diff options
Diffstat (limited to 'arch/x86')
154 files changed, 3896 insertions, 2406 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ba2657c4921..7f9a395c525 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -7,11 +7,13 @@ config 64BIT Say no to build a 32-bit kernel - formerly known as i386 config X86_32 - def_bool !64BIT + def_bool y + depends on !64BIT select CLKSRC_I8253 config X86_64 - def_bool 64BIT + def_bool y + depends on 64BIT select X86_DEV_DMA_OPS ### Arch settings @@ -36,6 +38,7 @@ config X86 select HAVE_KRETPROBES select HAVE_OPTPROBES select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FENTRY if X86_64 select HAVE_C_RECORDMCOUNT select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER @@ -60,6 +63,8 @@ config X86 select HAVE_MIXED_BREAKPOINTS_REGS select PERF_EVENTS select HAVE_PERF_EVENTS_NMI + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP select ANON_INODES select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386 select HAVE_CMPXCHG_LOCAL if !M386 @@ -97,9 +102,12 @@ config X86 select KTIME_SCALAR if X86_32 select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER + select HAVE_RCU_USER_QS if X86_64 + select HAVE_IRQ_TIME_ACCOUNTING config INSTRUCTION_DECODER - def_bool (KPROBES || PERF_EVENTS || UPROBES) + def_bool y + depends on KPROBES || PERF_EVENTS || UPROBES config OUTPUT_FORMAT string @@ -127,13 +135,15 @@ config SBUS bool config NEED_DMA_MAP_STATE - def_bool (X86_64 || INTEL_IOMMU || DMA_API_DEBUG) + def_bool y + depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG config NEED_SG_DMA_LENGTH def_bool y config GENERIC_ISA_DMA - def_bool ISA_DMA_API + def_bool y + depends on ISA_DMA_API config GENERIC_BUG def_bool y @@ -150,13 +160,16 @@ config GENERIC_GPIO bool config ARCH_MAY_HAVE_PC_FDC - def_bool ISA_DMA_API + def_bool y + depends on ISA_DMA_API config RWSEM_GENERIC_SPINLOCK - def_bool !X86_XADD + def_bool y + depends on !X86_XADD config RWSEM_XCHGADD_ALGORITHM - def_bool X86_XADD + def_bool y + depends on X86_XADD config GENERIC_CALIBRATE_DELAY def_bool y @@ -746,13 +759,14 @@ config SWIOTLB def_bool y if X86_64 ---help--- Support for software bounce buffers used on x86-64 systems - which don't have a hardware IOMMU (e.g. the current generation - of Intel's x86-64 CPUs). Using this PCI devices which can only - access 32-bits of memory can be used on systems with more than - 3 GB of memory. If unsure, say Y. + which don't have a hardware IOMMU. Using this PCI devices + which can only access 32-bits of memory can be used on systems + with more than 3 GB of memory. + If unsure, say Y. config IOMMU_HELPER - def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU) + def_bool y + depends on CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU config MAXSMP bool "Enable Maximum number of SMP Processors and NUMA Nodes" @@ -796,17 +810,6 @@ config SCHED_MC making when dealing with multi-core CPU chips at a cost of slightly increased overhead in some places. If unsure say N here. -config IRQ_TIME_ACCOUNTING - bool "Fine granularity task level IRQ time accounting" - default n - ---help--- - Select this option to enable fine granularity task irq time - accounting. This is done by reading a timestamp on each - transitions between softirq and hardirq state, so there can be a - small performance impact. - - If in doubt, say N here. - source "kernel/Kconfig.preempt" config X86_UP_APIC @@ -871,6 +874,7 @@ config X86_REROUTE_FOR_BROKEN_BOOT_IRQS config X86_MCE bool "Machine Check / overheating reporting" + default y ---help--- Machine Check support allows the processor to notify the kernel if it detects a problem (e.g. overheating, data corruption). @@ -982,25 +986,25 @@ config X86_REBOOTFIXUPS Say N otherwise. config MICROCODE - tristate "/dev/cpu/microcode - microcode support" + tristate "CPU microcode loading support" select FW_LOADER ---help--- + If you say Y here, you will be able to update the microcode on certain Intel and AMD processors. The Intel support is for the - IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, - Pentium 4, Xeon etc. The AMD support is for family 0x10 and - 0x11 processors, e.g. Opteron, Phenom and Turion 64 Ultra. - You will obviously need the actual microcode binary data itself - which is not shipped with the Linux kernel. + IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, + Xeon etc. The AMD support is for families 0x10 and later. You will + obviously need the actual microcode binary data itself which is not + shipped with the Linux kernel. This option selects the general module only, you need to select at least one vendor specific module as well. - To compile this driver as a module, choose M here: the - module will be called microcode. + To compile this driver as a module, choose M here: the module + will be called microcode. config MICROCODE_INTEL - bool "Intel microcode patch loading support" + bool "Intel microcode loading support" depends on MICROCODE default MICROCODE select FW_LOADER @@ -1013,7 +1017,7 @@ config MICROCODE_INTEL <http://www.urbanmyth.org/microcode/>. config MICROCODE_AMD - bool "AMD microcode patch loading support" + bool "AMD microcode loading support" depends on MICROCODE select FW_LOADER ---help--- @@ -1159,10 +1163,12 @@ config X86_PAE consumes more pagetable space per process. config ARCH_PHYS_ADDR_T_64BIT - def_bool X86_64 || X86_PAE + def_bool y + depends on X86_64 || X86_PAE config ARCH_DMA_ADDR_T_64BIT - def_bool X86_64 || HIGHMEM64G + def_bool y + depends on X86_64 || HIGHMEM64G config DIRECT_GBPAGES bool "Enable 1GB pages for kernel pagetables" if EXPERT @@ -1285,8 +1291,8 @@ config ARCH_SELECT_MEMORY_MODEL depends on ARCH_SPARSEMEM_ENABLE config ARCH_MEMORY_PROBE - def_bool X86_64 - depends on MEMORY_HOTPLUG + def_bool y + depends on X86_64 && MEMORY_HOTPLUG config ARCH_PROC_KCORE_TEXT def_bool y @@ -1487,6 +1493,17 @@ config ARCH_RANDOM If supported, this is a high bandwidth, cryptographically secure hardware random number generator. +config X86_SMAP + def_bool y + prompt "Supervisor Mode Access Prevention" if EXPERT + ---help--- + Supervisor Mode Access Prevention (SMAP) is a security + feature in newer Intel processors. There is a small + performance cost if this enabled and turned on; there is + also a small increase in the kernel size if this is enabled. + + If unsure, say Y. + config EFI bool "EFI runtime service support" depends on ACPI @@ -1527,7 +1544,7 @@ config SECCOMP If unsure, say Y. Only embedded should say N here. config CC_STACKPROTECTOR - bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)" + bool "Enable -fstack-protector buffer overflow detection" ---help--- This option turns on the -fstack-protector GCC feature. This feature puts, at the beginning of functions, a canary value on @@ -1975,7 +1992,6 @@ config PCI_MMCONFIG config PCI_CNB20LE_QUIRK bool "Read CNB20LE Host Bridge Windows" if EXPERT - default n depends on PCI && EXPERIMENTAL help Read the PCI windows out of the CNB20LE host bridge. This allows @@ -2186,18 +2202,18 @@ config COMPAT depends on IA32_EMULATION || X86_X32 select ARCH_WANT_OLD_COMPAT_IPC +if COMPAT config COMPAT_FOR_U64_ALIGNMENT - def_bool COMPAT - depends on X86_64 + def_bool y config SYSVIPC_COMPAT def_bool y - depends on COMPAT && SYSVIPC + depends on SYSVIPC config KEYS_COMPAT - bool - depends on COMPAT && KEYS - default y + def_bool y + depends on KEYS +endif endmenu diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 706e12e9984..f3b86d0df44 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -306,7 +306,8 @@ config X86_INTERNODE_CACHE_SHIFT default X86_L1_CACHE_SHIFT config X86_CMPXCHG - def_bool X86_64 || (X86_32 && !M386) + def_bool y + depends on X86_64 || (X86_32 && !M386) config X86_L1_CACHE_SHIFT int @@ -317,7 +318,7 @@ config X86_L1_CACHE_SHIFT config X86_XADD def_bool y - depends on X86_64 || !M386 + depends on !M386 config X86_PPRO_FENCE bool "PentiumPro memory ordering errata workaround" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index b0c5276861e..474ca35b1bc 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -27,6 +27,10 @@ ifeq ($(CONFIG_X86_32),y) KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return + # Never want PIC in a 32-bit kernel, prevent breakage with GCC built + # with nonstandard options + KBUILD_CFLAGS += -fno-pic + # prevent gcc from keeping the stack 16 byte aligned KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2) @@ -138,7 +142,7 @@ KBUILD_CFLAGS += $(call cc-option,-mno-avx,) KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) -archscripts: +archscripts: scripts_basic $(Q)$(MAKE) $(build)=arch/x86/tools relocs ### diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 5a747dd884d..f7535bedc33 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -57,7 +57,7 @@ KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \ -Wall -Wstrict-prototypes \ -march=i386 -mregparm=3 \ -include $(srctree)/$(src)/code16gcc.h \ - -fno-strict-aliasing -fomit-frame-pointer \ + -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ $(call cc-option, -ffreestanding) \ $(call cc-option, -fno-toplevel-reorder,\ $(call cc-option, -fno-unit-at-a-time)) \ diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index e398bb5d63b..8a84501acb1 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -28,6 +28,9 @@ VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \ $(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o \ $(obj)/piggy.o +$(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone +$(obj)/efi_stub_$(BITS).o: KBUILD_CLFAGS += -fshort-wchar -mno-red-zone + ifeq ($(CONFIG_EFI_STUB), y) VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o endif diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index b3e0227df2c..c760e073963 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -276,8 +276,9 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, nr_gops = size / sizeof(void *); for (i = 0; i < nr_gops; i++) { struct efi_graphics_output_mode_info *info; - efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; - void *pciio; + efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; + bool conout_found = false; + void *dummy; void *h = gop_handle[i]; status = efi_call_phys3(sys_table->boottime->handle_protocol, @@ -285,19 +286,21 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, if (status != EFI_SUCCESS) continue; - efi_call_phys3(sys_table->boottime->handle_protocol, - h, &pciio_proto, &pciio); + status = efi_call_phys3(sys_table->boottime->handle_protocol, + h, &conout_proto, &dummy); + + if (status == EFI_SUCCESS) + conout_found = true; status = efi_call_phys4(gop->query_mode, gop, gop->mode->mode, &size, &info); - if (status == EFI_SUCCESS && (!first_gop || pciio)) { + if (status == EFI_SUCCESS && (!first_gop || conout_found)) { /* - * Apple provide GOPs that are not backed by - * real hardware (they're used to handle - * multiple displays). The workaround is to - * search for a GOP implementing the PCIIO - * protocol, and if one isn't found, to just - * fallback to the first GOP. + * Systems that use the UEFI Console Splitter may + * provide multiple GOP devices, not all of which are + * backed by real hardware. The workaround is to search + * for a GOP implementing the ConOut protocol, and if + * one isn't found, to just fall back to the first GOP. */ width = info->horizontal_resolution; height = info->vertical_resolution; @@ -308,10 +311,10 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, pixels_per_scan_line = info->pixels_per_scan_line; /* - * Once we've found a GOP supporting PCIIO, + * Once we've found a GOP supporting ConOut, * don't bother looking any further. */ - if (pciio) + if (conout_found) break; first_gop = gop; @@ -328,7 +331,6 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, si->lfb_width = width; si->lfb_height = height; si->lfb_base = fb_base; - si->lfb_size = fb_size; si->pages = 1; if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) { @@ -376,6 +378,10 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, si->rsvd_pos = 0; } + si->lfb_size = si->lfb_linelength * si->lfb_height; + + si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; + free_handle: efi_call_phys1(sys_table->boottime->free_pool, gop_handle); return status; diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index 3b6e15627c5..e5b0a8f91c5 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -14,6 +14,10 @@ #define EFI_PAGE_SIZE (1UL << EFI_PAGE_SHIFT) #define EFI_READ_CHUNK_SIZE (1024 * 1024) +#define EFI_CONSOLE_OUT_DEVICE_GUID \ + EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x0, 0x90, 0x27, \ + 0x3f, 0xc1, 0x4d) + #define PIXEL_RGB_RESERVED_8BIT_PER_COLOR 0 #define PIXEL_BGR_RESERVED_8BIT_PER_COLOR 1 #define PIXEL_BIT_MASK 2 diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index b4e15dd6786..2a017441b8b 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -32,10 +32,6 @@ SYSSEG = 0x1000 /* historical load address >> 4 */ #define SVGA_MODE ASK_VGA #endif -#ifndef RAMDISK -#define RAMDISK 0 -#endif - #ifndef ROOT_RDONLY #define ROOT_RDONLY 1 #endif diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 119db67dcb0..5598547281a 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -8,6 +8,8 @@ CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_CGROUPS=y CONFIG_CGROUP_FREEZER=y @@ -34,8 +36,6 @@ CONFIG_SGI_PARTITION=y CONFIG_SUN_PARTITION=y CONFIG_KARMA_PARTITION=y CONFIG_EFI_PARTITION=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y CONFIG_SMP=y CONFIG_X86_GENERIC=y CONFIG_HPET_TIMER=y @@ -144,8 +144,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEBUG_DEVRES=y CONFIG_CONNECTOR=y CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=16384 CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_BLK_DEV_SR_VENDOR=y @@ -231,8 +229,6 @@ CONFIG_SND_HRTIMER=y CONFIG_SND_HDA_INTEL=y CONFIG_SND_HDA_HWDEP=y CONFIG_HIDRAW=y -CONFIG_HID_PID=y -CONFIG_USB_HIDDEV=y CONFIG_HID_GYRATION=y CONFIG_LOGITECH_FF=y CONFIG_HID_NTRIG=y @@ -243,11 +239,11 @@ CONFIG_HID_SAMSUNG=y CONFIG_HID_SONY=y CONFIG_HID_SUNPLUS=y CONFIG_HID_TOPSEED=y +CONFIG_HID_PID=y +CONFIG_USB_HIDDEV=y CONFIG_USB=y CONFIG_USB_DEBUG=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y -CONFIG_USB_DEVICEFS=y -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y # CONFIG_USB_EHCI_TT_NEWSCHED is not set @@ -262,10 +258,9 @@ CONFIG_RTC_CLASS=y CONFIG_DMADEVICES=y CONFIG_EEEPC_LAPTOP=y CONFIG_EFI_VARS=y -CONFIG_EXT3_FS=y -# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set -CONFIG_EXT3_FS_POSIX_ACL=y -CONFIG_EXT3_FS_SECURITY=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y CONFIG_QUOTA=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set @@ -280,7 +275,6 @@ CONFIG_PROC_KCORE=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y CONFIG_NFS_FS=y -CONFIG_NFS_V3=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y @@ -299,13 +293,11 @@ CONFIG_DEBUG_KERNEL=y CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y CONFIG_DEBUG_STACK_USAGE=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_PROVIDE_OHCI1394_DMA_INIT=y CONFIG_EARLY_PRINTK_DBGP=y CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_DEBUG_RODATA_TEST is not set -CONFIG_DEBUG_NX_TEST=m CONFIG_DEBUG_BOOT_PARAMS=y CONFIG_OPTIMIZE_INLINING=y CONFIG_KEYS_DEBUG_PROC_KEYS=y @@ -316,4 +308,3 @@ CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_CRYPTO_AES_586=y # CONFIG_CRYPTO_ANSI_CPRNG is not set -CONFIG_CRC_T10DIF=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 76eb2903809..671524d0f6c 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -8,6 +8,8 @@ CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_CGROUPS=y CONFIG_CGROUP_FREEZER=y @@ -34,8 +36,6 @@ CONFIG_SGI_PARTITION=y CONFIG_SUN_PARTITION=y CONFIG_KARMA_PARTITION=y CONFIG_EFI_PARTITION=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y CONFIG_SMP=y CONFIG_CALGARY_IOMMU=y CONFIG_NR_CPUS=64 @@ -144,8 +144,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEBUG_DEVRES=y CONFIG_CONNECTOR=y CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=16384 CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_BLK_DEV_SR_VENDOR=y @@ -227,8 +225,6 @@ CONFIG_SND_HRTIMER=y CONFIG_SND_HDA_INTEL=y CONFIG_SND_HDA_HWDEP=y CONFIG_HIDRAW=y -CONFIG_HID_PID=y -CONFIG_USB_HIDDEV=y CONFIG_HID_GYRATION=y CONFIG_LOGITECH_FF=y CONFIG_HID_NTRIG=y @@ -239,11 +235,11 @@ CONFIG_HID_SAMSUNG=y CONFIG_HID_SONY=y CONFIG_HID_SUNPLUS=y CONFIG_HID_TOPSEED=y +CONFIG_HID_PID=y +CONFIG_USB_HIDDEV=y CONFIG_USB=y CONFIG_USB_DEBUG=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y -CONFIG_USB_DEVICEFS=y -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y # CONFIG_USB_EHCI_TT_NEWSCHED is not set @@ -262,10 +258,9 @@ CONFIG_AMD_IOMMU_STATS=y CONFIG_INTEL_IOMMU=y # CONFIG_INTEL_IOMMU_DEFAULT_ON is not set CONFIG_EFI_VARS=y -CONFIG_EXT3_FS=y -# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set -CONFIG_EXT3_FS_POSIX_ACL=y -CONFIG_EXT3_FS_SECURITY=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y CONFIG_QUOTA=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set @@ -280,7 +275,6 @@ CONFIG_PROC_KCORE=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y CONFIG_NFS_FS=y -CONFIG_NFS_V3=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y @@ -298,13 +292,11 @@ CONFIG_DEBUG_KERNEL=y CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y CONFIG_DEBUG_STACK_USAGE=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_PROVIDE_OHCI1394_DMA_INIT=y CONFIG_EARLY_PRINTK_DBGP=y CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_DEBUG_RODATA_TEST is not set -CONFIG_DEBUG_NX_TEST=m CONFIG_DEBUG_BOOT_PARAMS=y CONFIG_OPTIMIZE_INLINING=y CONFIG_KEYS_DEBUG_PROC_KEYS=y @@ -314,4 +306,3 @@ CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y # CONFIG_CRYPTO_ANSI_CPRNG is not set -CONFIG_CRC_T10DIF=y diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 673ac9b63d6..efc6a958b71 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -32,6 +32,7 @@ #include <asm/sigframe.h> #include <asm/sighandling.h> #include <asm/sys_ia32.h> +#include <asm/smap.h> #define FIX_EFLAGS __FIX_EFLAGS @@ -162,7 +163,8 @@ asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr, } seg = get_fs(); set_fs(KERNEL_DS); - ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, regs->sp); + ret = do_sigaltstack((stack_t __force __user *) (uss_ptr ? &uss : NULL), + (stack_t __force __user *) &uoss, regs->sp); set_fs(seg); if (ret >= 0 && uoss_ptr) { if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t))) @@ -250,11 +252,12 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, get_user_ex(tmp, &sc->fpstate); buf = compat_ptr(tmp); - err |= restore_i387_xstate_ia32(buf); get_user_ex(*pax, &sc->ax); } get_user_catch(err); + err |= restore_xstate_sig(buf, 1); + return err; } @@ -361,7 +364,7 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc, */ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, - void **fpstate) + void __user **fpstate) { unsigned long sp; @@ -381,9 +384,12 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, sp = (unsigned long) ka->sa.sa_restorer; if (used_math()) { - sp = sp - sig_xstate_ia32_size; - *fpstate = (struct _fpstate_ia32 *) sp; - if (save_i387_xstate_ia32(*fpstate) < 0) + unsigned long fx_aligned, math_size; + + sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size); + *fpstate = (struct _fpstate_ia32 __user *) sp; + if (save_xstate_sig(*fpstate, (void __user *)fx_aligned, + math_size) < 0) return (void __user *) -1L; } @@ -448,7 +454,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka, * These are actually not used anymore, but left because some * gdb versions depend on them as a marker. */ - put_user_ex(*((u64 *)&code), (u64 *)frame->retcode); + put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode); } put_user_catch(err); if (err) @@ -502,7 +508,6 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, put_user_ex(sig, &frame->sig); put_user_ex(ptr_to_compat(&frame->info), &frame->pinfo); put_user_ex(ptr_to_compat(&frame->uc), &frame->puc); - err |= copy_siginfo_to_user32(&frame->info, info); /* Create the ucontext. */ if (cpu_has_xsave) @@ -514,9 +519,6 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, put_user_ex(sas_ss_flags(regs->sp), &frame->uc.uc_stack.ss_flags); put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); - err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (ka->sa.sa_flags & SA_RESTORER) restorer = ka->sa.sa_restorer; @@ -529,9 +531,14 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, * Not actually used anymore, but left because some gdb * versions need it. */ - put_user_ex(*((u64 *)&code), (u64 *)frame->retcode); + put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode); } put_user_catch(err); + err |= copy_siginfo_to_user32(&frame->info, info); + err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate, + regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) return -EFAULT; diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 20e5f7ba0e6..9c289504e68 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -14,6 +14,7 @@ #include <asm/segment.h> #include <asm/irqflags.h> #include <asm/asm.h> +#include <asm/smap.h> #include <linux/linkage.h> #include <linux/err.h> @@ -146,8 +147,10 @@ ENTRY(ia32_sysenter_target) SAVE_ARGS 0,1,0 /* no need to do an access_ok check here because rbp has been 32bit zero extended */ + ASM_STAC 1: movl (%rbp),%ebp _ASM_EXTABLE(1b,ia32_badarg) + ASM_CLAC orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) CFI_REMEMBER_STATE @@ -301,8 +304,10 @@ ENTRY(ia32_cstar_target) /* no need to do an access_ok check here because r8 has been 32bit zero extended */ /* hardware stack frame is complete now */ + ASM_STAC 1: movl (%r8),%r9d _ASM_EXTABLE(1b,ia32_badarg) + ASM_CLAC orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) CFI_REMEMBER_STATE @@ -365,6 +370,7 @@ cstar_tracesys: END(ia32_cstar_target) ia32_badarg: + ASM_CLAC movq $-EFAULT,%rax jmp ia32_sysret CFI_ENDPROC diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 4540bece094..c5b938d92ea 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -287,7 +287,7 @@ asmlinkage long sys32_sigaction(int sig, struct old_sigaction32 __user *act, return ret; } -asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int *stat_addr, +asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int __user *stat_addr, int options) { return compat_sys_wait4(pid, stat_addr, options, NULL); diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index 952bd0100c5..372231c22a4 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -1,3 +1,6 @@ +#ifndef _ASM_X86_ALTERNATIVE_ASM_H +#define _ASM_X86_ALTERNATIVE_ASM_H + #ifdef __ASSEMBLY__ #include <asm/asm.h> @@ -5,10 +8,10 @@ #ifdef CONFIG_SMP .macro LOCK_PREFIX 672: lock - .section .smp_locks,"a" + .pushsection .smp_locks,"a" .balign 4 .long 672b - . - .previous + .popsection .endm #else .macro LOCK_PREFIX @@ -24,3 +27,5 @@ .endm #endif /* __ASSEMBLY__ */ + +#endif /* _ASM_X86_ALTERNATIVE_ASM_H */ diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 70780689599..58ed6d96a6a 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -29,10 +29,10 @@ #ifdef CONFIG_SMP #define LOCK_PREFIX_HERE \ - ".section .smp_locks,\"a\"\n" \ - ".balign 4\n" \ - ".long 671f - .\n" /* offset */ \ - ".previous\n" \ + ".pushsection .smp_locks,\"a\"\n" \ + ".balign 4\n" \ + ".long 671f - .\n" /* offset */ \ + ".popsection\n" \ "671:" #define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; " @@ -60,7 +60,7 @@ extern void alternatives_smp_module_add(struct module *mod, char *name, void *locks, void *locks_end, void *text, void *text_end); extern void alternatives_smp_module_del(struct module *mod); -extern void alternatives_smp_switch(int smp); +extern void alternatives_enable_smp(void); extern int alternatives_text_reserved(void *start, void *end); extern bool skip_smp_alternatives; #else @@ -68,7 +68,7 @@ static inline void alternatives_smp_module_add(struct module *mod, char *name, void *locks, void *locks_end, void *text, void *text_end) {} static inline void alternatives_smp_module_del(struct module *mod) {} -static inline void alternatives_smp_switch(int smp) {} +static inline void alternatives_enable_smp(void) {} static inline int alternatives_text_reserved(void *start, void *end) { return 0; @@ -99,30 +99,30 @@ static inline int alternatives_text_reserved(void *start, void *end) /* alternative assembly primitive: */ #define ALTERNATIVE(oldinstr, newinstr, feature) \ OLDINSTR(oldinstr) \ - ".section .altinstructions,\"a\"\n" \ + ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(feature, 1) \ - ".previous\n" \ - ".section .discard,\"aw\",@progbits\n" \ + ".popsection\n" \ + ".pushsection .discard,\"aw\",@progbits\n" \ DISCARD_ENTRY(1) \ - ".previous\n" \ - ".section .altinstr_replacement, \"ax\"\n" \ + ".popsection\n" \ + ".pushsection .altinstr_replacement, \"ax\"\n" \ ALTINSTR_REPLACEMENT(newinstr, feature, 1) \ - ".previous" + ".popsection" #define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\ OLDINSTR(oldinstr) \ - ".section .altinstructions,\"a\"\n" \ + ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(feature1, 1) \ ALTINSTR_ENTRY(feature2, 2) \ - ".previous\n" \ - ".section .discard,\"aw\",@progbits\n" \ + ".popsection\n" \ + ".pushsection .discard,\"aw\",@progbits\n" \ DISCARD_ENTRY(1) \ DISCARD_ENTRY(2) \ - ".previous\n" \ - ".section .altinstr_replacement, \"ax\"\n" \ + ".popsection\n" \ + ".pushsection .altinstr_replacement, \"ax\"\n" \ ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \ ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \ - ".previous" + ".popsection" /* * This must be included *after* the definition of ALTERNATIVE due to diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 72f5009deb5..6dfd0195bb5 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -355,7 +355,7 @@ static int test_bit(int nr, const volatile unsigned long *addr); */ static inline unsigned long __ffs(unsigned long word) { - asm("bsf %1,%0" + asm("rep; bsf %1,%0" : "=r" (word) : "rm" (word)); return word; @@ -369,7 +369,7 @@ static inline unsigned long __ffs(unsigned long word) */ static inline unsigned long ffz(unsigned long word) { - asm("bsf %1,%0" + asm("rep; bsf %1,%0" : "=r" (word) : "r" (~word)); return word; @@ -417,10 +417,9 @@ static inline int ffs(int x) * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ - long tmp = -1; asm("bsfl %1,%0" : "=r" (r) - : "rm" (x), "0" (tmp)); + : "rm" (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsfl %1,%0\n\t" "cmovzl %2,%0" @@ -459,10 +458,9 @@ static inline int fls(int x) * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ - long tmp = -1; asm("bsrl %1,%0" : "=r" (r) - : "rm" (x), "0" (tmp)); + : "rm" (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsrl %1,%0\n\t" "cmovzl %2,%0" @@ -490,13 +488,13 @@ static inline int fls(int x) #ifdef CONFIG_X86_64 static __always_inline int fls64(__u64 x) { - long bitpos = -1; + int bitpos = -1; /* * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before. */ - asm("bsrq %1,%0" + asm("bsrq %1,%q0" : "+r" (bitpos) : "rm" (x)); return bitpos + 1; diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h index a9e3a740f69..7f8422a28a4 100644 --- a/arch/x86/include/asm/calling.h +++ b/arch/x86/include/asm/calling.h @@ -49,38 +49,36 @@ For 32-bit we have the following conventions - kernel is built with #include "dwarf2.h" /* - * 64-bit system call stack frame layout defines and helpers, for - * assembly code (note that the seemingly unnecessary parentheses - * are to prevent cpp from inserting spaces in expressions that get - * passed to macros): + * 64-bit system call stack frame layout defines and helpers, + * for assembly code: */ -#define R15 (0) -#define R14 (8) -#define R13 (16) -#define R12 (24) -#define RBP (32) -#define RBX (40) +#define R15 0 +#define R14 8 +#define R13 16 +#define R12 24 +#define RBP 32 +#define RBX 40 /* arguments: interrupts/non tracing syscalls only save up to here: */ -#define R11 (48) -#define R10 (56) -#define R9 (64) -#define R8 (72) -#define RAX (80) -#define RCX (88) -#define RDX (96) -#define RSI (104) -#define RDI (112) -#define ORIG_RAX (120) /* + error_code */ +#define R11 48 +#define R10 56 +#define R9 64 +#define R8 72 +#define RAX 80 +#define RCX 88 +#define RDX 96 +#define RSI 104 +#define RDI 112 +#define ORIG_RAX 120 /* + error_code */ /* end of arguments */ /* cpu exception frame or undefined in case of fast syscall: */ -#define RIP (128) -#define CS (136) -#define EFLAGS (144) -#define RSP (152) -#define SS (160) +#define RIP 128 +#define CS 136 +#define EFLAGS 144 +#define RSP 152 +#define SS 160 #define ARGOFFSET R11 #define SWFRAME ORIG_RAX diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 6b7ee5ff682..16cae425d1f 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -97,6 +97,7 @@ #define X86_FEATURE_EXTD_APICID (3*32+26) /* has extended APICID (8 bits) */ #define X86_FEATURE_AMD_DCM (3*32+27) /* multi-node processor */ #define X86_FEATURE_APERFMPERF (3*32+28) /* APERFMPERF */ +#define X86_FEATURE_EAGER_FPU (3*32+29) /* "eagerfpu" Non lazy FPU restore */ /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ #define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */ @@ -209,6 +210,7 @@ #define X86_FEATURE_RTM (9*32+11) /* Restricted Transactional Memory */ #define X86_FEATURE_RDSEED (9*32+18) /* The RDSEED instruction */ #define X86_FEATURE_ADX (9*32+19) /* The ADCX and ADOX instructions */ +#define X86_FEATURE_SMAP (9*32+20) /* Supervisor Mode Access Prevention */ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) @@ -299,12 +301,14 @@ extern const char * const x86_power_flags[32]; #define cpu_has_xmm4_2 boot_cpu_has(X86_FEATURE_XMM4_2) #define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC) #define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE) +#define cpu_has_xsaveopt boot_cpu_has(X86_FEATURE_XSAVEOPT) #define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE) #define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) #define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) #define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE) #define cpu_has_cx8 boot_cpu_has(X86_FEATURE_CX8) #define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16) +#define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64) # define cpu_has_invlpg 1 diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index 75f4c6d6a33..831dbb9c6c0 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -12,6 +12,7 @@ #include <linux/kernel_stat.h> #include <linux/regset.h> +#include <linux/compat.h> #include <linux/slab.h> #include <asm/asm.h> #include <asm/cpufeature.h> @@ -20,43 +21,76 @@ #include <asm/user.h> #include <asm/uaccess.h> #include <asm/xsave.h> +#include <asm/smap.h> -extern unsigned int sig_xstate_size; +#ifdef CONFIG_X86_64 +# include <asm/sigcontext32.h> +# include <asm/user32.h> +int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, + compat_sigset_t *set, struct pt_regs *regs); +int ia32_setup_frame(int sig, struct k_sigaction *ka, + compat_sigset_t *set, struct pt_regs *regs); +#else +# define user_i387_ia32_struct user_i387_struct +# define user32_fxsr_struct user_fxsr_struct +# define ia32_setup_frame __setup_frame +# define ia32_setup_rt_frame __setup_rt_frame +#endif + +extern unsigned int mxcsr_feature_mask; extern void fpu_init(void); +extern void eager_fpu_init(void); DECLARE_PER_CPU(struct task_struct *, fpu_owner_task); +extern void convert_from_fxsr(struct user_i387_ia32_struct *env, + struct task_struct *tsk); +extern void convert_to_fxsr(struct task_struct *tsk, + const struct user_i387_ia32_struct *env); + extern user_regset_active_fn fpregs_active, xfpregs_active; extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, xstateregs_get; extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, xstateregs_set; - /* * xstateregs_active == fpregs_active. Please refer to the comment * at the definition of fpregs_active. */ #define xstateregs_active fpregs_active -extern struct _fpx_sw_bytes fx_sw_reserved; -#ifdef CONFIG_IA32_EMULATION -extern unsigned int sig_xstate_ia32_size; -extern struct _fpx_sw_bytes fx_sw_reserved_ia32; -struct _fpstate_ia32; -struct _xstate_ia32; -extern int save_i387_xstate_ia32(void __user *buf); -extern int restore_i387_xstate_ia32(void __user *buf); -#endif - #ifdef CONFIG_MATH_EMULATION +# define HAVE_HWFP (boot_cpu_data.hard_math) extern void finit_soft_fpu(struct i387_soft_struct *soft); #else +# define HAVE_HWFP 1 static inline void finit_soft_fpu(struct i387_soft_struct *soft) {} #endif +static inline int is_ia32_compat_frame(void) +{ + return config_enabled(CONFIG_IA32_EMULATION) && + test_thread_flag(TIF_IA32); +} + +static inline int is_ia32_frame(void) +{ + return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame(); +} + +static inline int is_x32_frame(void) +{ + return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32); +} + #define X87_FSW_ES (1 << 7) /* Exception Summary */ +static __always_inline __pure bool use_eager_fpu(void) +{ + return static_cpu_has(X86_FEATURE_EAGER_FPU); +} + static __always_inline __pure bool use_xsaveopt(void) { return static_cpu_has(X86_FEATURE_XSAVEOPT); @@ -72,6 +106,13 @@ static __always_inline __pure bool use_fxsr(void) return static_cpu_has(X86_FEATURE_FXSR); } +static inline void fx_finit(struct i387_fxsave_struct *fx) +{ + memset(fx, 0, xstate_size); + fx->cwd = 0x37f; + fx->mxcsr = MXCSR_DEFAULT; +} + extern void __sanitize_i387_state(struct task_struct *); static inline void sanitize_i387_state(struct task_struct *tsk) @@ -81,131 +122,121 @@ static inline void sanitize_i387_state(struct task_struct *tsk) __sanitize_i387_state(tsk); } -#ifdef CONFIG_X86_64 -static inline int fxrstor_checking(struct i387_fxsave_struct *fx) -{ - int err; - - /* See comment in fxsave() below. */ -#ifdef CONFIG_AS_FXSAVEQ - asm volatile("1: fxrstorq %[fx]\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err) - : [fx] "m" (*fx), "0" (0)); -#else - asm volatile("1: rex64/fxrstor (%[fx])\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err) - : [fx] "R" (fx), "m" (*fx), "0" (0)); -#endif - return err; +#define user_insn(insn, output, input...) \ +({ \ + int err; \ + asm volatile(ASM_STAC "\n" \ + "1:" #insn "\n\t" \ + "2: " ASM_CLAC "\n" \ + ".section .fixup,\"ax\"\n" \ + "3: movl $-1,%[err]\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err), output \ + : "0"(0), input); \ + err; \ +}) + +#define check_insn(insn, output, input...) \ +({ \ + int err; \ + asm volatile("1:" #insn "\n\t" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3: movl $-1,%[err]\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err), output \ + : "0"(0), input); \ + err; \ +}) + +static inline int fsave_user(struct i387_fsave_struct __user *fx) +{ + return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); } static inline int fxsave_user(struct i387_fxsave_struct __user *fx) { - int err; + if (config_enabled(CONFIG_X86_32)) + return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); - /* - * Clear the bytes not touched by the fxsave and reserved - * for the SW usage. - */ - err = __clear_user(&fx->sw_reserved, - sizeof(struct _fpx_sw_bytes)); - if (unlikely(err)) - return -EFAULT; - - /* See comment in fxsave() below. */ -#ifdef CONFIG_AS_FXSAVEQ - asm volatile("1: fxsaveq %[fx]\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err), [fx] "=m" (*fx) - : "0" (0)); -#else - asm volatile("1: rex64/fxsave (%[fx])\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err), "=m" (*fx) - : [fx] "R" (fx), "0" (0)); -#endif - if (unlikely(err) && - __clear_user(fx, sizeof(struct i387_fxsave_struct))) - err = -EFAULT; - /* No need to clear here because the caller clears USED_MATH */ - return err; + /* See comment in fpu_fxsave() below. */ + return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx)); } -static inline void fpu_fxsave(struct fpu *fpu) +static inline int fxrstor_checking(struct i387_fxsave_struct *fx) { - /* Using "rex64; fxsave %0" is broken because, if the memory operand - uses any extended registers for addressing, a second REX prefix - will be generated (to the assembler, rex64 followed by semicolon - is a separate instruction), and hence the 64-bitness is lost. */ + if (config_enabled(CONFIG_X86_32)) + return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); -#ifdef CONFIG_AS_FXSAVEQ - /* Using "fxsaveq %0" would be the ideal choice, but is only supported - starting with gas 2.16. */ - __asm__ __volatile__("fxsaveq %0" - : "=m" (fpu->state->fxsave)); -#else - /* Using, as a workaround, the properly prefixed form below isn't - accepted by any binutils version so far released, complaining that - the same type of prefix is used twice if an extended register is - needed for addressing (fix submitted to mainline 2005-11-21). - asm volatile("rex64/fxsave %0" - : "=m" (fpu->state->fxsave)); - This, however, we can work around by forcing the compiler to select - an addressing mode that doesn't require extended registers. */ - asm volatile("rex64/fxsave (%[fx])" - : "=m" (fpu->state->fxsave) - : [fx] "R" (&fpu->state->fxsave)); -#endif + /* See comment in fpu_fxsave() below. */ + return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), + "m" (*fx)); } -#else /* CONFIG_X86_32 */ +static inline int fxrstor_user(struct i387_fxsave_struct __user *fx) +{ + if (config_enabled(CONFIG_X86_32)) + return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); -/* perform fxrstor iff the processor has extended states, otherwise frstor */ -static inline int fxrstor_checking(struct i387_fxsave_struct *fx) + /* See comment in fpu_fxsave() below. */ + return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), + "m" (*fx)); +} + +static inline int frstor_checking(struct i387_fsave_struct *fx) { - /* - * The "nop" is needed to make the instructions the same - * length. - */ - alternative_input( - "nop ; frstor %1", - "fxrstor %1", - X86_FEATURE_FXSR, - "m" (*fx)); + return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); +} - return 0; +static inline int frstor_user(struct i387_fsave_struct __user *fx) +{ + return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void fpu_fxsave(struct fpu *fpu) { - asm volatile("fxsave %[fx]" - : [fx] "=m" (fpu->state->fxsave)); + if (config_enabled(CONFIG_X86_32)) + asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + asm volatile("fxsaveq %0" : "=m" (fpu->state->fxsave)); + else { + /* Using "rex64; fxsave %0" is broken because, if the memory + * operand uses any extended registers for addressing, a second + * REX prefix will be generated (to the assembler, rex64 + * followed by semicolon is a separate instruction), and hence + * the 64-bitness is lost. + * + * Using "fxsaveq %0" would be the ideal choice, but is only + * supported starting with gas 2.16. + * + * Using, as a workaround, the properly prefixed form below + * isn't accepted by any binutils version so far released, + * complaining that the same type of prefix is used twice if + * an extended register is needed for addressing (fix submitted + * to mainline 2005-11-21). + * + * asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave)); + * + * This, however, we can work around by forcing the compiler to + * select an addressing mode that doesn't require extended + * registers. + */ + asm volatile( "rex64/fxsave (%[fx])" + : "=m" (fpu->state->fxsave) + : [fx] "R" (&fpu->state->fxsave)); + } } -#endif /* CONFIG_X86_64 */ - /* * These must be called with preempt disabled. Returns * 'true' if the FPU state is still intact. @@ -248,17 +279,14 @@ static inline int __save_init_fpu(struct task_struct *tsk) return fpu_save_init(&tsk->thread.fpu); } -static inline int fpu_fxrstor_checking(struct fpu *fpu) -{ - return fxrstor_checking(&fpu->state->fxsave); -} - static inline int fpu_restore_checking(struct fpu *fpu) { if (use_xsave()) - return fpu_xrstor_checking(fpu); + return fpu_xrstor_checking(&fpu->state->xsave); + else if (use_fxsr()) + return fxrstor_checking(&fpu->state->fxsave); else - return fpu_fxrstor_checking(fpu); + return frstor_checking(&fpu->state->fsave); } static inline int restore_fpu_checking(struct task_struct *tsk) @@ -310,15 +338,52 @@ static inline void __thread_set_has_fpu(struct task_struct *tsk) static inline void __thread_fpu_end(struct task_struct *tsk) { __thread_clear_has_fpu(tsk); - stts(); + if (!use_eager_fpu()) + stts(); } static inline void __thread_fpu_begin(struct task_struct *tsk) { - clts(); + if (!use_eager_fpu()) + clts(); __thread_set_has_fpu(tsk); } +static inline void __drop_fpu(struct task_struct *tsk) +{ + if (__thread_has_fpu(tsk)) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + __thread_fpu_end(tsk); + } +} + +static inline void drop_fpu(struct task_struct *tsk) +{ + /* + * Forget coprocessor state.. + */ + preempt_disable(); + tsk->fpu_counter = 0; + __drop_fpu(tsk); + clear_used_math(); + preempt_enable(); +} + +static inline void drop_init_fpu(struct task_struct *tsk) +{ + if (!use_eager_fpu()) + drop_fpu(tsk); + else { + if (use_xsave()) + xrstor_state(init_xstate_buf, -1); + else + fxrstor_checking(&init_xstate_buf->i387); + } +} + /* * FPU state switching for scheduling. * @@ -352,7 +417,12 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta { fpu_switch_t fpu; - fpu.preload = tsk_used_math(new) && new->fpu_counter > 5; + /* + * If the task has used the math, pre-load the FPU on xsave processors + * or if the past 5 consecutive context-switches used math. + */ + fpu.preload = tsk_used_math(new) && (use_eager_fpu() || + new->fpu_counter > 5); if (__thread_has_fpu(old)) { if (!__save_init_fpu(old)) cpu = ~0; @@ -364,14 +434,14 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta new->fpu_counter++; __thread_set_has_fpu(new); prefetch(new->thread.fpu.state); - } else + } else if (!use_eager_fpu()) stts(); } else { old->fpu_counter = 0; old->thread.fpu.last_cpu = ~0; if (fpu.preload) { new->fpu_counter++; - if (fpu_lazy_restore(new, cpu)) + if (!use_eager_fpu() && fpu_lazy_restore(new, cpu)) fpu.preload = 0; else prefetch(new->thread.fpu.state); @@ -391,44 +461,40 @@ static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu) { if (fpu.preload) { if (unlikely(restore_fpu_checking(new))) - __thread_fpu_end(new); + drop_init_fpu(new); } } /* * Signal frame handlers... */ -extern int save_i387_xstate(void __user *buf); -extern int restore_i387_xstate(void __user *buf); +extern int save_xstate_sig(void __user *buf, void __user *fx, int size); +extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size); -static inline void __clear_fpu(struct task_struct *tsk) +static inline int xstate_sigframe_size(void) { - if (__thread_has_fpu(tsk)) { - /* Ignore delayed exceptions from user space */ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); - __thread_fpu_end(tsk); + return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size; +} + +static inline int restore_xstate_sig(void __user *buf, int ia32_frame) +{ + void __user *buf_fx = buf; + int size = xstate_sigframe_size(); + + if (ia32_frame && use_fxsr()) { + buf_fx = buf + sizeof(struct i387_fsave_struct); + size += sizeof(struct i387_fsave_struct); } + + return __restore_xstate_sig(buf, buf_fx, size); } /* - * The actual user_fpu_begin/end() functions - * need to be preemption-safe. + * Need to be preemption-safe. * - * NOTE! user_fpu_end() must be used only after you - * have saved the FP state, and user_fpu_begin() must - * be used only immediately before restoring it. - * These functions do not do any save/restore on - * their own. + * NOTE! user_fpu_begin() must be used only immediately before restoring + * it. This function does not do any save/restore on their own. */ -static inline void user_fpu_end(void) -{ - preempt_disable(); - __thread_fpu_end(current); - preempt_enable(); -} - static inline void user_fpu_begin(void) { preempt_disable(); @@ -437,25 +503,32 @@ static inline void user_fpu_begin(void) preempt_enable(); } +static inline void __save_fpu(struct task_struct *tsk) +{ + if (use_xsave()) + xsave_state(&tsk->thread.fpu.state->xsave, -1); + else + fpu_fxsave(&tsk->thread.fpu); +} + /* * These disable preemption on their own and are safe */ static inline void save_init_fpu(struct task_struct *tsk) { WARN_ON_ONCE(!__thread_has_fpu(tsk)); + + if (use_eager_fpu()) { + __save_fpu(tsk); + return; + } + preempt_disable(); __save_init_fpu(tsk); __thread_fpu_end(tsk); preempt_enable(); } -static inline void clear_fpu(struct task_struct *tsk) -{ - preempt_disable(); - __clear_fpu(tsk); - preempt_enable(); -} - /* * i387 state interaction */ @@ -510,11 +583,34 @@ static inline void fpu_free(struct fpu *fpu) } } -static inline void fpu_copy(struct fpu *dst, struct fpu *src) +static inline void fpu_copy(struct task_struct *dst, struct task_struct *src) { - memcpy(dst->state, src->state, xstate_size); + if (use_eager_fpu()) { + memset(&dst->thread.fpu.state->xsave, 0, xstate_size); + __save_fpu(dst); + } else { + struct fpu *dfpu = &dst->thread.fpu; + struct fpu *sfpu = &src->thread.fpu; + + unlazy_fpu(src); + memcpy(dfpu->state, sfpu->state, xstate_size); + } } -extern void fpu_finit(struct fpu *fpu); +static inline unsigned long +alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx, + unsigned long *size) +{ + unsigned long frame_size = xstate_sigframe_size(); + + *buf_fx = sp = round_down(sp - frame_size, 64); + if (ia32_frame && use_fxsr()) { + frame_size += sizeof(struct i387_fsave_struct); + sp -= sizeof(struct i387_fsave_struct); + } + + *size = frame_size; + return sp; +} #endif diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index b0767bc0874..9a25b522d37 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -3,38 +3,54 @@ #ifdef __ASSEMBLY__ - .macro MCOUNT_SAVE_FRAME - /* taken from glibc */ - subq $0x38, %rsp - movq %rax, (%rsp) - movq %rcx, 8(%rsp) - movq %rdx, 16(%rsp) - movq %rsi, 24(%rsp) - movq %rdi, 32(%rsp) - movq %r8, 40(%rsp) - movq %r9, 48(%rsp) + /* skip is set if the stack was already partially adjusted */ + .macro MCOUNT_SAVE_FRAME skip=0 + /* + * We add enough stack to save all regs. + */ + subq $(SS+8-\skip), %rsp + movq %rax, RAX(%rsp) + movq %rcx, RCX(%rsp) + movq %rdx, RDX(%rsp) + movq %rsi, RSI(%rsp) + movq %rdi, RDI(%rsp) + movq %r8, R8(%rsp) + movq %r9, R9(%rsp) + /* Move RIP to its proper location */ + movq SS+8(%rsp), %rdx + movq %rdx, RIP(%rsp) .endm - .macro MCOUNT_RESTORE_FRAME - movq 48(%rsp), %r9 - movq 40(%rsp), %r8 - movq 32(%rsp), %rdi - movq 24(%rsp), %rsi - movq 16(%rsp), %rdx - movq 8(%rsp), %rcx - movq (%rsp), %rax - addq $0x38, %rsp + .macro MCOUNT_RESTORE_FRAME skip=0 + movq R9(%rsp), %r9 + movq R8(%rsp), %r8 + movq RDI(%rsp), %rdi + movq RSI(%rsp), %rsi + movq RDX(%rsp), %rdx + movq RCX(%rsp), %rcx + movq RAX(%rsp), %rax + addq $(SS+8-\skip), %rsp .endm #endif #ifdef CONFIG_FUNCTION_TRACER -#define MCOUNT_ADDR ((long)(mcount)) +#ifdef CC_USING_FENTRY +# define MCOUNT_ADDR ((long)(__fentry__)) +#else +# define MCOUNT_ADDR ((long)(mcount)) +#endif #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ +#ifdef CONFIG_DYNAMIC_FTRACE +#define ARCH_SUPPORTS_FTRACE_OPS 1 +#define ARCH_SUPPORTS_FTRACE_SAVE_REGS +#endif + #ifndef __ASSEMBLY__ extern void mcount(void); extern atomic_t modifying_ftrace_code; +extern void __fentry__(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h index 71ecbcba1a4..f373046e63e 100644 --- a/arch/x86/include/asm/futex.h +++ b/arch/x86/include/asm/futex.h @@ -9,10 +9,13 @@ #include <asm/asm.h> #include <asm/errno.h> #include <asm/processor.h> +#include <asm/smap.h> #define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \ - asm volatile("1:\t" insn "\n" \ - "2:\t.section .fixup,\"ax\"\n" \ + asm volatile("\t" ASM_STAC "\n" \ + "1:\t" insn "\n" \ + "2:\t" ASM_CLAC "\n" \ + "\t.section .fixup,\"ax\"\n" \ "3:\tmov\t%3, %1\n" \ "\tjmp\t2b\n" \ "\t.previous\n" \ @@ -21,12 +24,14 @@ : "i" (-EFAULT), "0" (oparg), "1" (0)) #define __futex_atomic_op2(insn, ret, oldval, uaddr, oparg) \ - asm volatile("1:\tmovl %2, %0\n" \ + asm volatile("\t" ASM_STAC "\n" \ + "1:\tmovl %2, %0\n" \ "\tmovl\t%0, %3\n" \ "\t" insn "\n" \ "2:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" \ "\tjnz\t1b\n" \ - "3:\t.section .fixup,\"ax\"\n" \ + "3:\t" ASM_CLAC "\n" \ + "\t.section .fixup,\"ax\"\n" \ "4:\tmov\t%5, %1\n" \ "\tjmp\t3b\n" \ "\t.previous\n" \ @@ -122,8 +127,10 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; - asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" - "2:\t.section .fixup, \"ax\"\n" + asm volatile("\t" ASM_STAC "\n" + "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" + "2:\t" ASM_CLAC "\n" + "\t.section .fixup, \"ax\"\n" "3:\tmov %3, %0\n" "\tjmp 2b\n" "\t.previous\n" diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index d3895dbf4dd..81f04cee5f7 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -18,6 +18,10 @@ typedef struct { #ifdef CONFIG_SMP unsigned int irq_resched_count; unsigned int irq_call_count; + /* + * irq_tlb_count is double-counted in irq_call_count, so it must be + * subtracted from irq_call_count when displaying irq_call_count + */ unsigned int irq_tlb_count; #endif #ifdef CONFIG_X86_THERMAL_VECTOR diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index 2c392d663dc..434e2106cc8 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -35,8 +35,6 @@ #define HPET_ID_NUMBER_SHIFT 8 #define HPET_ID_VENDOR_SHIFT 16 -#define HPET_ID_VENDOR_8086 0x8086 - #define HPET_CFG_ENABLE 0x001 #define HPET_CFG_LEGACY 0x002 #define HPET_LEGACY_8254 2 diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 257d9cca214..ed8089d6909 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -19,12 +19,37 @@ struct pt_regs; struct user_i387_struct; extern int init_fpu(struct task_struct *child); +extern void fpu_finit(struct fpu *fpu); extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); extern void math_state_restore(void); extern bool irq_fpu_usable(void); -extern void kernel_fpu_begin(void); -extern void kernel_fpu_end(void); + +/* + * Careful: __kernel_fpu_begin/end() must be called with preempt disabled + * and they don't touch the preempt state on their own. + * If you enable preemption after __kernel_fpu_begin(), preempt notifier + * should call the __kernel_fpu_end() to prevent the kernel/user FPU + * state from getting corrupted. KVM for example uses this model. + * + * All other cases use kernel_fpu_begin/end() which disable preemption + * during kernel FPU usage. + */ +extern void __kernel_fpu_begin(void); +extern void __kernel_fpu_end(void); + +static inline void kernel_fpu_begin(void) +{ + WARN_ON_ONCE(!irq_fpu_usable()); + preempt_disable(); + __kernel_fpu_begin(); +} + +static inline void kernel_fpu_end(void) +{ + __kernel_fpu_end(); + preempt_enable(); +} /* * Some instructions like VIA's padlock instructions generate a spurious diff --git a/arch/x86/include/asm/iommu_table.h b/arch/x86/include/asm/iommu_table.h index f229b13a5f3..f42a04735a0 100644 --- a/arch/x86/include/asm/iommu_table.h +++ b/arch/x86/include/asm/iommu_table.h @@ -48,7 +48,7 @@ struct iommu_table_entry { #define __IOMMU_INIT(_detect, _depend, _early_init, _late_init, _finish)\ - static const struct iommu_table_entry const \ + static const struct iommu_table_entry \ __iommu_entry_##_detect __used \ __attribute__ ((unused, __section__(".iommu_table"), \ aligned((sizeof(void *))))) \ @@ -63,10 +63,10 @@ struct iommu_table_entry { * to stop detecting the other IOMMUs after yours has been detected. */ #define IOMMU_INIT_POST(_detect) \ - __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb, 0, 0, 0) + __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb, NULL, NULL, 0) #define IOMMU_INIT_POST_FINISH(detect) \ - __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb, 0, 0, 1) + __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb, NULL, NULL, 1) /* * A more sophisticated version of IOMMU_INIT. This variant requires: diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 54788253915..d3ddd17405d 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -27,6 +27,7 @@ #include <asm/insn.h> #define __ARCH_WANT_KPROBES_INSN_SLOT +#define ARCH_SUPPORTS_KPROBES_ON_FTRACE struct pt_regs; struct kprobe; diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 246617efd67..41e08cb6a09 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -9,6 +9,22 @@ #include <linux/types.h> #include <linux/ioctl.h> +#define DE_VECTOR 0 +#define DB_VECTOR 1 +#define BP_VECTOR 3 +#define OF_VECTOR 4 +#define BR_VECTOR 5 +#define UD_VECTOR 6 +#define NM_VECTOR 7 +#define DF_VECTOR 8 +#define TS_VECTOR 10 +#define NP_VECTOR 11 +#define SS_VECTOR 12 +#define GP_VECTOR 13 +#define PF_VECTOR 14 +#define MF_VECTOR 16 +#define MC_VECTOR 18 + /* Select x86 specific features in <linux/kvm.h> */ #define __KVM_HAVE_PIT #define __KVM_HAVE_IOAPIC diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 09155d64cf7..1eaa6b05667 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -75,22 +75,6 @@ #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) -#define DE_VECTOR 0 -#define DB_VECTOR 1 -#define BP_VECTOR 3 -#define OF_VECTOR 4 -#define BR_VECTOR 5 -#define UD_VECTOR 6 -#define NM_VECTOR 7 -#define DF_VECTOR 8 -#define TS_VECTOR 10 -#define NP_VECTOR 11 -#define SS_VECTOR 12 -#define GP_VECTOR 13 -#define PF_VECTOR 14 -#define MF_VECTOR 16 -#define MC_VECTOR 18 - #define SELECTOR_TI_MASK (1 << 2) #define SELECTOR_RPL_MASK 0x03 diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 441520e4174..54d73b1f00a 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -33,6 +33,14 @@ #define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */ #define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */ #define MCI_STATUS_AR (1ULL<<55) /* Action required */ +#define MCACOD 0xffff /* MCA Error Code */ + +/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ +#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ +#define MCACOD_SCRUBMSK 0xfff0 +#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ +#define MCACOD_DATA 0x0134 /* Data Load */ +#define MCACOD_INSTR 0x0150 /* Instruction Fetch */ /* MCi_MISC register defines */ #define MCI_MISC_ADDR_LSB(m) ((m) & 0x3f) @@ -108,19 +116,9 @@ struct mce_log { /* Software defined banks */ #define MCE_EXTENDED_BANK 128 #define MCE_THERMAL_BANK MCE_EXTENDED_BANK + 0 - -#define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1) /* MCE_AMD */ -#define K8_MCE_THRESHOLD_BANK_0 (MCE_THRESHOLD_BASE + 0 * 9) -#define K8_MCE_THRESHOLD_BANK_1 (MCE_THRESHOLD_BASE + 1 * 9) -#define K8_MCE_THRESHOLD_BANK_2 (MCE_THRESHOLD_BASE + 2 * 9) -#define K8_MCE_THRESHOLD_BANK_3 (MCE_THRESHOLD_BASE + 3 * 9) -#define K8_MCE_THRESHOLD_BANK_4 (MCE_THRESHOLD_BASE + 4 * 9) -#define K8_MCE_THRESHOLD_BANK_5 (MCE_THRESHOLD_BASE + 5 * 9) -#define K8_MCE_THRESHOLD_DRAM_ECC (MCE_THRESHOLD_BANK_4 + 0) - +#define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1) #ifdef __KERNEL__ - extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); @@ -163,6 +161,7 @@ DECLARE_PER_CPU(struct device *, mce_device); #ifdef CONFIG_X86_MCE_INTEL extern int mce_cmci_disabled; extern int mce_ignore_ce; +extern int mce_bios_cmci_threshold; void mce_intel_feature_init(struct cpuinfo_x86 *c); void cmci_clear(void); void cmci_reenable(void); diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 4ebe157bf73..43d921b4752 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -15,8 +15,8 @@ struct microcode_ops { enum ucode_state (*request_microcode_user) (int cpu, const void __user *buf, size_t size); - enum ucode_state (*request_microcode_fw) (int cpu, - struct device *device); + enum ucode_state (*request_microcode_fw) (int cpu, struct device *, + bool refresh_fw); void (*microcode_fini_cpu) (int cpu); @@ -49,12 +49,6 @@ static inline struct microcode_ops * __init init_intel_microcode(void) #ifdef CONFIG_MICROCODE_AMD extern struct microcode_ops * __init init_amd_microcode(void); extern void __exit exit_amd_microcode(void); - -static inline void get_ucode_data(void *to, const u8 *from, size_t n) -{ - memcpy(to, from, n); -} - #else static inline struct microcode_ops * __init init_amd_microcode(void) { diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index dab39350e51..4fabcdf1cfa 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -196,11 +196,16 @@ static inline u32 get_ibs_caps(void) { return 0; } extern void perf_events_lapic_init(void); /* - * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups. - * This flag is otherwise unused and ABI specified to be 0, so nobody should - * care what we do with it. + * Abuse bits {3,5} of the cpu eflags register. These flags are otherwise + * unused and ABI specified to be 0, so nobody should care what we do with + * them. + * + * EXACT - the IP points to the exact instruction that triggered the + * event (HW bugs exempt). + * VM - original X86_VM_MASK; see set_linear_ip(). */ #define PERF_EFLAGS_EXACT (1UL << 3) +#define PERF_EFLAGS_VM (1UL << 5) struct pt_regs; extern unsigned long perf_instruction_pointer(struct pt_regs *regs); @@ -257,4 +262,6 @@ static inline void perf_check_microcode(void) { } static inline void amd_pmu_disable_virt(void) { } #endif +#define arch_perf_out_copy_user copy_from_user_nmi + #endif /* _ASM_X86_PERF_EVENT_H */ diff --git a/arch/x86/include/asm/perf_regs.h b/arch/x86/include/asm/perf_regs.h new file mode 100644 index 00000000000..3f2207bfd17 --- /dev/null +++ b/arch/x86/include/asm/perf_regs.h @@ -0,0 +1,33 @@ +#ifndef _ASM_X86_PERF_REGS_H +#define _ASM_X86_PERF_REGS_H + +enum perf_event_x86_regs { + PERF_REG_X86_AX, + PERF_REG_X86_BX, + PERF_REG_X86_CX, + PERF_REG_X86_DX, + PERF_REG_X86_SI, + PERF_REG_X86_DI, + PERF_REG_X86_BP, + PERF_REG_X86_SP, + PERF_REG_X86_IP, + PERF_REG_X86_FLAGS, + PERF_REG_X86_CS, + PERF_REG_X86_SS, + PERF_REG_X86_DS, + PERF_REG_X86_ES, + PERF_REG_X86_FS, + PERF_REG_X86_GS, + PERF_REG_X86_R8, + PERF_REG_X86_R9, + PERF_REG_X86_R10, + PERF_REG_X86_R11, + PERF_REG_X86_R12, + PERF_REG_X86_R13, + PERF_REG_X86_R14, + PERF_REG_X86_R15, + + PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1, + PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1, +}; +#endif /* _ASM_X86_PERF_REGS_H */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 013286a10c2..db8fec6d295 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -303,11 +303,9 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pte); extern void native_pagetable_reserve(u64 start, u64 end); #ifdef CONFIG_X86_32 -extern void native_pagetable_setup_start(pgd_t *base); -extern void native_pagetable_setup_done(pgd_t *base); +extern void native_pagetable_init(void); #else -#define native_pagetable_setup_start x86_init_pgd_noop -#define native_pagetable_setup_done x86_init_pgd_noop +#define native_pagetable_init paging_init #endif struct seq_file; diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index aea1d1d848c..680cf09ed10 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -65,6 +65,7 @@ #define X86_CR4_PCIDE 0x00020000 /* enable PCID support */ #define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */ #define X86_CR4_SMEP 0x00100000 /* enable SMEP support */ +#define X86_CR4_SMAP 0x00200000 /* enable SMAP support */ /* * x86-64 Task Priority Register, CR8 diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d048cad9bca..b98c0d958eb 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -423,7 +423,6 @@ DECLARE_INIT_PER_CPU(irq_stack_union); DECLARE_PER_CPU(char *, irq_stack_ptr); DECLARE_PER_CPU(unsigned int, irq_count); -extern unsigned long kernel_eflags; extern asmlinkage void ignore_sysret(void); #else /* X86_64 */ #ifdef CONFIG_CC_STACKPROTECTOR @@ -759,6 +758,8 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr) wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); } +extern void set_task_blockstep(struct task_struct *task, bool on); + /* * from system description table in BIOS. Mostly for MCA use, but * others may find it useful: diff --git a/arch/x86/include/asm/rcu.h b/arch/x86/include/asm/rcu.h new file mode 100644 index 00000000000..d1ac07a2397 --- /dev/null +++ b/arch/x86/include/asm/rcu.h @@ -0,0 +1,32 @@ +#ifndef _ASM_X86_RCU_H +#define _ASM_X86_RCU_H + +#ifndef __ASSEMBLY__ + +#include <linux/rcupdate.h> +#include <asm/ptrace.h> + +static inline void exception_enter(struct pt_regs *regs) +{ + rcu_user_exit(); +} + +static inline void exception_exit(struct pt_regs *regs) +{ +#ifdef CONFIG_RCU_USER_QS + if (user_mode(regs)) + rcu_user_enter(); +#endif +} + +#else /* __ASSEMBLY__ */ + +#ifdef CONFIG_RCU_USER_QS +# define SCHEDULE_USER call schedule_user +#else +# define SCHEDULE_USER call schedule +#endif + +#endif /* !__ASSEMBLY__ */ + +#endif diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 598457cbd0f..323973f4abf 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -31,6 +31,10 @@ typedef struct { unsigned long sig[_NSIG_WORDS]; } sigset_t; +#ifndef CONFIG_COMPAT +typedef sigset_t compat_sigset_t; +#endif + #else /* Here we must cater to libcs that poke about in kernel headers. */ diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h new file mode 100644 index 00000000000..8d3120f4e27 --- /dev/null +++ b/arch/x86/include/asm/smap.h @@ -0,0 +1,91 @@ +/* + * Supervisor Mode Access Prevention support + * + * Copyright (C) 2012 Intel Corporation + * Author: H. Peter Anvin <hpa@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. + */ + +#ifndef _ASM_X86_SMAP_H +#define _ASM_X86_SMAP_H + +#include <linux/stringify.h> +#include <asm/nops.h> +#include <asm/cpufeature.h> + +/* "Raw" instruction opcodes */ +#define __ASM_CLAC .byte 0x0f,0x01,0xca +#define __ASM_STAC .byte 0x0f,0x01,0xcb + +#ifdef __ASSEMBLY__ + +#include <asm/alternative-asm.h> + +#ifdef CONFIG_X86_SMAP + +#define ASM_CLAC \ + 661: ASM_NOP3 ; \ + .pushsection .altinstr_replacement, "ax" ; \ + 662: __ASM_CLAC ; \ + .popsection ; \ + .pushsection .altinstructions, "a" ; \ + altinstruction_entry 661b, 662b, X86_FEATURE_SMAP, 3, 3 ; \ + .popsection + +#define ASM_STAC \ + 661: ASM_NOP3 ; \ + .pushsection .altinstr_replacement, "ax" ; \ + 662: __ASM_STAC ; \ + .popsection ; \ + .pushsection .altinstructions, "a" ; \ + altinstruction_entry 661b, 662b, X86_FEATURE_SMAP, 3, 3 ; \ + .popsection + +#else /* CONFIG_X86_SMAP */ + +#define ASM_CLAC +#define ASM_STAC + +#endif /* CONFIG_X86_SMAP */ + +#else /* __ASSEMBLY__ */ + +#include <asm/alternative.h> + +#ifdef CONFIG_X86_SMAP + +static __always_inline void clac(void) +{ + /* Note: a barrier is implicit in alternative() */ + alternative(ASM_NOP3, __stringify(__ASM_CLAC), X86_FEATURE_SMAP); +} + +static __always_inline void stac(void) +{ + /* Note: a barrier is implicit in alternative() */ + alternative(ASM_NOP3, __stringify(__ASM_STAC), X86_FEATURE_SMAP); +} + +/* These macros can be used in asm() statements */ +#define ASM_CLAC \ + ALTERNATIVE(ASM_NOP3, __stringify(__ASM_CLAC), X86_FEATURE_SMAP) +#define ASM_STAC \ + ALTERNATIVE(ASM_NOP3, __stringify(__ASM_STAC), X86_FEATURE_SMAP) + +#else /* CONFIG_X86_SMAP */ + +static inline void clac(void) { } +static inline void stac(void) { } + +#define ASM_CLAC +#define ASM_STAC + +#endif /* CONFIG_X86_SMAP */ + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_X86_SMAP_H */ diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index b315a33867f..33692eaabab 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -12,8 +12,7 @@ * Simple spin lock operations. There are two variants, one clears IRQ's * on the local processor, one does not. * - * These are fair FIFO ticket locks, which are currently limited to 256 - * CPUs. + * These are fair FIFO ticket locks, which support up to 2^16 CPUs. * * (the type definitions are in asm/spinlock_types.h) */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index f2b83bc7d78..cdf5674dd23 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -1,6 +1,135 @@ #ifndef __SVM_H #define __SVM_H +#define SVM_EXIT_READ_CR0 0x000 +#define SVM_EXIT_READ_CR3 0x003 +#define SVM_EXIT_READ_CR4 0x004 +#define SVM_EXIT_READ_CR8 0x008 +#define SVM_EXIT_WRITE_CR0 0x010 +#define SVM_EXIT_WRITE_CR3 0x013 +#define SVM_EXIT_WRITE_CR4 0x014 +#define SVM_EXIT_WRITE_CR8 0x018 +#define SVM_EXIT_READ_DR0 0x020 +#define SVM_EXIT_READ_DR1 0x021 +#define SVM_EXIT_READ_DR2 0x022 +#define SVM_EXIT_READ_DR3 0x023 +#define SVM_EXIT_READ_DR4 0x024 +#define SVM_EXIT_READ_DR5 0x025 +#define SVM_EXIT_READ_DR6 0x026 +#define SVM_EXIT_READ_DR7 0x027 +#define SVM_EXIT_WRITE_DR0 0x030 +#define SVM_EXIT_WRITE_DR1 0x031 +#define SVM_EXIT_WRITE_DR2 0x032 +#define SVM_EXIT_WRITE_DR3 0x033 +#define SVM_EXIT_WRITE_DR4 0x034 +#define SVM_EXIT_WRITE_DR5 0x035 +#define SVM_EXIT_WRITE_DR6 0x036 +#define SVM_EXIT_WRITE_DR7 0x037 +#define SVM_EXIT_EXCP_BASE 0x040 +#define SVM_EXIT_INTR 0x060 +#define SVM_EXIT_NMI 0x061 +#define SVM_EXIT_SMI 0x062 +#define SVM_EXIT_INIT 0x063 +#define SVM_EXIT_VINTR 0x064 +#define SVM_EXIT_CR0_SEL_WRITE 0x065 +#define SVM_EXIT_IDTR_READ 0x066 +#define SVM_EXIT_GDTR_READ 0x067 +#define SVM_EXIT_LDTR_READ 0x068 +#define SVM_EXIT_TR_READ 0x069 +#define SVM_EXIT_IDTR_WRITE 0x06a +#define SVM_EXIT_GDTR_WRITE 0x06b +#define SVM_EXIT_LDTR_WRITE 0x06c +#define SVM_EXIT_TR_WRITE 0x06d +#define SVM_EXIT_RDTSC 0x06e +#define SVM_EXIT_RDPMC 0x06f +#define SVM_EXIT_PUSHF 0x070 +#define SVM_EXIT_POPF 0x071 +#define SVM_EXIT_CPUID 0x072 +#define SVM_EXIT_RSM 0x073 +#define SVM_EXIT_IRET 0x074 +#define SVM_EXIT_SWINT 0x075 +#define SVM_EXIT_INVD 0x076 +#define SVM_EXIT_PAUSE 0x077 +#define SVM_EXIT_HLT 0x078 +#define SVM_EXIT_INVLPG 0x079 +#define SVM_EXIT_INVLPGA 0x07a +#define SVM_EXIT_IOIO 0x07b +#define SVM_EXIT_MSR 0x07c +#define SVM_EXIT_TASK_SWITCH 0x07d +#define SVM_EXIT_FERR_FREEZE 0x07e +#define SVM_EXIT_SHUTDOWN 0x07f +#define SVM_EXIT_VMRUN 0x080 +#define SVM_EXIT_VMMCALL 0x081 +#define SVM_EXIT_VMLOAD 0x082 +#define SVM_EXIT_VMSAVE 0x083 +#define SVM_EXIT_STGI 0x084 +#define SVM_EXIT_CLGI 0x085 +#define SVM_EXIT_SKINIT 0x086 +#define SVM_EXIT_RDTSCP 0x087 +#define SVM_EXIT_ICEBP 0x088 +#define SVM_EXIT_WBINVD 0x089 +#define SVM_EXIT_MONITOR 0x08a +#define SVM_EXIT_MWAIT 0x08b +#define SVM_EXIT_MWAIT_COND 0x08c +#define SVM_EXIT_XSETBV 0x08d +#define SVM_EXIT_NPF 0x400 + +#define SVM_EXIT_ERR -1 + +#define SVM_EXIT_REASONS \ + { SVM_EXIT_READ_CR0, "read_cr0" }, \ + { SVM_EXIT_READ_CR3, "read_cr3" }, \ + { SVM_EXIT_READ_CR4, "read_cr4" }, \ + { SVM_EXIT_READ_CR8, "read_cr8" }, \ + { SVM_EXIT_WRITE_CR0, "write_cr0" }, \ + { SVM_EXIT_WRITE_CR3, "write_cr3" }, \ + { SVM_EXIT_WRITE_CR4, "write_cr4" }, \ + { SVM_EXIT_WRITE_CR8, "write_cr8" }, \ + { SVM_EXIT_READ_DR0, "read_dr0" }, \ + { SVM_EXIT_READ_DR1, "read_dr1" }, \ + { SVM_EXIT_READ_DR2, "read_dr2" }, \ + { SVM_EXIT_READ_DR3, "read_dr3" }, \ + { SVM_EXIT_WRITE_DR0, "write_dr0" }, \ + { SVM_EXIT_WRITE_DR1, "write_dr1" }, \ + { SVM_EXIT_WRITE_DR2, "write_dr2" }, \ + { SVM_EXIT_WRITE_DR3, "write_dr3" }, \ + { SVM_EXIT_WRITE_DR5, "write_dr5" }, \ + { SVM_EXIT_WRITE_DR7, "write_dr7" }, \ + { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, \ + { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, \ + { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \ + { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \ + { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \ + { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \ + { SVM_EXIT_INTR, "interrupt" }, \ + { SVM_EXIT_NMI, "nmi" }, \ + { SVM_EXIT_SMI, "smi" }, \ + { SVM_EXIT_INIT, "init" }, \ + { SVM_EXIT_VINTR, "vintr" }, \ + { SVM_EXIT_CPUID, "cpuid" }, \ + { SVM_EXIT_INVD, "invd" }, \ + { SVM_EXIT_HLT, "hlt" }, \ + { SVM_EXIT_INVLPG, "invlpg" }, \ + { SVM_EXIT_INVLPGA, "invlpga" }, \ + { SVM_EXIT_IOIO, "io" }, \ + { SVM_EXIT_MSR, "msr" }, \ + { SVM_EXIT_TASK_SWITCH, "task_switch" }, \ + { SVM_EXIT_SHUTDOWN, "shutdown" }, \ + { SVM_EXIT_VMRUN, "vmrun" }, \ + { SVM_EXIT_VMMCALL, "hypercall" }, \ + { SVM_EXIT_VMLOAD, "vmload" }, \ + { SVM_EXIT_VMSAVE, "vmsave" }, \ + { SVM_EXIT_STGI, "stgi" }, \ + { SVM_EXIT_CLGI, "clgi" }, \ + { SVM_EXIT_SKINIT, "skinit" }, \ + { SVM_EXIT_WBINVD, "wbinvd" }, \ + { SVM_EXIT_MONITOR, "monitor" }, \ + { SVM_EXIT_MWAIT, "mwait" }, \ + { SVM_EXIT_XSETBV, "xsetbv" }, \ + { SVM_EXIT_NPF, "npf" } + +#ifdef __KERNEL__ + enum { INTERCEPT_INTR, INTERCEPT_NMI, @@ -264,81 +393,6 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_EXITINFO_REG_MASK 0x0F -#define SVM_EXIT_READ_CR0 0x000 -#define SVM_EXIT_READ_CR3 0x003 -#define SVM_EXIT_READ_CR4 0x004 -#define SVM_EXIT_READ_CR8 0x008 -#define SVM_EXIT_WRITE_CR0 0x010 -#define SVM_EXIT_WRITE_CR3 0x013 -#define SVM_EXIT_WRITE_CR4 0x014 -#define SVM_EXIT_WRITE_CR8 0x018 -#define SVM_EXIT_READ_DR0 0x020 -#define SVM_EXIT_READ_DR1 0x021 -#define SVM_EXIT_READ_DR2 0x022 -#define SVM_EXIT_READ_DR3 0x023 -#define SVM_EXIT_READ_DR4 0x024 -#define SVM_EXIT_READ_DR5 0x025 -#define SVM_EXIT_READ_DR6 0x026 -#define SVM_EXIT_READ_DR7 0x027 -#define SVM_EXIT_WRITE_DR0 0x030 -#define SVM_EXIT_WRITE_DR1 0x031 -#define SVM_EXIT_WRITE_DR2 0x032 -#define SVM_EXIT_WRITE_DR3 0x033 -#define SVM_EXIT_WRITE_DR4 0x034 -#define SVM_EXIT_WRITE_DR5 0x035 -#define SVM_EXIT_WRITE_DR6 0x036 -#define SVM_EXIT_WRITE_DR7 0x037 -#define SVM_EXIT_EXCP_BASE 0x040 -#define SVM_EXIT_INTR 0x060 -#define SVM_EXIT_NMI 0x061 -#define SVM_EXIT_SMI 0x062 -#define SVM_EXIT_INIT 0x063 -#define SVM_EXIT_VINTR 0x064 -#define SVM_EXIT_CR0_SEL_WRITE 0x065 -#define SVM_EXIT_IDTR_READ 0x066 -#define SVM_EXIT_GDTR_READ 0x067 -#define SVM_EXIT_LDTR_READ 0x068 -#define SVM_EXIT_TR_READ 0x069 -#define SVM_EXIT_IDTR_WRITE 0x06a -#define SVM_EXIT_GDTR_WRITE 0x06b -#define SVM_EXIT_LDTR_WRITE 0x06c -#define SVM_EXIT_TR_WRITE 0x06d -#define SVM_EXIT_RDTSC 0x06e -#define SVM_EXIT_RDPMC 0x06f -#define SVM_EXIT_PUSHF 0x070 -#define SVM_EXIT_POPF 0x071 -#define SVM_EXIT_CPUID 0x072 -#define SVM_EXIT_RSM 0x073 -#define SVM_EXIT_IRET 0x074 -#define SVM_EXIT_SWINT 0x075 -#define SVM_EXIT_INVD 0x076 -#define SVM_EXIT_PAUSE 0x077 -#define SVM_EXIT_HLT 0x078 -#define SVM_EXIT_INVLPG 0x079 -#define SVM_EXIT_INVLPGA 0x07a -#define SVM_EXIT_IOIO 0x07b -#define SVM_EXIT_MSR 0x07c -#define SVM_EXIT_TASK_SWITCH 0x07d -#define SVM_EXIT_FERR_FREEZE 0x07e -#define SVM_EXIT_SHUTDOWN 0x07f -#define SVM_EXIT_VMRUN 0x080 -#define SVM_EXIT_VMMCALL 0x081 -#define SVM_EXIT_VMLOAD 0x082 -#define SVM_EXIT_VMSAVE 0x083 -#define SVM_EXIT_STGI 0x084 -#define SVM_EXIT_CLGI 0x085 -#define SVM_EXIT_SKINIT 0x086 -#define SVM_EXIT_RDTSCP 0x087 -#define SVM_EXIT_ICEBP 0x088 -#define SVM_EXIT_WBINVD 0x089 -#define SVM_EXIT_MONITOR 0x08a -#define SVM_EXIT_MWAIT 0x08b -#define SVM_EXIT_MWAIT_COND 0x08c -#define SVM_EXIT_XSETBV 0x08d -#define SVM_EXIT_NPF 0x400 - -#define SVM_EXIT_ERR -1 - #define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP) #define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda" @@ -350,3 +404,4 @@ struct __attribute__ ((__packed__)) vmcb { #endif +#endif diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 3fda9db4881..4ca1c611b55 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -40,7 +40,7 @@ asmlinkage long sys32_sigaction(int, struct old_sigaction32 __user *, struct old_sigaction32 __user *); asmlinkage long sys32_alarm(unsigned int); -asmlinkage long sys32_waitpid(compat_pid_t, unsigned int *, int); +asmlinkage long sys32_waitpid(compat_pid_t, unsigned int __user *, int); asmlinkage long sys32_sysfs(int, u32, u32); asmlinkage long sys32_sched_rr_get_interval(compat_pid_t, diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 89f794f007e..c535d847e3b 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -89,6 +89,7 @@ struct thread_info { #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_DEBUG 21 /* uses debug registers */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ @@ -114,6 +115,7 @@ struct thread_info { #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_DEBUG (1 << TIF_DEBUG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) @@ -126,12 +128,13 @@ struct thread_info { /* work to do in syscall_trace_enter() */ #define _TIF_WORK_SYSCALL_ENTRY \ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT | \ - _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT) + _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT | \ + _TIF_NOHZ) /* work to do in syscall_trace_leave() */ #define _TIF_WORK_SYSCALL_EXIT \ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \ - _TIF_SYSCALL_TRACEPOINT) + _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ) /* work to do on interrupt/exception return */ #define _TIF_WORK_MASK \ @@ -141,7 +144,8 @@ struct thread_info { /* work to do on any return to user space */ #define _TIF_ALLWORK_MASK \ - ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT) + ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT | \ + _TIF_NOHZ) /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index e1f3a17034f..a91acfbb1a9 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -9,6 +9,7 @@ #include <linux/string.h> #include <asm/asm.h> #include <asm/page.h> +#include <asm/smap.h> #define VERIFY_READ 0 #define VERIFY_WRITE 1 @@ -192,9 +193,10 @@ extern int __get_user_bad(void); #ifdef CONFIG_X86_32 #define __put_user_asm_u64(x, addr, err, errret) \ - asm volatile("1: movl %%eax,0(%2)\n" \ + asm volatile(ASM_STAC "\n" \ + "1: movl %%eax,0(%2)\n" \ "2: movl %%edx,4(%2)\n" \ - "3:\n" \ + "3: " ASM_CLAC "\n" \ ".section .fixup,\"ax\"\n" \ "4: movl %3,%0\n" \ " jmp 3b\n" \ @@ -205,9 +207,10 @@ extern int __get_user_bad(void); : "A" (x), "r" (addr), "i" (errret), "0" (err)) #define __put_user_asm_ex_u64(x, addr) \ - asm volatile("1: movl %%eax,0(%1)\n" \ + asm volatile(ASM_STAC "\n" \ + "1: movl %%eax,0(%1)\n" \ "2: movl %%edx,4(%1)\n" \ - "3:\n" \ + "3: " ASM_CLAC "\n" \ _ASM_EXTABLE_EX(1b, 2b) \ _ASM_EXTABLE_EX(2b, 3b) \ : : "A" (x), "r" (addr)) @@ -379,8 +382,9 @@ do { \ } while (0) #define __get_user_asm(x, addr, err, itype, rtype, ltype, errret) \ - asm volatile("1: mov"itype" %2,%"rtype"1\n" \ - "2:\n" \ + asm volatile(ASM_STAC "\n" \ + "1: mov"itype" %2,%"rtype"1\n" \ + "2: " ASM_CLAC "\n" \ ".section .fixup,\"ax\"\n" \ "3: mov %3,%0\n" \ " xor"itype" %"rtype"1,%"rtype"1\n" \ @@ -443,8 +447,9 @@ struct __large_struct { unsigned long buf[100]; }; * aliasing issues. */ #define __put_user_asm(x, addr, err, itype, rtype, ltype, errret) \ - asm volatile("1: mov"itype" %"rtype"1,%2\n" \ - "2:\n" \ + asm volatile(ASM_STAC "\n" \ + "1: mov"itype" %"rtype"1,%2\n" \ + "2: " ASM_CLAC "\n" \ ".section .fixup,\"ax\"\n" \ "3: mov %3,%0\n" \ " jmp 2b\n" \ @@ -463,13 +468,13 @@ struct __large_struct { unsigned long buf[100]; }; * uaccess_try and catch */ #define uaccess_try do { \ - int prev_err = current_thread_info()->uaccess_err; \ current_thread_info()->uaccess_err = 0; \ + stac(); \ barrier(); #define uaccess_catch(err) \ + clac(); \ (err) |= (current_thread_info()->uaccess_err ? -EFAULT : 0); \ - current_thread_info()->uaccess_err = prev_err; \ } while (0) /** @@ -569,6 +574,9 @@ strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strlen_user(const char __user *str); extern __must_check long strnlen_user(const char __user *str, long n); +unsigned long __must_check clear_user(void __user *mem, unsigned long len); +unsigned long __must_check __clear_user(void __user *mem, unsigned long len); + /* * movsl can be slow when source and dest are not both 8-byte aligned */ diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 576e39bca6a..7f760a9f1f6 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -213,7 +213,4 @@ static inline unsigned long __must_check copy_from_user(void *to, return n; } -unsigned long __must_check clear_user(void __user *mem, unsigned long len); -unsigned long __must_check __clear_user(void __user *mem, unsigned long len); - #endif /* _ASM_X86_UACCESS_32_H */ diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index d8def8b3dba..142810c457d 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -217,9 +217,6 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size) } } -__must_check unsigned long clear_user(void __user *mem, unsigned long len); -__must_check unsigned long __clear_user(void __user *mem, unsigned long len); - static __must_check __always_inline int __copy_from_user_inatomic(void *dst, const void __user *src, unsigned size) { diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index f3971bbcd1d..8ff8be7835a 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -42,10 +42,11 @@ struct arch_uprobe { }; struct arch_uprobe_task { - unsigned long saved_trap_nr; #ifdef CONFIG_X86_64 unsigned long saved_scratch_register; #endif + unsigned int saved_trap_nr; + unsigned int saved_tf; }; extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr); diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index bb0522850b7..fddb53d6391 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -11,7 +11,8 @@ extern const char VDSO32_PRELINK[]; #define VDSO32_SYMBOL(base, name) \ ({ \ extern const char VDSO32_##name[]; \ - (void *)(VDSO32_##name - VDSO32_PRELINK + (unsigned long)(base)); \ + (void __user *)(VDSO32_##name - VDSO32_PRELINK + \ + (unsigned long)(base)); \ }) #endif diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 74fcb963595..36ec21c36d6 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -25,6 +25,88 @@ * */ +#define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000 + +#define EXIT_REASON_EXCEPTION_NMI 0 +#define EXIT_REASON_EXTERNAL_INTERRUPT 1 +#define EXIT_REASON_TRIPLE_FAULT 2 + +#define EXIT_REASON_PENDING_INTERRUPT 7 +#define EXIT_REASON_NMI_WINDOW 8 +#define EXIT_REASON_TASK_SWITCH 9 +#define EXIT_REASON_CPUID 10 +#define EXIT_REASON_HLT 12 +#define EXIT_REASON_INVD 13 +#define EXIT_REASON_INVLPG 14 +#define EXIT_REASON_RDPMC 15 +#define EXIT_REASON_RDTSC 16 +#define EXIT_REASON_VMCALL 18 +#define EXIT_REASON_VMCLEAR 19 +#define EXIT_REASON_VMLAUNCH 20 +#define EXIT_REASON_VMPTRLD 21 +#define EXIT_REASON_VMPTRST 22 +#define EXIT_REASON_VMREAD 23 +#define EXIT_REASON_VMRESUME 24 +#define EXIT_REASON_VMWRITE 25 +#define EXIT_REASON_VMOFF 26 +#define EXIT_REASON_VMON 27 +#define EXIT_REASON_CR_ACCESS 28 +#define EXIT_REASON_DR_ACCESS 29 +#define EXIT_REASON_IO_INSTRUCTION 30 +#define EXIT_REASON_MSR_READ 31 +#define EXIT_REASON_MSR_WRITE 32 +#define EXIT_REASON_INVALID_STATE 33 +#define EXIT_REASON_MWAIT_INSTRUCTION 36 +#define EXIT_REASON_MONITOR_INSTRUCTION 39 +#define EXIT_REASON_PAUSE_INSTRUCTION 40 +#define EXIT_REASON_MCE_DURING_VMENTRY 41 +#define EXIT_REASON_TPR_BELOW_THRESHOLD 43 +#define EXIT_REASON_APIC_ACCESS 44 +#define EXIT_REASON_EPT_VIOLATION 48 +#define EXIT_REASON_EPT_MISCONFIG 49 +#define EXIT_REASON_WBINVD 54 +#define EXIT_REASON_XSETBV 55 +#define EXIT_REASON_INVPCID 58 + +#define VMX_EXIT_REASONS \ + { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ + { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ + { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ + { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \ + { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ + { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ + { EXIT_REASON_CPUID, "CPUID" }, \ + { EXIT_REASON_HLT, "HLT" }, \ + { EXIT_REASON_INVLPG, "INVLPG" }, \ + { EXIT_REASON_RDPMC, "RDPMC" }, \ + { EXIT_REASON_RDTSC, "RDTSC" }, \ + { EXIT_REASON_VMCALL, "VMCALL" }, \ + { EXIT_REASON_VMCLEAR, "VMCLEAR" }, \ + { EXIT_REASON_VMLAUNCH, "VMLAUNCH" }, \ + { EXIT_REASON_VMPTRLD, "VMPTRLD" }, \ + { EXIT_REASON_VMPTRST, "VMPTRST" }, \ + { EXIT_REASON_VMREAD, "VMREAD" }, \ + { EXIT_REASON_VMRESUME, "VMRESUME" }, \ + { EXIT_REASON_VMWRITE, "VMWRITE" }, \ + { EXIT_REASON_VMOFF, "VMOFF" }, \ + { EXIT_REASON_VMON, "VMON" }, \ + { EXIT_REASON_CR_ACCESS, "CR_ACCESS" }, \ + { EXIT_REASON_DR_ACCESS, "DR_ACCESS" }, \ + { EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \ + { EXIT_REASON_MSR_READ, "MSR_READ" }, \ + { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \ + { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \ + { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \ + { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \ + { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ + { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \ + { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \ + { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \ + { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \ + { EXIT_REASON_WBINVD, "WBINVD" } + +#ifdef __KERNEL__ + #include <linux/types.h> /* @@ -241,49 +323,6 @@ enum vmcs_field { HOST_RIP = 0x00006c16, }; -#define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000 - -#define EXIT_REASON_EXCEPTION_NMI 0 -#define EXIT_REASON_EXTERNAL_INTERRUPT 1 -#define EXIT_REASON_TRIPLE_FAULT 2 - -#define EXIT_REASON_PENDING_INTERRUPT 7 -#define EXIT_REASON_NMI_WINDOW 8 -#define EXIT_REASON_TASK_SWITCH 9 -#define EXIT_REASON_CPUID 10 -#define EXIT_REASON_HLT 12 -#define EXIT_REASON_INVD 13 -#define EXIT_REASON_INVLPG 14 -#define EXIT_REASON_RDPMC 15 -#define EXIT_REASON_RDTSC 16 -#define EXIT_REASON_VMCALL 18 -#define EXIT_REASON_VMCLEAR 19 -#define EXIT_REASON_VMLAUNCH 20 -#define EXIT_REASON_VMPTRLD 21 -#define EXIT_REASON_VMPTRST 22 -#define EXIT_REASON_VMREAD 23 -#define EXIT_REASON_VMRESUME 24 -#define EXIT_REASON_VMWRITE 25 -#define EXIT_REASON_VMOFF 26 -#define EXIT_REASON_VMON 27 -#define EXIT_REASON_CR_ACCESS 28 -#define EXIT_REASON_DR_ACCESS 29 -#define EXIT_REASON_IO_INSTRUCTION 30 -#define EXIT_REASON_MSR_READ 31 -#define EXIT_REASON_MSR_WRITE 32 -#define EXIT_REASON_INVALID_STATE 33 -#define EXIT_REASON_MWAIT_INSTRUCTION 36 -#define EXIT_REASON_MONITOR_INSTRUCTION 39 -#define EXIT_REASON_PAUSE_INSTRUCTION 40 -#define EXIT_REASON_MCE_DURING_VMENTRY 41 -#define EXIT_REASON_TPR_BELOW_THRESHOLD 43 -#define EXIT_REASON_APIC_ACCESS 44 -#define EXIT_REASON_EPT_VIOLATION 48 -#define EXIT_REASON_EPT_MISCONFIG 49 -#define EXIT_REASON_WBINVD 54 -#define EXIT_REASON_XSETBV 55 -#define EXIT_REASON_INVPCID 58 - /* * Interruption-information format */ @@ -488,3 +527,5 @@ enum vm_instruction_error_number { }; #endif + +#endif diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 38155f66714..57693498519 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -81,12 +81,13 @@ struct x86_init_mapping { /** * struct x86_init_paging - platform specific paging functions - * @pagetable_setup_start: platform specific pre paging_init() call - * @pagetable_setup_done: platform specific post paging_init() call + * @pagetable_init: platform specific paging initialization call to setup + * the kernel pagetables and prepare accessors functions. + * Callback must call paging_init(). Called once after the + * direct mapping for phys memory is available. */ struct x86_init_paging { - void (*pagetable_setup_start)(pgd_t *base); - void (*pagetable_setup_done)(pgd_t *base); + void (*pagetable_init)(void); }; /** diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 93971e841dd..472b9b78301 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -51,7 +51,8 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s, extern int m2p_add_override(unsigned long mfn, struct page *page, struct gnttab_map_grant_ref *kmap_op); -extern int m2p_remove_override(struct page *page, bool clear_pte); +extern int m2p_remove_override(struct page *page, + struct gnttab_map_grant_ref *kmap_op); extern struct page *m2p_find_override(unsigned long mfn); extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn); diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h index 454570891bd..aabd5850bdb 100644 --- a/arch/x86/include/asm/xor_32.h +++ b/arch/x86/include/asm/xor_32.h @@ -534,38 +534,6 @@ static struct xor_block_template xor_block_p5_mmx = { * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo) */ -#define XMMS_SAVE \ -do { \ - preempt_disable(); \ - cr0 = read_cr0(); \ - clts(); \ - asm volatile( \ - "movups %%xmm0,(%0) ;\n\t" \ - "movups %%xmm1,0x10(%0) ;\n\t" \ - "movups %%xmm2,0x20(%0) ;\n\t" \ - "movups %%xmm3,0x30(%0) ;\n\t" \ - : \ - : "r" (xmm_save) \ - : "memory"); \ -} while (0) - -#define XMMS_RESTORE \ -do { \ - asm volatile( \ - "sfence ;\n\t" \ - "movups (%0),%%xmm0 ;\n\t" \ - "movups 0x10(%0),%%xmm1 ;\n\t" \ - "movups 0x20(%0),%%xmm2 ;\n\t" \ - "movups 0x30(%0),%%xmm3 ;\n\t" \ - : \ - : "r" (xmm_save) \ - : "memory"); \ - write_cr0(cr0); \ - preempt_enable(); \ -} while (0) - -#define ALIGN16 __attribute__((aligned(16))) - #define OFFS(x) "16*("#x")" #define PF_OFFS(x) "256+16*("#x")" #define PF0(x) " prefetchnta "PF_OFFS(x)"(%1) ;\n" @@ -587,10 +555,8 @@ static void xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) { unsigned long lines = bytes >> 8; - char xmm_save[16*4] ALIGN16; - int cr0; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -633,7 +599,7 @@ xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) : : "memory"); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -641,10 +607,8 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3) { unsigned long lines = bytes >> 8; - char xmm_save[16*4] ALIGN16; - int cr0; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -694,7 +658,7 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, : : "memory" ); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -702,10 +666,8 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3, unsigned long *p4) { unsigned long lines = bytes >> 8; - char xmm_save[16*4] ALIGN16; - int cr0; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -762,7 +724,7 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, : : "memory" ); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -770,10 +732,8 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3, unsigned long *p4, unsigned long *p5) { unsigned long lines = bytes >> 8; - char xmm_save[16*4] ALIGN16; - int cr0; - XMMS_SAVE; + kernel_fpu_begin(); /* Make sure GCC forgets anything it knows about p4 or p5, such that it won't pass to the asm volatile below a @@ -850,7 +810,7 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, like assuming they have some legal value. */ asm("" : "=r" (p4), "=r" (p5)); - XMMS_RESTORE; + kernel_fpu_end(); } static struct xor_block_template xor_block_pIII_sse = { diff --git a/arch/x86/include/asm/xor_64.h b/arch/x86/include/asm/xor_64.h index b9b2323e90f..5fc06d0b7eb 100644 --- a/arch/x86/include/asm/xor_64.h +++ b/arch/x86/include/asm/xor_64.h @@ -34,41 +34,7 @@ * no advantages to be gotten from x86-64 here anyways. */ -typedef struct { - unsigned long a, b; -} __attribute__((aligned(16))) xmm_store_t; - -/* Doesn't use gcc to save the XMM registers, because there is no easy way to - tell it to do a clts before the register saving. */ -#define XMMS_SAVE \ -do { \ - preempt_disable(); \ - asm volatile( \ - "movq %%cr0,%0 ;\n\t" \ - "clts ;\n\t" \ - "movups %%xmm0,(%1) ;\n\t" \ - "movups %%xmm1,0x10(%1) ;\n\t" \ - "movups %%xmm2,0x20(%1) ;\n\t" \ - "movups %%xmm3,0x30(%1) ;\n\t" \ - : "=&r" (cr0) \ - : "r" (xmm_save) \ - : "memory"); \ -} while (0) - -#define XMMS_RESTORE \ -do { \ - asm volatile( \ - "sfence ;\n\t" \ - "movups (%1),%%xmm0 ;\n\t" \ - "movups 0x10(%1),%%xmm1 ;\n\t" \ - "movups 0x20(%1),%%xmm2 ;\n\t" \ - "movups 0x30(%1),%%xmm3 ;\n\t" \ - "movq %0,%%cr0 ;\n\t" \ - : \ - : "r" (cr0), "r" (xmm_save) \ - : "memory"); \ - preempt_enable(); \ -} while (0) +#include <asm/i387.h> #define OFFS(x) "16*("#x")" #define PF_OFFS(x) "256+16*("#x")" @@ -91,10 +57,8 @@ static void xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) { unsigned int lines = bytes >> 8; - unsigned long cr0; - xmm_store_t xmm_save[4]; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -135,7 +99,7 @@ xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) : [inc] "r" (256UL) : "memory"); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -143,11 +107,8 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3) { unsigned int lines = bytes >> 8; - xmm_store_t xmm_save[4]; - unsigned long cr0; - - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK #define BLOCK(i) \ @@ -194,7 +155,7 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3) : [inc] "r" (256UL) : "memory"); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -202,10 +163,8 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3, unsigned long *p4) { unsigned int lines = bytes >> 8; - xmm_store_t xmm_save[4]; - unsigned long cr0; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -261,7 +220,7 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, : [inc] "r" (256UL) : "memory" ); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -269,10 +228,8 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3, unsigned long *p4, unsigned long *p5) { unsigned int lines = bytes >> 8; - xmm_store_t xmm_save[4]; - unsigned long cr0; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -336,7 +293,7 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, : [inc] "r" (256UL) : "memory"); - XMMS_RESTORE; + kernel_fpu_end(); } static struct xor_block_template xor_block_sse = { diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h index 2510d35f480..7ea79c5fa1f 100644 --- a/arch/x86/include/asm/xor_avx.h +++ b/arch/x86/include/asm/xor_avx.h @@ -20,32 +20,6 @@ #include <linux/compiler.h> #include <asm/i387.h> -#define ALIGN32 __aligned(32) - -#define YMM_SAVED_REGS 4 - -#define YMMS_SAVE \ -do { \ - preempt_disable(); \ - cr0 = read_cr0(); \ - clts(); \ - asm volatile("vmovaps %%ymm0, %0" : "=m" (ymm_save[0]) : : "memory"); \ - asm volatile("vmovaps %%ymm1, %0" : "=m" (ymm_save[32]) : : "memory"); \ - asm volatile("vmovaps %%ymm2, %0" : "=m" (ymm_save[64]) : : "memory"); \ - asm volatile("vmovaps %%ymm3, %0" : "=m" (ymm_save[96]) : : "memory"); \ -} while (0); - -#define YMMS_RESTORE \ -do { \ - asm volatile("sfence" : : : "memory"); \ - asm volatile("vmovaps %0, %%ymm3" : : "m" (ymm_save[96])); \ - asm volatile("vmovaps %0, %%ymm2" : : "m" (ymm_save[64])); \ - asm volatile("vmovaps %0, %%ymm1" : : "m" (ymm_save[32])); \ - asm volatile("vmovaps %0, %%ymm0" : : "m" (ymm_save[0])); \ - write_cr0(cr0); \ - preempt_enable(); \ -} while (0); - #define BLOCK4(i) \ BLOCK(32 * i, 0) \ BLOCK(32 * (i + 1), 1) \ @@ -60,10 +34,9 @@ do { \ static void xor_avx_2(unsigned long bytes, unsigned long *p0, unsigned long *p1) { - unsigned long cr0, lines = bytes >> 9; - char ymm_save[32 * YMM_SAVED_REGS] ALIGN32; + unsigned long lines = bytes >> 9; - YMMS_SAVE + kernel_fpu_begin(); while (lines--) { #undef BLOCK @@ -82,16 +55,15 @@ do { \ p1 = (unsigned long *)((uintptr_t)p1 + 512); } - YMMS_RESTORE + kernel_fpu_end(); } static void xor_avx_3(unsigned long bytes, unsigned long *p0, unsigned long *p1, unsigned long *p2) { - unsigned long cr0, lines = bytes >> 9; - char ymm_save[32 * YMM_SAVED_REGS] ALIGN32; + unsigned long lines = bytes >> 9; - YMMS_SAVE + kernel_fpu_begin(); while (lines--) { #undef BLOCK @@ -113,16 +85,15 @@ do { \ p2 = (unsigned long *)((uintptr_t)p2 + 512); } - YMMS_RESTORE + kernel_fpu_end(); } static void xor_avx_4(unsigned long bytes, unsigned long *p0, unsigned long *p1, unsigned long *p2, unsigned long *p3) { - unsigned long cr0, lines = bytes >> 9; - char ymm_save[32 * YMM_SAVED_REGS] ALIGN32; + unsigned long lines = bytes >> 9; - YMMS_SAVE + kernel_fpu_begin(); while (lines--) { #undef BLOCK @@ -147,16 +118,15 @@ do { \ p3 = (unsigned long *)((uintptr_t)p3 + 512); } - YMMS_RESTORE + kernel_fpu_end(); } static void xor_avx_5(unsigned long bytes, unsigned long *p0, unsigned long *p1, unsigned long *p2, unsigned long *p3, unsigned long *p4) { - unsigned long cr0, lines = bytes >> 9; - char ymm_save[32 * YMM_SAVED_REGS] ALIGN32; + unsigned long lines = bytes >> 9; - YMMS_SAVE + kernel_fpu_begin(); while (lines--) { #undef BLOCK @@ -184,7 +154,7 @@ do { \ p4 = (unsigned long *)((uintptr_t)p4 + 512); } - YMMS_RESTORE + kernel_fpu_end(); } static struct xor_block_template xor_block_avx = { diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index 8a1b6f9b594..0415cdabb5a 100644 --- a/arch/x86/include/asm/xsave.h +++ b/arch/x86/include/asm/xsave.h @@ -34,17 +34,14 @@ extern unsigned int xstate_size; extern u64 pcntxt_mask; extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; +extern struct xsave_struct *init_xstate_buf; extern void xsave_init(void); extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); extern int init_fpu(struct task_struct *child); -extern int check_for_xstate(struct i387_fxsave_struct __user *buf, - void __user *fpstate, - struct _fpx_sw_bytes *sw); -static inline int fpu_xrstor_checking(struct fpu *fpu) +static inline int fpu_xrstor_checking(struct xsave_struct *fx) { - struct xsave_struct *fx = &fpu->state->xsave; int err; asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n\t" @@ -69,13 +66,13 @@ static inline int xsave_user(struct xsave_struct __user *buf) * Clear the xsave header first, so that reserved fields are * initialized to zero. */ - err = __clear_user(&buf->xsave_hdr, - sizeof(struct xsave_hdr_struct)); + err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr)); if (unlikely(err)) return -EFAULT; - __asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x27\n" - "2:\n" + __asm__ __volatile__(ASM_STAC "\n" + "1: .byte " REX_PREFIX "0x0f,0xae,0x27\n" + "2: " ASM_CLAC "\n" ".section .fixup,\"ax\"\n" "3: movl $-1,%[err]\n" " jmp 2b\n" @@ -84,9 +81,6 @@ static inline int xsave_user(struct xsave_struct __user *buf) : [err] "=r" (err) : "D" (buf), "a" (-1), "d" (-1), "0" (0) : "memory"); - if (unlikely(err) && __clear_user(buf, xstate_size)) - err = -EFAULT; - /* No need to clear here because the caller clears USED_MATH */ return err; } @@ -97,8 +91,9 @@ static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask) u32 lmask = mask; u32 hmask = mask >> 32; - __asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n" - "2:\n" + __asm__ __volatile__(ASM_STAC "\n" + "1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n" + "2: " ASM_CLAC "\n" ".section .fixup,\"ax\"\n" "3: movl $-1,%[err]\n" " jmp 2b\n" diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 8215e5652d9..8d7a619718b 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -100,6 +100,8 @@ obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_OF) += devicetree.o obj-$(CONFIG_UPROBES) += uprobes.o +obj-$(CONFIG_PERF_EVENTS) += perf_regs.o + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index b2297e58c6e..e651f7a589a 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -656,7 +656,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu) acpi_register_lapic(physid, ACPI_MADT_ENABLED); /* - * If mp_register_lapic successfully generates a new logical cpu + * If acpi_register_lapic successfully generates a new logical cpu * number, then the following will get us exactly what was mapped */ cpumask_andnot(new_map, cpu_present_mask, tmp_map); diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 95bf99de905..11676cf65ae 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -25,10 +25,6 @@ unsigned long acpi_realmode_flags; static char temp_stack[4096]; #endif -asmlinkage void acpi_enter_s3(void) -{ - acpi_enter_sleep_state(3, wake_sleep_flags); -} /** * acpi_suspend_lowlevel - save kernel state * @@ -47,17 +43,22 @@ int acpi_suspend_lowlevel(void) header->video_mode = saved_video_mode; + header->pmode_behavior = 0; + #ifndef CONFIG_64BIT store_gdt((struct desc_ptr *)&header->pmode_gdt); - if (rdmsr_safe(MSR_EFER, &header->pmode_efer_low, - &header->pmode_efer_high)) - header->pmode_efer_low = header->pmode_efer_high = 0; + if (!rdmsr_safe(MSR_EFER, + &header->pmode_efer_low, + &header->pmode_efer_high)) + header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_EFER); #endif /* !CONFIG_64BIT */ header->pmode_cr0 = read_cr0(); - header->pmode_cr4 = read_cr4_safe(); - header->pmode_behavior = 0; + if (__this_cpu_read(cpu_info.cpuid_level) >= 0) { + header->pmode_cr4 = read_cr4(); + header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_CR4); + } if (!rdmsr_safe(MSR_IA32_MISC_ENABLE, &header->pmode_misc_en_low, &header->pmode_misc_en_high)) diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index 5653a5791ec..67f59f8c695 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -2,7 +2,6 @@ * Variables and functions used by the code in sleep.c */ -#include <linux/linkage.h> #include <asm/realmode.h> extern unsigned long saved_video_mode; @@ -11,7 +10,6 @@ extern long saved_magic; extern int wakeup_pmode_return; extern u8 wake_sleep_flags; -extern asmlinkage void acpi_enter_s3(void); extern unsigned long acpi_copy_wakeup_routine(unsigned long); extern void wakeup_long64(void); diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index 72610839f03..13ab720573e 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -74,7 +74,9 @@ restore_registers: ENTRY(do_suspend_lowlevel) call save_processor_state call save_registers - call acpi_enter_s3 + pushl $3 + call acpi_enter_sleep_state + addl $4, %esp # In case of S3 failure, we'll emerge here. Jump # to ret_point to recover diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 014d1d28c39..8ea5164cbd0 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -71,7 +71,9 @@ ENTRY(do_suspend_lowlevel) movq %rsi, saved_rsi addq $8, %rsp - call acpi_enter_s3 + movl $3, %edi + xorl %eax, %eax + call acpi_enter_sleep_state /* in case something went wrong, restore the machine status and go on */ jmp resume_point diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 931280ff829..ef5ccca79a6 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -23,19 +23,6 @@ #define MAX_PATCH_LEN (255-1) -#ifdef CONFIG_HOTPLUG_CPU -static int smp_alt_once; - -static int __init bootonly(char *str) -{ - smp_alt_once = 1; - return 1; -} -__setup("smp-alt-boot", bootonly); -#else -#define smp_alt_once 1 -#endif - static int __initdata_or_module debug_alternative; static int __init debug_alt(char *str) @@ -165,7 +152,7 @@ static const unsigned char * const k7_nops[ASM_NOP_MAX+2] = #endif #ifdef P6_NOP1 -static const unsigned char __initconst_or_module p6nops[] = +static const unsigned char p6nops[] = { P6_NOP1, P6_NOP2, @@ -224,7 +211,7 @@ void __init arch_init_ideal_nops(void) ideal_nops = intel_nops; #endif } - + break; default: #ifdef CONFIG_X86_64 ideal_nops = k8_nops; @@ -317,7 +304,7 @@ static void alternatives_smp_lock(const s32 *start, const s32 *end, /* turn DS segment override prefix into lock prefix */ if (*ptr == 0x3e) text_poke(ptr, ((unsigned char []){0xf0}), 1); - }; + } mutex_unlock(&text_mutex); } @@ -326,9 +313,6 @@ static void alternatives_smp_unlock(const s32 *start, const s32 *end, { const s32 *poff; - if (noreplace_smp) - return; - mutex_lock(&text_mutex); for (poff = start; poff < end; poff++) { u8 *ptr = (u8 *)poff + *poff; @@ -338,7 +322,7 @@ static void alternatives_smp_unlock(const s32 *start, const s32 *end, /* turn lock prefix into DS segment override prefix */ if (*ptr == 0xf0) text_poke(ptr, ((unsigned char []){0x3E}), 1); - }; + } mutex_unlock(&text_mutex); } @@ -359,7 +343,7 @@ struct smp_alt_module { }; static LIST_HEAD(smp_alt_modules); static DEFINE_MUTEX(smp_alt); -static int smp_mode = 1; /* protected by smp_alt */ +static bool uniproc_patched = false; /* protected by smp_alt */ void __init_or_module alternatives_smp_module_add(struct module *mod, char *name, @@ -368,19 +352,18 @@ void __init_or_module alternatives_smp_module_add(struct module *mod, { struct smp_alt_module *smp; - if (noreplace_smp) - return; + mutex_lock(&smp_alt); + if (!uniproc_patched) + goto unlock; - if (smp_alt_once) { - if (boot_cpu_has(X86_FEATURE_UP)) - alternatives_smp_unlock(locks, locks_end, - text, text_end); - return; - } + if (num_possible_cpus() == 1) + /* Don't bother remembering, we'll never have to undo it. */ + goto smp_unlock; smp = kzalloc(sizeof(*smp), GFP_KERNEL); if (NULL == smp) - return; /* we'll run the (safe but slow) SMP code then ... */ + /* we'll run the (safe but slow) SMP code then ... */ + goto unlock; smp->mod = mod; smp->name = name; @@ -392,11 +375,10 @@ void __init_or_module alternatives_smp_module_add(struct module *mod, __func__, smp->locks, smp->locks_end, smp->text, smp->text_end, smp->name); - mutex_lock(&smp_alt); list_add_tail(&smp->next, &smp_alt_modules); - if (boot_cpu_has(X86_FEATURE_UP)) - alternatives_smp_unlock(smp->locks, smp->locks_end, - smp->text, smp->text_end); +smp_unlock: + alternatives_smp_unlock(locks, locks_end, text, text_end); +unlock: mutex_unlock(&smp_alt); } @@ -404,24 +386,18 @@ void __init_or_module alternatives_smp_module_del(struct module *mod) { struct smp_alt_module *item; - if (smp_alt_once || noreplace_smp) - return; - mutex_lock(&smp_alt); list_for_each_entry(item, &smp_alt_modules, next) { if (mod != item->mod) continue; list_del(&item->next); - mutex_unlock(&smp_alt); - DPRINTK("%s: %s\n", __func__, item->name); kfree(item); - return; + break; } mutex_unlock(&smp_alt); } -bool skip_smp_alternatives; -void alternatives_smp_switch(int smp) +void alternatives_enable_smp(void) { struct smp_alt_module *mod; @@ -436,34 +412,21 @@ void alternatives_smp_switch(int smp) pr_info("lockdep: fixing up alternatives\n"); #endif - if (noreplace_smp || smp_alt_once || skip_smp_alternatives) - return; - BUG_ON(!smp && (num_online_cpus() > 1)); + /* Why bother if there are no other CPUs? */ + BUG_ON(num_possible_cpus() == 1); mutex_lock(&smp_alt); - /* - * Avoid unnecessary switches because it forces JIT based VMs to - * throw away all cached translations, which can be quite costly. - */ - if (smp == smp_mode) { - /* nothing */ - } else if (smp) { + if (uniproc_patched) { pr_info("switching to SMP code\n"); + BUG_ON(num_online_cpus() != 1); clear_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); clear_cpu_cap(&cpu_data(0), X86_FEATURE_UP); list_for_each_entry(mod, &smp_alt_modules, next) alternatives_smp_lock(mod->locks, mod->locks_end, mod->text, mod->text_end); - } else { - pr_info("switching to UP code\n"); - set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); - set_cpu_cap(&cpu_data(0), X86_FEATURE_UP); - list_for_each_entry(mod, &smp_alt_modules, next) - alternatives_smp_unlock(mod->locks, mod->locks_end, - mod->text, mod->text_end); + uniproc_patched = false; } - smp_mode = smp; mutex_unlock(&smp_alt); } @@ -540,40 +503,22 @@ void __init alternative_instructions(void) apply_alternatives(__alt_instructions, __alt_instructions_end); - /* switch to patch-once-at-boottime-only mode and free the - * tables in case we know the number of CPUs will never ever - * change */ -#ifdef CONFIG_HOTPLUG_CPU - if (num_possible_cpus() < 2) - smp_alt_once = 1; -#endif - #ifdef CONFIG_SMP - if (smp_alt_once) { - if (1 == num_possible_cpus()) { - pr_info("switching to UP code\n"); - set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); - set_cpu_cap(&cpu_data(0), X86_FEATURE_UP); - - alternatives_smp_unlock(__smp_locks, __smp_locks_end, - _text, _etext); - } - } else { + /* Patch to UP if other cpus not imminent. */ + if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) { + uniproc_patched = true; alternatives_smp_module_add(NULL, "core kernel", __smp_locks, __smp_locks_end, _text, _etext); - - /* Only switch to UP mode if we don't immediately boot others */ - if (num_present_cpus() == 1 || setup_max_cpus <= 1) - alternatives_smp_switch(0); } -#endif - apply_paravirt(__parainstructions, __parainstructions_end); - if (smp_alt_once) + if (!uniproc_patched || num_possible_cpus() == 1) free_init_pages("SMP alternatives", (unsigned long)__smp_locks, (unsigned long)__smp_locks_end); +#endif + + apply_paravirt(__parainstructions, __parainstructions_end); restart_nmi(); } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 24deb308232..b17416e72fb 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1934,7 +1934,7 @@ void smp_error_interrupt(struct pt_regs *regs) apic_printk(APIC_DEBUG, KERN_CONT " : %s", error_interrupt_reason[i]); i++; v1 >>= 1; - }; + } apic_printk(APIC_DEBUG, KERN_CONT "\n"); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 406eee78468..c265593ec2c 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1204,7 +1204,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg) BUG_ON(!cfg->vector); vector = cfg->vector; - for_each_cpu(cpu, cfg->domain) + for_each_cpu_and(cpu, cfg->domain, cpu_online_mask) per_cpu(vector_irq, cpu)[vector] = -1; cfg->vector = 0; @@ -1212,7 +1212,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg) if (likely(!cfg->move_in_progress)) return; - for_each_cpu(cpu, cfg->old_domain) { + for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) { for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { if (per_cpu(vector_irq, cpu)[vector] != irq) @@ -1356,6 +1356,16 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, if (!IO_APIC_IRQ(irq)) return; + /* + * For legacy irqs, cfg->domain starts with cpu 0. Now that IO-APIC + * can handle this irq and the apic driver is finialized at this point, + * update the cfg->domain. + */ + if (irq < legacy_pic->nr_legacy_irqs && + cpumask_equal(cfg->domain, cpumask_of(0))) + apic->vector_allocation_domain(0, cfg->domain, + apic->target_cpus()); + if (assign_irq_vector(irq, cfg, apic->target_cpus())) return; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 9d92e19039f..f7e98a2c0d1 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -737,6 +737,72 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, } #endif +static void __cpuinit cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) +{ + if (!cpu_has_invlpg) + return; + + tlb_flushall_shift = 5; + + if (c->x86 <= 0x11) + tlb_flushall_shift = 4; +} + +static void __cpuinit cpu_detect_tlb_amd(struct cpuinfo_x86 *c) +{ + u32 ebx, eax, ecx, edx; + u16 mask = 0xfff; + + if (c->x86 < 0xf) + return; + + if (c->extended_cpuid_level < 0x80000006) + return; + + cpuid(0x80000006, &eax, &ebx, &ecx, &edx); + + tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask; + tlb_lli_4k[ENTRIES] = ebx & mask; + + /* + * K8 doesn't have 2M/4M entries in the L2 TLB so read out the L1 TLB + * characteristics from the CPUID function 0x80000005 instead. + */ + if (c->x86 == 0xf) { + cpuid(0x80000005, &eax, &ebx, &ecx, &edx); + mask = 0xff; + } + + /* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ + if (!((eax >> 16) & mask)) { + u32 a, b, c, d; + + cpuid(0x80000005, &a, &b, &c, &d); + tlb_lld_2m[ENTRIES] = (a >> 16) & 0xff; + } else { + tlb_lld_2m[ENTRIES] = (eax >> 16) & mask; + } + + /* a 4M entry uses two 2M entries */ + tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1; + + /* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ + if (!(eax & mask)) { + /* Erratum 658 */ + if (c->x86 == 0x15 && c->x86_model <= 0x1f) { + tlb_lli_2m[ENTRIES] = 1024; + } else { + cpuid(0x80000005, &eax, &ebx, &ecx, &edx); + tlb_lli_2m[ENTRIES] = eax & 0xff; + } + } else + tlb_lli_2m[ENTRIES] = eax & mask; + + tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1; + + cpu_set_tlb_flushall_shift(c); +} + static const struct cpu_dev __cpuinitconst amd_cpu_dev = { .c_vendor = "AMD", .c_ident = { "AuthenticAMD" }, @@ -756,6 +822,7 @@ static const struct cpu_dev __cpuinitconst amd_cpu_dev = { .c_size_cache = amd_size_cache, #endif .c_early_init = early_init_amd, + .c_detect_tlb = cpu_detect_tlb_amd, .c_bsp_init = bsp_init_amd, .c_init = init_amd, .c_x86_vendor = X86_VENDOR_AMD, diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index c97bb7b5a9f..d0e910da16c 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -165,10 +165,15 @@ void __init check_bugs(void) print_cpu_info(&boot_cpu_data); #endif check_config(); - check_fpu(); check_hlt(); check_popad(); init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); + + /* + * kernel_fpu_begin/end() in check_fpu() relies on the patched + * alternative instructions. + */ + check_fpu(); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 46d8786d655..7505f7b13e7 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -144,6 +144,8 @@ static int __init x86_xsave_setup(char *s) { setup_clear_cpu_cap(X86_FEATURE_XSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + setup_clear_cpu_cap(X86_FEATURE_AVX); + setup_clear_cpu_cap(X86_FEATURE_AVX2); return 1; } __setup("noxsave", x86_xsave_setup); @@ -257,23 +259,36 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c) } #endif -static int disable_smep __cpuinitdata; static __init int setup_disable_smep(char *arg) { - disable_smep = 1; + setup_clear_cpu_cap(X86_FEATURE_SMEP); return 1; } __setup("nosmep", setup_disable_smep); -static __cpuinit void setup_smep(struct cpuinfo_x86 *c) +static __always_inline void setup_smep(struct cpuinfo_x86 *c) { - if (cpu_has(c, X86_FEATURE_SMEP)) { - if (unlikely(disable_smep)) { - setup_clear_cpu_cap(X86_FEATURE_SMEP); - clear_in_cr4(X86_CR4_SMEP); - } else - set_in_cr4(X86_CR4_SMEP); - } + if (cpu_has(c, X86_FEATURE_SMEP)) + set_in_cr4(X86_CR4_SMEP); +} + +static __init int setup_disable_smap(char *arg) +{ + setup_clear_cpu_cap(X86_FEATURE_SMAP); + return 1; +} +__setup("nosmap", setup_disable_smap); + +static __always_inline void setup_smap(struct cpuinfo_x86 *c) +{ + unsigned long eflags; + + /* This should have been cleared long ago */ + raw_local_save_flags(eflags); + BUG_ON(eflags & X86_EFLAGS_AC); + + if (cpu_has(c, X86_FEATURE_SMAP)) + set_in_cr4(X86_CR4_SMAP); } /* @@ -474,7 +489,7 @@ void __cpuinit cpu_detect_tlb(struct cpuinfo_x86 *c) printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ - "tlb_flushall_shift is 0x%x\n", + "tlb_flushall_shift: %d\n", tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES], tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES], @@ -710,8 +725,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) c->cpu_index = 0; filter_cpuid_features(c, false); - setup_smep(c); - if (this_cpu->c_bsp_init) this_cpu->c_bsp_init(c); } @@ -796,8 +809,6 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c) c->phys_proc_id = c->initial_apicid; } - setup_smep(c); - get_model_name(c); /* Default name */ detect_nopl(c); @@ -862,6 +873,10 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) /* Disable the PN if appropriate */ squash_the_stupid_serial_number(c); + /* Set up SMEP/SMAP */ + setup_smep(c); + setup_smap(c); + /* * The vendor-specific functions might have changed features. * Now we do "generic changes." @@ -940,8 +955,7 @@ void __init identify_boot_cpu(void) #else vgetcpu_set_mode(); #endif - if (boot_cpu_data.cpuid_level >= 2) - cpu_detect_tlb(&boot_cpu_data); + cpu_detect_tlb(&boot_cpu_data); } void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c) @@ -1021,14 +1035,16 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) printk(KERN_CONT "%s ", vendor); if (c->x86_model_id[0]) - printk(KERN_CONT "%s", c->x86_model_id); + printk(KERN_CONT "%s", strim(c->x86_model_id)); else printk(KERN_CONT "%d86", c->x86); + printk(KERN_CONT " (fam: %02x, model: %02x", c->x86, c->x86_model); + if (c->x86_mask || c->cpuid_level >= 0) - printk(KERN_CONT " stepping %02x\n", c->x86_mask); + printk(KERN_CONT ", stepping: %02x)\n", c->x86_mask); else - printk(KERN_CONT "\n"); + printk(KERN_CONT ")\n"); print_cpu_msr(c); } @@ -1111,11 +1127,10 @@ void syscall_init(void) /* Flags to clear on syscall */ wrmsrl(MSR_SYSCALL_MASK, - X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|X86_EFLAGS_IOPL); + X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF| + X86_EFLAGS_IOPL|X86_EFLAGS_AC); } -unsigned long kernel_eflags; - /* * Copies of the original ist values from the tss are only accessed during * debugging, no special alignment required. @@ -1295,9 +1310,6 @@ void __cpuinit cpu_init(void) dbg_restore_debug_regs(); fpu_init(); - xsave_init(); - - raw_local_save_flags(kernel_eflags); if (is_uv_system()) uv_cpu_init(); @@ -1350,6 +1362,5 @@ void __cpuinit cpu_init(void) dbg_restore_debug_regs(); fpu_init(); - xsave_init(); } #endif diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 0a4ce2980a5..198e019a531 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -648,6 +648,10 @@ static void __cpuinit intel_detect_tlb(struct cpuinfo_x86 *c) int i, j, n; unsigned int regs[4]; unsigned char *desc = (unsigned char *)regs; + + if (c->cpuid_level < 2) + return; + /* Number of times to iterate */ n = cpuid_eax(2) & 0xFF; diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index fc4beb39357..ddc72f83933 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -78,6 +78,7 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs) } static cpumask_var_t mce_inject_cpumask; +static DEFINE_MUTEX(mce_inject_mutex); static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs) { @@ -194,7 +195,11 @@ static void raise_mce(struct mce *m) put_online_cpus(); } else #endif + { + preempt_disable(); raise_local(); + preempt_enable(); + } } /* Error injection interface */ @@ -225,7 +230,10 @@ static ssize_t mce_write(struct file *filp, const char __user *ubuf, * so do it a jiffie or two later everywhere. */ schedule_timeout(2); + + mutex_lock(&mce_inject_mutex); raise_mce(&m); + mutex_unlock(&mce_inject_mutex); return usize; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index ed44c8a6585..6a05c1d327a 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -28,6 +28,18 @@ extern int mce_ser; extern struct mce_bank *mce_banks; +#ifdef CONFIG_X86_MCE_INTEL +unsigned long mce_intel_adjust_timer(unsigned long interval); +void mce_intel_cmci_poll(void); +void mce_intel_hcpu_update(unsigned long cpu); +#else +# define mce_intel_adjust_timer mce_adjust_timer_default +static inline void mce_intel_cmci_poll(void) { } +static inline void mce_intel_hcpu_update(unsigned long cpu) { } +#endif + +void mce_timer_kick(unsigned long interval); + #ifdef CONFIG_ACPI_APEI int apei_write_mce(struct mce *m); ssize_t apei_read_mce(struct mce *m, u64 *record_id); diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 413c2ced887..13017626f9a 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -55,13 +55,6 @@ static struct severity { #define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S) #define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR) #define MCI_ADDR (MCI_STATUS_ADDRV|MCI_STATUS_MISCV) -#define MCACOD 0xffff -/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ -#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ -#define MCACOD_SCRUBMSK 0xfff0 -#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ -#define MCACOD_DATA 0x0134 /* Data Load */ -#define MCACOD_INSTR 0x0150 /* Instruction Fetch */ MCESEV( NO, "Invalid", diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 5e095f873e3..29e87d3b284 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -83,6 +83,7 @@ static int mce_dont_log_ce __read_mostly; int mce_cmci_disabled __read_mostly; int mce_ignore_ce __read_mostly; int mce_ser __read_mostly; +int mce_bios_cmci_threshold __read_mostly; struct mce_bank *mce_banks __read_mostly; @@ -103,6 +104,8 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { static DEFINE_PER_CPU(struct work_struct, mce_work); +static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); + /* * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. @@ -650,14 +653,18 @@ EXPORT_SYMBOL_GPL(machine_check_poll); * Do a quick check if any of the events requires a panic. * This decides if we keep the events around or clear them. */ -static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp) +static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, + struct pt_regs *regs) { int i, ret = 0; for (i = 0; i < banks; i++) { m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); - if (m->status & MCI_STATUS_VAL) + if (m->status & MCI_STATUS_VAL) { __set_bit(i, validp); + if (quirk_no_way_out) + quirk_no_way_out(i, m, regs); + } if (mce_severity(m, tolerant, msg) >= MCE_PANIC_SEVERITY) ret = 1; } @@ -1040,7 +1047,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) *final = m; memset(valid_banks, 0, sizeof(valid_banks)); - no_way_out = mce_no_way_out(&m, &msg, valid_banks); + no_way_out = mce_no_way_out(&m, &msg, valid_banks, regs); barrier(); @@ -1260,6 +1267,14 @@ static unsigned long check_interval = 5 * 60; /* 5 minutes */ static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ static DEFINE_PER_CPU(struct timer_list, mce_timer); +static unsigned long mce_adjust_timer_default(unsigned long interval) +{ + return interval; +} + +static unsigned long (*mce_adjust_timer)(unsigned long interval) = + mce_adjust_timer_default; + static void mce_timer_fn(unsigned long data) { struct timer_list *t = &__get_cpu_var(mce_timer); @@ -1270,6 +1285,7 @@ static void mce_timer_fn(unsigned long data) if (mce_available(__this_cpu_ptr(&cpu_info))) { machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_poll_banks)); + mce_intel_cmci_poll(); } /* @@ -1277,14 +1293,38 @@ static void mce_timer_fn(unsigned long data) * polling interval, otherwise increase the polling interval. */ iv = __this_cpu_read(mce_next_interval); - if (mce_notify_irq()) + if (mce_notify_irq()) { iv = max(iv / 2, (unsigned long) HZ/100); - else + } else { iv = min(iv * 2, round_jiffies_relative(check_interval * HZ)); + iv = mce_adjust_timer(iv); + } __this_cpu_write(mce_next_interval, iv); + /* Might have become 0 after CMCI storm subsided */ + if (iv) { + t->expires = jiffies + iv; + add_timer_on(t, smp_processor_id()); + } +} - t->expires = jiffies + iv; - add_timer_on(t, smp_processor_id()); +/* + * Ensure that the timer is firing in @interval from now. + */ +void mce_timer_kick(unsigned long interval) +{ + struct timer_list *t = &__get_cpu_var(mce_timer); + unsigned long when = jiffies + interval; + unsigned long iv = __this_cpu_read(mce_next_interval); + + if (timer_pending(t)) { + if (time_before(when, t->expires)) + mod_timer_pinned(t, when); + } else { + t->expires = round_jiffies(when); + add_timer_on(t, smp_processor_id()); + } + if (interval < iv) + __this_cpu_write(mce_next_interval, interval); } /* Must not be called in IRQ context where del_timer_sync() can deadlock */ @@ -1418,6 +1458,34 @@ static void __mcheck_cpu_init_generic(void) } } +/* + * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and + * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM + * Vol 3B Table 15-20). But this confuses both the code that determines + * whether the machine check occurred in kernel or user mode, and also + * the severity assessment code. Pretend that EIPV was set, and take the + * ip/cs values from the pt_regs that mce_gather_info() ignored earlier. + */ +static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs) +{ + if (bank != 0) + return; + if ((m->mcgstatus & (MCG_STATUS_EIPV|MCG_STATUS_RIPV)) != 0) + return; + if ((m->status & (MCI_STATUS_OVER|MCI_STATUS_UC| + MCI_STATUS_EN|MCI_STATUS_MISCV|MCI_STATUS_ADDRV| + MCI_STATUS_PCC|MCI_STATUS_S|MCI_STATUS_AR| + MCACOD)) != + (MCI_STATUS_UC|MCI_STATUS_EN| + MCI_STATUS_MISCV|MCI_STATUS_ADDRV|MCI_STATUS_S| + MCI_STATUS_AR|MCACOD_INSTR)) + return; + + m->mcgstatus |= MCG_STATUS_EIPV; + m->ip = regs->ip; + m->cs = regs->cs; +} + /* Add per CPU specific workarounds here */ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) { @@ -1515,6 +1583,9 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) */ if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0) mce_bootlog = 0; + + if (c->x86 == 6 && c->x86_model == 45) + quirk_no_way_out = quirk_sandybridge_ifu; } if (monarch_timeout < 0) monarch_timeout = 0; @@ -1548,6 +1619,7 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) switch (c->x86_vendor) { case X86_VENDOR_INTEL: mce_intel_feature_init(c); + mce_adjust_timer = mce_intel_adjust_timer; break; case X86_VENDOR_AMD: mce_amd_feature_init(c); @@ -1557,23 +1629,28 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) } } -static void __mcheck_cpu_init_timer(void) +static void mce_start_timer(unsigned int cpu, struct timer_list *t) { - struct timer_list *t = &__get_cpu_var(mce_timer); - unsigned long iv = check_interval * HZ; + unsigned long iv = mce_adjust_timer(check_interval * HZ); - setup_timer(t, mce_timer_fn, smp_processor_id()); + __this_cpu_write(mce_next_interval, iv); - if (mce_ignore_ce) + if (mce_ignore_ce || !iv) return; - __this_cpu_write(mce_next_interval, iv); - if (!iv) - return; t->expires = round_jiffies(jiffies + iv); add_timer_on(t, smp_processor_id()); } +static void __mcheck_cpu_init_timer(void) +{ + struct timer_list *t = &__get_cpu_var(mce_timer); + unsigned int cpu = smp_processor_id(); + + setup_timer(t, mce_timer_fn, cpu); + mce_start_timer(cpu, t); +} + /* Handle unconfigured int18 (should never happen) */ static void unexpected_machine_check(struct pt_regs *regs, long error_code) { @@ -1870,6 +1947,7 @@ static struct miscdevice mce_chrdev_device = { * check, or 0 to not wait * 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 */ static int __init mcheck_enable(char *str) { @@ -1889,6 +1967,8 @@ static int __init mcheck_enable(char *str) mce_ignore_ce = 1; else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) mce_bootlog = (str[0] == 'b'); + else if (!strcmp(str, "bios_cmci_threshold")) + mce_bios_cmci_threshold = 1; else if (isdigit(str[0])) { get_option(&str, &tolerant); if (*str == ',') { @@ -2129,6 +2209,11 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = { &mce_cmci_disabled }; +static struct dev_ext_attribute dev_attr_bios_cmci_threshold = { + __ATTR(bios_cmci_threshold, 0444, device_show_int, NULL), + &mce_bios_cmci_threshold +}; + static struct device_attribute *mce_device_attrs[] = { &dev_attr_tolerant.attr, &dev_attr_check_interval.attr, @@ -2137,6 +2222,7 @@ static struct device_attribute *mce_device_attrs[] = { &dev_attr_dont_log_ce.attr, &dev_attr_ignore_ce.attr, &dev_attr_cmci_disabled.attr, + &dev_attr_bios_cmci_threshold.attr, NULL }; @@ -2257,38 +2343,33 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) unsigned int cpu = (unsigned long)hcpu; struct timer_list *t = &per_cpu(mce_timer, cpu); - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: mce_device_create(cpu); if (threshold_cpu_callback) threshold_cpu_callback(action, cpu); break; case CPU_DEAD: - case CPU_DEAD_FROZEN: if (threshold_cpu_callback) threshold_cpu_callback(action, cpu); mce_device_remove(cpu); + mce_intel_hcpu_update(cpu); break; case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - del_timer_sync(t); smp_call_function_single(cpu, mce_disable_cpu, &action, 1); + del_timer_sync(t); break; case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - if (!mce_ignore_ce && check_interval) { - t->expires = round_jiffies(jiffies + - per_cpu(mce_next_interval, cpu)); - add_timer_on(t, cpu); - } smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); + mce_start_timer(cpu, t); break; - case CPU_POST_DEAD: + } + + if (action == CPU_POST_DEAD) { /* intentionally ignoring frozen here */ cmci_rediscover(cpu); - break; } + return NOTIFY_OK; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 38e49bc95ff..5f88abf07e9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -15,6 +15,8 @@ #include <asm/msr.h> #include <asm/mce.h> +#include "mce-internal.h" + /* * Support for Intel Correct Machine Check Interrupts. This allows * the CPU to raise an interrupt when a corrected machine check happened. @@ -30,7 +32,22 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); */ static DEFINE_RAW_SPINLOCK(cmci_discover_lock); -#define CMCI_THRESHOLD 1 +#define CMCI_THRESHOLD 1 +#define CMCI_POLL_INTERVAL (30 * HZ) +#define CMCI_STORM_INTERVAL (1 * HZ) +#define CMCI_STORM_THRESHOLD 15 + +static DEFINE_PER_CPU(unsigned long, cmci_time_stamp); +static DEFINE_PER_CPU(unsigned int, cmci_storm_cnt); +static DEFINE_PER_CPU(unsigned int, cmci_storm_state); + +enum { + CMCI_STORM_NONE, + CMCI_STORM_ACTIVE, + CMCI_STORM_SUBSIDED, +}; + +static atomic_t cmci_storm_on_cpus; static int cmci_supported(int *banks) { @@ -53,6 +70,93 @@ static int cmci_supported(int *banks) return !!(cap & MCG_CMCI_P); } +void mce_intel_cmci_poll(void) +{ + if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) + return; + machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); +} + +void mce_intel_hcpu_update(unsigned long cpu) +{ + if (per_cpu(cmci_storm_state, cpu) == CMCI_STORM_ACTIVE) + atomic_dec(&cmci_storm_on_cpus); + + per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE; +} + +unsigned long mce_intel_adjust_timer(unsigned long interval) +{ + int r; + + if (interval < CMCI_POLL_INTERVAL) + return interval; + + switch (__this_cpu_read(cmci_storm_state)) { + case CMCI_STORM_ACTIVE: + /* + * We switch back to interrupt mode once the poll timer has + * silenced itself. That means no events recorded and the + * timer interval is back to our poll interval. + */ + __this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED); + r = atomic_sub_return(1, &cmci_storm_on_cpus); + if (r == 0) + pr_notice("CMCI storm subsided: switching to interrupt mode\n"); + /* FALLTHROUGH */ + + case CMCI_STORM_SUBSIDED: + /* + * We wait for all cpus to go back to SUBSIDED + * state. When that happens we switch back to + * interrupt mode. + */ + if (!atomic_read(&cmci_storm_on_cpus)) { + __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE); + cmci_reenable(); + cmci_recheck(); + } + return CMCI_POLL_INTERVAL; + default: + /* + * We have shiny weather. Let the poll do whatever it + * thinks. + */ + return interval; + } +} + +static bool cmci_storm_detect(void) +{ + unsigned int cnt = __this_cpu_read(cmci_storm_cnt); + unsigned long ts = __this_cpu_read(cmci_time_stamp); + unsigned long now = jiffies; + int r; + + if (__this_cpu_read(cmci_storm_state) != CMCI_STORM_NONE) + return true; + + if (time_before_eq(now, ts + CMCI_STORM_INTERVAL)) { + cnt++; + } else { + cnt = 1; + __this_cpu_write(cmci_time_stamp, now); + } + __this_cpu_write(cmci_storm_cnt, cnt); + + if (cnt <= CMCI_STORM_THRESHOLD) + return false; + + cmci_clear(); + __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE); + r = atomic_add_return(1, &cmci_storm_on_cpus); + mce_timer_kick(CMCI_POLL_INTERVAL); + + if (r == 1) + pr_notice("CMCI storm detected: switching to poll mode\n"); + return true; +} + /* * The interrupt handler. This is called on every event. * Just call the poller directly to log any events. @@ -61,33 +165,28 @@ static int cmci_supported(int *banks) */ static void intel_threshold_interrupt(void) { + if (cmci_storm_detect()) + return; machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); mce_notify_irq(); } -static void print_update(char *type, int *hdr, int num) -{ - if (*hdr == 0) - printk(KERN_INFO "CPU %d MCA banks", smp_processor_id()); - *hdr = 1; - printk(KERN_CONT " %s:%d", type, num); -} - /* * Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks * on this CPU. Use the algorithm recommended in the SDM to discover shared * banks. */ -static void cmci_discover(int banks, int boot) +static void cmci_discover(int banks) { unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned); unsigned long flags; - int hdr = 0; int i; + int bios_wrong_thresh = 0; raw_spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { u64 val; + int bios_zero_thresh = 0; if (test_bit(i, owned)) continue; @@ -96,29 +195,52 @@ static void cmci_discover(int banks, int boot) /* Already owned by someone else? */ if (val & MCI_CTL2_CMCI_EN) { - if (test_and_clear_bit(i, owned) && !boot) - print_update("SHD", &hdr, i); + clear_bit(i, owned); __clear_bit(i, __get_cpu_var(mce_poll_banks)); continue; } - val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; - val |= MCI_CTL2_CMCI_EN | CMCI_THRESHOLD; + if (!mce_bios_cmci_threshold) { + val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; + val |= CMCI_THRESHOLD; + } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) { + /* + * If bios_cmci_threshold boot option was specified + * but the threshold is zero, we'll try to initialize + * it to 1. + */ + bios_zero_thresh = 1; + val |= CMCI_THRESHOLD; + } + + val |= MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(i), val); rdmsrl(MSR_IA32_MCx_CTL2(i), val); /* Did the enable bit stick? -- the bank supports CMCI */ if (val & MCI_CTL2_CMCI_EN) { - if (!test_and_set_bit(i, owned) && !boot) - print_update("CMCI", &hdr, i); + set_bit(i, owned); __clear_bit(i, __get_cpu_var(mce_poll_banks)); + /* + * We are able to set thresholds for some banks that + * had a threshold of 0. This means the BIOS has not + * set the thresholds properly or does not work with + * this boot option. Note down now and report later. + */ + if (mce_bios_cmci_threshold && bios_zero_thresh && + (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) + bios_wrong_thresh = 1; } else { WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); } } raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); - if (hdr) - printk(KERN_CONT "\n"); + if (mce_bios_cmci_threshold && bios_wrong_thresh) { + pr_info_once( + "bios_cmci_threshold: Some banks do not have valid thresholds set\n"); + pr_info_once( + "bios_cmci_threshold: Make sure your BIOS supports this boot option\n"); + } } /* @@ -156,7 +278,7 @@ void cmci_clear(void) continue; /* Disable CMCI */ rdmsrl(MSR_IA32_MCx_CTL2(i), val); - val &= ~(MCI_CTL2_CMCI_EN|MCI_CTL2_CMCI_THRESHOLD_MASK); + val &= ~MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(i), val); __clear_bit(i, __get_cpu_var(mce_banks_owned)); } @@ -186,7 +308,7 @@ void cmci_rediscover(int dying) continue; /* Recheck banks in case CPUs don't all have the same */ if (cmci_supported(&banks)) - cmci_discover(banks, 0); + cmci_discover(banks); } set_cpus_allowed_ptr(current, old); @@ -200,7 +322,7 @@ void cmci_reenable(void) { int banks; if (cmci_supported(&banks)) - cmci_discover(banks, 0); + cmci_discover(banks); } static void intel_init_cmci(void) @@ -211,7 +333,7 @@ static void intel_init_cmci(void) return; mce_threshold_vector = intel_threshold_interrupt; - cmci_discover(banks, 1); + cmci_discover(banks); /* * For CPU #0 this runs with still disabled APIC, but that's * ok because only the vector is set up. We still do another diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 29557aa06dd..915b876edd1 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -32,6 +32,8 @@ #include <asm/smp.h> #include <asm/alternative.h> #include <asm/timer.h> +#include <asm/desc.h> +#include <asm/ldt.h> #include "perf_event.h" @@ -1738,6 +1740,29 @@ valid_user_frame(const void __user *fp, unsigned long size) return (__range_not_ok(fp, size, TASK_SIZE) == 0); } +static unsigned long get_segment_base(unsigned int segment) +{ + struct desc_struct *desc; + int idx = segment >> 3; + + if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { + if (idx > LDT_ENTRIES) + return 0; + + if (idx > current->active_mm->context.size) + return 0; + + desc = current->active_mm->context.ldt; + } else { + if (idx > GDT_ENTRIES) + return 0; + + desc = __this_cpu_ptr(&gdt_page.gdt[0]); + } + + return get_desc_base(desc + idx); +} + #ifdef CONFIG_COMPAT #include <asm/compat.h> @@ -1746,13 +1771,17 @@ static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) { /* 32-bit process in 64-bit kernel. */ + unsigned long ss_base, cs_base; struct stack_frame_ia32 frame; const void __user *fp; if (!test_thread_flag(TIF_IA32)) return 0; - fp = compat_ptr(regs->bp); + cs_base = get_segment_base(regs->cs); + ss_base = get_segment_base(regs->ss); + + fp = compat_ptr(ss_base + regs->bp); while (entry->nr < PERF_MAX_STACK_DEPTH) { unsigned long bytes; frame.next_frame = 0; @@ -1765,8 +1794,8 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) if (!valid_user_frame(fp, sizeof(frame))) break; - perf_callchain_store(entry, frame.return_address); - fp = compat_ptr(frame.next_frame); + perf_callchain_store(entry, cs_base + frame.return_address); + fp = compat_ptr(ss_base + frame.next_frame); } return 1; } @@ -1789,6 +1818,12 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) return; } + /* + * We don't know what to do with VM86 stacks.. ignore them for now. + */ + if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM)) + return; + fp = (void __user *)regs->bp; perf_callchain_store(entry, regs->ip); @@ -1816,16 +1851,50 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) } } -unsigned long perf_instruction_pointer(struct pt_regs *regs) +/* + * Deal with code segment offsets for the various execution modes: + * + * VM86 - the good olde 16 bit days, where the linear address is + * 20 bits and we use regs->ip + 0x10 * regs->cs. + * + * IA32 - Where we need to look at GDT/LDT segment descriptor tables + * to figure out what the 32bit base address is. + * + * X32 - has TIF_X32 set, but is running in x86_64 + * + * X86_64 - CS,DS,SS,ES are all zero based. + */ +static unsigned long code_segment_base(struct pt_regs *regs) { - unsigned long ip; + /* + * If we are in VM86 mode, add the segment offset to convert to a + * linear address. + */ + if (regs->flags & X86_VM_MASK) + return 0x10 * regs->cs; + + /* + * For IA32 we look at the GDT/LDT segment base to convert the + * effective IP to a linear address. + */ +#ifdef CONFIG_X86_32 + if (user_mode(regs) && regs->cs != __USER_CS) + return get_segment_base(regs->cs); +#else + if (test_thread_flag(TIF_IA32)) { + if (user_mode(regs) && regs->cs != __USER32_CS) + return get_segment_base(regs->cs); + } +#endif + return 0; +} +unsigned long perf_instruction_pointer(struct pt_regs *regs) +{ if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) - ip = perf_guest_cbs->get_guest_ip(); - else - ip = instruction_pointer(regs); + return perf_guest_cbs->get_guest_ip(); - return ip; + return regs->ip + code_segment_base(regs); } unsigned long perf_misc_flags(struct pt_regs *regs) @@ -1838,7 +1907,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs) else misc |= PERF_RECORD_MISC_GUEST_KERNEL; } else { - if (!kernel_ip(regs->ip)) + if (user_mode(regs)) misc |= PERF_RECORD_MISC_USER; else misc |= PERF_RECORD_MISC_KERNEL; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 821d53b696d..8b6defe7eef 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -516,6 +516,26 @@ static inline bool kernel_ip(unsigned long ip) #endif } +/* + * Not all PMUs provide the right context information to place the reported IP + * into full context. Specifically segment registers are typically not + * supplied. + * + * Assuming the address is a linear address (it is for IBS), we fake the CS and + * vm86 mode using the known zero-based code segment and 'fix up' the registers + * to reflect this. + * + * Intel PEBS/LBR appear to typically provide the effective address, nothing + * much we can do about that but pray and treat it like a linear address. + */ +static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip) +{ + regs->cs = kernel_ip(ip) ? __KERNEL_CS : __USER_CS; + if (regs->flags & X86_VM_MASK) + regs->flags ^= (PERF_EFLAGS_VM | X86_VM_MASK); + regs->ip = ip; +} + #ifdef CONFIG_CPU_SUP_AMD int amd_pmu_init(void); @@ -566,6 +586,8 @@ extern struct event_constraint intel_westmere_pebs_event_constraints[]; extern struct event_constraint intel_snb_pebs_event_constraints[]; +extern struct event_constraint intel_ivb_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_enable(struct perf_event *event); diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index da9bcdcd985..eebd5ffe1bb 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -13,6 +13,8 @@ #include <asm/apic.h> +#include "perf_event.h" + static u32 ibs_caps; #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) @@ -207,6 +209,15 @@ static int perf_ibs_precise_event(struct perf_event *event, u64 *config) return -EOPNOTSUPP; } +static const struct perf_event_attr ibs_notsupp = { + .exclude_user = 1, + .exclude_kernel = 1, + .exclude_hv = 1, + .exclude_idle = 1, + .exclude_host = 1, + .exclude_guest = 1, +}; + static int perf_ibs_init(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -227,6 +238,9 @@ static int perf_ibs_init(struct perf_event *event) if (event->pmu != &perf_ibs->pmu) return -ENOENT; + if (perf_flags(&event->attr) & perf_flags(&ibs_notsupp)) + return -EINVAL; + if (config & ~perf_ibs->config_mask) return -EINVAL; @@ -536,7 +550,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) if (check_rip && (ibs_data.regs[2] & IBS_RIP_INVALID)) { regs.flags &= ~PERF_EFLAGS_EXACT; } else { - instruction_pointer_set(®s, ibs_data.regs[1]); + set_linear_ip(®s, ibs_data.regs[1]); regs.flags |= PERF_EFLAGS_EXACT; } diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 382366977d4..6bca492b854 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1522,8 +1522,16 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr) arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL; arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask; arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask; + /* + * If PMU counter has PEBS enabled it is not enough to disable counter + * on a guest entry since PEBS memory write can overshoot guest entry + * and corrupt guest memory. Disabling PEBS solves the problem. + */ + arr[1].msr = MSR_IA32_PEBS_ENABLE; + arr[1].host = cpuc->pebs_enabled; + arr[1].guest = 0; - *nr = 1; + *nr = 2; return arr; } @@ -2000,6 +2008,7 @@ __init int intel_pmu_init(void) break; case 28: /* Atom */ + case 54: /* Cedariew */ memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2039,7 +2048,6 @@ __init int intel_pmu_init(void) case 42: /* SandyBridge */ case 45: /* SandyBridge, "Romely-EP" */ x86_add_quirk(intel_sandybridge_quirk); - case 58: /* IvyBridge */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, @@ -2064,6 +2072,29 @@ __init int intel_pmu_init(void) pr_cont("SandyBridge events, "); break; + case 58: /* IvyBridge */ + memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_snb(); + + x86_pmu.event_constraints = intel_snb_event_constraints; + x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; + x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.extra_regs = intel_snb_extra_regs; + /* all extra regs are per-cpu when HT is on */ + x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.er_flags |= ERF_NO_HT_SHARING; + + /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */ + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = + X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); + + pr_cont("IvyBridge events, "); + break; + default: switch (x86_pmu.version) { diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 629ae0b7ad9..826054a4f2e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -407,6 +407,20 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_ivb_pebs_event_constraints[] = { + INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ + INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + EVENT_CONSTRAINT_END +}; + struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; @@ -499,7 +513,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) * We sampled a branch insn, rewind using the LBR stack */ if (ip == to) { - regs->ip = from; + set_linear_ip(regs, from); return 1; } @@ -529,7 +543,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) } while (to < ip); if (to == ip) { - regs->ip = old_to; + set_linear_ip(regs, old_to); return 1; } @@ -569,7 +583,8 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * A possible PERF_SAMPLE_REGS will have to transfer all regs. */ regs = *iregs; - regs.ip = pebs->ip; + regs.flags = pebs->flags; + set_linear_ip(®s, pebs->ip); regs.bp = pebs->bp; regs.sp = pebs->sp; diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 520b4265fcd..da02e9cc375 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -686,7 +686,8 @@ void intel_pmu_lbr_init_atom(void) * to have an operational LBR which can freeze * on PMU interrupt */ - if (boot_cpu_data.x86_mask < 10) { + if (boot_cpu_data.x86_model == 28 + && boot_cpu_data.x86_mask < 10) { pr_cont("LBR disabled due to erratum"); return; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 7563fda9f03..99d96a4978b 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -661,6 +661,11 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box) } } +static struct uncore_event_desc snb_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + { /* end: all zeroes */ }, +}; + static struct attribute *snb_uncore_formats_attr[] = { &format_attr_event.attr, &format_attr_umask.attr, @@ -704,6 +709,7 @@ static struct intel_uncore_type snb_uncore_cbox = { .constraints = snb_uncore_cbox_constraints, .ops = &snb_uncore_msr_ops, .format_group = &snb_uncore_format_group, + .event_descs = snb_uncore_events, }; static struct intel_uncore_type *snb_msr_uncores[] = { @@ -796,7 +802,6 @@ static struct intel_uncore_type *nhm_msr_uncores[] = { DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5"); DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7"); -DEFINE_UNCORE_FORMAT_ATTR(mm_cfg, mm_cfg, "config:63"); DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63"); DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63"); @@ -902,16 +907,21 @@ static struct attribute_group nhmex_uncore_cbox_format_group = { .attrs = nhmex_uncore_cbox_formats_attr, }; +/* msr offset for each instance of cbox */ +static unsigned nhmex_cbox_msr_offsets[] = { + 0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0, +}; + static struct intel_uncore_type nhmex_uncore_cbox = { .name = "cbox", .num_counters = 6, - .num_boxes = 8, + .num_boxes = 10, .perf_ctr_bits = 48, .event_ctl = NHMEX_C0_MSR_PMON_EV_SEL0, .perf_ctr = NHMEX_C0_MSR_PMON_CTR0, .event_mask = NHMEX_PMON_RAW_EVENT_MASK, .box_ctl = NHMEX_C0_MSR_PMON_GLOBAL_CTL, - .msr_offset = NHMEX_C_MSR_OFFSET, + .msr_offsets = nhmex_cbox_msr_offsets, .pair_ctr_ctl = 1, .ops = &nhmex_uncore_ops, .format_group = &nhmex_uncore_cbox_format_group @@ -1032,24 +1042,22 @@ static struct intel_uncore_type nhmex_uncore_bbox = { static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) { - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - if (event->attr.config & NHMEX_S_PMON_MM_CFG_EN) { - reg1->config = event->attr.config1; - reg2->config = event->attr.config2; - } else { - reg1->config = ~0ULL; - reg2->config = ~0ULL; - } + /* only TO_R_PROG_EV event uses the match/mask register */ + if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) != + NHMEX_S_EVENT_TO_R_PROG_EV) + return 0; if (box->pmu->pmu_idx == 0) reg1->reg = NHMEX_S0_MSR_MM_CFG; else reg1->reg = NHMEX_S1_MSR_MM_CFG; - reg1->idx = 0; - + reg1->config = event->attr.config1; + reg2->config = event->attr.config2; return 0; } @@ -1059,8 +1067,8 @@ static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct per struct hw_perf_event_extra *reg1 = &hwc->extra_reg; struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - wrmsrl(reg1->reg, 0); - if (reg1->config != ~0ULL || reg2->config != ~0ULL) { + if (reg1->idx != EXTRA_REG_NONE) { + wrmsrl(reg1->reg, 0); wrmsrl(reg1->reg + 1, reg1->config); wrmsrl(reg1->reg + 2, reg2->config); wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN); @@ -1074,7 +1082,6 @@ static struct attribute *nhmex_uncore_sbox_formats_attr[] = { &format_attr_edge.attr, &format_attr_inv.attr, &format_attr_thresh8.attr, - &format_attr_mm_cfg.attr, &format_attr_match.attr, &format_attr_mask.attr, NULL, @@ -1142,6 +1149,9 @@ static struct extra_reg nhmex_uncore_mbox_extra_regs[] = { EVENT_EXTRA_END }; +/* Nehalem-EX or Westmere-EX ? */ +bool uncore_nhmex; + static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config) { struct intel_uncore_extra_reg *er; @@ -1171,18 +1181,29 @@ static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 return false; /* mask of the shared fields */ - mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK; + if (uncore_nhmex) + mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK; + else + mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK; er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; raw_spin_lock_irqsave(&er->lock, flags); /* add mask of the non-shared field if it's in use */ - if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) - mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) { + if (uncore_nhmex) + mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + } if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) { atomic_add(1 << (idx * 8), &er->ref); - mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK | - NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + if (uncore_nhmex) + mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK | + NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK | + WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); er->config &= ~mask; er->config |= (config & mask); ret = true; @@ -1216,7 +1237,10 @@ u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) /* get the non-shared control bits and shift them */ idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + if (uncore_nhmex) + config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); if (new_idx > orig_idx) { idx = new_idx - orig_idx; config <<= 3 * idx; @@ -1226,6 +1250,10 @@ u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) } /* add the shared control bits back */ + if (uncore_nhmex) + config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; + else + config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; if (modify) { /* adjust the main event selector */ @@ -1264,7 +1292,8 @@ again: } /* for the match/mask registers */ - if ((uncore_box_is_fake(box) || !reg2->alloc) && + if (reg2->idx != EXTRA_REG_NONE && + (uncore_box_is_fake(box) || !reg2->alloc) && !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config)) goto fail; @@ -1278,7 +1307,8 @@ again: if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) nhmex_mbox_alter_er(event, idx[0], true); reg1->alloc |= alloc; - reg2->alloc = 1; + if (reg2->idx != EXTRA_REG_NONE) + reg2->alloc = 1; } return NULL; fail: @@ -1342,9 +1372,6 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event struct extra_reg *er; unsigned msr; int reg_idx = 0; - - if (WARN_ON_ONCE(reg1->idx != -1)) - return -EINVAL; /* * The mbox events may require 2 extra MSRs at the most. But only * the lower 32 bits in these MSRs are significant, so we can use @@ -1355,11 +1382,6 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event continue; if (event->attr.config1 & ~er->valid_mask) return -EINVAL; - if (er->idx == __BITS_VALUE(reg1->idx, 0, 8) || - er->idx == __BITS_VALUE(reg1->idx, 1, 8)) - continue; - if (WARN_ON_ONCE(reg_idx >= 2)) - return -EINVAL; msr = er->msr + type->msr_offset * box->pmu->pmu_idx; if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff)) @@ -1368,6 +1390,8 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event /* always use the 32~63 bits to pass the PLD config */ if (er->idx == EXTRA_REG_NHMEX_M_PLD) reg_idx = 1; + else if (WARN_ON_ONCE(reg_idx > 0)) + return -EINVAL; reg1->idx &= ~(0xff << (reg_idx * 8)); reg1->reg &= ~(0xffff << (reg_idx * 16)); @@ -1376,17 +1400,21 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event reg1->config = event->attr.config1; reg_idx++; } - /* use config2 to pass the filter config */ - reg2->idx = EXTRA_REG_NHMEX_M_FILTER; - if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN) - reg2->config = event->attr.config2; - else - reg2->config = ~0ULL; - if (box->pmu->pmu_idx == 0) - reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG; - else - reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG; - + /* + * The mbox only provides ability to perform address matching + * for the PLD events. + */ + if (reg_idx == 2) { + reg2->idx = EXTRA_REG_NHMEX_M_FILTER; + if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN) + reg2->config = event->attr.config2; + else + reg2->config = ~0ULL; + if (box->pmu->pmu_idx == 0) + reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG; + else + reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG; + } return 0; } @@ -1422,34 +1450,36 @@ static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct per wrmsrl(__BITS_VALUE(reg1->reg, 1, 16), nhmex_mbox_shared_reg_config(box, idx)); - wrmsrl(reg2->reg, 0); - if (reg2->config != ~0ULL) { - wrmsrl(reg2->reg + 1, - reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK); - wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK & - (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT)); - wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN); + if (reg2->idx != EXTRA_REG_NONE) { + wrmsrl(reg2->reg, 0); + if (reg2->config != ~0ULL) { + wrmsrl(reg2->reg + 1, + reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK); + wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK & + (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT)); + wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN); + } } wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); } -DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3"); -DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5"); -DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6"); -DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7"); -DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13"); -DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21"); -DEFINE_UNCORE_FORMAT_ATTR(filter_cfg, filter_cfg, "config2:63"); -DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33"); -DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61"); -DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3"); +DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5"); +DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6"); +DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7"); +DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13"); +DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21"); +DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en, filter_cfg_en, "config2:63"); +DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33"); +DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61"); +DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63"); static struct attribute *nhmex_uncore_mbox_formats_attr[] = { &format_attr_count_mode.attr, @@ -1458,7 +1488,7 @@ static struct attribute *nhmex_uncore_mbox_formats_attr[] = { &format_attr_flag_mode.attr, &format_attr_inc_sel.attr, &format_attr_set_flag_sel.attr, - &format_attr_filter_cfg.attr, + &format_attr_filter_cfg_en.attr, &format_attr_filter_match.attr, &format_attr_filter_mask.attr, &format_attr_dsp.attr, @@ -1482,6 +1512,12 @@ static struct uncore_event_desc nhmex_uncore_mbox_events[] = { { /* end: all zeroes */ }, }; +static struct uncore_event_desc wsmex_uncore_mbox_events[] = { + INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"), + INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"), + { /* end: all zeroes */ }, +}; + static struct intel_uncore_ops nhmex_uncore_mbox_ops = { NHMEX_UNCORE_OPS_COMMON_INIT(), .enable_event = nhmex_mbox_msr_enable_event, @@ -1513,7 +1549,7 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) struct hw_perf_event_extra *reg1 = &hwc->extra_reg; int port; - /* adjust the main event selector */ + /* adjust the main event selector and extra register index */ if (reg1->idx % 2) { reg1->idx--; hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; @@ -1522,29 +1558,17 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; } - /* adjust address or config of extra register */ + /* adjust extra register config */ port = reg1->idx / 6 + box->pmu->pmu_idx * 4; switch (reg1->idx % 6) { - case 0: - reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port); - break; - case 1: - reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port); - break; case 2: - /* the 8~15 bits to the 0~7 bits */ + /* shift the 8~15 bits to the 0~7 bits */ reg1->config >>= 8; break; case 3: - /* the 0~7 bits to the 8~15 bits */ + /* shift the 0~7 bits to the 8~15 bits */ reg1->config <<= 8; break; - case 4: - reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port); - break; - case 5: - reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port); - break; }; } @@ -1671,7 +1695,7 @@ static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - int port, idx; + int idx; idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >> NHMEX_R_PMON_CTL_EV_SEL_SHIFT; @@ -1681,27 +1705,11 @@ static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event reg1->idx = idx; reg1->config = event->attr.config1; - port = idx / 6 + box->pmu->pmu_idx * 4; - idx %= 6; - switch (idx) { - case 0: - reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port); - break; - case 1: - reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port); - break; - case 2: - case 3: - reg1->reg = NHMEX_R_MSR_PORTN_QLX_CFG(port); - break; + switch (idx % 6) { case 4: case 5: - if (idx == 4) - reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port); - else - reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port); - reg2->config = event->attr.config2; hwc->config |= event->attr.config & (~0ULL << 32); + reg2->config = event->attr.config2; break; }; return 0; @@ -1727,28 +1735,34 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &hwc->extra_reg; struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - int idx, er_idx; + int idx, port; - idx = reg1->idx % 6; - er_idx = idx; - if (er_idx > 2) - er_idx--; - er_idx += (reg1->idx / 6) * 5; + idx = reg1->idx; + port = idx / 6 + box->pmu->pmu_idx * 4; - switch (idx) { + switch (idx % 6) { case 0: + wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config); + break; case 1: - wrmsrl(reg1->reg, reg1->config); + wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config); break; case 2: case 3: - wrmsrl(reg1->reg, nhmex_rbox_shared_reg_config(box, er_idx)); + wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port), + nhmex_rbox_shared_reg_config(box, 2 + (idx / 6) * 5)); break; case 4: + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port), + hwc->config >> 32); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config); + break; case 5: - wrmsrl(reg1->reg, reg1->config); - wrmsrl(reg1->reg + 1, hwc->config >> 32); - wrmsrl(reg1->reg + 2, reg2->config); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port), + hwc->config >> 32); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config); break; }; @@ -1756,8 +1770,8 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per (hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK)); } -DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config:32-63"); -DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config1:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63"); DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63"); DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15"); DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31"); @@ -1936,7 +1950,7 @@ struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cp static struct intel_uncore_box * uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) { - static struct intel_uncore_box *box; + struct intel_uncore_box *box; box = *per_cpu_ptr(pmu->box, cpu); if (box) @@ -2303,6 +2317,7 @@ int uncore_pmu_event_init(struct perf_event *event) event->hw.idx = -1; event->hw.last_tag = ~0ULL; event->hw.extra_reg.idx = EXTRA_REG_NONE; + event->hw.branch_reg.idx = EXTRA_REG_NONE; if (event->attr.config == UNCORE_FIXED_EVENT) { /* no fixed counter */ @@ -2332,6 +2347,27 @@ int uncore_pmu_event_init(struct perf_event *event) return ret; } +static ssize_t uncore_get_attr_cpumask(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &uncore_cpu_mask); + + buf[n++] = '\n'; + buf[n] = '\0'; + return n; +} + +static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL); + +static struct attribute *uncore_pmu_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group uncore_pmu_attr_group = { + .attrs = uncore_pmu_attrs, +}; + static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu) { int ret; @@ -2369,11 +2405,11 @@ static void __init uncore_type_exit(struct intel_uncore_type *type) free_percpu(type->pmus[i].box); kfree(type->pmus); type->pmus = NULL; - kfree(type->attr_groups[1]); - type->attr_groups[1] = NULL; + kfree(type->events_group); + type->events_group = NULL; } -static void uncore_types_exit(struct intel_uncore_type **types) +static void __init uncore_types_exit(struct intel_uncore_type **types) { int i; for (i = 0; types[i]; i++) @@ -2422,9 +2458,10 @@ static int __init uncore_type_init(struct intel_uncore_type *type) for (j = 0; j < i; j++) attrs[j] = &type->event_descs[j].attr.attr; - type->attr_groups[1] = events_group; + type->events_group = events_group; } + type->pmu_group = &uncore_pmu_attr_group; type->pmus = pmus; return 0; fail: @@ -2814,7 +2851,13 @@ static int __init uncore_cpu_init(void) snbep_uncore_cbox.num_boxes = max_cores; msr_uncores = snbep_msr_uncores; break; - case 46: + case 46: /* Nehalem-EX */ + uncore_nhmex = true; + case 47: /* Westmere-EX aka. Xeon E7 */ + if (!uncore_nhmex) + nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events; + if (nhmex_uncore_cbox.num_boxes > max_cores) + nhmex_uncore_cbox.num_boxes = max_cores; msr_uncores = nhmex_msr_uncores; break; default: diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index f3851892e07..e68a4550e95 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -5,7 +5,7 @@ #include "perf_event.h" #define UNCORE_PMU_NAME_LEN 32 -#define UNCORE_PMU_HRTIMER_INTERVAL (60 * NSEC_PER_SEC) +#define UNCORE_PMU_HRTIMER_INTERVAL (60LL * NSEC_PER_SEC) #define UNCORE_FIXED_EVENT 0xff #define UNCORE_PMC_IDX_MAX_GENERIC 8 @@ -230,6 +230,7 @@ #define NHMEX_S1_MSR_MASK 0xe5a #define NHMEX_S_PMON_MM_CFG_EN (0x1ULL << 63) +#define NHMEX_S_EVENT_TO_R_PROG_EV 0 /* NHM-EX Mbox */ #define NHMEX_M0_MSR_GLOBAL_CTL 0xca0 @@ -275,18 +276,12 @@ NHMEX_M_PMON_CTL_INC_SEL_MASK | \ NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK) - -#define NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK 0x1f -#define NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK (0x7 << 5) -#define NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK (0x7 << 8) -#define NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR (1 << 23) -#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK \ - (NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK | \ - NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK | \ - NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK | \ - NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR) +#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 11) - 1) | (1 << 23)) #define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7 << (11 + 3 * (n))) +#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 12) - 1) | (1 << 24)) +#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7 << (12 + 3 * (n))) + /* * use the 9~13 bits to select event If the 7th bit is not set, * otherwise use the 19~21 bits to select event. @@ -368,15 +363,18 @@ struct intel_uncore_type { unsigned num_shared_regs:8; unsigned single_fixed:1; unsigned pair_ctr_ctl:1; + unsigned *msr_offsets; struct event_constraint unconstrainted; struct event_constraint *constraints; struct intel_uncore_pmu *pmus; struct intel_uncore_ops *ops; struct uncore_event_desc *event_descs; - const struct attribute_group *attr_groups[3]; + const struct attribute_group *attr_groups[4]; }; -#define format_group attr_groups[0] +#define pmu_group attr_groups[0] +#define format_group attr_groups[1] +#define events_group attr_groups[2] struct intel_uncore_ops { void (*init_box)(struct intel_uncore_box *); @@ -485,29 +483,31 @@ unsigned uncore_pci_perf_ctr(struct intel_uncore_box *box, int idx) return idx * 8 + box->pmu->type->perf_ctr; } -static inline -unsigned uncore_msr_box_ctl(struct intel_uncore_box *box) +static inline unsigned uncore_msr_box_offset(struct intel_uncore_box *box) +{ + struct intel_uncore_pmu *pmu = box->pmu; + return pmu->type->msr_offsets ? + pmu->type->msr_offsets[pmu->pmu_idx] : + pmu->type->msr_offset * pmu->pmu_idx; +} + +static inline unsigned uncore_msr_box_ctl(struct intel_uncore_box *box) { if (!box->pmu->type->box_ctl) return 0; - return box->pmu->type->box_ctl + - box->pmu->type->msr_offset * box->pmu->pmu_idx; + return box->pmu->type->box_ctl + uncore_msr_box_offset(box); } -static inline -unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box) +static inline unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box) { if (!box->pmu->type->fixed_ctl) return 0; - return box->pmu->type->fixed_ctl + - box->pmu->type->msr_offset * box->pmu->pmu_idx; + return box->pmu->type->fixed_ctl + uncore_msr_box_offset(box); } -static inline -unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box) +static inline unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box) { - return box->pmu->type->fixed_ctr + - box->pmu->type->msr_offset * box->pmu->pmu_idx; + return box->pmu->type->fixed_ctr + uncore_msr_box_offset(box); } static inline @@ -515,7 +515,7 @@ unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx) { return box->pmu->type->event_ctl + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + - box->pmu->type->msr_offset * box->pmu->pmu_idx; + uncore_msr_box_offset(box); } static inline @@ -523,7 +523,7 @@ unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx) { return box->pmu->type->perf_ctr + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + - box->pmu->type->msr_offset * box->pmu->pmu_idx; + uncore_msr_box_offset(box); } static inline diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 8022c668148..fbd89556229 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -140,10 +140,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { - if (*pos == 0) /* just in case, cpu 0 is not the first */ - *pos = cpumask_first(cpu_online_mask); - else - *pos = cpumask_next(*pos - 1, cpu_online_mask); + *pos = cpumask_next(*pos - 1, cpu_online_mask); if ((*pos) < nr_cpu_ids) return &cpu_data(*pos); return NULL; diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 39472dd2323..60c78917190 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -199,12 +199,14 @@ static int __init cpuid_init(void) goto out_chrdev; } cpuid_class->devnode = cpuid_devnode; + get_online_cpus(); for_each_online_cpu(i) { err = cpuid_device_create(i); if (err != 0) goto out_class; } register_hotcpu_notifier(&cpuid_class_cpu_notifier); + put_online_cpus(); err = 0; goto out; @@ -214,6 +216,7 @@ out_class: for_each_online_cpu(i) { cpuid_device_destroy(i); } + put_online_cpus(); class_destroy(cpuid_class); out_chrdev: __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid"); @@ -225,11 +228,13 @@ static void __exit cpuid_exit(void) { int cpu = 0; + get_online_cpus(); for_each_online_cpu(cpu) cpuid_device_destroy(cpu); class_destroy(cpuid_class); __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid"); unregister_hotcpu_notifier(&cpuid_class_cpu_notifier); + put_online_cpus(); } module_init(cpuid_init); diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 3ae2ced4a87..b1581527a23 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -342,6 +342,47 @@ const struct irq_domain_ops ioapic_irq_domain_ops = { .xlate = ioapic_xlate, }; +static void dt_add_ioapic_domain(unsigned int ioapic_num, + struct device_node *np) +{ + struct irq_domain *id; + struct mp_ioapic_gsi *gsi_cfg; + int ret; + int num; + + gsi_cfg = mp_ioapic_gsi_routing(ioapic_num); + num = gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1; + + id = irq_domain_add_linear(np, num, &ioapic_irq_domain_ops, + (void *)ioapic_num); + BUG_ON(!id); + if (gsi_cfg->gsi_base == 0) { + /* + * The first NR_IRQS_LEGACY irq descs are allocated in + * early_irq_init() and need just a mapping. The + * remaining irqs need both. All of them are preallocated + * and assigned so we can keep the 1:1 mapping which the ioapic + * is having. + */ + ret = irq_domain_associate_many(id, 0, 0, NR_IRQS_LEGACY); + if (ret) + pr_err("Error mapping legacy IRQs: %d\n", ret); + + if (num > NR_IRQS_LEGACY) { + ret = irq_create_strict_mappings(id, NR_IRQS_LEGACY, + NR_IRQS_LEGACY, num - NR_IRQS_LEGACY); + if (ret) + pr_err("Error creating mapping for the " + "remaining IRQs: %d\n", ret); + } + irq_set_default_host(id); + } else { + ret = irq_create_strict_mappings(id, gsi_cfg->gsi_base, 0, num); + if (ret) + pr_err("Error creating IRQ mapping: %d\n", ret); + } +} + static void __init ioapic_add_ofnode(struct device_node *np) { struct resource r; @@ -356,15 +397,7 @@ static void __init ioapic_add_ofnode(struct device_node *np) for (i = 0; i < nr_ioapics; i++) { if (r.start == mpc_ioapic_addr(i)) { - struct irq_domain *id; - struct mp_ioapic_gsi *gsi_cfg; - - gsi_cfg = mp_ioapic_gsi_routing(i); - - id = irq_domain_add_legacy(np, 32, gsi_cfg->gsi_base, 0, - &ioapic_irq_domain_ops, - (void*)i); - BUG_ON(!id); + dt_add_ioapic_domain(i, np); return; } } diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 623f2883747..0750e3ba87c 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -57,6 +57,7 @@ #include <asm/cpufeature.h> #include <asm/alternative-asm.h> #include <asm/asm.h> +#include <asm/smap.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> @@ -407,7 +408,9 @@ sysenter_past_esp: */ cmpl $__PAGE_OFFSET-3,%ebp jae syscall_fault + ASM_STAC 1: movl (%ebp),%ebp + ASM_CLAC movl %ebp,PT_EBP(%esp) _ASM_EXTABLE(1b,syscall_fault) @@ -488,6 +491,7 @@ ENDPROC(ia32_sysenter_target) # system call handler stub ENTRY(system_call) RING0_INT_FRAME # can't unwind into user space anyway + ASM_CLAC pushl_cfi %eax # save orig_eax SAVE_ALL GET_THREAD_INFO(%ebp) @@ -670,6 +674,7 @@ END(syscall_exit_work) RING0_INT_FRAME # can't unwind into user space anyway syscall_fault: + ASM_CLAC GET_THREAD_INFO(%ebp) movl $-EFAULT,PT_EAX(%esp) jmp resume_userspace @@ -825,6 +830,7 @@ END(interrupt) */ .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: + ASM_CLAC addl $-0x80,(%esp) /* Adjust vector into the [-256,-1] range */ SAVE_ALL TRACE_IRQS_OFF @@ -841,6 +847,7 @@ ENDPROC(common_interrupt) #define BUILD_INTERRUPT3(name, nr, fn) \ ENTRY(name) \ RING0_INT_FRAME; \ + ASM_CLAC; \ pushl_cfi $~(nr); \ SAVE_ALL; \ TRACE_IRQS_OFF \ @@ -857,6 +864,7 @@ ENDPROC(name) ENTRY(coprocessor_error) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_coprocessor_error jmp error_code @@ -865,6 +873,7 @@ END(coprocessor_error) ENTRY(simd_coprocessor_error) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 #ifdef CONFIG_X86_INVD_BUG /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ @@ -886,6 +895,7 @@ END(simd_coprocessor_error) ENTRY(device_not_available) RING0_INT_FRAME + ASM_CLAC pushl_cfi $-1 # mark this as an int pushl_cfi $do_device_not_available jmp error_code @@ -906,6 +916,7 @@ END(native_irq_enable_sysexit) ENTRY(overflow) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_overflow jmp error_code @@ -914,6 +925,7 @@ END(overflow) ENTRY(bounds) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_bounds jmp error_code @@ -922,6 +934,7 @@ END(bounds) ENTRY(invalid_op) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_invalid_op jmp error_code @@ -930,6 +943,7 @@ END(invalid_op) ENTRY(coprocessor_segment_overrun) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_coprocessor_segment_overrun jmp error_code @@ -938,6 +952,7 @@ END(coprocessor_segment_overrun) ENTRY(invalid_TSS) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_invalid_TSS jmp error_code CFI_ENDPROC @@ -945,6 +960,7 @@ END(invalid_TSS) ENTRY(segment_not_present) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_segment_not_present jmp error_code CFI_ENDPROC @@ -952,6 +968,7 @@ END(segment_not_present) ENTRY(stack_segment) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_stack_segment jmp error_code CFI_ENDPROC @@ -959,6 +976,7 @@ END(stack_segment) ENTRY(alignment_check) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_alignment_check jmp error_code CFI_ENDPROC @@ -966,6 +984,7 @@ END(alignment_check) ENTRY(divide_error) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 # no error code pushl_cfi $do_divide_error jmp error_code @@ -975,6 +994,7 @@ END(divide_error) #ifdef CONFIG_X86_MCE ENTRY(machine_check) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi machine_check_vector jmp error_code @@ -984,6 +1004,7 @@ END(machine_check) ENTRY(spurious_interrupt_bug) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_spurious_interrupt_bug jmp error_code @@ -1109,17 +1130,21 @@ ENTRY(ftrace_caller) pushl %eax pushl %ecx pushl %edx - movl 0xc(%esp), %eax + pushl $0 /* Pass NULL as regs pointer */ + movl 4*4(%esp), %eax movl 0x4(%ebp), %edx + leal function_trace_op, %ecx subl $MCOUNT_INSN_SIZE, %eax .globl ftrace_call ftrace_call: call ftrace_stub + addl $4,%esp /* skip NULL pointer */ popl %edx popl %ecx popl %eax +ftrace_ret: #ifdef CONFIG_FUNCTION_GRAPH_TRACER .globl ftrace_graph_call ftrace_graph_call: @@ -1131,6 +1156,71 @@ ftrace_stub: ret END(ftrace_caller) +ENTRY(ftrace_regs_caller) + pushf /* push flags before compare (in cs location) */ + cmpl $0, function_trace_stop + jne ftrace_restore_flags + + /* + * i386 does not save SS and ESP when coming from kernel. + * Instead, to get sp, ®s->sp is used (see ptrace.h). + * Unfortunately, that means eflags must be at the same location + * as the current return ip is. We move the return ip into the + * ip location, and move flags into the return ip location. + */ + pushl 4(%esp) /* save return ip into ip slot */ + + pushl $0 /* Load 0 into orig_ax */ + pushl %gs + pushl %fs + pushl %es + pushl %ds + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + + movl 13*4(%esp), %eax /* Get the saved flags */ + movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */ + /* clobbering return ip */ + movl $__KERNEL_CS,13*4(%esp) + + movl 12*4(%esp), %eax /* Load ip (1st parameter) */ + subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ + movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ + leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ + pushl %esp /* Save pt_regs as 4th parameter */ + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + addl $4, %esp /* Skip pt_regs */ + movl 14*4(%esp), %eax /* Move flags back into cs */ + movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */ + movl 12*4(%esp), %eax /* Get return ip from regs->ip */ + movl %eax, 14*4(%esp) /* Put return ip back for ret */ + + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax + popl %ds + popl %es + popl %fs + popl %gs + addl $8, %esp /* Skip orig_ax and ip */ + popf /* Pop flags at end (no addl to corrupt flags) */ + jmp ftrace_ret + +ftrace_restore_flags: + popf + jmp ftrace_stub #else /* ! CONFIG_DYNAMIC_FTRACE */ ENTRY(mcount) @@ -1171,9 +1261,6 @@ END(mcount) #ifdef CONFIG_FUNCTION_GRAPH_TRACER ENTRY(ftrace_graph_caller) - cmpl $0, function_trace_stop - jne ftrace_stub - pushl %eax pushl %ecx pushl %edx @@ -1207,6 +1294,7 @@ return_to_handler: ENTRY(page_fault) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_page_fault ALIGN error_code: @@ -1279,6 +1367,7 @@ END(page_fault) ENTRY(debug) RING0_INT_FRAME + ASM_CLAC cmpl $ia32_sysenter_target,(%esp) jne debug_stack_correct FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn @@ -1303,6 +1392,7 @@ END(debug) */ ENTRY(nmi) RING0_INT_FRAME + ASM_CLAC pushl_cfi %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax @@ -1373,6 +1463,7 @@ END(nmi) ENTRY(int3) RING0_INT_FRAME + ASM_CLAC pushl_cfi $-1 # mark this as an int SAVE_ALL TRACE_IRQS_OFF @@ -1393,6 +1484,7 @@ END(general_protection) #ifdef CONFIG_KVM_GUEST ENTRY(async_page_fault) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_async_page_fault jmp error_code CFI_ENDPROC diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 69babd8c834..44531acd9a8 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -56,6 +56,8 @@ #include <asm/ftrace.h> #include <asm/percpu.h> #include <asm/asm.h> +#include <asm/rcu.h> +#include <asm/smap.h> #include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ @@ -68,25 +70,51 @@ .section .entry.text, "ax" #ifdef CONFIG_FUNCTION_TRACER + +#ifdef CC_USING_FENTRY +# define function_hook __fentry__ +#else +# define function_hook mcount +#endif + #ifdef CONFIG_DYNAMIC_FTRACE -ENTRY(mcount) + +ENTRY(function_hook) retq -END(mcount) +END(function_hook) + +/* skip is set if stack has been adjusted */ +.macro ftrace_caller_setup skip=0 + MCOUNT_SAVE_FRAME \skip + + /* Load the ftrace_ops into the 3rd parameter */ + leaq function_trace_op, %rdx + + /* Load ip into the first parameter */ + movq RIP(%rsp), %rdi + subq $MCOUNT_INSN_SIZE, %rdi + /* Load the parent_ip into the second parameter */ +#ifdef CC_USING_FENTRY + movq SS+16(%rsp), %rsi +#else + movq 8(%rbp), %rsi +#endif +.endm ENTRY(ftrace_caller) + /* Check if tracing was disabled (quick check) */ cmpl $0, function_trace_stop jne ftrace_stub - MCOUNT_SAVE_FRAME - - movq 0x38(%rsp), %rdi - movq 8(%rbp), %rsi - subq $MCOUNT_INSN_SIZE, %rdi + ftrace_caller_setup + /* regs go into 4th parameter (but make it NULL) */ + movq $0, %rcx GLOBAL(ftrace_call) call ftrace_stub MCOUNT_RESTORE_FRAME +ftrace_return: #ifdef CONFIG_FUNCTION_GRAPH_TRACER GLOBAL(ftrace_graph_call) @@ -97,8 +125,78 @@ GLOBAL(ftrace_stub) retq END(ftrace_caller) +ENTRY(ftrace_regs_caller) + /* Save the current flags before compare (in SS location)*/ + pushfq + + /* Check if tracing was disabled (quick check) */ + cmpl $0, function_trace_stop + jne ftrace_restore_flags + + /* skip=8 to skip flags saved in SS */ + ftrace_caller_setup 8 + + /* Save the rest of pt_regs */ + movq %r15, R15(%rsp) + movq %r14, R14(%rsp) + movq %r13, R13(%rsp) + movq %r12, R12(%rsp) + movq %r11, R11(%rsp) + movq %r10, R10(%rsp) + movq %rbp, RBP(%rsp) + movq %rbx, RBX(%rsp) + /* Copy saved flags */ + movq SS(%rsp), %rcx + movq %rcx, EFLAGS(%rsp) + /* Kernel segments */ + movq $__KERNEL_DS, %rcx + movq %rcx, SS(%rsp) + movq $__KERNEL_CS, %rcx + movq %rcx, CS(%rsp) + /* Stack - skipping return address */ + leaq SS+16(%rsp), %rcx + movq %rcx, RSP(%rsp) + + /* regs go into 4th parameter */ + leaq (%rsp), %rcx + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + /* Copy flags back to SS, to restore them */ + movq EFLAGS(%rsp), %rax + movq %rax, SS(%rsp) + + /* Handlers can change the RIP */ + movq RIP(%rsp), %rax + movq %rax, SS+8(%rsp) + + /* restore the rest of pt_regs */ + movq R15(%rsp), %r15 + movq R14(%rsp), %r14 + movq R13(%rsp), %r13 + movq R12(%rsp), %r12 + movq R10(%rsp), %r10 + movq RBP(%rsp), %rbp + movq RBX(%rsp), %rbx + + /* skip=8 to skip flags saved in SS */ + MCOUNT_RESTORE_FRAME 8 + + /* Restore flags */ + popfq + + jmp ftrace_return +ftrace_restore_flags: + popfq + jmp ftrace_stub + +END(ftrace_regs_caller) + + #else /* ! CONFIG_DYNAMIC_FTRACE */ -ENTRY(mcount) + +ENTRY(function_hook) cmpl $0, function_trace_stop jne ftrace_stub @@ -119,8 +217,12 @@ GLOBAL(ftrace_stub) trace: MCOUNT_SAVE_FRAME - movq 0x38(%rsp), %rdi + movq RIP(%rsp), %rdi +#ifdef CC_USING_FENTRY + movq SS+16(%rsp), %rsi +#else movq 8(%rbp), %rsi +#endif subq $MCOUNT_INSN_SIZE, %rdi call *ftrace_trace_function @@ -128,20 +230,22 @@ trace: MCOUNT_RESTORE_FRAME jmp ftrace_stub -END(mcount) +END(function_hook) #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER ENTRY(ftrace_graph_caller) - cmpl $0, function_trace_stop - jne ftrace_stub - MCOUNT_SAVE_FRAME +#ifdef CC_USING_FENTRY + leaq SS+16(%rsp), %rdi + movq $0, %rdx /* No framepointers needed */ +#else leaq 8(%rbp), %rdi - movq 0x38(%rsp), %rsi movq (%rbp), %rdx +#endif + movq RIP(%rsp), %rsi subq $MCOUNT_INSN_SIZE, %rsi call prepare_ftrace_return @@ -342,15 +446,15 @@ ENDPROC(native_usergs_sysret64) .macro SAVE_ARGS_IRQ cld /* start from rbp in pt_regs and jump over */ - movq_cfi rdi, RDI-RBP - movq_cfi rsi, RSI-RBP - movq_cfi rdx, RDX-RBP - movq_cfi rcx, RCX-RBP - movq_cfi rax, RAX-RBP - movq_cfi r8, R8-RBP - movq_cfi r9, R9-RBP - movq_cfi r10, R10-RBP - movq_cfi r11, R11-RBP + movq_cfi rdi, (RDI-RBP) + movq_cfi rsi, (RSI-RBP) + movq_cfi rdx, (RDX-RBP) + movq_cfi rcx, (RCX-RBP) + movq_cfi rax, (RAX-RBP) + movq_cfi r8, (R8-RBP) + movq_cfi r9, (R9-RBP) + movq_cfi r10, (R10-RBP) + movq_cfi r11, (R11-RBP) /* Save rbp so that we can unwind from get_irq_regs() */ movq_cfi rbp, 0 @@ -384,7 +488,7 @@ ENDPROC(native_usergs_sysret64) .endm ENTRY(save_rest) - PARTIAL_FRAME 1 REST_SKIP+8 + PARTIAL_FRAME 1 (REST_SKIP+8) movq 5*8+16(%rsp), %r11 /* save return address */ movq_cfi rbx, RBX+16 movq_cfi rbp, RBP+16 @@ -440,7 +544,7 @@ ENTRY(ret_from_fork) LOCK ; btr $TIF_FORK,TI_flags(%r8) - pushq_cfi kernel_eflags(%rip) + pushq_cfi $0x0002 popfq_cfi # reset kernel eflags call schedule_tail # rdi: 'prev' task parameter @@ -465,7 +569,8 @@ END(ret_from_fork) * System call entry. Up to 6 arguments in registers are supported. * * SYSCALL does not save anything on the stack and does not change the - * stack pointer. + * stack pointer. However, it does mask the flags register for us, so + * CLD and CLAC are not needed. */ /* @@ -565,7 +670,7 @@ sysret_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi jmp sysret_check @@ -678,7 +783,7 @@ int_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF @@ -884,6 +989,7 @@ END(interrupt) */ .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: + ASM_CLAC XCPT_FRAME addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */ interrupt do_IRQ @@ -974,7 +1080,7 @@ retint_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi GET_THREAD_INFO(%rcx) DISABLE_INTERRUPTS(CLBR_NONE) @@ -1023,6 +1129,7 @@ END(common_interrupt) */ .macro apicinterrupt num sym do_sym ENTRY(\sym) + ASM_CLAC INTR_FRAME pushq_cfi $~(\num) .Lcommon_\sym: @@ -1077,6 +1184,7 @@ apicinterrupt IRQ_WORK_VECTOR \ */ .macro zeroentry sym do_sym ENTRY(\sym) + ASM_CLAC INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ @@ -1094,6 +1202,7 @@ END(\sym) .macro paranoidzeroentry sym do_sym ENTRY(\sym) + ASM_CLAC INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ @@ -1112,6 +1221,7 @@ END(\sym) #define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8) .macro paranoidzeroentry_ist sym do_sym ist ENTRY(\sym) + ASM_CLAC INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ @@ -1131,6 +1241,7 @@ END(\sym) .macro errorentry sym do_sym ENTRY(\sym) + ASM_CLAC XCPT_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME subq $ORIG_RAX-R15, %rsp @@ -1149,6 +1260,7 @@ END(\sym) /* error code is on the stack already */ .macro paranoiderrorentry sym do_sym ENTRY(\sym) + ASM_CLAC XCPT_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME subq $ORIG_RAX-R15, %rsp @@ -1449,7 +1561,7 @@ paranoid_userspace: paranoid_schedule: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_ANY) - call schedule + SCHEDULE_USER DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF jmp paranoid_userspace diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index c3a7cb4bf6e..1d414029f1d 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -206,6 +206,21 @@ static int ftrace_modify_code(unsigned long ip, unsigned const char *old_code, unsigned const char *new_code); +/* + * Should never be called: + * As it is only called by __ftrace_replace_code() which is called by + * ftrace_replace_code() that x86 overrides, and by ftrace_update_code() + * which is called to turn mcount into nops or nops into function calls + * but not to convert a function from not using regs to one that uses + * regs, which ftrace_modify_call() is for. + */ +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + WARN_ON(1); + return -EINVAL; +} + int ftrace_update_ftrace_func(ftrace_func_t func) { unsigned long ip = (unsigned long)(&ftrace_call); @@ -220,6 +235,14 @@ int ftrace_update_ftrace_func(ftrace_func_t func) ret = ftrace_modify_code(ip, old, new); + /* Also update the regs callback function */ + if (!ret) { + ip = (unsigned long)(&ftrace_regs_call); + memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE); + new = ftrace_call_replace(ip, (unsigned long)func); + ret = ftrace_modify_code(ip, old, new); + } + atomic_dec(&modifying_ftrace_code); return ret; @@ -299,6 +322,32 @@ static int add_brk_on_nop(struct dyn_ftrace *rec) return add_break(rec->ip, old); } +/* + * If the record has the FTRACE_FL_REGS set, that means that it + * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS + * is not not set, then it wants to convert to the normal callback. + */ +static unsigned long get_ftrace_addr(struct dyn_ftrace *rec) +{ + if (rec->flags & FTRACE_FL_REGS) + return (unsigned long)FTRACE_REGS_ADDR; + else + return (unsigned long)FTRACE_ADDR; +} + +/* + * The FTRACE_FL_REGS_EN is set when the record already points to + * a function that saves all the regs. Basically the '_EN' version + * represents the current state of the function. + */ +static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec) +{ + if (rec->flags & FTRACE_FL_REGS_EN) + return (unsigned long)FTRACE_REGS_ADDR; + else + return (unsigned long)FTRACE_ADDR; +} + static int add_breakpoints(struct dyn_ftrace *rec, int enable) { unsigned long ftrace_addr; @@ -306,7 +355,7 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable) ret = ftrace_test_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: @@ -316,6 +365,10 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable) /* converting nop to call */ return add_brk_on_nop(rec); + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: + ftrace_addr = get_ftrace_old_addr(rec); + /* fall through */ case FTRACE_UPDATE_MAKE_NOP: /* converting a call to a nop */ return add_brk_on_call(rec, ftrace_addr); @@ -360,13 +413,21 @@ static int remove_breakpoint(struct dyn_ftrace *rec) * If not, don't touch the breakpoint, we make just create * a disaster. */ - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); + nop = ftrace_call_replace(ip, ftrace_addr); + + if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0) + goto update; + + /* Check both ftrace_addr and ftrace_old_addr */ + ftrace_addr = get_ftrace_old_addr(rec); nop = ftrace_call_replace(ip, ftrace_addr); if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) return -EINVAL; } + update: return probe_kernel_write((void *)ip, &nop[0], 1); } @@ -405,12 +466,14 @@ static int add_update(struct dyn_ftrace *rec, int enable) ret = ftrace_test_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ return add_update_call(rec, ftrace_addr); @@ -455,12 +518,14 @@ static int finish_update(struct dyn_ftrace *rec, int enable) ret = ftrace_update_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ return finish_update_call(rec, ftrace_addr); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index d42ab17b739..957a47aec64 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -287,27 +287,28 @@ ENTRY(startup_32_smp) leal -__PAGE_OFFSET(%ecx),%esp default_entry: - /* * New page tables may be in 4Mbyte page mode and may * be using the global pages. * * NOTE! If we are on a 486 we may have no cr4 at all! - * So we do not try to touch it unless we really have - * some bits in it to set. This won't work if the BSP - * implements cr4 but this AP does not -- very unlikely - * but be warned! The same applies to the pse feature - * if not equally supported. --macro - * - * NOTE! We have to correct for the fact that we're - * not yet offset PAGE_OFFSET.. + * Specifically, cr4 exists if and only if CPUID exists, + * which in turn exists if and only if EFLAGS.ID exists. */ -#define cr4_bits pa(mmu_cr4_features) - movl cr4_bits,%edx - andl %edx,%edx - jz 6f - movl %cr4,%eax # Turn on paging options (PSE,PAE,..) - orl %edx,%eax + movl $X86_EFLAGS_ID,%ecx + pushl %ecx + popfl + pushfl + popl %eax + pushl $0 + popfl + pushfl + popl %edx + xorl %edx,%eax + testl %ecx,%eax + jz 6f # No ID flag = no CPUID = no CR4 + + movl pa(mmu_cr4_features),%eax movl %eax,%cr4 testb $X86_CR4_PAE, %al # check if PAE is enabled diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index f250431fb50..675a0501244 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -19,24 +19,17 @@ #include <asm/fpu-internal.h> #include <asm/user.h> -#ifdef CONFIG_X86_64 -# include <asm/sigcontext32.h> -# include <asm/user32.h> -#else -# define save_i387_xstate_ia32 save_i387_xstate -# define restore_i387_xstate_ia32 restore_i387_xstate -# define _fpstate_ia32 _fpstate -# define _xstate_ia32 _xstate -# define sig_xstate_ia32_size sig_xstate_size -# define fx_sw_reserved_ia32 fx_sw_reserved -# define user_i387_ia32_struct user_i387_struct -# define user32_fxsr_struct user_fxsr_struct -#endif - /* * Were we in an interrupt that interrupted kernel mode? * - * We can do a kernel_fpu_begin/end() pair *ONLY* if that + * For now, with eagerfpu we will return interrupted kernel FPU + * state as not-idle. TBD: Ideally we can change the return value + * to something like __thread_has_fpu(current). But we need to + * be careful of doing __thread_clear_has_fpu() before saving + * the FPU etc for supporting nested uses etc. For now, take + * the simple route! + * + * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that * pair does nothing at all: the thread must not have fpu (so * that we don't try to save the FPU state), and TS must * be set (so that the clts/stts pair does nothing that is @@ -44,6 +37,9 @@ */ static inline bool interrupted_kernel_fpu_idle(void) { + if (use_eager_fpu()) + return 0; + return !__thread_has_fpu(current) && (read_cr0() & X86_CR0_TS); } @@ -77,29 +73,29 @@ bool irq_fpu_usable(void) } EXPORT_SYMBOL(irq_fpu_usable); -void kernel_fpu_begin(void) +void __kernel_fpu_begin(void) { struct task_struct *me = current; - WARN_ON_ONCE(!irq_fpu_usable()); - preempt_disable(); if (__thread_has_fpu(me)) { __save_init_fpu(me); __thread_clear_has_fpu(me); - /* We do 'stts()' in kernel_fpu_end() */ - } else { + /* We do 'stts()' in __kernel_fpu_end() */ + } else if (!use_eager_fpu()) { this_cpu_write(fpu_owner_task, NULL); clts(); } } -EXPORT_SYMBOL(kernel_fpu_begin); +EXPORT_SYMBOL(__kernel_fpu_begin); -void kernel_fpu_end(void) +void __kernel_fpu_end(void) { - stts(); - preempt_enable(); + if (use_eager_fpu()) + math_state_restore(); + else + stts(); } -EXPORT_SYMBOL(kernel_fpu_end); +EXPORT_SYMBOL(__kernel_fpu_end); void unlazy_fpu(struct task_struct *tsk) { @@ -113,23 +109,15 @@ void unlazy_fpu(struct task_struct *tsk) } EXPORT_SYMBOL(unlazy_fpu); -#ifdef CONFIG_MATH_EMULATION -# define HAVE_HWFP (boot_cpu_data.hard_math) -#else -# define HAVE_HWFP 1 -#endif - -static unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; +unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; unsigned int xstate_size; EXPORT_SYMBOL_GPL(xstate_size); -unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32); static struct i387_fxsave_struct fx_scratch __cpuinitdata; static void __cpuinit mxcsr_feature_mask_init(void) { unsigned long mask = 0; - clts(); if (cpu_has_fxsr) { memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct)); asm volatile("fxsave %0" : : "m" (fx_scratch)); @@ -138,7 +126,6 @@ static void __cpuinit mxcsr_feature_mask_init(void) mask = 0x0000ffbf; } mxcsr_feature_mask &= mask; - stts(); } static void __cpuinit init_thread_xstate(void) @@ -192,9 +179,8 @@ void __cpuinit fpu_init(void) init_thread_xstate(); mxcsr_feature_mask_init(); - /* clean state in init */ - current_thread_info()->status = 0; - clear_used_math(); + xsave_init(); + eager_fpu_init(); } void fpu_finit(struct fpu *fpu) @@ -205,12 +191,7 @@ void fpu_finit(struct fpu *fpu) } if (cpu_has_fxsr) { - struct i387_fxsave_struct *fx = &fpu->state->fxsave; - - memset(fx, 0, xstate_size); - fx->cwd = 0x37f; - if (cpu_has_xmm) - fx->mxcsr = MXCSR_DEFAULT; + fx_finit(&fpu->state->fxsave); } else { struct i387_fsave_struct *fp = &fpu->state->fsave; memset(fp, 0, xstate_size); @@ -454,7 +435,7 @@ static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave) * FXSR floating point environment conversions. */ -static void +void convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) { struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; @@ -491,8 +472,8 @@ convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) memcpy(&to[i], &from[i], sizeof(to[0])); } -static void convert_to_fxsr(struct task_struct *tsk, - const struct user_i387_ia32_struct *env) +void convert_to_fxsr(struct task_struct *tsk, + const struct user_i387_ia32_struct *env) { struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; @@ -589,223 +570,6 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, } /* - * Signal frame handlers. - */ - -static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf) -{ - struct task_struct *tsk = current; - struct i387_fsave_struct *fp = &tsk->thread.fpu.state->fsave; - - fp->status = fp->swd; - if (__copy_to_user(buf, fp, sizeof(struct i387_fsave_struct))) - return -1; - return 1; -} - -static int save_i387_fxsave(struct _fpstate_ia32 __user *buf) -{ - struct task_struct *tsk = current; - struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave; - struct user_i387_ia32_struct env; - int err = 0; - - convert_from_fxsr(&env, tsk); - if (__copy_to_user(buf, &env, sizeof(env))) - return -1; - - err |= __put_user(fx->swd, &buf->status); - err |= __put_user(X86_FXSR_MAGIC, &buf->magic); - if (err) - return -1; - - if (__copy_to_user(&buf->_fxsr_env[0], fx, xstate_size)) - return -1; - return 1; -} - -static int save_i387_xsave(void __user *buf) -{ - struct task_struct *tsk = current; - struct _fpstate_ia32 __user *fx = buf; - int err = 0; - - - sanitize_i387_state(tsk); - - /* - * For legacy compatible, we always set FP/SSE bits in the bit - * vector while saving the state to the user context. - * This will enable us capturing any changes(during sigreturn) to - * the FP/SSE bits by the legacy applications which don't touch - * xstate_bv in the xsave header. - * - * xsave aware applications can change the xstate_bv in the xsave - * header as well as change any contents in the memory layout. - * xrestore as part of sigreturn will capture all the changes. - */ - tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE; - - if (save_i387_fxsave(fx) < 0) - return -1; - - err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved_ia32, - sizeof(struct _fpx_sw_bytes)); - err |= __put_user(FP_XSTATE_MAGIC2, - (__u32 __user *) (buf + sig_xstate_ia32_size - - FP_XSTATE_MAGIC2_SIZE)); - if (err) - return -1; - - return 1; -} - -int save_i387_xstate_ia32(void __user *buf) -{ - struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf; - struct task_struct *tsk = current; - - if (!used_math()) - return 0; - - if (!access_ok(VERIFY_WRITE, buf, sig_xstate_ia32_size)) - return -EACCES; - /* - * This will cause a "finit" to be triggered by the next - * attempted FPU operation by the 'current' process. - */ - clear_used_math(); - - if (!HAVE_HWFP) { - return fpregs_soft_get(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, fp) ? -1 : 1; - } - - unlazy_fpu(tsk); - - if (cpu_has_xsave) - return save_i387_xsave(fp); - if (cpu_has_fxsr) - return save_i387_fxsave(fp); - else - return save_i387_fsave(fp); -} - -static inline int restore_i387_fsave(struct _fpstate_ia32 __user *buf) -{ - struct task_struct *tsk = current; - - return __copy_from_user(&tsk->thread.fpu.state->fsave, buf, - sizeof(struct i387_fsave_struct)); -} - -static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf, - unsigned int size) -{ - struct task_struct *tsk = current; - struct user_i387_ia32_struct env; - int err; - - err = __copy_from_user(&tsk->thread.fpu.state->fxsave, &buf->_fxsr_env[0], - size); - /* mxcsr reserved bits must be masked to zero for security reasons */ - tsk->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask; - if (err || __copy_from_user(&env, buf, sizeof(env))) - return 1; - convert_to_fxsr(tsk, &env); - - return 0; -} - -static int restore_i387_xsave(void __user *buf) -{ - struct _fpx_sw_bytes fx_sw_user; - struct _fpstate_ia32 __user *fx_user = - ((struct _fpstate_ia32 __user *) buf); - struct i387_fxsave_struct __user *fx = - (struct i387_fxsave_struct __user *) &fx_user->_fxsr_env[0]; - struct xsave_hdr_struct *xsave_hdr = - ¤t->thread.fpu.state->xsave.xsave_hdr; - u64 mask; - int err; - - if (check_for_xstate(fx, buf, &fx_sw_user)) - goto fx_only; - - mask = fx_sw_user.xstate_bv; - - err = restore_i387_fxsave(buf, fx_sw_user.xstate_size); - - xsave_hdr->xstate_bv &= pcntxt_mask; - /* - * These bits must be zero. - */ - xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0; - - /* - * Init the state that is not present in the memory layout - * and enabled by the OS. - */ - mask = ~(pcntxt_mask & ~mask); - xsave_hdr->xstate_bv &= mask; - - return err; -fx_only: - /* - * Couldn't find the extended state information in the memory - * layout. Restore the FP/SSE and init the other extended state - * enabled by the OS. - */ - xsave_hdr->xstate_bv = XSTATE_FPSSE; - return restore_i387_fxsave(buf, sizeof(struct i387_fxsave_struct)); -} - -int restore_i387_xstate_ia32(void __user *buf) -{ - int err; - struct task_struct *tsk = current; - struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf; - - if (HAVE_HWFP) - clear_fpu(tsk); - - if (!buf) { - if (used_math()) { - clear_fpu(tsk); - clear_used_math(); - } - - return 0; - } else - if (!access_ok(VERIFY_READ, buf, sig_xstate_ia32_size)) - return -EACCES; - - if (!used_math()) { - err = init_fpu(tsk); - if (err) - return err; - } - - if (HAVE_HWFP) { - if (cpu_has_xsave) - err = restore_i387_xsave(buf); - else if (cpu_has_fxsr) - err = restore_i387_fxsave(fp, sizeof(struct - i387_fxsave_struct)); - else - err = restore_i387_fsave(fp); - } else { - err = fpregs_soft_set(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, fp) != 0; - } - set_used_math(); - - return err; -} - -/* * FPU state for core dumps. * This is only used for a.out dumps now. * It is declared generically using elf_fpregset_t (which is diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 36d1853e91a..9a5c460404d 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -263,7 +263,7 @@ static void i8259A_shutdown(void) * out of. */ outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ - outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-1 */ + outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ } static struct syscore_ops i8259_syscore_ops = { diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 1f5f1d5d2a0..e4595f10591 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -92,7 +92,8 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, " Rescheduling interrupts\n"); seq_printf(p, "%*s: ", prec, "CAL"); for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->irq_call_count); + seq_printf(p, "%10u ", irq_stats(j)->irq_call_count - + irq_stats(j)->irq_tlb_count); seq_printf(p, " Function call interrupts\n"); seq_printf(p, "%*s: ", prec, "TLB"); for_each_online_cpu(j) @@ -147,7 +148,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu) #ifdef CONFIG_SMP sum += irq_stats(cpu)->irq_resched_count; sum += irq_stats(cpu)->irq_call_count; - sum += irq_stats(cpu)->irq_tlb_count; #endif #ifdef CONFIG_X86_THERMAL_VECTOR sum += irq_stats(cpu)->irq_thermal_count; @@ -270,7 +270,7 @@ void fixup_irqs(void) if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { break_affinity = 1; - affinity = cpu_all_mask; + affinity = cpu_online_mask; } chip = irq_data_get_irq_chip(data); @@ -328,6 +328,7 @@ void fixup_irqs(void) chip->irq_retrigger(data); raw_spin_unlock(&desc->lock); } + __this_cpu_write(vector_irq[vector], -1); } } #endif diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 1d5d31ea686..dc1404bf8e4 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -107,7 +107,7 @@ static int __init create_setup_data_nodes(struct dentry *parent) { struct setup_data_node *node; struct setup_data *data; - int error = -ENOMEM; + int error; struct dentry *d; struct page *pg; u64 pa_data; @@ -121,8 +121,10 @@ static int __init create_setup_data_nodes(struct dentry *parent) while (pa_data) { node = kmalloc(sizeof(*node), GFP_KERNEL); - if (!node) + if (!node) { + error = -ENOMEM; goto err_dir; + } pg = pfn_to_page((pa_data+sizeof(*data)-1) >> PAGE_SHIFT); if (PageHighMem(pg)) { diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index e2f751efb7b..57916c0d3cf 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -541,6 +541,23 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb return 1; } +#ifdef KPROBES_CAN_USE_FTRACE +static void __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + /* + * Emulate singlestep (and also recover regs->ip) + * as if there is a 5byte nop + */ + regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + __this_cpu_write(current_kprobe, NULL); +} +#endif + /* * Interrupts are disabled on entry as trap3 is an interrupt gate and they * remain disabled throughout this function. @@ -599,6 +616,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) } else if (kprobe_running()) { p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { +#ifdef KPROBES_CAN_USE_FTRACE + if (kprobe_ftrace(p)) { + skip_singlestep(p, regs, kcb); + return 1; + } +#endif setup_singlestep(p, regs, kcb, 0); return 1; } @@ -1052,6 +1075,50 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) return 0; } +#ifdef KPROBES_CAN_USE_FTRACE +/* Ftrace callback handler for kprobes */ +void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) +{ + struct kprobe *p; + struct kprobe_ctlblk *kcb; + unsigned long flags; + + /* Disable irq for emulating a breakpoint and avoiding preempt */ + local_irq_save(flags); + + p = get_kprobe((kprobe_opcode_t *)ip); + if (unlikely(!p) || kprobe_disabled(p)) + goto end; + + kcb = get_kprobe_ctlblk(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(p); + } else { + /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ + regs->ip = ip + sizeof(kprobe_opcode_t); + + __this_cpu_write(current_kprobe, p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + if (!p->pre_handler || !p->pre_handler(p, regs)) + skip_singlestep(p, regs, kcb); + /* + * If pre_handler returns !0, it sets regs->ip and + * resets current kprobe. + */ + } +end: + local_irq_restore(flags); +} + +int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + p->ainsn.insn = NULL; + p->ainsn.boostable = -1; + return 0; +} +#endif + int __init arch_init_kprobes(void) { return arch_init_optprobes(); diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 8a2ce8fd41c..7720ff5a9ee 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -75,20 +75,113 @@ struct microcode_amd { static struct equiv_cpu_entry *equiv_cpu_table; -/* page-sized ucode patch buffer */ -void *patch; +struct ucode_patch { + struct list_head plist; + void *data; + u32 patch_id; + u16 equiv_cpu; +}; + +static LIST_HEAD(pcache); + +static u16 find_equiv_id(unsigned int cpu) +{ + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + int i = 0; + + if (!equiv_cpu_table) + return 0; + + while (equiv_cpu_table[i].installed_cpu != 0) { + if (uci->cpu_sig.sig == equiv_cpu_table[i].installed_cpu) + return equiv_cpu_table[i].equiv_cpu; + + i++; + } + return 0; +} + +static u32 find_cpu_family_by_equiv_cpu(u16 equiv_cpu) +{ + int i = 0; + + BUG_ON(!equiv_cpu_table); + + while (equiv_cpu_table[i].equiv_cpu != 0) { + if (equiv_cpu == equiv_cpu_table[i].equiv_cpu) + return equiv_cpu_table[i].installed_cpu; + i++; + } + return 0; +} + +/* + * a small, trivial cache of per-family ucode patches + */ +static struct ucode_patch *cache_find_patch(u16 equiv_cpu) +{ + struct ucode_patch *p; + + list_for_each_entry(p, &pcache, plist) + if (p->equiv_cpu == equiv_cpu) + return p; + return NULL; +} + +static void update_cache(struct ucode_patch *new_patch) +{ + struct ucode_patch *p; + + list_for_each_entry(p, &pcache, plist) { + if (p->equiv_cpu == new_patch->equiv_cpu) { + if (p->patch_id >= new_patch->patch_id) + /* we already have the latest patch */ + return; + + list_replace(&p->plist, &new_patch->plist); + kfree(p->data); + kfree(p); + return; + } + } + /* no patch found, add it */ + list_add_tail(&new_patch->plist, &pcache); +} + +static void free_cache(void) +{ + struct ucode_patch *p, *tmp; + + list_for_each_entry_safe(p, tmp, &pcache, plist) { + __list_del(p->plist.prev, p->plist.next); + kfree(p->data); + kfree(p); + } +} + +static struct ucode_patch *find_patch(unsigned int cpu) +{ + u16 equiv_id; + + equiv_id = find_equiv_id(cpu); + if (!equiv_id) + return NULL; + + return cache_find_patch(equiv_id); +} static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig) { struct cpuinfo_x86 *c = &cpu_data(cpu); + csig->sig = cpuid_eax(0x00000001); csig->rev = c->microcode; pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev); return 0; } -static unsigned int verify_ucode_size(int cpu, u32 patch_size, +static unsigned int verify_patch_size(int cpu, u32 patch_size, unsigned int size) { struct cpuinfo_x86 *c = &cpu_data(cpu); @@ -118,94 +211,37 @@ static unsigned int verify_ucode_size(int cpu, u32 patch_size, return patch_size; } -static u16 find_equiv_id(void) +static int apply_microcode_amd(int cpu) { - unsigned int current_cpu_id, i = 0; - - BUG_ON(equiv_cpu_table == NULL); - - current_cpu_id = cpuid_eax(0x00000001); - - while (equiv_cpu_table[i].installed_cpu != 0) { - if (current_cpu_id == equiv_cpu_table[i].installed_cpu) - return equiv_cpu_table[i].equiv_cpu; - - i++; - } - return 0; -} + struct cpuinfo_x86 *c = &cpu_data(cpu); + struct microcode_amd *mc_amd; + struct ucode_cpu_info *uci; + struct ucode_patch *p; + u32 rev, dummy; -/* - * we signal a good patch is found by returning its size > 0 - */ -static int get_matching_microcode(int cpu, const u8 *ucode_ptr, - unsigned int leftover_size, int rev, - unsigned int *current_size) -{ - struct microcode_header_amd *mc_hdr; - unsigned int actual_size; - u16 equiv_cpu_id; + BUG_ON(raw_smp_processor_id() != cpu); - /* size of the current patch we're staring at */ - *current_size = *(u32 *)(ucode_ptr + 4) + SECTION_HDR_SIZE; + uci = ucode_cpu_info + cpu; - equiv_cpu_id = find_equiv_id(); - if (!equiv_cpu_id) + p = find_patch(cpu); + if (!p) return 0; - /* - * let's look at the patch header itself now - */ - mc_hdr = (struct microcode_header_amd *)(ucode_ptr + SECTION_HDR_SIZE); + mc_amd = p->data; + uci->mc = p->data; - if (mc_hdr->processor_rev_id != equiv_cpu_id) - return 0; + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - /* ucode might be chipset specific -- currently we don't support this */ - if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) { - pr_err("CPU%d: chipset specific code not yet supported\n", - cpu); + /* need to apply patch? */ + if (rev >= mc_amd->hdr.patch_id) { + c->microcode = rev; return 0; } - if (mc_hdr->patch_id <= rev) - return 0; - - /* - * now that the header looks sane, verify its size - */ - actual_size = verify_ucode_size(cpu, *current_size, leftover_size); - if (!actual_size) - return 0; - - /* clear the patch buffer */ - memset(patch, 0, PAGE_SIZE); - - /* all looks ok, get the binary patch */ - get_ucode_data(patch, ucode_ptr + SECTION_HDR_SIZE, actual_size); - - return actual_size; -} - -static int apply_microcode_amd(int cpu) -{ - u32 rev, dummy; - int cpu_num = raw_smp_processor_id(); - struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; - struct microcode_amd *mc_amd = uci->mc; - struct cpuinfo_x86 *c = &cpu_data(cpu); - - /* We should bind the task to the CPU */ - BUG_ON(cpu_num != cpu); - - if (mc_amd == NULL) - return 0; - wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code); - /* get patch id after patching */ - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - /* check current patch id and patch's id for match */ + /* verify patch application was successful */ + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); if (rev != mc_amd->hdr.patch_id) { pr_err("CPU%d: update failed for patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); @@ -237,7 +273,7 @@ static int install_equiv_cpu_table(const u8 *buf) return -ENOMEM; } - get_ucode_data(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size); + memcpy(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size); /* add header length */ return size + CONTAINER_HDR_SZ; @@ -249,61 +285,113 @@ static void free_equiv_cpu_table(void) equiv_cpu_table = NULL; } -static enum ucode_state -generic_load_microcode(int cpu, const u8 *data, size_t size) +static void cleanup(void) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - struct microcode_header_amd *mc_hdr = NULL; - unsigned int mc_size, leftover, current_size = 0; + free_equiv_cpu_table(); + free_cache(); +} + +/* + * We return the current size even if some of the checks failed so that + * we can skip over the next patch. If we return a negative value, we + * signal a grave error like a memory allocation has failed and the + * driver cannot continue functioning normally. In such cases, we tear + * down everything we've used up so far and exit. + */ +static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) +{ + struct cpuinfo_x86 *c = &cpu_data(cpu); + struct microcode_header_amd *mc_hdr; + struct ucode_patch *patch; + unsigned int patch_size, crnt_size, ret; + u32 proc_fam; + u16 proc_id; + + patch_size = *(u32 *)(fw + 4); + crnt_size = patch_size + SECTION_HDR_SIZE; + mc_hdr = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE); + proc_id = mc_hdr->processor_rev_id; + + proc_fam = find_cpu_family_by_equiv_cpu(proc_id); + if (!proc_fam) { + pr_err("No patch family for equiv ID: 0x%04x\n", proc_id); + return crnt_size; + } + + /* check if patch is for the current family */ + proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff); + if (proc_fam != c->x86) + return crnt_size; + + if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) { + pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", + mc_hdr->patch_id); + return crnt_size; + } + + ret = verify_patch_size(cpu, patch_size, leftover); + if (!ret) { + pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id); + return crnt_size; + } + + patch = kzalloc(sizeof(*patch), GFP_KERNEL); + if (!patch) { + pr_err("Patch allocation failure.\n"); + return -EINVAL; + } + + patch->data = kzalloc(patch_size, GFP_KERNEL); + if (!patch->data) { + pr_err("Patch data allocation failure.\n"); + kfree(patch); + return -EINVAL; + } + + /* All looks ok, copy patch... */ + memcpy(patch->data, fw + SECTION_HDR_SIZE, patch_size); + INIT_LIST_HEAD(&patch->plist); + patch->patch_id = mc_hdr->patch_id; + patch->equiv_cpu = proc_id; + + /* ... and add to cache. */ + update_cache(patch); + + return crnt_size; +} + +static enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size) +{ + enum ucode_state ret = UCODE_ERROR; + unsigned int leftover; + u8 *fw = (u8 *)data; + int crnt_size = 0; int offset; - const u8 *ucode_ptr = data; - void *new_mc = NULL; - unsigned int new_rev = uci->cpu_sig.rev; - enum ucode_state state = UCODE_ERROR; - offset = install_equiv_cpu_table(ucode_ptr); + offset = install_equiv_cpu_table(data); if (offset < 0) { pr_err("failed to create equivalent cpu table\n"); - goto out; + return ret; } - ucode_ptr += offset; + fw += offset; leftover = size - offset; - if (*(u32 *)ucode_ptr != UCODE_UCODE_TYPE) { + if (*(u32 *)fw != UCODE_UCODE_TYPE) { pr_err("invalid type field in container file section header\n"); - goto free_table; + free_equiv_cpu_table(); + return ret; } while (leftover) { - mc_size = get_matching_microcode(cpu, ucode_ptr, leftover, - new_rev, ¤t_size); - if (mc_size) { - mc_hdr = patch; - new_mc = patch; - new_rev = mc_hdr->patch_id; - goto out_ok; - } - - ucode_ptr += current_size; - leftover -= current_size; - } + crnt_size = verify_and_add_patch(cpu, fw, leftover); + if (crnt_size < 0) + return ret; - if (!new_mc) { - state = UCODE_NFOUND; - goto free_table; + fw += crnt_size; + leftover -= crnt_size; } -out_ok: - uci->mc = new_mc; - state = UCODE_OK; - pr_debug("CPU%d update ucode (0x%08x -> 0x%08x)\n", - cpu, uci->cpu_sig.rev, new_rev); - -free_table: - free_equiv_cpu_table(); - -out: - return state; + return UCODE_OK; } /* @@ -314,7 +402,7 @@ out: * * This legacy file is always smaller than 2K in size. * - * Starting at family 15h they are in family specific firmware files: + * Beginning with family 15h, they are in family-specific firmware files: * * amd-ucode/microcode_amd_fam15h.bin * amd-ucode/microcode_amd_fam16h.bin @@ -322,12 +410,17 @@ out: * * These might be larger than 2K. */ -static enum ucode_state request_microcode_amd(int cpu, struct device *device) +static enum ucode_state request_microcode_amd(int cpu, struct device *device, + bool refresh_fw) { char fw_name[36] = "amd-ucode/microcode_amd.bin"; - const struct firmware *fw; - enum ucode_state ret = UCODE_NFOUND; struct cpuinfo_x86 *c = &cpu_data(cpu); + enum ucode_state ret = UCODE_NFOUND; + const struct firmware *fw; + + /* reload ucode container only on the boot cpu */ + if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index) + return UCODE_OK; if (c->x86 >= 0x15) snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); @@ -343,12 +436,17 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device) goto fw_release; } - ret = generic_load_microcode(cpu, fw->data, fw->size); + /* free old equiv table */ + free_equiv_cpu_table(); + + ret = load_microcode_amd(cpu, fw->data, fw->size); + if (ret != UCODE_OK) + cleanup(); -fw_release: + fw_release: release_firmware(fw); -out: + out: return ret; } @@ -382,14 +480,10 @@ struct microcode_ops * __init init_amd_microcode(void) return NULL; } - patch = (void *)get_zeroed_page(GFP_KERNEL); - if (!patch) - return NULL; - return µcode_amd_ops; } void __exit exit_amd_microcode(void) { - free_page((unsigned long)patch); + cleanup(); } diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 4873e62db6a..3a04b224d0c 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -225,6 +225,9 @@ static ssize_t microcode_write(struct file *file, const char __user *buf, if (do_microcode_update(buf, len) == 0) ret = (ssize_t)len; + if (ret > 0) + perf_check_microcode(); + mutex_unlock(µcode_mutex); put_online_cpus(); @@ -276,19 +279,18 @@ static struct platform_device *microcode_pdev; static int reload_for_cpu(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + enum ucode_state ustate; int err = 0; - if (uci->valid) { - enum ucode_state ustate; - - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev); - if (ustate == UCODE_OK) - apply_microcode_on_target(cpu); - else - if (ustate == UCODE_ERROR) - err = -EINVAL; - } + if (!uci->valid) + return err; + ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, true); + if (ustate == UCODE_OK) + apply_microcode_on_target(cpu); + else + if (ustate == UCODE_ERROR) + err = -EINVAL; return err; } @@ -370,18 +372,15 @@ static void microcode_fini_cpu(int cpu) static enum ucode_state microcode_resume_cpu(int cpu) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - - if (!uci->mc) - return UCODE_NFOUND; - pr_debug("CPU%d updated upon resume\n", cpu); - apply_microcode_on_target(cpu); + + if (apply_microcode_on_target(cpu)) + return UCODE_ERROR; return UCODE_OK; } -static enum ucode_state microcode_init_cpu(int cpu) +static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw) { enum ucode_state ustate; @@ -392,7 +391,8 @@ static enum ucode_state microcode_init_cpu(int cpu) if (system_state != SYSTEM_RUNNING) return UCODE_NFOUND; - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev); + ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, + refresh_fw); if (ustate == UCODE_OK) { pr_debug("CPU%d updated upon init\n", cpu); @@ -405,14 +405,11 @@ static enum ucode_state microcode_init_cpu(int cpu) static enum ucode_state microcode_update_cpu(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - enum ucode_state ustate; if (uci->valid) - ustate = microcode_resume_cpu(cpu); - else - ustate = microcode_init_cpu(cpu); + return microcode_resume_cpu(cpu); - return ustate; + return microcode_init_cpu(cpu, false); } static int mc_device_add(struct device *dev, struct subsys_interface *sif) @@ -428,7 +425,7 @@ static int mc_device_add(struct device *dev, struct subsys_interface *sif) if (err) return err; - if (microcode_init_cpu(cpu) == UCODE_ERROR) + if (microcode_init_cpu(cpu, true) == UCODE_ERROR) return -EINVAL; return err; @@ -477,34 +474,41 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) struct device *dev; dev = get_cpu_device(cpu); - switch (action) { + + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: microcode_update_cpu(cpu); - case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: 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; + case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: /* Suspend is in progress, only remove the interface */ sysfs_remove_group(&dev->kobj, &mc_attr_group); pr_debug("CPU%d removed\n", cpu); break; /* + * 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. */ - case CPU_UP_CANCELED_FROZEN: - /* The CPU refused to come up during a system resume */ - microcode_fini_cpu(cpu); - break; } + + /* The CPU refused to come up during a system resume */ + if (action == CPU_UP_CANCELED_FROZEN) + microcode_fini_cpu(cpu); + return NOTIFY_OK; } diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index 0327e2b3c40..3544aed3933 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -405,7 +405,8 @@ static int get_ucode_fw(void *to, const void *from, size_t n) return 0; } -static enum ucode_state request_microcode_fw(int cpu, struct device *device) +static enum ucode_state request_microcode_fw(int cpu, struct device *device, + bool refresh_fw) { char name[30]; struct cpuinfo_x86 *c = &cpu_data(cpu); diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index eb113693f04..a7c5661f849 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -257,12 +257,14 @@ static int __init msr_init(void) goto out_chrdev; } msr_class->devnode = msr_devnode; + get_online_cpus(); for_each_online_cpu(i) { err = msr_device_create(i); if (err != 0) goto out_class; } register_hotcpu_notifier(&msr_class_cpu_notifier); + put_online_cpus(); err = 0; goto out; @@ -271,6 +273,7 @@ out_class: i = 0; for_each_online_cpu(i) msr_device_destroy(i); + put_online_cpus(); class_destroy(msr_class); out_chrdev: __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr"); @@ -281,11 +284,13 @@ out: static void __exit msr_exit(void) { int cpu = 0; + get_online_cpus(); for_each_online_cpu(cpu) msr_device_destroy(cpu); class_destroy(msr_class); __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr"); unregister_hotcpu_notifier(&msr_class_cpu_notifier); + put_online_cpus(); } module_init(msr_init); diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c new file mode 100644 index 00000000000..e309cc5c276 --- /dev/null +++ b/arch/x86/kernel/perf_regs.c @@ -0,0 +1,105 @@ +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/perf_event.h> +#include <linux/bug.h> +#include <linux/stddef.h> +#include <asm/perf_regs.h> +#include <asm/ptrace.h> + +#ifdef CONFIG_X86_32 +#define PERF_REG_X86_MAX PERF_REG_X86_32_MAX +#else +#define PERF_REG_X86_MAX PERF_REG_X86_64_MAX +#endif + +#define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r) + +static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = { + PT_REGS_OFFSET(PERF_REG_X86_AX, ax), + PT_REGS_OFFSET(PERF_REG_X86_BX, bx), + PT_REGS_OFFSET(PERF_REG_X86_CX, cx), + PT_REGS_OFFSET(PERF_REG_X86_DX, dx), + PT_REGS_OFFSET(PERF_REG_X86_SI, si), + PT_REGS_OFFSET(PERF_REG_X86_DI, di), + PT_REGS_OFFSET(PERF_REG_X86_BP, bp), + PT_REGS_OFFSET(PERF_REG_X86_SP, sp), + PT_REGS_OFFSET(PERF_REG_X86_IP, ip), + PT_REGS_OFFSET(PERF_REG_X86_FLAGS, flags), + PT_REGS_OFFSET(PERF_REG_X86_CS, cs), + PT_REGS_OFFSET(PERF_REG_X86_SS, ss), +#ifdef CONFIG_X86_32 + PT_REGS_OFFSET(PERF_REG_X86_DS, ds), + PT_REGS_OFFSET(PERF_REG_X86_ES, es), + PT_REGS_OFFSET(PERF_REG_X86_FS, fs), + PT_REGS_OFFSET(PERF_REG_X86_GS, gs), +#else + /* + * The pt_regs struct does not store + * ds, es, fs, gs in 64 bit mode. + */ + (unsigned int) -1, + (unsigned int) -1, + (unsigned int) -1, + (unsigned int) -1, +#endif +#ifdef CONFIG_X86_64 + PT_REGS_OFFSET(PERF_REG_X86_R8, r8), + PT_REGS_OFFSET(PERF_REG_X86_R9, r9), + PT_REGS_OFFSET(PERF_REG_X86_R10, r10), + PT_REGS_OFFSET(PERF_REG_X86_R11, r11), + PT_REGS_OFFSET(PERF_REG_X86_R12, r12), + PT_REGS_OFFSET(PERF_REG_X86_R13, r13), + PT_REGS_OFFSET(PERF_REG_X86_R14, r14), + PT_REGS_OFFSET(PERF_REG_X86_R15, r15), +#endif +}; + +u64 perf_reg_value(struct pt_regs *regs, int idx) +{ + if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset))) + return 0; + + return regs_get_register(regs, pt_regs_offset[idx]); +} + +#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL)) + +#ifdef CONFIG_X86_32 +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + return 0; +} + +u64 perf_reg_abi(struct task_struct *task) +{ + return PERF_SAMPLE_REGS_ABI_32; +} +#else /* CONFIG_X86_64 */ +#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \ + (1ULL << PERF_REG_X86_ES) | \ + (1ULL << PERF_REG_X86_FS) | \ + (1ULL << PERF_REG_X86_GS)) + +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + if (mask & REG_NOSUPPORT) + return -EINVAL; + + return 0; +} + +u64 perf_reg_abi(struct task_struct *task) +{ + if (test_tsk_thread_flag(task, TIF_IA32)) + return PERF_SAMPLE_REGS_ABI_32; + else + return PERF_SAMPLE_REGS_ABI_64; +} +#endif /* CONFIG_X86_32 */ diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 0bc72e2069e..d5f15c3f7b2 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -150,7 +150,7 @@ static struct resource *find_oprom(struct pci_dev *pdev) return oprom; } -void *pci_map_biosrom(struct pci_dev *pdev) +void __iomem *pci_map_biosrom(struct pci_dev *pdev) { struct resource *oprom = find_oprom(pdev); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ef6a8456f71..dc3567e083f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -66,15 +66,13 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { int ret; - unlazy_fpu(src); - *dst = *src; if (fpu_allocated(&src->thread.fpu)) { memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu)); ret = fpu_alloc(&dst->thread.fpu); if (ret) return ret; - fpu_copy(&dst->thread.fpu, &src->thread.fpu); + fpu_copy(dst, src); } return 0; } @@ -97,16 +95,6 @@ void arch_task_cache_init(void) SLAB_PANIC | SLAB_NOTRACK, NULL); } -static inline void drop_fpu(struct task_struct *tsk) -{ - /* - * Forget coprocessor state.. - */ - tsk->fpu_counter = 0; - clear_fpu(tsk); - clear_used_math(); -} - /* * Free current thread data structures etc.. */ @@ -163,7 +151,13 @@ void flush_thread(void) flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - drop_fpu(tsk); + drop_init_fpu(tsk); + /* + * Free the FPU state for non xsave platforms. They get reallocated + * lazily at the first use. + */ + if (!use_eager_fpu()) + free_thread_xstate(tsk); } static void hard_disable_TSC(void) diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 516fa186121..b9ff83c7135 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -190,10 +190,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) regs->cs = __USER_CS; regs->ip = new_ip; regs->sp = new_sp; - /* - * Free the old FP and other extended state - */ - free_thread_xstate(current); } EXPORT_SYMBOL_GPL(start_thread); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 0a980c9d7cb..8a6d20ce197 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -232,10 +232,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, regs->cs = _cs; regs->ss = _ss; regs->flags = X86_EFLAGS_IF; - /* - * Free the old FP and other extended state - */ - free_thread_xstate(current); } void diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index c4c6a5c2bf0..b00b33a1839 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -21,6 +21,7 @@ #include <linux/signal.h> #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> +#include <linux/rcupdate.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -1332,9 +1333,6 @@ static const struct user_regset_view user_x86_64_view = { #define genregs32_get genregs_get #define genregs32_set genregs_set -#define user_i387_ia32_struct user_i387_struct -#define user32_fxsr_struct user_fxsr_struct - #endif /* CONFIG_X86_64 */ #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION @@ -1463,6 +1461,8 @@ long syscall_trace_enter(struct pt_regs *regs) { long ret = 0; + rcu_user_exit(); + /* * If we stepped into a sysenter/syscall insn, it trapped in * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. @@ -1526,4 +1526,6 @@ void syscall_trace_leave(struct pt_regs *regs) !test_thread_flag(TIF_SYSCALL_EMU); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, step); + + rcu_user_enter(); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f4b9b80e1b9..4f165479c45 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -961,9 +961,7 @@ void __init setup_arch(char **cmdline_p) kvmclock_init(); #endif - x86_init.paging.pagetable_setup_start(swapper_pg_dir); - paging_init(); - x86_init.paging.pagetable_setup_done(swapper_pg_dir); + x86_init.paging.pagetable_init(); if (boot_cpu_data.cpuid_level >= 0) { /* A CPU has %cr4 if and only if it has CPUID */ diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b280908a376..b33144c8b30 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -114,11 +114,12 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, regs->orig_ax = -1; /* disable syscall checks */ get_user_ex(buf, &sc->fpstate); - err |= restore_i387_xstate(buf); get_user_ex(*pax, &sc->ax); } get_user_catch(err); + err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32)); + return err; } @@ -206,35 +207,32 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { /* Default to using normal stack */ + unsigned long math_size = 0; unsigned long sp = regs->sp; + unsigned long buf_fx = 0; int onsigstack = on_sig_stack(sp); -#ifdef CONFIG_X86_64 /* redzone */ - sp -= 128; -#endif /* CONFIG_X86_64 */ + if (config_enabled(CONFIG_X86_64)) + sp -= 128; if (!onsigstack) { /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa.sa_flags & SA_ONSTACK) { if (current->sas_ss_size) sp = current->sas_ss_sp + current->sas_ss_size; - } else { -#ifdef CONFIG_X86_32 - /* This is the legacy signal stack switching. */ - if ((regs->ss & 0xffff) != __USER_DS && - !(ka->sa.sa_flags & SA_RESTORER) && - ka->sa.sa_restorer) + } else if (config_enabled(CONFIG_X86_32) && + (regs->ss & 0xffff) != __USER_DS && + !(ka->sa.sa_flags & SA_RESTORER) && + ka->sa.sa_restorer) { + /* This is the legacy signal stack switching. */ sp = (unsigned long) ka->sa.sa_restorer; -#endif /* CONFIG_X86_32 */ } } if (used_math()) { - sp -= sig_xstate_size; -#ifdef CONFIG_X86_64 - sp = round_down(sp, 64); -#endif /* CONFIG_X86_64 */ + sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32), + &buf_fx, &math_size); *fpstate = (void __user *)sp; } @@ -247,8 +245,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, if (onsigstack && !likely(on_sig_stack(sp))) return (void __user *)-1L; - /* save i387 state */ - if (used_math() && save_i387_xstate(*fpstate) < 0) + /* save i387 and extended state */ + if (used_math() && + save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0) return (void __user *)-1L; return (void __user *)sp; @@ -357,7 +356,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, put_user_ex(sig, &frame->sig); put_user_ex(&frame->info, &frame->pinfo); put_user_ex(&frame->uc, &frame->puc); - err |= copy_siginfo_to_user(&frame->info, info); /* Create the ucontext. */ if (cpu_has_xsave) @@ -369,9 +367,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, put_user_ex(sas_ss_flags(regs->sp), &frame->uc.uc_stack.ss_flags); put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); - err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); /* Set up to return from userspace. */ restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); @@ -388,6 +383,11 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, */ put_user_ex(*((u64 *)&rt_retcode), (u64 *)frame->retcode); } put_user_catch(err); + + err |= copy_siginfo_to_user(&frame->info, info); + err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, + regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (err) return -EFAULT; @@ -436,8 +436,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, put_user_ex(sas_ss_flags(regs->sp), &frame->uc.uc_stack.ss_flags); put_user_ex(me->sas_ss_size, &frame->uc.uc_stack.ss_size); - err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); /* Set up to return from userspace. If provided, use a stub already in userspace. */ @@ -450,6 +448,9 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, } } put_user_catch(err); + err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) return -EFAULT; @@ -474,6 +475,75 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, } #endif /* CONFIG_X86_32 */ +static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, + siginfo_t *info, compat_sigset_t *set, + struct pt_regs *regs) +{ +#ifdef CONFIG_X86_X32_ABI + struct rt_sigframe_x32 __user *frame; + void __user *restorer; + int err = 0; + void __user *fpstate = NULL; + + frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate); + + if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) + return -EFAULT; + + if (ka->sa.sa_flags & SA_SIGINFO) { + if (copy_siginfo_to_user32(&frame->info, info)) + return -EFAULT; + } + + put_user_try { + /* Create the ucontext. */ + if (cpu_has_xsave) + put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); + else + put_user_ex(0, &frame->uc.uc_flags); + put_user_ex(0, &frame->uc.uc_link); + put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + put_user_ex(sas_ss_flags(regs->sp), + &frame->uc.uc_stack.ss_flags); + put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + put_user_ex(0, &frame->uc.uc__pad0); + + if (ka->sa.sa_flags & SA_RESTORER) { + restorer = ka->sa.sa_restorer; + } else { + /* could use a vstub here */ + restorer = NULL; + err |= -EFAULT; + } + put_user_ex(restorer, &frame->pretcode); + } put_user_catch(err); + + err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, + regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + + if (err) + return -EFAULT; + + /* Set up registers for signal handler */ + regs->sp = (unsigned long) frame; + regs->ip = (unsigned long) ka->sa.sa_handler; + + /* We use the x32 calling convention here... */ + regs->di = sig; + regs->si = (unsigned long) &frame->info; + regs->dx = (unsigned long) &frame->uc; + + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); + + regs->cs = __USER_CS; + regs->ss = __USER_DS; +#endif /* CONFIG_X86_X32_ABI */ + + return 0; +} + #ifdef CONFIG_X86_32 /* * Atomically swap in the new signal mask, and wait for a signal. @@ -612,55 +682,22 @@ static int signr_convert(int sig) return sig; } -#ifdef CONFIG_X86_32 - -#define is_ia32 1 -#define ia32_setup_frame __setup_frame -#define ia32_setup_rt_frame __setup_rt_frame - -#else /* !CONFIG_X86_32 */ - -#ifdef CONFIG_IA32_EMULATION -#define is_ia32 test_thread_flag(TIF_IA32) -#else /* !CONFIG_IA32_EMULATION */ -#define is_ia32 0 -#endif /* CONFIG_IA32_EMULATION */ - -#ifdef CONFIG_X86_X32_ABI -#define is_x32 test_thread_flag(TIF_X32) - -static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, - siginfo_t *info, compat_sigset_t *set, - struct pt_regs *regs); -#else /* !CONFIG_X86_X32_ABI */ -#define is_x32 0 -#endif /* CONFIG_X86_X32_ABI */ - -int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, - sigset_t *set, struct pt_regs *regs); -int ia32_setup_frame(int sig, struct k_sigaction *ka, - sigset_t *set, struct pt_regs *regs); - -#endif /* CONFIG_X86_32 */ - static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, struct pt_regs *regs) { int usig = signr_convert(sig); sigset_t *set = sigmask_to_save(); + compat_sigset_t *cset = (compat_sigset_t *) set; /* Set up the stack frame */ - if (is_ia32) { + if (is_ia32_frame()) { if (ka->sa.sa_flags & SA_SIGINFO) - return ia32_setup_rt_frame(usig, ka, info, set, regs); + return ia32_setup_rt_frame(usig, ka, info, cset, regs); else - return ia32_setup_frame(usig, ka, set, regs); -#ifdef CONFIG_X86_X32_ABI - } else if (is_x32) { - return x32_setup_rt_frame(usig, ka, info, - (compat_sigset_t *)set, regs); -#endif + return ia32_setup_frame(usig, ka, cset, regs); + } else if (is_x32_frame()) { + return x32_setup_rt_frame(usig, ka, info, cset, regs); } else { return __setup_rt_frame(sig, ka, info, set, regs); } @@ -779,6 +816,8 @@ static void do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) { + rcu_user_exit(); + #ifdef CONFIG_X86_MCE /* notify userspace of pending MCEs */ if (thread_info_flags & _TIF_MCE_NOTIFY) @@ -804,6 +843,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) #ifdef CONFIG_X86_32 clear_thread_flag(TIF_IRET); #endif /* CONFIG_X86_32 */ + + rcu_user_enter(); } void signal_fault(struct pt_regs *regs, void __user *frame, char *where) @@ -824,72 +865,6 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) } #ifdef CONFIG_X86_X32_ABI -static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, - siginfo_t *info, compat_sigset_t *set, - struct pt_regs *regs) -{ - struct rt_sigframe_x32 __user *frame; - void __user *restorer; - int err = 0; - void __user *fpstate = NULL; - - frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate); - - if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) - return -EFAULT; - - if (ka->sa.sa_flags & SA_SIGINFO) { - if (copy_siginfo_to_user32(&frame->info, info)) - return -EFAULT; - } - - put_user_try { - /* Create the ucontext. */ - if (cpu_has_xsave) - put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); - else - put_user_ex(0, &frame->uc.uc_flags); - put_user_ex(0, &frame->uc.uc_link); - put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - put_user_ex(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); - put_user_ex(0, &frame->uc.uc__pad0); - err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); - - if (ka->sa.sa_flags & SA_RESTORER) { - restorer = ka->sa.sa_restorer; - } else { - /* could use a vstub here */ - restorer = NULL; - err |= -EFAULT; - } - put_user_ex(restorer, &frame->pretcode); - } put_user_catch(err); - - if (err) - return -EFAULT; - - /* Set up registers for signal handler */ - regs->sp = (unsigned long) frame; - regs->ip = (unsigned long) ka->sa.sa_handler; - - /* We use the x32 calling convention here... */ - regs->di = sig; - regs->si = (unsigned long) &frame->info; - regs->dx = (unsigned long) &frame->uc; - - loadsegment(ds, __USER_DS); - loadsegment(es, __USER_DS); - - regs->cs = __USER_CS; - regs->ss = __USER_DS; - - return 0; -} - asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs) { struct rt_sigframe_x32 __user *frame; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 7c5a8c314c0..c80a33bc528 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -665,7 +665,8 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long boot_error = 0; int timeout; - alternatives_smp_switch(1); + /* Just in case we booted with a single CPU. */ + alternatives_enable_smp(); idle->thread.sp = (unsigned long) (((struct pt_regs *) (THREAD_SIZE + task_stack_page(idle))) - 1); @@ -1053,20 +1054,6 @@ out: preempt_enable(); } -void arch_disable_nonboot_cpus_begin(void) -{ - /* - * Avoid the smp alternatives switch during the disable_nonboot_cpus(). - * In the suspend path, we will be back in the SMP mode shortly anyways. - */ - skip_smp_alternatives = true; -} - -void arch_disable_nonboot_cpus_end(void) -{ - skip_smp_alternatives = false; -} - void arch_enable_nonboot_cpus_begin(void) { set_mtrr_aps_delayed_init(); @@ -1256,9 +1243,6 @@ void native_cpu_die(unsigned int cpu) if (per_cpu(cpu_state, cpu) == CPU_DEAD) { if (system_state == SYSTEM_RUNNING) pr_info("CPU %u is now offline\n", cpu); - - if (1 == num_online_cpus()) - alternatives_smp_switch(0); return; } msleep(100); diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index c346d116148..cd3b2438a98 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -157,6 +157,33 @@ static int enable_single_step(struct task_struct *child) return 1; } +void set_task_blockstep(struct task_struct *task, bool on) +{ + unsigned long debugctl; + + /* + * Ensure irq/preemption can't change debugctl in between. + * Note also that both TIF_BLOCKSTEP and debugctl should + * be changed atomically wrt preemption. + * FIXME: this means that set/clear TIF_BLOCKSTEP is simply + * wrong if task != current, SIGKILL can wakeup the stopped + * tracee and set/clear can play with the running task, this + * can confuse the next __switch_to_xtra(). + */ + local_irq_disable(); + debugctl = get_debugctlmsr(); + if (on) { + debugctl |= DEBUGCTLMSR_BTF; + set_tsk_thread_flag(task, TIF_BLOCKSTEP); + } else { + debugctl &= ~DEBUGCTLMSR_BTF; + clear_tsk_thread_flag(task, TIF_BLOCKSTEP); + } + if (task == current) + update_debugctlmsr(debugctl); + local_irq_enable(); +} + /* * Enable single or block step. */ @@ -169,19 +196,10 @@ static void enable_step(struct task_struct *child, bool block) * So no one should try to use debugger block stepping in a program * that uses user-mode single stepping itself. */ - if (enable_single_step(child) && block) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl |= DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - set_tsk_thread_flag(child, TIF_BLOCKSTEP); - } else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl &= ~DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - clear_tsk_thread_flag(child, TIF_BLOCKSTEP); - } + if (enable_single_step(child) && block) + set_task_blockstep(child, true); + else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) + set_task_blockstep(child, false); } void user_enable_single_step(struct task_struct *child) @@ -199,13 +217,8 @@ void user_disable_single_step(struct task_struct *child) /* * Make sure block stepping (BTF) is disabled. */ - if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl &= ~DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - clear_tsk_thread_flag(child, TIF_BLOCKSTEP); - } + if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) + set_task_blockstep(child, false); /* Always clear TIF_SINGLESTEP... */ clear_tsk_thread_flag(child, TIF_SINGLESTEP); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b481341c936..8276dc6794c 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -55,6 +55,7 @@ #include <asm/i387.h> #include <asm/fpu-internal.h> #include <asm/mce.h> +#include <asm/rcu.h> #include <asm/mach_traps.h> @@ -107,30 +108,45 @@ static inline void preempt_conditional_cli(struct pt_regs *regs) dec_preempt_count(); } -static void __kprobes -do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, - long error_code, siginfo_t *info) +static int __kprobes +do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, + struct pt_regs *regs, long error_code) { - struct task_struct *tsk = current; - #ifdef CONFIG_X86_32 if (regs->flags & X86_VM_MASK) { /* - * traps 0, 1, 3, 4, and 5 should be forwarded to vm86. + * Traps 0, 1, 3, 4, and 5 should be forwarded to vm86. * On nmi (interrupt 2), do_trap should not be called. */ - if (trapnr < X86_TRAP_UD) - goto vm86_trap; - goto trap_signal; + if (trapnr < X86_TRAP_UD) { + if (!handle_vm86_trap((struct kernel_vm86_regs *) regs, + error_code, trapnr)) + return 0; + } + return -1; } #endif + if (!user_mode(regs)) { + if (!fixup_exception(regs)) { + tsk->thread.error_code = error_code; + tsk->thread.trap_nr = trapnr; + die(str, regs, error_code); + } + return 0; + } - if (!user_mode(regs)) - goto kernel_trap; + return -1; +} -#ifdef CONFIG_X86_32 -trap_signal: -#endif +static void __kprobes +do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, + long error_code, siginfo_t *info) +{ + struct task_struct *tsk = current; + + + if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code)) + return; /* * We want error_code and trap_nr set for userspace faults and * kernelspace faults which result in die(), but not @@ -158,33 +174,20 @@ trap_signal: force_sig_info(signr, info, tsk); else force_sig(signr, tsk); - return; - -kernel_trap: - if (!fixup_exception(regs)) { - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = trapnr; - die(str, regs, error_code); - } - return; - -#ifdef CONFIG_X86_32 -vm86_trap: - if (handle_vm86_trap((struct kernel_vm86_regs *) regs, - error_code, trapnr)) - goto trap_signal; - return; -#endif } #define DO_ERROR(trapnr, signr, str, name) \ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ + exception_enter(regs); \ + if (notify_die(DIE_TRAP, str, regs, error_code, \ + trapnr, signr) == NOTIFY_STOP) { \ + exception_exit(regs); \ return; \ + } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, NULL); \ + exception_exit(regs); \ } #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ @@ -195,11 +198,15 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ info.si_errno = 0; \ info.si_code = sicode; \ info.si_addr = (void __user *)siaddr; \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ + exception_enter(regs); \ + if (notify_die(DIE_TRAP, str, regs, error_code, \ + trapnr, signr) == NOTIFY_STOP) { \ + exception_exit(regs); \ return; \ + } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, &info); \ + exception_exit(regs); \ } DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, @@ -222,12 +229,14 @@ DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, /* Runs on IST stack */ dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) { + exception_enter(regs); if (notify_die(DIE_TRAP, "stack segment", regs, error_code, - X86_TRAP_SS, SIGBUS) == NOTIFY_STOP) - return; - preempt_conditional_sti(regs); - do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); - preempt_conditional_cli(regs); + X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { + preempt_conditional_sti(regs); + do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); + preempt_conditional_cli(regs); + } + exception_exit(regs); } dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) @@ -235,6 +244,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) static const char str[] = "double fault"; struct task_struct *tsk = current; + exception_enter(regs); /* Return not checked because double check cannot be ignored */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -255,16 +265,29 @@ do_general_protection(struct pt_regs *regs, long error_code) { struct task_struct *tsk; + exception_enter(regs); conditional_sti(regs); #ifdef CONFIG_X86_32 - if (regs->flags & X86_VM_MASK) - goto gp_in_vm86; + if (regs->flags & X86_VM_MASK) { + local_irq_enable(); + handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); + goto exit; + } #endif tsk = current; - if (!user_mode(regs)) - goto gp_in_kernel; + if (!user_mode(regs)) { + if (fixup_exception(regs)) + goto exit; + + tsk->thread.error_code = error_code; + tsk->thread.trap_nr = X86_TRAP_GP; + if (notify_die(DIE_GPF, "general protection fault", regs, error_code, + X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP) + die("general protection fault", regs, error_code); + goto exit; + } tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; @@ -279,25 +302,8 @@ do_general_protection(struct pt_regs *regs, long error_code) } force_sig(SIGSEGV, tsk); - return; - -#ifdef CONFIG_X86_32 -gp_in_vm86: - local_irq_enable(); - handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); - return; -#endif - -gp_in_kernel: - if (fixup_exception(regs)) - return; - - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = X86_TRAP_GP; - if (notify_die(DIE_GPF, "general protection fault", regs, error_code, - X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP) - return; - die("general protection fault", regs, error_code); +exit: + exception_exit(regs); } /* May run on IST stack. */ @@ -312,15 +318,16 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co ftrace_int3_handler(regs)) return; #endif + exception_enter(regs); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) - return; + goto exit; #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */ if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) - return; + goto exit; /* * Let others (NMI) know that the debug stack is in use @@ -331,6 +338,8 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); preempt_conditional_cli(regs); debug_stack_usage_dec(); +exit: + exception_exit(regs); } #ifdef CONFIG_X86_64 @@ -391,6 +400,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) unsigned long dr6; int si_code; + exception_enter(regs); + get_debugreg(dr6, 6); /* Filter out all the reserved bits which are preset to 1 */ @@ -406,7 +417,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) /* Catch kmemcheck conditions first of all! */ if ((dr6 & DR_STEP) && kmemcheck_trap(regs)) - return; + goto exit; /* DR6 may or may not be cleared by the CPU */ set_debugreg(0, 6); @@ -421,7 +432,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code, SIGTRAP) == NOTIFY_STOP) - return; + goto exit; /* * Let others (NMI) know that the debug stack is in use @@ -437,7 +448,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) X86_TRAP_DB); preempt_conditional_cli(regs); debug_stack_usage_dec(); - return; + goto exit; } /* @@ -458,7 +469,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) preempt_conditional_cli(regs); debug_stack_usage_dec(); - return; +exit: + exception_exit(regs); } /* @@ -555,14 +567,17 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) #ifdef CONFIG_X86_32 ignore_fpu_irq = 1; #endif - + exception_enter(regs); math_error(regs, error_code, X86_TRAP_MF); + exception_exit(regs); } dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { + exception_enter(regs); math_error(regs, error_code, X86_TRAP_XF); + exception_exit(regs); } dotraplinkage void @@ -613,11 +628,12 @@ void math_state_restore(void) } __thread_fpu_begin(tsk); + /* * Paranoid restore. send a SIGSEGV if we fail to restore the state. */ if (unlikely(restore_fpu_checking(tsk))) { - __thread_fpu_end(tsk); + drop_init_fpu(tsk); force_sig(SIGSEGV, tsk); return; } @@ -629,6 +645,9 @@ EXPORT_SYMBOL_GPL(math_state_restore); dotraplinkage void __kprobes do_device_not_available(struct pt_regs *regs, long error_code) { + exception_enter(regs); + BUG_ON(use_eager_fpu()); + #ifdef CONFIG_MATH_EMULATION if (read_cr0() & X86_CR0_EM) { struct math_emu_info info = { }; @@ -637,6 +656,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); + exception_exit(regs); return; } #endif @@ -644,12 +664,15 @@ do_device_not_available(struct pt_regs *regs, long error_code) #ifdef CONFIG_X86_32 conditional_sti(regs); #endif + exception_exit(regs); } #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) { siginfo_t info; + + exception_enter(regs); local_irq_enable(); info.si_signo = SIGILL; @@ -657,10 +680,11 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) info.si_code = ILL_BADSTK; info.si_addr = NULL; if (notify_die(DIE_TRAP, "iret exception", regs, error_code, - X86_TRAP_IRET, SIGILL) == NOTIFY_STOP) - return; - do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, - &info); + X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) { + do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, + &info); + } + exception_exit(regs); } #endif diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 36fd42091fa..9538f00827a 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -41,6 +41,9 @@ /* Adjust the return address of a call insn */ #define UPROBE_FIX_CALL 0x2 +/* Instruction will modify TF, don't change it */ +#define UPROBE_FIX_SETF 0x4 + #define UPROBE_FIX_RIP_AX 0x8000 #define UPROBE_FIX_RIP_CX 0x4000 @@ -239,6 +242,10 @@ static void prepare_fixups(struct arch_uprobe *auprobe, struct insn *insn) insn_get_opcode(insn); /* should be a nop */ switch (OPCODE1(insn)) { + case 0x9d: + /* popf */ + auprobe->fixups |= UPROBE_FIX_SETF; + break; case 0xc3: /* ret/lret */ case 0xcb: case 0xc2: @@ -646,7 +653,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) * Skip these instructions as per the currently known x86 ISA. * 0x66* { 0x90 | 0x0f 0x1f | 0x0f 0x19 | 0x87 0xc0 } */ -bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) { int i; @@ -673,3 +680,46 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) } return false; } + +bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + bool ret = __skip_sstep(auprobe, regs); + if (ret && (regs->flags & X86_EFLAGS_TF)) + send_sig(SIGTRAP, current, 0); + return ret; +} + +void arch_uprobe_enable_step(struct arch_uprobe *auprobe) +{ + struct task_struct *task = current; + struct arch_uprobe_task *autask = &task->utask->autask; + struct pt_regs *regs = task_pt_regs(task); + + autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF); + + regs->flags |= X86_EFLAGS_TF; + if (test_tsk_thread_flag(task, TIF_BLOCKSTEP)) + set_task_blockstep(task, false); +} + +void arch_uprobe_disable_step(struct arch_uprobe *auprobe) +{ + struct task_struct *task = current; + struct arch_uprobe_task *autask = &task->utask->autask; + bool trapped = (task->utask->state == UTASK_SSTEP_TRAPPED); + struct pt_regs *regs = task_pt_regs(task); + /* + * The state of TIF_BLOCKSTEP was not saved so we can get an extra + * SIGTRAP if we do not clear TF. We need to examine the opcode to + * make it right. + */ + if (unlikely(trapped)) { + if (!autask->saved_tf) + regs->flags &= ~X86_EFLAGS_TF; + } else { + if (autask->saved_tf) + send_sig(SIGTRAP, task, 0); + else if (!(auprobe->fixups & UPROBE_FIX_SETF)) + regs->flags &= ~X86_EFLAGS_TF; + } +} diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 6020f6f5927..1330dd10295 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -13,9 +13,13 @@ #include <asm/ftrace.h> #ifdef CONFIG_FUNCTION_TRACER -/* mcount is defined in assembly */ +/* mcount and __fentry__ are defined in assembly */ +#ifdef CC_USING_FENTRY +EXPORT_SYMBOL(__fentry__); +#else EXPORT_SYMBOL(mcount); #endif +#endif EXPORT_SYMBOL(__get_user_1); EXPORT_SYMBOL(__get_user_2); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 9f3167e891e..7a3d075a814 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -26,7 +26,6 @@ void __cpuinit x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } -void __init x86_init_pgd_noop(pgd_t *unused) { } int __init iommu_init_noop(void) { return 0; } void iommu_shutdown_noop(void) { } @@ -68,8 +67,7 @@ struct x86_init_ops x86_init __initdata = { }, .paging = { - .pagetable_setup_start = native_pagetable_setup_start, - .pagetable_setup_done = native_pagetable_setup_done, + .pagetable_init = native_pagetable_init, }, .timers = { diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 3d3e2070911..ada87a329ed 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -10,9 +10,7 @@ #include <linux/compat.h> #include <asm/i387.h> #include <asm/fpu-internal.h> -#ifdef CONFIG_IA32_EMULATION -#include <asm/sigcontext32.h> -#endif +#include <asm/sigframe.h> #include <asm/xcr.h> /* @@ -23,13 +21,9 @@ u64 pcntxt_mask; /* * Represents init state for the supported extended state. */ -static struct xsave_struct *init_xstate_buf; - -struct _fpx_sw_bytes fx_sw_reserved; -#ifdef CONFIG_IA32_EMULATION -struct _fpx_sw_bytes fx_sw_reserved_ia32; -#endif +struct xsave_struct *init_xstate_buf; +static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32; static unsigned int *xstate_offsets, *xstate_sizes, xstate_features; /* @@ -44,9 +38,9 @@ static unsigned int *xstate_offsets, *xstate_sizes, xstate_features; */ void __sanitize_i387_state(struct task_struct *tsk) { - u64 xstate_bv; - int feature_bit = 0x2; struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave; + int feature_bit = 0x2; + u64 xstate_bv; if (!fx) return; @@ -104,213 +98,326 @@ void __sanitize_i387_state(struct task_struct *tsk) * Check for the presence of extended state information in the * user fpstate pointer in the sigcontext. */ -int check_for_xstate(struct i387_fxsave_struct __user *buf, - void __user *fpstate, - struct _fpx_sw_bytes *fx_sw_user) +static inline int check_for_xstate(struct i387_fxsave_struct __user *buf, + void __user *fpstate, + struct _fpx_sw_bytes *fx_sw) { int min_xstate_size = sizeof(struct i387_fxsave_struct) + sizeof(struct xsave_hdr_struct); unsigned int magic2; - int err; - err = __copy_from_user(fx_sw_user, &buf->sw_reserved[0], - sizeof(struct _fpx_sw_bytes)); - if (err) - return -EFAULT; + if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw))) + return -1; - /* - * First Magic check failed. - */ - if (fx_sw_user->magic1 != FP_XSTATE_MAGIC1) - return -EINVAL; + /* Check for the first magic field and other error scenarios. */ + if (fx_sw->magic1 != FP_XSTATE_MAGIC1 || + fx_sw->xstate_size < min_xstate_size || + fx_sw->xstate_size > xstate_size || + fx_sw->xstate_size > fx_sw->extended_size) + return -1; /* - * Check for error scenarios. - */ - if (fx_sw_user->xstate_size < min_xstate_size || - fx_sw_user->xstate_size > xstate_size || - fx_sw_user->xstate_size > fx_sw_user->extended_size) - return -EINVAL; - - err = __get_user(magic2, (__u32 *) (((void *)fpstate) + - fx_sw_user->extended_size - - FP_XSTATE_MAGIC2_SIZE)); - if (err) - return err; - /* * Check for the presence of second magic word at the end of memory * layout. This detects the case where the user just copied the legacy * fpstate layout with out copying the extended state information * in the memory layout. */ - if (magic2 != FP_XSTATE_MAGIC2) - return -EFAULT; + if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)) + || magic2 != FP_XSTATE_MAGIC2) + return -1; return 0; } -#ifdef CONFIG_X86_64 /* * Signal frame handlers. */ - -int save_i387_xstate(void __user *buf) +static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) { - struct task_struct *tsk = current; - int err = 0; - - if (!access_ok(VERIFY_WRITE, buf, sig_xstate_size)) - return -EACCES; + if (use_fxsr()) { + struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct user_i387_ia32_struct env; + struct _fpstate_ia32 __user *fp = buf; - BUG_ON(sig_xstate_size < xstate_size); + convert_from_fxsr(&env, tsk); - if ((unsigned long)buf % 64) - pr_err("%s: bad fpstate %p\n", __func__, buf); - - if (!used_math()) - return 0; - - if (user_has_fpu()) { - if (use_xsave()) - err = xsave_user(buf); - else - err = fxsave_user(buf); - - if (err) - return err; - user_fpu_end(); + if (__copy_to_user(buf, &env, sizeof(env)) || + __put_user(xsave->i387.swd, &fp->status) || + __put_user(X86_FXSR_MAGIC, &fp->magic)) + return -1; } else { - sanitize_i387_state(tsk); - if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave, - xstate_size)) + struct i387_fsave_struct __user *fp = buf; + u32 swd; + if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status)) return -1; } - clear_used_math(); /* trigger finit */ + return 0; +} - if (use_xsave()) { - struct _fpstate __user *fx = buf; - struct _xstate __user *x = buf; - u64 xstate_bv; +static inline int save_xstate_epilog(void __user *buf, int ia32_frame) +{ + struct xsave_struct __user *x = buf; + struct _fpx_sw_bytes *sw_bytes; + u32 xstate_bv; + int err; - err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved, - sizeof(struct _fpx_sw_bytes)); + /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ + sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved; + err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes)); - err |= __put_user(FP_XSTATE_MAGIC2, - (__u32 __user *) (buf + sig_xstate_size - - FP_XSTATE_MAGIC2_SIZE)); + if (!use_xsave()) + return err; - /* - * Read the xstate_bv which we copied (directly from the cpu or - * from the state in task struct) to the user buffers and - * set the FP/SSE bits. - */ - err |= __get_user(xstate_bv, &x->xstate_hdr.xstate_bv); + err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size)); - /* - * For legacy compatible, we always set FP/SSE bits in the bit - * vector while saving the state to the user context. This will - * enable us capturing any changes(during sigreturn) to - * the FP/SSE bits by the legacy applications which don't touch - * xstate_bv in the xsave header. - * - * xsave aware apps can change the xstate_bv in the xsave - * header as well as change any contents in the memory layout. - * xrestore as part of sigreturn will capture all the changes. - */ - xstate_bv |= XSTATE_FPSSE; + /* + * Read the xstate_bv which we copied (directly from the cpu or + * from the state in task struct) to the user buffers. + */ + err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - err |= __put_user(xstate_bv, &x->xstate_hdr.xstate_bv); + /* + * For legacy compatible, we always set FP/SSE bits in the bit + * vector while saving the state to the user context. This will + * enable us capturing any changes(during sigreturn) to + * the FP/SSE bits by the legacy applications which don't touch + * xstate_bv in the xsave header. + * + * xsave aware apps can change the xstate_bv in the xsave + * header as well as change any contents in the memory layout. + * xrestore as part of sigreturn will capture all the changes. + */ + xstate_bv |= XSTATE_FPSSE; - if (err) - return err; - } + err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - return 1; + return err; +} + +static inline int save_user_xstate(struct xsave_struct __user *buf) +{ + int err; + + if (use_xsave()) + err = xsave_user(buf); + else if (use_fxsr()) + err = fxsave_user((struct i387_fxsave_struct __user *) buf); + else + err = fsave_user((struct i387_fsave_struct __user *) buf); + + if (unlikely(err) && __clear_user(buf, xstate_size)) + err = -EFAULT; + return err; } /* - * Restore the extended state if present. Otherwise, restore the FP/SSE - * state. + * Save the fpu, extended register state to the user signal frame. + * + * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save + * state is copied. + * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'. + * + * buf == buf_fx for 64-bit frames and 32-bit fsave frame. + * buf != buf_fx for 32-bit frames with fxstate. + * + * If the fpu, extended register state is live, save the state directly + * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise, + * copy the thread's fpu state to the user frame starting at 'buf_fx'. + * + * If this is a 32-bit frame with fxstate, put a fsave header before + * the aligned state at 'buf_fx'. + * + * For [f]xsave state, update the SW reserved fields in the [f]xsave frame + * indicating the absence/presence of the extended state to the user. */ -static int restore_user_xstate(void __user *buf) +int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) { - struct _fpx_sw_bytes fx_sw_user; - u64 mask; - int err; + struct xsave_struct *xsave = ¤t->thread.fpu.state->xsave; + struct task_struct *tsk = current; + int ia32_fxstate = (buf != buf_fx); - if (((unsigned long)buf % 64) || - check_for_xstate(buf, buf, &fx_sw_user)) - goto fx_only; + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); - mask = fx_sw_user.xstate_bv; + if (!access_ok(VERIFY_WRITE, buf, size)) + return -EACCES; - /* - * restore the state passed by the user. - */ - err = xrestore_user(buf, mask); - if (err) - return err; + if (!HAVE_HWFP) + return fpregs_soft_get(current, NULL, 0, + sizeof(struct user_i387_ia32_struct), NULL, + (struct _fpstate_ia32 __user *) buf) ? -1 : 1; - /* - * init the state skipped by the user. - */ - mask = pcntxt_mask & ~mask; - if (unlikely(mask)) - xrstor_state(init_xstate_buf, mask); + if (user_has_fpu()) { + /* Save the live register state to the user directly. */ + if (save_user_xstate(buf_fx)) + return -1; + /* Update the thread's fxstate to save the fsave header. */ + if (ia32_fxstate) + fpu_fxsave(&tsk->thread.fpu); + } else { + sanitize_i387_state(tsk); + if (__copy_to_user(buf_fx, xsave, xstate_size)) + return -1; + } + + /* Save the fsave header for the 32-bit frames. */ + if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf)) + return -1; + + if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) + return -1; + + drop_init_fpu(tsk); /* trigger finit */ return 0; +} -fx_only: - /* - * couldn't find the extended state information in the - * memory layout. Restore just the FP/SSE and init all - * the other extended state. - */ - xrstor_state(init_xstate_buf, pcntxt_mask & ~XSTATE_FPSSE); - return fxrstor_checking((__force struct i387_fxsave_struct *)buf); +static inline void +sanitize_restored_xstate(struct task_struct *tsk, + struct user_i387_ia32_struct *ia32_env, + u64 xstate_bv, int fx_only) +{ + struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr; + + if (use_xsave()) { + /* These bits must be zero. */ + xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0; + + /* + * Init the state that is not present in the memory + * layout and not enabled by the OS. + */ + if (fx_only) + xsave_hdr->xstate_bv = XSTATE_FPSSE; + else + xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv); + } + + if (use_fxsr()) { + /* + * mscsr reserved bits must be masked to zero for security + * reasons. + */ + xsave->i387.mxcsr &= mxcsr_feature_mask; + + convert_to_fxsr(tsk, ia32_env); + } } /* - * This restores directly out of user space. Exceptions are handled. + * Restore the extended state if present. Otherwise, restore the FP/SSE state. */ -int restore_i387_xstate(void __user *buf) +static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only) { + if (use_xsave()) { + if ((unsigned long)buf % 64 || fx_only) { + u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE; + xrstor_state(init_xstate_buf, init_bv); + return fxrstor_user(buf); + } else { + u64 init_bv = pcntxt_mask & ~xbv; + if (unlikely(init_bv)) + xrstor_state(init_xstate_buf, init_bv); + return xrestore_user(buf, xbv); + } + } else if (use_fxsr()) { + return fxrstor_user(buf); + } else + return frstor_user(buf); +} + +int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) +{ + int ia32_fxstate = (buf != buf_fx); struct task_struct *tsk = current; - int err = 0; + int state_size = xstate_size; + u64 xstate_bv = 0; + int fx_only = 0; + + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); if (!buf) { - if (used_math()) - goto clear; + drop_init_fpu(tsk); return 0; - } else - if (!access_ok(VERIFY_READ, buf, sig_xstate_size)) - return -EACCES; + } - if (!used_math()) { - err = init_fpu(tsk); - if (err) - return err; + if (!access_ok(VERIFY_READ, buf, size)) + return -EACCES; + + if (!used_math() && init_fpu(tsk)) + return -1; + + if (!HAVE_HWFP) { + return fpregs_soft_set(current, NULL, + 0, sizeof(struct user_i387_ia32_struct), + NULL, buf) != 0; } - user_fpu_begin(); - if (use_xsave()) - err = restore_user_xstate(buf); - else - err = fxrstor_checking((__force struct i387_fxsave_struct *) - buf); - if (unlikely(err)) { + if (use_xsave()) { + struct _fpx_sw_bytes fx_sw_user; + if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) { + /* + * Couldn't find the extended state information in the + * memory layout. Restore just the FP/SSE and init all + * the other extended state. + */ + state_size = sizeof(struct i387_fxsave_struct); + fx_only = 1; + } else { + state_size = fx_sw_user.xstate_size; + xstate_bv = fx_sw_user.xstate_bv; + } + } + + if (ia32_fxstate) { + /* + * For 32-bit frames with fxstate, copy the user state to the + * thread's fpu state, reconstruct fxstate from the fsave + * header. Sanitize the copied state etc. + */ + struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct user_i387_ia32_struct env; + int err = 0; + + /* + * Drop the current fpu which clears used_math(). This ensures + * that any context-switch during the copy of the new state, + * avoids the intermediate state from getting restored/saved. + * Thus avoiding the new restored state from getting corrupted. + * We will be ready to restore/save the state only after + * set_used_math() is again set. + */ + drop_fpu(tsk); + + if (__copy_from_user(xsave, buf_fx, state_size) || + __copy_from_user(&env, buf, sizeof(env))) { + err = -1; + } else { + sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only); + set_used_math(); + } + + if (use_eager_fpu()) + math_state_restore(); + + return err; + } else { /* - * Encountered an error while doing the restore from the - * user buffer, clear the fpu state. + * For 64-bit frames and 32-bit fsave frames, restore the user + * state to the registers directly (with exceptions handled). */ -clear: - clear_fpu(tsk); - clear_used_math(); + user_fpu_begin(); + if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) { + drop_init_fpu(tsk); + return -1; + } } - return err; + + return 0; } -#endif /* * Prepare the SW reserved portion of the fxsave memory layout, indicating @@ -321,31 +428,22 @@ clear: */ static void prepare_fx_sw_frame(void) { - int size_extended = (xstate_size - sizeof(struct i387_fxsave_struct)) + - FP_XSTATE_MAGIC2_SIZE; + int fsave_header_size = sizeof(struct i387_fsave_struct); + int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; - sig_xstate_size = sizeof(struct _fpstate) + size_extended; - -#ifdef CONFIG_IA32_EMULATION - sig_xstate_ia32_size = sizeof(struct _fpstate_ia32) + size_extended; -#endif - - memset(&fx_sw_reserved, 0, sizeof(fx_sw_reserved)); + if (config_enabled(CONFIG_X86_32)) + size += fsave_header_size; fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; - fx_sw_reserved.extended_size = sig_xstate_size; + fx_sw_reserved.extended_size = size; fx_sw_reserved.xstate_bv = pcntxt_mask; fx_sw_reserved.xstate_size = xstate_size; -#ifdef CONFIG_IA32_EMULATION - memcpy(&fx_sw_reserved_ia32, &fx_sw_reserved, - sizeof(struct _fpx_sw_bytes)); - fx_sw_reserved_ia32.extended_size = sig_xstate_ia32_size; -#endif -} -#ifdef CONFIG_X86_64 -unsigned int sig_xstate_size = sizeof(struct _fpstate); -#endif + if (config_enabled(CONFIG_IA32_EMULATION)) { + fx_sw_reserved_ia32 = fx_sw_reserved; + fx_sw_reserved_ia32.extended_size += fsave_header_size; + } +} /* * Enable the extended processor state save/restore feature @@ -384,19 +482,21 @@ static void __init setup_xstate_features(void) /* * setup the xstate image representing the init state */ -static void __init setup_xstate_init(void) +static void __init setup_init_fpu_buf(void) { - setup_xstate_features(); - /* * Setup init_xstate_buf to represent the init state of * all the features managed by the xsave */ init_xstate_buf = alloc_bootmem_align(xstate_size, __alignof__(struct xsave_struct)); - init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT; + fx_finit(&init_xstate_buf->i387); + + if (!cpu_has_xsave) + return; + + setup_xstate_features(); - clts(); /* * Init all the features state with header_bv being 0x0 */ @@ -406,9 +506,21 @@ static void __init setup_xstate_init(void) * of any feature which is not represented by all zero's. */ xsave_state(init_xstate_buf, -1); - stts(); } +static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; +static int __init eager_fpu_setup(char *s) +{ + if (!strcmp(s, "on")) + eagerfpu = ENABLE; + else if (!strcmp(s, "off")) + eagerfpu = DISABLE; + else if (!strcmp(s, "auto")) + eagerfpu = AUTO; + return 1; +} +__setup("eagerfpu=", eager_fpu_setup); + /* * Enable and initialize the xsave feature. */ @@ -445,8 +557,11 @@ static void __init xstate_enable_boot_cpu(void) update_regset_xstate_info(xstate_size, pcntxt_mask); prepare_fx_sw_frame(); + setup_init_fpu_buf(); - setup_xstate_init(); + /* Auto enable eagerfpu for xsaveopt */ + if (cpu_has_xsaveopt && eagerfpu != DISABLE) + eagerfpu = ENABLE; pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n", pcntxt_mask, xstate_size); @@ -471,3 +586,43 @@ void __cpuinit xsave_init(void) next_func = xstate_enable; this_func(); } + +static inline void __init eager_fpu_init_bp(void) +{ + current->thread.fpu.state = + alloc_bootmem_align(xstate_size, __alignof__(struct xsave_struct)); + if (!init_xstate_buf) + setup_init_fpu_buf(); +} + +void __cpuinit eager_fpu_init(void) +{ + static __refdata void (*boot_func)(void) = eager_fpu_init_bp; + + clear_used_math(); + current_thread_info()->status = 0; + + if (eagerfpu == ENABLE) + setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); + + if (!cpu_has_eager_fpu) { + stts(); + return; + } + + if (boot_func) { + boot_func(); + boot_func = NULL; + } + + /* + * This is same as math_state_restore(). But use_xsave() is + * not yet patched to use math_state_restore(). + */ + init_fpu(current); + __thread_fpu_begin(current); + if (cpu_has_xsave) + xrstor_state(init_xstate_buf, -1); + else + fxrstor_checking(&init_xstate_buf->i387); +} diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 97d9a9914ba..a3b57a27be8 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -475,13 +475,26 @@ register_address(struct x86_emulate_ctxt *ctxt, unsigned long reg) return address_mask(ctxt, reg); } +static void masked_increment(ulong *reg, ulong mask, int inc) +{ + assign_masked(reg, *reg + inc, mask); +} + static inline void register_address_increment(struct x86_emulate_ctxt *ctxt, unsigned long *reg, int inc) { + ulong mask; + if (ctxt->ad_bytes == sizeof(unsigned long)) - *reg += inc; + mask = ~0UL; else - *reg = (*reg & ~ad_mask(ctxt)) | ((*reg + inc) & ad_mask(ctxt)); + mask = ad_mask(ctxt); + masked_increment(reg, mask, inc); +} + +static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc) +{ + masked_increment(&ctxt->regs[VCPU_REGS_RSP], stack_mask(ctxt), inc); } static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) @@ -1522,8 +1535,8 @@ static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes) { struct segmented_address addr; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], -bytes); - addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]); + rsp_increment(ctxt, -bytes); + addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt); addr.seg = VCPU_SREG_SS; return segmented_write(ctxt, addr, data, bytes); @@ -1542,13 +1555,13 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt, int rc; struct segmented_address addr; - addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]); + addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt); addr.seg = VCPU_SREG_SS; rc = segmented_read(ctxt, addr, dest, len); if (rc != X86EMUL_CONTINUE) return rc; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], len); + rsp_increment(ctxt, len); return rc; } @@ -1688,8 +1701,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) while (reg >= VCPU_REGS_RAX) { if (reg == VCPU_REGS_RSP) { - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], - ctxt->op_bytes); + rsp_increment(ctxt, ctxt->op_bytes); --reg; } @@ -2825,7 +2837,7 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], ctxt->src.val); + rsp_increment(ctxt, ctxt->src.val); return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 1df8fb9e1d5..9fc9aa7ac70 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -316,6 +316,11 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) addr &= 1; if (addr == 0) { if (val & 0x10) { + u8 edge_irr = s->irr & ~s->elcr; + int i; + bool found = false; + struct kvm_vcpu *vcpu; + s->init4 = val & 1; s->last_irr = 0; s->irr &= s->elcr; @@ -333,6 +338,18 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) if (val & 0x08) pr_pic_unimpl( "level sensitive irq not supported"); + + kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm) + if (kvm_apic_accept_pic_intr(vcpu)) { + found = true; + break; + } + + + if (found) + for (irq = 0; irq < PIC_NUM_PINS/2; irq++) + if (edge_irr & (1 << irq)) + pic_clear_isr(s, irq); } else if (val & 0x08) { if (val & 0x04) s->poll = 1; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 01ca0042393..7fbd0d273ea 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4113,16 +4113,21 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) LIST_HEAD(invalid_list); /* + * Never scan more than sc->nr_to_scan VM instances. + * Will not hit this condition practically since we do not try + * to shrink more than one VM and it is very unlikely to see + * !n_used_mmu_pages so many times. + */ + if (!nr_to_scan--) + break; + /* * n_used_mmu_pages is accessed without holding kvm->mmu_lock * here. We may skip a VM instance errorneosly, but we do not * want to shrink a VM that only started to populate its MMU * anyway. */ - if (kvm->arch.n_used_mmu_pages > 0) { - if (!nr_to_scan--) - break; + if (!kvm->arch.n_used_mmu_pages) continue; - } idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index a71faf727ff..bca63f04dcc 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -183,95 +183,6 @@ TRACE_EVENT(kvm_apic, #define KVM_ISA_VMX 1 #define KVM_ISA_SVM 2 -#define VMX_EXIT_REASONS \ - { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ - { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ - { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ - { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \ - { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ - { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ - { EXIT_REASON_CPUID, "CPUID" }, \ - { EXIT_REASON_HLT, "HLT" }, \ - { EXIT_REASON_INVLPG, "INVLPG" }, \ - { EXIT_REASON_RDPMC, "RDPMC" }, \ - { EXIT_REASON_RDTSC, "RDTSC" }, \ - { EXIT_REASON_VMCALL, "VMCALL" }, \ - { EXIT_REASON_VMCLEAR, "VMCLEAR" }, \ - { EXIT_REASON_VMLAUNCH, "VMLAUNCH" }, \ - { EXIT_REASON_VMPTRLD, "VMPTRLD" }, \ - { EXIT_REASON_VMPTRST, "VMPTRST" }, \ - { EXIT_REASON_VMREAD, "VMREAD" }, \ - { EXIT_REASON_VMRESUME, "VMRESUME" }, \ - { EXIT_REASON_VMWRITE, "VMWRITE" }, \ - { EXIT_REASON_VMOFF, "VMOFF" }, \ - { EXIT_REASON_VMON, "VMON" }, \ - { EXIT_REASON_CR_ACCESS, "CR_ACCESS" }, \ - { EXIT_REASON_DR_ACCESS, "DR_ACCESS" }, \ - { EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \ - { EXIT_REASON_MSR_READ, "MSR_READ" }, \ - { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \ - { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \ - { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \ - { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \ - { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ - { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \ - { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \ - { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \ - { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \ - { EXIT_REASON_WBINVD, "WBINVD" } - -#define SVM_EXIT_REASONS \ - { SVM_EXIT_READ_CR0, "read_cr0" }, \ - { SVM_EXIT_READ_CR3, "read_cr3" }, \ - { SVM_EXIT_READ_CR4, "read_cr4" }, \ - { SVM_EXIT_READ_CR8, "read_cr8" }, \ - { SVM_EXIT_WRITE_CR0, "write_cr0" }, \ - { SVM_EXIT_WRITE_CR3, "write_cr3" }, \ - { SVM_EXIT_WRITE_CR4, "write_cr4" }, \ - { SVM_EXIT_WRITE_CR8, "write_cr8" }, \ - { SVM_EXIT_READ_DR0, "read_dr0" }, \ - { SVM_EXIT_READ_DR1, "read_dr1" }, \ - { SVM_EXIT_READ_DR2, "read_dr2" }, \ - { SVM_EXIT_READ_DR3, "read_dr3" }, \ - { SVM_EXIT_WRITE_DR0, "write_dr0" }, \ - { SVM_EXIT_WRITE_DR1, "write_dr1" }, \ - { SVM_EXIT_WRITE_DR2, "write_dr2" }, \ - { SVM_EXIT_WRITE_DR3, "write_dr3" }, \ - { SVM_EXIT_WRITE_DR5, "write_dr5" }, \ - { SVM_EXIT_WRITE_DR7, "write_dr7" }, \ - { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, \ - { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, \ - { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \ - { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \ - { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \ - { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \ - { SVM_EXIT_INTR, "interrupt" }, \ - { SVM_EXIT_NMI, "nmi" }, \ - { SVM_EXIT_SMI, "smi" }, \ - { SVM_EXIT_INIT, "init" }, \ - { SVM_EXIT_VINTR, "vintr" }, \ - { SVM_EXIT_CPUID, "cpuid" }, \ - { SVM_EXIT_INVD, "invd" }, \ - { SVM_EXIT_HLT, "hlt" }, \ - { SVM_EXIT_INVLPG, "invlpg" }, \ - { SVM_EXIT_INVLPGA, "invlpga" }, \ - { SVM_EXIT_IOIO, "io" }, \ - { SVM_EXIT_MSR, "msr" }, \ - { SVM_EXIT_TASK_SWITCH, "task_switch" }, \ - { SVM_EXIT_SHUTDOWN, "shutdown" }, \ - { SVM_EXIT_VMRUN, "vmrun" }, \ - { SVM_EXIT_VMMCALL, "hypercall" }, \ - { SVM_EXIT_VMLOAD, "vmload" }, \ - { SVM_EXIT_VMSAVE, "vmsave" }, \ - { SVM_EXIT_STGI, "stgi" }, \ - { SVM_EXIT_CLGI, "clgi" }, \ - { SVM_EXIT_SKINIT, "skinit" }, \ - { SVM_EXIT_WBINVD, "wbinvd" }, \ - { SVM_EXIT_MONITOR, "monitor" }, \ - { SVM_EXIT_MWAIT, "mwait" }, \ - { SVM_EXIT_XSETBV, "xsetbv" }, \ - { SVM_EXIT_NPF, "npf" } - /* * Tracepoint for kvm guest exit: */ diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c39b60707e0..851aa7c3b89 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1488,20 +1488,17 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) loadsegment(ds, vmx->host_state.ds_sel); loadsegment(es, vmx->host_state.es_sel); } -#else - /* - * The sysexit path does not restore ds/es, so we must set them to - * a reasonable value ourselves. - */ - loadsegment(ds, __USER_DS); - loadsegment(es, __USER_DS); #endif reload_tss(); #ifdef CONFIG_X86_64 wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif - if (user_has_fpu()) - clts(); + /* + * If the FPU is not active (through the host task or + * the guest vcpu), then restore the cr0.TS bit. + */ + if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded) + stts(); load_gdt(&__get_cpu_var(host_gdt)); } @@ -3626,6 +3623,7 @@ static void seg_setup(int seg) static int alloc_apic_access_page(struct kvm *kvm) { + struct page *page; struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; @@ -3640,7 +3638,13 @@ static int alloc_apic_access_page(struct kvm *kvm) if (r) goto out; - kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00); + page = gfn_to_page(kvm, 0xfee00); + if (is_error_page(page)) { + r = -EFAULT; + goto out; + } + + kvm->arch.apic_access_page = page; out: mutex_unlock(&kvm->slots_lock); return r; @@ -3648,6 +3652,7 @@ out: static int alloc_identity_pagetable(struct kvm *kvm) { + struct page *page; struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; @@ -3663,8 +3668,13 @@ static int alloc_identity_pagetable(struct kvm *kvm) if (r) goto out; - kvm->arch.ept_identity_pagetable = gfn_to_page(kvm, - kvm->arch.ept_identity_map_addr >> PAGE_SHIFT); + page = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT); + if (is_error_page(page)) { + r = -EFAULT; + goto out; + } + + kvm->arch.ept_identity_pagetable = page; out: mutex_unlock(&kvm->slots_lock); return r; @@ -3737,7 +3747,7 @@ static void vmx_set_constant_host_state(void) unsigned long tmpl; struct desc_ptr dt; - vmcs_writel(HOST_CR0, read_cr0() | X86_CR0_TS); /* 22.2.3 */ + vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS); /* 22.2.3 */ vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */ vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */ @@ -4537,7 +4547,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) vcpu->run->exit_reason = KVM_EXIT_SET_TPR; return 0; } - }; + } break; case 2: /* clts */ handle_clts(vcpu); @@ -6370,6 +6380,19 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif ); +#ifndef CONFIG_X86_64 + /* + * The sysexit path does not restore ds/es, so we must set them to + * a reasonable value ourselves. + * + * We can't defer this to vmx_load_host_state() since that function + * may be executed in interrupt context, which saves and restore segments + * around it, nullifying its effect. + */ + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); +#endif + vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) | (1 << VCPU_EXREG_RFLAGS) | (1 << VCPU_EXREG_CPL) @@ -6569,7 +6592,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) /* Exposing INVPCID only when PCID is exposed */ best = kvm_find_cpuid_entry(vcpu, 0x7, 0); if (vmx_invpcid_supported() && - best && (best->ecx & bit(X86_FEATURE_INVPCID)) && + best && (best->ebx & bit(X86_FEATURE_INVPCID)) && guest_cpuid_has_pcid(vcpu)) { exec_control |= SECONDARY_EXEC_ENABLE_INVPCID; vmcs_write32(SECONDARY_VM_EXEC_CONTROL, @@ -6579,7 +6602,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); if (best) - best->ecx &= ~bit(X86_FEATURE_INVPCID); + best->ebx &= ~bit(X86_FEATURE_INVPCID); } } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 59b59508ff0..1f09552572f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -806,7 +806,7 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc); * kvm-specific. Those are put in the beginning of the list. */ -#define KVM_SAVE_MSRS_BEGIN 9 +#define KVM_SAVE_MSRS_BEGIN 10 static u32 msrs_to_save[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, @@ -925,6 +925,10 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) */ getboottime(&boot); + if (kvm->arch.kvmclock_offset) { + struct timespec ts = ns_to_timespec(kvm->arch.kvmclock_offset); + boot = timespec_sub(boot, ts); + } wc.sec = boot.tv_sec; wc.nsec = boot.tv_nsec; wc.version = version; @@ -1996,6 +2000,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_KVM_STEAL_TIME: data = vcpu->arch.st.msr_val; break; + case MSR_KVM_PV_EOI_EN: + data = vcpu->arch.pv_eoi.msr_val; + break; case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: case MSR_IA32_MCG_CAP: @@ -5106,17 +5113,20 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) !kvm_event_needs_reinjection(vcpu); } -static void vapic_enter(struct kvm_vcpu *vcpu) +static int vapic_enter(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct page *page; if (!apic || !apic->vapic_addr) - return; + return 0; page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); + if (is_error_page(page)) + return -EFAULT; vcpu->arch.apic->vapic_page = page; + return 0; } static void vapic_exit(struct kvm_vcpu *vcpu) @@ -5423,7 +5433,11 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) } vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - vapic_enter(vcpu); + r = vapic_enter(vcpu); + if (r) { + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + return r; + } r = 1; while (r > 0) { @@ -5965,7 +5979,7 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) */ kvm_put_guest_xcr0(vcpu); vcpu->guest_fpu_loaded = 1; - unlazy_fpu(current); + __kernel_fpu_begin(); fpu_restore_checking(&vcpu->arch.guest_fpu); trace_kvm_fpu(1); } @@ -5979,6 +5993,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) vcpu->guest_fpu_loaded = 0; fpu_save_init(&vcpu->arch.guest_fpu); + __kernel_fpu_end(); ++vcpu->stat.fpu_reload; kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); trace_kvm_fpu(0); diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 5b2995f4557..a30ca15be21 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -17,6 +17,7 @@ #include <asm/cpufeature.h> #include <asm/alternative-asm.h> #include <asm/asm.h> +#include <asm/smap.h> /* * By placing feature2 after feature1 in altinstructions section, we logically @@ -130,6 +131,7 @@ ENDPROC(bad_from_user) */ ENTRY(copy_user_generic_unrolled) CFI_STARTPROC + ASM_STAC cmpl $8,%edx jb 20f /* less then 8 bytes, go to byte copy loop */ ALIGN_DESTINATION @@ -177,6 +179,7 @@ ENTRY(copy_user_generic_unrolled) decl %ecx jnz 21b 23: xor %eax,%eax + ASM_CLAC ret .section .fixup,"ax" @@ -232,6 +235,7 @@ ENDPROC(copy_user_generic_unrolled) */ ENTRY(copy_user_generic_string) CFI_STARTPROC + ASM_STAC andl %edx,%edx jz 4f cmpl $8,%edx @@ -246,6 +250,7 @@ ENTRY(copy_user_generic_string) 3: rep movsb 4: xorl %eax,%eax + ASM_CLAC ret .section .fixup,"ax" @@ -273,12 +278,14 @@ ENDPROC(copy_user_generic_string) */ ENTRY(copy_user_enhanced_fast_string) CFI_STARTPROC + ASM_STAC andl %edx,%edx jz 2f movl %edx,%ecx 1: rep movsb 2: xorl %eax,%eax + ASM_CLAC ret .section .fixup,"ax" diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S index cacddc7163e..6a4f43c2d9e 100644 --- a/arch/x86/lib/copy_user_nocache_64.S +++ b/arch/x86/lib/copy_user_nocache_64.S @@ -15,6 +15,7 @@ #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/asm.h> +#include <asm/smap.h> .macro ALIGN_DESTINATION #ifdef FIX_ALIGNMENT @@ -48,6 +49,7 @@ */ ENTRY(__copy_user_nocache) CFI_STARTPROC + ASM_STAC cmpl $8,%edx jb 20f /* less then 8 bytes, go to byte copy loop */ ALIGN_DESTINATION @@ -95,6 +97,7 @@ ENTRY(__copy_user_nocache) decl %ecx jnz 21b 23: xorl %eax,%eax + ASM_CLAC sfence ret diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index b33b1fb1e6d..156b9c80467 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -33,6 +33,7 @@ #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/asm.h> +#include <asm/smap.h> .text ENTRY(__get_user_1) @@ -40,8 +41,10 @@ ENTRY(__get_user_1) GET_THREAD_INFO(%_ASM_DX) cmp TI_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + ASM_STAC 1: movzb (%_ASM_AX),%edx xor %eax,%eax + ASM_CLAC ret CFI_ENDPROC ENDPROC(__get_user_1) @@ -53,8 +56,10 @@ ENTRY(__get_user_2) GET_THREAD_INFO(%_ASM_DX) cmp TI_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + ASM_STAC 2: movzwl -1(%_ASM_AX),%edx xor %eax,%eax + ASM_CLAC ret CFI_ENDPROC ENDPROC(__get_user_2) @@ -66,8 +71,10 @@ ENTRY(__get_user_4) GET_THREAD_INFO(%_ASM_DX) cmp TI_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + ASM_STAC 3: mov -3(%_ASM_AX),%edx xor %eax,%eax + ASM_CLAC ret CFI_ENDPROC ENDPROC(__get_user_4) @@ -80,8 +87,10 @@ ENTRY(__get_user_8) GET_THREAD_INFO(%_ASM_DX) cmp TI_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + ASM_STAC 4: movq -7(%_ASM_AX),%_ASM_DX xor %eax,%eax + ASM_CLAC ret CFI_ENDPROC ENDPROC(__get_user_8) @@ -91,6 +100,7 @@ bad_get_user: CFI_STARTPROC xor %edx,%edx mov $(-EFAULT),%_ASM_AX + ASM_CLAC ret CFI_ENDPROC END(bad_get_user) diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index 7f951c8f76c..fc6ba17a7ee 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -15,6 +15,7 @@ #include <asm/thread_info.h> #include <asm/errno.h> #include <asm/asm.h> +#include <asm/smap.h> /* @@ -31,7 +32,8 @@ #define ENTER CFI_STARTPROC ; \ GET_THREAD_INFO(%_ASM_BX) -#define EXIT ret ; \ +#define EXIT ASM_CLAC ; \ + ret ; \ CFI_ENDPROC .text @@ -39,6 +41,7 @@ ENTRY(__put_user_1) ENTER cmp TI_addr_limit(%_ASM_BX),%_ASM_CX jae bad_put_user + ASM_STAC 1: movb %al,(%_ASM_CX) xor %eax,%eax EXIT @@ -50,6 +53,7 @@ ENTRY(__put_user_2) sub $1,%_ASM_BX cmp %_ASM_BX,%_ASM_CX jae bad_put_user + ASM_STAC 2: movw %ax,(%_ASM_CX) xor %eax,%eax EXIT @@ -61,6 +65,7 @@ ENTRY(__put_user_4) sub $3,%_ASM_BX cmp %_ASM_BX,%_ASM_CX jae bad_put_user + ASM_STAC 3: movl %eax,(%_ASM_CX) xor %eax,%eax EXIT @@ -72,6 +77,7 @@ ENTRY(__put_user_8) sub $7,%_ASM_BX cmp %_ASM_BX,%_ASM_CX jae bad_put_user + ASM_STAC 4: mov %_ASM_AX,(%_ASM_CX) #ifdef CONFIG_X86_32 5: movl %edx,4(%_ASM_CX) diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 1781b2f950e..98f6d6b68f5 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -42,10 +42,11 @@ do { \ int __d0; \ might_fault(); \ __asm__ __volatile__( \ + ASM_STAC "\n" \ "0: rep; stosl\n" \ " movl %2,%0\n" \ "1: rep; stosb\n" \ - "2:\n" \ + "2: " ASM_CLAC "\n" \ ".section .fixup,\"ax\"\n" \ "3: lea 0(%2,%0,4),%0\n" \ " jmp 2b\n" \ @@ -626,10 +627,12 @@ survive: return n; } #endif + stac(); if (movsl_is_ok(to, from, n)) __copy_user(to, from, n); else n = __copy_user_intel(to, from, n); + clac(); return n; } EXPORT_SYMBOL(__copy_to_user_ll); @@ -637,10 +640,12 @@ EXPORT_SYMBOL(__copy_to_user_ll); unsigned long __copy_from_user_ll(void *to, const void __user *from, unsigned long n) { + stac(); if (movsl_is_ok(to, from, n)) __copy_user_zeroing(to, from, n); else n = __copy_user_zeroing_intel(to, from, n); + clac(); return n; } EXPORT_SYMBOL(__copy_from_user_ll); @@ -648,11 +653,13 @@ EXPORT_SYMBOL(__copy_from_user_ll); unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from, unsigned long n) { + stac(); if (movsl_is_ok(to, from, n)) __copy_user(to, from, n); else n = __copy_user_intel((void __user *)to, (const void *)from, n); + clac(); return n; } EXPORT_SYMBOL(__copy_from_user_ll_nozero); @@ -660,6 +667,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nozero); unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from, unsigned long n) { + stac(); #ifdef CONFIG_X86_INTEL_USERCOPY if (n > 64 && cpu_has_xmm2) n = __copy_user_zeroing_intel_nocache(to, from, n); @@ -668,6 +676,7 @@ unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from, #else __copy_user_zeroing(to, from, n); #endif + clac(); return n; } EXPORT_SYMBOL(__copy_from_user_ll_nocache); @@ -675,6 +684,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache); unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from, unsigned long n) { + stac(); #ifdef CONFIG_X86_INTEL_USERCOPY if (n > 64 && cpu_has_xmm2) n = __copy_user_intel_nocache(to, from, n); @@ -683,6 +693,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr #else __copy_user(to, from, n); #endif + clac(); return n; } EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero); diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index e5b130bc2d0..05928aae911 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -18,6 +18,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size) might_fault(); /* no memory constraint because it doesn't change any memory gcc knows about */ + stac(); asm volatile( " testq %[size8],%[size8]\n" " jz 4f\n" @@ -40,6 +41,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size) : [size8] "=&c"(size), [dst] "=&D" (__d0) : [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr), [zero] "r" (0UL), [eight] "r" (8UL)); + clac(); return size; } EXPORT_SYMBOL(__clear_user); @@ -82,5 +84,6 @@ copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest) for (c = 0, zero_len = len; zerorest && zero_len; --zero_len) if (__put_user_nocheck(c, to++, sizeof(char))) break; + clac(); return len; } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 76dcd9d8e0b..a530b230e7d 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -18,6 +18,7 @@ #include <asm/pgalloc.h> /* pgd_*(), ... */ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ #include <asm/fixmap.h> /* VSYSCALL_START */ +#include <asm/rcu.h> /* exception_enter(), ... */ /* * Page fault error code bits: @@ -995,13 +996,24 @@ static int fault_in_kernel_space(unsigned long address) return address >= TASK_SIZE_MAX; } +static inline bool smap_violation(int error_code, struct pt_regs *regs) +{ + if (error_code & PF_USER) + return false; + + if (!user_mode_vm(regs) && (regs->flags & X86_EFLAGS_AC)) + return false; + + return true; +} + /* * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate * routines. */ -dotraplinkage void __kprobes -do_page_fault(struct pt_regs *regs, unsigned long error_code) +static void __kprobes +__do_page_fault(struct pt_regs *regs, unsigned long error_code) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -1088,6 +1100,13 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) if (unlikely(error_code & PF_RSVD)) pgtable_bad(regs, error_code, address); + if (static_cpu_has(X86_FEATURE_SMAP)) { + if (unlikely(smap_violation(error_code, regs))) { + bad_area_nosemaphore(regs, error_code, address); + return; + } + } + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); /* @@ -1209,3 +1228,11 @@ good_area: up_read(&mm->mmap_sem); } + +dotraplinkage void __kprobes +do_page_fault(struct pt_regs *regs, unsigned long error_code) +{ + exception_enter(regs); + __do_page_fault(regs, error_code); + exception_exit(regs); +} diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index f6679a7fb8c..b91e4851242 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -56,9 +56,16 @@ static int vma_shareable(struct vm_area_struct *vma, unsigned long addr) } /* - * search for a shareable pmd page for hugetlb. + * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() + * and returns the corresponding pte. While this is not necessary for the + * !shared pmd case because we can allocate the pmd later as well, it makes the + * code much cleaner. pmd allocation is essential for the shared case because + * pud has to be populated inside the same i_mmap_mutex section - otherwise + * racing tasks could either miss the sharing (see huge_pte_offset) or select a + * bad pmd for sharing. */ -static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +static pte_t * +huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) { struct vm_area_struct *vma = find_vma(mm, addr); struct address_space *mapping = vma->vm_file->f_mapping; @@ -68,9 +75,10 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) struct vm_area_struct *svma; unsigned long saddr; pte_t *spte = NULL; + pte_t *pte; if (!vma_shareable(vma, addr)) - return; + return (pte_t *)pmd_alloc(mm, pud, addr); mutex_lock(&mapping->i_mmap_mutex); vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) { @@ -97,7 +105,9 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) put_page(virt_to_page(spte)); spin_unlock(&mm->page_table_lock); out: + pte = (pte_t *)pmd_alloc(mm, pud, addr); mutex_unlock(&mapping->i_mmap_mutex); + return pte; } /* @@ -142,8 +152,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, } else { BUG_ON(sz != PMD_SIZE); if (pud_none(*pud)) - huge_pmd_share(mm, addr, pud); - pte = (pte_t *) pmd_alloc(mm, pud, addr); + pte = huge_pmd_share(mm, addr, pud); + else + pte = (pte_t *)pmd_alloc(mm, pud, addr); } } BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte)); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index e0e6990723e..ab1f6a93b52 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -319,7 +319,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, */ int devmem_is_allowed(unsigned long pagenr) { - if (pagenr <= 256) + if (pagenr < 256) return 1; if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) return 0; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 575d86f85ce..11a58001b4c 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -445,10 +445,10 @@ static inline void permanent_kmaps_init(pgd_t *pgd_base) } #endif /* CONFIG_HIGHMEM */ -void __init native_pagetable_setup_start(pgd_t *base) +void __init native_pagetable_init(void) { unsigned long pfn, va; - pgd_t *pgd; + pgd_t *pgd, *base = swapper_pg_dir; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -475,10 +475,7 @@ void __init native_pagetable_setup_start(pgd_t *base) pte_clear(NULL, va, pte); } paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT); -} - -void __init native_pagetable_setup_done(pgd_t *base) -{ + paging_init(); } /* @@ -493,7 +490,7 @@ void __init native_pagetable_setup_done(pgd_t *base) * If we're booting paravirtualized under a hypervisor, then there are * more options: we may already be running PAE, and the pagetable may * or may not be based in swapper_pg_dir. In any case, - * paravirt_pagetable_setup_start() will set up swapper_pg_dir + * paravirt_pagetable_init() will set up swapper_pg_dir * appropriately for the rest of the initialization to work. * * In general, pagetable_init() assumes that the pagetable may already @@ -712,7 +709,7 @@ static void __init test_wp_bit(void) "Checking if this processor honours the WP bit even in supervisor mode..."); /* Any page-aligned address will do, the test is non-destructive */ - __set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_READONLY); + __set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_KERNEL_RO); boot_cpu_data.wp_works_ok = do_test_wp_bit(); clear_fixmap(FIX_WP_TEST); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 931930a9616..a718e0d2350 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -919,13 +919,11 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, /* * On success we use clflush, when the CPU supports it to - * avoid the wbindv. If the CPU does not support it, in the - * error case, and during early boot (for EFI) we fall back - * to cpa_flush_all (which uses wbinvd): + * avoid the wbindv. If the CPU does not support it and in the + * error case we fall back to cpa_flush_all (which uses + * wbindv): */ - if (early_boot_irqs_disabled) - __cpa_flush_all((void *)(long)cache); - else if (!ret && cpu_has_clflush) { + if (!ret && cpu_has_clflush) { if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) { cpa_flush_array(addr, numpages, cache, cpa.flags, pages); diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 4599c3e8bcb..4ddf497ca65 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -142,23 +142,23 @@ static inline int save_add_info(void) {return 0;} #endif /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ -void __init +int __init acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) { u64 start, end; int node, pxm; if (srat_disabled()) - return; + return -1; if (ma->header.length != sizeof(struct acpi_srat_mem_affinity)) { bad_srat(); - return; + return -1; } if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0) - return; + return -1; if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info()) - return; + return -1; start = ma->base_address; end = start + ma->length; pxm = ma->proximity_domain; @@ -168,12 +168,12 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains.\n"); bad_srat(); - return; + return -1; } if (numa_add_memblk(node, start, end) < 0) { bad_srat(); - return; + return -1; } node_set(node, numa_nodes_parsed); @@ -181,6 +181,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n", node, pxm, (unsigned long long) start, (unsigned long long) end - 1); + return 0; } void __init acpi_numa_arch_fixup(void) {} diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 613cd83e8c0..0777f042e40 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -98,6 +98,8 @@ static void flush_tlb_func(void *info) { struct flush_tlb_info *f = info; + inc_irq_stat(irq_tlb_count); + if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; @@ -320,7 +322,7 @@ static ssize_t tlbflush_write_file(struct file *file, if (kstrtos8(buf, 0, &shift)) return -EINVAL; - if (shift > 64) + if (shift < -1 || shift >= BITS_PER_LONG) return -EINVAL; tlb_flushall_shift = shift; diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 505acdd6d60..192397c9860 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -305,7 +305,6 @@ setup_resource(struct acpi_resource *acpi_res, void *data) res->flags = flags; res->start = start; res->end = end; - res->child = NULL; if (!pci_use_crs) { dev_printk(KERN_DEBUG, &info->bridge->dev, @@ -434,7 +433,7 @@ probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device, size = sizeof(*info->res) * info->res_num; info->res_num = 0; - info->res = kmalloc(size, GFP_KERNEL); + info->res = kzalloc(size, GFP_KERNEL); if (!info->res) return; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 937bcece700..704b9ec043d 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -585,7 +585,7 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header) while (i >= sizeof(struct acpi_mcfg_allocation)) { entries++; i -= sizeof(struct acpi_mcfg_allocation); - }; + } if (entries == 0) { pr_err(PREFIX "MMCONFIG has no entries\n"); return -ENODEV; diff --git a/arch/x86/pci/visws.c b/arch/x86/pci/visws.c index 6f2f8eeed17..3e6d2a6db86 100644 --- a/arch/x86/pci/visws.c +++ b/arch/x86/pci/visws.c @@ -62,11 +62,6 @@ out: return irq; } -void __init pcibios_update_irq(struct pci_dev *dev, int irq) -{ - pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq); -} - int __init pci_visws_init(void) { pcibios_enable_irq = &pci_visws_enable_irq; diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile index 73b8be0f367..6db1cc4c753 100644 --- a/arch/x86/platform/efi/Makefile +++ b/arch/x86/platform/efi/Makefile @@ -1 +1,2 @@ obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o +obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c new file mode 100644 index 00000000000..f6a0c1b8e51 --- /dev/null +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -0,0 +1,76 @@ +/* + * Copyright 2012 Intel Corporation + * Author: Josh Triplett <josh@joshtriplett.org> + * + * Based on the bgrt driver: + * Copyright 2012 Red Hat, Inc <mjg@redhat.com> + * Author: Matthew Garrett + * + * 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/acpi.h> +#include <linux/efi.h> +#include <linux/efi-bgrt.h> + +struct acpi_table_bgrt *bgrt_tab; +void *bgrt_image; +size_t bgrt_image_size; + +struct bmp_header { + u16 id; + u32 size; +} __packed; + +void efi_bgrt_init(void) +{ + acpi_status status; + void __iomem *image; + bool ioremapped = false; + struct bmp_header bmp_header; + + if (acpi_disabled) + return; + + status = acpi_get_table("BGRT", 0, + (struct acpi_table_header **)&bgrt_tab); + if (ACPI_FAILURE(status)) + return; + + if (bgrt_tab->version != 1) + return; + if (bgrt_tab->image_type != 0 || !bgrt_tab->image_address) + return; + + image = efi_lookup_mapped_addr(bgrt_tab->image_address); + if (!image) { + image = ioremap(bgrt_tab->image_address, sizeof(bmp_header)); + ioremapped = true; + if (!image) + return; + } + + memcpy_fromio(&bmp_header, image, sizeof(bmp_header)); + if (ioremapped) + iounmap(image); + bgrt_image_size = bmp_header.size; + + bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL); + if (!bgrt_image) + return; + + if (ioremapped) { + image = ioremap(bgrt_tab->image_address, bmp_header.size); + if (!image) { + kfree(bgrt_image); + bgrt_image = NULL; + return; + } + } + + memcpy_fromio(bgrt_image, image, bgrt_image_size); + if (ioremapped) + iounmap(image); +} diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 2dc29f51e75..aded2a91162 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -31,6 +31,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/efi.h> +#include <linux/efi-bgrt.h> #include <linux/export.h> #include <linux/bootmem.h> #include <linux/memblock.h> @@ -234,7 +235,22 @@ static efi_status_t __init phys_efi_set_virtual_address_map( return status; } -static int efi_set_rtc_mmss(unsigned long nowtime) +static efi_status_t __init phys_efi_get_time(efi_time_t *tm, + efi_time_cap_t *tc) +{ + unsigned long flags; + efi_status_t status; + + spin_lock_irqsave(&rtc_lock, flags); + efi_call_phys_prelog(); + status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm), + virt_to_phys(tc)); + efi_call_phys_epilog(); + spin_unlock_irqrestore(&rtc_lock, flags); + return status; +} + +int efi_set_rtc_mmss(unsigned long nowtime) { int real_seconds, real_minutes; efi_status_t status; @@ -263,7 +279,7 @@ static int efi_set_rtc_mmss(unsigned long nowtime) return 0; } -static unsigned long efi_get_time(void) +unsigned long efi_get_time(void) { efi_status_t status; efi_time_t eft; @@ -404,10 +420,21 @@ void __init efi_reserve_boot_services(void) } } -static void __init efi_free_boot_services(void) +static void __init efi_unmap_memmap(void) +{ + if (memmap.map) { + early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size); + memmap.map = NULL; + } +} + +void __init efi_free_boot_services(void) { void *p; + if (!efi_native) + return; + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { efi_memory_desc_t *md = p; unsigned long long start = md->phys_addr; @@ -423,6 +450,8 @@ static void __init efi_free_boot_services(void) free_bootmem_late(start, size); } + + efi_unmap_memmap(); } static int __init efi_systab_init(void *phys) @@ -606,13 +635,18 @@ static int __init efi_runtime_init(void) } /* * We will only need *early* access to the following - * EFI runtime service before set_virtual_address_map + * two EFI runtime services before set_virtual_address_map * is invoked. */ + efi_phys.get_time = (efi_get_time_t *)runtime->get_time; efi_phys.set_virtual_address_map = (efi_set_virtual_address_map_t *) runtime->set_virtual_address_map; - + /* + * Make efi_get_time can be called before entering + * virtual mode. + */ + efi.get_time = phys_efi_get_time; early_iounmap(runtime, sizeof(efi_runtime_services_t)); return 0; @@ -700,16 +734,23 @@ void __init efi_init(void) efi_enabled = 0; return; } +#ifdef CONFIG_X86_32 if (efi_native) { x86_platform.get_wallclock = efi_get_time; x86_platform.set_wallclock = efi_set_rtc_mmss; } +#endif #if EFI_DEBUG print_efi_memmap(); #endif } +void __init efi_late_init(void) +{ + efi_bgrt_init(); +} + void __init efi_set_executable(efi_memory_desc_t *md, bool executable) { u64 addr, npages; @@ -742,6 +783,34 @@ static void __init runtime_code_page_mkexec(void) } /* + * We can't ioremap data in EFI boot services RAM, because we've already mapped + * it as RAM. So, look it up in the existing EFI memory map instead. Only + * callable after efi_enter_virtual_mode and before efi_free_boot_services. + */ +void __iomem *efi_lookup_mapped_addr(u64 phys_addr) +{ + void *p; + if (WARN_ON(!memmap.map)) + return NULL; + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + efi_memory_desc_t *md = p; + u64 size = md->num_pages << EFI_PAGE_SHIFT; + u64 end = md->phys_addr + size; + if (!(md->attribute & EFI_MEMORY_RUNTIME) && + md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_BOOT_SERVICES_DATA) + continue; + if (!md->virt_addr) + continue; + if (phys_addr >= md->phys_addr && phys_addr < end) { + phys_addr += md->virt_addr - md->phys_addr; + return (__force void __iomem *)(unsigned long)phys_addr; + } + } + return NULL; +} + +/* * This function will switch the EFI runtime services to virtual mode. * Essentially, look through the EFI memmap and map every region that * has the runtime attribute bit set in its memory descriptor and update @@ -765,8 +834,10 @@ void __init efi_enter_virtual_mode(void) * non-native EFI */ - if (!efi_native) - goto out; + if (!efi_native) { + efi_unmap_memmap(); + return; + } /* Merge contiguous regions of the same type and attribute */ for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { @@ -856,18 +927,12 @@ void __init efi_enter_virtual_mode(void) } /* - * Thankfully, it does seem that no runtime services other than - * SetVirtualAddressMap() will touch boot services code, so we can - * get rid of it all at this point - */ - efi_free_boot_services(); - - /* * Now that EFI is in virtual mode, update the function * pointers in the runtime service table to the new virtual addresses. * * Call EFI services through wrapper functions. */ + efi.runtime_version = efi_systab.fw_revision; efi.get_time = virt_efi_get_time; efi.set_time = virt_efi_set_time; efi.get_wakeup_time = virt_efi_get_wakeup_time; @@ -884,9 +949,6 @@ void __init efi_enter_virtual_mode(void) if (__supported_pte_mask & _PAGE_NX) runtime_code_page_mkexec(); -out: - early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size); - memmap.map = NULL; kfree(new_memmap); } diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index b2d534cab25..88692871823 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -72,7 +72,7 @@ KBUILD_CFLAGS := $(LINUXINCLUDE) -m32 -g -Os -D_SETUP -D__KERNEL__ -D_WAKEUP \ -Wall -Wstrict-prototypes \ -march=i386 -mregparm=3 \ -include $(srctree)/$(src)/../../boot/code16gcc.h \ - -fno-strict-aliasing -fomit-frame-pointer \ + -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ $(call cc-option, -ffreestanding) \ $(call cc-option, -fno-toplevel-reorder,\ $(call cc-option, -fno-unit-at-a-time)) \ diff --git a/arch/x86/realmode/rm/wakeup.h b/arch/x86/realmode/rm/wakeup.h index 9317e0042f2..7dd86a419f5 100644 --- a/arch/x86/realmode/rm/wakeup.h +++ b/arch/x86/realmode/rm/wakeup.h @@ -36,5 +36,7 @@ extern struct wakeup_header wakeup_header; /* Wakeup behavior bits */ #define WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE 0 +#define WAKEUP_BEHAVIOR_RESTORE_CR4 1 +#define WAKEUP_BEHAVIOR_RESTORE_EFER 2 #endif /* ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H */ diff --git a/arch/x86/realmode/rm/wakeup_asm.S b/arch/x86/realmode/rm/wakeup_asm.S index 8905166b0bb..e56479e5805 100644 --- a/arch/x86/realmode/rm/wakeup_asm.S +++ b/arch/x86/realmode/rm/wakeup_asm.S @@ -74,9 +74,18 @@ ENTRY(wakeup_start) lidtl wakeup_idt - /* Clear the EFLAGS */ - pushl $0 + /* Clear the EFLAGS but remember if we have EFLAGS.ID */ + movl $X86_EFLAGS_ID, %ecx + pushl %ecx popfl + pushfl + popl %edi + pushl $0 + popfl + pushfl + popl %edx + xorl %edx, %edi + andl %ecx, %edi /* %edi is zero iff CPUID & %cr4 are missing */ /* Check header signature... */ movl signature, %eax @@ -93,8 +102,8 @@ ENTRY(wakeup_start) /* Restore MISC_ENABLE before entering protected mode, in case BIOS decided to clear XD_DISABLE during S3. */ - movl pmode_behavior, %eax - btl $WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE, %eax + movl pmode_behavior, %edi + btl $WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE, %edi jnc 1f movl pmode_misc_en, %eax @@ -110,15 +119,15 @@ ENTRY(wakeup_start) movl pmode_cr3, %eax movl %eax, %cr3 - movl pmode_cr4, %ecx - jecxz 1f - movl %ecx, %cr4 + btl $WAKEUP_BEHAVIOR_RESTORE_CR4, %edi + jz 1f + movl pmode_cr4, %eax + movl %eax, %cr4 1: + btl $WAKEUP_BEHAVIOR_RESTORE_EFER, %edi + jz 1f movl pmode_efer, %eax movl pmode_efer + 4, %edx - movl %eax, %ecx - orl %edx, %ecx - jz 1f movl $MSR_EFER, %ecx wrmsr 1: diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 51171aeff0d..a582bfed95b 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -60,8 +60,8 @@ 51 common getsockname sys_getsockname 52 common getpeername sys_getpeername 53 common socketpair sys_socketpair -54 common setsockopt sys_setsockopt -55 common getsockopt sys_getsockopt +54 64 setsockopt sys_setsockopt +55 64 getsockopt sys_getsockopt 56 common clone stub_clone 57 common fork stub_fork 58 common vfork stub_vfork @@ -318,7 +318,7 @@ 309 common getcpu sys_getcpu 310 64 process_vm_readv sys_process_vm_readv 311 64 process_vm_writev sys_process_vm_writev -312 64 kcmp sys_kcmp +312 common kcmp sys_kcmp # # x32-specific system call numbers start at 512 to avoid cache impact @@ -353,3 +353,5 @@ 538 x32 sendmmsg compat_sys_sendmmsg 539 x32 process_vm_readv compat_sys_process_vm_readv 540 x32 process_vm_writev compat_sys_process_vm_writev +541 x32 setsockopt compat_sys_setsockopt +542 x32 getsockopt compat_sys_getsockopt diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index 9926e11a772..aeaff8bef2f 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -21,6 +21,7 @@ config 64BIT config X86_32 def_bool !64BIT select HAVE_AOUT + select ARCH_WANT_IPC_PARSE_VERSION config X86_64 def_bool 64BIT diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h index 5868526b5ee..46a9df99f3c 100644 --- a/arch/x86/um/shared/sysdep/kernel-offsets.h +++ b/arch/x86/um/shared/sysdep/kernel-offsets.h @@ -7,9 +7,6 @@ #define DEFINE(sym, val) \ asm volatile("\n->" #sym " %0 " #val : : "i" (val)) -#define STR(x) #x -#define DEFINE_STR(sym, val) asm volatile("\n->" #sym " " STR(val) " " #val: : ) - #define BLANK() asm volatile("\n->" : : ) #define OFFSET(sym, str, mem) \ diff --git a/arch/x86/um/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls.h index bd9a89b67e4..ca255a805ed 100644 --- a/arch/x86/um/shared/sysdep/syscalls.h +++ b/arch/x86/um/shared/sysdep/syscalls.h @@ -1,3 +1,5 @@ +extern long sys_clone(unsigned long clone_flags, unsigned long newsp, + void __user *parent_tid, void __user *child_tid); #ifdef __i386__ #include "syscalls_32.h" #else diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index a508cea1350..ba7363ecf89 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -416,9 +416,6 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig, PT_REGS_AX(regs) = (unsigned long) sig; PT_REGS_DX(regs) = (unsigned long) 0; PT_REGS_CX(regs) = (unsigned long) 0; - - if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED)) - ptrace_notify(SIGTRAP); return 0; } @@ -466,9 +463,6 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, PT_REGS_AX(regs) = (unsigned long) sig; PT_REGS_DX(regs) = (unsigned long) &frame->info; PT_REGS_CX(regs) = (unsigned long) &frame->uc; - - if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED)) - ptrace_notify(SIGTRAP); return 0; } diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 68d1dc91b37..b5408cecac6 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -28,7 +28,7 @@ #define ptregs_execve sys_execve #define ptregs_iopl sys_iopl #define ptregs_vm86old sys_vm86old -#define ptregs_clone sys_clone +#define ptregs_clone i386_clone #define ptregs_vm86 sys_vm86 #define ptregs_sigaltstack sys_sigaltstack #define ptregs_vfork sys_vfork diff --git a/arch/x86/um/syscalls_32.c b/arch/x86/um/syscalls_32.c index b853e8600b9..db444c7218f 100644 --- a/arch/x86/um/syscalls_32.c +++ b/arch/x86/um/syscalls_32.c @@ -3,37 +3,24 @@ * Licensed under the GPL */ -#include "linux/sched.h" -#include "linux/shm.h" -#include "linux/ipc.h" -#include "linux/syscalls.h" -#include "asm/mman.h" -#include "asm/uaccess.h" -#include "asm/unistd.h" +#include <linux/syscalls.h> +#include <sysdep/syscalls.h> /* * The prototype on i386 is: * - * int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls, int * child_tidptr) + * int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls * * and the "newtls" arg. on i386 is read by copy_thread directly from the * register saved on the stack. */ -long sys_clone(unsigned long clone_flags, unsigned long newsp, - int __user *parent_tid, void *newtls, int __user *child_tid) +long i386_clone(unsigned long clone_flags, unsigned long newsp, + int __user *parent_tid, void *newtls, int __user *child_tid) { - long ret; - - if (!newsp) - newsp = UPT_SP(¤t->thread.regs.regs); - - current->thread.forking = 1; - ret = do_fork(clone_flags, newsp, ¤t->thread.regs, 0, parent_tid, - child_tid); - current->thread.forking = 0; - return ret; + return sys_clone(clone_flags, newsp, parent_tid, child_tid); } + long sys_sigaction(int sig, const struct old_sigaction __user *act, struct old_sigaction __user *oact) { diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c index f3d82bb6e15..adb08eb5c22 100644 --- a/arch/x86/um/syscalls_64.c +++ b/arch/x86/um/syscalls_64.c @@ -5,12 +5,9 @@ * Licensed under the GPL */ -#include "linux/linkage.h" -#include "linux/personality.h" -#include "linux/utsname.h" -#include "asm/prctl.h" /* XXX This should get the constants from libc */ -#include "asm/uaccess.h" -#include "os.h" +#include <linux/sched.h> +#include <asm/prctl.h> /* XXX This should get the constants from libc */ +#include <os.h> long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) { @@ -79,20 +76,6 @@ long sys_arch_prctl(int code, unsigned long addr) return arch_prctl(current, code, (unsigned long __user *) addr); } -long sys_clone(unsigned long clone_flags, unsigned long newsp, - void __user *parent_tid, void __user *child_tid) -{ - long ret; - - if (!newsp) - newsp = UPT_SP(¤t->thread.regs.regs); - current->thread.forking = 1; - ret = do_fork(clone_flags, newsp, ¤t->thread.regs, 0, parent_tid, - child_tid); - current->thread.forking = 0; - return ret; -} - void arch_switch_to(struct task_struct *to) { if ((to->thread.arch.fs == 0) || (to->mm == NULL)) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index bf4bda6d3e9..1fbe75a95f1 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -31,7 +31,6 @@ #include <linux/pci.h> #include <linux/gfp.h> #include <linux/memblock.h> -#include <linux/syscore_ops.h> #include <xen/xen.h> #include <xen/interface/xen.h> @@ -1453,6 +1452,10 @@ asmlinkage void __init xen_start_kernel(void) pci_request_acs(); xen_acpi_sleep_register(); + + /* Avoid searching for BIOS MP tables */ + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.mpparse.get_smp_config = x86_init_uint_noop; } #ifdef CONFIG_PCI /* PCI BIOS service won't work from a PV guest. */ @@ -1470,130 +1473,38 @@ asmlinkage void __init xen_start_kernel(void) #endif } -#ifdef CONFIG_XEN_PVHVM -/* - * The pfn containing the shared_info is located somewhere in RAM. This - * will cause trouble if the current kernel is doing a kexec boot into a - * new kernel. The new kernel (and its startup code) can not know where - * the pfn is, so it can not reserve the page. The hypervisor will - * continue to update the pfn, and as a result memory corruption occours - * in the new kernel. - * - * One way to work around this issue is to allocate a page in the - * xen-platform pci device's BAR memory range. But pci init is done very - * late and the shared_info page is already in use very early to read - * the pvclock. So moving the pfn from RAM to MMIO is racy because some - * code paths on other vcpus could access the pfn during the small - * window when the old pfn is moved to the new pfn. There is even a - * small window were the old pfn is not backed by a mfn, and during that - * time all reads return -1. - * - * Because it is not known upfront where the MMIO region is located it - * can not be used right from the start in xen_hvm_init_shared_info. - * - * To minimise trouble the move of the pfn is done shortly before kexec. - * This does not eliminate the race because all vcpus are still online - * when the syscore_ops will be called. But hopefully there is no work - * pending at this point in time. Also the syscore_op is run last which - * reduces the risk further. - */ - -static struct shared_info *xen_hvm_shared_info; - -static void xen_hvm_connect_shared_info(unsigned long pfn) +void __ref xen_hvm_init_shared_info(void) { + int cpu; struct xen_add_to_physmap xatp; + static struct shared_info *shared_info_page = 0; + if (!shared_info_page) + shared_info_page = (struct shared_info *) + extend_brk(PAGE_SIZE, PAGE_SIZE); xatp.domid = DOMID_SELF; xatp.idx = 0; xatp.space = XENMAPSPACE_shared_info; - xatp.gpfn = pfn; + xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT; if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) BUG(); -} -static void xen_hvm_set_shared_info(struct shared_info *sip) -{ - int cpu; - - HYPERVISOR_shared_info = sip; + HYPERVISOR_shared_info = (struct shared_info *)shared_info_page; /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info * page, we use it in the event channel upcall and in some pvclock * related functions. We don't need the vcpu_info placement * optimizations because we don't use any pv_mmu or pv_irq op on * HVM. - * When xen_hvm_set_shared_info is run at boot time only vcpu 0 is - * online but xen_hvm_set_shared_info is run at resume time too and + * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is + * online but xen_hvm_init_shared_info is run at resume time too and * in that case multiple vcpus might be online. */ for_each_online_cpu(cpu) { per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; } } -/* Reconnect the shared_info pfn to a mfn */ -void xen_hvm_resume_shared_info(void) -{ - xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT); -} - -#ifdef CONFIG_KEXEC -static struct shared_info *xen_hvm_shared_info_kexec; -static unsigned long xen_hvm_shared_info_pfn_kexec; - -/* Remember a pfn in MMIO space for kexec reboot */ -void __devinit xen_hvm_prepare_kexec(struct shared_info *sip, unsigned long pfn) -{ - xen_hvm_shared_info_kexec = sip; - xen_hvm_shared_info_pfn_kexec = pfn; -} - -static void xen_hvm_syscore_shutdown(void) -{ - struct xen_memory_reservation reservation = { - .domid = DOMID_SELF, - .nr_extents = 1, - }; - unsigned long prev_pfn; - int rc; - - if (!xen_hvm_shared_info_kexec) - return; - - prev_pfn = __pa(xen_hvm_shared_info) >> PAGE_SHIFT; - set_xen_guest_handle(reservation.extent_start, &prev_pfn); - - /* Move pfn to MMIO, disconnects previous pfn from mfn */ - xen_hvm_connect_shared_info(xen_hvm_shared_info_pfn_kexec); - - /* Update pointers, following hypercall is also a memory barrier */ - xen_hvm_set_shared_info(xen_hvm_shared_info_kexec); - - /* Allocate new mfn for previous pfn */ - do { - rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation); - if (rc == 0) - msleep(123); - } while (rc == 0); - - /* Make sure the previous pfn is really connected to a (new) mfn */ - BUG_ON(rc != 1); -} - -static struct syscore_ops xen_hvm_syscore_ops = { - .shutdown = xen_hvm_syscore_shutdown, -}; -#endif - -/* Use a pfn in RAM, may move to MMIO before kexec. */ -static void __init xen_hvm_init_shared_info(void) -{ - /* Remember pointer for resume */ - xen_hvm_shared_info = extend_brk(PAGE_SIZE, PAGE_SIZE); - xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT); - xen_hvm_set_shared_info(xen_hvm_shared_info); -} - +#ifdef CONFIG_XEN_PVHVM static void __init init_hvm_pv_info(void) { int major, minor; @@ -1644,9 +1555,6 @@ static void __init xen_hvm_guest_init(void) init_hvm_pv_info(); xen_hvm_init_shared_info(); -#ifdef CONFIG_KEXEC - register_syscore_ops(&xen_hvm_syscore_ops); -#endif if (xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index b65a76133f4..7a769b7526c 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1174,8 +1174,13 @@ static void xen_exit_mmap(struct mm_struct *mm) spin_unlock(&mm->page_table_lock); } -static void __init xen_pagetable_setup_start(pgd_t *base) +static void xen_post_allocator_init(void); + +static void __init xen_pagetable_init(void) { + paging_init(); + xen_setup_shared_info(); + xen_post_allocator_init(); } static __init void xen_mapping_pagetable_reserve(u64 start, u64 end) @@ -1192,14 +1197,6 @@ static __init void xen_mapping_pagetable_reserve(u64 start, u64 end) } } -static void xen_post_allocator_init(void); - -static void __init xen_pagetable_setup_done(pgd_t *base) -{ - xen_setup_shared_info(); - xen_post_allocator_init(); -} - static void xen_write_cr2(unsigned long cr2) { this_cpu_read(xen_vcpu)->arch.cr2 = cr2; @@ -1283,7 +1280,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask)); args->op.cmd = MMUEXT_TLB_FLUSH_MULTI; - if (start != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) { + if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) { args->op.cmd = MMUEXT_INVLPG_MULTI; args->op.arg1.linear_addr = start; } @@ -2068,8 +2065,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { void __init xen_init_mmu_ops(void) { x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve; - x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start; - x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done; + x86_init.paging.pagetable_init = xen_pagetable_init; pv_mmu_ops = xen_mmu_ops; memset(dummy_mapping, 0xff, PAGE_SIZE); diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 64effdc6da9..72213da605f 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -194,6 +194,13 @@ RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID * boundary violation will require three middle nodes. */ RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3); +/* When we populate back during bootup, the amount of pages can vary. The + * max we have is seen is 395979, but that does not mean it can't be more. + * Some machines can have 3GB I/O holes even. With early_can_reuse_p2m_middle + * it can re-use Xen provided mfn_list array, so we only need to allocate at + * most three P2M top nodes. */ +RESERVE_BRK(p2m_populated, PAGE_SIZE * 3); + static inline unsigned p2m_top_index(unsigned long pfn) { BUG_ON(pfn >= MAX_P2M_PFN); @@ -570,12 +577,99 @@ static bool __init early_alloc_p2m(unsigned long pfn) } return true; } + +/* + * Skim over the P2M tree looking at pages that are either filled with + * INVALID_P2M_ENTRY or with 1:1 PFNs. If found, re-use that page and + * replace the P2M leaf with a p2m_missing or p2m_identity. + * Stick the old page in the new P2M tree location. + */ +bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_mfn) +{ + unsigned topidx; + unsigned mididx; + unsigned ident_pfns; + unsigned inv_pfns; + unsigned long *p2m; + unsigned long *mid_mfn_p; + unsigned idx; + unsigned long pfn; + + /* We only look when this entails a P2M middle layer */ + if (p2m_index(set_pfn)) + return false; + + for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) { + topidx = p2m_top_index(pfn); + + if (!p2m_top[topidx]) + continue; + + if (p2m_top[topidx] == p2m_mid_missing) + continue; + + mididx = p2m_mid_index(pfn); + p2m = p2m_top[topidx][mididx]; + if (!p2m) + continue; + + if ((p2m == p2m_missing) || (p2m == p2m_identity)) + continue; + + if ((unsigned long)p2m == INVALID_P2M_ENTRY) + continue; + + ident_pfns = 0; + inv_pfns = 0; + for (idx = 0; idx < P2M_PER_PAGE; idx++) { + /* IDENTITY_PFNs are 1:1 */ + if (p2m[idx] == IDENTITY_FRAME(pfn + idx)) + ident_pfns++; + else if (p2m[idx] == INVALID_P2M_ENTRY) + inv_pfns++; + else + break; + } + if ((ident_pfns == P2M_PER_PAGE) || (inv_pfns == P2M_PER_PAGE)) + goto found; + } + return false; +found: + /* Found one, replace old with p2m_identity or p2m_missing */ + p2m_top[topidx][mididx] = (ident_pfns ? p2m_identity : p2m_missing); + /* And the other for save/restore.. */ + mid_mfn_p = p2m_top_mfn_p[topidx]; + /* NOTE: Even if it is a p2m_identity it should still be point to + * a page filled with INVALID_P2M_ENTRY entries. */ + mid_mfn_p[mididx] = virt_to_mfn(p2m_missing); + + /* Reset where we want to stick the old page in. */ + topidx = p2m_top_index(set_pfn); + mididx = p2m_mid_index(set_pfn); + + /* This shouldn't happen */ + if (WARN_ON(p2m_top[topidx] == p2m_mid_missing)) + early_alloc_p2m(set_pfn); + + if (WARN_ON(p2m_top[topidx][mididx] != p2m_missing)) + return false; + + p2m_init(p2m); + p2m_top[topidx][mididx] = p2m; + mid_mfn_p = p2m_top_mfn_p[topidx]; + mid_mfn_p[mididx] = virt_to_mfn(p2m); + + return true; +} bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn) { if (unlikely(!__set_phys_to_machine(pfn, mfn))) { if (!early_alloc_p2m(pfn)) return false; + if (early_can_reuse_p2m_middle(pfn, mfn)) + return __set_phys_to_machine(pfn, mfn); + if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/)) return false; @@ -734,9 +828,6 @@ int m2p_add_override(unsigned long mfn, struct page *page, xen_mc_issue(PARAVIRT_LAZY_MMU); } - /* let's use dev_bus_addr to record the old mfn instead */ - kmap_op->dev_bus_addr = page->index; - page->index = (unsigned long) kmap_op; } spin_lock_irqsave(&m2p_override_lock, flags); list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]); @@ -763,7 +854,8 @@ int m2p_add_override(unsigned long mfn, struct page *page, return 0; } EXPORT_SYMBOL_GPL(m2p_add_override); -int m2p_remove_override(struct page *page, bool clear_pte) +int m2p_remove_override(struct page *page, + struct gnttab_map_grant_ref *kmap_op) { unsigned long flags; unsigned long mfn; @@ -793,10 +885,8 @@ int m2p_remove_override(struct page *page, bool clear_pte) WARN_ON(!PagePrivate(page)); ClearPagePrivate(page); - if (clear_pte) { - struct gnttab_map_grant_ref *map_op = - (struct gnttab_map_grant_ref *) page->index; - set_phys_to_machine(pfn, map_op->dev_bus_addr); + set_phys_to_machine(pfn, page->index); + if (kmap_op != NULL) { if (!PageHighMem(page)) { struct multicall_space mcs; struct gnttab_unmap_grant_ref *unmap_op; @@ -808,13 +898,13 @@ int m2p_remove_override(struct page *page, bool clear_pte) * issued. In this case handle is going to -1 because * it hasn't been modified yet. */ - if (map_op->handle == -1) + if (kmap_op->handle == -1) xen_mc_flush(); /* - * Now if map_op->handle is negative it means that the + * Now if kmap_op->handle is negative it means that the * hypercall actually returned an error. */ - if (map_op->handle == GNTST_general_error) { + if (kmap_op->handle == GNTST_general_error) { printk(KERN_WARNING "m2p_remove_override: " "pfn %lx mfn %lx, failed to modify kernel mappings", pfn, mfn); @@ -824,8 +914,8 @@ int m2p_remove_override(struct page *page, bool clear_pte) mcs = xen_mc_entry( sizeof(struct gnttab_unmap_grant_ref)); unmap_op = mcs.args; - unmap_op->host_addr = map_op->host_addr; - unmap_op->handle = map_op->handle; + unmap_op->host_addr = kmap_op->host_addr; + unmap_op->handle = kmap_op->handle; unmap_op->dev_bus_addr = 0; MULTI_grant_table_op(mcs.mc, @@ -836,10 +926,9 @@ int m2p_remove_override(struct page *page, bool clear_pte) set_pte_at(&init_mm, address, ptep, pfn_pte(pfn, PAGE_KERNEL)); __flush_tlb_single(address); - map_op->host_addr = 0; + kmap_op->host_addr = 0; } - } else - set_phys_to_machine(pfn, page->index); + } /* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present * somewhere in this domain, even before being added to the diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index ead85576d54..e2d62d697b5 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -17,6 +17,7 @@ #include <asm/e820.h> #include <asm/setup.h> #include <asm/acpi.h> +#include <asm/numa.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> @@ -78,9 +79,16 @@ static void __init xen_add_extra_mem(u64 start, u64 size) memblock_reserve(start, size); xen_max_p2m_pfn = PFN_DOWN(start + size); + for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) { + unsigned long mfn = pfn_to_mfn(pfn); + + if (WARN(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn)) + continue; + WARN(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n", + pfn, mfn); - for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++) __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); + } } static unsigned long __init xen_do_chunk(unsigned long start, @@ -537,4 +545,7 @@ void __init xen_arch_setup(void) disable_cpufreq(); WARN_ON(set_pm_idle_to_default()); fiddle_vdso(); +#ifdef CONFIG_NUMA + numa_off = 1; +#endif } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index f58dca7a6e5..353c50f1870 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -377,7 +377,8 @@ static int __cpuinit xen_cpu_up(unsigned int cpu, struct task_struct *idle) return rc; if (num_online_cpus() == 1) - alternatives_smp_switch(1); + /* Just in case we booted with a single CPU. */ + alternatives_enable_smp(); rc = xen_smp_intr_init(cpu); if (rc) @@ -424,9 +425,6 @@ static void xen_cpu_die(unsigned int cpu) unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL); xen_uninit_lock_cpu(cpu); xen_teardown_timer(cpu); - - if (num_online_cpus() == 1) - alternatives_smp_switch(0); } static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */ diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index ae8a00c39de..45329c8c226 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -30,7 +30,7 @@ void xen_arch_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; - xen_hvm_resume_shared_info(); + xen_hvm_init_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 1e4329e04e0..202d4c15015 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -41,7 +41,7 @@ void xen_enable_syscall(void); void xen_vcpu_restore(void); void xen_callback_vector(void); -void xen_hvm_resume_shared_info(void); +void xen_hvm_init_shared_info(void); void xen_unplug_emulated_devices(void); void __init xen_build_dynamic_phys_to_machine(void); |