diff options
Diffstat (limited to 'arch/x86')
98 files changed, 2107 insertions, 1026 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5ce8694..7f9a395 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 @@ -1986,7 +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 @@ -2197,18 +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 706e12e..f3b86d0 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 682e9c2..474ca35 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -142,7 +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/compressed/Makefile b/arch/x86/boot/compressed/Makefile index e398bb5..8a84501 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 b3e0227..c760e07 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 3b6e156..e5b0a8f 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 b4e15dd..2a01744 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 119db67..5598547 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 76eb290..671524d 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/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 87bc00d..58ed6d9 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -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; diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 72f5009..6dfd019 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 a9e3a74..7f8422a 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/ftrace.h b/arch/x86/include/asm/ftrace.h index b0767bc..9a25b52 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/hardirq.h b/arch/x86/include/asm/hardirq.h index d3895db..81f04ce 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 2c392d6..434e210 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/kprobes.h b/arch/x86/include/asm/kprobes.h index 5478825..d3ddd17 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 246617e..41e08cb 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 09155d6..1eaa6b0 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 a3ac52b..54d73b1 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -116,19 +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); @@ -171,6 +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 4ebe157..43d921b 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 cb4e43b..4fabcdf 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -262,4 +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 0000000..3f2207b --- /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 013286a1..db8fec6 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.h b/arch/x86/include/asm/processor.h index d048cad..b98c0d9 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 0000000..d1ac07a --- /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/svm.h b/arch/x86/include/asm/svm.h index f2b83bc..cdf5674 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/thread_info.h b/arch/x86/include/asm/thread_info.h index 89f794f..c535d847 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/uprobes.h b/arch/x86/include/asm/uprobes.h index f3971bb..8ff8be7 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/vmx.h b/arch/x86/include/asm/vmx.h index 74fcb96..36ec21c 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 38155f6..5769349 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 93971e8..472b9b7 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/kernel/Makefile b/arch/x86/kernel/Makefile index 8215e56..8d7a619 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 b2297e5..e651f7a 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/alternative.c b/arch/x86/kernel/alternative.c index ced4534..ef5ccca 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) @@ -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 24deb30..b17416e 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/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 9d92e19..f7e98a2 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/common.c b/arch/x86/kernel/cpu/common.c index fefd9b7..7505f7b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -489,7 +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], @@ -955,8 +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) @@ -1036,14 +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); } @@ -1130,8 +1131,6 @@ void syscall_init(void) 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. @@ -1312,8 +1311,6 @@ void __cpuinit cpu_init(void) fpu_init(); - raw_local_save_flags(kernel_eflags); - if (is_uv_system()) uv_cpu_init(); } diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 0a4ce29..198e019 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 fc4beb3..ddc72f8 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 ed44c8a..6a05c1d 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.c b/arch/x86/kernel/cpu/mcheck/mce.c index 292d025..29e87d3 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; @@ -1266,6 +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); @@ -1276,6 +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(); } /* @@ -1283,14 +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 */ @@ -1585,6 +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); @@ -1594,23 +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) { @@ -1907,6 +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) { @@ -1926,6 +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 == ',') { @@ -2166,6 +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, @@ -2174,6 +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 }; @@ -2294,38 +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 38e49bc9..5f88abf 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.h b/arch/x86/kernel/cpu/perf_event.h index 6605a81..8b6defe 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -586,6 +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 7bfb5be..eebd5ff 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -209,6 +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; @@ -229,6 +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; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 7f2739e..6bca492 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2008,6 +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)); @@ -2047,7 +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, @@ -2072,6 +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 e38d97b..826054a 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; diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 520b426..da02e9c 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 0a55710..99d96a4 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[] = { @@ -1944,7 +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) @@ -2341,6 +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; @@ -2378,8 +2405,8 @@ 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 __init uncore_types_exit(struct intel_uncore_type **types) @@ -2431,9 +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: diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 5b81c18..e68a455 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -369,10 +369,12 @@ struct intel_uncore_type { 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 *); diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 8022c66..fbd8955 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 39472dd..60c7891 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 3ae2ced..b158152 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 9ebbeca..0750e3b 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1130,17 +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: @@ -1152,6 +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) @@ -1192,9 +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 diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index ce87e3d..44531ac 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -56,6 +56,7 @@ #include <asm/ftrace.h> #include <asm/percpu.h> #include <asm/asm.h> +#include <asm/rcu.h> #include <asm/smap.h> #include <linux/err.h> @@ -69,25 +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) @@ -98,8 +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 @@ -120,8 +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 @@ -129,20 +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 @@ -343,15 +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 @@ -385,7 +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 @@ -441,7 +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 @@ -567,7 +670,7 @@ sysret_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi jmp sysret_check @@ -680,7 +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 @@ -977,7 +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) @@ -1458,7 +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 c3a7cb4..1d41402 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/i8259.c b/arch/x86/kernel/i8259.c index 36d1853..9a5c460 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 d44f782..e4595f1 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; diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index e2f751e..57916c0 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 82746f9..7720ff5 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); @@ -118,95 +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, patch_size; - u16 equiv_cpu_id; + BUG_ON(raw_smp_processor_id() != cpu); - /* size of the current patch we're staring at */ - patch_size = *(u32 *)(ucode_ptr + 4); - *current_size = patch_size + 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, patch_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); @@ -238,7 +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; @@ -250,61 +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; } /* @@ -315,7 +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 @@ -323,12 +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); @@ -344,12 +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; } @@ -383,14 +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 4873e62..3a04b22 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 0327e2b..3544aed 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 eb11369..a7c5661 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 0000000..e309cc5 --- /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/ptrace.c b/arch/x86/kernel/ptrace.c index 861a9d1..b00b33a 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> @@ -1460,6 +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. @@ -1523,4 +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 f4b9b80..4f16547 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 036bddb..b33144c 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -816,6 +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) @@ -841,6 +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) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 7c5a8c3..c80a33b 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 c346d11..cd3b243 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 4f4aba0..8276dc6 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 @@ -630,6 +645,7 @@ 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 @@ -640,6 +656,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); + exception_exit(regs); return; } #endif @@ -647,12 +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; @@ -660,10 +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 36fd420..9538f00 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 6020f6f..1330dd1 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 9f3167e..7a3d075 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/kvm/i8259.c b/arch/x86/kvm/i8259.c index e498b18..9fc9aa7 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -318,7 +318,7 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) if (val & 0x10) { u8 edge_irr = s->irr & ~s->elcr; int i; - bool found; + bool found = false; struct kvm_vcpu *vcpu; s->init4 = val & 1; diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index a71faf7..bca63f0 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 70dfcec..851aa7c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3623,6 +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; @@ -3637,7 +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; @@ -3645,6 +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; @@ -3660,8 +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; @@ -4534,7 +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); @@ -6579,7 +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, @@ -6589,7 +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 02b2cd5..1f09552 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5113,17 +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) @@ -5430,7 +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) { diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index f2fb75d..a530b23 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: @@ -1011,8 +1012,8 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs) * 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; @@ -1227,3 +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/init.c b/arch/x86/mm/init.c index e0e6990..ab1f6a9 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 e537b35..11a5800 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 diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 613cd83..0777f04 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 505acdd..192397c 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 937bcec..704b9ec 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 6f2f8ee..3e6d2a6 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 73b8be0..6db1cc4 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 0000000..f6a0c1b --- /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 92660eda..aded2a9 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> @@ -419,10 +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; @@ -438,6 +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) @@ -732,6 +746,11 @@ void __init efi_init(void) #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; @@ -764,6 +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 @@ -787,8 +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) { @@ -878,18 +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; @@ -906,9 +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/um/Kconfig b/arch/x86/um/Kconfig index 9926e11..aeaff8b 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 5868526..46a9df9 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 bd9a89b..ca255a8 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 a508cea1..ba7363e 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 68d1dc9..b5408ce 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 b853e86..db444c7 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 f3d82bb..adb08eb 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 9642d4a..1fbe75a 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1452,6 +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. */ diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index b65a761..7a769b7 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 d4b2554..72213da 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -599,7 +599,7 @@ bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_ if (p2m_index(set_pfn)) return false; - for (pfn = 0; pfn <= MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) { + for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) { topidx = p2m_top_index(pfn); if (!p2m_top[topidx]) @@ -828,9 +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)]); @@ -857,7 +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; @@ -887,10 +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; @@ -902,13 +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); @@ -918,8 +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, @@ -930,10 +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 d11ca11..e2d62d6 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> @@ -544,4 +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 f58dca7..353c50f 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 */ |