_KM_AES_128_DEC 0x92 -#define CPACF_KM_AES_192_ENC 0x13 -#define CPACF_KM_AES_192_DEC 0x93 -#define CPACF_KM_AES_256_ENC 0x14 -#define CPACF_KM_AES_256_DEC 0x94 -#define CPACF_KM_XTS_128_ENC 0x32 -#define CPACF_KM_XTS_128_DEC 0xb2 -#define CPACF_KM_XTS_256_ENC 0x34 -#define CPACF_KM_XTS_256_DEC 0xb4 +#define CPACF_KM_DEA 0x01 +#define CPACF_KM_TDEA_128 0x02 +#define CPACF_KM_TDEA_192 0x03 +#define CPACF_KM_AES_128 0x12 +#define CPACF_KM_AES_192 0x13 +#define CPACF_KM_AES_256 0x14 +#define CPACF_KM_XTS_128 0x32 +#define CPACF_KM_XTS_256 0x34 /* * Function codes for the KMC (CIPHER MESSAGE WITH CHAINING) - * instruction (0x80 is the decipher modifier bit) + * instruction */ #define CPACF_KMC_QUERY 0x00 -#define CPACF_KMC_DEA_ENC 0x01 -#define CPACF_KMC_DEA_DEC 0x81 -#define CPACF_KMC_TDEA_128_ENC 0x02 -#define CPACF_KMC_TDEA_128_DEC 0x82 -#define CPACF_KMC_TDEA_192_ENC 0x03 -#define CPACF_KMC_TDEA_192_DEC 0x83 -#define CPACF_KMC_AES_128_ENC 0x12 -#define CPACF_KMC_AES_128_DEC 0x92 -#define CPACF_KMC_AES_192_ENC 0x13 -#define CPACF_KMC_AES_192_DEC 0x93 -#define CPACF_KMC_AES_256_ENC 0x14 -#define CPACF_KMC_AES_256_DEC 0x94 +#define CPACF_KMC_DEA 0x01 +#define CPACF_KMC_TDEA_128 0x02 +#define CPACF_KMC_TDEA_192 0x03 +#define CPACF_KMC_AES_128 0x12 +#define CPACF_KMC_AES_192 0x13 +#define CPACF_KMC_AES_256 0x14 #define CPACF_KMC_PRNG 0x43 /* * Function codes for the KMCTR (CIPHER MESSAGE WITH COUNTER) - * instruction (0x80 is the decipher modifier bit) + * instruction */ -#define CPACF_KMCTR_QUERY 0x00 -#define CPACF_KMCTR_DEA_ENC 0x01 -#define CPACF_KMCTR_DEA_DEC 0x81 -#define CPACF_KMCTR_TDEA_128_ENC 0x02 -#define CPACF_KMCTR_TDEA_128_DEC 0x82 -#define CPACF_KMCTR_TDEA_192_ENC 0x03 -#define CPACF_KMCTR_TDEA_192_DEC 0x83 -#define CPACF_KMCTR_AES_128_ENC 0x12 -#define CPACF_KMCTR_AES_128_DEC 0x92 -#define CPACF_KMCTR_AES_192_ENC 0x13 -#define CPACF_KMCTR_AES_192_DEC 0x93 -#define CPACF_KMCTR_AES_256_ENC 0x14 -#define CPACF_KMCTR_AES_256_DEC 0x94 +#define CPACF_KMCTR_QUERY 0x00 +#define CPACF_KMCTR_DEA 0x01 +#define CPACF_KMCTR_TDEA_128 0x02 +#define CPACF_KMCTR_TDEA_192 0x03 +#define CPACF_KMCTR_AES_128 0x12 +#define CPACF_KMCTR_AES_192 0x13 +#define CPACF_KMCTR_AES_256 0x14 /* * Function codes for the KIMD (COMPUTE INTERMEDIATE MESSAGE DIGEST) - * instruction (0x80 is the decipher modifier bit) + * instruction */ #define CPACF_KIMD_QUERY 0x00 #define CPACF_KIMD_SHA_1 0x01 @@ -98,7 +82,7 @@ /* * Function codes for the KLMD (COMPUTE LAST MESSAGE DIGEST) - * instruction (0x80 is the decipher modifier bit) + * instruction */ #define CPACF_KLMD_QUERY 0x00 #define CPACF_KLMD_SHA_1 0x01 @@ -107,7 +91,7 @@ /* * function codes for the KMAC (COMPUTE MESSAGE AUTHENTICATION CODE) - * instruction (0x80 is the decipher modifier bit) + * instruction */ #define CPACF_KMAC_QUERY 0x00 #define CPACF_KMAC_DEA 0x01 @@ -116,12 +100,14 @@ /* * Function codes for the PPNO (PERFORM PSEUDORANDOM NUMBER OPERATION) - * instruction (0x80 is the decipher modifier bit) + * instruction */ #define CPACF_PPNO_QUERY 0x00 #define CPACF_PPNO_SHA512_DRNG_GEN 0x03 #define CPACF_PPNO_SHA512_DRNG_SEED 0x83 +typedef struct { unsigned char bytes[16]; } cpacf_mask_t; + /** * cpacf_query() - check if a specific CPACF function is available * @opcode: the opcode of the crypto instruction @@ -132,55 +118,66 @@ * * Returns 1 if @func is available for @opcode, 0 otherwise */ -static inline void __cpacf_query(unsigned int opcode, unsigned char *status) +static inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask) { - typedef struct { unsigned char _[16]; } status_type; register unsigned long r0 asm("0") = 0; /* query function */ - register unsigned long r1 asm("1") = (unsigned long) status; + register unsigned long r1 asm("1") = (unsigned long) mask; asm volatile( " spm 0\n" /* pckmo doesn't change the cc */ /* Parameter registers are ignored, but may not be 0 */ "0: .insn rrf,%[opc] << 16,2,2,2,0\n" " brc 1,0b\n" /* handle partial completion */ - : "=m" (*(status_type *) status) + : "=m" (*mask) : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (opcode) : "cc"); } -static inline int cpacf_query(unsigned int opcode, unsigned int func) +static inline int __cpacf_check_opcode(unsigned int opcode) { - unsigned char status[16]; - switch (opcode) { case CPACF_KMAC: case CPACF_KM: case CPACF_KMC: case CPACF_KIMD: case CPACF_KLMD: - if (!test_facility(17)) /* check for MSA */ - return 0; - break; + return test_facility(17); /* check for MSA */ case CPACF_PCKMO: - if (!test_facility(76)) /* check for MSA3 */ - return 0; - break; + return test_facility(76); /* check for MSA3 */ case CPACF_KMF: case CPACF_KMO: case CPACF_PCC: case CPACF_KMCTR: - if (!test_facility(77)) /* check for MSA4 */ - return 0; - break; + return test_facility(77); /* check for MSA4 */ case CPACF_PPNO: - if (!test_facility(57)) /* check for MSA5 */ - return 0; - break; + return test_facility(57); /* check for MSA5 */ default: BUG(); } - __cpacf_query(opcode, status); - return (status[func >> 3] & (0x80 >> (func & 7))) != 0; +} + +static inline int cpacf_query(unsigned int opcode, cpacf_mask_t *mask) +{ + if (__cpacf_check_opcode(opcode)) { + __cpacf_query(opcode, mask); + return 1; + } + memset(mask, 0, sizeof(*mask)); + return 0; +} + +static inline int cpacf_test_func(cpacf_mask_t *mask, unsigned int func) +{ + return (mask->bytes[func >> 3] & (0x80 >> (func & 7))) != 0; +} + +static inline int cpacf_query_func(unsigned int opcode, unsigned int func) +{ + cpacf_mask_t mask; + + if (cpacf_query(opcode, &mask)) + return cpacf_test_func(&mask, func); + return 0; } /** @@ -194,7 +191,7 @@ static inline int cpacf_query(unsigned int opcode, unsigned int func) * Returns 0 for the query func, number of processed bytes for * encryption/decryption funcs */ -static inline int cpacf_km(long func, void *param, +static inline int cpacf_km(unsigned long func, void *param, u8 *dest, const u8 *src, long src_len) { register unsigned long r0 asm("0") = (unsigned long) func; @@ -224,7 +221,7 @@ static inline int cpacf_km(long func, void *param, * Returns 0 for the query func, number of processed bytes for * encryption/decryption funcs */ -static inline int cpacf_kmc(long func, void *param, +static inline int cpacf_kmc(unsigned long func, void *param, u8 *dest, const u8 *src, long src_len) { register unsigned long r0 asm("0") = (unsigned long) func; @@ -250,11 +247,9 @@ static inline int cpacf_kmc(long func, void *param, * @param: address of parameter block; see POP for details on each func * @src: address of source memory area * @src_len: length of src operand in bytes - * - * Returns 0 for the query func, number of processed bytes for digest funcs */ -static inline int cpacf_kimd(long func, void *param, - const u8 *src, long src_len) +static inline void cpacf_kimd(unsigned long func, void *param, + const u8 *src, long src_len) { register unsigned long r0 asm("0") = (unsigned long) func; register unsigned long r1 asm("1") = (unsigned long) param; @@ -267,8 +262,6 @@ static inline int cpacf_kimd(long func, void *param, : [src] "+a" (r2), [len] "+d" (r3) : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_KIMD) : "cc", "memory"); - - return src_len - r3; } /** @@ -277,11 +270,9 @@ static inline int cpacf_kimd(long func, void *param, * @param: address of parameter block; see POP for details on each func * @src: address of source memory area * @src_len: length of src operand in bytes - * - * Returns 0 for the query func, number of processed bytes for digest funcs */ -static inline int cpacf_klmd(long func, void *param, - const u8 *src, long src_len) +static inline void cpacf_klmd(unsigned long func, void *param, + const u8 *src, long src_len) { register unsigned long r0 asm("0") = (unsigned long) func; register unsigned long r1 asm("1") = (unsigned long) param; @@ -294,8 +285,6 @@ static inline int cpacf_klmd(long func, void *param, : [src] "+a" (r2), [len] "+d" (r3) : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_KLMD) : "cc", "memory"); - - return src_len - r3; } /** @@ -308,7 +297,7 @@ static inline int cpacf_klmd(long func, void *param, * * Returns 0 for the query func, number of processed bytes for digest funcs */ -static inline int cpacf_kmac(long func, void *param, +static inline int cpacf_kmac(unsigned long func, void *param, const u8 *src, long src_len) { register unsigned long r0 asm("0") = (unsigned long) func; @@ -338,7 +327,7 @@ static inline int cpacf_kmac(long func, void *param, * Returns 0 for the query func, number of processed bytes for * encryption/decryption funcs */ -static inline int cpacf_kmctr(long func, void *param, u8 *dest, +static inline int cpacf_kmctr(unsigned long func, void *param, u8 *dest, const u8 *src, long src_len, u8 *counter) { register unsigned long r0 asm("0") = (unsigned long) func; @@ -368,13 +357,10 @@ static inline int cpacf_kmctr(long func, void *param, u8 *dest, * @dest_len: size of destination memory area in bytes * @seed: address of seed data * @seed_len: size of seed data in bytes - * - * Returns 0 for the query func, number of random bytes stored in - * dest buffer for generate function */ -static inline int cpacf_ppno(long func, void *param, - u8 *dest, long dest_len, - const u8 *seed, long seed_len) +static inline void cpacf_ppno(unsigned long func, void *param, + u8 *dest, long dest_len, + const u8 *seed, long seed_len) { register unsigned long r0 asm("0") = (unsigned long) func; register unsigned long r1 asm("1") = (unsigned long) param; @@ -390,8 +376,6 @@ static inline int cpacf_ppno(long func, void *param, : [fc] "d" (r0), [pba] "a" (r1), [seed] "a" (r4), [slen] "d" (r5), [opc] "i" (CPACF_PPNO) : "cc", "memory"); - - return dest_len - r3; } /** @@ -399,10 +383,8 @@ static inline int cpacf_ppno(long func, void *param, * instruction * @func: the function code passed to PCC; see CPACF_KM_xxx defines * @param: address of parameter block; see POP for details on each func - * - * Returns 0. */ -static inline int cpacf_pcc(long func, void *param) +static inline void cpacf_pcc(unsigned long func, void *param) { register unsigned long r0 asm("0") = (unsigned long) func; register unsigned long r1 asm("1") = (unsigned long) param; @@ -413,8 +395,6 @@ static inline int cpacf_pcc(long func, void *param) : : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_PCC) : "cc", "memory"); - - return 0; } #endif /* _ASM_S390_CPACF_H */ diff --git a/arch/s390/include/asm/facilities_src.h b/arch/s390/include/asm/facilities_src.h index 4917728e5828..3b758f66e48b 100644 --- a/arch/s390/include/asm/facilities_src.h +++ b/arch/s390/include/asm/facilities_src.h @@ -55,4 +55,28 @@ static struct facility_def facility_defs[] = { -1 /* END */ } }, + { + .name = "FACILITIES_KVM", + .bits = (int[]){ + 0, /* N3 instructions */ + 1, /* z/Arch mode installed */ + 2, /* z/Arch mode active */ + 3, /* DAT-enhancement */ + 4, /* idte segment table */ + 5, /* idte region table */ + 6, /* ASN-and-LX reuse */ + 7, /* stfle */ + 8, /* enhanced-DAT 1 */ + 9, /* sense-running-status */ + 10, /* conditional sske */ + 13, /* ipte-range */ + 14, /* nonquiescing key-setting */ + 73, /* transactional execution */ + 75, /* access-exception-fetch/store indication */ + 76, /* msa extension 3 */ + 77, /* msa extension 4 */ + 78, /* enhanced-DAT 2 */ + -1 /* END */ + } + }, }; diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h index 6aba6fc406ad..02124d66bfb5 100644 --- a/arch/s390/include/asm/fpu/api.h +++ b/arch/s390/include/asm/fpu/api.h @@ -64,18 +64,18 @@ static inline int test_fp_ctl(u32 fpc) return rc; } -#define KERNEL_VXR_V0V7 1 -#define KERNEL_VXR_V8V15 2 -#define KERNEL_VXR_V16V23 4 -#define KERNEL_VXR_V24V31 8 -#define KERNEL_FPR 16 -#define KERNEL_FPC 256 +#define KERNEL_FPC 1 +#define KERNEL_VXR_V0V7 2 +#define KERNEL_VXR_V8V15 4 +#define KERNEL_VXR_V16V23 8 +#define KERNEL_VXR_V24V31 16 #define KERNEL_VXR_LOW (KERNEL_VXR_V0V7|KERNEL_VXR_V8V15) #define KERNEL_VXR_MID (KERNEL_VXR_V8V15|KERNEL_VXR_V16V23) #define KERNEL_VXR_HIGH (KERNEL_VXR_V16V23|KERNEL_VXR_V24V31) -#define KERNEL_FPU_MASK (KERNEL_VXR_LOW|KERNEL_VXR_HIGH|KERNEL_FPR) +#define KERNEL_VXR (KERNEL_VXR_LOW|KERNEL_VXR_HIGH) +#define KERNEL_FPR (KERNEL_FPC|KERNEL_VXR_V0V7) struct kernel_fpu; @@ -87,18 +87,28 @@ struct kernel_fpu; * Prefer using the kernel_fpu_begin()/kernel_fpu_end() pair of functions. */ void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags); -void __kernel_fpu_end(struct kernel_fpu *state); +void __kernel_fpu_end(struct kernel_fpu *state, u32 flags); static inline void kernel_fpu_begin(struct kernel_fpu *state, u32 flags) { preempt_disable(); - __kernel_fpu_begin(state, flags); + state->mask = S390_lowcore.fpu_flags; + if (!test_cpu_flag(CIF_FPU)) + /* Save user space FPU state and register contents */ + save_fpu_regs(); + else if (state->mask & flags) + /* Save FPU/vector register in-use by the kernel */ + __kernel_fpu_begin(state, flags); + S390_lowcore.fpu_flags |= flags; } -static inline void kernel_fpu_end(struct kernel_fpu *state) +static inline void kernel_fpu_end(struct kernel_fpu *state, u32 flags) { - __kernel_fpu_end(state); + S390_lowcore.fpu_flags = state->mask; + if (state->mask & flags) + /* Restore FPU/vector register in-use by the kernel */ + __kernel_fpu_end(state, flags); preempt_enable(); } diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 8e5daf7a76ce..a41faf34b034 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -28,7 +28,7 @@ #define KVM_S390_BSCA_CPU_SLOTS 64 #define KVM_S390_ESCA_CPU_SLOTS 248 -#define KVM_MAX_VCPUS KVM_S390_ESCA_CPU_SLOTS +#define KVM_MAX_VCPUS 255 #define KVM_USER_MEM_SLOTS 32 /* @@ -245,72 +245,72 @@ struct sie_page { } __packed; struct kvm_vcpu_stat { - u32 exit_userspace; - u32 exit_null; - u32 exit_external_request; - u32 exit_external_interrupt; - u32 exit_stop_request; - u32 exit_validity; - u32 exit_instruction; - u32 exit_pei; - u32 halt_successful_poll; - u32 halt_attempted_poll; - u32 halt_poll_invalid; - u32 halt_wakeup; - u32 instruction_lctl; - u32 instruction_lctlg; - u32 instruction_stctl; - u32 instruction_stctg; - u32 exit_program_interruption; - u32 exit_instr_and_program; - u32 exit_operation_exception; - u32 deliver_external_call; - u32 deliver_emergency_signal; - u32 deliver_service_signal; - u32 deliver_virtio_interrupt; - u32 deliver_stop_signal; - u32 deliver_prefix_signal; - u32 deliver_restart_signal; - u32 deliver_program_int; - u32 deliver_io_int; - u32 exit_wait_state; - u32 instruction_pfmf; - u32 instruction_stidp; - u32 instruction_spx; - u32 instruction_stpx; - u32 instruction_stap; - u32 instruction_storage_key; - u32 instruction_ipte_interlock; - u32 instruction_stsch; - u32 instruction_chsc; - u32 instruction_stsi; - u32 instruction_stfl; - u32 instruction_tprot; - u32 instruction_sie; - u32 instruction_essa; - u32 instruction_sthyi; - u32 instruction_sigp_sense; - u32 instruction_sigp_sense_running; - u32 instruction_sigp_external_call; - u32 instruction_sigp_emergency; - u32 instruction_sigp_cond_emergency; - u32 instruction_sigp_start; - u32 instruction_sigp_stop; - u32 instruction_sigp_stop_store_status; - u32 instruction_sigp_store_status; - u32 instruction_sigp_store_adtl_status; - u32 instruction_sigp_arch; - u32 instruction_sigp_prefix; - u32 instruction_sigp_restart; - u32 instruction_sigp_init_cpu_reset; - u32 instruction_sigp_cpu_reset; - u32 instruction_sigp_unknown; - u32 diagnose_10; - u32 diagnose_44; - u32 diagnose_9c; - u32 diagnose_258; - u32 diagnose_308; - u32 diagnose_500; + u64 exit_userspace; + u64 exit_null; + u64 exit_external_request; + u64 exit_external_interrupt; + u64 exit_stop_request; + u64 exit_validity; + u64 exit_instruction; + u64 exit_pei; + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_poll_invalid; + u64 halt_wakeup; + u64 instruction_lctl; + u64 instruction_lctlg; + u64 instruction_stctl; + u64 instruction_stctg; + u64 exit_program_interruption; + u64 exit_instr_and_program; + u64 exit_operation_exception; + u64 deliver_external_call; + u64 deliver_emergency_signal; + u64 deliver_service_signal; + u64 deliver_virtio_interrupt; + u64 deliver_stop_signal; + u64 deliver_prefix_signal; + u64 deliver_restart_signal; + u64 deliver_program_int; + u64 deliver_io_int; + u64 exit_wait_state; + u64 instruction_pfmf; + u64 instruction_stidp; + u64 instruction_spx; + u64 instruction_stpx; + u64 instruction_stap; + u64 instruction_storage_key; + u64 instruction_ipte_interlock; + u64 instruction_stsch; + u64 instruction_chsc; + u64 instruction_stsi; + u64 instruction_stfl; + u64 instruction_tprot; + u64 instruction_sie; + u64 instruction_essa; + u64 instruction_sthyi; + u64 instruction_sigp_sense; + u64 instruction_sigp_sense_running; + u64 instruction_sigp_external_call; + u64 instruction_sigp_emergency; + u64 instruction_sigp_cond_emergency; + u64 instruction_sigp_start; + u64 instruction_sigp_stop; + u64 instruction_sigp_stop_store_status; + u64 instruction_sigp_store_status; + u64 instruction_sigp_store_adtl_status; + u64 instruction_sigp_arch; + u64 instruction_sigp_prefix; + u64 instruction_sigp_restart; + u64 instruction_sigp_init_cpu_reset; + u64 instruction_sigp_cpu_reset; + u64 instruction_sigp_unknown; + u64 diagnose_10; + u64 diagnose_44; + u64 diagnose_9c; + u64 diagnose_258; + u64 diagnose_308; + u64 diagnose_500; }; #define PGM_OPERATION 0x01 @@ -577,7 +577,7 @@ struct kvm_vcpu_arch { }; struct kvm_vm_stat { - u32 remote_tlb_flush; + ulong remote_tlb_flush; }; struct kvm_arch_memory_slot { diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index d79ba7cf75b0..7b93b78f423c 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -129,7 +129,8 @@ struct lowcore { __u8 pad_0x0390[0x0398-0x0390]; /* 0x0390 */ __u64 gmap; /* 0x0398 */ __u32 spinlock_lockval; /* 0x03a0 */ - __u8 pad_0x03a0[0x0400-0x03a4]; /* 0x03a4 */ + __u32 fpu_flags; /* 0x03a4 */ + __u8 pad_0x03a8[0x0400-0x03a8]; /* 0x03a8 */ /* Per cpu primary space access list */ __u32 paste[16]; /* 0x0400 */ diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index 6d39329c894b..bea785d7f853 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -12,6 +12,7 @@ typedef struct { struct list_head pgtable_list; spinlock_t gmap_lock; struct list_head gmap_list; + unsigned long gmap_asce; unsigned long asce; unsigned long asce_limit; unsigned long vdso_base; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index c6a088c91aee..515fea5a3fc4 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -21,6 +21,7 @@ static inline int init_new_context(struct task_struct *tsk, INIT_LIST_HEAD(&mm->context.gmap_list); cpumask_clear(&mm->context.cpu_attach_mask); atomic_set(&mm->context.flush_count, 0); + mm->context.gmap_asce = 0; mm->context.flush_mm = 0; #ifdef CONFIG_PGSTE mm->context.alloc_pgste = page_table_allocate_pgste; diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 0da91c4d30fd..6611f798d2be 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -11,6 +11,7 @@ #include <asm-generic/pci.h> #include <asm/pci_clp.h> #include <asm/pci_debug.h> +#include <asm/sclp.h> #define PCIBIOS_MIN_IO 0x1000 #define PCIBIOS_MIN_MEM 0x10000000 @@ -117,6 +118,7 @@ struct zpci_dev { spinlock_t iommu_bitmap_lock; unsigned long *iommu_bitmap; + unsigned long *lazy_bitmap; unsigned long iommu_size; unsigned long iommu_pages; unsigned int next_bit; @@ -216,6 +218,9 @@ void zpci_debug_init_device(struct zpci_dev *, const char *); void zpci_debug_exit_device(struct zpci_dev *); void zpci_debug_info(struct zpci_dev *, struct seq_file *); +/* Error reporting */ +int zpci_report_error(struct pci_dev *, struct zpci_report_error_header *); + #ifdef CONFIG_NUMA /* Returns the node based on PCI bus */ diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 72c7f60bfe83..0362cd5fa187 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -874,35 +874,31 @@ static inline pte_t pte_mkhuge(pte_t pte) } #endif -static inline void __ptep_ipte(unsigned long address, pte_t *ptep) -{ - unsigned long pto = (unsigned long) ptep; - - /* Invalidation + global TLB flush for the pte */ - asm volatile( - " ipte %2,%3" - : "=m" (*ptep) : "m" (*ptep), "a" (pto), "a" (address)); -} +#define IPTE_GLOBAL 0 +#define IPTE_LOCAL 1 -static inline void __ptep_ipte_local(unsigned long address, pte_t *ptep) +static inline void __ptep_ipte(unsigned long address, pte_t *ptep, int local) { unsigned long pto = (unsigned long) ptep; - /* Invalidation + local TLB flush for the pte */ + /* Invalidation + TLB flush for the pte */ asm volatile( - " .insn rrf,0xb2210000,%2,%3,0,1" - : "=m" (*ptep) : "m" (*ptep), "a" (pto), "a" (address)); + " .insn rrf,0xb2210000,%[r1],%[r2],0,%[m4]" + : "+m" (*ptep) : [r1] "a" (pto), [r2] "a" (address), + [m4] "i" (local)); } -static inline void __ptep_ipte_range(unsigned long address, int nr, pte_t *ptep) +static inline void __ptep_ipte_range(unsigned long address, int nr, + pte_t *ptep, int local) { unsigned long pto = (unsigned long) ptep; - /* Invalidate a range of ptes + global TLB flush of the ptes */ + /* Invalidate a range of ptes + TLB flush of the ptes */ do { asm volatile( - " .insn rrf,0xb2210000,%2,%0,%1,0" - : "+a" (address), "+a" (nr) : "a" (pto) : "memory"); + " .insn rrf,0xb2210000,%[r1],%[r2],%[r3],%[m4]" + : [r2] "+a" (address), [r3] "+a" (nr) + : [r1] "a" (pto), [m4] "i" (local) : "memory"); } while (nr != 255); } @@ -1239,53 +1235,33 @@ static inline void __pmdp_csp(pmd_t *pmdp) pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID); } -static inline void __pmdp_idte(unsigned long address, pmd_t *pmdp) -{ - unsigned long sto; - - sto = (unsigned long) pmdp - pmd_index(address) * sizeof(pmd_t); - asm volatile( - " .insn rrf,0xb98e0000,%2,%3,0,0" - : "=m" (*pmdp) - : "m" (*pmdp), "a" (sto), "a" ((address & HPAGE_MASK)) - : "cc" ); -} - -static inline void __pudp_idte(unsigned long address, pud_t *pudp) -{ - unsigned long r3o; - - r3o = (unsigned long) pudp - pud_index(address) * sizeof(pud_t); - r3o |= _ASCE_TYPE_REGION3; - asm volatile( - " .insn rrf,0xb98e0000,%2,%3,0,0" - : "=m" (*pudp) - : "m" (*pudp), "a" (r3o), "a" ((address & PUD_MASK)) - : "cc"); -} +#define IDTE_GLOBAL 0 +#define IDTE_LOCAL 1 -static inline void __pmdp_idte_local(unsigned long address, pmd_t *pmdp) +static inline void __pmdp_idte(unsigned long address, pmd_t *pmdp, int local) { unsigned long sto; sto = (unsigned long) pmdp - pmd_index(address) * sizeof(pmd_t); asm volatile( - " .insn rrf,0xb98e0000,%2,%3,0,1" - : "=m" (*pmdp) - : "m" (*pmdp), "a" (sto), "a" ((address & HPAGE_MASK)) + " .insn rrf,0xb98e0000,%[r1],%[r2],0,%[m4]" + : "+m" (*pmdp) + : [r1] "a" (sto), [r2] "a" ((address & HPAGE_MASK)), + [m4] "i" (local) : "cc" ); } -static inline void __pudp_idte_local(unsigned long address, pud_t *pudp) +static inline void __pudp_idte(unsigned long address, pud_t *pudp, int local) { unsigned long r3o; r3o = (unsigned long) pudp - pud_index(address) * sizeof(pud_t); r3o |= _ASCE_TYPE_REGION3; asm volatile( - " .insn rrf,0xb98e0000,%2,%3,0,1" - : "=m" (*pudp) - : "m" (*pudp), "a" (r3o), "a" ((address & PUD_MASK)) + " .insn rrf,0xb98e0000,%[r1],%[r2],0,%[m4]" + : "+m" (*pudp) + : [r1] "a" (r3o), [r2] "a" ((address & PUD_MASK)), + [m4] "i" (local) : "cc"); } diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index 1a691ef740cf..39846100682a 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -26,17 +26,6 @@ static inline void __tlb_flush_idte(unsigned long asce) : : "a" (2048), "a" (asce) : "cc"); } -/* - * Flush TLB entries for a specific ASCE on the local CPU - */ -static inline void __tlb_flush_idte_local(unsigned long asce) -{ - /* Local TLB flush for the mm */ - asm volatile( - " .insn rrf,0xb98e0000,0,%0,%1,1" - : : "a" (2048), "a" (asce) : "cc"); -} - #ifdef CONFIG_SMP void smp_ptlb_all(void); @@ -65,35 +54,33 @@ static inline void __tlb_flush_full(struct mm_struct *mm) /* Global TLB flush */ __tlb_flush_global(); /* Reset TLB flush mask */ - if (MACHINE_HAS_TLB_LC) - cpumask_copy(mm_cpumask(mm), - &mm->context.cpu_attach_mask); + cpumask_copy(mm_cpumask(mm), &mm->context.cpu_attach_mask); } atomic_dec(&mm->context.flush_count); preempt_enable(); } -/* - * Flush TLB entries for a specific ASCE on all CPUs. Should never be used - * when more than one asce (e.g. gmap) ran on this mm. - */ -static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce) +static inline void __tlb_flush_mm(struct mm_struct *mm) { + unsigned long gmap_asce; + + /* + * If the machine has IDTE we prefer to do a per mm flush + * on all cpus instead of doing a local flush if the mm + * only ran on the local cpu. + */ preempt_disable(); atomic_inc(&mm->context.flush_count); - if (MACHINE_HAS_TLB_LC && - cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) { - __tlb_flush_idte_local(asce); + gmap_asce = READ_ONCE(mm->context.gmap_asce); + if (MACHINE_HAS_IDTE && gmap_asce != -1UL) { + if (gmap_asce) + __tlb_flush_idte(gmap_asce); + __tlb_flush_idte(mm->context.asce); } else { - if (MACHINE_HAS_IDTE) - __tlb_flush_idte(asce); - else - __tlb_flush_global(); - /* Reset TLB flush mask */ - if (MACHINE_HAS_TLB_LC) - cpumask_copy(mm_cpumask(mm), - &mm->context.cpu_attach_mask); + __tlb_flush_full(mm); } + /* Reset TLB flush mask */ + cpumask_copy(mm_cpumask(mm), &mm->context.cpu_attach_mask); atomic_dec(&mm->context.flush_count); preempt_enable(); } @@ -112,36 +99,17 @@ static inline void __tlb_flush_kernel(void) /* * Flush TLB entries for a specific ASCE on all CPUs. */ -static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce) +static inline void __tlb_flush_mm(struct mm_struct *mm) { - if (MACHINE_HAS_TLB_LC) - __tlb_flush_idte_local(asce); - else - __tlb_flush_local(); + __tlb_flush_local(); } static inline void __tlb_flush_kernel(void) { - if (MACHINE_HAS_TLB_LC) - __tlb_flush_idte_local(init_mm.context.asce); - else - __tlb_flush_local(); + __tlb_flush_local(); } #endif -static inline void __tlb_flush_mm(struct mm_struct * mm) -{ - /* - * If the machine has IDTE we prefer to do a per mm flush - * on all cpus instead of doing a local flush if the mm - * only ran on the local cpu. - */ - if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list)) - __tlb_flush_asce(mm, mm->context.asce); - else - __tlb_flush_full(mm); -} - static inline void __tlb_flush_mm_lazy(struct mm_struct * mm) { if (mm->context.flush_mm) { diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 9b49cf1daa8f..52d7c8709279 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -266,28 +266,28 @@ int __put_user_bad(void) __attribute__((noreturn)); __chk_user_ptr(ptr); \ switch (sizeof(*(ptr))) { \ case 1: { \ - unsigned char __x; \ + unsigned char __x = 0; \ __gu_err = __get_user_fn(&__x, ptr, \ sizeof(*(ptr))); \ (x) = *(__force __typeof__(*(ptr)) *) &__x; \ break; \ }; \ case 2: { \ - unsigned short __x; \ + unsigned short __x = 0; \ __gu_err = __get_user_fn(&__x, ptr, \ sizeof(*(ptr))); \ (x) = *(__force __typeof__(*(ptr)) *) &__x; \ break; \ }; \ case 4: { \ - unsigned int __x; \ + unsigned int __x = 0; \ __gu_err = __get_user_fn(&__x, ptr, \ sizeof(*(ptr))); \ (x) = *(__force __typeof__(*(ptr)) *) &__x; \ break; \ }; \ case 8: { \ - unsigned long long __x; \ + unsigned long long __x = 0; \ __gu_err = __get_user_fn(&__x, ptr, \ sizeof(*(ptr))); \ (x) = *(__force __typeof__(*(ptr)) *) &__x; \ @@ -311,6 +311,14 @@ int __get_user_bad(void) __attribute__((noreturn)); #define __put_user_unaligned __put_user #define __get_user_unaligned __get_user +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} + /** * copy_to_user: - Copy a block of data into user space. * @to: Destination address, in user space. @@ -332,12 +340,6 @@ copy_to_user(void __user *to, const void *from, unsigned long n) return __copy_to_user(to, from, n); } -void copy_from_user_overflow(void) -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -__compiletime_warning("copy_from_user() buffer size is not provably correct") -#endif -; - /** * copy_from_user: - Copy a block of data from user space. * @to: Destination address, in kernel space. @@ -362,7 +364,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n) might_fault(); if (unlikely(sz != -1 && sz < n)) { - copy_from_user_overflow(); + if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); + else + __bad_copy_user(); return n; } return __copy_from_user(to, from, n); diff --git a/arch/s390/include/asm/vx-insn.h b/arch/s390/include/asm/vx-insn.h index 4a3135620f5e..49c24a2afce0 100644 --- a/arch/s390/include/asm/vx-insn.h +++ b/arch/s390/include/asm/vx-insn.h @@ -16,15 +16,13 @@ /* Macros to generate vector instruction byte code */ -#define REG_NUM_INVALID 255 - /* GR_NUM - Retrieve general-purpose register number * * @opd: Operand to store register number * @r64: String designation register in the format "%rN" */ .macro GR_NUM opd gr - \opd = REG_NUM_INVALID + \opd = 255 .ifc \gr,%r0 \opd = 0 .endif @@ -73,14 +71,11 @@ .ifc \gr,%r15 \opd = 15 .endif - .if \opd == REG_NUM_INVALID - .error "Invalid general-purpose register designation: \gr" + .if \opd == 255 + \opd = \gr .endif .endm -/* VX_R() - Macro to encode the VX_NUM into the instruction */ -#define VX_R(v) (v & 0x0F) - /* VX_NUM - Retrieve vector register number * * @opd: Operand to store register number @@ -88,11 +83,10 @@ * * The vector register number is used for as input number to the * instruction and, as well as, to compute the RXB field of the - * instruction. To encode the particular vector register number, - * use the VX_R(v) macro to extract the instruction opcode. + * instruction. */ .macro VX_NUM opd vxr - \opd = REG_NUM_INVALID + \opd = 255 .ifc \vxr,%v0 \opd = 0 .endif @@ -189,8 +183,8 @@ .ifc \vxr,%v31 \opd = 31 .endif - .if \opd == REG_NUM_INVALID - .error "Invalid vector register designation: \vxr" + .if \opd == 255 + \opd = \vxr .endif .endm @@ -251,7 +245,7 @@ /* VECTOR GENERATE BYTE MASK */ .macro VGBM vr imm2 VX_NUM v1, \vr - .word (0xE700 | (VX_R(v1) << 4)) + .word (0xE700 | ((v1&15) << 4)) .word \imm2 MRXBOPC 0, 0x44, v1 .endm @@ -267,7 +261,7 @@ VX_NUM v1, \v GR_NUM b2, "%r0" GR_NUM r3, \gr - .word 0xE700 | (VX_R(v1) << 4) | r3 + .word 0xE700 | ((v1&15) << 4) | r3 .word (b2 << 12) | (\disp) MRXBOPC \m, 0x22, v1 .endm @@ -284,12 +278,21 @@ VLVG \v, \gr, \index, 3 .endm +/* VECTOR LOAD REGISTER */ +.macro VLR v1, v2 + VX_NUM v1, \v1 + VX_NUM v2, \v2 + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word 0 + MRXBOPC 0, 0x56, v1, v2 +.endm + /* VECTOR LOAD */ .macro VL v, disp, index="%r0", base VX_NUM v1, \v GR_NUM x2, \index GR_NUM b2, \base - .word 0xE700 | (VX_R(v1) << 4) | x2 + .word 0xE700 | ((v1&15) << 4) | x2 .word (b2 << 12) | (\disp) MRXBOPC 0, 0x06, v1 .endm @@ -299,7 +302,7 @@ VX_NUM v1, \vr1 GR_NUM x2, \index GR_NUM b2, \base - .word 0xE700 | (VX_R(v1) << 4) | x2 + .word 0xE700 | ((v1&15) << 4) | x2 .word (b2 << 12) | (\disp) MRXBOPC \m3, \opc, v1 .endm @@ -319,7 +322,7 @@ /* VECTOR LOAD ELEMENT IMMEDIATE */ .macro VLEIx vr1, imm2, m3, opc VX_NUM v1, \vr1 - .word 0xE700 | (VX_R(v1) << 4) + .word 0xE700 | ((v1&15) << 4) .word \imm2 MRXBOPC \m3, \opc, v1 .endm @@ -341,7 +344,7 @@ GR_NUM r1, \gr GR_NUM b2, \base VX_NUM v3, \vr - .word 0xE700 | (r1 << 4) | VX_R(v3) + .word 0xE700 | (r1 << 4) | (v3&15) .word (b2 << 12) | (\disp) MRXBOPC \m, 0x21, v3 .endm @@ -363,7 +366,7 @@ VX_NUM v1, \vfrom VX_NUM v3, \vto GR_NUM b2, \base /* Base register */ - .word 0xE700 | (VX_R(v1) << 4) | VX_R(v3) + .word 0xE700 | ((v1&15) << 4) | (v3&15) .word (b2 << 12) | (\disp) MRXBOPC 0, 0x36, v1, v3 .endm @@ -373,7 +376,7 @@ VX_NUM v1, \vfrom VX_NUM v3, \vto GR_NUM b2, \base /* Base register */ - .word 0xE700 | (VX_R(v1) << 4) | VX_R(v3) + .word 0xE700 | ((v1&15) << 4) | (v3&15) .word (b2 << 12) | (\disp) MRXBOPC 0, 0x3E, v1, v3 .endm @@ -384,16 +387,16 @@ VX_NUM v2, \vr2 VX_NUM v3, \vr3 VX_NUM v4, \vr4 - .word 0xE700 | (VX_R(v1) << 4) | VX_R(v2) - .word (VX_R(v3) << 12) - MRXBOPC VX_R(v4), 0x8C, v1, v2, v3, v4 + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word ((v3&15) << 12) + MRXBOPC (v4&15), 0x8C, v1, v2, v3, v4 .endm /* VECTOR UNPACK LOGICAL LOW */ .macro VUPLL vr1, vr2, m3 VX_NUM v1, \vr1 VX_NUM v2, \vr2 - .word 0xE700 | (VX_R(v1) << 4) | VX_R(v2) + .word 0xE700 | ((v1&15) << 4) | (v2&15) .word 0x0000 MRXBOPC \m3, 0xD4, v1, v2 .endm @@ -410,13 +413,23 @@ /* Vector integer instructions */ +/* VECTOR AND */ +.macro VN vr1, vr2, vr3 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + VX_NUM v3, \vr3 + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word ((v3&15) << 12) + MRXBOPC 0, 0x68, v1, v2, v3 +.endm + /* VECTOR EXCLUSIVE OR */ .macro VX vr1, vr2, vr3 VX_NUM v1, \vr1 VX_NUM v2, \vr2 VX_NUM v3, \vr3 - .word 0xE700 | (VX_R(v1) << 4) | VX_R(v2) - .word (VX_R(v3) << 12) + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word ((v3&15) << 12) MRXBOPC 0, 0x6D, v1, v2, v3 .endm @@ -425,8 +438,8 @@ VX_NUM v1, \vr1 VX_NUM v2, \vr2 VX_NUM v3, \vr3 - .word 0xE700 | (VX_R(v1) << 4) | VX_R(v2) - .word (VX_R(v3) << 12) + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word ((v3&15) << 12) MRXBOPC \m4, 0xB4, v1, v2, v3 .endm .macro VGFMB vr1, vr2, vr3 @@ -448,9 +461,9 @@ VX_NUM v2, \vr2 VX_NUM v3, \vr3 VX_NUM v4, \vr4 - .word 0xE700 | (VX_R(v1) << 4) | VX_R(v2) - .word (VX_R(v3) << 12) | (\m5 << 8) - MRXBOPC VX_R(v4), 0xBC, v1, v2, v3, v4 + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word ((v3&15) << 12) | (\m5 << 8) + MRXBOPC (v4&15), 0xBC, v1, v2, v3, v4 .endm .macro VGFMAB vr1, vr2, vr3, vr4 VGFMA \vr1, \vr2, \vr3, \vr4, 0 @@ -470,11 +483,78 @@ VX_NUM v1, \vr1 VX_NUM v2, \vr2 VX_NUM v3, \vr3 - .word 0xE700 | (VX_R(v1) << 4) | VX_R(v2) - .word (VX_R(v3) << 12) + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word ((v3&15) << 12) MRXBOPC 0, 0x7D, v1, v2, v3 .endm +/* VECTOR REPLICATE IMMEDIATE */ +.macro VREPI vr1, imm2, m3 + VX_NUM v1, \vr1 + .word 0xE700 | ((v1&15) << 4) + .word \imm2 + MRXBOPC \m3, 0x45, v1 +.endm +.macro VREPIB vr1, imm2 + VREPI \vr1, \imm2, 0 +.endm +.macro VREPIH vr1, imm2 + VREPI \vr1, \imm2, 1 +.endm +.macro VREPIF vr1, imm2 + VREPI \vr1, \imm2, 2 +.endm +.macro VREPIG vr1, imm2 + VREP \vr1, \imm2, 3 +.endm + +/* VECTOR ADD */ +.macro VA vr1, vr2, vr3, m4 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + VX_NUM v3, \vr3 + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word ((v3&15) << 12) + MRXBOPC \m4, 0xF3, v1, v2, v3 +.endm +.macro VAB vr1, vr2, vr3 + VA \vr1, \vr2, \vr3, 0 +.endm +.macro VAH vr1, vr2, vr3 + VA \vr1, \vr2, \vr3, 1 +.endm +.macro VAF vr1, vr2, vr3 + VA \vr1, \vr2, \vr3, 2 +.endm +.macro VAG vr1, vr2, vr3 + VA \vr1, \vr2, \vr3, 3 +.endm +.macro VAQ vr1, vr2, vr3 + VA \vr1, \vr2, \vr3, 4 +.endm + +/* VECTOR ELEMENT SHIFT RIGHT ARITHMETIC */ +.macro VESRAV vr1, vr2, vr3, m4 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + VX_NUM v3, \vr3 + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word ((v3&15) << 12) + MRXBOPC \m4, 0x7A, v1, v2, v3 +.endm + +.macro VESRAVB vr1, vr2, vr3 + VESRAV \vr1, \vr2, \vr3, 0 +.endm +.macro VESRAVH vr1, vr2, vr3 + VESRAV \vr1, \vr2, \vr3, 1 +.endm +.macro VESRAVF vr1, vr2, vr3 + VESRAV \vr1, \vr2, \vr3, 2 +.endm +.macro VESRAVG vr1, vr2, vr3 + VESRAV \vr1, \vr2, \vr3, 3 +.endm #endif /* __ASSEMBLY__ */ #endif /* __ASM_S390_VX_INSN_H */ diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild index 08fe6dad9026..cc44b09c25fc 100644 --- a/arch/s390/include/uapi/asm/Kbuild +++ b/arch/s390/include/uapi/asm/Kbuild @@ -6,6 +6,7 @@ header-y += bitsperlong.h header-y += byteorder.h header-y += chpid.h header-y += chsc.h +header-y += clp.h header-y += cmb.h header-y += dasd.h header-y += debug.h diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 3234817c7d47..72ccc41444dc 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -48,6 +48,9 @@ AFLAGS_head.o += -march=z900 endif GCOV_PROFILE_sclp.o := n GCOV_PROFILE_als.o := n +UBSAN_SANITIZE_als.o := n +UBSAN_SANITIZE_early.o := n +UBSAN_SANITIZE_sclp.o := n obj-y := traps.o time.o process.o base.o early.o setup.o idle.o vtime.o obj-y += processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 1f95cc1faeb7..f3df9e0a5dec 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -125,6 +125,7 @@ int main(void) OFFSET(__LC_STFL_FAC_LIST, lowcore, stfl_fac_list); OFFSET(__LC_STFLE_FAC_LIST, lowcore, stfle_fac_list); OFFSET(__LC_MCCK_CODE, lowcore, mcck_interruption_code); + OFFSET(__LC_EXT_DAMAGE_CODE, lowcore, external_damage_code); OFFSET(__LC_MCCK_FAIL_STOR_ADDR, lowcore, failing_storage_address); OFFSET(__LC_LAST_BREAK, lowcore, breaking_event_addr); OFFSET(__LC_RST_OLD_PSW, lowcore, restart_old_psw); diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index 29df8484282b..f9293bfefb7f 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -71,9 +71,7 @@ struct save_area * __init save_area_alloc(bool is_boot_cpu) */ struct save_area * __init save_area_boot_cpu(void) { - if (list_empty(&dump_save_areas)) - return NULL; - return list_first_entry(&dump_save_areas, struct save_area, list); + return list_first_entry_or_null(&dump_save_areas, struct save_area, list); } /* diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 717b03aa16b5..2374c5b46bbc 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -13,7 +13,7 @@ #include <linux/string.h> #include <linux/ctype.h> #include <linux/lockdep.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/pfn.h> #include <linux/uaccess.h> #include <linux/kernel.h> diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c index 81d1d1887507..1235b9438df4 100644 --- a/arch/s390/kernel/fpu.c +++ b/arch/s390/kernel/fpu.c @@ -10,240 +10,167 @@ #include <asm/fpu/types.h> #include <asm/fpu/api.h> -/* - * Per-CPU variable to maintain FPU register ranges that are in use - * by the kernel. - */ -static DEFINE_PER_CPU(u32, kernel_fpu_state); - -#define KERNEL_FPU_STATE_MASK (KERNEL_FPU_MASK|KERNEL_FPC) - +asm(".include \"asm/vx-insn.h\"\n"); void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags) { - if (!__this_cpu_read(kernel_fpu_state)) { - /* - * Save user space FPU state and register contents. Multiple - * calls because of interruptions do not matter and return - * immediately. This also sets CIF_FPU to lazy restore FP/VX - * register contents when returning to user space. - */ - save_fpu_regs(); - } - - /* Update flags to use the vector facility for KERNEL_FPR */ - if (MACHINE_HAS_VX && (state->mask & KERNEL_FPR)) { - flags |= KERNEL_VXR_LOW | KERNEL_FPC; - flags &= ~KERNEL_FPR; - } - - /* Save and update current kernel VX state */ - state->mask = __this_cpu_read(kernel_fpu_state); - __this_cpu_or(kernel_fpu_state, flags & KERNEL_FPU_STATE_MASK); - /* - * If this is the first call to __kernel_fpu_begin(), no additional - * work is required. + * Limit the save to the FPU/vector registers already + * in use by the previous context */ - if (!(state->mask & KERNEL_FPU_STATE_MASK)) - return; + flags &= state->mask; - /* - * If KERNEL_FPR is still set, the vector facility is not available - * and, thus, save floating-point control and registers only. - */ - if (state->mask & KERNEL_FPR) { - asm volatile("stfpc %0" : "=Q" (state->fpc)); - asm volatile("std 0,%0" : "=Q" (state->fprs[0])); - asm volatile("std 1,%0" : "=Q" (state->fprs[1])); - asm volatile("std 2,%0" : "=Q" (state->fprs[2])); - asm volatile("std 3,%0" : "=Q" (state->fprs[3])); - asm volatile("std 4,%0" : "=Q" (state->fprs[4])); - asm volatile("std 5,%0" : "=Q" (state->fprs[5])); - asm volatile("std 6,%0" : "=Q" (state->fprs[6])); - asm volatile("std 7,%0" : "=Q" (state->fprs[7])); - asm volatile("std 8,%0" : "=Q" (state->fprs[8])); - asm volatile("std 9,%0" : "=Q" (state->fprs[9])); - asm volatile("std 10,%0" : "=Q" (state->fprs[10])); - asm volatile("std 11,%0" : "=Q" (state->fprs[11])); - asm volatile("std 12,%0" : "=Q" (state->fprs[12])); - asm volatile("std 13,%0" : "=Q" (state->fprs[13])); - asm volatile("std 14,%0" : "=Q" (state->fprs[14])); - asm volatile("std 15,%0" : "=Q" (state->fprs[15])); + if (flags & KERNEL_FPC) + /* Save floating point control */ + asm volatile("stfpc %0" : "=m" (state->fpc)); + + if (!MACHINE_HAS_VX) { + if (flags & KERNEL_VXR_V0V7) { + /* Save floating-point registers */ + asm volatile("std 0,%0" : "=Q" (state->fprs[0])); + asm volatile("std 1,%0" : "=Q" (state->fprs[1])); + asm volatile("std 2,%0" : "=Q" (state->fprs[2])); + asm volatile("std 3,%0" : "=Q" (state->fprs[3])); + asm volatile("std 4,%0" : "=Q" (state->fprs[4])); + asm volatile("std 5,%0" : "=Q" (state->fprs[5])); + asm volatile("std 6,%0" : "=Q" (state->fprs[6])); + asm volatile("std 7,%0" : "=Q" (state->fprs[7])); + asm volatile("std 8,%0" : "=Q" (state->fprs[8])); + asm volatile("std 9,%0" : "=Q" (state->fprs[9])); + asm volatile("std 10,%0" : "=Q" (state->fprs[10])); + asm volatile("std 11,%0" : "=Q" (state->fprs[11])); + asm volatile("std 12,%0" : "=Q" (state->fprs[12])); + asm volatile("std 13,%0" : "=Q" (state->fprs[13])); + asm volatile("std 14,%0" : "=Q" (state->fprs[14])); + asm volatile("std 15,%0" : "=Q" (state->fprs[15])); + } return; } - /* - * If this is a nested call to __kernel_fpu_begin(), check the saved - * state mask to save and later restore the vector registers that - * are already in use. Let's start with checking floating-point - * controls. - */ - if (state->mask & KERNEL_FPC) - asm volatile("stfpc %0" : "=m" (state->fpc)); - /* Test and save vector registers */ asm volatile ( /* * Test if any vector register must be saved and, if so, * test if all register can be saved. */ - " tmll %[m],15\n" /* KERNEL_VXR_MASK */ - " jz 20f\n" /* no work -> done */ " la 1,%[vxrs]\n" /* load save area */ - " jo 18f\n" /* -> save V0..V31 */ - + " tmll %[m],30\n" /* KERNEL_VXR */ + " jz 7f\n" /* no work -> done */ + " jo 5f\n" /* -> save V0..V31 */ /* - * Test if V8..V23 can be saved at once... this speeds up - * for KERNEL_fpu_MID only. Otherwise continue to split the - * range of vector registers into two halves and test them - * separately. + * Test for special case KERNEL_FPU_MID only. In this + * case a vstm V8..V23 is the best instruction */ - " tmll %[m],6\n" /* KERNEL_VXR_MID */ - " jo 17f\n" /* -> save V8..V23 */ - + " chi %[m],12\n" /* KERNEL_VXR_MID */ + " jne 0f\n" /* -> save V8..V23 */ + " VSTM 8,23,128,1\n" /* vstm %v8,%v23,128(%r1) */ + " j 7f\n" /* Test and save the first half of 16 vector registers */ - "1: tmll %[m],3\n" /* KERNEL_VXR_LOW */ - " jz 10f\n" /* -> KERNEL_VXR_HIGH */ + "0: tmll %[m],6\n" /* KERNEL_VXR_LOW */ + " jz 3f\n" /* -> KERNEL_VXR_HIGH */ " jo 2f\n" /* 11 -> save V0..V15 */ - " brc 4,3f\n" /* 01 -> save V0..V7 */ - " brc 2,4f\n" /* 10 -> save V8..V15 */ - + " brc 2,1f\n" /* 10 -> save V8..V15 */ + " VSTM 0,7,0,1\n" /* vstm %v0,%v7,0(%r1) */ + " j 3f\n" + "1: VSTM 8,15,128,1\n" /* vstm %v8,%v15,128(%r1) */ + " j 3f\n" + "2: VSTM 0,15,0,1\n" /* vstm %v0,%v15,0(%r1) */ /* Test and save the second half of 16 vector registers */ - "10: tmll %[m],12\n" /* KERNEL_VXR_HIGH */ - " jo 19f\n" /* 11 -> save V16..V31 */ - " brc 4,11f\n" /* 01 -> save V16..V23 */ - " brc 2,12f\n" /* 10 -> save V24..V31 */ - " j 20f\n" /* 00 -> done */ - - /* - * Below are the vstm combinations to save multiple vector - * registers at once. - */ - "2: .word 0xe70f,0x1000,0x003e\n" /* vstm 0,15,0(1) */ - " j 10b\n" /* -> VXR_HIGH */ - "3: .word 0xe707,0x1000,0x003e\n" /* vstm 0,7,0(1) */ - " j 10b\n" /* -> VXR_HIGH */ - "4: .word 0xe78f,0x1080,0x003e\n" /* vstm 8,15,128(1) */ - " j 10b\n" /* -> VXR_HIGH */ - "\n" - "11: .word 0xe707,0x1100,0x0c3e\n" /* vstm 16,23,256(1) */ - " j 20f\n" /* -> done */ - "12: .word 0xe78f,0x1180,0x0c3e\n" /* vstm 24,31,384(1) */ - " j 20f\n" /* -> done */ - "\n" - "17: .word 0xe787,0x1080,0x043e\n" /* vstm 8,23,128(1) */ - " nill %[m],249\n" /* m &= ~VXR_MID */ - " j 1b\n" /* -> VXR_LOW */ - "\n" - "18: .word 0xe70f,0x1000,0x003e\n" /* vstm 0,15,0(1) */ - "19: .word 0xe70f,0x1100,0x0c3e\n" /* vstm 16,31,256(1) */ - "20:" + "3: tmll %[m],24\n" /* KERNEL_VXR_HIGH */ + " jz 7f\n" + " jo 6f\n" /* 11 -> save V16..V31 */ + " brc 2,4f\n" /* 10 -> save V24..V31 */ + " VSTM 16,23,256,1\n" /* vstm %v16,%v23,256(%r1) */ + " j 7f\n" + "4: VSTM 24,31,384,1\n" /* vstm %v24,%v31,384(%r1) */ + " j 7f\n" + "5: VSTM 0,15,0,1\n" /* vstm %v0,%v15,0(%r1) */ + "6: VSTM 16,31,256,1\n" /* vstm %v16,%v31,256(%r1) */ + "7:" : [vxrs] "=Q" (*(struct vx_array *) &state->vxrs) - : [m] "d" (state->mask) + : [m] "d" (flags) : "1", "cc"); } EXPORT_SYMBOL(__kernel_fpu_begin); -void __kernel_fpu_end(struct kernel_fpu *state) +void __kernel_fpu_end(struct kernel_fpu *state, u32 flags) { - /* Just update the per-CPU state if there is nothing to restore */ - if (!(state->mask & KERNEL_FPU_STATE_MASK)) - goto update_fpu_state; - /* - * If KERNEL_FPR is specified, the vector facility is not available - * and, thus, restore floating-point control and registers only. + * Limit the restore to the FPU/vector registers of the + * previous context that have been overwritte by the + * current context */ - if (state->mask & KERNEL_FPR) { - asm volatile("lfpc %0" : : "Q" (state->fpc)); - asm volatile("ld 0,%0" : : "Q" (state->fprs[0])); - asm volatile("ld 1,%0" : : "Q" (state->fprs[1])); - asm volatile("ld 2,%0" : : "Q" (state->fprs[2])); - asm volatile("ld 3,%0" : : "Q" (state->fprs[3])); - asm volatile("ld 4,%0" : : "Q" (state->fprs[4])); - asm volatile("ld 5,%0" : : "Q" (state->fprs[5])); - asm volatile("ld 6,%0" : : "Q" (state->fprs[6])); - asm volatile("ld 7,%0" : : "Q" (state->fprs[7])); - asm volatile("ld 8,%0" : : "Q" (state->fprs[8])); - asm volatile("ld 9,%0" : : "Q" (state->fprs[9])); - asm volatile("ld 10,%0" : : "Q" (state->fprs[10])); - asm volatile("ld 11,%0" : : "Q" (state->fprs[11])); - asm volatile("ld 12,%0" : : "Q" (state->fprs[12])); - asm volatile("ld 13,%0" : : "Q" (state->fprs[13])); - asm volatile("ld 14,%0" : : "Q" (state->fprs[14])); - asm volatile("ld 15,%0" : : "Q" (state->fprs[15])); - goto update_fpu_state; - } + flags &= state->mask; - /* Test and restore floating-point controls */ - if (state->mask & KERNEL_FPC) + if (flags & KERNEL_FPC) + /* Restore floating-point controls */ asm volatile("lfpc %0" : : "Q" (state->fpc)); + if (!MACHINE_HAS_VX) { + if (flags & KERNEL_VXR_V0V7) { + /* Restore floating-point registers */ + asm volatile("ld 0,%0" : : "Q" (state->fprs[0])); + asm volatile("ld 1,%0" : : "Q" (state->fprs[1])); + asm volatile("ld 2,%0" : : "Q" (state->fprs[2])); + asm volatile("ld 3,%0" : : "Q" (state->fprs[3])); + asm volatile("ld 4,%0" : : "Q" (state->fprs[4])); + asm volatile("ld 5,%0" : : "Q" (state->fprs[5])); + asm volatile("ld 6,%0" : : "Q" (state->fprs[6])); + asm volatile("ld 7,%0" : : "Q" (state->fprs[7])); + asm volatile("ld 8,%0" : : "Q" (state->fprs[8])); + asm volatile("ld 9,%0" : : "Q" (state->fprs[9])); + asm volatile("ld 10,%0" : : "Q" (state->fprs[10])); + asm volatile("ld 11,%0" : : "Q" (state->fprs[11])); + asm volatile("ld 12,%0" : : "Q" (state->fprs[12])); + asm volatile("ld 13,%0" : : "Q" (state->fprs[13])); + asm volatile("ld 14,%0" : : "Q" (state->fprs[14])); + asm volatile("ld 15,%0" : : "Q" (state->fprs[15])); + } + return; + } + /* Test and restore (load) vector registers */ asm volatile ( /* - * Test if any vector registers must be loaded and, if so, + * Test if any vector register must be loaded and, if so, * test if all registers can be loaded at once. */ - " tmll %[m],15\n" /* KERNEL_VXR_MASK */ - " jz 20f\n" /* no work -> done */ - " la 1,%[vxrs]\n" /* load load area */ - " jo 18f\n" /* -> load V0..V31 */ - - /* - * Test if V8..V23 can be restored at once... this speeds up - * for KERNEL_VXR_MID only. Otherwise continue to split the - * range of vector registers into two halves and test them - * separately. - */ - " tmll %[m],6\n" /* KERNEL_VXR_MID */ - " jo 17f\n" /* -> load V8..V23 */ - - /* Test and load the first half of 16 vector registers */ - "1: tmll %[m],3\n" /* KERNEL_VXR_LOW */ - " jz 10f\n" /* -> KERNEL_VXR_HIGH */ - " jo 2f\n" /* 11 -> load V0..V15 */ - " brc 4,3f\n" /* 01 -> load V0..V7 */ - " brc 2,4f\n" /* 10 -> load V8..V15 */ - - /* Test and load the second half of 16 vector registers */ - "10: tmll %[m],12\n" /* KERNEL_VXR_HIGH */ - " jo 19f\n" /* 11 -> load V16..V31 */ - " brc 4,11f\n" /* 01 -> load V16..V23 */ - " brc 2,12f\n" /* 10 -> load V24..V31 */ - " j 20f\n" /* 00 -> done */ - + " la 1,%[vxrs]\n" /* load restore area */ + " tmll %[m],30\n" /* KERNEL_VXR */ + " jz 7f\n" /* no work -> done */ + " jo 5f\n" /* -> restore V0..V31 */ /* - * Below are the vstm combinations to load multiple vector - * registers at once. + * Test for special case KERNEL_FPU_MID only. In this + * case a vlm V8..V23 is the best instruction */ - "2: .word 0xe70f,0x1000,0x0036\n" /* vlm 0,15,0(1) */ - " j 10b\n" /* -> VXR_HIGH */ - "3: .word 0xe707,0x1000,0x0036\n" /* vlm 0,7,0(1) */ - " j 10b\n" /* -> VXR_HIGH */ - "4: .word 0xe78f,0x1080,0x0036\n" /* vlm 8,15,128(1) */ - " j 10b\n" /* -> VXR_HIGH */ - "\n" - "11: .word 0xe707,0x1100,0x0c36\n" /* vlm 16,23,256(1) */ - " j 20f\n" /* -> done */ - "12: .word 0xe78f,0x1180,0x0c36\n" /* vlm 24,31,384(1) */ - " j 20f\n" /* -> done */ - "\n" - "17: .word 0xe787,0x1080,0x0436\n" /* vlm 8,23,128(1) */ - " nill %[m],249\n" /* m &= ~VXR_MID */ - " j 1b\n" /* -> VXR_LOW */ - "\n" - "18: .word 0xe70f,0x1000,0x0036\n" /* vlm 0,15,0(1) */ - "19: .word 0xe70f,0x1100,0x0c36\n" /* vlm 16,31,256(1) */ - "20:" - : - : [vxrs] "Q" (*(struct vx_array *) &state->vxrs), - [m] "d" (state->mask) + " chi %[m],12\n" /* KERNEL_VXR_MID */ + " jne 0f\n" /* -> restore V8..V23 */ + " VLM 8,23,128,1\n" /* vlm %v8,%v23,128(%r1) */ + " j 7f\n" + /* Test and restore the first half of 16 vector registers */ + "0: tmll %[m],6\n" /* KERNEL_VXR_LOW */ + " jz 3f\n" /* -> KERNEL_VXR_HIGH */ + " jo 2f\n" /* 11 -> restore V0..V15 */ + " brc 2,1f\n" /* 10 -> restore V8..V15 */ + " VLM 0,7,0,1\n" /* vlm %v0,%v7,0(%r1) */ + " j 3f\n" + "1: VLM 8,15,128,1\n" /* vlm %v8,%v15,128(%r1) */ + " j 3f\n" + "2: VLM 0,15,0,1\n" /* vlm %v0,%v15,0(%r1) */ + /* Test and restore the second half of 16 vector registers */ + "3: tmll %[m],24\n" /* KERNEL_VXR_HIGH */ + " jz 7f\n" + " jo 6f\n" /* 11 -> restore V16..V31 */ + " brc 2,4f\n" /* 10 -> restore V24..V31 */ + " VLM 16,23,256,1\n" /* vlm %v16,%v23,256(%r1) */ + " j 7f\n" + "4: VLM 24,31,384,1\n" /* vlm %v24,%v31,384(%r1) */ + " j 7f\n" + "5: VLM 0,15,0,1\n" /* vlm %v0,%v15,0(%r1) */ + "6: VLM 16,31,256,1\n" /* vlm %v16,%v31,256(%r1) */ + "7:" + : [vxrs] "=Q" (*(struct vx_array *) &state->vxrs) + : [m] "d" (flags) : "1", "cc"); - -update_fpu_state: - /* Update current kernel VX state */ - __this_cpu_write(kernel_fpu_state, state->mask); } EXPORT_SYMBOL(__kernel_fpu_end); diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 0f7bfeba6da6..60a8a4e207ed 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -209,7 +209,8 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) /* Only trace if the calling function expects to. */ if (!ftrace_graph_entry(&trace)) goto out; - if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) + if (ftrace_push_return_trace(parent, ip, &trace.depth, 0, + NULL) == -EBUSY) goto out; parent = (unsigned long) return_to_handler; out: diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index dd6306c51bd6..fdb40424acfe 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -26,12 +26,14 @@ #include <linux/stop_machine.h> #include <linux/kdebug.h> #include <linux/uaccess.h> +#include <linux/extable.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/hardirq.h> #include <linux/ftrace.h> #include <asm/cacheflush.h> #include <asm/sections.h> +#include <asm/uaccess.h> #include <asm/dis.h> DEFINE_PER_CPU(struct kprobe *, current_kprobe); diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 29376f0e725c..9a32f7419d78 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -98,7 +98,7 @@ EXPORT_SYMBOL_GPL(s390_handle_mcck); * returns 0 if all registers could be validated * returns 1 otherwise */ -static int notrace s390_validate_registers(union mci mci) +static int notrace s390_validate_registers(union mci mci, int umode) { int kill_task; u64 zero; @@ -110,26 +110,41 @@ static int notrace s390_validate_registers(union mci mci) if (!mci.gr) { /* * General purpose registers couldn't be restored and have - * unknown contents. Process needs to be terminated. + * unknown contents. Stop system or terminate process. */ + if (!umode) + s390_handle_damage(); kill_task = 1; } if (!mci.fp) { /* - * Floating point registers can't be restored and - * therefore the process needs to be terminated. + * Floating point registers can't be restored. If the + * kernel currently uses floating point registers the + * system is stopped. If the process has its floating + * pointer registers loaded it is terminated. + * Otherwise just revalidate the registers. */ - kill_task = 1; + if (S390_lowcore.fpu_flags & KERNEL_VXR_V0V7) + s390_handle_damage(); + if (!test_cpu_flag(CIF_FPU)) + kill_task = 1; } fpt_save_area = &S390_lowcore.floating_pt_save_area; fpt_creg_save_area = &S390_lowcore.fpt_creg_save_area; if (!mci.fc) { /* * Floating point control register can't be restored. - * Task will be terminated. + * If the kernel currently uses the floating pointer + * registers and needs the FPC register the system is + * stopped. If the process has its floating pointer + * registers loaded it is terminated. Otherwiese the + * FPC is just revalidated. */ + if (S390_lowcore.fpu_flags & KERNEL_FPC) + s390_handle_damage(); asm volatile("lfpc 0(%0)" : : "a" (&zero), "m" (zero)); - kill_task = 1; + if (!test_cpu_flag(CIF_FPU)) + kill_task = 1; } else asm volatile("lfpc 0(%0)" : : "a" (fpt_creg_save_area)); @@ -159,10 +174,16 @@ static int notrace s390_validate_registers(union mci mci) if (!mci.vr) { /* - * Vector registers can't be restored and therefore - * the process needs to be terminated. + * Vector registers can't be restored. If the kernel + * currently uses vector registers the system is + * stopped. If the process has its vector registers + * loaded it is terminated. Otherwise just revalidate + * the registers. */ - kill_task = 1; + if (S390_lowcore.fpu_flags & KERNEL_VXR) + s390_handle_damage(); + if (!test_cpu_flag(CIF_FPU)) + kill_task = 1; } cr0.val = S390_lowcore.cregs_save_area[0]; cr0.afp = cr0.vx = 1; @@ -250,13 +271,11 @@ void notrace s390_do_machine_check(struct pt_regs *regs) struct mcck_struct *mcck; unsigned long long tmp; union mci mci; - int umode; nmi_enter(); inc_irq_stat(NMI_NMI); mci.val = S390_lowcore.mcck_interruption_code; mcck = this_cpu_ptr(&cpu_mcck); - umode = user_mode(regs); if (mci.sd) { /* System damage -> stopping machine */ @@ -297,22 +316,14 @@ void notrace s390_do_machine_check(struct pt_regs *regs) s390_handle_damage(); } } - if (s390_validate_registers(mci)) { - if (umode) { - /* - * Couldn't restore all register contents while in - * user mode -> mark task for termination. - */ - mcck->kill_task = 1; - mcck->mcck_code = mci.val; - set_cpu_flag(CIF_MCCK_PENDING); - } else { - /* - * Couldn't restore all register contents while in - * kernel mode -> stopping machine. - */ - s390_handle_damage(); - } + if (s390_validate_registers(mci, user_mode(regs))) { + /* + * Couldn't restore all register contents for the + * user space process -> mark task for termination. + */ + mcck->kill_task = 1; + mcck->mcck_code = mci.val; + set_cpu_flag(CIF_MCCK_PENDING); } if (mci.cd) { /* Timing facility damage */ diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index 050b8d067d3b..bfda6aa40280 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -454,7 +454,7 @@ void s390_adjust_jiffies(void) : "Q" (info->capability), "d" (10000000), "d" (0) : "cc" ); - kernel_fpu_end(&fpu); + kernel_fpu_end(&fpu, KERNEL_FPR); } else /* * Really old machine without stsi block for basic diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 4e9949800562..0bfcc492987e 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -50,10 +50,6 @@ #include <asm/cio.h> #include "entry.h" -/* change this if you have some constant time drift */ -#define USECS_PER_JIFFY ((unsigned long) 1000000/HZ) -#define CLK_TICKS_PER_JIFFY ((unsigned long) USECS_PER_JIFFY << 12) - u64 sched_clock_base_cc = -1; /* Force to data section. */ EXPORT_SYMBOL_GPL(sched_clock_base_cc); @@ -282,13 +278,8 @@ extern struct timezone sys_tz; void update_vsyscall_tz(void) { - /* Make userspace gettimeofday spin until we're done. */ - ++vdso_data->tb_update_count; - smp_wmb(); vdso_data->tz_minuteswest = sys_tz.tz_minuteswest; vdso_data->tz_dsttime = sys_tz.tz_dsttime; - smp_wmb(); - ++vdso_data->tb_update_count; } /* @@ -318,51 +309,12 @@ void __init time_init(void) vtime_init(); } -/* - * The time is "clock". old is what we think the time is. - * Adjust the value by a multiple of jiffies and add the delta to ntp. - * "delay" is an approximation how long the synchronization took. If - * the time correction is positive, then "delay" is subtracted from - * the time difference and only the remaining part is passed to ntp. - */ -static unsigned long long adjust_time(unsigned long long old, - unsigned long long clock, - unsigned long long delay) -{ - unsigned long long delta, ticks; - struct timex adjust; - - if (clock > old) { - /* It is later than we thought. */ - delta = ticks = clock - old; - delta = ticks = (delta < delay) ? 0 : delta - delay; - delta -= do_div(ticks, CLK_TICKS_PER_JIFFY); - adjust.offset = ticks * (1000000 / HZ); - } else { - /* It is earlier than we thought. */ - delta = ticks = old - clock; - delta -= do_div(ticks, CLK_TICKS_PER_JIFFY); - delta = -delta; - adjust.offset = -ticks * (1000000 / HZ); - } - sched_clock_base_cc += delta; - if (adjust.offset != 0) { - pr_notice("The ETR interface has adjusted the clock " - "by %li microseconds\n", adjust.offset); - adjust.modes = ADJ_OFFSET_SINGLESHOT; - do_adjtimex(&adjust); - } - return delta; -} - static DEFINE_PER_CPU(atomic_t, clock_sync_word); static DEFINE_MUTEX(clock_sync_mutex); static unsigned long clock_sync_flags; -#define CLOCK_SYNC_HAS_ETR 0 -#define CLOCK_SYNC_HAS_STP 1 -#define CLOCK_SYNC_ETR 2 -#define CLOCK_SYNC_STP 3 +#define CLOCK_SYNC_HAS_STP 0 +#define CLOCK_SYNC_STP 1 /* * The get_clock function for the physical clock. It will get the current @@ -384,34 +336,32 @@ int get_phys_clock(unsigned long long *clock) if (sw0 == sw1 && (sw0 & 0x80000000U)) /* Success: time is in sync. */ return 0; - if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags) && - !test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags)) + if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags)) return -EOPNOTSUPP; - if (!test_bit(CLOCK_SYNC_ETR, &clock_sync_flags) && - !test_bit(CLOCK_SYNC_STP, &clock_sync_flags)) + if (!test_bit(CLOCK_SYNC_STP, &clock_sync_flags)) return -EACCES; return -EAGAIN; } EXPORT_SYMBOL(get_phys_clock); /* - * Make get_sync_clock return -EAGAIN. + * Make get_phys_clock() return -EAGAIN. */ static void disable_sync_clock(void *dummy) { atomic_t *sw_ptr = this_cpu_ptr(&clock_sync_word); /* - * Clear the in-sync bit 2^31. All get_sync_clock calls will + * Clear the in-sync bit 2^31. All get_phys_clock calls will * fail until the sync bit is turned back on. In addition * increase the "sequence" counter to avoid the race of an - * etr event and the complete recovery against get_sync_clock. + * stp event and the complete recovery against get_phys_clock. */ atomic_andnot(0x80000000, sw_ptr); atomic_inc(sw_ptr); } /* - * Make get_sync_clock return 0 again. + * Make get_phys_clock() return 0 again. * Needs to be called from a context disabled for preemption. */ static void enable_sync_clock(void) @@ -434,7 +384,7 @@ static inline int check_sync_clock(void) return rc; } -/* Single threaded workqueue used for etr and stp sync events */ +/* Single threaded workqueue used for stp sync events */ static struct workqueue_struct *time_sync_wq; static void __init time_init_wq(void) @@ -448,20 +398,12 @@ struct clock_sync_data { atomic_t cpus; int in_sync; unsigned long long fixup_cc; - int etr_port; - struct etr_aib *etr_aib; }; static void clock_sync_cpu(struct clock_sync_data *sync) { atomic_dec(&sync->cpus); enable_sync_clock(); - /* - * This looks like a busy wait loop but it isn't. etr_sync_cpus - * is called on all other cpus while the TOD clocks is stopped. - * __udelay will stop the cpu on an enabled wait psw until the - * TOD is running again. - */ while (sync->in_sync == 0) { __udelay(1); /* @@ -582,7 +524,7 @@ void stp_queue_work(void) static int stp_sync_clock(void *data) { static int first; - unsigned long long old_clock, delta, new_clock, clock_delta; + unsigned long long clock_delta; struct clock_sync_data *stp_sync; struct ptff_qto qto; int rc; @@ -605,18 +547,18 @@ static int stp_sync_clock(void *data) if (stp_info.todoff[0] || stp_info.todoff[1] || stp_info.todoff[2] || stp_info.todoff[3] || stp_info.tmd != 2) { - old_clock = get_tod_clock(); rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0, &clock_delta); if (rc == 0) { - new_clock = old_clock + clock_delta; - delta = adjust_time(old_clock, new_clock, 0); + /* fixup the monotonic sched clock */ + sched_clock_base_cc += clock_delta; if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0) /* Update LPAR offset */ lpar_offset = qto.tod_epoch_difference; atomic_notifier_call_chain(&s390_epoch_delta_notifier, 0, &clock_delta); - fixup_clock_comparator(delta); + stp_sync->fixup_cc = clock_delta; + fixup_clock_comparator(clock_delta); rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi)); if (rc == 0 && stp_info.tmd != 2) diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index dd97a3e8a34a..d0539f76fd24 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -14,11 +14,12 @@ */ #include <linux/kprobes.h> #include <linux/kdebug.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/ptrace.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/slab.h> +#include <asm/uaccess.h> #include <asm/fpu/api.h> #include "entry.h" diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index 68145456fee2..6cc947896c77 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -24,8 +24,9 @@ obj-y += vdso32_wrapper.o extra-y += vdso32.lds CPPFLAGS_vdso32.lds += -P -C -U$(ARCH) -# Disable gcov profiling for VDSO code +# Disable gcov profiling and ubsan for VDSO code GCOV_PROFILE := n +UBSAN_SANITIZE := n # Force dependency (incbin is bad) $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index 0b0fd22c869a..2d54c18089eb 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -24,8 +24,9 @@ obj-y += vdso64_wrapper.o extra-y += vdso64.lds CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) -# Disable gcov profiling for VDSO code +# Disable gcov profiling and ubsan for VDSO code GCOV_PROFILE := n +UBSAN_SANITIZE := n # Force dependency (incbin is bad) $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 54200208bf24..4aa8a7e2a1da 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -495,6 +495,18 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code; switch (code) { + case PGM_PROTECTION: + switch (prot) { + case PROT_TYPE_ALC: + tec->b60 = 1; + /* FALL THROUGH */ + case PROT_TYPE_DAT: + tec->b61 = 1; + break; + default: /* LA and KEYC set b61 to 0, other params undefined */ + return code; + } + /* FALL THROUGH */ case PGM_ASCE_TYPE: case PGM_PAGE_TRANSLATION: case PGM_REGION_FIRST_TRANS: @@ -504,8 +516,7 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, /* * op_access_id only applies to MOVE_PAGE -> set bit 61 * exc_access_id has to be set to 0 for some instructions. Both - * cases have to be handled by the caller. We can always store - * exc_access_id, as it is undefined for non-ar cases. + * cases have to be handled by the caller. */ tec->addr = gva >> PAGE_SHIFT; tec->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH; @@ -516,25 +527,13 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, case PGM_ASTE_VALIDITY: case PGM_ASTE_SEQUENCE: case PGM_EXTENDED_AUTHORITY: + /* + * We can always store exc_access_id, as it is + * undefined for non-ar cases. It is undefined for + * most DAT protection exceptions. + */ pgm->exc_access_id = ar; break; - case PGM_PROTECTION: - switch (prot) { - case PROT_TYPE_ALC: - tec->b60 = 1; - /* FALL THROUGH */ - case PROT_TYPE_DAT: - tec->b61 = 1; - tec->addr = gva >> PAGE_SHIFT; - tec->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH; - tec->as = psw_bits(vcpu->arch.sie_block->gpsw).as; - /* exc_access_id is undefined for most cases */ - pgm->exc_access_id = ar; - break; - default: /* LA and KEYC set b61 to 0, other params undefined */ - break; - } - break; } return code; } diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index 31a05330d11c..d7c6a7f53ced 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -206,7 +206,7 @@ static int __import_wp_info(struct kvm_vcpu *vcpu, int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - int ret = 0, nr_wp = 0, nr_bp = 0, i, size; + int ret = 0, nr_wp = 0, nr_bp = 0, i; struct kvm_hw_breakpoint *bp_data = NULL; struct kvm_hw_wp_info_arch *wp_info = NULL; struct kvm_hw_bp_info_arch *bp_info = NULL; @@ -216,17 +216,10 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, else if (dbg->arch.nr_hw_bp > MAX_BP_COUNT) return -EINVAL; - size = dbg->arch.nr_hw_bp * sizeof(struct kvm_hw_breakpoint); - bp_data = kmalloc(size, GFP_KERNEL); - if (!bp_data) { - ret = -ENOMEM; - goto error; - } - - if (copy_from_user(bp_data, dbg->arch.hw_bp, size)) { - ret = -EFAULT; - goto error; - } + bp_data = memdup_user(dbg->arch.hw_bp, + sizeof(*bp_data) * dbg->arch.nr_hw_bp); + if (IS_ERR(bp_data)) + return PTR_ERR(bp_data); for (i = 0; i < dbg->arch.nr_hw_bp; i++) { switch (bp_data[i].type) { @@ -241,17 +234,19 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, } } - size = nr_wp * sizeof(struct kvm_hw_wp_info_arch); - if (size > 0) { - wp_info = kmalloc(size, GFP_KERNEL); + if (nr_wp > 0) { + wp_info = kmalloc_array(nr_wp, + sizeof(*wp_info), + GFP_KERNEL); if (!wp_info) { ret = -ENOMEM; goto error; } } - size = nr_bp * sizeof(struct kvm_hw_bp_info_arch); - if (size > 0) { - bp_info = kmalloc(size, GFP_KERNEL); + if (nr_bp > 0) { + bp_info = kmalloc_array(nr_bp, + sizeof(*bp_info), + GFP_KERNEL); if (!bp_info) { ret = -ENOMEM; goto error; @@ -382,14 +377,20 @@ void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu) vcpu->guest_debug &= ~KVM_GUESTDBG_EXIT_PENDING; } +#define PER_CODE_MASK (PER_EVENT_MASK >> 24) +#define PER_CODE_BRANCH (PER_EVENT_BRANCH >> 24) +#define PER_CODE_IFETCH (PER_EVENT_IFETCH >> 24) +#define PER_CODE_STORE (PER_EVENT_STORE >> 24) +#define PER_CODE_STORE_REAL (PER_EVENT_STORE_REAL >> 24) + #define per_bp_event(code) \ - (code & (PER_EVENT_IFETCH | PER_EVENT_BRANCH)) + (code & (PER_CODE_IFETCH | PER_CODE_BRANCH)) #define per_write_wp_event(code) \ - (code & (PER_EVENT_STORE | PER_EVENT_STORE_REAL)) + (code & (PER_CODE_STORE | PER_CODE_STORE_REAL)) static int debug_exit_required(struct kvm_vcpu *vcpu) { - u32 perc = (vcpu->arch.sie_block->perc << 24); + u8 perc = vcpu->arch.sie_block->perc; struct kvm_debug_exit_arch *debug_exit = &vcpu->run->debug.arch; struct kvm_hw_wp_info_arch *wp_info = NULL; struct kvm_hw_bp_info_arch *bp_info = NULL; @@ -444,7 +445,7 @@ int kvm_s390_handle_per_ifetch_icpt(struct kvm_vcpu *vcpu) const u8 ilen = kvm_s390_get_ilen(vcpu); struct kvm_s390_pgm_info pgm_info = { .code = PGM_PER, - .per_code = PER_EVENT_IFETCH >> 24, + .per_code = PER_CODE_IFETCH, .per_address = __rewind_psw(vcpu->arch.sie_block->gpsw, ilen), }; @@ -458,33 +459,33 @@ int kvm_s390_handle_per_ifetch_icpt(struct kvm_vcpu *vcpu) static void filter_guest_per_event(struct kvm_vcpu *vcpu) { - u32 perc = vcpu->arch.sie_block->perc << 24; + const u8 perc = vcpu->arch.sie_block->perc; u64 peraddr = vcpu->arch.sie_block->peraddr; u64 addr = vcpu->arch.sie_block->gpsw.addr; u64 cr9 = vcpu->arch.sie_block->gcr[9]; u64 cr10 = vcpu->arch.sie_block->gcr[10]; u64 cr11 = vcpu->arch.sie_block->gcr[11]; /* filter all events, demanded by the guest */ - u32 guest_perc = perc & cr9 & PER_EVENT_MASK; + u8 guest_perc = perc & (cr9 >> 24) & PER_CODE_MASK; if (!guest_per_enabled(vcpu)) guest_perc = 0; /* filter "successful-branching" events */ - if (guest_perc & PER_EVENT_BRANCH && + if (guest_perc & PER_CODE_BRANCH && cr9 & PER_CONTROL_BRANCH_ADDRESS && !in_addr_range(addr, cr10, cr11)) - guest_perc &= ~PER_EVENT_BRANCH; + guest_perc &= ~PER_CODE_BRANCH; /* filter "instruction-fetching" events */ - if (guest_perc & PER_EVENT_IFETCH && + if (guest_perc & PER_CODE_IFETCH && !in_addr_range(peraddr, cr10, cr11)) - guest_perc &= ~PER_EVENT_IFETCH; + guest_perc &= ~PER_CODE_IFETCH; /* All other PER events will be given to the guest */ /* TODO: Check altered address/address space */ - vcpu->arch.sie_block->perc = guest_perc >> 24; + vcpu->arch.sie_block->perc = guest_perc; if (!guest_perc) vcpu->arch.sie_block->iprcc &= ~PGM_PER; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index dfd0ca2638fa..1cab8a177d0e 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -29,6 +29,7 @@ static const intercept_handler_t instruction_handlers[256] = { [0x01] = kvm_s390_handle_01, [0x82] = kvm_s390_handle_lpsw, [0x83] = kvm_s390_handle_diag, + [0xaa] = kvm_s390_handle_aa, [0xae] = kvm_s390_handle_sigp, [0xb2] = kvm_s390_handle_b2, [0xb6] = kvm_s390_handle_stctl, diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 24524c0f3ef8..be4db07f70d3 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -24,6 +24,8 @@ #include <asm/sclp.h> #include <asm/isc.h> #include <asm/gmap.h> +#include <asm/switch_to.h> +#include <asm/nmi.h> #include "kvm-s390.h" #include "gaccess.h" #include "trace-s390.h" @@ -40,6 +42,7 @@ static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id) if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND)) return 0; + BUG_ON(!kvm_s390_use_sca_entries()); read_lock(&vcpu->kvm->arch.sca_lock); if (vcpu->kvm->arch.use_esca) { struct esca_block *sca = vcpu->kvm->arch.sca; @@ -68,6 +71,7 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) { int expect, rc; + BUG_ON(!kvm_s390_use_sca_entries()); read_lock(&vcpu->kvm->arch.sca_lock); if (vcpu->kvm->arch.use_esca) { struct esca_block *sca = vcpu->kvm->arch.sca; @@ -109,6 +113,8 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu) struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; int rc, expect; + if (!kvm_s390_use_sca_entries()) + return; atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags); read_lock(&vcpu->kvm->arch.sca_lock); if (vcpu->kvm->arch.use_esca) { @@ -400,12 +406,78 @@ static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu) return rc ? -EFAULT : 0; } +static int __write_machine_check(struct kvm_vcpu *vcpu, + struct kvm_s390_mchk_info *mchk) +{ + unsigned long ext_sa_addr; + freg_t fprs[NUM_FPRS]; + union mci mci; + int rc; + + mci.val = mchk->mcic; + /* take care of lazy register loading via vcpu load/put */ + save_fpu_regs(); + save_access_regs(vcpu->run->s.regs.acrs); + + /* Extended save area */ + rc = read_guest_lc(vcpu, __LC_VX_SAVE_AREA_ADDR, &ext_sa_addr, + sizeof(unsigned long)); + /* Only bits 0-53 are used for address formation */ + ext_sa_addr &= ~0x3ffUL; + if (!rc && mci.vr && ext_sa_addr && test_kvm_facility(vcpu->kvm, 129)) { + if (write_guest_abs(vcpu, ext_sa_addr, vcpu->run->s.regs.vrs, + 512)) + mci.vr = 0; + } else { + mci.vr = 0; + } + + /* General interruption information */ + rc |= put_guest_lc(vcpu, 1, (u8 __user *) __LC_AR_MODE_ID); + rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, mci.val, (u64 __user *) __LC_MCCK_CODE); + + /* Register-save areas */ + if (MACHINE_HAS_VX) { + convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs); + rc |= write_guest_lc(vcpu, __LC_FPREGS_SAVE_AREA, fprs, 128); + } else { + rc |= write_guest_lc(vcpu, __LC_FPREGS_SAVE_AREA, + vcpu->run->s.regs.fprs, 128); + } + rc |= write_guest_lc(vcpu, __LC_GPREGS_SAVE_AREA, + vcpu->run->s.regs.gprs, 128); + rc |= put_guest_lc(vcpu, current->thread.fpu.fpc, + (u32 __user *) __LC_FP_CREG_SAVE_AREA); + rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->todpr, + (u32 __user *) __LC_TOD_PROGREG_SAVE_AREA); + rc |= put_guest_lc(vcpu, kvm_s390_get_cpu_timer(vcpu), + (u64 __user *) __LC_CPU_TIMER_SAVE_AREA); + rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->ckc >> 8, + (u64 __user *) __LC_CLOCK_COMP_SAVE_AREA); + rc |= write_guest_lc(vcpu, __LC_AREGS_SAVE_AREA, + &vcpu->run->s.regs.acrs, 64); + rc |= write_guest_lc(vcpu, __LC_CREGS_SAVE_AREA, + &vcpu->arch.sie_block->gcr, 128); + + /* Extended interruption information */ + rc |= put_guest_lc(vcpu, mchk->ext_damage_code, + (u32 __user *) __LC_EXT_DAMAGE_CODE); + rc |= put_guest_lc(vcpu, mchk->failing_storage_address, + (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); + rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, &mchk->fixed_logout, + sizeof(mchk->fixed_logout)); + return rc ? -EFAULT : 0; +} + static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu) { struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; struct kvm_s390_mchk_info mchk = {}; - unsigned long adtl_status_addr; int deliver = 0; int rc = 0; @@ -446,29 +518,9 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu) trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_MCHK, mchk.cr14, mchk.mcic); - - rc = kvm_s390_vcpu_store_status(vcpu, - KVM_S390_STORE_STATUS_PREFIXED); - rc |= read_guest_lc(vcpu, __LC_VX_SAVE_AREA_ADDR, - &adtl_status_addr, - sizeof(unsigned long)); - rc |= kvm_s390_vcpu_store_adtl_status(vcpu, - adtl_status_addr); - rc |= put_guest_lc(vcpu, mchk.mcic, - (u64 __user *) __LC_MCCK_CODE); - rc |= put_guest_lc(vcpu, mchk.failing_storage_address, - (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); - rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, - &mchk.fixed_logout, - sizeof(mchk.fixed_logout)); - rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); + rc = __write_machine_check(vcpu, &mchk); } - return rc ? -EFAULT : 0; + return rc; } static int __must_check __deliver_restart(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f142215ed30d..9c7a1ecfe6bd 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -132,10 +132,7 @@ module_param(nested, int, S_IRUGO); MODULE_PARM_DESC(nested, "Nested virtualization support"); /* upper facilities limit for kvm */ -unsigned long kvm_s390_fac_list_mask[16] = { - 0xffe6000000000000UL, - 0x005e000000000000UL, -}; +unsigned long kvm_s390_fac_list_mask[16] = { FACILITIES_KVM }; unsigned long kvm_s390_fac_list_mask_size(void) { @@ -248,22 +245,33 @@ static void kvm_s390_cpu_feat_init(void) PTFF_QAF); if (test_facility(17)) { /* MSA */ - __cpacf_query(CPACF_KMAC, kvm_s390_available_subfunc.kmac); - __cpacf_query(CPACF_KMC, kvm_s390_available_subfunc.kmc); - __cpacf_query(CPACF_KM, kvm_s390_available_subfunc.km); - __cpacf_query(CPACF_KIMD, kvm_s390_available_subfunc.kimd); - __cpacf_query(CPACF_KLMD, kvm_s390_available_subfunc.klmd); + __cpacf_query(CPACF_KMAC, (cpacf_mask_t *) + kvm_s390_available_subfunc.kmac); + __cpacf_query(CPACF_KMC, (cpacf_mask_t *) + kvm_s390_available_subfunc.kmc); + __cpacf_query(CPACF_KM, (cpacf_mask_t *) + kvm_s390_available_subfunc.km); + __cpacf_query(CPACF_KIMD, (cpacf_mask_t *) + kvm_s390_available_subfunc.kimd); + __cpacf_query(CPACF_KLMD, (cpacf_mask_t *) + kvm_s390_available_subfunc.klmd); } if (test_facility(76)) /* MSA3 */ - __cpacf_query(CPACF_PCKMO, kvm_s390_available_subfunc.pckmo); + __cpacf_query(CPACF_PCKMO, (cpacf_mask_t *) + kvm_s390_available_subfunc.pckmo); if (test_facility(77)) { /* MSA4 */ - __cpacf_query(CPACF_KMCTR, kvm_s390_available_subfunc.kmctr); - __cpacf_query(CPACF_KMF, kvm_s390_available_subfunc.kmf); - __cpacf_query(CPACF_KMO, kvm_s390_available_subfunc.kmo); - __cpacf_query(CPACF_PCC, kvm_s390_available_subfunc.pcc); + __cpacf_query(CPACF_KMCTR, (cpacf_mask_t *) + kvm_s390_available_subfunc.kmctr); + __cpacf_query(CPACF_KMF, (cpacf_mask_t *) + kvm_s390_available_subfunc.kmf); + __cpacf_query(CPACF_KMO, (cpacf_mask_t *) + kvm_s390_available_subfunc.kmo); + __cpacf_query(CPACF_PCC, (cpacf_mask_t *) + kvm_s390_available_subfunc.pcc); } if (test_facility(57)) /* MSA5 */ - __cpacf_query(CPACF_PPNO, kvm_s390_available_subfunc.ppno); + __cpacf_query(CPACF_PPNO, (cpacf_mask_t *) + kvm_s390_available_subfunc.ppno); if (MACHINE_HAS_ESOP) allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP); @@ -376,7 +384,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_NR_VCPUS: case KVM_CAP_MAX_VCPUS: r = KVM_S390_BSCA_CPU_SLOTS; - if (sclp.has_esca && sclp.has_64bscao) + if (!kvm_s390_use_sca_entries()) + r = KVM_MAX_VCPUS; + else if (sclp.has_esca && sclp.has_64bscao) r = KVM_S390_ESCA_CPU_SLOTS; break; case KVM_CAP_NR_MEMSLOTS: @@ -1490,6 +1500,16 @@ out_err: return rc; } +bool kvm_arch_has_vcpu_debugfs(void) +{ + return false; +} + +int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +{ + return 0; +} + void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { VCPU_EVENT(vcpu, 3, "%s", "free cpu"); @@ -1553,6 +1573,8 @@ static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu) static void sca_del_vcpu(struct kvm_vcpu *vcpu) { + if (!kvm_s390_use_sca_entries()) + return; read_lock(&vcpu->kvm->arch.sca_lock); if (vcpu->kvm->arch.use_esca) { struct esca_block *sca = vcpu->kvm->arch.sca; @@ -1570,6 +1592,13 @@ static void sca_del_vcpu(struct kvm_vcpu *vcpu) static void sca_add_vcpu(struct kvm_vcpu *vcpu) { + if (!kvm_s390_use_sca_entries()) { + struct bsca_block *sca = vcpu->kvm->arch.sca; + + /* we still need the basic sca for the ipte control */ + vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32); + vcpu->arch.sie_block->scaol = (__u32)(__u64)sca; + } read_lock(&vcpu->kvm->arch.sca_lock); if (vcpu->kvm->arch.use_esca) { struct esca_block *sca = vcpu->kvm->arch.sca; @@ -1650,6 +1679,11 @@ static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id) { int rc; + if (!kvm_s390_use_sca_entries()) { + if (id < KVM_MAX_VCPUS) + return true; + return false; + } if (id < KVM_S390_BSCA_CPU_SLOTS) return true; if (!sclp.has_esca || !sclp.has_64bscao) @@ -1938,8 +1972,6 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->eca |= 1; if (sclp.has_sigpif) vcpu->arch.sie_block->eca |= 0x10000000U; - if (test_kvm_facility(vcpu->kvm, 64)) - vcpu->arch.sie_block->ecb3 |= 0x01; if (test_kvm_facility(vcpu->kvm, 129)) { vcpu->arch.sie_block->eca |= 0x00020000; vcpu->arch.sie_block->ecd |= 0x20000000; @@ -2231,9 +2263,10 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) return -EINVAL; current->thread.fpu.fpc = fpu->fpc; if (MACHINE_HAS_VX) - convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs); + convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs, + (freg_t *) fpu->fprs); else - memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs)); + memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs)); return 0; } @@ -2242,9 +2275,10 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) /* make sure we have the latest values */ save_fpu_regs(); if (MACHINE_HAS_VX) - convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs); + convert_vx_to_fp((freg_t *) fpu->fprs, + (__vector128 *) vcpu->run->s.regs.vrs); else - memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs)); + memcpy(fpu->fprs, vcpu->run->s.regs.fprs, sizeof(fpu->fprs)); fpu->fpc = current->thread.fpu.fpc; return 0; } @@ -2694,6 +2728,19 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID) kvm_clear_async_pf_completion_queue(vcpu); } + /* + * If userspace sets the riccb (e.g. after migration) to a valid state, + * we should enable RI here instead of doing the lazy enablement. + */ + if ((kvm_run->kvm_dirty_regs & KVM_SYNC_RICCB) && + test_kvm_facility(vcpu->kvm, 64)) { + struct runtime_instr_cb *riccb = + (struct runtime_instr_cb *) &kvm_run->s.regs.riccb; + + if (riccb->valid) + vcpu->arch.sie_block->ecb3 |= 0x01; + } + kvm_run->kvm_dirty_regs = 0; } @@ -2837,38 +2884,6 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) return kvm_s390_store_status_unloaded(vcpu, addr); } -/* - * store additional status at address - */ -int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu, - unsigned long gpa) -{ - /* Only bits 0-53 are used for address formation */ - if (!(gpa & ~0x3ff)) - return 0; - - return write_guest_abs(vcpu, gpa & ~0x3ff, - (void *)&vcpu->run->s.regs.vrs, 512); -} - -int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr) -{ - if (!test_kvm_facility(vcpu->kvm, 129)) - return 0; - - /* - * The guest VXRS are in the host VXRs due to the lazy - * copying in vcpu load/put. We can simply call save_fpu_regs() - * to save the current register state because we are in the - * middle of a load/put cycle. - * - * Let's update our copies before we save it into the save area. - */ - save_fpu_regs(); - - return kvm_s390_store_adtl_status_unloaded(vcpu, addr); -} - static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu) { kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index b8432862a817..3a4e97f1a9e6 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -20,6 +20,7 @@ #include <linux/kvm_host.h> #include <asm/facility.h> #include <asm/processor.h> +#include <asm/sclp.h> typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); @@ -245,6 +246,7 @@ static inline void kvm_s390_retry_instr(struct kvm_vcpu *vcpu) /* implemented in priv.c */ int is_valid_psw(psw_t *psw); +int kvm_s390_handle_aa(struct kvm_vcpu *vcpu); int kvm_s390_handle_b2(struct kvm_vcpu *vcpu); int kvm_s390_handle_e5(struct kvm_vcpu *vcpu); int kvm_s390_handle_01(struct kvm_vcpu *vcpu); @@ -273,10 +275,7 @@ int handle_sthyi(struct kvm_vcpu *vcpu); void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod); long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr); -int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu, - unsigned long addr); int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); -int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu); @@ -389,4 +388,13 @@ static inline union ipte_control *kvm_s390_get_ipte_control(struct kvm *kvm) return &sca->ipte_control; } +static inline int kvm_s390_use_sca_entries(void) +{ + /* + * Without SIGP interpretation, only SRS interpretation (if available) + * might use the entries. By not setting the entries and keeping them + * invalid, hardware will not access them but intercept. + */ + return sclp.has_sigpif; +} #endif diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 46160388e996..e18435355c16 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -32,6 +32,24 @@ #include "kvm-s390.h" #include "trace.h" +static int handle_ri(struct kvm_vcpu *vcpu) +{ + if (test_kvm_facility(vcpu->kvm, 64)) { + vcpu->arch.sie_block->ecb3 |= 0x01; + kvm_s390_retry_instr(vcpu); + return 0; + } else + return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); +} + +int kvm_s390_handle_aa(struct kvm_vcpu *vcpu) +{ + if ((vcpu->arch.sie_block->ipa & 0xf) <= 4) + return handle_ri(vcpu); + else + return -EOPNOTSUPP; +} + /* Handle SCK (SET CLOCK) interception */ static int handle_set_clock(struct kvm_vcpu *vcpu) { @@ -1093,6 +1111,9 @@ static int handle_stctg(struct kvm_vcpu *vcpu) static const intercept_handler_t eb_handlers[256] = { [0x2f] = handle_lctlg, [0x25] = handle_stctg, + [0x60] = handle_ri, + [0x61] = handle_ri, + [0x62] = handle_ri, }; int kvm_s390_handle_eb(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index c106488b4137..d8673e243f13 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -584,7 +584,7 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) /* Validity 0x0044 will be checked by SIE */ if (rc) goto unpin; - scb_s->gvrd = hpa; + scb_s->riccbd = hpa; } return 0; unpin: diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index a58bca62a93b..661d9fe63c43 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -24,7 +24,7 @@ #include <linux/kdebug.h> #include <linux/init.h> #include <linux/console.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/hardirq.h> #include <linux/kprobes.h> #include <linux/uaccess.h> @@ -740,28 +740,21 @@ out: put_task_struct(tsk); } -static int pfault_cpu_notify(struct notifier_block *self, unsigned long action, - void *hcpu) +static int pfault_cpu_dead(unsigned int cpu) { struct thread_struct *thread, *next; struct task_struct *tsk; - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DEAD: - spin_lock_irq(&pfault_lock); - list_for_each_entry_safe(thread, next, &pfault_list, list) { - thread->pfault_wait = 0; - list_del(&thread->list); - tsk = container_of(thread, struct task_struct, thread); - wake_up_process(tsk); - put_task_struct(tsk); - } - spin_unlock_irq(&pfault_lock); - break; - default: - break; + spin_lock_irq(&pfault_lock); + list_for_each_entry_safe(thread, next, &pfault_list, list) { + thread->pfault_wait = 0; + list_del(&thread->list); + tsk = container_of(thread, struct task_struct, thread); + wake_up_process(tsk); + put_task_struct(tsk); } - return NOTIFY_OK; + spin_unlock_irq(&pfault_lock); + return 0; } static int __init pfault_irq_init(void) @@ -775,7 +768,8 @@ static int __init pfault_irq_init(void) if (rc) goto out_pfault; irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL); - hotcpu_notifier(pfault_cpu_notify, 0); + cpuhp_setup_state_nocalls(CPUHP_S390_PFAULT_DEAD, "s390/pfault:dead", + NULL, pfault_cpu_dead); return 0; out_pfault: diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 2ce6bb3bab32..3ba622702ce4 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -94,6 +94,7 @@ out: struct gmap *gmap_create(struct mm_struct *mm, unsigned long limit) { struct gmap *gmap; + unsigned long gmap_asce; gmap = gmap_alloc(limit); if (!gmap) @@ -101,6 +102,11 @@ struct gmap *gmap_create(struct mm_struct *mm, unsigned long limit) gmap->mm = mm; spin_lock(&mm->context.gmap_lock); list_add_rcu(&gmap->list, &mm->context.gmap_list); + if (list_is_singular(&mm->context.gmap_list)) + gmap_asce = gmap->asce; + else + gmap_asce = -1UL; + WRITE_ONCE(mm->context.gmap_asce, gmap_asce); spin_unlock(&mm->context.gmap_lock); return gmap; } @@ -230,6 +236,7 @@ EXPORT_SYMBOL_GPL(gmap_put); void gmap_remove(struct gmap *gmap) { struct gmap *sg, *next; + unsigned long gmap_asce; /* Remove all shadow gmaps linked to this gmap */ if (!list_empty(&gmap->children)) { @@ -243,6 +250,14 @@ void gmap_remove(struct gmap *gmap) /* Remove gmap from the pre-mm list */ spin_lock(&gmap->mm->context.gmap_lock); list_del_rcu(&gmap->list); + if (list_empty(&gmap->mm->context.gmap_list)) + gmap_asce = 0; + else if (list_is_singular(&gmap->mm->context.gmap_list)) + gmap_asce = list_first_entry(&gmap->mm->context.gmap_list, + struct gmap, list)->asce; + else + gmap_asce = -1UL; + WRITE_ONCE(gmap->mm->context.gmap_asce, gmap_asce); spin_unlock(&gmap->mm->context.gmap_lock); synchronize_rcu(); /* Put reference */ diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index af7cf28cf97e..44f150312a16 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -309,11 +309,11 @@ static void ipte_range(pte_t *pte, unsigned long address, int nr) int i; if (test_facility(13)) { - __ptep_ipte_range(address, nr - 1, pte); + __ptep_ipte_range(address, nr - 1, pte, IPTE_GLOBAL); return; } for (i = 0; i < nr; i++) { - __ptep_ipte(address, pte); + __ptep_ipte(address, pte, IPTE_GLOBAL); address += PAGE_SIZE; pte++; } diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 5f092015aaa7..7a1897c51c54 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -35,9 +35,9 @@ static inline pte_t ptep_flush_direct(struct mm_struct *mm, atomic_inc(&mm->context.flush_count); if (MACHINE_HAS_TLB_LC && cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) - __ptep_ipte_local(addr, ptep); + __ptep_ipte(addr, ptep, IPTE_LOCAL); else - __ptep_ipte(addr, ptep); + __ptep_ipte(addr, ptep, IPTE_GLOBAL); atomic_dec(&mm->context.flush_count); return old; } @@ -56,7 +56,7 @@ static inline pte_t ptep_flush_lazy(struct mm_struct *mm, pte_val(*ptep) |= _PAGE_INVALID; mm->context.flush_mm = 1; } else - __ptep_ipte(addr, ptep); + __ptep_ipte(addr, ptep, IPTE_GLOBAL); atomic_dec(&mm->context.flush_count); return old; } @@ -301,9 +301,9 @@ static inline pmd_t pmdp_flush_direct(struct mm_struct *mm, atomic_inc(&mm->context.flush_count); if (MACHINE_HAS_TLB_LC && cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) - __pmdp_idte_local(addr, pmdp); + __pmdp_idte(addr, pmdp, IDTE_LOCAL); else - __pmdp_idte(addr, pmdp); + __pmdp_idte(addr, pmdp, IDTE_GLOBAL); atomic_dec(&mm->context.flush_count); return old; } @@ -322,7 +322,7 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm, pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID; mm->context.flush_mm = 1; } else if (MACHINE_HAS_IDTE) - __pmdp_idte(addr, pmdp); + __pmdp_idte(addr, pmdp, IDTE_GLOBAL); else __pmdp_csp(pmdp); atomic_dec(&mm->context.flush_count); @@ -374,9 +374,9 @@ static inline pud_t pudp_flush_direct(struct mm_struct *mm, atomic_inc(&mm->context.flush_count); if (MACHINE_HAS_TLB_LC && cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) - __pudp_idte_local(addr, pudp); + __pudp_idte(addr, pudp, IDTE_LOCAL); else - __pudp_idte(addr, pudp); + __pudp_idte(addr, pudp, IDTE_GLOBAL); atomic_dec(&mm->context.flush_count); return old; } @@ -620,7 +620,7 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr) pte = *ptep; if (dirty && (pte_val(pte) & _PAGE_PRESENT)) { pgste = pgste_pte_notify(mm, addr, ptep, pgste); - __ptep_ipte(addr, ptep); + __ptep_ipte(addr, ptep, IPTE_GLOBAL); if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE)) pte_val(pte) |= _PAGE_PROTECT; else diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 871af75c69c2..15ffc19c8c0c 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -854,6 +854,15 @@ void zpci_stop_device(struct zpci_dev *zdev) } EXPORT_SYMBOL_GPL(zpci_stop_device); +int zpci_report_error(struct pci_dev *pdev, + struct zpci_report_error_header *report) +{ + struct zpci_dev *zdev = to_zpci(pdev); + + return sclp_pci_report(report, zdev->fh, zdev->fid); +} +EXPORT_SYMBOL(zpci_report_error); + static inline int barsize(u8 size) { return (size) ? (1 << size) >> 10 : 0; diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 7297fce9bf80..7350c8bc13a2 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -129,12 +129,11 @@ void dma_update_cpu_trans(unsigned long *entry, void *page_addr, int flags) entry_clr_protected(entry); } -static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa, - dma_addr_t dma_addr, size_t size, int flags) +static int __dma_update_trans(struct zpci_dev *zdev, unsigned long pa, + dma_addr_t dma_addr, size_t size, int flags) { unsigned int nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; u8 *page_addr = (u8 *) (pa & PAGE_MASK); - dma_addr_t start_dma_addr = dma_addr; unsigned long irq_flags; unsigned long *entry; int i, rc = 0; @@ -145,7 +144,7 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa, spin_lock_irqsave(&zdev->dma_table_lock, irq_flags); if (!zdev->dma_table) { rc = -EINVAL; - goto no_refresh; + goto out_unlock; } for (i = 0; i < nr_pages; i++) { @@ -159,20 +158,6 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa, dma_addr += PAGE_SIZE; } - /* - * With zdev->tlb_refresh == 0, rpcit is not required to establish new - * translations when previously invalid translation-table entries are - * validated. With lazy unmap, it also is skipped for previously valid - * entries, but a global rpcit is then required before any address can - * be re-used, i.e. after each iommu bitmap wrap-around. - */ - if (!zdev->tlb_refresh && - (!s390_iommu_strict || - ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID))) - goto no_refresh; - - rc = zpci_refresh_trans((u64) zdev->fh << 32, start_dma_addr, - nr_pages * PAGE_SIZE); undo_cpu_trans: if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) { flags = ZPCI_PTE_INVALID; @@ -185,12 +170,46 @@ undo_cpu_trans: dma_update_cpu_trans(entry, page_addr, flags); } } - -no_refresh: +out_unlock: spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags); return rc; } +static int __dma_purge_tlb(struct zpci_dev *zdev, dma_addr_t dma_addr, + size_t size, int flags) +{ + /* + * With zdev->tlb_refresh == 0, rpcit is not required to establish new + * translations when previously invalid translation-table entries are + * validated. With lazy unmap, it also is skipped for previously valid + * entries, but a global rpcit is then required before any address can + * be re-used, i.e. after each iommu bitmap wrap-around. + */ + if (!zdev->tlb_refresh && + (!s390_iommu_strict || + ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID))) + return 0; + + return zpci_refresh_trans((u64) zdev->fh << 32, dma_addr, + PAGE_ALIGN(size)); +} + +static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa, + dma_addr_t dma_addr, size_t size, int flags) +{ + int rc; + + rc = __dma_update_trans(zdev, pa, dma_addr, size, flags); + if (rc) + return rc; + + rc = __dma_purge_tlb(zdev, dma_addr, size, flags); + if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) + __dma_update_trans(zdev, pa, dma_addr, size, ZPCI_PTE_INVALID); + + return rc; +} + void dma_free_seg_table(unsigned long entry) { unsigned long *sto = get_rt_sto(entry); @@ -230,45 +249,54 @@ static unsigned long __dma_alloc_iommu(struct device *dev, boundary_size, 0); } -static unsigned long dma_alloc_iommu(struct device *dev, int size) +static dma_addr_t dma_alloc_address(struct device *dev, int size) { struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); unsigned long offset, flags; - int wrap = 0; spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags); offset = __dma_alloc_iommu(dev, zdev->next_bit, size); if (offset == -1) { + if (!zdev->tlb_refresh && !s390_iommu_strict) { + /* global flush before DMA addresses are reused */ + if (zpci_refresh_global(zdev)) + goto out_error; + + bitmap_andnot(zdev->iommu_bitmap, zdev->iommu_bitmap, + zdev->lazy_bitmap, zdev->iommu_pages); + bitmap_zero(zdev->lazy_bitmap, zdev->iommu_pages); + } /* wrap-around */ offset = __dma_alloc_iommu(dev, 0, size); - wrap = 1; + if (offset == -1) + goto out_error; } + zdev->next_bit = offset + size; + spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags); - if (offset != -1) { - zdev->next_bit = offset + size; - if (!zdev->tlb_refresh && !s390_iommu_strict && wrap) - /* global flush after wrap-around with lazy unmap */ - zpci_refresh_global(zdev); - } + return zdev->start_dma + offset * PAGE_SIZE; + +out_error: spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags); - return offset; + return DMA_ERROR_CODE; } -static void dma_free_iommu(struct device *dev, unsigned long offset, int size) +static void dma_free_address(struct device *dev, dma_addr_t dma_addr, int size) { struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - unsigned long flags; + unsigned long flags, offset; + + offset = (dma_addr - zdev->start_dma) >> PAGE_SHIFT; spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags); if (!zdev->iommu_bitmap) goto out; - bitmap_clear(zdev->iommu_bitmap, offset, size); - /* - * Lazy flush for unmap: need to move next_bit to avoid address re-use - * until wrap-around. - */ - if (!s390_iommu_strict && offset >= zdev->next_bit) - zdev->next_bit = offset + size; + + if (zdev->tlb_refresh || s390_iommu_strict) + bitmap_clear(zdev->iommu_bitmap, offset, size); + else + bitmap_set(zdev->lazy_bitmap, offset, size); + out: spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags); } @@ -289,16 +317,16 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, unsigned long attrs) { struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - unsigned long nr_pages, iommu_page_index; unsigned long pa = page_to_phys(page) + offset; int flags = ZPCI_PTE_VALID; + unsigned long nr_pages; dma_addr_t dma_addr; int ret; /* This rounds up number of pages based on size and offset */ nr_pages = iommu_num_pages(pa, size, PAGE_SIZE); - iommu_page_index = dma_alloc_iommu(dev, nr_pages); - if (iommu_page_index == -1) { + dma_addr = dma_alloc_address(dev, nr_pages); + if (dma_addr == DMA_ERROR_CODE) { ret = -ENOSPC; goto out_err; } @@ -306,12 +334,6 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, /* Use rounded up size */ size = nr_pages * PAGE_SIZE; - dma_addr = zdev->start_dma + iommu_page_index * PAGE_SIZE; - if (dma_addr + size > zdev->end_dma) { - ret = -ERANGE; - goto out_free; - } - if (direction == DMA_NONE || direction == DMA_TO_DEVICE) flags |= ZPCI_TABLE_PROTECTED; @@ -323,7 +345,7 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, return dma_addr + (offset & ~PAGE_MASK); out_free: - dma_free_iommu(dev, iommu_page_index, nr_pages); + dma_free_address(dev, dma_addr, nr_pages); out_err: zpci_err("map error:\n"); zpci_err_dma(ret, pa); @@ -335,7 +357,6 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr, unsigned long attrs) { struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - unsigned long iommu_page_index; int npages, ret; npages = iommu_num_pages(dma_addr, size, PAGE_SIZE); @@ -349,8 +370,7 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr, } atomic64_add(npages, &zdev->unmapped_pages); - iommu_page_index = (dma_addr - zdev->start_dma) >> PAGE_SHIFT; - dma_free_iommu(dev, iommu_page_index, npages); + dma_free_address(dev, dma_addr, npages); } static void *s390_dma_alloc(struct device *dev, size_t size, @@ -394,37 +414,98 @@ static void s390_dma_free(struct device *dev, size_t size, free_pages((unsigned long) pa, get_order(size)); } -static int s390_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nr_elements, enum dma_data_direction dir, - unsigned long attrs) +/* Map a segment into a contiguous dma address area */ +static int __s390_dma_map_sg(struct device *dev, struct scatterlist *sg, + size_t size, dma_addr_t *handle, + enum dma_data_direction dir) { - int mapped_elements = 0; + struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); + dma_addr_t dma_addr_base, dma_addr; + int flags = ZPCI_PTE_VALID; struct scatterlist *s; - int i; + unsigned long pa; + int ret; - for_each_sg(sg, s, nr_elements, i) { - struct page *page = sg_page(s); - s->dma_address = s390_dma_map_pages(dev, page, s->offset, - s->length, dir, 0); - if (!dma_mapping_error(dev, s->dma_address)) { - s->dma_length = s->length; - mapped_elements++; - } else + size = PAGE_ALIGN(size); + dma_addr_base = dma_alloc_address(dev, size >> PAGE_SHIFT); + if (dma_addr_base == DMA_ERROR_CODE) + return -ENOMEM; + + dma_addr = dma_addr_base; + if (dir == DMA_NONE || dir == DMA_TO_DEVICE) + flags |= ZPCI_TABLE_PROTECTED; + + for (s = sg; dma_addr < dma_addr_base + size; s = sg_next(s)) { + pa = page_to_phys(sg_page(s)) + s->offset; + ret = __dma_update_trans(zdev, pa, dma_addr, s->length, flags); + if (ret) goto unmap; + + dma_addr += s->length; } -out: - return mapped_elements; + ret = __dma_purge_tlb(zdev, dma_addr_base, size, flags); + if (ret) + goto unmap; + + *handle = dma_addr_base; + atomic64_add(size >> PAGE_SHIFT, &zdev->mapped_pages); + + return ret; unmap: - for_each_sg(sg, s, mapped_elements, i) { - if (s->dma_address) - s390_dma_unmap_pages(dev, s->dma_address, s->dma_length, - dir, 0); - s->dma_address = 0; + dma_update_trans(zdev, 0, dma_addr_base, dma_addr - dma_addr_base, + ZPCI_PTE_INVALID); + dma_free_address(dev, dma_addr_base, size >> PAGE_SHIFT); + zpci_err("map error:\n"); + zpci_err_dma(ret, pa); + return ret; +} + +static int s390_dma_map_sg(struct device *dev, struct scatterlist *sg, + int nr_elements, enum dma_data_direction dir, + unsigned long attrs) +{ + struct scatterlist *s = sg, *start = sg, *dma = sg; + unsigned int max = dma_get_max_seg_size(dev); + unsigned int size = s->offset + s->length; + unsigned int offset = s->offset; + int count = 0, i; + + for (i = 1; i < nr_elements; i++) { + s = sg_next(s); + + s->dma_address = DMA_ERROR_CODE; s->dma_length = 0; + + if (s->offset || (size & ~PAGE_MASK) || + size + s->length > max) { + if (__s390_dma_map_sg(dev, start, size, + &dma->dma_address, dir)) + goto unmap; + + dma->dma_address += offset; + dma->dma_length = size - offset; + + size = offset = s->offset; + start = s; + dma = sg_next(dma); + count++; + } + size += s->length; } - mapped_elements = 0; - goto out; + if (__s390_dma_map_sg(dev, start, size, &dma->dma_address, dir)) + goto unmap; + + dma->dma_address += offset; + dma->dma_length = size - offset; + + return count + 1; +unmap: + for_each_sg(sg, s, count, i) + s390_dma_unmap_pages(dev, sg_dma_address(s), sg_dma_len(s), + dir, attrs); + + return 0; } static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg, @@ -435,8 +516,9 @@ static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int i; for_each_sg(sg, s, nr_elements, i) { - s390_dma_unmap_pages(dev, s->dma_address, s->dma_length, dir, - 0); + if (s->dma_length) + s390_dma_unmap_pages(dev, s->dma_address, s->dma_length, + dir, attrs); s->dma_address = 0; s->dma_length = 0; } @@ -482,7 +564,14 @@ int zpci_dma_init_device(struct zpci_dev *zdev) rc = -ENOMEM; goto free_dma_table; } + if (!zdev->tlb_refresh && !s390_iommu_strict) { + zdev->lazy_bitmap = vzalloc(zdev->iommu_pages / 8); + if (!zdev->lazy_bitmap) { + rc = -ENOMEM; + goto free_bitmap; + } + } rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, (u64) zdev->dma_table); if (rc) @@ -492,6 +581,8 @@ int zpci_dma_init_device(struct zpci_dev *zdev) free_bitmap: vfree(zdev->iommu_bitmap); zdev->iommu_bitmap = NULL; + vfree(zdev->lazy_bitmap); + zdev->lazy_bitmap = NULL; free_dma_table: dma_free_cpu_table(zdev->dma_table); zdev->dma_table = NULL; @@ -513,6 +604,9 @@ void zpci_dma_exit_device(struct zpci_dev *zdev) zdev->dma_table = NULL; vfree(zdev->iommu_bitmap); zdev->iommu_bitmap = NULL; + vfree(zdev->lazy_bitmap); + zdev->lazy_bitmap = NULL; + zdev->next_bit = 0; } diff --git a/arch/score/include/asm/uaccess.h b/arch/score/include/asm/uaccess.h index 20a3591225cc..01aec8ccde83 100644 --- a/arch/score/include/asm/uaccess.h +++ b/arch/score/include/asm/uaccess.h @@ -163,7 +163,7 @@ do { \ __get_user_asm(val, "lw", ptr); \ break; \ case 8: \ - if ((copy_from_user((void *)&val, ptr, 8)) == 0) \ + if (__copy_from_user((void *)&val, ptr, 8) == 0) \ __gu_err = 0; \ else \ __gu_err = -EFAULT; \ @@ -188,6 +188,8 @@ do { \ \ if (likely(access_ok(VERIFY_READ, __gu_ptr, size))) \ __get_user_common((x), size, __gu_ptr); \ + else \ + (x) = 0; \ \ __gu_err; \ }) @@ -201,6 +203,7 @@ do { \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3:li %0, %4\n" \ + "li %1, 0\n" \ "j 2b\n" \ ".previous\n" \ ".section __ex_table,\"a\"\n" \ @@ -298,35 +301,34 @@ extern int __copy_tofrom_user(void *to, const void *from, unsigned long len); static inline unsigned long copy_from_user(void *to, const void *from, unsigned long len) { - unsigned long over; + unsigned long res = len; - if (access_ok(VERIFY_READ, from, len)) - return __copy_tofrom_user(to, from, len); + if (likely(access_ok(VERIFY_READ, from, len))) + res = __copy_tofrom_user(to, from, len); - if ((unsigned long)from < TASK_SIZE) { - over = (unsigned long)from + len - TASK_SIZE; - return __copy_tofrom_user(to, from, len - over) + over; - } - return len; + if (unlikely(res)) + memset(to + (len - res), 0, res); + + return res; } static inline unsigned long copy_to_user(void *to, const void *from, unsigned long len) { - unsigned long over; - - if (access_ok(VERIFY_WRITE, to, len)) - return __copy_tofrom_user(to, from, len); + if (likely(access_ok(VERIFY_WRITE, to, len))) + len = __copy_tofrom_user(to, from, len); - if ((unsigned long)to < TASK_SIZE) { - over = (unsigned long)to + len - TASK_SIZE; - return __copy_tofrom_user(to, from, len - over) + over; - } return len; } -#define __copy_from_user(to, from, len) \ - __copy_tofrom_user((to), (from), (len)) +static inline unsigned long +__copy_from_user(void *to, const void *from, unsigned long len) +{ + unsigned long left = __copy_tofrom_user(to, from, len); + if (unlikely(left)) + memset(to + (len - left), 0, left); + return left; +} #define __copy_to_user(to, from, len) \ __copy_tofrom_user((to), (from), (len)) @@ -340,17 +342,17 @@ __copy_to_user_inatomic(void *to, const void *from, unsigned long len) static inline unsigned long __copy_from_user_inatomic(void *to, const void *from, unsigned long len) { - return __copy_from_user(to, from, len); + return __copy_tofrom_user(to, from, len); } -#define __copy_in_user(to, from, len) __copy_from_user(to, from, len) +#define __copy_in_user(to, from, len) __copy_tofrom_user(to, from, len) static inline unsigned long copy_in_user(void *to, const void *from, unsigned long len) { if (access_ok(VERIFY_READ, from, len) && access_ok(VERFITY_WRITE, to, len)) - return copy_from_user(to, from, len); + return __copy_tofrom_user(to, from, len); } /* diff --git a/arch/sh/include/asm/atomic-llsc.h b/arch/sh/include/asm/atomic-llsc.h index caea2c45f6c2..1d159ce50f5a 100644 --- a/arch/sh/include/asm/atomic-llsc.h +++ b/arch/sh/include/asm/atomic-llsc.h @@ -60,7 +60,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ " movco.l %0, @%3 \n" \ " bf 1b \n" \ " synco \n" \ - : "=&z" (temp), "=&z" (res) \ + : "=&z" (temp), "=&r" (res) \ : "r" (i), "r" (&v->counter) \ : "t"); \ \ diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h index a49635c51266..92ade79ac427 100644 --- a/arch/sh/include/asm/uaccess.h +++ b/arch/sh/include/asm/uaccess.h @@ -151,7 +151,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n) __kernel_size_t __copy_size = (__kernel_size_t) n; if (__copy_size && __access_ok(__copy_from, __copy_size)) - return __copy_user(to, from, __copy_size); + __copy_size = __copy_user(to, from, __copy_size); + + if (unlikely(__copy_size)) + memset(to + (n - __copy_size), 0, __copy_size); return __copy_size; } diff --git a/arch/sh/include/asm/uaccess_64.h b/arch/sh/include/asm/uaccess_64.h index c01376c76b86..ca5073dd4596 100644 --- a/arch/sh/include/asm/uaccess_64.h +++ b/arch/sh/include/asm/uaccess_64.h @@ -24,6 +24,7 @@ #define __get_user_size(x,ptr,size,retval) \ do { \ retval = 0; \ + x = 0; \ switch (size) { \ case 1: \ retval = __get_user_asm_b((void *)&x, \ diff --git a/arch/sh/kernel/cpu/sh4a/smp-shx3.c b/arch/sh/kernel/cpu/sh4a/smp-shx3.c index 839612c8a0a0..0d3637c494bf 100644 --- a/arch/sh/kernel/cpu/sh4a/smp-shx3.c +++ b/arch/sh/kernel/cpu/sh4a/smp-shx3.c @@ -122,32 +122,16 @@ static void shx3_update_boot_vector(unsigned int cpu) __raw_writel(STBCR_RESET, STBCR_REG(cpu)); } -static int -shx3_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) +static int shx3_cpu_prepare(unsigned int cpu) { - unsigned int cpu = (unsigned int)hcpu; - - switch (action) { - case CPU_UP_PREPARE: - shx3_update_boot_vector(cpu); - break; - case CPU_ONLINE: - pr_info("CPU %u is now online\n", cpu); - break; - case CPU_DEAD: - break; - } - - return NOTIFY_OK; + shx3_update_boot_vector(cpu); + return 0; } -static struct notifier_block shx3_cpu_notifier = { - .notifier_call = shx3_cpu_callback, -}; - static int register_shx3_cpu_notifier(void) { - register_hotcpu_notifier(&shx3_cpu_notifier); + cpuhp_setup_state_nocalls(CPUHP_SH_SH3X_PREPARE, "sh/shx3:prepare", + shx3_cpu_prepare, NULL); return 0; } late_initcall(register_shx3_cpu_notifier); diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c index 38993e09ef03..53783978162e 100644 --- a/arch/sh/kernel/ftrace.c +++ b/arch/sh/kernel/ftrace.c @@ -139,7 +139,7 @@ static void ftrace_mod_code(void) clear_mod_flag(); } -void ftrace_nmi_enter(void) +void arch_ftrace_nmi_enter(void) { if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) { smp_rmb(); @@ -150,7 +150,7 @@ void ftrace_nmi_enter(void) smp_mb(); } -void ftrace_nmi_exit(void) +void arch_ftrace_nmi_exit(void) { /* Finish all executions before clearing nmi_running */ smp_mb(); @@ -382,7 +382,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0); + err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0, NULL); if (err == -EBUSY) { __raw_writel(old, parent); return; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 59b09600dd32..f5d60f14a0bc 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -56,7 +56,6 @@ config SPARC64 def_bool 64BIT select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_GRAPH_FP_TEST select HAVE_KRETPROBES select HAVE_KPROBES select HAVE_RCU_TABLE_FREE if SMP diff --git a/arch/sparc/include/asm/ftrace.h b/arch/sparc/include/asm/ftrace.h index 3192a8e42fd6..62755a339a59 100644 --- a/arch/sparc/include/asm/ftrace.h +++ b/arch/sparc/include/asm/ftrace.h @@ -9,6 +9,10 @@ void _mcount(void); #endif +#endif /* CONFIG_MCOUNT */ + +#if defined(CONFIG_SPARC64) && !defined(CC_USE_FENTRY) +#define HAVE_FUNCTION_GRAPH_FP_TEST #endif #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h index f5b6537306f0..666d5ba230d2 100644 --- a/arch/sparc/include/asm/hypervisor.h +++ b/arch/sparc/include/asm/hypervisor.h @@ -1744,6 +1744,7 @@ unsigned long sun4v_vintr_set_target(unsigned long dev_handle, #define HV_PCI_MAP_ATTR_READ 0x01 #define HV_PCI_MAP_ATTR_WRITE 0x02 +#define HV_PCI_MAP_ATTR_RELAXED_ORDER 0x04 #define HV_PCI_DEVICE_BUILD(b,d,f) \ ((((b) & 0xff) << 16) | \ diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h index 8c2a8c937540..c1263fc390db 100644 --- a/arch/sparc/include/asm/page_64.h +++ b/arch/sparc/include/asm/page_64.h @@ -25,6 +25,7 @@ #define HPAGE_MASK (~(HPAGE_SIZE - 1UL)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA +#define REAL_HPAGE_PER_HPAGE (_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT)) #endif #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h index 26d9e7726867..ce2233f7e662 100644 --- a/arch/sparc/include/asm/smp_64.h +++ b/arch/sparc/include/asm/smp_64.h @@ -43,6 +43,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask); int hard_smp_processor_id(void); #define raw_smp_processor_id() (current_thread_info()->cpu) +void smp_fill_in_cpu_possible_map(void); void smp_fill_in_sib_core_maps(void); void cpu_play_dead(void); @@ -72,6 +73,7 @@ void __cpu_die(unsigned int cpu); #define smp_fill_in_sib_core_maps() do { } while (0) #define smp_fetch_global_regs() do { } while (0) #define smp_fetch_global_pmu() do { } while (0) +#define smp_fill_in_cpu_possible_map() do { } while (0) #endif /* !(CONFIG_SMP) */ diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h index 341a5a133f48..ea55f86d7ccd 100644 --- a/arch/sparc/include/asm/uaccess_32.h +++ b/arch/sparc/include/asm/uaccess_32.h @@ -249,8 +249,7 @@ unsigned long __copy_user(void __user *to, const void __user *from, unsigned lon static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n) { if (n && __access_ok((unsigned long) to, n)) { - if (!__builtin_constant_p(n)) - check_object_size(from, n, true); + check_object_size(from, n, true); return __copy_user(to, (__force void __user *) from, n); } else return n; @@ -258,19 +257,19 @@ static inline unsigned long copy_to_user(void __user *to, const void *from, unsi static inline unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { - if (!__builtin_constant_p(n)) - check_object_size(from, n, true); + check_object_size(from, n, true); return __copy_user(to, (__force void __user *) from, n); } static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n) { if (n && __access_ok((unsigned long) from, n)) { - if (!__builtin_constant_p(n)) - check_object_size(to, n, false); + check_object_size(to, n, false); return __copy_user((__force void __user *) to, from, n); - } else + } else { + memset(to, 0, n); return n; + } } static inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index 8bda94fab8e8..37a315d0ddd4 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -212,8 +212,7 @@ copy_from_user(void *to, const void __user *from, unsigned long size) { unsigned long ret; - if (!__builtin_constant_p(size)) - check_object_size(to, size, false); + check_object_size(to, size, false); ret = ___copy_from_user(to, from, size); if (unlikely(ret)) @@ -233,8 +232,8 @@ copy_to_user(void __user *to, const void *from, unsigned long size) { unsigned long ret; - if (!__builtin_constant_p(size)) - check_object_size(from, size, true); + check_object_size(from, size, true); + ret = ___copy_to_user(to, from, size); if (unlikely(ret)) ret = copy_to_user_fixup(to, from, size); diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c index 0a2d2ddff543..6bcff698069b 100644 --- a/arch/sparc/kernel/ftrace.c +++ b/arch/sparc/kernel/ftrace.c @@ -131,7 +131,7 @@ unsigned long prepare_ftrace_return(unsigned long parent, return parent + 8UL; if (ftrace_push_return_trace(parent, self_addr, &trace.depth, - frame_pointer) == -EBUSY) + frame_pointer, NULL) == -EBUSY) return parent + 8UL; trace.func = self_addr; diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c index cd83be527586..b0377db12d83 100644 --- a/arch/sparc/kernel/kprobes.c +++ b/arch/sparc/kernel/kprobes.c @@ -5,7 +5,7 @@ #include <linux/kernel.h> #include <linux/kprobes.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/kdebug.h> #include <linux/slab.h> #include <linux/context_tracking.h> diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index 61c6f935accc..db57d8acdc01 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -30,8 +30,19 @@ #define DRIVER_NAME "pci_sun4v" #define PFX DRIVER_NAME ": " -static unsigned long vpci_major = 1; -static unsigned long vpci_minor = 1; +static unsigned long vpci_major; +static unsigned long vpci_minor; + +struct vpci_version { + unsigned long major; + unsigned long minor; +}; + +/* Ordered from largest major to lowest */ +static struct vpci_version vpci_versions[] = { + { .major = 2, .minor = 0 }, + { .major = 1, .minor = 1 }, +}; #define PGLIST_NENTS (PAGE_SIZE / sizeof(u64)) @@ -67,6 +78,10 @@ static long iommu_batch_flush(struct iommu_batch *p) u64 *pglist = p->pglist; unsigned long npages = p->npages; + /* VPCI maj=1, min=[0,1] only supports read and write */ + if (vpci_major < 2) + prot &= (HV_PCI_MAP_ATTR_READ | HV_PCI_MAP_ATTR_WRITE); + while (npages != 0) { long num; @@ -133,6 +148,7 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, unsigned long attrs) { unsigned long flags, order, first_page, npages, n; + unsigned long prot = 0; struct iommu *iommu; struct page *page; void *ret; @@ -146,6 +162,9 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, npages = size >> IO_PAGE_SHIFT; + if (attrs & DMA_ATTR_WEAK_ORDERING) + prot = HV_PCI_MAP_ATTR_RELAXED_ORDER; + nid = dev->archdata.numa_node; page = alloc_pages_node(nid, gfp, order); if (unlikely(!page)) @@ -169,7 +188,7 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, local_irq_save(flags); iommu_batch_start(dev, - (HV_PCI_MAP_ATTR_READ | + (HV_PCI_MAP_ATTR_READ | prot | HV_PCI_MAP_ATTR_WRITE), entry); @@ -266,6 +285,9 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page, if (direction != DMA_TO_DEVICE) prot |= HV_PCI_MAP_ATTR_WRITE; + if (attrs & DMA_ATTR_WEAK_ORDERING) + prot |= HV_PCI_MAP_ATTR_RELAXED_ORDER; + local_irq_save(flags); iommu_batch_start(dev, prot, entry); @@ -344,6 +366,9 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, if (direction != DMA_TO_DEVICE) prot |= HV_PCI_MAP_ATTR_WRITE; + if (attrs & DMA_ATTR_WEAK_ORDERING) + prot |= HV_PCI_MAP_ATTR_RELAXED_ORDER; + outs = s = segstart = &sglist[0]; outcount = 1; incount = nelems; @@ -907,22 +932,27 @@ static int pci_sun4v_probe(struct platform_device *op) struct device_node *dp; struct iommu *iommu; u32 devhandle; - int i, err; + int i, err = -ENODEV; dp = op->dev.of_node; if (!hvapi_negotiated++) { - err = sun4v_hvapi_register(HV_GRP_PCI, - vpci_major, - &vpci_minor); + for (i = 0; i < ARRAY_SIZE(vpci_versions); i++) { + vpci_major = vpci_versions[i].major; + vpci_minor = vpci_versions[i].minor; + + err = sun4v_hvapi_register(HV_GRP_PCI, vpci_major, + &vpci_minor); + if (!err) + break; + } if (err) { - printk(KERN_ERR PFX "Could not register hvapi, " - "err=%d\n", err); + pr_err(PFX "Could not register hvapi, err=%d\n", err); return err; } - printk(KERN_INFO PFX "Registered hvapi major[%lu] minor[%lu]\n", - vpci_major, vpci_minor); + pr_info(PFX "Registered hvapi major[%lu] minor[%lu]\n", + vpci_major, vpci_minor); dma_ops = &sun4v_dma_ops; } diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 599f1207eed2..6b7331d198e9 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -31,6 +31,7 @@ #include <linux/initrd.h> #include <linux/module.h> #include <linux/start_kernel.h> +#include <linux/bootmem.h> #include <asm/io.h> #include <asm/processor.h> @@ -50,6 +51,8 @@ #include <asm/elf.h> #include <asm/mdesc.h> #include <asm/cacheflush.h> +#include <asm/dma.h> +#include <asm/irq.h> #ifdef CONFIG_IP_PNP #include <net/ipconfig.h> @@ -590,6 +593,22 @@ static void __init init_sparc64_elf_hwcap(void) pause_patch(); } +void __init alloc_irqstack_bootmem(void) +{ + unsigned int i, node; + + for_each_possible_cpu(i) { + node = cpu_to_node(i); + + softirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node), + THREAD_SIZE, + THREAD_SIZE, 0); + hardirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node), + THREAD_SIZE, + THREAD_SIZE, 0); + } +} + void __init setup_arch(char **cmdline_p) { /* Initialize PROM console and command line. */ @@ -650,6 +669,13 @@ void __init setup_arch(char **cmdline_p) paging_init(); init_sparc64_elf_hwcap(); + smp_fill_in_cpu_possible_map(); + /* + * Once the OF device tree and MDESC have been setup and nr_cpus has + * been parsed, we know the list of possible cpus. Therefore we can + * allocate the IRQ stacks. + */ + alloc_irqstack_bootmem(); } extern int stop_a_enabled; diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c index fb30e7c6a5b1..e80e6ba3d500 100644 --- a/arch/sparc/kernel/smp_32.c +++ b/arch/sparc/kernel/smp_32.c @@ -352,9 +352,7 @@ static void sparc_start_secondary(void *arg) preempt_disable(); cpu = smp_processor_id(); - /* Invoke the CPU_STARTING notifier callbacks */ notify_cpu_starting(cpu); - arch_cpu_pre_online(arg); /* Set the CPU in the cpu_online_mask */ diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 8a6151a628ce..d3035ba6cd31 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1227,6 +1227,20 @@ void __init smp_setup_processor_id(void) xcall_deliver_impl = hypervisor_xcall_deliver; } +void __init smp_fill_in_cpu_possible_map(void) +{ + int possible_cpus = num_possible_cpus(); + int i; + + if (possible_cpus > nr_cpu_ids) + possible_cpus = nr_cpu_ids; + + for (i = 0; i < possible_cpus; i++) + set_cpu_possible(i, true); + for (; i < NR_CPUS; i++) + set_cpu_possible(i, false); +} + void smp_fill_in_sib_core_maps(void) { unsigned int i; diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index d21cd625c0de..4094a51b1970 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -8,7 +8,7 @@ * I like traps on v9, :)))) */ -#include <linux/module.h> +#include <linux/extable.h> #include <linux/sched.h> #include <linux/linkage.h> #include <linux/kernel.h> diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c index 9aacb9159262..52c00d90d4b4 100644 --- a/arch/sparc/kernel/unaligned_64.c +++ b/arch/sparc/kernel/unaligned_64.c @@ -11,7 +11,7 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/mm.h> -#include <linux/module.h> +#include <linux/extable.h> #include <asm/asi.h> #include <asm/ptrace.h> #include <asm/pstate.h> diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index e16fdd28a931..643c149a3151 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -14,7 +14,7 @@ #include <linux/mman.h> #include <linux/signal.h> #include <linux/mm.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/init.h> #include <linux/perf_event.h> #include <linux/interrupt.h> @@ -484,6 +484,7 @@ good_area: tsb_grow(mm, MM_TSB_BASE, mm_rss); #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) mm_rss = mm->context.hugetlb_pte_count + mm->context.thp_pte_count; + mm_rss *= REAL_HPAGE_PER_HPAGE; if (unlikely(mm_rss > mm->context.tsb_block[MM_TSB_HUGE].tsb_rss_limit)) { if (mm->context.tsb_block[MM_TSB_HUGE].tsb) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 65457c9f1365..439784b7b7ac 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -5,7 +5,7 @@ * Copyright (C) 1997-1999 Jakub Jelinek (jj@sunsite.mff.cuni.cz) */ -#include <linux/module.h> +#include <linux/extable.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/string.h> @@ -1160,7 +1160,7 @@ int __node_distance(int from, int to) return numa_latency[from][to]; } -static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp) +static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp) { int i; @@ -1173,8 +1173,8 @@ static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp) return i; } -static void find_numa_latencies_for_group(struct mdesc_handle *md, u64 grp, - int index) +static void __init find_numa_latencies_for_group(struct mdesc_handle *md, + u64 grp, int index) { u64 arc; @@ -2081,7 +2081,6 @@ void __init paging_init(void) { unsigned long end_pfn, shift, phys_base; unsigned long real_end, i; - int node; setup_page_offset(); @@ -2250,21 +2249,6 @@ void __init paging_init(void) /* Setup bootmem... */ last_valid_pfn = end_pfn = bootmem_init(phys_base); - /* Once the OF device tree and MDESC have been setup, we know - * the list of possible cpus. Therefore we can allocate the - * IRQ stacks. - */ - for_each_possible_cpu(i) { - node = cpu_to_node(i); - - softirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node), - THREAD_SIZE, - THREAD_SIZE, 0); - hardirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node), - THREAD_SIZE, - THREAD_SIZE, 0); - } - kernel_physical_mapping_init(); { diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index 3659d37b4d81..c56a195c9071 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -174,10 +174,25 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, return; if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) { - if (pmd_val(pmd) & _PAGE_PMD_HUGE) - mm->context.thp_pte_count++; - else - mm->context.thp_pte_count--; + /* + * Note that this routine only sets pmds for THP pages. + * Hugetlb pages are handled elsewhere. We need to check + * for huge zero page. Huge zero pages are like hugetlb + * pages in that there is no RSS, but there is the need + * for TSB entries. So, huge zero page counts go into + * hugetlb_pte_count. + */ + if (pmd_val(pmd) & _PAGE_PMD_HUGE) { + if (is_huge_zero_page(pmd_page(pmd))) + mm->context.hugetlb_pte_count++; + else + mm->context.thp_pte_count++; + } else { + if (is_huge_zero_page(pmd_page(orig))) + mm->context.hugetlb_pte_count--; + else + mm->context.thp_pte_count--; + } /* Do not try to allocate the TSB hash table if we * don't have one already. We have various locks held @@ -204,6 +219,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, } } +/* + * This routine is only called when splitting a THP + */ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { @@ -213,6 +231,15 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, set_pmd_at(vma->vm_mm, address, pmdp, entry); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + + /* + * set_pmd_at() will not be called in a way to decrement + * thp_pte_count when splitting a THP, so do it now. + * Sanity check pmd before doing the actual decrement. + */ + if ((pmd_val(entry) & _PAGE_PMD_HUGE) && + !is_huge_zero_page(pmd_page(entry))) + (vma->vm_mm)->context.thp_pte_count--; } void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 6725ed45580e..f2b77112e9d8 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -469,8 +469,10 @@ retry_tsb_alloc: int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + unsigned long mm_rss = get_mm_rss(mm); #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) - unsigned long total_huge_pte_count; + unsigned long saved_hugetlb_pte_count; + unsigned long saved_thp_pte_count; #endif unsigned int i; @@ -483,10 +485,12 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) * will re-increment the counters as the parent PTEs are * copied into the child address space. */ - total_huge_pte_count = mm->context.hugetlb_pte_count + - mm->context.thp_pte_count; + saved_hugetlb_pte_count = mm->context.hugetlb_pte_count; + saved_thp_pte_count = mm->context.thp_pte_count; mm->context.hugetlb_pte_count = 0; mm->context.thp_pte_count = 0; + + mm_rss -= saved_thp_pte_count * (HPAGE_SIZE / PAGE_SIZE); #endif /* copy_mm() copies over the parent's mm_struct before calling @@ -499,11 +503,13 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) /* If this is fork, inherit the parent's TSB size. We would * grow it to that size on the first page fault anyways. */ - tsb_grow(mm, MM_TSB_BASE, get_mm_rss(mm)); + tsb_grow(mm, MM_TSB_BASE, mm_rss); #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) - if (unlikely(total_huge_pte_count)) - tsb_grow(mm, MM_TSB_HUGE, total_huge_pte_count); + if (unlikely(saved_hugetlb_pte_count + saved_thp_pte_count)) + tsb_grow(mm, MM_TSB_HUGE, + (saved_hugetlb_pte_count + saved_thp_pte_count) * + REAL_HPAGE_PER_HPAGE); #endif if (unlikely(!mm->context.tsb_block[MM_TSB_BASE].tsb)) diff --git a/arch/sparc/prom/ranges.c b/arch/sparc/prom/ranges.c index ad143c13bdc0..6d8dc2aa94ce 100644 --- a/arch/sparc/prom/ranges.c +++ b/arch/sparc/prom/ranges.c @@ -16,9 +16,8 @@ static struct linux_prom_ranges promlib_obio_ranges[PROMREG_MAX]; static int num_obio_ranges; /* Adjust register values based upon the ranges parameters. */ -static void -prom_adjust_regs(struct linux_prom_registers *regp, int nregs, - struct linux_prom_ranges *rangep, int nranges) +static void prom_adjust_regs(struct linux_prom_registers *regp, int nregs, + struct linux_prom_ranges *rangep, int nranges) { int regc, rngc; @@ -34,33 +33,30 @@ prom_adjust_regs(struct linux_prom_registers *regp, int nregs, } } -static void -prom_adjust_ranges(struct linux_prom_ranges *ranges1, int nranges1, - struct linux_prom_ranges *ranges2, int nranges2) +static void prom_adjust_ranges(struct linux_prom_ranges *ranges1, int nranges1, + struct linux_prom_ranges *ranges2, int nranges2) { int rng1c, rng2c; - for(rng1c=0; rng1c < nranges1; rng1c++) { - for(rng2c=0; rng2c < nranges2; rng2c++) - if(ranges1[rng1c].ot_parent_space == ranges2[rng2c].ot_child_space && + for (rng1c = 0; rng1c < nranges1; rng1c++) { + for (rng2c = 0; rng2c < nranges2; rng2c++) + if (ranges1[rng1c].ot_parent_space == ranges2[rng2c].ot_child_space && ranges1[rng1c].ot_parent_base >= ranges2[rng2c].ot_child_base && ranges2[rng2c].ot_child_base + ranges2[rng2c].or_size - ranges1[rng1c].ot_parent_base > 0U) break; - if(rng2c == nranges2) /* oops */ + if (rng2c == nranges2) /* oops */ prom_printf("adjust_ranges: Could not find matching bus type...\n"); else if (ranges1[rng1c].ot_parent_base + ranges1[rng1c].or_size > ranges2[rng2c].ot_child_base + ranges2[rng2c].or_size) - ranges1[rng1c].or_size = - ranges2[rng2c].ot_child_base + ranges2[rng2c].or_size - ranges1[rng1c].ot_parent_base; + ranges1[rng1c].or_size = ranges2[rng2c].ot_child_base + ranges2[rng2c].or_size - ranges1[rng1c].ot_parent_base; ranges1[rng1c].ot_parent_space = ranges2[rng2c].ot_parent_space; ranges1[rng1c].ot_parent_base += ranges2[rng2c].ot_parent_base; } } /* Apply probed obio ranges to registers passed, if no ranges return. */ -void -prom_apply_obio_ranges(struct linux_prom_registers *regs, int nregs) +void prom_apply_obio_ranges(struct linux_prom_registers *regs, int nregs) { - if(num_obio_ranges) + if (num_obio_ranges) prom_adjust_regs(regs, nregs, promlib_obio_ranges, num_obio_ranges); } EXPORT_SYMBOL(prom_apply_obio_ranges); @@ -76,40 +72,40 @@ void __init prom_ranges_init(void) node = prom_getchild(prom_root_node); obio_node = prom_searchsiblings(node, "obio"); - if(obio_node) { + if (obio_node) { success = prom_getproperty(obio_node, "ranges", (char *) promlib_obio_ranges, sizeof(promlib_obio_ranges)); - if(success != -1) - num_obio_ranges = (success/sizeof(struct linux_prom_ranges)); + if (success != -1) + num_obio_ranges = (success / sizeof(struct linux_prom_ranges)); } - if(num_obio_ranges) + if (num_obio_ranges) prom_printf("PROMLIB: obio_ranges %d\n", num_obio_ranges); } void prom_apply_generic_ranges(phandle node, phandle parent, - struct linux_prom_registers *regs, int nregs) + struct linux_prom_registers *regs, int nregs) { int success; int num_ranges; struct linux_prom_ranges ranges[PROMREG_MAX]; - + success = prom_getproperty(node, "ranges", (char *) ranges, - sizeof (ranges)); + sizeof(ranges)); if (success != -1) { - num_ranges = (success/sizeof(struct linux_prom_ranges)); + num_ranges = (success / sizeof(struct linux_prom_ranges)); if (parent) { struct linux_prom_ranges parent_ranges[PROMREG_MAX]; int num_parent_ranges; - + success = prom_getproperty(parent, "ranges", - (char *) parent_ranges, - sizeof (parent_ranges)); + (char *) parent_ranges, + sizeof(parent_ranges)); if (success != -1) { - num_parent_ranges = (success/sizeof(struct linux_prom_ranges)); - prom_adjust_ranges (ranges, num_ranges, parent_ranges, num_parent_ranges); + num_parent_ranges = (success / sizeof(struct linux_prom_ranges)); + prom_adjust_ranges(ranges, num_ranges, parent_ranges, num_parent_ranges); } } prom_adjust_regs(regs, nregs, ranges, num_ranges); diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 4820a02838ac..78da75b670bc 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -4,7 +4,6 @@ config TILE def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_WANT_FRAME_POINTERS diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h index 0a9c4265763b..a77369e91e54 100644 --- a/arch/tile/include/asm/uaccess.h +++ b/arch/tile/include/asm/uaccess.h @@ -416,14 +416,13 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) return n; } -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -/* - * There are still unprovable places in the generic code as of 2.6.34, so this - * option is not really compatible with -Werror, which is more useful in - * general. - */ -extern void copy_from_user_overflow(void) - __compiletime_warning("copy_from_user() size is not provably correct"); +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, @@ -433,14 +432,13 @@ static inline unsigned long __must_check copy_from_user(void *to, if (likely(sz == -1 || sz >= n)) n = _copy_from_user(to, from, n); + else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - copy_from_user_overflow(); + __bad_copy_user(); return n; } -#else -#define copy_from_user _copy_from_user -#endif #ifdef __tilegx__ /** diff --git a/arch/tile/kernel/ftrace.c b/arch/tile/kernel/ftrace.c index 4a572088b270..b827a418b155 100644 --- a/arch/tile/kernel/ftrace.c +++ b/arch/tile/kernel/ftrace.c @@ -184,7 +184,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, *parent = return_hooker; err = ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer); + frame_pointer, NULL); if (err == -EBUSY) { *parent = old; return; diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c index 2d0266d0254d..3282787bbcfb 100644 --- a/arch/um/drivers/harddog_kern.c +++ b/arch/um/drivers/harddog_kern.c @@ -175,27 +175,4 @@ static struct miscdevice harddog_miscdev = { .name = "watchdog", .fops = &harddog_fops, }; - -static char banner[] __initdata = KERN_INFO "UML Watchdog Timer\n"; - -static int __init harddog_init(void) -{ - int ret; - - ret = misc_register(&harddog_miscdev); - - if (ret) - return ret; - - printk(banner); - - return 0; -} - -static void __exit harddog_exit(void) -{ - misc_deregister(&harddog_miscdev); -} - -module_init(harddog_init); -module_exit(harddog_exit); +module_misc_device(harddog_miscdev); diff --git a/arch/um/kernel/skas/syscall.c b/arch/um/kernel/skas/syscall.c index ef4b8f949b51..b783ac87d98a 100644 --- a/arch/um/kernel/skas/syscall.c +++ b/arch/um/kernel/skas/syscall.c @@ -21,21 +21,17 @@ void handle_syscall(struct uml_pt_regs *r) PT_REGS_SET_SYSCALL_RETURN(regs, -ENOSYS); if (syscall_trace_enter(regs)) - return; + goto out; /* Do the seccomp check after ptrace; failures should be fast. */ if (secure_computing(NULL) == -1) - return; + goto out; - /* Update the syscall number after orig_ax has potentially been updated - * with ptrace. - */ - UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp); syscall = UPT_SYSCALL_NR(r); - if (syscall >= 0 && syscall <= __NR_syscall_max) PT_REGS_SET_SYSCALL_RETURN(regs, EXECUTE_SYSCALL(syscall, regs)); +out: syscall_trace_leave(regs); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c580d8c33562..58bec8f9641a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -24,7 +24,6 @@ config X86 select ARCH_DISCARD_MEMBLOCK select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER @@ -94,6 +93,7 @@ config X86 select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_ARCH_WITHIN_STACK_FRAMES select HAVE_EBPF_JIT if X86_64 + select HAVE_ARCH_VMAP_STACK if X86_64 select HAVE_CC_STACKPROTECTOR select HAVE_CMPXCHG_DOUBLE select HAVE_CMPXCHG_LOCAL @@ -110,7 +110,6 @@ config X86 select HAVE_EXIT_THREAD select HAVE_FENTRY if X86_64 select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_FUNCTION_GRAPH_FP_TEST select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS @@ -158,6 +157,7 @@ config X86 select SPARSE_IRQ select SRCU select SYSCTL_EXCEPTION_TRACE + select THREAD_INFO_IN_TASK select USER_STACKTRACE_SUPPORT select VIRT_TO_BUS select X86_DEV_DMA_OPS if X86_64 @@ -550,6 +550,18 @@ config X86_INTEL_QUARK Say Y here if you have a Quark based system such as the Arduino compatible Intel Galileo. +config MLX_PLATFORM + tristate "Mellanox Technologies platform support" + depends on X86_64 + depends on X86_EXTENDED_PLATFORM + ---help--- + This option enables system support for the Mellanox Technologies + platform. + + Say Y here if you are building a kernel for Mellanox system. + + Otherwise, say N. + config X86_INTEL_LPSS bool "Intel Low Power Subsystem Support" depends on X86 && ACPI @@ -706,7 +718,6 @@ config PARAVIRT_DEBUG config PARAVIRT_SPINLOCKS bool "Paravirtualization layer for spinlocks" depends on PARAVIRT && SMP - select UNINLINE_SPIN_UNLOCK if !QUEUED_SPINLOCKS ---help--- Paravirtualized spinlocks allow a pvops backend to replace the spinlock implementation with something virtualization-friendly @@ -719,7 +730,7 @@ config PARAVIRT_SPINLOCKS config QUEUED_LOCK_STAT bool "Paravirt queued spinlock statistics" - depends on PARAVIRT_SPINLOCKS && DEBUG_FS && QUEUED_SPINLOCKS + depends on PARAVIRT_SPINLOCKS && DEBUG_FS ---help--- Enable the collection of statistical data on the slowpath behavior of paravirtualized queued spinlocks and report @@ -2746,19 +2757,6 @@ config PMC_ATOM def_bool y depends on PCI -config VMD - depends on PCI_MSI - tristate "Volume Management Device Driver" - default N - ---help--- - Adds support for the Intel Volume Management Device (VMD). VMD is a - secondary PCI host bridge that allows PCI Express root ports, - and devices attached to them, to be removed from the default - PCI domain and placed within the VMD domain. This provides - more bus resources than are otherwise possible with a - single domain. If you know your system provides one of these and - has devices attached to it, say Y; if you are not sure, say N. - source "net/Kconfig" source "drivers/Kconfig" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 830ed391e7ef..2d449337a360 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -163,11 +163,12 @@ asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1) asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1) avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1) avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1) +avx512_instr :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,-DCONFIG_AS_AVX512=1) sha1_ni_instr :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA1_NI=1) sha256_ni_instr :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA256_NI=1) -KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(sha1_ni_instr) $(sha256_ni_instr) -KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(sha1_ni_instr) $(sha256_ni_instr) +KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) +KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) LDFLAGS := -m elf_$(UTS_MACHINE) diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index ff574dad95cc..cc69e37548db 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -29,22 +29,11 @@ __pure const struct efi_config *__efi_early(void) static void setup_boot_services##bits(struct efi_config *c) \ { \ efi_system_table_##bits##_t *table; \ - efi_boot_services_##bits##_t *bt; \ \ table = (typeof(table))sys_table; \ \ + c->boot_services = table->boottime; \ c->text_output = table->con_out; \ - \ - bt = (typeof(bt))(unsigned long)(table->boottime); \ - \ - c->allocate_pool = bt->allocate_pool; \ - c->allocate_pages = bt->allocate_pages; \ - c->get_memory_map = bt->get_memory_map; \ - c->free_pool = bt->free_pool; \ - c->free_pages = bt->free_pages; \ - c->locate_handle = bt->locate_handle; \ - c->handle_protocol = bt->handle_protocol; \ - c->exit_boot_services = bt->exit_boot_services; \ } BOOT_SERVICES(32); BOOT_SERVICES(64); @@ -286,29 +275,6 @@ void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) } } -static void find_bits(unsigned long mask, u8 *pos, u8 *size) -{ - u8 first, len; - - first = 0; - len = 0; - - if (mask) { - while (!(mask & 0x1)) { - mask = mask >> 1; - first++; - } - - while (mask & 0x1) { - mask = mask >> 1; - len++; - } - } - - *pos = first; - *size = len; -} - static efi_status_t __setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom) { @@ -578,7 +544,7 @@ setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height) efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; unsigned long nr_ugas; u32 *handles = (u32 *)uga_handle;; - efi_status_t status; + efi_status_t status = EFI_INVALID_PARAMETER; int i; first_uga = NULL; @@ -623,7 +589,7 @@ setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height) efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; unsigned long nr_ugas; u64 *handles = (u64 *)uga_handle;; - efi_status_t status; + efi_status_t status = EFI_INVALID_PARAMETER; int i; first_uga = NULL; @@ -1004,79 +970,87 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext, return status; } -static efi_status_t exit_boot(struct boot_params *boot_params, - void *handle, bool is64) -{ - struct efi_info *efi = &boot_params->efi_info; - unsigned long map_sz, key, desc_size; - efi_memory_desc_t *mem_map; +struct exit_boot_struct { + struct boot_params *boot_params; + struct efi_info *efi; struct setup_data *e820ext; - const char *signature; __u32 e820ext_size; - __u32 nr_desc, prev_nr_desc; - efi_status_t status; - __u32 desc_version; - bool called_exit = false; - u8 nr_entries; - int i; - - nr_desc = 0; - e820ext = NULL; - e820ext_size = 0; - -get_map: - status = efi_get_memory_map(sys_table, &mem_map, &map_sz, &desc_size, - &desc_version, &key); - - if (status != EFI_SUCCESS) - return status; - - prev_nr_desc = nr_desc; - nr_desc = map_sz / desc_size; - if (nr_desc > prev_nr_desc && - nr_desc > ARRAY_SIZE(boot_params->e820_map)) { - u32 nr_e820ext = nr_desc - ARRAY_SIZE(boot_params->e820_map); - - status = alloc_e820ext(nr_e820ext, &e820ext, &e820ext_size); - if (status != EFI_SUCCESS) - goto free_mem_map; + bool is64; +}; - efi_call_early(free_pool, mem_map); - goto get_map; /* Allocated memory, get map again */ +static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, + struct efi_boot_memmap *map, + void *priv) +{ + static bool first = true; + const char *signature; + __u32 nr_desc; + efi_status_t status; + struct exit_boot_struct *p = priv; + + if (first) { + nr_desc = *map->buff_size / *map->desc_size; + if (nr_desc > ARRAY_SIZE(p->boot_params->e820_map)) { + u32 nr_e820ext = nr_desc - + ARRAY_SIZE(p->boot_params->e820_map); + + status = alloc_e820ext(nr_e820ext, &p->e820ext, + &p->e820ext_size); + if (status != EFI_SUCCESS) + return status; + } + first = false; } - signature = is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE; - memcpy(&efi->efi_loader_signature, signature, sizeof(__u32)); + signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE; + memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32)); - efi->efi_systab = (unsigned long)sys_table; - efi->efi_memdesc_size = desc_size; - efi->efi_memdesc_version = desc_version; - efi->efi_memmap = (unsigned long)mem_map; - efi->efi_memmap_size = map_sz; + p->efi->efi_systab = (unsigned long)sys_table_arg; + p->efi->efi_memdesc_size = *map->desc_size; + p->efi->efi_memdesc_version = *map->desc_ver; + p->efi->efi_memmap = (unsigned long)*map->map; + p->efi->efi_memmap_size = *map->map_size; #ifdef CONFIG_X86_64 - efi->efi_systab_hi = (unsigned long)sys_table >> 32; - efi->efi_memmap_hi = (unsigned long)mem_map >> 32; + p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32; + p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32; #endif + return EFI_SUCCESS; +} + +static efi_status_t exit_boot(struct boot_params *boot_params, + void *handle, bool is64) +{ + unsigned long map_sz, key, desc_size, buff_size; + efi_memory_desc_t *mem_map; + struct setup_data *e820ext; + __u32 e820ext_size; + efi_status_t status; + __u32 desc_version; + struct efi_boot_memmap map; + struct exit_boot_struct priv; + + map.map = &mem_map; + map.map_size = &map_sz; + map.desc_size = &desc_size; + map.desc_ver = &desc_version; + map.key_ptr = &key; + map.buff_size = &buff_size; + priv.boot_params = boot_params; + priv.efi = &boot_params->efi_info; + priv.e820ext = NULL; + priv.e820ext_size = 0; + priv.is64 = is64; + /* Might as well exit boot services now */ - status = efi_call_early(exit_boot_services, handle, key); - if (status != EFI_SUCCESS) { - /* - * ExitBootServices() will fail if any of the event - * handlers change the memory map. In which case, we - * must be prepared to retry, but only once so that - * we're guaranteed to exit on repeated failures instead - * of spinning forever. - */ - if (called_exit) - goto free_mem_map; - - called_exit = true; - efi_call_early(free_pool, mem_map); - goto get_map; - } + status = efi_exit_boot_services(sys_table, handle, &map, &priv, + exit_boot_func); + if (status != EFI_SUCCESS) + return status; + e820ext = priv.e820ext; + e820ext_size = priv.e820ext_size; /* Historic? */ boot_params->alt_mem_k = 32 * 1024; @@ -1085,10 +1059,6 @@ get_map: return status; return EFI_SUCCESS; - -free_mem_map: - efi_call_early(free_pool, mem_map); - return status; } /* diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 1038524270e7..fd0b6a272dd5 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -82,7 +82,7 @@ ENTRY(efi_pe_entry) /* Relocate efi_config->call() */ leal efi32_config(%esi), %eax - add %esi, 88(%eax) + add %esi, 32(%eax) pushl %eax call make_boot_params @@ -108,7 +108,7 @@ ENTRY(efi32_stub_entry) /* Relocate efi_config->call() */ leal efi32_config(%esi), %eax - add %esi, 88(%eax) + add %esi, 32(%eax) pushl %eax 2: call efi_main @@ -264,7 +264,7 @@ relocated: #ifdef CONFIG_EFI_STUB .data efi32_config: - .fill 11,8,0 + .fill 4,8,0 .long efi_call_phys .long 0 .byte 0 diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 0d80a7ad65cd..efdfba21a5b2 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -265,7 +265,7 @@ ENTRY(efi_pe_entry) /* * Relocate efi_config->call(). */ - addq %rbp, efi64_config+88(%rip) + addq %rbp, efi64_config+32(%rip) movq %rax, %rdi call make_boot_params @@ -285,7 +285,7 @@ handover_entry: * Relocate efi_config->call(). */ movq efi_config(%rip), %rax - addq %rbp, 88(%rax) + addq %rbp, 32(%rax) 2: movq efi_config(%rip), %rdi call efi_main @@ -457,14 +457,14 @@ efi_config: #ifdef CONFIG_EFI_MIXED .global efi32_config efi32_config: - .fill 11,8,0 + .fill 4,8,0 .quad efi64_thunk .byte 0 #endif .global efi64_config efi64_config: - .fill 11,8,0 + .fill 4,8,0 .quad efi_call .byte 1 #endif /* CONFIG_EFI_STUB */ diff --git a/arch/x86/configs/kvm_guest.config b/arch/x86/configs/kvm_guest.config deleted file mode 100644 index 9906505c998a..000000000000 --- a/arch/x86/configs/kvm_guest.config +++ /dev/null @@ -1,31 +0,0 @@ -CONFIG_NET=y -CONFIG_NET_CORE=y -CONFIG_NETDEVICES=y -CONFIG_BLOCK=y -CONFIG_BLK_DEV=y -CONFIG_NETWORK_FILESYSTEMS=y -CONFIG_INET=y -CONFIG_TTY=y -CONFIG_SERIAL_8250=y -CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_BINFMT_ELF=y -CONFIG_PCI=y -CONFIG_PCI_MSI=y -CONFIG_DEBUG_KERNEL=y -CONFIG_VIRTUALIZATION=y -CONFIG_HYPERVISOR_GUEST=y -CONFIG_PARAVIRT=y -CONFIG_KVM_GUEST=y -CONFIG_VIRTIO=y -CONFIG_VIRTIO_PCI=y -CONFIG_VIRTIO_BLK=y -CONFIG_VIRTIO_CONSOLE=y -CONFIG_VIRTIO_NET=y -CONFIG_9P_FS=y -CONFIG_NET_9P=y -CONFIG_NET_9P_VIRTIO=y -CONFIG_SCSI_LOWLEVEL=y -CONFIG_SCSI_VIRTIO=y -CONFIG_VIRTIO_INPUT=y diff --git a/arch/x86/configs/tiny.config b/arch/x86/configs/tiny.config index 4e2ecfa23c15..4b429df40d7a 100644 --- a/arch/x86/configs/tiny.config +++ b/arch/x86/configs/tiny.config @@ -1 +1,3 @@ CONFIG_NOHIGHMEM=y +# CONFIG_HIGHMEM4G is not set +# CONFIG_HIGHMEM64G is not set diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 1433f6b4607d..bdd9cc59d20f 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -31,13 +31,6 @@ #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> -static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs) -{ - unsigned long top_of_stack = - (unsigned long)(regs + 1) + TOP_OF_KERNEL_STACK_PADDING; - return (struct thread_info *)(top_of_stack - THREAD_SIZE); -} - #ifdef CONFIG_CONTEXT_TRACKING /* Called on entry from user mode with IRQs off. */ __visible inline void enter_from_user_mode(void) @@ -71,7 +64,7 @@ static long syscall_trace_enter(struct pt_regs *regs) { u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; - struct thread_info *ti = pt_regs_to_thread_info(regs); + struct thread_info *ti = current_thread_info(); unsigned long ret = 0; bool emulated = false; u32 work; @@ -173,18 +166,17 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) /* Disable IRQs and retry */ local_irq_disable(); - cached_flags = READ_ONCE(pt_regs_to_thread_info(regs)->flags); + cached_flags = READ_ONCE(current_thread_info()->flags); if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS)) break; - } } /* Called with IRQs disabled. */ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) { - struct thread_info *ti = pt_regs_to_thread_info(regs); + struct thread_info *ti = current_thread_info(); u32 cached_flags; if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled())) @@ -209,7 +201,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) * special case only applies after poking regs and before the * very next return to user mode. */ - ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); + current->thread.status &= ~(TS_COMPAT|TS_I386_REGS_POKED); #endif user_enter_irqoff(); @@ -247,7 +239,7 @@ static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags) */ __visible inline void syscall_return_slowpath(struct pt_regs *regs) { - struct thread_info *ti = pt_regs_to_thread_info(regs); + struct thread_info *ti = current_thread_info(); u32 cached_flags = READ_ONCE(ti->flags); CT_WARN_ON(ct_state() != CONTEXT_KERNEL); @@ -270,7 +262,7 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs) #ifdef CONFIG_X86_64 __visible void do_syscall_64(struct pt_regs *regs) { - struct thread_info *ti = pt_regs_to_thread_info(regs); + struct thread_info *ti = current_thread_info(); unsigned long nr = regs->orig_ax; enter_from_user_mode(); @@ -303,11 +295,11 @@ __visible void do_syscall_64(struct pt_regs *regs) */ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) { - struct thread_info *ti = pt_regs_to_thread_info(regs); + struct thread_info *ti = current_thread_info(); unsigned int nr = (unsigned int)regs->orig_ax; #ifdef CONFIG_IA32_EMULATION - ti->status |= TS_COMPAT; + current->thread.status |= TS_COMPAT; #endif if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) { diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 0b56666e6039..b75a8bcd2d23 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -204,34 +204,70 @@ POP_GS_EX .endm +/* + * %eax: prev task + * %edx: next task + */ +ENTRY(__switch_to_asm) + /* + * Save callee-saved registers + * This must match the order in struct inactive_task_frame + */ + pushl %ebp + pushl %ebx + pushl %edi + pushl %esi + + /* switch stack */ + movl %esp, TASK_threadsp(%eax) + movl TASK_threadsp(%edx), %esp + +#ifdef CONFIG_CC_STACKPROTECTOR + movl TASK_stack_canary(%edx), %ebx + movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset +#endif + + /* restore callee-saved registers */ + popl %esi + popl %edi + popl %ebx + popl %ebp + + jmp __switch_to +END(__switch_to_asm) + +/* + * A newly forked process directly context switches into this address. + * + * eax: prev task we switched from + * ebx: kernel thread func (NULL for user thread) + * edi: kernel thread arg + */ ENTRY(ret_from_fork) pushl %eax call schedule_tail popl %eax + testl %ebx, %ebx + jnz 1f /* kernel threads are uncommon */ + +2: /* When we fork, we trace the syscall return in the child, too. */ movl %esp, %eax call syscall_return_slowpath jmp restore_all -END(ret_from_fork) - -ENTRY(ret_from_kernel_thread) - pushl %eax - call schedule_tail - popl %eax - movl PT_EBP(%esp), %eax - call *PT_EBX(%esp) - movl $0, PT_EAX(%esp) + /* kernel thread */ +1: movl %edi, %eax + call *%ebx /* - * Kernel threads return to userspace as if returning from a syscall. - * We should check whether anything actually uses this path and, if so, - * consider switching it over to ret_from_fork. + * A kernel thread is allowed to return here after successfully + * calling do_execve(). Exit to userspace to complete the execve() + * syscall. */ - movl %esp, %eax - call syscall_return_slowpath - jmp restore_all -ENDPROC(ret_from_kernel_thread) + movl $0, PT_EAX(%esp) + jmp 2b +END(ret_from_fork) /* * Return to user mode is not as complex as all this looks, diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index d172c619c449..c98ec2efd750 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -179,7 +179,8 @@ GLOBAL(entry_SYSCALL_64_after_swapgs) * If we need to do entry work or if we guess we'll need to do * exit work, go straight to the slow path. */ - testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + movq PER_CPU_VAR(current_task), %r11 + testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) jnz entry_SYSCALL64_slow_path entry_SYSCALL_64_fastpath: @@ -217,7 +218,8 @@ entry_SYSCALL_64_fastpath: */ DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + movq PER_CPU_VAR(current_task), %r11 + testl $_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) jnz 1f LOCKDEP_SYS_EXIT @@ -351,8 +353,7 @@ ENTRY(stub_ptregs_64) jmp entry_SYSCALL64_slow_path 1: - /* Called from C */ - jmp *%rax /* called from C */ + jmp *%rax /* Called from C */ END(stub_ptregs_64) .macro ptregs_stub func @@ -369,41 +370,73 @@ END(ptregs_\func) #include <asm/syscalls_64.h> /* + * %rdi: prev task + * %rsi: next task + */ +ENTRY(__switch_to_asm) + /* + * Save callee-saved registers + * This must match the order in inactive_task_frame + */ + pushq %rbp + pushq %rbx + pushq %r12 + pushq %r13 + pushq %r14 + pushq %r15 + + /* switch stack */ + movq %rsp, TASK_threadsp(%rdi) + movq TASK_threadsp(%rsi), %rsp + +#ifdef CONFIG_CC_STACKPROTECTOR + movq TASK_stack_canary(%rsi), %rbx + movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset +#endif + + /* restore callee-saved registers */ + popq %r15 + popq %r14 + popq %r13 + popq %r12 + popq %rbx + popq %rbp + + jmp __switch_to +END(__switch_to_asm) + +/* * A newly forked process directly context switches into this address. * - * rdi: prev task we switched from + * rax: prev task we switched from + * rbx: kernel thread func (NULL for user thread) + * r12: kernel thread arg */ ENTRY(ret_from_fork) - LOCK ; btr $TIF_FORK, TI_flags(%r8) - + movq %rax, %rdi call schedule_tail /* rdi: 'prev' task parameter */ - testb $3, CS(%rsp) /* from kernel_thread? */ - jnz 1f - - /* - * We came from kernel_thread. This code path is quite twisted, and - * someone should clean it up. - * - * copy_thread_tls stashes the function pointer in RBX and the - * parameter to be passed in RBP. The called function is permitted - * to call do_execve and thereby jump to user mode. - */ - movq RBP(%rsp), %rdi - call *RBX(%rsp) - movl $0, RAX(%rsp) + testq %rbx, %rbx /* from kernel_thread? */ + jnz 1f /* kernel threads are uncommon */ - /* - * Fall through as though we're exiting a syscall. This makes a - * twisted sort of sense if we just called do_execve. - */ - -1: +2: movq %rsp, %rdi call syscall_return_slowpath /* returns with IRQs disabled */ TRACE_IRQS_ON /* user mode is traced as IRQS on */ SWAPGS jmp restore_regs_and_iret + +1: + /* kernel thread */ + movq %r12, %rdi + call *%rbx + /* + * A kernel thread is allowed to return here after successfully + * calling do_execve(). Exit to userspace to complete the execve() + * syscall. + */ + movq $0, RAX(%rsp) + jmp 2b END(ret_from_fork) /* @@ -555,27 +588,69 @@ native_irq_return_iret: #ifdef CONFIG_X86_ESPFIX64 native_irq_return_ldt: - pushq %rax - pushq %rdi + /* + * We are running with user GSBASE. All GPRs contain their user + * values. We have a percpu ESPFIX stack that is eight slots + * long (see ESPFIX_STACK_SIZE). espfix_waddr points to the bottom + * of the ESPFIX stack. + * + * We clobber RAX and RDI in this code. We stash RDI on the + * normal stack and RAX on the ESPFIX stack. + * + * The ESPFIX stack layout we set up looks like this: + * + * --- top of ESPFIX stack --- + * SS + * RSP + * RFLAGS + * CS + * RIP <-- RSP points here when we're done + * RAX <-- espfix_waddr points here + * --- bottom of ESPFIX stack --- + */ + + pushq %rdi /* Stash user RDI */ SWAPGS movq PER_CPU_VAR(espfix_waddr), %rdi - movq %rax, (0*8)(%rdi) /* RAX */ - movq (2*8)(%rsp), %rax /* RIP */ + movq %rax, (0*8)(%rdi) /* user RAX */ + movq (1*8)(%rsp), %rax /* user RIP */ movq %rax, (1*8)(%rdi) - movq (3*8)(%rsp), %rax /* CS */ + movq (2*8)(%rsp), %rax /* user CS */ movq %rax, (2*8)(%rdi) - movq (4*8)(%rsp), %rax /* RFLAGS */ + movq (3*8)(%rsp), %rax /* user RFLAGS */ movq %rax, (3*8)(%rdi) - movq (6*8)(%rsp), %rax /* SS */ + movq (5*8)(%rsp), %rax /* user SS */ movq %rax, (5*8)(%rdi) - movq (5*8)(%rsp), %rax /* RSP */ + movq (4*8)(%rsp), %rax /* user RSP */ movq %rax, (4*8)(%rdi) - andl $0xffff0000, %eax - popq %rdi + /* Now RAX == RSP. */ + + andl $0xffff0000, %eax /* RAX = (RSP & 0xffff0000) */ + popq %rdi /* Restore user RDI */ + + /* + * espfix_stack[31:16] == 0. The page tables are set up such that + * (espfix_stack | (X & 0xffff0000)) points to a read-only alias of + * espfix_waddr for any X. That is, there are 65536 RO aliases of + * the same page. Set up RSP so that RSP[31:16] contains the + * respective 16 bits of the /userspace/ RSP and RSP nonetheless + * still points to an RO alias of the ESPFIX stack. + */ orq PER_CPU_VAR(espfix_stack), %rax SWAPGS movq %rax, %rsp - popq %rax + + /* + * At this point, we cannot write to the stack any more, but we can + * still read. + */ + popq %rax /* Restore user RAX */ + + /* + * RSP now points to an ordinary IRET frame, except that the page + * is read-only and RSP[31:16] are preloaded with the userspace + * values. We can now IRET back to userspace. + */ jmp native_irq_return_iret #endif END(common_interrupt) @@ -1002,7 +1077,6 @@ ENTRY(error_entry) testb $3, CS+8(%rsp) jz .Lerror_kernelspace -.Lerror_entry_from_usermode_swapgs: /* * We entered from user mode or we're pretending to have entered * from user mode due to an IRET fault. @@ -1045,7 +1119,8 @@ ENTRY(error_entry) * gsbase and proceed. We'll fix up the exception and land in * .Lgs_change's error handler with kernel gsbase. */ - jmp .Lerror_entry_from_usermode_swapgs + SWAPGS + jmp .Lerror_entry_done .Lbstep_iret: /* Fix truncated RIP */ @@ -1073,7 +1148,7 @@ END(error_entry) /* - * On entry, EBS is a "return to kernel mode" flag: + * On entry, EBX is a "return to kernel mode" flag: * 1: already in kernel mode, don't need SWAPGS * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode */ diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 94d54d0defa7..02223cb4bcfd 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -129,7 +129,7 @@ static notrace cycle_t vread_pvclock(int *mode) return 0; } - ret = __pvclock_read_cycles(pvti); + ret = __pvclock_read_cycles(pvti, rdtsc_ordered()); } while (pvclock_read_retry(pvti, version)); /* refer to vread_tsc() comment for rationale */ diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h index 4f741192846d..3dab75f2a673 100644 --- a/arch/x86/entry/vdso/vdso2c.h +++ b/arch/x86/entry/vdso/vdso2c.h @@ -22,7 +22,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len, ELF(Phdr) *pt = (ELF(Phdr) *)(raw_addr + GET_LE(&hdr->e_phoff)); - if (hdr->e_type != ET_DYN) + if (GET_LE(&hdr->e_type) != ET_DYN) fail("input is not a shared object\n"); /* Walk the segment table. */ diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index f840766659a8..23c881caabd1 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -37,54 +37,6 @@ void __init init_vdso_image(const struct vdso_image *image) struct linux_binprm; -/* - * Put the vdso above the (randomized) stack with another randomized - * offset. This way there is no hole in the middle of address space. - * To save memory make sure it is still in the same PTE as the stack - * top. This doesn't give that many random bits. - * - * Note that this algorithm is imperfect: the distribution of the vdso - * start address within a PMD is biased toward the end. - * - * Only used for the 64-bit and x32 vdsos. - */ -static unsigned long vdso_addr(unsigned long start, unsigned len) -{ -#ifdef CONFIG_X86_32 - return 0; -#else - unsigned long addr, end; - unsigned offset; - - /* - * Round up the start address. It can start out unaligned as a result - * of stack start randomization. - */ - start = PAGE_ALIGN(start); - - /* Round the lowest possible end address up to a PMD boundary. */ - end = (start + len + PMD_SIZE - 1) & PMD_MASK; - if (end >= TASK_SIZE_MAX) - end = TASK_SIZE_MAX; - end -= len; - - if (end > start) { - offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1); - addr = start + (offset << PAGE_SHIFT); - } else { - addr = start; - } - - /* - * Forcibly align the final address in case we have a hardware - * issue that requires alignment for performance reasons. - */ - addr = align_vdso_addr(addr); - - return addr; -#endif -} - static int vdso_fault(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf) { @@ -176,30 +128,28 @@ static int vvar_fault(const struct vm_special_mapping *sm, return VM_FAULT_SIGBUS; } -static int map_vdso(const struct vdso_image *image, bool calculate_addr) +static const struct vm_special_mapping vdso_mapping = { + .name = "[vdso]", + .fault = vdso_fault, + .mremap = vdso_mremap, +}; +static const struct vm_special_mapping vvar_mapping = { + .name = "[vvar]", + .fault = vvar_fault, +}; + +/* + * Add vdso and vvar mappings to current process. + * @image - blob to map + * @addr - request a specific address (zero to map at free addr) + */ +static int map_vdso(const struct vdso_image *image, unsigned long addr) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - unsigned long addr, text_start; + unsigned long text_start; int ret = 0; - static const struct vm_special_mapping vdso_mapping = { - .name = "[vdso]", - .fault = vdso_fault, - .mremap = vdso_mremap, - }; - static const struct vm_special_mapping vvar_mapping = { - .name = "[vvar]", - .fault = vvar_fault, - }; - - if (calculate_addr) { - addr = vdso_addr(current->mm->start_stack, - image->size - image->sym_vvar_start); - } else { - addr = 0; - } - if (down_write_killable(&mm->mmap_sem)) return -EINTR; @@ -238,24 +188,104 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) if (IS_ERR(vma)) { ret = PTR_ERR(vma); - goto up_fail; + do_munmap(mm, text_start, image->size); } up_fail: - if (ret) + if (ret) { current->mm->context.vdso = NULL; + current->mm->context.vdso_image = NULL; + } up_write(&mm->mmap_sem); return ret; } +#ifdef CONFIG_X86_64 +/* + * Put the vdso above the (randomized) stack with another randomized + * offset. This way there is no hole in the middle of address space. + * To save memory make sure it is still in the same PTE as the stack + * top. This doesn't give that many random bits. + * + * Note that this algorithm is imperfect: the distribution of the vdso + * start address within a PMD is biased toward the end. + * + * Only used for the 64-bit and x32 vdsos. + */ +static unsigned long vdso_addr(unsigned long start, unsigned len) +{ + unsigned long addr, end; + unsigned offset; + + /* + * Round up the start address. It can start out unaligned as a result + * of stack start randomization. + */ + start = PAGE_ALIGN(start); + + /* Round the lowest possible end address up to a PMD boundary. */ + end = (start + len + PMD_SIZE - 1) & PMD_MASK; + if (end >= TASK_SIZE_MAX) + end = TASK_SIZE_MAX; + end -= len; + + if (end > start) { + offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1); + addr = start + (offset << PAGE_SHIFT); + } else { + addr = start; + } + + /* + * Forcibly align the final address in case we have a hardware + * issue that requires alignment for performance reasons. + */ + addr = align_vdso_addr(addr); + + return addr; +} + +static int map_vdso_randomized(const struct vdso_image *image) +{ + unsigned long addr = vdso_addr(current->mm->start_stack, image->size-image->sym_vvar_start); + + return map_vdso(image, addr); +} +#endif + +int map_vdso_once(const struct vdso_image *image, unsigned long addr) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + + down_write(&mm->mmap_sem); + /* + * Check if we have already mapped vdso blob - fail to prevent + * abusing from userspace install_speciall_mapping, which may + * not do accounting and rlimit right. + * We could search vma near context.vdso, but it's a slowpath, + * so let's explicitely check all VMAs to be completely sure. + */ + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (vma_is_special_mapping(vma, &vdso_mapping) || + vma_is_special_mapping(vma, &vvar_mapping)) { + up_write(&mm->mmap_sem); + return -EEXIST; + } + } + up_write(&mm->mmap_sem); + + return map_vdso(image, addr); +} + #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) static int load_vdso32(void) { if (vdso32_enabled != 1) /* Other values all mean "disabled" */ return 0; - return map_vdso(&vdso_image_32, false); + return map_vdso(&vdso_image_32, 0); } #endif @@ -265,7 +295,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (!vdso64_enabled) return 0; - return map_vdso(&vdso_image_64, true); + return map_vdso_randomized(&vdso_image_64); } #ifdef CONFIG_COMPAT @@ -276,8 +306,7 @@ int compat_arch_setup_additional_pages(struct linux_binprm *bprm, if (test_thread_flag(TIF_X32)) { if (!vdso64_enabled) return 0; - - return map_vdso(&vdso_image_x32, true); + return map_vdso_randomized(&vdso_image_x32); } #endif #ifdef CONFIG_IA32_EMULATION diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index e07a22bb9308..f5f4b3fbbbc2 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -119,8 +119,8 @@ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0080, - [PERF_COUNT_HW_CACHE_MISSES] = 0x0081, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d, + [PERF_COUNT_HW_CACHE_MISSES] = 0x077e, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */ diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index e6131d4454e6..65577f081d07 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -29,6 +29,8 @@ #define COUNTER_SHIFT 16 +static HLIST_HEAD(uncore_unused_list); + struct amd_uncore { int id; int refcnt; @@ -39,7 +41,7 @@ struct amd_uncore { cpumask_t *active_mask; struct pmu *pmu; struct perf_event *events[MAX_COUNTERS]; - struct amd_uncore *free_when_cpu_online; + struct hlist_node node; }; static struct amd_uncore * __percpu *amd_uncore_nb; @@ -306,6 +308,7 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu) uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL; uncore_nb->active_mask = &amd_nb_active_mask; uncore_nb->pmu = &amd_nb_pmu; + uncore_nb->id = -1; *per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb; } @@ -319,6 +322,7 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu) uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL; uncore_l2->active_mask = &amd_l2_active_mask; uncore_l2->pmu = &amd_l2_pmu; + uncore_l2->id = -1; *per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2; } @@ -348,7 +352,7 @@ amd_uncore_find_online_sibling(struct amd_uncore *this, continue; if (this->id == that->id) { - that->free_when_cpu_online = this; + hlist_add_head(&this->node, &uncore_unused_list); this = that; break; } @@ -388,13 +392,23 @@ static int amd_uncore_cpu_starting(unsigned int cpu) return 0; } +static void uncore_clean_online(void) +{ + struct amd_uncore *uncore; + struct hlist_node *n; + + hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) { + hlist_del(&uncore->node); + kfree(uncore); + } +} + static void uncore_online(unsigned int cpu, struct amd_uncore * __percpu *uncores) { struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu); - kfree(uncore->free_when_cpu_online); - uncore->free_when_cpu_online = NULL; + uncore_clean_online(); if (cpu == uncore->cpu) cpumask_set_cpu(cpu, uncore->active_mask); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index d0efb5cb1b00..d31735f37ed7 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -37,6 +37,7 @@ #include <asm/timer.h> #include <asm/desc.h> #include <asm/ldt.h> +#include <asm/unwind.h> #include "perf_event.h" @@ -1201,6 +1202,9 @@ static int x86_pmu_add(struct perf_event *event, int flags) * If group events scheduling transaction was started, * skip the schedulability test here, it will be performed * at commit time (->commit_txn) as a whole. + * + * If commit fails, we'll call ->del() on all events + * for which ->add() was called. */ if (cpuc->txn_flags & PERF_PMU_TXN_ADD) goto done_collect; @@ -1223,6 +1227,14 @@ done_collect: cpuc->n_added += n - n0; cpuc->n_txn += n - n0; + if (x86_pmu.add) { + /* + * This is before x86_pmu_enable() will call x86_pmu_start(), + * so we enable LBRs before an event needs them etc.. + */ + x86_pmu.add(event); + } + ret = 0; out: return ret; @@ -1346,7 +1358,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) event->hw.flags &= ~PERF_X86_EVENT_COMMITTED; /* - * If we're called during a txn, we don't need to do anything. + * If we're called during a txn, we only need to undo x86_pmu.add. * The events never got scheduled and ->cancel_txn will truncate * the event_list. * @@ -1354,7 +1366,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) * an event added during that same TXN. */ if (cpuc->txn_flags & PERF_PMU_TXN_ADD) - return; + goto do_del; /* * Not a TXN, therefore cleanup properly. @@ -1384,6 +1396,15 @@ static void x86_pmu_del(struct perf_event *event, int flags) --cpuc->n_events; perf_event_update_userpage(event); + +do_del: + if (x86_pmu.del) { + /* + * This is after x86_pmu_stop(); so we disable LBRs after any + * event can need them etc.. + */ + x86_pmu.del(event); + } } int x86_pmu_handle_irq(struct pt_regs *regs) @@ -2247,39 +2268,26 @@ void arch_perf_update_userpage(struct perf_event *event, cyc2ns_read_end(data); } -/* - * callchain support - */ - -static int backtrace_stack(void *data, char *name) -{ - return 0; -} - -static int backtrace_address(void *data, unsigned long addr, int reliable) -{ - struct perf_callchain_entry_ctx *entry = data; - - return perf_callchain_store(entry, addr); -} - -static const struct stacktrace_ops backtrace_ops = { - .stack = backtrace_stack, - .address = backtrace_address, - .walk_stack = print_context_stack_bp, -}; - void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + struct unwind_state state; + unsigned long addr; + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { /* TODO: We don't support guest os callchain now */ return; } - perf_callchain_store(entry, regs->ip); + if (perf_callchain_store(entry, regs->ip)) + return; - dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry); + for (unwind_start(&state, current, regs, NULL); !unwind_done(&state); + unwind_next_frame(&state)) { + addr = unwind_get_return_address(&state); + if (!addr || perf_callchain_store(entry, addr)) + return; + } } static inline int diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 0a6e393a2e62..982c9e31daca 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -31,7 +31,17 @@ struct bts_ctx { struct perf_output_handle handle; struct debug_store ds_back; - int started; + int state; +}; + +/* BTS context states: */ +enum { + /* no ongoing AUX transactions */ + BTS_STATE_STOPPED = 0, + /* AUX transaction is on, BTS tracing is disabled */ + BTS_STATE_INACTIVE, + /* AUX transaction is on, BTS tracing is running */ + BTS_STATE_ACTIVE, }; static DEFINE_PER_CPU(struct bts_ctx, bts_ctx); @@ -204,6 +214,15 @@ static void bts_update(struct bts_ctx *bts) static int bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle); +/* + * Ordering PMU callbacks wrt themselves and the PMI is done by means + * of bts::state, which: + * - is set when bts::handle::event is valid, that is, between + * perf_aux_output_begin() and perf_aux_output_end(); + * - is zero otherwise; + * - is ordered against bts::handle::event with a compiler barrier. + */ + static void __bts_event_start(struct perf_event *event) { struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); @@ -221,10 +240,13 @@ static void __bts_event_start(struct perf_event *event) /* * local barrier to make sure that ds configuration made it - * before we enable BTS + * before we enable BTS and bts::state goes ACTIVE */ wmb(); + /* INACTIVE/STOPPED -> ACTIVE */ + WRITE_ONCE(bts->state, BTS_STATE_ACTIVE); + intel_pmu_enable_bts(config); } @@ -251,9 +273,6 @@ static void bts_event_start(struct perf_event *event, int flags) __bts_event_start(event); - /* PMI handler: this counter is running and likely generating PMIs */ - ACCESS_ONCE(bts->started) = 1; - return; fail_end_stop: @@ -263,30 +282,34 @@ fail_stop: event->hw.state = PERF_HES_STOPPED; } -static void __bts_event_stop(struct perf_event *event) +static void __bts_event_stop(struct perf_event *event, int state) { + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + + /* ACTIVE -> INACTIVE(PMI)/STOPPED(->stop()) */ + WRITE_ONCE(bts->state, state); + /* * No extra synchronization is mandated by the documentation to have * BTS data stores globally visible. */ intel_pmu_disable_bts(); - - if (event->hw.state & PERF_HES_STOPPED) - return; - - ACCESS_ONCE(event->hw.state) |= PERF_HES_STOPPED; } static void bts_event_stop(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); - struct bts_buffer *buf = perf_get_aux(&bts->handle); + struct bts_buffer *buf = NULL; + int state = READ_ONCE(bts->state); - /* PMI handler: don't restart this counter */ - ACCESS_ONCE(bts->started) = 0; + if (state == BTS_STATE_ACTIVE) + __bts_event_stop(event, BTS_STATE_STOPPED); - __bts_event_stop(event); + if (state != BTS_STATE_STOPPED) + buf = perf_get_aux(&bts->handle); + + event->hw.state |= PERF_HES_STOPPED; if (flags & PERF_EF_UPDATE) { bts_update(bts); @@ -296,6 +319,7 @@ static void bts_event_stop(struct perf_event *event, int flags) bts->handle.head = local_xchg(&buf->data_size, buf->nr_pages << PAGE_SHIFT); + perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), !!local_xchg(&buf->lost, 0)); } @@ -310,8 +334,20 @@ static void bts_event_stop(struct perf_event *event, int flags) void intel_bts_enable_local(void) { struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + int state = READ_ONCE(bts->state); + + /* + * Here we transition from INACTIVE to ACTIVE; + * if we instead are STOPPED from the interrupt handler, + * stay that way. Can't be ACTIVE here though. + */ + if (WARN_ON_ONCE(state == BTS_STATE_ACTIVE)) + return; + + if (state == BTS_STATE_STOPPED) + return; - if (bts->handle.event && bts->started) + if (bts->handle.event) __bts_event_start(bts->handle.event); } @@ -319,8 +355,15 @@ void intel_bts_disable_local(void) { struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + /* + * Here we transition from ACTIVE to INACTIVE; + * do nothing for STOPPED or INACTIVE. + */ + if (READ_ONCE(bts->state) != BTS_STATE_ACTIVE) + return; + if (bts->handle.event) - __bts_event_stop(bts->handle.event); + __bts_event_stop(bts->handle.event, BTS_STATE_INACTIVE); } static int @@ -335,8 +378,6 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle) return 0; head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1); - if (WARN_ON_ONCE(head != local_read(&buf->head))) - return -EINVAL; phys = &buf->buf[buf->cur_buf]; space = phys->offset + phys->displacement + phys->size - head; @@ -403,22 +444,37 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle) int intel_bts_interrupt(void) { + struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds; struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); struct perf_event *event = bts->handle.event; struct bts_buffer *buf; s64 old_head; - int err; + int err = -ENOSPC, handled = 0; - if (!event || !bts->started) - return 0; + /* + * The only surefire way of knowing if this NMI is ours is by checking + * the write ptr against the PMI threshold. + */ + if (ds && (ds->bts_index >= ds->bts_interrupt_threshold)) + handled = 1; + + /* + * this is wrapped in intel_bts_enable_local/intel_bts_disable_local, + * so we can only be INACTIVE or STOPPED + */ + if (READ_ONCE(bts->state) == BTS_STATE_STOPPED) + return handled; buf = perf_get_aux(&bts->handle); + if (!buf) + return handled; + /* * Skip snapshot counters: they don't use the interrupt, but * there's no other way of telling, because the pointer will * keep moving */ - if (!buf || buf->snapshot) + if (buf->snapshot) return 0; old_head = local_read(&buf->head); @@ -426,18 +482,27 @@ int intel_bts_interrupt(void) /* no new data */ if (old_head == local_read(&buf->head)) - return 0; + return handled; perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), !!local_xchg(&buf->lost, 0)); buf = perf_aux_output_begin(&bts->handle, event); - if (!buf) - return 1; + if (buf) + err = bts_buffer_reset(buf, &bts->handle); + + if (err) { + WRITE_ONCE(bts->state, BTS_STATE_STOPPED); - err = bts_buffer_reset(buf, &bts->handle); - if (err) - perf_aux_output_end(&bts->handle, 0, false); + if (buf) { + /* + * BTS_STATE_STOPPED should be visible before + * cleared handle::event + */ + barrier(); + perf_aux_output_end(&bts->handle, 0, false); + } + } return 1; } @@ -519,7 +584,8 @@ static __init int bts_init(void) if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts) return -ENODEV; - bts_pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE; + bts_pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE | + PERF_PMU_CAP_EXCLUSIVE; bts_pmu.task_ctx_nr = perf_sw_context; bts_pmu.event_init = bts_event_init; bts_pmu.add = bts_event_add; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2cbde2f449aa..a3a9eb84b5cf 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -1730,9 +1730,11 @@ static __initconst const u64 knl_hw_cache_extra_regs * disabled state if called consecutively. * * During consecutive calls, the same disable value will be written to related - * registers, so the PMU state remains unchanged. hw.state in - * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive - * calls. + * registers, so the PMU state remains unchanged. + * + * intel_bts events don't coexist with intel PMU's BTS events because of + * x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them + * disabled around intel PMU's event batching etc, only inside the PMI handler. */ static void __intel_pmu_disable_all(void) { @@ -1742,8 +1744,6 @@ static void __intel_pmu_disable_all(void) if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) intel_pmu_disable_bts(); - else - intel_bts_disable_local(); intel_pmu_pebs_disable_all(); } @@ -1771,8 +1771,7 @@ static void __intel_pmu_enable_all(int added, bool pmi) return; intel_pmu_enable_bts(event->hw.config); - } else - intel_bts_enable_local(); + } } static void intel_pmu_enable_all(int added) @@ -1907,13 +1906,6 @@ static void intel_pmu_disable_event(struct perf_event *event) cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx); cpuc->intel_cp_status &= ~(1ull << hwc->idx); - /* - * must disable before any actual event - * because any event may be combined with LBR - */ - if (needs_branch_stack(event)) - intel_pmu_lbr_disable(event); - if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { intel_pmu_disable_fixed(hwc); return; @@ -1925,6 +1917,14 @@ static void intel_pmu_disable_event(struct perf_event *event) intel_pmu_pebs_disable(event); } +static void intel_pmu_del_event(struct perf_event *event) +{ + if (needs_branch_stack(event)) + intel_pmu_lbr_del(event); + if (event->attr.precise_ip) + intel_pmu_pebs_del(event); +} + static void intel_pmu_enable_fixed(struct hw_perf_event *hwc) { int idx = hwc->idx - INTEL_PMC_IDX_FIXED; @@ -1968,12 +1968,6 @@ static void intel_pmu_enable_event(struct perf_event *event) intel_pmu_enable_bts(hwc->config); return; } - /* - * must enabled before any actual event - * because any event may be combined with LBR - */ - if (needs_branch_stack(event)) - intel_pmu_lbr_enable(event); if (event->attr.exclude_host) cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx); @@ -1994,6 +1988,14 @@ static void intel_pmu_enable_event(struct perf_event *event) __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); } +static void intel_pmu_add_event(struct perf_event *event) +{ + if (event->attr.precise_ip) + intel_pmu_pebs_add(event); + if (needs_branch_stack(event)) + intel_pmu_lbr_add(event); +} + /* * Save and restart an expired event. Called by NMI contexts, * so it has to be careful about preempting normal event ops: @@ -2073,6 +2075,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) */ if (!x86_pmu.late_ack) apic_write(APIC_LVTPC, APIC_DM_NMI); + intel_bts_disable_local(); __intel_pmu_disable_all(); handled = intel_pmu_drain_bts_buffer(); handled += intel_bts_interrupt(); @@ -2172,6 +2175,7 @@ done: /* Only restore PMU state when it's active. See x86_pmu_disable(). */ if (cpuc->enabled) __intel_pmu_enable_all(0, true); + intel_bts_enable_local(); /* * Only unmask the NMI after the overflow counters @@ -3290,6 +3294,8 @@ static __initconst const struct x86_pmu intel_pmu = { .enable_all = intel_pmu_enable_all, .enable = intel_pmu_enable_event, .disable = intel_pmu_disable_event, + .add = intel_pmu_add_event, + .del = intel_pmu_del_event, .hw_config = intel_pmu_hw_config, .schedule_events = x86_schedule_events, .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c index 783c49ddef29..8f82b02934fa 100644 --- a/arch/x86/events/intel/cqm.c +++ b/arch/x86/events/intel/cqm.c @@ -458,6 +458,11 @@ static void __intel_cqm_event_count(void *info); static void init_mbm_sample(u32 rmid, u32 evt_type); static void __intel_mbm_event_count(void *info); +static bool is_cqm_event(int e) +{ + return (e == QOS_L3_OCCUP_EVENT_ID); +} + static bool is_mbm_event(int e) { return (e >= QOS_MBM_TOTAL_EVENT_ID && e <= QOS_MBM_LOCAL_EVENT_ID); @@ -1366,6 +1371,10 @@ static int intel_cqm_event_init(struct perf_event *event) (event->attr.config > QOS_MBM_LOCAL_EVENT_ID)) return -EINVAL; + if ((is_cqm_event(event->attr.config) && !cqm_enabled) || + (is_mbm_event(event->attr.config) && !mbm_enabled)) + return -EINVAL; + /* unsupported modes and filters */ if (event->attr.exclude_user || event->attr.exclude_kernel || diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 7ce9f3f669e6..0319311dbdbb 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -806,9 +806,65 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) return &emptyconstraint; } -static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc) +/* + * We need the sched_task callback even for per-cpu events when we use + * the large interrupt threshold, such that we can provide PID and TID + * to PEBS samples. + */ +static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc) +{ + return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs); +} + +static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) +{ + struct debug_store *ds = cpuc->ds; + u64 threshold; + + if (cpuc->n_pebs == cpuc->n_large_pebs) { + threshold = ds->pebs_absolute_maximum - + x86_pmu.max_pebs_events * x86_pmu.pebs_record_size; + } else { + threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size; + } + + ds->pebs_interrupt_threshold = threshold; +} + +static void +pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu) { - return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1)); + /* + * Make sure we get updated with the first PEBS + * event. It will trigger also during removal, but + * that does not hurt: + */ + bool update = cpuc->n_pebs == 1; + + if (needed_cb != pebs_needs_sched_cb(cpuc)) { + if (!needed_cb) + perf_sched_cb_inc(pmu); + else + perf_sched_cb_dec(pmu); + + update = true; + } + + if (update) + pebs_update_threshold(cpuc); +} + +void intel_pmu_pebs_add(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + bool needed_cb = pebs_needs_sched_cb(cpuc); + + cpuc->n_pebs++; + if (hwc->flags & PERF_X86_EVENT_FREERUNNING) + cpuc->n_large_pebs++; + + pebs_update_state(needed_cb, cpuc, event->ctx->pmu); } void intel_pmu_pebs_enable(struct perf_event *event) @@ -816,12 +872,9 @@ void intel_pmu_pebs_enable(struct perf_event *event) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; struct debug_store *ds = cpuc->ds; - bool first_pebs; - u64 threshold; hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; - first_pebs = !pebs_is_enabled(cpuc); cpuc->pebs_enabled |= 1ULL << hwc->idx; if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) @@ -830,46 +883,34 @@ void intel_pmu_pebs_enable(struct perf_event *event) cpuc->pebs_enabled |= 1ULL << 63; /* - * When the event is constrained enough we can use a larger - * threshold and run the event with less frequent PMI. + * Use auto-reload if possible to save a MSR write in the PMI. + * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD. */ - if (hwc->flags & PERF_X86_EVENT_FREERUNNING) { - threshold = ds->pebs_absolute_maximum - - x86_pmu.max_pebs_events * x86_pmu.pebs_record_size; - - if (first_pebs) - perf_sched_cb_inc(event->ctx->pmu); - } else { - threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size; - - /* - * If not all events can use larger buffer, - * roll back to threshold = 1 - */ - if (!first_pebs && - (ds->pebs_interrupt_threshold > threshold)) - perf_sched_cb_dec(event->ctx->pmu); - } - - /* Use auto-reload if possible to save a MSR write in the PMI */ if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { ds->pebs_event_reset[hwc->idx] = (u64)(-hwc->sample_period) & x86_pmu.cntval_mask; } +} + +void intel_pmu_pebs_del(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + bool needed_cb = pebs_needs_sched_cb(cpuc); - if (first_pebs || ds->pebs_interrupt_threshold > threshold) - ds->pebs_interrupt_threshold = threshold; + cpuc->n_pebs--; + if (hwc->flags & PERF_X86_EVENT_FREERUNNING) + cpuc->n_large_pebs--; + + pebs_update_state(needed_cb, cpuc, event->ctx->pmu); } void intel_pmu_pebs_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - struct debug_store *ds = cpuc->ds; - bool large_pebs = ds->pebs_interrupt_threshold > - ds->pebs_buffer_base + x86_pmu.pebs_record_size; - if (large_pebs) + if (cpuc->n_pebs == cpuc->n_large_pebs) intel_pmu_drain_pebs_buffer(); cpuc->pebs_enabled &= ~(1ULL << hwc->idx); @@ -879,9 +920,6 @@ void intel_pmu_pebs_disable(struct perf_event *event) else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled &= ~(1ULL << 63); - if (large_pebs && !pebs_is_enabled(cpuc)) - perf_sched_cb_dec(event->ctx->pmu); - if (cpuc->enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); @@ -1274,18 +1312,18 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) struct pebs_record_nhm *p = at; u64 pebs_status; - /* PEBS v3 has accurate status bits */ + pebs_status = p->status & cpuc->pebs_enabled; + pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1; + + /* PEBS v3 has more accurate status bits */ if (x86_pmu.intel_cap.pebs_format >= 3) { - for_each_set_bit(bit, (unsigned long *)&p->status, - MAX_PEBS_EVENTS) + for_each_set_bit(bit, (unsigned long *)&pebs_status, + x86_pmu.max_pebs_events) counts[bit]++; continue; } - pebs_status = p->status & cpuc->pebs_enabled; - pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1; - /* * On some CPUs the PEBS status can be zero when PEBS is * racing with clearing of GLOBAL_STATUS. @@ -1333,8 +1371,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) continue; event = cpuc->events[bit]; - WARN_ON_ONCE(!event); - WARN_ON_ONCE(!event->attr.precise_ip); + if (WARN_ON_ONCE(!event)) + continue; + + if (WARN_ON_ONCE(!event->attr.precise_ip)) + continue; /* log dropped samples number */ if (error[bit]) diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 707d358e0dff..fc6cf21c535e 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -380,7 +380,6 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) { - struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx; /* @@ -390,31 +389,21 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) */ task_ctx = ctx ? ctx->task_ctx_data : NULL; if (task_ctx) { - if (sched_in) { + if (sched_in) __intel_pmu_lbr_restore(task_ctx); - cpuc->lbr_context = ctx; - } else { + else __intel_pmu_lbr_save(task_ctx); - } return; } /* - * When sampling the branck stack in system-wide, it may be - * necessary to flush the stack on context switch. This happens - * when the branch stack does not tag its entries with the pid - * of the current task. Otherwise it becomes impossible to - * associate a branch entry with a task. This ambiguity is more - * likely to appear when the branch stack supports priv level - * filtering and the user sets it to monitor only at the user - * level (which could be a useful measurement in system-wide - * mode). In that case, the risk is high of having a branch - * stack with branch from multiple tasks. - */ - if (sched_in) { + * Since a context switch can flip the address space and LBR entries + * are not tagged with an identifier, we need to wipe the LBR, even for + * per-cpu events. You simply cannot resolve the branches from the old + * address space. + */ + if (sched_in) intel_pmu_lbr_reset(); - cpuc->lbr_context = ctx; - } } static inline bool branch_user_callstack(unsigned br_sel) @@ -422,7 +411,7 @@ static inline bool branch_user_callstack(unsigned br_sel) return (br_sel & X86_BR_USER) && (br_sel & X86_BR_CALL_STACK); } -void intel_pmu_lbr_enable(struct perf_event *event) +void intel_pmu_lbr_add(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx; @@ -430,27 +419,38 @@ void intel_pmu_lbr_enable(struct perf_event *event) if (!x86_pmu.lbr_nr) return; - /* - * Reset the LBR stack if we changed task context to - * avoid data leaks. - */ - if (event->ctx->task && cpuc->lbr_context != event->ctx) { - intel_pmu_lbr_reset(); - cpuc->lbr_context = event->ctx; - } cpuc->br_sel = event->hw.branch_reg.reg; - if (branch_user_callstack(cpuc->br_sel) && event->ctx && - event->ctx->task_ctx_data) { + if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data) { task_ctx = event->ctx->task_ctx_data; task_ctx->lbr_callstack_users++; } - cpuc->lbr_users++; + /* + * Request pmu::sched_task() callback, which will fire inside the + * regular perf event scheduling, so that call will: + * + * - restore or wipe; when LBR-callstack, + * - wipe; otherwise, + * + * when this is from __perf_event_task_sched_in(). + * + * However, if this is from perf_install_in_context(), no such callback + * will follow and we'll need to reset the LBR here if this is the + * first LBR event. + * + * The problem is, we cannot tell these cases apart... but we can + * exclude the biggest chunk of cases by looking at + * event->total_time_running. An event that has accrued runtime cannot + * be 'new'. Conversely, a new event can get installed through the + * context switch path for the first time. + */ perf_sched_cb_inc(event->ctx->pmu); + if (!cpuc->lbr_users++ && !event->total_time_running) + intel_pmu_lbr_reset(); } -void intel_pmu_lbr_disable(struct perf_event *event) +void intel_pmu_lbr_del(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx; @@ -467,12 +467,6 @@ void intel_pmu_lbr_disable(struct perf_event *event) cpuc->lbr_users--; WARN_ON_ONCE(cpuc->lbr_users < 0); perf_sched_cb_dec(event->ctx->pmu); - - if (cpuc->enabled && !cpuc->lbr_users) { - __intel_pmu_lbr_disable(); - /* avoid stale pointer */ - cpuc->lbr_context = NULL; - } } void intel_pmu_lbr_enable_all(bool pmi) diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 04bb5fb5a8d7..c5047b8f777b 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -69,6 +69,8 @@ static struct pt_cap_desc { PT_CAP(psb_cyc, 0, CR_EBX, BIT(1)), PT_CAP(ip_filtering, 0, CR_EBX, BIT(2)), PT_CAP(mtc, 0, CR_EBX, BIT(3)), + PT_CAP(ptwrite, 0, CR_EBX, BIT(4)), + PT_CAP(power_event_trace, 0, CR_EBX, BIT(5)), PT_CAP(topa_output, 0, CR_ECX, BIT(0)), PT_CAP(topa_multiple_entries, 0, CR_ECX, BIT(1)), PT_CAP(single_range_output, 0, CR_ECX, BIT(2)), @@ -259,10 +261,16 @@ fail: #define RTIT_CTL_MTC (RTIT_CTL_MTC_EN | \ RTIT_CTL_MTC_RANGE) +#define RTIT_CTL_PTW (RTIT_CTL_PTW_EN | \ + RTIT_CTL_FUP_ON_PTW) + #define PT_CONFIG_MASK (RTIT_CTL_TSC_EN | \ RTIT_CTL_DISRETC | \ RTIT_CTL_CYC_PSB | \ - RTIT_CTL_MTC) + RTIT_CTL_MTC | \ + RTIT_CTL_PWR_EVT_EN | \ + RTIT_CTL_FUP_ON_PTW | \ + RTIT_CTL_PTW_EN) static bool pt_event_valid(struct perf_event *event) { @@ -311,6 +319,20 @@ static bool pt_event_valid(struct perf_event *event) return false; } + if (config & RTIT_CTL_PWR_EVT_EN && + !pt_cap_get(PT_CAP_power_event_trace)) + return false; + + if (config & RTIT_CTL_PTW) { + if (!pt_cap_get(PT_CAP_ptwrite)) + return false; + + /* FUPonPTW without PTW doesn't make sense */ + if ((config & RTIT_CTL_FUP_ON_PTW) && + !(config & RTIT_CTL_PTW_EN)) + return false; + } + return true; } @@ -1074,6 +1096,11 @@ static void pt_addr_filters_fini(struct perf_event *event) event->hw.addr_filters = NULL; } +static inline bool valid_kernel_ip(unsigned long ip) +{ + return virt_addr_valid(ip) && kernel_ip(ip); +} + static int pt_event_addr_filters_validate(struct list_head *filters) { struct perf_addr_filter *filter; @@ -1081,11 +1108,16 @@ static int pt_event_addr_filters_validate(struct list_head *filters) list_for_each_entry(filter, filters, entry) { /* PT doesn't support single address triggers */ - if (!filter->range) + if (!filter->range || !filter->size) return -EOPNOTSUPP; - if (!filter->inode && !kernel_ip(filter->offset)) - return -EINVAL; + if (!filter->inode) { + if (!valid_kernel_ip(filter->offset)) + return -EINVAL; + + if (!valid_kernel_ip(filter->offset + filter->size)) + return -EINVAL; + } if (++range > pt_cap_get(PT_CAP_num_address_ranges)) return -EOPNOTSUPP; @@ -1111,7 +1143,7 @@ static void pt_event_addr_filters_sync(struct perf_event *event) } else { /* apply the offset */ msr_a = filter->offset + offs[range]; - msr_b = filter->size + msr_a; + msr_b = filter->size + msr_a - 1; } filters->filter[range].msr_a = msr_a; diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h index efffa4a09f68..53473c21b554 100644 --- a/arch/x86/events/intel/pt.h +++ b/arch/x86/events/intel/pt.h @@ -26,11 +26,14 @@ #define RTIT_CTL_CYCLEACC BIT(1) #define RTIT_CTL_OS BIT(2) #define RTIT_CTL_USR BIT(3) +#define RTIT_CTL_PWR_EVT_EN BIT(4) +#define RTIT_CTL_FUP_ON_PTW BIT(5) #define RTIT_CTL_CR3EN BIT(7) #define RTIT_CTL_TOPA BIT(8) #define RTIT_CTL_MTC_EN BIT(9) #define RTIT_CTL_TSC_EN BIT(10) #define RTIT_CTL_DISRETC BIT(11) +#define RTIT_CTL_PTW_EN BIT(12) #define RTIT_CTL_BRANCH_EN BIT(13) #define RTIT_CTL_MTC_RANGE_OFFSET 14 #define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET) @@ -91,6 +94,8 @@ enum pt_capabilities { PT_CAP_psb_cyc, PT_CAP_ip_filtering, PT_CAP_mtc, + PT_CAP_ptwrite, + PT_CAP_power_event_trace, PT_CAP_topa_output, PT_CAP_topa_multiple_entries, PT_CAP_single_range_output, diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 28865938aadf..b0f0e835a770 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -357,6 +357,8 @@ static int rapl_pmu_event_init(struct perf_event *event) if (event->cpu < 0) return -EINVAL; + event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG; + /* * check event is known (determines counter) */ @@ -765,6 +767,8 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, hsx_rapl_init), + + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init), {}, }; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 463dc7a5a6c3..d9844cc74486 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -664,6 +664,8 @@ static int uncore_pmu_event_init(struct perf_event *event) event->cpu = box->cpu; event->pmu_private = box; + event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG; + event->hw.idx = -1; event->hw.last_tag = ~0ULL; event->hw.extra_reg.idx = EXTRA_REG_NONE; @@ -683,7 +685,8 @@ static int uncore_pmu_event_init(struct perf_event *event) /* fixed counters have event field hardcoded to zero */ hwc->config = 0ULL; } else { - hwc->config = event->attr.config & pmu->type->event_mask; + hwc->config = event->attr.config & + (pmu->type->event_mask | ((u64)pmu->type->event_mask_ext << 32)); if (pmu->type->ops->hw_config) { ret = pmu->type->ops->hw_config(box, event); if (ret) @@ -1321,6 +1324,11 @@ static const struct intel_uncore_init_fun skl_uncore_init __initconst = { .pci_init = skl_uncore_pci_init, }; +static const struct intel_uncore_init_fun skx_uncore_init __initconst = { + .cpu_init = skx_uncore_cpu_init, + .pci_init = skx_uncore_pci_init, +}; + static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init), @@ -1343,6 +1351,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init), {}, }; diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 78b9c23e2d8d..ad986c1e29bc 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -44,6 +44,7 @@ struct intel_uncore_type { unsigned perf_ctr; unsigned event_ctl; unsigned event_mask; + unsigned event_mask_ext; unsigned fixed_ctr; unsigned fixed_ctl; unsigned box_ctl; @@ -120,6 +121,7 @@ struct intel_uncore_box { }; #define UNCORE_BOX_FLAG_INITIATED 0 +#define UNCORE_BOX_FLAG_CTL_OFFS8 1 /* event config registers are 8-byte apart */ struct uncore_event_desc { struct kobj_attribute attr; @@ -172,6 +174,9 @@ static inline unsigned uncore_pci_fixed_ctr(struct intel_uncore_box *box) static inline unsigned uncore_pci_event_ctl(struct intel_uncore_box *box, int idx) { + if (test_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags)) + return idx * 8 + box->pmu->type->event_ctl; + return idx * 4 + box->pmu->type->event_ctl; } @@ -377,6 +382,8 @@ int bdx_uncore_pci_init(void); void bdx_uncore_cpu_init(void); int knl_uncore_pci_init(void); void knl_uncore_cpu_init(void); +int skx_uncore_pci_init(void); +void skx_uncore_cpu_init(void); /* perf_event_intel_uncore_nhmex.c */ void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 9d35ec0cb8fc..5f845eef9a4d 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -388,6 +388,8 @@ static int snb_uncore_imc_event_init(struct perf_event *event) event->cpu = box->cpu; event->pmu_private = box; + event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG; + event->hw.idx = -1; event->hw.last_tag = ~0ULL; event->hw.extra_reg.idx = EXTRA_REG_NONE; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 8aee83bcf71f..272427700d48 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1,6 +1,10 @@ /* SandyBridge-EP/IvyTown uncore support */ #include "uncore.h" +/* SNB-EP pci bus to socket mapping */ +#define SNBEP_CPUNODEID 0x40 +#define SNBEP_GIDNIDMAP 0x54 + /* SNB-EP Box level control */ #define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0) #define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1) @@ -264,15 +268,72 @@ SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) +/* SKX pci bus to socket mapping */ +#define SKX_CPUNODEID 0xc0 +#define SKX_GIDNIDMAP 0xd4 + +/* SKX CHA */ +#define SKX_CHA_MSR_PMON_BOX_FILTER_TID (0x1ffULL << 0) +#define SKX_CHA_MSR_PMON_BOX_FILTER_LINK (0xfULL << 9) +#define SKX_CHA_MSR_PMON_BOX_FILTER_STATE (0x3ffULL << 17) +#define SKX_CHA_MSR_PMON_BOX_FILTER_REM (0x1ULL << 32) +#define SKX_CHA_MSR_PMON_BOX_FILTER_LOC (0x1ULL << 33) +#define SKX_CHA_MSR_PMON_BOX_FILTER_ALL_OPC (0x1ULL << 35) +#define SKX_CHA_MSR_PMON_BOX_FILTER_NM (0x1ULL << 36) +#define SKX_CHA_MSR_PMON_BOX_FILTER_NOT_NM (0x1ULL << 37) +#define SKX_CHA_MSR_PMON_BOX_FILTER_OPC0 (0x3ffULL << 41) +#define SKX_CHA_MSR_PMON_BOX_FILTER_OPC1 (0x3ffULL << 51) +#define SKX_CHA_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61) +#define SKX_CHA_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62) +#define SKX_CHA_MSR_PMON_BOX_FILTER_ISOC (0x1ULL << 63) + +/* SKX IIO */ +#define SKX_IIO0_MSR_PMON_CTL0 0xa48 +#define SKX_IIO0_MSR_PMON_CTR0 0xa41 +#define SKX_IIO0_MSR_PMON_BOX_CTL 0xa40 +#define SKX_IIO_MSR_OFFSET 0x20 + +#define SKX_PMON_CTL_TRESH_MASK (0xff << 24) +#define SKX_PMON_CTL_TRESH_MASK_EXT (0xf) +#define SKX_PMON_CTL_CH_MASK (0xff << 4) +#define SKX_PMON_CTL_FC_MASK (0x7 << 12) +#define SKX_IIO_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_INVERT | \ + SKX_PMON_CTL_TRESH_MASK) +#define SKX_IIO_PMON_RAW_EVENT_MASK_EXT (SKX_PMON_CTL_TRESH_MASK_EXT | \ + SKX_PMON_CTL_CH_MASK | \ + SKX_PMON_CTL_FC_MASK) + +/* SKX IRP */ +#define SKX_IRP0_MSR_PMON_CTL0 0xa5b +#define SKX_IRP0_MSR_PMON_CTR0 0xa59 +#define SKX_IRP0_MSR_PMON_BOX_CTL 0xa58 +#define SKX_IRP_MSR_OFFSET 0x20 + +/* SKX UPI */ +#define SKX_UPI_PCI_PMON_CTL0 0x350 +#define SKX_UPI_PCI_PMON_CTR0 0x318 +#define SKX_UPI_PCI_PMON_BOX_CTL 0x378 +#define SKX_PMON_CTL_UMASK_EXT 0xff + +/* SKX M2M */ +#define SKX_M2M_PCI_PMON_CTL0 0x228 +#define SKX_M2M_PCI_PMON_CTR0 0x200 +#define SKX_M2M_PCI_PMON_BOX_CTL 0x258 + DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6"); DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-39"); DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(thresh9, thresh, "config:24-35"); DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); DEFINE_UNCORE_FORMAT_ATTR(thresh6, thresh, "config:24-29"); DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); @@ -280,6 +341,8 @@ DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31"); +DEFINE_UNCORE_FORMAT_ATTR(ch_mask, ch_mask, "config:36-43"); +DEFINE_UNCORE_FORMAT_ATTR(fc_mask, fc_mask, "config:44-46"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5"); @@ -288,18 +351,26 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5"); DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_link3, filter_link, "config1:12"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link4, filter_link, "config1:9-12"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23"); DEFINE_UNCORE_FORMAT_ATTR(filter_state4, filter_state, "config1:18-20"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state5, filter_state, "config1:17-26"); +DEFINE_UNCORE_FORMAT_ATTR(filter_rem, filter_rem, "config1:32"); +DEFINE_UNCORE_FORMAT_ATTR(filter_loc, filter_loc, "config1:33"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nm, filter_nm, "config1:36"); +DEFINE_UNCORE_FORMAT_ATTR(filter_not_nm, filter_not_nm, "config1:37"); DEFINE_UNCORE_FORMAT_ATTR(filter_local, filter_local, "config1:33"); DEFINE_UNCORE_FORMAT_ATTR(filter_all_op, filter_all_op, "config1:35"); DEFINE_UNCORE_FORMAT_ATTR(filter_nnm, filter_nnm, "config1:37"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc3, filter_opc, "config1:41-60"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc_0, filter_opc0, "config1:41-50"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc_1, filter_opc1, "config1:51-60"); DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62"); DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61"); DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63"); @@ -1153,7 +1224,7 @@ static struct pci_driver snbep_uncore_pci_driver = { /* * build pci bus to socket mapping */ -static int snbep_pci2phy_map_init(int devid) +static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool reverse) { struct pci_dev *ubox_dev = NULL; int i, bus, nodeid, segment; @@ -1168,12 +1239,12 @@ static int snbep_pci2phy_map_init(int devid) break; bus = ubox_dev->bus->number; /* get the Node ID of the local register */ - err = pci_read_config_dword(ubox_dev, 0x40, &config); + err = pci_read_config_dword(ubox_dev, nodeid_loc, &config); if (err) break; nodeid = config; /* get the Node ID mapping */ - err = pci_read_config_dword(ubox_dev, 0x54, &config); + err = pci_read_config_dword(ubox_dev, idmap_loc, &config); if (err) break; @@ -1207,11 +1278,20 @@ static int snbep_pci2phy_map_init(int devid) raw_spin_lock(&pci2phy_map_lock); list_for_each_entry(map, &pci2phy_map_head, list) { i = -1; - for (bus = 255; bus >= 0; bus--) { - if (map->pbus_to_physid[bus] >= 0) - i = map->pbus_to_physid[bus]; - else - map->pbus_to_physid[bus] = i; + if (reverse) { + for (bus = 255; bus >= 0; bus--) { + if (map->pbus_to_physid[bus] >= 0) + i = map->pbus_to_physid[bus]; + else + map->pbus_to_physid[bus] = i; + } + } else { + for (bus = 0; bus <= 255; bus++) { + if (map->pbus_to_physid[bus] >= 0) + i = map->pbus_to_physid[bus]; + else + map->pbus_to_physid[bus] = i; + } } } raw_spin_unlock(&pci2phy_map_lock); @@ -1224,7 +1304,7 @@ static int snbep_pci2phy_map_init(int devid) int snbep_uncore_pci_init(void) { - int ret = snbep_pci2phy_map_init(0x3ce0); + int ret = snbep_pci2phy_map_init(0x3ce0, SNBEP_CPUNODEID, SNBEP_GIDNIDMAP, true); if (ret) return ret; uncore_pci_uncores = snbep_pci_uncores; @@ -1788,7 +1868,7 @@ static struct pci_driver ivbep_uncore_pci_driver = { int ivbep_uncore_pci_init(void) { - int ret = snbep_pci2phy_map_init(0x0e1e); + int ret = snbep_pci2phy_map_init(0x0e1e, SNBEP_CPUNODEID, SNBEP_GIDNIDMAP, true); if (ret) return ret; uncore_pci_uncores = ivbep_pci_uncores; @@ -2897,7 +2977,7 @@ static struct pci_driver hswep_uncore_pci_driver = { int hswep_uncore_pci_init(void) { - int ret = snbep_pci2phy_map_init(0x2f1e); + int ret = snbep_pci2phy_map_init(0x2f1e, SNBEP_CPUNODEID, SNBEP_GIDNIDMAP, true); if (ret) return ret; uncore_pci_uncores = hswep_pci_uncores; @@ -3186,7 +3266,7 @@ static struct pci_driver bdx_uncore_pci_driver = { int bdx_uncore_pci_init(void) { - int ret = snbep_pci2phy_map_init(0x6f1e); + int ret = snbep_pci2phy_map_init(0x6f1e, SNBEP_CPUNODEID, SNBEP_GIDNIDMAP, true); if (ret) return ret; @@ -3196,3 +3276,525 @@ int bdx_uncore_pci_init(void) } /* end of BDX uncore support */ + +/* SKX uncore support */ + +static struct intel_uncore_type skx_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = HSWEP_U_MSR_PMON_CTR0, + .event_ctl = HSWEP_U_MSR_PMON_CTL0, + .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &ivbep_uncore_msr_ops, + .format_group = &ivbep_uncore_ubox_format_group, +}; + +static struct attribute *skx_uncore_cha_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid4.attr, + &format_attr_filter_link4.attr, + &format_attr_filter_state5.attr, + &format_attr_filter_rem.attr, + &format_attr_filter_loc.attr, + &format_attr_filter_nm.attr, + &format_attr_filter_all_op.attr, + &format_attr_filter_not_nm.attr, + &format_attr_filter_opc_0.attr, + &format_attr_filter_opc_1.attr, + &format_attr_filter_nc.attr, + &format_attr_filter_c6.attr, + &format_attr_filter_isoc.attr, + NULL, +}; + +static struct attribute_group skx_uncore_chabox_format_group = { + .name = "format", + .attrs = skx_uncore_cha_formats_attr, +}; + +static struct event_constraint skx_uncore_chabox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct extra_reg skx_uncore_cha_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x2134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x8134, 0xffff, 0x4), +}; + +static u64 skx_cha_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_LINK; + if (fields & 0x4) + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_STATE; + return mask; +} + +static struct event_constraint * +skx_cha_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, skx_cha_filter_mask); +} + +static int skx_cha_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = skx_uncore_cha_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 + + HSWEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & skx_cha_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static struct intel_uncore_ops skx_uncore_chabox_ops = { + /* There is no frz_en for chabox ctl */ + .init_box = ivbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = hswep_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = skx_cha_hw_config, + .get_constraint = skx_cha_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type skx_uncore_chabox = { + .name = "cha", + .num_counters = 4, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_C0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, + .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = skx_uncore_chabox_constraints, + .ops = &skx_uncore_chabox_ops, + .format_group = &skx_uncore_chabox_format_group, +}; + +static struct attribute *skx_uncore_iio_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh9.attr, + &format_attr_ch_mask.attr, + &format_attr_fc_mask.attr, + NULL, +}; + +static struct attribute_group skx_uncore_iio_format_group = { + .name = "format", + .attrs = skx_uncore_iio_formats_attr, +}; + +static struct event_constraint skx_uncore_iio_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x83, 0x3), + UNCORE_EVENT_CONSTRAINT(0x88, 0xc), + UNCORE_EVENT_CONSTRAINT(0x95, 0xc), + UNCORE_EVENT_CONSTRAINT(0xc0, 0xc), + UNCORE_EVENT_CONSTRAINT(0xc5, 0xc), + UNCORE_EVENT_CONSTRAINT(0xd4, 0xc), + EVENT_CONSTRAINT_END +}; + +static void skx_iio_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops skx_uncore_iio_ops = { + .init_box = ivbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = skx_iio_enable_event, + .read_counter = uncore_msr_read_counter, +}; + +static struct intel_uncore_type skx_uncore_iio = { + .name = "iio", + .num_counters = 4, + .num_boxes = 5, + .perf_ctr_bits = 48, + .event_ctl = SKX_IIO0_MSR_PMON_CTL0, + .perf_ctr = SKX_IIO0_MSR_PMON_CTR0, + .event_mask = SKX_IIO_PMON_RAW_EVENT_MASK, + .event_mask_ext = SKX_IIO_PMON_RAW_EVENT_MASK_EXT, + .box_ctl = SKX_IIO0_MSR_PMON_BOX_CTL, + .msr_offset = SKX_IIO_MSR_OFFSET, + .constraints = skx_uncore_iio_constraints, + .ops = &skx_uncore_iio_ops, + .format_group = &skx_uncore_iio_format_group, +}; + +static struct attribute *skx_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group skx_uncore_format_group = { + .name = "format", + .attrs = skx_uncore_formats_attr, +}; + +static struct intel_uncore_type skx_uncore_irp = { + .name = "irp", + .num_counters = 2, + .num_boxes = 5, + .perf_ctr_bits = 48, + .event_ctl = SKX_IRP0_MSR_PMON_CTL0, + .perf_ctr = SKX_IRP0_MSR_PMON_CTR0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SKX_IRP0_MSR_PMON_BOX_CTL, + .msr_offset = SKX_IRP_MSR_OFFSET, + .ops = &skx_uncore_iio_ops, + .format_group = &skx_uncore_format_group, +}; + +static struct intel_uncore_ops skx_uncore_pcu_ops = { + IVBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = hswep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + +static struct intel_uncore_type skx_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = HSWEP_PCU_MSR_PMON_CTR0, + .event_ctl = HSWEP_PCU_MSR_PMON_CTL0, + .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &skx_uncore_pcu_ops, + .format_group = &snbep_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *skx_msr_uncores[] = { + &skx_uncore_ubox, + &skx_uncore_chabox, + &skx_uncore_iio, + &skx_uncore_irp, + &skx_uncore_pcu, + NULL, +}; + +static int skx_count_chabox(void) +{ + struct pci_dev *chabox_dev = NULL; + int bus, count = 0; + + while (1) { + chabox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x208d, chabox_dev); + if (!chabox_dev) + break; + if (count == 0) + bus = chabox_dev->bus->number; + if (bus != chabox_dev->bus->number) + break; + count++; + } + + pci_dev_put(chabox_dev); + return count; +} + +void skx_uncore_cpu_init(void) +{ + skx_uncore_chabox.num_boxes = skx_count_chabox(); + uncore_msr_uncores = skx_msr_uncores; +} + +static struct intel_uncore_type skx_uncore_imc = { + .name = "imc", + .num_counters = 4, + .num_boxes = 6, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = hswep_uncore_imc_events, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &ivbep_uncore_pci_ops, + .format_group = &skx_uncore_format_group, +}; + +static struct attribute *skx_upi_uncore_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_umask_ext.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group skx_upi_uncore_format_group = { + .name = "format", + .attrs = skx_upi_uncore_formats_attr, +}; + +static void skx_upi_uncore_pci_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + + __set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags); + pci_write_config_dword(pdev, SKX_UPI_PCI_PMON_BOX_CTL, IVBEP_PMON_BOX_CTL_INT); +} + +static struct intel_uncore_ops skx_upi_uncore_pci_ops = { + .init_box = skx_upi_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_uncore_pci_enable_event, + .read_counter = snbep_uncore_pci_read_counter, +}; + +static struct intel_uncore_type skx_uncore_upi = { + .name = "upi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SKX_UPI_PCI_PMON_CTR0, + .event_ctl = SKX_UPI_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .event_mask_ext = SKX_PMON_CTL_UMASK_EXT, + .box_ctl = SKX_UPI_PCI_PMON_BOX_CTL, + .ops = &skx_upi_uncore_pci_ops, + .format_group = &skx_upi_uncore_format_group, +}; + +static void skx_m2m_uncore_pci_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + + __set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags); + pci_write_config_dword(pdev, SKX_M2M_PCI_PMON_BOX_CTL, IVBEP_PMON_BOX_CTL_INT); +} + +static struct intel_uncore_ops skx_m2m_uncore_pci_ops = { + .init_box = skx_m2m_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_uncore_pci_enable_event, + .read_counter = snbep_uncore_pci_read_counter, +}; + +static struct intel_uncore_type skx_uncore_m2m = { + .name = "m2m", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .perf_ctr = SKX_M2M_PCI_PMON_CTR0, + .event_ctl = SKX_M2M_PCI_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SKX_M2M_PCI_PMON_BOX_CTL, + .ops = &skx_m2m_uncore_pci_ops, + .format_group = &skx_uncore_format_group, +}; + +static struct event_constraint skx_uncore_m2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type skx_uncore_m2pcie = { + .name = "m2pcie", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .constraints = skx_uncore_m2pcie_constraints, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &ivbep_uncore_pci_ops, + .format_group = &skx_uncore_format_group, +}; + +static struct event_constraint skx_uncore_m3upi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x1d, 0x1), + UNCORE_EVENT_CONSTRAINT(0x1e, 0x1), + UNCORE_EVENT_CONSTRAINT(0x40, 0x7), + UNCORE_EVENT_CONSTRAINT(0x4e, 0x7), + UNCORE_EVENT_CONSTRAINT(0x4f, 0x7), + UNCORE_EVENT_CONSTRAINT(0x50, 0x7), + UNCORE_EVENT_CONSTRAINT(0x51, 0x7), + UNCORE_EVENT_CONSTRAINT(0x52, 0x7), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type skx_uncore_m3upi = { + .name = "m3upi", + .num_counters = 3, + .num_boxes = 3, + .perf_ctr_bits = 48, + .constraints = skx_uncore_m3upi_constraints, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &ivbep_uncore_pci_ops, + .format_group = &skx_uncore_format_group, +}; + +enum { + SKX_PCI_UNCORE_IMC, + SKX_PCI_UNCORE_M2M, + SKX_PCI_UNCORE_UPI, + SKX_PCI_UNCORE_M2PCIE, + SKX_PCI_UNCORE_M3UPI, +}; + +static struct intel_uncore_type *skx_pci_uncores[] = { + [SKX_PCI_UNCORE_IMC] = &skx_uncore_imc, + [SKX_PCI_UNCORE_M2M] = &skx_uncore_m2m, + [SKX_PCI_UNCORE_UPI] = &skx_uncore_upi, + [SKX_PCI_UNCORE_M2PCIE] = &skx_uncore_m2pcie, + [SKX_PCI_UNCORE_M3UPI] = &skx_uncore_m3upi, + NULL, +}; + +static const struct pci_device_id skx_uncore_pci_ids[] = { + { /* MC0 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2042), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(10, 2, SKX_PCI_UNCORE_IMC, 0), + }, + { /* MC0 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2046), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(10, 6, SKX_PCI_UNCORE_IMC, 1), + }, + { /* MC0 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204a), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(11, 2, SKX_PCI_UNCORE_IMC, 2), + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2042), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 2, SKX_PCI_UNCORE_IMC, 3), + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2046), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 6, SKX_PCI_UNCORE_IMC, 4), + }, + { /* MC1 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204a), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(13, 2, SKX_PCI_UNCORE_IMC, 5), + }, + { /* M2M0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2066), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(8, 0, SKX_PCI_UNCORE_M2M, 0), + }, + { /* M2M1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2066), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(9, 0, SKX_PCI_UNCORE_M2M, 1), + }, + { /* UPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2058), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(14, 0, SKX_PCI_UNCORE_UPI, 0), + }, + { /* UPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2058), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(15, 0, SKX_PCI_UNCORE_UPI, 1), + }, + { /* UPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2058), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(16, 0, SKX_PCI_UNCORE_UPI, 2), + }, + { /* M2PCIe 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2088), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 1, SKX_PCI_UNCORE_M2PCIE, 0), + }, + { /* M2PCIe 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2088), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(22, 1, SKX_PCI_UNCORE_M2PCIE, 1), + }, + { /* M2PCIe 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2088), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(23, 1, SKX_PCI_UNCORE_M2PCIE, 2), + }, + { /* M2PCIe 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2088), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3), + }, + { /* M3UPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0), + }, + { /* M3UPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1), + }, + { /* M3UPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2), + }, + { /* end: all zeroes */ } +}; + + +static struct pci_driver skx_uncore_pci_driver = { + .name = "skx_uncore", + .id_table = skx_uncore_pci_ids, +}; + +int skx_uncore_pci_init(void) +{ + /* need to double check pci address */ + int ret = snbep_pci2phy_map_init(0x2014, SKX_CPUNODEID, SKX_GIDNIDMAP, false); + + if (ret) + return ret; + + uncore_pci_uncores = skx_pci_uncores; + uncore_pci_driver = &skx_uncore_pci_driver; + return 0; +} + +/* end of SKX uncore support */ diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 8c4a47706296..5874d8de1f8d 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -194,12 +194,13 @@ struct cpu_hw_events { */ struct debug_store *ds; u64 pebs_enabled; + int n_pebs; + int n_large_pebs; /* * Intel LBR bits */ int lbr_users; - void *lbr_context; struct perf_branch_stack lbr_stack; struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; struct er_account *lbr_sel; @@ -508,6 +509,8 @@ struct x86_pmu { void (*enable_all)(int added); void (*enable)(struct perf_event *); void (*disable)(struct perf_event *); + void (*add)(struct perf_event *); + void (*del)(struct perf_event *); int (*hw_config)(struct perf_event *event); int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); unsigned eventsel; @@ -888,6 +891,10 @@ extern struct event_constraint intel_skl_pebs_event_constraints[]; struct event_constraint *intel_pebs_constraints(struct perf_event *event); +void intel_pmu_pebs_add(struct perf_event *event); + +void intel_pmu_pebs_del(struct perf_event *event); + void intel_pmu_pebs_enable(struct perf_event *event); void intel_pmu_pebs_disable(struct perf_event *event); @@ -906,9 +913,9 @@ u64 lbr_from_signext_quirk_wr(u64 val); void intel_pmu_lbr_reset(void); -void intel_pmu_lbr_enable(struct perf_event *event); +void intel_pmu_lbr_add(struct perf_event *event); -void intel_pmu_lbr_disable(struct perf_event *event); +void intel_pmu_lbr_del(struct perf_event *event); void intel_pmu_lbr_enable_all(bool pmi); diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 2f29f4e407c3..cb13c0564ea7 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -378,7 +378,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode); } put_user_catch(err); - err |= copy_siginfo_to_user32(&frame->info, &ksig->info); + err |= __copy_siginfo_to_user32(&frame->info, &ksig->info, false); err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate, regs, set->sig[0]); err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index e77a6443104f..1b020381ab38 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -217,10 +217,14 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \ output, input...) \ +{ \ + register void *__sp asm(_ASM_SP); \ asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\ "call %P[new2]", feature2) \ - : output : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ - [new2] "i" (newfunc2), ## input) + : output, "+r" (__sp) \ + : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ + [new2] "i" (newfunc2), ## input); \ +} /* * use this macro(s) if you need more than one output parameter diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 124357773ffa..f5aaf6c83222 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -650,8 +650,8 @@ static inline void entering_ack_irq(void) static inline void ipi_entering_ack_irq(void) { - ack_APIC_irq(); irq_enter(); + ack_APIC_irq(); } static inline void exiting_irq(void) @@ -661,9 +661,8 @@ static inline void exiting_irq(void) static inline void exiting_ack_irq(void) { - irq_exit(); - /* Ack only at the end to avoid potential reentry */ ack_APIC_irq(); + irq_exit(); } extern void ioapic_zap_locks(void); diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index 9733361fed6f..97848cdfcb1a 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -158,53 +158,9 @@ extern void __add_wrong_size(void) * value of "*ptr". * * xadd() is locked when multiple CPUs are online - * xadd_sync() is always locked - * xadd_local() is never locked */ #define __xadd(ptr, inc, lock) __xchg_op((ptr), (inc), xadd, lock) #define xadd(ptr, inc) __xadd((ptr), (inc), LOCK_PREFIX) -#define xadd_sync(ptr, inc) __xadd((ptr), (inc), "lock; ") -#define xadd_local(ptr, inc) __xadd((ptr), (inc), "") - -#define __add(ptr, inc, lock) \ - ({ \ - __typeof__ (*(ptr)) __ret = (inc); \ - switch (sizeof(*(ptr))) { \ - case __X86_CASE_B: \ - asm volatile (lock "addb %b1, %0\n" \ - : "+m" (*(ptr)) : "qi" (inc) \ - : "memory", "cc"); \ - break; \ - case __X86_CASE_W: \ - asm volatile (lock "addw %w1, %0\n" \ - : "+m" (*(ptr)) : "ri" (inc) \ - : "memory", "cc"); \ - break; \ - case __X86_CASE_L: \ - asm volatile (lock "addl %1, %0\n" \ - : "+m" (*(ptr)) : "ri" (inc) \ - : "memory", "cc"); \ - break; \ - case __X86_CASE_Q: \ - asm volatile (lock "addq %1, %0\n" \ - : "+m" (*(ptr)) : "ri" (inc) \ - : "memory", "cc"); \ - break; \ - default: \ - __add_wrong_size(); \ - } \ - __ret; \ - }) - -/* - * add_*() adds "inc" to "*ptr" - * - * __add() takes a lock prefix - * add_smp() is locked when multiple CPUs are online - * add_sync() is always locked - */ -#define add_smp(ptr, inc) __add((ptr), (inc), LOCK_PREFIX) -#define add_sync(ptr, inc) __add((ptr), (inc), "lock; ") #define __cmpxchg_double(pfx, p1, p2, o1, o2, n1, n2) \ ({ \ diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index a18806165fe4..03d269bed941 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -275,10 +275,10 @@ struct compat_shmid64_ds { #ifdef CONFIG_X86_X32_ABI typedef struct user_regs_struct compat_elf_gregset_t; -#define PR_REG_SIZE(S) (test_thread_flag(TIF_IA32) ? 68 : 216) -#define PRSTATUS_SIZE(S) (test_thread_flag(TIF_IA32) ? 144 : 296) -#define SET_PR_FPVALID(S,V) \ - do { *(int *) (((void *) &((S)->pr_reg)) + PR_REG_SIZE(0)) = (V); } \ +/* Full regset -- prstatus on x32, otherwise on ia32 */ +#define PRSTATUS_SIZE(S, R) (R != sizeof(S.pr_reg) ? 144 : 296) +#define SET_PR_FPVALID(S, V, R) \ + do { *(int *) (((void *) &((S)->pr_reg)) + R) = (V); } \ while (0) #define COMPAT_USE_64BIT_TIME \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 92a8308b96f6..1188bc849ee3 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -106,7 +106,6 @@ #define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ #define X86_FEATURE_EAGER_FPU ( 3*32+29) /* "eagerfpu" Non lazy FPU restore */ #define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ -#define X86_FEATURE_MCE_RECOVERY ( 3*32+31) /* cpu has recoverable machine checks */ /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ #define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 4e10d73cf018..12080d87da3b 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -36,7 +36,7 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in extern struct desc_ptr idt_descr; extern gate_desc idt_table[]; -extern struct desc_ptr debug_idt_descr; +extern const struct desc_ptr debug_idt_descr; extern gate_desc debug_idt_table[]; struct gdt_page { diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 3ab0537872fb..476b574de99e 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -10,8 +10,8 @@ #include <uapi/asm/e820.h> #ifndef __ASSEMBLY__ /* see comment in arch/x86/kernel/e820.c */ -extern struct e820map e820; -extern struct e820map e820_saved; +extern struct e820map *e820; +extern struct e820map *e820_saved; extern unsigned long pci_mem_start; extern int e820_any_mapped(u64 start, u64 end, unsigned type); @@ -53,6 +53,8 @@ extern void e820_reserve_resources_late(void); extern void setup_memory_map(void); extern char *default_machine_specific_memory_setup(void); +extern void e820_reallocate_tables(void); + /* * Returns true iff the specified range [s,e) is completely contained inside * the ISA region. diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index d0bb76d81402..389d700b961e 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -117,7 +117,6 @@ extern int __init efi_memblock_x86_reserve_range(void); extern pgd_t * __init efi_call_phys_prolog(void); extern void __init efi_call_phys_epilog(pgd_t *save_pgd); extern void __init efi_print_memmap(void); -extern void __init efi_unmap_memmap(void); extern void __init efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); extern void __init efi_map_region_fixed(efi_memory_desc_t *md); @@ -192,14 +191,7 @@ static inline efi_status_t efi_thunk_set_virtual_address_map( struct efi_config { u64 image_handle; u64 table; - u64 allocate_pool; - u64 allocate_pages; - u64 get_memory_map; - u64 free_pool; - u64 free_pages; - u64 locate_handle; - u64 handle_protocol; - u64 exit_boot_services; + u64 boot_services; u64 text_output; efi_status_t (*call)(unsigned long, ...); bool is64; @@ -207,14 +199,27 @@ struct efi_config { __pure const struct efi_config *__efi_early(void); +static inline bool efi_is_64bit(void) +{ + if (!IS_ENABLED(CONFIG_X86_64)) + return false; + + if (!IS_ENABLED(CONFIG_EFI_MIXED)) + return true; + + return __efi_early()->is64; +} + #define efi_call_early(f, ...) \ - __efi_early()->call(__efi_early()->f, __VA_ARGS__); + __efi_early()->call(efi_is_64bit() ? \ + ((efi_boot_services_64_t *)(unsigned long) \ + __efi_early()->boot_services)->f : \ + ((efi_boot_services_32_t *)(unsigned long) \ + __efi_early()->boot_services)->f, __VA_ARGS__) #define __efi_call_early(f, ...) \ __efi_early()->call((unsigned long)f, __VA_ARGS__); -#define efi_is_64bit() __efi_early()->is64 - extern bool efi_reboot_required(void); #else diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h index 0e970d00dfcd..20a1fbf7fe4e 100644 --- a/arch/x86/include/asm/fpu/signal.h +++ b/arch/x86/include/asm/fpu/signal.h @@ -19,6 +19,12 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, # define ia32_setup_rt_frame __setup_rt_frame #endif +#ifdef CONFIG_COMPAT +int __copy_siginfo_to_user32(compat_siginfo_t __user *to, + const siginfo_t *from, bool x32_ABI); +#endif + + extern void convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk); extern void convert_to_fxsr(struct task_struct *tsk, diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index ae55a43e09c0..d4957ac72b48 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -45,7 +45,8 @@ extern u64 xfeatures_mask; extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; -extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); +extern void __init update_regset_xstate_info(unsigned int size, + u64 xstate_mask); void fpu__xstate_clear_all_cpu_caps(void); void *get_xsave_addr(struct xregs_state *xsave, int xstate); diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index a4820d4df617..eccd0ac6bc38 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -6,6 +6,7 @@ # define MCOUNT_ADDR ((unsigned long)(__fentry__)) #else # define MCOUNT_ADDR ((unsigned long)(mcount)) +# define HAVE_FUNCTION_GRAPH_FP_TEST #endif #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ @@ -13,6 +14,8 @@ #define ARCH_SUPPORTS_FTRACE_OPS 1 #endif +#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR + #ifndef __ASSEMBLY__ extern void mcount(void); extern atomic_t modifying_ftrace_code; diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 055ea9941dd5..67942b6ad4b7 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -43,6 +43,9 @@ struct hypervisor_x86 { /* X2APIC detection (run once per boot) */ bool (*x2apic_available)(void); + + /* pin current vcpu to specified physical cpu (run rarely) */ + void (*pin_vcpu)(int); }; extern const struct hypervisor_x86 *x86_hyper; @@ -56,6 +59,7 @@ extern const struct hypervisor_x86 x86_hyper_kvm; extern void init_hypervisor(struct cpuinfo_x86 *c); extern void init_hypervisor_platform(void); extern bool hypervisor_x2apic_available(void); +extern void hypervisor_pin_vcpu(int cpu); #else static inline void init_hypervisor(struct cpuinfo_x86 *c) { } static inline void init_hypervisor_platform(void) { } diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 627719475457..9ae5ab80a497 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -56,8 +56,8 @@ #define INTEL_FAM6_ATOM_SILVERMONT1 0x37 /* BayTrail/BYT / Valleyview */ #define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */ #define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */ -#define INTEL_FAM6_ATOM_MERRIFIELD1 0x4A /* Tangier */ -#define INTEL_FAM6_ATOM_MERRIFIELD2 0x5A /* Annidale */ +#define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */ +#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Annidale */ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C #define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */ diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h index 9d6b097aa73d..5b6753d1f7f4 100644 --- a/arch/x86/include/asm/intel-mid.h +++ b/arch/x86/include/asm/intel-mid.h @@ -18,6 +18,8 @@ extern int intel_mid_pci_init(void); extern int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state); +extern void intel_mid_pwr_power_off(void); + #define INTEL_MID_PWR_LSS_OFFSET 4 #define INTEL_MID_PWR_LSS_TYPE (1 << 7) diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h index 925b605eb5c6..4fb1d0abef95 100644 --- a/arch/x86/include/asm/intel_scu_ipc.h +++ b/arch/x86/include/asm/intel_scu_ipc.h @@ -3,6 +3,8 @@ #include <linux/notifier.h> +#define IPCMSG_COLD_OFF 0x80 /* Only for Tangier */ + #define IPCMSG_WARM_RESET 0xF0 #define IPCMSG_COLD_RESET 0xF1 #define IPCMSG_SOFT_RESET 0xF2 diff --git a/arch/x86/include/asm/kaslr.h b/arch/x86/include/asm/kaslr.h index 2674ee3de748..1052a797d71d 100644 --- a/arch/x86/include/asm/kaslr.h +++ b/arch/x86/include/asm/kaslr.h @@ -6,6 +6,7 @@ unsigned long kaslr_get_random_long(const char *purpose); #ifdef CONFIG_RANDOMIZE_MEMORY extern unsigned long page_offset_base; extern unsigned long vmalloc_base; +extern unsigned long vmemmap_base; void kernel_randomize_memory(void); #else diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 1ef9d581b5d9..d31881188431 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -24,8 +24,6 @@ enum die_val { extern void printk_address(unsigned long address); extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); -extern void show_trace(struct task_struct *t, struct pt_regs *regs, - unsigned long *sp, unsigned long bp); extern void show_stack_regs(struct pt_regs *regs); extern void __show_regs(struct pt_regs *regs, int all); extern unsigned long oops_begin(void); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 33ae3a4d0159..4b20f7304b9c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -568,6 +568,7 @@ struct kvm_vcpu_arch { struct kvm_steal_time steal; } st; + u64 tsc_offset; u64 last_guest_tsc; u64 last_host_tsc; u64 tsc_offset_adjustment; @@ -701,6 +702,8 @@ struct kvm_hv { /* Hyper-v based guest crash (NT kernel bugcheck) parameters */ u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS]; u64 hv_crash_ctl; + + HV_REFERENCE_TSC_PAGE tsc_ref; }; struct kvm_arch { @@ -781,54 +784,56 @@ struct kvm_arch { bool disabled_lapic_found; /* Struct members for AVIC */ + u32 avic_vm_id; u32 ldr_mode; struct page *avic_logical_id_table_page; struct page *avic_physical_id_table_page; + struct hlist_node hnode; bool x2apic_format; bool x2apic_broadcast_quirk_disabled; }; struct kvm_vm_stat { - u32 mmu_shadow_zapped; - u32 mmu_pte_write; - u32 mmu_pte_updated; - u32 mmu_pde_zapped; - u32 mmu_flooded; - u32 mmu_recycled; - u32 mmu_cache_miss; - u32 mmu_unsync; - u32 remote_tlb_flush; - u32 lpages; + ulong mmu_shadow_zapped; + ulong mmu_pte_write; + ulong mmu_pte_updated; + ulong mmu_pde_zapped; + ulong mmu_flooded; + ulong mmu_recycled; + ulong mmu_cache_miss; + ulong mmu_unsync; + ulong remote_tlb_flush; + ulong lpages; }; struct kvm_vcpu_stat { - u32 pf_fixed; - u32 pf_guest; - u32 tlb_flush; - u32 invlpg; - - u32 exits; - u32 io_exits; - u32 mmio_exits; - u32 signal_exits; - u32 irq_window_exits; - u32 nmi_window_exits; - u32 halt_exits; - u32 halt_successful_poll; - u32 halt_attempted_poll; - u32 halt_poll_invalid; - u32 halt_wakeup; - u32 request_irq_exits; - u32 irq_exits; - u32 host_state_reload; - u32 efer_reload; - u32 fpu_reload; - u32 insn_emulation; - u32 insn_emulation_fail; - u32 hypercalls; - u32 irq_injections; - u32 nmi_injections; + u64 pf_fixed; + u64 pf_guest; + u64 tlb_flush; + u64 invlpg; + + u64 exits; + u64 io_exits; + u64 mmio_exits; + u64 signal_exits; + u64 irq_window_exits; + u64 nmi_window_exits; + u64 halt_exits; + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_poll_invalid; + u64 halt_wakeup; + u64 request_irq_exits; + u64 irq_exits; + u64 host_state_reload; + u64 efer_reload; + u64 fpu_reload; + u64 insn_emulation; + u64 insn_emulation_fail; + u64 hypercalls; + u64 irq_injections; + u64 nmi_injections; }; struct x86_instruction_info; @@ -951,7 +956,6 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); - u64 (*read_tsc_offset)(struct kvm_vcpu *vcpu); void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu, u64 host_tsc); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 8bf766ef0e18..9bd7ff5ffbcc 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -40,9 +40,10 @@ #define MCI_STATUS_AR (1ULL<<55) /* Action required */ /* AMD-specific bits */ +#define MCI_STATUS_TCC (1ULL<<55) /* Task context corrupt */ +#define MCI_STATUS_SYNDV (1ULL<<53) /* synd reg. valid */ #define MCI_STATUS_DEFERRED (1ULL<<44) /* uncorrected error, deferred exception */ #define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */ -#define MCI_STATUS_TCC (1ULL<<55) /* Task context corrupt */ /* * McaX field if set indicates a given bank supports MCA extensions: @@ -110,6 +111,7 @@ #define MSR_AMD64_SMCA_MC0_MISC0 0xc0002003 #define MSR_AMD64_SMCA_MC0_CONFIG 0xc0002004 #define MSR_AMD64_SMCA_MC0_IPID 0xc0002005 +#define MSR_AMD64_SMCA_MC0_SYND 0xc0002006 #define MSR_AMD64_SMCA_MC0_DESTAT 0xc0002008 #define MSR_AMD64_SMCA_MC0_DEADDR 0xc0002009 #define MSR_AMD64_SMCA_MC0_MISC1 0xc000200a @@ -119,6 +121,7 @@ #define MSR_AMD64_SMCA_MCx_MISC(x) (MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_CONFIG(x) (MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_IPID(x) (MSR_AMD64_SMCA_MC0_IPID + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_SYND(x) (MSR_AMD64_SMCA_MC0_SYND + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_DESTAT(x) (MSR_AMD64_SMCA_MC0_DESTAT + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_DEADDR(x) (MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x))) @@ -334,44 +337,47 @@ extern void apei_mce_report_mem_error(int corrected, * Scalable MCA. */ #ifdef CONFIG_X86_MCE_AMD -enum amd_ip_types { - SMCA_F17H_CORE = 0, /* Core errors */ - SMCA_DF, /* Data Fabric */ - SMCA_UMC, /* Unified Memory Controller */ - SMCA_PB, /* Parameter Block */ - SMCA_PSP, /* Platform Security Processor */ - SMCA_SMU, /* System Management Unit */ - N_AMD_IP_TYPES -}; - -struct amd_hwid { - const char *name; - unsigned int hwid; -}; - -extern struct amd_hwid amd_hwids[N_AMD_IP_TYPES]; -enum amd_core_mca_blocks { +/* These may be used by multiple smca_hwid_mcatypes */ +enum smca_bank_types { SMCA_LS = 0, /* Load Store */ SMCA_IF, /* Instruction Fetch */ - SMCA_L2_CACHE, /* L2 cache */ - SMCA_DE, /* Decoder unit */ - RES, /* Reserved */ - SMCA_EX, /* Execution unit */ + SMCA_L2_CACHE, /* L2 Cache */ + SMCA_DE, /* Decoder Unit */ + SMCA_EX, /* Execution Unit */ SMCA_FP, /* Floating Point */ - SMCA_L3_CACHE, /* L3 cache */ - N_CORE_MCA_BLOCKS + SMCA_L3_CACHE, /* L3 Cache */ + SMCA_CS, /* Coherent Slave */ + SMCA_PIE, /* Power, Interrupts, etc. */ + SMCA_UMC, /* Unified Memory Controller */ + SMCA_PB, /* Parameter Block */ + SMCA_PSP, /* Platform Security Processor */ + SMCA_SMU, /* System Management Unit */ + N_SMCA_BANK_TYPES }; -extern const char * const amd_core_mcablock_names[N_CORE_MCA_BLOCKS]; +struct smca_bank_name { + const char *name; /* Short name for sysfs */ + const char *long_name; /* Long name for pretty-printing */ +}; + +extern struct smca_bank_name smca_bank_names[N_SMCA_BANK_TYPES]; + +#define HWID_MCATYPE(hwid, mcatype) ((hwid << 16) | mcatype) -enum amd_df_mca_blocks { - SMCA_CS = 0, /* Coherent Slave */ - SMCA_PIE, /* Power management, Interrupts, etc */ - N_DF_BLOCKS +struct smca_hwid_mcatype { + unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */ + u32 hwid_mcatype; /* (hwid,mcatype) tuple */ + u32 xec_bitmap; /* Bitmap of valid ExtErrorCodes; current max is 21. */ }; -extern const char * const amd_df_mcablock_names[N_DF_BLOCKS]; +struct smca_bank_info { + struct smca_hwid_mcatype *type; + u32 type_instance; +}; + +extern struct smca_bank_info smca_banks[MAX_NR_BANKS]; + #endif #endif /* _ASM_X86_MCE_H */ diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index b07233b64578..32007041ef8c 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -6,7 +6,6 @@ #include <asm/x86_init.h> #include <asm/apicdef.h> -extern int apic_version[]; extern int pic_mode; #ifdef CONFIG_X86_32 @@ -40,6 +39,7 @@ extern int mp_bus_id_to_type[MAX_MP_BUSSES]; extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES); extern unsigned int boot_cpu_physical_apicid; +extern u8 boot_cpu_apic_version; extern unsigned long mp_lapic_addr; #ifdef CONFIG_X86_LOCAL_APIC @@ -86,6 +86,7 @@ static inline void early_reserve_e820_mpc_new(void) { } #endif int generic_processor_info(int apicid, int version); +int __generic_processor_info(int apicid, int version, bool enabled); #define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_LOCAL_APIC) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 2970d22d7766..ce932812f142 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -80,10 +80,6 @@ static inline unsigned long __read_cr4(void) { return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4); } -static inline unsigned long __read_cr4_safe(void) -{ - return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4_safe); -} static inline void __write_cr4(unsigned long x) { @@ -661,8 +657,6 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) -#ifdef CONFIG_QUEUED_SPINLOCKS - static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) { @@ -684,22 +678,6 @@ static __always_inline void pv_kick(int cpu) PVOP_VCALL1(pv_lock_ops.kick, cpu); } -#else /* !CONFIG_QUEUED_SPINLOCKS */ - -static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, - __ticket_t ticket) -{ - PVOP_VCALLEE2(pv_lock_ops.lock_spinning, lock, ticket); -} - -static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock, - __ticket_t ticket) -{ - PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket); -} - -#endif /* CONFIG_QUEUED_SPINLOCKS */ - #endif /* SMP && PARAVIRT_SPINLOCKS */ #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 7fa9e7740ba3..0f400c0e4979 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -108,7 +108,6 @@ struct pv_cpu_ops { unsigned long (*read_cr0)(void); void (*write_cr0)(unsigned long); - unsigned long (*read_cr4_safe)(void); unsigned long (*read_cr4)(void); void (*write_cr4)(unsigned long); @@ -301,23 +300,16 @@ struct pv_mmu_ops { struct arch_spinlock; #ifdef CONFIG_SMP #include <asm/spinlock_types.h> -#else -typedef u16 __ticket_t; #endif struct qspinlock; struct pv_lock_ops { -#ifdef CONFIG_QUEUED_SPINLOCKS void (*queued_spin_lock_slowpath)(struct qspinlock *lock, u32 val); struct paravirt_callee_save queued_spin_unlock; void (*wait)(u8 *ptr, u8 val); void (*kick)(int cpu); -#else /* !CONFIG_QUEUED_SPINLOCKS */ - struct paravirt_callee_save lock_spinning; - void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket); -#endif /* !CONFIG_QUEUED_SPINLOCKS */ }; /* This contains all the paravirt structures: we get a convenient diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 9ab7507ca1c2..1411dbed5e5e 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -23,6 +23,9 @@ struct pci_sysdata { #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN void *fwnode; /* IRQ domain for MSI assignment */ #endif +#if IS_ENABLED(CONFIG_VMD) + bool vmd_domain; /* True if in Intel VMD domain */ +#endif }; extern int pci_routeirq; @@ -56,6 +59,17 @@ static inline void *_pci_root_bus_fwnode(struct pci_bus *bus) #define pci_root_bus_fwnode _pci_root_bus_fwnode #endif +static inline bool is_vmd(struct pci_bus *bus) +{ +#if IS_ENABLED(CONFIG_VMD) + struct pci_sysdata *sd = bus->sysdata; + + return sd->vmd_domain; +#else + return false; +#endif +} + /* Can be used to override the logic in pci_scan_bus for skipping already-configured bus numbers - to be used for buggy BIOSes or architectures with incomplete PCI setup by the loader */ diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 6fdef9eef2d5..3a264200c62f 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -57,11 +57,13 @@ typedef struct { pteval_t pte; } pte_t; #define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL) #define VMALLOC_SIZE_TB _AC(32, UL) #define __VMALLOC_BASE _AC(0xffffc90000000000, UL) -#define VMEMMAP_START _AC(0xffffea0000000000, UL) +#define __VMEMMAP_BASE _AC(0xffffea0000000000, UL) #ifdef CONFIG_RANDOMIZE_MEMORY #define VMALLOC_START vmalloc_base +#define VMEMMAP_START vmemmap_base #else #define VMALLOC_START __VMALLOC_BASE +#define VMEMMAP_START __VMEMMAP_BASE #endif /* CONFIG_RANDOMIZE_MEMORY */ #define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL)) #define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h index 643eba42d620..2c1ebeb4d737 100644 --- a/arch/x86/include/asm/pmem.h +++ b/arch/x86/include/asm/pmem.h @@ -46,10 +46,7 @@ static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n) static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n) { - if (static_cpu_has(X86_FEATURE_MCE_RECOVERY)) - return memcpy_mcsafe(dst, src, n); - memcpy(dst, src, n); - return 0; + return memcpy_mcsafe(dst, src, n); } /** diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 63def9537a2d..984a7bf17f6a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -389,9 +389,9 @@ struct thread_struct { unsigned short fsindex; unsigned short gsindex; #endif -#ifdef CONFIG_X86_32 - unsigned long ip; -#endif + + u32 status; /* thread synchronous flags */ + #ifdef CONFIG_X86_64 unsigned long fsbase; unsigned long gsbase; @@ -438,6 +438,15 @@ struct thread_struct { }; /* + * Thread-synchronous status. + * + * This is different from the flags in that nobody else + * ever touches our thread-synchronous status, so we don't + * have to worry about atomic accesses. + */ +#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ + +/* * Set IOPL bits in EFLAGS from given mask */ static inline void native_set_iopl_mask(unsigned mask) @@ -724,8 +733,6 @@ static inline void spin_lock_prefetch(const void *x) .addr_limit = KERNEL_DS, \ } -extern unsigned long thread_saved_pc(struct task_struct *tsk); - /* * TOP_OF_KERNEL_STACK_PADDING reserves 8 bytes on top of the ring0 stack. * This is necessary to guarantee that the entire "struct pt_regs" @@ -776,17 +783,13 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); .addr_limit = KERNEL_DS, \ } -/* - * Return saved PC of a blocked thread. - * What is this good for? it will be always the scheduler or ret_from_fork. - */ -#define thread_saved_pc(t) READ_ONCE_NOCHECK(*(unsigned long *)((t)->thread.sp - 8)) - #define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1) extern unsigned long KSTK_ESP(struct task_struct *task); #endif /* CONFIG_X86_64 */ +extern unsigned long thread_saved_pc(struct task_struct *tsk); + extern void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp); diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index d019f0cc80ec..3ad741b84072 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -87,9 +87,10 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) } static __always_inline -cycle_t __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src) +cycle_t __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, + u64 tsc) { - u64 delta = rdtsc_ordered() - src->tsc_timestamp; + u64 delta = tsc - src->tsc_timestamp; cycle_t offset = pvclock_scale_delta(delta, src->tsc_to_system_mul, src->tsc_shift); return src->system_time + offset; diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index b2988c0ed829..230e1903acf0 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -44,9 +44,9 @@ struct trampoline_header { extern struct real_mode_header *real_mode_header; extern unsigned char real_mode_blob_end[]; -extern unsigned long init_rsp; extern unsigned long initial_code; extern unsigned long initial_gs; +extern unsigned long initial_stack; extern unsigned char real_mode_blob[]; extern unsigned char real_mode_relocs[]; diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index 8dbc762ad132..3d33a719f5c1 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -154,7 +154,7 @@ static inline bool __down_write_trylock(struct rw_semaphore *sem) : "+m" (sem->count), "=&a" (tmp0), "=&r" (tmp1), CC_OUT(e) (result) : "er" (RWSEM_ACTIVE_WRITE_BIAS) - : "memory", "cc"); + : "memory"); return result; } diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index dd1e7d6387ab..8af22be0fe61 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -23,6 +23,10 @@ typedef struct { unsigned long sig[_NSIG_WORDS]; } sigset_t; +/* non-uapi in-kernel SA_FLAGS for those indicates ABI for a signal frame */ +#define SA_IA32_ABI 0x02000000u +#define SA_X32_ABI 0x01000000u + #ifndef CONFIG_COMPAT typedef sigset_t compat_sigset_t; #endif diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index ebd0c164cd4e..19980b36f394 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -39,9 +39,6 @@ DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid); #endif -/* Static state in head.S used to set up a CPU */ -extern unsigned long stack_start; /* Initial stack pointer address */ - struct task_struct; struct smp_ops { diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 587d7914ea4b..19a2224f9e16 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -59,22 +59,19 @@ static inline void native_write_cr3(unsigned long val) static inline unsigned long native_read_cr4(void) { unsigned long val; - asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline unsigned long native_read_cr4_safe(void) -{ - unsigned long val; - /* This could fault if %cr4 does not exist. In x86_64, a cr4 always - * exists, so it will never fail. */ #ifdef CONFIG_X86_32 + /* + * This could fault if CR4 does not exist. Non-existent CR4 + * is functionally equivalent to CR4 == 0. Keep it simple and pretend + * that CR4 == 0 on CPUs that don't have CR4. + */ asm volatile("1: mov %%cr4, %0\n" "2:\n" _ASM_EXTABLE(1b, 2b) : "=r" (val), "=m" (__force_order) : "0" (0)); #else - val = native_read_cr4(); + /* CR4 always exists on x86_64. */ + asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order)); #endif return val; } @@ -182,11 +179,6 @@ static inline unsigned long __read_cr4(void) return native_read_cr4(); } -static inline unsigned long __read_cr4_safe(void) -{ - return native_read_cr4_safe(); -} - static inline void __write_cr4(unsigned long x) { native_write_cr4(x); diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index be0a05913b91..921bea7a2708 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -20,187 +20,13 @@ * (the type definitions are in asm/spinlock_types.h) */ -#ifdef CONFIG_X86_32 -# define LOCK_PTR_REG "a" -#else -# define LOCK_PTR_REG "D" -#endif - -#if defined(CONFIG_X86_32) && (defined(CONFIG_X86_PPRO_FENCE)) -/* - * On PPro SMP, we use a locked operation to unlock - * (PPro errata 66, 92) - */ -# define UNLOCK_LOCK_PREFIX LOCK_PREFIX -#else -# define UNLOCK_LOCK_PREFIX -#endif - /* How long a lock should spin before we consider blocking */ #define SPIN_THRESHOLD (1 << 15) extern struct static_key paravirt_ticketlocks_enabled; static __always_inline bool static_key_false(struct static_key *key); -#ifdef CONFIG_QUEUED_SPINLOCKS #include <asm/qspinlock.h> -#else - -#ifdef CONFIG_PARAVIRT_SPINLOCKS - -static inline void __ticket_enter_slowpath(arch_spinlock_t *lock) -{ - set_bit(0, (volatile unsigned long *)&lock->tickets.head); -} - -#else /* !CONFIG_PARAVIRT_SPINLOCKS */ -static __always_inline void __ticket_lock_spinning(arch_spinlock_t *lock, - __ticket_t ticket) -{ -} -static inline void __ticket_unlock_kick(arch_spinlock_t *lock, - __ticket_t ticket) -{ -} - -#endif /* CONFIG_PARAVIRT_SPINLOCKS */ -static inline int __tickets_equal(__ticket_t one, __ticket_t two) -{ - return !((one ^ two) & ~TICKET_SLOWPATH_FLAG); -} - -static inline void __ticket_check_and_clear_slowpath(arch_spinlock_t *lock, - __ticket_t head) -{ - if (head & TICKET_SLOWPATH_FLAG) { - arch_spinlock_t old, new; - - old.tickets.head = head; - new.tickets.head = head & ~TICKET_SLOWPATH_FLAG; - old.tickets.tail = new.tickets.head + TICKET_LOCK_INC; - new.tickets.tail = old.tickets.tail; - - /* try to clear slowpath flag when there are no contenders */ - cmpxchg(&lock->head_tail, old.head_tail, new.head_tail); - } -} - -static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) -{ - return __tickets_equal(lock.tickets.head, lock.tickets.tail); -} - -/* - * Ticket locks are conceptually two parts, one indicating the current head of - * the queue, and the other indicating the current tail. The lock is acquired - * by atomically noting the tail and incrementing it by one (thus adding - * ourself to the queue and noting our position), then waiting until the head - * becomes equal to the the initial value of the tail. - * - * We use an xadd covering *both* parts of the lock, to increment the tail and - * also load the position of the head, which takes care of memory ordering - * issues and should be optimal for the uncontended case. Note the tail must be - * in the high part, because a wide xadd increment of the low part would carry - * up and contaminate the high part. - */ -static __always_inline void arch_spin_lock(arch_spinlock_t *lock) -{ - register struct __raw_tickets inc = { .tail = TICKET_LOCK_INC }; - - inc = xadd(&lock->tickets, inc); - if (likely(inc.head == inc.tail)) - goto out; - - for (;;) { - unsigned count = SPIN_THRESHOLD; - - do { - inc.head = READ_ONCE(lock->tickets.head); - if (__tickets_equal(inc.head, inc.tail)) - goto clear_slowpath; - cpu_relax(); - } while (--count); - __ticket_lock_spinning(lock, inc.tail); - } -clear_slowpath: - __ticket_check_and_clear_slowpath(lock, inc.head); -out: - barrier(); /* make sure nothing creeps before the lock is taken */ -} - -static __always_inline int arch_spin_trylock(arch_spinlock_t *lock) -{ - arch_spinlock_t old, new; - - old.tickets = READ_ONCE(lock->tickets); - if (!__tickets_equal(old.tickets.head, old.tickets.tail)) - return 0; - - new.head_tail = old.head_tail + (TICKET_LOCK_INC << TICKET_SHIFT); - new.head_tail &= ~TICKET_SLOWPATH_FLAG; - - /* cmpxchg is a full barrier, so nothing can move before it */ - return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail; -} - -static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - if (TICKET_SLOWPATH_FLAG && - static_key_false(¶virt_ticketlocks_enabled)) { - __ticket_t head; - - BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS); - - head = xadd(&lock->tickets.head, TICKET_LOCK_INC); - - if (unlikely(head & TICKET_SLOWPATH_FLAG)) { - head &= ~TICKET_SLOWPATH_FLAG; - __ticket_unlock_kick(lock, (head + TICKET_LOCK_INC)); - } - } else - __add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX); -} - -static inline int arch_spin_is_locked(arch_spinlock_t *lock) -{ - struct __raw_tickets tmp = READ_ONCE(lock->tickets); - - return !__tickets_equal(tmp.tail, tmp.head); -} - -static inline int arch_spin_is_contended(arch_spinlock_t *lock) -{ - struct __raw_tickets tmp = READ_ONCE(lock->tickets); - - tmp.head &= ~TICKET_SLOWPATH_FLAG; - return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC; -} -#define arch_spin_is_contended arch_spin_is_contended - -static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock, - unsigned long flags) -{ - arch_spin_lock(lock); -} - -static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) -{ - __ticket_t head = READ_ONCE(lock->tickets.head); - - for (;;) { - struct __raw_tickets tmp = READ_ONCE(lock->tickets); - /* - * We need to check "unlocked" in a loop, tmp.head == head - * can be false positive because of overflow. - */ - if (__tickets_equal(tmp.head, tmp.tail) || - !__tickets_equal(tmp.head, head)) - break; - - cpu_relax(); - } -} -#endif /* CONFIG_QUEUED_SPINLOCKS */ /* * Read-write spinlocks, allowing multiple readers diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index 65c3e37f879a..25311ebb446c 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -23,20 +23,7 @@ typedef u32 __ticketpair_t; #define TICKET_SHIFT (sizeof(__ticket_t) * 8) -#ifdef CONFIG_QUEUED_SPINLOCKS #include <asm-generic/qspinlock_types.h> -#else -typedef struct arch_spinlock { - union { - __ticketpair_t head_tail; - struct __raw_tickets { - __ticket_t head, tail; - } tickets; - }; -} arch_spinlock_t; - -#define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } } -#endif /* CONFIG_QUEUED_SPINLOCKS */ #include <asm-generic/qrwlock_types.h> diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 0944218af9e2..37f2e0b377ad 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -8,86 +8,86 @@ #include <linux/uaccess.h> #include <linux/ptrace.h> +#include <asm/switch_to.h> + +enum stack_type { + STACK_TYPE_UNKNOWN, + STACK_TYPE_TASK, + STACK_TYPE_IRQ, + STACK_TYPE_SOFTIRQ, + STACK_TYPE_EXCEPTION, + STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1, +}; -extern int kstack_depth_to_print; - -struct thread_info; -struct stacktrace_ops; - -typedef unsigned long (*walk_stack_t)(struct task_struct *task, - unsigned long *stack, - unsigned long bp, - const struct stacktrace_ops *ops, - void *data, - unsigned long *end, - int *graph); - -extern unsigned long -print_context_stack(struct task_struct *task, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data, - unsigned long *end, int *graph); - -extern unsigned long -print_context_stack_bp(struct task_struct *task, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data, - unsigned long *end, int *graph); - -/* Generic stack tracer with callbacks */ - -struct stacktrace_ops { - int (*address)(void *data, unsigned long address, int reliable); - /* On negative return stop dumping */ - int (*stack)(void *data, char *name); - walk_stack_t walk_stack; +struct stack_info { + enum stack_type type; + unsigned long *begin, *end, *next_sp; }; -void dump_trace(struct task_struct *tsk, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data); +bool in_task_stack(unsigned long *stack, struct task_struct *task, + struct stack_info *info); + +int get_stack_info(unsigned long *stack, struct task_struct *task, + struct stack_info *info, unsigned long *visit_mask); + +void stack_type_str(enum stack_type type, const char **begin, + const char **end); + +static inline bool on_stack(struct stack_info *info, void *addr, size_t len) +{ + void *begin = info->begin; + void *end = info->end; + + return (info->type != STACK_TYPE_UNKNOWN && + addr >= begin && addr < end && + addr + len > begin && addr + len <= end); +} + +extern int kstack_depth_to_print; #ifdef CONFIG_X86_32 #define STACKSLOTS_PER_LINE 8 -#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :) #else #define STACKSLOTS_PER_LINE 4 -#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) #endif #ifdef CONFIG_FRAME_POINTER -static inline unsigned long -stack_frame(struct task_struct *task, struct pt_regs *regs) +static inline unsigned long * +get_frame_pointer(struct task_struct *task, struct pt_regs *regs) { - unsigned long bp; - if (regs) - return regs->bp; + return (unsigned long *)regs->bp; - if (task == current) { - /* Grab bp right from our regs */ - get_bp(bp); - return bp; - } + if (task == current) + return __builtin_frame_address(0); - /* bp is the last reg pushed by switch_to */ - return *(unsigned long *)task->thread.sp; + return (unsigned long *)((struct inactive_task_frame *)task->thread.sp)->bp; } #else -static inline unsigned long -stack_frame(struct task_struct *task, struct pt_regs *regs) +static inline unsigned long * +get_frame_pointer(struct task_struct *task, struct pt_regs *regs) { - return 0; + return NULL; +} +#endif /* CONFIG_FRAME_POINTER */ + +static inline unsigned long * +get_stack_pointer(struct task_struct *task, struct pt_regs *regs) +{ + if (regs) + return (unsigned long *)kernel_stack_pointer(regs); + + if (task == current) + return __builtin_frame_address(0); + + return (unsigned long *)task->thread.sp; } -#endif -extern void -show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl); +void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, char *log_lvl); -extern void -show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl); +void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *sp, char *log_lvl); extern unsigned int code_bytes; @@ -106,7 +106,7 @@ static inline unsigned long caller_frame_pointer(void) { struct stack_frame *frame; - get_bp(frame); + frame = __builtin_frame_address(0); #ifdef CONFIG_FRAME_POINTER frame = frame->next_frame; diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 90dbbd9666d4..a164862d77e3 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -2,6 +2,7 @@ #define _ASM_X86_STRING_64_H #ifdef __KERNEL__ +#include <linux/jump_label.h> /* Written 2002 by Andi Kleen */ @@ -78,6 +79,9 @@ int strcmp(const char *cs, const char *ct); #define memset(s, c, n) __memset(s, c, n) #endif +__must_check int memcpy_mcsafe_unrolled(void *dst, const void *src, size_t cnt); +DECLARE_STATIC_KEY_FALSE(mcsafe_key); + /** * memcpy_mcsafe - copy memory with indication if a machine check happened * @@ -86,10 +90,23 @@ int strcmp(const char *cs, const char *ct); * @cnt: number of bytes to copy * * Low level memory copy function that catches machine checks + * We only call into the "safe" function on systems that can + * actually do machine check recovery. Everyone else can just + * use memcpy(). * * Return 0 for success, -EFAULT for fail */ -int memcpy_mcsafe(void *dst, const void *src, size_t cnt); +static __always_inline __must_check int +memcpy_mcsafe(void *dst, const void *src, size_t cnt) +{ +#ifdef CONFIG_X86_MCE + if (static_branch_unlikely(&mcsafe_key)) + return memcpy_mcsafe_unrolled(dst, src, cnt); + else +#endif + memcpy(dst, src, cnt); + return 0; +} #endif /* __KERNEL__ */ diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 8f321a1b03a1..5cb436acd463 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -2,130 +2,66 @@ #define _ASM_X86_SWITCH_TO_H struct task_struct; /* one of the stranger aspects of C forward declarations */ + +struct task_struct *__switch_to_asm(struct task_struct *prev, + struct task_struct *next); + __visible struct task_struct *__switch_to(struct task_struct *prev, - struct task_struct *next); + struct task_struct *next); struct tss_struct; void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, struct tss_struct *tss); -#ifdef CONFIG_X86_32 +/* This runs runs on the previous thread's stack. */ +static inline void prepare_switch_to(struct task_struct *prev, + struct task_struct *next) +{ +#ifdef CONFIG_VMAP_STACK + /* + * If we switch to a stack that has a top-level paging entry + * that is not present in the current mm, the resulting #PF will + * will be promoted to a double-fault and we'll panic. Probe + * the new stack now so that vmalloc_fault can fix up the page + * tables if needed. This can only happen if we use a stack + * in vmap space. + * + * We assume that the stack is aligned so that it never spans + * more than one top-level paging entry. + * + * To minimize cache pollution, just follow the stack pointer. + */ + READ_ONCE(*(unsigned char *)next->thread.sp); +#endif +} + +asmlinkage void ret_from_fork(void); + +/* data that is pointed to by thread.sp */ +struct inactive_task_frame { +#ifdef CONFIG_X86_64 + unsigned long r15; + unsigned long r14; + unsigned long r13; + unsigned long r12; +#else + unsigned long si; + unsigned long di; +#endif + unsigned long bx; + unsigned long bp; + unsigned long ret_addr; +}; -#ifdef CONFIG_CC_STACKPROTECTOR -#define __switch_canary \ - "movl %P[task_canary](%[next]), %%ebx\n\t" \ - "movl %%ebx, "__percpu_arg([stack_canary])"\n\t" -#define __switch_canary_oparam \ - , [stack_canary] "=m" (stack_canary.canary) -#define __switch_canary_iparam \ - , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) -#else /* CC_STACKPROTECTOR */ -#define __switch_canary -#define __switch_canary_oparam -#define __switch_canary_iparam -#endif /* CC_STACKPROTECTOR */ +struct fork_frame { + struct inactive_task_frame frame; + struct pt_regs regs; +}; -/* - * Saving eflags is important. It switches not only IOPL between tasks, - * it also protects other tasks from NT leaking through sysenter etc. - */ #define switch_to(prev, next, last) \ do { \ - /* \ - * Context-switching clobbers all registers, so we clobber \ - * them explicitly, via unused output variables. \ - * (EAX and EBP is not listed because EBP is saved/restored \ - * explicitly for wchan access and EAX is the return value of \ - * __switch_to()) \ - */ \ - unsigned long ebx, ecx, edx, esi, edi; \ - \ - asm volatile("pushl %%ebp\n\t" /* save EBP */ \ - "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \ - "movl %[next_sp],%%esp\n\t" /* restore ESP */ \ - "movl $1f,%[prev_ip]\n\t" /* save EIP */ \ - "pushl %[next_ip]\n\t" /* restore EIP */ \ - __switch_canary \ - "jmp __switch_to\n" /* regparm call */ \ - "1:\t" \ - "popl %%ebp\n\t" /* restore EBP */ \ - \ - /* output parameters */ \ - : [prev_sp] "=m" (prev->thread.sp), \ - [prev_ip] "=m" (prev->thread.ip), \ - "=a" (last), \ - \ - /* clobbered output registers: */ \ - "=b" (ebx), "=c" (ecx), "=d" (edx), \ - "=S" (esi), "=D" (edi) \ - \ - __switch_canary_oparam \ - \ - /* input parameters: */ \ - : [next_sp] "m" (next->thread.sp), \ - [next_ip] "m" (next->thread.ip), \ - \ - /* regparm parameters for __switch_to(): */ \ - [prev] "a" (prev), \ - [next] "d" (next) \ + prepare_switch_to(prev, next); \ \ - __switch_canary_iparam \ - \ - : /* reloaded segment registers */ \ - "memory"); \ + ((last) = __switch_to_asm((prev), (next))); \ } while (0) -#else /* CONFIG_X86_32 */ - -/* frame pointer must be last for get_wchan */ -#define SAVE_CONTEXT "pushq %%rbp ; movq %%rsi,%%rbp\n\t" -#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t" - -#define __EXTRA_CLOBBER \ - , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \ - "r12", "r13", "r14", "r15", "flags" - -#ifdef CONFIG_CC_STACKPROTECTOR -#define __switch_canary \ - "movq %P[task_canary](%%rsi),%%r8\n\t" \ - "movq %%r8,"__percpu_arg([gs_canary])"\n\t" -#define __switch_canary_oparam \ - , [gs_canary] "=m" (irq_stack_union.stack_canary) -#define __switch_canary_iparam \ - , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) -#else /* CC_STACKPROTECTOR */ -#define __switch_canary -#define __switch_canary_oparam -#define __switch_canary_iparam -#endif /* CC_STACKPROTECTOR */ - -/* - * There is no need to save or restore flags, because flags are always - * clean in kernel mode, with the possible exception of IOPL. Kernel IOPL - * has no effect. - */ -#define switch_to(prev, next, last) \ - asm volatile(SAVE_CONTEXT \ - "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ - "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \ - "call __switch_to\n\t" \ - "movq "__percpu_arg([current_task])",%%rsi\n\t" \ - __switch_canary \ - "movq %P[thread_info](%%rsi),%%r8\n\t" \ - "movq %%rax,%%rdi\n\t" \ - "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \ - "jnz ret_from_fork\n\t" \ - RESTORE_CONTEXT \ - : "=a" (last) \ - __switch_canary_oparam \ - : [next] "S" (next), [prev] "D" (prev), \ - [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \ - [ti_flags] "i" (offsetof(struct thread_info, flags)), \ - [_tif_fork] "i" (_TIF_FORK), \ - [thread_info] "i" (offsetof(struct task_struct, stack)), \ - [current_task] "m" (current_task) \ - __switch_canary_iparam \ - : "memory", "cc" __EXTRA_CLOBBER) - -#endif /* CONFIG_X86_32 */ - #endif /* _ASM_X86_SWITCH_TO_H */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 4e23dd15c661..e3c95e8e61c5 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -60,7 +60,7 @@ static inline long syscall_get_error(struct task_struct *task, * TS_COMPAT is set for 32-bit syscall entries and then * remains set until we return to user mode. */ - if (task_thread_info(task)->status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) /* * Sign-extend the value so (int)-EFOO becomes (long)-EFOO * and will match correctly in comparisons. @@ -116,7 +116,7 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task_thread_info(task)->status & TS_COMPAT) + if (task->thread.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; @@ -177,7 +177,7 @@ static inline void syscall_set_arguments(struct task_struct *task, const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task_thread_info(task)->status & TS_COMPAT) + if (task->thread.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; @@ -234,18 +234,8 @@ static inline void syscall_set_arguments(struct task_struct *task, static inline int syscall_get_arch(void) { -#ifdef CONFIG_IA32_EMULATION - /* - * TS_COMPAT is set for 32-bit syscall entry and then - * remains set until we return to user mode. - * - * x32 tasks should be considered AUDIT_ARCH_X86_64. - */ - if (task_thread_info(current)->status & TS_COMPAT) - return AUDIT_ARCH_I386; -#endif - /* Both x32 and x86_64 are considered "64-bit". */ - return AUDIT_ARCH_X86_64; + /* x32 tasks should be considered AUDIT_ARCH_X86_64. */ + return in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; } #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 8b7c8d8e0852..2aaca53c0974 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -52,21 +52,6 @@ struct task_struct; #include <asm/cpufeature.h> #include <linux/atomic.h> -struct thread_info { - struct task_struct *task; /* main task structure */ - __u32 flags; /* low level flags */ - __u32 status; /* thread synchronous flags */ - __u32 cpu; /* current CPU */ -}; - -#define INIT_THREAD_INFO(tsk) \ -{ \ - .task = &tsk, \ - .flags = 0, \ - .cpu = 0, \ -} - -#define init_thread_info (init_thread_union.thread_info) #define init_stack (init_thread_union.stack) #else /* !__ASSEMBLY__ */ @@ -95,7 +80,6 @@ struct thread_info { #define TIF_UPROBE 12 /* breakpointed or singlestepping */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* IA32 compatibility process */ -#define TIF_FORK 18 /* ret_from_fork */ #define TIF_NOHZ 19 /* in adaptive nohz mode */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ @@ -119,7 +103,6 @@ struct thread_info { #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) -#define _TIF_FORK (1 << TIF_FORK) #define _TIF_NOHZ (1 << TIF_NOHZ) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) @@ -160,11 +143,6 @@ struct thread_info { */ #ifndef __ASSEMBLY__ -static inline struct thread_info *current_thread_info(void) -{ - return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE); -} - static inline unsigned long current_stack_pointer(void) { unsigned long sp; @@ -226,60 +204,19 @@ static inline int arch_within_stack_frames(const void * const stack, # define cpu_current_top_of_stack (cpu_tss + TSS_sp0) #endif -/* - * ASM operand which evaluates to a 'thread_info' address of - * the current task, if it is known that "reg" is exactly "off" - * bytes below the top of the stack currently. - * - * ( The kernel stack's size is known at build time, it is usually - * 2 or 4 pages, and the bottom of the kernel stack contains - * the thread_info structure. So to access the thread_info very - * quickly from assembly code we can calculate down from the - * top of the kernel stack to the bottom, using constant, - * build-time calculations only. ) - * - * For example, to fetch the current thread_info->flags value into %eax - * on x86-64 defconfig kernels, in syscall entry code where RSP is - * currently at exactly SIZEOF_PTREGS bytes away from the top of the - * stack: - * - * mov ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS), %eax - * - * will translate to: - * - * 8b 84 24 b8 c0 ff ff mov -0x3f48(%rsp), %eax - * - * which is below the current RSP by almost 16K. - */ -#define ASM_THREAD_INFO(field, reg, off) ((field)+(off)-THREAD_SIZE)(reg) - #endif -/* - * Thread-synchronous status. - * - * This is different from the flags in that nobody else - * ever touches our thread-synchronous status, so we don't - * have to worry about atomic accesses. - */ -#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ #ifdef CONFIG_COMPAT #define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ #endif - #ifndef __ASSEMBLY__ -static inline bool in_ia32_syscall(void) -{ #ifdef CONFIG_X86_32 - return true; -#endif -#ifdef CONFIG_IA32_EMULATION - if (current_thread_info()->status & TS_COMPAT) - return true; +#define in_ia32_syscall() true +#else +#define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \ + current->thread.status & TS_COMPAT) #endif - return false; -} /* * Force syscall return via IRET by making it look as if there was diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index c3496619740a..01fd0a7f48cd 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -117,6 +117,12 @@ extern void ist_exit(struct pt_regs *regs); extern void ist_begin_non_atomic(struct pt_regs *regs); extern void ist_end_non_atomic(void); +#ifdef CONFIG_VMAP_STACK +void __noreturn handle_stack_overflow(const char *message, + struct pt_regs *regs, + unsigned long fault_address); +#endif + /* Interrupts/Exceptions */ enum { X86_TRAP_DE = 0, /* 0, Divide-by-zero */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index a0ae610b9280..2131c4ce7d8a 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -433,7 +433,11 @@ do { \ #define __get_user_asm_ex(x, addr, itype, rtype, ltype) \ asm volatile("1: mov"itype" %1,%"rtype"0\n" \ "2:\n" \ - _ASM_EXTABLE_EX(1b, 2b) \ + ".section .fixup,\"ax\"\n" \ + "3:xor"itype" %"rtype"0,%"rtype"0\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE_EX(1b, 3b) \ : ltype(x) : "m" (__m(addr))) #define __put_user_nocheck(x, ptr, size) \ @@ -697,44 +701,15 @@ unsigned long __must_check _copy_from_user(void *to, const void __user *from, unsigned long __must_check _copy_to_user(void __user *to, const void *from, unsigned n); -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -# define copy_user_diag __compiletime_error -#else -# define copy_user_diag __compiletime_warning -#endif - -extern void copy_user_diag("copy_from_user() buffer size is too small") -copy_from_user_overflow(void); -extern void copy_user_diag("copy_to_user() buffer size is too small") -copy_to_user_overflow(void) __asm__("copy_from_user_overflow"); - -#undef copy_user_diag - -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS - -extern void -__compiletime_warning("copy_from_user() buffer size is not provably correct") -__copy_from_user_overflow(void) __asm__("copy_from_user_overflow"); -#define __copy_from_user_overflow(size, count) __copy_from_user_overflow() - -extern void -__compiletime_warning("copy_to_user() buffer size is not provably correct") -__copy_to_user_overflow(void) __asm__("copy_from_user_overflow"); -#define __copy_to_user_overflow(size, count) __copy_to_user_overflow() +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); -#else - -static inline void -__copy_from_user_overflow(int size, unsigned long count) +static inline void copy_user_overflow(int size, unsigned long count) { WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); } -#define __copy_to_user_overflow __copy_from_user_overflow - -#endif - -static inline unsigned long __must_check +static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { int sz = __compiletime_object_size(to); @@ -743,36 +718,18 @@ copy_from_user(void *to, const void __user *from, unsigned long n) kasan_check_write(to, n); - /* - * While we would like to have the compiler do the checking for us - * even in the non-constant size case, any false positives there are - * a problem (especially when DEBUG_STRICT_USER_COPY_CHECKS, but even - * without - the [hopefully] dangerous looking nature of the warning - * would make people go look at the respecitive call sites over and - * over again just to find that there's no problem). - * - * And there are cases where it's just not realistic for the compiler - * to prove the count to be in range. For example when multiple call - * sites of a helper function - perhaps in different source files - - * all doing proper range checking, yet the helper function not doing - * so again. - * - * Therefore limit the compile time checking to the constant size - * case, and do only runtime checking for non-constant sizes. - */ - if (likely(sz < 0 || sz >= n)) { check_object_size(to, n, false); n = _copy_from_user(to, from, n); - } else if (__builtin_constant_p(n)) - copy_from_user_overflow(); + } else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - __copy_from_user_overflow(sz, n); + __bad_copy_user(); return n; } -static inline unsigned long __must_check +static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { int sz = __compiletime_object_size(from); @@ -781,21 +738,17 @@ copy_to_user(void __user *to, const void *from, unsigned long n) might_fault(); - /* See the comment in copy_from_user() above. */ if (likely(sz < 0 || sz >= n)) { check_object_size(from, n, true); n = _copy_to_user(to, from, n); - } else if (__builtin_constant_p(n)) - copy_to_user_overflow(); + } else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - __copy_to_user_overflow(sz, n); + __bad_copy_user(); return n; } -#undef __copy_from_user_overflow -#undef __copy_to_user_overflow - /* * We rely on the nested NMI work to allow atomic faults from the NMI path; the * nested NMI paths are careful to preserve CR2. diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h new file mode 100644 index 000000000000..c4b6d1cafa46 --- /dev/null +++ b/arch/x86/include/asm/unwind.h @@ -0,0 +1,73 @@ +#ifndef _ASM_X86_UNWIND_H +#define _ASM_X86_UNWIND_H + +#include <linux/sched.h> +#include <linux/ftrace.h> +#include <asm/ptrace.h> +#include <asm/stacktrace.h> + +struct unwind_state { + struct stack_info stack_info; + unsigned long stack_mask; + struct task_struct *task; + int graph_idx; +#ifdef CONFIG_FRAME_POINTER + unsigned long *bp; +#else + unsigned long *sp; +#endif +}; + +void __unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs, unsigned long *first_frame); + +bool unwind_next_frame(struct unwind_state *state); + +static inline bool unwind_done(struct unwind_state *state) +{ + return state->stack_info.type == STACK_TYPE_UNKNOWN; +} + +static inline +void unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs, unsigned long *first_frame) +{ + first_frame = first_frame ? : get_stack_pointer(task, regs); + + __unwind_start(state, task, regs, first_frame); +} + +#ifdef CONFIG_FRAME_POINTER + +static inline +unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) +{ + if (unwind_done(state)) + return NULL; + + return state->bp + 1; +} + +unsigned long unwind_get_return_address(struct unwind_state *state); + +#else /* !CONFIG_FRAME_POINTER */ + +static inline +unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) +{ + return NULL; +} + +static inline +unsigned long unwind_get_return_address(struct unwind_state *state) +{ + if (unwind_done(state)) + return 0; + + return ftrace_graph_ret_addr(state->task, &state->graph_idx, + *state->sp, state->sp); +} + +#endif /* CONFIG_FRAME_POINTER */ + +#endif /* _ASM_X86_UNWIND_H */ diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index cc44d926c17e..57ab86d94d64 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -49,14 +49,12 @@ #define UV_NET_ENDPOINT_INTD (is_uv1_hub() ? \ UV1_NET_ENDPOINT_INTD : UV2_NET_ENDPOINT_INTD) #define UV_DESC_PSHIFT 49 -#define UV_PAYLOADQ_PNODE_SHIFT 49 +#define UV_PAYLOADQ_GNODE_SHIFT 49 #define UV_PTC_BASENAME "sgi_uv/ptc_statistics" #define UV_BAU_BASENAME "sgi_uv/bau_tunables" #define UV_BAU_TUNABLES_DIR "sgi_uv" #define UV_BAU_TUNABLES_FILE "bau_tunables" #define WHITESPACE " \t\n" -#define uv_mmask ((1UL << uv_hub_info->m_val) - 1) -#define uv_physnodeaddr(x) ((__pa((unsigned long)(x)) & uv_mmask)) #define cpubit_isset(cpu, bau_local_cpumask) \ test_bit((cpu), (bau_local_cpumask).bits) @@ -387,6 +385,17 @@ struct uv2_3_bau_msg_header { /* bits 127:120 */ }; +/* Abstracted BAU functions */ +struct bau_operations { + unsigned long (*read_l_sw_ack)(void); + unsigned long (*read_g_sw_ack)(int pnode); + unsigned long (*bau_gpa_to_offset)(unsigned long vaddr); + void (*write_l_sw_ack)(unsigned long mmr); + void (*write_g_sw_ack)(int pnode, unsigned long mmr); + void (*write_payload_first)(int pnode, unsigned long mmr); + void (*write_payload_last)(int pnode, unsigned long mmr); +}; + /* * The activation descriptor: * The format of the message to send, plus all accompanying control @@ -655,6 +664,16 @@ static inline void write_gmmr_activation(int pnode, unsigned long mmr_image) write_gmmr(pnode, UVH_LB_BAU_SB_ACTIVATION_CONTROL, mmr_image); } +static inline void write_mmr_proc_payload_first(int pnode, unsigned long mmr_image) +{ + write_gmmr(pnode, UV4H_LB_PROC_INTD_QUEUE_FIRST, mmr_image); +} + +static inline void write_mmr_proc_payload_last(int pnode, unsigned long mmr_image) +{ + write_gmmr(pnode, UV4H_LB_PROC_INTD_QUEUE_LAST, mmr_image); +} + static inline void write_mmr_payload_first(int pnode, unsigned long mmr_image) { write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST, mmr_image); @@ -700,6 +719,26 @@ static inline unsigned long read_gmmr_sw_ack(int pnode) return read_gmmr(pnode, UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE); } +static inline void write_mmr_proc_sw_ack(unsigned long mr) +{ + uv_write_local_mmr(UV4H_LB_PROC_INTD_SOFT_ACK_CLEAR, mr); +} + +static inline void write_gmmr_proc_sw_ack(int pnode, unsigned long mr) +{ + write_gmmr(pnode, UV4H_LB_PROC_INTD_SOFT_ACK_CLEAR, mr); +} + +static inline unsigned long read_mmr_proc_sw_ack(void) +{ + return read_lmmr(UV4H_LB_PROC_INTD_SOFT_ACK_PENDING); +} + +static inline unsigned long read_gmmr_proc_sw_ack(int pnode) +{ + return read_gmmr(pnode, UV4H_LB_PROC_INTD_SOFT_ACK_PENDING); +} + static inline void write_mmr_data_config(int pnode, unsigned long mr) { uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, mr); diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 43dc55be524e..2444189cbe28 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -41,6 +41,8 @@ extern const struct vdso_image vdso_image_32; extern void __init init_vdso_image(const struct vdso_image *image); +extern int map_vdso_once(const struct vdso_image *image, unsigned long addr); + #endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_VDSO_H */ diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h index e6911caf5bbf..608a79d5a466 100644 --- a/arch/x86/include/asm/xen/events.h +++ b/arch/x86/include/asm/xen/events.h @@ -20,15 +20,4 @@ static inline int xen_irqs_disabled(struct pt_regs *regs) /* No need for a barrier -- XCHG is a barrier on x86. */ #define xchg_xen_ulong(ptr, val) xchg((ptr), (val)) -extern int xen_have_vector_callback; - -/* - * Events delivered via platform PCI interrupts are always - * routed to vcpu 0 and hence cannot be rebound. - */ -static inline bool xen_support_evtchn_rebind(void) -{ - return (!xen_hvm_domain() || xen_have_vector_callback); -} - #endif /* _ASM_X86_XEN_EVENTS_H */ diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index 2184943341bf..69a6e07e3149 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -26,6 +26,8 @@ struct mce { __u32 socketid; /* CPU socket ID */ __u32 apicid; /* CPU initial apic ID */ __u64 mcgcap; /* MCGCAP MSR: machine check capabilities of CPU */ + __u64 synd; /* MCA_SYND MSR: only valid on SMCA systems */ + __u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */ }; #define MCE_GET_RECORD_LEN _IOR('M', 1, int) diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index 3ac5032fae09..ae135de547f5 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -6,4 +6,10 @@ #define ARCH_GET_FS 0x1003 #define ARCH_GET_GS 0x1004 +#ifdef CONFIG_CHECKPOINT_RESTORE +# define ARCH_MAP_VDSO_X32 0x2001 +# define ARCH_MAP_VDSO_32 0x2002 +# define ARCH_MAP_VDSO_64 0x2003 +#endif + #endif /* _ASM_X86_PRCTL_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0503f5bfb18d..4dd5d500eb60 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -83,6 +83,7 @@ obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-y += apic/ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o +obj-$(CONFIG_LIVEPATCH) += livepatch.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_X86_TSC) += trace_clock.o @@ -125,6 +126,12 @@ obj-$(CONFIG_EFI) += sysfb_efi.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o +ifdef CONFIG_FRAME_POINTER +obj-y += unwind_frame.o +else +obj-y += unwind_guess.o +endif + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index 3242e591fa82..26b78d86f25a 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -1,6 +1,7 @@ obj-$(CONFIG_ACPI) += boot.o obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o obj-$(CONFIG_ACPI_APEI) += apei.o +obj-$(CONFIG_ACPI_CPPC_LIB) += cppc_msr.o ifneq ($(CONFIG_ACPI_PROCESSOR),) obj-y += cstate.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 90d84c3eee53..32a7d70913ac 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -176,15 +176,10 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled) return -EINVAL; } - if (!enabled) { - ++disabled_cpus; - return -EINVAL; - } - if (boot_cpu_physical_apicid != -1U) - ver = apic_version[boot_cpu_physical_apicid]; + ver = boot_cpu_apic_version; - cpu = generic_processor_info(id, ver); + cpu = __generic_processor_info(id, ver, enabled); if (cpu >= 0) early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid; @@ -282,6 +277,8 @@ acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header, if (BAD_MADT_ENTRY(lapic_addr_ovr, end)) return -EINVAL; + acpi_table_print_madt_entry(header); + acpi_lapic_addr = lapic_addr_ovr->address; return 0; @@ -705,7 +702,7 @@ static void __init acpi_set_irq_model_ioapic(void) #ifdef CONFIG_ACPI_HOTPLUG_CPU #include <acpi/processor.h> -static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) +int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) { #ifdef CONFIG_ACPI_NUMA int nid; @@ -716,6 +713,7 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) numa_set_node(cpu, nid); } #endif + return 0; } int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu) @@ -998,21 +996,6 @@ static int __init acpi_parse_madt_lapic_entries(void) if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; - /* - * Note that the LAPIC address is obtained from the MADT (32-bit value) - * and (optionally) overridden by a LAPIC_ADDR_OVR entry (64-bit value). - */ - - count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE, - acpi_parse_lapic_addr_ovr, 0); - if (count < 0) { - printk(KERN_ERR PREFIX - "Error parsing LAPIC address override entry\n"); - return count; - } - - register_lapic_address(acpi_lapic_addr); - count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC, acpi_parse_sapic, MAX_LOCAL_APIC); @@ -1031,8 +1014,8 @@ static int __init acpi_parse_madt_lapic_entries(void) return ret; } - x2count = madt_proc[0].count; - count = madt_proc[1].count; + count = madt_proc[0].count; + x2count = madt_proc[1].count; } if (!count && !x2count) { printk(KERN_ERR PREFIX "No LAPIC entries present\n"); @@ -1513,7 +1496,7 @@ void __init acpi_boot_table_init(void) * If acpi_disabled, bail out */ if (acpi_disabled) - return; + return; /* * Initialize the ACPI boot-time table parser. diff --git a/arch/x86/kernel/acpi/cppc_msr.c b/arch/x86/kernel/acpi/cppc_msr.c new file mode 100644 index 000000000000..6fb478bf82fd --- /dev/null +++ b/arch/x86/kernel/acpi/cppc_msr.c @@ -0,0 +1,58 @@ +/* + * cppc_msr.c: MSR Interface for CPPC + * Copyright (c) 2016, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#include <acpi/cppc_acpi.h> +#include <asm/msr.h> + +/* Refer to drivers/acpi/cppc_acpi.c for the description of functions */ + +bool cpc_ffh_supported(void) +{ + return true; +} + +int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val) +{ + int err; + + err = rdmsrl_safe_on_cpu(cpunum, reg->address, val); + if (!err) { + u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1, + reg->bit_offset); + + *val &= mask; + *val >>= reg->bit_offset; + } + return err; +} + +int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val) +{ + u64 rd_val; + int err; + + err = rdmsrl_safe_on_cpu(cpunum, reg->address, &rd_val); + if (!err) { + u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1, + reg->bit_offset); + + val <<= reg->bit_offset; + val &= mask; + rd_val &= ~mask; + rd_val |= val; + err = wrmsrl_safe_on_cpu(cpunum, reg->address, rd_val); + } + return err; +} diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index adb3eaf8fe2a..48587335ede8 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -99,7 +99,7 @@ int x86_acpi_suspend_lowlevel(void) saved_magic = 0x12345678; #else /* CONFIG_64BIT */ #ifdef CONFIG_SMP - stack_start = (unsigned long)temp_stack + sizeof(temp_stack); + initial_stack = (unsigned long)temp_stack + sizeof(temp_stack); early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(smp_processor_id()); initial_gs = per_cpu_offset(smp_processor_id()); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 50c95af0f017..f266b8a92a9e 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -64,6 +64,8 @@ unsigned disabled_cpus; unsigned int boot_cpu_physical_apicid = -1U; EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid); +u8 boot_cpu_apic_version; + /* * The highest APIC ID seen during enumeration. */ @@ -1374,7 +1376,6 @@ void setup_local_APIC(void) * Actually disabling the focus CPU check just makes the hang less * frequent as it makes the interrupt distributon model be more * like LRU than MRU (the short-term load is more even across CPUs). - * See also the comment in end_level_ioapic_irq(). --macro */ /* @@ -1816,8 +1817,7 @@ void __init init_apic_mappings(void) * since smp_sanity_check is prepared for such a case * and disable smp mode */ - apic_version[new_apicid] = - GET_APIC_VERSION(apic_read(APIC_LVR)); + boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR)); } } @@ -1828,17 +1828,14 @@ void __init register_lapic_address(unsigned long address) if (!x2apic_mode) { set_fixmap_nocache(FIX_APIC_BASE, address); apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n", - APIC_BASE, mp_lapic_addr); + APIC_BASE, address); } if (boot_cpu_physical_apicid == -1U) { boot_cpu_physical_apicid = read_apic_id(); - apic_version[boot_cpu_physical_apicid] = - GET_APIC_VERSION(apic_read(APIC_LVR)); + boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR)); } } -int apic_version[MAX_LOCAL_APIC]; - /* * Local APIC interrupts */ @@ -2027,7 +2024,53 @@ void disconnect_bsp_APIC(int virt_wire_setup) apic_write(APIC_LVT1, value); } -int generic_processor_info(int apicid, int version) +/* + * The number of allocated logical CPU IDs. Since logical CPU IDs are allocated + * contiguously, it equals to current allocated max logical CPU ID plus 1. + * All allocated CPU ID should be in [0, nr_logical_cpuidi), so the maximum of + * nr_logical_cpuids is nr_cpu_ids. + * + * NOTE: Reserve 0 for BSP. + */ +static int nr_logical_cpuids = 1; + +/* + * Used to store mapping between logical CPU IDs and APIC IDs. + */ +static int cpuid_to_apicid[] = { + [0 ... NR_CPUS - 1] = -1, +}; + +/* + * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids + * and cpuid_to_apicid[] synchronized. + */ +static int allocate_logical_cpuid(int apicid) +{ + int i; + + /* + * cpuid <-> apicid mapping is persistent, so when a cpu is up, + * check if the kernel has allocated a cpuid for it. + */ + for (i = 0; i < nr_logical_cpuids; i++) { + if (cpuid_to_apicid[i] == apicid) + return i; + } + + /* Allocate a new cpuid. */ + if (nr_logical_cpuids >= nr_cpu_ids) { + WARN_ONCE(1, "Only %d processors supported." + "Processor %d/0x%x and the rest are ignored.\n", + nr_cpu_ids - 1, nr_logical_cpuids, apicid); + return -1; + } + + cpuid_to_apicid[nr_logical_cpuids] = apicid; + return nr_logical_cpuids++; +} + +int __generic_processor_info(int apicid, int version, bool enabled) { int cpu, max = nr_cpu_ids; bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid, @@ -2093,7 +2136,6 @@ int generic_processor_info(int apicid, int version) return -EINVAL; } - num_processors++; if (apicid == boot_cpu_physical_apicid) { /* * x86_bios_cpu_apicid is required to have processors listed @@ -2103,8 +2145,16 @@ int generic_processor_info(int apicid, int version) * for BSP. */ cpu = 0; - } else - cpu = cpumask_next_zero(-1, cpu_present_mask); + + /* Logical cpuid 0 is reserved for BSP. */ + cpuid_to_apicid[0] = apicid; + } else { + cpu = allocate_logical_cpuid(apicid); + if (cpu < 0) { + disabled_cpus++; + return -EINVAL; + } + } /* * This can happen on physical hotplug. The sanity check at boot time @@ -2116,6 +2166,7 @@ int generic_processor_info(int apicid, int version) pr_warning("APIC: Package limit reached. Processor %d/0x%x ignored.\n", thiscpu, apicid); + disabled_cpus++; return -ENOSPC; } @@ -2128,14 +2179,12 @@ int generic_processor_info(int apicid, int version) cpu, apicid); version = 0x10; } - apic_version[apicid] = version; - if (version != apic_version[boot_cpu_physical_apicid]) { + if (version != boot_cpu_apic_version) { pr_warning("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n", - apic_version[boot_cpu_physical_apicid], cpu, version); + boot_cpu_apic_version, cpu, version); } - physid_set(apicid, phys_cpu_present_map); if (apicid > max_physical_apicid) max_physical_apicid = apicid; @@ -2148,11 +2197,23 @@ int generic_processor_info(int apicid, int version) apic->x86_32_early_logical_apicid(cpu); #endif set_cpu_possible(cpu, true); - set_cpu_present(cpu, true); + + if (enabled) { + num_processors++; + physid_set(apicid, phys_cpu_present_map); + set_cpu_present(cpu, true); + } else { + disabled_cpus++; + } return cpu; } +int generic_processor_info(int apicid, int version) +{ + return __generic_processor_info(apicid, version, true); +} + int hard_smp_processor_id(void) { return read_apic_id(); @@ -2275,7 +2336,7 @@ int __init APIC_init_uniprocessor(void) * Complain if the BIOS pretends there is one. */ if (!boot_cpu_has(X86_FEATURE_APIC) && - APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) { + APIC_INTEGRATED(boot_cpu_apic_version)) { pr_err("BIOS bug, local APIC 0x%x not detected!...\n", boot_cpu_physical_apicid); return -1; diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 5b2ae106bd4a..a4d7ff20ed22 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -25,7 +25,7 @@ static struct apic apic_physflat; static struct apic apic_flat; -struct apic __read_mostly *apic = &apic_flat; +struct apic *apic __ro_after_init = &apic_flat; EXPORT_SYMBOL_GPL(apic); static int flat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) @@ -116,27 +116,17 @@ static void flat_send_IPI_all(int vector) static unsigned int flat_get_apic_id(unsigned long x) { - unsigned int id; - - id = (((x)>>24) & 0xFFu); - - return id; + return (x >> 24) & 0xFF; } static unsigned long set_apic_id(unsigned int id) { - unsigned long x; - - x = ((id & 0xFFu)<<24); - return x; + return (id & 0xFF) << 24; } static unsigned int read_xapic_id(void) { - unsigned int id; - - id = flat_get_apic_id(apic_read(APIC_ID)); - return id; + return flat_get_apic_id(apic_read(APIC_ID)); } static int flat_apic_id_registered(void) @@ -154,7 +144,7 @@ static int flat_probe(void) return 1; } -static struct apic apic_flat = { +static struct apic apic_flat __ro_after_init = { .name = "flat", .probe = flat_probe, .acpi_madt_oem_check = flat_acpi_madt_oem_check, @@ -248,7 +238,7 @@ static int physflat_probe(void) return 0; } -static struct apic apic_physflat = { +static struct apic apic_physflat __ro_after_init = { .name = "physical flat", .probe = physflat_probe, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index c05688b2deff..b109e4389c92 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -108,7 +108,7 @@ static void noop_apic_write(u32 reg, u32 v) WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic); } -struct apic apic_noop = { +struct apic apic_noop __ro_after_init = { .name = "noop", .probe = noop_probe, .acpi_madt_oem_check = NULL, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 714d4fda0d52..e08fe2c8dd8c 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -40,10 +40,7 @@ static unsigned int numachip1_get_apic_id(unsigned long x) static unsigned long numachip1_set_apic_id(unsigned int id) { - unsigned long x; - - x = ((id & 0xffU) << 24); - return x; + return (id & 0xff) << 24; } static unsigned int numachip2_get_apic_id(unsigned long x) diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 06dbaa458bfe..56012010332c 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -142,7 +142,7 @@ static int probe_bigsmp(void) return dmi_bigsmp; } -static struct apic apic_bigsmp = { +static struct apic apic_bigsmp __ro_after_init = { .name = "bigsmp", .probe = probe_bigsmp, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 7491f417a8e4..48e6d84f173e 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1593,7 +1593,7 @@ void __init setup_ioapic_ids_from_mpc(void) * no meaning without the serial APIC bus. */ if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) - || APIC_XAPIC(apic_version[boot_cpu_physical_apicid])) + || APIC_XAPIC(boot_cpu_apic_version)) return; setup_ioapic_ids_from_mpc_nocheck(); } @@ -2423,7 +2423,7 @@ static int io_apic_get_unique_id(int ioapic, int apic_id) static u8 io_apic_unique_id(int idx, u8 id) { if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && - !APIC_XAPIC(apic_version[boot_cpu_physical_apicid])) + !APIC_XAPIC(boot_cpu_apic_version)) return io_apic_get_unique_id(idx, id); else return id; diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index ade25320df96..015bbf30e3e3 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -269,7 +269,7 @@ static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg) hpet_msi_write(irq_data_get_irq_handler_data(data), msg); } -static struct irq_chip hpet_msi_controller = { +static struct irq_chip hpet_msi_controller __ro_after_init = { .name = "HPET-MSI", .irq_unmask = hpet_msi_unmask, .irq_mask = hpet_msi_mask, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 7c43e716c158..c48264e202fd 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -72,7 +72,7 @@ static int probe_default(void) return 1; } -static struct apic apic_default = { +static struct apic apic_default __ro_after_init = { .name = "default", .probe = probe_default, @@ -126,7 +126,7 @@ static struct apic apic_default = { apic_driver(apic_default); -struct apic *apic = &apic_default; +struct apic *apic __ro_after_init = &apic_default; EXPORT_SYMBOL_GPL(apic); static int cmdline_apic __initdata; @@ -152,7 +152,7 @@ early_param("apic", parse_apic); void __init default_setup_apic_routing(void) { - int version = apic_version[boot_cpu_physical_apicid]; + int version = boot_cpu_apic_version; if (num_possible_cpus() > 8) { switch (boot_cpu_data.x86_vendor) { diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 54f35d988025..200af5ae9662 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -227,7 +227,7 @@ static void cluster_vector_allocation_domain(int cpu, struct cpumask *retmask, cpumask_and(retmask, mask, per_cpu(cpus_in_cluster, cpu)); } -static struct apic apic_x2apic_cluster = { +static struct apic apic_x2apic_cluster __ro_after_init = { .name = "cluster x2apic", .probe = x2apic_cluster_probe, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 4f13f54f1b1f..ff111f05a314 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -98,7 +98,7 @@ static int x2apic_phys_probe(void) return apic == &apic_x2apic_phys; } -static struct apic apic_x2apic_phys = { +static struct apic apic_x2apic_phys __ro_after_init = { .name = "physical x2apic", .probe = x2apic_phys_probe, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index cb0673c1e940..aeef53ce93e1 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -533,11 +533,8 @@ static unsigned int x2apic_get_apic_id(unsigned long x) static unsigned long set_apic_id(unsigned int id) { - unsigned long x; - - /* maskout x2apic_extra_bits ? */ - x = id; - return x; + /* CHECKME: Do we need to mask out the xapic extra bits? */ + return id; } static unsigned int uv_read_apic_id(void) @@ -560,7 +557,7 @@ static int uv_probe(void) return apic == &apic_x2apic_uv_x; } -static struct apic __refdata apic_x2apic_uv_x = { +static struct apic apic_x2apic_uv_x __ro_after_init = { .name = "UV large system", .probe = uv_probe, @@ -927,7 +924,7 @@ static void uv_heartbeat(unsigned long ignored) mod_timer(timer, jiffies + SCIR_CPU_HB_INTERVAL); } -static void uv_heartbeat_enable(int cpu) +static int uv_heartbeat_enable(unsigned int cpu) { while (!uv_cpu_scir_info(cpu)->enabled) { struct timer_list *timer = &uv_cpu_scir_info(cpu)->timer; @@ -941,43 +938,24 @@ static void uv_heartbeat_enable(int cpu) /* also ensure that boot cpu is enabled */ cpu = 0; } + return 0; } #ifdef CONFIG_HOTPLUG_CPU -static void uv_heartbeat_disable(int cpu) +static int uv_heartbeat_disable(unsigned int cpu) { if (uv_cpu_scir_info(cpu)->enabled) { uv_cpu_scir_info(cpu)->enabled = 0; del_timer(&uv_cpu_scir_info(cpu)->timer); } uv_set_cpu_scir_bits(cpu, 0xff); -} - -/* - * cpu hotplug notifier - */ -static int uv_scir_cpu_notify(struct notifier_block *self, unsigned long action, - void *hcpu) -{ - long cpu = (long)hcpu; - - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DOWN_FAILED: - case CPU_ONLINE: - uv_heartbeat_enable(cpu); - break; - case CPU_DOWN_PREPARE: - uv_heartbeat_disable(cpu); - break; - default: - break; - } - return NOTIFY_OK; + return 0; } static __init void uv_scir_register_cpu_notifier(void) { - hotcpu_notifier(uv_scir_cpu_notify, 0); + cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/x2apic-uvx:online", + uv_heartbeat_enable, uv_heartbeat_disable); } #else /* !CONFIG_HOTPLUG_CPU */ diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 2bd5c6ff7ee7..c62e015b126c 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -29,10 +29,13 @@ void common(void) { BLANK(); - OFFSET(TI_flags, thread_info, flags); - OFFSET(TI_status, thread_info, status); + OFFSET(TASK_threadsp, task_struct, thread.sp); +#ifdef CONFIG_CC_STACKPROTECTOR + OFFSET(TASK_stack_canary, task_struct, stack_canary); +#endif BLANK(); + OFFSET(TASK_TI_flags, task_struct, thread_info.flags); OFFSET(TASK_addr_limit, task_struct, thread.addr_limit); BLANK(); diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index ecdc1d217dc0..880aa093268d 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -57,6 +57,11 @@ void foo(void) /* Size of SYSENTER_stack */ DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack)); +#ifdef CONFIG_CC_STACKPROTECTOR + BLANK(); + OFFSET(stack_canary_offset, stack_canary, canary); +#endif + #if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE) BLANK(); OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index d875f97d4e0b..210927ee2e74 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -56,6 +56,11 @@ int main(void) OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); BLANK(); +#ifdef CONFIG_CC_STACKPROTECTOR + DEFINE(stack_canary_offset, offsetof(union irq_stack_union, stack_canary)); + BLANK(); +#endif + DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1); DEFINE(NR_syscalls, sizeof(syscalls_64)); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f5c69d8974e1..b81fe2d63e15 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -669,6 +669,17 @@ static void init_amd_gh(struct cpuinfo_x86 *c) set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); } +#define MSR_AMD64_DE_CFG 0xC0011029 + +static void init_amd_ln(struct cpuinfo_x86 *c) +{ + /* + * Apply erratum 665 fix unconditionally so machines without a BIOS + * fix work. + */ + msr_set_bit(MSR_AMD64_DE_CFG, 31); +} + static void init_amd_bd(struct cpuinfo_x86 *c) { u64 value; @@ -726,6 +737,7 @@ static void init_amd(struct cpuinfo_x86 *c) case 6: init_amd_k7(c); break; case 0xf: init_amd_k8(c); break; case 0x10: init_amd_gh(c); break; + case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 809eda03c527..9bd910a7dd0a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -804,21 +804,20 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) identify_cpu_without_cpuid(c); /* cyrix could have cpuid enabled via c_identify()*/ - if (!have_cpuid_p()) - return; - - cpu_detect(c); - get_cpu_vendor(c); - get_cpu_cap(c); + if (have_cpuid_p()) { + cpu_detect(c); + get_cpu_vendor(c); + get_cpu_cap(c); - if (this_cpu->c_early_init) - this_cpu->c_early_init(c); + if (this_cpu->c_early_init) + this_cpu->c_early_init(c); - c->cpu_index = 0; - filter_cpuid_features(c, false); + c->cpu_index = 0; + filter_cpuid_features(c, false); - if (this_cpu->c_bsp_init) - this_cpu->c_bsp_init(c); + if (this_cpu->c_bsp_init) + this_cpu->c_bsp_init(c); + } setup_force_cpu_cap(X86_FEATURE_ALWAYS); fpu__init_system(c); @@ -1265,9 +1264,14 @@ static __init int setup_disablecpuid(char *arg) __setup("clearcpuid=", setup_disablecpuid); #ifdef CONFIG_X86_64 -struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table }; -struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1, - (unsigned long) debug_idt_table }; +struct desc_ptr idt_descr __ro_after_init = { + .size = NR_VECTORS * 16 - 1, + .address = (unsigned long) idt_table, +}; +const struct desc_ptr debug_idt_descr = { + .size = NR_VECTORS * 16 - 1, + .address = (unsigned long) debug_idt_table, +}; DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE) __visible; @@ -1281,7 +1285,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned = EXPORT_PER_CPU_SYMBOL(current_task); DEFINE_PER_CPU(char *, irq_stack_ptr) = - init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64; + init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE; DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; @@ -1305,11 +1309,6 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks /* May not be marked __init: used by software suspend */ void syscall_init(void) { - /* - * LSTAR and STAR live in a bit strange symbiosis. - * They both write to the same internal register. STAR allows to - * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip. - */ wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 27e46658ebe3..35691a6b0d32 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -86,3 +86,14 @@ bool __init hypervisor_x2apic_available(void) x86_hyper->x2apic_available && x86_hyper->x2apic_available(); } + +void hypervisor_pin_vcpu(int cpu) +{ + if (!x86_hyper) + return; + + if (x86_hyper->pin_vcpu) + x86_hyper->pin_vcpu(cpu); + else + WARN_ONCE(1, "vcpu pinning requested but not supported!\n"); +} diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 79d8ec849468..a7fdf453d895 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -41,6 +41,7 @@ #include <linux/debugfs.h> #include <linux/irq_work.h> #include <linux/export.h> +#include <linux/jump_label.h> #include <asm/processor.h> #include <asm/traps.h> @@ -292,6 +293,13 @@ static void print_mce(struct mce *m) if (m->misc) pr_cont("MISC %llx ", m->misc); + if (mce_flags.smca) { + if (m->synd) + pr_cont("SYND %llx ", m->synd); + if (m->ipid) + pr_cont("IPID %llx ", m->ipid); + } + pr_cont("\n"); /* * Note this output is parsed by external tools and old fields @@ -568,6 +576,7 @@ static void mce_read_aux(struct mce *m, int i) { if (m->status & MCI_STATUS_MISCV) m->misc = mce_rdmsrl(msr_ops.misc(i)); + if (m->status & MCI_STATUS_ADDRV) { m->addr = mce_rdmsrl(msr_ops.addr(i)); @@ -579,6 +588,23 @@ static void mce_read_aux(struct mce *m, int i) m->addr >>= shift; m->addr <<= shift; } + + /* + * Extract [55:<lsb>] where lsb is the least significant + * *valid* bit of the address bits. + */ + if (mce_flags.smca) { + u8 lsb = (m->addr >> 56) & 0x3f; + + m->addr &= GENMASK_ULL(55, lsb); + } + } + + if (mce_flags.smca) { + m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i)); + + if (m->status & MCI_STATUS_SYNDV) + m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i)); } } @@ -1633,17 +1659,6 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (c->x86 == 6 && c->x86_model == 45) quirk_no_way_out = quirk_sandybridge_ifu; - /* - * MCG_CAP.MCG_SER_P is necessary but not sufficient to know - * whether this processor will actually generate recoverable - * machine checks. Check to see if this is an E7 model Xeon. - * We can't do a model number check because E5 and E7 use the - * same model number. E5 doesn't support recovery, E7 does. - */ - if (mca_cfg.recovery || (mca_cfg.ser && - !strncmp(c->x86_model_id, - "Intel(R) Xeon(R) CPU E7-", 24))) - set_cpu_cap(c, X86_FEATURE_MCE_RECOVERY); } if (cfg->monarch_timeout < 0) cfg->monarch_timeout = 0; @@ -2080,6 +2095,7 @@ void mce_disable_bank(int bank) * mce=bootlog Log MCEs from before booting. Disabled by default on AMD. * mce=nobootlog Don't log MCEs from before booting. * mce=bios_cmci_threshold Don't program the CMCI threshold + * mce=recovery force enable memcpy_mcsafe() */ static int __init mcheck_enable(char *str) { @@ -2676,8 +2692,14 @@ static int __init mcheck_debugfs_init(void) static int __init mcheck_debugfs_init(void) { return -EINVAL; } #endif +DEFINE_STATIC_KEY_FALSE(mcsafe_key); +EXPORT_SYMBOL_GPL(mcsafe_key); + static int __init mcheck_late_init(void) { + if (mca_cfg.recovery) + static_branch_inc(&mcsafe_key); + mcheck_debugfs_init(); /* diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 7b7f3be783d4..9b5403462936 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -20,6 +20,7 @@ #include <linux/init.h> #include <linux/cpu.h> #include <linux/smp.h> +#include <linux/string.h> #include <asm/amd_nb.h> #include <asm/apic.h> @@ -63,34 +64,71 @@ static const char * const th_names[] = { "execution_unit", }; -/* Define HWID to IP type mappings for Scalable MCA */ -struct amd_hwid amd_hwids[] = { - [SMCA_F17H_CORE] = { "f17h_core", 0xB0 }, - [SMCA_DF] = { "data_fabric", 0x2E }, - [SMCA_UMC] = { "umc", 0x96 }, - [SMCA_PB] = { "param_block", 0x5 }, - [SMCA_PSP] = { "psp", 0xFF }, - [SMCA_SMU] = { "smu", 0x1 }, +static const char * const smca_umc_block_names[] = { + "dram_ecc", + "misc_umc" }; -EXPORT_SYMBOL_GPL(amd_hwids); - -const char * const amd_core_mcablock_names[] = { - [SMCA_LS] = "load_store", - [SMCA_IF] = "insn_fetch", - [SMCA_L2_CACHE] = "l2_cache", - [SMCA_DE] = "decode_unit", - [RES] = "", - [SMCA_EX] = "execution_unit", - [SMCA_FP] = "floating_point", - [SMCA_L3_CACHE] = "l3_cache", + +struct smca_bank_name smca_bank_names[] = { + [SMCA_LS] = { "load_store", "Load Store Unit" }, + [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" }, + [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" }, + [SMCA_DE] = { "decode_unit", "Decode Unit" }, + [SMCA_EX] = { "execution_unit", "Execution Unit" }, + [SMCA_FP] = { "floating_point", "Floating Point Unit" }, + [SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" }, + [SMCA_CS] = { "coherent_slave", "Coherent Slave" }, + [SMCA_PIE] = { "pie", "Power, Interrupts, etc." }, + [SMCA_UMC] = { "umc", "Unified Memory Controller" }, + [SMCA_PB] = { "param_block", "Parameter Block" }, + [SMCA_PSP] = { "psp", "Platform Security Processor" }, + [SMCA_SMU] = { "smu", "System Management Unit" }, }; -EXPORT_SYMBOL_GPL(amd_core_mcablock_names); +EXPORT_SYMBOL_GPL(smca_bank_names); + +static struct smca_hwid_mcatype smca_hwid_mcatypes[] = { + /* { bank_type, hwid_mcatype, xec_bitmap } */ + + /* ZN Core (HWID=0xB0) MCA types */ + { SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFEF }, + { SMCA_IF, HWID_MCATYPE(0xB0, 0x1), 0x3FFF }, + { SMCA_L2_CACHE, HWID_MCATYPE(0xB0, 0x2), 0xF }, + { SMCA_DE, HWID_MCATYPE(0xB0, 0x3), 0x1FF }, + /* HWID 0xB0 MCATYPE 0x4 is Reserved */ + { SMCA_EX, HWID_MCATYPE(0xB0, 0x5), 0x7FF }, + { SMCA_FP, HWID_MCATYPE(0xB0, 0x6), 0x7F }, + { SMCA_L3_CACHE, HWID_MCATYPE(0xB0, 0x7), 0xFF }, + + /* Data Fabric MCA types */ + { SMCA_CS, HWID_MCATYPE(0x2E, 0x0), 0x1FF }, + { SMCA_PIE, HWID_MCATYPE(0x2E, 0x1), 0xF }, + + /* Unified Memory Controller MCA type */ + { SMCA_UMC, HWID_MCATYPE(0x96, 0x0), 0x3F }, + + /* Parameter Block MCA type */ + { SMCA_PB, HWID_MCATYPE(0x05, 0x0), 0x1 }, + + /* Platform Security Processor MCA type */ + { SMCA_PSP, HWID_MCATYPE(0xFF, 0x0), 0x1 }, -const char * const amd_df_mcablock_names[] = { - [SMCA_CS] = "coherent_slave", - [SMCA_PIE] = "pie", + /* System Management Unit MCA type */ + { SMCA_SMU, HWID_MCATYPE(0x01, 0x0), 0x1 }, }; -EXPORT_SYMBOL_GPL(amd_df_mcablock_names); + +struct smca_bank_info smca_banks[MAX_NR_BANKS]; +EXPORT_SYMBOL_GPL(smca_banks); + +/* + * In SMCA enabled processors, we can have multiple banks for a given IP type. + * So to define a unique name for each bank, we use a temp c-string to append + * the MCA_IPID[InstanceId] to type's name in get_name(). + * + * InstanceId is 32 bits which is 8 characters. Make sure MAX_MCATYPE_NAME_LEN + * is greater than 8 plus 1 (for underscore) plus length of longest type name. + */ +#define MAX_MCATYPE_NAME_LEN 30 +static char buf_mcatype[MAX_MCATYPE_NAME_LEN]; static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks); static DEFINE_PER_CPU(unsigned int, bank_map); /* see which banks are on */ @@ -108,6 +146,36 @@ void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt; * CPU Initialization */ +static void get_smca_bank_info(unsigned int bank) +{ + unsigned int i, hwid_mcatype, cpu = smp_processor_id(); + struct smca_hwid_mcatype *type; + u32 high, instanceId; + u16 hwid, mcatype; + + /* Collect bank_info using CPU 0 for now. */ + if (cpu) + return; + + if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &instanceId, &high)) { + pr_warn("Failed to read MCA_IPID for bank %d\n", bank); + return; + } + + hwid = high & MCI_IPID_HWID; + mcatype = (high & MCI_IPID_MCATYPE) >> 16; + hwid_mcatype = HWID_MCATYPE(hwid, mcatype); + + for (i = 0; i < ARRAY_SIZE(smca_hwid_mcatypes); i++) { + type = &smca_hwid_mcatypes[i]; + if (hwid_mcatype == type->hwid_mcatype) { + smca_banks[bank].type = type; + smca_banks[bank].type_instance = instanceId; + break; + } + } +} + struct thresh_restart { struct threshold_block *b; int reset; @@ -293,7 +361,7 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c) wrmsr(MSR_CU_DEF_ERR, low, high); } -static u32 get_block_address(u32 current_addr, u32 low, u32 high, +static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 high, unsigned int bank, unsigned int block) { u32 addr = 0, offset = 0; @@ -309,13 +377,13 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high, */ u32 low, high; - if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) + if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) return addr; if (!(low & MCI_CONFIG_MCAX)) return addr; - if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) && + if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) && (low & MASK_BLKPTR_LO)) addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); } @@ -395,6 +463,20 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, */ smca_high &= ~BIT(2); + /* + * SMCA sets the Deferred Error Interrupt type per bank. + * + * MCA_CONFIG[DeferredIntTypeSupported] is bit 5, and tells us + * if the DeferredIntType bit field is available. + * + * MCA_CONFIG[DeferredIntType] is bits [38:37] ([6:5] in the + * high portion of the MSR). OS should set this to 0x1 to enable + * APIC based interrupt. First, check that no interrupt has been + * set. + */ + if ((smca_low & BIT(5)) && !((smca_high >> 5) & 0x3)) + smca_high |= BIT(5); + wrmsr(smca_addr, smca_low, smca_high); } @@ -421,12 +503,15 @@ out: void mce_amd_feature_init(struct cpuinfo_x86 *c) { u32 low = 0, high = 0, address = 0; - unsigned int bank, block; + unsigned int bank, block, cpu = smp_processor_id(); int offset = -1; for (bank = 0; bank < mca_cfg.banks; ++bank) { + if (mce_flags.smca) + get_smca_bank_info(bank); + for (block = 0; block < NR_BLOCKS; ++block) { - address = get_block_address(address, low, high, bank, block); + address = get_block_address(cpu, address, low, high, bank, block); if (!address) break; @@ -476,9 +561,27 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) if (threshold_err) m.misc = misc; - if (m.status & MCI_STATUS_ADDRV) + if (m.status & MCI_STATUS_ADDRV) { rdmsrl(msr_addr, m.addr); + /* + * Extract [55:<lsb>] where lsb is the least significant + * *valid* bit of the address bits. + */ + if (mce_flags.smca) { + u8 lsb = (m.addr >> 56) & 0x3f; + + m.addr &= GENMASK_ULL(55, lsb); + } + } + + if (mce_flags.smca) { + rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), m.ipid); + + if (m.status & MCI_STATUS_SYNDV) + rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m.synd); + } + mce_log(&m); wrmsrl(msr_status, 0); @@ -541,15 +644,14 @@ static void amd_deferred_error_interrupt(void) static void amd_threshold_interrupt(void) { u32 low = 0, high = 0, address = 0; - int cpu = smp_processor_id(); - unsigned int bank, block; + unsigned int bank, block, cpu = smp_processor_id(); /* assume first bank caused it */ for (bank = 0; bank < mca_cfg.banks; ++bank) { if (!(per_cpu(bank_map, cpu) & (1 << bank))) continue; for (block = 0; block < NR_BLOCKS; ++block) { - address = get_block_address(address, low, high, bank, block); + address = get_block_address(cpu, address, low, high, bank, block); if (!address) break; @@ -713,6 +815,34 @@ static struct kobj_type threshold_ktype = { .default_attrs = default_attrs, }; +static const char *get_name(unsigned int bank, struct threshold_block *b) +{ + unsigned int bank_type; + + if (!mce_flags.smca) { + if (b && bank == 4) + return bank4_names(b); + + return th_names[bank]; + } + + if (!smca_banks[bank].type) + return NULL; + + bank_type = smca_banks[bank].type->bank_type; + + if (b && bank_type == SMCA_UMC) { + if (b->block < ARRAY_SIZE(smca_umc_block_names)) + return smca_umc_block_names[b->block]; + return NULL; + } + + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, + "%s_%x", smca_bank_names[bank_type].name, + smca_banks[bank].type_instance); + return buf_mcatype; +} + static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, unsigned int block, u32 address) { @@ -767,11 +897,11 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, err = kobject_init_and_add(&b->kobj, &threshold_ktype, per_cpu(threshold_banks, cpu)[bank]->kobj, - (bank == 4 ? bank4_names(b) : th_names[bank])); + get_name(bank, b)); if (err) goto out_free; recurse: - address = get_block_address(address, low, high, bank, ++block); + address = get_block_address(cpu, address, low, high, bank, ++block); if (!address) return 0; @@ -822,7 +952,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) struct device *dev = per_cpu(mce_device, cpu); struct amd_northbridge *nb = NULL; struct threshold_bank *b = NULL; - const char *name = th_names[bank]; + const char *name = get_name(bank, NULL); int err = 0; if (is_shared_bank(bank)) { @@ -869,7 +999,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) } } - err = allocate_threshold_blocks(cpu, bank, 0, MSR_IA32_MCx_MISC(bank)); + err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank)); if (!err) goto out; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index b816971f5da4..620ab06bcf45 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -54,6 +54,7 @@ static LIST_HEAD(pcache); */ static u8 *container; static size_t container_size; +static bool ucode_builtin; static u32 ucode_new_rev; static u8 amd_ucode_patch[PATCH_MAX_SIZE]; @@ -281,18 +282,22 @@ static bool __init load_builtin_amd_microcode(struct cpio_data *cp, void __init load_ucode_amd_bsp(unsigned int family) { struct cpio_data cp; + bool *builtin; void **data; size_t *size; #ifdef CONFIG_X86_32 data = (void **)__pa_nodebug(&ucode_cpio.data); size = (size_t *)__pa_nodebug(&ucode_cpio.size); + builtin = (bool *)__pa_nodebug(&ucode_builtin); #else data = &ucode_cpio.data; size = &ucode_cpio.size; + builtin = &ucode_builtin; #endif - if (!load_builtin_amd_microcode(&cp, family)) + *builtin = load_builtin_amd_microcode(&cp, family); + if (!*builtin) cp = find_ucode_in_initrd(); if (!(cp.data && cp.size)) @@ -373,7 +378,8 @@ void load_ucode_amd_ap(void) return; /* Add CONFIG_RANDOMIZE_MEMORY offset. */ - cont += PAGE_OFFSET - __PAGE_OFFSET_BASE; + if (!ucode_builtin) + cont += PAGE_OFFSET - __PAGE_OFFSET_BASE; eax = cpuid_eax(0x00000001); eq = (struct equiv_cpu_entry *)(cont + CONTAINER_HDR_SZ); @@ -439,7 +445,8 @@ int __init save_microcode_in_initrd_amd(void) container = cont_va; /* Add CONFIG_RANDOMIZE_MEMORY offset. */ - container += PAGE_OFFSET - __PAGE_OFFSET_BASE; + if (!ucode_builtin) + container += PAGE_OFFSET - __PAGE_OFFSET_BASE; eax = cpuid_eax(0x00000001); eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index df04b2d033f6..5ce5155f0695 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -558,55 +558,36 @@ static struct syscore_ops mc_syscore_ops = { .resume = mc_bp_resume, }; -static int -mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) +static int mc_cpu_online(unsigned int cpu) { - unsigned int cpu = (unsigned long)hcpu; struct device *dev; dev = get_cpu_device(cpu); + microcode_update_cpu(cpu); + pr_debug("CPU%d added\n", cpu); - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_ONLINE: - microcode_update_cpu(cpu); - pr_debug("CPU%d added\n", cpu); - /* - * "break" is missing on purpose here because we want to fall - * through in order to create the sysfs group. - */ - - case CPU_DOWN_FAILED: - if (sysfs_create_group(&dev->kobj, &mc_attr_group)) - pr_err("Failed to create group for CPU%d\n", cpu); - break; + if (sysfs_create_group(&dev->kobj, &mc_attr_group)) + pr_err("Failed to create group for CPU%d\n", cpu); + return 0; +} - case CPU_DOWN_PREPARE: - /* Suspend is in progress, only remove the interface */ - sysfs_remove_group(&dev->kobj, &mc_attr_group); - pr_debug("CPU%d removed\n", cpu); - break; +static int mc_cpu_down_prep(unsigned int cpu) +{ + struct device *dev; + dev = get_cpu_device(cpu); + /* Suspend is in progress, only remove the interface */ + sysfs_remove_group(&dev->kobj, &mc_attr_group); + pr_debug("CPU%d removed\n", cpu); /* - * case CPU_DEAD: - * * When a CPU goes offline, don't free up or invalidate the copy of * the microcode in kernel memory, so that we can reuse it when the * CPU comes back online without unnecessarily requesting the userspace * for it again. */ - } - - /* The CPU refused to come up during a system resume */ - if (action == CPU_UP_CANCELED_FROZEN) - microcode_fini_cpu(cpu); - - return NOTIFY_OK; + return 0; } -static struct notifier_block mc_cpu_notifier = { - .notifier_call = mc_cpu_callback, -}; - static struct attribute *cpu_root_microcode_attrs[] = { &dev_attr_reload.attr, NULL @@ -665,7 +646,8 @@ int __init microcode_init(void) goto out_ucode_group; register_syscore_ops(&mc_syscore_ops); - register_hotcpu_notifier(&mc_cpu_notifier); + cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online", + mc_cpu_online, mc_cpu_down_prep); pr_info("Microcode Update Driver: v" MICROCODE_VERSION " <tigran@aivazian.fsnet.co.uk>, Peter Oruba\n"); diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 28f1b54b7fad..24e87e74990d 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -72,14 +72,14 @@ static DEFINE_MUTEX(mtrr_mutex); u64 size_or_mask, size_and_mask; static bool mtrr_aps_delayed_init; -static const struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM]; +static const struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM] __ro_after_init; const struct mtrr_ops *mtrr_if; static void set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type); -void set_mtrr_ops(const struct mtrr_ops *ops) +void __init set_mtrr_ops(const struct mtrr_ops *ops) { if (ops->vendor && ops->vendor < X86_VENDOR_NUM) mtrr_ops[ops->vendor] = ops; diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 6c7ced07d16d..ad8bd763efa5 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -54,7 +54,7 @@ void fill_mtrr_var_range(unsigned int index, bool get_mtrr_state(void); void mtrr_bp_pat_init(void); -extern void set_mtrr_ops(const struct mtrr_ops *ops); +extern void __init set_mtrr_ops(const struct mtrr_ops *ops); extern u64 size_or_mask, size_and_mask; extern const struct mtrr_ops *mtrr_if; diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 92e8f0a7159c..9b7cf5c28f5f 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -17,7 +17,7 @@ #include <linux/sysfs.h> #include <asm/stacktrace.h> - +#include <asm/unwind.h> int panic_on_unrecovered_nmi; int panic_on_io_nmi; @@ -25,11 +25,29 @@ unsigned int code_bytes = 64; int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE; static int die_counter; +bool in_task_stack(unsigned long *stack, struct task_struct *task, + struct stack_info *info) +{ + unsigned long *begin = task_stack_page(task); + unsigned long *end = task_stack_page(task) + THREAD_SIZE; + + if (stack < begin || stack >= end) + return false; + + info->type = STACK_TYPE_TASK; + info->begin = begin; + info->end = end; + info->next_sp = NULL; + + return true; +} + static void printk_stack_address(unsigned long address, int reliable, - void *data) + char *log_lvl) { + touch_nmi_watchdog(); printk("%s [<%p>] %s%pB\n", - (char *)data, (void *)address, reliable ? "" : "? ", + log_lvl, (void *)address, reliable ? "" : "? ", (void *)address); } @@ -38,176 +56,120 @@ void printk_address(unsigned long address) pr_cont(" [<%p>] %pS\n", (void *)address, (void *)address); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -static void -print_ftrace_graph_addr(unsigned long addr, void *data, - const struct stacktrace_ops *ops, - struct task_struct *task, int *graph) +void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, char *log_lvl) { - unsigned long ret_addr; - int index; - - if (addr != (unsigned long)return_to_handler) - return; - - index = task->curr_ret_stack; - - if (!task->ret_stack || index < *graph) - return; - - index -= *graph; - ret_addr = task->ret_stack[index].ret; - - ops->address(data, ret_addr, 1); + struct unwind_state state; + struct stack_info stack_info = {0}; + unsigned long visit_mask = 0; + int graph_idx = 0; - (*graph)++; -} -#else -static inline void -print_ftrace_graph_addr(unsigned long addr, void *data, - const struct stacktrace_ops *ops, - struct task_struct *task, int *graph) -{ } -#endif - -/* - * x86-64 can have up to three kernel stacks: - * process stack - * interrupt stack - * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack - */ - -static inline int valid_stack_ptr(struct task_struct *task, - void *p, unsigned int size, void *end) -{ - void *t = task_stack_page(task); - if (end) { - if (p < end && p >= (end-THREAD_SIZE)) - return 1; - else - return 0; - } - return p >= t && p < t + THREAD_SIZE - size; -} + printk("%sCall Trace:\n", log_lvl); -unsigned long -print_context_stack(struct task_struct *task, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data, - unsigned long *end, int *graph) -{ - struct stack_frame *frame = (struct stack_frame *)bp; + unwind_start(&state, task, regs, stack); /* - * If we overflowed the stack into a guard page, jump back to the - * bottom of the usable stack. + * Iterate through the stacks, starting with the current stack pointer. + * Each stack has a pointer to the next one. + * + * x86-64 can have several stacks: + * - task stack + * - interrupt stack + * - HW exception stacks (double fault, nmi, debug, mce) + * + * x86-32 can have up to three stacks: + * - task stack + * - softirq stack + * - hardirq stack */ - if ((unsigned long)task_stack_page(task) - (unsigned long)stack < - PAGE_SIZE) - stack = (unsigned long *)task_stack_page(task); - - while (valid_stack_ptr(task, stack, sizeof(*stack), end)) { - unsigned long addr; - - addr = *stack; - if (__kernel_text_address(addr)) { - if ((unsigned long) stack == bp + sizeof(long)) { - ops->address(data, addr, 1); - frame = frame->next_frame; - bp = (unsigned long) frame; - } else { - ops->address(data, addr, 0); - } - print_ftrace_graph_addr(addr, data, ops, task, graph); - } - stack++; - } - return bp; -} -EXPORT_SYMBOL_GPL(print_context_stack); - -unsigned long -print_context_stack_bp(struct task_struct *task, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data, - unsigned long *end, int *graph) -{ - struct stack_frame *frame = (struct stack_frame *)bp; - unsigned long *ret_addr = &frame->return_address; + for (; stack; stack = stack_info.next_sp) { + const char *str_begin, *str_end; - while (valid_stack_ptr(task, ret_addr, sizeof(*ret_addr), end)) { - unsigned long addr = *ret_addr; + /* + * If we overflowed the task stack into a guard page, jump back + * to the bottom of the usable stack. + */ + if (task_stack_page(task) - (void *)stack < PAGE_SIZE) + stack = task_stack_page(task); - if (!__kernel_text_address(addr)) + if (get_stack_info(stack, task, &stack_info, &visit_mask)) break; - if (ops->address(data, addr, 1)) - break; - frame = frame->next_frame; - ret_addr = &frame->return_address; - print_ftrace_graph_addr(addr, data, ops, task, graph); - } - - return (unsigned long)frame; -} -EXPORT_SYMBOL_GPL(print_context_stack_bp); - -static int print_trace_stack(void *data, char *name) -{ - printk("%s <%s> ", (char *)data, name); - return 0; -} - -/* - * Print one address/symbol entries per line. - */ -static int print_trace_address(void *data, unsigned long addr, int reliable) -{ - touch_nmi_watchdog(); - printk_stack_address(addr, reliable, data); - return 0; -} - -static const struct stacktrace_ops print_trace_ops = { - .stack = print_trace_stack, - .address = print_trace_address, - .walk_stack = print_context_stack, -}; - -void -show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl) -{ - printk("%sCall Trace:\n", log_lvl); - dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl); -} + stack_type_str(stack_info.type, &str_begin, &str_end); + if (str_begin) + printk("%s <%s> ", log_lvl, str_begin); + + /* + * Scan the stack, printing any text addresses we find. At the + * same time, follow proper stack frames with the unwinder. + * + * Addresses found during the scan which are not reported by + * the unwinder are considered to be additional clues which are + * sometimes useful for debugging and are prefixed with '?'. + * This also serves as a failsafe option in case the unwinder + * goes off in the weeds. + */ + for (; stack < stack_info.end; stack++) { + unsigned long real_addr; + int reliable = 0; + unsigned long addr = *stack; + unsigned long *ret_addr_p = + unwind_get_return_address_ptr(&state); + + if (!__kernel_text_address(addr)) + continue; + + if (stack == ret_addr_p) + reliable = 1; + + /* + * When function graph tracing is enabled for a + * function, its return address on the stack is + * replaced with the address of an ftrace handler + * (return_to_handler). In that case, before printing + * the "real" address, we want to print the handler + * address as an "unreliable" hint that function graph + * tracing was involved. + */ + real_addr = ftrace_graph_ret_addr(task, &graph_idx, + addr, stack); + if (real_addr != addr) + printk_stack_address(addr, 0, log_lvl); + printk_stack_address(real_addr, reliable, log_lvl); + + if (!reliable) + continue; + + /* + * Get the next frame from the unwinder. No need to + * check for an error: if anything goes wrong, the rest + * of the addresses will just be printed as unreliable. + */ + unwind_next_frame(&state); + } -void show_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp) -{ - show_trace_log_lvl(task, regs, stack, bp, ""); + if (str_end) + printk("%s <%s> ", log_lvl, str_end); + } } void show_stack(struct task_struct *task, unsigned long *sp) { - unsigned long bp = 0; - unsigned long stack; + task = task ? : current; /* * Stack frames below this one aren't interesting. Don't show them * if we're printing for %current. */ - if (!sp && (!task || task == current)) { - sp = &stack; - bp = stack_frame(current, NULL); - } + if (!sp && task == current) + sp = get_stack_pointer(current, NULL); - show_stack_log_lvl(task, NULL, sp, bp, ""); + show_stack_log_lvl(task, NULL, sp, ""); } void show_stack_regs(struct pt_regs *regs) { - show_stack_log_lvl(current, regs, (unsigned long *)regs->sp, regs->bp, ""); + show_stack_log_lvl(current, regs, NULL, ""); } static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED; diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 09675712eba8..06eb322b5f9f 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -16,93 +16,121 @@ #include <asm/stacktrace.h> -static void *is_irq_stack(void *p, void *irq) +void stack_type_str(enum stack_type type, const char **begin, const char **end) { - if (p < irq || p >= (irq + THREAD_SIZE)) - return NULL; - return irq + THREAD_SIZE; + switch (type) { + case STACK_TYPE_IRQ: + case STACK_TYPE_SOFTIRQ: + *begin = "IRQ"; + *end = "EOI"; + break; + default: + *begin = NULL; + *end = NULL; + } } - -static void *is_hardirq_stack(unsigned long *stack, int cpu) +static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info) { - void *irq = per_cpu(hardirq_stack, cpu); + unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack); + unsigned long *end = begin + (THREAD_SIZE / sizeof(long)); - return is_irq_stack(stack, irq); -} + /* + * This is a software stack, so 'end' can be a valid stack pointer. + * It just means the stack is empty. + */ + if (stack < begin || stack > end) + return false; -static void *is_softirq_stack(unsigned long *stack, int cpu) -{ - void *irq = per_cpu(softirq_stack, cpu); + info->type = STACK_TYPE_IRQ; + info->begin = begin; + info->end = end; - return is_irq_stack(stack, irq); + /* + * See irq_32.c -- the next stack pointer is stored at the beginning of + * the stack. + */ + info->next_sp = (unsigned long *)*begin; + + return true; } -void dump_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data) +static bool in_softirq_stack(unsigned long *stack, struct stack_info *info) { - const unsigned cpu = get_cpu(); - int graph = 0; - u32 *prev_esp; + unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack); + unsigned long *end = begin + (THREAD_SIZE / sizeof(long)); - if (!task) - task = current; + /* + * This is a software stack, so 'end' can be a valid stack pointer. + * It just means the stack is empty. + */ + if (stack < begin || stack > end) + return false; - if (!stack) { - unsigned long dummy; + info->type = STACK_TYPE_SOFTIRQ; + info->begin = begin; + info->end = end; - stack = &dummy; - if (task != current) - stack = (unsigned long *)task->thread.sp; - } + /* + * The next stack pointer is stored at the beginning of the stack. + * See irq_32.c. + */ + info->next_sp = (unsigned long *)*begin; - if (!bp) - bp = stack_frame(task, regs); + return true; +} - for (;;) { - void *end_stack; +int get_stack_info(unsigned long *stack, struct task_struct *task, + struct stack_info *info, unsigned long *visit_mask) +{ + if (!stack) + goto unknown; - end_stack = is_hardirq_stack(stack, cpu); - if (!end_stack) - end_stack = is_softirq_stack(stack, cpu); + task = task ? : current; - bp = ops->walk_stack(task, stack, bp, ops, data, - end_stack, &graph); + if (in_task_stack(stack, task, info)) + goto recursion_check; - /* Stop if not on irq stack */ - if (!end_stack) - break; + if (task != current) + goto unknown; - /* The previous esp is saved on the bottom of the stack */ - prev_esp = (u32 *)(end_stack - THREAD_SIZE); - stack = (unsigned long *)*prev_esp; - if (!stack) - break; + if (in_hardirq_stack(stack, info)) + goto recursion_check; - if (ops->stack(data, "IRQ") < 0) - break; - touch_nmi_watchdog(); + if (in_softirq_stack(stack, info)) + goto recursion_check; + + goto unknown; + +recursion_check: + /* + * Make sure we don't iterate through any given stack more than once. + * If it comes up a second time then there's something wrong going on: + * just break out and report an unknown stack type. + */ + if (visit_mask) { + if (*visit_mask & (1UL << info->type)) + goto unknown; + *visit_mask |= 1UL << info->type; } - put_cpu(); + + return 0; + +unknown: + info->type = STACK_TYPE_UNKNOWN; + return -EINVAL; } -EXPORT_SYMBOL(dump_trace); -void -show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl) +void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *sp, char *log_lvl) { unsigned long *stack; int i; - if (sp == NULL) { - if (regs) - sp = (unsigned long *)regs->sp; - else if (task) - sp = (unsigned long *)task->thread.sp; - else - sp = (unsigned long *)&sp; - } + if (!try_get_task_stack(task)) + return; + + sp = sp ? : get_stack_pointer(task, regs); stack = sp; for (i = 0; i < kstack_depth_to_print; i++) { @@ -117,7 +145,9 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, touch_nmi_watchdog(); } pr_cont("\n"); - show_trace_log_lvl(task, regs, sp, bp, log_lvl); + show_trace_log_lvl(task, regs, sp, log_lvl); + + put_task_stack(task); } @@ -139,7 +169,7 @@ void show_regs(struct pt_regs *regs) u8 *ip; pr_emerg("Stack:\n"); - show_stack_log_lvl(NULL, regs, ®s->sp, 0, KERN_EMERG); + show_stack_log_lvl(current, regs, NULL, KERN_EMERG); pr_emerg("Code:"); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 9ee4520ce83c..36cf1a498227 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -16,261 +16,145 @@ #include <asm/stacktrace.h> +static char *exception_stack_names[N_EXCEPTION_STACKS] = { + [ DOUBLEFAULT_STACK-1 ] = "#DF", + [ NMI_STACK-1 ] = "NMI", + [ DEBUG_STACK-1 ] = "#DB", + [ MCE_STACK-1 ] = "#MC", +}; -#define N_EXCEPTION_STACKS_END \ - (N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2) - -static char x86_stack_ids[][8] = { - [ DEBUG_STACK-1 ] = "#DB", - [ NMI_STACK-1 ] = "NMI", - [ DOUBLEFAULT_STACK-1 ] = "#DF", - [ MCE_STACK-1 ] = "#MC", -#if DEBUG_STKSZ > EXCEPTION_STKSZ - [ N_EXCEPTION_STACKS ... - N_EXCEPTION_STACKS_END ] = "#DB[?]" -#endif +static unsigned long exception_stack_sizes[N_EXCEPTION_STACKS] = { + [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, + [DEBUG_STACK - 1] = DEBUG_STKSZ }; -static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, - unsigned *usedp, char **idp) +void stack_type_str(enum stack_type type, const char **begin, const char **end) { - unsigned k; - - /* - * Iterate over all exception stacks, and figure out whether - * 'stack' is in one of them: - */ - for (k = 0; k < N_EXCEPTION_STACKS; k++) { - unsigned long end = per_cpu(orig_ist, cpu).ist[k]; - /* - * Is 'stack' above this exception frame's end? - * If yes then skip to the next frame. - */ - if (stack >= end) - continue; - /* - * Is 'stack' above this exception frame's start address? - * If yes then we found the right frame. - */ - if (stack >= end - EXCEPTION_STKSZ) { - /* - * Make sure we only iterate through an exception - * stack once. If it comes up for the second time - * then there's something wrong going on - just - * break out and return NULL: - */ - if (*usedp & (1U << k)) - break; - *usedp |= 1U << k; - *idp = x86_stack_ids[k]; - return (unsigned long *)end; - } - /* - * If this is a debug stack, and if it has a larger size than - * the usual exception stacks, then 'stack' might still - * be within the lower portion of the debug stack: - */ -#if DEBUG_STKSZ > EXCEPTION_STKSZ - if (k == DEBUG_STACK - 1 && stack >= end - DEBUG_STKSZ) { - unsigned j = N_EXCEPTION_STACKS - 1; - - /* - * Black magic. A large debug stack is composed of - * multiple exception stack entries, which we - * iterate through now. Dont look: - */ - do { - ++j; - end -= EXCEPTION_STKSZ; - x86_stack_ids[j][4] = '1' + - (j - N_EXCEPTION_STACKS); - } while (stack < end - EXCEPTION_STKSZ); - if (*usedp & (1U << j)) - break; - *usedp |= 1U << j; - *idp = x86_stack_ids[j]; - return (unsigned long *)end; - } -#endif + BUILD_BUG_ON(N_EXCEPTION_STACKS != 4); + + switch (type) { + case STACK_TYPE_IRQ: + *begin = "IRQ"; + *end = "EOI"; + break; + case STACK_TYPE_EXCEPTION ... STACK_TYPE_EXCEPTION_LAST: + *begin = exception_stack_names[type - STACK_TYPE_EXCEPTION]; + *end = "EOE"; + break; + default: + *begin = NULL; + *end = NULL; } - return NULL; } -static inline int -in_irq_stack(unsigned long *stack, unsigned long *irq_stack, - unsigned long *irq_stack_end) +static bool in_exception_stack(unsigned long *stack, struct stack_info *info) { - return (stack >= irq_stack && stack < irq_stack_end); -} - -static const unsigned long irq_stack_size = - (IRQ_STACK_SIZE - 64) / sizeof(unsigned long); - -enum stack_type { - STACK_IS_UNKNOWN, - STACK_IS_NORMAL, - STACK_IS_EXCEPTION, - STACK_IS_IRQ, -}; - -static enum stack_type -analyze_stack(int cpu, struct task_struct *task, unsigned long *stack, - unsigned long **stack_end, unsigned long *irq_stack, - unsigned *used, char **id) -{ - unsigned long addr; + unsigned long *begin, *end; + struct pt_regs *regs; + unsigned k; - addr = ((unsigned long)stack & (~(THREAD_SIZE - 1))); - if ((unsigned long)task_stack_page(task) == addr) - return STACK_IS_NORMAL; + BUILD_BUG_ON(N_EXCEPTION_STACKS != 4); - *stack_end = in_exception_stack(cpu, (unsigned long)stack, - used, id); - if (*stack_end) - return STACK_IS_EXCEPTION; + for (k = 0; k < N_EXCEPTION_STACKS; k++) { + end = (unsigned long *)raw_cpu_ptr(&orig_ist)->ist[k]; + begin = end - (exception_stack_sizes[k] / sizeof(long)); + regs = (struct pt_regs *)end - 1; - if (!irq_stack) - return STACK_IS_NORMAL; + if (stack < begin || stack >= end) + continue; - *stack_end = irq_stack; - irq_stack = irq_stack - irq_stack_size; + info->type = STACK_TYPE_EXCEPTION + k; + info->begin = begin; + info->end = end; + info->next_sp = (unsigned long *)regs->sp; - if (in_irq_stack(stack, irq_stack, *stack_end)) - return STACK_IS_IRQ; + return true; + } - return STACK_IS_UNKNOWN; + return false; } -/* - * x86-64 can have up to three kernel stacks: - * process stack - * interrupt stack - * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack - */ - -void dump_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data) +static bool in_irq_stack(unsigned long *stack, struct stack_info *info) { - const unsigned cpu = get_cpu(); - unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu); - unsigned long dummy; - unsigned used = 0; - int graph = 0; - int done = 0; - - if (!task) - task = current; - - if (!stack) { - if (regs) - stack = (unsigned long *)regs->sp; - else if (task != current) - stack = (unsigned long *)task->thread.sp; - else - stack = &dummy; - } + unsigned long *end = (unsigned long *)this_cpu_read(irq_stack_ptr); + unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long)); - if (!bp) - bp = stack_frame(task, regs); /* - * Print function call entries in all stacks, starting at the - * current stack address. If the stacks consist of nested - * exceptions + * This is a software stack, so 'end' can be a valid stack pointer. + * It just means the stack is empty. */ - while (!done) { - unsigned long *stack_end; - enum stack_type stype; - char *id; + if (stack < begin || stack > end) + return false; - stype = analyze_stack(cpu, task, stack, &stack_end, - irq_stack, &used, &id); + info->type = STACK_TYPE_IRQ; + info->begin = begin; + info->end = end; - /* Default finish unless specified to continue */ - done = 1; + /* + * The next stack pointer is the first thing pushed by the entry code + * after switching to the irq stack. + */ + info->next_sp = (unsigned long *)*(end - 1); - switch (stype) { + return true; +} - /* Break out early if we are on the thread stack */ - case STACK_IS_NORMAL: - break; +int get_stack_info(unsigned long *stack, struct task_struct *task, + struct stack_info *info, unsigned long *visit_mask) +{ + if (!stack) + goto unknown; - case STACK_IS_EXCEPTION: + task = task ? : current; - if (ops->stack(data, id) < 0) - break; + if (in_task_stack(stack, task, info)) + goto recursion_check; - bp = ops->walk_stack(task, stack, bp, ops, - data, stack_end, &graph); - ops->stack(data, "<EOE>"); - /* - * We link to the next stack via the - * second-to-last pointer (index -2 to end) in the - * exception stack: - */ - stack = (unsigned long *) stack_end[-2]; - done = 0; - break; + if (task != current) + goto unknown; - case STACK_IS_IRQ: + if (in_exception_stack(stack, info)) + goto recursion_check; - if (ops->stack(data, "IRQ") < 0) - break; - bp = ops->walk_stack(task, stack, bp, - ops, data, stack_end, &graph); - /* - * We link to the next stack (which would be - * the process stack normally) the last - * pointer (index -1 to end) in the IRQ stack: - */ - stack = (unsigned long *) (stack_end[-1]); - irq_stack = NULL; - ops->stack(data, "EOI"); - done = 0; - break; + if (in_irq_stack(stack, info)) + goto recursion_check; - case STACK_IS_UNKNOWN: - ops->stack(data, "UNK"); - break; - } - } + goto unknown; +recursion_check: /* - * This handles the process stack: + * Make sure we don't iterate through any given stack more than once. + * If it comes up a second time then there's something wrong going on: + * just break out and report an unknown stack type. */ - bp = ops->walk_stack(task, stack, bp, ops, data, NULL, &graph); - put_cpu(); + if (visit_mask) { + if (*visit_mask & (1UL << info->type)) + goto unknown; + *visit_mask |= 1UL << info->type; + } + + return 0; + +unknown: + info->type = STACK_TYPE_UNKNOWN; + return -EINVAL; } -EXPORT_SYMBOL(dump_trace); -void -show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl) +void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *sp, char *log_lvl) { unsigned long *irq_stack_end; unsigned long *irq_stack; unsigned long *stack; - int cpu; int i; - preempt_disable(); - cpu = smp_processor_id(); + if (!try_get_task_stack(task)) + return; - irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu)); - irq_stack = (unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE); + irq_stack_end = (unsigned long *)this_cpu_read(irq_stack_ptr); + irq_stack = irq_stack_end - (IRQ_STACK_SIZE / sizeof(long)); - /* - * Debugging aid: "show_stack(NULL, NULL);" prints the - * back trace for this cpu: - */ - if (sp == NULL) { - if (regs) - sp = (unsigned long *)regs->sp; - else if (task) - sp = (unsigned long *)task->thread.sp; - else - sp = (unsigned long *)&sp; - } + sp = sp ? : get_stack_pointer(task, regs); stack = sp; for (i = 0; i < kstack_depth_to_print; i++) { @@ -299,18 +183,17 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, stack++; touch_nmi_watchdog(); } - preempt_enable(); pr_cont("\n"); - show_trace_log_lvl(task, regs, sp, bp, log_lvl); + show_trace_log_lvl(task, regs, sp, log_lvl); + + put_task_stack(task); } void show_regs(struct pt_regs *regs) { int i; - unsigned long sp; - sp = regs->sp; show_regs_print_info(KERN_DEFAULT); __show_regs(regs, 1); @@ -325,8 +208,7 @@ void show_regs(struct pt_regs *regs) u8 *ip; printk(KERN_DEFAULT "Stack:\n"); - show_stack_log_lvl(NULL, regs, (unsigned long *)sp, - 0, KERN_DEFAULT); + show_stack_log_lvl(current, regs, NULL, KERN_DEFAULT); printk(KERN_DEFAULT "Code: "); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 621b501f8935..b85fe5f91c3f 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -40,8 +40,10 @@ * user can e.g. boot the original kernel with mem=1G while still booting the * next kernel with full memory. */ -struct e820map e820; -struct e820map e820_saved; +static struct e820map initial_e820 __initdata; +static struct e820map initial_e820_saved __initdata; +struct e820map *e820 __refdata = &initial_e820; +struct e820map *e820_saved __refdata = &initial_e820_saved; /* For PCI or other memory-mapped resources */ unsigned long pci_mem_start = 0xaeedbabe; @@ -58,8 +60,8 @@ e820_any_mapped(u64 start, u64 end, unsigned type) { int i; - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; + for (i = 0; i < e820->nr_map; i++) { + struct e820entry *ei = &e820->map[i]; if (type && ei->type != type) continue; @@ -81,8 +83,8 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type) { int i; - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; + for (i = 0; i < e820->nr_map; i++) { + struct e820entry *ei = &e820->map[i]; if (type && ei->type != type) continue; @@ -128,7 +130,7 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size, void __init e820_add_region(u64 start, u64 size, int type) { - __e820_add_region(&e820, start, size, type); + __e820_add_region(e820, start, size, type); } static void __init e820_print_type(u32 type) @@ -164,12 +166,12 @@ void __init e820_print_map(char *who) { int i; - for (i = 0; i < e820.nr_map; i++) { + for (i = 0; i < e820->nr_map; i++) { printk(KERN_INFO "%s: [mem %#018Lx-%#018Lx] ", who, - (unsigned long long) e820.map[i].addr, + (unsigned long long) e820->map[i].addr, (unsigned long long) - (e820.map[i].addr + e820.map[i].size - 1)); - e820_print_type(e820.map[i].type); + (e820->map[i].addr + e820->map[i].size - 1)); + e820_print_type(e820->map[i].type); printk(KERN_CONT "\n"); } } @@ -348,7 +350,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, * continue building up new bios map based on this * information */ - if (current_type != last_type || current_type == E820_PRAM) { + if (current_type != last_type) { if (last_type != 0) { new_bios[new_bios_entry].size = change_point[chgidx]->addr - last_addr; @@ -388,11 +390,11 @@ static int __init __append_e820_map(struct e820entry *biosmap, int nr_map) while (nr_map) { u64 start = biosmap->addr; u64 size = biosmap->size; - u64 end = start + size; + u64 end = start + size - 1; u32 type = biosmap->type; /* Overflow in 64 bits? Ignore the memory map. */ - if (start > end) + if (start > end && likely(size)) return -1; e820_add_region(start, size, type); @@ -493,13 +495,13 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start, u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, unsigned new_type) { - return __e820_update_range(&e820, start, size, old_type, new_type); + return __e820_update_range(e820, start, size, old_type, new_type); } static u64 __init e820_update_range_saved(u64 start, u64 size, unsigned old_type, unsigned new_type) { - return __e820_update_range(&e820_saved, start, size, old_type, + return __e820_update_range(e820_saved, start, size, old_type, new_type); } @@ -521,8 +523,8 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, e820_print_type(old_type); printk(KERN_CONT "\n"); - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; + for (i = 0; i < e820->nr_map; i++) { + struct e820entry *ei = &e820->map[i]; u64 final_start, final_end; u64 ei_end; @@ -566,15 +568,15 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, void __init update_e820(void) { - if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map)) + if (sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map)) return; printk(KERN_INFO "e820: modified physical RAM map:\n"); e820_print_map("modified"); } static void __init update_e820_saved(void) { - sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map), - &e820_saved.nr_map); + sanitize_e820_map(e820_saved->map, ARRAY_SIZE(e820_saved->map), + &e820_saved->nr_map); } #define MAX_GAP_END 0x100000000ull /* @@ -584,14 +586,14 @@ __init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, unsigned long start_addr, unsigned long long end_addr) { unsigned long long last; - int i = e820.nr_map; + int i = e820->nr_map; int found = 0; last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END; while (--i >= 0) { - unsigned long long start = e820.map[i].addr; - unsigned long long end = start + e820.map[i].size; + unsigned long long start = e820->map[i].addr; + unsigned long long end = start + e820->map[i].size; if (end < start_addr) continue; @@ -649,6 +651,33 @@ __init void e820_setup_gap(void) gapstart, gapstart + gapsize - 1); } +/* + * Called late during init, in free_initmem(). + * + * Initial e820 and e820_saved are largish __initdata arrays. + * Copy them to (usually much smaller) dynamically allocated area. + * This is done after all tweaks we ever do to them: + * all functions which modify them are __init functions, + * they won't exist after this point. + */ +__init void e820_reallocate_tables(void) +{ + struct e820map *n; + int size; + + size = offsetof(struct e820map, map) + sizeof(struct e820entry) * e820->nr_map; + n = kmalloc(size, GFP_KERNEL); + BUG_ON(!n); + memcpy(n, e820, size); + e820 = n; + + size = offsetof(struct e820map, map) + sizeof(struct e820entry) * e820_saved->nr_map; + n = kmalloc(size, GFP_KERNEL); + BUG_ON(!n); + memcpy(n, e820_saved, size); + e820_saved = n; +} + /** * Because of the size limitation of struct boot_params, only first * 128 E820 memory entries are passed to kernel via @@ -665,7 +694,7 @@ void __init parse_e820_ext(u64 phys_addr, u32 data_len) entries = sdata->len / sizeof(struct e820entry); extmap = (struct e820entry *)(sdata->data); __append_e820_map(extmap, entries); - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); early_memunmap(sdata, data_len); printk(KERN_INFO "e820: extended physical RAM map:\n"); e820_print_map("extended"); @@ -686,8 +715,8 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn) int i; unsigned long pfn = 0; - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; + for (i = 0; i < e820->nr_map; i++) { + struct e820entry *ei = &e820->map[i]; if (pfn < PFN_UP(ei->addr)) register_nosave_region(pfn, PFN_UP(ei->addr)); @@ -712,8 +741,8 @@ static int __init e820_mark_nvs_memory(void) { int i; - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; + for (i = 0; i < e820->nr_map; i++) { + struct e820entry *ei = &e820->map[i]; if (ei->type == E820_NVS) acpi_nvs_register(ei->addr, ei->size); @@ -754,22 +783,18 @@ u64 __init early_reserve_e820(u64 size, u64 align) /* * Find the highest page frame number we have available */ -static unsigned long __init e820_end_pfn(unsigned long limit_pfn) +static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) { int i; unsigned long last_pfn = 0; unsigned long max_arch_pfn = MAX_ARCH_PFN; - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; + for (i = 0; i < e820->nr_map; i++) { + struct e820entry *ei = &e820->map[i]; unsigned long start_pfn; unsigned long end_pfn; - /* - * Persistent memory is accounted as ram for purposes of - * establishing max_pfn and mem_map. - */ - if (ei->type != E820_RAM && ei->type != E820_PRAM) + if (ei->type != type) continue; start_pfn = ei->addr >> PAGE_SHIFT; @@ -794,15 +819,15 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn) } unsigned long __init e820_end_of_ram_pfn(void) { - return e820_end_pfn(MAX_ARCH_PFN); + return e820_end_pfn(MAX_ARCH_PFN, E820_RAM); } unsigned long __init e820_end_of_low_ram_pfn(void) { - return e820_end_pfn(1UL << (32-PAGE_SHIFT)); + return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_RAM); } -static void early_panic(char *msg) +static void __init early_panic(char *msg) { early_printk(msg); panic(msg); @@ -856,7 +881,7 @@ static int __init parse_memmap_one(char *p) */ saved_max_pfn = e820_end_of_ram_pfn(); #endif - e820.nr_map = 0; + e820->nr_map = 0; userdef = 1; return 0; } @@ -903,8 +928,8 @@ early_param("memmap", parse_memmap_opt); void __init finish_e820_parsing(void) { if (userdef) { - if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), - &e820.nr_map) < 0) + if (sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), + &e820->nr_map) < 0) early_panic("Invalid user supplied memory map"); printk(KERN_INFO "e820: user-defined physical RAM map:\n"); @@ -912,7 +937,7 @@ void __init finish_e820_parsing(void) } } -static const char *e820_type_to_string(int e820_type) +static const char *__init e820_type_to_string(int e820_type) { switch (e820_type) { case E820_RESERVED_KERN: @@ -926,7 +951,7 @@ static const char *e820_type_to_string(int e820_type) } } -static unsigned long e820_type_to_iomem_type(int e820_type) +static unsigned long __init e820_type_to_iomem_type(int e820_type) { switch (e820_type) { case E820_RESERVED_KERN: @@ -942,7 +967,7 @@ static unsigned long e820_type_to_iomem_type(int e820_type) } } -static unsigned long e820_type_to_iores_desc(int e820_type) +static unsigned long __init e820_type_to_iores_desc(int e820_type) { switch (e820_type) { case E820_ACPI: @@ -961,7 +986,7 @@ static unsigned long e820_type_to_iores_desc(int e820_type) } } -static bool do_mark_busy(u32 type, struct resource *res) +static bool __init do_mark_busy(u32 type, struct resource *res) { /* this is the legacy bios/dos rom-shadow + mmio region */ if (res->start < (1ULL<<20)) @@ -991,35 +1016,35 @@ void __init e820_reserve_resources(void) struct resource *res; u64 end; - res = alloc_bootmem(sizeof(struct resource) * e820.nr_map); + res = alloc_bootmem(sizeof(struct resource) * e820->nr_map); e820_res = res; - for (i = 0; i < e820.nr_map; i++) { - end = e820.map[i].addr + e820.map[i].size - 1; + for (i = 0; i < e820->nr_map; i++) { + end = e820->map[i].addr + e820->map[i].size - 1; if (end != (resource_size_t)end) { res++; continue; } - res->name = e820_type_to_string(e820.map[i].type); - res->start = e820.map[i].addr; + res->name = e820_type_to_string(e820->map[i].type); + res->start = e820->map[i].addr; res->end = end; - res->flags = e820_type_to_iomem_type(e820.map[i].type); - res->desc = e820_type_to_iores_desc(e820.map[i].type); + res->flags = e820_type_to_iomem_type(e820->map[i].type); + res->desc = e820_type_to_iores_desc(e820->map[i].type); /* * don't register the region that could be conflicted with * pci device BAR resource and insert them later in * pcibios_resource_survey() */ - if (do_mark_busy(e820.map[i].type, res)) { + if (do_mark_busy(e820->map[i].type, res)) { res->flags |= IORESOURCE_BUSY; insert_resource(&iomem_resource, res); } res++; } - for (i = 0; i < e820_saved.nr_map; i++) { - struct e820entry *entry = &e820_saved.map[i]; + for (i = 0; i < e820_saved->nr_map; i++) { + struct e820entry *entry = &e820_saved->map[i]; firmware_map_add_early(entry->addr, entry->addr + entry->size, e820_type_to_string(entry->type)); @@ -1027,7 +1052,7 @@ void __init e820_reserve_resources(void) } /* How much should we pad RAM ending depending on where it is? */ -static unsigned long ram_alignment(resource_size_t pos) +static unsigned long __init ram_alignment(resource_size_t pos) { unsigned long mb = pos >> 20; @@ -1051,7 +1076,7 @@ void __init e820_reserve_resources_late(void) struct resource *res; res = e820_res; - for (i = 0; i < e820.nr_map; i++) { + for (i = 0; i < e820->nr_map; i++) { if (!res->parent && res->end) insert_resource_expand_to_fit(&iomem_resource, res); res++; @@ -1061,8 +1086,8 @@ void __init e820_reserve_resources_late(void) * Try to bump up RAM regions to reasonable boundaries to * avoid stolen RAM: */ - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *entry = &e820.map[i]; + for (i = 0; i < e820->nr_map; i++) { + struct e820entry *entry = &e820->map[i]; u64 start, end; if (entry->type != E820_RAM) @@ -1110,7 +1135,7 @@ char *__init default_machine_specific_memory_setup(void) who = "BIOS-e801"; } - e820.nr_map = 0; + e820->nr_map = 0; e820_add_region(0, LOWMEMSIZE(), E820_RAM); e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM); } @@ -1124,7 +1149,7 @@ void __init setup_memory_map(void) char *who; who = x86_init.resources.memory_setup(); - memcpy(&e820_saved, &e820, sizeof(struct e820map)); + memcpy(e820_saved, e820, sizeof(struct e820map)); printk(KERN_INFO "e820: BIOS-provided physical RAM map:\n"); e820_print_map(who); } @@ -1141,8 +1166,8 @@ void __init memblock_x86_fill(void) */ memblock_allow_resize(); - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; + for (i = 0; i < e820->nr_map; i++) { + struct e820entry *ei = &e820->map[i]; end = ei->addr + ei->size; if (end != (resource_size_t)end) diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index de7501edb21c..18bb3a639197 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -555,7 +555,7 @@ intel_graphics_stolen(int num, int slot, int func, /* Mark this space as reserved */ e820_add_region(base, size, E820_RESERVED); - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); } static void __init intel_graphics_quirks(int num, int slot, int func) diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 93982aebb398..2f2b8c7ccb85 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -317,7 +317,6 @@ static void __init fpu__init_system_ctx_switch(void) on_boot_cpu = 0; WARN_ON_FPU(current->thread.fpu.fpstate_active); - current_thread_info()->status = 0; if (boot_cpu_has(X86_FEATURE_XSAVEOPT) && eagerfpu != DISABLE) eagerfpu = ENABLE; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index d036cfb4495d..8639bb2ae058 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -1029,7 +1029,7 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, } if (ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer) == -EBUSY) { + frame_pointer, parent) == -EBUSY) { *parent = old; return; } diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 6f8902b0d151..5f401262f12d 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -94,7 +94,7 @@ RESERVE_BRK(pagetables, INIT_MAP_SIZE) */ __HEAD ENTRY(startup_32) - movl pa(stack_start),%ecx + movl pa(initial_stack),%ecx /* test KEEP_SEGMENTS flag to see if the bootloader is asking us to not reload segments */ @@ -286,7 +286,7 @@ num_subarch_entries = (. - subarch_entries) / 4 * start_secondary(). */ ENTRY(start_cpu0) - movl stack_start, %ecx + movl initial_stack, %ecx movl %ecx, %esp jmp *(initial_code) ENDPROC(start_cpu0) @@ -307,7 +307,7 @@ ENTRY(startup_32_smp) movl %eax,%es movl %eax,%fs movl %eax,%gs - movl pa(stack_start),%ecx + movl pa(initial_stack),%ecx movl %eax,%ss leal -__PAGE_OFFSET(%ecx),%esp @@ -703,7 +703,7 @@ ENTRY(initial_page_table) .data .balign 4 -ENTRY(stack_start) +ENTRY(initial_stack) .long init_thread_union+THREAD_SIZE __INITRODATA diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 9f8efc9f0075..c98a559c346e 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -66,7 +66,7 @@ startup_64: */ /* - * Setup stack for verify_cpu(). "-8" because stack_start is defined + * Setup stack for verify_cpu(). "-8" because initial_stack is defined * this way, see below. Our best guess is a NULL ptr for stack * termination heuristics and we don't want to break anything which * might depend on it (kgdb, ...). @@ -226,7 +226,7 @@ ENTRY(secondary_startup_64) movq %rax, %cr0 /* Setup a boot time stack */ - movq stack_start(%rip), %rsp + movq initial_stack(%rip), %rsp /* zero EFLAGS after setting rsp */ pushq $0 @@ -310,7 +310,7 @@ ENDPROC(secondary_startup_64) * start_secondary(). */ ENTRY(start_cpu0) - movq stack_start(%rip),%rsp + movq initial_stack(%rip),%rsp movq initial_code(%rip),%rax pushq $0 # fake return address to stop unwinder pushq $__KERNEL_CS # set correct cs @@ -319,17 +319,15 @@ ENTRY(start_cpu0) ENDPROC(start_cpu0) #endif - /* SMP bootup changes these two */ + /* Both SMP bootup and ACPI suspend change these variables */ __REFDATA .balign 8 GLOBAL(initial_code) .quad x86_64_start_kernel GLOBAL(initial_gs) .quad INIT_PER_CPU_VAR(irq_stack_union) - - GLOBAL(stack_start) + GLOBAL(initial_stack) .quad init_thread_union+THREAD_SIZE-8 - .word 0 __FINITDATA bad_address: diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index c6dfd801df97..274fab99169d 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -756,10 +756,104 @@ static void hpet_reserve_msi_timers(struct hpet_data *hd) /* * Clock source related code */ +#if defined(CONFIG_SMP) && defined(CONFIG_64BIT) +/* + * Reading the HPET counter is a very slow operation. If a large number of + * CPUs are trying to access the HPET counter simultaneously, it can cause + * massive delay and slow down system performance dramatically. This may + * happen when HPET is the default clock source instead of TSC. For a + * really large system with hundreds of CPUs, the slowdown may be so + * severe that it may actually crash the system because of a NMI watchdog + * soft lockup, for example. + * + * If multiple CPUs are trying to access the HPET counter at the same time, + * we don't actually need to read the counter multiple times. Instead, the + * other CPUs can use the counter value read by the first CPU in the group. + * + * This special feature is only enabled on x86-64 systems. It is unlikely + * that 32-bit x86 systems will have enough CPUs to require this feature + * with its associated locking overhead. And we also need 64-bit atomic + * read. + * + * The lock and the hpet value are stored together and can be read in a + * single atomic 64-bit read. It is explicitly assumed that arch_spinlock_t + * is 32 bits in size. + */ +union hpet_lock { + struct { + arch_spinlock_t lock; + u32 value; + }; + u64 lockval; +}; + +static union hpet_lock hpet __cacheline_aligned = { + { .lock = __ARCH_SPIN_LOCK_UNLOCKED, }, +}; + +static cycle_t read_hpet(struct clocksource *cs) +{ + unsigned long flags; + union hpet_lock old, new; + + BUILD_BUG_ON(sizeof(union hpet_lock) != 8); + + /* + * Read HPET directly if in NMI. + */ + if (in_nmi()) + return (cycle_t)hpet_readl(HPET_COUNTER); + + /* + * Read the current state of the lock and HPET value atomically. + */ + old.lockval = READ_ONCE(hpet.lockval); + + if (arch_spin_is_locked(&old.lock)) + goto contended; + + local_irq_save(flags); + if (arch_spin_trylock(&hpet.lock)) { + new.value = hpet_readl(HPET_COUNTER); + /* + * Use WRITE_ONCE() to prevent store tearing. + */ + WRITE_ONCE(hpet.value, new.value); + arch_spin_unlock(&hpet.lock); + local_irq_restore(flags); + return (cycle_t)new.value; + } + local_irq_restore(flags); + +contended: + /* + * Contended case + * -------------- + * Wait until the HPET value change or the lock is free to indicate + * its value is up-to-date. + * + * It is possible that old.value has already contained the latest + * HPET value while the lock holder was in the process of releasing + * the lock. Checking for lock state change will enable us to return + * the value immediately instead of waiting for the next HPET reader + * to come along. + */ + do { + cpu_relax(); + new.lockval = READ_ONCE(hpet.lockval); + } while ((new.value == old.value) && arch_spin_is_locked(&new.lock)); + + return (cycle_t)new.value; +} +#else +/* + * For UP or 32-bit. + */ static cycle_t read_hpet(struct clocksource *cs) { return (cycle_t)hpet_readl(HPET_COUNTER); } +#endif static struct clocksource clocksource_hpet = { .name = "hpet", diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 4a7903714065..9ebd0b0e73d9 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -40,8 +40,7 @@ static inline void stack_overflow_check(struct pt_regs *regs) if (user_mode(regs)) return; - if (regs->sp >= curbase + sizeof(struct thread_info) + - sizeof(struct pt_regs) + STACK_TOP_MARGIN && + if (regs->sp >= curbase + sizeof(struct pt_regs) + STACK_TOP_MARGIN && regs->sp <= curbase + THREAD_SIZE) return; diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index f2356bda2b05..3407b148c240 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -99,14 +99,14 @@ static int setup_e820_entries(struct boot_params *params) { unsigned int nr_e820_entries; - nr_e820_entries = e820_saved.nr_map; + nr_e820_entries = e820_saved->nr_map; /* TODO: Pass entries more than E820MAX in bootparams setup data */ if (nr_e820_entries > E820MAX) nr_e820_entries = E820MAX; params->e820_entries = nr_e820_entries; - memcpy(¶ms->e820_map, &e820_saved.map, + memcpy(¶ms->e820_map, &e820_saved->map, nr_e820_entries * sizeof(struct e820entry)); return 0; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 04cde527d728..8e36f249646e 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -50,6 +50,7 @@ #include <asm/apicdef.h> #include <asm/apic.h> #include <asm/nmi.h> +#include <asm/switch_to.h> struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { @@ -166,21 +167,19 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) gdb_regs[GDB_DX] = 0; gdb_regs[GDB_SI] = 0; gdb_regs[GDB_DI] = 0; - gdb_regs[GDB_BP] = *(unsigned long *)p->thread.sp; + gdb_regs[GDB_BP] = ((struct inactive_task_frame *)p->thread.sp)->bp; #ifdef CONFIG_X86_32 gdb_regs[GDB_DS] = __KERNEL_DS; gdb_regs[GDB_ES] = __KERNEL_DS; gdb_regs[GDB_PS] = 0; gdb_regs[GDB_CS] = __KERNEL_CS; - gdb_regs[GDB_PC] = p->thread.ip; gdb_regs[GDB_SS] = __KERNEL_DS; gdb_regs[GDB_FS] = 0xFFFF; gdb_regs[GDB_GS] = 0xFFFF; #else - gdb_regs32[GDB_PS] = *(unsigned long *)(p->thread.sp + 8); + gdb_regs32[GDB_PS] = 0; gdb_regs32[GDB_CS] = __KERNEL_CS; gdb_regs32[GDB_SS] = __KERNEL_DS; - gdb_regs[GDB_PC] = 0; gdb_regs[GDB_R8] = 0; gdb_regs[GDB_R9] = 0; gdb_regs[GDB_R10] = 0; @@ -190,6 +189,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) gdb_regs[GDB_R14] = 0; gdb_regs[GDB_R15] = 0; #endif + gdb_regs[GDB_PC] = 0; gdb_regs[GDB_SP] = p->thread.sp; } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 7847e5c0e0b5..28cee019209c 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -45,7 +45,7 @@ #include <linux/slab.h> #include <linux/hardirq.h> #include <linux/preempt.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/kdebug.h> #include <linux/kallsyms.h> #include <linux/ftrace.h> diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 4425f593f0ec..3bb4c5f021f6 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -24,7 +24,7 @@ #include <linux/slab.h> #include <linux/hardirq.h> #include <linux/preempt.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/kdebug.h> #include <linux/kallsyms.h> #include <linux/ftrace.h> diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index c2bedaea11f7..4afc67f5facc 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -184,7 +184,7 @@ out: static struct kobj_attribute type_attr = __ATTR_RO(type); -static struct bin_attribute data_attr = { +static struct bin_attribute data_attr __ro_after_init = { .attr = { .name = "data", .mode = S_IRUGO, diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 1726c4c12336..edbbfc854e39 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -423,12 +423,7 @@ static void __init kvm_smp_prepare_boot_cpu(void) kvm_spinlock_init(); } -static void kvm_guest_cpu_online(void *dummy) -{ - kvm_guest_cpu_init(); -} - -static void kvm_guest_cpu_offline(void *dummy) +static void kvm_guest_cpu_offline(void) { kvm_disable_steal_time(); if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) @@ -437,29 +432,21 @@ static void kvm_guest_cpu_offline(void *dummy) apf_task_wake_all(); } -static int kvm_cpu_notify(struct notifier_block *self, unsigned long action, - void *hcpu) +static int kvm_cpu_online(unsigned int cpu) { - int cpu = (unsigned long)hcpu; - switch (action) { - case CPU_ONLINE: - case CPU_DOWN_FAILED: - case CPU_ONLINE_FROZEN: - smp_call_function_single(cpu, kvm_guest_cpu_online, NULL, 0); - break; - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - smp_call_function_single(cpu, kvm_guest_cpu_offline, NULL, 1); - break; - default: - break; - } - return NOTIFY_OK; + local_irq_disable(); + kvm_guest_cpu_init(); + local_irq_enable(); + return 0; } -static struct notifier_block kvm_cpu_notifier = { - .notifier_call = kvm_cpu_notify, -}; +static int kvm_cpu_down_prepare(unsigned int cpu) +{ + local_irq_disable(); + kvm_guest_cpu_offline(); + local_irq_enable(); + return 0; +} #endif static void __init kvm_apf_trap_init(void) @@ -494,7 +481,9 @@ void __init kvm_guest_init(void) #ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; - register_cpu_notifier(&kvm_cpu_notifier); + if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online", + kvm_cpu_online, kvm_cpu_down_prepare) < 0) + pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n"); #else kvm_guest_cpu_init(); #endif @@ -575,9 +564,6 @@ static void kvm_kick_cpu(int cpu) kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid); } - -#ifdef CONFIG_QUEUED_SPINLOCKS - #include <asm/qspinlock.h> static void kvm_wait(u8 *ptr, u8 val) @@ -606,243 +592,6 @@ out: local_irq_restore(flags); } -#else /* !CONFIG_QUEUED_SPINLOCKS */ - -enum kvm_contention_stat { - TAKEN_SLOW, - TAKEN_SLOW_PICKUP, - RELEASED_SLOW, - RELEASED_SLOW_KICKED, - NR_CONTENTION_STATS -}; - -#ifdef CONFIG_KVM_DEBUG_FS -#define HISTO_BUCKETS 30 - -static struct kvm_spinlock_stats -{ - u32 contention_stats[NR_CONTENTION_STATS]; - u32 histo_spin_blocked[HISTO_BUCKETS+1]; - u64 time_blocked; -} spinlock_stats; - -static u8 zero_stats; - -static inline void check_zero(void) -{ - u8 ret; - u8 old; - - old = READ_ONCE(zero_stats); - if (unlikely(old)) { - ret = cmpxchg(&zero_stats, old, 0); - /* This ensures only one fellow resets the stat */ - if (ret == old) - memset(&spinlock_stats, 0, sizeof(spinlock_stats)); - } -} - -static inline void add_stats(enum kvm_contention_stat var, u32 val) -{ - check_zero(); - spinlock_stats.contention_stats[var] += val; -} - - -static inline u64 spin_time_start(void) -{ - return sched_clock(); -} - -static void __spin_time_accum(u64 delta, u32 *array) -{ - unsigned index; - - index = ilog2(delta); - check_zero(); - - if (index < HISTO_BUCKETS) - array[index]++; - else - array[HISTO_BUCKETS]++; -} - -static inline void spin_time_accum_blocked(u64 start) -{ - u32 delta; - - delta = sched_clock() - start; - __spin_time_accum(delta, spinlock_stats.histo_spin_blocked); - spinlock_stats.time_blocked += delta; -} - -static struct dentry *d_spin_debug; -static struct dentry *d_kvm_debug; - -static struct dentry *kvm_init_debugfs(void) -{ - d_kvm_debug = debugfs_create_dir("kvm-guest", NULL); - if (!d_kvm_debug) - printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n"); - - return d_kvm_debug; -} - -static int __init kvm_spinlock_debugfs(void) -{ - struct dentry *d_kvm; - - d_kvm = kvm_init_debugfs(); - if (d_kvm == NULL) - return -ENOMEM; - - d_spin_debug = debugfs_create_dir("spinlocks", d_kvm); - - debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats); - - debugfs_create_u32("taken_slow", 0444, d_spin_debug, - &spinlock_stats.contention_stats[TAKEN_SLOW]); - debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug, - &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]); - - debugfs_create_u32("released_slow", 0444, d_spin_debug, - &spinlock_stats.contention_stats[RELEASED_SLOW]); - debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug, - &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]); - - debugfs_create_u64("time_blocked", 0444, d_spin_debug, - &spinlock_stats.time_blocked); - - debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug, - spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1); - - return 0; -} -fs_initcall(kvm_spinlock_debugfs); -#else /* !CONFIG_KVM_DEBUG_FS */ -static inline void add_stats(enum kvm_contention_stat var, u32 val) -{ -} - -static inline u64 spin_time_start(void) -{ - return 0; -} - -static inline void spin_time_accum_blocked(u64 start) -{ -} -#endif /* CONFIG_KVM_DEBUG_FS */ - -struct kvm_lock_waiting { - struct arch_spinlock *lock; - __ticket_t want; -}; - -/* cpus 'waiting' on a spinlock to become available */ -static cpumask_t waiting_cpus; - -/* Track spinlock on which a cpu is waiting */ -static DEFINE_PER_CPU(struct kvm_lock_waiting, klock_waiting); - -__visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want) -{ - struct kvm_lock_waiting *w; - int cpu; - u64 start; - unsigned long flags; - __ticket_t head; - - if (in_nmi()) - return; - - w = this_cpu_ptr(&klock_waiting); - cpu = smp_processor_id(); - start = spin_time_start(); - - /* - * Make sure an interrupt handler can't upset things in a - * partially setup state. - */ - local_irq_save(flags); - - /* - * The ordering protocol on this is that the "lock" pointer - * may only be set non-NULL if the "want" ticket is correct. - * If we're updating "want", we must first clear "lock". - */ - w->lock = NULL; - smp_wmb(); - w->want = want; - smp_wmb(); - w->lock = lock; - - add_stats(TAKEN_SLOW, 1); - - /* - * This uses set_bit, which is atomic but we should not rely on its - * reordering gurantees. So barrier is needed after this call. - */ - cpumask_set_cpu(cpu, &waiting_cpus); - - barrier(); - - /* - * Mark entry to slowpath before doing the pickup test to make - * sure we don't deadlock with an unlocker. - */ - __ticket_enter_slowpath(lock); - - /* make sure enter_slowpath, which is atomic does not cross the read */ - smp_mb__after_atomic(); - - /* - * check again make sure it didn't become free while - * we weren't looking. - */ - head = READ_ONCE(lock->tickets.head); - if (__tickets_equal(head, want)) { - add_stats(TAKEN_SLOW_PICKUP, 1); - goto out; - } - - /* - * halt until it's our turn and kicked. Note that we do safe halt - * for irq enabled case to avoid hang when lock info is overwritten - * in irq spinlock slowpath and no spurious interrupt occur to save us. - */ - if (arch_irqs_disabled_flags(flags)) - halt(); - else - safe_halt(); - -out: - cpumask_clear_cpu(cpu, &waiting_cpus); - w->lock = NULL; - local_irq_restore(flags); - spin_time_accum_blocked(start); -} -PV_CALLEE_SAVE_REGS_THUNK(kvm_lock_spinning); - -/* Kick vcpu waiting on @lock->head to reach value @ticket */ -static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket) -{ - int cpu; - - add_stats(RELEASED_SLOW, 1); - for_each_cpu(cpu, &waiting_cpus) { - const struct kvm_lock_waiting *w = &per_cpu(klock_waiting, cpu); - if (READ_ONCE(w->lock) == lock && - READ_ONCE(w->want) == ticket) { - add_stats(RELEASED_SLOW_KICKED, 1); - kvm_kick_cpu(cpu); - break; - } - } -} - -#endif /* !CONFIG_QUEUED_SPINLOCKS */ - /* * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. */ @@ -854,16 +603,11 @@ void __init kvm_spinlock_init(void) if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) return; -#ifdef CONFIG_QUEUED_SPINLOCKS __pv_init_lock_hash(); pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); pv_lock_ops.wait = kvm_wait; pv_lock_ops.kick = kvm_kick_cpu; -#else /* !CONFIG_QUEUED_SPINLOCKS */ - pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); - pv_lock_ops.unlock_kick = kvm_unlock_kick; -#endif } static __init int kvm_spinlock_init_jump(void) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 1d39bfbd26bb..60b9949f1e65 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -29,7 +29,7 @@ #include <asm/x86_init.h> #include <asm/reboot.h> -static int kvmclock = 1; +static int kvmclock __ro_after_init = 1; static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK; static cycle_t kvm_sched_clock_offset; @@ -289,6 +289,7 @@ void __init kvmclock_init(void) put_cpu(); x86_platform.calibrate_tsc = kvm_get_tsc_khz; + x86_platform.calibrate_cpu = kvm_get_tsc_khz; x86_platform.get_wallclock = kvm_get_wallclock; x86_platform.set_wallclock = kvm_set_wallclock; #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c new file mode 100644 index 000000000000..e9d252d873aa --- /dev/null +++ b/arch/x86/kernel/livepatch.c @@ -0,0 +1,65 @@ +/* + * livepatch.c - x86-specific Kernel Live Patching Core + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/livepatch.h> +#include <asm/text-patching.h> + +/* Apply per-object alternatives. Based on x86 module_finalize() */ +void arch_klp_init_object_loaded(struct klp_patch *patch, + struct klp_object *obj) +{ + int cnt; + struct klp_modinfo *info; + Elf_Shdr *s, *alt = NULL, *para = NULL; + void *aseg, *pseg; + const char *objname; + char sec_objname[MODULE_NAME_LEN]; + char secname[KSYM_NAME_LEN]; + + info = patch->mod->klp_info; + objname = obj->name ? obj->name : "vmlinux"; + + /* See livepatch core code for BUILD_BUG_ON() explanation */ + BUILD_BUG_ON(MODULE_NAME_LEN < 56 || KSYM_NAME_LEN != 128); + + for (s = info->sechdrs; s < info->sechdrs + info->hdr.e_shnum; s++) { + /* Apply per-object .klp.arch sections */ + cnt = sscanf(info->secstrings + s->sh_name, + ".klp.arch.%55[^.].%127s", + sec_objname, secname); + if (cnt != 2) + continue; + if (strcmp(sec_objname, objname)) + continue; + if (!strcmp(".altinstructions", secname)) + alt = s; + if (!strcmp(".parainstructions", secname)) + para = s; + } + + if (alt) { + aseg = (void *) alt->sh_addr; + apply_alternatives(aseg, aseg + alt->sh_size); + } + + if (para) { + pseg = (void *) para->sh_addr; + apply_paravirt(pseg, pseg + para->sh_size); + } +} diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 068c4a929de6..0f8d20497383 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -499,6 +499,9 @@ void __init default_get_smp_config(unsigned int early) { struct mpf_intel *mpf = mpf_found; + if (!smp_found_config) + return; + if (!mpf) return; diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 1939a0269377..2c55a003b793 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -8,7 +8,6 @@ #include <asm/paravirt.h> -#ifdef CONFIG_QUEUED_SPINLOCKS __visible void __native_queued_spin_unlock(struct qspinlock *lock) { native_queued_spin_unlock(lock); @@ -21,19 +20,13 @@ bool pv_is_native_spin_unlock(void) return pv_lock_ops.queued_spin_unlock.func == __raw_callee_save___native_queued_spin_unlock; } -#endif struct pv_lock_ops pv_lock_ops = { #ifdef CONFIG_SMP -#ifdef CONFIG_QUEUED_SPINLOCKS .queued_spin_lock_slowpath = native_queued_spin_lock_slowpath, .queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock), .wait = paravirt_nop, .kick = paravirt_nop, -#else /* !CONFIG_QUEUED_SPINLOCKS */ - .lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop), - .unlock_kick = paravirt_nop, -#endif /* !CONFIG_QUEUED_SPINLOCKS */ #endif /* SMP */ }; EXPORT_SYMBOL(pv_lock_ops); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index ad5bc9578a73..bbf3d5933eaa 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -56,12 +56,12 @@ asm (".pushsection .entry.text, \"ax\"\n" ".popsection"); /* identity function, which can be inlined */ -u32 _paravirt_ident_32(u32 x) +u32 notrace _paravirt_ident_32(u32 x) { return x; } -u64 _paravirt_ident_64(u64 x) +u64 notrace _paravirt_ident_64(u64 x) { return x; } @@ -332,7 +332,6 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .read_cr0 = native_read_cr0, .write_cr0 = native_write_cr0, .read_cr4 = native_read_cr4, - .read_cr4_safe = native_read_cr4_safe, .write_cr4 = native_write_cr4, #ifdef CONFIG_X86_64 .read_cr8 = native_read_cr8, @@ -389,7 +388,7 @@ NOKPROBE_SYMBOL(native_load_idt); #define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64) #endif -struct pv_mmu_ops pv_mmu_ops = { +struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .read_cr2 = native_read_cr2, .write_cr2 = native_write_cr2, diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index 158dc0650d5d..920c6ae08592 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -10,7 +10,7 @@ DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3"); DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); -#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) +#if defined(CONFIG_PARAVIRT_SPINLOCKS) DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)"); #endif @@ -49,7 +49,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); PATCH_SITE(pv_cpu_ops, clts); -#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) +#if defined(CONFIG_PARAVIRT_SPINLOCKS) case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): if (pv_is_native_spin_unlock()) { start = start_pv_lock_ops_queued_spin_unlock; diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index e70087a04cc8..bb3840cedb4f 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -19,7 +19,7 @@ DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs"); DEF_NATIVE(, mov32, "mov %edi, %eax"); DEF_NATIVE(, mov64, "mov %rdi, %rax"); -#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) +#if defined(CONFIG_PARAVIRT_SPINLOCKS) DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)"); #endif @@ -61,7 +61,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_cpu_ops, clts); PATCH_SITE(pv_mmu_ops, flush_tlb_single); PATCH_SITE(pv_cpu_ops, wbinvd); -#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) +#if defined(CONFIG_PARAVIRT_SPINLOCKS) case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): if (pv_is_native_spin_unlock()) { start = start_pv_lock_ops_queued_spin_unlock; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 62c0b0ea2ce4..4002b475171c 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -32,6 +32,7 @@ #include <asm/tlbflush.h> #include <asm/mce.h> #include <asm/vm86.h> +#include <asm/switch_to.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -513,6 +514,17 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) } /* + * Return saved PC of a blocked thread. + * What is this good for? it will be always the scheduler or ret_from_fork. + */ +unsigned long thread_saved_pc(struct task_struct *tsk) +{ + struct inactive_task_frame *frame = + (struct inactive_task_frame *) READ_ONCE(tsk->thread.sp); + return READ_ONCE_NOCHECK(frame->ret_addr); +} + +/* * Called from fs/proc with a reference on @p to find the function * which called into schedule(). This needs to be done carefully * because the task might wake up and we might look at a stack @@ -520,15 +532,18 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) */ unsigned long get_wchan(struct task_struct *p) { - unsigned long start, bottom, top, sp, fp, ip; + unsigned long start, bottom, top, sp, fp, ip, ret = 0; int count = 0; if (!p || p == current || p->state == TASK_RUNNING) return 0; + if (!try_get_task_stack(p)) + return 0; + start = (unsigned long)task_stack_page(p); if (!start) - return 0; + goto out; /* * Layout of the stack page: @@ -537,9 +552,7 @@ unsigned long get_wchan(struct task_struct *p) * PADDING * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING * stack - * ----------- bottom = start + sizeof(thread_info) - * thread_info - * ----------- start + * ----------- bottom = start * * The tasks stack pointer points at the location where the * framepointer is stored. The data on the stack is: @@ -550,20 +563,25 @@ unsigned long get_wchan(struct task_struct *p) */ top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; top -= 2 * sizeof(unsigned long); - bottom = start + sizeof(struct thread_info); + bottom = start; sp = READ_ONCE(p->thread.sp); if (sp < bottom || sp > top) - return 0; + goto out; - fp = READ_ONCE_NOCHECK(*(unsigned long *)sp); + fp = READ_ONCE_NOCHECK(((struct inactive_task_frame *)sp)->bp); do { if (fp < bottom || fp > top) - return 0; + goto out; ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long))); - if (!in_sched_functions(ip)) - return ip; + if (!in_sched_functions(ip)) { + ret = ip; + goto out; + } fp = READ_ONCE_NOCHECK(*(unsigned long *)fp); } while (count++ < 16 && p->state != TASK_RUNNING); - return 0; + +out: + put_task_stack(p); + return ret; } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index d86be29c38c7..bd7be8efdc4c 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -55,17 +55,6 @@ #include <asm/switch_to.h> #include <asm/vm86.h> -asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); -asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread"); - -/* - * Return saved PC of a blocked thread. - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - return ((unsigned long *)tsk->thread.sp)[3]; -} - void __show_regs(struct pt_regs *regs, int all) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; @@ -101,7 +90,7 @@ void __show_regs(struct pt_regs *regs, int all) cr0 = read_cr0(); cr2 = read_cr2(); cr3 = read_cr3(); - cr4 = __read_cr4_safe(); + cr4 = __read_cr4(); printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4); @@ -133,35 +122,31 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, unsigned long arg, struct task_struct *p, unsigned long tls) { struct pt_regs *childregs = task_pt_regs(p); + struct fork_frame *fork_frame = container_of(childregs, struct fork_frame, regs); + struct inactive_task_frame *frame = &fork_frame->frame; struct task_struct *tsk; int err; - p->thread.sp = (unsigned long) childregs; + frame->bp = 0; + frame->ret_addr = (unsigned long) ret_from_fork; + p->thread.sp = (unsigned long) fork_frame; p->thread.sp0 = (unsigned long) (childregs+1); memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); - p->thread.ip = (unsigned long) ret_from_kernel_thread; - task_user_gs(p) = __KERNEL_STACK_CANARY; - childregs->ds = __USER_DS; - childregs->es = __USER_DS; - childregs->fs = __KERNEL_PERCPU; - childregs->bx = sp; /* function */ - childregs->bp = arg; - childregs->orig_ax = -1; - childregs->cs = __KERNEL_CS | get_kernel_rpl(); - childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; + frame->bx = sp; /* function */ + frame->di = arg; p->thread.io_bitmap_ptr = NULL; return 0; } + frame->bx = 0; *childregs = *current_pt_regs(); childregs->ax = 0; if (sp) childregs->sp = sp; - p->thread.ip = (unsigned long) ret_from_fork; task_user_gs(p) = get_user_gs(current_pt_regs()); p->thread.io_bitmap_ptr = NULL; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 63236d8f84bf..ee944bd2310d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -49,8 +49,7 @@ #include <asm/debugreg.h> #include <asm/switch_to.h> #include <asm/xen/hypervisor.h> - -asmlinkage extern void ret_from_fork(void); +#include <asm/vdso.h> __visible DEFINE_PER_CPU(unsigned long, rsp_scratch); @@ -141,12 +140,17 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, { int err; struct pt_regs *childregs; + struct fork_frame *fork_frame; + struct inactive_task_frame *frame; struct task_struct *me = current; p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE; childregs = task_pt_regs(p); - p->thread.sp = (unsigned long) childregs; - set_tsk_thread_flag(p, TIF_FORK); + fork_frame = container_of(childregs, struct fork_frame, regs); + frame = &fork_frame->frame; + frame->bp = 0; + frame->ret_addr = (unsigned long) ret_from_fork; + p->thread.sp = (unsigned long) fork_frame; p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); @@ -160,15 +164,11 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); - childregs->sp = (unsigned long)childregs; - childregs->ss = __KERNEL_DS; - childregs->bx = sp; /* function */ - childregs->bp = arg; - childregs->orig_ax = -1; - childregs->cs = __KERNEL_CS | get_kernel_rpl(); - childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; + frame->bx = sp; /* function */ + frame->r12 = arg; return 0; } + frame->bx = 0; *childregs = *current_pt_regs(); childregs->ax = 0; @@ -511,7 +511,7 @@ void set_personality_ia32(bool x32) current->personality &= ~READ_IMPLIES_EXEC; /* in_compat_syscall() uses the presence of the x32 syscall bit flag to determine compat status */ - current_thread_info()->status &= ~TS_COMPAT; + current->thread.status &= ~TS_COMPAT; } else { set_thread_flag(TIF_IA32); clear_thread_flag(TIF_X32); @@ -519,11 +519,24 @@ void set_personality_ia32(bool x32) current->mm->context.ia32_compat = TIF_IA32; current->personality |= force_personality32; /* Prepare the first "return" to user space */ - current_thread_info()->status |= TS_COMPAT; + current->thread.status |= TS_COMPAT; } } EXPORT_SYMBOL_GPL(set_personality_ia32); +#ifdef CONFIG_CHECKPOINT_RESTORE +static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr) +{ + int ret; + + ret = map_vdso_once(image, addr); + if (ret) + return ret; + + return (long)image->size; +} +#endif + long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) { int ret = 0; @@ -577,6 +590,19 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) break; } +#ifdef CONFIG_CHECKPOINT_RESTORE +# ifdef CONFIG_X86_X32_ABI + case ARCH_MAP_VDSO_X32: + return prctl_map_vdso(&vdso_image_x32, addr); +# endif +# if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION + case ARCH_MAP_VDSO_32: + return prctl_map_vdso(&vdso_image_32, addr); +# endif + case ARCH_MAP_VDSO_64: + return prctl_map_vdso(&vdso_image_64, addr); +#endif + default: ret = -EINVAL; break; diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index f79576a541ff..0e63c0267f99 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -173,8 +173,8 @@ unsigned long kernel_stack_pointer(struct pt_regs *regs) return sp; prev_esp = (u32 *)(context); - if (prev_esp) - return (unsigned long)prev_esp; + if (*prev_esp) + return (unsigned long)*prev_esp; return (unsigned long)regs; } @@ -934,7 +934,7 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value) */ regs->orig_ax = value; if (syscall_get_nr(child, regs) >= 0) - task_thread_info(child)->status |= TS_I386_REGS_POKED; + child->thread.status |= TS_I386_REGS_POKED; break; case offsetof(struct user32, regs.eflags): @@ -1250,7 +1250,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, #ifdef CONFIG_X86_64 -static struct user_regset x86_64_regsets[] __read_mostly = { +static struct user_regset x86_64_regsets[] __ro_after_init = { [REGSET_GENERAL] = { .core_note_type = NT_PRSTATUS, .n = sizeof(struct user_regs_struct) / sizeof(long), @@ -1291,7 +1291,7 @@ static const struct user_regset_view user_x86_64_view = { #endif /* CONFIG_X86_64 */ #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION -static struct user_regset x86_32_regsets[] __read_mostly = { +static struct user_regset x86_32_regsets[] __ro_after_init = { [REGSET_GENERAL] = { .core_note_type = NT_PRSTATUS, .n = sizeof(struct user_regs_struct32) / sizeof(u32), @@ -1344,7 +1344,7 @@ static const struct user_regset_view user_x86_32_view = { */ u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; -void update_regset_xstate_info(unsigned int size, u64 xstate_mask) +void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask) { #ifdef CONFIG_X86_64 x86_64_regsets[REGSET_XSTATE].n = size / sizeof(u64); @@ -1358,7 +1358,7 @@ void update_regset_xstate_info(unsigned int size, u64 xstate_mask) const struct user_regset_view *task_user_regset_view(struct task_struct *task) { #ifdef CONFIG_IA32_EMULATION - if (test_tsk_thread_flag(task, TIF_IA32)) + if (!user_64bit_mode(task_pt_regs(task))) #endif #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION return &user_x86_32_view; diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 3599404e3089..5b2cc889ce34 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -80,7 +80,7 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) do { version = pvclock_read_begin(src); - ret = __pvclock_read_cycles(src); + ret = __pvclock_read_cycles(src, rdtsc_ordered()); flags = src->flags; } while (pvclock_read_retry(src, version)); diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index cc457ff818ad..51402a7e4ca6 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -626,3 +626,34 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3, amd_disable_seq_and_redirect_scrub); #endif + +#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE) +#include <linux/jump_label.h> +#include <asm/string_64.h> + +/* Ivy Bridge, Haswell, Broadwell */ +static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev) +{ + u32 capid0; + + pci_read_config_dword(pdev, 0x84, &capid0); + + if (capid0 & 0x10) + static_branch_inc(&mcsafe_key); +} + +/* Skylake */ +static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev) +{ + u32 capid0; + + pci_read_config_dword(pdev, 0x84, &capid0); + + if ((capid0 & 0xc0) == 0xc0) + static_branch_inc(&mcsafe_key); +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ras_cap); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, quirk_intel_brickland_xeon_ras_cap); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2083, quirk_intel_purley_xeon_ras_cap); +#endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 63bf27d972b7..e244c19a2451 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -705,7 +705,7 @@ static void native_machine_power_off(void) tboot_shutdown(TB_SHUTDOWN_HALT); } -struct machine_ops machine_ops = { +struct machine_ops machine_ops __ro_after_init = { .power_off = native_machine_power_off, .shutdown = native_machine_shutdown, .emergency_restart = native_machine_emergency_restart, diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index 80eab01c1a68..2408c1603438 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -27,8 +27,8 @@ static void remove_e820_regions(struct resource *avail) int i; struct e820entry *entry; - for (i = 0; i < e820.nr_map; i++) { - entry = &e820.map[i]; + for (i = 0; i < e820->nr_map; i++) { + entry = &e820->map[i]; resource_clip(avail, entry->addr, entry->addr + entry->size - 1); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 0fa60f5f5a16..bbfbca5fea0c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -210,9 +210,9 @@ EXPORT_SYMBOL(boot_cpu_data); #if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64) -__visible unsigned long mmu_cr4_features; +__visible unsigned long mmu_cr4_features __ro_after_init; #else -__visible unsigned long mmu_cr4_features = X86_CR4_PAE; +__visible unsigned long mmu_cr4_features __ro_after_init = X86_CR4_PAE; #endif /* Boot loader ID and version as integers, for the benefit of proc_dointvec */ @@ -458,8 +458,8 @@ static void __init e820_reserve_setup_data(void) early_memunmap(data, sizeof(*data)); } - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); - memcpy(&e820_saved, &e820, sizeof(struct e820map)); + sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); + memcpy(e820_saved, e820, sizeof(struct e820map)); printk(KERN_INFO "extended physical RAM map:\n"); e820_print_map("reserve setup_data"); } @@ -763,7 +763,7 @@ static void __init trim_bios_range(void) */ e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1); - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); } /* called before trim_bios_range() to spare extra sanitize */ @@ -1032,7 +1032,7 @@ void __init setup_arch(char **cmdline_p) if (ppro_with_ram_bug()) { e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM, E820_RESERVED); - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); printk(KERN_INFO "fixed physical RAM map:\n"); e820_print_map("bad_ppro"); } @@ -1096,19 +1096,19 @@ void __init setup_arch(char **cmdline_p) memblock_set_current_limit(ISA_END_ADDRESS); memblock_x86_fill(); - if (efi_enabled(EFI_BOOT)) { + reserve_bios_regions(); + + if (efi_enabled(EFI_MEMMAP)) { efi_fake_memmap(); efi_find_mirror(); - } - - reserve_bios_regions(); + efi_esrt_init(); - /* - * The EFI specification says that boot service code won't be called - * after ExitBootServices(). This is, in fact, a lie. - */ - if (efi_enabled(EFI_MEMMAP)) + /* + * The EFI specification says that boot service code won't be + * called after ExitBootServices(). This is, in fact, a lie. + */ efi_reserve_boot_services(); + } /* preallocate 4k for mptable mpc */ early_reserve_e820_mpc_new(); @@ -1137,9 +1137,7 @@ void __init setup_arch(char **cmdline_p) * auditing all the early-boot CR4 manipulation would be needed to * rule it out. */ - if (boot_cpu_data.cpuid_level >= 0) - /* A CPU has %cr4 if and only if it has CPUID. */ - mmu_cr4_features = __read_cr4(); + mmu_cr4_features = __read_cr4(); memblock_set_current_limit(get_max_mapped()); @@ -1221,8 +1219,7 @@ void __init setup_arch(char **cmdline_p) /* * get boot-time SMP configuration: */ - if (smp_found_config) - get_smp_config(); + get_smp_config(); prefill_possible_map(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 7a40e068302d..2bbd27f89802 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -33,7 +33,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_number); DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET; EXPORT_PER_CPU_SYMBOL(this_cpu_off); -unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = { +unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init = { [0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET, }; EXPORT_SYMBOL(__per_cpu_offset); @@ -246,7 +246,7 @@ void __init setup_per_cpu_areas(void) #ifdef CONFIG_X86_64 per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack_union.irq_stack, cpu) + - IRQ_STACK_SIZE - 64; + IRQ_STACK_SIZE; #endif #ifdef CONFIG_NUMA per_cpu(x86_cpu_to_node_map, cpu) = diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 04cb3212db2d..763af1d0de64 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -42,6 +42,7 @@ #include <asm/syscalls.h> #include <asm/sigframe.h> +#include <asm/signal.h> #define COPY(x) do { \ get_user_ex(regs->x, &sc->x); \ @@ -547,7 +548,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, return -EFAULT; if (ksig->ka.sa.sa_flags & SA_SIGINFO) { - if (copy_siginfo_to_user32(&frame->info, &ksig->info)) + if (__copy_siginfo_to_user32(&frame->info, &ksig->info, true)) return -EFAULT; } @@ -660,20 +661,21 @@ badframe: return 0; } -static inline int is_ia32_compat_frame(void) +static inline int is_ia32_compat_frame(struct ksignal *ksig) { return IS_ENABLED(CONFIG_IA32_EMULATION) && - test_thread_flag(TIF_IA32); + ksig->ka.sa.sa_flags & SA_IA32_ABI; } -static inline int is_ia32_frame(void) +static inline int is_ia32_frame(struct ksignal *ksig) { - return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(); + return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(ksig); } -static inline int is_x32_frame(void) +static inline int is_x32_frame(struct ksignal *ksig) { - return IS_ENABLED(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32); + return IS_ENABLED(CONFIG_X86_X32_ABI) && + ksig->ka.sa.sa_flags & SA_X32_ABI; } static int @@ -684,12 +686,12 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) compat_sigset_t *cset = (compat_sigset_t *) set; /* Set up the stack frame */ - if (is_ia32_frame()) { + if (is_ia32_frame(ksig)) { if (ksig->ka.sa.sa_flags & SA_SIGINFO) return ia32_setup_rt_frame(usig, ksig, cset, regs); else return ia32_setup_frame(usig, ksig, cset, regs); - } else if (is_x32_frame()) { + } else if (is_x32_frame(ksig)) { return x32_setup_rt_frame(ksig, cset, regs); } else { return __setup_rt_frame(ksig->sig, ksig, set, regs); @@ -783,7 +785,7 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) * than the tracee. */ #ifdef CONFIG_IA32_EMULATION - if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (current->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index b44564bf86a8..40df33753bae 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -1,5 +1,6 @@ #include <linux/compat.h> #include <linux/uaccess.h> +#include <linux/ptrace.h> /* * The compat_siginfo_t structure and handing code is very easy @@ -92,10 +93,31 @@ static inline void signal_compat_build_tests(void) /* any new si_fields should be added here */ } -int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) +void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact) +{ + /* Don't leak in-kernel non-uapi flags to user-space */ + if (oact) + oact->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI); + + if (!act) + return; + + /* Don't let flags to be set from userspace */ + act->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI); + + if (user_64bit_mode(current_pt_regs())) + return; + + if (in_ia32_syscall()) + act->sa.sa_flags |= SA_IA32_ABI; + if (in_x32_syscall()) + act->sa.sa_flags |= SA_X32_ABI; +} + +int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from, + bool x32_ABI) { int err = 0; - bool ia32 = test_thread_flag(TIF_IA32); signal_compat_build_tests(); @@ -146,7 +168,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) put_user_ex(from->si_arch, &to->si_arch); break; case __SI_CHLD >> 16: - if (ia32) { + if (!x32_ABI) { put_user_ex(from->si_utime, &to->si_utime); put_user_ex(from->si_stime, &to->si_stime); } else { @@ -180,6 +202,12 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) return err; } +/* from syscall's path, where we know the ABI */ +int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) +{ + return __copy_siginfo_to_user32(to, from, in_x32_syscall()); +} + int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) { int err = 0; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 4296beb8fdd3..42a93621f5b0 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -471,7 +471,7 @@ static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) return false; } -static struct sched_domain_topology_level numa_inside_package_topology[] = { +static struct sched_domain_topology_level x86_numa_in_package_topology[] = { #ifdef CONFIG_SCHED_SMT { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, #endif @@ -480,22 +480,23 @@ static struct sched_domain_topology_level numa_inside_package_topology[] = { #endif { NULL, }, }; + +static struct sched_domain_topology_level x86_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + /* - * set_sched_topology() sets the topology internal to a CPU. The - * NUMA topologies are layered on top of it to build the full - * system topology. - * - * If NUMA nodes are observed to occur within a CPU package, this - * function should be called. It forces the sched domain code to - * only use the SMT level for the CPU portion of the topology. - * This essentially falls back to relying on NUMA information - * from the SRAT table to describe the entire system topology - * (except for hyperthreads). + * Set if a package/die has multiple NUMA nodes inside. + * AMD Magny-Cours and Intel Cluster-on-Die have this. */ -static void primarily_use_numa_for_topology(void) -{ - set_sched_topology(numa_inside_package_topology); -} +static bool x86_has_numa_in_package; void set_cpu_sibling_map(int cpu) { @@ -558,7 +559,7 @@ void set_cpu_sibling_map(int cpu) c->booted_cores = cpu_data(i).booted_cores; } if (match_die(c, o) && !topology_same_node(c, o)) - primarily_use_numa_for_topology(); + x86_has_numa_in_package = true; } threads = cpumask_weight(topology_sibling_cpumask(cpu)); @@ -690,7 +691,7 @@ wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip) * Give the other CPU some time to accept the IPI. */ udelay(200); - if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) { + if (APIC_INTEGRATED(boot_cpu_apic_version)) { maxlvt = lapic_get_maxlvt(); if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ apic_write(APIC_ESR, 0); @@ -717,7 +718,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) /* * Be paranoid about clearing APIC errors. */ - if (APIC_INTEGRATED(apic_version[phys_apicid])) { + if (APIC_INTEGRATED(boot_cpu_apic_version)) { if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ apic_write(APIC_ESR, 0); apic_read(APIC_ESR); @@ -756,7 +757,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) * Determine this based on the APIC version. * If we don't have an integrated APIC, don't send the STARTUP IPIs. */ - if (APIC_INTEGRATED(apic_version[phys_apicid])) + if (APIC_INTEGRATED(boot_cpu_apic_version)) num_starts = 2; else num_starts = 0; @@ -942,7 +943,6 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle) per_cpu(cpu_current_top_of_stack, cpu) = (unsigned long)task_stack_page(idle) + THREAD_SIZE; #else - clear_tsk_thread_flag(idle, TIF_FORK); initial_gs = per_cpu_offset(cpu); #endif } @@ -969,7 +969,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); initial_code = (unsigned long)start_secondary; - stack_start = idle->thread.sp; + initial_stack = idle->thread.sp; /* * Enable the espfix hack for this CPU @@ -994,7 +994,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) /* * Be paranoid about clearing APIC errors. */ - if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) { + if (APIC_INTEGRATED(boot_cpu_apic_version)) { apic_write(APIC_ESR, 0); apic_read(APIC_ESR); } @@ -1115,17 +1115,8 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) common_cpu_up(cpu, tidle); - /* - * We have to walk the irq descriptors to setup the vector - * space for the cpu which comes online. Prevent irq - * alloc/free across the bringup. - */ - irq_lock_sparse(); - err = do_boot_cpu(apicid, cpu, tidle); - if (err) { - irq_unlock_sparse(); pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); return -EIO; } @@ -1143,8 +1134,6 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) touch_nmi_watchdog(); } - irq_unlock_sparse(); - return 0; } @@ -1249,7 +1238,7 @@ static int __init smp_sanity_check(unsigned max_cpus) /* * If we couldn't find a local APIC, then get out of here now! */ - if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) && + if (APIC_INTEGRATED(boot_cpu_apic_version) && !boot_cpu_has(X86_FEATURE_APIC)) { if (!disable_apic) { pr_err("BIOS bug, local APIC #%d not detected!...\n", @@ -1304,6 +1293,16 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL); } + + /* + * Set 'default' x86 topology, this matches default_topology() in that + * it has NUMA nodes as a topology level. See also + * native_smp_cpus_done(). + * + * Must be done before set_cpus_sibling_map() is ran. + */ + set_sched_topology(x86_topology); + set_cpu_sibling_map(0); switch (smp_sanity_check(max_cpus)) { @@ -1323,14 +1322,13 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) break; } - default_setup_apic_routing(); - if (read_apic_id() != boot_cpu_physical_apicid) { panic("Boot APIC ID in local APIC unexpected (%d vs %d)", read_apic_id(), boot_cpu_physical_apicid); /* Or can we switch back to PIC here? */ } + default_setup_apic_routing(); cpu0_logical_apicid = apic_bsp_setup(false); pr_info("CPU%d: ", 0); @@ -1370,6 +1368,9 @@ void __init native_smp_cpus_done(unsigned int max_cpus) { pr_debug("Boot done\n"); + if (x86_has_numa_in_package) + set_sched_topology(x86_numa_in_package_topology); + nmi_selftest(); impress_friends(); setup_ioapic_dest(); diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 4738f5e0f2ab..0653788026e2 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -8,80 +8,69 @@ #include <linux/export.h> #include <linux/uaccess.h> #include <asm/stacktrace.h> +#include <asm/unwind.h> -static int save_stack_stack(void *data, char *name) +static int save_stack_address(struct stack_trace *trace, unsigned long addr, + bool nosched) { - return 0; -} - -static int -__save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched) -{ - struct stack_trace *trace = data; -#ifdef CONFIG_FRAME_POINTER - if (!reliable) - return 0; -#endif if (nosched && in_sched_functions(addr)) return 0; + if (trace->skip > 0) { trace->skip--; return 0; } - if (trace->nr_entries < trace->max_entries) { - trace->entries[trace->nr_entries++] = addr; - return 0; - } else { - return -1; /* no more room, stop walking the stack */ - } -} -static int save_stack_address(void *data, unsigned long addr, int reliable) -{ - return __save_stack_address(data, addr, reliable, false); + if (trace->nr_entries >= trace->max_entries) + return -1; + + trace->entries[trace->nr_entries++] = addr; + return 0; } -static int -save_stack_address_nosched(void *data, unsigned long addr, int reliable) +static void __save_stack_trace(struct stack_trace *trace, + struct task_struct *task, struct pt_regs *regs, + bool nosched) { - return __save_stack_address(data, addr, reliable, true); -} + struct unwind_state state; + unsigned long addr; -static const struct stacktrace_ops save_stack_ops = { - .stack = save_stack_stack, - .address = save_stack_address, - .walk_stack = print_context_stack, -}; + if (regs) + save_stack_address(trace, regs->ip, nosched); -static const struct stacktrace_ops save_stack_ops_nosched = { - .stack = save_stack_stack, - .address = save_stack_address_nosched, - .walk_stack = print_context_stack, -}; + for (unwind_start(&state, task, regs, NULL); !unwind_done(&state); + unwind_next_frame(&state)) { + addr = unwind_get_return_address(&state); + if (!addr || save_stack_address(trace, addr, nosched)) + break; + } + + if (trace->nr_entries < trace->max_entries) + trace->entries[trace->nr_entries++] = ULONG_MAX; +} /* * Save stack-backtrace addresses into a stack_trace buffer. */ void save_stack_trace(struct stack_trace *trace) { - dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; + __save_stack_trace(trace, current, NULL, false); } EXPORT_SYMBOL_GPL(save_stack_trace); void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) { - dump_trace(current, regs, NULL, 0, &save_stack_ops, trace); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; + __save_stack_trace(trace, current, regs, false); } void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { - dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; + if (!try_get_task_stack(tsk)) + return; + + __save_stack_trace(trace, tsk, NULL, true); + + put_task_stack(tsk); } EXPORT_SYMBOL_GPL(save_stack_trace_tsk); diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 654f6c66fe45..8402907825b0 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -188,12 +188,12 @@ static int tboot_setup_sleep(void) tboot->num_mac_regions = 0; - for (i = 0; i < e820.nr_map; i++) { - if ((e820.map[i].type != E820_RAM) - && (e820.map[i].type != E820_RESERVED_KERN)) + for (i = 0; i < e820->nr_map; i++) { + if ((e820->map[i].type != E820_RAM) + && (e820->map[i].type != E820_RESERVED_KERN)) continue; - add_mac_region(e820.map[i].addr, e820.map[i].size); + add_mac_region(e820->map[i].addr, e820->map[i].size); } tboot->acpi_sinfo.kernel_s3_resume_vector = diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b70ca12dd389..bd4e3d4d3625 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -292,12 +292,30 @@ DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present) DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment) DO_ERROR(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check) +#ifdef CONFIG_VMAP_STACK +__visible void __noreturn handle_stack_overflow(const char *message, + struct pt_regs *regs, + unsigned long fault_address) +{ + printk(KERN_EMERG "BUG: stack guard page was hit at %p (stack is %p..%p)\n", + (void *)fault_address, current->stack, + (char *)current->stack + THREAD_SIZE - 1); + die(message, regs, 0); + + /* Be absolutely certain we don't return. */ + panic(message); +} +#endif + #ifdef CONFIG_X86_64 /* Runs on IST stack */ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) { static const char str[] = "double fault"; struct task_struct *tsk = current; +#ifdef CONFIG_VMAP_STACK + unsigned long cr2; +#endif #ifdef CONFIG_X86_ESPFIX64 extern unsigned char native_irq_return_iret[]; @@ -332,6 +350,49 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_DF; +#ifdef CONFIG_VMAP_STACK + /* + * If we overflow the stack into a guard page, the CPU will fail + * to deliver #PF and will send #DF instead. Similarly, if we + * take any non-IST exception while too close to the bottom of + * the stack, the processor will get a page fault while + * delivering the exception and will generate a double fault. + * + * According to the SDM (footnote in 6.15 under "Interrupt 14 - + * Page-Fault Exception (#PF): + * + * Processors update CR2 whenever a page fault is detected. If a + * second page fault occurs while an earlier page fault is being + * deliv- ered, the faulting linear address of the second fault will + * overwrite the contents of CR2 (replacing the previous + * address). These updates to CR2 occur even if the page fault + * results in a double fault or occurs during the delivery of a + * double fault. + * + * The logic below has a small possibility of incorrectly diagnosing + * some errors as stack overflows. For example, if the IDT or GDT + * gets corrupted such that #GP delivery fails due to a bad descriptor + * causing #GP and we hit this condition while CR2 coincidentally + * points to the stack guard page, we'll think we overflowed the + * stack. Given that we're going to panic one way or another + * if this happens, this isn't necessarily worth fixing. + * + * If necessary, we could improve the test by only diagnosing + * a stack overflow if the saved RSP points within 47 bytes of + * the bottom of the stack: if RSP == tsk_stack + 48 and we + * take an exception, the stack is already aligned and there + * will be enough room SS, RSP, RFLAGS, CS, RIP, and a + * possible error code, so a stack overflow would *not* double + * fault. With any less space left, exception delivery could + * fail, and, as a practical matter, we've overflowed the + * stack even if the actual trigger for the double fault was + * something else. + */ + cr2 = read_cr2(); + if ((unsigned long)task_stack_page(tsk) - 1 - cr2 < PAGE_SIZE) + handle_stack_overflow("kernel stack overflow (double-fault)", regs, cr2); +#endif + #ifdef CONFIG_DOUBLEFAULT df_debug(regs, error_code); #endif diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 78b9cb5a26af..46b2f41f8b05 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -23,6 +23,7 @@ #include <asm/x86_init.h> #include <asm/geode.h> #include <asm/apic.h> +#include <asm/intel-family.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -686,11 +687,16 @@ unsigned long native_calibrate_tsc(void) if (crystal_khz == 0) { switch (boot_cpu_data.x86_model) { - case 0x4E: /* SKL */ - case 0x5E: /* SKL */ + case INTEL_FAM6_SKYLAKE_MOBILE: + case INTEL_FAM6_SKYLAKE_DESKTOP: + case INTEL_FAM6_KABYLAKE_MOBILE: + case INTEL_FAM6_KABYLAKE_DESKTOP: crystal_khz = 24000; /* 24.0 MHz */ break; - case 0x5C: /* BXT */ + case INTEL_FAM6_SKYLAKE_X: + crystal_khz = 25000; /* 25.0 MHz */ + break; + case INTEL_FAM6_ATOM_GOLDMONT: crystal_khz = 19200; /* 19.2 MHz */ break; } diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c new file mode 100644 index 000000000000..a2456d4d286a --- /dev/null +++ b/arch/x86/kernel/unwind_frame.c @@ -0,0 +1,93 @@ +#include <linux/sched.h> +#include <asm/ptrace.h> +#include <asm/bitops.h> +#include <asm/stacktrace.h> +#include <asm/unwind.h> + +#define FRAME_HEADER_SIZE (sizeof(long) * 2) + +unsigned long unwind_get_return_address(struct unwind_state *state) +{ + unsigned long addr; + unsigned long *addr_p = unwind_get_return_address_ptr(state); + + if (unwind_done(state)) + return 0; + + addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p, + addr_p); + + return __kernel_text_address(addr) ? addr : 0; +} +EXPORT_SYMBOL_GPL(unwind_get_return_address); + +static bool update_stack_state(struct unwind_state *state, void *addr, + size_t len) +{ + struct stack_info *info = &state->stack_info; + + /* + * If addr isn't on the current stack, switch to the next one. + * + * We may have to traverse multiple stacks to deal with the possibility + * that 'info->next_sp' could point to an empty stack and 'addr' could + * be on a subsequent stack. + */ + while (!on_stack(info, addr, len)) + if (get_stack_info(info->next_sp, state->task, info, + &state->stack_mask)) + return false; + + return true; +} + +bool unwind_next_frame(struct unwind_state *state) +{ + unsigned long *next_bp; + + if (unwind_done(state)) + return false; + + next_bp = (unsigned long *)*state->bp; + + /* make sure the next frame's data is accessible */ + if (!update_stack_state(state, next_bp, FRAME_HEADER_SIZE)) + return false; + + /* move to the next frame */ + state->bp = next_bp; + return true; +} +EXPORT_SYMBOL_GPL(unwind_next_frame); + +void __unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs, unsigned long *first_frame) +{ + memset(state, 0, sizeof(*state)); + state->task = task; + + /* don't even attempt to start from user mode regs */ + if (regs && user_mode(regs)) { + state->stack_info.type = STACK_TYPE_UNKNOWN; + return; + } + + /* set up the starting stack frame */ + state->bp = get_frame_pointer(task, regs); + + /* initialize stack info and make sure the frame data is accessible */ + get_stack_info(state->bp, state->task, &state->stack_info, + &state->stack_mask); + update_stack_state(state, state->bp, FRAME_HEADER_SIZE); + + /* + * The caller can provide the address of the first frame directly + * (first_frame) or indirectly (regs->sp) to indicate which stack frame + * to start unwinding at. Skip ahead until we reach it. + */ + while (!unwind_done(state) && + (!on_stack(&state->stack_info, first_frame, sizeof(long)) || + state->bp < first_frame)) + unwind_next_frame(state); +} +EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c new file mode 100644 index 000000000000..b5a834c93065 --- /dev/null +++ b/arch/x86/kernel/unwind_guess.c @@ -0,0 +1,43 @@ +#include <linux/sched.h> +#include <linux/ftrace.h> +#include <asm/ptrace.h> +#include <asm/bitops.h> +#include <asm/stacktrace.h> +#include <asm/unwind.h> + +bool unwind_next_frame(struct unwind_state *state) +{ + struct stack_info *info = &state->stack_info; + + if (unwind_done(state)) + return false; + + do { + for (state->sp++; state->sp < info->end; state->sp++) + if (__kernel_text_address(*state->sp)) + return true; + + state->sp = info->next_sp; + + } while (!get_stack_info(state->sp, state->task, info, + &state->stack_mask)); + + return false; +} +EXPORT_SYMBOL_GPL(unwind_next_frame); + +void __unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs, unsigned long *first_frame) +{ + memset(state, 0, sizeof(*state)); + + state->task = task; + state->sp = first_frame; + + get_stack_info(first_frame, state->task, &state->stack_info, + &state->stack_mask); + + if (!__kernel_text_address(*first_frame)) + unwind_next_frame(state); +} +EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 95e49f6e4fc3..b2cee3d19477 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -38,7 +38,7 @@ EXPORT_SYMBOL(__copy_user_nocache); EXPORT_SYMBOL(_copy_from_user); EXPORT_SYMBOL(_copy_to_user); -EXPORT_SYMBOL_GPL(memcpy_mcsafe); +EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled); EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(clear_page); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 76c5e52436c4..0bd9f1287f39 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -91,7 +91,7 @@ struct x86_cpuinit_ops x86_cpuinit = { static void default_nmi_init(void) { }; static int default_i8042_detect(void) { return 1; }; -struct x86_platform_ops x86_platform = { +struct x86_platform_ops x86_platform __ro_after_init = { .calibrate_cpu = native_calibrate_cpu, .calibrate_tsc = native_calibrate_tsc, .get_wallclock = mach_get_cmos_time, @@ -108,7 +108,7 @@ struct x86_platform_ops x86_platform = { EXPORT_SYMBOL_GPL(x86_platform); #if defined(CONFIG_PCI_MSI) -struct x86_msi_ops x86_msi = { +struct x86_msi_ops x86_msi __ro_after_init = { .setup_msi_irqs = native_setup_msi_irqs, .teardown_msi_irq = native_teardown_msi_irq, .teardown_msi_irqs = default_teardown_msi_irqs, @@ -137,7 +137,7 @@ void arch_restore_msi_irqs(struct pci_dev *dev) } #endif -struct x86_io_apic_ops x86_io_apic_ops = { +struct x86_io_apic_ops x86_io_apic_ops __ro_after_init = { .read = native_io_apic_read, .disable = native_disable_io_apic, }; diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 464fa477afbf..3bff20710471 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -13,7 +13,7 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ - hyperv.o page_track.o + hyperv.o page_track.o debugfs.o kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += assigned-dev.o iommu.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 3235e0fe7792..afa7bbb596cd 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -366,7 +366,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) | F(ADX) | F(SMAP) | F(AVX512F) | F(AVX512PF) | F(AVX512ER) | - F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB); + F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) | + F(AVX512BW) | F(AVX512VL); /* cpuid 0xD.1.eax */ const u32 kvm_cpuid_D_1_eax_x86_features = diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c new file mode 100644 index 000000000000..c19c7ede9bd6 --- /dev/null +++ b/arch/x86/kvm/debugfs.c @@ -0,0 +1,69 @@ +/* + * Kernel-based Virtual Machine driver for Linux + * + * Copyright 2016 Red Hat, Inc. and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ +#include <linux/kvm_host.h> +#include <linux/debugfs.h> + +bool kvm_arch_has_vcpu_debugfs(void) +{ + return true; +} + +static int vcpu_get_tsc_offset(void *data, u64 *val) +{ + struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data; + *val = vcpu->arch.tsc_offset; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(vcpu_tsc_offset_fops, vcpu_get_tsc_offset, NULL, "%lld\n"); + +static int vcpu_get_tsc_scaling_ratio(void *data, u64 *val) +{ + struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data; + *val = vcpu->arch.tsc_scaling_ratio; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(vcpu_tsc_scaling_fops, vcpu_get_tsc_scaling_ratio, NULL, "%llu\n"); + +static int vcpu_get_tsc_scaling_frac_bits(void *data, u64 *val) +{ + *val = kvm_tsc_scaling_ratio_frac_bits; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(vcpu_tsc_scaling_frac_fops, vcpu_get_tsc_scaling_frac_bits, NULL, "%llu\n"); + +int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +{ + struct dentry *ret; + + ret = debugfs_create_file("tsc-offset", 0444, + vcpu->debugfs_dentry, + vcpu, &vcpu_tsc_offset_fops); + if (!ret) + return -ENOMEM; + + if (kvm_has_tsc_control) { + ret = debugfs_create_file("tsc-scaling-ratio", 0444, + vcpu->debugfs_dentry, + vcpu, &vcpu_tsc_scaling_fops); + if (!ret) + return -ENOMEM; + ret = debugfs_create_file("tsc-scaling-ratio-frac-bits", 0444, + vcpu->debugfs_dentry, + vcpu, &vcpu_tsc_scaling_frac_fops); + if (!ret) + return -ENOMEM; + + } + + return 0; +} diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 01bd7b7a6866..42b1c83741c8 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -386,7 +386,21 @@ static void synic_init(struct kvm_vcpu_hv_synic *synic) static u64 get_time_ref_counter(struct kvm *kvm) { - return div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); + struct kvm_hv *hv = &kvm->arch.hyperv; + struct kvm_vcpu *vcpu; + u64 tsc; + + /* + * The guest has not set up the TSC page or the clock isn't + * stable, fall back to get_kvmclock_ns. + */ + if (!hv->tsc_ref.tsc_sequence) + return div_u64(get_kvmclock_ns(kvm), 100); + + vcpu = kvm_get_vcpu(kvm, 0); + tsc = kvm_read_l1_tsc(vcpu, rdtsc()); + return mul_u64_u64_shr(tsc, hv->tsc_ref.tsc_scale, 64) + + hv->tsc_ref.tsc_offset; } static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, @@ -756,6 +770,129 @@ static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu, return 0; } +/* + * The kvmclock and Hyper-V TSC page use similar formulas, and converting + * between them is possible: + * + * kvmclock formula: + * nsec = (ticks - tsc_timestamp) * tsc_to_system_mul * 2^(tsc_shift-32) + * + system_time + * + * Hyper-V formula: + * nsec/100 = ticks * scale / 2^64 + offset + * + * When tsc_timestamp = system_time = 0, offset is zero in the Hyper-V formula. + * By dividing the kvmclock formula by 100 and equating what's left we get: + * ticks * scale / 2^64 = ticks * tsc_to_system_mul * 2^(tsc_shift-32) / 100 + * scale / 2^64 = tsc_to_system_mul * 2^(tsc_shift-32) / 100 + * scale = tsc_to_system_mul * 2^(32+tsc_shift) / 100 + * + * Now expand the kvmclock formula and divide by 100: + * nsec = ticks * tsc_to_system_mul * 2^(tsc_shift-32) + * - tsc_timestamp * tsc_to_system_mul * 2^(tsc_shift-32) + * + system_time + * nsec/100 = ticks * tsc_to_system_mul * 2^(tsc_shift-32) / 100 + * - tsc_timestamp * tsc_to_system_mul * 2^(tsc_shift-32) / 100 + * + system_time / 100 + * + * Replace tsc_to_system_mul * 2^(tsc_shift-32) / 100 by scale / 2^64: + * nsec/100 = ticks * scale / 2^64 + * - tsc_timestamp * scale / 2^64 + * + system_time / 100 + * + * Equate with the Hyper-V formula so that ticks * scale / 2^64 cancels out: + * offset = system_time / 100 - tsc_timestamp * scale / 2^64 + * + * These two equivalencies are implemented in this function. + */ +static bool compute_tsc_page_parameters(struct pvclock_vcpu_time_info *hv_clock, + HV_REFERENCE_TSC_PAGE *tsc_ref) +{ + u64 max_mul; + + if (!(hv_clock->flags & PVCLOCK_TSC_STABLE_BIT)) + return false; + + /* + * check if scale would overflow, if so we use the time ref counter + * tsc_to_system_mul * 2^(tsc_shift+32) / 100 >= 2^64 + * tsc_to_system_mul / 100 >= 2^(32-tsc_shift) + * tsc_to_system_mul >= 100 * 2^(32-tsc_shift) + */ + max_mul = 100ull << (32 - hv_clock->tsc_shift); + if (hv_clock->tsc_to_system_mul >= max_mul) + return false; + + /* + * Otherwise compute the scale and offset according to the formulas + * derived above. + */ + tsc_ref->tsc_scale = + mul_u64_u32_div(1ULL << (32 + hv_clock->tsc_shift), + hv_clock->tsc_to_system_mul, + 100); + + tsc_ref->tsc_offset = hv_clock->system_time; + do_div(tsc_ref->tsc_offset, 100); + tsc_ref->tsc_offset -= + mul_u64_u64_shr(hv_clock->tsc_timestamp, tsc_ref->tsc_scale, 64); + return true; +} + +void kvm_hv_setup_tsc_page(struct kvm *kvm, + struct pvclock_vcpu_time_info *hv_clock) +{ + struct kvm_hv *hv = &kvm->arch.hyperv; + u32 tsc_seq; + u64 gfn; + + BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence)); + BUILD_BUG_ON(offsetof(HV_REFERENCE_TSC_PAGE, tsc_sequence) != 0); + + if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) + return; + + gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; + /* + * Because the TSC parameters only vary when there is a + * change in the master clock, do not bother with caching. + */ + if (unlikely(kvm_read_guest(kvm, gfn_to_gpa(gfn), + &tsc_seq, sizeof(tsc_seq)))) + return; + + /* + * While we're computing and writing the parameters, force the + * guest to use the time reference count MSR. + */ + hv->tsc_ref.tsc_sequence = 0; + if (kvm_write_guest(kvm, gfn_to_gpa(gfn), + &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) + return; + + if (!compute_tsc_page_parameters(hv_clock, &hv->tsc_ref)) + return; + + /* Ensure sequence is zero before writing the rest of the struct. */ + smp_wmb(); + if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref))) + return; + + /* + * Now switch to the TSC page mechanism by writing the sequence. + */ + tsc_seq++; + if (tsc_seq == 0xFFFFFFFF || tsc_seq == 0) + tsc_seq = 1; + + /* Write the struct entirely before the non-zero sequence. */ + smp_wmb(); + + hv->tsc_ref.tsc_sequence = tsc_seq; + kvm_write_guest(kvm, gfn_to_gpa(gfn), + &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)); +} + static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { @@ -793,23 +930,11 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, mark_page_dirty(kvm, gfn); break; } - case HV_X64_MSR_REFERENCE_TSC: { - u64 gfn; - HV_REFERENCE_TSC_PAGE tsc_ref; - - memset(&tsc_ref, 0, sizeof(tsc_ref)); + case HV_X64_MSR_REFERENCE_TSC: hv->hv_tsc_page = data; - if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE)) - break; - gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; - if (kvm_write_guest( - kvm, - gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT, - &tsc_ref, sizeof(tsc_ref))) - return 1; - mark_page_dirty(kvm, gfn); + if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE) + kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); break; - } case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: return kvm_hv_msr_set_crash_data(vcpu, msr - HV_X64_MSR_CRASH_P0, diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 60eccd4bd1d3..cd1119538add 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -84,4 +84,7 @@ static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu) void kvm_hv_process_stimers(struct kvm_vcpu *vcpu); +void kvm_hv_setup_tsc_page(struct kvm *kvm, + struct pvclock_vcpu_time_info *hv_clock); + #endif diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 5f42d038fcb4..c7220ba94aa7 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -109,6 +109,7 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu) { bool new_val, old_val; struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; + struct dest_map *dest_map = &ioapic->rtc_status.dest_map; union kvm_ioapic_redirect_entry *e; e = &ioapic->redirtbl[RTC_GSI]; @@ -117,16 +118,17 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu) return; new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector); - old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map); + old_val = test_bit(vcpu->vcpu_id, dest_map->map); if (new_val == old_val) return; if (new_val) { - __set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map); + __set_bit(vcpu->vcpu_id, dest_map->map); + dest_map->vectors[vcpu->vcpu_id] = e->fields.vector; ioapic->rtc_status.pending_eoi++; } else { - __clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map); + __clear_bit(vcpu->vcpu_id, dest_map->map); ioapic->rtc_status.pending_eoi--; rtc_status_pending_eoi_check_valid(ioapic); } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index b62c85229711..23b99f305382 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1761,9 +1761,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) if (value & MSR_IA32_APICBASE_ENABLE) { kvm_apic_set_xapic_id(apic, vcpu->vcpu_id); static_key_slow_dec_deferred(&apic_hw_disabled); - } else + } else { static_key_slow_inc(&apic_hw_disabled.key); - recalculate_apic_map(vcpu->kvm); + recalculate_apic_map(vcpu->kvm); + } } if ((old_value ^ value) & X2APIC_ENABLE) { diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 3d4cc8cc56a3..d9c7e986b4e4 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1207,7 +1207,7 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) * * Return true if tlb need be flushed. */ -static bool spte_write_protect(struct kvm *kvm, u64 *sptep, bool pt_protect) +static bool spte_write_protect(u64 *sptep, bool pt_protect) { u64 spte = *sptep; @@ -1233,12 +1233,12 @@ static bool __rmap_write_protect(struct kvm *kvm, bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) - flush |= spte_write_protect(kvm, sptep, pt_protect); + flush |= spte_write_protect(sptep, pt_protect); return flush; } -static bool spte_clear_dirty(struct kvm *kvm, u64 *sptep) +static bool spte_clear_dirty(u64 *sptep) { u64 spte = *sptep; @@ -1256,12 +1256,12 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) - flush |= spte_clear_dirty(kvm, sptep); + flush |= spte_clear_dirty(sptep); return flush; } -static bool spte_set_dirty(struct kvm *kvm, u64 *sptep) +static bool spte_set_dirty(u64 *sptep) { u64 spte = *sptep; @@ -1279,7 +1279,7 @@ static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) - flush |= spte_set_dirty(kvm, sptep); + flush |= spte_set_dirty(sptep); return flush; } diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c index 39b91127ef07..cd944435dfbd 100644 --- a/arch/x86/kvm/pmu_amd.c +++ b/arch/x86/kvm/pmu_amd.c @@ -23,8 +23,8 @@ static struct kvm_event_hw_type_mapping amd_event_mapping[] = { [0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES }, [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, - [2] = { 0x80, 0x00, PERF_COUNT_HW_CACHE_REFERENCES }, - [3] = { 0x81, 0x00, PERF_COUNT_HW_CACHE_MISSES }, + [2] = { 0x7d, 0x07, PERF_COUNT_HW_CACHE_REFERENCES }, + [3] = { 0x7e, 0x07, PERF_COUNT_HW_CACHE_MISSES }, [4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, [5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, [6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index af523d84d102..f8157a36ab09 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -34,6 +34,8 @@ #include <linux/sched.h> #include <linux/trace_events.h> #include <linux/slab.h> +#include <linux/amd-iommu.h> +#include <linux/hashtable.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -41,6 +43,7 @@ #include <asm/desc.h> #include <asm/debugreg.h> #include <asm/kvm_para.h> +#include <asm/irq_remapping.h> #include <asm/virtext.h> #include "trace.h" @@ -96,6 +99,19 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); #define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 #define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF +/* AVIC GATAG is encoded using VM and VCPU IDs */ +#define AVIC_VCPU_ID_BITS 8 +#define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1) + +#define AVIC_VM_ID_BITS 24 +#define AVIC_VM_ID_NR (1 << AVIC_VM_ID_BITS) +#define AVIC_VM_ID_MASK ((1 << AVIC_VM_ID_BITS) - 1) + +#define AVIC_GATAG(x, y) (((x & AVIC_VM_ID_MASK) << AVIC_VCPU_ID_BITS) | \ + (y & AVIC_VCPU_ID_MASK)) +#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK) +#define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK) + static bool erratum_383_found __read_mostly; static const u32 host_save_user_msrs[] = { @@ -185,6 +201,23 @@ struct vcpu_svm { struct page *avic_backing_page; u64 *avic_physical_id_cache; bool avic_is_running; + + /* + * Per-vcpu list of struct amd_svm_iommu_ir: + * This is used mainly to store interrupt remapping information used + * when update the vcpu affinity. This avoids the need to scan for + * IRTE and try to match ga_tag in the IOMMU driver. + */ + struct list_head ir_list; + spinlock_t ir_list_lock; +}; + +/* + * This is a wrapper of struct amd_iommu_ir_data. + */ +struct amd_svm_iommu_ir { + struct list_head node; /* Used by SVM for per-vcpu ir_list */ + void *data; /* Storing pointer to struct amd_ir_data */ }; #define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) @@ -242,6 +275,10 @@ static int avic; module_param(avic, int, S_IRUGO); #endif +/* AVIC VM ID bit masks and lock */ +static DECLARE_BITMAP(avic_vm_id_bitmap, AVIC_VM_ID_NR); +static DEFINE_SPINLOCK(avic_vm_id_lock); + static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu); static void svm_complete_interrupts(struct vcpu_svm *svm); @@ -928,6 +965,55 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0); } +/* Note: + * This hash table is used to map VM_ID to a struct kvm_arch, + * when handling AMD IOMMU GALOG notification to schedule in + * a particular vCPU. + */ +#define SVM_VM_DATA_HASH_BITS 8 +DECLARE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS); +static spinlock_t svm_vm_data_hash_lock; + +/* Note: + * This function is called from IOMMU driver to notify + * SVM to schedule in a particular vCPU of a particular VM. + */ +static int avic_ga_log_notifier(u32 ga_tag) +{ + unsigned long flags; + struct kvm_arch *ka = NULL; + struct kvm_vcpu *vcpu = NULL; + u32 vm_id = AVIC_GATAG_TO_VMID(ga_tag); + u32 vcpu_id = AVIC_GATAG_TO_VCPUID(ga_tag); + + pr_debug("SVM: %s: vm_id=%#x, vcpu_id=%#x\n", __func__, vm_id, vcpu_id); + + spin_lock_irqsave(&svm_vm_data_hash_lock, flags); + hash_for_each_possible(svm_vm_data_hash, ka, hnode, vm_id) { + struct kvm *kvm = container_of(ka, struct kvm, arch); + struct kvm_arch *vm_data = &kvm->arch; + + if (vm_data->avic_vm_id != vm_id) + continue; + vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); + break; + } + spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); + + if (!vcpu) + return 0; + + /* Note: + * At this point, the IOMMU should have already set the pending + * bit in the vAPIC backing page. So, we just need to schedule + * in the vcpu. + */ + if (vcpu->mode == OUTSIDE_GUEST_MODE) + kvm_vcpu_wake_up(vcpu); + + return 0; +} + static __init int svm_hardware_setup(void) { int cpu; @@ -986,10 +1072,15 @@ static __init int svm_hardware_setup(void) if (avic) { if (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC) || - !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) + !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) { avic = false; - else + } else { pr_info("AVIC enabled\n"); + + hash_init(svm_vm_data_hash); + spin_lock_init(&svm_vm_data_hash_lock); + amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); + } } return 0; @@ -1028,13 +1119,6 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } -static u64 svm_read_tsc_offset(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - return svm->vmcb->control.tsc_offset; -} - static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1280,19 +1364,55 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return 0; } +static inline int avic_get_next_vm_id(void) +{ + int id; + + spin_lock(&avic_vm_id_lock); + + /* AVIC VM ID is one-based. */ + id = find_next_zero_bit(avic_vm_id_bitmap, AVIC_VM_ID_NR, 1); + if (id <= AVIC_VM_ID_MASK) + __set_bit(id, avic_vm_id_bitmap); + else + id = -EAGAIN; + + spin_unlock(&avic_vm_id_lock); + return id; +} + +static inline int avic_free_vm_id(int id) +{ + if (id <= 0 || id > AVIC_VM_ID_MASK) + return -EINVAL; + + spin_lock(&avic_vm_id_lock); + __clear_bit(id, avic_vm_id_bitmap); + spin_unlock(&avic_vm_id_lock); + return 0; +} + static void avic_vm_destroy(struct kvm *kvm) { + unsigned long flags; struct kvm_arch *vm_data = &kvm->arch; + avic_free_vm_id(vm_data->avic_vm_id); + if (vm_data->avic_logical_id_table_page) __free_page(vm_data->avic_logical_id_table_page); if (vm_data->avic_physical_id_table_page) __free_page(vm_data->avic_physical_id_table_page); + + spin_lock_irqsave(&svm_vm_data_hash_lock, flags); + hash_del(&vm_data->hnode); + spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); } static int avic_vm_init(struct kvm *kvm) { - int err = -ENOMEM; + unsigned long flags; + int vm_id, err = -ENOMEM; struct kvm_arch *vm_data = &kvm->arch; struct page *p_page; struct page *l_page; @@ -1300,6 +1420,11 @@ static int avic_vm_init(struct kvm *kvm) if (!avic) return 0; + vm_id = avic_get_next_vm_id(); + if (vm_id < 0) + return vm_id; + vm_data->avic_vm_id = (u32)vm_id; + /* Allocating physical APIC ID table (4KB) */ p_page = alloc_page(GFP_KERNEL); if (!p_page) @@ -1316,6 +1441,10 @@ static int avic_vm_init(struct kvm *kvm) vm_data->avic_logical_id_table_page = l_page; clear_page(page_address(l_page)); + spin_lock_irqsave(&svm_vm_data_hash_lock, flags); + hash_add(svm_vm_data_hash, &vm_data->hnode, vm_data->avic_vm_id); + spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); + return 0; free_avic: @@ -1323,31 +1452,34 @@ free_avic: return err; } -/** - * This function is called during VCPU halt/unhalt. - */ -static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) +static inline int +avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) { - u64 entry; - int h_physical_id = kvm_cpu_get_apicid(vcpu->cpu); + int ret = 0; + unsigned long flags; + struct amd_svm_iommu_ir *ir; struct vcpu_svm *svm = to_svm(vcpu); - if (!kvm_vcpu_apicv_active(vcpu)) - return; - - svm->avic_is_running = is_run; + if (!kvm_arch_has_assigned_device(vcpu->kvm)) + return 0; - /* ID = 0xff (broadcast), ID > 0xff (reserved) */ - if (WARN_ON(h_physical_id >= AVIC_MAX_PHYSICAL_ID_COUNT)) - return; + /* + * Here, we go through the per-vcpu ir_list to update all existing + * interrupt remapping table entry targeting this vcpu. + */ + spin_lock_irqsave(&svm->ir_list_lock, flags); - entry = READ_ONCE(*(svm->avic_physical_id_cache)); - WARN_ON(is_run == !!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)); + if (list_empty(&svm->ir_list)) + goto out; - entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; - if (is_run) - entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; - WRITE_ONCE(*(svm->avic_physical_id_cache), entry); + list_for_each_entry(ir, &svm->ir_list, node) { + ret = amd_iommu_update_ga(cpu, r, ir->data); + if (ret) + break; + } +out: + spin_unlock_irqrestore(&svm->ir_list_lock, flags); + return ret; } static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -1374,6 +1506,8 @@ static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; WRITE_ONCE(*(svm->avic_physical_id_cache), entry); + avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, + svm->avic_is_running); } static void avic_vcpu_put(struct kvm_vcpu *vcpu) @@ -1385,10 +1519,27 @@ static void avic_vcpu_put(struct kvm_vcpu *vcpu) return; entry = READ_ONCE(*(svm->avic_physical_id_cache)); + if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK) + avic_update_iommu_vcpu_affinity(vcpu, -1, 0); + entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; WRITE_ONCE(*(svm->avic_physical_id_cache), entry); } +/** + * This function is called during VCPU halt/unhalt. + */ +static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->avic_is_running = is_run; + if (is_run) + avic_vcpu_load(vcpu, vcpu->cpu); + else + avic_vcpu_put(vcpu); +} + static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1450,6 +1601,9 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) err = avic_init_backing_page(&svm->vcpu); if (err) goto free_page4; + + INIT_LIST_HEAD(&svm->ir_list); + spin_lock_init(&svm->ir_list_lock); } /* We initialize this flag to true to make sure that the is_running @@ -4246,6 +4400,209 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) kvm_vcpu_wake_up(vcpu); } +static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) +{ + unsigned long flags; + struct amd_svm_iommu_ir *cur; + + spin_lock_irqsave(&svm->ir_list_lock, flags); + list_for_each_entry(cur, &svm->ir_list, node) { + if (cur->data != pi->ir_data) + continue; + list_del(&cur->node); + kfree(cur); + break; + } + spin_unlock_irqrestore(&svm->ir_list_lock, flags); +} + +static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) +{ + int ret = 0; + unsigned long flags; + struct amd_svm_iommu_ir *ir; + + /** + * In some cases, the existing irte is updaed and re-set, + * so we need to check here if it's already been * added + * to the ir_list. + */ + if (pi->ir_data && (pi->prev_ga_tag != 0)) { + struct kvm *kvm = svm->vcpu.kvm; + u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag); + struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); + struct vcpu_svm *prev_svm; + + if (!prev_vcpu) { + ret = -EINVAL; + goto out; + } + + prev_svm = to_svm(prev_vcpu); + svm_ir_list_del(prev_svm, pi); + } + + /** + * Allocating new amd_iommu_pi_data, which will get + * add to the per-vcpu ir_list. + */ + ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL); + if (!ir) { + ret = -ENOMEM; + goto out; + } + ir->data = pi->ir_data; + + spin_lock_irqsave(&svm->ir_list_lock, flags); + list_add(&ir->node, &svm->ir_list); + spin_unlock_irqrestore(&svm->ir_list_lock, flags); +out: + return ret; +} + +/** + * Note: + * The HW cannot support posting multicast/broadcast + * interrupts to a vCPU. So, we still use legacy interrupt + * remapping for these kind of interrupts. + * + * For lowest-priority interrupts, we only support + * those with single CPU as the destination, e.g. user + * configures the interrupts via /proc/irq or uses + * irqbalance to make the interrupts single-CPU. + */ +static int +get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, + struct vcpu_data *vcpu_info, struct vcpu_svm **svm) +{ + struct kvm_lapic_irq irq; + struct kvm_vcpu *vcpu = NULL; + + kvm_set_msi_irq(kvm, e, &irq); + + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) { + pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n", + __func__, irq.vector); + return -1; + } + + pr_debug("SVM: %s: use GA mode for irq %u\n", __func__, + irq.vector); + *svm = to_svm(vcpu); + vcpu_info->pi_desc_addr = page_to_phys((*svm)->avic_backing_page); + vcpu_info->vector = irq.vector; + + return 0; +} + +/* + * svm_update_pi_irte - set IRTE for Posted-Interrupts + * + * @kvm: kvm + * @host_irq: host irq of the interrupt + * @guest_irq: gsi of the interrupt + * @set: set or unset PI + * returns 0 on success, < 0 on failure + */ +static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, + uint32_t guest_irq, bool set) +{ + struct kvm_kernel_irq_routing_entry *e; + struct kvm_irq_routing_table *irq_rt; + int idx, ret = -EINVAL; + + if (!kvm_arch_has_assigned_device(kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return 0; + + pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n", + __func__, host_irq, guest_irq, set); + + idx = srcu_read_lock(&kvm->irq_srcu); + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); + WARN_ON(guest_irq >= irq_rt->nr_rt_entries); + + hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { + struct vcpu_data vcpu_info; + struct vcpu_svm *svm = NULL; + + if (e->type != KVM_IRQ_ROUTING_MSI) + continue; + + /** + * Here, we setup with legacy mode in the following cases: + * 1. When cannot target interrupt to a specific vcpu. + * 2. Unsetting posted interrupt. + * 3. APIC virtialization is disabled for the vcpu. + */ + if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set && + kvm_vcpu_apicv_active(&svm->vcpu)) { + struct amd_iommu_pi_data pi; + + /* Try to enable guest_mode in IRTE */ + pi.base = page_to_phys(svm->avic_backing_page) & AVIC_HPA_MASK; + pi.ga_tag = AVIC_GATAG(kvm->arch.avic_vm_id, + svm->vcpu.vcpu_id); + pi.is_guest_mode = true; + pi.vcpu_data = &vcpu_info; + ret = irq_set_vcpu_affinity(host_irq, &pi); + + /** + * Here, we successfully setting up vcpu affinity in + * IOMMU guest mode. Now, we need to store the posted + * interrupt information in a per-vcpu ir_list so that + * we can reference to them directly when we update vcpu + * scheduling information in IOMMU irte. + */ + if (!ret && pi.is_guest_mode) + svm_ir_list_add(svm, &pi); + } else { + /* Use legacy mode in IRTE */ + struct amd_iommu_pi_data pi; + + /** + * Here, pi is used to: + * - Tell IOMMU to use legacy mode for this interrupt. + * - Retrieve ga_tag of prior interrupt remapping data. + */ + pi.is_guest_mode = false; + ret = irq_set_vcpu_affinity(host_irq, &pi); + + /** + * Check if the posted interrupt was previously + * setup with the guest_mode by checking if the ga_tag + * was cached. If so, we need to clean up the per-vcpu + * ir_list. + */ + if (!ret && pi.prev_ga_tag) { + int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag); + struct kvm_vcpu *vcpu; + + vcpu = kvm_get_vcpu_by_id(kvm, id); + if (vcpu) + svm_ir_list_del(to_svm(vcpu), &pi); + } + } + + if (!ret && svm) { + trace_kvm_pi_irte_update(svm->vcpu.vcpu_id, + host_irq, e->gsi, + vcpu_info.vector, + vcpu_info.pi_desc_addr, set); + } + + if (ret < 0) { + pr_err("%s: failed to update PI IRTE\n", __func__); + goto out; + } + } + + ret = 0; +out: + srcu_read_unlock(&kvm->irq_srcu, idx); + return ret; +} + static int svm_nmi_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -4961,7 +5318,7 @@ static inline void avic_post_state_restore(struct kvm_vcpu *vcpu) avic_handle_ldr_update(vcpu); } -static struct kvm_x86_ops svm_x86_ops = { +static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, .hardware_setup = svm_hardware_setup, @@ -5064,7 +5421,6 @@ static struct kvm_x86_ops svm_x86_ops = { .has_wbinvd_exit = svm_has_wbinvd_exit, - .read_tsc_offset = svm_read_tsc_offset, .write_tsc_offset = svm_write_tsc_offset, .adjust_tsc_offset_guest = svm_adjust_tsc_offset_guest, .read_l1_tsc = svm_read_l1_tsc, @@ -5078,6 +5434,7 @@ static struct kvm_x86_ops svm_x86_ops = { .pmu_ops = &amd_pmu_ops, .deliver_posted_interrupt = svm_deliver_avic_intr, + .update_pi_irte = svm_update_pi_irte, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 5cede40e2552..cf1b16dbc98a 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -927,6 +927,8 @@ static unsigned long *vmx_msr_bitmap_legacy; static unsigned long *vmx_msr_bitmap_longmode; static unsigned long *vmx_msr_bitmap_legacy_x2apic; static unsigned long *vmx_msr_bitmap_longmode_x2apic; +static unsigned long *vmx_msr_bitmap_legacy_x2apic_apicv_inactive; +static unsigned long *vmx_msr_bitmap_longmode_x2apic_apicv_inactive; static unsigned long *vmx_vmread_bitmap; static unsigned long *vmx_vmwrite_bitmap; @@ -939,6 +941,7 @@ static DEFINE_SPINLOCK(vmx_vpid_lock); static struct vmcs_config { int size; int order; + u32 basic_cap; u32 revision_id; u32 pin_based_exec_ctrl; u32 cpu_based_exec_ctrl; @@ -1215,6 +1218,11 @@ static inline bool cpu_has_vmx_ple(void) SECONDARY_EXEC_PAUSE_LOOP_EXITING; } +static inline bool cpu_has_vmx_basic_inout(void) +{ + return (((u64)vmcs_config.basic_cap << 32) & VMX_BASIC_INOUT); +} + static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu) { return flexpriority_enabled && lapic_in_kernel(vcpu); @@ -2518,10 +2526,17 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) else if (cpu_has_secondary_exec_ctrls() && (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic; + if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) { + if (is_long_mode(vcpu)) + msr_bitmap = vmx_msr_bitmap_longmode_x2apic; + else + msr_bitmap = vmx_msr_bitmap_legacy_x2apic; + } else { + if (is_long_mode(vcpu)) + msr_bitmap = vmx_msr_bitmap_longmode_x2apic_apicv_inactive; + else + msr_bitmap = vmx_msr_bitmap_legacy_x2apic_apicv_inactive; + } } else { if (is_long_mode(vcpu)) msr_bitmap = vmx_msr_bitmap_longmode; @@ -2603,11 +2618,6 @@ static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) return host_tsc + tsc_offset; } -static u64 vmx_read_tsc_offset(struct kvm_vcpu *vcpu) -{ - return vmcs_read64(TSC_OFFSET); -} - /* * writes 'offset' into guest's timestamp counter offset register */ @@ -2877,6 +2887,8 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) *pdata = VMCS12_REVISION | VMX_BASIC_TRUE_CTLS | ((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) | (VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT); + if (cpu_has_vmx_basic_inout()) + *pdata |= VMX_BASIC_INOUT; break; case MSR_IA32_VMX_TRUE_PINBASED_CTLS: case MSR_IA32_VMX_PINBASED_CTLS: @@ -3457,7 +3469,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) return -EIO; vmcs_conf->size = vmx_msr_high & 0x1fff; - vmcs_conf->order = get_order(vmcs_config.size); + vmcs_conf->order = get_order(vmcs_conf->size); + vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; vmcs_conf->revision_id = vmx_msr_low; vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; @@ -4678,28 +4691,49 @@ static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only) msr, MSR_TYPE_R | MSR_TYPE_W); } -static void vmx_enable_intercept_msr_read_x2apic(u32 msr) +static void vmx_enable_intercept_msr_read_x2apic(u32 msr, bool apicv_active) { - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, MSR_TYPE_R); - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, MSR_TYPE_R); + if (apicv_active) { + __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, + msr, MSR_TYPE_R); + __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, + msr, MSR_TYPE_R); + } else { + __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, + msr, MSR_TYPE_R); + __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, + msr, MSR_TYPE_R); + } } -static void vmx_disable_intercept_msr_read_x2apic(u32 msr) +static void vmx_disable_intercept_msr_read_x2apic(u32 msr, bool apicv_active) { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, MSR_TYPE_R); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, MSR_TYPE_R); + if (apicv_active) { + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, + msr, MSR_TYPE_R); + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, + msr, MSR_TYPE_R); + } else { + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, + msr, MSR_TYPE_R); + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, + msr, MSR_TYPE_R); + } } -static void vmx_disable_intercept_msr_write_x2apic(u32 msr) +static void vmx_disable_intercept_msr_write_x2apic(u32 msr, bool apicv_active) { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, MSR_TYPE_W); + if (apicv_active) { + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, + msr, MSR_TYPE_W); + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, + msr, MSR_TYPE_W); + } else { + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, + msr, MSR_TYPE_W); + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, + msr, MSR_TYPE_W); + } } static bool vmx_get_enable_apicv(void) @@ -5279,29 +5313,30 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (is_guest_mode(vcpu)) - return; + if (!is_guest_mode(vcpu)) { + if (!cpu_has_virtual_nmis()) { + /* + * Tracking the NMI-blocked state in software is built upon + * finding the next open IRQ window. This, in turn, depends on + * well-behaving guests: They have to keep IRQs disabled at + * least as long as the NMI handler runs. Otherwise we may + * cause NMI nesting, maybe breaking the guest. But as this is + * highly unlikely, we can live with the residual risk. + */ + vmx->soft_vnmi_blocked = 1; + vmx->vnmi_blocked_time = 0; + } - if (!cpu_has_virtual_nmis()) { - /* - * Tracking the NMI-blocked state in software is built upon - * finding the next open IRQ window. This, in turn, depends on - * well-behaving guests: They have to keep IRQs disabled at - * least as long as the NMI handler runs. Otherwise we may - * cause NMI nesting, maybe breaking the guest. But as this is - * highly unlikely, we can live with the residual risk. - */ - vmx->soft_vnmi_blocked = 1; - vmx->vnmi_blocked_time = 0; + ++vcpu->stat.nmi_injections; + vmx->nmi_known_unmasked = false; } - ++vcpu->stat.nmi_injections; - vmx->nmi_known_unmasked = false; if (vmx->rmode.vm86_active) { if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0) != EMULATE_DONE) kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return; } + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR); } @@ -6109,7 +6144,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) exit_qualification = vmcs_readl(EXIT_QUALIFICATION); gla_validity = (exit_qualification >> 7) & 0x3; - if (gla_validity != 0x3 && gla_validity != 0x1 && gla_validity != 0) { + if (gla_validity == 0x2) { printk(KERN_ERR "EPT: Handling EPT violation failed!\n"); printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n", (long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS), @@ -6360,22 +6395,32 @@ static __init int hardware_setup(void) if (!vmx_msr_bitmap_legacy_x2apic) goto out2; + vmx_msr_bitmap_legacy_x2apic_apicv_inactive = + (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx_msr_bitmap_legacy_x2apic_apicv_inactive) + goto out3; + vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_msr_bitmap_longmode) - goto out3; + goto out4; vmx_msr_bitmap_longmode_x2apic = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_msr_bitmap_longmode_x2apic) - goto out4; + goto out5; + + vmx_msr_bitmap_longmode_x2apic_apicv_inactive = + (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx_msr_bitmap_longmode_x2apic_apicv_inactive) + goto out6; vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmread_bitmap) - goto out6; + goto out7; vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmwrite_bitmap) - goto out7; + goto out8; memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE); memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE); @@ -6394,7 +6439,7 @@ static __init int hardware_setup(void) if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; - goto out8; + goto out9; } if (boot_cpu_has(X86_FEATURE_NX)) @@ -6461,20 +6506,35 @@ static __init int hardware_setup(void) vmx_msr_bitmap_legacy, PAGE_SIZE); memcpy(vmx_msr_bitmap_longmode_x2apic, vmx_msr_bitmap_longmode, PAGE_SIZE); + memcpy(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, + vmx_msr_bitmap_legacy, PAGE_SIZE); + memcpy(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, + vmx_msr_bitmap_longmode, PAGE_SIZE); set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ + /* + * enable_apicv && kvm_vcpu_apicv_active() + */ for (msr = 0x800; msr <= 0x8ff; msr++) - vmx_disable_intercept_msr_read_x2apic(msr); + vmx_disable_intercept_msr_read_x2apic(msr, true); /* TMCCT */ - vmx_enable_intercept_msr_read_x2apic(0x839); + vmx_enable_intercept_msr_read_x2apic(0x839, true); /* TPR */ - vmx_disable_intercept_msr_write_x2apic(0x808); + vmx_disable_intercept_msr_write_x2apic(0x808, true); /* EOI */ - vmx_disable_intercept_msr_write_x2apic(0x80b); + vmx_disable_intercept_msr_write_x2apic(0x80b, true); /* SELF-IPI */ - vmx_disable_intercept_msr_write_x2apic(0x83f); + vmx_disable_intercept_msr_write_x2apic(0x83f, true); + + /* + * (enable_apicv && !kvm_vcpu_apicv_active()) || + * !enable_apicv + */ + /* TPR */ + vmx_disable_intercept_msr_read_x2apic(0x808, false); + vmx_disable_intercept_msr_write_x2apic(0x808, false); if (enable_ept) { kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, @@ -6521,14 +6581,18 @@ static __init int hardware_setup(void) return alloc_kvm_area(); -out8: +out9: free_page((unsigned long)vmx_vmwrite_bitmap); -out7: +out8: free_page((unsigned long)vmx_vmread_bitmap); +out7: + free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic_apicv_inactive); out6: free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); -out4: +out5: free_page((unsigned long)vmx_msr_bitmap_longmode); +out4: + free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic_apicv_inactive); out3: free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic); out2: @@ -6544,7 +6608,9 @@ out: static __exit void hardware_unsetup(void) { free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic); + free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic_apicv_inactive); free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); + free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic_apicv_inactive); free_page((unsigned long)vmx_msr_bitmap_legacy); free_page((unsigned long)vmx_msr_bitmap_longmode); free_page((unsigned long)vmx_io_bitmap_b); @@ -6726,7 +6792,7 @@ static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator) { /* TODO: not to reset guest simply here. */ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); - pr_warn("kvm: nested vmx abort, indicator %d\n", indicator); + pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator); } static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer) @@ -7013,7 +7079,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu) vmx->nested.vmcs02_num = 0; hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL); + HRTIMER_MODE_REL_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; vmx->nested.vmxon = true; @@ -8435,12 +8501,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) return; } - /* - * There is not point to enable virtualize x2apic without enable - * apicv - */ - if (!cpu_has_vmx_virtualize_x2apic_mode() || - !kvm_vcpu_apicv_active(vcpu)) + if (!cpu_has_vmx_virtualize_x2apic_mode()) return; if (!cpu_need_tpr_shadow(vcpu)) @@ -9598,7 +9659,7 @@ static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, maxphyaddr = cpuid_maxphyaddr(vcpu); if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr || (addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr) { - pr_warn_ratelimited( + pr_debug_ratelimited( "nVMX: invalid MSR switch (0x%lx, %d, %llu, 0x%08llx)", addr_field, maxphyaddr, count, addr); return -EINVAL; @@ -9671,13 +9732,13 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) for (i = 0; i < count; i++) { if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e), &e, sizeof(e))) { - pr_warn_ratelimited( + pr_debug_ratelimited( "%s cannot read MSR entry (%u, 0x%08llx)\n", __func__, i, gpa + i * sizeof(e)); goto fail; } if (nested_vmx_load_msr_check(vcpu, &e)) { - pr_warn_ratelimited( + pr_debug_ratelimited( "%s check failed (%u, 0x%x, 0x%x)\n", __func__, i, e.index, e.reserved); goto fail; @@ -9685,7 +9746,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) msr.index = e.index; msr.data = e.value; if (kvm_set_msr(vcpu, &msr)) { - pr_warn_ratelimited( + pr_debug_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", __func__, i, e.index, e.value); goto fail; @@ -9706,13 +9767,13 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e), &e, 2 * sizeof(u32))) { - pr_warn_ratelimited( + pr_debug_ratelimited( "%s cannot read MSR entry (%u, 0x%08llx)\n", __func__, i, gpa + i * sizeof(e)); return -EINVAL; } if (nested_vmx_store_msr_check(vcpu, &e)) { - pr_warn_ratelimited( + pr_debug_ratelimited( "%s check failed (%u, 0x%x, 0x%x)\n", __func__, i, e.index, e.reserved); return -EINVAL; @@ -9720,7 +9781,7 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) msr_info.host_initiated = false; msr_info.index = e.index; if (kvm_get_msr(vcpu, &msr_info)) { - pr_warn_ratelimited( + pr_debug_ratelimited( "%s cannot read MSR (%u, 0x%x)\n", __func__, i, e.index); return -EINVAL; @@ -9729,7 +9790,7 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) gpa + i * sizeof(e) + offsetof(struct vmx_msr_entry, value), &msr_info.data, sizeof(msr_info.data))) { - pr_warn_ratelimited( + pr_debug_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", __func__, i, e.index, msr_info.data); return -EINVAL; @@ -10500,6 +10561,9 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3); } + if (nested_cpu_has_ept(vmcs12)) + vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS); + if (nested_cpu_has_vid(vmcs12)) vmcs12->guest_intr_status = vmcs_read16(GUEST_INTR_STATUS); @@ -10793,7 +10857,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, * We are now running in L2, mmu_notifier will force to reload the * page's hpa for L2 vmcs. Need to reload it for L1 before entering L1. */ - kvm_vcpu_reload_apic_access_page(vcpu); + kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); /* * Exiting from L2 to L1, we're now back to L1 which thinks it just @@ -11177,7 +11241,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) ~FEATURE_CONTROL_LMCE; } -static struct kvm_x86_ops vmx_x86_ops = { +static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, .hardware_setup = hardware_setup, @@ -11274,7 +11338,6 @@ static struct kvm_x86_ops vmx_x86_ops = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - .read_tsc_offset = vmx_read_tsc_offset, .write_tsc_offset = vmx_write_tsc_offset, .adjust_tsc_offset_guest = vmx_adjust_tsc_offset_guest, .read_l1_tsc = vmx_read_l1_tsc, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 19f9f9e05c2a..6c633de84dd7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1367,7 +1367,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) { - u64 curr_offset = kvm_x86_ops->read_tsc_offset(vcpu); + u64 curr_offset = vcpu->arch.tsc_offset; vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; } @@ -1413,6 +1413,12 @@ u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) } EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); +static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +{ + kvm_x86_ops->write_tsc_offset(vcpu, offset); + vcpu->arch.tsc_offset = offset; +} + void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct kvm *kvm = vcpu->kvm; @@ -1425,7 +1431,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); offset = kvm_compute_tsc_offset(vcpu, data); - ns = get_kernel_ns(); + ns = ktime_get_boot_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; if (vcpu->arch.virtual_tsc_khz) { @@ -1522,7 +1528,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) if (guest_cpuid_has_tsc_adjust(vcpu) && !msr->host_initiated) update_ia32_tsc_adjust_msr(vcpu, offset); - kvm_x86_ops->write_tsc_offset(vcpu, offset); + kvm_vcpu_write_tsc_offset(vcpu, offset); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); spin_lock(&kvm->arch.pvclock_gtod_sync_lock); @@ -1716,6 +1722,88 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) #endif } +static u64 __get_kvmclock_ns(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0); + struct kvm_arch *ka = &kvm->arch; + s64 ns; + + if (vcpu->arch.hv_clock.flags & PVCLOCK_TSC_STABLE_BIT) { + u64 tsc = kvm_read_l1_tsc(vcpu, rdtsc()); + ns = __pvclock_read_cycles(&vcpu->arch.hv_clock, tsc); + } else { + ns = ktime_get_boot_ns() + ka->kvmclock_offset; + } + + return ns; +} + +u64 get_kvmclock_ns(struct kvm *kvm) +{ + unsigned long flags; + s64 ns; + + local_irq_save(flags); + ns = __get_kvmclock_ns(kvm); + local_irq_restore(flags); + + return ns; +} + +static void kvm_setup_pvclock_page(struct kvm_vcpu *v) +{ + struct kvm_vcpu_arch *vcpu = &v->arch; + struct pvclock_vcpu_time_info guest_hv_clock; + + if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time, + &guest_hv_clock, sizeof(guest_hv_clock)))) + return; + + /* This VCPU is paused, but it's legal for a guest to read another + * VCPU's kvmclock, so we really have to follow the specification where + * it says that version is odd if data is being modified, and even after + * it is consistent. + * + * Version field updates must be kept separate. This is because + * kvm_write_guest_cached might use a "rep movs" instruction, and + * writes within a string instruction are weakly ordered. So there + * are three writes overall. + * + * As a small optimization, only write the version field in the first + * and third write. The vcpu->pv_time cache is still valid, because the + * version field is the first in the struct. + */ + BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0); + + vcpu->hv_clock.version = guest_hv_clock.version + 1; + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); + + smp_wmb(); + + /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ + vcpu->hv_clock.flags |= (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED); + + if (vcpu->pvclock_set_guest_stopped_request) { + vcpu->hv_clock.flags |= PVCLOCK_GUEST_STOPPED; + vcpu->pvclock_set_guest_stopped_request = false; + } + + trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); + + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock)); + + smp_wmb(); + + vcpu->hv_clock.version++; + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); +} + static int kvm_guest_time_update(struct kvm_vcpu *v) { unsigned long flags, tgt_tsc_khz; @@ -1723,7 +1811,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) struct kvm_arch *ka = &v->kvm->arch; s64 kernel_ns; u64 tsc_timestamp, host_tsc; - struct pvclock_vcpu_time_info guest_hv_clock; u8 pvclock_flags; bool use_master_clock; @@ -1752,7 +1839,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) } if (!use_master_clock) { host_tsc = rdtsc(); - kernel_ns = get_kernel_ns(); + kernel_ns = ktime_get_boot_ns(); } tsc_timestamp = kvm_read_l1_tsc(v, host_tsc); @@ -1777,8 +1864,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) local_irq_restore(flags); - if (!vcpu->pv_time_enabled) - return 0; + /* With all the info we got, fill in the values */ if (kvm_has_tsc_control) tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz); @@ -1790,64 +1876,21 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hw_tsc_khz = tgt_tsc_khz; } - /* With all the info we got, fill in the values */ vcpu->hv_clock.tsc_timestamp = tsc_timestamp; vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; vcpu->last_guest_tsc = tsc_timestamp; - if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time, - &guest_hv_clock, sizeof(guest_hv_clock)))) - return 0; - - /* This VCPU is paused, but it's legal for a guest to read another - * VCPU's kvmclock, so we really have to follow the specification where - * it says that version is odd if data is being modified, and even after - * it is consistent. - * - * Version field updates must be kept separate. This is because - * kvm_write_guest_cached might use a "rep movs" instruction, and - * writes within a string instruction are weakly ordered. So there - * are three writes overall. - * - * As a small optimization, only write the version field in the first - * and third write. The vcpu->pv_time cache is still valid, because the - * version field is the first in the struct. - */ - BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0); - - vcpu->hv_clock.version = guest_hv_clock.version + 1; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); - - smp_wmb(); - - /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ - pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED); - - if (vcpu->pvclock_set_guest_stopped_request) { - pvclock_flags |= PVCLOCK_GUEST_STOPPED; - vcpu->pvclock_set_guest_stopped_request = false; - } - /* If the host uses TSC clocksource, then it is stable */ + pvclock_flags = 0; if (use_master_clock) pvclock_flags |= PVCLOCK_TSC_STABLE_BIT; vcpu->hv_clock.flags = pvclock_flags; - trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); - - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock)); - - smp_wmb(); - - vcpu->hv_clock.version++; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); + if (vcpu->pv_time_enabled) + kvm_setup_pvclock_page(v); + if (v == kvm_get_vcpu(v->kvm, 0)) + kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } @@ -2743,16 +2786,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (tsc_delta < 0) mark_tsc_unstable("KVM discovered backwards TSC"); - if (kvm_lapic_hv_timer_in_use(vcpu) && - kvm_x86_ops->set_hv_timer(vcpu, - kvm_get_lapic_tscdeadline_msr(vcpu))) - kvm_lapic_switch_to_sw_timer(vcpu); if (check_tsc_unstable()) { u64 offset = kvm_compute_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); - kvm_x86_ops->write_tsc_offset(vcpu, offset); + kvm_vcpu_write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; } + if (kvm_lapic_hv_timer_in_use(vcpu) && + kvm_x86_ops->set_hv_timer(vcpu, + kvm_get_lapic_tscdeadline_msr(vcpu))) + kvm_lapic_switch_to_sw_timer(vcpu); /* * On a host with synchronized TSC, there is no need to update * kvmclock on vcpu->cpu migration @@ -4039,7 +4082,6 @@ long kvm_arch_vm_ioctl(struct file *filp, case KVM_SET_CLOCK: { struct kvm_clock_data user_ns; u64 now_ns; - s64 delta; r = -EFAULT; if (copy_from_user(&user_ns, argp, sizeof(user_ns))) @@ -4051,10 +4093,9 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; local_irq_disable(); - now_ns = get_kernel_ns(); - delta = user_ns.clock - now_ns; + now_ns = __get_kvmclock_ns(kvm); + kvm->arch.kvmclock_offset += user_ns.clock - now_ns; local_irq_enable(); - kvm->arch.kvmclock_offset = delta; kvm_gen_update_masterclock(kvm); break; } @@ -4062,10 +4103,8 @@ long kvm_arch_vm_ioctl(struct file *filp, struct kvm_clock_data user_ns; u64 now_ns; - local_irq_disable(); - now_ns = get_kernel_ns(); - user_ns.clock = kvm->arch.kvmclock_offset + now_ns; - local_irq_enable(); + now_ns = get_kvmclock_ns(kvm); + user_ns.clock = now_ns; user_ns.flags = 0; memset(&user_ns.pad, 0, sizeof(user_ns.pad)); @@ -6700,7 +6739,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_put_guest_xcr0(vcpu); - /* Interrupt is enabled by handle_external_intr() */ kvm_x86_ops->handle_external_intr(vcpu); ++vcpu->stat.exits; @@ -7530,7 +7568,7 @@ int kvm_arch_hardware_enable(void) * before any KVM threads can be running. Unfortunately, we can't * bring the TSCs fully up to date with real time, as we aren't yet far * enough into CPU bringup that we know how much real time has actually - * elapsed; our helper function, get_kernel_ns() will be using boot + * elapsed; our helper function, ktime_get_boot_ns() will be using boot * variables that haven't been updated yet. * * So we simply find the maximum observed TSC above, then record the @@ -7765,6 +7803,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) mutex_init(&kvm->arch.apic_map_lock); spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); + kvm->arch.kvmclock_offset = -ktime_get_boot_ns(); pvclock_update_vm_gtod_copy(kvm); INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index a82ca466b62e..e8ff3e4ce38a 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -148,11 +148,6 @@ static inline void kvm_register_writel(struct kvm_vcpu *vcpu, return kvm_register_write(vcpu, reg, val); } -static inline u64 get_kernel_ns(void) -{ - return ktime_get_boot_ns(); -} - static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) { return !(kvm->arch.disabled_quirks & quirk); @@ -164,6 +159,7 @@ void kvm_set_pending_timer(struct kvm_vcpu *vcpu); int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr); +u64 get_kvmclock_ns(struct kvm *kvm); int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 2ec0b0abbfaa..49e6ebac7e73 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -181,11 +181,11 @@ ENDPROC(memcpy_orig) #ifndef CONFIG_UML /* - * memcpy_mcsafe - memory copy with machine check exception handling + * memcpy_mcsafe_unrolled - memory copy with machine check exception handling * Note that we only catch machine checks when reading the source addresses. * Writes to target are posted and don't generate machine checks. */ -ENTRY(memcpy_mcsafe) +ENTRY(memcpy_mcsafe_unrolled) cmpl $8, %edx /* Less than 8 bytes? Go to byte copy loop */ jb .L_no_whole_words @@ -273,7 +273,7 @@ ENTRY(memcpy_mcsafe) .L_done_memcpy_trap: xorq %rax, %rax ret -ENDPROC(memcpy_mcsafe) +ENDPROC(memcpy_mcsafe_unrolled) .section .fixup, "ax" /* Return -EFAULT for any failure */ diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index ba47524f56e8..d1c7de095808 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -52,21 +52,6 @@ static __init int find_northbridge(void) return -ENOENT; } -static __init void early_get_boot_cpu_id(void) -{ - /* - * need to get the APIC ID of the BSP so can use that to - * create apicid_to_node in amd_scan_nodes() - */ -#ifdef CONFIG_X86_MPPARSE - /* - * get boot-time SMP configuration: - */ - if (smp_found_config) - early_get_smp_config(); -#endif -} - int __init amd_numa_init(void) { u64 start = PFN_PHYS(0); @@ -180,8 +165,11 @@ int __init amd_numa_init(void) cores = 1 << bits; apicid_base = 0; - /* get the APIC ID of the BSP early for systems with apicid lifting */ - early_get_boot_cpu_id(); + /* + * get boot-time SMP configuration: + */ + early_get_smp_config(); + if (boot_cpu_physical_apicid > 0) { pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid); apicid_base = boot_cpu_physical_apicid; diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 832b98f822be..79ae939970d3 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -1,4 +1,4 @@ -#include <linux/module.h> +#include <linux/extable.h> #include <asm/uaccess.h> #include <asm/traps.h> #include <asm/kdebug.h> diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index dc8023060456..1e525122cbe4 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -5,7 +5,7 @@ */ #include <linux/sched.h> /* test_thread_flag(), ... */ #include <linux/kdebug.h> /* oops_begin/end, ... */ -#include <linux/module.h> /* search_exception_table */ +#include <linux/extable.h> /* search_exception_table */ #include <linux/bootmem.h> /* max_low_pfn */ #include <linux/kprobes.h> /* NOKPROBE_SYMBOL, ... */ #include <linux/mmiotrace.h> /* kmmio_handler, ... */ @@ -753,6 +753,38 @@ no_context(struct pt_regs *regs, unsigned long error_code, return; } +#ifdef CONFIG_VMAP_STACK + /* + * Stack overflow? During boot, we can fault near the initial + * stack in the direct map, but that's not an overflow -- check + * that we're in vmalloc space to avoid this. + */ + if (is_vmalloc_addr((void *)address) && + (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) || + address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) { + register void *__sp asm("rsp"); + unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *); + /* + * We're likely to be running with very little stack space + * left. It's plausible that we'd hit this condition but + * double-fault even before we get this far, in which case + * we're fine: the double-fault handler will deal with it. + * + * We don't want to make it all the way into the oops code + * and then double-fault, though, because we're likely to + * break the console driver and lose most of the stack dump. + */ + asm volatile ("movq %[stack], %%rsp\n\t" + "call handle_stack_overflow\n\t" + "1: jmp 1b" + : "+r" (__sp) + : "D" ("kernel stack overflow (page fault)"), + "S" (regs), "d" (address), + [stack] "rm" (stack)); + unreachable(); + } +#endif + /* * 32-bit: * diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index d28a2d741f9e..22af912d66d2 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -699,8 +699,10 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end) } } -void free_initmem(void) +void __ref free_initmem(void) { + e820_reallocate_tables(); + free_init_pages("unused kernel", (unsigned long)(&__init_begin), (unsigned long)(&__init_end)); diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index bda8d5eef04d..ddd2661c4502 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -40,17 +40,26 @@ * You need to add an if/def entry if you introduce a new memory region * compatible with KASLR. Your entry must be in logical order with memory * layout. For example, ESPFIX is before EFI because its virtual address is - * before. You also need to add a BUILD_BUG_ON in kernel_randomize_memory to + * before. You also need to add a BUILD_BUG_ON() in kernel_randomize_memory() to * ensure that this order is correct and won't be changed. */ static const unsigned long vaddr_start = __PAGE_OFFSET_BASE; -static const unsigned long vaddr_end = VMEMMAP_START; + +#if defined(CONFIG_X86_ESPFIX64) +static const unsigned long vaddr_end = ESPFIX_BASE_ADDR; +#elif defined(CONFIG_EFI) +static const unsigned long vaddr_end = EFI_VA_START; +#else +static const unsigned long vaddr_end = __START_KERNEL_map; +#endif /* Default values */ unsigned long page_offset_base = __PAGE_OFFSET_BASE; EXPORT_SYMBOL(page_offset_base); unsigned long vmalloc_base = __VMALLOC_BASE; EXPORT_SYMBOL(vmalloc_base); +unsigned long vmemmap_base = __VMEMMAP_BASE; +EXPORT_SYMBOL(vmemmap_base); /* * Memory regions randomized by KASLR (except modules that use a separate logic @@ -63,6 +72,7 @@ static __initdata struct kaslr_memory_region { } kaslr_regions[] = { { &page_offset_base, 64/* Maximum */ }, { &vmalloc_base, VMALLOC_SIZE_TB }, + { &vmemmap_base, 1 }, }; /* Get size in bytes used by the memory region */ @@ -89,6 +99,18 @@ void __init kernel_randomize_memory(void) struct rnd_state rand_state; unsigned long remain_entropy; + /* + * All these BUILD_BUG_ON checks ensures the memory layout is + * consistent with the vaddr_start/vaddr_end variables. + */ + BUILD_BUG_ON(vaddr_start >= vaddr_end); + BUILD_BUG_ON(config_enabled(CONFIG_X86_ESPFIX64) && + vaddr_end >= EFI_VA_START); + BUILD_BUG_ON((config_enabled(CONFIG_X86_ESPFIX64) || + config_enabled(CONFIG_EFI)) && + vaddr_end >= __START_KERNEL_map); + BUILD_BUG_ON(vaddr_end > __START_KERNEL_map); + if (!kaslr_memory_enabled()) return; diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index fb682108f4dc..3f35b48d1d9d 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -722,22 +722,19 @@ void __init x86_numa_init(void) numa_init(dummy_numa_init); } -static __init int find_near_online_node(int node) +static void __init init_memory_less_node(int nid) { - int n, val; - int min_val = INT_MAX; - int best_node = -1; + unsigned long zones_size[MAX_NR_ZONES] = {0}; + unsigned long zholes_size[MAX_NR_ZONES] = {0}; - for_each_online_node(n) { - val = node_distance(node, n); + /* Allocate and initialize node data. Memory-less node is now online.*/ + alloc_node_data(nid); + free_area_init_node(nid, zones_size, 0, zholes_size); - if (val < min_val) { - min_val = val; - best_node = n; - } - } - - return best_node; + /* + * All zonelists will be built later in start_kernel() after per cpu + * areas are initialized. + */ } /* @@ -766,8 +763,10 @@ void __init init_cpu_to_node(void) if (node == NUMA_NO_NODE) continue; + if (!node_online(node)) - node = find_near_online_node(node); + init_memory_less_node(node); + numa_set_node(cpu, node); } } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 849dc09fa4f0..e3353c97d086 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -917,11 +917,11 @@ static void populate_pte(struct cpa_data *cpa, } } -static int populate_pmd(struct cpa_data *cpa, - unsigned long start, unsigned long end, - unsigned num_pages, pud_t *pud, pgprot_t pgprot) +static long populate_pmd(struct cpa_data *cpa, + unsigned long start, unsigned long end, + unsigned num_pages, pud_t *pud, pgprot_t pgprot) { - unsigned int cur_pages = 0; + long cur_pages = 0; pmd_t *pmd; pgprot_t pmd_pgprot; @@ -991,12 +991,12 @@ static int populate_pmd(struct cpa_data *cpa, return num_pages; } -static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, - pgprot_t pgprot) +static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, + pgprot_t pgprot) { pud_t *pud; unsigned long end; - int cur_pages = 0; + long cur_pages = 0; pgprot_t pud_pgprot; end = start + (cpa->numpages << PAGE_SHIFT); @@ -1052,7 +1052,7 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, /* Map trailing leftover */ if (start < end) { - int tmp; + long tmp; pud = pud_offset(pgd, start); if (pud_none(*pud)) @@ -1078,7 +1078,7 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) pgprot_t pgprot = __pgprot(_KERNPG_TABLE); pud_t *pud = NULL; /* shut up gcc */ pgd_t *pgd_entry; - int ret; + long ret; pgd_entry = cpa->pgd + pgd_index(addr); @@ -1327,7 +1327,8 @@ static int cpa_process_alias(struct cpa_data *cpa) static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) { - int ret, numpages = cpa->numpages; + unsigned long numpages = cpa->numpages; + int ret; while (numpages) { /* diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index ecb1b69c1651..170cc4ff057b 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -927,9 +927,10 @@ int track_pfn_copy(struct vm_area_struct *vma) } /* - * prot is passed in as a parameter for the new mapping. If the vma has a - * linear pfn mapping for the entire range reserve the entire vma range with - * single reserve_pfn_range call. + * prot is passed in as a parameter for the new mapping. If the vma has + * a linear pfn mapping for the entire range, or no vma is provided, + * reserve the entire pfn + size range with single reserve_pfn_range + * call. */ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long addr, unsigned long size) @@ -938,11 +939,12 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, enum page_cache_mode pcm; /* reserve the whole chunk starting from paddr */ - if (addr == vma->vm_start && size == (vma->vm_end - vma->vm_start)) { + if (!vma || (addr == vma->vm_start + && size == (vma->vm_end - vma->vm_start))) { int ret; ret = reserve_pfn_range(paddr, size, prot, 0); - if (!ret) + if (ret == 0 && vma) vma->vm_flags |= VM_PAT; return ret; } @@ -997,7 +999,7 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, resource_size_t paddr; unsigned long prot; - if (!(vma->vm_flags & VM_PAT)) + if (vma && !(vma->vm_flags & VM_PAT)) return; /* free the chunk starting from pfn or the whole chunk */ @@ -1011,7 +1013,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, size = vma->vm_end - vma->vm_start; } free_pfn_range(paddr, size); - vma->vm_flags &= ~VM_PAT; + if (vma) + vma->vm_flags &= ~VM_PAT; } /* diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index de391b7bc19a..159b52ccd600 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -254,9 +254,7 @@ struct memtype *rbt_memtype_erase(u64 start, u64 end) struct memtype *rbt_memtype_lookup(u64 addr) { - struct memtype *data; - data = memtype_rb_lowest_match(&memtype_rbroot, addr, addr + PAGE_SIZE); - return data; + return memtype_rb_lowest_match(&memtype_rbroot, addr, addr + PAGE_SIZE); } #if defined(CONFIG_DEBUG_FS) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 4dbe65622810..a7655f6caf7d 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -77,10 +77,25 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, unsigned cpu = smp_processor_id(); if (likely(prev != next)) { + if (IS_ENABLED(CONFIG_VMAP_STACK)) { + /* + * If our current stack is in vmalloc space and isn't + * mapped in the new pgd, we'll double-fault. Forcibly + * map it. + */ + unsigned int stack_pgd_index = pgd_index(current_stack_pointer()); + + pgd_t *pgd = next->pgd + stack_pgd_index; + + if (unlikely(pgd_none(*pgd))) + set_pgd(pgd, init_mm.pgd[stack_pgd_index]); + } + #ifdef CONFIG_SMP this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); this_cpu_write(cpu_tlbstate.active_mm, next); #endif + cpumask_set_cpu(cpu, mm_cpumask(next)); /* diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index cb31a4440e58..a2488b6e27d6 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -16,27 +16,7 @@ #include <asm/ptrace.h> #include <asm/stacktrace.h> - -static int backtrace_stack(void *data, char *name) -{ - /* Yes, we want all stacks */ - return 0; -} - -static int backtrace_address(void *data, unsigned long addr, int reliable) -{ - unsigned int *depth = data; - - if ((*depth)--) - oprofile_add_trace(addr); - return 0; -} - -static struct stacktrace_ops backtrace_ops = { - .stack = backtrace_stack, - .address = backtrace_address, - .walk_stack = print_context_stack, -}; +#include <asm/unwind.h> #ifdef CONFIG_COMPAT static struct stack_frame_ia32 * @@ -113,10 +93,29 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth) struct stack_frame *head = (struct stack_frame *)frame_pointer(regs); if (!user_mode(regs)) { - unsigned long stack = kernel_stack_pointer(regs); - if (depth) - dump_trace(NULL, regs, (unsigned long *)stack, 0, - &backtrace_ops, &depth); + struct unwind_state state; + unsigned long addr; + + if (!depth) + return; + + oprofile_add_trace(regs->ip); + + if (!--depth) + return; + + for (unwind_start(&state, current, regs, NULL); + !unwind_done(&state); unwind_next_frame(&state)) { + addr = unwind_get_return_address(&state); + if (!addr) + break; + + oprofile_add_trace(addr); + + if (!--depth) + break; + } + return; } diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index 97062a635b77..5c6fc3577a49 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -23,8 +23,6 @@ obj-y += bus_numa.o obj-$(CONFIG_AMD_NB) += amd_bus.o obj-$(CONFIG_PCI_CNB20LE_QUIRK) += broadcom_bus.o -obj-$(CONFIG_VMD) += vmd.o - ifeq ($(CONFIG_PCI_DEBUG),y) EXTRA_CFLAGS += -DDEBUG endif diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 7b6a9d14c8c0..a4fdfa7dcc1b 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -677,6 +677,12 @@ static void set_dma_domain_ops(struct pci_dev *pdev) static void set_dma_domain_ops(struct pci_dev *pdev) {} #endif +static void set_dev_domain_options(struct pci_dev *pdev) +{ + if (is_vmd(pdev->bus)) + pdev->hotplug_user_indicators = 1; +} + int pcibios_add_device(struct pci_dev *dev) { struct setup_data *data; @@ -707,6 +713,7 @@ int pcibios_add_device(struct pci_dev *dev) iounmap(data); } set_dma_domain_ops(dev); + set_dev_domain_options(dev); return 0; } diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 837ea36a837d..6d52b94f4bb9 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -553,15 +553,21 @@ static void twinhead_reserve_killing_zone(struct pci_dev *dev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone); /* - * Broadwell EP Home Agent BARs erroneously return non-zero values when read. + * Device [8086:2fc0] + * Erratum HSE43 + * CONFIG_TDP_NOMINAL CSR Implemented at Incorrect Offset + * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v3-spec-update.html * - * See http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html - * entry BDF2. + * Devices [8086:6f60,6fa0,6fc0] + * Erratum BDF2 + * PCI BARs in the Home Agent Will Return Non-Zero Values During Enumeration + * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html */ -static void pci_bdwep_bar(struct pci_dev *dev) +static void pci_invalid_bar(struct pci_dev *dev) { dev->non_compliant_bars = 1; } -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_bdwep_bar); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, pci_invalid_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_invalid_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_invalid_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_invalid_bar); diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 9770e55e768f..1d97cea3b3a4 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -120,9 +120,12 @@ static unsigned long __init bios32_service(unsigned long service) static struct { unsigned long address; unsigned short segment; -} pci_indirect = { 0, __KERNEL_CS }; +} pci_indirect __ro_after_init = { + .address = 0, + .segment = __KERNEL_CS, +}; -static int pci_bios_present; +static int pci_bios_present __ro_after_init; static int __init check_pcibios(void) { diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c deleted file mode 100644 index 7948be342ee9..000000000000 --- a/arch/x86/pci/vmd.c +++ /dev/null @@ -1,771 +0,0 @@ -/* - * Volume Management Device driver - * Copyright (c) 2015, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - */ - -#include <linux/device.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/msi.h> -#include <linux/pci.h> -#include <linux/rculist.h> -#include <linux/rcupdate.h> - -#include <asm/irqdomain.h> -#include <asm/device.h> -#include <asm/msi.h> -#include <asm/msidef.h> - -#define VMD_CFGBAR 0 -#define VMD_MEMBAR1 2 -#define VMD_MEMBAR2 4 - -/* - * Lock for manipulating VMD IRQ lists. - */ -static DEFINE_RAW_SPINLOCK(list_lock); - -/** - * struct vmd_irq - private data to map driver IRQ to the VMD shared vector - * @node: list item for parent traversal. - * @rcu: RCU callback item for freeing. - * @irq: back pointer to parent. - * @enabled: true if driver enabled IRQ - * @virq: the virtual IRQ value provided to the requesting driver. - * - * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to - * a VMD IRQ using this structure. - */ -struct vmd_irq { - struct list_head node; - struct rcu_head rcu; - struct vmd_irq_list *irq; - bool enabled; - unsigned int virq; -}; - -/** - * struct vmd_irq_list - list of driver requested IRQs mapping to a VMD vector - * @irq_list: the list of irq's the VMD one demuxes to. - * @vmd_vector: the h/w IRQ assigned to the VMD. - * @index: index into the VMD MSI-X table; used for message routing. - * @count: number of child IRQs assigned to this vector; used to track - * sharing. - */ -struct vmd_irq_list { - struct list_head irq_list; - struct vmd_dev *vmd; - unsigned int vmd_vector; - unsigned int index; - unsigned int count; -}; - -struct vmd_dev { - struct pci_dev *dev; - - spinlock_t cfg_lock; - char __iomem *cfgbar; - - int msix_count; - struct msix_entry *msix_entries; - struct vmd_irq_list *irqs; - - struct pci_sysdata sysdata; - struct resource resources[3]; - struct irq_domain *irq_domain; - struct pci_bus *bus; - -#ifdef CONFIG_X86_DEV_DMA_OPS - struct dma_map_ops dma_ops; - struct dma_domain dma_domain; -#endif -}; - -static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus) -{ - return container_of(bus->sysdata, struct vmd_dev, sysdata); -} - -/* - * Drivers managing a device in a VMD domain allocate their own IRQs as before, - * but the MSI entry for the hardware it's driving will be programmed with a - * destination ID for the VMD MSI-X table. The VMD muxes interrupts in its - * domain into one of its own, and the VMD driver de-muxes these for the - * handlers sharing that VMD IRQ. The vmd irq_domain provides the operations - * and irq_chip to set this up. - */ -static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) -{ - struct vmd_irq *vmdirq = data->chip_data; - struct vmd_irq_list *irq = vmdirq->irq; - - msg->address_hi = MSI_ADDR_BASE_HI; - msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_DEST_ID(irq->index); - msg->data = 0; -} - -/* - * We rely on MSI_FLAG_USE_DEF_CHIP_OPS to set the IRQ mask/unmask ops. - */ -static void vmd_irq_enable(struct irq_data *data) -{ - struct vmd_irq *vmdirq = data->chip_data; - unsigned long flags; - - raw_spin_lock_irqsave(&list_lock, flags); - WARN_ON(vmdirq->enabled); - list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list); - vmdirq->enabled = true; - raw_spin_unlock_irqrestore(&list_lock, flags); - - data->chip->irq_unmask(data); -} - -static void vmd_irq_disable(struct irq_data *data) -{ - struct vmd_irq *vmdirq = data->chip_data; - unsigned long flags; - - data->chip->irq_mask(data); - - raw_spin_lock_irqsave(&list_lock, flags); - if (vmdirq->enabled) { - list_del_rcu(&vmdirq->node); - vmdirq->enabled = false; - } - raw_spin_unlock_irqrestore(&list_lock, flags); -} - -/* - * XXX: Stubbed until we develop acceptable way to not create conflicts with - * other devices sharing the same vector. - */ -static int vmd_irq_set_affinity(struct irq_data *data, - const struct cpumask *dest, bool force) -{ - return -EINVAL; -} - -static struct irq_chip vmd_msi_controller = { - .name = "VMD-MSI", - .irq_enable = vmd_irq_enable, - .irq_disable = vmd_irq_disable, - .irq_compose_msi_msg = vmd_compose_msi_msg, - .irq_set_affinity = vmd_irq_set_affinity, -}; - -static irq_hw_number_t vmd_get_hwirq(struct msi_domain_info *info, - msi_alloc_info_t *arg) -{ - return 0; -} - -/* - * XXX: We can be even smarter selecting the best IRQ once we solve the - * affinity problem. - */ -static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *desc) -{ - int i, best = 1; - unsigned long flags; - - if (!desc->msi_attrib.is_msix || vmd->msix_count == 1) - return &vmd->irqs[0]; - - raw_spin_lock_irqsave(&list_lock, flags); - for (i = 1; i < vmd->msix_count; i++) - if (vmd->irqs[i].count < vmd->irqs[best].count) - best = i; - vmd->irqs[best].count++; - raw_spin_unlock_irqrestore(&list_lock, flags); - - return &vmd->irqs[best]; -} - -static int vmd_msi_init(struct irq_domain *domain, struct msi_domain_info *info, - unsigned int virq, irq_hw_number_t hwirq, - msi_alloc_info_t *arg) -{ - struct msi_desc *desc = arg->desc; - struct vmd_dev *vmd = vmd_from_bus(msi_desc_to_pci_dev(desc)->bus); - struct vmd_irq *vmdirq = kzalloc(sizeof(*vmdirq), GFP_KERNEL); - - if (!vmdirq) - return -ENOMEM; - - INIT_LIST_HEAD(&vmdirq->node); - vmdirq->irq = vmd_next_irq(vmd, desc); - vmdirq->virq = virq; - - irq_domain_set_info(domain, virq, vmdirq->irq->vmd_vector, info->chip, - vmdirq, handle_untracked_irq, vmd, NULL); - return 0; -} - -static void vmd_msi_free(struct irq_domain *domain, - struct msi_domain_info *info, unsigned int virq) -{ - struct vmd_irq *vmdirq = irq_get_chip_data(virq); - unsigned long flags; - - /* XXX: Potential optimization to rebalance */ - raw_spin_lock_irqsave(&list_lock, flags); - vmdirq->irq->count--; - raw_spin_unlock_irqrestore(&list_lock, flags); - - kfree_rcu(vmdirq, rcu); -} - -static int vmd_msi_prepare(struct irq_domain *domain, struct device *dev, - int nvec, msi_alloc_info_t *arg) -{ - struct pci_dev *pdev = to_pci_dev(dev); - struct vmd_dev *vmd = vmd_from_bus(pdev->bus); - - if (nvec > vmd->msix_count) - return vmd->msix_count; - - memset(arg, 0, sizeof(*arg)); - return 0; -} - -static void vmd_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) -{ - arg->desc = desc; -} - -static struct msi_domain_ops vmd_msi_domain_ops = { - .get_hwirq = vmd_get_hwirq, - .msi_init = vmd_msi_init, - .msi_free = vmd_msi_free, - .msi_prepare = vmd_msi_prepare, - .set_desc = vmd_set_desc, -}; - -static struct msi_domain_info vmd_msi_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_PCI_MSIX, - .ops = &vmd_msi_domain_ops, - .chip = &vmd_msi_controller, -}; - -#ifdef CONFIG_X86_DEV_DMA_OPS -/* - * VMD replaces the requester ID with its own. DMA mappings for devices in a - * VMD domain need to be mapped for the VMD, not the device requiring - * the mapping. - */ -static struct device *to_vmd_dev(struct device *dev) -{ - struct pci_dev *pdev = to_pci_dev(dev); - struct vmd_dev *vmd = vmd_from_bus(pdev->bus); - - return &vmd->dev->dev; -} - -static struct dma_map_ops *vmd_dma_ops(struct device *dev) -{ - return get_dma_ops(to_vmd_dev(dev)); -} - -static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr, - gfp_t flag, unsigned long attrs) -{ - return vmd_dma_ops(dev)->alloc(to_vmd_dev(dev), size, addr, flag, - attrs); -} - -static void vmd_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t addr, unsigned long attrs) -{ - return vmd_dma_ops(dev)->free(to_vmd_dev(dev), size, vaddr, addr, - attrs); -} - -static int vmd_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t addr, size_t size, - unsigned long attrs) -{ - return vmd_dma_ops(dev)->mmap(to_vmd_dev(dev), vma, cpu_addr, addr, - size, attrs); -} - -static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt, - void *cpu_addr, dma_addr_t addr, size_t size, - unsigned long attrs) -{ - return vmd_dma_ops(dev)->get_sgtable(to_vmd_dev(dev), sgt, cpu_addr, - addr, size, attrs); -} - -static dma_addr_t vmd_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - return vmd_dma_ops(dev)->map_page(to_vmd_dev(dev), page, offset, size, - dir, attrs); -} - -static void vmd_unmap_page(struct device *dev, dma_addr_t addr, size_t size, - enum dma_data_direction dir, unsigned long attrs) -{ - vmd_dma_ops(dev)->unmap_page(to_vmd_dev(dev), addr, size, dir, attrs); -} - -static int vmd_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, unsigned long attrs) -{ - return vmd_dma_ops(dev)->map_sg(to_vmd_dev(dev), sg, nents, dir, attrs); -} - -static void vmd_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, unsigned long attrs) -{ - vmd_dma_ops(dev)->unmap_sg(to_vmd_dev(dev), sg, nents, dir, attrs); -} - -static void vmd_sync_single_for_cpu(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir) -{ - vmd_dma_ops(dev)->sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir); -} - -static void vmd_sync_single_for_device(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir) -{ - vmd_dma_ops(dev)->sync_single_for_device(to_vmd_dev(dev), addr, size, - dir); -} - -static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir) -{ - vmd_dma_ops(dev)->sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir); -} - -static void vmd_sync_sg_for_device(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir) -{ - vmd_dma_ops(dev)->sync_sg_for_device(to_vmd_dev(dev), sg, nents, dir); -} - -static int vmd_mapping_error(struct device *dev, dma_addr_t addr) -{ - return vmd_dma_ops(dev)->mapping_error(to_vmd_dev(dev), addr); -} - -static int vmd_dma_supported(struct device *dev, u64 mask) -{ - return vmd_dma_ops(dev)->dma_supported(to_vmd_dev(dev), mask); -} - -#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK -static u64 vmd_get_required_mask(struct device *dev) -{ - return vmd_dma_ops(dev)->get_required_mask(to_vmd_dev(dev)); -} -#endif - -static void vmd_teardown_dma_ops(struct vmd_dev *vmd) -{ - struct dma_domain *domain = &vmd->dma_domain; - - if (get_dma_ops(&vmd->dev->dev)) - del_dma_domain(domain); -} - -#define ASSIGN_VMD_DMA_OPS(source, dest, fn) \ - do { \ - if (source->fn) \ - dest->fn = vmd_##fn; \ - } while (0) - -static void vmd_setup_dma_ops(struct vmd_dev *vmd) -{ - const struct dma_map_ops *source = get_dma_ops(&vmd->dev->dev); - struct dma_map_ops *dest = &vmd->dma_ops; - struct dma_domain *domain = &vmd->dma_domain; - - domain->domain_nr = vmd->sysdata.domain; - domain->dma_ops = dest; - - if (!source) - return; - ASSIGN_VMD_DMA_OPS(source, dest, alloc); - ASSIGN_VMD_DMA_OPS(source, dest, free); - ASSIGN_VMD_DMA_OPS(source, dest, mmap); - ASSIGN_VMD_DMA_OPS(source, dest, get_sgtable); - ASSIGN_VMD_DMA_OPS(source, dest, map_page); - ASSIGN_VMD_DMA_OPS(source, dest, unmap_page); - ASSIGN_VMD_DMA_OPS(source, dest, map_sg); - ASSIGN_VMD_DMA_OPS(source, dest, unmap_sg); - ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_cpu); - ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_device); - ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_cpu); - ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_device); - ASSIGN_VMD_DMA_OPS(source, dest, mapping_error); - ASSIGN_VMD_DMA_OPS(source, dest, dma_supported); -#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK - ASSIGN_VMD_DMA_OPS(source, dest, get_required_mask); -#endif - add_dma_domain(domain); -} -#undef ASSIGN_VMD_DMA_OPS -#else -static void vmd_teardown_dma_ops(struct vmd_dev *vmd) {} -static void vmd_setup_dma_ops(struct vmd_dev *vmd) {} -#endif - -static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus, - unsigned int devfn, int reg, int len) -{ - char __iomem *addr = vmd->cfgbar + - (bus->number << 20) + (devfn << 12) + reg; - - if ((addr - vmd->cfgbar) + len >= - resource_size(&vmd->dev->resource[VMD_CFGBAR])) - return NULL; - - return addr; -} - -/* - * CPU may deadlock if config space is not serialized on some versions of this - * hardware, so all config space access is done under a spinlock. - */ -static int vmd_pci_read(struct pci_bus *bus, unsigned int devfn, int reg, - int len, u32 *value) -{ - struct vmd_dev *vmd = vmd_from_bus(bus); - char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); - unsigned long flags; - int ret = 0; - - if (!addr) - return -EFAULT; - - spin_lock_irqsave(&vmd->cfg_lock, flags); - switch (len) { - case 1: - *value = readb(addr); - break; - case 2: - *value = readw(addr); - break; - case 4: - *value = readl(addr); - break; - default: - ret = -EINVAL; - break; - } - spin_unlock_irqrestore(&vmd->cfg_lock, flags); - return ret; -} - -/* - * VMD h/w converts non-posted config writes to posted memory writes. The - * read-back in this function forces the completion so it returns only after - * the config space was written, as expected. - */ -static int vmd_pci_write(struct pci_bus *bus, unsigned int devfn, int reg, - int len, u32 value) -{ - struct vmd_dev *vmd = vmd_from_bus(bus); - char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); - unsigned long flags; - int ret = 0; - - if (!addr) - return -EFAULT; - - spin_lock_irqsave(&vmd->cfg_lock, flags); - switch (len) { - case 1: - writeb(value, addr); - readb(addr); - break; - case 2: - writew(value, addr); - readw(addr); - break; - case 4: - writel(value, addr); - readl(addr); - break; - default: - ret = -EINVAL; - break; - } - spin_unlock_irqrestore(&vmd->cfg_lock, flags); - return ret; -} - -static struct pci_ops vmd_ops = { - .read = vmd_pci_read, - .write = vmd_pci_write, -}; - -static void vmd_attach_resources(struct vmd_dev *vmd) -{ - vmd->dev->resource[VMD_MEMBAR1].child = &vmd->resources[1]; - vmd->dev->resource[VMD_MEMBAR2].child = &vmd->resources[2]; -} - -static void vmd_detach_resources(struct vmd_dev *vmd) -{ - vmd->dev->resource[VMD_MEMBAR1].child = NULL; - vmd->dev->resource[VMD_MEMBAR2].child = NULL; -} - -/* - * VMD domains start at 0x1000 to not clash with ACPI _SEG domains. - */ -static int vmd_find_free_domain(void) -{ - int domain = 0xffff; - struct pci_bus *bus = NULL; - - while ((bus = pci_find_next_bus(bus)) != NULL) - domain = max_t(int, domain, pci_domain_nr(bus)); - return domain + 1; -} - -static int vmd_enable_domain(struct vmd_dev *vmd) -{ - struct pci_sysdata *sd = &vmd->sysdata; - struct resource *res; - u32 upper_bits; - unsigned long flags; - LIST_HEAD(resources); - - res = &vmd->dev->resource[VMD_CFGBAR]; - vmd->resources[0] = (struct resource) { - .name = "VMD CFGBAR", - .start = 0, - .end = (resource_size(res) >> 20) - 1, - .flags = IORESOURCE_BUS | IORESOURCE_PCI_FIXED, - }; - - /* - * If the window is below 4GB, clear IORESOURCE_MEM_64 so we can - * put 32-bit resources in the window. - * - * There's no hardware reason why a 64-bit window *couldn't* - * contain a 32-bit resource, but pbus_size_mem() computes the - * bridge window size assuming a 64-bit window will contain no - * 32-bit resources. __pci_assign_resource() enforces that - * artificial restriction to make sure everything will fit. - * - * The only way we could use a 64-bit non-prefechable MEMBAR is - * if its address is <4GB so that we can convert it to a 32-bit - * resource. To be visible to the host OS, all VMD endpoints must - * be initially configured by platform BIOS, which includes setting - * up these resources. We can assume the device is configured - * according to the platform needs. - */ - res = &vmd->dev->resource[VMD_MEMBAR1]; - upper_bits = upper_32_bits(res->end); - flags = res->flags & ~IORESOURCE_SIZEALIGN; - if (!upper_bits) - flags &= ~IORESOURCE_MEM_64; - vmd->resources[1] = (struct resource) { - .name = "VMD MEMBAR1", - .start = res->start, - .end = res->end, - .flags = flags, - .parent = res, - }; - - res = &vmd->dev->resource[VMD_MEMBAR2]; - upper_bits = upper_32_bits(res->end); - flags = res->flags & ~IORESOURCE_SIZEALIGN; - if (!upper_bits) - flags &= ~IORESOURCE_MEM_64; - vmd->resources[2] = (struct resource) { - .name = "VMD MEMBAR2", - .start = res->start + 0x2000, - .end = res->end, - .flags = flags, - .parent = res, - }; - - sd->domain = vmd_find_free_domain(); - if (sd->domain < 0) - return sd->domain; - - sd->node = pcibus_to_node(vmd->dev->bus); - - vmd->irq_domain = pci_msi_create_irq_domain(NULL, &vmd_msi_domain_info, - x86_vector_domain); - if (!vmd->irq_domain) - return -ENODEV; - - pci_add_resource(&resources, &vmd->resources[0]); - pci_add_resource(&resources, &vmd->resources[1]); - pci_add_resource(&resources, &vmd->resources[2]); - vmd->bus = pci_create_root_bus(&vmd->dev->dev, 0, &vmd_ops, sd, - &resources); - if (!vmd->bus) { - pci_free_resource_list(&resources); - irq_domain_remove(vmd->irq_domain); - return -ENODEV; - } - - vmd_attach_resources(vmd); - vmd_setup_dma_ops(vmd); - dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain); - pci_rescan_bus(vmd->bus); - - WARN(sysfs_create_link(&vmd->dev->dev.kobj, &vmd->bus->dev.kobj, - "domain"), "Can't create symlink to domain\n"); - return 0; -} - -static irqreturn_t vmd_irq(int irq, void *data) -{ - struct vmd_irq_list *irqs = data; - struct vmd_irq *vmdirq; - - rcu_read_lock(); - list_for_each_entry_rcu(vmdirq, &irqs->irq_list, node) - generic_handle_irq(vmdirq->virq); - rcu_read_unlock(); - - return IRQ_HANDLED; -} - -static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id) -{ - struct vmd_dev *vmd; - int i, err; - - if (resource_size(&dev->resource[VMD_CFGBAR]) < (1 << 20)) - return -ENOMEM; - - vmd = devm_kzalloc(&dev->dev, sizeof(*vmd), GFP_KERNEL); - if (!vmd) - return -ENOMEM; - - vmd->dev = dev; - err = pcim_enable_device(dev); - if (err < 0) - return err; - - vmd->cfgbar = pcim_iomap(dev, VMD_CFGBAR, 0); - if (!vmd->cfgbar) - return -ENOMEM; - - pci_set_master(dev); - if (dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(64)) && - dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32))) - return -ENODEV; - - vmd->msix_count = pci_msix_vec_count(dev); - if (vmd->msix_count < 0) - return -ENODEV; - - vmd->irqs = devm_kcalloc(&dev->dev, vmd->msix_count, sizeof(*vmd->irqs), - GFP_KERNEL); - if (!vmd->irqs) - return -ENOMEM; - - vmd->msix_entries = devm_kcalloc(&dev->dev, vmd->msix_count, - sizeof(*vmd->msix_entries), - GFP_KERNEL); - if (!vmd->msix_entries) - return -ENOMEM; - for (i = 0; i < vmd->msix_count; i++) - vmd->msix_entries[i].entry = i; - - vmd->msix_count = pci_enable_msix_range(vmd->dev, vmd->msix_entries, 1, - vmd->msix_count); - if (vmd->msix_count < 0) - return vmd->msix_count; - - for (i = 0; i < vmd->msix_count; i++) { - INIT_LIST_HEAD(&vmd->irqs[i].irq_list); - vmd->irqs[i].vmd_vector = vmd->msix_entries[i].vector; - vmd->irqs[i].index = i; - - err = devm_request_irq(&dev->dev, vmd->irqs[i].vmd_vector, - vmd_irq, 0, "vmd", &vmd->irqs[i]); - if (err) - return err; - } - - spin_lock_init(&vmd->cfg_lock); - pci_set_drvdata(dev, vmd); - err = vmd_enable_domain(vmd); - if (err) - return err; - - dev_info(&vmd->dev->dev, "Bound to PCI domain %04x\n", - vmd->sysdata.domain); - return 0; -} - -static void vmd_remove(struct pci_dev *dev) -{ - struct vmd_dev *vmd = pci_get_drvdata(dev); - - vmd_detach_resources(vmd); - pci_set_drvdata(dev, NULL); - sysfs_remove_link(&vmd->dev->dev.kobj, "domain"); - pci_stop_root_bus(vmd->bus); - pci_remove_root_bus(vmd->bus); - vmd_teardown_dma_ops(vmd); - irq_domain_remove(vmd->irq_domain); -} - -#ifdef CONFIG_PM -static int vmd_suspend(struct device *dev) -{ - struct pci_dev *pdev = to_pci_dev(dev); - - pci_save_state(pdev); - return 0; -} - -static int vmd_resume(struct device *dev) -{ - struct pci_dev *pdev = to_pci_dev(dev); - - pci_restore_state(pdev); - return 0; -} -#endif -static SIMPLE_DEV_PM_OPS(vmd_dev_pm_ops, vmd_suspend, vmd_resume); - -static const struct pci_device_id vmd_ids[] = { - {PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x201d),}, - {0,} -}; -MODULE_DEVICE_TABLE(pci, vmd_ids); - -static struct pci_driver vmd_drv = { - .name = "vmd", - .id_table = vmd_ids, - .probe = vmd_probe, - .remove = vmd_remove, - .driver = { - .pm = &vmd_dev_pm_ops, - }, -}; -module_pci_driver(vmd_drv); - -MODULE_AUTHOR("Intel Corporation"); -MODULE_LICENSE("GPL v2"); -MODULE_VERSION("0.6"); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 3a483cb5ac81..bedfab98077a 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -456,7 +456,7 @@ void __init xen_msi_init(void) int __init pci_xen_hvm_init(void) { - if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs)) + if (!xen_feature(XENFEAT_hvm_pirqs)) return 0; #ifdef CONFIG_ACPI diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile index 184842ef332e..3c3c19ea94df 100644 --- a/arch/x86/platform/Makefile +++ b/arch/x86/platform/Makefile @@ -8,6 +8,7 @@ obj-y += iris/ obj-y += intel/ obj-y += intel-mid/ obj-y += intel-quark/ +obj-y += mellanox/ obj-y += olpc/ obj-y += scx200/ obj-y += sfi/ diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c index 8ff7b9355416..d49d3be81953 100644 --- a/arch/x86/platform/atom/punit_atom_debug.c +++ b/arch/x86/platform/atom/punit_atom_debug.c @@ -155,7 +155,7 @@ static void punit_dbgfs_unregister(void) static const struct x86_cpu_id intel_punit_cpu_ids[] = { ICPU(INTEL_FAM6_ATOM_SILVERMONT1, punit_device_byt), - ICPU(INTEL_FAM6_ATOM_MERRIFIELD1, punit_device_tng), + ICPU(INTEL_FAM6_ATOM_MERRIFIELD, punit_device_tng), ICPU(INTEL_FAM6_ATOM_AIRMONT, punit_device_cht), {} }; diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index 6a2f5691b1ab..6aad870e8962 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -82,21 +82,12 @@ void __init efi_bgrt_init(void) } bgrt_image_size = bmp_header.size; - bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL | __GFP_NOWARN); + bgrt_image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB); if (!bgrt_image) { - pr_notice("Ignoring BGRT: failed to allocate memory for image (wanted %zu bytes)\n", - bgrt_image_size); - return; - } - - image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB); - if (!image) { pr_notice("Ignoring BGRT: failed to map image memory\n"); - kfree(bgrt_image); bgrt_image = NULL; return; } - memcpy(bgrt_image, image, bgrt_image_size); - memunmap(image); + efi_mem_reserve(bgrt_tab->image_address, bgrt_image_size); } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 1fbb408e2e72..bf99aa7005eb 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -166,13 +166,15 @@ static void __init do_add_efi_memmap(void) } e820_add_region(start, size, e820_type); } - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); } int __init efi_memblock_x86_reserve_range(void) { struct efi_info *e = &boot_params.efi_info; + struct efi_memory_map_data data; phys_addr_t pmap; + int rv; if (efi_enabled(EFI_PARAVIRT)) return 0; @@ -187,11 +189,17 @@ int __init efi_memblock_x86_reserve_range(void) #else pmap = (e->efi_memmap | ((__u64)e->efi_memmap_hi << 32)); #endif - efi.memmap.phys_map = pmap; - efi.memmap.nr_map = e->efi_memmap_size / - e->efi_memdesc_size; - efi.memmap.desc_size = e->efi_memdesc_size; - efi.memmap.desc_version = e->efi_memdesc_version; + data.phys_map = pmap; + data.size = e->efi_memmap_size; + data.desc_size = e->efi_memdesc_size; + data.desc_version = e->efi_memdesc_version; + + rv = efi_memmap_init_early(&data); + if (rv) + return rv; + + if (add_efi_memmap) + do_add_efi_memmap(); WARN(efi.memmap.desc_version != 1, "Unexpected EFI_MEMORY_DESCRIPTOR version %ld", @@ -218,19 +226,6 @@ void __init efi_print_memmap(void) } } -void __init efi_unmap_memmap(void) -{ - unsigned long size; - - clear_bit(EFI_MEMMAP, &efi.flags); - - size = efi.memmap.nr_map * efi.memmap.desc_size; - if (efi.memmap.map) { - early_memunmap(efi.memmap.map, size); - efi.memmap.map = NULL; - } -} - static int __init efi_systab_init(void *phys) { if (efi_enabled(EFI_64BIT)) { @@ -414,33 +409,6 @@ static int __init efi_runtime_init(void) return 0; } -static int __init efi_memmap_init(void) -{ - unsigned long addr, size; - - if (efi_enabled(EFI_PARAVIRT)) - return 0; - - /* Map the EFI memory map */ - size = efi.memmap.nr_map * efi.memmap.desc_size; - addr = (unsigned long)efi.memmap.phys_map; - - efi.memmap.map = early_memremap(addr, size); - if (efi.memmap.map == NULL) { - pr_err("Could not map the memory map!\n"); - return -ENOMEM; - } - - efi.memmap.map_end = efi.memmap.map + size; - - if (add_efi_memmap) - do_add_efi_memmap(); - - set_bit(EFI_MEMMAP, &efi.flags); - - return 0; -} - void __init efi_init(void) { efi_char16_t *c16; @@ -498,16 +466,14 @@ void __init efi_init(void) if (!efi_runtime_supported()) pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n"); else { - if (efi_runtime_disabled() || efi_runtime_init()) + if (efi_runtime_disabled() || efi_runtime_init()) { + efi_memmap_unmap(); return; + } } - if (efi_memmap_init()) - return; if (efi_enabled(EFI_DBG)) efi_print_memmap(); - - efi_esrt_init(); } void __init efi_late_init(void) @@ -624,42 +590,6 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md) } } -static void __init save_runtime_map(void) -{ -#ifdef CONFIG_KEXEC_CORE - unsigned long desc_size; - efi_memory_desc_t *md; - void *tmp, *q = NULL; - int count = 0; - - if (efi_enabled(EFI_OLD_MEMMAP)) - return; - - desc_size = efi.memmap.desc_size; - - for_each_efi_memory_desc(md) { - if (!(md->attribute & EFI_MEMORY_RUNTIME) || - (md->type == EFI_BOOT_SERVICES_CODE) || - (md->type == EFI_BOOT_SERVICES_DATA)) - continue; - tmp = krealloc(q, (count + 1) * desc_size, GFP_KERNEL); - if (!tmp) - goto out; - q = tmp; - - memcpy(q + count * desc_size, md, desc_size); - count++; - } - - efi_runtime_map_setup(q, count, desc_size); - return; - -out: - kfree(q); - pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n"); -#endif -} - static void *realloc_pages(void *old_memmap, int old_shift) { void *ret; @@ -745,6 +675,46 @@ static void *efi_map_next_entry(void *entry) return entry; } +static bool should_map_region(efi_memory_desc_t *md) +{ + /* + * Runtime regions always require runtime mappings (obviously). + */ + if (md->attribute & EFI_MEMORY_RUNTIME) + return true; + + /* + * 32-bit EFI doesn't suffer from the bug that requires us to + * reserve boot services regions, and mixed mode support + * doesn't exist for 32-bit kernels. + */ + if (IS_ENABLED(CONFIG_X86_32)) + return false; + + /* + * Map all of RAM so that we can access arguments in the 1:1 + * mapping when making EFI runtime calls. + */ + if (IS_ENABLED(CONFIG_EFI_MIXED) && !efi_is_native()) { + if (md->type == EFI_CONVENTIONAL_MEMORY || + md->type == EFI_LOADER_DATA || + md->type == EFI_LOADER_CODE) + return true; + } + + /* + * Map boot services regions as a workaround for buggy + * firmware that accesses them even when they shouldn't. + * + * See efi_{reserve,free}_boot_services(). + */ + if (md->type == EFI_BOOT_SERVICES_CODE || + md->type == EFI_BOOT_SERVICES_DATA) + return true; + + return false; +} + /* * Map the efi memory ranges of the runtime services and update new_mmap with * virtual addresses. @@ -761,13 +731,9 @@ static void * __init efi_map_regions(int *count, int *pg_shift) p = NULL; while ((p = efi_map_next_entry(p))) { md = p; - if (!(md->attribute & EFI_MEMORY_RUNTIME)) { -#ifdef CONFIG_X86_64 - if (md->type != EFI_BOOT_SERVICES_CODE && - md->type != EFI_BOOT_SERVICES_DATA) -#endif - continue; - } + + if (!should_map_region(md)) + continue; efi_map_region(md); get_systab_virt_addr(md); @@ -803,7 +769,7 @@ static void __init kexec_enter_virtual_mode(void) * non-native EFI */ if (!efi_is_native()) { - efi_unmap_memmap(); + efi_memmap_unmap(); clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); return; } @@ -823,7 +789,18 @@ static void __init kexec_enter_virtual_mode(void) get_systab_virt_addr(md); } - save_runtime_map(); + /* + * Unregister the early EFI memmap from efi_init() and install + * the new EFI memory map. + */ + efi_memmap_unmap(); + + if (efi_memmap_init_late(efi.memmap.phys_map, + efi.memmap.desc_size * efi.memmap.nr_map)) { + pr_err("Failed to remap late EFI memory map\n"); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return; + } BUG_ON(!efi.systab); @@ -884,6 +861,7 @@ static void __init __efi_enter_virtual_mode(void) int count = 0, pg_shift = 0; void *new_memmap = NULL; efi_status_t status; + phys_addr_t pa; efi.systab = NULL; @@ -901,11 +879,24 @@ static void __init __efi_enter_virtual_mode(void) return; } - save_runtime_map(); + pa = __pa(new_memmap); + + /* + * Unregister the early EFI memmap from efi_init() and install + * the new EFI memory map that we are about to pass to the + * firmware via SetVirtualAddressMap(). + */ + efi_memmap_unmap(); + + if (efi_memmap_init_late(pa, efi.memmap.desc_size * count)) { + pr_err("Failed to remap late EFI memory map\n"); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return; + } BUG_ON(!efi.systab); - if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift)) { + if (efi_setup_page_tables(pa, 1 << pg_shift)) { clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); return; } @@ -917,14 +908,14 @@ static void __init __efi_enter_virtual_mode(void) efi.memmap.desc_size * count, efi.memmap.desc_size, efi.memmap.desc_version, - (efi_memory_desc_t *)__pa(new_memmap)); + (efi_memory_desc_t *)pa); } else { status = efi_thunk_set_virtual_address_map( efi_phys.set_virtual_address_map, efi.memmap.desc_size * count, efi.memmap.desc_size, efi.memmap.desc_version, - (efi_memory_desc_t *)__pa(new_memmap)); + (efi_memory_desc_t *)pa); } if (status != EFI_SUCCESS) { @@ -956,15 +947,6 @@ static void __init __efi_enter_virtual_mode(void) efi_runtime_update_mappings(); efi_dump_pagetable(); - /* - * We mapped the descriptor array into the EFI pagetable above - * but we're not unmapping it here because if we're running in - * EFI mixed mode we need all of memory to be accessible when - * we pass parameters to the EFI runtime services in the - * thunking code. - */ - free_pages((unsigned long)new_memmap, pg_shift); - /* clean DUMMY object */ efi_delete_dummy_variable(); } diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 677e29e29473..58b0f801f66f 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -85,7 +85,7 @@ pgd_t * __init efi_call_phys_prolog(void) early_code_mapping_set_exec(1); n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE); - save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL); + save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL); for (pgd = 0; pgd < n_pgds; pgd++) { save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE); @@ -214,7 +214,6 @@ void efi_sync_low_kernel_mappings(void) int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) { unsigned long pfn, text; - efi_memory_desc_t *md; struct page *page; unsigned npages; pgd_t *pgd; @@ -245,28 +244,9 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) * text and allocate a new stack because we can't rely on the * stack pointer being < 4GB. */ - if (!IS_ENABLED(CONFIG_EFI_MIXED)) + if (!IS_ENABLED(CONFIG_EFI_MIXED) || efi_is_native()) return 0; - /* - * Map all of RAM so that we can access arguments in the 1:1 - * mapping when making EFI runtime calls. - */ - for_each_efi_memory_desc(md) { - if (md->type != EFI_CONVENTIONAL_MEMORY && - md->type != EFI_LOADER_DATA && - md->type != EFI_LOADER_CODE) - continue; - - pfn = md->phys_addr >> PAGE_SHIFT; - npages = md->num_pages; - - if (kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, npages, _PAGE_RW)) { - pr_err("Failed to map 1:1 memory\n"); - return 1; - } - } - page = alloc_page(GFP_KERNEL|__GFP_DMA32); if (!page) panic("Unable to allocate EFI runtime stack < 4GB\n"); @@ -359,6 +339,7 @@ void __init efi_map_region(efi_memory_desc_t *md) */ void __init efi_map_region_fixed(efi_memory_desc_t *md) { + __map_region(md, md->phys_addr); __map_region(md, md->virt_addr); } diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 89d1146f5a6f..10aca63a50d7 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -164,6 +164,75 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size, EXPORT_SYMBOL_GPL(efi_query_variable_store); /* + * The UEFI specification makes it clear that the operating system is + * free to do whatever it wants with boot services code after + * ExitBootServices() has been called. Ignoring this recommendation a + * significant bunch of EFI implementations continue calling into boot + * services code (SetVirtualAddressMap). In order to work around such + * buggy implementations we reserve boot services region during EFI + * init and make sure it stays executable. Then, after + * SetVirtualAddressMap(), it is discarded. + * + * However, some boot services regions contain data that is required + * by drivers, so we need to track which memory ranges can never be + * freed. This is done by tagging those regions with the + * EFI_MEMORY_RUNTIME attribute. + * + * Any driver that wants to mark a region as reserved must use + * efi_mem_reserve() which will insert a new EFI memory descriptor + * into efi.memmap (splitting existing regions if necessary) and tag + * it with EFI_MEMORY_RUNTIME. + */ +void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) +{ + phys_addr_t new_phys, new_size; + struct efi_mem_range mr; + efi_memory_desc_t md; + int num_entries; + void *new; + + if (efi_mem_desc_lookup(addr, &md)) { + pr_err("Failed to lookup EFI memory descriptor for %pa\n", &addr); + return; + } + + if (addr + size > md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT)) { + pr_err("Region spans EFI memory descriptors, %pa\n", &addr); + return; + } + + size += addr % EFI_PAGE_SIZE; + size = round_up(size, EFI_PAGE_SIZE); + addr = round_down(addr, EFI_PAGE_SIZE); + + mr.range.start = addr; + mr.range.end = addr + size - 1; + mr.attribute = md.attribute | EFI_MEMORY_RUNTIME; + + num_entries = efi_memmap_split_count(&md, &mr.range); + num_entries += efi.memmap.nr_map; + + new_size = efi.memmap.desc_size * num_entries; + + new_phys = memblock_alloc(new_size, 0); + if (!new_phys) { + pr_err("Could not allocate boot services memmap\n"); + return; + } + + new = early_memremap(new_phys, new_size); + if (!new) { + pr_err("Failed to map new boot services memmap\n"); + return; + } + + efi_memmap_insert(&efi.memmap, new, &mr); + early_memunmap(new, new_size); + + efi_memmap_install(new_phys, num_entries); +} + +/* * Helper function for efi_reserve_boot_services() to figure out if we * can free regions in efi_free_boot_services(). * @@ -184,15 +253,6 @@ static bool can_free_region(u64 start, u64 size) return true; } -/* - * The UEFI specification makes it clear that the operating system is free to do - * whatever it wants with boot services code after ExitBootServices() has been - * called. Ignoring this recommendation a significant bunch of EFI implementations - * continue calling into boot services code (SetVirtualAddressMap). In order to - * work around such buggy implementations we reserve boot services region during - * EFI init and make sure it stays executable. Then, after SetVirtualAddressMap(), it -* is discarded. -*/ void __init efi_reserve_boot_services(void) { efi_memory_desc_t *md; @@ -249,7 +309,10 @@ void __init efi_reserve_boot_services(void) void __init efi_free_boot_services(void) { + phys_addr_t new_phys, new_size; efi_memory_desc_t *md; + int num_entries = 0; + void *new, *new_md; for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; @@ -257,12 +320,16 @@ void __init efi_free_boot_services(void) size_t rm_size; if (md->type != EFI_BOOT_SERVICES_CODE && - md->type != EFI_BOOT_SERVICES_DATA) + md->type != EFI_BOOT_SERVICES_DATA) { + num_entries++; continue; + } /* Do not free, someone else owns it: */ - if (md->attribute & EFI_MEMORY_RUNTIME) + if (md->attribute & EFI_MEMORY_RUNTIME) { + num_entries++; continue; + } /* * Nasty quirk: if all sub-1MB memory is used for boot @@ -287,7 +354,41 @@ void __init efi_free_boot_services(void) free_bootmem_late(start, size); } - efi_unmap_memmap(); + new_size = efi.memmap.desc_size * num_entries; + new_phys = memblock_alloc(new_size, 0); + if (!new_phys) { + pr_err("Failed to allocate new EFI memmap\n"); + return; + } + + new = memremap(new_phys, new_size, MEMREMAP_WB); + if (!new) { + pr_err("Failed to map new EFI memmap\n"); + return; + } + + /* + * Build a new EFI memmap that excludes any boot services + * regions that are not tagged EFI_MEMORY_RUNTIME, since those + * regions have now been freed. + */ + new_md = new; + for_each_efi_memory_desc(md) { + if (!(md->attribute & EFI_MEMORY_RUNTIME) && + (md->type == EFI_BOOT_SERVICES_CODE || + md->type == EFI_BOOT_SERVICES_DATA)) + continue; + + memcpy(new_md, md, efi.memmap.desc_size); + new_md += efi.memmap.desc_size; + } + + memunmap(new); + + if (efi_memmap_install(new_phys, num_entries)) { + pr_err("Could not install new EFI memmap\n"); + return; + } } /* @@ -365,7 +466,7 @@ void __init efi_apply_memmap_quirks(void) */ if (!efi_runtime_supported()) { pr_info("Setup done, disabling due to 32/64-bit mismatch\n"); - efi_unmap_memmap(); + efi_memmap_unmap(); } /* UV2+ BIOS has a fix for this issue. UV1 still needs the quirk. */ diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile index fc135bf70511..429d08be7848 100644 --- a/arch/x86/platform/intel-mid/device_libs/Makefile +++ b/arch/x86/platform/intel-mid/device_libs/Makefile @@ -1,5 +1,9 @@ # Family-Level Interface Shim (FLIS) obj-$(subst m,y,$(CONFIG_PINCTRL_MERRIFIELD)) += platform_mrfld_pinctrl.o +# SDHCI Devices +obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI)) += platform_mrfld_sd.o +# WiFi +obj-$(subst m,y,$(CONFIG_BRCMFMAC_SDIO)) += platform_bcm43xx.o # IPC Devices obj-y += platform_ipc.o obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic.o diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c new file mode 100644 index 000000000000..4392c15ed9e0 --- /dev/null +++ b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c @@ -0,0 +1,95 @@ +/* + * platform_bcm43xx.c: bcm43xx platform data initilization file + * + * (C) Copyright 2016 Intel Corporation + * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include <linux/gpio.h> +#include <linux/platform_device.h> +#include <linux/regulator/machine.h> +#include <linux/regulator/fixed.h> +#include <linux/sfi.h> + +#include <asm/intel-mid.h> + +#define WLAN_SFI_GPIO_IRQ_NAME "WLAN-interrupt" +#define WLAN_SFI_GPIO_ENABLE_NAME "WLAN-enable" + +#define WLAN_DEV_NAME "0000:00:01.3" + +static struct regulator_consumer_supply bcm43xx_vmmc_supply = { + .dev_name = WLAN_DEV_NAME, + .supply = "vmmc", +}; + +static struct regulator_init_data bcm43xx_vmmc_data = { + .constraints = { + .valid_ops_mask = REGULATOR_CHANGE_STATUS, + }, + .num_consumer_supplies = 1, + .consumer_supplies = &bcm43xx_vmmc_supply, +}; + +static struct fixed_voltage_config bcm43xx_vmmc = { + .supply_name = "bcm43xx-vmmc-regulator", + /* + * Announce 2.0V here to be compatible with SDIO specification. The + * real voltage and signaling are still 1.8V. + */ + .microvolts = 2000000, /* 1.8V */ + .gpio = -EINVAL, + .startup_delay = 250 * 1000, /* 250ms */ + .enable_high = 1, /* active high */ + .enabled_at_boot = 0, /* disabled at boot */ + .init_data = &bcm43xx_vmmc_data, +}; + +static struct platform_device bcm43xx_vmmc_regulator = { + .name = "reg-fixed-voltage", + .id = PLATFORM_DEVID_AUTO, + .dev = { + .platform_data = &bcm43xx_vmmc, + }, +}; + +static int __init bcm43xx_regulator_register(void) +{ + int ret; + + bcm43xx_vmmc.gpio = get_gpio_by_name(WLAN_SFI_GPIO_ENABLE_NAME); + ret = platform_device_register(&bcm43xx_vmmc_regulator); + if (ret) { + pr_err("%s: vmmc regulator register failed\n", __func__); + return ret; + } + + return 0; +} + +static void __init *bcm43xx_platform_data(void *info) +{ + int ret; + + ret = bcm43xx_regulator_register(); + if (ret) + return NULL; + + pr_info("Using generic wifi platform data\n"); + + /* For now it's empty */ + return NULL; +} + +static const struct devs_id bcm43xx_clk_vmmc_dev_id __initconst = { + .name = "bcm43xx_clk_vmmc", + .type = SFI_DEV_TYPE_SD, + .get_platform_data = &bcm43xx_platform_data, +}; + +sfi_device(bcm43xx_clk_vmmc_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c new file mode 100644 index 000000000000..00c4a034ad93 --- /dev/null +++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c @@ -0,0 +1,47 @@ +/* + * SDHCI platform data initilisation file + * + * (C) Copyright 2016 Intel Corporation + * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include <linux/init.h> +#include <linux/pci.h> + +#include <linux/mmc/sdhci-pci-data.h> + +#include <asm/intel-mid.h> + +#define INTEL_MRFLD_SD 2 +#define INTEL_MRFLD_SD_CD_GPIO 77 + +static struct sdhci_pci_data mrfld_sdhci_pci_data = { + .rst_n_gpio = -EINVAL, + .cd_gpio = INTEL_MRFLD_SD_CD_GPIO, +}; + +static struct sdhci_pci_data * +mrfld_sdhci_pci_get_data(struct pci_dev *pdev, int slotno) +{ + unsigned int func = PCI_FUNC(pdev->devfn); + + if (func == INTEL_MRFLD_SD) + return &mrfld_sdhci_pci_data; + + return NULL; +} + +static int __init mrfld_sd_init(void) +{ + if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) + return -ENODEV; + + sdhci_pci_get_data = mrfld_sdhci_pci_get_data; + return 0; +} +arch_initcall(mrfld_sd_init); diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index ce119d2ba0d0..7850128f0026 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -70,6 +70,11 @@ EXPORT_SYMBOL_GPL(__intel_mid_cpu_chip); static void intel_mid_power_off(void) { + /* Shut down South Complex via PWRMU */ + intel_mid_pwr_power_off(); + + /* Only for Tangier, the rest will ignore this command */ + intel_scu_ipc_simple_command(IPCMSG_COLD_OFF, 1); }; static void intel_mid_reboot(void) diff --git a/arch/x86/platform/intel-mid/pwr.c b/arch/x86/platform/intel-mid/pwr.c index c901a3423772..5d3b45ad1c03 100644 --- a/arch/x86/platform/intel-mid/pwr.c +++ b/arch/x86/platform/intel-mid/pwr.c @@ -44,7 +44,19 @@ /* Bits in PM_CMD */ #define PM_CMD_CMD(x) ((x) << 0) #define PM_CMD_IOC (1 << 8) -#define PM_CMD_D3cold (1 << 21) +#define PM_CMD_CM_NOP (0 << 9) +#define PM_CMD_CM_IMMEDIATE (1 << 9) +#define PM_CMD_CM_DELAY (2 << 9) +#define PM_CMD_CM_TRIGGER (3 << 9) + +/* System states */ +#define PM_CMD_SYS_STATE_S5 (5 << 16) + +/* Trigger variants */ +#define PM_CMD_CFG_TRIGGER_NC (3 << 19) + +/* Message to wait for TRIGGER_NC case */ +#define TRIGGER_NC_MSG_2 (2 << 22) /* List of commands */ #define CMD_SET_CFG 0x01 @@ -137,7 +149,7 @@ static int mid_pwr_wait(struct mid_pwr *pwr) static int mid_pwr_wait_for_cmd(struct mid_pwr *pwr, u8 cmd) { - writel(PM_CMD_CMD(cmd), pwr->regs + PM_CMD); + writel(PM_CMD_CMD(cmd) | PM_CMD_CM_IMMEDIATE, pwr->regs + PM_CMD); return mid_pwr_wait(pwr); } @@ -260,6 +272,20 @@ int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state) } EXPORT_SYMBOL_GPL(intel_mid_pci_set_power_state); +void intel_mid_pwr_power_off(void) +{ + struct mid_pwr *pwr = midpwr; + u32 cmd = PM_CMD_SYS_STATE_S5 | + PM_CMD_CMD(CMD_SET_CFG) | + PM_CMD_CM_TRIGGER | + PM_CMD_CFG_TRIGGER_NC | + TRIGGER_NC_MSG_2; + + /* Send command to SCU */ + writel(cmd, pwr->regs + PM_CMD); + mid_pwr_wait(pwr); +} + int intel_mid_pwr_get_lss_id(struct pci_dev *pdev) { int vndr; @@ -354,7 +380,7 @@ static int mid_pwr_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; } -static int mid_set_initial_state(struct mid_pwr *pwr) +static int mid_set_initial_state(struct mid_pwr *pwr, const u32 *states) { unsigned int i, j; int ret; @@ -379,10 +405,10 @@ static int mid_set_initial_state(struct mid_pwr *pwr) * NOTE: The actual device mapping is provided by a platform at run * time using vendor capability of PCI configuration space. */ - mid_pwr_set_state(pwr, 0, 0xffffffff); - mid_pwr_set_state(pwr, 1, 0xffffffff); - mid_pwr_set_state(pwr, 2, 0xffffffff); - mid_pwr_set_state(pwr, 3, 0xffffffff); + mid_pwr_set_state(pwr, 0, states[0]); + mid_pwr_set_state(pwr, 1, states[1]); + mid_pwr_set_state(pwr, 2, states[2]); + mid_pwr_set_state(pwr, 3, states[3]); /* Send command to SCU */ ret = mid_pwr_wait_for_cmd(pwr, CMD_SET_CFG); @@ -397,13 +423,41 @@ static int mid_set_initial_state(struct mid_pwr *pwr) return 0; } -static const struct mid_pwr_device_info mid_info = { - .set_initial_state = mid_set_initial_state, +static int pnw_set_initial_state(struct mid_pwr *pwr) +{ + /* On Penwell SRAM must stay powered on */ + const u32 states[] = { + 0xf00fffff, /* PM_SSC(0) */ + 0xffffffff, /* PM_SSC(1) */ + 0xffffffff, /* PM_SSC(2) */ + 0xffffffff, /* PM_SSC(3) */ + }; + return mid_set_initial_state(pwr, states); +} + +static int tng_set_initial_state(struct mid_pwr *pwr) +{ + const u32 states[] = { + 0xffffffff, /* PM_SSC(0) */ + 0xffffffff, /* PM_SSC(1) */ + 0xffffffff, /* PM_SSC(2) */ + 0xffffffff, /* PM_SSC(3) */ + }; + return mid_set_initial_state(pwr, states); +} + +static const struct mid_pwr_device_info pnw_info = { + .set_initial_state = pnw_set_initial_state, +}; + +static const struct mid_pwr_device_info tng_info = { + .set_initial_state = tng_set_initial_state, }; +/* This table should be in sync with the one in drivers/pci/pci-mid.c */ static const struct pci_device_id mid_pwr_pci_ids[] = { - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_PENWELL), (kernel_ulong_t)&mid_info }, - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_TANGIER), (kernel_ulong_t)&mid_info }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_PENWELL), (kernel_ulong_t)&pnw_info }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_TANGIER), (kernel_ulong_t)&tng_info }, {} }; diff --git a/arch/x86/platform/mellanox/Makefile b/arch/x86/platform/mellanox/Makefile new file mode 100644 index 000000000000..f43c93188a1d --- /dev/null +++ b/arch/x86/platform/mellanox/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_MLX_PLATFORM) += mlx-platform.o diff --git a/arch/x86/platform/mellanox/mlx-platform.c b/arch/x86/platform/mellanox/mlx-platform.c new file mode 100644 index 000000000000..7dcfcca97399 --- /dev/null +++ b/arch/x86/platform/mellanox/mlx-platform.c @@ -0,0 +1,266 @@ +/* + * arch/x86/platform/mellanox/mlx-platform.c + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Vadim Pasternak <vadimp@mellanox.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/device.h> +#include <linux/dmi.h> +#include <linux/i2c.h> +#include <linux/i2c-mux.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/platform_data/i2c-mux-reg.h> + +#define MLX_PLAT_DEVICE_NAME "mlxplat" + +/* LPC bus IO offsets */ +#define MLXPLAT_CPLD_LPC_I2C_BASE_ADRR 0x2000 +#define MLXPLAT_CPLD_LPC_REG_BASE_ADRR 0x2500 +#define MLXPLAT_CPLD_LPC_IO_RANGE 0x100 +#define MLXPLAT_CPLD_LPC_I2C_CH1_OFF 0xdb +#define MLXPLAT_CPLD_LPC_I2C_CH2_OFF 0xda +#define MLXPLAT_CPLD_LPC_PIO_OFFSET 0x10000UL +#define MLXPLAT_CPLD_LPC_REG1 ((MLXPLAT_CPLD_LPC_REG_BASE_ADRR + \ + MLXPLAT_CPLD_LPC_I2C_CH1_OFF) | \ + MLXPLAT_CPLD_LPC_PIO_OFFSET) +#define MLXPLAT_CPLD_LPC_REG2 ((MLXPLAT_CPLD_LPC_REG_BASE_ADRR + \ + MLXPLAT_CPLD_LPC_I2C_CH2_OFF) | \ + MLXPLAT_CPLD_LPC_PIO_OFFSET) + +/* Start channel numbers */ +#define MLXPLAT_CPLD_CH1 2 +#define MLXPLAT_CPLD_CH2 10 + +/* Number of LPC attached MUX platform devices */ +#define MLXPLAT_CPLD_LPC_MUX_DEVS 2 + +/* mlxplat_priv - platform private data + * @pdev_i2c - i2c controller platform device + * @pdev_mux - array of mux platform devices + */ +struct mlxplat_priv { + struct platform_device *pdev_i2c; + struct platform_device *pdev_mux[MLXPLAT_CPLD_LPC_MUX_DEVS]; +}; + +/* Regions for LPC I2C controller and LPC base register space */ +static const struct resource mlxplat_lpc_resources[] = { + [0] = DEFINE_RES_NAMED(MLXPLAT_CPLD_LPC_I2C_BASE_ADRR, + MLXPLAT_CPLD_LPC_IO_RANGE, + "mlxplat_cpld_lpc_i2c_ctrl", IORESOURCE_IO), + [1] = DEFINE_RES_NAMED(MLXPLAT_CPLD_LPC_REG_BASE_ADRR, + MLXPLAT_CPLD_LPC_IO_RANGE, + "mlxplat_cpld_lpc_regs", + IORESOURCE_IO), +}; + +/* Platform default channels */ +static const int mlxplat_default_channels[][8] = { + { + MLXPLAT_CPLD_CH1, MLXPLAT_CPLD_CH1 + 1, MLXPLAT_CPLD_CH1 + 2, + MLXPLAT_CPLD_CH1 + 3, MLXPLAT_CPLD_CH1 + 4, MLXPLAT_CPLD_CH1 + + 5, MLXPLAT_CPLD_CH1 + 6, MLXPLAT_CPLD_CH1 + 7 + }, + { + MLXPLAT_CPLD_CH2, MLXPLAT_CPLD_CH2 + 1, MLXPLAT_CPLD_CH2 + 2, + MLXPLAT_CPLD_CH2 + 3, MLXPLAT_CPLD_CH2 + 4, MLXPLAT_CPLD_CH2 + + 5, MLXPLAT_CPLD_CH2 + 6, MLXPLAT_CPLD_CH2 + 7 + }, +}; + +/* Platform channels for MSN21xx system family */ +static const int mlxplat_msn21xx_channels[] = { 1, 2, 3, 4, 5, 6, 7, 8 }; + +/* Platform mux data */ +static struct i2c_mux_reg_platform_data mlxplat_mux_data[] = { + { + .parent = 1, + .base_nr = MLXPLAT_CPLD_CH1, + .write_only = 1, + .reg = (void __iomem *)MLXPLAT_CPLD_LPC_REG1, + .reg_size = 1, + .idle_in_use = 1, + }, + { + .parent = 1, + .base_nr = MLXPLAT_CPLD_CH2, + .write_only = 1, + .reg = (void __iomem *)MLXPLAT_CPLD_LPC_REG2, + .reg_size = 1, + .idle_in_use = 1, + }, + +}; + +static struct platform_device *mlxplat_dev; + +static int __init mlxplat_dmi_default_matched(const struct dmi_system_id *dmi) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mlxplat_mux_data); i++) { + mlxplat_mux_data[i].values = mlxplat_default_channels[i]; + mlxplat_mux_data[i].n_values = + ARRAY_SIZE(mlxplat_default_channels[i]); + } + + return 1; +}; + +static int __init mlxplat_dmi_msn21xx_matched(const struct dmi_system_id *dmi) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mlxplat_mux_data); i++) { + mlxplat_mux_data[i].values = mlxplat_msn21xx_channels; + mlxplat_mux_data[i].n_values = + ARRAY_SIZE(mlxplat_msn21xx_channels); + } + + return 1; +}; + +static struct dmi_system_id mlxplat_dmi_table[] __initdata = { + { + .callback = mlxplat_dmi_default_matched, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"), + DMI_MATCH(DMI_PRODUCT_NAME, "MSN24"), + }, + }, + { + .callback = mlxplat_dmi_default_matched, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"), + DMI_MATCH(DMI_PRODUCT_NAME, "MSN27"), + }, + }, + { + .callback = mlxplat_dmi_default_matched, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"), + DMI_MATCH(DMI_PRODUCT_NAME, "MSB"), + }, + }, + { + .callback = mlxplat_dmi_default_matched, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"), + DMI_MATCH(DMI_PRODUCT_NAME, "MSX"), + }, + }, + { + .callback = mlxplat_dmi_msn21xx_matched, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"), + DMI_MATCH(DMI_PRODUCT_NAME, "MSN21"), + }, + }, + { } +}; + +static int __init mlxplat_init(void) +{ + struct mlxplat_priv *priv; + int i, err; + + if (!dmi_check_system(mlxplat_dmi_table)) + return -ENODEV; + + mlxplat_dev = platform_device_register_simple(MLX_PLAT_DEVICE_NAME, -1, + mlxplat_lpc_resources, + ARRAY_SIZE(mlxplat_lpc_resources)); + + if (IS_ERR(mlxplat_dev)) + return PTR_ERR(mlxplat_dev); + + priv = devm_kzalloc(&mlxplat_dev->dev, sizeof(struct mlxplat_priv), + GFP_KERNEL); + if (!priv) { + err = -ENOMEM; + goto fail_alloc; + } + platform_set_drvdata(mlxplat_dev, priv); + + priv->pdev_i2c = platform_device_register_simple("i2c_mlxcpld", -1, + NULL, 0); + if (IS_ERR(priv->pdev_i2c)) { + err = PTR_ERR(priv->pdev_i2c); + goto fail_alloc; + }; + + for (i = 0; i < ARRAY_SIZE(mlxplat_mux_data); i++) { + priv->pdev_mux[i] = platform_device_register_resndata( + &mlxplat_dev->dev, + "i2c-mux-reg", i, NULL, + 0, &mlxplat_mux_data[i], + sizeof(mlxplat_mux_data[i])); + if (IS_ERR(priv->pdev_mux[i])) { + err = PTR_ERR(priv->pdev_mux[i]); + goto fail_platform_mux_register; + } + } + + return 0; + +fail_platform_mux_register: + for (i--; i > 0 ; i--) + platform_device_unregister(priv->pdev_mux[i]); + platform_device_unregister(priv->pdev_i2c); +fail_alloc: + platform_device_unregister(mlxplat_dev); + + return err; +} +module_init(mlxplat_init); + +static void __exit mlxplat_exit(void) +{ + struct mlxplat_priv *priv = platform_get_drvdata(mlxplat_dev); + int i; + + for (i = ARRAY_SIZE(mlxplat_mux_data) - 1; i >= 0 ; i--) + platform_device_unregister(priv->pdev_mux[i]); + + platform_device_unregister(priv->pdev_i2c); + platform_device_unregister(mlxplat_dev); +} +module_exit(mlxplat_exit); + +MODULE_AUTHOR("Vadim Pasternak (vadimp@mellanox.com)"); +MODULE_DESCRIPTION("Mellanox platform driver"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_ALIAS("dmi:*:*Mellanox*:MSN24*:"); +MODULE_ALIAS("dmi:*:*Mellanox*:MSN27*:"); +MODULE_ALIAS("dmi:*:*Mellanox*:MSB*:"); +MODULE_ALIAS("dmi:*:*Mellanox*:MSX*:"); +MODULE_ALIAS("dmi:*:*Mellanox*:MSN21*:"); diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index 23f2f3e41c7f..b4d5e95fe4df 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -149,11 +149,8 @@ EXPORT_SYMBOL_GPL(uv_bios_change_memprotect); s64 uv_bios_reserved_page_pa(u64 buf, u64 *cookie, u64 *addr, u64 *len) { - s64 ret; - - ret = uv_bios_call_irqsave(UV_BIOS_GET_PARTITION_ADDR, (u64)cookie, - (u64)addr, buf, (u64)len, 0); - return ret; + return uv_bios_call_irqsave(UV_BIOS_GET_PARTITION_ADDR, (u64)cookie, + (u64)addr, buf, (u64)len, 0); } EXPORT_SYMBOL_GPL(uv_bios_reserved_page_pa); diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index fdb4d42b4ce5..9e42842e924a 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -24,6 +24,29 @@ #include <asm/irq_vectors.h> #include <asm/timer.h> +static struct bau_operations ops; + +static struct bau_operations uv123_bau_ops = { + .bau_gpa_to_offset = uv_gpa_to_offset, + .read_l_sw_ack = read_mmr_sw_ack, + .read_g_sw_ack = read_gmmr_sw_ack, + .write_l_sw_ack = write_mmr_sw_ack, + .write_g_sw_ack = write_gmmr_sw_ack, + .write_payload_first = write_mmr_payload_first, + .write_payload_last = write_mmr_payload_last, +}; + +static struct bau_operations uv4_bau_ops = { + .bau_gpa_to_offset = uv_gpa_to_soc_phys_ram, + .read_l_sw_ack = read_mmr_proc_sw_ack, + .read_g_sw_ack = read_gmmr_proc_sw_ack, + .write_l_sw_ack = write_mmr_proc_sw_ack, + .write_g_sw_ack = write_gmmr_proc_sw_ack, + .write_payload_first = write_mmr_proc_payload_first, + .write_payload_last = write_mmr_proc_payload_last, +}; + + /* timeouts in nanoseconds (indexed by UVH_AGING_PRESCALE_SEL urgency7 30:28) */ static int timeout_base_ns[] = { 20, @@ -55,16 +78,16 @@ static int congested_reps = CONGESTED_REPS; static int disabled_period = DISABLED_PERIOD; static struct tunables tunables[] = { - {&max_concurr, MAX_BAU_CONCURRENT}, /* must be [0] */ - {&plugged_delay, PLUGGED_DELAY}, - {&plugsb4reset, PLUGSB4RESET}, - {&timeoutsb4reset, TIMEOUTSB4RESET}, - {&ipi_reset_limit, IPI_RESET_LIMIT}, - {&complete_threshold, COMPLETE_THRESHOLD}, - {&congested_respns_us, CONGESTED_RESPONSE_US}, - {&congested_reps, CONGESTED_REPS}, - {&disabled_period, DISABLED_PERIOD}, - {&giveup_limit, GIVEUP_LIMIT} + {&max_concurr, MAX_BAU_CONCURRENT}, /* must be [0] */ + {&plugged_delay, PLUGGED_DELAY}, + {&plugsb4reset, PLUGSB4RESET}, + {&timeoutsb4reset, TIMEOUTSB4RESET}, + {&ipi_reset_limit, IPI_RESET_LIMIT}, + {&complete_threshold, COMPLETE_THRESHOLD}, + {&congested_respns_us, CONGESTED_RESPONSE_US}, + {&congested_reps, CONGESTED_REPS}, + {&disabled_period, DISABLED_PERIOD}, + {&giveup_limit, GIVEUP_LIMIT} }; static struct dentry *tunables_dir; @@ -216,7 +239,7 @@ static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp, msg = mdp->msg; if (!msg->canceled && do_acknowledge) { dw = (msg->swack_vec << UV_SW_ACK_NPENDING) | msg->swack_vec; - write_mmr_sw_ack(dw); + ops.write_l_sw_ack(dw); } msg->replied_to = 1; msg->swack_vec = 0; @@ -252,7 +275,7 @@ static void bau_process_retry_msg(struct msg_desc *mdp, msg->swack_vec) == 0) && (msg2->sending_cpu == msg->sending_cpu) && (msg2->msg_type != MSG_NOOP)) { - mmr = read_mmr_sw_ack(); + mmr = ops.read_l_sw_ack(); msg_res = msg2->swack_vec; /* * This is a message retry; clear the resources held @@ -270,7 +293,7 @@ static void bau_process_retry_msg(struct msg_desc *mdp, stat->d_canceled++; cancel_count++; mr = (msg_res << UV_SW_ACK_NPENDING) | msg_res; - write_mmr_sw_ack(mr); + ops.write_l_sw_ack(mr); } } } @@ -403,12 +426,12 @@ static void do_reset(void *ptr) /* * only reset the resource if it is still pending */ - mmr = read_mmr_sw_ack(); + mmr = ops.read_l_sw_ack(); msg_res = msg->swack_vec; mr = (msg_res << UV_SW_ACK_NPENDING) | msg_res; if (mmr & msg_res) { stat->d_rcanceled++; - write_mmr_sw_ack(mr); + ops.write_l_sw_ack(mr); } } } @@ -580,11 +603,7 @@ static int uv1_wait_completion(struct bau_desc *bau_desc, */ static unsigned long uv2_3_read_status(unsigned long offset, int rshft, int desc) { - unsigned long descriptor_status; - - descriptor_status = - ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK) << 1; - return descriptor_status; + return ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK) << 1; } /* @@ -1202,7 +1221,7 @@ void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp) struct bau_pq_entry *msg = mdp->msg; struct bau_pq_entry *other_msg; - mmr_image = read_mmr_sw_ack(); + mmr_image = ops.read_l_sw_ack(); swack_vec = msg->swack_vec; if ((swack_vec & mmr_image) == 0) { @@ -1431,7 +1450,7 @@ static int ptc_seq_show(struct seq_file *file, void *data) /* destination side statistics */ seq_printf(file, "%lx %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld\n", - read_gmmr_sw_ack(uv_cpu_to_pnode(cpu)), + ops.read_g_sw_ack(uv_cpu_to_pnode(cpu)), stat->d_requestee, cycles_2_us(stat->d_time), stat->d_alltlb, stat->d_onetlb, stat->d_multmsg, stat->d_nomsg, stat->d_retries, stat->d_canceled, @@ -1497,16 +1516,16 @@ static ssize_t ptc_proc_write(struct file *file, const char __user *user, } if (kstrtol(optstr, 10, &input_arg) < 0) { - printk(KERN_DEBUG "%s is invalid\n", optstr); + pr_debug("%s is invalid\n", optstr); return -EINVAL; } if (input_arg == 0) { elements = ARRAY_SIZE(stat_description); - printk(KERN_DEBUG "# cpu: cpu number\n"); - printk(KERN_DEBUG "Sender statistics:\n"); + pr_debug("# cpu: cpu number\n"); + pr_debug("Sender statistics:\n"); for (i = 0; i < elements; i++) - printk(KERN_DEBUG "%s\n", stat_description[i]); + pr_debug("%s\n", stat_description[i]); } else if (input_arg == -1) { for_each_present_cpu(cpu) { stat = &per_cpu(ptcstats, cpu); @@ -1554,7 +1573,7 @@ static int parse_tunables_write(struct bau_control *bcp, char *instr, break; } if (cnt != e) { - printk(KERN_INFO "bau tunable error: should be %d values\n", e); + pr_info("bau tunable error: should be %d values\n", e); return -EINVAL; } @@ -1571,7 +1590,7 @@ static int parse_tunables_write(struct bau_control *bcp, char *instr, continue; } if (val < 1 || val > bcp->cpus_in_uvhub) { - printk(KERN_DEBUG + pr_debug( "Error: BAU max concurrent %d is invalid\n", val); return -EINVAL; @@ -1619,17 +1638,17 @@ static ssize_t tunables_write(struct file *file, const char __user *user, for_each_present_cpu(cpu) { bcp = &per_cpu(bau_control, cpu); - bcp->max_concurr = max_concurr; - bcp->max_concurr_const = max_concurr; - bcp->plugged_delay = plugged_delay; - bcp->plugsb4reset = plugsb4reset; - bcp->timeoutsb4reset = timeoutsb4reset; - bcp->ipi_reset_limit = ipi_reset_limit; - bcp->complete_threshold = complete_threshold; - bcp->cong_response_us = congested_respns_us; - bcp->cong_reps = congested_reps; - bcp->disabled_period = sec_2_cycles(disabled_period); - bcp->giveup_limit = giveup_limit; + bcp->max_concurr = max_concurr; + bcp->max_concurr_const = max_concurr; + bcp->plugged_delay = plugged_delay; + bcp->plugsb4reset = plugsb4reset; + bcp->timeoutsb4reset = timeoutsb4reset; + bcp->ipi_reset_limit = ipi_reset_limit; + bcp->complete_threshold = complete_threshold; + bcp->cong_response_us = congested_respns_us; + bcp->cong_reps = congested_reps; + bcp->disabled_period = sec_2_cycles(disabled_period); + bcp->giveup_limit = giveup_limit; } return count; } @@ -1676,21 +1695,21 @@ static int __init uv_ptc_init(void) proc_uv_ptc = proc_create(UV_PTC_BASENAME, 0444, NULL, &proc_uv_ptc_operations); if (!proc_uv_ptc) { - printk(KERN_ERR "unable to create %s proc entry\n", + pr_err("unable to create %s proc entry\n", UV_PTC_BASENAME); return -EINVAL; } tunables_dir = debugfs_create_dir(UV_BAU_TUNABLES_DIR, NULL); if (!tunables_dir) { - printk(KERN_ERR "unable to create debugfs directory %s\n", + pr_err("unable to create debugfs directory %s\n", UV_BAU_TUNABLES_DIR); return -EINVAL; } tunables_file = debugfs_create_file(UV_BAU_TUNABLES_FILE, 0600, tunables_dir, NULL, &tunables_fops); if (!tunables_file) { - printk(KERN_ERR "unable to create debugfs file %s\n", + pr_err("unable to create debugfs file %s\n", UV_BAU_TUNABLES_FILE); return -EINVAL; } @@ -1725,7 +1744,7 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) gpa = uv_gpa(bau_desc); n = uv_gpa_to_gnode(gpa); - m = uv_gpa_to_offset(gpa); + m = ops.bau_gpa_to_offset(gpa); if (is_uv1_hub()) uv1 = 1; @@ -1740,7 +1759,7 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) memset(bd2, 0, sizeof(struct bau_desc)); if (uv1) { uv1_hdr = &bd2->header.uv1_hdr; - uv1_hdr->swack_flag = 1; + uv1_hdr->swack_flag = 1; /* * The base_dest_nasid set in the message header * is the nasid of the first uvhub in the partition. @@ -1749,10 +1768,10 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) * if nasid striding is being used. */ uv1_hdr->base_dest_nasid = - UV_PNODE_TO_NASID(base_pnode); - uv1_hdr->dest_subnodeid = UV_LB_SUBNODEID; - uv1_hdr->command = UV_NET_ENDPOINT_INTD; - uv1_hdr->int_both = 1; + UV_PNODE_TO_NASID(base_pnode); + uv1_hdr->dest_subnodeid = UV_LB_SUBNODEID; + uv1_hdr->command = UV_NET_ENDPOINT_INTD; + uv1_hdr->int_both = 1; /* * all others need to be set to zero: * fairness chaining multilevel count replied_to @@ -1763,11 +1782,11 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) * uses native mode for selective broadcasts. */ uv2_3_hdr = &bd2->header.uv2_3_hdr; - uv2_3_hdr->swack_flag = 1; + uv2_3_hdr->swack_flag = 1; uv2_3_hdr->base_dest_nasid = - UV_PNODE_TO_NASID(base_pnode); - uv2_3_hdr->dest_subnodeid = UV_LB_SUBNODEID; - uv2_3_hdr->command = UV_NET_ENDPOINT_INTD; + UV_PNODE_TO_NASID(base_pnode); + uv2_3_hdr->dest_subnodeid = UV_LB_SUBNODEID; + uv2_3_hdr->command = UV_NET_ENDPOINT_INTD; } } for_each_present_cpu(cpu) { @@ -1790,10 +1809,7 @@ static void pq_init(int node, int pnode) size_t plsize; char *cp; void *vp; - unsigned long pn; - unsigned long first; - unsigned long pn_first; - unsigned long last; + unsigned long gnode, first, last, tail; struct bau_pq_entry *pqp; struct bau_control *bcp; @@ -1814,17 +1830,25 @@ static void pq_init(int node, int pnode) bcp->bau_msg_head = pqp; bcp->queue_last = pqp + (DEST_Q_SIZE - 1); } + + first = ops.bau_gpa_to_offset(uv_gpa(pqp)); + last = ops.bau_gpa_to_offset(uv_gpa(pqp + (DEST_Q_SIZE - 1))); + /* - * need the gnode of where the memory was really allocated + * Pre UV4, the gnode is required to locate the payload queue + * and the payload queue tail must be maintained by the kernel. */ - pn = uv_gpa_to_gnode(uv_gpa(pqp)); - first = uv_physnodeaddr(pqp); - pn_first = ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) | first; - last = uv_physnodeaddr(pqp + (DEST_Q_SIZE - 1)); - write_mmr_payload_first(pnode, pn_first); - write_mmr_payload_tail(pnode, first); - write_mmr_payload_last(pnode, last); - write_gmmr_sw_ack(pnode, 0xffffUL); + bcp = &per_cpu(bau_control, smp_processor_id()); + if (bcp->uvhub_version <= 3) { + tail = first; + gnode = uv_gpa_to_gnode(uv_gpa(pqp)); + first = (gnode << UV_PAYLOADQ_GNODE_SHIFT) | tail; + write_mmr_payload_tail(pnode, tail); + } + + ops.write_payload_first(pnode, first); + ops.write_payload_last(pnode, last); + ops.write_g_sw_ack(pnode, 0xffffUL); /* in effect, all msg_type's are set to MSG_NOOP */ memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE); @@ -1914,8 +1938,8 @@ static void __init init_per_cpu_tunables(void) bcp->complete_threshold = complete_threshold; bcp->cong_response_us = congested_respns_us; bcp->cong_reps = congested_reps; - bcp->disabled_period = sec_2_cycles(disabled_period); - bcp->giveup_limit = giveup_limit; + bcp->disabled_period = sec_2_cycles(disabled_period); + bcp->giveup_limit = giveup_limit; spin_lock_init(&bcp->queue_lock); spin_lock_init(&bcp->uvhub_lock); spin_lock_init(&bcp->disable_lock); @@ -1944,7 +1968,7 @@ static int __init get_cpu_topology(int base_pnode, pnode = uv_cpu_hub_info(cpu)->pnode; if ((pnode - base_pnode) >= UV_DISTRIBUTION_SIZE) { - printk(KERN_EMERG + pr_emerg( "cpu %d pnode %d-%d beyond %d; BAU disabled\n", cpu, pnode, base_pnode, UV_DISTRIBUTION_SIZE); return 1; @@ -1969,7 +1993,7 @@ static int __init get_cpu_topology(int base_pnode, sdp->cpu_number[sdp->num_cpus] = cpu; sdp->num_cpus++; if (sdp->num_cpus > MAX_CPUS_PER_SOCKET) { - printk(KERN_EMERG "%d cpus per socket invalid\n", + pr_emerg("%d cpus per socket invalid\n", sdp->num_cpus); return 1; } @@ -2035,15 +2059,17 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp, bcp->uvhub_version = 2; else if (is_uv3_hub()) bcp->uvhub_version = 3; + else if (is_uv4_hub()) + bcp->uvhub_version = 4; else { - printk(KERN_EMERG "uvhub version not 1, 2 or 3\n"); + pr_emerg("uvhub version not 1, 2, 3, or 4\n"); return 1; } bcp->uvhub_master = *hmasterp; bcp->uvhub_cpu = uv_cpu_blade_processor_id(cpu); if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) { - printk(KERN_EMERG "%d cpus per uvhub invalid\n", + pr_emerg("%d cpus per uvhub invalid\n", bcp->uvhub_cpu); return 1; } @@ -2098,7 +2124,8 @@ static int __init init_per_cpu(int nuvhubs, int base_part_pnode) void *vp; struct uvhub_desc *uvhub_descs; - timeout_us = calculate_destination_timeout(); + if (is_uv3_hub() || is_uv2_hub() || is_uv1_hub()) + timeout_us = calculate_destination_timeout(); vp = kmalloc(nuvhubs * sizeof(struct uvhub_desc), GFP_KERNEL); uvhub_descs = (struct uvhub_desc *)vp; @@ -2138,6 +2165,15 @@ static int __init uv_bau_init(void) if (!is_uv_system()) return 0; + if (is_uv4_hub()) + ops = uv4_bau_ops; + else if (is_uv3_hub()) + ops = uv123_bau_ops; + else if (is_uv2_hub()) + ops = uv123_bau_ops; + else if (is_uv1_hub()) + ops = uv123_bau_ops; + for_each_possible_cpu(cur_cpu) { mask = &per_cpu(uv_flush_tlb_mask, cur_cpu); zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cur_cpu)); @@ -2153,7 +2189,9 @@ static int __init uv_bau_init(void) uv_base_pnode = uv_blade_to_pnode(uvhub); } - enable_timeouts(); + /* software timeouts are not supported on UV4 */ + if (is_uv3_hub() || is_uv2_hub() || is_uv1_hub()) + enable_timeouts(); if (init_per_cpu(nuvhubs, uv_base_pnode)) { set_bau_off(); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index b12c26e2e309..53cace2ec0e2 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -130,7 +130,7 @@ static void __save_processor_state(struct saved_context *ctxt) ctxt->cr0 = read_cr0(); ctxt->cr2 = read_cr2(); ctxt->cr3 = read_cr3(); - ctxt->cr4 = __read_cr4_safe(); + ctxt->cr4 = __read_cr4(); #ifdef CONFIG_X86_64 ctxt->cr8 = read_cr8(); #endif diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c index 1104515d5ad2..1ac76479c266 100644 --- a/arch/x86/ras/mce_amd_inj.c +++ b/arch/x86/ras/mce_amd_inj.c @@ -68,6 +68,7 @@ static int inj_##reg##_set(void *data, u64 val) \ MCE_INJECT_SET(status); MCE_INJECT_SET(misc); MCE_INJECT_SET(addr); +MCE_INJECT_SET(synd); #define MCE_INJECT_GET(reg) \ static int inj_##reg##_get(void *data, u64 *val) \ @@ -81,10 +82,12 @@ static int inj_##reg##_get(void *data, u64 *val) \ MCE_INJECT_GET(status); MCE_INJECT_GET(misc); MCE_INJECT_GET(addr); +MCE_INJECT_GET(synd); DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n"); DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n"); DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(synd_fops, inj_synd_get, inj_synd_set, "%llx\n"); /* * Caller needs to be make sure this cpu doesn't disappear @@ -243,27 +246,27 @@ static void toggle_nb_mca_mst_cpu(u16 nid) static void prepare_msrs(void *info) { - struct mce i_mce = *(struct mce *)info; - u8 b = i_mce.bank; + struct mce m = *(struct mce *)info; + u8 b = m.bank; - wrmsrl(MSR_IA32_MCG_STATUS, i_mce.mcgstatus); + wrmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus); if (boot_cpu_has(X86_FEATURE_SMCA)) { - if (i_mce.inject_flags == DFR_INT_INJ) { - wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(b), i_mce.status); - wrmsrl(MSR_AMD64_SMCA_MCx_DEADDR(b), i_mce.addr); + if (m.inject_flags == DFR_INT_INJ) { + wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(b), m.status); + wrmsrl(MSR_AMD64_SMCA_MCx_DEADDR(b), m.addr); } else { - wrmsrl(MSR_AMD64_SMCA_MCx_STATUS(b), i_mce.status); - wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), i_mce.addr); + wrmsrl(MSR_AMD64_SMCA_MCx_STATUS(b), m.status); + wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr); } - wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), i_mce.misc); + wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc); + wrmsrl(MSR_AMD64_SMCA_MCx_SYND(b), m.synd); } else { - wrmsrl(MSR_IA32_MCx_STATUS(b), i_mce.status); - wrmsrl(MSR_IA32_MCx_ADDR(b), i_mce.addr); - wrmsrl(MSR_IA32_MCx_MISC(b), i_mce.misc); + wrmsrl(MSR_IA32_MCx_STATUS(b), m.status); + wrmsrl(MSR_IA32_MCx_ADDR(b), m.addr); + wrmsrl(MSR_IA32_MCx_MISC(b), m.misc); } - } static void do_inject(void) @@ -275,6 +278,9 @@ static void do_inject(void) if (i_mce.misc) i_mce.status |= MCI_STATUS_MISCV; + if (i_mce.synd) + i_mce.status |= MCI_STATUS_SYNDV; + if (inj_type == SW_INJ) { mce_inject_log(&i_mce); return; @@ -301,7 +307,9 @@ static void do_inject(void) * only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for * Fam10h and later BKDGs. */ - if (static_cpu_has(X86_FEATURE_AMD_DCM) && b == 4) { + if (static_cpu_has(X86_FEATURE_AMD_DCM) && + b == 4 && + boot_cpu_data.x86 < 0x17) { toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu)); cpu = get_nbc_for_node(amd_get_nb_id(cpu)); } @@ -371,6 +379,9 @@ static const char readme_msg[] = "\t used for error thresholding purposes and its validity is indicated by\n" "\t MCi_STATUS[MiscV].\n" "\n" +"synd:\t Set MCi_SYND: provide syndrome info about the error. Only valid on\n" +"\t Scalable MCA systems, and its validity is indicated by MCi_STATUS[SyndV].\n" +"\n" "addr:\t Error address value to be written to MCi_ADDR. Log address information\n" "\t associated with the error.\n" "\n" @@ -420,6 +431,7 @@ static struct dfs_node { { .name = "status", .fops = &status_fops, .perm = S_IRUSR | S_IWUSR }, { .name = "misc", .fops = &misc_fops, .perm = S_IRUSR | S_IWUSR }, { .name = "addr", .fops = &addr_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "synd", .fops = &synd_fops, .perm = S_IRUSR | S_IWUSR }, { .name = "bank", .fops = &bank_fops, .perm = S_IRUSR | S_IWUSR }, { .name = "flags", .fops = &flags_fops, .perm = S_IRUSR | S_IWUSR }, { .name = "cpu", .fops = &extcpu_fops, .perm = S_IRUSR | S_IWUSR }, @@ -428,7 +440,7 @@ static struct dfs_node { static int __init init_mce_inject(void) { - int i; + unsigned int i; u64 cap; rdmsrl(MSR_IA32_MCG_CAP, cap); @@ -452,26 +464,22 @@ static int __init init_mce_inject(void) return 0; err_dfs_add: - while (--i >= 0) + while (i-- > 0) debugfs_remove(dfs_fls[i].d); debugfs_remove(dfs_inj); dfs_inj = NULL; - return -ENOMEM; + return -ENODEV; } static void __exit exit_mce_inject(void) { - int i; - for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) - debugfs_remove(dfs_fls[i].d); + debugfs_remove_recursive(dfs_inj); + dfs_inj = NULL; memset(&dfs_fls, 0, sizeof(dfs_fls)); - - debugfs_remove(dfs_inj); - dfs_inj = NULL; } module_init(init_mce_inject); module_exit(exit_mce_inject); diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c index ebd4dd6ef73b..5766ead6fdb9 100644 --- a/arch/x86/um/ptrace_32.c +++ b/arch/x86/um/ptrace_32.c @@ -84,7 +84,10 @@ int putreg(struct task_struct *child, int regno, unsigned long value) case EAX: case EIP: case UESP: + break; case ORIG_EAX: + /* Update the syscall number. */ + UPT_SYSCALL_NR(&child->thread.regs.regs) = value; break; case FS: if (value && (value & 3) != 3) @@ -191,7 +194,7 @@ int peek_user(struct task_struct *child, long addr, long data) static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { - int err, n, cpu = ((struct thread_info *) child->stack)->cpu; + int err, n, cpu = task_cpu(child); struct user_i387_struct fpregs; err = save_i387_registers(userspace_pid[cpu], @@ -208,7 +211,7 @@ static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *c static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { - int n, cpu = ((struct thread_info *) child->stack)->cpu; + int n, cpu = task_cpu(child); struct user_i387_struct fpregs; n = copy_from_user(&fpregs, buf, sizeof(fpregs)); @@ -221,7 +224,7 @@ static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *c static int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) { - int err, n, cpu = ((struct thread_info *) child->stack)->cpu; + int err, n, cpu = task_cpu(child); struct user_fxsr_struct fpregs; err = save_fpx_registers(userspace_pid[cpu], (unsigned long *) &fpregs); @@ -237,7 +240,7 @@ static int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct * static int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) { - int n, cpu = ((struct thread_info *) child->stack)->cpu; + int n, cpu = task_cpu(child); struct user_fxsr_struct fpregs; n = copy_from_user(&fpregs, buf, sizeof(fpregs)); diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c index faab418876ce..0b5c184dd5b3 100644 --- a/arch/x86/um/ptrace_64.c +++ b/arch/x86/um/ptrace_64.c @@ -78,7 +78,11 @@ int putreg(struct task_struct *child, int regno, unsigned long value) case RSI: case RDI: case RBP: + break; + case ORIG_RAX: + /* Update the syscall number. */ + UPT_SYSCALL_NR(&child->thread.regs.regs) = value; break; case FS: diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index b86ebb1a9a7f..c0fdd57da7aa 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -137,8 +137,10 @@ struct shared_info xen_dummy_shared_info; void *xen_initial_gdt; RESERVE_BRK(shared_info_page_brk, PAGE_SIZE); -__read_mostly int xen_have_vector_callback; -EXPORT_SYMBOL_GPL(xen_have_vector_callback); + +static int xen_cpu_up_prepare(unsigned int cpu); +static int xen_cpu_up_online(unsigned int cpu); +static int xen_cpu_dead(unsigned int cpu); /* * Point at some empty memory to start with. We map the real shared_info @@ -1237,7 +1239,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .write_cr0 = xen_write_cr0, .read_cr4 = native_read_cr4, - .read_cr4_safe = native_read_cr4_safe, .write_cr4 = xen_write_cr4, #ifdef CONFIG_X86_64 @@ -1520,10 +1521,7 @@ static void __init xen_pvh_early_guest_init(void) if (!xen_feature(XENFEAT_auto_translated_physmap)) return; - if (!xen_feature(XENFEAT_hvm_callback_vector)) - return; - - xen_have_vector_callback = 1; + BUG_ON(!xen_feature(XENFEAT_hvm_callback_vector)); xen_pvh_early_cpu_init(0, false); xen_pvh_set_cr_flags(0); @@ -1539,6 +1537,24 @@ static void __init xen_dom0_set_legacy_features(void) x86_platform.legacy.rtc = 1; } +static int xen_cpuhp_setup(void) +{ + int rc; + + rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE, + "XEN_HVM_GUEST_PREPARE", + xen_cpu_up_prepare, xen_cpu_dead); + if (rc >= 0) { + rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "XEN_HVM_GUEST_ONLINE", + xen_cpu_up_online, NULL); + if (rc < 0) + cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE); + } + + return rc >= 0 ? 0 : rc; +} + /* First C function to be called on Xen boot */ asmlinkage __visible void __init xen_start_kernel(void) { @@ -1640,6 +1656,8 @@ asmlinkage __visible void __init xen_start_kernel(void) possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; + WARN_ON(xen_cpuhp_setup()); + local_irq_disable(); early_boot_irqs_disabled = true; @@ -1820,31 +1838,54 @@ static void __init init_hvm_pv_info(void) xen_domain_type = XEN_HVM_DOMAIN; } -static int xen_hvm_cpu_notify(struct notifier_block *self, unsigned long action, - void *hcpu) +static int xen_cpu_up_prepare(unsigned int cpu) { - int cpu = (long)hcpu; - switch (action) { - case CPU_UP_PREPARE: + int rc; + + if (xen_hvm_domain()) { + /* + * This can happen if CPU was offlined earlier and + * offlining timed out in common_cpu_die(). + */ + if (cpu_report_state(cpu) == CPU_DEAD_FROZEN) { + xen_smp_intr_free(cpu); + xen_uninit_lock_cpu(cpu); + } + if (cpu_acpi_id(cpu) != U32_MAX) per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu); else per_cpu(xen_vcpu_id, cpu) = cpu; xen_vcpu_setup(cpu); - if (xen_have_vector_callback) { - if (xen_feature(XENFEAT_hvm_safe_pvclock)) - xen_setup_timer(cpu); - } - break; - default: - break; } - return NOTIFY_OK; + + if (xen_pv_domain() || xen_feature(XENFEAT_hvm_safe_pvclock)) + xen_setup_timer(cpu); + + rc = xen_smp_intr_init(cpu); + if (rc) { + WARN(1, "xen_smp_intr_init() for CPU %d failed: %d\n", + cpu, rc); + return rc; + } + return 0; } -static struct notifier_block xen_hvm_cpu_notifier = { - .notifier_call = xen_hvm_cpu_notify, -}; +static int xen_cpu_dead(unsigned int cpu) +{ + xen_smp_intr_free(cpu); + + if (xen_pv_domain() || xen_feature(XENFEAT_hvm_safe_pvclock)) + xen_teardown_timer(cpu); + + return 0; +} + +static int xen_cpu_up_online(unsigned int cpu) +{ + xen_init_lock_cpu(cpu); + return 0; +} #ifdef CONFIG_KEXEC_CORE static void xen_hvm_shutdown(void) @@ -1872,10 +1913,10 @@ static void __init xen_hvm_guest_init(void) xen_panic_handler_init(); - if (xen_feature(XENFEAT_hvm_callback_vector)) - xen_have_vector_callback = 1; + BUG_ON(!xen_feature(XENFEAT_hvm_callback_vector)); + xen_hvm_smp_init(); - register_cpu_notifier(&xen_hvm_cpu_notifier); + WARN_ON(xen_cpuhp_setup()); xen_unplug_emulated_devices(); x86_init.irqs.intr_init = xen_init_IRQ; xen_hvm_init_time_ops(); @@ -1911,7 +1952,7 @@ bool xen_hvm_need_lapic(void) return false; if (!xen_hvm_domain()) return false; - if (xen_feature(XENFEAT_hvm_pirqs) && xen_have_vector_callback) + if (xen_feature(XENFEAT_hvm_pirqs)) return false; return true; } @@ -1925,6 +1966,45 @@ static void xen_set_cpu_features(struct cpuinfo_x86 *c) } } +static void xen_pin_vcpu(int cpu) +{ + static bool disable_pinning; + struct sched_pin_override pin_override; + int ret; + + if (disable_pinning) + return; + + pin_override.pcpu = cpu; + ret = HYPERVISOR_sched_op(SCHEDOP_pin_override, &pin_override); + + /* Ignore errors when removing override. */ + if (cpu < 0) + return; + + switch (ret) { + case -ENOSYS: + pr_warn("Unable to pin on physical cpu %d. In case of problems consider vcpu pinning.\n", + cpu); + disable_pinning = true; + break; + case -EPERM: + WARN(1, "Trying to pin vcpu without having privilege to do so\n"); + disable_pinning = true; + break; + case -EINVAL: + case -EBUSY: + pr_warn("Physical cpu %d not available for pinning. Check Xen cpu configuration.\n", + cpu); + break; + case 0: + break; + default: + WARN(1, "rc %d while trying to pin vcpu\n", ret); + disable_pinning = true; + } +} + const struct hypervisor_x86 x86_hyper_xen = { .name = "Xen", .detect = xen_platform, @@ -1933,6 +2013,7 @@ const struct hypervisor_x86 x86_hyper_xen = { #endif .x2apic_available = xen_x2apic_para_available, .set_cpu_features = xen_set_cpu_features, + .pin_vcpu = xen_pin_vcpu, }; EXPORT_SYMBOL(x86_hyper_xen); diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c index de4144c24f1c..809b6c812654 100644 --- a/arch/x86/xen/grant-table.c +++ b/arch/x86/xen/grant-table.c @@ -89,7 +89,7 @@ void arch_gnttab_unmap(void *shared, unsigned long nr_gframes) static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames) { - area->ptes = kmalloc(sizeof(pte_t *) * nr_frames, GFP_KERNEL); + area->ptes = kmalloc_array(nr_frames, sizeof(*area->ptes), GFP_KERNEL); if (area->ptes == NULL) return -ENOMEM; diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c index d37a0c7f82cb..90d1b83cf35f 100644 --- a/arch/x86/xen/platform-pci-unplug.c +++ b/arch/x86/xen/platform-pci-unplug.c @@ -61,7 +61,7 @@ static int check_platform_magic(void) } break; default: - printk(KERN_WARNING "Xen Platform PCI: unknown I/O protocol version"); + printk(KERN_WARNING "Xen Platform PCI: unknown I/O protocol version\n"); return XEN_PLATFORM_ERR_PROTOCOL; } diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index 32bdc2c90297..b9fc52556bcc 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -547,8 +547,11 @@ void xen_pmu_init(int cpu) return; fail: - pr_info_once("Could not initialize VPMU for cpu %d, error %d\n", - cpu, err); + if (err == -EOPNOTSUPP || err == -ENOSYS) + pr_info_once("VPMU disabled by hypervisor.\n"); + else + pr_info_once("Could not initialize VPMU for cpu %d, error %d\n", + cpu, err); free_pages((unsigned long)xenpmu_data, 0); } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 176425233e4d..f8960fca0827 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -861,7 +861,7 @@ char * __init xen_memory_setup(void) e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS, E820_RESERVED); - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); /* * Check whether the kernel itself conflicts with the target E820 map. diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 0b4d04c8ab4d..9fa27ceeecfd 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -87,6 +87,12 @@ static void cpu_bringup(void) cpu_data(cpu).x86_max_cores = 1; set_cpu_sibling_map(cpu); + /* + * identify_cpu() may have set logical_pkg_id to -1 due + * to incorrect phys_proc_id. Let's re-comupte it. + */ + topology_update_package_map(apic->cpu_present_to_apicid(cpu), cpu); + xen_setup_cpu_clockevents(); notify_cpu_starting(cpu); @@ -115,7 +121,7 @@ asmlinkage __visible void cpu_bringup_and_idle(int cpu) cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } -static void xen_smp_intr_free(unsigned int cpu) +void xen_smp_intr_free(unsigned int cpu) { if (per_cpu(xen_resched_irq, cpu).irq >= 0) { unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu).irq, NULL); @@ -159,7 +165,7 @@ static void xen_smp_intr_free(unsigned int cpu) per_cpu(xen_pmu_irq, cpu).name = NULL; } }; -static int xen_smp_intr_init(unsigned int cpu) +int xen_smp_intr_init(unsigned int cpu) { int rc; char *resched_name, *callfunc_name, *debug_name, *pmu_name; @@ -475,8 +481,6 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle) common_cpu_up(cpu, idle); xen_setup_runstate_info(cpu); - xen_setup_timer(cpu); - xen_init_lock_cpu(cpu); /* * PV VCPUs are always successfully taken down (see 'while' loop @@ -495,10 +499,6 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle) xen_pmu_init(cpu); - rc = xen_smp_intr_init(cpu); - if (rc) - return rc; - rc = HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL); BUG_ON(rc); @@ -769,47 +769,10 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) xen_init_lock_cpu(0); } -static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle) -{ - int rc; - - /* - * This can happen if CPU was offlined earlier and - * offlining timed out in common_cpu_die(). - */ - if (cpu_report_state(cpu) == CPU_DEAD_FROZEN) { - xen_smp_intr_free(cpu); - xen_uninit_lock_cpu(cpu); - } - - /* - * xen_smp_intr_init() needs to run before native_cpu_up() - * so that IPI vectors are set up on the booting CPU before - * it is marked online in native_cpu_up(). - */ - rc = xen_smp_intr_init(cpu); - WARN_ON(rc); - if (!rc) - rc = native_cpu_up(cpu, tidle); - - /* - * We must initialize the slowpath CPU kicker _after_ the native - * path has executed. If we initialized it before none of the - * unlocker IPI kicks would reach the booting CPU as the booting - * CPU had not set itself 'online' in cpu_online_mask. That mask - * is checked when IPIs are sent (on HVM at least). - */ - xen_init_lock_cpu(cpu); - return rc; -} - void __init xen_hvm_smp_init(void) { - if (!xen_have_vector_callback) - return; smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; smp_ops.smp_send_reschedule = xen_smp_send_reschedule; - smp_ops.cpu_up = xen_hvm_cpu_up; smp_ops.cpu_die = xen_cpu_die; smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi; smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi; diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h index 963d62a35c82..c5c16dc4f694 100644 --- a/arch/x86/xen/smp.h +++ b/arch/x86/xen/smp.h @@ -1,5 +1,6 @@ #ifndef _XEN_SMP_H +#ifdef CONFIG_SMP extern void xen_send_IPI_mask(const struct cpumask *mask, int vector); extern void xen_send_IPI_mask_allbutself(const struct cpumask *mask, @@ -8,6 +9,18 @@ extern void xen_send_IPI_allbutself(int vector); extern void xen_send_IPI_all(int vector); extern void xen_send_IPI_self(int vector); +extern int xen_smp_intr_init(unsigned int cpu); +extern void xen_smp_intr_free(unsigned int cpu); + +#else /* CONFIG_SMP */ + +static inline int xen_smp_intr_init(unsigned int cpu) +{ + return 0; +} +static inline void xen_smp_intr_free(unsigned int cpu) {} +#endif /* CONFIG_SMP */ + #ifdef CONFIG_XEN_PVH extern void xen_pvh_early_cpu_init(int cpu, bool entry); #else diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index f42e78de1e10..3d6e0064cbfc 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -21,8 +21,6 @@ static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; static DEFINE_PER_CPU(char *, irq_name); static bool xen_pvspin = true; -#ifdef CONFIG_QUEUED_SPINLOCKS - #include <asm/qspinlock.h> static void xen_qlock_kick(int cpu) @@ -71,207 +69,6 @@ static void xen_qlock_wait(u8 *byte, u8 val) xen_poll_irq(irq); } -#else /* CONFIG_QUEUED_SPINLOCKS */ - -enum xen_contention_stat { - TAKEN_SLOW, - TAKEN_SLOW_PICKUP, - TAKEN_SLOW_SPURIOUS, - RELEASED_SLOW, - RELEASED_SLOW_KICKED, - NR_CONTENTION_STATS -}; - - -#ifdef CONFIG_XEN_DEBUG_FS -#define HISTO_BUCKETS 30 -static struct xen_spinlock_stats -{ - u32 contention_stats[NR_CONTENTION_STATS]; - u32 histo_spin_blocked[HISTO_BUCKETS+1]; - u64 time_blocked; -} spinlock_stats; - -static u8 zero_stats; - -static inline void check_zero(void) -{ - u8 ret; - u8 old = READ_ONCE(zero_stats); - if (unlikely(old)) { - ret = cmpxchg(&zero_stats, old, 0); - /* This ensures only one fellow resets the stat */ - if (ret == old) - memset(&spinlock_stats, 0, sizeof(spinlock_stats)); - } -} - -static inline void add_stats(enum xen_contention_stat var, u32 val) -{ - check_zero(); - spinlock_stats.contention_stats[var] += val; -} - -static inline u64 spin_time_start(void) -{ - return xen_clocksource_read(); -} - -static void __spin_time_accum(u64 delta, u32 *array) -{ - unsigned index = ilog2(delta); - - check_zero(); - - if (index < HISTO_BUCKETS) - array[index]++; - else - array[HISTO_BUCKETS]++; -} - -static inline void spin_time_accum_blocked(u64 start) -{ - u32 delta = xen_clocksource_read() - start; - - __spin_time_accum(delta, spinlock_stats.histo_spin_blocked); - spinlock_stats.time_blocked += delta; -} -#else /* !CONFIG_XEN_DEBUG_FS */ -static inline void add_stats(enum xen_contention_stat var, u32 val) -{ -} - -static inline u64 spin_time_start(void) -{ - return 0; -} - -static inline void spin_time_accum_blocked(u64 start) -{ -} -#endif /* CONFIG_XEN_DEBUG_FS */ - -struct xen_lock_waiting { - struct arch_spinlock *lock; - __ticket_t want; -}; - -static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting); -static cpumask_t waiting_cpus; - -__visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want) -{ - int irq = __this_cpu_read(lock_kicker_irq); - struct xen_lock_waiting *w = this_cpu_ptr(&lock_waiting); - int cpu = smp_processor_id(); - u64 start; - __ticket_t head; - unsigned long flags; - - /* If kicker interrupts not initialized yet, just spin */ - if (irq == -1) - return; - - start = spin_time_start(); - - /* - * Make sure an interrupt handler can't upset things in a - * partially setup state. - */ - local_irq_save(flags); - /* - * We don't really care if we're overwriting some other - * (lock,want) pair, as that would mean that we're currently - * in an interrupt context, and the outer context had - * interrupts enabled. That has already kicked the VCPU out - * of xen_poll_irq(), so it will just return spuriously and - * retry with newly setup (lock,want). - * - * The ordering protocol on this is that the "lock" pointer - * may only be set non-NULL if the "want" ticket is correct. - * If we're updating "want", we must first clear "lock". - */ - w->lock = NULL; - smp_wmb(); - w->want = want; - smp_wmb(); - w->lock = lock; - - /* This uses set_bit, which atomic and therefore a barrier */ - cpumask_set_cpu(cpu, &waiting_cpus); - add_stats(TAKEN_SLOW, 1); - - /* clear pending */ - xen_clear_irq_pending(irq); - - /* Only check lock once pending cleared */ - barrier(); - - /* - * Mark entry to slowpath before doing the pickup test to make - * sure we don't deadlock with an unlocker. - */ - __ticket_enter_slowpath(lock); - - /* make sure enter_slowpath, which is atomic does not cross the read */ - smp_mb__after_atomic(); - - /* - * check again make sure it didn't become free while - * we weren't looking - */ - head = READ_ONCE(lock->tickets.head); - if (__tickets_equal(head, want)) { - add_stats(TAKEN_SLOW_PICKUP, 1); - goto out; - } - - /* Allow interrupts while blocked */ - local_irq_restore(flags); - - /* - * If an interrupt happens here, it will leave the wakeup irq - * pending, which will cause xen_poll_irq() to return - * immediately. - */ - - /* Block until irq becomes pending (or perhaps a spurious wakeup) */ - xen_poll_irq(irq); - add_stats(TAKEN_SLOW_SPURIOUS, !xen_test_irq_pending(irq)); - - local_irq_save(flags); - - kstat_incr_irq_this_cpu(irq); -out: - cpumask_clear_cpu(cpu, &waiting_cpus); - w->lock = NULL; - - local_irq_restore(flags); - - spin_time_accum_blocked(start); -} -PV_CALLEE_SAVE_REGS_THUNK(xen_lock_spinning); - -static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next) -{ - int cpu; - - add_stats(RELEASED_SLOW, 1); - - for_each_cpu(cpu, &waiting_cpus) { - const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu); - - /* Make sure we read lock before want */ - if (READ_ONCE(w->lock) == lock && - READ_ONCE(w->want) == next) { - add_stats(RELEASED_SLOW_KICKED, 1); - xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR); - break; - } - } -} -#endif /* CONFIG_QUEUED_SPINLOCKS */ - static irqreturn_t dummy_handler(int irq, void *dev_id) { BUG(); @@ -334,16 +131,12 @@ void __init xen_init_spinlocks(void) return; } printk(KERN_DEBUG "xen: PV spinlocks enabled\n"); -#ifdef CONFIG_QUEUED_SPINLOCKS + __pv_init_lock_hash(); pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); pv_lock_ops.wait = xen_qlock_wait; pv_lock_ops.kick = xen_qlock_kick; -#else - pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning); - pv_lock_ops.unlock_kick = xen_unlock_kick; -#endif } /* @@ -372,44 +165,3 @@ static __init int xen_parse_nopvspin(char *arg) } early_param("xen_nopvspin", xen_parse_nopvspin); -#if defined(CONFIG_XEN_DEBUG_FS) && !defined(CONFIG_QUEUED_SPINLOCKS) - -static struct dentry *d_spin_debug; - -static int __init xen_spinlock_debugfs(void) -{ - struct dentry *d_xen = xen_init_debugfs(); - - if (d_xen == NULL) - return -ENOMEM; - - if (!xen_pvspin) - return 0; - - d_spin_debug = debugfs_create_dir("spinlocks", d_xen); - - debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats); - - debugfs_create_u32("taken_slow", 0444, d_spin_debug, - &spinlock_stats.contention_stats[TAKEN_SLOW]); - debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug, - &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]); - debugfs_create_u32("taken_slow_spurious", 0444, d_spin_debug, - &spinlock_stats.contention_stats[TAKEN_SLOW_SPURIOUS]); - - debugfs_create_u32("released_slow", 0444, d_spin_debug, - &spinlock_stats.contention_stats[RELEASED_SLOW]); - debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug, - &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]); - - debugfs_create_u64("time_blocked", 0444, d_spin_debug, - &spinlock_stats.time_blocked); - - debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug, - spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1); - - return 0; -} -fs_initcall(xen_spinlock_debugfs); - -#endif /* CONFIG_XEN_DEBUG_FS */ diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 67356d29d74d..33d8f6a7829d 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -432,11 +432,6 @@ static void xen_hvm_setup_cpu_clockevents(void) void __init xen_hvm_init_time_ops(void) { - /* vector callback is needed otherwise we cannot receive interrupts - * on cpu > 0 and at this point we don't know how many cpus are - * available */ - if (!xen_have_vector_callback) - return; if (!xen_feature(XENFEAT_hvm_safe_pvclock)) { printk(KERN_INFO "Xen doesn't support pvclock on HVM," "disable pv timer\n"); diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 64336f666fb6..f61058617ada 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -13,16 +13,19 @@ config XTENSA select GENERIC_IRQ_SHOW select GENERIC_PCI_IOMAP select GENERIC_SCHED_CLOCK + select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_API_DEBUG select HAVE_EXIT_THREAD select HAVE_FUNCTION_TRACER select HAVE_FUTEX_CMPXCHG if !MMU select HAVE_HW_BREAKPOINT if PERF_EVENTS select HAVE_IRQ_TIME_ACCOUNTING + select HAVE_MEMBLOCK select HAVE_OPROFILE select HAVE_PERF_EVENTS select IRQ_DOMAIN select MODULES_USE_ELF_RELA + select NO_BOOTMEM select PERF_USE_VMALLOC select VIRT_TO_BUS help @@ -209,7 +212,8 @@ config HOTPLUG_CPU config INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX bool "Initialize Xtensa MMU inside the Linux kernel code" - default y + depends on !XTENSA_VARIANT_FSF && !XTENSA_VARIANT_DC232B + default y if XTENSA_VARIANT_DC233C || XTENSA_VARIANT_CUSTOM help Earlier version initialized the MMU in the exception vector before jumping to _startup in head.S and had an advantage that @@ -236,6 +240,71 @@ config INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX If in doubt, say Y. +config KSEG_PADDR + hex "Physical address of the KSEG mapping" + depends on INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX && MMU + default 0x00000000 + help + This is the physical address where KSEG is mapped. Please refer to + the chosen KSEG layout help for the required address alignment. + Unpacked kernel image (including vectors) must be located completely + within KSEG. + Physical memory below this address is not available to linux. + + If unsure, leave the default value here. + +config KERNEL_LOAD_ADDRESS + hex "Kernel load address" + default 0x60003000 if !MMU + default 0x00003000 if MMU && INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX + default 0xd0003000 if MMU && !INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX + help + This is the address where the kernel is loaded. + It is virtual address for MMUv2 configurations and physical address + for all other configurations. + + If unsure, leave the default value here. + +config VECTORS_OFFSET + hex "Kernel vectors offset" + default 0x00003000 + help + This is the offset of the kernel image from the relocatable vectors + base. + + If unsure, leave the default value here. + +choice + prompt "KSEG layout" + depends on MMU + default XTENSA_KSEG_MMU_V2 + +config XTENSA_KSEG_MMU_V2 + bool "MMUv2: 128MB cached + 128MB uncached" + help + MMUv2 compatible kernel memory map: TLB way 5 maps 128MB starting + at KSEG_PADDR to 0xd0000000 with cache and to 0xd8000000 + without cache. + KSEG_PADDR must be aligned to 128MB. + +config XTENSA_KSEG_256M + bool "256MB cached + 256MB uncached" + depends on INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX + help + TLB way 6 maps 256MB starting at KSEG_PADDR to 0xb0000000 + with cache and to 0xc0000000 without cache. + KSEG_PADDR must be aligned to 256MB. + +config XTENSA_KSEG_512M + bool "512MB cached + 512MB uncached" + depends on INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX + help + TLB way 6 maps 512MB starting at KSEG_PADDR to 0xa0000000 + with cache and to 0xc0000000 without cache. + KSEG_PADDR must be aligned to 256MB. + +endchoice + config HIGHMEM bool "High Memory Support" depends on MMU @@ -331,7 +400,7 @@ config XTENSA_PLATFORM_XT2000 config XTENSA_PLATFORM_XTFPGA bool "XTFPGA" select ETHOC if ETHERNET - select PLATFORM_WANT_DEFAULT_MEM + select PLATFORM_WANT_DEFAULT_MEM if !MMU select SERIAL_CONSOLE select XTENSA_CALIBRATE_CCOUNT help @@ -369,6 +438,7 @@ config USE_OF bool "Flattened Device Tree support" select OF select OF_EARLY_FLATTREE + select OF_RESERVED_MEM help Include support for flattened device tree machine descriptions. @@ -439,16 +509,9 @@ config DEFAULT_MEM_START default 0x00000000 if MMU default 0x60000000 if !MMU help - This is a fallback start address of the default memory area, it is - used when no physical memory size is passed through DTB or through - boot parameter from bootloader. - - In noMMU configuration the following parameters are derived from it: - - kernel load address; - - kernel entry point address; - - relocatable vectors base address; - - uBoot load address; - - TASK_SIZE. + This is the base address of the default memory area. + Default memory area has platform-specific meaning, it may be used + for e.g. early cache initialization. If unsure, leave the default value here. @@ -457,11 +520,9 @@ config DEFAULT_MEM_SIZE depends on PLATFORM_WANT_DEFAULT_MEM default 0x04000000 help - This is a fallback size of the default memory area, it is used when - no physical memory size is passed through DTB or through boot - parameter from bootloader. - - It's also used for TASK_SIZE calculation in noMMU configuration. + This is the size of the default memory area. + Default memory area has platform-specific meaning, it may be used + for e.g. early cache initialization. If unsure, leave the default value here. diff --git a/arch/xtensa/boot/boot-elf/boot.lds.S b/arch/xtensa/boot/boot-elf/boot.lds.S index e54f2c9df63a..a30993054e9c 100644 --- a/arch/xtensa/boot/boot-elf/boot.lds.S +++ b/arch/xtensa/boot/boot-elf/boot.lds.S @@ -23,7 +23,7 @@ SECTIONS *(.ResetVector.text) } - .image KERNELOFFSET: AT (LOAD_MEMORY_ADDRESS) + .image KERNELOFFSET: AT (CONFIG_KERNEL_LOAD_ADDRESS) { _image_start = .; *(image) diff --git a/arch/xtensa/boot/boot-elf/bootstrap.S b/arch/xtensa/boot/boot-elf/bootstrap.S index e6bf313613cf..b6aa85328ac0 100644 --- a/arch/xtensa/boot/boot-elf/bootstrap.S +++ b/arch/xtensa/boot/boot-elf/bootstrap.S @@ -35,7 +35,12 @@ _ResetVector: .align 4 RomInitAddr: - .word LOAD_MEMORY_ADDRESS +#if defined(CONFIG_INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX) && \ + XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY + .word CONFIG_KERNEL_LOAD_ADDRESS +#else + .word KERNELOFFSET +#endif RomBootParam: .word _bootparam _bootparam: diff --git a/arch/xtensa/boot/boot-uboot/Makefile b/arch/xtensa/boot/boot-uboot/Makefile index 403fcf23405c..0f4c417b4196 100644 --- a/arch/xtensa/boot/boot-uboot/Makefile +++ b/arch/xtensa/boot/boot-uboot/Makefile @@ -4,15 +4,7 @@ # for more details. # -ifdef CONFIG_MMU -ifdef CONFIG_INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX -UIMAGE_LOADADDR = 0x00003000 -else -UIMAGE_LOADADDR = 0xd0003000 -endif -else -UIMAGE_LOADADDR = $(shell printf "0x%x" $$(( ${CONFIG_DEFAULT_MEM_START} + 0x3000 )) ) -endif +UIMAGE_LOADADDR = $(CONFIG_KERNEL_LOAD_ADDRESS) UIMAGE_COMPRESSION = gzip $(obj)/../uImage: vmlinux.bin.gz FORCE diff --git a/arch/xtensa/boot/dts/csp.dts b/arch/xtensa/boot/dts/csp.dts new file mode 100644 index 000000000000..4082f26716b9 --- /dev/null +++ b/arch/xtensa/boot/dts/csp.dts @@ -0,0 +1,54 @@ +/dts-v1/; + +/ { + compatible = "cdns,xtensa-xtfpga"; + #address-cells = <1>; + #size-cells = <1>; + interrupt-parent = <&pic>; + + chosen { + bootargs = "earlycon=cdns,0xfd000000,115200 console=tty0 console=ttyPS0,115200 root=/dev/ram0 rw earlyprintk xilinx_uartps.rx_trigger_level=32 loglevel=8 nohz=off ignore_loglevel"; + }; + + memory@0 { + device_type = "memory"; + reg = <0x00000000 0x40000000>; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + cpu@0 { + compatible = "cdns,xtensa-cpu"; + reg = <0>; + }; + }; + + pic: pic { + compatible = "cdns,xtensa-pic"; + #interrupt-cells = <2>; + interrupt-controller; + }; + + clocks { + osc: main-oscillator { + #clock-cells = <0>; + compatible = "fixed-clock"; + }; + }; + + soc { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-bus"; + ranges = <0x00000000 0xf0000000 0x10000000>; + + uart0: serial@0d000000 { + compatible = "xlnx,xuartps", "cdns,uart-r1p8"; + clocks = <&osc>, <&osc>; + clock-names = "uart_clk", "pclk"; + reg = <0x0d000000 0x1000>; + interrupts = <0 1>; + }; + }; +}; diff --git a/arch/xtensa/boot/dts/xtfpga.dtsi b/arch/xtensa/boot/dts/xtfpga.dtsi index cd45f9c2c448..91616a9d79df 100644 --- a/arch/xtensa/boot/dts/xtfpga.dtsi +++ b/arch/xtensa/boot/dts/xtfpga.dtsi @@ -19,9 +19,7 @@ cpu@0 { compatible = "cdns,xtensa-cpu"; reg = <0>; - /* Filled in by platform_setup from FPGA register - * clock-frequency = <100000000>; - */ + clocks = <&osc>; }; }; @@ -36,11 +34,6 @@ }; clocks { - osc: main-oscillator { - #clock-cells = <0>; - compatible = "fixed-clock"; - }; - clk54: clk54 { #clock-cells = <0>; compatible = "fixed-clock"; @@ -54,6 +47,12 @@ compatible = "simple-bus"; ranges = <0x00000000 0xf0000000 0x10000000>; + osc: main-oscillator { + #clock-cells = <0>; + compatible = "cdns,xtfpga-clock"; + reg = <0x0d020004 0x4>; + }; + serial0: serial@0d050020 { device_type = "serial"; compatible = "ns16550a"; diff --git a/arch/xtensa/configs/audio_kc705_defconfig b/arch/xtensa/configs/audio_kc705_defconfig index c4904db15582..8d16925765cb 100644 --- a/arch/xtensa/configs/audio_kc705_defconfig +++ b/arch/xtensa/configs/audio_kc705_defconfig @@ -33,7 +33,7 @@ CONFIG_HIGHMEM=y # CONFIG_PCI is not set CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="earlycon=uart8250,mmio32,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug" +CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0" CONFIG_USE_OF=y CONFIG_BUILTIN_DTB="kc705" # CONFIG_COMPACTION is not set diff --git a/arch/xtensa/configs/cadence_csp_defconfig b/arch/xtensa/configs/cadence_csp_defconfig new file mode 100644 index 000000000000..f2d3094aa1d1 --- /dev/null +++ b/arch/xtensa/configs/cadence_csp_defconfig @@ -0,0 +1,122 @@ +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_USELIB=y +CONFIG_IRQ_DOMAIN_DEBUG=y +CONFIG_NO_HZ_IDLE=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IRQ_TIME_ACCOUNTING=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_DEBUG=y +CONFIG_NAMESPACES=y +CONFIG_SCHED_AUTOGROUP=y +CONFIG_RELAY=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="$$KERNEL_INITRAMFS_SOURCE" +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_LZMA is not set +# CONFIG_RD_XZ is not set +# CONFIG_RD_LZO is not set +# CONFIG_RD_LZ4 is not set +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_SYSCTL_SYSCALL=y +CONFIG_EMBEDDED=y +CONFIG_PROFILING=y +CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y +# CONFIG_IOSCHED_DEADLINE is not set +# CONFIG_IOSCHED_CFQ is not set +CONFIG_XTENSA_VARIANT_CUSTOM=y +CONFIG_XTENSA_VARIANT_CUSTOM_NAME="csp" +CONFIG_XTENSA_UNALIGNED_USER=y +CONFIG_PREEMPT=y +CONFIG_HIGHMEM=y +# CONFIG_PCI is not set +CONFIG_XTENSA_PLATFORM_XTFPGA=y +CONFIG_USE_OF=y +CONFIG_BUILTIN_DTB="csp" +# CONFIG_COMPACTION is not set +CONFIG_XTFPGA_LCD=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_INET_DIAG is not set +# CONFIG_IPV6 is not set +# CONFIG_WIRELESS is not set +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +# CONFIG_STANDALONE is not set +# CONFIG_FW_LOADER is not set +CONFIG_MTD=y +CONFIG_MTD_CFI=y +CONFIG_MTD_JEDECPROBE=y +CONFIG_MTD_CFI_INTELEXT=y +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_MTD_CFI_STAA=y +CONFIG_MTD_PHYSMAP_OF=y +CONFIG_MTD_UBI=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y +# CONFIG_INPUT_MOUSEDEV is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +CONFIG_LEGACY_PTY_COUNT=16 +CONFIG_SERIAL_XILINX_PS_UART=y +CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y +CONFIG_HW_RANDOM=y +# CONFIG_HWMON is not set +CONFIG_WATCHDOG=y +CONFIG_WATCHDOG_NOWAYOUT=y +CONFIG_SOFT_WATCHDOG=y +# CONFIG_VGA_CONSOLE is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT3_FS=y +CONFIG_FANOTIFY=y +CONFIG_VFAT_FS=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_NFS_FS=y +CONFIG_NFS_V4=y +CONFIG_NFS_SWAP=y +CONFIG_ROOT_NFS=y +CONFIG_SUNRPC_DEBUG=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ISO8859_1=y +CONFIG_PRINTK_TIME=y +CONFIG_DYNAMIC_DEBUG=y +CONFIG_DEBUG_INFO=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_LOCKUP_DETECTOR=y +# CONFIG_SCHED_DEBUG is not set +CONFIG_SCHEDSTATS=y +CONFIG_TIMER_STATS=y +CONFIG_DEBUG_RT_MUTEXES=y +CONFIG_PROVE_LOCKING=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_RCU_TRACE=y +CONFIG_FUNCTION_TRACER=y +# CONFIG_S32C1I_SELFTEST is not set +# CONFIG_CRYPTO_ECHAINIV is not set +CONFIG_CRYPTO_DEFLATE=y +CONFIG_CRYPTO_LZO=y +# CONFIG_CRYPTO_HW is not set diff --git a/arch/xtensa/configs/common_defconfig b/arch/xtensa/configs/common_defconfig index 721df1214bc3..4bcc76b02109 100644 --- a/arch/xtensa/configs/common_defconfig +++ b/arch/xtensa/configs/common_defconfig @@ -1,204 +1,15 @@ -# -# Automatically generated make config: don't edit -# Linux kernel version: 2.6.11-rc2 -# Tue Mar 1 16:36:53 2005 -# -# CONFIG_FRAME_POINTER is not set -CONFIG_XTENSA=y -# CONFIG_UID16 is not set -CONFIG_RWSEM_XCHGADD_ALGORITHM=y -CONFIG_HAVE_DEC_LOCK=y - -# -# Code maturity level options -# -CONFIG_EXPERIMENTAL=y -CONFIG_CLEAN_COMPILE=y -CONFIG_BROKEN_ON_SMP=y - -# -# General setup -# -CONFIG_LOCALVERSION="" -CONFIG_SWAP=y CONFIG_SYSVIPC=y -# CONFIG_POSIX_MQUEUE is not set CONFIG_BSD_PROCESS_ACCT=y -# CONFIG_BSD_PROCESS_ACCT_V3 is not set -CONFIG_SYSCTL=y -# CONFIG_AUDIT is not set CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_HOTPLUG is not set -CONFIG_KOBJECT_UEVENT=y -# CONFIG_IKCONFIG is not set -# CONFIG_EXPERT is not set -CONFIG_KALLSYMS=y -# CONFIG_KALLSYMS_ALL is not set -# CONFIG_KALLSYMS_EXTRA_PASS is not set -CONFIG_FUTEX=y -CONFIG_EPOLL=y -# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 -# CONFIG_TINY_SHMEM is not set - -# -# Loadable module support -# CONFIG_MODULES=y -# CONFIG_MODULE_UNLOAD is not set -CONFIG_OBSOLETE_MODPARM=y CONFIG_MODVERSIONS=y -# CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_KMOD=y - -# -# Processor type and features -# -CONFIG_XTENSA_ARCH_LINUX_BE=y -# CONFIG_XTENSA_ARCH_LINUX_LE is not set -# CONFIG_XTENSA_ARCH_LINUX_TEST is not set -# CONFIG_XTENSA_ARCH_S5 is not set -# CONFIG_XTENSA_CUSTOM is not set -CONFIG_MMU=y -# CONFIG_XTENSA_UNALIGNED_USER is not set -# CONFIG_PREEMPT is not set -# CONFIG_HIGHMEM is not set - -# -# Platform options -# -# CONFIG_XTENSA_PLATFORM_ISS is not set CONFIG_XTENSA_PLATFORM_XT2000=y -CONFIG_XTENSA_CALIBRATE_CCOUNT=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0,38400 ip=bootp root=nfs nfsroot=/opt/montavista/pro/devkit/xtensa/linux_be/target" - -# -# Bus options -# -CONFIG_PCI=y -# CONFIG_PCI_LEGACY_PROC is not set -# CONFIG_PCI_NAMES is not set - -# -# PCCARD (PCMCIA/CardBus) support -# -# CONFIG_PCCARD is not set - -# -# PC-card bridges -# - -# -# PCI Hotplug Support -# -# CONFIG_HOTPLUG_PCI is not set - -# -# Exectuable file formats -# -CONFIG_KCORE_ELF=y -CONFIG_BINFMT_ELF=y +CONFIG_CMDLINE="console=ttyS0,38400 ip=bootp root=nfs nfsroot=/opt/montavista/pro/devkit/xtensa/linux_be/target memmap=128M@0" CONFIG_BINFMT_MISC=y - -# -# Device Drivers -# - -# -# Generic Driver Options -# -CONFIG_STANDALONE=y -CONFIG_PREVENT_FIRMWARE_BUILD=y -# CONFIG_FW_LOADER is not set -# CONFIG_DEBUG_DRIVER is not set - -# -# Memory Technology Devices (MTD) -# -# CONFIG_MTD is not set - -# -# Parallel port support -# -# CONFIG_PARPORT is not set - -# -# Plug and Play support -# - -# -# Block devices -# -# CONFIG_BLK_DEV_FD is not set -# CONFIG_BLK_CPQ_DA is not set -# CONFIG_BLK_CPQ_CISS_DA is not set -# CONFIG_BLK_DEV_DAC960 is not set -# CONFIG_BLK_DEV_UMEM is not set -# CONFIG_BLK_DEV_COW_COMMON is not set -# CONFIG_BLK_DEV_LOOP is not set -# CONFIG_BLK_DEV_NBD is not set -# CONFIG_BLK_DEV_SX8 is not set -# CONFIG_BLK_DEV_RAM is not set -CONFIG_BLK_DEV_RAM_COUNT=16 -CONFIG_INITRAMFS_SOURCE="" -# CONFIG_CDROM_PKTCDVD is not set - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_AS=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y -# CONFIG_ATA_OVER_ETH is not set - -# -# ATA/ATAPI/MFM/RLL support -# -# CONFIG_IDE is not set - -# -# SCSI device support -# -# CONFIG_SCSI is not set - -# -# Multi-device support (RAID and LVM) -# -# CONFIG_MD is not set - -# -# Fusion MPT device support -# - -# -# IEEE 1394 (FireWire) support -# -# CONFIG_IEEE1394 is not set - -# -# I2O device support -# -# CONFIG_I2O is not set - -# -# Networking support -# CONFIG_NET=y - -# -# Networking options -# -# CONFIG_PACKET is not set -# CONFIG_NETLINK_DEV is not set CONFIG_UNIX=y -# CONFIG_NET_KEY is not set CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y @@ -209,47 +20,10 @@ CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y -# CONFIG_NET_IPIP is not set -# CONFIG_NET_IPGRE is not set -# CONFIG_IP_MROUTE is not set -# CONFIG_ARPD is not set -# CONFIG_SYN_COOKIES is not set -# CONFIG_INET_AH is not set -# CONFIG_INET_ESP is not set -# CONFIG_INET_IPCOMP is not set -# CONFIG_INET_TUNNEL is not set -# CONFIG_IP_TCPDIAG is not set -# CONFIG_IP_TCPDIAG_IPV6 is not set # CONFIG_IPV6 is not set -# CONFIG_NETFILTER is not set - -# -# SCTP Configuration (EXPERIMENTAL) -# -# CONFIG_IP_SCTP is not set -# CONFIG_ATM is not set -# CONFIG_BRIDGE is not set -# CONFIG_VLAN_8021Q is not set -# CONFIG_DECNET is not set -# CONFIG_LLC2 is not set -# CONFIG_IPX is not set -# CONFIG_ATALK is not set -# CONFIG_X25 is not set -# CONFIG_LAPB is not set -# CONFIG_NET_DIVERT is not set -# CONFIG_ECONET is not set -# CONFIG_WAN_ROUTER is not set - -# -# QoS and/or fair queueing -# CONFIG_NET_SCHED=y -CONFIG_NET_SCH_CLK_JIFFIES=y -# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set -# CONFIG_NET_SCH_CLK_CPU is not set CONFIG_NET_SCH_CBQ=m CONFIG_NET_SCH_HTB=m -# CONFIG_NET_SCH_HFSC is not set CONFIG_NET_SCH_PRIO=m CONFIG_NET_SCH_RED=m CONFIG_NET_SCH_SFQ=m @@ -257,399 +31,24 @@ CONFIG_NET_SCH_TEQL=m CONFIG_NET_SCH_TBF=m CONFIG_NET_SCH_GRED=m CONFIG_NET_SCH_DSMARK=m -# CONFIG_NET_SCH_NETEM is not set -CONFIG_NET_SCH_INGRESS=m -CONFIG_NET_QOS=y -CONFIG_NET_ESTIMATOR=y -CONFIG_NET_CLS=y CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_CLS_ROUTE4=m -CONFIG_NET_CLS_ROUTE=y CONFIG_NET_CLS_FW=m CONFIG_NET_CLS_U32=m -# CONFIG_CLS_U32_PERF is not set -# CONFIG_NET_CLS_IND is not set CONFIG_NET_CLS_RSVP=m CONFIG_NET_CLS_RSVP6=m -# CONFIG_NET_CLS_ACT is not set -CONFIG_NET_CLS_POLICE=y - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -# CONFIG_NETPOLL is not set -# CONFIG_NET_POLL_CONTROLLER is not set -# CONFIG_HAMRADIO is not set -# CONFIG_IRDA is not set -# CONFIG_BT is not set CONFIG_NETDEVICES=y CONFIG_DUMMY=y -# CONFIG_BONDING is not set -# CONFIG_EQUALIZER is not set -# CONFIG_TUN is not set - -# -# ARCnet devices -# -# CONFIG_ARCNET is not set - -# -# Ethernet (10 or 100Mbit) -# -CONFIG_NET_ETHERNET=y -# CONFIG_MII is not set -CONFIG_XT2000_SONIC=y -# CONFIG_HAPPYMEAL is not set -# CONFIG_SUNGEM is not set # CONFIG_NET_VENDOR_3COM is not set - -# -# Tulip family network device support -# -# CONFIG_NET_TULIP is not set -# CONFIG_HP100 is not set -# CONFIG_NET_PCI is not set - -# -# Ethernet (1000 Mbit) -# -# CONFIG_ACENIC is not set -# CONFIG_DL2K is not set -# CONFIG_E1000 is not set -# CONFIG_NS83820 is not set -# CONFIG_HAMACHI is not set -# CONFIG_YELLOWFIN is not set -# CONFIG_R8169 is not set -# CONFIG_SK98LIN is not set -# CONFIG_TIGON3 is not set - -# -# Ethernet (10000 Mbit) -# -# CONFIG_IXGB is not set -# CONFIG_S2IO is not set - -# -# Wireless LAN (non-hamradio) -# -CONFIG_NET_RADIO=y - -# -# Obsolete Wireless cards support (pre-802.11) -# -CONFIG_STRIP=m - -# -# Wireless 802.11b ISA/PCI cards support -# -CONFIG_HERMES=m -# CONFIG_PLX_HERMES is not set -# CONFIG_TMD_HERMES is not set -# CONFIG_PCI_HERMES is not set -# CONFIG_ATMEL is not set - -# -# Prism GT/Duette 802.11(a/b/g) PCI/Cardbus support -# -# CONFIG_PRISM54 is not set -CONFIG_NET_WIRELESS=y - -# -# Wan interfaces -# -# CONFIG_WAN is not set -# CONFIG_FDDI is not set -# CONFIG_HIPPI is not set -# CONFIG_PPP is not set -# CONFIG_SLIP is not set -# CONFIG_SHAPER is not set -# CONFIG_NETCONSOLE is not set - -# -# ISDN subsystem -# -# CONFIG_ISDN is not set - -# -# Telephony Support -# -# CONFIG_PHONE is not set - -# -# Input device support -# -CONFIG_INPUT=y - -# -# Userland interfaces -# -CONFIG_INPUT_MOUSEDEV=y # CONFIG_INPUT_MOUSEDEV_PSAUX is not set -CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 -# CONFIG_INPUT_JOYDEV is not set -# CONFIG_INPUT_TSDEV is not set -# CONFIG_INPUT_EVDEV is not set -# CONFIG_INPUT_EVBUG is not set - -# -# Input I/O drivers -# -# CONFIG_GAMEPORT is not set -CONFIG_SOUND_GAMEPORT=y -CONFIG_SERIO=y -# CONFIG_SERIO_I8042 is not set -# CONFIG_SERIO_SERPORT is not set -# CONFIG_SERIO_CT82C710 is not set -# CONFIG_SERIO_PCIPS2 is not set -# CONFIG_SERIO_RAW is not set - -# -# Input Device Drivers -# # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set -# CONFIG_INPUT_JOYSTICK is not set -# CONFIG_INPUT_TOUCHSCREEN is not set -# CONFIG_INPUT_MISC is not set - -# -# Character devices -# -CONFIG_VT=y -CONFIG_VT_CONSOLE=y -CONFIG_HW_CONSOLE=y -# CONFIG_SERIAL_NONSTANDARD is not set - -# -# Serial drivers -# +# CONFIG_SERIO_SERPORT is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_SERIAL_8250_NR_UARTS=4 -# CONFIG_SERIAL_8250_EXTENDED is not set - -# -# Non-8250 serial port support -# -CONFIG_SERIAL_CORE=y -CONFIG_SERIAL_CORE_CONSOLE=y -CONFIG_UNIX98_PTYS=y -CONFIG_LEGACY_PTYS=y -CONFIG_LEGACY_PTY_COUNT=256 - -# -# IPMI -# -# CONFIG_IPMI_HANDLER is not set - -# -# Watchdog Cards -# -# CONFIG_WATCHDOG is not set -# CONFIG_RTC is not set -# CONFIG_GEN_RTC is not set -# CONFIG_DTLK is not set -# CONFIG_R3964 is not set -# CONFIG_APPLICOM is not set - -# -# Ftape, the floppy tape device driver -# -# CONFIG_DRM is not set -# CONFIG_RAW_DRIVER is not set - -# -# I2C support -# -# CONFIG_I2C is not set - -# -# Dallas's 1-wire bus -# -# CONFIG_W1 is not set - -# -# Misc devices -# - -# -# Multimedia devices -# -# CONFIG_VIDEO_DEV is not set - -# -# Digital Video Broadcasting Devices -# -# CONFIG_DVB is not set - -# -# Graphics support -# -# CONFIG_FB is not set - -# -# Console display driver support -# # CONFIG_VGA_CONSOLE is not set -CONFIG_DUMMY_CONSOLE=y -# CONFIG_BACKLIGHT_LCD_SUPPORT is not set - -# -# Sound -# -# CONFIG_SOUND is not set - -# -# USB support -# -# CONFIG_USB is not set -CONFIG_USB_ARCH_HAS_HCD=y -CONFIG_USB_ARCH_HAS_OHCI=y - -# -# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information -# - -# -# USB Gadget Support -# -# CONFIG_USB_GADGET is not set - -# -# MMC/SD Card support -# -# CONFIG_MMC is not set - -# -# InfiniBand support -# -# CONFIG_INFINIBAND is not set - -# -# File systems -# -# CONFIG_EXT2_FS is not set -# CONFIG_EXT3_FS is not set -# CONFIG_JBD is not set -# CONFIG_REISERFS_FS is not set -# CONFIG_JFS_FS is not set -# CONFIG_XFS_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_ROMFS_FS is not set -# CONFIG_QUOTA is not set -CONFIG_DNOTIFY=y -# CONFIG_AUTOFS_FS is not set -# CONFIG_AUTOFS4_FS is not set - -# -# CD-ROM/DVD Filesystems -# -# CONFIG_ISO9660_FS is not set -# CONFIG_UDF_FS is not set - -# -# DOS/FAT/NT Filesystems -# -# CONFIG_MSDOS_FS is not set -# CONFIG_VFAT_FS is not set -# CONFIG_NTFS_FS is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y -# CONFIG_PROC_KCORE is not set -CONFIG_SYSFS=y -CONFIG_DEVFS_FS=y -# CONFIG_DEVFS_MOUNT is not set -# CONFIG_DEVFS_DEBUG is not set -# CONFIG_DEVPTS_FS_XATTR is not set -# CONFIG_TMPFS is not set -# CONFIG_HUGETLB_PAGE is not set -CONFIG_RAMFS=y - -# -# Miscellaneous filesystems -# -# CONFIG_ADFS_FS is not set -# CONFIG_AFFS_FS is not set -# CONFIG_HFS_FS is not set -# CONFIG_HFSPLUS_FS is not set -# CONFIG_BEFS_FS is not set -# CONFIG_BFS_FS is not set -# CONFIG_EFS_FS is not set -# CONFIG_CRAMFS is not set -# CONFIG_VXFS_FS is not set -# CONFIG_HPFS_FS is not set -# CONFIG_QNX4FS_FS is not set -# CONFIG_SYSV_FS is not set -# CONFIG_UFS_FS is not set - -# -# Network File Systems -# CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -# CONFIG_NFS_V4 is not set -# CONFIG_NFS_DIRECTIO is not set -# CONFIG_NFSD is not set CONFIG_ROOT_NFS=y -CONFIG_LOCKD=y -CONFIG_LOCKD_V4=y -# CONFIG_EXPORTFS is not set -CONFIG_SUNRPC=y -# CONFIG_RPCSEC_GSS_KRB5 is not set -# CONFIG_RPCSEC_GSS_SPKM3 is not set -# CONFIG_SMB_FS is not set -# CONFIG_CIFS is not set -# CONFIG_NCP_FS is not set -# CONFIG_CODA_FS is not set -# CONFIG_AFS_FS is not set - -# -# Partition Types -# -# CONFIG_PARTITION_ADVANCED is not set -CONFIG_MSDOS_PARTITION=y - -# -# Native Language Support -# -# CONFIG_NLS is not set - -# -# Kernel hacking -# -CONFIG_DEBUG_KERNEL=y -# CONFIG_DEBUG_STACKOVERFLOW is not set -# CONFIG_DEBUG_SLAB is not set +# CONFIG_FRAME_POINTER is not set CONFIG_MAGIC_SYSRQ=y -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_PAGEALLOC is not set -# CONFIG_DEBUG_INFO is not set -# CONFIG_DEBUG_SPINLOCK_SLEEP is not set -# CONFIG_KGDB is not set - -# -# Security options -# -# CONFIG_KEYS is not set -# CONFIG_SECURITY is not set - -# -# Cryptographic options -# -# CONFIG_CRYPTO is not set - -# -# Hardware crypto devices -# - -# -# Library routines -# -# CONFIG_CRC_CCITT is not set -# CONFIG_CRC32 is not set -# CONFIG_LIBCRC32C is not set +CONFIG_DEBUG_KERNEL=y diff --git a/arch/xtensa/configs/generic_kc705_defconfig b/arch/xtensa/configs/generic_kc705_defconfig index d9444f01f4da..744adeaf2945 100644 --- a/arch/xtensa/configs/generic_kc705_defconfig +++ b/arch/xtensa/configs/generic_kc705_defconfig @@ -32,7 +32,7 @@ CONFIG_HIGHMEM=y # CONFIG_PCI is not set CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="earlycon=uart8250,mmio32,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug" +CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0" CONFIG_USE_OF=y CONFIG_BUILTIN_DTB="kc705" # CONFIG_COMPACTION is not set diff --git a/arch/xtensa/configs/iss_defconfig b/arch/xtensa/configs/iss_defconfig index 44c6764d9146..4bb5b76d9524 100644 --- a/arch/xtensa/configs/iss_defconfig +++ b/arch/xtensa/configs/iss_defconfig @@ -1,758 +1,34 @@ -# -# Automatically generated make config: don't edit -# Linux kernel version: 2.6.34-rc6 -# Tue Aug 3 00:10:54 2010 -# -# CONFIG_FRAME_POINTER is not set -CONFIG_ZONE_DMA=y -CONFIG_XTENSA=y -CONFIG_RWSEM_XCHGADD_ALGORITHM=y -CONFIG_GENERIC_FIND_NEXT_BIT=y -CONFIG_GENERIC_HWEIGHT=y -# CONFIG_ARCH_HAS_ILOG2_U32 is not set -# CONFIG_ARCH_HAS_ILOG2_U64 is not set -CONFIG_NO_IOPORT_MAP=y -CONFIG_HZ=100 -CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" -CONFIG_CONSTRUCTORS=y - -# -# General setup -# -CONFIG_EXPERIMENTAL=y -CONFIG_BROKEN_ON_SMP=y -CONFIG_INIT_ENV_ARG_LIMIT=32 -CONFIG_LOCALVERSION="" -CONFIG_LOCALVERSION_AUTO=y -CONFIG_SWAP=y CONFIG_SYSVIPC=y -CONFIG_SYSVIPC_SYSCTL=y -# CONFIG_POSIX_MQUEUE is not set -# CONFIG_BSD_PROCESS_ACCT is not set -# CONFIG_TASKSTATS is not set -# CONFIG_AUDIT is not set - -# -# RCU Subsystem -# -CONFIG_TREE_RCU=y -# CONFIG_TREE_PREEMPT_RCU is not set -# CONFIG_TINY_RCU is not set -# CONFIG_RCU_TRACE is not set -CONFIG_RCU_FANOUT=32 -# CONFIG_RCU_FANOUT_EXACT is not set -# CONFIG_TREE_RCU_TRACE is not set -# CONFIG_IKCONFIG is not set CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_CGROUPS is not set -# CONFIG_SYSFS_DEPRECATED_V2 is not set -# CONFIG_RELAY is not set -# CONFIG_NAMESPACES is not set -# CONFIG_BLK_DEV_INITRD is not set -# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -CONFIG_SYSCTL=y -CONFIG_ANON_INODES=y CONFIG_EXPERT=y CONFIG_SYSCTL_SYSCALL=y -CONFIG_KALLSYMS=y -# CONFIG_KALLSYMS_ALL is not set -# CONFIG_KALLSYMS_EXTRA_PASS is not set -# CONFIG_HOTPLUG is not set -CONFIG_PRINTK=y -CONFIG_BUG=y -CONFIG_ELF_CORE=y -CONFIG_BASE_FULL=y -CONFIG_FUTEX=y -CONFIG_EPOLL=y -CONFIG_SIGNALFD=y -CONFIG_TIMERFD=y -CONFIG_EVENTFD=y -CONFIG_SHMEM=y -CONFIG_AIO=y - -# -# Kernel Performance Events And Counters -# -CONFIG_VM_EVENT_COUNTERS=y -CONFIG_SLUB_DEBUG=y -CONFIG_COMPAT_BRK=y -# CONFIG_SLAB is not set -CONFIG_SLUB=y -# CONFIG_SLOB is not set -# CONFIG_PROFILING is not set - -# -# GCOV-based kernel profiling -# -# CONFIG_SLOW_WORK is not set -# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set -CONFIG_SLABINFO=y -CONFIG_RT_MUTEXES=y -CONFIG_BASE_SMALL=0 -# CONFIG_MODULES is not set -CONFIG_BLOCK=y -CONFIG_LBDAF=y -CONFIG_BLK_DEV_BSG=y -# CONFIG_BLK_DEV_INTEGRITY is not set - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set -# CONFIG_DEFAULT_DEADLINE is not set -# CONFIG_DEFAULT_CFQ is not set -CONFIG_DEFAULT_NOOP=y -CONFIG_DEFAULT_IOSCHED="noop" -# CONFIG_INLINE_SPIN_TRYLOCK is not set -# CONFIG_INLINE_SPIN_TRYLOCK_BH is not set -# CONFIG_INLINE_SPIN_LOCK is not set -# CONFIG_INLINE_SPIN_LOCK_BH is not set -# CONFIG_INLINE_SPIN_LOCK_IRQ is not set -# CONFIG_INLINE_SPIN_LOCK_IRQSAVE is not set -# CONFIG_UNINLINE_SPIN_UNLOCK is not set -# CONFIG_INLINE_SPIN_UNLOCK_BH is not set -CONFIG_INLINE_SPIN_UNLOCK_IRQ=y -# CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE is not set -# CONFIG_INLINE_READ_TRYLOCK is not set -# CONFIG_INLINE_READ_LOCK is not set -# CONFIG_INLINE_READ_LOCK_BH is not set -# CONFIG_INLINE_READ_LOCK_IRQ is not set -# CONFIG_INLINE_READ_LOCK_IRQSAVE is not set -CONFIG_INLINE_READ_UNLOCK=y -# CONFIG_INLINE_READ_UNLOCK_BH is not set -CONFIG_INLINE_READ_UNLOCK_IRQ=y -# CONFIG_INLINE_READ_UNLOCK_IRQRESTORE is not set -# CONFIG_INLINE_WRITE_TRYLOCK is not set -# CONFIG_INLINE_WRITE_LOCK is not set -# CONFIG_INLINE_WRITE_LOCK_BH is not set -# CONFIG_INLINE_WRITE_LOCK_IRQ is not set -# CONFIG_INLINE_WRITE_LOCK_IRQSAVE is not set -CONFIG_INLINE_WRITE_UNLOCK=y -# CONFIG_INLINE_WRITE_UNLOCK_BH is not set -CONFIG_INLINE_WRITE_UNLOCK_IRQ=y -# CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE is not set -# CONFIG_MUTEX_SPIN_ON_OWNER is not set -# CONFIG_FREEZER is not set -CONFIG_MMU=y -# CONFIG_VARIANT_IRQ_SWITCH is not set - -# -# Processor type and features -# -CONFIG_XTENSA_VARIANT_FSF=y -# CONFIG_XTENSA_VARIANT_DC232B is not set -# CONFIG_XTENSA_UNALIGNED_USER is not set -# CONFIG_PREEMPT is not set -CONFIG_XTENSA_CALIBRATE_CCOUNT=y -CONFIG_SERIAL_CONSOLE=y -CONFIG_XTENSA_ISS_NETWORK=y - -# -# Bus options -# # CONFIG_PCI is not set -# CONFIG_ARCH_SUPPORTS_MSI is not set - -# -# Platform options -# -CONFIG_XTENSA_PLATFORM_ISS=y -# CONFIG_XTENSA_PLATFORM_XT2000 is not set -# CONFIG_GENERIC_CALIBRATE_DELAY is not set CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0,38400 eth0=tuntap,,tap0 ip=192.168.168.5:192.168.168.1 root=nfs nfsroot=192.168.168.1:/opt/montavista/pro/devkit/xtensa/linux_be/target" -CONFIG_SELECT_MEMORY_MODEL=y -CONFIG_FLATMEM_MANUAL=y -# CONFIG_DISCONTIGMEM_MANUAL is not set -# CONFIG_SPARSEMEM_MANUAL is not set -CONFIG_FLATMEM=y -CONFIG_FLAT_NODE_MEM_MAP=y -CONFIG_SPLIT_PTLOCK_CPUS=4 -# CONFIG_PHYS_ADDR_T_64BIT is not set -CONFIG_ZONE_DMA_FLAG=1 -CONFIG_BOUNCE=y -CONFIG_VIRT_TO_BUS=y -# CONFIG_KSM is not set -CONFIG_DEFAULT_MMAP_MIN_ADDR=4096 - -# -# Executable file formats -# -CONFIG_KCORE_ELF=y -CONFIG_BINFMT_ELF=y +CONFIG_CMDLINE="console=ttyS0,38400 eth0=tuntap,,tap0 ip=192.168.168.5:192.168.168.1 root=nfs nfsroot=192.168.168.1:/opt/montavista/pro/devkit/xtensa/linux_be/target memmap=128M@0" # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -# CONFIG_HAVE_AOUT is not set -# CONFIG_BINFMT_MISC is not set CONFIG_NET=y - -# -# Networking options -# CONFIG_PACKET=y CONFIG_UNIX=y -CONFIG_XFRM=y -# CONFIG_XFRM_USER is not set -# CONFIG_XFRM_SUB_POLICY is not set -# CONFIG_XFRM_MIGRATE is not set -# CONFIG_XFRM_STATISTICS is not set -# CONFIG_NET_KEY is not set CONFIG_INET=y -# CONFIG_IP_MULTICAST is not set -# CONFIG_IP_ADVANCED_ROUTER is not set -CONFIG_IP_FIB_HASH=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y -# CONFIG_NET_IPIP is not set -# CONFIG_NET_IPGRE is not set -# CONFIG_ARPD is not set -# CONFIG_SYN_COOKIES is not set -# CONFIG_INET_AH is not set -# CONFIG_INET_ESP is not set -# CONFIG_INET_IPCOMP is not set -# CONFIG_INET_XFRM_TUNNEL is not set -# CONFIG_INET_TUNNEL is not set -CONFIG_INET_XFRM_MODE_TRANSPORT=y -CONFIG_INET_XFRM_MODE_TUNNEL=y -CONFIG_INET_XFRM_MODE_BEET=y -CONFIG_INET_LRO=y -CONFIG_INET_DIAG=y -CONFIG_INET_TCP_DIAG=y -# CONFIG_TCP_CONG_ADVANCED is not set -CONFIG_TCP_CONG_CUBIC=y -CONFIG_DEFAULT_TCP_CONG="cubic" -# CONFIG_TCP_MD5SIG is not set # CONFIG_IPV6 is not set -# CONFIG_NETWORK_SECMARK is not set -# CONFIG_NETFILTER is not set -# CONFIG_IP_DCCP is not set -# CONFIG_IP_SCTP is not set -# CONFIG_RDS is not set -# CONFIG_TIPC is not set -# CONFIG_ATM is not set -# CONFIG_BRIDGE is not set -# CONFIG_NET_DSA is not set -# CONFIG_VLAN_8021Q is not set -# CONFIG_DECNET is not set -# CONFIG_LLC2 is not set -# CONFIG_IPX is not set -# CONFIG_ATALK is not set -# CONFIG_X25 is not set -# CONFIG_LAPB is not set -# CONFIG_ECONET is not set -# CONFIG_WAN_ROUTER is not set -# CONFIG_PHONET is not set -# CONFIG_IEEE802154 is not set -# CONFIG_NET_SCHED is not set -# CONFIG_DCB is not set - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -# CONFIG_HAMRADIO is not set -# CONFIG_CAN is not set -# CONFIG_IRDA is not set -# CONFIG_BT is not set -# CONFIG_AF_RXRPC is not set -CONFIG_WIRELESS=y -# CONFIG_CFG80211 is not set -# CONFIG_LIB80211 is not set - -# -# CFG80211 needs to be enabled for MAC80211 -# -# CONFIG_WIMAX is not set -# CONFIG_RFKILL is not set -# CONFIG_NET_9P is not set - -# -# Device Drivers -# - -# -# Generic Driver Options -# # CONFIG_STANDALONE is not set -CONFIG_PREVENT_FIRMWARE_BUILD=y -# CONFIG_DEBUG_DRIVER is not set -# CONFIG_DEBUG_DEVRES is not set -# CONFIG_SYS_HYPERVISOR is not set -# CONFIG_CONNECTOR is not set -# CONFIG_MTD is not set -# CONFIG_PARPORT is not set -CONFIG_BLK_DEV=y -# CONFIG_BLK_DEV_COW_COMMON is not set -# CONFIG_BLK_DEV_LOOP is not set - -# -# DRBD disabled because PROC_FS, INET or CONNECTOR not selected -# -# CONFIG_BLK_DEV_NBD is not set -# CONFIG_BLK_DEV_RAM is not set -# CONFIG_CDROM_PKTCDVD is not set -# CONFIG_ATA_OVER_ETH is not set -# CONFIG_BLK_DEV_HD is not set -CONFIG_MISC_DEVICES=y -# CONFIG_ENCLOSURE_SERVICES is not set -# CONFIG_C2PORT is not set - -# -# EEPROM support -# -# CONFIG_EEPROM_93CX6 is not set -# CONFIG_HAVE_IDE is not set -# CONFIG_IDE is not set - -# -# SCSI device support -# -CONFIG_SCSI_MOD=y -# CONFIG_RAID_ATTRS is not set -# CONFIG_SCSI is not set -# CONFIG_SCSI_DMA is not set -# CONFIG_SCSI_NETLINK is not set -# CONFIG_ATA is not set -# CONFIG_MD is not set -# CONFIG_NETDEVICES is not set -# CONFIG_ISDN is not set -# CONFIG_PHONE is not set - -# -# Input device support -# -CONFIG_INPUT=y -# CONFIG_INPUT_FF_MEMLESS is not set -# CONFIG_INPUT_POLLDEV is not set -# CONFIG_INPUT_SPARSEKMAP is not set - -# -# Userland interfaces -# # CONFIG_INPUT_MOUSEDEV is not set -# CONFIG_INPUT_JOYDEV is not set -# CONFIG_INPUT_EVDEV is not set -# CONFIG_INPUT_EVBUG is not set - -# -# Input Device Drivers -# # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set -# CONFIG_INPUT_JOYSTICK is not set -# CONFIG_INPUT_TABLET is not set -# CONFIG_INPUT_TOUCHSCREEN is not set -# CONFIG_INPUT_MISC is not set - -# -# Hardware I/O ports -# # CONFIG_SERIO is not set -# CONFIG_GAMEPORT is not set - -# -# Character devices -# -CONFIG_VT=y -CONFIG_CONSOLE_TRANSLATIONS=y -CONFIG_VT_CONSOLE=y -CONFIG_HW_CONSOLE=y -# CONFIG_VT_HW_CONSOLE_BINDING is not set -CONFIG_DEVKMEM=y -# CONFIG_SERIAL_NONSTANDARD is not set - -# -# Serial drivers -# -# CONFIG_SERIAL_8250 is not set - -# -# Non-8250 serial port support -# -# CONFIG_SERIAL_TIMBERDALE is not set -CONFIG_UNIX98_PTYS=y -# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set -CONFIG_LEGACY_PTYS=y -CONFIG_LEGACY_PTY_COUNT=256 -# CONFIG_IPMI_HANDLER is not set -CONFIG_HW_RANDOM=y -# CONFIG_HW_RANDOM_TIMERIOMEM is not set -# CONFIG_RTC is not set -# CONFIG_GEN_RTC is not set -# CONFIG_R3964 is not set -# CONFIG_RAW_DRIVER is not set -# CONFIG_TCG_TPM is not set -# CONFIG_I2C is not set -# CONFIG_SPI is not set - -# -# PPS support -# -# CONFIG_PPS is not set -# CONFIG_W1 is not set -# CONFIG_POWER_SUPPLY is not set -CONFIG_HWMON=y -# CONFIG_HWMON_VID is not set -# CONFIG_HWMON_DEBUG_CHIP is not set - -# -# Native drivers -# -# CONFIG_SENSORS_F71805F is not set -# CONFIG_SENSORS_F71882FG is not set -# CONFIG_SENSORS_IT87 is not set -# CONFIG_SENSORS_PC87360 is not set -# CONFIG_SENSORS_PC87427 is not set -# CONFIG_SENSORS_SHT15 is not set -# CONFIG_SENSORS_SMSC47M1 is not set -# CONFIG_SENSORS_SMSC47B397 is not set -# CONFIG_SENSORS_VT1211 is not set -# CONFIG_SENSORS_W83627HF is not set -# CONFIG_SENSORS_W83627EHF is not set -# CONFIG_THERMAL is not set CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y - -# -# Watchdog Device Drivers -# CONFIG_SOFT_WATCHDOG=y -CONFIG_SSB_POSSIBLE=y - -# -# Sonics Silicon Backplane -# -# CONFIG_SSB is not set - -# -# Multifunction device drivers -# -# CONFIG_MFD_CORE is not set -# CONFIG_MFD_SM501 is not set -# CONFIG_HTC_PASIC3 is not set -# CONFIG_MFD_TMIO is not set -# CONFIG_REGULATOR is not set -# CONFIG_MEDIA_SUPPORT is not set - -# -# Graphics support -# -# CONFIG_VGASTATE is not set -# CONFIG_VIDEO_OUTPUT_CONTROL is not set -# CONFIG_FB is not set -# CONFIG_BACKLIGHT_LCD_SUPPORT is not set - -# -# Display device support -# -# CONFIG_DISPLAY_SUPPORT is not set - -# -# Console display driver support -# # CONFIG_VGA_CONSOLE is not set -CONFIG_DUMMY_CONSOLE=y -# CONFIG_SOUND is not set -CONFIG_HID_SUPPORT=y -CONFIG_HID=y -# CONFIG_HIDRAW is not set -# CONFIG_HID_PID is not set - -# -# Special HID drivers -# -CONFIG_USB_SUPPORT=y -# CONFIG_USB_ARCH_HAS_HCD is not set -# CONFIG_USB_ARCH_HAS_OHCI is not set -# CONFIG_USB_ARCH_HAS_EHCI is not set -# CONFIG_USB_OTG_WHITELIST is not set -# CONFIG_USB_OTG_BLACKLIST_HUB is not set - -# -# Enable Host or Gadget support to see Inventra options -# - -# -# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may -# -# CONFIG_USB_GADGET is not set - -# -# OTG and related infrastructure -# -# CONFIG_MMC is not set -# CONFIG_MEMSTICK is not set -# CONFIG_NEW_LEDS is not set -# CONFIG_ACCESSIBILITY is not set -# CONFIG_RTC_CLASS is not set -# CONFIG_DMADEVICES is not set -# CONFIG_AUXDISPLAY is not set -# CONFIG_UIO is not set - -# -# TI VLYNQ -# -# CONFIG_STAGING is not set - -# -# File systems -# -# CONFIG_EXT2_FS is not set -# CONFIG_EXT3_FS is not set -# CONFIG_EXT4_FS is not set -# CONFIG_REISERFS_FS is not set -# CONFIG_JFS_FS is not set -# CONFIG_FS_POSIX_ACL is not set -# CONFIG_XFS_FS is not set -# CONFIG_GFS2_FS is not set -# CONFIG_OCFS2_FS is not set -# CONFIG_BTRFS_FS is not set -# CONFIG_NILFS2_FS is not set -CONFIG_FILE_LOCKING=y -CONFIG_FSNOTIFY=y # CONFIG_DNOTIFY is not set -# CONFIG_INOTIFY is not set -CONFIG_INOTIFY_USER=y -# CONFIG_QUOTA is not set -# CONFIG_AUTOFS_FS is not set -# CONFIG_AUTOFS4_FS is not set -# CONFIG_FUSE_FS is not set - -# -# Caches -# -# CONFIG_FSCACHE is not set - -# -# CD-ROM/DVD Filesystems -# -# CONFIG_ISO9660_FS is not set -# CONFIG_UDF_FS is not set - -# -# DOS/FAT/NT Filesystems -# -# CONFIG_MSDOS_FS is not set -# CONFIG_VFAT_FS is not set -# CONFIG_NTFS_FS is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y CONFIG_PROC_KCORE=y -CONFIG_PROC_SYSCTL=y -CONFIG_PROC_PAGE_MONITOR=y -CONFIG_SYSFS=y CONFIG_TMPFS=y -# CONFIG_TMPFS_POSIX_ACL is not set -# CONFIG_HUGETLB_PAGE is not set -# CONFIG_CONFIGFS_FS is not set -CONFIG_MISC_FILESYSTEMS=y -# CONFIG_ADFS_FS is not set -# CONFIG_AFFS_FS is not set -# CONFIG_HFS_FS is not set -# CONFIG_HFSPLUS_FS is not set -# CONFIG_BEFS_FS is not set -# CONFIG_BFS_FS is not set -# CONFIG_EFS_FS is not set -# CONFIG_LOGFS is not set -# CONFIG_CRAMFS is not set -# CONFIG_SQUASHFS is not set -# CONFIG_VXFS_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_OMFS_FS is not set -# CONFIG_HPFS_FS is not set -# CONFIG_QNX4FS_FS is not set -# CONFIG_ROMFS_FS is not set -# CONFIG_SYSV_FS is not set -# CONFIG_UFS_FS is not set -CONFIG_NETWORK_FILESYSTEMS=y -# CONFIG_NFS_FS is not set -# CONFIG_NFSD is not set -# CONFIG_SMB_FS is not set -# CONFIG_CEPH_FS is not set -# CONFIG_CIFS is not set -# CONFIG_NCP_FS is not set -# CONFIG_CODA_FS is not set -# CONFIG_AFS_FS is not set - -# -# Partition Types -# -# CONFIG_PARTITION_ADVANCED is not set -CONFIG_MSDOS_PARTITION=y -# CONFIG_NLS is not set -# CONFIG_DLM is not set - -# -# Kernel hacking -# -# CONFIG_PRINTK_TIME is not set -CONFIG_ENABLE_WARN_DEPRECATED=y -CONFIG_ENABLE_MUST_CHECK=y -CONFIG_FRAME_WARN=1024 -# CONFIG_MAGIC_SYSRQ is not set -# CONFIG_STRIP_ASM_SYMS is not set -# CONFIG_UNUSED_SYMBOLS is not set -# CONFIG_DEBUG_FS is not set -# CONFIG_HEADERS_CHECK is not set -CONFIG_DEBUG_KERNEL=y -# CONFIG_DEBUG_SHIRQ is not set -CONFIG_DETECT_SOFTLOCKUP=y -# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set -CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0 +# CONFIG_FRAME_POINTER is not set CONFIG_DETECT_HUNG_TASK=y -# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set -CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0 -CONFIG_SCHED_DEBUG=y -# CONFIG_SCHEDSTATS is not set -# CONFIG_TIMER_STATS is not set -# CONFIG_DEBUG_OBJECTS is not set -# CONFIG_SLUB_DEBUG_ON is not set -# CONFIG_SLUB_STATS is not set -# CONFIG_DEBUG_RT_MUTEXES is not set -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_MUTEXES is not set -# CONFIG_DEBUG_SPINLOCK_SLEEP is not set -# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set -# CONFIG_DEBUG_KOBJECT is not set -# CONFIG_DEBUG_INFO is not set -# CONFIG_DEBUG_VM is not set -# CONFIG_DEBUG_MEMORY_INIT is not set -# CONFIG_DEBUG_LIST is not set -# CONFIG_DEBUG_SG is not set -# CONFIG_DEBUG_NOTIFIERS is not set -# CONFIG_DEBUG_CREDENTIALS is not set -# CONFIG_RCU_TORTURE_TEST is not set -CONFIG_RCU_CPU_STALL_DETECTOR=y -# CONFIG_BACKTRACE_SELF_TEST is not set -# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set -# CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set -# CONFIG_FAULT_INJECTION is not set -# CONFIG_SYSCTL_SYSCALL_CHECK is not set -# CONFIG_PAGE_POISONING is not set -# CONFIG_SAMPLES is not set - -# -# Security options -# -# CONFIG_KEYS is not set -# CONFIG_SECURITY is not set -# CONFIG_SECURITYFS is not set -# CONFIG_DEFAULT_SECURITY_SELINUX is not set -# CONFIG_DEFAULT_SECURITY_SMACK is not set -# CONFIG_DEFAULT_SECURITY_TOMOYO is not set -CONFIG_DEFAULT_SECURITY_DAC=y -CONFIG_DEFAULT_SECURITY="" -CONFIG_CRYPTO=y - -# -# Crypto core or helper -# -# CONFIG_CRYPTO_FIPS is not set -CONFIG_CRYPTO_ALGAPI=y -CONFIG_CRYPTO_ALGAPI2=y -CONFIG_CRYPTO_RNG=y -CONFIG_CRYPTO_RNG2=y -# CONFIG_CRYPTO_MANAGER is not set -# CONFIG_CRYPTO_MANAGER2 is not set -# CONFIG_CRYPTO_GF128MUL is not set -# CONFIG_CRYPTO_NULL is not set -# CONFIG_CRYPTO_CRYPTD is not set -# CONFIG_CRYPTO_AUTHENC is not set - -# -# Authenticated Encryption with Associated Data -# -# CONFIG_CRYPTO_CCM is not set -# CONFIG_CRYPTO_GCM is not set -# CONFIG_CRYPTO_SEQIV is not set - -# -# Block modes -# -# CONFIG_CRYPTO_CBC is not set -# CONFIG_CRYPTO_CTR is not set -# CONFIG_CRYPTO_CTS is not set -# CONFIG_CRYPTO_ECB is not set -# CONFIG_CRYPTO_LRW is not set -# CONFIG_CRYPTO_PCBC is not set -# CONFIG_CRYPTO_XTS is not set - -# -# Hash modes -# -# CONFIG_CRYPTO_HMAC is not set -# CONFIG_CRYPTO_XCBC is not set -# CONFIG_CRYPTO_VMAC is not set - -# -# Digest -# -# CONFIG_CRYPTO_CRC32C is not set -# CONFIG_CRYPTO_GHASH is not set -# CONFIG_CRYPTO_MD4 is not set -# CONFIG_CRYPTO_MD5 is not set -# CONFIG_CRYPTO_MICHAEL_MIC is not set -# CONFIG_CRYPTO_RMD128 is not set -# CONFIG_CRYPTO_RMD160 is not set -# CONFIG_CRYPTO_RMD256 is not set -# CONFIG_CRYPTO_RMD320 is not set -# CONFIG_CRYPTO_SHA1 is not set -# CONFIG_CRYPTO_SHA256 is not set -# CONFIG_CRYPTO_SHA512 is not set -# CONFIG_CRYPTO_TGR192 is not set -# CONFIG_CRYPTO_WP512 is not set - -# -# Ciphers -# -CONFIG_CRYPTO_AES=y -# CONFIG_CRYPTO_ANUBIS is not set -# CONFIG_CRYPTO_ARC4 is not set -# CONFIG_CRYPTO_BLOWFISH is not set -# CONFIG_CRYPTO_CAMELLIA is not set -# CONFIG_CRYPTO_CAST5 is not set -# CONFIG_CRYPTO_CAST6 is not set -# CONFIG_CRYPTO_DES is not set -# CONFIG_CRYPTO_FCRYPT is not set -# CONFIG_CRYPTO_KHAZAD is not set -# CONFIG_CRYPTO_SALSA20 is not set -# CONFIG_CRYPTO_SEED is not set -# CONFIG_CRYPTO_SERPENT is not set -# CONFIG_CRYPTO_TEA is not set -# CONFIG_CRYPTO_TWOFISH is not set - -# -# Compression -# -# CONFIG_CRYPTO_DEFLATE is not set -# CONFIG_CRYPTO_ZLIB is not set -# CONFIG_CRYPTO_LZO is not set - -# -# Random Number Generation -# CONFIG_CRYPTO_ANSI_CPRNG=y -CONFIG_CRYPTO_HW=y -# CONFIG_BINARY_PRINTF is not set - -# -# Library routines -# -CONFIG_GENERIC_FIND_LAST_BIT=y -# CONFIG_CRC_CCITT is not set -# CONFIG_CRC16 is not set -# CONFIG_CRC_T10DIF is not set -# CONFIG_CRC_ITU_T is not set -# CONFIG_CRC32 is not set -# CONFIG_CRC7 is not set -# CONFIG_LIBCRC32C is not set -CONFIG_HAS_IOMEM=y -CONFIG_HAS_DMA=y -CONFIG_NLATTR=y -CONFIG_LD_NO_RELAX=y diff --git a/arch/xtensa/configs/nommu_kc705_defconfig b/arch/xtensa/configs/nommu_kc705_defconfig index 337d5ba2d285..78c2529d0459 100644 --- a/arch/xtensa/configs/nommu_kc705_defconfig +++ b/arch/xtensa/configs/nommu_kc705_defconfig @@ -37,7 +37,7 @@ CONFIG_PREEMPT=y # CONFIG_PCI is not set CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="earlycon=uart8250,mmio32,0x9d050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug" +CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0x9d050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=256M@0x60000000" CONFIG_USE_OF=y CONFIG_BUILTIN_DTB="kc705_nommu" CONFIG_DEFAULT_MEM_SIZE=0x10000000 diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig index 61f943c95619..14e3ca353ac8 100644 --- a/arch/xtensa/configs/smp_lx200_defconfig +++ b/arch/xtensa/configs/smp_lx200_defconfig @@ -36,7 +36,7 @@ CONFIG_HOTPLUG_CPU=y # CONFIG_PCI is not set CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="earlycon=uart8250,mmio32,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug" +CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=96M@0" CONFIG_USE_OF=y CONFIG_BUILTIN_DTB="lx200mx" # CONFIG_COMPACTION is not set diff --git a/arch/xtensa/include/asm/bitops.h b/arch/xtensa/include/asm/bitops.h index 3f44fa2a53e9..d3490189792b 100644 --- a/arch/xtensa/include/asm/bitops.h +++ b/arch/xtensa/include/asm/bitops.h @@ -48,7 +48,7 @@ static inline int ffz(unsigned long x) * __ffs: Find first bit set in word. Return 0 for bit 0 */ -static inline int __ffs(unsigned long x) +static inline unsigned long __ffs(unsigned long x) { return 31 - __cntlz(x & -x); } diff --git a/arch/xtensa/include/asm/cacheasm.h b/arch/xtensa/include/asm/cacheasm.h index e0f9e1109c83..2041abb10a23 100644 --- a/arch/xtensa/include/asm/cacheasm.h +++ b/arch/xtensa/include/asm/cacheasm.h @@ -69,26 +69,23 @@ .endm -#if XCHAL_DCACHE_LINE_LOCKABLE - .macro ___unlock_dcache_all ar at -#if XCHAL_DCACHE_SIZE +#if XCHAL_DCACHE_LINE_LOCKABLE && XCHAL_DCACHE_SIZE __loop_cache_all \ar \at diu XCHAL_DCACHE_SIZE XCHAL_DCACHE_LINEWIDTH #endif .endm -#endif - -#if XCHAL_ICACHE_LINE_LOCKABLE .macro ___unlock_icache_all ar at +#if XCHAL_ICACHE_LINE_LOCKABLE && XCHAL_ICACHE_SIZE __loop_cache_all \ar \at iiu XCHAL_ICACHE_SIZE XCHAL_ICACHE_LINEWIDTH +#endif .endm -#endif + .macro ___flush_invalidate_dcache_all ar at diff --git a/arch/xtensa/include/asm/fixmap.h b/arch/xtensa/include/asm/fixmap.h index 62b507deea9d..0d30403b6c95 100644 --- a/arch/xtensa/include/asm/fixmap.h +++ b/arch/xtensa/include/asm/fixmap.h @@ -59,6 +59,11 @@ enum fixed_addresses { */ static __always_inline unsigned long fix_to_virt(const unsigned int idx) { + /* Check if this memory layout is broken because fixmap overlaps page + * table. + */ + BUILD_BUG_ON(FIXADDR_START < + XCHAL_PAGE_TABLE_VADDR + XCHAL_PAGE_TABLE_SIZE); BUILD_BUG_ON(idx >= __end_of_fixed_addresses); return __fix_to_virt(idx); } diff --git a/arch/xtensa/include/asm/highmem.h b/arch/xtensa/include/asm/highmem.h index 01cef6b40829..6e070db1022e 100644 --- a/arch/xtensa/include/asm/highmem.h +++ b/arch/xtensa/include/asm/highmem.h @@ -68,6 +68,11 @@ void kunmap_high(struct page *page); static inline void *kmap(struct page *page) { + /* Check if this memory layout is broken because PKMAP overlaps + * page table. + */ + BUILD_BUG_ON(PKMAP_BASE < + XCHAL_PAGE_TABLE_VADDR + XCHAL_PAGE_TABLE_SIZE); BUG_ON(in_interrupt()); if (!PageHighMem(page)) return page_address(page); diff --git a/arch/xtensa/include/asm/initialize_mmu.h b/arch/xtensa/include/asm/initialize_mmu.h index 7a1e075969a3..42410f253597 100644 --- a/arch/xtensa/include/asm/initialize_mmu.h +++ b/arch/xtensa/include/asm/initialize_mmu.h @@ -77,13 +77,16 @@ .align 4 1: movi a2, 0x10000000 - movi a3, 0x18000000 - add a2, a2, a0 -9: bgeu a2, a3, 9b /* PC is out of the expected range */ + +#if CONFIG_KERNEL_LOAD_ADDRESS < 0x40000000ul +#define TEMP_MAPPING_VADDR 0x40000000 +#else +#define TEMP_MAPPING_VADDR 0x00000000 +#endif /* Step 1: invalidate mapping at 0x40000000..0x5FFFFFFF. */ - movi a2, 0x40000000 | XCHAL_SPANNING_WAY + movi a2, TEMP_MAPPING_VADDR | XCHAL_SPANNING_WAY idtlb a2 iitlb a2 isync @@ -95,14 +98,14 @@ srli a3, a0, 27 slli a3, a3, 27 addi a3, a3, CA_BYPASS - addi a7, a2, -1 + addi a7, a2, 5 - XCHAL_SPANNING_WAY wdtlb a3, a7 witlb a3, a7 isync slli a4, a0, 5 srli a4, a4, 5 - addi a5, a2, -6 + addi a5, a2, -XCHAL_SPANNING_WAY add a4, a4, a5 jx a4 @@ -116,35 +119,48 @@ add a5, a5, a4 bne a5, a2, 3b - /* Step 4: Setup MMU with the old V2 mappings. */ + /* Step 4: Setup MMU with the requested static mappings. */ + movi a6, 0x01000000 wsr a6, ITLBCFG wsr a6, DTLBCFG isync - movi a5, 0xd0000005 - movi a4, CA_WRITEBACK + movi a5, XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_TLB_WAY + movi a4, XCHAL_KSEG_PADDR + CA_WRITEBACK wdtlb a4, a5 witlb a4, a5 - movi a5, 0xd8000005 - movi a4, CA_BYPASS + movi a5, XCHAL_KSEG_BYPASS_VADDR + XCHAL_KSEG_TLB_WAY + movi a4, XCHAL_KSEG_PADDR + CA_BYPASS wdtlb a4, a5 witlb a4, a5 - movi a5, XCHAL_KIO_CACHED_VADDR + 6 +#ifdef CONFIG_XTENSA_KSEG_512M + movi a5, XCHAL_KSEG_CACHED_VADDR + 0x10000000 + XCHAL_KSEG_TLB_WAY + movi a4, XCHAL_KSEG_PADDR + 0x10000000 + CA_WRITEBACK + wdtlb a4, a5 + witlb a4, a5 + + movi a5, XCHAL_KSEG_BYPASS_VADDR + 0x10000000 + XCHAL_KSEG_TLB_WAY + movi a4, XCHAL_KSEG_PADDR + 0x10000000 + CA_BYPASS + wdtlb a4, a5 + witlb a4, a5 +#endif + + movi a5, XCHAL_KIO_CACHED_VADDR + XCHAL_KIO_TLB_WAY movi a4, XCHAL_KIO_DEFAULT_PADDR + CA_WRITEBACK wdtlb a4, a5 witlb a4, a5 - movi a5, XCHAL_KIO_BYPASS_VADDR + 6 + movi a5, XCHAL_KIO_BYPASS_VADDR + XCHAL_KIO_TLB_WAY movi a4, XCHAL_KIO_DEFAULT_PADDR + CA_BYPASS wdtlb a4, a5 witlb a4, a5 isync - /* Jump to self, using MMU v2 mappings. */ + /* Jump to self, using final mappings. */ movi a4, 1f jx a4 diff --git a/arch/xtensa/include/asm/kmem_layout.h b/arch/xtensa/include/asm/kmem_layout.h new file mode 100644 index 000000000000..561f8729bcde --- /dev/null +++ b/arch/xtensa/include/asm/kmem_layout.h @@ -0,0 +1,74 @@ +/* + * Kernel virtual memory layout definitions. + * + * This file is subject to the terms and conditions of the GNU General + * Public License. See the file "COPYING" in the main directory of + * this archive for more details. + * + * Copyright (C) 2016 Cadence Design Systems Inc. + */ + +#ifndef _XTENSA_KMEM_LAYOUT_H +#define _XTENSA_KMEM_LAYOUT_H + +#include <asm/types.h> + +#ifdef CONFIG_MMU + +/* + * Fixed TLB translations in the processor. + */ + +#define XCHAL_PAGE_TABLE_VADDR __XTENSA_UL_CONST(0x80000000) +#define XCHAL_PAGE_TABLE_SIZE __XTENSA_UL_CONST(0x00400000) + +#if defined(CONFIG_XTENSA_KSEG_MMU_V2) + +#define XCHAL_KSEG_CACHED_VADDR __XTENSA_UL_CONST(0xd0000000) +#define XCHAL_KSEG_BYPASS_VADDR __XTENSA_UL_CONST(0xd8000000) +#define XCHAL_KSEG_SIZE __XTENSA_UL_CONST(0x08000000) +#define XCHAL_KSEG_ALIGNMENT __XTENSA_UL_CONST(0x08000000) +#define XCHAL_KSEG_TLB_WAY 5 +#define XCHAL_KIO_TLB_WAY 6 + +#elif defined(CONFIG_XTENSA_KSEG_256M) + +#define XCHAL_KSEG_CACHED_VADDR __XTENSA_UL_CONST(0xb0000000) +#define XCHAL_KSEG_BYPASS_VADDR __XTENSA_UL_CONST(0xc0000000) +#define XCHAL_KSEG_SIZE __XTENSA_UL_CONST(0x10000000) +#define XCHAL_KSEG_ALIGNMENT __XTENSA_UL_CONST(0x10000000) +#define XCHAL_KSEG_TLB_WAY 6 +#define XCHAL_KIO_TLB_WAY 6 + +#elif defined(CONFIG_XTENSA_KSEG_512M) + +#define XCHAL_KSEG_CACHED_VADDR __XTENSA_UL_CONST(0xa0000000) +#define XCHAL_KSEG_BYPASS_VADDR __XTENSA_UL_CONST(0xc0000000) +#define XCHAL_KSEG_SIZE __XTENSA_UL_CONST(0x20000000) +#define XCHAL_KSEG_ALIGNMENT __XTENSA_UL_CONST(0x10000000) +#define XCHAL_KSEG_TLB_WAY 6 +#define XCHAL_KIO_TLB_WAY 6 + +#else +#error Unsupported KSEG configuration +#endif + +#ifdef CONFIG_KSEG_PADDR +#define XCHAL_KSEG_PADDR __XTENSA_UL_CONST(CONFIG_KSEG_PADDR) +#else +#define XCHAL_KSEG_PADDR __XTENSA_UL_CONST(0x00000000) +#endif + +#if XCHAL_KSEG_PADDR & (XCHAL_KSEG_ALIGNMENT - 1) +#error XCHAL_KSEG_PADDR is not properly aligned to XCHAL_KSEG_ALIGNMENT +#endif + +#else + +#define XCHAL_KSEG_CACHED_VADDR __XTENSA_UL_CONST(0xd0000000) +#define XCHAL_KSEG_BYPASS_VADDR __XTENSA_UL_CONST(0xd8000000) +#define XCHAL_KSEG_SIZE __XTENSA_UL_CONST(0x08000000) + +#endif + +#endif diff --git a/arch/xtensa/include/asm/page.h b/arch/xtensa/include/asm/page.h index ad38500471fa..976b1d70edbc 100644 --- a/arch/xtensa/include/asm/page.h +++ b/arch/xtensa/include/asm/page.h @@ -15,15 +15,7 @@ #include <asm/types.h> #include <asm/cache.h> #include <platform/hardware.h> - -/* - * Fixed TLB translations in the processor. - */ - -#define XCHAL_KSEG_CACHED_VADDR __XTENSA_UL_CONST(0xd0000000) -#define XCHAL_KSEG_BYPASS_VADDR __XTENSA_UL_CONST(0xd8000000) -#define XCHAL_KSEG_PADDR __XTENSA_UL_CONST(0x00000000) -#define XCHAL_KSEG_SIZE __XTENSA_UL_CONST(0x08000000) +#include <asm/kmem_layout.h> /* * PAGE_SHIFT determines the page size @@ -35,10 +27,13 @@ #ifdef CONFIG_MMU #define PAGE_OFFSET XCHAL_KSEG_CACHED_VADDR -#define MAX_MEM_PFN XCHAL_KSEG_SIZE +#define PHYS_OFFSET XCHAL_KSEG_PADDR +#define MAX_LOW_PFN (PHYS_PFN(XCHAL_KSEG_PADDR) + \ + PHYS_PFN(XCHAL_KSEG_SIZE)) #else -#define PAGE_OFFSET __XTENSA_UL_CONST(0) -#define MAX_MEM_PFN (PLATFORM_DEFAULT_MEM_START + PLATFORM_DEFAULT_MEM_SIZE) +#define PAGE_OFFSET PLATFORM_DEFAULT_MEM_START +#define PHYS_OFFSET PLATFORM_DEFAULT_MEM_START +#define MAX_LOW_PFN PHYS_PFN(0xfffffffful) #endif #define PGTABLE_START 0x80000000 @@ -167,10 +162,12 @@ void copy_user_highpage(struct page *to, struct page *from, * addresses. */ -#define ARCH_PFN_OFFSET (PLATFORM_DEFAULT_MEM_START >> PAGE_SHIFT) +#define ARCH_PFN_OFFSET (PHYS_OFFSET >> PAGE_SHIFT) -#define __pa(x) ((unsigned long) (x) - PAGE_OFFSET) -#define __va(x) ((void *)((unsigned long) (x) + PAGE_OFFSET)) +#define __pa(x) \ + ((unsigned long) (x) - PAGE_OFFSET + PHYS_OFFSET) +#define __va(x) \ + ((void *)((unsigned long) (x) - PHYS_OFFSET + PAGE_OFFSET)) #define pfn_valid(pfn) \ ((pfn) >= ARCH_PFN_OFFSET && ((pfn) - ARCH_PFN_OFFSET) < max_mapnr) diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index fb02fdc5ecee..8aa0e0d9cbb2 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -13,6 +13,7 @@ #include <asm-generic/pgtable-nopmd.h> #include <asm/page.h> +#include <asm/kmem_layout.h> /* * We only use two ring levels, user and kernel space. @@ -68,9 +69,9 @@ * Virtual memory area. We keep a distance to other memory regions to be * on the safe side. We also use this area for cache aliasing. */ -#define VMALLOC_START 0xC0000000 -#define VMALLOC_END 0xC7FEFFFF -#define TLBTEMP_BASE_1 0xC7FF0000 +#define VMALLOC_START (XCHAL_KSEG_CACHED_VADDR - 0x10000000) +#define VMALLOC_END (VMALLOC_START + 0x07FEFFFF) +#define TLBTEMP_BASE_1 (VMALLOC_END + 1) #define TLBTEMP_BASE_2 (TLBTEMP_BASE_1 + DCACHE_WAY_SIZE) #if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE #define TLBTEMP_SIZE (2 * DCACHE_WAY_SIZE) diff --git a/arch/xtensa/include/asm/platform.h b/arch/xtensa/include/asm/platform.h index 32e98f27ce97..f8fbef67bc5f 100644 --- a/arch/xtensa/include/asm/platform.h +++ b/arch/xtensa/include/asm/platform.h @@ -69,4 +69,10 @@ extern int platform_pcibios_fixup (void); */ extern void platform_calibrate_ccount (void); +/* + * Flush and reset the mmu, simulate a processor reset, and + * jump to the reset vector. + */ +void cpu_reset(void) __attribute__((noreturn)); + #endif /* _XTENSA_PLATFORM_H */ diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index d2e40d39c615..b42d68bfe3cf 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -37,7 +37,7 @@ #ifdef CONFIG_MMU #define TASK_SIZE __XTENSA_UL_CONST(0x40000000) #else -#define TASK_SIZE (PLATFORM_DEFAULT_MEM_START + PLATFORM_DEFAULT_MEM_SIZE) +#define TASK_SIZE __XTENSA_UL_CONST(0xffffffff) #endif #define STACK_TOP TASK_SIZE diff --git a/arch/xtensa/include/asm/sysmem.h b/arch/xtensa/include/asm/sysmem.h index c015c5c8e3f7..552cdfd8590e 100644 --- a/arch/xtensa/include/asm/sysmem.h +++ b/arch/xtensa/include/asm/sysmem.h @@ -11,27 +11,8 @@ #ifndef _XTENSA_SYSMEM_H #define _XTENSA_SYSMEM_H -#define SYSMEM_BANKS_MAX 31 +#include <linux/memblock.h> -struct meminfo { - unsigned long start; - unsigned long end; -}; - -/* - * Bank array is sorted by .start. - * Banks don't overlap and there's at least one page gap - * between adjacent bank entries. - */ -struct sysmem_info { - int nr_banks; - struct meminfo bank[SYSMEM_BANKS_MAX]; -}; - -extern struct sysmem_info sysmem; - -int add_sysmem_bank(unsigned long start, unsigned long end); -int mem_reserve(unsigned long, unsigned long, int); void bootmem_init(void); void zones_init(void); diff --git a/arch/xtensa/include/asm/vectors.h b/arch/xtensa/include/asm/vectors.h index 288c776736d3..77d41cc7a688 100644 --- a/arch/xtensa/include/asm/vectors.h +++ b/arch/xtensa/include/asm/vectors.h @@ -20,6 +20,7 @@ #include <variant/core.h> #include <platform/hardware.h> +#include <asm/kmem_layout.h> #if XCHAL_HAVE_PTP_MMU #define XCHAL_KIO_CACHED_VADDR 0xe0000000 @@ -47,61 +48,42 @@ static inline unsigned long xtensa_get_kio_paddr(void) #if defined(CONFIG_MMU) -/* Will Become VECBASE */ -#define VIRTUAL_MEMORY_ADDRESS 0xD0000000 - +#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY /* Image Virtual Start Address */ -#define KERNELOFFSET 0xD0003000 - -#if defined(XCHAL_HAVE_PTP_MMU) && XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY - /* MMU v3 - XCHAL_HAVE_PTP_MMU == 1 */ - #define LOAD_MEMORY_ADDRESS 0x00003000 +#define KERNELOFFSET (XCHAL_KSEG_CACHED_VADDR + \ + CONFIG_KERNEL_LOAD_ADDRESS - \ + XCHAL_KSEG_PADDR) #else - /* MMU V2 - XCHAL_HAVE_PTP_MMU == 0 */ - #define LOAD_MEMORY_ADDRESS 0xD0003000 +#define KERNELOFFSET CONFIG_KERNEL_LOAD_ADDRESS #endif -#define RESET_VECTOR1_VADDR (VIRTUAL_MEMORY_ADDRESS + \ - XCHAL_RESET_VECTOR1_PADDR) - #else /* !defined(CONFIG_MMU) */ /* MMU Not being used - Virtual == Physical */ - /* VECBASE */ - #define VIRTUAL_MEMORY_ADDRESS (PLATFORM_DEFAULT_MEM_START + 0x2000) +/* Location of the start of the kernel text, _start */ +#define KERNELOFFSET CONFIG_KERNEL_LOAD_ADDRESS - /* Location of the start of the kernel text, _start */ - #define KERNELOFFSET (PLATFORM_DEFAULT_MEM_START + 0x3000) - - /* Loaded just above possibly live vectors */ - #define LOAD_MEMORY_ADDRESS (PLATFORM_DEFAULT_MEM_START + 0x3000) - -#define RESET_VECTOR1_VADDR (XCHAL_RESET_VECTOR1_VADDR) #endif /* CONFIG_MMU */ -#define XC_VADDR(offset) (VIRTUAL_MEMORY_ADDRESS + offset) - -/* Used to set VECBASE register */ -#define VECBASE_RESET_VADDR VIRTUAL_MEMORY_ADDRESS +#define RESET_VECTOR1_VADDR (XCHAL_RESET_VECTOR1_VADDR) +#define VECBASE_VADDR (KERNELOFFSET - CONFIG_VECTORS_OFFSET) #if defined(XCHAL_HAVE_VECBASE) && XCHAL_HAVE_VECBASE -#define USER_VECTOR_VADDR XC_VADDR(XCHAL_USER_VECOFS) -#define KERNEL_VECTOR_VADDR XC_VADDR(XCHAL_KERNEL_VECOFS) -#define DOUBLEEXC_VECTOR_VADDR XC_VADDR(XCHAL_DOUBLEEXC_VECOFS) -#define WINDOW_VECTORS_VADDR XC_VADDR(XCHAL_WINDOW_OF4_VECOFS) -#define INTLEVEL2_VECTOR_VADDR XC_VADDR(XCHAL_INTLEVEL2_VECOFS) -#define INTLEVEL3_VECTOR_VADDR XC_VADDR(XCHAL_INTLEVEL3_VECOFS) -#define INTLEVEL4_VECTOR_VADDR XC_VADDR(XCHAL_INTLEVEL4_VECOFS) -#define INTLEVEL5_VECTOR_VADDR XC_VADDR(XCHAL_INTLEVEL5_VECOFS) -#define INTLEVEL6_VECTOR_VADDR XC_VADDR(XCHAL_INTLEVEL6_VECOFS) - -#define DEBUG_VECTOR_VADDR XC_VADDR(XCHAL_DEBUG_VECOFS) +#define VECTOR_VADDR(offset) (VECBASE_VADDR + offset) -#define NMI_VECTOR_VADDR XC_VADDR(XCHAL_NMI_VECOFS) - -#define INTLEVEL7_VECTOR_VADDR XC_VADDR(XCHAL_INTLEVEL7_VECOFS) +#define USER_VECTOR_VADDR VECTOR_VADDR(XCHAL_USER_VECOFS) +#define KERNEL_VECTOR_VADDR VECTOR_VADDR(XCHAL_KERNEL_VECOFS) +#define DOUBLEEXC_VECTOR_VADDR VECTOR_VADDR(XCHAL_DOUBLEEXC_VECOFS) +#define WINDOW_VECTORS_VADDR VECTOR_VADDR(XCHAL_WINDOW_OF4_VECOFS) +#define INTLEVEL2_VECTOR_VADDR VECTOR_VADDR(XCHAL_INTLEVEL2_VECOFS) +#define INTLEVEL3_VECTOR_VADDR VECTOR_VADDR(XCHAL_INTLEVEL3_VECOFS) +#define INTLEVEL4_VECTOR_VADDR VECTOR_VADDR(XCHAL_INTLEVEL4_VECOFS) +#define INTLEVEL5_VECTOR_VADDR VECTOR_VADDR(XCHAL_INTLEVEL5_VECOFS) +#define INTLEVEL6_VECTOR_VADDR VECTOR_VADDR(XCHAL_INTLEVEL6_VECOFS) +#define INTLEVEL7_VECTOR_VADDR VECTOR_VADDR(XCHAL_INTLEVEL7_VECOFS) +#define DEBUG_VECTOR_VADDR VECTOR_VADDR(XCHAL_DEBUG_VECOFS) /* * These XCHAL_* #defines from varian/core.h @@ -109,7 +91,6 @@ static inline unsigned long xtensa_get_kio_paddr(void) * constants are defined above and should be used. */ #undef XCHAL_VECBASE_RESET_VADDR -#undef XCHAL_RESET_VECTOR0_VADDR #undef XCHAL_USER_VECTOR_VADDR #undef XCHAL_KERNEL_VECTOR_VADDR #undef XCHAL_DOUBLEEXC_VECTOR_VADDR @@ -119,9 +100,8 @@ static inline unsigned long xtensa_get_kio_paddr(void) #undef XCHAL_INTLEVEL4_VECTOR_VADDR #undef XCHAL_INTLEVEL5_VECTOR_VADDR #undef XCHAL_INTLEVEL6_VECTOR_VADDR -#undef XCHAL_DEBUG_VECTOR_VADDR -#undef XCHAL_NMI_VECTOR_VADDR #undef XCHAL_INTLEVEL7_VECTOR_VADDR +#undef XCHAL_DEBUG_VECTOR_VADDR #else @@ -134,6 +114,7 @@ static inline unsigned long xtensa_get_kio_paddr(void) #define INTLEVEL4_VECTOR_VADDR XCHAL_INTLEVEL4_VECTOR_VADDR #define INTLEVEL5_VECTOR_VADDR XCHAL_INTLEVEL5_VECTOR_VADDR #define INTLEVEL6_VECTOR_VADDR XCHAL_INTLEVEL6_VECTOR_VADDR +#define INTLEVEL7_VECTOR_VADDR XCHAL_INTLEVEL6_VECTOR_VADDR #define DEBUG_VECTOR_VADDR XCHAL_DEBUG_VECTOR_VADDR #endif diff --git a/arch/xtensa/include/uapi/asm/types.h b/arch/xtensa/include/uapi/asm/types.h index 87ec7ae73cb1..2efc921506c4 100644 --- a/arch/xtensa/include/uapi/asm/types.h +++ b/arch/xtensa/include/uapi/asm/types.h @@ -18,7 +18,8 @@ # define __XTENSA_UL_CONST(x) x #else # define __XTENSA_UL(x) ((unsigned long)(x)) -# define __XTENSA_UL_CONST(x) x##UL +# define ___XTENSA_UL_CONST(x) x##UL +# define __XTENSA_UL_CONST(x) ___XTENSA_UL_CONST(x) #endif #ifndef __ASSEMBLY__ diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h index b95c30594355..de9b14b2d348 100644 --- a/arch/xtensa/include/uapi/asm/unistd.h +++ b/arch/xtensa/include/uapi/asm/unistd.h @@ -754,7 +754,20 @@ __SYSCALL(340, sys_bpf, 3) #define __NR_execveat 341 __SYSCALL(341, sys_execveat, 5) -#define __NR_syscall_count 342 +#define __NR_userfaultfd 342 +__SYSCALL(342, sys_userfaultfd, 1) +#define __NR_membarrier 343 +__SYSCALL(343, sys_membarrier, 2) +#define __NR_mlock2 344 +__SYSCALL(344, sys_mlock2, 3) +#define __NR_copy_file_range 345 +__SYSCALL(345, sys_copy_file_range, 6) +#define __NR_preadv2 346 +__SYSCALL(346, sys_preadv2, 6) +#define __NR_pwritev2 347 +__SYSCALL(347, sys_pwritev2, 6) + +#define __NR_syscall_count 348 /* * sysxtensa syscall handler diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index fe8f7e7efb9d..fa04d9d368a7 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1632,10 +1632,11 @@ ENTRY(fast_second_level_miss) * The messy computation for 'pteval' above really simplifies * into the following: * - * pteval = ((pmdval - PAGE_OFFSET) & PAGE_MASK) | PAGE_DIRECTORY + * pteval = ((pmdval - PAGE_OFFSET + PHYS_OFFSET) & PAGE_MASK) + * | PAGE_DIRECTORY */ - movi a1, (-PAGE_OFFSET) & 0xffffffff + movi a1, (PHYS_OFFSET - PAGE_OFFSET) & 0xffffffff add a0, a0, a1 # pmdval - PAGE_OFFSET extui a1, a0, 0, PAGE_SHIFT # ... & PAGE_MASK xor a0, a0, a1 diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S index bc4f4bf05099..23ce62e60435 100644 --- a/arch/xtensa/kernel/head.S +++ b/arch/xtensa/kernel/head.S @@ -113,7 +113,7 @@ ENTRY(_startup) movi a0, 0 #if XCHAL_HAVE_VECBASE - movi a2, VECBASE_RESET_VADDR + movi a2, VECBASE_VADDR wsr a2, vecbase #endif diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 143251ede897..88a044af7504 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -7,6 +7,7 @@ * * Copyright (C) 1995 Linus Torvalds * Copyright (C) 2001 - 2005 Tensilica Inc. + * Copyright (C) 2014 - 2016 Cadence Design Systems Inc. * * Chris Zankel <chris@zankel.net> * Joe Taylor <joe@tensilica.com, joetylr@yahoo.com> @@ -22,7 +23,6 @@ #include <linux/bootmem.h> #include <linux/kernel.h> #include <linux/percpu.h> -#include <linux/clk-provider.h> #include <linux/cpu.h> #include <linux/of.h> #include <linux/of_fdt.h> @@ -114,7 +114,7 @@ static int __init parse_tag_mem(const bp_tag_t *tag) if (mi->type != MEMORY_TYPE_CONVENTIONAL) return -1; - return add_sysmem_bank(mi->start, mi->end); + return memblock_add(mi->start, mi->end - mi->start); } __tagtable(BP_TAG_MEMORY, parse_tag_mem); @@ -188,7 +188,6 @@ static int __init parse_bootparam(const bp_tag_t* tag) } #ifdef CONFIG_OF -bool __initdata dt_memory_scan = false; #if !XCHAL_HAVE_PTP_MMU || XCHAL_HAVE_SPANNING_WAY unsigned long xtensa_kio_paddr = XCHAL_KIO_DEFAULT_PADDR; @@ -228,11 +227,8 @@ static int __init xtensa_dt_io_area(unsigned long node, const char *uname, void __init early_init_dt_add_memory_arch(u64 base, u64 size) { - if (!dt_memory_scan) - return; - size &= PAGE_MASK; - add_sysmem_bank(base, base + size); + memblock_add(base, size); } void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) @@ -242,9 +238,6 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) void __init early_init_devtree(void *params) { - if (sysmem.nr_banks == 0) - dt_memory_scan = true; - early_init_dt_scan(params); of_scan_flat_dt(xtensa_dt_io_area, NULL); @@ -252,14 +245,6 @@ void __init early_init_devtree(void *params) strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); } -static int __init xtensa_device_probe(void) -{ - of_clk_init(NULL); - return 0; -} - -device_initcall(xtensa_device_probe); - #endif /* CONFIG_OF */ /* @@ -277,12 +262,6 @@ void __init init_arch(bp_tag_t *bp_start) early_init_devtree(dtb_start); #endif - if (sysmem.nr_banks == 0) { - add_sysmem_bank(PLATFORM_DEFAULT_MEM_START, - PLATFORM_DEFAULT_MEM_START + - PLATFORM_DEFAULT_MEM_SIZE); - } - #ifdef CONFIG_CMDLINE_BOOL if (!command_line[0]) strlcpy(command_line, default_command_line, COMMAND_LINE_SIZE); @@ -452,6 +431,10 @@ static int __init check_s32c1i(void) early_initcall(check_s32c1i); #endif /* CONFIG_S32C1I_SELFTEST */ +static inline int mem_reserve(unsigned long start, unsigned long end) +{ + return memblock_reserve(start, end - start); +} void __init setup_arch(char **cmdline_p) { @@ -463,54 +446,54 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_BLK_DEV_INITRD if (initrd_start < initrd_end) { initrd_is_mapped = mem_reserve(__pa(initrd_start), - __pa(initrd_end), 0) == 0; + __pa(initrd_end)) == 0; initrd_below_start_ok = 1; } else { initrd_start = 0; } #endif - mem_reserve(__pa(&_stext),__pa(&_end), 1); + mem_reserve(__pa(&_stext), __pa(&_end)); mem_reserve(__pa(&_WindowVectors_text_start), - __pa(&_WindowVectors_text_end), 0); + __pa(&_WindowVectors_text_end)); mem_reserve(__pa(&_DebugInterruptVector_literal_start), - __pa(&_DebugInterruptVector_text_end), 0); + __pa(&_DebugInterruptVector_text_end)); mem_reserve(__pa(&_KernelExceptionVector_literal_start), - __pa(&_KernelExceptionVector_text_end), 0); + __pa(&_KernelExceptionVector_text_end)); mem_reserve(__pa(&_UserExceptionVector_literal_start), - __pa(&_UserExceptionVector_text_end), 0); + __pa(&_UserExceptionVector_text_end)); mem_reserve(__pa(&_DoubleExceptionVector_literal_start), - __pa(&_DoubleExceptionVector_text_end), 0); + __pa(&_DoubleExceptionVector_text_end)); #if XCHAL_EXCM_LEVEL >= 2 mem_reserve(__pa(&_Level2InterruptVector_text_start), - __pa(&_Level2InterruptVector_text_end), 0); + __pa(&_Level2InterruptVector_text_end)); #endif #if XCHAL_EXCM_LEVEL >= 3 mem_reserve(__pa(&_Level3InterruptVector_text_start), - __pa(&_Level3InterruptVector_text_end), 0); + __pa(&_Level3InterruptVector_text_end)); #endif #if XCHAL_EXCM_LEVEL >= 4 mem_reserve(__pa(&_Level4InterruptVector_text_start), - __pa(&_Level4InterruptVector_text_end), 0); + __pa(&_Level4InterruptVector_text_end)); #endif #if XCHAL_EXCM_LEVEL >= 5 mem_reserve(__pa(&_Level5InterruptVector_text_start), - __pa(&_Level5InterruptVector_text_end), 0); + __pa(&_Level5InterruptVector_text_end)); #endif #if XCHAL_EXCM_LEVEL >= 6 mem_reserve(__pa(&_Level6InterruptVector_text_start), - __pa(&_Level6InterruptVector_text_end), 0); + __pa(&_Level6InterruptVector_text_end)); #endif #ifdef CONFIG_SMP mem_reserve(__pa(&_SecondaryResetVector_text_start), - __pa(&_SecondaryResetVector_text_end), 0); + __pa(&_SecondaryResetVector_text_end)); #endif parse_early_param(); bootmem_init(); @@ -555,6 +538,137 @@ static int __init topology_init(void) } subsys_initcall(topology_init); +void cpu_reset(void) +{ +#if XCHAL_HAVE_PTP_MMU + local_irq_disable(); + /* + * We have full MMU: all autoload ways, ways 7, 8 and 9 of DTLB must + * be flushed. + * Way 4 is not currently used by linux. + * Ways 5 and 6 shall not be touched on MMUv2 as they are hardwired. + * Way 5 shall be flushed and way 6 shall be set to identity mapping + * on MMUv3. + */ + local_flush_tlb_all(); + invalidate_page_directory(); +#if XCHAL_HAVE_SPANNING_WAY + /* MMU v3 */ + { + unsigned long vaddr = (unsigned long)cpu_reset; + unsigned long paddr = __pa(vaddr); + unsigned long tmpaddr = vaddr + SZ_512M; + unsigned long tmp0, tmp1, tmp2, tmp3; + + /* + * Find a place for the temporary mapping. It must not be + * in the same 512MB region with vaddr or paddr, otherwise + * there may be multihit exception either on entry to the + * temporary mapping, or on entry to the identity mapping. + * (512MB is the biggest page size supported by TLB.) + */ + while (((tmpaddr ^ paddr) & -SZ_512M) == 0) + tmpaddr += SZ_512M; + + /* Invalidate mapping in the selected temporary area */ + if (itlb_probe(tmpaddr) & 0x8) + invalidate_itlb_entry(itlb_probe(tmpaddr)); + if (itlb_probe(tmpaddr + PAGE_SIZE) & 0x8) + invalidate_itlb_entry(itlb_probe(tmpaddr + PAGE_SIZE)); + + /* + * Map two consecutive pages starting at the physical address + * of this function to the temporary mapping area. + */ + write_itlb_entry(__pte((paddr & PAGE_MASK) | + _PAGE_HW_VALID | + _PAGE_HW_EXEC | + _PAGE_CA_BYPASS), + tmpaddr & PAGE_MASK); + write_itlb_entry(__pte(((paddr & PAGE_MASK) + PAGE_SIZE) | + _PAGE_HW_VALID | + _PAGE_HW_EXEC | + _PAGE_CA_BYPASS), + (tmpaddr & PAGE_MASK) + PAGE_SIZE); + + /* Reinitialize TLB */ + __asm__ __volatile__ ("movi %0, 1f\n\t" + "movi %3, 2f\n\t" + "add %0, %0, %4\n\t" + "add %3, %3, %5\n\t" + "jx %0\n" + /* + * No literal, data or stack access + * below this point + */ + "1:\n\t" + /* Initialize *tlbcfg */ + "movi %0, 0\n\t" + "wsr %0, itlbcfg\n\t" + "wsr %0, dtlbcfg\n\t" + /* Invalidate TLB way 5 */ + "movi %0, 4\n\t" + "movi %1, 5\n" + "1:\n\t" + "iitlb %1\n\t" + "idtlb %1\n\t" + "add %1, %1, %6\n\t" + "addi %0, %0, -1\n\t" + "bnez %0, 1b\n\t" + /* Initialize TLB way 6 */ + "movi %0, 7\n\t" + "addi %1, %9, 3\n\t" + "addi %2, %9, 6\n" + "1:\n\t" + "witlb %1, %2\n\t" + "wdtlb %1, %2\n\t" + "add %1, %1, %7\n\t" + "add %2, %2, %7\n\t" + "addi %0, %0, -1\n\t" + "bnez %0, 1b\n\t" + /* Jump to identity mapping */ + "jx %3\n" + "2:\n\t" + /* Complete way 6 initialization */ + "witlb %1, %2\n\t" + "wdtlb %1, %2\n\t" + /* Invalidate temporary mapping */ + "sub %0, %9, %7\n\t" + "iitlb %0\n\t" + "add %0, %0, %8\n\t" + "iitlb %0" + : "=&a"(tmp0), "=&a"(tmp1), "=&a"(tmp2), + "=&a"(tmp3) + : "a"(tmpaddr - vaddr), + "a"(paddr - vaddr), + "a"(SZ_128M), "a"(SZ_512M), + "a"(PAGE_SIZE), + "a"((tmpaddr + SZ_512M) & PAGE_MASK) + : "memory"); + } +#endif +#endif + __asm__ __volatile__ ("movi a2, 0\n\t" + "wsr a2, icountlevel\n\t" + "movi a2, 0\n\t" + "wsr a2, icount\n\t" +#if XCHAL_NUM_IBREAK > 0 + "wsr a2, ibreakenable\n\t" +#endif +#if XCHAL_HAVE_LOOPS + "wsr a2, lcount\n\t" +#endif + "movi a2, 0x1f\n\t" + "wsr a2, ps\n\t" + "isync\n\t" + "jx %0\n\t" + : + : "a" (XCHAL_RESET_VECTOR_VADDR) + : "a2"); + for (;;) + ; +} + void machine_restart(char * cmd) { platform_restart(); diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index b9ad9feadc2d..9a5bcd0381a7 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -12,6 +12,8 @@ * Chris Zankel <chris@zankel.net> */ +#include <linux/clk.h> +#include <linux/clk-provider.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/time.h> @@ -134,16 +136,52 @@ void local_timer_setup(unsigned cpu) 0xf, 0xffffffff); } +#ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT +#ifdef CONFIG_OF +static void __init calibrate_ccount(void) +{ + struct device_node *cpu; + struct clk *clk; + + cpu = of_find_compatible_node(NULL, NULL, "cdns,xtensa-cpu"); + if (cpu) { + clk = of_clk_get(cpu, 0); + if (!IS_ERR(clk)) { + ccount_freq = clk_get_rate(clk); + return; + } else { + pr_warn("%s: CPU input clock not found\n", + __func__); + } + } else { + pr_warn("%s: CPU node not found in the device tree\n", + __func__); + } + + platform_calibrate_ccount(); +} +#else +static inline void calibrate_ccount(void) +{ + platform_calibrate_ccount(); +} +#endif +#endif + void __init time_init(void) { + of_clk_init(NULL); #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT printk("Calibrating CPU frequency "); - platform_calibrate_ccount(); + calibrate_ccount(); printk("%d.%02d MHz\n", (int)ccount_freq/1000000, (int)(ccount_freq/10000)%100); #else ccount_freq = CONFIG_XTENSA_CPU_CLOCK*1000000UL; #endif + WARN(!ccount_freq, + "%s: CPU clock frequency is not set up correctly\n", + __func__); clocksource_register_hz(&ccount_clocksource, ccount_freq); local_timer_setup(0); setup_irq(this_cpu_ptr(&ccount_timer)->evt.irq, &timer_irqaction); diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S index c417cbe4ec87..72cfe3587dd8 100644 --- a/arch/xtensa/kernel/vmlinux.lds.S +++ b/arch/xtensa/kernel/vmlinux.lds.S @@ -30,10 +30,6 @@ jiffies = jiffies_64 + 4; jiffies = jiffies_64; #endif -#ifndef KERNELOFFSET -#define KERNELOFFSET 0xd0003000 -#endif - /* Note: In the following macros, it would be nice to specify only the vector name and section kind and construct "sym" and "section" using CPP concatenation, but that does not work reliably. Concatenating a diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 9a9a5935bd36..80e4cfb2471a 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -8,7 +8,7 @@ * for more details. * * Copyright (C) 2001 - 2005 Tensilica Inc. - * Copyright (C) 2014 Cadence Design Systems Inc. + * Copyright (C) 2014 - 2016 Cadence Design Systems Inc. * * Chris Zankel <chris@zankel.net> * Joe Taylor <joe@tensilica.com, joetylr@yahoo.com> @@ -25,284 +25,43 @@ #include <linux/mman.h> #include <linux/nodemask.h> #include <linux/mm.h> +#include <linux/of_fdt.h> #include <asm/bootparam.h> #include <asm/page.h> #include <asm/sections.h> #include <asm/sysmem.h> -struct sysmem_info sysmem __initdata; - -static void __init sysmem_dump(void) -{ - unsigned i; - - pr_debug("Sysmem:\n"); - for (i = 0; i < sysmem.nr_banks; ++i) - pr_debug(" 0x%08lx - 0x%08lx (%ldK)\n", - sysmem.bank[i].start, sysmem.bank[i].end, - (sysmem.bank[i].end - sysmem.bank[i].start) >> 10); -} - -/* - * Find bank with maximal .start such that bank.start <= start - */ -static inline struct meminfo * __init find_bank(unsigned long start) -{ - unsigned i; - struct meminfo *it = NULL; - - for (i = 0; i < sysmem.nr_banks; ++i) - if (sysmem.bank[i].start <= start) - it = sysmem.bank + i; - else - break; - return it; -} - -/* - * Move all memory banks starting at 'from' to a new place at 'to', - * adjust nr_banks accordingly. - * Both 'from' and 'to' must be inside the sysmem.bank. - * - * Returns: 0 (success), -ENOMEM (not enough space in the sysmem.bank). - */ -static int __init move_banks(struct meminfo *to, struct meminfo *from) -{ - unsigned n = sysmem.nr_banks - (from - sysmem.bank); - - if (to > from && to - from + sysmem.nr_banks > SYSMEM_BANKS_MAX) - return -ENOMEM; - if (to != from) - memmove(to, from, n * sizeof(struct meminfo)); - sysmem.nr_banks += to - from; - return 0; -} - -/* - * Add new bank to sysmem. Resulting sysmem is the union of bytes of the - * original sysmem and the new bank. - * - * Returns: 0 (success), < 0 (error) - */ -int __init add_sysmem_bank(unsigned long start, unsigned long end) -{ - unsigned i; - struct meminfo *it = NULL; - unsigned long sz; - unsigned long bank_sz = 0; - - if (start == end || - (start < end) != (PAGE_ALIGN(start) < (end & PAGE_MASK))) { - pr_warn("Ignoring small memory bank 0x%08lx size: %ld bytes\n", - start, end - start); - return -EINVAL; - } - - start = PAGE_ALIGN(start); - end &= PAGE_MASK; - sz = end - start; - - it = find_bank(start); - - if (it) - bank_sz = it->end - it->start; - - if (it && bank_sz >= start - it->start) { - if (end - it->start > bank_sz) - it->end = end; - else - return 0; - } else { - if (!it) - it = sysmem.bank; - else - ++it; - - if (it - sysmem.bank < sysmem.nr_banks && - it->start - start <= sz) { - it->start = start; - if (it->end - it->start < sz) - it->end = end; - else - return 0; - } else { - if (move_banks(it + 1, it) < 0) { - pr_warn("Ignoring memory bank 0x%08lx size %ld bytes\n", - start, end - start); - return -EINVAL; - } - it->start = start; - it->end = end; - return 0; - } - } - sz = it->end - it->start; - for (i = it + 1 - sysmem.bank; i < sysmem.nr_banks; ++i) - if (sysmem.bank[i].start - it->start <= sz) { - if (sz < sysmem.bank[i].end - it->start) - it->end = sysmem.bank[i].end; - } else { - break; - } - - move_banks(it + 1, sysmem.bank + i); - return 0; -} - -/* - * mem_reserve(start, end, must_exist) - * - * Reserve some memory from the memory pool. - * If must_exist is set and a part of the region being reserved does not exist - * memory map is not altered. - * - * Parameters: - * start Start of region, - * end End of region, - * must_exist Must exist in memory pool. - * - * Returns: - * 0 (success) - * < 0 (error) - */ - -int __init mem_reserve(unsigned long start, unsigned long end, int must_exist) -{ - struct meminfo *it; - struct meminfo *rm = NULL; - unsigned long sz; - unsigned long bank_sz = 0; - - start = start & PAGE_MASK; - end = PAGE_ALIGN(end); - sz = end - start; - if (!sz) - return -EINVAL; - - it = find_bank(start); - - if (it) - bank_sz = it->end - it->start; - - if ((!it || end - it->start > bank_sz) && must_exist) { - pr_warn("mem_reserve: [0x%0lx, 0x%0lx) not in any region!\n", - start, end); - return -EINVAL; - } - - if (it && start - it->start <= bank_sz) { - if (start == it->start) { - if (end - it->start < bank_sz) { - it->start = end; - return 0; - } else { - rm = it; - } - } else { - it->end = start; - if (end - it->start < bank_sz) - return add_sysmem_bank(end, - it->start + bank_sz); - ++it; - } - } - - if (!it) - it = sysmem.bank; - - for (; it < sysmem.bank + sysmem.nr_banks; ++it) { - if (it->end - start <= sz) { - if (!rm) - rm = it; - } else { - if (it->start - start < sz) - it->start = end; - break; - } - } - - if (rm) - move_banks(rm, it); - - return 0; -} - - /* * Initialize the bootmem system and give it all low memory we have available. */ void __init bootmem_init(void) { - unsigned long pfn; - unsigned long bootmap_start, bootmap_size; - int i; - - /* Reserve all memory below PLATFORM_DEFAULT_MEM_START, as memory + /* Reserve all memory below PHYS_OFFSET, as memory * accounting doesn't work for pages below that address. * - * If PLATFORM_DEFAULT_MEM_START is zero reserve page at address 0: + * If PHYS_OFFSET is zero reserve page at address 0: * successfull allocations should never return NULL. */ - if (PLATFORM_DEFAULT_MEM_START) - mem_reserve(0, PLATFORM_DEFAULT_MEM_START, 0); + if (PHYS_OFFSET) + memblock_reserve(0, PHYS_OFFSET); else - mem_reserve(0, 1, 0); + memblock_reserve(0, 1); - sysmem_dump(); - max_low_pfn = max_pfn = 0; - min_low_pfn = ~0; - - for (i=0; i < sysmem.nr_banks; i++) { - pfn = PAGE_ALIGN(sysmem.bank[i].start) >> PAGE_SHIFT; - if (pfn < min_low_pfn) - min_low_pfn = pfn; - pfn = PAGE_ALIGN(sysmem.bank[i].end - 1) >> PAGE_SHIFT; - if (pfn > max_pfn) - max_pfn = pfn; - } + early_init_fdt_scan_reserved_mem(); - if (min_low_pfn > max_pfn) + if (!memblock_phys_mem_size()) panic("No memory found!\n"); - max_low_pfn = max_pfn < MAX_MEM_PFN >> PAGE_SHIFT ? - max_pfn : MAX_MEM_PFN >> PAGE_SHIFT; + min_low_pfn = PFN_UP(memblock_start_of_DRAM()); + min_low_pfn = max(min_low_pfn, PFN_UP(PHYS_OFFSET)); + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = min(max_pfn, MAX_LOW_PFN); - /* Find an area to use for the bootmem bitmap. */ - - bootmap_size = bootmem_bootmap_pages(max_low_pfn - min_low_pfn); - bootmap_size <<= PAGE_SHIFT; - bootmap_start = ~0; - - for (i=0; i<sysmem.nr_banks; i++) - if (sysmem.bank[i].end - sysmem.bank[i].start >= bootmap_size) { - bootmap_start = sysmem.bank[i].start; - break; - } - - if (bootmap_start == ~0UL) - panic("Cannot find %ld bytes for bootmap\n", bootmap_size); - - /* Reserve the bootmem bitmap area */ - - mem_reserve(bootmap_start, bootmap_start + bootmap_size, 1); - bootmap_size = init_bootmem_node(NODE_DATA(0), - bootmap_start >> PAGE_SHIFT, - min_low_pfn, - max_low_pfn); - - /* Add all remaining memory pieces into the bootmem map */ - - for (i = 0; i < sysmem.nr_banks; i++) { - if (sysmem.bank[i].start >> PAGE_SHIFT < max_low_pfn) { - unsigned long end = min(max_low_pfn << PAGE_SHIFT, - sysmem.bank[i].end); - free_bootmem(sysmem.bank[i].start, - end - sysmem.bank[i].start); - } - } + memblock_set_current_limit(PFN_PHYS(max_low_pfn)); + memblock_dump_all(); } @@ -344,7 +103,7 @@ void __init mem_init(void) " fixmap : 0x%08lx - 0x%08lx (%5lu kB)\n" #endif #ifdef CONFIG_MMU - " vmalloc : 0x%08x - 0x%08x (%5u MB)\n" + " vmalloc : 0x%08lx - 0x%08lx (%5lu MB)\n" #endif " lowmem : 0x%08lx - 0x%08lx (%5lu MB)\n", #ifdef CONFIG_HIGHMEM @@ -395,16 +154,16 @@ static void __init parse_memmap_one(char *p) switch (*p) { case '@': start_at = memparse(p + 1, &p); - add_sysmem_bank(start_at, start_at + mem_size); + memblock_add(start_at, mem_size); break; case '$': start_at = memparse(p + 1, &p); - mem_reserve(start_at, start_at + mem_size, 0); + memblock_reserve(start_at, mem_size); break; case 0: - mem_reserve(mem_size, 0, 0); + memblock_reserve(mem_size, -mem_size); break; default: diff --git a/arch/xtensa/platforms/iss/include/platform/simcall.h b/arch/xtensa/platforms/iss/include/platform/simcall.h index 12b15ad1e586..27d7a528b41a 100644 --- a/arch/xtensa/platforms/iss/include/platform/simcall.h +++ b/arch/xtensa/platforms/iss/include/platform/simcall.h @@ -76,6 +76,11 @@ static inline int __simc(int a, int b, int c, int d) return ret; } +static inline int simc_exit(int exit_code) +{ + return __simc(SYS_exit, exit_code, 0, 0); +} + static inline int simc_open(const char *file, int flags, int mode) { return __simc(SYS_open, (int) file, flags, mode); diff --git a/arch/xtensa/platforms/iss/setup.c b/arch/xtensa/platforms/iss/setup.c index 391820539f0a..379aeddcc638 100644 --- a/arch/xtensa/platforms/iss/setup.c +++ b/arch/xtensa/platforms/iss/setup.c @@ -32,6 +32,8 @@ #include <asm/platform.h> #include <asm/bootparam.h> +#include <platform/simcall.h> + void __init platform_init(bp_tag_t* bootparam) { @@ -41,37 +43,19 @@ void __init platform_init(bp_tag_t* bootparam) void platform_halt(void) { pr_info(" ** Called platform_halt() **\n"); - __asm__ __volatile__("movi a2, 1\nsimcall\n"); + simc_exit(0); } void platform_power_off(void) { pr_info(" ** Called platform_power_off() **\n"); - __asm__ __volatile__("movi a2, 1\nsimcall\n"); + simc_exit(0); } void platform_restart(void) { /* Flush and reset the mmu, simulate a processor reset, and * jump to the reset vector. */ - - __asm__ __volatile__("movi a2, 15\n\t" - "wsr a2, icountlevel\n\t" - "movi a2, 0\n\t" - "wsr a2, icount\n\t" -#if XCHAL_NUM_IBREAK > 0 - "wsr a2, ibreakenable\n\t" -#endif -#if XCHAL_HAVE_LOOPS - "wsr a2, lcount\n\t" -#endif - "movi a2, 0x1f\n\t" - "wsr a2, ps\n\t" - "isync\n\t" - "jx %0\n\t" - : - : "a" (XCHAL_RESET_VECTOR_VADDR) - : "a2"); - + cpu_reset(); /* control never gets here */ } @@ -98,7 +82,7 @@ void platform_heartbeat(void) static int iss_panic_event(struct notifier_block *this, unsigned long event, void *ptr) { - __asm__ __volatile__("movi a2, -1; simcall\n"); + simc_exit(1); return NOTIFY_DONE; } diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index f58a4e6472cb..ede04cca30dd 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -86,6 +86,7 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector, unsigned long io; simc_lseek(dev->fd, offset, SEEK_SET); + READ_ONCE(*buffer); if (write) io = simc_write(dev->fd, buffer, nbytes); else diff --git a/arch/xtensa/platforms/xt2000/setup.c b/arch/xtensa/platforms/xt2000/setup.c index 4904c5c16918..9c2f1fb960d0 100644 --- a/arch/xtensa/platforms/xt2000/setup.c +++ b/arch/xtensa/platforms/xt2000/setup.c @@ -64,26 +64,7 @@ void platform_restart(void) { /* Flush and reset the mmu, simulate a processor reset, and * jump to the reset vector. */ - - __asm__ __volatile__ ("movi a2, 15\n\t" - "wsr a2, icountlevel\n\t" - "movi a2, 0\n\t" - "wsr a2, icount\n\t" -#if XCHAL_NUM_IBREAK > 0 - "wsr a2, ibreakenable\n\t" -#endif -#if XCHAL_HAVE_LOOPS - "wsr a2, lcount\n\t" -#endif - "movi a2, 0x1f\n\t" - "wsr a2, ps\n\t" - "isync\n\t" - "jx %0\n\t" - : - : "a" (XCHAL_RESET_VECTOR_VADDR) - : "a2" - ); - + cpu_reset(); /* control never gets here */ } diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c index b509d1f55ed5..779be723eb2b 100644 --- a/arch/xtensa/platforms/xtfpga/setup.c +++ b/arch/xtensa/platforms/xtfpga/setup.c @@ -26,6 +26,8 @@ #include <linux/console.h> #include <linux/delay.h> #include <linux/of.h> +#include <linux/clk-provider.h> +#include <linux/of_address.h> #include <asm/timex.h> #include <asm/processor.h> @@ -54,58 +56,63 @@ void platform_restart(void) { /* Flush and reset the mmu, simulate a processor reset, and * jump to the reset vector. */ + cpu_reset(); + /* control never gets here */ +} +void __init platform_setup(char **cmdline) +{ +} - __asm__ __volatile__ ("movi a2, 15\n\t" - "wsr a2, icountlevel\n\t" - "movi a2, 0\n\t" - "wsr a2, icount\n\t" -#if XCHAL_NUM_IBREAK > 0 - "wsr a2, ibreakenable\n\t" -#endif -#if XCHAL_HAVE_LOOPS - "wsr a2, lcount\n\t" -#endif - "movi a2, 0x1f\n\t" - "wsr a2, ps\n\t" - "isync\n\t" - "jx %0\n\t" - : - : "a" (XCHAL_RESET_VECTOR_VADDR) - : "a2" - ); +/* early initialization */ - /* control never gets here */ +void __init platform_init(bp_tag_t *first) +{ } -void __init platform_setup(char **cmdline) +/* Heartbeat. */ + +void platform_heartbeat(void) +{ +} + +#ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT + +void __init platform_calibrate_ccount(void) { + ccount_freq = *(long *)XTFPGA_CLKFRQ_VADDR; } +#endif + #ifdef CONFIG_OF -static void __init update_clock_frequency(struct device_node *node) +static void __init xtfpga_clk_setup(struct device_node *np) { - struct property *newfreq; + void __iomem *base = of_iomap(np, 0); + struct clk *clk; u32 freq; - if (!of_property_read_u32(node, "clock-frequency", &freq) && freq != 0) + if (!base) { + pr_err("%s: invalid address\n", np->name); return; + } - newfreq = kzalloc(sizeof(*newfreq) + sizeof(u32), GFP_KERNEL); - if (!newfreq) - return; - newfreq->value = newfreq + 1; - newfreq->length = sizeof(freq); - newfreq->name = kstrdup("clock-frequency", GFP_KERNEL); - if (!newfreq->name) { - kfree(newfreq); + freq = __raw_readl(base); + iounmap(base); + clk = clk_register_fixed_rate(NULL, np->name, NULL, 0, freq); + + if (IS_ERR(clk)) { + pr_err("%s: clk registration failed\n", np->name); return; } - *(u32 *)newfreq->value = cpu_to_be32(*(u32 *)XTFPGA_CLKFRQ_VADDR); - of_update_property(node, newfreq); + if (of_clk_add_provider(np, of_clk_src_simple_get, clk)) { + pr_err("%s: clk provider registration failed\n", np->name); + return; + } } +CLK_OF_DECLARE(xtfpga_clk, "cdns,xtfpga-clock", xtfpga_clk_setup); #define MAC_LEN 6 static void __init update_local_mac(struct device_node *node) @@ -137,56 +144,15 @@ static void __init update_local_mac(struct device_node *node) static int __init machine_setup(void) { - struct device_node *clock; struct device_node *eth = NULL; - for_each_node_by_name(clock, "main-oscillator") - update_clock_frequency(clock); - if ((eth = of_find_compatible_node(eth, NULL, "opencores,ethoc"))) update_local_mac(eth); return 0; } arch_initcall(machine_setup); -#endif - -/* early initialization */ - -void __init platform_init(bp_tag_t *first) -{ -} - -/* Heartbeat. */ - -void platform_heartbeat(void) -{ -} - -#ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT - -void __init platform_calibrate_ccount(void) -{ - long clk_freq = 0; -#ifdef CONFIG_OF - struct device_node *cpu = - of_find_compatible_node(NULL, NULL, "cdns,xtensa-cpu"); - if (cpu) { - u32 freq; - update_clock_frequency(cpu); - if (!of_property_read_u32(cpu, "clock-frequency", &freq)) - clk_freq = freq; - } -#endif - if (!clk_freq) - clk_freq = *(long *)XTFPGA_CLKFRQ_VADDR; - - ccount_freq = clk_freq; -} - -#endif - -#ifndef CONFIG_OF +#else #include <linux/serial_8250.h> #include <linux/if.h> diff --git a/arch/xtensa/variants/csp/include/variant/core.h b/arch/xtensa/variants/csp/include/variant/core.h new file mode 100644 index 000000000000..ccd81f07eaf3 --- /dev/null +++ b/arch/xtensa/variants/csp/include/variant/core.h @@ -0,0 +1,575 @@ +/* + * xtensa/config/core-isa.h -- HAL definitions that are dependent on Xtensa + * processor CORE configuration + * + * See <xtensa/config/core.h>, which includes this file, for more details. + */ + +/* Xtensa processor core configuration information. + + Copyright (c) 1999-2015 Tensilica Inc. + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to + permit persons to whom the Software is furnished to do so, subject to + the following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. + IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY + CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, + TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE + SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. */ + +#ifndef _XTENSA_CORE_CONFIGURATION_H +#define _XTENSA_CORE_CONFIGURATION_H + + +/**************************************************************************** + Parameters Useful for Any Code, USER or PRIVILEGED + ****************************************************************************/ + +/* + * Note: Macros of the form XCHAL_HAVE_*** have a value of 1 if the option is + * configured, and a value of 0 otherwise. These macros are always defined. + */ + + +/*---------------------------------------------------------------------- + ISA + ----------------------------------------------------------------------*/ + +#define XCHAL_HAVE_BE 0 /* big-endian byte ordering */ +#define XCHAL_HAVE_WINDOWED 1 /* windowed registers option */ +#define XCHAL_NUM_AREGS 32 /* num of physical addr regs */ +#define XCHAL_NUM_AREGS_LOG2 5 /* log2(XCHAL_NUM_AREGS) */ +#define XCHAL_MAX_INSTRUCTION_SIZE 8 /* max instr bytes (3..8) */ +#define XCHAL_HAVE_DEBUG 1 /* debug option */ +#define XCHAL_HAVE_DENSITY 1 /* 16-bit instructions */ +#define XCHAL_HAVE_LOOPS 1 /* zero-overhead loops */ +#define XCHAL_LOOP_BUFFER_SIZE 0 /* zero-ov. loop instr buffer size */ +#define XCHAL_HAVE_NSA 1 /* NSA/NSAU instructions */ +#define XCHAL_HAVE_MINMAX 1 /* MIN/MAX instructions */ +#define XCHAL_HAVE_SEXT 1 /* SEXT instruction */ +#define XCHAL_HAVE_DEPBITS 0 /* DEPBITS instruction */ +#define XCHAL_HAVE_CLAMPS 1 /* CLAMPS instruction */ +#define XCHAL_HAVE_MUL16 1 /* MUL16S/MUL16U instructions */ +#define XCHAL_HAVE_MUL32 1 /* MULL instruction */ +#define XCHAL_HAVE_MUL32_HIGH 1 /* MULUH/MULSH instructions */ +#define XCHAL_HAVE_DIV32 1 /* QUOS/QUOU/REMS/REMU instructions */ +#define XCHAL_HAVE_L32R 1 /* L32R instruction */ +#define XCHAL_HAVE_ABSOLUTE_LITERALS 0 /* non-PC-rel (extended) L32R */ +#define XCHAL_HAVE_CONST16 0 /* CONST16 instruction */ +#define XCHAL_HAVE_ADDX 1 /* ADDX#/SUBX# instructions */ +#define XCHAL_HAVE_WIDE_BRANCHES 0 /* B*.W18 or B*.W15 instr's */ +#define XCHAL_HAVE_PREDICTED_BRANCHES 0 /* B[EQ/EQZ/NE/NEZ]T instr's */ +#define XCHAL_HAVE_CALL4AND12 1 /* (obsolete option) */ +#define XCHAL_HAVE_ABS 1 /* ABS instruction */ +/*#define XCHAL_HAVE_POPC 0*/ /* POPC instruction */ +/*#define XCHAL_HAVE_CRC 0*/ /* CRC instruction */ +#define XCHAL_HAVE_RELEASE_SYNC 1 /* L32AI/S32RI instructions */ +#define XCHAL_HAVE_S32C1I 1 /* S32C1I instruction */ +#define XCHAL_HAVE_SPECULATION 0 /* speculation */ +#define XCHAL_HAVE_FULL_RESET 1 /* all regs/state reset */ +#define XCHAL_NUM_CONTEXTS 1 /* */ +#define XCHAL_NUM_MISC_REGS 4 /* num of scratch regs (0..4) */ +#define XCHAL_HAVE_TAP_MASTER 0 /* JTAG TAP control instr's */ +#define XCHAL_HAVE_PRID 1 /* processor ID register */ +#define XCHAL_HAVE_EXTERN_REGS 1 /* WER/RER instructions */ +#define XCHAL_HAVE_MX 0 /* MX core (Tensilica internal) */ +#define XCHAL_HAVE_MP_INTERRUPTS 0 /* interrupt distributor port */ +#define XCHAL_HAVE_MP_RUNSTALL 0 /* core RunStall control port */ +#define XCHAL_HAVE_PSO 0 /* Power Shut-Off */ +#define XCHAL_HAVE_PSO_CDM 0 /* core/debug/mem pwr domains */ +#define XCHAL_HAVE_PSO_FULL_RETENTION 0 /* all regs preserved on PSO */ +#define XCHAL_HAVE_THREADPTR 1 /* THREADPTR register */ +#define XCHAL_HAVE_BOOLEANS 1 /* boolean registers */ +#define XCHAL_HAVE_CP 1 /* CPENABLE reg (coprocessor) */ +#define XCHAL_CP_MAXCFG 8 /* max allowed cp id plus one */ +#define XCHAL_HAVE_MAC16 1 /* MAC16 package */ + +#define XCHAL_HAVE_FUSION 0 /* Fusion*/ +#define XCHAL_HAVE_FUSION_FP 0 /* Fusion FP option */ +#define XCHAL_HAVE_FUSION_LOW_POWER 0 /* Fusion Low Power option */ +#define XCHAL_HAVE_FUSION_AES 0 /* Fusion BLE/Wifi AES-128 CCM option */ +#define XCHAL_HAVE_FUSION_CONVENC 0 /* Fusion Conv Encode option */ +#define XCHAL_HAVE_FUSION_LFSR_CRC 0 /* Fusion LFSR-CRC option */ +#define XCHAL_HAVE_FUSION_BITOPS 0 /* Fusion Bit Operations Support option */ +#define XCHAL_HAVE_FUSION_AVS 0 /* Fusion AVS option */ +#define XCHAL_HAVE_FUSION_16BIT_BASEBAND 0 /* Fusion 16-bit Baseband option */ +#define XCHAL_HAVE_HIFIPRO 0 /* HiFiPro Audio Engine pkg */ +#define XCHAL_HAVE_HIFI4 0 /* HiFi4 Audio Engine pkg */ +#define XCHAL_HAVE_HIFI4_VFPU 0 /* HiFi4 Audio Engine VFPU option */ +#define XCHAL_HAVE_HIFI3 0 /* HiFi3 Audio Engine pkg */ +#define XCHAL_HAVE_HIFI3_VFPU 0 /* HiFi3 Audio Engine VFPU option */ +#define XCHAL_HAVE_HIFI2 0 /* HiFi2 Audio Engine pkg */ +#define XCHAL_HAVE_HIFI2EP 0 /* HiFi2EP */ +#define XCHAL_HAVE_HIFI_MINI 0 + + +#define XCHAL_HAVE_VECTORFPU2005 0 /* vector or user floating-point pkg */ +#define XCHAL_HAVE_USER_DPFPU 0 /* user DP floating-point pkg */ +#define XCHAL_HAVE_USER_SPFPU 0 /* user DP floating-point pkg */ +#define XCHAL_HAVE_FP 0 /* single prec floating point */ +#define XCHAL_HAVE_FP_DIV 0 /* FP with DIV instructions */ +#define XCHAL_HAVE_FP_RECIP 0 /* FP with RECIP instructions */ +#define XCHAL_HAVE_FP_SQRT 0 /* FP with SQRT instructions */ +#define XCHAL_HAVE_FP_RSQRT 0 /* FP with RSQRT instructions */ +#define XCHAL_HAVE_DFP 0 /* double precision FP pkg */ +#define XCHAL_HAVE_DFP_DIV 0 /* DFP with DIV instructions */ +#define XCHAL_HAVE_DFP_RECIP 0 /* DFP with RECIP instructions*/ +#define XCHAL_HAVE_DFP_SQRT 0 /* DFP with SQRT instructions */ +#define XCHAL_HAVE_DFP_RSQRT 0 /* DFP with RSQRT instructions*/ +#define XCHAL_HAVE_DFP_ACCEL 0 /* double precision FP acceleration pkg */ +#define XCHAL_HAVE_DFP_accel XCHAL_HAVE_DFP_ACCEL /* for backward compatibility */ + +#define XCHAL_HAVE_DFPU_SINGLE_ONLY 0 /* DFPU Coprocessor, single precision only */ +#define XCHAL_HAVE_DFPU_SINGLE_DOUBLE 0 /* DFPU Coprocessor, single and double precision */ +#define XCHAL_HAVE_VECTRA1 0 /* Vectra I pkg */ +#define XCHAL_HAVE_VECTRALX 0 /* Vectra LX pkg */ +#define XCHAL_HAVE_PDX4 0 /* PDX4 */ +#define XCHAL_HAVE_CONNXD2 0 /* ConnX D2 pkg */ +#define XCHAL_HAVE_CONNXD2_DUALLSFLIX 0 /* ConnX D2 & Dual LoadStore Flix */ +#define XCHAL_HAVE_BBE16 0 /* ConnX BBE16 pkg */ +#define XCHAL_HAVE_BBE16_RSQRT 0 /* BBE16 & vector recip sqrt */ +#define XCHAL_HAVE_BBE16_VECDIV 0 /* BBE16 & vector divide */ +#define XCHAL_HAVE_BBE16_DESPREAD 0 /* BBE16 & despread */ +#define XCHAL_HAVE_BBENEP 0 /* ConnX BBENEP pkgs */ +#define XCHAL_HAVE_BSP3 0 /* ConnX BSP3 pkg */ +#define XCHAL_HAVE_BSP3_TRANSPOSE 0 /* BSP3 & transpose32x32 */ +#define XCHAL_HAVE_SSP16 0 /* ConnX SSP16 pkg */ +#define XCHAL_HAVE_SSP16_VITERBI 0 /* SSP16 & viterbi */ +#define XCHAL_HAVE_TURBO16 0 /* ConnX Turbo16 pkg */ +#define XCHAL_HAVE_BBP16 0 /* ConnX BBP16 pkg */ +#define XCHAL_HAVE_FLIX3 0 /* basic 3-way FLIX option */ +#define XCHAL_HAVE_GRIVPEP 0 /* GRIVPEP is General Release of IVPEP */ +#define XCHAL_HAVE_GRIVPEP_HISTOGRAM 0 /* Histogram option on GRIVPEP */ + + +/*---------------------------------------------------------------------- + MISC + ----------------------------------------------------------------------*/ + +#define XCHAL_NUM_LOADSTORE_UNITS 1 /* load/store units */ +#define XCHAL_NUM_WRITEBUFFER_ENTRIES 8 /* size of write buffer */ +#define XCHAL_INST_FETCH_WIDTH 8 /* instr-fetch width in bytes */ +#define XCHAL_DATA_WIDTH 16 /* data width in bytes */ +#define XCHAL_DATA_PIPE_DELAY 1 /* d-side pipeline delay + (1 = 5-stage, 2 = 7-stage) */ +#define XCHAL_CLOCK_GATING_GLOBAL 0 /* global clock gating */ +#define XCHAL_CLOCK_GATING_FUNCUNIT 0 /* funct. unit clock gating */ +/* In T1050, applies to selected core load and store instructions (see ISA): */ +#define XCHAL_UNALIGNED_LOAD_EXCEPTION 1 /* unaligned loads cause exc. */ +#define XCHAL_UNALIGNED_STORE_EXCEPTION 1 /* unaligned stores cause exc.*/ +#define XCHAL_UNALIGNED_LOAD_HW 0 /* unaligned loads work in hw */ +#define XCHAL_UNALIGNED_STORE_HW 0 /* unaligned stores work in hw*/ + +#define XCHAL_SW_VERSION 1100002 /* sw version of this header */ + +#define XCHAL_CORE_ID "xt_lnx" /* alphanum core name + (CoreID) set in the Xtensa + Processor Generator */ + +#define XCHAL_BUILD_UNIQUE_ID 0x00057D54 /* 22-bit sw build ID */ + +/* + * These definitions describe the hardware targeted by this software. + */ +#define XCHAL_HW_CONFIGID0 0xC1B3FFFE /* ConfigID hi 32 bits*/ +#define XCHAL_HW_CONFIGID1 0x1C857D54 /* ConfigID lo 32 bits*/ +#define XCHAL_HW_VERSION_NAME "LX6.0.2" /* full version name */ +#define XCHAL_HW_VERSION_MAJOR 2600 /* major ver# of targeted hw */ +#define XCHAL_HW_VERSION_MINOR 2 /* minor ver# of targeted hw */ +#define XCHAL_HW_VERSION 260002 /* major*100+minor */ +#define XCHAL_HW_REL_LX6 1 +#define XCHAL_HW_REL_LX6_0 1 +#define XCHAL_HW_REL_LX6_0_2 1 +#define XCHAL_HW_CONFIGID_RELIABLE 1 +/* If software targets a *range* of hardware versions, these are the bounds: */ +#define XCHAL_HW_MIN_VERSION_MAJOR 2600 /* major v of earliest tgt hw */ +#define XCHAL_HW_MIN_VERSION_MINOR 2 /* minor v of earliest tgt hw */ +#define XCHAL_HW_MIN_VERSION 260002 /* earliest targeted hw */ +#define XCHAL_HW_MAX_VERSION_MAJOR 2600 /* major v of latest tgt hw */ +#define XCHAL_HW_MAX_VERSION_MINOR 2 /* minor v of latest tgt hw */ +#define XCHAL_HW_MAX_VERSION 260002 /* latest targeted hw */ + + +/*---------------------------------------------------------------------- + CACHE + ----------------------------------------------------------------------*/ + +#define XCHAL_ICACHE_LINESIZE 64 /* I-cache line size in bytes */ +#define XCHAL_DCACHE_LINESIZE 64 /* D-cache line size in bytes */ +#define XCHAL_ICACHE_LINEWIDTH 6 /* log2(I line size in bytes) */ +#define XCHAL_DCACHE_LINEWIDTH 6 /* log2(D line size in bytes) */ + +#define XCHAL_ICACHE_SIZE 65536 /* I-cache size in bytes or 0 */ +#define XCHAL_DCACHE_SIZE 16384 /* D-cache size in bytes or 0 */ + +#define XCHAL_DCACHE_IS_WRITEBACK 1 /* writeback feature */ +#define XCHAL_DCACHE_IS_COHERENT 0 /* MP coherence feature */ + +#define XCHAL_HAVE_PREFETCH 0 /* PREFCTL register */ +#define XCHAL_HAVE_PREFETCH_L1 0 /* prefetch to L1 dcache */ +#define XCHAL_PREFETCH_CASTOUT_LINES 0 /* dcache pref. castout bufsz */ +#define XCHAL_PREFETCH_ENTRIES 0 /* cache prefetch entries */ +#define XCHAL_PREFETCH_BLOCK_ENTRIES 0 /* prefetch block streams */ +#define XCHAL_HAVE_CACHE_BLOCKOPS 0 /* block prefetch for caches */ +#define XCHAL_HAVE_ICACHE_TEST 1 /* Icache test instructions */ +#define XCHAL_HAVE_DCACHE_TEST 1 /* Dcache test instructions */ +#define XCHAL_HAVE_ICACHE_DYN_WAYS 0 /* Icache dynamic way support */ +#define XCHAL_HAVE_DCACHE_DYN_WAYS 0 /* Dcache dynamic way support */ + + + + +/**************************************************************************** + Parameters Useful for PRIVILEGED (Supervisory or Non-Virtualized) Code + ****************************************************************************/ + + +#ifndef XTENSA_HAL_NON_PRIVILEGED_ONLY + +/*---------------------------------------------------------------------- + CACHE + ----------------------------------------------------------------------*/ + +#define XCHAL_HAVE_PIF 1 /* any outbound PIF present */ + +/* If present, cache size in bytes == (ways * 2^(linewidth + setwidth)). */ + +/* Number of cache sets in log2(lines per way): */ +#define XCHAL_ICACHE_SETWIDTH 8 +#define XCHAL_DCACHE_SETWIDTH 6 + +/* Cache set associativity (number of ways): */ +#define XCHAL_ICACHE_WAYS 4 +#define XCHAL_DCACHE_WAYS 4 + +/* Cache features: */ +#define XCHAL_ICACHE_LINE_LOCKABLE 1 +#define XCHAL_DCACHE_LINE_LOCKABLE 1 +#define XCHAL_ICACHE_ECC_PARITY 0 +#define XCHAL_DCACHE_ECC_PARITY 0 + +/* Cache access size in bytes (affects operation of SICW instruction): */ +#define XCHAL_ICACHE_ACCESS_SIZE 16 +#define XCHAL_DCACHE_ACCESS_SIZE 16 + +#define XCHAL_DCACHE_BANKS 1 /* number of banks */ + +/* Number of encoded cache attr bits (see <xtensa/hal.h> for decoded bits): */ +#define XCHAL_CA_BITS 4 + +/* Whether MEMCTL register has anything useful */ +#define XCHAL_USE_MEMCTL (((XCHAL_LOOP_BUFFER_SIZE > 0) || \ + XCHAL_DCACHE_IS_COHERENT || \ + XCHAL_HAVE_ICACHE_DYN_WAYS || \ + XCHAL_HAVE_DCACHE_DYN_WAYS) && \ + (XCHAL_HW_MIN_VERSION >= XTENSA_HWVERSION_RE_2012_0)) + + +/*---------------------------------------------------------------------- + INTERNAL I/D RAM/ROMs and XLMI + ----------------------------------------------------------------------*/ + +#define XCHAL_NUM_INSTROM 0 /* number of core instr. ROMs */ +#define XCHAL_NUM_INSTRAM 0 /* number of core instr. RAMs */ +#define XCHAL_NUM_DATAROM 0 /* number of core data ROMs */ +#define XCHAL_NUM_DATARAM 0 /* number of core data RAMs */ +#define XCHAL_NUM_URAM 0 /* number of core unified RAMs*/ +#define XCHAL_NUM_XLMI 0 /* number of core XLMI ports */ + +#define XCHAL_HAVE_IMEM_LOADSTORE 1 /* can load/store to IROM/IRAM*/ + + +/*---------------------------------------------------------------------- + INTERRUPTS and TIMERS + ----------------------------------------------------------------------*/ + +#define XCHAL_HAVE_INTERRUPTS 1 /* interrupt option */ +#define XCHAL_HAVE_HIGHPRI_INTERRUPTS 1 /* med/high-pri. interrupts */ +#define XCHAL_HAVE_NMI 1 /* non-maskable interrupt */ +#define XCHAL_HAVE_CCOUNT 1 /* CCOUNT reg. (timer option) */ +#define XCHAL_NUM_TIMERS 3 /* number of CCOMPAREn regs */ +#define XCHAL_NUM_INTERRUPTS 22 /* number of interrupts */ +#define XCHAL_NUM_INTERRUPTS_LOG2 5 /* ceil(log2(NUM_INTERRUPTS)) */ +#define XCHAL_NUM_EXTINTERRUPTS 16 /* num of external interrupts */ +#define XCHAL_NUM_INTLEVELS 6 /* number of interrupt levels + (not including level zero) */ +#define XCHAL_EXCM_LEVEL 3 /* level masked by PS.EXCM */ + /* (always 1 in XEA1; levels 2 .. EXCM_LEVEL are "medium priority") */ + +/* Masks of interrupts at each interrupt level: */ +#define XCHAL_INTLEVEL1_MASK 0x001F00BF +#define XCHAL_INTLEVEL2_MASK 0x00001140 +#define XCHAL_INTLEVEL3_MASK 0x00200E00 +#define XCHAL_INTLEVEL4_MASK 0x00008000 +#define XCHAL_INTLEVEL5_MASK 0x00002000 +#define XCHAL_INTLEVEL6_MASK 0x00000000 +#define XCHAL_INTLEVEL7_MASK 0x00004000 + +/* Masks of interrupts at each range 1..n of interrupt levels: */ +#define XCHAL_INTLEVEL1_ANDBELOW_MASK 0x001F00BF +#define XCHAL_INTLEVEL2_ANDBELOW_MASK 0x001F11FF +#define XCHAL_INTLEVEL3_ANDBELOW_MASK 0x003F1FFF +#define XCHAL_INTLEVEL4_ANDBELOW_MASK 0x003F9FFF +#define XCHAL_INTLEVEL5_ANDBELOW_MASK 0x003FBFFF +#define XCHAL_INTLEVEL6_ANDBELOW_MASK 0x003FBFFF +#define XCHAL_INTLEVEL7_ANDBELOW_MASK 0x003FFFFF + +/* Level of each interrupt: */ +#define XCHAL_INT0_LEVEL 1 +#define XCHAL_INT1_LEVEL 1 +#define XCHAL_INT2_LEVEL 1 +#define XCHAL_INT3_LEVEL 1 +#define XCHAL_INT4_LEVEL 1 +#define XCHAL_INT5_LEVEL 1 +#define XCHAL_INT6_LEVEL 2 +#define XCHAL_INT7_LEVEL 1 +#define XCHAL_INT8_LEVEL 2 +#define XCHAL_INT9_LEVEL 3 +#define XCHAL_INT10_LEVEL 3 +#define XCHAL_INT11_LEVEL 3 +#define XCHAL_INT12_LEVEL 2 +#define XCHAL_INT13_LEVEL 5 +#define XCHAL_INT14_LEVEL 7 +#define XCHAL_INT15_LEVEL 4 +#define XCHAL_INT16_LEVEL 1 +#define XCHAL_INT17_LEVEL 1 +#define XCHAL_INT18_LEVEL 1 +#define XCHAL_INT19_LEVEL 1 +#define XCHAL_INT20_LEVEL 1 +#define XCHAL_INT21_LEVEL 3 +#define XCHAL_DEBUGLEVEL 6 /* debug interrupt level */ +#define XCHAL_HAVE_DEBUG_EXTERN_INT 1 /* OCD external db interrupt */ +#define XCHAL_NMILEVEL 7 /* NMI "level" (for use with + EXCSAVE/EPS/EPC_n, RFI n) */ + +/* Type of each interrupt: */ +#define XCHAL_INT0_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT1_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT2_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT3_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT4_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT5_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT6_TYPE XTHAL_INTTYPE_TIMER +#define XCHAL_INT7_TYPE XTHAL_INTTYPE_SOFTWARE +#define XCHAL_INT8_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT9_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT10_TYPE XTHAL_INTTYPE_TIMER +#define XCHAL_INT11_TYPE XTHAL_INTTYPE_SOFTWARE +#define XCHAL_INT12_TYPE XTHAL_INTTYPE_EXTERN_EDGE +#define XCHAL_INT13_TYPE XTHAL_INTTYPE_TIMER +#define XCHAL_INT14_TYPE XTHAL_INTTYPE_NMI +#define XCHAL_INT15_TYPE XTHAL_INTTYPE_PROFILING +#define XCHAL_INT16_TYPE XTHAL_INTTYPE_EXTERN_EDGE +#define XCHAL_INT17_TYPE XTHAL_INTTYPE_EXTERN_EDGE +#define XCHAL_INT18_TYPE XTHAL_INTTYPE_EXTERN_EDGE +#define XCHAL_INT19_TYPE XTHAL_INTTYPE_EXTERN_EDGE +#define XCHAL_INT20_TYPE XTHAL_INTTYPE_EXTERN_EDGE +#define XCHAL_INT21_TYPE XTHAL_INTTYPE_EXTERN_EDGE + +/* Masks of interrupts for each type of interrupt: */ +#define XCHAL_INTTYPE_MASK_UNCONFIGURED 0xFFC00000 +#define XCHAL_INTTYPE_MASK_SOFTWARE 0x00000880 +#define XCHAL_INTTYPE_MASK_EXTERN_EDGE 0x003F1000 +#define XCHAL_INTTYPE_MASK_EXTERN_LEVEL 0x0000033F +#define XCHAL_INTTYPE_MASK_TIMER 0x00002440 +#define XCHAL_INTTYPE_MASK_NMI 0x00004000 +#define XCHAL_INTTYPE_MASK_WRITE_ERROR 0x00000000 +#define XCHAL_INTTYPE_MASK_PROFILING 0x00008000 + +/* Interrupt numbers assigned to specific interrupt sources: */ +#define XCHAL_TIMER0_INTERRUPT 6 /* CCOMPARE0 */ +#define XCHAL_TIMER1_INTERRUPT 10 /* CCOMPARE1 */ +#define XCHAL_TIMER2_INTERRUPT 13 /* CCOMPARE2 */ +#define XCHAL_TIMER3_INTERRUPT XTHAL_TIMER_UNCONFIGURED +#define XCHAL_NMI_INTERRUPT 14 /* non-maskable interrupt */ +#define XCHAL_PROFILING_INTERRUPT 15 /* profiling interrupt */ + +/* Interrupt numbers for levels at which only one interrupt is configured: */ +#define XCHAL_INTLEVEL4_NUM 15 +#define XCHAL_INTLEVEL5_NUM 13 +#define XCHAL_INTLEVEL7_NUM 14 +/* (There are many interrupts each at level(s) 1, 2, 3.) */ + + +/* + * External interrupt mapping. + * These macros describe how Xtensa processor interrupt numbers + * (as numbered internally, eg. in INTERRUPT and INTENABLE registers) + * map to external BInterrupt<n> pins, for those interrupts + * configured as external (level-triggered, edge-triggered, or NMI). + * See the Xtensa processor databook for more details. + */ + +/* Core interrupt numbers mapped to each EXTERNAL BInterrupt pin number: */ +#define XCHAL_EXTINT0_NUM 0 /* (intlevel 1) */ +#define XCHAL_EXTINT1_NUM 1 /* (intlevel 1) */ +#define XCHAL_EXTINT2_NUM 2 /* (intlevel 1) */ +#define XCHAL_EXTINT3_NUM 3 /* (intlevel 1) */ +#define XCHAL_EXTINT4_NUM 4 /* (intlevel 1) */ +#define XCHAL_EXTINT5_NUM 5 /* (intlevel 1) */ +#define XCHAL_EXTINT6_NUM 8 /* (intlevel 2) */ +#define XCHAL_EXTINT7_NUM 9 /* (intlevel 3) */ +#define XCHAL_EXTINT8_NUM 12 /* (intlevel 2) */ +#define XCHAL_EXTINT9_NUM 14 /* (intlevel 7) */ +#define XCHAL_EXTINT10_NUM 16 /* (intlevel 1) */ +#define XCHAL_EXTINT11_NUM 17 /* (intlevel 1) */ +#define XCHAL_EXTINT12_NUM 18 /* (intlevel 1) */ +#define XCHAL_EXTINT13_NUM 19 /* (intlevel 1) */ +#define XCHAL_EXTINT14_NUM 20 /* (intlevel 1) */ +#define XCHAL_EXTINT15_NUM 21 /* (intlevel 3) */ +/* EXTERNAL BInterrupt pin numbers mapped to each core interrupt number: */ +#define XCHAL_INT0_EXTNUM 0 /* (intlevel 1) */ +#define XCHAL_INT1_EXTNUM 1 /* (intlevel 1) */ +#define XCHAL_INT2_EXTNUM 2 /* (intlevel 1) */ +#define XCHAL_INT3_EXTNUM 3 /* (intlevel 1) */ +#define XCHAL_INT4_EXTNUM 4 /* (intlevel 1) */ +#define XCHAL_INT5_EXTNUM 5 /* (intlevel 1) */ +#define XCHAL_INT8_EXTNUM 6 /* (intlevel 2) */ +#define XCHAL_INT9_EXTNUM 7 /* (intlevel 3) */ +#define XCHAL_INT12_EXTNUM 8 /* (intlevel 2) */ +#define XCHAL_INT14_EXTNUM 9 /* (intlevel 7) */ +#define XCHAL_INT16_EXTNUM 10 /* (intlevel 1) */ +#define XCHAL_INT17_EXTNUM 11 /* (intlevel 1) */ +#define XCHAL_INT18_EXTNUM 12 /* (intlevel 1) */ +#define XCHAL_INT19_EXTNUM 13 /* (intlevel 1) */ +#define XCHAL_INT20_EXTNUM 14 /* (intlevel 1) */ +#define XCHAL_INT21_EXTNUM 15 /* (intlevel 3) */ + + +/*---------------------------------------------------------------------- + EXCEPTIONS and VECTORS + ----------------------------------------------------------------------*/ + +#define XCHAL_XEA_VERSION 2 /* Xtensa Exception Architecture + number: 1 == XEA1 (old) + 2 == XEA2 (new) + 0 == XEAX (extern) or TX */ +#define XCHAL_HAVE_XEA1 0 /* Exception Architecture 1 */ +#define XCHAL_HAVE_XEA2 1 /* Exception Architecture 2 */ +#define XCHAL_HAVE_XEAX 0 /* External Exception Arch. */ +#define XCHAL_HAVE_EXCEPTIONS 1 /* exception option */ +#define XCHAL_HAVE_HALT 0 /* halt architecture option */ +#define XCHAL_HAVE_BOOTLOADER 0 /* boot loader (for TX) */ +#define XCHAL_HAVE_MEM_ECC_PARITY 0 /* local memory ECC/parity */ +#define XCHAL_HAVE_VECTOR_SELECT 1 /* relocatable vectors */ +#define XCHAL_HAVE_VECBASE 1 /* relocatable vectors */ +#define XCHAL_VECBASE_RESET_VADDR 0x00002000 /* VECBASE reset value */ +#define XCHAL_VECBASE_RESET_PADDR 0x00002000 +#define XCHAL_RESET_VECBASE_OVERLAP 0 + +#define XCHAL_RESET_VECTOR0_VADDR 0xFE000000 +#define XCHAL_RESET_VECTOR0_PADDR 0xFE000000 +#define XCHAL_RESET_VECTOR1_VADDR 0x00001000 +#define XCHAL_RESET_VECTOR1_PADDR 0x00001000 +#define XCHAL_RESET_VECTOR_VADDR 0xFE000000 +#define XCHAL_RESET_VECTOR_PADDR 0xFE000000 +#define XCHAL_USER_VECOFS 0x00000340 +#define XCHAL_USER_VECTOR_VADDR 0x00002340 +#define XCHAL_USER_VECTOR_PADDR 0x00002340 +#define XCHAL_KERNEL_VECOFS 0x00000300 +#define XCHAL_KERNEL_VECTOR_VADDR 0x00002300 +#define XCHAL_KERNEL_VECTOR_PADDR 0x00002300 +#define XCHAL_DOUBLEEXC_VECOFS 0x000003C0 +#define XCHAL_DOUBLEEXC_VECTOR_VADDR 0x000023C0 +#define XCHAL_DOUBLEEXC_VECTOR_PADDR 0x000023C0 +#define XCHAL_WINDOW_OF4_VECOFS 0x00000000 +#define XCHAL_WINDOW_UF4_VECOFS 0x00000040 +#define XCHAL_WINDOW_OF8_VECOFS 0x00000080 +#define XCHAL_WINDOW_UF8_VECOFS 0x000000C0 +#define XCHAL_WINDOW_OF12_VECOFS 0x00000100 +#define XCHAL_WINDOW_UF12_VECOFS 0x00000140 +#define XCHAL_WINDOW_VECTORS_VADDR 0x00002000 +#define XCHAL_WINDOW_VECTORS_PADDR 0x00002000 +#define XCHAL_INTLEVEL2_VECOFS 0x00000180 +#define XCHAL_INTLEVEL2_VECTOR_VADDR 0x00002180 +#define XCHAL_INTLEVEL2_VECTOR_PADDR 0x00002180 +#define XCHAL_INTLEVEL3_VECOFS 0x000001C0 +#define XCHAL_INTLEVEL3_VECTOR_VADDR 0x000021C0 +#define XCHAL_INTLEVEL3_VECTOR_PADDR 0x000021C0 +#define XCHAL_INTLEVEL4_VECOFS 0x00000200 +#define XCHAL_INTLEVEL4_VECTOR_VADDR 0x00002200 +#define XCHAL_INTLEVEL4_VECTOR_PADDR 0x00002200 +#define XCHAL_INTLEVEL5_VECOFS 0x00000240 +#define XCHAL_INTLEVEL5_VECTOR_VADDR 0x00002240 +#define XCHAL_INTLEVEL5_VECTOR_PADDR 0x00002240 +#define XCHAL_INTLEVEL6_VECOFS 0x00000280 +#define XCHAL_INTLEVEL6_VECTOR_VADDR 0x00002280 +#define XCHAL_INTLEVEL6_VECTOR_PADDR 0x00002280 +#define XCHAL_DEBUG_VECOFS XCHAL_INTLEVEL6_VECOFS +#define XCHAL_DEBUG_VECTOR_VADDR XCHAL_INTLEVEL6_VECTOR_VADDR +#define XCHAL_DEBUG_VECTOR_PADDR XCHAL_INTLEVEL6_VECTOR_PADDR +#define XCHAL_NMI_VECOFS 0x000002C0 +#define XCHAL_NMI_VECTOR_VADDR 0x000022C0 +#define XCHAL_NMI_VECTOR_PADDR 0x000022C0 +#define XCHAL_INTLEVEL7_VECOFS XCHAL_NMI_VECOFS +#define XCHAL_INTLEVEL7_VECTOR_VADDR XCHAL_NMI_VECTOR_VADDR +#define XCHAL_INTLEVEL7_VECTOR_PADDR XCHAL_NMI_VECTOR_PADDR + + +/*---------------------------------------------------------------------- + DEBUG MODULE + ----------------------------------------------------------------------*/ + +/* Misc */ +#define XCHAL_HAVE_DEBUG_ERI 1 /* ERI to debug module */ +#define XCHAL_HAVE_DEBUG_APB 1 /* APB to debug module */ +#define XCHAL_HAVE_DEBUG_JTAG 1 /* JTAG to debug module */ + +/* On-Chip Debug (OCD) */ +#define XCHAL_HAVE_OCD 1 /* OnChipDebug option */ +#define XCHAL_NUM_IBREAK 2 /* number of IBREAKn regs */ +#define XCHAL_NUM_DBREAK 2 /* number of DBREAKn regs */ +#define XCHAL_HAVE_OCD_DIR_ARRAY 0 /* faster OCD option (to LX4) */ +#define XCHAL_HAVE_OCD_LS32DDR 1 /* L32DDR/S32DDR (faster OCD) */ + +/* TRAX (in core) */ +#define XCHAL_HAVE_TRAX 1 /* TRAX in debug module */ +#define XCHAL_TRAX_MEM_SIZE 262144 /* TRAX memory size in bytes */ +#define XCHAL_TRAX_MEM_SHAREABLE 1 /* start/end regs; ready sig. */ +#define XCHAL_TRAX_ATB_WIDTH 0 /* ATB width (bits), 0=no ATB */ +#define XCHAL_TRAX_TIME_WIDTH 0 /* timestamp bitwidth, 0=none */ + +/* Perf counters */ +#define XCHAL_NUM_PERF_COUNTERS 8 /* performance counters */ + + +/*---------------------------------------------------------------------- + MMU + ----------------------------------------------------------------------*/ + +/* See core-matmap.h header file for more details. */ + +#define XCHAL_HAVE_TLBS 1 /* inverse of HAVE_CACHEATTR */ +#define XCHAL_HAVE_SPANNING_WAY 1 /* one way maps I+D 4GB vaddr */ +#define XCHAL_SPANNING_WAY 6 /* TLB spanning way number */ +#define XCHAL_HAVE_IDENTITY_MAP 0 /* vaddr == paddr always */ +#define XCHAL_HAVE_CACHEATTR 0 /* CACHEATTR register present */ +#define XCHAL_HAVE_MIMIC_CACHEATTR 0 /* region protection */ +#define XCHAL_HAVE_XLT_CACHEATTR 0 /* region prot. w/translation */ +#define XCHAL_HAVE_PTP_MMU 1 /* full MMU (with page table + [autorefill] and protection) + usable for an MMU-based OS */ +/* If none of the above last 4 are set, it's a custom TLB configuration. */ +#define XCHAL_ITLB_ARF_ENTRIES_LOG2 2 /* log2(autorefill way size) */ +#define XCHAL_DTLB_ARF_ENTRIES_LOG2 2 /* log2(autorefill way size) */ + +#define XCHAL_MMU_ASID_BITS 8 /* number of bits in ASIDs */ +#define XCHAL_MMU_RINGS 4 /* number of rings (1..4) */ +#define XCHAL_MMU_RING_BITS 2 /* num of bits in RING field */ + +#endif /* !XTENSA_HAL_NON_PRIVILEGED_ONLY */ + + +#endif /* _XTENSA_CORE_CONFIGURATION_H */ + diff --git a/arch/xtensa/variants/csp/include/variant/tie-asm.h b/arch/xtensa/variants/csp/include/variant/tie-asm.h new file mode 100644 index 000000000000..ba773c4a26a2 --- /dev/null +++ b/arch/xtensa/variants/csp/include/variant/tie-asm.h @@ -0,0 +1,194 @@ +/* + * tie-asm.h -- compile-time HAL assembler definitions dependent on CORE & TIE + * + * NOTE: This header file is not meant to be included directly. + */ + +/* This header file contains assembly-language definitions (assembly + macros, etc.) for this specific Xtensa processor's TIE extensions + and options. It is customized to this Xtensa processor configuration. + + Copyright (c) 1999-2015 Cadence Design Systems Inc. + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to + permit persons to whom the Software is furnished to do so, subject to + the following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. + IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY + CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, + TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE + SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. */ + +#ifndef _XTENSA_CORE_TIE_ASM_H +#define _XTENSA_CORE_TIE_ASM_H + +/* Selection parameter values for save-area save/restore macros: */ +/* Option vs. TIE: */ +#define XTHAL_SAS_TIE 0x0001 /* custom extension or coprocessor */ +#define XTHAL_SAS_OPT 0x0002 /* optional (and not a coprocessor) */ +#define XTHAL_SAS_ANYOT 0x0003 /* both of the above */ +/* Whether used automatically by compiler: */ +#define XTHAL_SAS_NOCC 0x0004 /* not used by compiler w/o special opts/code */ +#define XTHAL_SAS_CC 0x0008 /* used by compiler without special opts/code */ +#define XTHAL_SAS_ANYCC 0x000C /* both of the above */ +/* ABI handling across function calls: */ +#define XTHAL_SAS_CALR 0x0010 /* caller-saved */ +#define XTHAL_SAS_CALE 0x0020 /* callee-saved */ +#define XTHAL_SAS_GLOB 0x0040 /* global across function calls (in thread) */ +#define XTHAL_SAS_ANYABI 0x0070 /* all of the above three */ +/* Misc */ +#define XTHAL_SAS_ALL 0xFFFF /* include all default NCP contents */ +#define XTHAL_SAS3(optie,ccuse,abi) ( ((optie) & XTHAL_SAS_ANYOT) \ + | ((ccuse) & XTHAL_SAS_ANYCC) \ + | ((abi) & XTHAL_SAS_ANYABI) ) + + + /* + * Macro to store all non-coprocessor (extra) custom TIE and optional state + * (not including zero-overhead loop registers). + * Required parameters: + * ptr Save area pointer address register (clobbered) + * (register must contain a 4 byte aligned address). + * at1..at4 Four temporary address registers (first XCHAL_NCP_NUM_ATMPS + * registers are clobbered, the remaining are unused). + * Optional parameters: + * continue If macro invoked as part of a larger store sequence, set to 1 + * if this is not the first in the sequence. Defaults to 0. + * ofs Offset from start of larger sequence (from value of first ptr + * in sequence) at which to store. Defaults to next available space + * (or 0 if <continue> is 0). + * select Select what category(ies) of registers to store, as a bitmask + * (see XTHAL_SAS_xxx constants). Defaults to all registers. + * alloc Select what category(ies) of registers to allocate; if any + * category is selected here that is not in <select>, space for + * the corresponding registers is skipped without doing any store. + */ + .macro xchal_ncp_store ptr at1 at2 at3 at4 continue=0 ofs=-1 select=XTHAL_SAS_ALL alloc=0 + xchal_sa_start \continue, \ofs + // Optional global registers used by default by the compiler: + .ifeq (XTHAL_SAS_OPT | XTHAL_SAS_CC | XTHAL_SAS_GLOB) & ~(\select) + xchal_sa_align \ptr, 0, 1020, 4, 4 + rur.THREADPTR \at1 // threadptr option + s32i \at1, \ptr, .Lxchal_ofs_+0 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 4 + .elseif ((XTHAL_SAS_OPT | XTHAL_SAS_CC | XTHAL_SAS_GLOB) & ~(\alloc)) == 0 + xchal_sa_align \ptr, 0, 1020, 4, 4 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 4 + .endif + // Optional caller-saved registers used by default by the compiler: + .ifeq (XTHAL_SAS_OPT | XTHAL_SAS_CC | XTHAL_SAS_CALR) & ~(\select) + xchal_sa_align \ptr, 0, 1016, 4, 4 + rsr.ACCLO \at1 // MAC16 option + s32i \at1, \ptr, .Lxchal_ofs_+0 + rsr.ACCHI \at1 // MAC16 option + s32i \at1, \ptr, .Lxchal_ofs_+4 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 8 + .elseif ((XTHAL_SAS_OPT | XTHAL_SAS_CC | XTHAL_SAS_CALR) & ~(\alloc)) == 0 + xchal_sa_align \ptr, 0, 1016, 4, 4 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 8 + .endif + // Optional caller-saved registers not used by default by the compiler: + .ifeq (XTHAL_SAS_OPT | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~(\select) + xchal_sa_align \ptr, 0, 1000, 4, 4 + rsr.BR \at1 // boolean option + s32i \at1, \ptr, .Lxchal_ofs_+0 + rsr.SCOMPARE1 \at1 // conditional store option + s32i \at1, \ptr, .Lxchal_ofs_+4 + rsr.M0 \at1 // MAC16 option + s32i \at1, \ptr, .Lxchal_ofs_+8 + rsr.M1 \at1 // MAC16 option + s32i \at1, \ptr, .Lxchal_ofs_+12 + rsr.M2 \at1 // MAC16 option + s32i \at1, \ptr, .Lxchal_ofs_+16 + rsr.M3 \at1 // MAC16 option + s32i \at1, \ptr, .Lxchal_ofs_+20 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 24 + .elseif ((XTHAL_SAS_OPT | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~(\alloc)) == 0 + xchal_sa_align \ptr, 0, 1000, 4, 4 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 24 + .endif + .endm // xchal_ncp_store + + /* + * Macro to load all non-coprocessor (extra) custom TIE and optional state + * (not including zero-overhead loop registers). + * Required parameters: + * ptr Save area pointer address register (clobbered) + * (register must contain a 4 byte aligned address). + * at1..at4 Four temporary address registers (first XCHAL_NCP_NUM_ATMPS + * registers are clobbered, the remaining are unused). + * Optional parameters: + * continue If macro invoked as part of a larger load sequence, set to 1 + * if this is not the first in the sequence. Defaults to 0. + * ofs Offset from start of larger sequence (from value of first ptr + * in sequence) at which to load. Defaults to next available space + * (or 0 if <continue> is 0). + * select Select what category(ies) of registers to load, as a bitmask + * (see XTHAL_SAS_xxx constants). Defaults to all registers. + * alloc Select what category(ies) of registers to allocate; if any + * category is selected here that is not in <select>, space for + * the corresponding registers is skipped without doing any load. + */ + .macro xchal_ncp_load ptr at1 at2 at3 at4 continue=0 ofs=-1 select=XTHAL_SAS_ALL alloc=0 + xchal_sa_start \continue, \ofs + // Optional global registers used by default by the compiler: + .ifeq (XTHAL_SAS_OPT | XTHAL_SAS_CC | XTHAL_SAS_GLOB) & ~(\select) + xchal_sa_align \ptr, 0, 1020, 4, 4 + l32i \at1, \ptr, .Lxchal_ofs_+0 + wur.THREADPTR \at1 // threadptr option + .set .Lxchal_ofs_, .Lxchal_ofs_ + 4 + .elseif ((XTHAL_SAS_OPT | XTHAL_SAS_CC | XTHAL_SAS_GLOB) & ~(\alloc)) == 0 + xchal_sa_align \ptr, 0, 1020, 4, 4 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 4 + .endif + // Optional caller-saved registers used by default by the compiler: + .ifeq (XTHAL_SAS_OPT | XTHAL_SAS_CC | XTHAL_SAS_CALR) & ~(\select) + xchal_sa_align \ptr, 0, 1016, 4, 4 + l32i \at1, \ptr, .Lxchal_ofs_+0 + wsr.ACCLO \at1 // MAC16 option + l32i \at1, \ptr, .Lxchal_ofs_+4 + wsr.ACCHI \at1 // MAC16 option + .set .Lxchal_ofs_, .Lxchal_ofs_ + 8 + .elseif ((XTHAL_SAS_OPT | XTHAL_SAS_CC | XTHAL_SAS_CALR) & ~(\alloc)) == 0 + xchal_sa_align \ptr, 0, 1016, 4, 4 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 8 + .endif + // Optional caller-saved registers not used by default by the compiler: + .ifeq (XTHAL_SAS_OPT | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~(\select) + xchal_sa_align \ptr, 0, 1000, 4, 4 + l32i \at1, \ptr, .Lxchal_ofs_+0 + wsr.BR \at1 // boolean option + l32i \at1, \ptr, .Lxchal_ofs_+4 + wsr.SCOMPARE1 \at1 // conditional store option + l32i \at1, \ptr, .Lxchal_ofs_+8 + wsr.M0 \at1 // MAC16 option + l32i \at1, \ptr, .Lxchal_ofs_+12 + wsr.M1 \at1 // MAC16 option + l32i \at1, \ptr, .Lxchal_ofs_+16 + wsr.M2 \at1 // MAC16 option + l32i \at1, \ptr, .Lxchal_ofs_+20 + wsr.M3 \at1 // MAC16 option + .set .Lxchal_ofs_, .Lxchal_ofs_ + 24 + .elseif ((XTHAL_SAS_OPT | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~(\alloc)) == 0 + xchal_sa_align \ptr, 0, 1000, 4, 4 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 24 + .endif + .endm // xchal_ncp_load + + +#define XCHAL_NCP_NUM_ATMPS 1 + +#define XCHAL_SA_NUM_ATMPS 1 + +#endif /*_XTENSA_CORE_TIE_ASM_H*/ + diff --git a/arch/xtensa/variants/csp/include/variant/tie.h b/arch/xtensa/variants/csp/include/variant/tie.h new file mode 100644 index 000000000000..3ce391cfe449 --- /dev/null +++ b/arch/xtensa/variants/csp/include/variant/tie.h @@ -0,0 +1,161 @@ +/* + * tie.h -- compile-time HAL definitions dependent on CORE & TIE configuration + * + * NOTE: This header file is not meant to be included directly. + */ + +/* This header file describes this specific Xtensa processor's TIE extensions + that extend basic Xtensa core functionality. It is customized to this + Xtensa processor configuration. + + Copyright (c) 1999-2015 Cadence Design Systems Inc. + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to + permit persons to whom the Software is furnished to do so, subject to + the following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. + IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY + CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, + TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE + SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. */ + +#ifndef _XTENSA_CORE_TIE_H +#define _XTENSA_CORE_TIE_H + +#define XCHAL_CP_NUM 1 /* number of coprocessors */ +#define XCHAL_CP_MAX 8 /* max CP ID + 1 (0 if none) */ +#define XCHAL_CP_MASK 0x80 /* bitmask of all CPs by ID */ +#define XCHAL_CP_PORT_MASK 0x80 /* bitmask of only port CPs */ + +/* Basic parameters of each coprocessor: */ +#define XCHAL_CP7_NAME "XTIOP" +#define XCHAL_CP7_IDENT XTIOP +#define XCHAL_CP7_SA_SIZE 0 /* size of state save area */ +#define XCHAL_CP7_SA_ALIGN 1 /* min alignment of save area */ +#define XCHAL_CP_ID_XTIOP 7 /* coprocessor ID (0..7) */ + +/* Filler info for unassigned coprocessors, to simplify arrays etc: */ +#define XCHAL_CP0_SA_SIZE 0 +#define XCHAL_CP0_SA_ALIGN 1 +#define XCHAL_CP1_SA_SIZE 0 +#define XCHAL_CP1_SA_ALIGN 1 +#define XCHAL_CP2_SA_SIZE 0 +#define XCHAL_CP2_SA_ALIGN 1 +#define XCHAL_CP3_SA_SIZE 0 +#define XCHAL_CP3_SA_ALIGN 1 +#define XCHAL_CP4_SA_SIZE 0 +#define XCHAL_CP4_SA_ALIGN 1 +#define XCHAL_CP5_SA_SIZE 0 +#define XCHAL_CP5_SA_ALIGN 1 +#define XCHAL_CP6_SA_SIZE 0 +#define XCHAL_CP6_SA_ALIGN 1 + +/* Save area for non-coprocessor optional and custom (TIE) state: */ +#define XCHAL_NCP_SA_SIZE 36 +#define XCHAL_NCP_SA_ALIGN 4 + +/* Total save area for optional and custom state (NCP + CPn): */ +#define XCHAL_TOTAL_SA_SIZE 48 /* with 16-byte align padding */ +#define XCHAL_TOTAL_SA_ALIGN 4 /* actual minimum alignment */ + +/* + * Detailed contents of save areas. + * NOTE: caller must define the XCHAL_SA_REG macro (not defined here) + * before expanding the XCHAL_xxx_SA_LIST() macros. + * + * XCHAL_SA_REG(s,ccused,abikind,kind,opt,name,galign,align,asize, + * dbnum,base,regnum,bitsz,gapsz,reset,x...) + * + * s = passed from XCHAL_*_LIST(s), eg. to select how to expand + * ccused = set if used by compiler without special options or code + * abikind = 0 (caller-saved), 1 (callee-saved), or 2 (thread-global) + * kind = 0 (special reg), 1 (TIE user reg), or 2 (TIE regfile reg) + * opt = 0 (custom TIE extension or coprocessor), or 1 (optional reg) + * name = lowercase reg name (no quotes) + * galign = group byte alignment (power of 2) (galign >= align) + * align = register byte alignment (power of 2) + * asize = allocated size in bytes (asize*8 == bitsz + gapsz + padsz) + * (not including any pad bytes required to galign this or next reg) + * dbnum = unique target number f/debug (see <xtensa-libdb-macros.h>) + * base = reg shortname w/o index (or sr=special, ur=TIE user reg) + * regnum = reg index in regfile, or special/TIE-user reg number + * bitsz = number of significant bits (regfile width, or ur/sr mask bits) + * gapsz = intervening bits, if bitsz bits not stored contiguously + * (padsz = pad bits at end [TIE regfile] or at msbits [ur,sr] of asize) + * reset = register reset value (or 0 if undefined at reset) + * x = reserved for future use (0 until then) + * + * To filter out certain registers, e.g. to expand only the non-global + * registers used by the compiler, you can do something like this: + * + * #define XCHAL_SA_REG(s,ccused,p...) SELCC##ccused(p) + * #define SELCC0(p...) + * #define SELCC1(abikind,p...) SELAK##abikind(p) + * #define SELAK0(p...) REG(p) + * #define SELAK1(p...) REG(p) + * #define SELAK2(p...) + * #define REG(kind,tie,name,galn,aln,asz,csz,dbnum,base,rnum,bsz,rst,x...) \ + * ...what you want to expand... + */ + +#define XCHAL_NCP_SA_NUM 9 +#define XCHAL_NCP_SA_LIST(s) \ + XCHAL_SA_REG(s,1,2,1,1, threadptr, 4, 4, 4,0x03E7, ur,231, 32,0,0,0) \ + XCHAL_SA_REG(s,1,0,0,1, acclo, 4, 4, 4,0x0210, sr,16 , 32,0,0,0) \ + XCHAL_SA_REG(s,1,0,0,1, acchi, 4, 4, 4,0x0211, sr,17 , 8,0,0,0) \ + XCHAL_SA_REG(s,0,0,0,1, br, 4, 4, 4,0x0204, sr,4 , 16,0,0,0) \ + XCHAL_SA_REG(s,0,0,0,1, scompare1, 4, 4, 4,0x020C, sr,12 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,0,1, m0, 4, 4, 4,0x0220, sr,32 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,0,1, m1, 4, 4, 4,0x0221, sr,33 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,0,1, m2, 4, 4, 4,0x0222, sr,34 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,0,1, m3, 4, 4, 4,0x0223, sr,35 , 32,0,0,0) + +#define XCHAL_CP0_SA_NUM 0 +#define XCHAL_CP0_SA_LIST(s) /* empty */ + +#define XCHAL_CP1_SA_NUM 0 +#define XCHAL_CP1_SA_LIST(s) /* empty */ + +#define XCHAL_CP2_SA_NUM 0 +#define XCHAL_CP2_SA_LIST(s) /* empty */ + +#define XCHAL_CP3_SA_NUM 0 +#define XCHAL_CP3_SA_LIST(s) /* empty */ + +#define XCHAL_CP4_SA_NUM 0 +#define XCHAL_CP4_SA_LIST(s) /* empty */ + +#define XCHAL_CP5_SA_NUM 0 +#define XCHAL_CP5_SA_LIST(s) /* empty */ + +#define XCHAL_CP6_SA_NUM 0 +#define XCHAL_CP6_SA_LIST(s) /* empty */ + +#define XCHAL_CP7_SA_NUM 0 +#define XCHAL_CP7_SA_LIST(s) /* empty */ + +/* Byte length of instruction from its first nibble (op0 field), per FLIX. */ +#define XCHAL_OP0_FORMAT_LENGTHS 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3 +/* Byte length of instruction from its first byte, per FLIX. */ +#define XCHAL_BYTE0_FORMAT_LENGTHS \ + 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3, 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3,\ + 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3, 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3,\ + 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3, 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3,\ + 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3, 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3,\ + 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3, 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3,\ + 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3, 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3,\ + 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3, 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3,\ + 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3, 3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3 + +#endif /*_XTENSA_CORE_TIE_H*/ + |