diff options
Diffstat (limited to 'arch/x86')
319 files changed, 16701 insertions, 10700 deletions
diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore new file mode 100644 index 00000000000..028079065af --- /dev/null +++ b/arch/x86/.gitignore @@ -0,0 +1,3 @@ +boot/compressed/vmlinux +tools/test_get_len + diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9458685902b..a84fc34c8f7 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -53,11 +53,16 @@ config X86 select HAVE_KERNEL_LZMA select HAVE_KERNEL_LZO select HAVE_HW_BREAKPOINT + select HAVE_MIXED_BREAKPOINTS_REGS select PERF_EVENTS + select HAVE_PERF_EVENTS_NMI select ANON_INODES select HAVE_ARCH_KMEMCHECK select HAVE_USER_RETURN_NOTIFIER +config INSTRUCTION_DECODER + def_bool (KPROBES || PERF_EVENTS) + config OUTPUT_FORMAT string default "elf32-i386" if X86_32 @@ -68,9 +73,6 @@ config ARCH_DEFCONFIG default "arch/x86/configs/i386_defconfig" if X86_32 default "arch/x86/configs/x86_64_defconfig" if X86_64 -config GENERIC_TIME - def_bool y - config GENERIC_CMOS_UPDATE def_bool y @@ -105,6 +107,9 @@ config SBUS config NEED_DMA_MAP_STATE def_bool (X86_64 || DMAR || DMA_API_DEBUG) +config NEED_SG_DMA_LENGTH + def_bool y + config GENERIC_ISA_DMA def_bool y @@ -197,20 +202,17 @@ config HAVE_INTEL_TXT # Use the generic interrupt handling code in kernel/irq/: config GENERIC_HARDIRQS - bool - default y + def_bool y config GENERIC_HARDIRQS_NO__DO_IRQ def_bool y config GENERIC_IRQ_PROBE - bool - default y + def_bool y config GENERIC_PENDING_IRQ - bool + def_bool y depends on GENERIC_HARDIRQS && SMP - default y config USE_GENERIC_SMP_HELPERS def_bool y @@ -225,19 +227,22 @@ config X86_64_SMP depends on X86_64 && SMP config X86_HT - bool + def_bool y depends on SMP - default y config X86_TRAMPOLINE - bool + def_bool y depends on SMP || (64BIT && ACPI_SLEEP) - default y config X86_32_LAZY_GS def_bool y depends on X86_32 && !CC_STACKPROTECTOR +config ARCH_HWEIGHT_CFLAGS + string + default "-fcall-saved-ecx -fcall-saved-edx" if X86_32 + default "-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64 + config KTIME_SCALAR def_bool X86_32 source "init/Kconfig" @@ -447,7 +452,7 @@ config X86_NUMAQ firmware with - send email to <Martin.Bligh@us.ibm.com>. config X86_SUPPORTS_MEMORY_FAILURE - bool + def_bool y # MCE code calls memory_failure(): depends on X86_MCE # On 32-bit this adds too big of NODES_SHIFT and we run out of page flags: @@ -455,7 +460,6 @@ config X86_SUPPORTS_MEMORY_FAILURE # On 32-bit SPARSEMEM adds too big of SECTIONS_WIDTH: depends on X86_64 || !SPARSEMEM select ARCH_SUPPORTS_MEMORY_FAILURE - default y config X86_VISWS bool "SGI 320/540 (Visual Workstation)" @@ -570,7 +574,6 @@ config PARAVIRT_SPINLOCKS config PARAVIRT_CLOCK bool - default n endif @@ -749,7 +752,6 @@ config MAXSMP bool "Configure Maximum number of SMP Processors and NUMA Nodes" depends on X86_64 && SMP && DEBUG_KERNEL && EXPERIMENTAL select CPUMASK_OFFSTACK - default n ---help--- Configure maximum number of CPUS and NUMA Nodes for this architecture. If unsure, say N. @@ -829,7 +831,6 @@ config X86_VISWS_APIC config X86_REROUTE_FOR_BROKEN_BOOT_IRQS bool "Reroute for broken boot IRQs" - default n depends on X86_IO_APIC ---help--- This option enables a workaround that fixes a source of @@ -876,9 +877,8 @@ config X86_MCE_AMD the DRAM Error Threshold. config X86_ANCIENT_MCE - def_bool n + bool "Support for old Pentium 5 / WinChip machine checks" depends on X86_32 && X86_MCE - prompt "Support for old Pentium 5 / WinChip machine checks" ---help--- Include support for machine check handling on old Pentium 5 or WinChip systems. These typically need to be enabled explicitely on the command @@ -886,8 +886,7 @@ config X86_ANCIENT_MCE config X86_MCE_THRESHOLD depends on X86_MCE_AMD || X86_MCE_INTEL - bool - default y + def_bool y config X86_MCE_INJECT depends on X86_MCE @@ -1026,8 +1025,8 @@ config X86_CPUID choice prompt "High Memory Support" - default HIGHMEM4G if !X86_NUMAQ default HIGHMEM64G if X86_NUMAQ + default HIGHMEM4G depends on X86_32 config NOHIGHMEM @@ -1285,7 +1284,7 @@ source "mm/Kconfig" config HIGHPTE bool "Allocate 3rd-level pagetables from highmem" - depends on X86_32 && (HIGHMEM4G || HIGHMEM64G) + depends on HIGHMEM ---help--- The VM uses one page table entry for each page of physical memory. For systems with a lot of RAM, this can be wasteful of precious @@ -1369,8 +1368,7 @@ config MATH_EMULATION kernel, it won't hurt. config MTRR - bool - default y + def_bool y prompt "MTRR (Memory Type Range Register) support" if EMBEDDED ---help--- On Intel P6 family processors (Pentium Pro, Pentium II and later) @@ -1436,8 +1434,7 @@ config MTRR_SANITIZER_SPARE_REG_NR_DEFAULT mtrr_spare_reg_nr=N on the kernel command line. config X86_PAT - bool - default y + def_bool y prompt "x86 PAT support" if EMBEDDED depends on MTRR ---help--- @@ -1605,8 +1602,7 @@ config X86_NEED_RELOCS depends on X86_32 && RELOCATABLE config PHYSICAL_ALIGN - hex - prompt "Alignment value to which kernel should be aligned" if X86_32 + hex "Alignment value to which kernel should be aligned" if X86_32 default "0x1000000" range 0x2000 0x1000000 ---help--- @@ -1653,7 +1649,6 @@ config COMPAT_VDSO config CMDLINE_BOOL bool "Built-in kernel command line" - default n ---help--- Allow for specifying boot arguments to the kernel at build time. On some systems (e.g. embedded ones), it is @@ -1687,7 +1682,6 @@ config CMDLINE config CMDLINE_OVERRIDE bool "Built-in command line overrides boot loader arguments" - default n depends on CMDLINE_BOOL ---help--- Set this option to 'Y' to have the kernel ignore the boot loader @@ -1710,6 +1704,10 @@ config HAVE_ARCH_EARLY_PFN_TO_NID def_bool X86_64 depends on NUMA +config USE_PERCPU_NUMA_NODE_ID + def_bool X86_64 + depends on NUMA + menu "Power management and ACPI options" config ARCH_HIBERNATION_HEADER @@ -1723,8 +1721,7 @@ source "drivers/acpi/Kconfig" source "drivers/sfi/Kconfig" config X86_APM_BOOT - bool - default y + def_bool y depends on APM || APM_MODULE menuconfig APM @@ -1931,6 +1928,14 @@ config PCI_MMCONFIG bool "Support mmconfig PCI config space access" depends on X86_64 && PCI && ACPI +config PCI_CNB20LE_QUIRK + bool "Read CNB20LE Host Bridge Windows" + depends on PCI + help + Read the PCI windows out of the CNB20LE host bridge. This allows + PCI hotplug to work on systems with the CNB20LE chipset which do + not have ACPI. + config DMAR bool "Support for DMA Remapping Devices (EXPERIMENTAL)" depends on PCI_MSI && ACPI && EXPERIMENTAL @@ -1953,8 +1958,7 @@ config DMAR_DEFAULT_ON experimental. config DMAR_BROKEN_GFX_WA - def_bool n - prompt "Workaround broken graphics drivers (going away soon)" + bool "Workaround broken graphics drivers (going away soon)" depends on DMAR && BROKEN ---help--- Current Graphics drivers tend to use physical address @@ -2040,7 +2044,7 @@ config SCx200 config SCx200HR_TIMER tristate "NatSemi SCx200 27MHz High-Resolution Timer Support" - depends on SCx200 && GENERIC_TIME + depends on SCx200 default y ---help--- This driver provides a clocksource built upon the on-chip @@ -2052,11 +2056,19 @@ config SCx200HR_TIMER config OLPC bool "One Laptop Per Child support" select GPIOLIB - default n ---help--- Add support for detecting the unique features of the OLPC XO hardware. +config OLPC_OPENFIRMWARE + bool "Support for OLPC's Open Firmware" + depends on !X86_64 && !X86_PAE + default y if OLPC + help + This option adds support for the implementation of Open Firmware + that is used on the OLPC XO-1 Children's Machine. + If unsure, say N here. + endif # X86_32 config K8_NB diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index a19829374e6..2ac9069890c 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -338,6 +338,10 @@ config X86_F00F_BUG def_bool y depends on M586MMX || M586TSC || M586 || M486 || M386 +config X86_INVD_BUG + def_bool y + depends on M486 || M386 + config X86_WP_WORKS_OK def_bool y depends on !M386 @@ -502,23 +506,3 @@ config CPU_SUP_UMC_32 CPU might render the kernel unbootable. If unsure, say N. - -config X86_DS - def_bool X86_PTRACE_BTS - depends on X86_DEBUGCTLMSR - select HAVE_HW_BRANCH_TRACER - -config X86_PTRACE_BTS - bool "Branch Trace Store" - default y - depends on X86_DEBUGCTLMSR - depends on BROKEN - ---help--- - This adds a ptrace interface to the hardware's branch trace store. - - Debuggers may use it to collect an execution trace of the debugged - application in order to answer the question 'how did I get here?'. - Debuggers may trace user mode as well as kernel mode. - - Say Y unless there is no application development on this machine - and you want to save a small amount of code size. diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index bc01e3ebfeb..75085080b63 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -45,7 +45,6 @@ config EARLY_PRINTK config EARLY_PRINTK_DBGP bool "Early printk via EHCI debug port" - default n depends on EARLY_PRINTK && PCI ---help--- Write kernel log output directly into the EHCI debug port. @@ -76,7 +75,6 @@ config DEBUG_PER_CPU_MAPS bool "Debug access to per_cpu maps" depends on DEBUG_KERNEL depends on SMP - default n ---help--- Say Y to verify that the per_cpu map being accessed has been setup. Adds a fair amount of code to kernel memory @@ -174,15 +172,6 @@ config IOMMU_LEAK Add a simple leak tracer to the IOMMU code. This is useful when you are debugging a buggy device driver that leaks IOMMU mappings. -config X86_DS_SELFTEST - bool "DS selftest" - default y - depends on DEBUG_KERNEL - depends on X86_DS - ---help--- - Perform Debug Store selftests at boot time. - If in doubt, say "N". - config HAVE_MMIOTRACE_SUPPORT def_bool y diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 0a43dc515e4..8aa1b59b907 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -95,8 +95,9 @@ sp-$(CONFIG_X86_64) := rsp cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_endproc,-DCONFIG_AS_CFI=1) # is .cfi_signal_frame supported too? cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1) -KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) -KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) +cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1) +KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) +KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) LDFLAGS := -m elf_$(UTS_MACHINE) diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index ec749c2bfdd..f7cb086b4ad 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -26,10 +26,10 @@ targets := vmlinux.bin setup.bin setup.elf bzImage targets += fdimage fdimage144 fdimage288 image.iso mtools.conf subdir- := compressed -setup-y += a20.o bioscall.o cmdline.o copy.o cpu.o cpucheck.o edd.o -setup-y += header.o main.o mca.o memory.o pm.o pmjump.o -setup-y += printf.o regs.o string.o tty.o video.o video-mode.o -setup-y += version.o +setup-y += a20.o bioscall.o cmdline.o copy.o cpu.o cpucheck.o +setup-y += early_serial_console.o edd.o header.o main.o mca.o memory.o +setup-y += pm.o pmjump.o printf.o regs.o string.o tty.o video.o +setup-y += video-mode.o version.o setup-$(CONFIG_X86_APM_BOOT) += apm.o # The link order of the video-*.o modules can matter. In particular, diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 98239d2658f..c7093bd9f2d 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -28,6 +28,7 @@ #include "bitops.h" #include <asm/cpufeature.h> #include <asm/processor-flags.h> +#include "ctype.h" /* Useful macros */ #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) @@ -37,6 +38,8 @@ extern struct setup_header hdr; extern struct boot_params boot_params; +#define cpu_relax() asm volatile("rep; nop") + /* Basic port I/O */ static inline void outb(u8 v, u16 port) { @@ -198,11 +201,6 @@ static inline int memcmp_gs(const void *s1, addr_t s2, size_t len) return diff; } -static inline int isdigit(int ch) -{ - return (ch >= '0') && (ch <= '9'); -} - /* Heap -- available for dynamic lists. */ extern char _end[]; extern char *HEAP; @@ -287,8 +285,18 @@ struct biosregs { void intcall(u8 int_no, const struct biosregs *ireg, struct biosregs *oreg); /* cmdline.c */ -int cmdline_find_option(const char *option, char *buffer, int bufsize); -int cmdline_find_option_bool(const char *option); +int __cmdline_find_option(u32 cmdline_ptr, const char *option, char *buffer, int bufsize); +int __cmdline_find_option_bool(u32 cmdline_ptr, const char *option); +static inline int cmdline_find_option(const char *option, char *buffer, int bufsize) +{ + return __cmdline_find_option(boot_params.hdr.cmd_line_ptr, option, buffer, bufsize); +} + +static inline int cmdline_find_option_bool(const char *option) +{ + return __cmdline_find_option_bool(boot_params.hdr.cmd_line_ptr, option); +} + /* cpu.c, cpucheck.c */ struct cpu_features { @@ -300,6 +308,10 @@ extern struct cpu_features cpu; int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr); int validate_cpu(void); +/* early_serial_console.c */ +extern int early_serial_base; +void console_init(void); + /* edd.c */ void query_edd(void); @@ -329,8 +341,10 @@ void initregs(struct biosregs *regs); /* string.c */ int strcmp(const char *str1, const char *str2); +int strncmp(const char *cs, const char *ct, size_t count); size_t strnlen(const char *s, size_t maxlen); unsigned int atou(const char *s); +unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base); /* tty.c */ void puts(const char *); diff --git a/arch/x86/boot/cmdline.c b/arch/x86/boot/cmdline.c index a1d35634bce..6b3b6f708c0 100644 --- a/arch/x86/boot/cmdline.c +++ b/arch/x86/boot/cmdline.c @@ -27,9 +27,8 @@ static inline int myisspace(u8 c) * Returns the length of the argument (regardless of if it was * truncated to fit in the buffer), or -1 on not found. */ -int cmdline_find_option(const char *option, char *buffer, int bufsize) +int __cmdline_find_option(u32 cmdline_ptr, const char *option, char *buffer, int bufsize) { - u32 cmdline_ptr = boot_params.hdr.cmd_line_ptr; addr_t cptr; char c; int len = -1; @@ -100,9 +99,8 @@ int cmdline_find_option(const char *option, char *buffer, int bufsize) * Returns the position of that option (starts counting with 1) * or 0 on not found */ -int cmdline_find_option_bool(const char *option) +int __cmdline_find_option_bool(u32 cmdline_ptr, const char *option) { - u32 cmdline_ptr = boot_params.hdr.cmd_line_ptr; addr_t cptr; char c; int pos = 0, wstart = 0; diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index fbb47daf245..0c229551eea 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -4,7 +4,7 @@ # create a compressed vmlinux image from the original vmlinux # -targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.lzo head_$(BITS).o misc.o piggy.o +targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.lzo head_$(BITS).o misc.o string.o cmdline.o early_serial_console.o piggy.o KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC @@ -23,7 +23,7 @@ LDFLAGS_vmlinux := -T hostprogs-y := mkpiggy -$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/piggy.o FORCE +$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o $(obj)/piggy.o FORCE $(call if_changed,ld) @: diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c new file mode 100644 index 00000000000..cb62f786990 --- /dev/null +++ b/arch/x86/boot/compressed/cmdline.c @@ -0,0 +1,21 @@ +#include "misc.h" + +static unsigned long fs; +static inline void set_fs(unsigned long seg) +{ + fs = seg << 4; /* shift it back */ +} +typedef unsigned long addr_t; +static inline char rdfs8(addr_t addr) +{ + return *((char *)(fs + addr)); +} +#include "../cmdline.c" +int cmdline_find_option(const char *option, char *buffer, int bufsize) +{ + return __cmdline_find_option(real_mode->hdr.cmd_line_ptr, option, buffer, bufsize); +} +int cmdline_find_option_bool(const char *option) +{ + return __cmdline_find_option_bool(real_mode->hdr.cmd_line_ptr, option); +} diff --git a/arch/x86/boot/compressed/early_serial_console.c b/arch/x86/boot/compressed/early_serial_console.c new file mode 100644 index 00000000000..261e81fb958 --- /dev/null +++ b/arch/x86/boot/compressed/early_serial_console.c @@ -0,0 +1,5 @@ +#include "misc.h" + +int early_serial_base; + +#include "../early_serial_console.c" diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index f543b70ffae..67a655a39ce 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -124,6 +124,19 @@ relocated: rep stosl /* + * Adjust our own GOT + */ + leal _got(%ebx), %edx + leal _egot(%ebx), %ecx +1: + cmpl %ecx, %edx + jae 2f + addl %ebx, (%edx) + addl $4, %edx + jmp 1b +2: + +/* * Do the decompression, and jump to the new kernel.. */ leal z_extract_offset_negative(%ebx), %ebp diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index faff0dc9c06..52f85a196fa 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -280,6 +280,19 @@ relocated: rep stosq /* + * Adjust our own GOT + */ + leaq _got(%rip), %rdx + leaq _egot(%rip), %rcx +1: + cmpq %rcx, %rdx + jae 2f + addq %rbx, (%rdx) + addq $8, %rdx + jmp 1b +2: + +/* * Do the decompression, and jump to the new kernel.. */ pushq %rsi /* Save the real mode argument */ diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 51e240779a4..8f7bef8e9ff 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -9,23 +9,7 @@ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996 */ -/* - * we have to be careful, because no indirections are allowed here, and - * paravirt_ops is a kind of one. As it will only run in baremetal anyway, - * we just keep it from happening - */ -#undef CONFIG_PARAVIRT -#ifdef CONFIG_X86_32 -#define _ASM_X86_DESC_H 1 -#endif - -#include <linux/linkage.h> -#include <linux/screen_info.h> -#include <linux/elf.h> -#include <linux/io.h> -#include <asm/page.h> -#include <asm/boot.h> -#include <asm/bootparam.h> +#include "misc.h" /* WARNING!! * This code is compiled with -fPIC and it is relocated dynamically @@ -123,15 +107,13 @@ static void error(char *m); /* * This is set up by the setup-routine at boot-time */ -static struct boot_params *real_mode; /* Pointer to real-mode data */ +struct boot_params *real_mode; /* Pointer to real-mode data */ static int quiet; +static int debug; void *memset(void *s, int c, size_t n); void *memcpy(void *dest, const void *src, size_t n); -static void __putstr(int, const char *); -#define putstr(__x) __putstr(0, __x) - #ifdef CONFIG_X86_64 #define memptr long #else @@ -170,7 +152,21 @@ static void scroll(void) vidmem[i] = ' '; } -static void __putstr(int error, const char *s) +#define XMTRDY 0x20 + +#define TXR 0 /* Transmit register (WRITE) */ +#define LSR 5 /* Line Status */ +static void serial_putchar(int ch) +{ + unsigned timeout = 0xffff; + + while ((inb(early_serial_base + LSR) & XMTRDY) == 0 && --timeout) + cpu_relax(); + + outb(ch, early_serial_base + TXR); +} + +void __putstr(int error, const char *s) { int x, y, pos; char c; @@ -179,6 +175,14 @@ static void __putstr(int error, const char *s) if (!error) return; #endif + if (early_serial_base) { + const char *str = s; + while (*str) { + if (*str == '\n') + serial_putchar('\r'); + serial_putchar(*str++); + } + } if (real_mode->screen_info.orig_video_mode == 0 && lines == 0 && cols == 0) @@ -305,8 +309,10 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, { real_mode = rmode; - if (real_mode->hdr.loadflags & QUIET_FLAG) + if (cmdline_find_option_bool("quiet")) quiet = 1; + if (cmdline_find_option_bool("debug")) + debug = 1; if (real_mode->screen_info.orig_video_mode == 7) { vidmem = (char *) 0xb0000; @@ -319,6 +325,10 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, lines = real_mode->screen_info.orig_video_lines; cols = real_mode->screen_info.orig_video_cols; + console_init(); + if (debug) + putstr("early console in decompress_kernel\n"); + free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h new file mode 100644 index 00000000000..3f19c81a620 --- /dev/null +++ b/arch/x86/boot/compressed/misc.h @@ -0,0 +1,39 @@ +#ifndef BOOT_COMPRESSED_MISC_H +#define BOOT_COMPRESSED_MISC_H + +/* + * we have to be careful, because no indirections are allowed here, and + * paravirt_ops is a kind of one. As it will only run in baremetal anyway, + * we just keep it from happening + */ +#undef CONFIG_PARAVIRT +#ifdef CONFIG_X86_32 +#define _ASM_X86_DESC_H 1 +#endif + +#include <linux/linkage.h> +#include <linux/screen_info.h> +#include <linux/elf.h> +#include <linux/io.h> +#include <asm/page.h> +#include <asm/boot.h> +#include <asm/bootparam.h> + +#define BOOT_BOOT_H +#include "../ctype.h" + +/* misc.c */ +extern struct boot_params *real_mode; /* Pointer to real-mode data */ +void __putstr(int error, const char *s); +#define putstr(__x) __putstr(0, __x) +#define puts(__x) __putstr(0, __x) + +/* cmdline.c */ +int cmdline_find_option(const char *option, char *buffer, int bufsize); +int cmdline_find_option_bool(const char *option); + +/* early_serial_console.c */ +extern int early_serial_base; +void console_init(void); + +#endif diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c index bcbd36c4143..5c228129d17 100644 --- a/arch/x86/boot/compressed/mkpiggy.c +++ b/arch/x86/boot/compressed/mkpiggy.c @@ -77,7 +77,7 @@ int main(int argc, char *argv[]) offs += 32*1024 + 18; /* Add 32K + 18 bytes slack */ offs = (offs+4095) & ~4095; /* Round to a 4K boundary */ - printf(".section \".rodata.compressed\",\"a\",@progbits\n"); + printf(".section \".rodata..compressed\",\"a\",@progbits\n"); printf(".globl z_input_len\n"); printf("z_input_len = %lu\n", ilen); printf(".globl z_output_len\n"); diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c new file mode 100644 index 00000000000..19b3e693cd7 --- /dev/null +++ b/arch/x86/boot/compressed/string.c @@ -0,0 +1,2 @@ +#include "misc.h" +#include "../string.c" diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index a6f1a59a5b0..34d047c9828 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -26,8 +26,8 @@ SECTIONS HEAD_TEXT _ehead = . ; } - .rodata.compressed : { - *(.rodata.compressed) + .rodata..compressed : { + *(.rodata..compressed) } .text : { _text = .; /* Text */ @@ -41,6 +41,12 @@ SECTIONS *(.rodata.*) _erodata = . ; } + .got : { + _got = .; + KEEP(*(.got.plt)) + KEEP(*(.got)) + _egot = .; + } .data : { _data = . ; *(.data) diff --git a/arch/x86/boot/ctype.h b/arch/x86/boot/ctype.h new file mode 100644 index 00000000000..25e13403193 --- /dev/null +++ b/arch/x86/boot/ctype.h @@ -0,0 +1,21 @@ +#ifndef BOOT_ISDIGIT_H + +#define BOOT_ISDIGIT_H + +static inline int isdigit(int ch) +{ + return (ch >= '0') && (ch <= '9'); +} + +static inline int isxdigit(int ch) +{ + if (isdigit(ch)) + return true; + + if ((ch >= 'a') && (ch <= 'f')) + return true; + + return (ch >= 'A') && (ch <= 'F'); +} + +#endif diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c new file mode 100644 index 00000000000..030f4b93e25 --- /dev/null +++ b/arch/x86/boot/early_serial_console.c @@ -0,0 +1,139 @@ +#include "boot.h" + +#define DEFAULT_SERIAL_PORT 0x3f8 /* ttyS0 */ + +#define XMTRDY 0x20 + +#define DLAB 0x80 + +#define TXR 0 /* Transmit register (WRITE) */ +#define RXR 0 /* Receive register (READ) */ +#define IER 1 /* Interrupt Enable */ +#define IIR 2 /* Interrupt ID */ +#define FCR 2 /* FIFO control */ +#define LCR 3 /* Line control */ +#define MCR 4 /* Modem control */ +#define LSR 5 /* Line Status */ +#define MSR 6 /* Modem Status */ +#define DLL 0 /* Divisor Latch Low */ +#define DLH 1 /* Divisor latch High */ + +#define DEFAULT_BAUD 9600 + +static void early_serial_init(int port, int baud) +{ + unsigned char c; + unsigned divisor; + + outb(0x3, port + LCR); /* 8n1 */ + outb(0, port + IER); /* no interrupt */ + outb(0, port + FCR); /* no fifo */ + outb(0x3, port + MCR); /* DTR + RTS */ + + divisor = 115200 / baud; + c = inb(port + LCR); + outb(c | DLAB, port + LCR); + outb(divisor & 0xff, port + DLL); + outb((divisor >> 8) & 0xff, port + DLH); + outb(c & ~DLAB, port + LCR); + + early_serial_base = port; +} + +static void parse_earlyprintk(void) +{ + int baud = DEFAULT_BAUD; + char arg[32]; + int pos = 0; + int port = 0; + + if (cmdline_find_option("earlyprintk", arg, sizeof arg) > 0) { + char *e; + + if (!strncmp(arg, "serial", 6)) { + port = DEFAULT_SERIAL_PORT; + pos += 6; + } + + if (arg[pos] == ',') + pos++; + + if (!strncmp(arg, "ttyS", 4)) { + static const int bases[] = { 0x3f8, 0x2f8 }; + int idx = 0; + + if (!strncmp(arg + pos, "ttyS", 4)) + pos += 4; + + if (arg[pos++] == '1') + idx = 1; + + port = bases[idx]; + } + + if (arg[pos] == ',') + pos++; + + baud = simple_strtoull(arg + pos, &e, 0); + if (baud == 0 || arg + pos == e) + baud = DEFAULT_BAUD; + } + + if (port) + early_serial_init(port, baud); +} + +#define BASE_BAUD (1843200/16) +static unsigned int probe_baud(int port) +{ + unsigned char lcr, dll, dlh; + unsigned int quot; + + lcr = inb(port + LCR); + outb(lcr | DLAB, port + LCR); + dll = inb(port + DLL); + dlh = inb(port + DLH); + outb(lcr, port + LCR); + quot = (dlh << 8) | dll; + + return BASE_BAUD / quot; +} + +static void parse_console_uart8250(void) +{ + char optstr[64], *options; + int baud = DEFAULT_BAUD; + int port = 0; + + /* + * console=uart8250,io,0x3f8,115200n8 + * need to make sure it is last one console ! + */ + if (cmdline_find_option("console", optstr, sizeof optstr) <= 0) + return; + + options = optstr; + + if (!strncmp(options, "uart8250,io,", 12)) + port = simple_strtoull(options + 12, &options, 0); + else if (!strncmp(options, "uart,io,", 8)) + port = simple_strtoull(options + 8, &options, 0); + else + return; + + if (options && (options[0] == ',')) + baud = simple_strtoull(options + 1, &options, 0); + else + baud = probe_baud(port); + + if (port) + early_serial_init(port, baud); +} + +void console_init(void) +{ + parse_earlyprintk(); + + if (!early_serial_base) + parse_console_uart8250(); +} diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index 140172b895b..40358c8905b 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -130,6 +130,11 @@ void main(void) /* First, copy the boot header into the "zeropage" */ copy_boot_params(); + /* Initialize the early-boot console */ + console_init(); + if (cmdline_find_option_bool("debug")) + puts("early console in setup code\n"); + /* End of heap check */ init_heap(); @@ -168,10 +173,6 @@ void main(void) /* Set the video mode */ set_video(); - /* Parse command line for 'quiet' and pass it to decompressor. */ - if (cmdline_find_option_bool("quiet")) - boot_params.hdr.loadflags |= QUIET_FLAG; - /* Do the last things and invoke protected mode */ go_to_protected_mode(); } diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c index 50e47cdbddd..cdac91ca55d 100644 --- a/arch/x86/boot/printf.c +++ b/arch/x86/boot/printf.c @@ -34,7 +34,7 @@ static int skip_atoi(const char **s) #define SMALL 32 /* Must be 32 == 0x20 */ #define SPECIAL 64 /* 0x */ -#define do_div(n,base) ({ \ +#define __do_div(n, base) ({ \ int __res; \ __res = ((unsigned long) n) % (unsigned) base; \ n = ((unsigned long) n) / (unsigned) base; \ @@ -83,7 +83,7 @@ static char *number(char *str, long num, int base, int size, int precision, tmp[i++] = '0'; else while (num != 0) - tmp[i++] = (digits[do_div(num, base)] | locase); + tmp[i++] = (digits[__do_div(num, base)] | locase); if (i > precision) precision = i; size -= precision; diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index f94b7a0c2ab..3cbc4058dd2 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -30,6 +30,22 @@ int strcmp(const char *str1, const char *str2) return 0; } +int strncmp(const char *cs, const char *ct, size_t count) +{ + unsigned char c1, c2; + + while (count) { + c1 = *cs++; + c2 = *ct++; + if (c1 != c2) + return c1 < c2 ? -1 : 1; + if (!c1) + break; + count--; + } + return 0; +} + size_t strnlen(const char *s, size_t maxlen) { const char *es = s; @@ -48,3 +64,50 @@ unsigned int atou(const char *s) i = i * 10 + (*s++ - '0'); return i; } + +/* Works only for digits and letters, but small and fast */ +#define TOLOWER(x) ((x) | 0x20) + +static unsigned int simple_guess_base(const char *cp) +{ + if (cp[0] == '0') { + if (TOLOWER(cp[1]) == 'x' && isxdigit(cp[2])) + return 16; + else + return 8; + } else { + return 10; + } +} + +/** + * simple_strtoull - convert a string to an unsigned long long + * @cp: The start of the string + * @endp: A pointer to the end of the parsed string will be placed here + * @base: The number base to use + */ + +unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) +{ + unsigned long long result = 0; + + if (!base) + base = simple_guess_base(cp); + + if (base == 16 && cp[0] == '0' && TOLOWER(cp[1]) == 'x') + cp += 2; + + while (isxdigit(*cp)) { + unsigned int value; + + value = isdigit(*cp) ? *cp - '0' : TOLOWER(*cp) - 'a' + 10; + if (value >= base) + break; + result = result * base + value; + cp++; + } + if (endp) + *endp = (char *)cp; + + return result; +} diff --git a/arch/x86/boot/tty.c b/arch/x86/boot/tty.c index 01ec69c901c..def2451f46a 100644 --- a/arch/x86/boot/tty.c +++ b/arch/x86/boot/tty.c @@ -10,23 +10,36 @@ * ----------------------------------------------------------------------- */ /* - * Very simple screen I/O - * XXX: Probably should add very simple serial I/O? + * Very simple screen and serial I/O */ #include "boot.h" +int early_serial_base; + +#define XMTRDY 0x20 + +#define TXR 0 /* Transmit register (WRITE) */ +#define LSR 5 /* Line Status */ + /* * These functions are in .inittext so they can be used to signal * error during initialization. */ -void __attribute__((section(".inittext"))) putchar(int ch) +static void __attribute__((section(".inittext"))) serial_putchar(int ch) { - struct biosregs ireg; + unsigned timeout = 0xffff; - if (ch == '\n') - putchar('\r'); /* \n -> \r\n */ + while ((inb(early_serial_base + LSR) & XMTRDY) == 0 && --timeout) + cpu_relax(); + + outb(ch, early_serial_base + TXR); +} + +static void __attribute__((section(".inittext"))) bios_putchar(int ch) +{ + struct biosregs ireg; initregs(&ireg); ireg.bx = 0x0007; @@ -36,6 +49,17 @@ void __attribute__((section(".inittext"))) putchar(int ch) intcall(0x10, &ireg, NULL); } +void __attribute__((section(".inittext"))) putchar(int ch) +{ + if (ch == '\n') + putchar('\r'); /* \n -> \r\n */ + + bios_putchar(ch); + + if (early_serial_base != 0) + serial_putchar(ch); +} + void __attribute__((section(".inittext"))) puts(const char *str) { while (*str) @@ -112,3 +136,4 @@ int getchar_timeout(void) return 0; /* Timeout! */ } + diff --git a/arch/x86/boot/video-vga.c b/arch/x86/boot/video-vga.c index ed7aeff786b..45bc9402aa4 100644 --- a/arch/x86/boot/video-vga.c +++ b/arch/x86/boot/video-vga.c @@ -41,13 +41,12 @@ static __videocard video_vga; static u8 vga_set_basic_mode(void) { struct biosregs ireg, oreg; - u16 ax; u8 mode; initregs(&ireg); /* Query current mode */ - ax = 0x0f00; + ireg.ax = 0x0f00; intcall(0x10, &ireg, &oreg); mode = oreg.al; diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index d28fad19654..e3a32431ca1 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -1471,6 +1471,7 @@ CONFIG_HWMON=y # CONFIG_SENSORS_GL518SM is not set # CONFIG_SENSORS_GL520SM is not set # CONFIG_SENSORS_CORETEMP is not set +# CONFIG_SENSORS_PKGTEMP is not set # CONFIG_SENSORS_IT87 is not set # CONFIG_SENSORS_LM63 is not set # CONFIG_SENSORS_LM75 is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 6c86acd847a..4251f837205 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -1456,6 +1456,7 @@ CONFIG_HWMON=y # CONFIG_SENSORS_GL518SM is not set # CONFIG_SENSORS_GL520SM is not set # CONFIG_SENSORS_CORETEMP is not set +# CONFIG_SENSORS_PKGTEMP is not set # CONFIG_SENSORS_IT87 is not set # CONFIG_SENSORS_LM63 is not set # CONFIG_SENSORS_LM75 is not set diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 20bb0e1ac68..ff16756a51c 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -32,6 +32,9 @@ #define IN IN1 #define KEY %xmm2 #define IV %xmm3 +#define BSWAP_MASK %xmm10 +#define CTR %xmm11 +#define INC %xmm12 #define KEYP %rdi #define OUTP %rsi @@ -42,6 +45,7 @@ #define T1 %r10 #define TKEYP T1 #define T2 %r11 +#define TCTR_LOW T2 _key_expansion_128: _key_expansion_256a: @@ -724,3 +728,114 @@ ENTRY(aesni_cbc_dec) movups IV, (IVP) .Lcbc_dec_just_ret: ret + +.align 16 +.Lbswap_mask: + .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0 + +/* + * _aesni_inc_init: internal ABI + * setup registers used by _aesni_inc + * input: + * IV + * output: + * CTR: == IV, in little endian + * TCTR_LOW: == lower qword of CTR + * INC: == 1, in little endian + * BSWAP_MASK == endian swapping mask + */ +_aesni_inc_init: + movaps .Lbswap_mask, BSWAP_MASK + movaps IV, CTR + PSHUFB_XMM BSWAP_MASK CTR + mov $1, TCTR_LOW + MOVQ_R64_XMM TCTR_LOW INC + MOVQ_R64_XMM CTR TCTR_LOW + ret + +/* + * _aesni_inc: internal ABI + * Increase IV by 1, IV is in big endian + * input: + * IV + * CTR: == IV, in little endian + * TCTR_LOW: == lower qword of CTR + * INC: == 1, in little endian + * BSWAP_MASK == endian swapping mask + * output: + * IV: Increase by 1 + * changed: + * CTR: == output IV, in little endian + * TCTR_LOW: == lower qword of CTR + */ +_aesni_inc: + paddq INC, CTR + add $1, TCTR_LOW + jnc .Linc_low + pslldq $8, INC + paddq INC, CTR + psrldq $8, INC +.Linc_low: + movaps CTR, IV + PSHUFB_XMM BSWAP_MASK IV + ret + +/* + * void aesni_ctr_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len, u8 *iv) + */ +ENTRY(aesni_ctr_enc) + cmp $16, LEN + jb .Lctr_enc_just_ret + mov 480(KEYP), KLEN + movups (IVP), IV + call _aesni_inc_init + cmp $64, LEN + jb .Lctr_enc_loop1 +.align 4 +.Lctr_enc_loop4: + movaps IV, STATE1 + call _aesni_inc + movups (INP), IN1 + movaps IV, STATE2 + call _aesni_inc + movups 0x10(INP), IN2 + movaps IV, STATE3 + call _aesni_inc + movups 0x20(INP), IN3 + movaps IV, STATE4 + call _aesni_inc + movups 0x30(INP), IN4 + call _aesni_enc4 + pxor IN1, STATE1 + movups STATE1, (OUTP) + pxor IN2, STATE2 + movups STATE2, 0x10(OUTP) + pxor IN3, STATE3 + movups STATE3, 0x20(OUTP) + pxor IN4, STATE4 + movups STATE4, 0x30(OUTP) + sub $64, LEN + add $64, INP + add $64, OUTP + cmp $64, LEN + jge .Lctr_enc_loop4 + cmp $16, LEN + jb .Lctr_enc_ret +.align 4 +.Lctr_enc_loop1: + movaps IV, STATE + call _aesni_inc + movups (INP), IN + call _aesni_enc1 + pxor IN, STATE + movups STATE, (OUTP) + sub $16, LEN + add $16, INP + add $16, OUTP + cmp $16, LEN + jge .Lctr_enc_loop1 +.Lctr_enc_ret: + movups IV, (IVP) +.Lctr_enc_just_ret: + ret diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 49c552c060e..2cb3dcc4490 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -18,6 +18,7 @@ #include <crypto/algapi.h> #include <crypto/aes.h> #include <crypto/cryptd.h> +#include <crypto/ctr.h> #include <asm/i387.h> #include <asm/aes.h> @@ -58,6 +59,8 @@ asmlinkage void aesni_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in, unsigned int len, u8 *iv); asmlinkage void aesni_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in, unsigned int len, u8 *iv); +asmlinkage void aesni_ctr_enc(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv); static inline struct crypto_aes_ctx *aes_ctx(void *raw_ctx) { @@ -321,6 +324,72 @@ static struct crypto_alg blk_cbc_alg = { }, }; +static void ctr_crypt_final(struct crypto_aes_ctx *ctx, + struct blkcipher_walk *walk) +{ + u8 *ctrblk = walk->iv; + u8 keystream[AES_BLOCK_SIZE]; + u8 *src = walk->src.virt.addr; + u8 *dst = walk->dst.virt.addr; + unsigned int nbytes = walk->nbytes; + + aesni_enc(ctx, keystream, ctrblk); + crypto_xor(keystream, src, nbytes); + memcpy(dst, keystream, nbytes); + crypto_inc(ctrblk, AES_BLOCK_SIZE); +} + +static int ctr_crypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_blkcipher_ctx(desc->tfm)); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + + kernel_fpu_begin(); + while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { + aesni_ctr_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + if (walk.nbytes) { + ctr_crypt_final(ctx, &walk); + err = blkcipher_walk_done(desc, &walk, 0); + } + kernel_fpu_end(); + + return err; +} + +static struct crypto_alg blk_ctr_alg = { + .cra_name = "__ctr-aes-aesni", + .cra_driver_name = "__driver-ctr-aes-aesni", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct crypto_aes_ctx)+AESNI_ALIGN-1, + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(blk_ctr_alg.cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = aes_set_key, + .encrypt = ctr_crypt, + .decrypt = ctr_crypt, + }, + }, +}; + static int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key, unsigned int key_len) { @@ -467,13 +536,11 @@ static struct crypto_alg ablk_cbc_alg = { }, }; -#ifdef HAS_CTR static int ablk_ctr_init(struct crypto_tfm *tfm) { struct cryptd_ablkcipher *cryptd_tfm; - cryptd_tfm = cryptd_alloc_ablkcipher("fpu(ctr(__driver-aes-aesni))", - 0, 0); + cryptd_tfm = cryptd_alloc_ablkcipher("__driver-ctr-aes-aesni", 0, 0); if (IS_ERR(cryptd_tfm)) return PTR_ERR(cryptd_tfm); ablk_init_common(tfm, cryptd_tfm); @@ -500,11 +567,50 @@ static struct crypto_alg ablk_ctr_alg = { .ivsize = AES_BLOCK_SIZE, .setkey = ablk_set_key, .encrypt = ablk_encrypt, - .decrypt = ablk_decrypt, + .decrypt = ablk_encrypt, .geniv = "chainiv", }, }, }; + +#ifdef HAS_CTR +static int ablk_rfc3686_ctr_init(struct crypto_tfm *tfm) +{ + struct cryptd_ablkcipher *cryptd_tfm; + + cryptd_tfm = cryptd_alloc_ablkcipher( + "rfc3686(__driver-ctr-aes-aesni)", 0, 0); + if (IS_ERR(cryptd_tfm)) + return PTR_ERR(cryptd_tfm); + ablk_init_common(tfm, cryptd_tfm); + return 0; +} + +static struct crypto_alg ablk_rfc3686_ctr_alg = { + .cra_name = "rfc3686(ctr(aes))", + .cra_driver_name = "rfc3686-ctr-aes-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct async_aes_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(ablk_rfc3686_ctr_alg.cra_list), + .cra_init = ablk_rfc3686_ctr_init, + .cra_exit = ablk_exit, + .cra_u = { + .ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE+CTR_RFC3686_NONCE_SIZE, + .max_keysize = AES_MAX_KEY_SIZE+CTR_RFC3686_NONCE_SIZE, + .ivsize = CTR_RFC3686_IV_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + .geniv = "seqiv", + }, + }, +}; #endif #ifdef HAS_LRW @@ -640,13 +746,17 @@ static int __init aesni_init(void) goto blk_ecb_err; if ((err = crypto_register_alg(&blk_cbc_alg))) goto blk_cbc_err; + if ((err = crypto_register_alg(&blk_ctr_alg))) + goto blk_ctr_err; if ((err = crypto_register_alg(&ablk_ecb_alg))) goto ablk_ecb_err; if ((err = crypto_register_alg(&ablk_cbc_alg))) goto ablk_cbc_err; -#ifdef HAS_CTR if ((err = crypto_register_alg(&ablk_ctr_alg))) goto ablk_ctr_err; +#ifdef HAS_CTR + if ((err = crypto_register_alg(&ablk_rfc3686_ctr_alg))) + goto ablk_rfc3686_ctr_err; #endif #ifdef HAS_LRW if ((err = crypto_register_alg(&ablk_lrw_alg))) @@ -675,13 +785,17 @@ ablk_pcbc_err: ablk_lrw_err: #endif #ifdef HAS_CTR + crypto_unregister_alg(&ablk_rfc3686_ctr_alg); +ablk_rfc3686_ctr_err: +#endif crypto_unregister_alg(&ablk_ctr_alg); ablk_ctr_err: -#endif crypto_unregister_alg(&ablk_cbc_alg); ablk_cbc_err: crypto_unregister_alg(&ablk_ecb_alg); ablk_ecb_err: + crypto_unregister_alg(&blk_ctr_alg); +blk_ctr_err: crypto_unregister_alg(&blk_cbc_alg); blk_cbc_err: crypto_unregister_alg(&blk_ecb_alg); @@ -705,10 +819,12 @@ static void __exit aesni_exit(void) crypto_unregister_alg(&ablk_lrw_alg); #endif #ifdef HAS_CTR - crypto_unregister_alg(&ablk_ctr_alg); + crypto_unregister_alg(&ablk_rfc3686_ctr_alg); #endif + crypto_unregister_alg(&ablk_ctr_alg); crypto_unregister_alg(&ablk_cbc_alg); crypto_unregister_alg(&ablk_ecb_alg); + crypto_unregister_alg(&blk_ctr_alg); crypto_unregister_alg(&blk_cbc_alg); crypto_unregister_alg(&blk_ecb_alg); crypto_unregister_alg(&__aesni_alg); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index e790bc1fbfa..b86feabed69 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -842,4 +842,7 @@ ia32_sys_call_table: .quad compat_sys_rt_tgsigqueueinfo /* 335 */ .quad sys_perf_event_open .quad compat_sys_recvmmsg + .quad sys_fanotify_init + .quad sys32_fanotify_mark + .quad sys_prlimit64 /* 340 */ ia32_syscall_end: diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 626be156d88..3d093311d5e 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -546,3 +546,12 @@ asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo, return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, ((u64)len_hi << 32) | len_lo); } + +asmlinkage long sys32_fanotify_mark(int fanotify_fd, unsigned int flags, + u32 mask_lo, u32 mask_hi, + int fd, const char __user *pathname) +{ + return sys_fanotify_mark(fanotify_fd, flags, + ((u64)mask_hi << 32) | mask_lo, + fd, pathname); +} diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 56f462cf22d..92091de1111 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -85,7 +85,6 @@ extern int acpi_ioapic; extern int acpi_noirq; extern int acpi_strict; extern int acpi_disabled; -extern int acpi_ht; extern int acpi_pci_disabled; extern int acpi_skip_timer_override; extern int acpi_use_timer_override; @@ -97,7 +96,6 @@ void acpi_pic_sci_set_trigger(unsigned int, u16); static inline void disable_acpi(void) { acpi_disabled = 1; - acpi_ht = 0; acpi_pci_disabled = 1; acpi_noirq = 1; } @@ -136,7 +134,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) boot_cpu_data.x86_model <= 0x05 && boot_cpu_data.x86_mask < 0x0A) return 1; - else if (boot_cpu_has(X86_FEATURE_AMDC1E)) + else if (c1e_detected) return 1; else return max_cstate; diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index b97f786a48d..a63a68be1cc 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -6,8 +6,8 @@ .macro LOCK_PREFIX 1: lock .section .smp_locks,"a" - _ASM_ALIGN - _ASM_PTR 1b + .balign 4 + .long 1b - . .previous .endm #else diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index b09ec55650b..bc6abb7bc7e 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -28,27 +28,26 @@ */ #ifdef CONFIG_SMP -#define LOCK_PREFIX \ +#define LOCK_PREFIX_HERE \ ".section .smp_locks,\"a\"\n" \ - _ASM_ALIGN "\n" \ - _ASM_PTR "661f\n" /* address */ \ + ".balign 4\n" \ + ".long 671f - .\n" /* offset */ \ ".previous\n" \ - "661:\n\tlock; " + "671:" + +#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; " #else /* ! CONFIG_SMP */ +#define LOCK_PREFIX_HERE "" #define LOCK_PREFIX "" #endif -/* This must be included *after* the definition of LOCK_PREFIX */ -#include <asm/cpufeature.h> - struct alt_instr { u8 *instr; /* original instruction */ u8 *replacement; - u8 cpuid; /* cpuid bit set for replacement */ + u16 cpuid; /* cpuid bit set for replacement */ u8 instrlen; /* length of original instruction */ u8 replacementlen; /* length of new instruction, <= instrlen */ - u8 pad1; #ifdef CONFIG_X86_64 u32 pad2; #endif @@ -86,9 +85,11 @@ static inline int alternatives_text_reserved(void *start, void *end) _ASM_ALIGN "\n" \ _ASM_PTR "661b\n" /* label */ \ _ASM_PTR "663f\n" /* new instruction */ \ - " .byte " __stringify(feature) "\n" /* feature bit */ \ + " .word " __stringify(feature) "\n" /* feature bit */ \ " .byte 662b-661b\n" /* sourcelen */ \ " .byte 664f-663f\n" /* replacementlen */ \ + ".previous\n" \ + ".section .discard,\"aw\",@progbits\n" \ " .byte 0xff + (664f-663f) - (662b-661b)\n" /* rlen <= slen */ \ ".previous\n" \ ".section .altinstr_replacement, \"ax\"\n" \ @@ -96,6 +97,12 @@ static inline int alternatives_text_reserved(void *start, void *end) ".previous" /* + * This must be included *after* the definition of ALTERNATIVE due to + * <asm/arch_hweight.h> + */ +#include <asm/cpufeature.h> + +/* * Alternative instructions for different CPU types or capabilities. * * This allows to use optimized instructions even on generic binary diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h index 86a0ff0aeac..7014e88bc77 100644 --- a/arch/x86/include/asm/amd_iommu_types.h +++ b/arch/x86/include/asm/amd_iommu_types.h @@ -174,6 +174,40 @@ (~((1ULL << (12 + ((lvl) * 9))) - 1))) #define PM_ALIGNED(lvl, addr) ((PM_MAP_MASK(lvl) & (addr)) == (addr)) +/* + * Returns the page table level to use for a given page size + * Pagesize is expected to be a power-of-two + */ +#define PAGE_SIZE_LEVEL(pagesize) \ + ((__ffs(pagesize) - 12) / 9) +/* + * Returns the number of ptes to use for a given page size + * Pagesize is expected to be a power-of-two + */ +#define PAGE_SIZE_PTE_COUNT(pagesize) \ + (1ULL << ((__ffs(pagesize) - 12) % 9)) + +/* + * Aligns a given io-virtual address to a given page size + * Pagesize is expected to be a power-of-two + */ +#define PAGE_SIZE_ALIGN(address, pagesize) \ + ((address) & ~((pagesize) - 1)) +/* + * Creates an IOMMU PTE for an address an a given pagesize + * The PTE has no permission bits set + * Pagesize is expected to be a power-of-two larger than 4096 + */ +#define PAGE_SIZE_PTE(address, pagesize) \ + (((address) | ((pagesize) - 1)) & \ + (~(pagesize >> 1)) & PM_ADDR_MASK) + +/* + * Takes a PTE value with mode=0x07 and returns the page size it maps + */ +#define PTE_PAGE_SIZE(pte) \ + (1ULL << (1 + ffz(((pte) | 0xfffULL)))) + #define IOMMU_PTE_P (1ULL << 0) #define IOMMU_PTE_TV (1ULL << 1) #define IOMMU_PTE_U (1ULL << 59) diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h index c74a2eebe57..a69b1ac9eaf 100644 --- a/arch/x86/include/asm/apb_timer.h +++ b/arch/x86/include/asm/apb_timer.h @@ -55,7 +55,6 @@ extern unsigned long apbt_quick_calibrate(void); extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu); extern void apbt_setup_secondary_clock(void); extern unsigned int boot_cpu_id; -extern int disable_apbt_percpu; extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint); extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index b4ac2cdcb64..1fa03e04ae4 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -373,6 +373,7 @@ extern atomic_t init_deasserted; extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip); #endif +#ifdef CONFIG_X86_LOCAL_APIC static inline u32 apic_read(u32 reg) { return apic->read(reg); @@ -403,10 +404,19 @@ static inline u32 safe_apic_wait_icr_idle(void) return apic->safe_wait_icr_idle(); } +#else /* CONFIG_X86_LOCAL_APIC */ + +static inline u32 apic_read(u32 reg) { return 0; } +static inline void apic_write(u32 reg, u32 val) { } +static inline u64 apic_icr_read(void) { return 0; } +static inline void apic_icr_write(u32 low, u32 high) { } +static inline void apic_wait_icr_idle(void) { } +static inline u32 safe_apic_wait_icr_idle(void) { return 0; } + +#endif /* CONFIG_X86_LOCAL_APIC */ static inline void ack_APIC_irq(void) { -#ifdef CONFIG_X86_LOCAL_APIC /* * ack_APIC_irq() actually gets compiled as a single instruction * ... yummie. @@ -414,7 +424,6 @@ static inline void ack_APIC_irq(void) /* Docs say use 0 for future compatibility */ apic_write(APIC_EOI, 0); -#endif } static inline unsigned default_get_apic_id(unsigned long x) diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h new file mode 100644 index 00000000000..9686c3d9ff7 --- /dev/null +++ b/arch/x86/include/asm/arch_hweight.h @@ -0,0 +1,61 @@ +#ifndef _ASM_X86_HWEIGHT_H +#define _ASM_X86_HWEIGHT_H + +#ifdef CONFIG_64BIT +/* popcnt %edi, %eax -- redundant REX prefix for alignment */ +#define POPCNT32 ".byte 0xf3,0x40,0x0f,0xb8,0xc7" +/* popcnt %rdi, %rax */ +#define POPCNT64 ".byte 0xf3,0x48,0x0f,0xb8,0xc7" +#define REG_IN "D" +#define REG_OUT "a" +#else +/* popcnt %eax, %eax */ +#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc0" +#define REG_IN "a" +#define REG_OUT "a" +#endif + +/* + * __sw_hweightXX are called from within the alternatives below + * and callee-clobbered registers need to be taken care of. See + * ARCH_HWEIGHT_CFLAGS in <arch/x86/Kconfig> for the respective + * compiler switches. + */ +static inline unsigned int __arch_hweight32(unsigned int w) +{ + unsigned int res = 0; + + asm (ALTERNATIVE("call __sw_hweight32", POPCNT32, X86_FEATURE_POPCNT) + : "="REG_OUT (res) + : REG_IN (w)); + + return res; +} + +static inline unsigned int __arch_hweight16(unsigned int w) +{ + return __arch_hweight32(w & 0xffff); +} + +static inline unsigned int __arch_hweight8(unsigned int w) +{ + return __arch_hweight32(w & 0xff); +} + +static inline unsigned long __arch_hweight64(__u64 w) +{ + unsigned long res = 0; + +#ifdef CONFIG_X86_32 + return __arch_hweight32((u32)w) + + __arch_hweight32((u32)(w >> 32)); +#else + asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT) + : "="REG_OUT (res) + : REG_IN (w)); +#endif /* CONFIG_X86_32 */ + + return res; +} + +#endif diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 8f8217b9bda..952a826ac4e 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -22,7 +22,7 @@ */ static inline int atomic_read(const atomic_t *v) { - return v->counter; + return (*(volatile int *)&(v)->counter); } /** @@ -246,6 +246,29 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) +/* + * atomic_dec_if_positive - decrement by 1 if old value positive + * @v: pointer of type atomic_t + * + * The function returns the old value of *v minus 1, even if + * the atomic variable, v, was not decremented. + */ +static inline int atomic_dec_if_positive(atomic_t *v) +{ + int c, old, dec; + c = atomic_read(v); + for (;;) { + dec = c - 1; + if (unlikely(dec < 0)) + break; + old = atomic_cmpxchg((v), c, dec); + if (likely(old == c)) + break; + c = old; + } + return dec; +} + /** * atomic_inc_short - increment of a short integer * @v: pointer to type int diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 03027bf28de..2a934aa19a4 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -14,109 +14,193 @@ typedef struct { #define ATOMIC64_INIT(val) { (val) } -extern u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val); +#ifdef CONFIG_X86_CMPXCHG64 +#define ATOMIC64_ALTERNATIVE_(f, g) "call atomic64_" #g "_cx8" +#else +#define ATOMIC64_ALTERNATIVE_(f, g) ALTERNATIVE("call atomic64_" #f "_386", "call atomic64_" #g "_cx8", X86_FEATURE_CX8) +#endif + +#define ATOMIC64_ALTERNATIVE(f) ATOMIC64_ALTERNATIVE_(f, f) + +/** + * atomic64_cmpxchg - cmpxchg atomic64 variable + * @p: pointer to type atomic64_t + * @o: expected value + * @n: new value + * + * Atomically sets @v to @n if it was equal to @o and returns + * the old value. + */ + +static inline long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n) +{ + return cmpxchg64(&v->counter, o, n); +} /** * atomic64_xchg - xchg atomic64 variable - * @ptr: pointer to type atomic64_t - * @new_val: value to assign + * @v: pointer to type atomic64_t + * @n: value to assign * - * Atomically xchgs the value of @ptr to @new_val and returns + * Atomically xchgs the value of @v to @n and returns * the old value. */ -extern u64 atomic64_xchg(atomic64_t *ptr, u64 new_val); +static inline long long atomic64_xchg(atomic64_t *v, long long n) +{ + long long o; + unsigned high = (unsigned)(n >> 32); + unsigned low = (unsigned)n; + asm volatile(ATOMIC64_ALTERNATIVE(xchg) + : "=A" (o), "+b" (low), "+c" (high) + : "S" (v) + : "memory" + ); + return o; +} /** * atomic64_set - set atomic64 variable - * @ptr: pointer to type atomic64_t - * @new_val: value to assign + * @v: pointer to type atomic64_t + * @n: value to assign * - * Atomically sets the value of @ptr to @new_val. + * Atomically sets the value of @v to @n. */ -extern void atomic64_set(atomic64_t *ptr, u64 new_val); +static inline void atomic64_set(atomic64_t *v, long long i) +{ + unsigned high = (unsigned)(i >> 32); + unsigned low = (unsigned)i; + asm volatile(ATOMIC64_ALTERNATIVE(set) + : "+b" (low), "+c" (high) + : "S" (v) + : "eax", "edx", "memory" + ); +} /** * atomic64_read - read atomic64 variable - * @ptr: pointer to type atomic64_t + * @v: pointer to type atomic64_t * - * Atomically reads the value of @ptr and returns it. + * Atomically reads the value of @v and returns it. */ -static inline u64 atomic64_read(atomic64_t *ptr) +static inline long long atomic64_read(atomic64_t *v) { - u64 res; - - /* - * Note, we inline this atomic64_t primitive because - * it only clobbers EAX/EDX and leaves the others - * untouched. We also (somewhat subtly) rely on the - * fact that cmpxchg8b returns the current 64-bit value - * of the memory location we are touching: - */ - asm volatile( - "mov %%ebx, %%eax\n\t" - "mov %%ecx, %%edx\n\t" - LOCK_PREFIX "cmpxchg8b %1\n" - : "=&A" (res) - : "m" (*ptr) - ); - - return res; -} - -extern u64 atomic64_read(atomic64_t *ptr); + long long r; + asm volatile(ATOMIC64_ALTERNATIVE(read) + : "=A" (r), "+c" (v) + : : "memory" + ); + return r; + } /** * atomic64_add_return - add and return - * @delta: integer value to add - * @ptr: pointer to type atomic64_t + * @i: integer value to add + * @v: pointer to type atomic64_t * - * Atomically adds @delta to @ptr and returns @delta + *@ptr + * Atomically adds @i to @v and returns @i + *@v */ -extern u64 atomic64_add_return(u64 delta, atomic64_t *ptr); +static inline long long atomic64_add_return(long long i, atomic64_t *v) +{ + asm volatile(ATOMIC64_ALTERNATIVE(add_return) + : "+A" (i), "+c" (v) + : : "memory" + ); + return i; +} /* * Other variants with different arithmetic operators: */ -extern u64 atomic64_sub_return(u64 delta, atomic64_t *ptr); -extern u64 atomic64_inc_return(atomic64_t *ptr); -extern u64 atomic64_dec_return(atomic64_t *ptr); +static inline long long atomic64_sub_return(long long i, atomic64_t *v) +{ + asm volatile(ATOMIC64_ALTERNATIVE(sub_return) + : "+A" (i), "+c" (v) + : : "memory" + ); + return i; +} + +static inline long long atomic64_inc_return(atomic64_t *v) +{ + long long a; + asm volatile(ATOMIC64_ALTERNATIVE(inc_return) + : "=A" (a) + : "S" (v) + : "memory", "ecx" + ); + return a; +} + +static inline long long atomic64_dec_return(atomic64_t *v) +{ + long long a; + asm volatile(ATOMIC64_ALTERNATIVE(dec_return) + : "=A" (a) + : "S" (v) + : "memory", "ecx" + ); + return a; +} /** * atomic64_add - add integer to atomic64 variable - * @delta: integer value to add - * @ptr: pointer to type atomic64_t + * @i: integer value to add + * @v: pointer to type atomic64_t * - * Atomically adds @delta to @ptr. + * Atomically adds @i to @v. */ -extern void atomic64_add(u64 delta, atomic64_t *ptr); +static inline long long atomic64_add(long long i, atomic64_t *v) +{ + asm volatile(ATOMIC64_ALTERNATIVE_(add, add_return) + : "+A" (i), "+c" (v) + : : "memory" + ); + return i; +} /** * atomic64_sub - subtract the atomic64 variable - * @delta: integer value to subtract - * @ptr: pointer to type atomic64_t + * @i: integer value to subtract + * @v: pointer to type atomic64_t * - * Atomically subtracts @delta from @ptr. + * Atomically subtracts @i from @v. */ -extern void atomic64_sub(u64 delta, atomic64_t *ptr); +static inline long long atomic64_sub(long long i, atomic64_t *v) +{ + asm volatile(ATOMIC64_ALTERNATIVE_(sub, sub_return) + : "+A" (i), "+c" (v) + : : "memory" + ); + return i; +} /** * atomic64_sub_and_test - subtract value from variable and test result - * @delta: integer value to subtract - * @ptr: pointer to type atomic64_t - * - * Atomically subtracts @delta from @ptr and returns + * @i: integer value to subtract + * @v: pointer to type atomic64_t + * + * Atomically subtracts @i from @v and returns * true if the result is zero, or false for all * other cases. */ -extern int atomic64_sub_and_test(u64 delta, atomic64_t *ptr); +static inline int atomic64_sub_and_test(long long i, atomic64_t *v) +{ + return atomic64_sub_return(i, v) == 0; +} /** * atomic64_inc - increment atomic64 variable - * @ptr: pointer to type atomic64_t + * @v: pointer to type atomic64_t * - * Atomically increments @ptr by 1. + * Atomically increments @v by 1. */ -extern void atomic64_inc(atomic64_t *ptr); +static inline void atomic64_inc(atomic64_t *v) +{ + asm volatile(ATOMIC64_ALTERNATIVE_(inc, inc_return) + : : "S" (v) + : "memory", "eax", "ecx", "edx" + ); +} /** * atomic64_dec - decrement atomic64 variable @@ -124,37 +208,97 @@ extern void atomic64_inc(atomic64_t *ptr); * * Atomically decrements @ptr by 1. */ -extern void atomic64_dec(atomic64_t *ptr); +static inline void atomic64_dec(atomic64_t *v) +{ + asm volatile(ATOMIC64_ALTERNATIVE_(dec, dec_return) + : : "S" (v) + : "memory", "eax", "ecx", "edx" + ); +} /** * atomic64_dec_and_test - decrement and test - * @ptr: pointer to type atomic64_t + * @v: pointer to type atomic64_t * - * Atomically decrements @ptr by 1 and + * Atomically decrements @v by 1 and * returns true if the result is 0, or false for all other * cases. */ -extern int atomic64_dec_and_test(atomic64_t *ptr); +static inline int atomic64_dec_and_test(atomic64_t *v) +{ + return atomic64_dec_return(v) == 0; +} /** * atomic64_inc_and_test - increment and test - * @ptr: pointer to type atomic64_t + * @v: pointer to type atomic64_t * - * Atomically increments @ptr by 1 + * Atomically increments @v by 1 * and returns true if the result is zero, or false for all * other cases. */ -extern int atomic64_inc_and_test(atomic64_t *ptr); +static inline int atomic64_inc_and_test(atomic64_t *v) +{ + return atomic64_inc_return(v) == 0; +} /** * atomic64_add_negative - add and test if negative - * @delta: integer value to add - * @ptr: pointer to type atomic64_t + * @i: integer value to add + * @v: pointer to type atomic64_t * - * Atomically adds @delta to @ptr and returns true + * Atomically adds @i to @v and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ -extern int atomic64_add_negative(u64 delta, atomic64_t *ptr); +static inline int atomic64_add_negative(long long i, atomic64_t *v) +{ + return atomic64_add_return(i, v) < 0; +} + +/** + * atomic64_add_unless - add unless the number is a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as it was not @u. + * Returns non-zero if @v was not @u, and zero otherwise. + */ +static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) +{ + unsigned low = (unsigned)u; + unsigned high = (unsigned)(u >> 32); + asm volatile(ATOMIC64_ALTERNATIVE(add_unless) "\n\t" + : "+A" (a), "+c" (v), "+S" (low), "+D" (high) + : : "memory"); + return (int)a; +} + + +static inline int atomic64_inc_not_zero(atomic64_t *v) +{ + int r; + asm volatile(ATOMIC64_ALTERNATIVE(inc_not_zero) + : "=a" (r) + : "S" (v) + : "ecx", "edx", "memory" + ); + return r; +} + +static inline long long atomic64_dec_if_positive(atomic64_t *v) +{ + long long r; + asm volatile(ATOMIC64_ALTERNATIVE(dec_if_positive) + : "=A" (r) + : "S" (v) + : "ecx", "memory" + ); + return r; +} + +#undef ATOMIC64_ALTERNATIVE +#undef ATOMIC64_ALTERNATIVE_ #endif /* _ASM_X86_ATOMIC64_32_H */ diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 51c5b405692..49fd1ea2295 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -18,7 +18,7 @@ */ static inline long atomic64_read(const atomic64_t *v) { - return v->counter; + return (*(volatile long *)&(v)->counter); } /** @@ -221,4 +221,27 @@ static inline int atomic64_add_unless(atomic64_t *v, long a, long u) #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) +/* + * atomic64_dec_if_positive - decrement by 1 if old value positive + * @v: pointer of type atomic_t + * + * The function returns the old value of *v minus 1, even if + * the atomic variable, v, was not decremented. + */ +static inline long atomic64_dec_if_positive(atomic64_t *v) +{ + long c, old, dec; + c = atomic64_read(v); + for (;;) { + dec = c - 1; + if (unlikely(dec < 0)) + break; + old = atomic64_cmpxchg((v), c, dec); + if (likely(old == c)) + break; + c = old; + } + return dec; +} + #endif /* _ASM_X86_ATOMIC64_64_H */ diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 02b47a603fc..545776efeb1 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -444,7 +444,9 @@ static inline int fls(int x) #define ARCH_HAS_FAST_MULTIPLIER 1 -#include <asm-generic/bitops/hweight.h> +#include <asm/arch_hweight.h> + +#include <asm-generic/bitops/const_hweight.h> #endif /* __KERNEL__ */ diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 7a1065958ba..3b62ab56c7a 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -24,7 +24,7 @@ #define MIN_KERNEL_ALIGN (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2) #if (CONFIG_PHYSICAL_ALIGN & (CONFIG_PHYSICAL_ALIGN-1)) || \ - (CONFIG_PHYSICAL_ALIGN < (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2)) + (CONFIG_PHYSICAL_ALIGN < MIN_KERNEL_ALIGN) #error "Invalid value for CONFIG_PHYSICAL_ALIGN" #endif diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h index 6be33d83c71..8e6218550e7 100644 --- a/arch/x86/include/asm/bootparam.h +++ b/arch/x86/include/asm/bootparam.h @@ -70,6 +70,14 @@ struct sys_desc_table { __u8 table[14]; }; +/* Gleaned from OFW's set-parameters in cpu/x86/pc/linux.fth */ +struct olpc_ofw_header { + __u32 ofw_magic; /* OFW signature */ + __u32 ofw_version; + __u32 cif_handler; /* callback into OFW */ + __u32 irq_desc_table; +} __attribute__((packed)); + struct efi_info { __u32 efi_loader_signature; __u32 efi_systab; @@ -92,7 +100,8 @@ struct boot_params { __u8 hd0_info[16]; /* obsolete! */ /* 0x080 */ __u8 hd1_info[16]; /* obsolete! */ /* 0x090 */ struct sys_desc_table sys_desc_table; /* 0x0a0 */ - __u8 _pad4[144]; /* 0x0b0 */ + struct olpc_ofw_header olpc_ofw_header; /* 0x0b0 */ + __u8 _pad4[128]; /* 0x0c0 */ struct edid_info edid_info; /* 0x140 */ struct efi_info efi_info; /* 0x1c0 */ __u32 alt_mem_k; /* 0x1e0 */ diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h index 2f9047cfaac..48f99f15452 100644 --- a/arch/x86/include/asm/cache.h +++ b/arch/x86/include/asm/cache.h @@ -7,7 +7,7 @@ #define L1_CACHE_SHIFT (CONFIG_X86_L1_CACHE_SHIFT) #define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) -#define __read_mostly __attribute__((__section__(".data.read_mostly"))) +#define __read_mostly __attribute__((__section__(".data..read_mostly"))) #define INTERNODE_CACHE_SHIFT CONFIG_X86_INTERNODE_CACHE_SHIFT #define INTERNODE_CACHE_BYTES (1 << INTERNODE_CACHE_SHIFT) diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 634c40a739a..63e35ec9075 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -44,9 +44,6 @@ static inline void copy_from_user_page(struct vm_area_struct *vma, memcpy(dst, src, len); } -#define PG_WC PG_arch_1 -PAGEFLAG(WC, WC) - #ifdef CONFIG_X86_PAT /* * X86 PAT uses page flags WC and Uncached together to keep track of @@ -55,16 +52,24 @@ PAGEFLAG(WC, WC) * _PAGE_CACHE_UC_MINUS and fourth state where page's memory type has not * been changed from its default (value of -1 used to denote this). * Note we do not support _PAGE_CACHE_UC here. - * - * Caller must hold memtype_lock for atomicity. */ + +#define _PGMT_DEFAULT 0 +#define _PGMT_WC (1UL << PG_arch_1) +#define _PGMT_UC_MINUS (1UL << PG_uncached) +#define _PGMT_WB (1UL << PG_uncached | 1UL << PG_arch_1) +#define _PGMT_MASK (1UL << PG_uncached | 1UL << PG_arch_1) +#define _PGMT_CLEAR_MASK (~_PGMT_MASK) + static inline unsigned long get_page_memtype(struct page *pg) { - if (!PageUncached(pg) && !PageWC(pg)) + unsigned long pg_flags = pg->flags & _PGMT_MASK; + + if (pg_flags == _PGMT_DEFAULT) return -1; - else if (!PageUncached(pg) && PageWC(pg)) + else if (pg_flags == _PGMT_WC) return _PAGE_CACHE_WC; - else if (PageUncached(pg) && !PageWC(pg)) + else if (pg_flags == _PGMT_UC_MINUS) return _PAGE_CACHE_UC_MINUS; else return _PAGE_CACHE_WB; @@ -72,25 +77,26 @@ static inline unsigned long get_page_memtype(struct page *pg) static inline void set_page_memtype(struct page *pg, unsigned long memtype) { + unsigned long memtype_flags = _PGMT_DEFAULT; + unsigned long old_flags; + unsigned long new_flags; + switch (memtype) { case _PAGE_CACHE_WC: - ClearPageUncached(pg); - SetPageWC(pg); + memtype_flags = _PGMT_WC; break; case _PAGE_CACHE_UC_MINUS: - SetPageUncached(pg); - ClearPageWC(pg); + memtype_flags = _PGMT_UC_MINUS; break; case _PAGE_CACHE_WB: - SetPageUncached(pg); - SetPageWC(pg); - break; - default: - case -1: - ClearPageUncached(pg); - ClearPageWC(pg); + memtype_flags = _PGMT_WB; break; } + + do { + old_flags = pg->flags; + new_flags = (old_flags & _PGMT_CLEAR_MASK) | memtype_flags; + } while (cmpxchg(&pg->flags, old_flags, new_flags) != old_flags); } #else static inline unsigned long get_page_memtype(struct page *pg) { return -1; } @@ -139,9 +145,11 @@ int set_memory_np(unsigned long addr, int numpages); int set_memory_4k(unsigned long addr, int numpages); int set_memory_array_uc(unsigned long *addr, int addrinarray); +int set_memory_array_wc(unsigned long *addr, int addrinarray); int set_memory_array_wb(unsigned long *addr, int addrinarray); int set_pages_array_uc(struct page **pages, int addrinarray); +int set_pages_array_wc(struct page **pages, int addrinarray); int set_pages_array_wb(struct page **pages, int addrinarray); /* diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index ffb9bb6b6c3..284a6e8f7ce 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -11,38 +11,42 @@ extern void __xchg_wrong_size(void); /* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway - * Note 2: xchg has side effect, so that attribute volatile is necessary, - * but generally the primitive is invalid, *ptr is output argument. --ANK + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway. + * Since this is generally used to protect other memory information, we + * use "asm volatile" and "memory" clobbers to prevent gcc from moving + * information around. */ - -struct __xchg_dummy { - unsigned long a[100]; -}; -#define __xg(x) ((struct __xchg_dummy *)(x)) - #define __xchg(x, ptr, size) \ ({ \ __typeof(*(ptr)) __x = (x); \ switch (size) { \ case 1: \ - asm volatile("xchgb %b0,%1" \ - : "=q" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile("xchgb %0,%1" \ + : "=q" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile("xchgw %w0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile("xchgw %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 4: \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ asm volatile("xchgl %0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ default: \ __xchg_wrong_size(); \ } \ @@ -53,60 +57,33 @@ struct __xchg_dummy { __xchg((v), (ptr), sizeof(*ptr)) /* - * The semantics of XCHGCMP8B are a bit strange, this is why - * there is a loop and the loading of %%eax and %%edx has to - * be inside. This inlines well in most cases, the cached - * cost is around ~38 cycles. (in the future we might want - * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that - * might have an implicit FPU-save as a cost, so it's not - * clear which path to go.) + * CMPXCHG8B only writes to the target if we had the previous + * value in registers, otherwise it acts as a read and gives us the + * "new previous" value. That is why there is a loop. Preloading + * EDX:EAX is a performance optimization: in the common case it means + * we need only one locked operation. + * + * A SIMD/3DNOW!/MMX/FPU 64-bit store here would require at the very + * least an FPU save and/or %cr0.ts manipulation. * - * cmpxchg8b must be used with the lock prefix here to allow - * the instruction to be executed atomically, see page 3-102 - * of the instruction set reference 24319102.pdf. We need - * the reader side to see the coherent 64bit value. + * cmpxchg8b must be used with the lock prefix here to allow the + * instruction to be executed atomically. We need to have the reader + * side to see the coherent 64bit value. */ -static inline void __set_64bit(unsigned long long *ptr, - unsigned int low, unsigned int high) +static inline void set_64bit(volatile u64 *ptr, u64 value) { + u32 low = value; + u32 high = value >> 32; + u64 prev = *ptr; + asm volatile("\n1:\t" - "movl (%0), %%eax\n\t" - "movl 4(%0), %%edx\n\t" - LOCK_PREFIX "cmpxchg8b (%0)\n\t" + LOCK_PREFIX "cmpxchg8b %0\n\t" "jnz 1b" - : /* no outputs */ - : "D"(ptr), - "b"(low), - "c"(high) - : "ax", "dx", "memory"); -} - -static inline void __set_64bit_constant(unsigned long long *ptr, - unsigned long long value) -{ - __set_64bit(ptr, (unsigned int)value, (unsigned int)(value >> 32)); -} - -#define ll_low(x) *(((unsigned int *)&(x)) + 0) -#define ll_high(x) *(((unsigned int *)&(x)) + 1) - -static inline void __set_64bit_var(unsigned long long *ptr, - unsigned long long value) -{ - __set_64bit(ptr, ll_low(value), ll_high(value)); + : "=m" (*ptr), "+A" (prev) + : "b" (low), "c" (high) + : "memory"); } -#define set_64bit(ptr, value) \ - (__builtin_constant_p((value)) \ - ? __set_64bit_constant((ptr), (value)) \ - : __set_64bit_var((ptr), (value))) - -#define _set_64bit(ptr, value) \ - (__builtin_constant_p(value) \ - ? __set_64bit(ptr, (unsigned int)(value), \ - (unsigned int)((value) >> 32)) \ - : __set_64bit(ptr, ll_low((value)), ll_high((value)))) - extern void __cmpxchg_wrong_size(void); /* @@ -121,23 +98,32 @@ extern void __cmpxchg_wrong_size(void); __typeof__(*(ptr)) __new = (new); \ switch (size) { \ case 1: \ - asm volatile(lock "cmpxchgb %b1,%2" \ - : "=a"(__ret) \ - : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile(lock "cmpxchgb %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "q" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile(lock "cmpxchgw %w1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile(lock "cmpxchgw %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 4: \ - asm volatile(lock "cmpxchgl %1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile(lock "cmpxchgl %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ default: \ __cmpxchg_wrong_size(); \ } \ @@ -175,32 +161,28 @@ extern void __cmpxchg_wrong_size(void); (unsigned long long)(n))) #endif -static inline unsigned long long __cmpxchg64(volatile void *ptr, - unsigned long long old, - unsigned long long new) +static inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new) { - unsigned long long prev; - asm volatile(LOCK_PREFIX "cmpxchg8b %3" - : "=A"(prev) - : "b"((unsigned long)new), - "c"((unsigned long)(new >> 32)), - "m"(*__xg(ptr)), - "0"(old) + u64 prev; + asm volatile(LOCK_PREFIX "cmpxchg8b %1" + : "=A" (prev), + "+m" (*ptr) + : "b" ((u32)new), + "c" ((u32)(new >> 32)), + "0" (old) : "memory"); return prev; } -static inline unsigned long long __cmpxchg64_local(volatile void *ptr, - unsigned long long old, - unsigned long long new) +static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new) { - unsigned long long prev; - asm volatile("cmpxchg8b %3" - : "=A"(prev) - : "b"((unsigned long)new), - "c"((unsigned long)(new >> 32)), - "m"(*__xg(ptr)), - "0"(old) + u64 prev; + asm volatile("cmpxchg8b %1" + : "=A" (prev), + "+m" (*ptr) + : "b" ((u32)new), + "c" ((u32)(new >> 32)), + "0" (old) : "memory"); return prev; } @@ -264,14 +246,13 @@ static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old, * to simulate the cmpxchg8b on the 80386 and 80486 CPU. */ -extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64); - #define cmpxchg64(ptr, o, n) \ ({ \ __typeof__(*(ptr)) __ret; \ __typeof__(*(ptr)) __old = (o); \ __typeof__(*(ptr)) __new = (n); \ - alternative_io("call cmpxchg8b_emu", \ + alternative_io(LOCK_PREFIX_HERE \ + "call cmpxchg8b_emu", \ "lock; cmpxchg8b (%%esi)" , \ X86_FEATURE_CX8, \ "=A" (__ret), \ @@ -282,20 +263,20 @@ extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64); __ret; }) - -#define cmpxchg64_local(ptr, o, n) \ -({ \ - __typeof__(*(ptr)) __ret; \ - if (likely(boot_cpu_data.x86 > 4)) \ - __ret = (__typeof__(*(ptr)))__cmpxchg64_local((ptr), \ - (unsigned long long)(o), \ - (unsigned long long)(n)); \ - else \ - __ret = (__typeof__(*(ptr)))cmpxchg_486_u64((ptr), \ - (unsigned long long)(o), \ - (unsigned long long)(n)); \ - __ret; \ -}) +#define cmpxchg64_local(ptr, o, n) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) __old = (o); \ + __typeof__(*(ptr)) __new = (n); \ + alternative_io("call cmpxchg8b_emu", \ + "cmpxchg8b (%%esi)" , \ + X86_FEATURE_CX8, \ + "=A" (__ret), \ + "S" ((ptr)), "0" (__old), \ + "b" ((unsigned int)__new), \ + "c" ((unsigned int)(__new>>32)) \ + : "memory"); \ + __ret; }) #endif diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 485ae415fae..423ae58aa02 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -3,51 +3,60 @@ #include <asm/alternative.h> /* Provides LOCK_PREFIX */ -#define __xg(x) ((volatile long *)(x)) - -static inline void set_64bit(volatile unsigned long *ptr, unsigned long val) +static inline void set_64bit(volatile u64 *ptr, u64 val) { *ptr = val; } -#define _set_64bit set_64bit - extern void __xchg_wrong_size(void); extern void __cmpxchg_wrong_size(void); /* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway - * Note 2: xchg has side effect, so that attribute volatile is necessary, - * but generally the primitive is invalid, *ptr is output argument. --ANK + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway. + * Since this is generally used to protect other memory information, we + * use "asm volatile" and "memory" clobbers to prevent gcc from moving + * information around. */ #define __xchg(x, ptr, size) \ ({ \ __typeof(*(ptr)) __x = (x); \ switch (size) { \ case 1: \ - asm volatile("xchgb %b0,%1" \ - : "=q" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile("xchgb %0,%1" \ + : "=q" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile("xchgw %w0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile("xchgw %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 4: \ - asm volatile("xchgl %k0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile("xchgl %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 8: \ + { \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ asm volatile("xchgq %0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ default: \ __xchg_wrong_size(); \ } \ @@ -71,29 +80,41 @@ extern void __cmpxchg_wrong_size(void); __typeof__(*(ptr)) __new = (new); \ switch (size) { \ case 1: \ - asm volatile(lock "cmpxchgb %b1,%2" \ - : "=a"(__ret) \ - : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile(lock "cmpxchgb %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "q" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile(lock "cmpxchgw %w1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile(lock "cmpxchgw %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 4: \ - asm volatile(lock "cmpxchgl %k1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile(lock "cmpxchgl %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 8: \ - asm volatile(lock "cmpxchgq %1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ + asm volatile(lock "cmpxchgq %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ default: \ __cmpxchg_wrong_size(); \ } \ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 0cd82d06861..781a50b29a4 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -6,7 +6,7 @@ #include <asm/required-features.h> -#define NCAPINTS 9 /* N 32-bit words worth of info */ +#define NCAPINTS 10 /* N 32-bit words worth of info */ /* * Note: If the comment begins with a quoted string, that string is used @@ -89,7 +89,7 @@ #define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */ #define X86_FEATURE_11AP (3*32+19) /* "" Bad local APIC aka 11AP */ #define X86_FEATURE_NOPL (3*32+20) /* The NOPL (0F 1F) instructions */ -#define X86_FEATURE_AMDC1E (3*32+21) /* AMD C1E detected */ + /* 21 available, was AMD_C1E */ #define X86_FEATURE_XTOPOLOGY (3*32+22) /* cpu topology enum extensions */ #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */ #define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */ @@ -124,6 +124,8 @@ #define X86_FEATURE_XSAVE (4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */ #define X86_FEATURE_OSXSAVE (4*32+27) /* "" XSAVE enabled in the OS */ #define X86_FEATURE_AVX (4*32+28) /* Advanced Vector Extensions */ +#define X86_FEATURE_F16C (4*32+29) /* 16-bit fp conversions */ +#define X86_FEATURE_RDRND (4*32+30) /* The RDRAND instruction */ #define X86_FEATURE_HYPERVISOR (4*32+31) /* Running on a hypervisor */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ @@ -157,24 +159,33 @@ /* * Auxiliary flags: Linux defined - For features scattered in various - * CPUID levels like 0x6, 0xA etc + * CPUID levels like 0x6, 0xA etc, word 7 */ #define X86_FEATURE_IDA (7*32+ 0) /* Intel Dynamic Acceleration */ #define X86_FEATURE_ARAT (7*32+ 1) /* Always Running APIC Timer */ +#define X86_FEATURE_CPB (7*32+ 2) /* AMD Core Performance Boost */ +#define X86_FEATURE_EPB (7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_XSAVEOPT (7*32+ 4) /* Optimized Xsave */ +#define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */ -/* Virtualization flags: Linux defined */ +/* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW (8*32+ 0) /* Intel TPR Shadow */ #define X86_FEATURE_VNMI (8*32+ 1) /* Intel Virtual NMI */ #define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */ #define X86_FEATURE_EPT (8*32+ 3) /* Intel Extended Page Table */ #define X86_FEATURE_VPID (8*32+ 4) /* Intel Virtual Processor ID */ -#define X86_FEATURE_NPT (8*32+5) /* AMD Nested Page Table support */ -#define X86_FEATURE_LBRV (8*32+6) /* AMD LBR Virtualization support */ -#define X86_FEATURE_SVML (8*32+7) /* "svm_lock" AMD SVM locking MSR */ -#define X86_FEATURE_NRIPS (8*32+8) /* "nrip_save" AMD SVM next_rip save */ +#define X86_FEATURE_NPT (8*32+ 5) /* AMD Nested Page Table support */ +#define X86_FEATURE_LBRV (8*32+ 6) /* AMD LBR Virtualization support */ +#define X86_FEATURE_SVML (8*32+ 7) /* "svm_lock" AMD SVM locking MSR */ +#define X86_FEATURE_NRIPS (8*32+ 8) /* "nrip_save" AMD SVM next_rip save */ + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ +#define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) +#include <asm/asm.h> #include <linux/bitops.h> extern const char * const x86_cap_flags[NCAPINTS*32]; @@ -192,7 +203,9 @@ extern const char * const x86_power_flags[32]; (((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4)) || \ (((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5)) || \ (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) || \ - (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) ) \ + (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) || \ + (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) || \ + (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) ) \ ? 1 : \ test_cpu_cap(c, bit)) @@ -283,6 +296,71 @@ extern const char * const x86_power_flags[32]; #endif /* CONFIG_X86_64 */ +/* + * Static testing of CPU features. Used the same as boot_cpu_has(). + * These are only valid after alternatives have run, but will statically + * patch the target code for additional performance. + * + */ +static __always_inline __pure bool __static_cpu_has(u16 bit) +{ +#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 5) + asm goto("1: jmp %l[t_no]\n" + "2:\n" + ".section .altinstructions,\"a\"\n" + _ASM_ALIGN "\n" + _ASM_PTR "1b\n" + _ASM_PTR "0\n" /* no replacement */ + " .word %P0\n" /* feature bit */ + " .byte 2b - 1b\n" /* source len */ + " .byte 0\n" /* replacement len */ + ".previous\n" + /* skipping size check since replacement size = 0 */ + : : "i" (bit) : : t_no); + return true; + t_no: + return false; +#else + u8 flag; + /* Open-coded due to __stringify() in ALTERNATIVE() */ + asm volatile("1: movb $0,%0\n" + "2:\n" + ".section .altinstructions,\"a\"\n" + _ASM_ALIGN "\n" + _ASM_PTR "1b\n" + _ASM_PTR "3f\n" + " .word %P1\n" /* feature bit */ + " .byte 2b - 1b\n" /* source len */ + " .byte 4f - 3f\n" /* replacement len */ + ".previous\n" + ".section .discard,\"aw\",@progbits\n" + " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */ + ".previous\n" + ".section .altinstr_replacement,\"ax\"\n" + "3: movb $1,%0\n" + "4:\n" + ".previous\n" + : "=qm" (flag) : "i" (bit)); + return flag; +#endif +} + +#if __GNUC__ >= 4 +#define static_cpu_has(bit) \ +( \ + __builtin_constant_p(boot_cpu_has(bit)) ? \ + boot_cpu_has(bit) : \ + __builtin_constant_p(bit) ? \ + __static_cpu_has(bit) : \ + boot_cpu_has(bit) \ +) +#else +/* + * gcc 3.x is too stupid to do the static test; fall back to dynamic. + */ +#define static_cpu_has(bit) boot_cpu_has(bit) +#endif + #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */ #endif /* _ASM_X86_CPUFEATURE_H */ diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index ac91eed2106..d4c419f883a 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -54,7 +54,6 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) -#define dma_is_consistent(d, h) (1) extern int dma_supported(struct device *hwdev, u64 mask); extern int dma_set_mask(struct device *dev, u64 mask); @@ -87,13 +86,6 @@ dma_cache_sync(struct device *dev, void *vaddr, size_t size, flush_write_buffers(); } -static inline int dma_get_cache_alignment(void) -{ - /* no easy way to get cache size on all x86, so return the - * maximum possible, to be safe */ - return boot_cpu_data.x86_clflush_size; -} - static inline unsigned long dma_alloc_coherent_mask(struct device *dev, gfp_t gfp) { diff --git a/arch/x86/include/asm/ds.h b/arch/x86/include/asm/ds.h deleted file mode 100644 index 70dac199b09..00000000000 --- a/arch/x86/include/asm/ds.h +++ /dev/null @@ -1,302 +0,0 @@ -/* - * Debug Store (DS) support - * - * This provides a low-level interface to the hardware's Debug Store - * feature that is used for branch trace store (BTS) and - * precise-event based sampling (PEBS). - * - * It manages: - * - DS and BTS hardware configuration - * - buffer overflow handling (to be done) - * - buffer access - * - * It does not do: - * - security checking (is the caller allowed to trace the task) - * - buffer allocation (memory accounting) - * - * - * Copyright (C) 2007-2009 Intel Corporation. - * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009 - */ - -#ifndef _ASM_X86_DS_H -#define _ASM_X86_DS_H - - -#include <linux/types.h> -#include <linux/init.h> -#include <linux/err.h> - - -#ifdef CONFIG_X86_DS - -struct task_struct; -struct ds_context; -struct ds_tracer; -struct bts_tracer; -struct pebs_tracer; - -typedef void (*bts_ovfl_callback_t)(struct bts_tracer *); -typedef void (*pebs_ovfl_callback_t)(struct pebs_tracer *); - - -/* - * A list of features plus corresponding macros to talk about them in - * the ds_request function's flags parameter. - * - * We use the enum to index an array of corresponding control bits; - * we use the macro to index a flags bit-vector. - */ -enum ds_feature { - dsf_bts = 0, - dsf_bts_kernel, -#define BTS_KERNEL (1 << dsf_bts_kernel) - /* trace kernel-mode branches */ - - dsf_bts_user, -#define BTS_USER (1 << dsf_bts_user) - /* trace user-mode branches */ - - dsf_bts_overflow, - dsf_bts_max, - dsf_pebs = dsf_bts_max, - - dsf_pebs_max, - dsf_ctl_max = dsf_pebs_max, - dsf_bts_timestamps = dsf_ctl_max, -#define BTS_TIMESTAMPS (1 << dsf_bts_timestamps) - /* add timestamps into BTS trace */ - -#define BTS_USER_FLAGS (BTS_KERNEL | BTS_USER | BTS_TIMESTAMPS) -}; - - -/* - * Request BTS or PEBS - * - * Due to alignement constraints, the actual buffer may be slightly - * smaller than the requested or provided buffer. - * - * Returns a pointer to a tracer structure on success, or - * ERR_PTR(errcode) on failure. - * - * The interrupt threshold is independent from the overflow callback - * to allow users to use their own overflow interrupt handling mechanism. - * - * The function might sleep. - * - * task: the task to request recording for - * cpu: the cpu to request recording for - * base: the base pointer for the (non-pageable) buffer; - * size: the size of the provided buffer in bytes - * ovfl: pointer to a function to be called on buffer overflow; - * NULL if cyclic buffer requested - * th: the interrupt threshold in records from the end of the buffer; - * -1 if no interrupt threshold is requested. - * flags: a bit-mask of the above flags - */ -extern struct bts_tracer *ds_request_bts_task(struct task_struct *task, - void *base, size_t size, - bts_ovfl_callback_t ovfl, - size_t th, unsigned int flags); -extern struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size, - bts_ovfl_callback_t ovfl, - size_t th, unsigned int flags); -extern struct pebs_tracer *ds_request_pebs_task(struct task_struct *task, - void *base, size_t size, - pebs_ovfl_callback_t ovfl, - size_t th, unsigned int flags); -extern struct pebs_tracer *ds_request_pebs_cpu(int cpu, - void *base, size_t size, - pebs_ovfl_callback_t ovfl, - size_t th, unsigned int flags); - -/* - * Release BTS or PEBS resources - * Suspend and resume BTS or PEBS tracing - * - * Must be called with irq's enabled. - * - * tracer: the tracer handle returned from ds_request_~() - */ -extern void ds_release_bts(struct bts_tracer *tracer); -extern void ds_suspend_bts(struct bts_tracer *tracer); -extern void ds_resume_bts(struct bts_tracer *tracer); -extern void ds_release_pebs(struct pebs_tracer *tracer); -extern void ds_suspend_pebs(struct pebs_tracer *tracer); -extern void ds_resume_pebs(struct pebs_tracer *tracer); - -/* - * Release BTS or PEBS resources - * Suspend and resume BTS or PEBS tracing - * - * Cpu tracers must call this on the traced cpu. - * Task tracers must call ds_release_~_noirq() for themselves. - * - * May be called with irq's disabled. - * - * Returns 0 if successful; - * -EPERM if the cpu tracer does not trace the current cpu. - * -EPERM if the task tracer does not trace itself. - * - * tracer: the tracer handle returned from ds_request_~() - */ -extern int ds_release_bts_noirq(struct bts_tracer *tracer); -extern int ds_suspend_bts_noirq(struct bts_tracer *tracer); -extern int ds_resume_bts_noirq(struct bts_tracer *tracer); -extern int ds_release_pebs_noirq(struct pebs_tracer *tracer); -extern int ds_suspend_pebs_noirq(struct pebs_tracer *tracer); -extern int ds_resume_pebs_noirq(struct pebs_tracer *tracer); - - -/* - * The raw DS buffer state as it is used for BTS and PEBS recording. - * - * This is the low-level, arch-dependent interface for working - * directly on the raw trace data. - */ -struct ds_trace { - /* the number of bts/pebs records */ - size_t n; - /* the size of a bts/pebs record in bytes */ - size_t size; - /* pointers into the raw buffer: - - to the first entry */ - void *begin; - /* - one beyond the last entry */ - void *end; - /* - one beyond the newest entry */ - void *top; - /* - the interrupt threshold */ - void *ith; - /* flags given on ds_request() */ - unsigned int flags; -}; - -/* - * An arch-independent view on branch trace data. - */ -enum bts_qualifier { - bts_invalid, -#define BTS_INVALID bts_invalid - - bts_branch, -#define BTS_BRANCH bts_branch - - bts_task_arrives, -#define BTS_TASK_ARRIVES bts_task_arrives - - bts_task_departs, -#define BTS_TASK_DEPARTS bts_task_departs - - bts_qual_bit_size = 4, - bts_qual_max = (1 << bts_qual_bit_size), -}; - -struct bts_struct { - __u64 qualifier; - union { - /* BTS_BRANCH */ - struct { - __u64 from; - __u64 to; - } lbr; - /* BTS_TASK_ARRIVES or BTS_TASK_DEPARTS */ - struct { - __u64 clock; - pid_t pid; - } event; - } variant; -}; - - -/* - * The BTS state. - * - * This gives access to the raw DS state and adds functions to provide - * an arch-independent view of the BTS data. - */ -struct bts_trace { - struct ds_trace ds; - - int (*read)(struct bts_tracer *tracer, const void *at, - struct bts_struct *out); - int (*write)(struct bts_tracer *tracer, const struct bts_struct *in); -}; - - -/* - * The PEBS state. - * - * This gives access to the raw DS state and the PEBS-specific counter - * reset value. - */ -struct pebs_trace { - struct ds_trace ds; - - /* the number of valid counters in the below array */ - unsigned int counters; - -#define MAX_PEBS_COUNTERS 4 - /* the counter reset value */ - unsigned long long counter_reset[MAX_PEBS_COUNTERS]; -}; - - -/* - * Read the BTS or PEBS trace. - * - * Returns a view on the trace collected for the parameter tracer. - * - * The view remains valid as long as the traced task is not running or - * the tracer is suspended. - * Writes into the trace buffer are not reflected. - * - * tracer: the tracer handle returned from ds_request_~() - */ -extern const struct bts_trace *ds_read_bts(struct bts_tracer *tracer); -extern const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer); - - -/* - * Reset the write pointer of the BTS/PEBS buffer. - * - * Returns 0 on success; -Eerrno on error - * - * tracer: the tracer handle returned from ds_request_~() - */ -extern int ds_reset_bts(struct bts_tracer *tracer); -extern int ds_reset_pebs(struct pebs_tracer *tracer); - -/* - * Set the PEBS counter reset value. - * - * Returns 0 on success; -Eerrno on error - * - * tracer: the tracer handle returned from ds_request_pebs() - * counter: the index of the counter - * value: the new counter reset value - */ -extern int ds_set_pebs_reset(struct pebs_tracer *tracer, - unsigned int counter, u64 value); - -/* - * Initialization - */ -struct cpuinfo_x86; -extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *); - -/* - * Context switch work - */ -extern void ds_switch_to(struct task_struct *prev, struct task_struct *next); - -#else /* CONFIG_X86_DS */ - -struct cpuinfo_x86; -static inline void __cpuinit ds_init_intel(struct cpuinfo_x86 *ignored) {} -static inline void ds_switch_to(struct task_struct *prev, - struct task_struct *next) {} - -#endif /* CONFIG_X86_DS */ -#endif /* _ASM_X86_DS_H */ diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h index ae6253ab902..733f7e91e7a 100644 --- a/arch/x86/include/asm/dwarf2.h +++ b/arch/x86/include/asm/dwarf2.h @@ -34,6 +34,18 @@ #define CFI_SIGNAL_FRAME #endif +#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__) + /* + * Emit CFI data in .debug_frame sections, not .eh_frame sections. + * The latter we currently just discard since we don't do DWARF + * unwinding at runtime. So only the offline DWARF information is + * useful to anyone. Note we should not use this directive if this + * file is used in the vDSO assembly, or if vmlinux.lds.S gets + * changed so it doesn't discard .eh_frame. + */ + .cfi_sections .debug_frame +#endif + #else /* diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 0e22296790d..ec8a52d14ab 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -45,7 +45,12 @@ #define E820_NVS 4 #define E820_UNUSABLE 5 -/* reserved RAM used by kernel itself */ +/* + * reserved RAM used by kernel itself + * if CONFIG_INTEL_TXT is enabled, memory of this type will be + * included in the S3 integrity calculation and so should not include + * any memory that BIOS might alter over the S3 transition + */ #define E820_RESERVED_KERN 128 #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 0f8576427cf..aeab29aee61 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -35,7 +35,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); #define __ARCH_IRQ_STAT -#define inc_irq_stat(member) percpu_add(irq_stat.member, 1) +#define inc_irq_stat(member) percpu_inc(irq_stat.member) #define local_softirq_pending() percpu_read(irq_stat.__softirq_pending) diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h index a726650fc80..8caac76ac32 100644 --- a/arch/x86/include/asm/highmem.h +++ b/arch/x86/include/asm/highmem.h @@ -61,7 +61,7 @@ void *kmap(struct page *page); void kunmap(struct page *page); void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot); void *kmap_atomic(struct page *page, enum km_type type); -void kunmap_atomic(void *kvaddr, enum km_type type); +void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type); void *kmap_atomic_pfn(unsigned long pfn, enum km_type type); void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot); struct page *kmap_atomic_to_page(void *ptr); diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index 1d5c08a1bdf..004e6e25e91 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -68,6 +68,7 @@ extern unsigned long force_hpet_address; extern u8 hpet_blockid; extern int hpet_force_user; extern u8 hpet_msi_disable; +extern u8 hpet_readback_cmp; extern int is_hpet_enabled(void); extern int hpet_enable(void); extern void hpet_disable(void); diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index 2a1bd8f4f23..528a11e8d3e 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -20,10 +20,10 @@ struct arch_hw_breakpoint { #include <linux/list.h> /* Available HW breakpoint length encodings */ +#define X86_BREAKPOINT_LEN_X 0x00 #define X86_BREAKPOINT_LEN_1 0x40 #define X86_BREAKPOINT_LEN_2 0x44 #define X86_BREAKPOINT_LEN_4 0x4c -#define X86_BREAKPOINT_LEN_EXECUTE 0x40 #ifdef CONFIG_X86_64 #define X86_BREAKPOINT_LEN_8 0x48 @@ -41,12 +41,16 @@ struct arch_hw_breakpoint { /* Total number of available HW breakpoint registers */ #define HBP_NUM 4 +static inline int hw_breakpoint_slots(int type) +{ + return HBP_NUM; +} + struct perf_event; struct pmu; -extern int arch_check_va_in_userspace(unsigned long va, u8 hbp_len); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp, - struct task_struct *tsk); +extern int arch_check_bp_in_kernelspace(struct perf_event *bp); +extern int arch_validate_hwbkpt_settings(struct perf_event *bp); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/x86/include/asm/hyperv.h b/arch/x86/include/asm/hyperv.h index e153a2b3889..5df477ac3af 100644 --- a/arch/x86/include/asm/hyperv.h +++ b/arch/x86/include/asm/hyperv.h @@ -1,5 +1,5 @@ -#ifndef _ASM_X86_KVM_HYPERV_H -#define _ASM_X86_KVM_HYPERV_H +#ifndef _ASM_X86_HYPERV_H +#define _ASM_X86_HYPERV_H #include <linux/types.h> @@ -14,6 +14,10 @@ #define HYPERV_CPUID_ENLIGHTMENT_INFO 0x40000004 #define HYPERV_CPUID_IMPLEMENT_LIMITS 0x40000005 +#define HYPERV_HYPERVISOR_PRESENT_BIT 0x80000000 +#define HYPERV_CPUID_MIN 0x40000005 +#define HYPERV_CPUID_MAX 0x4000ffff + /* * Feature identification. EAX indicates which features are available * to the partition based upon the current partition privileges. @@ -129,6 +133,9 @@ /* MSR used to provide vcpu index */ #define HV_X64_MSR_VP_INDEX 0x40000002 +/* MSR used to read the per-partition time reference counter */ +#define HV_X64_MSR_TIME_REF_COUNT 0x40000020 + /* Define the virtual APIC registers */ #define HV_X64_MSR_EOI 0x40000070 #define HV_X64_MSR_ICR 0x40000071 diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index b78c0941e42..ff2546ce717 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -17,10 +17,34 @@ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. * */ -#ifndef ASM_X86__HYPERVISOR_H -#define ASM_X86__HYPERVISOR_H +#ifndef _ASM_X86_HYPERVISOR_H +#define _ASM_X86_HYPERVISOR_H extern void init_hypervisor(struct cpuinfo_x86 *c); extern void init_hypervisor_platform(void); +/* + * x86 hypervisor information + */ +struct hypervisor_x86 { + /* Hypervisor name */ + const char *name; + + /* Detection routine */ + bool (*detect)(void); + + /* Adjust CPU feature bits (run once per CPU) */ + void (*set_cpu_features)(struct cpuinfo_x86 *); + + /* Platform setup (run once per boot) */ + void (*init_platform)(void); +}; + +extern const struct hypervisor_x86 *x86_hyper; + +/* Recognized hypervisors */ +extern const struct hypervisor_x86 x86_hyper_vmware; +extern const struct hypervisor_x86 x86_hyper_ms_hyperv; +extern const struct hypervisor_x86 x86_hyper_xen_hvm; + #endif diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index da293092450..a73a8d5a5e6 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -16,7 +16,9 @@ #include <linux/kernel_stat.h> #include <linux/regset.h> #include <linux/hardirq.h> +#include <linux/slab.h> #include <asm/asm.h> +#include <asm/cpufeature.h> #include <asm/processor.h> #include <asm/sigcontext.h> #include <asm/user.h> @@ -29,7 +31,6 @@ extern void mxcsr_feature_mask_init(void); extern int init_fpu(struct task_struct *child); extern asmlinkage void math_state_restore(void); extern void __math_state_restore(void); -extern void init_thread_xstate(void); extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); extern user_regset_active_fn fpregs_active, xfpregs_active; @@ -56,6 +57,25 @@ extern int restore_i387_xstate_ia32(void __user *buf); #define X87_FSW_ES (1 << 7) /* Exception Summary */ +static __always_inline __pure bool use_xsaveopt(void) +{ + return static_cpu_has(X86_FEATURE_XSAVEOPT); +} + +static __always_inline __pure bool use_xsave(void) +{ + return static_cpu_has(X86_FEATURE_XSAVE); +} + +extern void __sanitize_i387_state(struct task_struct *); + +static inline void sanitize_i387_state(struct task_struct *tsk) +{ + if (!use_xsaveopt()) + return; + __sanitize_i387_state(tsk); +} + #ifdef CONFIG_X86_64 /* Ignore delayed exceptions from user space */ @@ -91,15 +111,15 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx) values. The kernel data segment can be sometimes 0 and sometimes new user value. Both should be ok. Use the PDA as safe address because it should be already in L1. */ -static inline void clear_fpu_state(struct task_struct *tsk) +static inline void fpu_clear(struct fpu *fpu) { - struct xsave_struct *xstate = &tsk->thread.xstate->xsave; - struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave; + struct xsave_struct *xstate = &fpu->state->xsave; + struct i387_fxsave_struct *fx = &fpu->state->fxsave; /* * xsave header may indicate the init state of the FP. */ - if ((task_thread_info(tsk)->status & TS_XSAVE) && + if (use_xsave() && !(xstate->xsave_hdr.xstate_bv & XSTATE_FP)) return; @@ -111,10 +131,24 @@ static inline void clear_fpu_state(struct task_struct *tsk) X86_FEATURE_FXSAVE_LEAK); } +static inline void clear_fpu_state(struct task_struct *tsk) +{ + fpu_clear(&tsk->thread.fpu); +} + static inline int fxsave_user(struct i387_fxsave_struct __user *fx) { int err; + /* + * Clear the bytes not touched by the fxsave and reserved + * for the SW usage. + */ + err = __clear_user(&fx->sw_reserved, + sizeof(struct _fpx_sw_bytes)); + if (unlikely(err)) + return -EFAULT; + asm volatile("1: rex64/fxsave (%[fx])\n\t" "2:\n" ".section .fixup,\"ax\"\n" @@ -135,7 +169,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx) return err; } -static inline void fxsave(struct task_struct *tsk) +static inline void fpu_fxsave(struct fpu *fpu) { /* Using "rex64; fxsave %0" is broken because, if the memory operand uses any extended registers for addressing, a second REX prefix @@ -145,42 +179,45 @@ static inline void fxsave(struct task_struct *tsk) /* Using "fxsaveq %0" would be the ideal choice, but is only supported starting with gas 2.16. */ __asm__ __volatile__("fxsaveq %0" - : "=m" (tsk->thread.xstate->fxsave)); + : "=m" (fpu->state->fxsave)); #elif 0 /* Using, as a workaround, the properly prefixed form below isn't accepted by any binutils version so far released, complaining that the same type of prefix is used twice if an extended register is needed for addressing (fix submitted to mainline 2005-11-21). */ __asm__ __volatile__("rex64/fxsave %0" - : "=m" (tsk->thread.xstate->fxsave)); + : "=m" (fpu->state->fxsave)); #else /* This, however, we can work around by forcing the compiler to select an addressing mode that doesn't require extended registers. */ __asm__ __volatile__("rex64/fxsave (%1)" - : "=m" (tsk->thread.xstate->fxsave) - : "cdaSDb" (&tsk->thread.xstate->fxsave)); + : "=m" (fpu->state->fxsave) + : "cdaSDb" (&fpu->state->fxsave)); #endif } -static inline void __save_init_fpu(struct task_struct *tsk) +static inline void fpu_save_init(struct fpu *fpu) { - if (task_thread_info(tsk)->status & TS_XSAVE) - xsave(tsk); + if (use_xsave()) + fpu_xsave(fpu); else - fxsave(tsk); + fpu_fxsave(fpu); + + fpu_clear(fpu); +} - clear_fpu_state(tsk); +static inline void __save_init_fpu(struct task_struct *tsk) +{ + fpu_save_init(&tsk->thread.fpu); task_thread_info(tsk)->status &= ~TS_USEDFPU; } #else /* CONFIG_X86_32 */ #ifdef CONFIG_MATH_EMULATION -extern void finit_task(struct task_struct *tsk); +extern void finit_soft_fpu(struct i387_soft_struct *soft); #else -static inline void finit_task(struct task_struct *tsk) -{ -} +static inline void finit_soft_fpu(struct i387_soft_struct *soft) {} #endif static inline void tolerant_fwait(void) @@ -216,13 +253,13 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx) /* * These must be called with preempt disabled */ -static inline void __save_init_fpu(struct task_struct *tsk) +static inline void fpu_save_init(struct fpu *fpu) { - if (task_thread_info(tsk)->status & TS_XSAVE) { - struct xsave_struct *xstate = &tsk->thread.xstate->xsave; - struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave; + if (use_xsave()) { + struct xsave_struct *xstate = &fpu->state->xsave; + struct i387_fxsave_struct *fx = &fpu->state->fxsave; - xsave(tsk); + fpu_xsave(fpu); /* * xsave header may indicate the init state of the FP. @@ -246,8 +283,8 @@ static inline void __save_init_fpu(struct task_struct *tsk) "fxsave %[fx]\n" "bt $7,%[fsw] ; jnc 1f ; fnclex\n1:", X86_FEATURE_FXSR, - [fx] "m" (tsk->thread.xstate->fxsave), - [fsw] "m" (tsk->thread.xstate->fxsave.swd) : "memory"); + [fx] "m" (fpu->state->fxsave), + [fsw] "m" (fpu->state->fxsave.swd) : "memory"); clear_state: /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is pending. Clear the x87 state here by setting it to fixed @@ -259,17 +296,34 @@ clear_state: X86_FEATURE_FXSAVE_LEAK, [addr] "m" (safe_address)); end: + ; +} + +static inline void __save_init_fpu(struct task_struct *tsk) +{ + fpu_save_init(&tsk->thread.fpu); task_thread_info(tsk)->status &= ~TS_USEDFPU; } + #endif /* CONFIG_X86_64 */ -static inline int restore_fpu_checking(struct task_struct *tsk) +static inline int fpu_fxrstor_checking(struct fpu *fpu) +{ + return fxrstor_checking(&fpu->state->fxsave); +} + +static inline int fpu_restore_checking(struct fpu *fpu) { - if (task_thread_info(tsk)->status & TS_XSAVE) - return xrstor_checking(&tsk->thread.xstate->xsave); + if (use_xsave()) + return fpu_xrstor_checking(fpu); else - return fxrstor_checking(&tsk->thread.xstate->fxsave); + return fpu_fxrstor_checking(fpu); +} + +static inline int restore_fpu_checking(struct task_struct *tsk) +{ + return fpu_restore_checking(&tsk->thread.fpu); } /* @@ -397,30 +451,61 @@ static inline void clear_fpu(struct task_struct *tsk) static inline unsigned short get_fpu_cwd(struct task_struct *tsk) { if (cpu_has_fxsr) { - return tsk->thread.xstate->fxsave.cwd; + return tsk->thread.fpu.state->fxsave.cwd; } else { - return (unsigned short)tsk->thread.xstate->fsave.cwd; + return (unsigned short)tsk->thread.fpu.state->fsave.cwd; } } static inline unsigned short get_fpu_swd(struct task_struct *tsk) { if (cpu_has_fxsr) { - return tsk->thread.xstate->fxsave.swd; + return tsk->thread.fpu.state->fxsave.swd; } else { - return (unsigned short)tsk->thread.xstate->fsave.swd; + return (unsigned short)tsk->thread.fpu.state->fsave.swd; } } static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk) { if (cpu_has_xmm) { - return tsk->thread.xstate->fxsave.mxcsr; + return tsk->thread.fpu.state->fxsave.mxcsr; } else { return MXCSR_DEFAULT; } } +static bool fpu_allocated(struct fpu *fpu) +{ + return fpu->state != NULL; +} + +static inline int fpu_alloc(struct fpu *fpu) +{ + if (fpu_allocated(fpu)) + return 0; + fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL); + if (!fpu->state) + return -ENOMEM; + WARN_ON((unsigned long)fpu->state & 15); + return 0; +} + +static inline void fpu_free(struct fpu *fpu) +{ + if (fpu->state) { + kmem_cache_free(task_xstate_cachep, fpu->state); + fpu->state = NULL; + } +} + +static inline void fpu_copy(struct fpu *dst, struct fpu *src) +{ + memcpy(dst->state, src->state, xstate_size); +} + +extern void fpu_finit(struct fpu *fpu); + #endif /* __ASSEMBLY__ */ #define PSHUFB_XMM5_XMM0 .byte 0x66, 0x0f, 0x38, 0x00, 0xc5 diff --git a/arch/x86/include/asm/i8253.h b/arch/x86/include/asm/i8253.h index 1edbf89680f..fc1f579fb96 100644 --- a/arch/x86/include/asm/i8253.h +++ b/arch/x86/include/asm/i8253.h @@ -6,7 +6,7 @@ #define PIT_CH0 0x40 #define PIT_CH2 0x42 -extern spinlock_t i8253_lock; +extern raw_spinlock_t i8253_lock; extern struct clock_event_device *global_clock_event; diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index 96c2e0ad04c..88c765e1641 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -68,6 +68,8 @@ struct insn { const insn_byte_t *next_byte; }; +#define MAX_INSN_SIZE 16 + #define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6) #define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3) #define X86_MODRM_RM(modrm) ((modrm) & 0x07) diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h index 14cf526091f..280bf7fb6ab 100644 --- a/arch/x86/include/asm/inst.h +++ b/arch/x86/include/asm/inst.h @@ -7,7 +7,66 @@ #ifdef __ASSEMBLY__ +#define REG_NUM_INVALID 100 + +#define REG_TYPE_R64 0 +#define REG_TYPE_XMM 1 +#define REG_TYPE_INVALID 100 + + .macro R64_NUM opd r64 + \opd = REG_NUM_INVALID + .ifc \r64,%rax + \opd = 0 + .endif + .ifc \r64,%rcx + \opd = 1 + .endif + .ifc \r64,%rdx + \opd = 2 + .endif + .ifc \r64,%rbx + \opd = 3 + .endif + .ifc \r64,%rsp + \opd = 4 + .endif + .ifc \r64,%rbp + \opd = 5 + .endif + .ifc \r64,%rsi + \opd = 6 + .endif + .ifc \r64,%rdi + \opd = 7 + .endif + .ifc \r64,%r8 + \opd = 8 + .endif + .ifc \r64,%r9 + \opd = 9 + .endif + .ifc \r64,%r10 + \opd = 10 + .endif + .ifc \r64,%r11 + \opd = 11 + .endif + .ifc \r64,%r12 + \opd = 12 + .endif + .ifc \r64,%r13 + \opd = 13 + .endif + .ifc \r64,%r14 + \opd = 14 + .endif + .ifc \r64,%r15 + \opd = 15 + .endif + .endm + .macro XMM_NUM opd xmm + \opd = REG_NUM_INVALID .ifc \xmm,%xmm0 \opd = 0 .endif @@ -58,13 +117,25 @@ .endif .endm + .macro REG_TYPE type reg + R64_NUM reg_type_r64 \reg + XMM_NUM reg_type_xmm \reg + .if reg_type_r64 <> REG_NUM_INVALID + \type = REG_TYPE_R64 + .elseif reg_type_xmm <> REG_NUM_INVALID + \type = REG_TYPE_XMM + .else + \type = REG_TYPE_INVALID + .endif + .endm + .macro PFX_OPD_SIZE .byte 0x66 .endm - .macro PFX_REX opd1 opd2 - .if (\opd1 | \opd2) & 8 - .byte 0x40 | ((\opd1 & 8) >> 3) | ((\opd2 & 8) >> 1) + .macro PFX_REX opd1 opd2 W=0 + .if ((\opd1 | \opd2) & 8) || \W + .byte 0x40 | ((\opd1 & 8) >> 3) | ((\opd2 & 8) >> 1) | (\W << 3) .endif .endm @@ -145,6 +216,25 @@ .byte 0x0f, 0x38, 0xdf MODRM 0xc0 aesdeclast_opd1 aesdeclast_opd2 .endm + + .macro MOVQ_R64_XMM opd1 opd2 + REG_TYPE movq_r64_xmm_opd1_type \opd1 + .if movq_r64_xmm_opd1_type == REG_TYPE_XMM + XMM_NUM movq_r64_xmm_opd1 \opd1 + R64_NUM movq_r64_xmm_opd2 \opd2 + .else + R64_NUM movq_r64_xmm_opd1 \opd1 + XMM_NUM movq_r64_xmm_opd2 \opd2 + .endif + PFX_OPD_SIZE + PFX_REX movq_r64_xmm_opd1 movq_r64_xmm_opd2 1 + .if movq_r64_xmm_opd1_type == REG_TYPE_XMM + .byte 0x0f, 0x7e + .else + .byte 0x0f, 0x6e + .endif + MODRM 0xc0 movq_r64_xmm_opd1 movq_r64_xmm_opd2 + .endm #endif #endif diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h new file mode 100644 index 00000000000..29f66793cc5 --- /dev/null +++ b/arch/x86/include/asm/intel_scu_ipc.h @@ -0,0 +1,47 @@ +#ifndef _ASM_X86_INTEL_SCU_IPC_H_ +#define _ASM_X86_INTEL_SCU_IPC_H_ + +#define IPCMSG_VRTC 0xFA /* Set vRTC device */ + +/* Command id associated with message IPCMSG_VRTC */ +#define IPC_CMD_VRTC_SETTIME 1 /* Set time */ +#define IPC_CMD_VRTC_SETALARM 2 /* Set alarm */ + +/* Read single register */ +int intel_scu_ipc_ioread8(u16 addr, u8 *data); + +/* Read two sequential registers */ +int intel_scu_ipc_ioread16(u16 addr, u16 *data); + +/* Read four sequential registers */ +int intel_scu_ipc_ioread32(u16 addr, u32 *data); + +/* Read a vector */ +int intel_scu_ipc_readv(u16 *addr, u8 *data, int len); + +/* Write single register */ +int intel_scu_ipc_iowrite8(u16 addr, u8 data); + +/* Write two sequential registers */ +int intel_scu_ipc_iowrite16(u16 addr, u16 data); + +/* Write four sequential registers */ +int intel_scu_ipc_iowrite32(u16 addr, u32 data); + +/* Write a vector */ +int intel_scu_ipc_writev(u16 *addr, u8 *data, int len); + +/* Update single register based on the mask */ +int intel_scu_ipc_update_register(u16 addr, u8 data, u8 mask); + +/* Issue commands to the SCU with or without data */ +int intel_scu_ipc_simple_command(int cmd, int sub); +int intel_scu_ipc_command(int cmd, int sub, u32 *in, int inlen, + u32 *out, int outlen); +/* I2C control api */ +int intel_scu_ipc_i2c_cntrl(u32 addr, u32 *data); + +/* Update FW version */ +int intel_scu_ipc_fw_update(u8 *buffer, u32 length); + +#endif diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 35832a03a51..9cb2edb87c2 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -159,7 +159,6 @@ struct io_apic_irq_attr; extern int io_apic_set_pci_routing(struct device *dev, int irq, struct io_apic_irq_attr *irq_attr); void setup_IO_APIC_irq_extra(u32 gsi); -extern int (*ioapic_renumber_irq)(int ioapic, int irq); extern void ioapic_init_mappings(void); extern void ioapic_insert_resources(void); @@ -180,12 +179,13 @@ extern void ioapic_write_entry(int apic, int pin, extern void setup_ioapic_ids_from_mpc(void); struct mp_ioapic_gsi{ - int gsi_base; - int gsi_end; + u32 gsi_base; + u32 gsi_end; }; extern struct mp_ioapic_gsi mp_gsi_routing[]; -int mp_find_ioapic(int gsi); -int mp_find_ioapic_pin(int ioapic, int gsi); +extern u32 gsi_top; +int mp_find_ioapic(u32 gsi); +int mp_find_ioapic_pin(int ioapic, u32 gsi); void __init mp_register_ioapic(int id, u32 address, u32 gsi_base); extern void __init pre_init_apic_IRQ0(void); @@ -197,7 +197,8 @@ static const int timer_through_8259 = 0; static inline void ioapic_init_mappings(void) { } static inline void ioapic_insert_resources(void) { } static inline void probe_nr_irqs_gsi(void) { } -static inline int mp_find_ioapic(int gsi) { return 0; } +#define gsi_top (NR_IRQS_LEGACY) +static inline int mp_find_ioapic(u32 gsi) { return 0; } struct io_apic_irq_attr; static inline int io_apic_set_pci_routing(struct device *dev, int irq, diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 8767d99c4f6..e2ca3009255 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -125,6 +125,9 @@ */ #define MCE_SELF_VECTOR 0xeb +/* Xen vector callback to receive events in a HVM domain */ +#define XEN_HVM_EVTCHN_CALLBACK 0xe9 + #define NR_VECTORS 256 #define FPU_IRQ 13 diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h index e6c6c808489..396f5b5fc4d 100644 --- a/arch/x86/include/asm/kgdb.h +++ b/arch/x86/include/asm/kgdb.h @@ -39,9 +39,11 @@ enum regnames { GDB_FS, /* 14 */ GDB_GS, /* 15 */ }; +#define GDB_ORIG_AX 41 +#define DBG_MAX_REG_NUM 16 #define NUMREGBYTES ((GDB_GS+1)*4) #else /* ! CONFIG_X86_32 */ -enum regnames64 { +enum regnames { GDB_AX, /* 0 */ GDB_BX, /* 1 */ GDB_CX, /* 2 */ @@ -59,15 +61,15 @@ enum regnames64 { GDB_R14, /* 14 */ GDB_R15, /* 15 */ GDB_PC, /* 16 */ + GDB_PS, /* 17 */ + GDB_CS, /* 18 */ + GDB_SS, /* 19 */ }; - -enum regnames32 { - GDB_PS = 34, - GDB_CS, - GDB_SS, -}; -#define NUMREGBYTES ((GDB_SS+1)*4) -#endif /* CONFIG_X86_32 */ +#define GDB_ORIG_AX 57 +#define DBG_MAX_REG_NUM 20 +/* 17 64 bit regs and 3 32 bit regs */ +#define NUMREGBYTES ((17 * 8) + (3 * 4)) +#endif /* ! CONFIG_X86_32 */ static inline void arch_kgdb_breakpoint(void) { @@ -76,4 +78,7 @@ static inline void arch_kgdb_breakpoint(void) #define BREAK_INSTR_SIZE 1 #define CACHE_FLUSH_IS_SAFE 1 +extern int kgdb_ll_trap(int cmd, const char *str, + struct pt_regs *regs, long err, int trap, int sig); + #endif /* _ASM_X86_KGDB_H */ diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 4ffa345a8cc..54788253915 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -24,6 +24,7 @@ #include <linux/types.h> #include <linux/ptrace.h> #include <linux/percpu.h> +#include <asm/insn.h> #define __ARCH_WANT_KPROBES_INSN_SLOT @@ -36,7 +37,6 @@ typedef u8 kprobe_opcode_t; #define RELATIVEJUMP_SIZE 5 #define RELATIVECALL_OPCODE 0xe8 #define RELATIVE_ADDR_SIZE 4 -#define MAX_INSN_SIZE 16 #define MAX_STACK_SIZE 64 #define MIN_STACK_SIZE(ADDR) \ (((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \ diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index f46b79f6c16..4d8dcbdfc12 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -21,6 +21,9 @@ #define __KVM_HAVE_PIT_STATE2 #define __KVM_HAVE_XEN_HVM #define __KVM_HAVE_VCPU_EVENTS +#define __KVM_HAVE_DEBUGREGS +#define __KVM_HAVE_XSAVE +#define __KVM_HAVE_XCRS /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -257,6 +260,11 @@ struct kvm_reinject_control { /* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */ #define KVM_VCPUEVENT_VALID_NMI_PENDING 0x00000001 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002 +#define KVM_VCPUEVENT_VALID_SHADOW 0x00000004 + +/* Interrupt shadow states */ +#define KVM_X86_SHADOW_INT_MOV_SS 0x01 +#define KVM_X86_SHADOW_INT_STI 0x02 /* for KVM_GET/SET_VCPU_EVENTS */ struct kvm_vcpu_events { @@ -271,7 +279,7 @@ struct kvm_vcpu_events { __u8 injected; __u8 nr; __u8 soft; - __u8 pad; + __u8 shadow; } interrupt; struct { __u8 injected; @@ -284,4 +292,33 @@ struct kvm_vcpu_events { __u32 reserved[10]; }; +/* for KVM_GET/SET_DEBUGREGS */ +struct kvm_debugregs { + __u64 db[4]; + __u64 dr6; + __u64 dr7; + __u64 flags; + __u64 reserved[9]; +}; + +/* for KVM_CAP_XSAVE */ +struct kvm_xsave { + __u32 region[1024]; +}; + +#define KVM_MAX_XCRS 16 + +struct kvm_xcr { + __u32 xcr; + __u32 reserved; + __u64 value; +}; + +struct kvm_xcrs { + __u32 nr_xcrs; + __u32 flags; + struct kvm_xcr xcrs[KVM_MAX_XCRS]; + __u64 padding[16]; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 7a6f54fa13b..51cfd730ac5 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -11,6 +11,8 @@ #ifndef _ASM_X86_KVM_X86_EMULATE_H #define _ASM_X86_KVM_X86_EMULATE_H +#include <asm/desc_defs.h> + struct x86_emulate_ctxt; /* @@ -49,8 +51,10 @@ struct x86_emulate_ctxt; #define X86EMUL_UNHANDLEABLE 1 /* Terminate emulation but return success to the caller. */ #define X86EMUL_PROPAGATE_FAULT 2 /* propagate a generated fault to guest */ -#define X86EMUL_RETRY_INSTR 2 /* retry the instruction for some reason */ -#define X86EMUL_CMPXCHG_FAILED 2 /* cmpxchg did not see expected value */ +#define X86EMUL_RETRY_INSTR 3 /* retry the instruction for some reason */ +#define X86EMUL_CMPXCHG_FAILED 4 /* cmpxchg did not see expected value */ +#define X86EMUL_IO_NEEDED 5 /* IO is needed to complete emulation */ + struct x86_emulate_ops { /* * read_std: Read bytes of standard (non-emulated/special) memory. @@ -63,6 +67,15 @@ struct x86_emulate_ops { unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error); /* + * write_std: Write bytes of standard (non-emulated/special) memory. + * Used for descriptor writing. + * @addr: [IN ] Linear address to which to write. + * @val: [OUT] Value write to memory, zero-extended to 'u_long'. + * @bytes: [IN ] Number of bytes to write to memory. + */ + int (*write_std)(unsigned long addr, void *val, + unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error); + /* * fetch: Read bytes of standard (non-emulated/special) memory. * Used for instruction fetch. * @addr: [IN ] Linear address from which to read. @@ -81,6 +94,7 @@ struct x86_emulate_ops { int (*read_emulated)(unsigned long addr, void *val, unsigned int bytes, + unsigned int *error, struct kvm_vcpu *vcpu); /* @@ -93,6 +107,7 @@ struct x86_emulate_ops { int (*write_emulated)(unsigned long addr, const void *val, unsigned int bytes, + unsigned int *error, struct kvm_vcpu *vcpu); /* @@ -107,15 +122,41 @@ struct x86_emulate_ops { const void *old, const void *new, unsigned int bytes, + unsigned int *error, struct kvm_vcpu *vcpu); + int (*pio_in_emulated)(int size, unsigned short port, void *val, + unsigned int count, struct kvm_vcpu *vcpu); + + int (*pio_out_emulated)(int size, unsigned short port, const void *val, + unsigned int count, struct kvm_vcpu *vcpu); + + bool (*get_cached_descriptor)(struct desc_struct *desc, + int seg, struct kvm_vcpu *vcpu); + void (*set_cached_descriptor)(struct desc_struct *desc, + int seg, struct kvm_vcpu *vcpu); + u16 (*get_segment_selector)(int seg, struct kvm_vcpu *vcpu); + void (*set_segment_selector)(u16 sel, int seg, struct kvm_vcpu *vcpu); + unsigned long (*get_cached_segment_base)(int seg, struct kvm_vcpu *vcpu); + void (*get_gdt)(struct desc_ptr *dt, struct kvm_vcpu *vcpu); + ulong (*get_cr)(int cr, struct kvm_vcpu *vcpu); + int (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu); + int (*cpl)(struct kvm_vcpu *vcpu); + int (*get_dr)(int dr, unsigned long *dest, struct kvm_vcpu *vcpu); + int (*set_dr)(int dr, unsigned long value, struct kvm_vcpu *vcpu); + int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); + int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); }; /* Type, address-of, and value of an instruction's operand. */ struct operand { enum { OP_REG, OP_MEM, OP_IMM, OP_NONE } type; unsigned int bytes; - unsigned long val, orig_val, *ptr; + unsigned long orig_val, *ptr; + union { + unsigned long val; + char valptr[sizeof(unsigned long) + 2]; + }; }; struct fetch_cache { @@ -124,6 +165,12 @@ struct fetch_cache { unsigned long end; }; +struct read_cache { + u8 data[1024]; + unsigned long pos; + unsigned long end; +}; + struct decode_cache { u8 twobyte; u8 b; @@ -139,7 +186,7 @@ struct decode_cache { u8 seg_override; unsigned int d; unsigned long regs[NR_VCPU_REGS]; - unsigned long eip, eip_orig; + unsigned long eip; /* modrm */ u8 modrm; u8 modrm_mod; @@ -151,16 +198,16 @@ struct decode_cache { void *modrm_ptr; unsigned long modrm_val; struct fetch_cache fetch; + struct read_cache io_read; + struct read_cache mem_read; }; -#define X86_SHADOW_INT_MOV_SS 1 -#define X86_SHADOW_INT_STI 2 - struct x86_emulate_ctxt { /* Register state before/after emulation. */ struct kvm_vcpu *vcpu; unsigned long eflags; + unsigned long eip; /* eip before instruction emulation */ /* Emulated execution mode, represented by an X86EMUL_MODE value. */ int mode; u32 cs_base; @@ -168,6 +215,13 @@ struct x86_emulate_ctxt { /* interruptibility state, as a result of execution of STI or MOV SS */ int interruptibility; + bool restart; /* restart string instruction after writeback */ + + int exception; /* exception that happens during emulation or -1 */ + u32 error_code; /* error code for exception */ + bool error_code_valid; + unsigned long cr2; /* faulted address in case of #PF */ + /* decode cache */ struct decode_cache decode; }; @@ -194,5 +248,9 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops); int x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops); +int emulator_task_switch(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 tss_selector, int reason, + bool has_error_code, u32 error_code); #endif /* _ASM_X86_KVM_X86_EMULATE_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 06d9e79ca37..502e53f999c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -15,6 +15,7 @@ #include <linux/mm.h> #include <linux/mmu_notifier.h> #include <linux/tracepoint.h> +#include <linux/cpumask.h> #include <linux/kvm.h> #include <linux/kvm_para.h> @@ -39,11 +40,14 @@ 0xFFFFFF0000000000ULL) #define INVALID_PAGE (~(hpa_t)0) +#define VALID_PAGE(x) ((x) != INVALID_PAGE) + #define UNMAPPED_GVA (~(gpa_t)0) /* KVM Hugepage definitions for x86 */ #define KVM_NR_PAGE_SIZES 3 -#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + (((x) - 1) * 9)) +#define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 9) +#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x)) #define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x)) #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) @@ -69,8 +73,6 @@ #define IOPL_SHIFT 12 -#define KVM_ALIAS_SLOTS 4 - #define KVM_PERMILLE_MMU_PAGES 20 #define KVM_MIN_ALLOC_MMU_PAGES 64 #define KVM_MMU_HASH_SHIFT 10 @@ -171,15 +173,15 @@ struct kvm_pte_chain { union kvm_mmu_page_role { unsigned word; struct { - unsigned glevels:4; unsigned level:4; + unsigned cr4_pae:1; unsigned quadrant:2; unsigned pad_for_nice_hex_output:6; unsigned direct:1; unsigned access:3; unsigned invalid:1; - unsigned cr4_pge:1; unsigned nxe:1; + unsigned cr0_wp:1; }; }; @@ -187,8 +189,6 @@ struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; - struct list_head oos_link; - /* * The following two entries are used to key the shadow page in the * hash table. @@ -204,9 +204,9 @@ struct kvm_mmu_page { * in this shadow page. */ DECLARE_BITMAP(slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS); - int multimapped; /* More than one parent_pte? */ - int root_count; /* Currently serving as active root */ + bool multimapped; /* More than one parent_pte? */ bool unsync; + int root_count; /* Currently serving as active root */ unsigned int unsync_children; union { u64 *parent_pte; /* !multimapped */ @@ -224,14 +224,9 @@ struct kvm_pv_mmu_op_buffer { struct kvm_pio_request { unsigned long count; - int cur_count; - gva_t guest_gva; int in; int port; int size; - int string; - int down; - int rep; }; /* @@ -248,7 +243,7 @@ struct kvm_mmu { void (*prefetch_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page); int (*sync_page)(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp); + struct kvm_mmu_page *sp, bool clear_unsync); void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva); hpa_t root_hpa; int root_level; @@ -308,8 +303,8 @@ struct kvm_vcpu_arch { unsigned long mmu_seq; } update_pte; - struct i387_fxsave_struct host_fx_image; - struct i387_fxsave_struct guest_fx_image; + struct fpu guest_fpu; + u64 xcr0; gva_t mmio_fault_cr2; struct kvm_pio_request pio; @@ -320,6 +315,7 @@ struct kvm_vcpu_arch { struct kvm_queued_exception { bool pending; bool has_error_code; + bool reinject; u8 nr; u32 error_code; } exception; @@ -362,33 +358,19 @@ struct kvm_vcpu_arch { u64 *mce_banks; /* used for guest single stepping over the given code position */ - u16 singlestep_cs; unsigned long singlestep_rip; + /* fields used by HYPER-V emulation */ u64 hv_vapic; -}; - -struct kvm_mem_alias { - gfn_t base_gfn; - unsigned long npages; - gfn_t target_gfn; -#define KVM_ALIAS_INVALID 1UL - unsigned long flags; -}; - -#define KVM_ARCH_HAS_UNALIAS_INSTANTIATION -struct kvm_mem_aliases { - struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS]; - int naliases; + cpumask_var_t wbinvd_dirty_mask; }; struct kvm_arch { - struct kvm_mem_aliases *aliases; - unsigned int n_free_mmu_pages; unsigned int n_requested_mmu_pages; unsigned int n_alloc_mmu_pages; + atomic_t invlpg_counter; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; /* * Hash table of struct kvm_mmu_page. @@ -461,11 +443,6 @@ struct kvm_vcpu_stat { u32 nmi_injections; }; -struct descriptor_table { - u16 limit; - unsigned long base; -} __attribute__((packed)); - struct kvm_x86_ops { int (*cpu_has_kvm_support)(void); /* __init */ int (*disabled_by_bios)(void); /* __init */ @@ -503,12 +480,11 @@ struct kvm_x86_ops { void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer); - void (*get_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); - void (*set_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); - void (*get_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); - void (*set_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); - int (*get_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long *dest); - int (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value); + void (*get_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); + void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); + void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); + void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); + void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); @@ -527,7 +503,8 @@ struct kvm_x86_ops { void (*set_irq)(struct kvm_vcpu *vcpu); void (*set_nmi)(struct kvm_vcpu *vcpu); void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr, - bool has_error_code, u32 error_code); + bool has_error_code, u32 error_code, + bool reinject); int (*interrupt_allowed)(struct kvm_vcpu *vcpu); int (*nmi_allowed)(struct kvm_vcpu *vcpu); bool (*get_nmi_mask)(struct kvm_vcpu *vcpu); @@ -541,6 +518,10 @@ struct kvm_x86_ops { int (*get_lpage_level)(void); bool (*rdtscp_supported)(void); + void (*set_supported_cpuid)(u32 func, struct kvm_cpuid_entry2 *entry); + + bool (*has_wbinvd_exit)(void); + const struct trace_print_flags *exit_reasons_str; }; @@ -584,47 +565,38 @@ enum emulation_result { #define EMULTYPE_SKIP (1 << 2) int emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, u16 error_code, int emulation_type); -void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context); void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); -void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, - unsigned long *rflags); -unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr); -void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value, - unsigned long *rflags); void kvm_enable_efer_bits(u64); int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data); int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); struct x86_emulate_ctxt; -int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, - int size, unsigned port); -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in, - int size, unsigned long count, int down, - gva_t address, int rep, unsigned port); +int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port); void kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address); int emulate_clts(struct kvm_vcpu *vcpu); -int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, - unsigned long *dest); -int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, - unsigned long value); +int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg); -int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason); +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, + bool has_error_code, u32 error_code); -void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); -void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); -void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); +int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); +int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8); +int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val); +int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val); unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw); void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); +int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr); int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data); @@ -634,6 +606,8 @@ void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); +void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr); +void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2, u32 error_code); bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl); @@ -642,14 +616,7 @@ int kvm_pic_set_irq(void *opaque, int irq, int level); void kvm_inject_nmi(struct kvm_vcpu *vcpu); -void fx_init(struct kvm_vcpu *vcpu); - -int emulator_write_emulated(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu); - -unsigned long segment_base(u16 selector); +int fx_init(struct kvm_vcpu *vcpu); void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu); void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, @@ -675,12 +642,9 @@ void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_enable_tdp(void); void kvm_disable_tdp(void); -int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); int complete_pio(struct kvm_vcpu *vcpu); bool kvm_check_iopl(struct kvm_vcpu *vcpu); -struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn); - static inline struct kvm_mmu_page *page_header(hpa_t shadow_page) { struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT); @@ -724,23 +688,6 @@ static inline void kvm_load_ldt(u16 sel) asm("lldt %0" : : "rm"(sel)); } -static inline void kvm_get_idt(struct descriptor_table *table) -{ - asm("sidt %0" : "=m"(*table)); -} - -static inline void kvm_get_gdt(struct descriptor_table *table) -{ - asm("sgdt %0" : "=m"(*table)); -} - -static inline unsigned long kvm_read_tr_base(void) -{ - u16 tr; - asm("str %0" : "=g"(tr)); - return segment_base(tr); -} - #ifdef CONFIG_X86_64 static inline unsigned long read_msr(unsigned long msr) { @@ -751,21 +698,6 @@ static inline unsigned long read_msr(unsigned long msr) } #endif -static inline void kvm_fx_save(struct i387_fxsave_struct *image) -{ - asm("fxsave (%0)":: "r" (image)); -} - -static inline void kvm_fx_restore(struct i387_fxsave_struct *image) -{ - asm("fxrstor (%0)":: "r" (image)); -} - -static inline void kvm_fx_finit(void) -{ - asm("finit"); -} - static inline u32 get_rdx_init_val(void) { return 0x600; /* P6 family */ @@ -826,4 +758,6 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_define_shared_msr(unsigned index, u32 msr); void kvm_set_shared_msr(unsigned index, u64 val, u64 mask); +bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index ffae1420e7d..05eba5e9a8e 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -16,10 +16,23 @@ #define KVM_FEATURE_CLOCKSOURCE 0 #define KVM_FEATURE_NOP_IO_DELAY 1 #define KVM_FEATURE_MMU_OP 2 +/* This indicates that the new set of kvmclock msrs + * are available. The use of 0x11 and 0x12 is deprecated + */ +#define KVM_FEATURE_CLOCKSOURCE2 3 + +/* The last 8 bits are used to indicate how to interpret the flags field + * in pvclock structure. If no bits are set, all flags are ignored. + */ +#define KVM_FEATURE_CLOCKSOURCE_STABLE_BIT 24 #define MSR_KVM_WALL_CLOCK 0x11 #define MSR_KVM_SYSTEM_TIME 0x12 +/* Custom MSRs falls in the range 0x4b564d00-0x4b564dff */ +#define MSR_KVM_WALL_CLOCK_NEW 0x4b564d00 +#define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01 + #define KVM_MAX_MMU_OP_BATCH 32 /* Operations for KVM_HC_MMU_OP */ diff --git a/arch/x86/include/asm/local64.h b/arch/x86/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/x86/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 6c3fdd631ed..c62c13cb978 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -38,6 +38,10 @@ #define MCM_ADDR_MEM 3 /* memory address */ #define MCM_ADDR_GENERIC 7 /* generic */ +/* CTL2 register defines */ +#define MCI_CTL2_CMCI_EN (1ULL << 30) +#define MCI_CTL2_CMCI_THRESHOLD_MASK 0x7fffULL + #define MCJ_CTX_MASK 3 #define MCJ_CTX(flags) ((flags) & MCJ_CTX_MASK) #define MCJ_CTX_RANDOM 0 /* inject context: random */ @@ -225,5 +229,13 @@ extern void mcheck_intel_therm_init(void); static inline void mcheck_intel_therm_init(void) { } #endif +/* + * Used by APEI to report memory error via /dev/mcelog + */ + +struct cper_sec_mem_err; +extern void apei_mce_report_mem_error(int corrected, + struct cper_sec_mem_err *mem_err); + #endif /* __KERNEL__ */ #endif /* _ASM_X86_MCE_H */ diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index d8bf23a88d0..c82868e9f90 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -105,16 +105,6 @@ extern void mp_config_acpi_legacy_irqs(void); struct device; extern int mp_register_gsi(struct device *dev, u32 gsi, int edge_level, int active_high_low); -extern int acpi_probe_gsi(void); -#ifdef CONFIG_X86_IO_APIC -extern int mp_find_ioapic(int gsi); -extern int mp_find_ioapic_pin(int ioapic, int gsi); -#endif -#else /* !CONFIG_ACPI: */ -static inline int acpi_probe_gsi(void) -{ - return 0; -} #endif /* CONFIG_ACPI */ #define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_APICS) diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h index 451d30e7f62..16350740edf 100644 --- a/arch/x86/include/asm/mrst.h +++ b/arch/x86/include/asm/mrst.h @@ -13,6 +13,32 @@ extern int pci_mrst_init(void); int __init sfi_parse_mrtc(struct sfi_table_header *table); +/* + * Medfield is the follow-up of Moorestown, it combines two chip solution into + * one. Other than that it also added always-on and constant tsc and lapic + * timers. Medfield is the platform name, and the chip name is called Penwell + * we treat Medfield/Penwell as a variant of Moorestown. Penwell can be + * identified via MSRs. + */ +enum mrst_cpu_type { + MRST_CPU_CHIP_LINCROFT = 1, + MRST_CPU_CHIP_PENWELL, +}; + +extern enum mrst_cpu_type __mrst_cpu_chip; +static enum mrst_cpu_type mrst_identify_cpu(void) +{ + return __mrst_cpu_chip; +} + +enum mrst_timer_options { + MRST_TIMER_DEFAULT, + MRST_TIMER_APBT_ONLY, + MRST_TIMER_LAPIC_APBT, +}; + +extern enum mrst_timer_options mrst_timer_options; + #define SFI_MTMR_MAX_NUM 8 #define SFI_MRTC_MAX 8 diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h new file mode 100644 index 00000000000..79ce5685ab6 --- /dev/null +++ b/arch/x86/include/asm/mshyperv.h @@ -0,0 +1,14 @@ +#ifndef _ASM_X86_MSHYPER_H +#define _ASM_X86_MSHYPER_H + +#include <linux/types.h> +#include <asm/hyperv.h> + +struct ms_hyperv_info { + u32 features; + u32 hints; +}; + +extern struct ms_hyperv_info ms_hyperv; + +#endif diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 4604e6a54d3..986f7790fdb 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -20,6 +20,7 @@ #define _EFER_LMA 10 /* Long mode active (read-only) */ #define _EFER_NX 11 /* No execute enable */ #define _EFER_SVME 12 /* Enable virtualization */ +#define _EFER_LMSLE 13 /* Long Mode Segment Limit Enable */ #define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */ #define EFER_SCE (1<<_EFER_SCE) @@ -27,6 +28,7 @@ #define EFER_LMA (1<<_EFER_LMA) #define EFER_NX (1<<_EFER_NX) #define EFER_SVME (1<<_EFER_SVME) +#define EFER_LMSLE (1<<_EFER_LMSLE) #define EFER_FFXSR (1<<_EFER_FFXSR) /* Intel MSRs. Some also available on other CPUs */ @@ -71,11 +73,14 @@ #define MSR_IA32_LASTINTTOIP 0x000001de /* DEBUGCTLMSR bits (others vary by model): */ -#define _DEBUGCTLMSR_LBR 0 /* last branch recording */ -#define _DEBUGCTLMSR_BTF 1 /* single-step on branches */ - -#define DEBUGCTLMSR_LBR (1UL << _DEBUGCTLMSR_LBR) -#define DEBUGCTLMSR_BTF (1UL << _DEBUGCTLMSR_BTF) +#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ +#define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ +#define DEBUGCTLMSR_TR (1UL << 6) +#define DEBUGCTLMSR_BTS (1UL << 7) +#define DEBUGCTLMSR_BTINT (1UL << 8) +#define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9) +#define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) +#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) #define MSR_IA32_MC0_CTL 0x00000400 #define MSR_IA32_MC0_STATUS 0x00000401 @@ -91,9 +96,6 @@ #define MSR_IA32_MC0_CTL2 0x00000280 #define MSR_IA32_MCx_CTL2(x) (MSR_IA32_MC0_CTL2 + (x)) -#define CMCI_EN (1ULL << 30) -#define CMCI_THRESHOLD_MASK 0xffffULL - #define MSR_P6_PERFCTR0 0x000000c1 #define MSR_P6_PERFCTR1 0x000000c2 #define MSR_P6_EVNTSEL0 0x00000186 @@ -107,6 +109,7 @@ #define MSR_AMD64_PATCH_LOADER 0xc0010020 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 +#define MSR_AMD64_DC_CFG 0xc0011022 #define MSR_AMD64_IBSFETCHCTL 0xc0011030 #define MSR_AMD64_IBSFETCHLINAD 0xc0011031 #define MSR_AMD64_IBSFETCHPHYSAD 0xc0011032 @@ -155,8 +158,6 @@ #define MSR_K7_FID_VID_STATUS 0xc0010042 /* K6 MSRs */ -#define MSR_K6_EFER 0xc0000080 -#define MSR_K6_STAR 0xc0000081 #define MSR_K6_WHCR 0xc0000082 #define MSR_K6_UWCCR 0xc0000085 #define MSR_K6_EPMR 0xc0000086 @@ -199,8 +200,9 @@ #define MSR_IA32_EBL_CR_POWERON 0x0000002a #define MSR_IA32_FEATURE_CONTROL 0x0000003a -#define FEATURE_CONTROL_LOCKED (1<<0) -#define FEATURE_CONTROL_VMXON_ENABLED (1<<2) +#define FEATURE_CONTROL_LOCKED (1<<0) +#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1) +#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2) #define MSR_IA32_APICBASE 0x0000001b #define MSR_IA32_APICBASE_BSP (1<<8) @@ -219,12 +221,14 @@ #define MSR_IA32_THERM_CONTROL 0x0000019a #define MSR_IA32_THERM_INTERRUPT 0x0000019b -#define THERM_INT_LOW_ENABLE (1 << 0) -#define THERM_INT_HIGH_ENABLE (1 << 1) +#define THERM_INT_HIGH_ENABLE (1 << 0) +#define THERM_INT_LOW_ENABLE (1 << 1) +#define THERM_INT_PLN_ENABLE (1 << 24) #define MSR_IA32_THERM_STATUS 0x0000019c #define THERM_STATUS_PROCHOT (1 << 0) +#define THERM_STATUS_POWER_LIMIT (1 << 10) #define MSR_THERM2_CTL 0x0000019d @@ -232,6 +236,21 @@ #define MSR_IA32_MISC_ENABLE 0x000001a0 +#define MSR_IA32_TEMPERATURE_TARGET 0x000001a2 + +#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0 + +#define MSR_IA32_PACKAGE_THERM_STATUS 0x000001b1 + +#define PACKAGE_THERM_STATUS_PROCHOT (1 << 0) +#define PACKAGE_THERM_STATUS_POWER_LIMIT (1 << 10) + +#define MSR_IA32_PACKAGE_THERM_INTERRUPT 0x000001b2 + +#define PACKAGE_THERM_INT_HIGH_ENABLE (1 << 0) +#define PACKAGE_THERM_INT_LOW_ENABLE (1 << 1) +#define PACKAGE_THERM_INT_PLN_ENABLE (1 << 24) + /* MISC_ENABLE bits: architectural */ #define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << 0) #define MSR_IA32_MISC_ENABLE_TCC (1ULL << 1) @@ -359,6 +378,8 @@ #define MSR_P4_U2L_ESCR0 0x000003b0 #define MSR_P4_U2L_ESCR1 0x000003b1 +#define MSR_P4_PEBS_MATRIX_VERT 0x000003f2 + /* Intel Core-based CPU performance counters */ #define MSR_CORE_PERF_FIXED_CTR0 0x00000309 #define MSR_CORE_PERF_FIXED_CTR1 0x0000030a diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index c5bc4c2d33f..084ef95274c 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -148,8 +148,8 @@ static inline unsigned long long native_read_pmc(int counter) #define rdmsr(msr, val1, val2) \ do { \ u64 __val = native_read_msr((msr)); \ - (val1) = (u32)__val; \ - (val2) = (u32)(__val >> 32); \ + (void)((val1) = (u32)__val); \ + (void)((val2) = (u32)(__val >> 32)); \ } while (0) static inline void wrmsr(unsigned msr, unsigned low, unsigned high) diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 93da9c3f334..932f0f86b4b 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -17,7 +17,9 @@ int do_nmi_callback(struct pt_regs *regs, int cpu); extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); extern int check_nmi_watchdog(void); +#if !defined(CONFIG_LOCKUP_DETECTOR) extern int nmi_watchdog_enabled; +#endif extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); extern int reserve_perfctr_nmi(unsigned int); extern void release_perfctr_nmi(unsigned int); diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h new file mode 100644 index 00000000000..08fde475cb3 --- /dev/null +++ b/arch/x86/include/asm/olpc_ofw.h @@ -0,0 +1,31 @@ +#ifndef _ASM_X86_OLPC_OFW_H +#define _ASM_X86_OLPC_OFW_H + +/* index into the page table containing the entry OFW occupies */ +#define OLPC_OFW_PDE_NR 1022 + +#define OLPC_OFW_SIG 0x2057464F /* aka "OFW " */ + +#ifdef CONFIG_OLPC_OPENFIRMWARE + +/* run an OFW command by calling into the firmware */ +#define olpc_ofw(name, args, res) \ + __olpc_ofw((name), ARRAY_SIZE(args), args, ARRAY_SIZE(res), res) + +extern int __olpc_ofw(const char *name, int nr_args, const void **args, int nr_res, + void **res); + +/* determine whether OFW is available and lives in the proper memory */ +extern void olpc_ofw_detect(void); + +/* install OFW's pde permanently into the kernel's pgtable */ +extern void setup_olpc_ofw_pgd(void); + +#else /* !CONFIG_OLPC_OPENFIRMWARE */ + +static inline void olpc_ofw_detect(void) { } +static inline void setup_olpc_ofw_pgd(void) { } + +#endif /* !CONFIG_OLPC_OPENFIRMWARE */ + +#endif /* _ASM_X86_OLPC_OFW_H */ diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 1a0422348d6..49c7219826f 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -30,6 +30,7 @@ #define PCI_HAS_IO_ECS 0x40000 #define PCI_NOASSIGN_ROMS 0x80000 #define PCI_ROOT_NO_CRS 0x100000 +#define PCI_NOASSIGN_BARS 0x200000 extern unsigned int pci_probe; extern unsigned long pirq_table_addr; @@ -53,6 +54,8 @@ extern int pcibios_last_bus; extern struct pci_bus *pci_root_bus; extern struct pci_ops pci_root_ops; +void pcibios_scan_specific_bus(int busn); + /* pci-irq.c */ struct irq_info { @@ -83,7 +86,7 @@ struct irq_routing_table { extern unsigned int pcibios_irq_mask; -extern spinlock_t pci_config_lock; +extern raw_spinlock_t pci_config_lock; extern int (*pcibios_enable_irq)(struct pci_dev *dev); extern void (*pcibios_disable_irq)(struct pci_dev *dev); diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 66a272dfd8b..cd28f9ad910 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -77,6 +77,7 @@ do { \ if (0) { \ pto_T__ pto_tmp__; \ pto_tmp__ = (val); \ + (void)pto_tmp__; \ } \ switch (sizeof(var)) { \ case 1: \ @@ -105,7 +106,7 @@ do { \ /* * Generate a percpu add to memory instruction and optimize code - * if a one is added or subtracted. + * if one is added or subtracted. */ #define percpu_add_op(var, val) \ do { \ @@ -115,6 +116,7 @@ do { \ if (0) { \ pao_T__ pao_tmp__; \ pao_tmp__ = (val); \ + (void)pao_tmp__; \ } \ switch (sizeof(var)) { \ case 1: \ @@ -190,6 +192,29 @@ do { \ pfo_ret__; \ }) +#define percpu_unary_op(op, var) \ +({ \ + switch (sizeof(var)) { \ + case 1: \ + asm(op "b "__percpu_arg(0) \ + : "+m" (var)); \ + break; \ + case 2: \ + asm(op "w "__percpu_arg(0) \ + : "+m" (var)); \ + break; \ + case 4: \ + asm(op "l "__percpu_arg(0) \ + : "+m" (var)); \ + break; \ + case 8: \ + asm(op "q "__percpu_arg(0) \ + : "+m" (var)); \ + break; \ + default: __bad_percpu_size(); \ + } \ +}) + /* * percpu_read() makes gcc load the percpu variable every time it is * accessed while percpu_read_stable() allows the value to be cached. @@ -207,6 +232,7 @@ do { \ #define percpu_and(var, val) percpu_to_op("and", var, val) #define percpu_or(var, val) percpu_to_op("or", var, val) #define percpu_xor(var, val) percpu_to_op("xor", var, val) +#define percpu_inc(var) percpu_unary_op("inc", var) #define __this_cpu_read_1(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) #define __this_cpu_read_2(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index db6109a885a..6e742cc4251 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -5,7 +5,7 @@ * Performance event hw details: */ -#define X86_PMC_MAX_GENERIC 8 +#define X86_PMC_MAX_GENERIC 32 #define X86_PMC_MAX_FIXED 3 #define X86_PMC_IDX_GENERIC 0 @@ -18,39 +18,31 @@ #define MSR_ARCH_PERFMON_EVENTSEL0 0x186 #define MSR_ARCH_PERFMON_EVENTSEL1 0x187 -#define ARCH_PERFMON_EVENTSEL_ENABLE (1 << 22) -#define ARCH_PERFMON_EVENTSEL_ANY (1 << 21) -#define ARCH_PERFMON_EVENTSEL_INT (1 << 20) -#define ARCH_PERFMON_EVENTSEL_OS (1 << 17) -#define ARCH_PERFMON_EVENTSEL_USR (1 << 16) - -/* - * Includes eventsel and unit mask as well: - */ - - -#define INTEL_ARCH_EVTSEL_MASK 0x000000FFULL -#define INTEL_ARCH_UNIT_MASK 0x0000FF00ULL -#define INTEL_ARCH_EDGE_MASK 0x00040000ULL -#define INTEL_ARCH_INV_MASK 0x00800000ULL -#define INTEL_ARCH_CNT_MASK 0xFF000000ULL -#define INTEL_ARCH_EVENT_MASK (INTEL_ARCH_UNIT_MASK|INTEL_ARCH_EVTSEL_MASK) - -/* - * filter mask to validate fixed counter events. - * the following filters disqualify for fixed counters: - * - inv - * - edge - * - cnt-mask - * The other filters are supported by fixed counters. - * The any-thread option is supported starting with v3. - */ -#define INTEL_ARCH_FIXED_MASK \ - (INTEL_ARCH_CNT_MASK| \ - INTEL_ARCH_INV_MASK| \ - INTEL_ARCH_EDGE_MASK|\ - INTEL_ARCH_UNIT_MASK|\ - INTEL_ARCH_EVENT_MASK) +#define ARCH_PERFMON_EVENTSEL_EVENT 0x000000FFULL +#define ARCH_PERFMON_EVENTSEL_UMASK 0x0000FF00ULL +#define ARCH_PERFMON_EVENTSEL_USR (1ULL << 16) +#define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17) +#define ARCH_PERFMON_EVENTSEL_EDGE (1ULL << 18) +#define ARCH_PERFMON_EVENTSEL_INT (1ULL << 20) +#define ARCH_PERFMON_EVENTSEL_ANY (1ULL << 21) +#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22) +#define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23) +#define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL + +#define AMD64_EVENTSEL_EVENT \ + (ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32)) +#define INTEL_ARCH_EVENT_MASK \ + (ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT) + +#define X86_RAW_EVENT_MASK \ + (ARCH_PERFMON_EVENTSEL_EVENT | \ + ARCH_PERFMON_EVENTSEL_UMASK | \ + ARCH_PERFMON_EVENTSEL_EDGE | \ + ARCH_PERFMON_EVENTSEL_INV | \ + ARCH_PERFMON_EVENTSEL_CMASK) +#define AMD64_RAW_EVENT_MASK \ + (X86_RAW_EVENT_MASK | \ + AMD64_EVENTSEL_EVENT) #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8) @@ -67,7 +59,7 @@ union cpuid10_eax { struct { unsigned int version_id:8; - unsigned int num_events:8; + unsigned int num_counters:8; unsigned int bit_width:8; unsigned int mask_length:8; } split; @@ -76,8 +68,9 @@ union cpuid10_eax { union cpuid10_edx { struct { - unsigned int num_events_fixed:4; - unsigned int reserved:28; + unsigned int num_counters_fixed:5; + unsigned int bit_width_fixed:8; + unsigned int reserved:19; } split; unsigned int full; }; @@ -136,6 +129,31 @@ extern void perf_events_lapic_init(void); #define PERF_EVENT_INDEX_OFFSET 0 +/* + * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups. + * This flag is otherwise unused and ABI specified to be 0, so nobody should + * care what we do with it. + */ +#define PERF_EFLAGS_EXACT (1UL << 3) + +struct pt_regs; +extern unsigned long perf_instruction_pointer(struct pt_regs *regs); +extern unsigned long perf_misc_flags(struct pt_regs *regs); +#define perf_misc_flags(regs) perf_misc_flags(regs) + +#include <asm/stacktrace.h> + +/* + * We abuse bit 3 from flags to pass exact information, see perf_misc_flags + * and the comment with PERF_EFLAGS_EXACT. + */ +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->ip = (__ip); \ + (regs)->bp = caller_frame_pointer(); \ + (regs)->cs = __KERNEL_CS; \ + regs->flags = 0; \ +} + #else static inline void init_hw_perf_events(void) { } static inline void perf_events_lapic_init(void) { } diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h new file mode 100644 index 00000000000..def500776b1 --- /dev/null +++ b/arch/x86/include/asm/perf_event_p4.h @@ -0,0 +1,800 @@ +/* + * Netburst Perfomance Events (P4, old Xeon) + */ + +#ifndef PERF_EVENT_P4_H +#define PERF_EVENT_P4_H + +#include <linux/cpu.h> +#include <linux/bitops.h> + +/* + * NetBurst has perfomance MSRs shared between + * threads if HT is turned on, ie for both logical + * processors (mem: in turn in Atom with HT support + * perf-MSRs are not shared and every thread has its + * own perf-MSRs set) + */ +#define ARCH_P4_TOTAL_ESCR (46) +#define ARCH_P4_RESERVED_ESCR (2) /* IQ_ESCR(0,1) not always present */ +#define ARCH_P4_MAX_ESCR (ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR) +#define ARCH_P4_MAX_CCCR (18) + +#define P4_ESCR_EVENT_MASK 0x7e000000U +#define P4_ESCR_EVENT_SHIFT 25 +#define P4_ESCR_EVENTMASK_MASK 0x01fffe00U +#define P4_ESCR_EVENTMASK_SHIFT 9 +#define P4_ESCR_TAG_MASK 0x000001e0U +#define P4_ESCR_TAG_SHIFT 5 +#define P4_ESCR_TAG_ENABLE 0x00000010U +#define P4_ESCR_T0_OS 0x00000008U +#define P4_ESCR_T0_USR 0x00000004U +#define P4_ESCR_T1_OS 0x00000002U +#define P4_ESCR_T1_USR 0x00000001U + +#define P4_ESCR_EVENT(v) ((v) << P4_ESCR_EVENT_SHIFT) +#define P4_ESCR_EMASK(v) ((v) << P4_ESCR_EVENTMASK_SHIFT) +#define P4_ESCR_TAG(v) ((v) << P4_ESCR_TAG_SHIFT) + +/* Non HT mask */ +#define P4_ESCR_MASK \ + (P4_ESCR_EVENT_MASK | \ + P4_ESCR_EVENTMASK_MASK | \ + P4_ESCR_TAG_MASK | \ + P4_ESCR_TAG_ENABLE | \ + P4_ESCR_T0_OS | \ + P4_ESCR_T0_USR) + +/* HT mask */ +#define P4_ESCR_MASK_HT \ + (P4_ESCR_MASK | P4_ESCR_T1_OS | P4_ESCR_T1_USR) + +#define P4_CCCR_OVF 0x80000000U +#define P4_CCCR_CASCADE 0x40000000U +#define P4_CCCR_OVF_PMI_T0 0x04000000U +#define P4_CCCR_OVF_PMI_T1 0x08000000U +#define P4_CCCR_FORCE_OVF 0x02000000U +#define P4_CCCR_EDGE 0x01000000U +#define P4_CCCR_THRESHOLD_MASK 0x00f00000U +#define P4_CCCR_THRESHOLD_SHIFT 20 +#define P4_CCCR_COMPLEMENT 0x00080000U +#define P4_CCCR_COMPARE 0x00040000U +#define P4_CCCR_ESCR_SELECT_MASK 0x0000e000U +#define P4_CCCR_ESCR_SELECT_SHIFT 13 +#define P4_CCCR_ENABLE 0x00001000U +#define P4_CCCR_THREAD_SINGLE 0x00010000U +#define P4_CCCR_THREAD_BOTH 0x00020000U +#define P4_CCCR_THREAD_ANY 0x00030000U +#define P4_CCCR_RESERVED 0x00000fffU + +#define P4_CCCR_THRESHOLD(v) ((v) << P4_CCCR_THRESHOLD_SHIFT) +#define P4_CCCR_ESEL(v) ((v) << P4_CCCR_ESCR_SELECT_SHIFT) + +/* Non HT mask */ +#define P4_CCCR_MASK \ + (P4_CCCR_OVF | \ + P4_CCCR_CASCADE | \ + P4_CCCR_OVF_PMI_T0 | \ + P4_CCCR_FORCE_OVF | \ + P4_CCCR_EDGE | \ + P4_CCCR_THRESHOLD_MASK | \ + P4_CCCR_COMPLEMENT | \ + P4_CCCR_COMPARE | \ + P4_CCCR_ESCR_SELECT_MASK | \ + P4_CCCR_ENABLE) + +/* HT mask */ +#define P4_CCCR_MASK_HT \ + (P4_CCCR_MASK | P4_CCCR_OVF_PMI_T1 | P4_CCCR_THREAD_ANY) + +#define P4_GEN_ESCR_EMASK(class, name, bit) \ + class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT) +#define P4_ESCR_EMASK_BIT(class, name) class##__##name + +/* + * config field is 64bit width and consists of + * HT << 63 | ESCR << 32 | CCCR + * where HT is HyperThreading bit (since ESCR + * has it reserved we may use it for own purpose) + * + * note that this is NOT the addresses of respective + * ESCR and CCCR but rather an only packed value should + * be unpacked and written to a proper addresses + * + * the base idea is to pack as much info as possible + */ +#define p4_config_pack_escr(v) (((u64)(v)) << 32) +#define p4_config_pack_cccr(v) (((u64)(v)) & 0xffffffffULL) +#define p4_config_unpack_escr(v) (((u64)(v)) >> 32) +#define p4_config_unpack_cccr(v) (((u64)(v)) & 0xffffffffULL) + +#define p4_config_unpack_emask(v) \ + ({ \ + u32 t = p4_config_unpack_escr((v)); \ + t = t & P4_ESCR_EVENTMASK_MASK; \ + t = t >> P4_ESCR_EVENTMASK_SHIFT; \ + t; \ + }) + +#define p4_config_unpack_event(v) \ + ({ \ + u32 t = p4_config_unpack_escr((v)); \ + t = t & P4_ESCR_EVENT_MASK; \ + t = t >> P4_ESCR_EVENT_SHIFT; \ + t; \ + }) + +#define P4_CONFIG_HT_SHIFT 63 +#define P4_CONFIG_HT (1ULL << P4_CONFIG_HT_SHIFT) + +static inline bool p4_is_event_cascaded(u64 config) +{ + u32 cccr = p4_config_unpack_cccr(config); + return !!(cccr & P4_CCCR_CASCADE); +} + +static inline int p4_ht_config_thread(u64 config) +{ + return !!(config & P4_CONFIG_HT); +} + +static inline u64 p4_set_ht_bit(u64 config) +{ + return config | P4_CONFIG_HT; +} + +static inline u64 p4_clear_ht_bit(u64 config) +{ + return config & ~P4_CONFIG_HT; +} + +static inline int p4_ht_active(void) +{ +#ifdef CONFIG_SMP + return smp_num_siblings > 1; +#endif + return 0; +} + +static inline int p4_ht_thread(int cpu) +{ +#ifdef CONFIG_SMP + if (smp_num_siblings == 2) + return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map)); +#endif + return 0; +} + +static inline int p4_should_swap_ts(u64 config, int cpu) +{ + return p4_ht_config_thread(config) ^ p4_ht_thread(cpu); +} + +static inline u32 p4_default_cccr_conf(int cpu) +{ + /* + * Note that P4_CCCR_THREAD_ANY is "required" on + * non-HT machines (on HT machines we count TS events + * regardless the state of second logical processor + */ + u32 cccr = P4_CCCR_THREAD_ANY; + + if (!p4_ht_thread(cpu)) + cccr |= P4_CCCR_OVF_PMI_T0; + else + cccr |= P4_CCCR_OVF_PMI_T1; + + return cccr; +} + +static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_usr) +{ + u32 escr = 0; + + if (!p4_ht_thread(cpu)) { + if (!exclude_os) + escr |= P4_ESCR_T0_OS; + if (!exclude_usr) + escr |= P4_ESCR_T0_USR; + } else { + if (!exclude_os) + escr |= P4_ESCR_T1_OS; + if (!exclude_usr) + escr |= P4_ESCR_T1_USR; + } + + return escr; +} + +/* + * This are the events which should be used in "Event Select" + * field of ESCR register, they are like unique keys which allow + * the kernel to determinate which CCCR and COUNTER should be + * used to track an event + */ +enum P4_EVENTS { + P4_EVENT_TC_DELIVER_MODE, + P4_EVENT_BPU_FETCH_REQUEST, + P4_EVENT_ITLB_REFERENCE, + P4_EVENT_MEMORY_CANCEL, + P4_EVENT_MEMORY_COMPLETE, + P4_EVENT_LOAD_PORT_REPLAY, + P4_EVENT_STORE_PORT_REPLAY, + P4_EVENT_MOB_LOAD_REPLAY, + P4_EVENT_PAGE_WALK_TYPE, + P4_EVENT_BSQ_CACHE_REFERENCE, + P4_EVENT_IOQ_ALLOCATION, + P4_EVENT_IOQ_ACTIVE_ENTRIES, + P4_EVENT_FSB_DATA_ACTIVITY, + P4_EVENT_BSQ_ALLOCATION, + P4_EVENT_BSQ_ACTIVE_ENTRIES, + P4_EVENT_SSE_INPUT_ASSIST, + P4_EVENT_PACKED_SP_UOP, + P4_EVENT_PACKED_DP_UOP, + P4_EVENT_SCALAR_SP_UOP, + P4_EVENT_SCALAR_DP_UOP, + P4_EVENT_64BIT_MMX_UOP, + P4_EVENT_128BIT_MMX_UOP, + P4_EVENT_X87_FP_UOP, + P4_EVENT_TC_MISC, + P4_EVENT_GLOBAL_POWER_EVENTS, + P4_EVENT_TC_MS_XFER, + P4_EVENT_UOP_QUEUE_WRITES, + P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, + P4_EVENT_RETIRED_BRANCH_TYPE, + P4_EVENT_RESOURCE_STALL, + P4_EVENT_WC_BUFFER, + P4_EVENT_B2B_CYCLES, + P4_EVENT_BNR, + P4_EVENT_SNOOP, + P4_EVENT_RESPONSE, + P4_EVENT_FRONT_END_EVENT, + P4_EVENT_EXECUTION_EVENT, + P4_EVENT_REPLAY_EVENT, + P4_EVENT_INSTR_RETIRED, + P4_EVENT_UOPS_RETIRED, + P4_EVENT_UOP_TYPE, + P4_EVENT_BRANCH_RETIRED, + P4_EVENT_MISPRED_BRANCH_RETIRED, + P4_EVENT_X87_ASSIST, + P4_EVENT_MACHINE_CLEAR, + P4_EVENT_INSTR_COMPLETED, +}; + +#define P4_OPCODE(event) event##_OPCODE +#define P4_OPCODE_ESEL(opcode) ((opcode & 0x00ff) >> 0) +#define P4_OPCODE_EVNT(opcode) ((opcode & 0xff00) >> 8) +#define P4_OPCODE_PACK(event, sel) (((event) << 8) | sel) + +/* + * Comments below the event represent ESCR restriction + * for this event and counter index per ESCR + * + * MSR_P4_IQ_ESCR0 and MSR_P4_IQ_ESCR1 are available only on early + * processor builds (family 0FH, models 01H-02H). These MSRs + * are not available on later versions, so that we don't use + * them completely + * + * Also note that CCCR1 do not have P4_CCCR_ENABLE bit properly + * working so that we should not use this CCCR and respective + * counter as result + */ +enum P4_EVENT_OPCODES { + P4_OPCODE(P4_EVENT_TC_DELIVER_MODE) = P4_OPCODE_PACK(0x01, 0x01), + /* + * MSR_P4_TC_ESCR0: 4, 5 + * MSR_P4_TC_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST) = P4_OPCODE_PACK(0x03, 0x00), + /* + * MSR_P4_BPU_ESCR0: 0, 1 + * MSR_P4_BPU_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_ITLB_REFERENCE) = P4_OPCODE_PACK(0x18, 0x03), + /* + * MSR_P4_ITLB_ESCR0: 0, 1 + * MSR_P4_ITLB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_MEMORY_CANCEL) = P4_OPCODE_PACK(0x02, 0x05), + /* + * MSR_P4_DAC_ESCR0: 8, 9 + * MSR_P4_DAC_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_MEMORY_COMPLETE) = P4_OPCODE_PACK(0x08, 0x02), + /* + * MSR_P4_SAAT_ESCR0: 8, 9 + * MSR_P4_SAAT_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY) = P4_OPCODE_PACK(0x04, 0x02), + /* + * MSR_P4_SAAT_ESCR0: 8, 9 + * MSR_P4_SAAT_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY) = P4_OPCODE_PACK(0x05, 0x02), + /* + * MSR_P4_SAAT_ESCR0: 8, 9 + * MSR_P4_SAAT_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY) = P4_OPCODE_PACK(0x03, 0x02), + /* + * MSR_P4_MOB_ESCR0: 0, 1 + * MSR_P4_MOB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE) = P4_OPCODE_PACK(0x01, 0x04), + /* + * MSR_P4_PMH_ESCR0: 0, 1 + * MSR_P4_PMH_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE) = P4_OPCODE_PACK(0x0c, 0x07), + /* + * MSR_P4_BSU_ESCR0: 0, 1 + * MSR_P4_BSU_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_IOQ_ALLOCATION) = P4_OPCODE_PACK(0x03, 0x06), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES) = P4_OPCODE_PACK(0x1a, 0x06), + /* + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY) = P4_OPCODE_PACK(0x17, 0x06), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_BSQ_ALLOCATION) = P4_OPCODE_PACK(0x05, 0x07), + /* + * MSR_P4_BSU_ESCR0: 0, 1 + */ + + P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES) = P4_OPCODE_PACK(0x06, 0x07), + /* + * NOTE: no ESCR name in docs, it's guessed + * MSR_P4_BSU_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST) = P4_OPCODE_PACK(0x34, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_PACKED_SP_UOP) = P4_OPCODE_PACK(0x08, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_PACKED_DP_UOP) = P4_OPCODE_PACK(0x0c, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_SCALAR_SP_UOP) = P4_OPCODE_PACK(0x0a, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_SCALAR_DP_UOP) = P4_OPCODE_PACK(0x0e, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_64BIT_MMX_UOP) = P4_OPCODE_PACK(0x02, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_128BIT_MMX_UOP) = P4_OPCODE_PACK(0x1a, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_X87_FP_UOP) = P4_OPCODE_PACK(0x04, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_TC_MISC) = P4_OPCODE_PACK(0x06, 0x01), + /* + * MSR_P4_TC_ESCR0: 4, 5 + * MSR_P4_TC_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS) = P4_OPCODE_PACK(0x13, 0x06), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_TC_MS_XFER) = P4_OPCODE_PACK(0x05, 0x00), + /* + * MSR_P4_MS_ESCR0: 4, 5 + * MSR_P4_MS_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES) = P4_OPCODE_PACK(0x09, 0x00), + /* + * MSR_P4_MS_ESCR0: 4, 5 + * MSR_P4_MS_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE) = P4_OPCODE_PACK(0x05, 0x02), + /* + * MSR_P4_TBPU_ESCR0: 4, 5 + * MSR_P4_TBPU_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE) = P4_OPCODE_PACK(0x04, 0x02), + /* + * MSR_P4_TBPU_ESCR0: 4, 5 + * MSR_P4_TBPU_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_RESOURCE_STALL) = P4_OPCODE_PACK(0x01, 0x01), + /* + * MSR_P4_ALF_ESCR0: 12, 13, 16 + * MSR_P4_ALF_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_WC_BUFFER) = P4_OPCODE_PACK(0x05, 0x05), + /* + * MSR_P4_DAC_ESCR0: 8, 9 + * MSR_P4_DAC_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_B2B_CYCLES) = P4_OPCODE_PACK(0x16, 0x03), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_BNR) = P4_OPCODE_PACK(0x08, 0x03), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_SNOOP) = P4_OPCODE_PACK(0x06, 0x03), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_RESPONSE) = P4_OPCODE_PACK(0x04, 0x03), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_FRONT_END_EVENT) = P4_OPCODE_PACK(0x08, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_EXECUTION_EVENT) = P4_OPCODE_PACK(0x0c, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_REPLAY_EVENT) = P4_OPCODE_PACK(0x09, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_INSTR_RETIRED) = P4_OPCODE_PACK(0x02, 0x04), + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_UOPS_RETIRED) = P4_OPCODE_PACK(0x01, 0x04), + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_UOP_TYPE) = P4_OPCODE_PACK(0x02, 0x02), + /* + * MSR_P4_RAT_ESCR0: 12, 13, 16 + * MSR_P4_RAT_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_BRANCH_RETIRED) = P4_OPCODE_PACK(0x06, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED) = P4_OPCODE_PACK(0x03, 0x04), + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_X87_ASSIST) = P4_OPCODE_PACK(0x03, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_MACHINE_CLEAR) = P4_OPCODE_PACK(0x02, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_INSTR_COMPLETED) = P4_OPCODE_PACK(0x07, 0x04), + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ +}; + +/* + * a caller should use P4_ESCR_EMASK_NAME helper to + * pick the EventMask needed, for example + * + * P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DD) + */ +enum P4_ESCR_EMASKS { + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DD, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DB, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DI, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BD, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BB, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BI, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, ID, 6), + + P4_GEN_ESCR_EMASK(P4_EVENT_BPU_FETCH_REQUEST, TCMISS, 0), + + P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, MISS, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT_UK, 2), + + P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, ST_RB_FULL, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, 64K_CONF, 3), + + P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, LSC, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, SSC, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_LOAD_PORT_REPLAY, SPLIT_LD, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_STORE_PORT_REPLAY, SPLIT_ST, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STA, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STD, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, PARTIAL_DATA, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, UNALGN_ADDR, 5), + + P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, DTMISS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, ITMISS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS, 10), + + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, DEFAULT, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_READ, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_WRITE, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_UC, 7), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WC, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WT, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WP, 10), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WB, 11), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OWN, 13), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OTHER, 14), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, PREFETCH, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, DEFAULT, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_READ, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_WRITE, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_UC, 7), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WC, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WT, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WP, 10), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WB, 11), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OWN, 13), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OTHER, 14), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, PREFETCH, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OTHER, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_DRV, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OWN, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OTHER, 5), + + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE0, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE1, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN0, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN1, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_IO_TYPE, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LOCK_TYPE, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_CACHE_TYPE, 7), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_SPLIT_TYPE, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_DEM_TYPE, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_ORD_TYPE, 10), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE0, 11), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE1, 12), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE2, 13), + + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE0, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE1, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN0, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN1, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_IO_TYPE, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LOCK_TYPE, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_CACHE_TYPE, 7), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_SPLIT_TYPE, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_DEM_TYPE, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_ORD_TYPE, 10), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE0, 11), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE1, 12), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE2, 13), + + P4_GEN_ESCR_EMASK(P4_EVENT_SSE_INPUT_ASSIST, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_SP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_DP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_SP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_DP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_64BIT_MMX_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_128BIT_MMX_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_X87_FP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_TC_MISC, FLUSH, 4), + + P4_GEN_ESCR_EMASK(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING, 0), + + P4_GEN_ESCR_EMASK(P4_EVENT_TC_MS_XFER, CISC, 0), + + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_BUILD, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_DELIVER, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_ROM, 2), + + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CONDITIONAL, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CALL, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, RETURN, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, INDIRECT, 4), + + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CALL, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT, 4), + + P4_GEN_ESCR_EMASK(P4_EVENT_RESOURCE_STALL, SBFULL, 5), + + P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_EVICTS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_FULL_EVICTS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, NBOGUS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, BOGUS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS0, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS1, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS2, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS3, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS0, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS1, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS2, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS3, 7), + + P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, NBOGUS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, BOGUS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSTAG, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSNTAG, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSTAG, 3), + + P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, NBOGUS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, BOGUS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGLOADS, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGSTORES, 2), + + P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNP, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNM, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTP, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTM, 3), + + P4_GEN_ESCR_EMASK(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS, 0), + + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSU, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSO, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAO, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAU, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, PREA, 4), + + P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, CLEAR, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, MOCLEAR, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, SMCLEAR, 2), + + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, NBOGUS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, BOGUS, 1), +}; + +/* + * P4 PEBS specifics (Replay Event only) + * + * Format (bits): + * 0-6: metric from P4_PEBS_METRIC enum + * 7 : reserved + * 8 : reserved + * 9-11 : reserved + * + * Note we have UOP and PEBS bits reserved for now + * just in case if we will need them once + */ +#define P4_PEBS_CONFIG_ENABLE (1 << 7) +#define P4_PEBS_CONFIG_UOP_TAG (1 << 8) +#define P4_PEBS_CONFIG_METRIC_MASK 0x3f +#define P4_PEBS_CONFIG_MASK 0xff + +/* + * mem: Only counters MSR_IQ_COUNTER4 (16) and + * MSR_IQ_COUNTER5 (17) are allowed for PEBS sampling + */ +#define P4_PEBS_ENABLE 0x02000000U +#define P4_PEBS_ENABLE_UOP_TAG 0x01000000U + +#define p4_config_unpack_metric(v) (((u64)(v)) & P4_PEBS_CONFIG_METRIC_MASK) +#define p4_config_unpack_pebs(v) (((u64)(v)) & P4_PEBS_CONFIG_MASK) + +#define p4_config_pebs_has(v, mask) (p4_config_unpack_pebs(v) & (mask)) + +enum P4_PEBS_METRIC { + P4_PEBS_METRIC__none, + + P4_PEBS_METRIC__1stl_cache_load_miss_retired, + P4_PEBS_METRIC__2ndl_cache_load_miss_retired, + P4_PEBS_METRIC__dtlb_load_miss_retired, + P4_PEBS_METRIC__dtlb_store_miss_retired, + P4_PEBS_METRIC__dtlb_all_miss_retired, + P4_PEBS_METRIC__tagged_mispred_branch, + P4_PEBS_METRIC__mob_load_replay_retired, + P4_PEBS_METRIC__split_load_retired, + P4_PEBS_METRIC__split_store_retired, + + P4_PEBS_METRIC__max +}; + +#endif /* PERF_EVENT_P4_H */ + diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index 5e67c153231..ed5903be26f 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -26,7 +26,7 @@ */ #define VMALLOC_OFFSET (8 * 1024 * 1024) -#ifndef __ASSEMBLER__ +#ifndef __ASSEMBLY__ extern bool __vmalloc_start_set; /* set once high_memory is set */ #endif diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 181be528c61..076052cd62b 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -126,8 +126,8 @@ static inline int pgd_large(pgd_t pgd) { return 0; } /* x86-64 always has all page tables mapped. */ #define pte_offset_map(dir, address) pte_offset_kernel((dir), (address)) #define pte_offset_map_nested(dir, address) pte_offset_kernel((dir), (address)) -#define pte_unmap(pte) /* NOP */ -#define pte_unmap_nested(pte) /* NOP */ +#define pte_unmap(pte) ((void)(pte))/* NOP */ +#define pte_unmap_nested(pte) ((void)(pte)) /* NOP */ #define update_mmu_cache(vma, address, ptep) do { } while (0) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index b753ea59703..325b7bdbeba 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -21,7 +21,6 @@ struct mm_struct; #include <asm/msr.h> #include <asm/desc_defs.h> #include <asm/nops.h> -#include <asm/ds.h> #include <linux/personality.h> #include <linux/cpumask.h> @@ -29,6 +28,7 @@ struct mm_struct; #include <linux/threads.h> #include <linux/math64.h> #include <linux/init.h> +#include <linux/err.h> #define HBP_NUM 4 /* @@ -113,7 +113,6 @@ struct cpuinfo_x86 { /* Index into per_cpu list: */ u16 cpu_index; #endif - unsigned int x86_hyper_vendor; } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define X86_VENDOR_INTEL 0 @@ -127,9 +126,6 @@ struct cpuinfo_x86 { #define X86_VENDOR_UNKNOWN 0xff -#define X86_HYPER_VENDOR_NONE 0 -#define X86_HYPER_VENDOR_VMWARE 1 - /* * capabilities of CPUs */ @@ -380,6 +376,10 @@ union thread_xstate { struct xsave_struct xsave; }; +struct fpu { + union thread_xstate *state; +}; + #ifdef CONFIG_X86_64 DECLARE_PER_CPU(struct orig_ist, orig_ist); @@ -457,7 +457,7 @@ struct thread_struct { unsigned long trap_no; unsigned long error_code; /* floating point and extended processor state */ - union thread_xstate *xstate; + struct fpu fpu; #ifdef CONFIG_X86_32 /* Virtual 86 mode info */ struct vm86_struct __user *vm86_info; @@ -473,10 +473,6 @@ struct thread_struct { unsigned long iopl; /* Max allowed port in the bitmap, in bytes: */ unsigned io_bitmap_max; -/* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set. */ - unsigned long debugctlmsr; - /* Debug Store context; see asm/ds.h */ - struct ds_context *ds_ctx; }; static inline unsigned long native_get_debugreg(int regno) @@ -766,6 +762,7 @@ extern void init_c1e_mask(void); extern unsigned long boot_option_idle_override; extern unsigned long idle_halt; extern unsigned long idle_nomwait; +extern bool c1e_detected; /* * on systems with caches, caches must be flashed as the absolute @@ -793,6 +790,8 @@ static inline void wbinvd_halt(void) extern void enable_sep_cpu(void); extern int sysenter_setup(void); +extern void early_trap_init(void); + /* Defined in head.S */ extern struct desc_ptr early_gdt_descr; @@ -803,7 +802,7 @@ extern void cpu_init(void); static inline unsigned long get_debugctlmsr(void) { - unsigned long debugctlmsr = 0; + unsigned long debugctlmsr = 0; #ifndef CONFIG_X86_DEBUGCTLMSR if (boot_cpu_data.x86 < 6) @@ -811,21 +810,6 @@ static inline unsigned long get_debugctlmsr(void) #endif rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); - return debugctlmsr; -} - -static inline unsigned long get_debugctlmsr_on_cpu(int cpu) -{ - u64 debugctlmsr = 0; - u32 val1, val2; - -#ifndef CONFIG_X86_DEBUGCTLMSR - if (boot_cpu_data.x86 < 6) - return 0; -#endif - rdmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, &val1, &val2); - debugctlmsr = val1 | ((u64)val2 << 32); - return debugctlmsr; } @@ -838,18 +822,6 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr) wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); } -static inline void update_debugctlmsr_on_cpu(int cpu, - unsigned long debugctlmsr) -{ -#ifndef CONFIG_X86_DEBUGCTLMSR - if (boot_cpu_data.x86 < 6) - return; -#endif - wrmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, - (u32)((u64)debugctlmsr), - (u32)((u64)debugctlmsr >> 32)); -} - /* * from system description table in BIOS. Mostly for MCA use, but * others may find it useful: @@ -1054,4 +1026,24 @@ unsigned long calc_aperfmperf_ratio(struct aperfmperf *old, return ratio; } +/* + * AMD errata checking + */ +#ifdef CONFIG_CPU_SUP_AMD +extern const int amd_erratum_383[]; +extern const int amd_erratum_400[]; +extern bool cpu_has_amd_erratum(const int *); + +#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } +#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } +#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ + ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) +#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) +#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) +#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) + +#else +#define cpu_has_amd_erratum(x) (false) +#endif /* CONFIG_CPU_SUP_AMD */ + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h index 86723035a51..52b098a6eeb 100644 --- a/arch/x86/include/asm/ptrace-abi.h +++ b/arch/x86/include/asm/ptrace-abi.h @@ -82,61 +82,6 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> - -/* configuration/status structure used in PTRACE_BTS_CONFIG and - PTRACE_BTS_STATUS commands. -*/ -struct ptrace_bts_config { - /* requested or actual size of BTS buffer in bytes */ - __u32 size; - /* bitmask of below flags */ - __u32 flags; - /* buffer overflow signal */ - __u32 signal; - /* actual size of bts_struct in bytes */ - __u32 bts_size; -}; -#endif /* __ASSEMBLY__ */ - -#define PTRACE_BTS_O_TRACE 0x1 /* branch trace */ -#define PTRACE_BTS_O_SCHED 0x2 /* scheduling events w/ jiffies */ -#define PTRACE_BTS_O_SIGNAL 0x4 /* send SIG<signal> on buffer overflow - instead of wrapping around */ -#define PTRACE_BTS_O_ALLOC 0x8 /* (re)allocate buffer */ - -#define PTRACE_BTS_CONFIG 40 -/* Configure branch trace recording. - ADDR points to a struct ptrace_bts_config. - DATA gives the size of that buffer. - A new buffer is allocated, if requested in the flags. - An overflow signal may only be requested for new buffers. - Returns the number of bytes read. -*/ -#define PTRACE_BTS_STATUS 41 -/* Return the current configuration in a struct ptrace_bts_config - pointed to by ADDR; DATA gives the size of that buffer. - Returns the number of bytes written. -*/ -#define PTRACE_BTS_SIZE 42 -/* Return the number of available BTS records for draining. - DATA and ADDR are ignored. -*/ -#define PTRACE_BTS_GET 43 -/* Get a single BTS record. - DATA defines the index into the BTS array, where 0 is the newest - entry, and higher indices refer to older entries. - ADDR is pointing to struct bts_struct (see asm/ds.h). -*/ -#define PTRACE_BTS_CLEAR 44 -/* Clear the BTS buffer. - DATA and ADDR are ignored. -*/ -#define PTRACE_BTS_DRAIN 45 -/* Read all available BTS records and clear the buffer. - ADDR points to an array of struct bts_struct. - DATA gives the size of that buffer. - BTS records are read from oldest to newest. - Returns number of BTS records drained. -*/ +#endif #endif /* _ASM_X86_PTRACE_ABI_H */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 69a686a7dff..78cd1ea9450 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -289,12 +289,6 @@ extern int do_get_thread_area(struct task_struct *p, int idx, extern int do_set_thread_area(struct task_struct *p, int idx, struct user_desc __user *info, int can_allocate); -#ifdef CONFIG_X86_PTRACE_BTS -extern void ptrace_bts_untrace(struct task_struct *tsk); - -#define arch_ptrace_untrace(tsk) ptrace_bts_untrace(tsk) -#endif /* CONFIG_X86_PTRACE_BTS */ - #endif /* __KERNEL__ */ #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h index 6d93508f262..35f2d1948ad 100644 --- a/arch/x86/include/asm/pvclock-abi.h +++ b/arch/x86/include/asm/pvclock-abi.h @@ -29,7 +29,8 @@ struct pvclock_vcpu_time_info { u64 system_time; u32 tsc_to_system_mul; s8 tsc_shift; - u8 pad[3]; + u8 flags; + u8 pad[2]; } __attribute__((__packed__)); /* 32 bytes */ struct pvclock_wall_clock { @@ -38,5 +39,6 @@ struct pvclock_wall_clock { u32 nsec; } __attribute__((__packed__)); +#define PVCLOCK_TSC_STABLE_BIT (1 << 0) #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PVCLOCK_ABI_H */ diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 53235fd5f8c..cd02f324aa6 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -6,6 +6,7 @@ /* some helper functions for xen and kvm pv clock sources */ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src); +void pvclock_set_flags(u8 flags); unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src); void pvclock_read_wallclock(struct pvclock_wall_clock *wall, struct pvclock_vcpu_time_info *vcpu, diff --git a/arch/x86/include/asm/rdc321x_defs.h b/arch/x86/include/asm/rdc321x_defs.h deleted file mode 100644 index c8e9c8bed3d..00000000000 --- a/arch/x86/include/asm/rdc321x_defs.h +++ /dev/null @@ -1,12 +0,0 @@ -#define PFX "rdc321x: " - -/* General purpose configuration and data registers */ -#define RDC3210_CFGREG_ADDR 0x0CF8 -#define RDC3210_CFGREG_DATA 0x0CFC - -#define RDC321X_GPIO_CTRL_REG1 0x48 -#define RDC321X_GPIO_CTRL_REG2 0x84 -#define RDC321X_GPIO_DATA_REG1 0x4c -#define RDC321X_GPIO_DATA_REG2 0x88 - -#define RDC321X_MAX_GPIO 58 diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 64cf2d24fad..6c7fc25f2c3 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -84,5 +84,7 @@ #define REQUIRED_MASK5 0 #define REQUIRED_MASK6 0 #define REQUIRED_MASK7 0 +#define REQUIRED_MASK8 0 +#define REQUIRED_MASK9 0 #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index 606ede12697..d1e41b0f9b6 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -118,7 +118,7 @@ static inline void __down_read(struct rw_semaphore *sem) { asm volatile("# beginning down_read\n\t" LOCK_PREFIX _ASM_INC "(%1)\n\t" - /* adds 0x00000001, returns the old value */ + /* adds 0x00000001 */ " jns 1f\n" " call call_rwsem_down_read_failed\n" "1:\n\t" @@ -156,11 +156,9 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) { rwsem_count_t tmp; - - tmp = RWSEM_ACTIVE_WRITE_BIAS; asm volatile("# beginning down_write\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" - /* subtract 0x0000ffff, returns the old value */ + /* adds 0xffff0001, returns the old value */ " test %1,%1\n\t" /* was the count 0 before? */ " jz 1f\n" @@ -168,7 +166,7 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) "1:\n" "# ending down_write" : "+m" (sem->count), "=d" (tmp) - : "a" (sem), "1" (tmp) + : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) : "memory", "cc"); } @@ -195,16 +193,16 @@ static inline int __down_write_trylock(struct rw_semaphore *sem) */ static inline void __up_read(struct rw_semaphore *sem) { - rwsem_count_t tmp = -RWSEM_ACTIVE_READ_BIAS; + rwsem_count_t tmp; asm volatile("# beginning __up_read\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" /* subtracts 1, returns the old value */ " jns 1f\n\t" - " call call_rwsem_wake\n" + " call call_rwsem_wake\n" /* expects old value in %edx */ "1:\n" "# ending __up_read\n" : "+m" (sem->count), "=d" (tmp) - : "a" (sem), "1" (tmp) + : "a" (sem), "1" (-RWSEM_ACTIVE_READ_BIAS) : "memory", "cc"); } @@ -216,10 +214,9 @@ static inline void __up_write(struct rw_semaphore *sem) rwsem_count_t tmp; asm volatile("# beginning __up_write\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" - /* tries to transition - 0xffff0001 -> 0x00000000 */ - " jz 1f\n" - " call call_rwsem_wake\n" + /* subtracts 0xffff0001, returns the old value */ + " jns 1f\n\t" + " call call_rwsem_wake\n" /* expects old value in %edx */ "1:\n\t" "# ending __up_write\n" : "+m" (sem->count), "=d" (tmp) diff --git a/arch/x86/include/asm/scatterlist.h b/arch/x86/include/asm/scatterlist.h index 75af592677e..4240878b9d7 100644 --- a/arch/x86/include/asm/scatterlist.h +++ b/arch/x86/include/asm/scatterlist.h @@ -1,8 +1,8 @@ #ifndef _ASM_X86_SCATTERLIST_H #define _ASM_X86_SCATTERLIST_H -#define ISA_DMA_THRESHOLD (0x00ffffff) - #include <asm-generic/scatterlist.h> +#define ARCH_HAS_SG_CHAIN + #endif /* _ASM_X86_SCATTERLIST_H */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 86b1506f417..ef292c792d7 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -82,7 +82,7 @@ void *extend_brk(size_t size, size_t align); * executable.) */ #define RESERVE_BRK(name,sz) \ - static void __section(.discard) __used \ + static void __section(.discard.text) __used \ __brk_reservation_fn_##name##__(void) { \ asm volatile ( \ ".pushsection .brk_reservation,\"aw\",@nobits;" \ diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 4dab78edbad..2b16a2ad23d 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -1,6 +1,13 @@ +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs + */ + #ifndef _ASM_X86_STACKTRACE_H #define _ASM_X86_STACKTRACE_H +#include <linux/uaccess.h> + extern int kstack_depth_to_print; struct thread_info; @@ -42,4 +49,46 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data); +#ifdef CONFIG_X86_32 +#define STACKSLOTS_PER_LINE 8 +#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :) +#else +#define STACKSLOTS_PER_LINE 4 +#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) +#endif + +extern void +show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp, char *log_lvl); + +extern void +show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *sp, unsigned long bp, char *log_lvl); + +extern unsigned int code_bytes; + +/* The form of the top of the frame on the stack */ +struct stack_frame { + struct stack_frame *next_frame; + unsigned long return_address; +}; + +struct stack_frame_ia32 { + u32 next_frame; + u32 return_address; +}; + +static inline unsigned long caller_frame_pointer(void) +{ + struct stack_frame *frame; + + get_bp(frame); + +#ifdef CONFIG_FRAME_POINTER + frame = frame->next_frame; +#endif + + return (unsigned long)frame; +} + #endif /* _ASM_X86_STACKTRACE_H */ diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 48dcfa62ea0..fd921c3a684 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -15,6 +15,8 @@ static inline int arch_prepare_suspend(void) { return 0; } struct saved_context { u16 es, fs, gs, ss; unsigned long cr0, cr2, cr3, cr4; + u64 misc_enable; + bool misc_enable_saved; struct desc_ptr gdt; struct desc_ptr idt; u16 ldt; diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 06284f42b75..8d942afae68 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -27,6 +27,8 @@ struct saved_context { u16 ds, es, fs, gs, ss; unsigned long gs_base, gs_kernel_base, fs_base; unsigned long cr0, cr2, cr3, cr4, cr8; + u64 misc_enable; + bool misc_enable_saved; unsigned long efer; u16 gdt_pad; u16 gdt_limit; diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 38638cd2fa4..0e831059ac5 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -81,7 +81,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u32 event_inj_err; u64 nested_cr3; u64 lbr_ctl; - u8 reserved_5[832]; + u64 reserved_5; + u64 next_rip; + u8 reserved_6[816]; }; @@ -115,6 +117,10 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT) #define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT) +#define SVM_VM_CR_VALID_MASK 0x001fULL +#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL +#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL + struct __attribute__ ((__packed__)) vmcb_seg { u16 selector; u16 attrib; @@ -238,6 +244,7 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_EXITINFOSHIFT_TS_REASON_IRET 36 #define SVM_EXITINFOSHIFT_TS_REASON_JMP 38 +#define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44 #define SVM_EXIT_READ_CR0 0x000 #define SVM_EXIT_READ_CR3 0x003 diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 3ad421784ae..cf4e2e381cb 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -80,4 +80,7 @@ asmlinkage long sys32_rt_sigreturn(struct pt_regs *); /* ia32/ipc32.c */ asmlinkage long sys32_ipc(u32, int, int, int, compat_uptr_t, u32); + +asmlinkage long sys32_fanotify_mark(int, unsigned int, u32, u32, int, + const char __user *); #endif /* _ASM_X86_SYS_IA32_H */ diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index b8fe48ee2ed..33ecc3ea878 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -451,10 +451,17 @@ void stop_this_cpu(void *dummy); * * (Could use an alternative three way for this if there was one.) */ -static inline void rdtsc_barrier(void) +static __always_inline void rdtsc_barrier(void) { alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC); alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); } +/* + * We handle most unaligned accesses in hardware. On the other hand + * unaligned DMA can be quite expensive on some Nehalem processors. + * + * Based on this we disable the IP header alignment in network drivers. + */ +#define NET_IP_ALIGN 0 #endif /* _ASM_X86_SYSTEM_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index e0d28901e96..f0b6e5dbc5a 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -87,13 +87,12 @@ struct thread_info { #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* 32bit process */ #define TIF_FORK 18 /* ret_from_fork */ -#define TIF_MEMDIE 20 +#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 */ #define TIF_FREEZE 23 /* is freezing for suspend */ #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ -#define TIF_DEBUGCTLMSR 25 /* uses thread_struct.debugctlmsr */ -#define TIF_DS_AREA_MSR 26 /* uses thread_struct.ds_area_msr */ +#define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */ #define TIF_LAZY_MMU_UPDATES 27 /* task is updating the mmu lazily */ #define TIF_SYSCALL_TRACEPOINT 28 /* syscall tracepoint instrumentation */ @@ -115,8 +114,7 @@ struct thread_info { #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_FREEZE (1 << TIF_FREEZE) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) -#define _TIF_DEBUGCTLMSR (1 << TIF_DEBUGCTLMSR) -#define _TIF_DS_AREA_MSR (1 << TIF_DS_AREA_MSR) +#define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP) #define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) @@ -147,7 +145,7 @@ struct thread_info { /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ - (_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC) + (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP) #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG) @@ -241,10 +239,9 @@ static inline struct thread_info *current_thread_info(void) #define TS_USEDFPU 0x0001 /* FPU was used by this task this quantum (SMP) */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ -#define TS_POLLING 0x0004 /* true if in idle loop - and not sleeping */ +#define TS_POLLING 0x0004 /* idle task polling need_resched, + skip sending interrupt */ #define TS_RESTORE_SIGMASK 0x0008 /* restore signal mask in do_signal() */ -#define TS_XSAVE 0x0010 /* Use xsave/xrstor */ #define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING) diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index c5087d79658..21899cc31e5 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -53,33 +53,29 @@ extern int cpu_to_node_map[]; /* Returns the number of the node containing CPU 'cpu' */ -static inline int cpu_to_node(int cpu) +static inline int __cpu_to_node(int cpu) { return cpu_to_node_map[cpu]; } -#define early_cpu_to_node(cpu) cpu_to_node(cpu) +#define early_cpu_to_node __cpu_to_node +#define cpu_to_node __cpu_to_node #else /* CONFIG_X86_64 */ /* Mappings between logical cpu number and node number */ DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map); -/* Returns the number of the current Node. */ -DECLARE_PER_CPU(int, node_number); -#define numa_node_id() percpu_read(node_number) - #ifdef CONFIG_DEBUG_PER_CPU_MAPS -extern int cpu_to_node(int cpu); +/* + * override generic percpu implementation of cpu_to_node + */ +extern int __cpu_to_node(int cpu); +#define cpu_to_node __cpu_to_node + extern int early_cpu_to_node(int cpu); #else /* !CONFIG_DEBUG_PER_CPU_MAPS */ -/* Returns the number of the node containing CPU 'cpu' */ -static inline int cpu_to_node(int cpu) -{ - return per_cpu(x86_cpu_to_node_map, cpu); -} - /* Same function but used if called before per_cpu areas are setup */ static inline int early_cpu_to_node(int cpu) { @@ -170,6 +166,10 @@ static inline int numa_node_id(void) { return 0; } +/* + * indicate override: + */ +#define numa_node_id numa_node_id static inline int early_cpu_to_node(int cpu) { diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 4da91ad69e0..f66cda56781 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -79,7 +79,7 @@ static inline int get_si_code(unsigned long condition) extern int panic_on_unrecovered_nmi; -void math_error(void __user *); +void math_error(struct pt_regs *, int, int); void math_emulate(struct math_emu_info *); #ifndef CONFIG_X86_32 asmlinkage void smp_thermal_interrupt(void); diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index beb9b5f8f8a..b766a5e8ba0 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -343,10 +343,13 @@ #define __NR_rt_tgsigqueueinfo 335 #define __NR_perf_event_open 336 #define __NR_recvmmsg 337 +#define __NR_fanotify_init 338 +#define __NR_fanotify_mark 339 +#define __NR_prlimit64 340 #ifdef __KERNEL__ -#define NR_syscalls 338 +#define NR_syscalls 341 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index ff4307b0e81..363e9b8a715 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -663,6 +663,12 @@ __SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo) __SYSCALL(__NR_perf_event_open, sys_perf_event_open) #define __NR_recvmmsg 299 __SYSCALL(__NR_recvmmsg, sys_recvmmsg) +#define __NR_fanotify_init 300 +__SYSCALL(__NR_fanotify_init, sys_fanotify_init) +#define __NR_fanotify_mark 301 +__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark) +#define __NR_prlimit64 302 +__SYSCALL(__NR_prlimit64, sys_prlimit64) #ifndef __NO_STUBS #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index b414d2b401f..aa558ac0306 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -27,13 +27,14 @@ * set 2 is at BASE + 2*512, set 3 at BASE + 3*512, and so on. * * We will use 31 sets, one for sending BAU messages from each of the 32 - * cpu's on the node. + * cpu's on the uvhub. * * TLB shootdown will use the first of the 8 descriptors of each set. * Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set). */ #define UV_ITEMS_PER_DESCRIPTOR 8 +#define MAX_BAU_CONCURRENT 3 #define UV_CPUS_PER_ACT_STATUS 32 #define UV_ACT_STATUS_MASK 0x3 #define UV_ACT_STATUS_SIZE 2 @@ -45,6 +46,9 @@ #define UV_PAYLOADQ_PNODE_SHIFT 49 #define UV_PTC_BASENAME "sgi_uv/ptc_statistics" #define uv_physnodeaddr(x) ((__pa((unsigned long)(x)) & uv_mmask)) +#define UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT 15 +#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT 16 +#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x000000000bUL /* * bits in UVH_LB_BAU_SB_ACTIVATION_STATUS_0/1 @@ -55,15 +59,29 @@ #define DESC_STATUS_SOURCE_TIMEOUT 3 /* - * source side thresholds at which message retries print a warning + * source side threshholds at which message retries print a warning */ #define SOURCE_TIMEOUT_LIMIT 20 #define DESTINATION_TIMEOUT_LIMIT 20 /* + * misc. delays, in microseconds + */ +#define THROTTLE_DELAY 10 +#define TIMEOUT_DELAY 10 +#define BIOS_TO 1000 +/* BIOS is assumed to set the destination timeout to 1003520 nanoseconds */ + +/* + * threshholds at which to use IPI to free resources + */ +#define PLUGSB4RESET 100 +#define TIMEOUTSB4RESET 100 + +/* * number of entries in the destination side payload queue */ -#define DEST_Q_SIZE 17 +#define DEST_Q_SIZE 20 /* * number of destination side software ack resources */ @@ -72,9 +90,10 @@ /* * completion statuses for sending a TLB flush message */ -#define FLUSH_RETRY 1 -#define FLUSH_GIVEUP 2 -#define FLUSH_COMPLETE 3 +#define FLUSH_RETRY_PLUGGED 1 +#define FLUSH_RETRY_TIMEOUT 2 +#define FLUSH_GIVEUP 3 +#define FLUSH_COMPLETE 4 /* * Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor) @@ -86,14 +105,14 @@ * 'base_dest_nodeid' field of the header corresponds to the * destination nodeID associated with that specified bit. */ -struct bau_target_nodemask { - unsigned long bits[BITS_TO_LONGS(256)]; +struct bau_target_uvhubmask { + unsigned long bits[BITS_TO_LONGS(UV_DISTRIBUTION_SIZE)]; }; /* - * mask of cpu's on a node + * mask of cpu's on a uvhub * (during initialization we need to check that unsigned long has - * enough bits for max. cpu's per node) + * enough bits for max. cpu's per uvhub) */ struct bau_local_cpumask { unsigned long bits; @@ -135,8 +154,8 @@ struct bau_msg_payload { struct bau_msg_header { unsigned int dest_subnodeid:6; /* must be 0x10, for the LB */ /* bits 5:0 */ - unsigned int base_dest_nodeid:15; /* nasid>>1 (pnode) of */ - /* bits 20:6 */ /* first bit in node_map */ + unsigned int base_dest_nodeid:15; /* nasid (pnode<<1) of */ + /* bits 20:6 */ /* first bit in uvhub map */ unsigned int command:8; /* message type */ /* bits 28:21 */ /* 0x38: SN3net EndPoint Message */ @@ -146,26 +165,38 @@ struct bau_msg_header { unsigned int rsvd_2:9; /* must be zero */ /* bits 40:32 */ /* Suppl_A is 56-41 */ - unsigned int payload_2a:8;/* becomes byte 16 of msg */ - /* bits 48:41 */ /* not currently using */ - unsigned int payload_2b:8;/* becomes byte 17 of msg */ - /* bits 56:49 */ /* not currently using */ + unsigned int sequence:16;/* message sequence number */ + /* bits 56:41 */ /* becomes bytes 16-17 of msg */ /* Address field (96:57) is never used as an address (these are address bits 42:3) */ + unsigned int rsvd_3:1; /* must be zero */ /* bit 57 */ /* address bits 27:4 are payload */ - /* these 24 bits become bytes 12-14 of msg */ + /* these next 24 (58-81) bits become bytes 12-14 of msg */ + + /* bits 65:58 land in byte 12 */ unsigned int replied_to:1;/* sent as 0 by the source to byte 12 */ /* bit 58 */ - - unsigned int payload_1a:5;/* not currently used */ - /* bits 63:59 */ - unsigned int payload_1b:8;/* not currently used */ - /* bits 71:64 */ - unsigned int payload_1c:8;/* not currently used */ - /* bits 79:72 */ - unsigned int payload_1d:2;/* not currently used */ + unsigned int msg_type:3; /* software type of the message*/ + /* bits 61:59 */ + unsigned int canceled:1; /* message canceled, resource to be freed*/ + /* bit 62 */ + unsigned int payload_1a:1;/* not currently used */ + /* bit 63 */ + unsigned int payload_1b:2;/* not currently used */ + /* bits 65:64 */ + + /* bits 73:66 land in byte 13 */ + unsigned int payload_1ca:6;/* not currently used */ + /* bits 71:66 */ + unsigned int payload_1c:2;/* not currently used */ + /* bits 73:72 */ + + /* bits 81:74 land in byte 14 */ + unsigned int payload_1d:6;/* not currently used */ + /* bits 79:74 */ + unsigned int payload_1e:2;/* not currently used */ /* bits 81:80 */ unsigned int rsvd_4:7; /* must be zero */ @@ -178,7 +209,7 @@ struct bau_msg_header { /* bits 95:90 */ unsigned int rsvd_6:5; /* must be zero */ /* bits 100:96 */ - unsigned int int_both:1;/* if 1, interrupt both sockets on the blade */ + unsigned int int_both:1;/* if 1, interrupt both sockets on the uvhub */ /* bit 101*/ unsigned int fairness:3;/* usually zero */ /* bits 104:102 */ @@ -191,13 +222,18 @@ struct bau_msg_header { /* bits 127:107 */ }; +/* see msg_type: */ +#define MSG_NOOP 0 +#define MSG_REGULAR 1 +#define MSG_RETRY 2 + /* * The activation descriptor: * The format of the message to send, plus all accompanying control * Should be 64 bytes */ struct bau_desc { - struct bau_target_nodemask distribution; + struct bau_target_uvhubmask distribution; /* * message template, consisting of header and payload: */ @@ -237,19 +273,25 @@ struct bau_payload_queue_entry { unsigned short acknowledge_count; /* filled in by destination */ /* 16 bits, bytes 10-11 */ - unsigned short replied_to:1; /* sent as 0 by the source */ - /* 1 bit */ - unsigned short unused1:7; /* not currently using */ - /* 7 bits: byte 12) */ + /* these next 3 bytes come from bits 58-81 of the message header */ + unsigned short replied_to:1; /* sent as 0 by the source */ + unsigned short msg_type:3; /* software message type */ + unsigned short canceled:1; /* sent as 0 by the source */ + unsigned short unused1:3; /* not currently using */ + /* byte 12 */ - unsigned char unused2[2]; /* not currently using */ - /* bytes 13-14 */ + unsigned char unused2a; /* not currently using */ + /* byte 13 */ + unsigned char unused2; /* not currently using */ + /* byte 14 */ unsigned char sw_ack_vector; /* filled in by the hardware */ /* byte 15 (bits 127:120) */ - unsigned char unused4[3]; /* not currently using bytes 17-19 */ - /* bytes 17-19 */ + unsigned short sequence; /* message sequence number */ + /* bytes 16-17 */ + unsigned char unused4[2]; /* not currently using bytes 18-19 */ + /* bytes 18-19 */ int number_of_cpus; /* filled in at destination */ /* 32 bits, bytes 20-23 (aligned) */ @@ -259,63 +301,93 @@ struct bau_payload_queue_entry { }; /* - * one for every slot in the destination payload queue - */ -struct bau_msg_status { - struct bau_local_cpumask seen_by; /* map of cpu's */ -}; - -/* - * one for every slot in the destination software ack resources - */ -struct bau_sw_ack_status { - struct bau_payload_queue_entry *msg; /* associated message */ - int watcher; /* cpu monitoring, or -1 */ -}; - -/* - * one on every node and per-cpu; to locate the software tables + * one per-cpu; to locate the software tables */ struct bau_control { struct bau_desc *descriptor_base; - struct bau_payload_queue_entry *bau_msg_head; struct bau_payload_queue_entry *va_queue_first; struct bau_payload_queue_entry *va_queue_last; - struct bau_msg_status *msg_statuses; - int *watching; /* pointer to array */ + struct bau_payload_queue_entry *bau_msg_head; + struct bau_control *uvhub_master; + struct bau_control *socket_master; + unsigned long timeout_interval; + atomic_t active_descriptor_count; + int max_concurrent; + int max_concurrent_constant; + int retry_message_scans; + int plugged_tries; + int timeout_tries; + int ipi_attempts; + int conseccompletes; + short cpu; + short uvhub_cpu; + short uvhub; + short cpus_in_socket; + short cpus_in_uvhub; + unsigned short message_number; + unsigned short uvhub_quiesce; + short socket_acknowledge_count[DEST_Q_SIZE]; + cycles_t send_message; + spinlock_t masks_lock; + spinlock_t uvhub_lock; + spinlock_t queue_lock; }; /* * This structure is allocated per_cpu for UV TLB shootdown statistics. */ struct ptc_stats { - unsigned long ptc_i; /* number of IPI-style flushes */ - unsigned long requestor; /* number of nodes this cpu sent to */ - unsigned long requestee; /* times cpu was remotely requested */ - unsigned long alltlb; /* times all tlb's on this cpu were flushed */ - unsigned long onetlb; /* times just one tlb on this cpu was flushed */ - unsigned long s_retry; /* retries on source side timeouts */ - unsigned long d_retry; /* retries on destination side timeouts */ - unsigned long sflush; /* cycles spent in uv_flush_tlb_others */ - unsigned long dflush; /* cycles spent on destination side */ - unsigned long retriesok; /* successes on retries */ - unsigned long nomsg; /* interrupts with no message */ - unsigned long multmsg; /* interrupts with multiple messages */ - unsigned long ntargeted;/* nodes targeted */ + /* sender statistics */ + unsigned long s_giveup; /* number of fall backs to IPI-style flushes */ + unsigned long s_requestor; /* number of shootdown requests */ + unsigned long s_stimeout; /* source side timeouts */ + unsigned long s_dtimeout; /* destination side timeouts */ + unsigned long s_time; /* time spent in sending side */ + unsigned long s_retriesok; /* successful retries */ + unsigned long s_ntargcpu; /* number of cpus targeted */ + unsigned long s_ntarguvhub; /* number of uvhubs targeted */ + unsigned long s_ntarguvhub16; /* number of times >= 16 target hubs */ + unsigned long s_ntarguvhub8; /* number of times >= 8 target hubs */ + unsigned long s_ntarguvhub4; /* number of times >= 4 target hubs */ + unsigned long s_ntarguvhub2; /* number of times >= 2 target hubs */ + unsigned long s_ntarguvhub1; /* number of times == 1 target hub */ + unsigned long s_resets_plug; /* ipi-style resets from plug state */ + unsigned long s_resets_timeout; /* ipi-style resets from timeouts */ + unsigned long s_busy; /* status stayed busy past s/w timer */ + unsigned long s_throttles; /* waits in throttle */ + unsigned long s_retry_messages; /* retry broadcasts */ + /* destination statistics */ + unsigned long d_alltlb; /* times all tlb's on this cpu were flushed */ + unsigned long d_onetlb; /* times just one tlb on this cpu was flushed */ + unsigned long d_multmsg; /* interrupts with multiple messages */ + unsigned long d_nomsg; /* interrupts with no message */ + unsigned long d_time; /* time spent on destination side */ + unsigned long d_requestee; /* number of messages processed */ + unsigned long d_retries; /* number of retry messages processed */ + unsigned long d_canceled; /* number of messages canceled by retries */ + unsigned long d_nocanceled; /* retries that found nothing to cancel */ + unsigned long d_resets; /* number of ipi-style requests processed */ + unsigned long d_rcanceled; /* number of messages canceled by resets */ }; -static inline int bau_node_isset(int node, struct bau_target_nodemask *dstp) +static inline int bau_uvhub_isset(int uvhub, struct bau_target_uvhubmask *dstp) { - return constant_test_bit(node, &dstp->bits[0]); + return constant_test_bit(uvhub, &dstp->bits[0]); } -static inline void bau_node_set(int node, struct bau_target_nodemask *dstp) +static inline void bau_uvhub_set(int uvhub, struct bau_target_uvhubmask *dstp) { - __set_bit(node, &dstp->bits[0]); + __set_bit(uvhub, &dstp->bits[0]); } -static inline void bau_nodes_clear(struct bau_target_nodemask *dstp, int nbits) +static inline void bau_uvhubs_clear(struct bau_target_uvhubmask *dstp, + int nbits) { bitmap_zero(&dstp->bits[0], nbits); } +static inline int bau_uvhub_weight(struct bau_target_uvhubmask *dstp) +{ + return bitmap_weight((unsigned long *)&dstp->bits[0], + UV_DISTRIBUTION_SIZE); +} static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits) { @@ -328,4 +400,35 @@ static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits) extern void uv_bau_message_intr1(void); extern void uv_bau_timeout_intr1(void); +struct atomic_short { + short counter; +}; + +/** + * atomic_read_short - read a short atomic variable + * @v: pointer of type atomic_short + * + * Atomically reads the value of @v. + */ +static inline int atomic_read_short(const struct atomic_short *v) +{ + return v->counter; +} + +/** + * atomic_add_short_return - add and return a short int + * @i: short value to add + * @v: pointer of type atomic_short + * + * Atomically adds @i to @v and returns @i + @v + */ +static inline int atomic_add_short_return(short i, struct atomic_short *v) +{ + short __i = i; + asm volatile(LOCK_PREFIX "xaddw %0, %1" + : "+r" (i), "+m" (v->counter) + : : "memory"); + return i + __i; +} + #endif /* _ASM_X86_UV_UV_BAU_H */ diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 14cc74ba5d2..bf6b88ef8ee 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -307,7 +307,7 @@ static inline unsigned long uv_read_global_mmr32(int pnode, unsigned long offset * Access Global MMR space using the MMR space located at the top of physical * memory. */ -static inline unsigned long *uv_global_mmr64_address(int pnode, unsigned long offset) +static inline volatile void __iomem *uv_global_mmr64_address(int pnode, unsigned long offset) { return __va(UV_GLOBAL_MMR64_BASE | UV_GLOBAL_MMR64_PNODE_BITS(pnode) | offset); diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index 2cae46c7c8a..b2f2d2e05ce 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -1,4 +1,3 @@ - /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive @@ -15,13 +14,25 @@ #define UV_MMR_ENABLE (1UL << 63) /* ========================================================================= */ +/* UVH_BAU_DATA_BROADCAST */ +/* ========================================================================= */ +#define UVH_BAU_DATA_BROADCAST 0x61688UL +#define UVH_BAU_DATA_BROADCAST_32 0x0440 + +#define UVH_BAU_DATA_BROADCAST_ENABLE_SHFT 0 +#define UVH_BAU_DATA_BROADCAST_ENABLE_MASK 0x0000000000000001UL + +union uvh_bau_data_broadcast_u { + unsigned long v; + struct uvh_bau_data_broadcast_s { + unsigned long enable : 1; /* RW */ + unsigned long rsvd_1_63: 63; /* */ + } s; +}; + +/* ========================================================================= */ /* UVH_BAU_DATA_CONFIG */ /* ========================================================================= */ -#define UVH_LB_BAU_MISC_CONTROL 0x320170UL -#define UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT 15 -#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT 16 -#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x000000000bUL -/* 1011 timebase 7 (168millisec) * 3 ticks -> 500ms */ #define UVH_BAU_DATA_CONFIG 0x61680UL #define UVH_BAU_DATA_CONFIG_32 0x0438 @@ -604,6 +615,68 @@ union uvh_lb_bau_intd_software_acknowledge_u { #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0x0a70 /* ========================================================================= */ +/* UVH_LB_BAU_MISC_CONTROL */ +/* ========================================================================= */ +#define UVH_LB_BAU_MISC_CONTROL 0x320170UL +#define UVH_LB_BAU_MISC_CONTROL_32 0x00a10 + +#define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0 +#define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL +#define UVH_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8 +#define UVH_LB_BAU_MISC_CONTROL_APIC_MODE_MASK 0x0000000000000100UL +#define UVH_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT 9 +#define UVH_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL +#define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10 +#define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL +#define UVH_LB_BAU_MISC_CONTROL_CSI_AGENT_PRESENCE_VECTOR_SHFT 11 +#define UVH_LB_BAU_MISC_CONTROL_CSI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL +#define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14 +#define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL +#define UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15 +#define UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL +#define UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16 +#define UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL +#define UVH_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20 +#define UVH_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL +#define UVH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21 +#define UVH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL +#define UVH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22 +#define UVH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL +#define UVH_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_SHFT 23 +#define UVH_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_MASK 0x0000000000800000UL +#define UVH_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24 +#define UVH_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL +#define UVH_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27 +#define UVH_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL +#define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28 +#define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL +#define UVH_LB_BAU_MISC_CONTROL_FUN_SHFT 48 +#define UVH_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL + +union uvh_lb_bau_misc_control_u { + unsigned long v; + struct uvh_lb_bau_misc_control_s { + unsigned long rejection_delay : 8; /* RW */ + unsigned long apic_mode : 1; /* RW */ + unsigned long force_broadcast : 1; /* RW */ + unsigned long force_lock_nop : 1; /* RW */ + unsigned long csi_agent_presence_vector : 3; /* RW */ + unsigned long descriptor_fetch_mode : 1; /* RW */ + unsigned long enable_intd_soft_ack_mode : 1; /* RW */ + unsigned long intd_soft_ack_timeout_period : 4; /* RW */ + unsigned long enable_dual_mapping_mode : 1; /* RW */ + unsigned long vga_io_port_decode_enable : 1; /* RW */ + unsigned long vga_io_port_16_bit_decode : 1; /* RW */ + unsigned long suppress_dest_registration : 1; /* RW */ + unsigned long programmed_initial_priority : 3; /* RW */ + unsigned long use_incoming_priority : 1; /* RW */ + unsigned long enable_programmed_initial_priority : 1; /* RW */ + unsigned long rsvd_29_47 : 19; /* */ + unsigned long fun : 16; /* RW */ + } s; +}; + +/* ========================================================================= */ /* UVH_LB_BAU_SB_ACTIVATION_CONTROL */ /* ========================================================================= */ #define UVH_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL @@ -681,334 +754,6 @@ union uvh_lb_bau_sb_descriptor_base_u { }; /* ========================================================================= */ -/* UVH_LB_MCAST_AOERR0_RPT_ENABLE */ -/* ========================================================================= */ -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE 0x50b20UL - -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_OBESE_MSG_SHFT 0 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_OBESE_MSG_MASK 0x0000000000000001UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_DATA_SB_ERR_SHFT 1 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_DATA_SB_ERR_MASK 0x0000000000000002UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_NACK_BUFF_PARITY_SHFT 2 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_NACK_BUFF_PARITY_MASK 0x0000000000000004UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_TIMEOUT_SHFT 3 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_TIMEOUT_MASK 0x0000000000000008UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_INACTIVE_REPLY_SHFT 4 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_INACTIVE_REPLY_MASK 0x0000000000000010UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_UPGRADE_ERROR_SHFT 5 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_UPGRADE_ERROR_MASK 0x0000000000000020UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REG_COUNT_UNDERFLOW_SHFT 6 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REG_COUNT_UNDERFLOW_MASK 0x0000000000000040UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REP_OBESE_MSG_SHFT 7 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REP_OBESE_MSG_MASK 0x0000000000000080UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_RUNT_MSG_SHFT 8 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_RUNT_MSG_MASK 0x0000000000000100UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_OBESE_MSG_SHFT 9 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_OBESE_MSG_MASK 0x0000000000000200UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_DATA_SB_ERR_SHFT 10 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_DATA_SB_ERR_MASK 0x0000000000000400UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_RUNT_MSG_SHFT 11 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_RUNT_MSG_MASK 0x0000000000000800UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_OBESE_MSG_SHFT 12 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_OBESE_MSG_MASK 0x0000000000001000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_DATA_SB_ERR_SHFT 13 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_DATA_SB_ERR_MASK 0x0000000000002000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_COMMAND_ERR_SHFT 14 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_COMMAND_ERR_MASK 0x0000000000004000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_PEND_TIMEOUT_SHFT 15 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_PEND_TIMEOUT_MASK 0x0000000000008000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_RUNT_MSG_SHFT 16 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_RUNT_MSG_MASK 0x0000000000010000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_OBESE_MSG_SHFT 17 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_OBESE_MSG_MASK 0x0000000000020000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_DATA_SB_ERR_SHFT 18 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_DATA_SB_ERR_MASK 0x0000000000040000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_RUNT_MSG_SHFT 19 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_RUNT_MSG_MASK 0x0000000000080000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_OBESE_MSG_SHFT 20 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_OBESE_MSG_MASK 0x0000000000100000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_DATA_SB_ERR_SHFT 21 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_DATA_SB_ERR_MASK 0x0000000000200000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_AMO_TIMEOUT_SHFT 22 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_AMO_TIMEOUT_MASK 0x0000000000400000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_PUT_TIMEOUT_SHFT 23 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_PUT_TIMEOUT_MASK 0x0000000000800000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_SPURIOUS_EVENT_SHFT 24 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_SPURIOUS_EVENT_MASK 0x0000000001000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IOH_DESTINATION_TABLE_PARITY_SHFT 25 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IOH_DESTINATION_TABLE_PARITY_MASK 0x0000000002000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_HAD_ERROR_REPLY_SHFT 26 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_HAD_ERROR_REPLY_MASK 0x0000000004000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_TIMEOUT_SHFT 27 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_TIMEOUT_MASK 0x0000000008000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_LOCK_MANAGER_HAD_ERROR_REPLY_SHFT 28 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_LOCK_MANAGER_HAD_ERROR_REPLY_MASK 0x0000000010000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_HAD_ERROR_REPLY_SHFT 29 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_HAD_ERROR_REPLY_MASK 0x0000000020000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_TIMEOUT_SHFT 30 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_TIMEOUT_MASK 0x0000000040000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SB_ACTIVATION_OVERRUN_SHFT 31 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SB_ACTIVATION_OVERRUN_MASK 0x0000000080000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_HAD_ERROR_REPLY_SHFT 32 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_HAD_ERROR_REPLY_MASK 0x0000000100000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_TIMEOUT_SHFT 33 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_TIMEOUT_MASK 0x0000000200000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_0_PARITY_SHFT 34 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_0_PARITY_MASK 0x0000000400000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_1_PARITY_SHFT 35 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_1_PARITY_MASK 0x0000000800000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SOCKET_DESTINATION_TABLE_PARITY_SHFT 36 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SOCKET_DESTINATION_TABLE_PARITY_MASK 0x0000001000000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_BAU_REPLY_PAYLOAD_CORRUPTION_SHFT 37 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_BAU_REPLY_PAYLOAD_CORRUPTION_MASK 0x0000002000000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IO_PORT_DESTINATION_TABLE_PARITY_SHFT 38 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IO_PORT_DESTINATION_TABLE_PARITY_MASK 0x0000004000000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INTD_SOFT_ACK_TIMEOUT_SHFT 39 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INTD_SOFT_ACK_TIMEOUT_MASK 0x0000008000000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_OBESE_MSG_SHFT 40 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_OBESE_MSG_MASK 0x0000010000000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_COMMAND_ERR_SHFT 41 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_COMMAND_ERR_MASK 0x0000020000000000UL -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_TIMEOUT_SHFT 42 -#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_TIMEOUT_MASK 0x0000040000000000UL - -union uvh_lb_mcast_aoerr0_rpt_enable_u { - unsigned long v; - struct uvh_lb_mcast_aoerr0_rpt_enable_s { - unsigned long mcast_obese_msg : 1; /* RW */ - unsigned long mcast_data_sb_err : 1; /* RW */ - unsigned long mcast_nack_buff_parity : 1; /* RW */ - unsigned long mcast_timeout : 1; /* RW */ - unsigned long mcast_inactive_reply : 1; /* RW */ - unsigned long mcast_upgrade_error : 1; /* RW */ - unsigned long mcast_reg_count_underflow : 1; /* RW */ - unsigned long mcast_rep_obese_msg : 1; /* RW */ - unsigned long ucache_req_runt_msg : 1; /* RW */ - unsigned long ucache_req_obese_msg : 1; /* RW */ - unsigned long ucache_req_data_sb_err : 1; /* RW */ - unsigned long ucache_rep_runt_msg : 1; /* RW */ - unsigned long ucache_rep_obese_msg : 1; /* RW */ - unsigned long ucache_rep_data_sb_err : 1; /* RW */ - unsigned long ucache_rep_command_err : 1; /* RW */ - unsigned long ucache_pend_timeout : 1; /* RW */ - unsigned long macc_req_runt_msg : 1; /* RW */ - unsigned long macc_req_obese_msg : 1; /* RW */ - unsigned long macc_req_data_sb_err : 1; /* RW */ - unsigned long macc_rep_runt_msg : 1; /* RW */ - unsigned long macc_rep_obese_msg : 1; /* RW */ - unsigned long macc_rep_data_sb_err : 1; /* RW */ - unsigned long macc_amo_timeout : 1; /* RW */ - unsigned long macc_put_timeout : 1; /* RW */ - unsigned long macc_spurious_event : 1; /* RW */ - unsigned long ioh_destination_table_parity : 1; /* RW */ - unsigned long get_had_error_reply : 1; /* RW */ - unsigned long get_timeout : 1; /* RW */ - unsigned long lock_manager_had_error_reply : 1; /* RW */ - unsigned long put_had_error_reply : 1; /* RW */ - unsigned long put_timeout : 1; /* RW */ - unsigned long sb_activation_overrun : 1; /* RW */ - unsigned long completed_gb_activation_had_error_reply : 1; /* RW */ - unsigned long completed_gb_activation_timeout : 1; /* RW */ - unsigned long descriptor_buffer_0_parity : 1; /* RW */ - unsigned long descriptor_buffer_1_parity : 1; /* RW */ - unsigned long socket_destination_table_parity : 1; /* RW */ - unsigned long bau_reply_payload_corruption : 1; /* RW */ - unsigned long io_port_destination_table_parity : 1; /* RW */ - unsigned long intd_soft_ack_timeout : 1; /* RW */ - unsigned long int_rep_obese_msg : 1; /* RW */ - unsigned long int_rep_command_err : 1; /* RW */ - unsigned long int_timeout : 1; /* RW */ - unsigned long rsvd_43_63 : 21; /* */ - } s; -}; - -/* ========================================================================= */ -/* UVH_LOCAL_INT0_CONFIG */ -/* ========================================================================= */ -#define UVH_LOCAL_INT0_CONFIG 0x61000UL - -#define UVH_LOCAL_INT0_CONFIG_VECTOR_SHFT 0 -#define UVH_LOCAL_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL -#define UVH_LOCAL_INT0_CONFIG_DM_SHFT 8 -#define UVH_LOCAL_INT0_CONFIG_DM_MASK 0x0000000000000700UL -#define UVH_LOCAL_INT0_CONFIG_DESTMODE_SHFT 11 -#define UVH_LOCAL_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL -#define UVH_LOCAL_INT0_CONFIG_STATUS_SHFT 12 -#define UVH_LOCAL_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL -#define UVH_LOCAL_INT0_CONFIG_P_SHFT 13 -#define UVH_LOCAL_INT0_CONFIG_P_MASK 0x0000000000002000UL -#define UVH_LOCAL_INT0_CONFIG_T_SHFT 15 -#define UVH_LOCAL_INT0_CONFIG_T_MASK 0x0000000000008000UL -#define UVH_LOCAL_INT0_CONFIG_M_SHFT 16 -#define UVH_LOCAL_INT0_CONFIG_M_MASK 0x0000000000010000UL -#define UVH_LOCAL_INT0_CONFIG_APIC_ID_SHFT 32 -#define UVH_LOCAL_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL - -union uvh_local_int0_config_u { - unsigned long v; - struct uvh_local_int0_config_s { - unsigned long vector_ : 8; /* RW */ - unsigned long dm : 3; /* RW */ - unsigned long destmode : 1; /* RW */ - unsigned long status : 1; /* RO */ - unsigned long p : 1; /* RO */ - unsigned long rsvd_14 : 1; /* */ - unsigned long t : 1; /* RO */ - unsigned long m : 1; /* RW */ - unsigned long rsvd_17_31: 15; /* */ - unsigned long apic_id : 32; /* RW */ - } s; -}; - -/* ========================================================================= */ -/* UVH_LOCAL_INT0_ENABLE */ -/* ========================================================================= */ -#define UVH_LOCAL_INT0_ENABLE 0x65000UL - -#define UVH_LOCAL_INT0_ENABLE_LB_HCERR_SHFT 0 -#define UVH_LOCAL_INT0_ENABLE_LB_HCERR_MASK 0x0000000000000001UL -#define UVH_LOCAL_INT0_ENABLE_GR0_HCERR_SHFT 1 -#define UVH_LOCAL_INT0_ENABLE_GR0_HCERR_MASK 0x0000000000000002UL -#define UVH_LOCAL_INT0_ENABLE_GR1_HCERR_SHFT 2 -#define UVH_LOCAL_INT0_ENABLE_GR1_HCERR_MASK 0x0000000000000004UL -#define UVH_LOCAL_INT0_ENABLE_LH_HCERR_SHFT 3 -#define UVH_LOCAL_INT0_ENABLE_LH_HCERR_MASK 0x0000000000000008UL -#define UVH_LOCAL_INT0_ENABLE_RH_HCERR_SHFT 4 -#define UVH_LOCAL_INT0_ENABLE_RH_HCERR_MASK 0x0000000000000010UL -#define UVH_LOCAL_INT0_ENABLE_XN_HCERR_SHFT 5 -#define UVH_LOCAL_INT0_ENABLE_XN_HCERR_MASK 0x0000000000000020UL -#define UVH_LOCAL_INT0_ENABLE_SI_HCERR_SHFT 6 -#define UVH_LOCAL_INT0_ENABLE_SI_HCERR_MASK 0x0000000000000040UL -#define UVH_LOCAL_INT0_ENABLE_LB_AOERR0_SHFT 7 -#define UVH_LOCAL_INT0_ENABLE_LB_AOERR0_MASK 0x0000000000000080UL -#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR0_SHFT 8 -#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR0_MASK 0x0000000000000100UL -#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR0_SHFT 9 -#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR0_MASK 0x0000000000000200UL -#define UVH_LOCAL_INT0_ENABLE_LH_AOERR0_SHFT 10 -#define UVH_LOCAL_INT0_ENABLE_LH_AOERR0_MASK 0x0000000000000400UL -#define UVH_LOCAL_INT0_ENABLE_RH_AOERR0_SHFT 11 -#define UVH_LOCAL_INT0_ENABLE_RH_AOERR0_MASK 0x0000000000000800UL -#define UVH_LOCAL_INT0_ENABLE_XN_AOERR0_SHFT 12 -#define UVH_LOCAL_INT0_ENABLE_XN_AOERR0_MASK 0x0000000000001000UL -#define UVH_LOCAL_INT0_ENABLE_SI_AOERR0_SHFT 13 -#define UVH_LOCAL_INT0_ENABLE_SI_AOERR0_MASK 0x0000000000002000UL -#define UVH_LOCAL_INT0_ENABLE_LB_AOERR1_SHFT 14 -#define UVH_LOCAL_INT0_ENABLE_LB_AOERR1_MASK 0x0000000000004000UL -#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR1_SHFT 15 -#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR1_MASK 0x0000000000008000UL -#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR1_SHFT 16 -#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR1_MASK 0x0000000000010000UL -#define UVH_LOCAL_INT0_ENABLE_LH_AOERR1_SHFT 17 -#define UVH_LOCAL_INT0_ENABLE_LH_AOERR1_MASK 0x0000000000020000UL -#define UVH_LOCAL_INT0_ENABLE_RH_AOERR1_SHFT 18 -#define UVH_LOCAL_INT0_ENABLE_RH_AOERR1_MASK 0x0000000000040000UL -#define UVH_LOCAL_INT0_ENABLE_XN_AOERR1_SHFT 19 -#define UVH_LOCAL_INT0_ENABLE_XN_AOERR1_MASK 0x0000000000080000UL -#define UVH_LOCAL_INT0_ENABLE_SI_AOERR1_SHFT 20 -#define UVH_LOCAL_INT0_ENABLE_SI_AOERR1_MASK 0x0000000000100000UL -#define UVH_LOCAL_INT0_ENABLE_RH_VPI_INT_SHFT 21 -#define UVH_LOCAL_INT0_ENABLE_RH_VPI_INT_MASK 0x0000000000200000UL -#define UVH_LOCAL_INT0_ENABLE_SYSTEM_SHUTDOWN_INT_SHFT 22 -#define UVH_LOCAL_INT0_ENABLE_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_0_SHFT 23 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_0_MASK 0x0000000000800000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_1_SHFT 24 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_1_MASK 0x0000000001000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_2_SHFT 25 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_2_MASK 0x0000000002000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_3_SHFT 26 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_3_MASK 0x0000000004000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_4_SHFT 27 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_4_MASK 0x0000000008000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_5_SHFT 28 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_5_MASK 0x0000000010000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_6_SHFT 29 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_6_MASK 0x0000000020000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_7_SHFT 30 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_7_MASK 0x0000000040000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_8_SHFT 31 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_8_MASK 0x0000000080000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_9_SHFT 32 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_9_MASK 0x0000000100000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_10_SHFT 33 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_10_MASK 0x0000000200000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_11_SHFT 34 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_11_MASK 0x0000000400000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_12_SHFT 35 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_12_MASK 0x0000000800000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_13_SHFT 36 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_13_MASK 0x0000001000000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_14_SHFT 37 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_14_MASK 0x0000002000000000UL -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_15_SHFT 38 -#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_15_MASK 0x0000004000000000UL -#define UVH_LOCAL_INT0_ENABLE_L1_NMI_INT_SHFT 39 -#define UVH_LOCAL_INT0_ENABLE_L1_NMI_INT_MASK 0x0000008000000000UL -#define UVH_LOCAL_INT0_ENABLE_STOP_CLOCK_SHFT 40 -#define UVH_LOCAL_INT0_ENABLE_STOP_CLOCK_MASK 0x0000010000000000UL -#define UVH_LOCAL_INT0_ENABLE_ASIC_TO_L1_SHFT 41 -#define UVH_LOCAL_INT0_ENABLE_ASIC_TO_L1_MASK 0x0000020000000000UL -#define UVH_LOCAL_INT0_ENABLE_L1_TO_ASIC_SHFT 42 -#define UVH_LOCAL_INT0_ENABLE_L1_TO_ASIC_MASK 0x0000040000000000UL -#define UVH_LOCAL_INT0_ENABLE_LTC_INT_SHFT 43 -#define UVH_LOCAL_INT0_ENABLE_LTC_INT_MASK 0x0000080000000000UL -#define UVH_LOCAL_INT0_ENABLE_LA_SEQ_TRIGGER_SHFT 44 -#define UVH_LOCAL_INT0_ENABLE_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL - -union uvh_local_int0_enable_u { - unsigned long v; - struct uvh_local_int0_enable_s { - unsigned long lb_hcerr : 1; /* RW */ - unsigned long gr0_hcerr : 1; /* RW */ - unsigned long gr1_hcerr : 1; /* RW */ - unsigned long lh_hcerr : 1; /* RW */ - unsigned long rh_hcerr : 1; /* RW */ - unsigned long xn_hcerr : 1; /* RW */ - unsigned long si_hcerr : 1; /* RW */ - unsigned long lb_aoerr0 : 1; /* RW */ - unsigned long gr0_aoerr0 : 1; /* RW */ - unsigned long gr1_aoerr0 : 1; /* RW */ - unsigned long lh_aoerr0 : 1; /* RW */ - unsigned long rh_aoerr0 : 1; /* RW */ - unsigned long xn_aoerr0 : 1; /* RW */ - unsigned long si_aoerr0 : 1; /* RW */ - unsigned long lb_aoerr1 : 1; /* RW */ - unsigned long gr0_aoerr1 : 1; /* RW */ - unsigned long gr1_aoerr1 : 1; /* RW */ - unsigned long lh_aoerr1 : 1; /* RW */ - unsigned long rh_aoerr1 : 1; /* RW */ - unsigned long xn_aoerr1 : 1; /* RW */ - unsigned long si_aoerr1 : 1; /* RW */ - unsigned long rh_vpi_int : 1; /* RW */ - unsigned long system_shutdown_int : 1; /* RW */ - unsigned long lb_irq_int_0 : 1; /* RW */ - unsigned long lb_irq_int_1 : 1; /* RW */ - unsigned long lb_irq_int_2 : 1; /* RW */ - unsigned long lb_irq_int_3 : 1; /* RW */ - unsigned long lb_irq_int_4 : 1; /* RW */ - unsigned long lb_irq_int_5 : 1; /* RW */ - unsigned long lb_irq_int_6 : 1; /* RW */ - unsigned long lb_irq_int_7 : 1; /* RW */ - unsigned long lb_irq_int_8 : 1; /* RW */ - unsigned long lb_irq_int_9 : 1; /* RW */ - unsigned long lb_irq_int_10 : 1; /* RW */ - unsigned long lb_irq_int_11 : 1; /* RW */ - unsigned long lb_irq_int_12 : 1; /* RW */ - unsigned long lb_irq_int_13 : 1; /* RW */ - unsigned long lb_irq_int_14 : 1; /* RW */ - unsigned long lb_irq_int_15 : 1; /* RW */ - unsigned long l1_nmi_int : 1; /* RW */ - unsigned long stop_clock : 1; /* RW */ - unsigned long asic_to_l1 : 1; /* RW */ - unsigned long l1_to_asic : 1; /* RW */ - unsigned long ltc_int : 1; /* RW */ - unsigned long la_seq_trigger : 1; /* RW */ - unsigned long rsvd_45_63 : 19; /* */ - } s; -}; - -/* ========================================================================= */ /* UVH_NODE_ID */ /* ========================================================================= */ #define UVH_NODE_ID 0x0UL @@ -1112,26 +857,6 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u { }; /* ========================================================================= */ -/* UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR */ -/* ========================================================================= */ -#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR 0x1600020UL - -#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_SHFT 26 -#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL -#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 -#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL - -union uvh_rh_gam_cfg_overlay_config_mmr_u { - unsigned long v; - struct uvh_rh_gam_cfg_overlay_config_mmr_s { - unsigned long rsvd_0_25: 26; /* */ - unsigned long base : 20; /* RW */ - unsigned long rsvd_46_62: 17; /* */ - unsigned long enable : 1; /* RW */ - } s; -}; - -/* ========================================================================= */ /* UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR */ /* ========================================================================= */ #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL @@ -1263,101 +988,6 @@ union uvh_rtc1_int_config_u { }; /* ========================================================================= */ -/* UVH_RTC2_INT_CONFIG */ -/* ========================================================================= */ -#define UVH_RTC2_INT_CONFIG 0x61600UL - -#define UVH_RTC2_INT_CONFIG_VECTOR_SHFT 0 -#define UVH_RTC2_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL -#define UVH_RTC2_INT_CONFIG_DM_SHFT 8 -#define UVH_RTC2_INT_CONFIG_DM_MASK 0x0000000000000700UL -#define UVH_RTC2_INT_CONFIG_DESTMODE_SHFT 11 -#define UVH_RTC2_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL -#define UVH_RTC2_INT_CONFIG_STATUS_SHFT 12 -#define UVH_RTC2_INT_CONFIG_STATUS_MASK 0x0000000000001000UL -#define UVH_RTC2_INT_CONFIG_P_SHFT 13 -#define UVH_RTC2_INT_CONFIG_P_MASK 0x0000000000002000UL -#define UVH_RTC2_INT_CONFIG_T_SHFT 15 -#define UVH_RTC2_INT_CONFIG_T_MASK 0x0000000000008000UL -#define UVH_RTC2_INT_CONFIG_M_SHFT 16 -#define UVH_RTC2_INT_CONFIG_M_MASK 0x0000000000010000UL -#define UVH_RTC2_INT_CONFIG_APIC_ID_SHFT 32 -#define UVH_RTC2_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL - -union uvh_rtc2_int_config_u { - unsigned long v; - struct uvh_rtc2_int_config_s { - unsigned long vector_ : 8; /* RW */ - unsigned long dm : 3; /* RW */ - unsigned long destmode : 1; /* RW */ - unsigned long status : 1; /* RO */ - unsigned long p : 1; /* RO */ - unsigned long rsvd_14 : 1; /* */ - unsigned long t : 1; /* RO */ - unsigned long m : 1; /* RW */ - unsigned long rsvd_17_31: 15; /* */ - unsigned long apic_id : 32; /* RW */ - } s; -}; - -/* ========================================================================= */ -/* UVH_RTC3_INT_CONFIG */ -/* ========================================================================= */ -#define UVH_RTC3_INT_CONFIG 0x61640UL - -#define UVH_RTC3_INT_CONFIG_VECTOR_SHFT 0 -#define UVH_RTC3_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL -#define UVH_RTC3_INT_CONFIG_DM_SHFT 8 -#define UVH_RTC3_INT_CONFIG_DM_MASK 0x0000000000000700UL -#define UVH_RTC3_INT_CONFIG_DESTMODE_SHFT 11 -#define UVH_RTC3_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL -#define UVH_RTC3_INT_CONFIG_STATUS_SHFT 12 -#define UVH_RTC3_INT_CONFIG_STATUS_MASK 0x0000000000001000UL -#define UVH_RTC3_INT_CONFIG_P_SHFT 13 -#define UVH_RTC3_INT_CONFIG_P_MASK 0x0000000000002000UL -#define UVH_RTC3_INT_CONFIG_T_SHFT 15 -#define UVH_RTC3_INT_CONFIG_T_MASK 0x0000000000008000UL -#define UVH_RTC3_INT_CONFIG_M_SHFT 16 -#define UVH_RTC3_INT_CONFIG_M_MASK 0x0000000000010000UL -#define UVH_RTC3_INT_CONFIG_APIC_ID_SHFT 32 -#define UVH_RTC3_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL - -union uvh_rtc3_int_config_u { - unsigned long v; - struct uvh_rtc3_int_config_s { - unsigned long vector_ : 8; /* RW */ - unsigned long dm : 3; /* RW */ - unsigned long destmode : 1; /* RW */ - unsigned long status : 1; /* RO */ - unsigned long p : 1; /* RO */ - unsigned long rsvd_14 : 1; /* */ - unsigned long t : 1; /* RO */ - unsigned long m : 1; /* RW */ - unsigned long rsvd_17_31: 15; /* */ - unsigned long apic_id : 32; /* RW */ - } s; -}; - -/* ========================================================================= */ -/* UVH_RTC_INC_RATIO */ -/* ========================================================================= */ -#define UVH_RTC_INC_RATIO 0x350000UL - -#define UVH_RTC_INC_RATIO_FRACTION_SHFT 0 -#define UVH_RTC_INC_RATIO_FRACTION_MASK 0x00000000000fffffUL -#define UVH_RTC_INC_RATIO_RATIO_SHFT 20 -#define UVH_RTC_INC_RATIO_RATIO_MASK 0x0000000000700000UL - -union uvh_rtc_inc_ratio_u { - unsigned long v; - struct uvh_rtc_inc_ratio_s { - unsigned long fraction : 20; /* RW */ - unsigned long ratio : 3; /* RW */ - unsigned long rsvd_23_63: 41; /* */ - } s; -}; - -/* ========================================================================= */ /* UVH_SI_ADDR_MAP_CONFIG */ /* ========================================================================= */ #define UVH_SI_ADDR_MAP_CONFIG 0xc80000UL diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h deleted file mode 100644 index e49ed6d2fd4..00000000000 --- a/arch/x86/include/asm/vmware.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * Copyright (C) 2008, VMware, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or - * NON INFRINGEMENT. See the GNU General Public License for more - * details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. - * - */ -#ifndef ASM_X86__VMWARE_H -#define ASM_X86__VMWARE_H - -extern void vmware_platform_setup(void); -extern int vmware_platform(void); -extern void vmware_set_feature_bits(struct cpuinfo_x86 *c); - -#endif diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index fb9a080740e..9f0cbd987d5 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -25,6 +25,8 @@ * */ +#include <linux/types.h> + /* * Definitions of Primary Processor-Based VM-Execution Controls. */ @@ -120,6 +122,8 @@ enum vmcs_field { GUEST_IA32_DEBUGCTL_HIGH = 0x00002803, GUEST_IA32_PAT = 0x00002804, GUEST_IA32_PAT_HIGH = 0x00002805, + GUEST_IA32_EFER = 0x00002806, + GUEST_IA32_EFER_HIGH = 0x00002807, GUEST_PDPTR0 = 0x0000280a, GUEST_PDPTR0_HIGH = 0x0000280b, GUEST_PDPTR1 = 0x0000280c, @@ -130,6 +134,8 @@ enum vmcs_field { GUEST_PDPTR3_HIGH = 0x00002811, HOST_IA32_PAT = 0x00002c00, HOST_IA32_PAT_HIGH = 0x00002c01, + HOST_IA32_EFER = 0x00002c02, + HOST_IA32_EFER_HIGH = 0x00002c03, PIN_BASED_VM_EXEC_CONTROL = 0x00004000, CPU_BASED_VM_EXEC_CONTROL = 0x00004002, EXCEPTION_BITMAP = 0x00004004, @@ -251,6 +257,7 @@ enum vmcs_field { #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 @@ -260,6 +267,7 @@ enum vmcs_field { #define EXIT_REASON_EPT_VIOLATION 48 #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_WBINVD 54 +#define EXIT_REASON_XSETBV 55 /* * Interruption-information format @@ -369,6 +377,9 @@ enum vmcs_field { #define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25) #define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26) +#define VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT (1ull << 9) /* (41 - 32) */ +#define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT (1ull << 10) /* (42 - 32) */ + #define VMX_EPT_DEFAULT_GAW 3 #define VMX_EPT_MAX_GAW 0x4 #define VMX_EPT_MT_EPTE_SHIFT 3 @@ -394,6 +405,10 @@ enum vmcs_field { #define ASM_VMX_INVEPT ".byte 0x66, 0x0f, 0x38, 0x80, 0x08" #define ASM_VMX_INVVPID ".byte 0x66, 0x0f, 0x38, 0x81, 0x08" - +struct vmx_msr_entry { + u32 index; + u32 reserved; + u64 value; +} __aligned(16); #endif diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 519b54327d7..baa579c8e03 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -142,6 +142,7 @@ struct x86_cpuinit_ops { * @set_wallclock: set time back to HW clock * @is_untracked_pat_range exclude from PAT logic * @nmi_init enable NMI on cpus + * @i8042_detect pre-detect if i8042 controller exists */ struct x86_platform_ops { unsigned long (*calibrate_tsc)(void); @@ -150,6 +151,7 @@ struct x86_platform_ops { void (*iommu_shutdown)(void); bool (*is_untracked_pat_range)(u64 start, u64 end); void (*nmi_init)(void); + int (*i8042_detect)(void); }; extern struct x86_init_ops x86_init; diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 9c371e4a9fa..7fda040a76c 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -417,6 +417,12 @@ HYPERVISOR_nmi_op(unsigned long op, unsigned long arg) return _hypercall2(int, nmi_op, op, arg); } +static inline unsigned long __must_check +HYPERVISOR_hvm_op(int op, void *arg) +{ + return _hypercall2(unsigned long, hvm_op, op, arg); +} + static inline void MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) { diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index ddc04ccad03..c6ce2452f10 100644 --- a/arch/x86/include/asm/xsave.h +++ b/arch/x86/include/asm/xsave.h @@ -3,7 +3,8 @@ #include <linux/types.h> #include <asm/processor.h> -#include <asm/i387.h> + +#define XSTATE_CPUID 0x0000000d #define XSTATE_FP 0x1 #define XSTATE_SSE 0x2 @@ -13,6 +14,12 @@ #define FXSAVE_SIZE 512 +#define XSAVE_HDR_SIZE 64 +#define XSAVE_HDR_OFFSET FXSAVE_SIZE + +#define XSAVE_YMM_SIZE 256 +#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) + /* * These are the features that the OS can handle currently. */ @@ -26,10 +33,8 @@ extern unsigned int xstate_size; extern u64 pcntxt_mask; -extern struct xsave_struct *init_xstate_buf; extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; -extern void xsave_cntxt_init(void); extern void xsave_init(void); extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); extern int init_fpu(struct task_struct *child); @@ -37,8 +42,9 @@ extern int check_for_xstate(struct i387_fxsave_struct __user *buf, void __user *fpstate, struct _fpx_sw_bytes *sw); -static inline int xrstor_checking(struct xsave_struct *fx) +static inline int fpu_xrstor_checking(struct fpu *fpu) { + struct xsave_struct *fx = &fpu->state->xsave; int err; asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n\t" @@ -58,6 +64,16 @@ static inline int xrstor_checking(struct xsave_struct *fx) static inline int xsave_user(struct xsave_struct __user *buf) { int err; + + /* + * Clear the xsave header first, so that reserved fields are + * initialized to zero. + */ + err = __clear_user(&buf->xsave_hdr, + sizeof(struct xsave_hdr_struct)); + if (unlikely(err)) + return -EFAULT; + __asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x27\n" "2:\n" ".section .fixup,\"ax\"\n" @@ -110,12 +126,25 @@ static inline void xrstor_state(struct xsave_struct *fx, u64 mask) : "memory"); } -static inline void xsave(struct task_struct *tsk) +static inline void xsave_state(struct xsave_struct *fx, u64 mask) +{ + u32 lmask = mask; + u32 hmask = mask >> 32; + + asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x27\n\t" + : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + : "memory"); +} + +static inline void fpu_xsave(struct fpu *fpu) { /* This, however, we can work around by forcing the compiler to select an addressing mode that doesn't require extended registers. */ - __asm__ __volatile__(".byte " REX_PREFIX "0x0f,0xae,0x27" - : : "D" (&(tsk->thread.xstate->xsave)), - "a" (-1), "d"(-1) : "memory"); + alternative_input( + ".byte " REX_PREFIX "0x0f,0xae,0x27", + ".byte " REX_PREFIX "0x0f,0xae,0x37", + X86_FEATURE_XSAVEOPT, + [fx] "D" (&fpu->state->xsave), "a" (-1), "d" (-1) : + "memory"); } #endif diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 4c58352209e..0925676266b 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -47,8 +47,6 @@ obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o obj-y += process.o obj-y += i387.o xsave.o obj-y += ptrace.o -obj-$(CONFIG_X86_DS) += ds.o -obj-$(CONFIG_X86_DS_SELFTEST) += ds_selftest.o obj-$(CONFIG_X86_32) += tls.o obj-$(CONFIG_IA32_EMULATION) += tls.o obj-y += step.o @@ -106,6 +104,7 @@ obj-$(CONFIG_SCx200) += scx200.o scx200-y += scx200_32.o obj-$(CONFIG_OLPC) += olpc.o +obj-$(CONFIG_OLPC_OPENFIRMWARE) += olpc_ofw.o obj-$(CONFIG_X86_MRST) += mrst.o microcode-y := microcode_core.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index cd40aba6aa9..c05872aa3ce 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -63,7 +63,6 @@ EXPORT_SYMBOL(acpi_disabled); int acpi_noirq; /* skip ACPI IRQ initialization */ int acpi_pci_disabled; /* skip ACPI PCI scan and IRQ initialization */ EXPORT_SYMBOL(acpi_pci_disabled); -int acpi_ht __initdata = 1; /* enable HT */ int acpi_lapic; int acpi_ioapic; @@ -94,6 +93,53 @@ enum acpi_irq_model_id acpi_irq_model = ACPI_IRQ_MODEL_PIC; /* + * ISA irqs by default are the first 16 gsis but can be + * any gsi as specified by an interrupt source override. + */ +static u32 isa_irq_to_gsi[NR_IRQS_LEGACY] __read_mostly = { + 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 +}; + +static unsigned int gsi_to_irq(unsigned int gsi) +{ + unsigned int irq = gsi + NR_IRQS_LEGACY; + unsigned int i; + + for (i = 0; i < NR_IRQS_LEGACY; i++) { + if (isa_irq_to_gsi[i] == gsi) { + return i; + } + } + + /* Provide an identity mapping of gsi == irq + * except on truly weird platforms that have + * non isa irqs in the first 16 gsis. + */ + if (gsi >= NR_IRQS_LEGACY) + irq = gsi; + else + irq = gsi_top + gsi; + + return irq; +} + +static u32 irq_to_gsi(int irq) +{ + unsigned int gsi; + + if (irq < NR_IRQS_LEGACY) + gsi = isa_irq_to_gsi[irq]; + else if (irq < gsi_top) + gsi = irq; + else if (irq < (gsi_top + NR_IRQS_LEGACY)) + gsi = irq - gsi_top; + else + gsi = 0xffffffff; + + return gsi; +} + +/* * Temporarily use the virtual area starting from FIX_IO_APIC_BASE_END, * to map the target physical address. The problem is that set_fixmap() * provides a single page, and it is possible that the page is not @@ -313,7 +359,7 @@ acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end) /* * Parse Interrupt Source Override for the ACPI SCI */ -static void __init acpi_sci_ioapic_setup(u32 gsi, u16 polarity, u16 trigger) +static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, u32 gsi) { if (trigger == 0) /* compatible SCI trigger is level */ trigger = 3; @@ -333,7 +379,7 @@ static void __init acpi_sci_ioapic_setup(u32 gsi, u16 polarity, u16 trigger) * If GSI is < 16, this will update its flags, * else it will create a new mp_irqs[] entry. */ - mp_override_legacy_irq(gsi, polarity, trigger, gsi); + mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); /* * stash over-ride to indicate we've been here @@ -357,9 +403,10 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header, acpi_table_print_madt_entry(header); if (intsrc->source_irq == acpi_gbl_FADT.sci_interrupt) { - acpi_sci_ioapic_setup(intsrc->global_irq, + acpi_sci_ioapic_setup(intsrc->source_irq, intsrc->inti_flags & ACPI_MADT_POLARITY_MASK, - (intsrc->inti_flags & ACPI_MADT_TRIGGER_MASK) >> 2); + (intsrc->inti_flags & ACPI_MADT_TRIGGER_MASK) >> 2, + intsrc->global_irq); return 0; } @@ -448,7 +495,7 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) { - *irq = gsi; + *irq = gsi_to_irq(gsi); #ifdef CONFIG_X86_IO_APIC if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) @@ -458,6 +505,14 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) return 0; } +int acpi_isa_irq_to_gsi(unsigned isa_irq, u32 *gsi) +{ + if (isa_irq >= 16) + return -1; + *gsi = irq_to_gsi(isa_irq); + return 0; +} + /* * success: return IRQ number (>=0) * failure: return < 0 @@ -482,7 +537,7 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) plat_gsi = mp_register_gsi(dev, gsi, trigger, polarity); } #endif - irq = plat_gsi; + irq = gsi_to_irq(plat_gsi); return irq; } @@ -867,29 +922,6 @@ static int __init acpi_parse_madt_lapic_entries(void) extern int es7000_plat; #endif -int __init acpi_probe_gsi(void) -{ - int idx; - int gsi; - int max_gsi = 0; - - if (acpi_disabled) - return 0; - - if (!acpi_ioapic) - return 0; - - max_gsi = 0; - for (idx = 0; idx < nr_ioapics; idx++) { - gsi = mp_gsi_routing[idx].gsi_end; - - if (gsi > max_gsi) - max_gsi = gsi; - } - - return max_gsi + 1; -} - static void assign_to_mp_irq(struct mpc_intsrc *m, struct mpc_intsrc *mp_irq) { @@ -947,13 +979,13 @@ void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) mp_irq.dstirq = pin; /* INTIN# */ save_mp_irq(&mp_irq); + + isa_irq_to_gsi[bus_irq] = gsi; } void __init mp_config_acpi_legacy_irqs(void) { int i; - int ioapic; - unsigned int dstapic; struct mpc_intsrc mp_irq; #if defined (CONFIG_MCA) || defined (CONFIG_EISA) @@ -974,19 +1006,27 @@ void __init mp_config_acpi_legacy_irqs(void) #endif /* - * Locate the IOAPIC that manages the ISA IRQs (0-15). - */ - ioapic = mp_find_ioapic(0); - if (ioapic < 0) - return; - dstapic = mp_ioapics[ioapic].apicid; - - /* * Use the default configuration for the IRQs 0-15. Unless * overridden by (MADT) interrupt source override entries. */ for (i = 0; i < 16; i++) { + int ioapic, pin; + unsigned int dstapic; int idx; + u32 gsi; + + /* Locate the gsi that irq i maps to. */ + if (acpi_isa_irq_to_gsi(i, &gsi)) + continue; + + /* + * Locate the IOAPIC that manages the ISA IRQ. + */ + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) + continue; + pin = mp_find_ioapic_pin(ioapic, gsi); + dstapic = mp_ioapics[ioapic].apicid; for (idx = 0; idx < mp_irq_entries; idx++) { struct mpc_intsrc *irq = mp_irqs + idx; @@ -996,7 +1036,7 @@ void __init mp_config_acpi_legacy_irqs(void) break; /* Do we already have a mapping for this IOAPIC pin */ - if (irq->dstapic == dstapic && irq->dstirq == i) + if (irq->dstapic == dstapic && irq->dstirq == pin) break; } @@ -1011,7 +1051,7 @@ void __init mp_config_acpi_legacy_irqs(void) mp_irq.dstapic = dstapic; mp_irq.irqtype = mp_INT; mp_irq.srcbusirq = i; /* Identity mapped */ - mp_irq.dstirq = i; + mp_irq.dstirq = pin; save_mp_irq(&mp_irq); } @@ -1076,11 +1116,6 @@ int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) ioapic_pin = mp_find_ioapic_pin(ioapic, gsi); -#ifdef CONFIG_X86_32 - if (ioapic_renumber_irq) - gsi = ioapic_renumber_irq(ioapic, gsi); -#endif - if (ioapic_pin > MP_MAX_IOAPIC_PIN) { printk(KERN_ERR "Invalid reference to IOAPIC pin " "%d-%d\n", mp_ioapics[ioapic].apicid, @@ -1094,7 +1129,7 @@ int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin, trigger == ACPI_EDGE_SENSITIVE ? 0 : 1, polarity == ACPI_ACTIVE_HIGH ? 0 : 1); - io_apic_set_pci_routing(dev, gsi, &irq_attr); + io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr); return gsi; } @@ -1154,7 +1189,8 @@ static int __init acpi_parse_madt_ioapic_entries(void) * pretend we got one so we can set the SCI flags. */ if (!acpi_sci_override_gsi) - acpi_sci_ioapic_setup(acpi_gbl_FADT.sci_interrupt, 0, 0); + acpi_sci_ioapic_setup(acpi_gbl_FADT.sci_interrupt, 0, 0, + acpi_gbl_FADT.sci_interrupt); /* Fill in identity legacy mappings where no override */ mp_config_acpi_legacy_irqs(); @@ -1464,9 +1500,8 @@ void __init acpi_boot_table_init(void) /* * If acpi_disabled, bail out - * One exception: acpi=ht continues far enough to enumerate LAPICs */ - if (acpi_disabled && !acpi_ht) + if (acpi_disabled) return; /* @@ -1497,9 +1532,8 @@ int __init early_acpi_boot_init(void) { /* * If acpi_disabled, bail out - * One exception: acpi=ht continues far enough to enumerate LAPICs */ - if (acpi_disabled && !acpi_ht) + if (acpi_disabled) return 1; /* @@ -1517,9 +1551,8 @@ int __init acpi_boot_init(void) /* * If acpi_disabled, bail out - * One exception: acpi=ht continues far enough to enumerate LAPICs */ - if (acpi_disabled && !acpi_ht) + if (acpi_disabled) return 1; acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf); @@ -1554,21 +1587,12 @@ static int __init parse_acpi(char *arg) /* acpi=force to over-ride black-list */ else if (strcmp(arg, "force") == 0) { acpi_force = 1; - acpi_ht = 1; acpi_disabled = 0; } /* acpi=strict disables out-of-spec workarounds */ else if (strcmp(arg, "strict") == 0) { acpi_strict = 1; } - /* Limit ACPI just to boot-time to enable HT */ - else if (strcmp(arg, "ht") == 0) { - if (!acpi_force) { - printk(KERN_WARNING "acpi=ht will be removed in Linux-2.6.35\n"); - disable_acpi(); - } - acpi_ht = 1; - } /* acpi=rsdt use RSDT instead of XSDT */ else if (strcmp(arg, "rsdt") == 0) { acpi_rsdt_forced = 1; @@ -1576,6 +1600,10 @@ static int __init parse_acpi(char *arg) /* "acpi=noirq" disables ACPI interrupt routing */ else if (strcmp(arg, "noirq") == 0) { acpi_noirq_set(); + } + /* "acpi=copy_dsdt" copys DSDT */ + else if (strcmp(arg, "copy_dsdt") == 0) { + acpi_gbl_copy_dsdt_locally = 1; } else { /* Core will printk when we return error. */ return -EINVAL; diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 2e837f5080f..fb7a5f052e2 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -145,6 +145,15 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, percpu_entry->states[cx->index].eax = cx->address; percpu_entry->states[cx->index].ecx = MWAIT_ECX_INTERRUPT_BREAK; } + + /* + * For _CST FFH on Intel, if GAS.access_size bit 1 is cleared, + * then we should skip checking BM_STS for this C-state. + * ref: "Intel Processor Vendor-Specific ACPI Interface Specification" + */ + if ((c->x86_vendor == X86_VENDOR_INTEL) && !(reg->access_size & 0x2)) + cx->bm_sts_skip = 1; + return retval; } EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe); diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S index 580b4e29601..28595d6df47 100644 --- a/arch/x86/kernel/acpi/realmode/wakeup.S +++ b/arch/x86/kernel/acpi/realmode/wakeup.S @@ -104,7 +104,7 @@ _start: movl %eax, %ecx orl %edx, %ecx jz 1f - movl $0xc0000080, %ecx + movl $MSR_EFER, %ecx wrmsr 1: diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index f9961034e55..33cec152070 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -2,7 +2,7 @@ * sleep.c - x86-specific ACPI sleep support. * * Copyright (C) 2001-2003 Patrick Mochel - * Copyright (C) 2001-2003 Pavel Machek <pavel@suse.cz> + * Copyright (C) 2001-2003 Pavel Machek <pavel@ucw.cz> */ #include <linux/acpi.h> @@ -157,13 +157,16 @@ static int __init acpi_sleep_setup(char *str) #ifdef CONFIG_HIBERNATION if (strncmp(str, "s4_nohwsig", 10) == 0) acpi_no_s4_hw_signature(); - if (strncmp(str, "s4_nonvs", 8) == 0) - acpi_s4_no_nvs(); + if (strncmp(str, "s4_nonvs", 8) == 0) { + pr_warning("ACPI: acpi_sleep=s4_nonvs is deprecated, " + "please use acpi_sleep=nonvs instead"); + acpi_nvs_nosave(); + } #endif + if (strncmp(str, "nonvs", 5) == 0) + acpi_nvs_nosave(); if (strncmp(str, "old_ordering", 12) == 0) acpi_old_suspend_ordering(); - if (strncmp(str, "sci_force_enable", 16) == 0) - acpi_set_sci_en_on_resume(); str = strchr(str, ','); if (str != NULL) str += strspn(str, ", \t"); diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index 8ded418b059..13ab720573e 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -1,4 +1,4 @@ - .section .text.page_aligned + .section .text..page_aligned #include <linux/linkage.h> #include <asm/segment.h> #include <asm/page_types.h> diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 1a160d5d44d..f65ab8b014c 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -194,7 +194,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len) } extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; -extern u8 *__smp_locks[], *__smp_locks_end[]; +extern s32 __smp_locks[], __smp_locks_end[]; static void *text_poke_early(void *addr, const void *opcode, size_t len); /* Replace instructions with better alternatives for this CPU type. @@ -214,6 +214,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start, u8 *instr = a->instr; BUG_ON(a->replacementlen > a->instrlen); BUG_ON(a->instrlen > sizeof(insnbuf)); + BUG_ON(a->cpuid >= NCAPINTS*32); if (!boot_cpu_has(a->cpuid)) continue; #ifdef CONFIG_X86_64 @@ -235,37 +236,41 @@ void __init_or_module apply_alternatives(struct alt_instr *start, #ifdef CONFIG_SMP -static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end) +static void alternatives_smp_lock(const s32 *start, const s32 *end, + u8 *text, u8 *text_end) { - u8 **ptr; + const s32 *poff; mutex_lock(&text_mutex); - for (ptr = start; ptr < end; ptr++) { - if (*ptr < text) - continue; - if (*ptr > text_end) + for (poff = start; poff < end; poff++) { + u8 *ptr = (u8 *)poff + *poff; + + if (!*poff || ptr < text || ptr >= text_end) continue; /* turn DS segment override prefix into lock prefix */ - text_poke(*ptr, ((unsigned char []){0xf0}), 1); + if (*ptr == 0x3e) + text_poke(ptr, ((unsigned char []){0xf0}), 1); }; mutex_unlock(&text_mutex); } -static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end) +static void alternatives_smp_unlock(const s32 *start, const s32 *end, + u8 *text, u8 *text_end) { - u8 **ptr; + const s32 *poff; if (noreplace_smp) return; mutex_lock(&text_mutex); - for (ptr = start; ptr < end; ptr++) { - if (*ptr < text) - continue; - if (*ptr > text_end) + for (poff = start; poff < end; poff++) { + u8 *ptr = (u8 *)poff + *poff; + + if (!*poff || ptr < text || ptr >= text_end) continue; /* turn lock prefix into DS segment override prefix */ - text_poke(*ptr, ((unsigned char []){0x3E}), 1); + if (*ptr == 0xf0) + text_poke(ptr, ((unsigned char []){0x3E}), 1); }; mutex_unlock(&text_mutex); } @@ -276,8 +281,8 @@ struct smp_alt_module { char *name; /* ptrs to lock prefixes */ - u8 **locks; - u8 **locks_end; + const s32 *locks; + const s32 *locks_end; /* .text segment, needed to avoid patching init code ;) */ u8 *text; @@ -398,16 +403,19 @@ void alternatives_smp_switch(int smp) int alternatives_text_reserved(void *start, void *end) { struct smp_alt_module *mod; - u8 **ptr; + const s32 *poff; u8 *text_start = start; u8 *text_end = end; list_for_each_entry(mod, &smp_alt_modules, next) { if (mod->text > text_end || mod->text_end < text_start) continue; - for (ptr = mod->locks; ptr < mod->locks_end; ptr++) - if (text_start <= *ptr && text_end >= *ptr) + for (poff = mod->locks; poff < mod->locks_end; poff++) { + const u8 *ptr = (const u8 *)poff + *poff; + + if (text_start <= ptr && text_end > ptr) return 1; + } } return 0; diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index f854d89b7ed..fa044e1e30a 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -731,18 +731,22 @@ static bool increase_address_space(struct protection_domain *domain, static u64 *alloc_pte(struct protection_domain *domain, unsigned long address, - int end_lvl, + unsigned long page_size, u64 **pte_page, gfp_t gfp) { + int level, end_lvl; u64 *pte, *page; - int level; + + BUG_ON(!is_power_of_2(page_size)); while (address > PM_LEVEL_SIZE(domain->mode)) increase_address_space(domain, gfp); - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + level = domain->mode - 1; + pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + address = PAGE_SIZE_ALIGN(address, page_size); + end_lvl = PAGE_SIZE_LEVEL(page_size); while (level > end_lvl) { if (!IOMMU_PTE_PRESENT(*pte)) { @@ -752,6 +756,10 @@ static u64 *alloc_pte(struct protection_domain *domain, *pte = PM_LEVEL_PDE(level, virt_to_phys(page)); } + /* No level skipping support yet */ + if (PM_PTE_LEVEL(*pte) != level) + return NULL; + level -= 1; pte = IOMMU_PTE_PAGE(*pte); @@ -769,28 +777,47 @@ static u64 *alloc_pte(struct protection_domain *domain, * This function checks if there is a PTE for a given dma address. If * there is one, it returns the pointer to it. */ -static u64 *fetch_pte(struct protection_domain *domain, - unsigned long address, int map_size) +static u64 *fetch_pte(struct protection_domain *domain, unsigned long address) { int level; u64 *pte; - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + if (address > PM_LEVEL_SIZE(domain->mode)) + return NULL; - while (level > map_size) { + level = domain->mode - 1; + pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + + while (level > 0) { + + /* Not Present */ if (!IOMMU_PTE_PRESENT(*pte)) return NULL; + /* Large PTE */ + if (PM_PTE_LEVEL(*pte) == 0x07) { + unsigned long pte_mask, __pte; + + /* + * If we have a series of large PTEs, make + * sure to return a pointer to the first one. + */ + pte_mask = PTE_PAGE_SIZE(*pte); + pte_mask = ~((PAGE_SIZE_PTE_COUNT(pte_mask) << 3) - 1); + __pte = ((unsigned long)pte) & pte_mask; + + return (u64 *)__pte; + } + + /* No level skipping support yet */ + if (PM_PTE_LEVEL(*pte) != level) + return NULL; + level -= 1; + /* Walk to the next level */ pte = IOMMU_PTE_PAGE(*pte); pte = &pte[PM_LEVEL_INDEX(level, address)]; - - if ((PM_PTE_LEVEL(*pte) == 0) && level != map_size) { - pte = NULL; - break; - } } return pte; @@ -807,44 +834,84 @@ static int iommu_map_page(struct protection_domain *dom, unsigned long bus_addr, unsigned long phys_addr, int prot, - int map_size) + unsigned long page_size) { u64 __pte, *pte; - - bus_addr = PAGE_ALIGN(bus_addr); - phys_addr = PAGE_ALIGN(phys_addr); - - BUG_ON(!PM_ALIGNED(map_size, bus_addr)); - BUG_ON(!PM_ALIGNED(map_size, phys_addr)); + int i, count; if (!(prot & IOMMU_PROT_MASK)) return -EINVAL; - pte = alloc_pte(dom, bus_addr, map_size, NULL, GFP_KERNEL); + bus_addr = PAGE_ALIGN(bus_addr); + phys_addr = PAGE_ALIGN(phys_addr); + count = PAGE_SIZE_PTE_COUNT(page_size); + pte = alloc_pte(dom, bus_addr, page_size, NULL, GFP_KERNEL); + + for (i = 0; i < count; ++i) + if (IOMMU_PTE_PRESENT(pte[i])) + return -EBUSY; - if (IOMMU_PTE_PRESENT(*pte)) - return -EBUSY; + if (page_size > PAGE_SIZE) { + __pte = PAGE_SIZE_PTE(phys_addr, page_size); + __pte |= PM_LEVEL_ENC(7) | IOMMU_PTE_P | IOMMU_PTE_FC; + } else + __pte = phys_addr | IOMMU_PTE_P | IOMMU_PTE_FC; - __pte = phys_addr | IOMMU_PTE_P; if (prot & IOMMU_PROT_IR) __pte |= IOMMU_PTE_IR; if (prot & IOMMU_PROT_IW) __pte |= IOMMU_PTE_IW; - *pte = __pte; + for (i = 0; i < count; ++i) + pte[i] = __pte; update_domain(dom); return 0; } -static void iommu_unmap_page(struct protection_domain *dom, - unsigned long bus_addr, int map_size) +static unsigned long iommu_unmap_page(struct protection_domain *dom, + unsigned long bus_addr, + unsigned long page_size) { - u64 *pte = fetch_pte(dom, bus_addr, map_size); + unsigned long long unmap_size, unmapped; + u64 *pte; + + BUG_ON(!is_power_of_2(page_size)); + + unmapped = 0; + + while (unmapped < page_size) { + + pte = fetch_pte(dom, bus_addr); + + if (!pte) { + /* + * No PTE for this address + * move forward in 4kb steps + */ + unmap_size = PAGE_SIZE; + } else if (PM_PTE_LEVEL(*pte) == 0) { + /* 4kb PTE found for this address */ + unmap_size = PAGE_SIZE; + *pte = 0ULL; + } else { + int count, i; + + /* Large PTE found which maps this address */ + unmap_size = PTE_PAGE_SIZE(*pte); + count = PAGE_SIZE_PTE_COUNT(unmap_size); + for (i = 0; i < count; i++) + pte[i] = 0ULL; + } - if (pte) - *pte = 0; + bus_addr = (bus_addr & ~(unmap_size - 1)) + unmap_size; + unmapped += unmap_size; + } + + BUG_ON(!is_power_of_2(unmapped)); + + return unmapped; } /* @@ -878,7 +945,7 @@ static int dma_ops_unity_map(struct dma_ops_domain *dma_dom, for (addr = e->address_start; addr < e->address_end; addr += PAGE_SIZE) { ret = iommu_map_page(&dma_dom->domain, addr, addr, e->prot, - PM_MAP_4k); + PAGE_SIZE); if (ret) return ret; /* @@ -1006,7 +1073,7 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom, u64 *pte, *pte_page; for (i = 0; i < num_ptes; ++i) { - pte = alloc_pte(&dma_dom->domain, address, PM_MAP_4k, + pte = alloc_pte(&dma_dom->domain, address, PAGE_SIZE, &pte_page, gfp); if (!pte) goto out_free; @@ -1042,7 +1109,7 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom, for (i = dma_dom->aperture[index]->offset; i < dma_dom->aperture_size; i += PAGE_SIZE) { - u64 *pte = fetch_pte(&dma_dom->domain, i, PM_MAP_4k); + u64 *pte = fetch_pte(&dma_dom->domain, i); if (!pte || !IOMMU_PTE_PRESENT(*pte)) continue; @@ -1420,6 +1487,7 @@ static int __attach_device(struct device *dev, struct protection_domain *domain) { struct iommu_dev_data *dev_data, *alias_data; + int ret; dev_data = get_dev_data(dev); alias_data = get_dev_data(dev_data->alias); @@ -1431,13 +1499,14 @@ static int __attach_device(struct device *dev, spin_lock(&domain->lock); /* Some sanity checks */ + ret = -EBUSY; if (alias_data->domain != NULL && alias_data->domain != domain) - return -EBUSY; + goto out_unlock; if (dev_data->domain != NULL && dev_data->domain != domain) - return -EBUSY; + goto out_unlock; /* Do real assignment */ if (dev_data->alias != dev) { @@ -1453,10 +1522,14 @@ static int __attach_device(struct device *dev, atomic_inc(&dev_data->bind); + ret = 0; + +out_unlock: + /* ready */ spin_unlock(&domain->lock); - return 0; + return ret; } /* @@ -1712,7 +1785,7 @@ static u64* dma_ops_get_pte(struct dma_ops_domain *dom, pte = aperture->pte_pages[APERTURE_PAGE_INDEX(address)]; if (!pte) { - pte = alloc_pte(&dom->domain, address, PM_MAP_4k, &pte_page, + pte = alloc_pte(&dom->domain, address, PAGE_SIZE, &pte_page, GFP_ATOMIC); aperture->pte_pages[APERTURE_PAGE_INDEX(address)] = pte_page; } else @@ -2257,10 +2330,6 @@ int __init amd_iommu_init_dma_ops(void) iommu_detected = 1; swiotlb = 0; -#ifdef CONFIG_GART_IOMMU - gart_iommu_aperture_disabled = 1; - gart_iommu_aperture = 0; -#endif /* Make the driver finally visible to the drivers */ dma_ops = &amd_iommu_dma_ops; @@ -2439,12 +2508,11 @@ static int amd_iommu_attach_device(struct iommu_domain *dom, return ret; } -static int amd_iommu_map_range(struct iommu_domain *dom, - unsigned long iova, phys_addr_t paddr, - size_t size, int iommu_prot) +static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, + phys_addr_t paddr, int gfp_order, int iommu_prot) { + unsigned long page_size = 0x1000UL << gfp_order; struct protection_domain *domain = dom->priv; - unsigned long i, npages = iommu_num_pages(paddr, size, PAGE_SIZE); int prot = 0; int ret; @@ -2453,61 +2521,50 @@ static int amd_iommu_map_range(struct iommu_domain *dom, if (iommu_prot & IOMMU_WRITE) prot |= IOMMU_PROT_IW; - iova &= PAGE_MASK; - paddr &= PAGE_MASK; - mutex_lock(&domain->api_lock); - - for (i = 0; i < npages; ++i) { - ret = iommu_map_page(domain, iova, paddr, prot, PM_MAP_4k); - if (ret) - return ret; - - iova += PAGE_SIZE; - paddr += PAGE_SIZE; - } - + ret = iommu_map_page(domain, iova, paddr, prot, page_size); mutex_unlock(&domain->api_lock); - return 0; + return ret; } -static void amd_iommu_unmap_range(struct iommu_domain *dom, - unsigned long iova, size_t size) +static int amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, + int gfp_order) { - struct protection_domain *domain = dom->priv; - unsigned long i, npages = iommu_num_pages(iova, size, PAGE_SIZE); + unsigned long page_size, unmap_size; - iova &= PAGE_MASK; + page_size = 0x1000UL << gfp_order; mutex_lock(&domain->api_lock); - - for (i = 0; i < npages; ++i) { - iommu_unmap_page(domain, iova, PM_MAP_4k); - iova += PAGE_SIZE; - } + unmap_size = iommu_unmap_page(domain, iova, page_size); + mutex_unlock(&domain->api_lock); iommu_flush_tlb_pde(domain); - mutex_unlock(&domain->api_lock); + return get_order(unmap_size); } static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, unsigned long iova) { struct protection_domain *domain = dom->priv; - unsigned long offset = iova & ~PAGE_MASK; + unsigned long offset_mask; phys_addr_t paddr; - u64 *pte; + u64 *pte, __pte; - pte = fetch_pte(domain, iova, PM_MAP_4k); + pte = fetch_pte(domain, iova); if (!pte || !IOMMU_PTE_PRESENT(*pte)) return 0; - paddr = *pte & IOMMU_PAGE_MASK; - paddr |= offset; + if (PM_PTE_LEVEL(*pte) == 0) + offset_mask = PAGE_SIZE - 1; + else + offset_mask = PTE_PAGE_SIZE(*pte) - 1; + + __pte = *pte & PM_ADDR_MASK; + paddr = (__pte & ~offset_mask) | (iova & offset_mask); return paddr; } @@ -2515,6 +2572,11 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, static int amd_iommu_domain_has_cap(struct iommu_domain *domain, unsigned long cap) { + switch (cap) { + case IOMMU_CAP_CACHE_COHERENCY: + return 1; + } + return 0; } @@ -2523,8 +2585,8 @@ static struct iommu_ops amd_iommu_ops = { .domain_destroy = amd_iommu_domain_destroy, .attach_dev = amd_iommu_attach_device, .detach_dev = amd_iommu_detach_device, - .map = amd_iommu_map_range, - .unmap = amd_iommu_unmap_range, + .map = amd_iommu_map, + .unmap = amd_iommu_unmap, .iova_to_phys = amd_iommu_iova_to_phys, .domain_has_cap = amd_iommu_domain_has_cap, }; @@ -2552,8 +2614,7 @@ int __init amd_iommu_init_passthrough(void) pt_domain->mode |= PAGE_MODE_NONE; - while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { - + for_each_pci_dev(dev) { if (!check_device(&dev->dev)) continue; diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 6360abf993d..3cc63e2b8dd 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -120,6 +120,7 @@ struct ivmd_header { bool amd_iommu_dump; static int __initdata amd_iommu_detected; +static bool __initdata amd_iommu_disabled; u16 amd_iommu_last_bdf; /* largest PCI device id we have to handle */ @@ -286,8 +287,12 @@ static u8 * __init iommu_map_mmio_space(u64 address) { u8 *ret; - if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu")) + if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu")) { + pr_err("AMD-Vi: Can not reserve memory region %llx for mmio\n", + address); + pr_err("AMD-Vi: This is a BIOS bug. Please contact your hardware vendor\n"); return NULL; + } ret = ioremap_nocache(address, MMIO_REGION_LENGTH); if (ret != NULL) @@ -1313,7 +1318,7 @@ static int __init amd_iommu_init(void) ret = amd_iommu_init_dma_ops(); if (ret) - goto free; + goto free_disable; amd_iommu_init_api(); @@ -1331,9 +1336,10 @@ static int __init amd_iommu_init(void) out: return ret; -free: +free_disable: disable_iommus(); +free: amd_iommu_uninit_devices(); free_pages((unsigned long)amd_iommu_pd_alloc_bitmap, @@ -1352,6 +1358,15 @@ free: free_unity_maps(); +#ifdef CONFIG_GART_IOMMU + /* + * We failed to initialize the AMD IOMMU - try fallback to GART + * if possible. + */ + gart_iommu_init(); + +#endif + goto out; } @@ -1372,6 +1387,9 @@ void __init amd_iommu_detect(void) if (no_iommu || (iommu_detected && !gart_iommu_aperture)) return; + if (amd_iommu_disabled) + return; + if (acpi_table_parse("IVRS", early_amd_iommu_detect) == 0) { iommu_detected = 1; amd_iommu_detected = 1; @@ -1401,6 +1419,8 @@ static int __init parse_amd_iommu_options(char *str) for (; *str; ++str) { if (strncmp(str, "fullflush", 9) == 0) amd_iommu_unmap_flush = true; + if (strncmp(str, "off", 3) == 0) + amd_iommu_disabled = true; } return 1; diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index a35347501d3..8dd77800ff5 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -43,10 +43,11 @@ #include <asm/fixmap.h> #include <asm/apb_timer.h> +#include <asm/mrst.h> #define APBT_MASK CLOCKSOURCE_MASK(32) #define APBT_SHIFT 22 -#define APBT_CLOCKEVENT_RATING 150 +#define APBT_CLOCKEVENT_RATING 110 #define APBT_CLOCKSOURCE_RATING 250 #define APBT_MIN_DELTA_USEC 200 @@ -83,8 +84,6 @@ struct apbt_dev { char name[10]; }; -int disable_apbt_percpu __cpuinitdata; - static DEFINE_PER_CPU(struct apbt_dev, cpu_apbt_dev); #ifdef CONFIG_SMP @@ -195,29 +194,6 @@ static struct clock_event_device apbt_clockevent = { }; /* - * if user does not want to use per CPU apb timer, just give it a lower rating - * than local apic timer and skip the late per cpu timer init. - */ -static inline int __init setup_x86_mrst_timer(char *arg) -{ - if (!arg) - return -EINVAL; - - if (strcmp("apbt_only", arg) == 0) - disable_apbt_percpu = 0; - else if (strcmp("lapic_and_apbt", arg) == 0) - disable_apbt_percpu = 1; - else { - pr_warning("X86 MRST timer option %s not recognised" - " use x86_mrst_timer=apbt_only or lapic_and_apbt\n", - arg); - return -EINVAL; - } - return 0; -} -__setup("x86_mrst_timer=", setup_x86_mrst_timer); - -/* * start count down from 0xffff_ffff. this is done by toggling the enable bit * then load initial load count to ~0. */ @@ -335,7 +311,7 @@ static int __init apbt_clockevent_register(void) adev->num = smp_processor_id(); memcpy(&adev->evt, &apbt_clockevent, sizeof(struct clock_event_device)); - if (disable_apbt_percpu) { + if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) { apbt_clockevent.rating = APBT_CLOCKEVENT_RATING - 100; global_clock_event = &adev->evt; printk(KERN_DEBUG "%s clockevent registered as global\n", @@ -429,7 +405,8 @@ static int apbt_cpuhp_notify(struct notifier_block *n, static __init int apbt_late_init(void) { - if (disable_apbt_percpu || !apb_timer_block_enabled) + if (mrst_timer_options == MRST_TIMER_LAPIC_APBT || + !apb_timer_block_enabled) return 0; /* This notifier should be called after workqueue is ready */ hotcpu_notifier(apbt_cpuhp_notify, -20); @@ -450,6 +427,8 @@ static void apbt_set_mode(enum clock_event_mode mode, int timer_num; struct apbt_dev *adev = EVT_TO_APBT_DEV(evt); + BUG_ON(!apbt_virt_address); + timer_num = adev->num; pr_debug("%s CPU %d timer %d mode=%d\n", __func__, first_cpu(*evt->cpumask), timer_num, mode); @@ -676,7 +655,7 @@ void __init apbt_time_init(void) } #ifdef CONFIG_SMP /* kernel cmdline disable apb timer, so we will use lapic timers */ - if (disable_apbt_percpu) { + if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) { printk(KERN_INFO "apbt: disabled per cpu timer\n"); return; } diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index b5d8b0bcf23..a2e0caf26e1 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -280,7 +280,7 @@ void __init early_gart_iommu_check(void) * or BIOS forget to put that in reserved. * try to update e820 to make that region as reserved. */ - u32 agp_aper_base = 0, agp_aper_order = 0; + u32 agp_aper_order = 0; int i, fix, slot, valid_agp = 0; u32 ctl; u32 aper_size = 0, aper_order = 0, last_aper_order = 0; @@ -291,7 +291,7 @@ void __init early_gart_iommu_check(void) return; /* This is mostly duplicate of iommu_hole_init */ - agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp); + search_agp_bridge(&agp_aper_order, &valid_agp); fix = 0; for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 565c1bfc507..910f20b457c 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -2,7 +2,12 @@ # Makefile for local APIC drivers and for the IO-APIC code # -obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o nmi.o +obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o +ifneq ($(CONFIG_HARDLOCKUP_DETECTOR),y) +obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o +endif +obj-$(CONFIG_HARDLOCKUP_DETECTOR) += hw_nmi.o + obj-$(CONFIG_X86_IO_APIC) += io_apic.o obj-$(CONFIG_SMP) += ipi.o diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index e5a4a1e0161..980508c7908 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -51,6 +51,7 @@ #include <asm/smp.h> #include <asm/mce.h> #include <asm/kvm_para.h> +#include <asm/tsc.h> unsigned int num_processors; @@ -459,7 +460,7 @@ static void lapic_timer_broadcast(const struct cpumask *mask) } /* - * Setup the local APIC timer for this CPU. Copy the initilized values + * Setup the local APIC timer for this CPU. Copy the initialized values * of the boot CPU and register the clock event in the framework. */ static void __cpuinit setup_APIC_timer(void) @@ -920,7 +921,7 @@ void disable_local_APIC(void) unsigned int value; /* APIC hasn't been mapped yet */ - if (!apic_phys) + if (!x2apic_mode && !apic_phys) return; clear_local_APIC(); @@ -1151,8 +1152,13 @@ static void __cpuinit lapic_setup_esr(void) */ void __cpuinit setup_local_APIC(void) { - unsigned int value; - int i, j; + unsigned int value, queued; + int i, j, acked = 0; + unsigned long long tsc = 0, ntsc; + long long max_loops = cpu_khz; + + if (cpu_has_tsc) + rdtscll(tsc); if (disable_apic) { arch_disable_smp_support(); @@ -1204,13 +1210,32 @@ void __cpuinit setup_local_APIC(void) * the interrupt. Hence a vector might get locked. It was noticed * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. */ - for (i = APIC_ISR_NR - 1; i >= 0; i--) { - value = apic_read(APIC_ISR + i*0x10); - for (j = 31; j >= 0; j--) { - if (value & (1<<j)) - ack_APIC_irq(); + do { + queued = 0; + for (i = APIC_ISR_NR - 1; i >= 0; i--) + queued |= apic_read(APIC_IRR + i*0x10); + + for (i = APIC_ISR_NR - 1; i >= 0; i--) { + value = apic_read(APIC_ISR + i*0x10); + for (j = 31; j >= 0; j--) { + if (value & (1<<j)) { + ack_APIC_irq(); + acked++; + } + } } - } + if (acked > 256) { + printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n", + acked); + break; + } + if (cpu_has_tsc) { + rdtscll(ntsc); + max_loops = (cpu_khz << 10) - (ntsc - tsc); + } else + max_loops--; + } while (queued && max_loops > 0); + WARN_ON(max_loops <= 0); /* * Now that we are all set up, enable the APIC diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 03ba1b895f5..8593582d802 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -129,25 +129,6 @@ int es7000_plat; * GSI override for ES7000 platforms. */ -static unsigned int base; - -static int -es7000_rename_gsi(int ioapic, int gsi) -{ - if (es7000_plat == ES7000_ZORRO) - return gsi; - - if (!base) { - int i; - for (i = 0; i < nr_ioapics; i++) - base += nr_ioapic_registers[i]; - } - - if (!ioapic && (gsi < 16)) - gsi += base; - - return gsi; -} static int __cpuinit wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip) { @@ -190,7 +171,6 @@ static void setup_unisys(void) es7000_plat = ES7000_ZORRO; else es7000_plat = ES7000_CLASSIC; - ioapic_renumber_irq = es7000_rename_gsi; } /* diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c new file mode 100644 index 00000000000..cefd6942f0e --- /dev/null +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -0,0 +1,107 @@ +/* + * HW NMI watchdog support + * + * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. + * + * Arch specific calls to support NMI watchdog + * + * Bits copied from original nmi.c file + * + */ +#include <asm/apic.h> + +#include <linux/cpumask.h> +#include <linux/kdebug.h> +#include <linux/notifier.h> +#include <linux/kprobes.h> +#include <linux/nmi.h> +#include <linux/module.h> + +/* For reliability, we're prepared to waste bits here. */ +static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; + +u64 hw_nmi_get_sample_period(void) +{ + return (u64)(cpu_khz) * 1000 * 60; +} + +#ifdef ARCH_HAS_NMI_WATCHDOG +void arch_trigger_all_cpu_backtrace(void) +{ + int i; + + cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); + + printk(KERN_INFO "sending NMI to all CPUs:\n"); + apic->send_IPI_all(NMI_VECTOR); + + /* Wait for up to 10 seconds for all CPUs to do the backtrace */ + for (i = 0; i < 10 * 1000; i++) { + if (cpumask_empty(to_cpumask(backtrace_mask))) + break; + mdelay(1); + } +} + +static int __kprobes +arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self, + unsigned long cmd, void *__args) +{ + struct die_args *args = __args; + struct pt_regs *regs; + int cpu = smp_processor_id(); + + switch (cmd) { + case DIE_NMI: + case DIE_NMI_IPI: + break; + + default: + return NOTIFY_DONE; + } + + regs = args->regs; + + if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { + static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED; + + arch_spin_lock(&lock); + printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); + show_regs(regs); + dump_stack(); + arch_spin_unlock(&lock); + cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); + return NOTIFY_STOP; + } + + return NOTIFY_DONE; +} + +static __read_mostly struct notifier_block backtrace_notifier = { + .notifier_call = arch_trigger_all_cpu_backtrace_handler, + .next = NULL, + .priority = 1 +}; + +static int __init register_trigger_all_cpu_backtrace(void) +{ + register_die_notifier(&backtrace_notifier); + return 0; +} +early_initcall(register_trigger_all_cpu_backtrace); +#endif + +/* STUB calls to mimic old nmi_watchdog behaviour */ +#if defined(CONFIG_X86_LOCAL_APIC) +unsigned int nmi_watchdog = NMI_NONE; +EXPORT_SYMBOL(nmi_watchdog); +void acpi_nmi_enable(void) { return; } +void acpi_nmi_disable(void) { return; } +#endif +atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ +EXPORT_SYMBOL(nmi_active); +int unknown_nmi_panic; +void cpu_nmi_set_wd_enabled(void) { return; } +void stop_apic_nmi_watchdog(void *unused) { return; } +void setup_apic_nmi_watchdog(void *unused) { return; } +int __init check_nmi_watchdog(void) { return 0; } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index eb2789c3f72..4dc0084ec1b 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -89,6 +89,9 @@ int nr_ioapics; /* IO APIC gsi routing info */ struct mp_ioapic_gsi mp_gsi_routing[MAX_IO_APICS]; +/* The one past the highest gsi number used */ +u32 gsi_top; + /* MP IRQ source entries */ struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES]; @@ -1013,10 +1016,9 @@ static inline int irq_trigger(int idx) return MPBIOS_trigger(idx); } -int (*ioapic_renumber_irq)(int ioapic, int irq); static int pin_2_irq(int idx, int apic, int pin) { - int irq, i; + int irq; int bus = mp_irqs[idx].srcbus; /* @@ -1028,18 +1030,12 @@ static int pin_2_irq(int idx, int apic, int pin) if (test_bit(bus, mp_bus_not_pci)) { irq = mp_irqs[idx].srcbusirq; } else { - /* - * PCI IRQs are mapped in order - */ - i = irq = 0; - while (i < apic) - irq += nr_ioapic_registers[i++]; - irq += pin; - /* - * For MPS mode, so far only needed by ES7000 platform - */ - if (ioapic_renumber_irq) - irq = ioapic_renumber_irq(apic, irq); + u32 gsi = mp_gsi_routing[apic].gsi_base + pin; + + if (gsi >= NR_IRQS_LEGACY) + irq = gsi; + else + irq = gsi_top + gsi; } #ifdef CONFIG_X86_32 @@ -1950,20 +1946,8 @@ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 }; void __init enable_IO_APIC(void) { - union IO_APIC_reg_01 reg_01; int i8259_apic, i8259_pin; int apic; - unsigned long flags; - - /* - * The number of IO-APIC IRQ registers (== #pins): - */ - for (apic = 0; apic < nr_ioapics; apic++) { - raw_spin_lock_irqsave(&ioapic_lock, flags); - reg_01.raw = io_apic_read(apic, 1); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - nr_ioapic_registers[apic] = reg_01.bits.entries+1; - } if (!legacy_pic->nr_legacy_irqs) return; @@ -3413,7 +3397,7 @@ static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask) cfg = desc->chip_data; - read_msi_msg_desc(desc, &msg); + get_cached_msi_msg_desc(desc, &msg); msg.data &= ~MSI_DATA_VECTOR_MASK; msg.data |= MSI_DATA_VECTOR(cfg->vector); @@ -3858,27 +3842,20 @@ int __init io_apic_get_redir_entries (int ioapic) reg_01.raw = io_apic_read(ioapic, 1); raw_spin_unlock_irqrestore(&ioapic_lock, flags); - return reg_01.bits.entries; + /* The register returns the maximum index redir index + * supported, which is one less than the total number of redir + * entries. + */ + return reg_01.bits.entries + 1; } void __init probe_nr_irqs_gsi(void) { - int nr = 0; + int nr; - nr = acpi_probe_gsi(); - if (nr > nr_irqs_gsi) { + nr = gsi_top + NR_IRQS_LEGACY; + if (nr > nr_irqs_gsi) nr_irqs_gsi = nr; - } else { - /* for acpi=off or acpi is not compiled in */ - int idx; - - nr = 0; - for (idx = 0; idx < nr_ioapics; idx++) - nr += io_apic_get_redir_entries(idx) + 1; - - if (nr > nr_irqs_gsi) - nr_irqs_gsi = nr; - } printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi); } @@ -4085,22 +4062,27 @@ int __init io_apic_get_version(int ioapic) return reg_01.bits.version; } -int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity) +int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) { - int i; + int ioapic, pin, idx; if (skip_ioapic_setup) return -1; - for (i = 0; i < mp_irq_entries; i++) - if (mp_irqs[i].irqtype == mp_INT && - mp_irqs[i].srcbusirq == bus_irq) - break; - if (i >= mp_irq_entries) + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) return -1; - *trigger = irq_trigger(i); - *polarity = irq_polarity(i); + pin = mp_find_ioapic_pin(ioapic, gsi); + if (pin < 0) + return -1; + + idx = find_irq_entry(ioapic, pin, mp_INT); + if (idx < 0) + return -1; + + *trigger = irq_trigger(idx); + *polarity = irq_polarity(idx); return 0; } @@ -4241,7 +4223,7 @@ void __init ioapic_insert_resources(void) } } -int mp_find_ioapic(int gsi) +int mp_find_ioapic(u32 gsi) { int i = 0; @@ -4256,7 +4238,7 @@ int mp_find_ioapic(int gsi) return -1; } -int mp_find_ioapic_pin(int ioapic, int gsi) +int mp_find_ioapic_pin(int ioapic, u32 gsi) { if (WARN_ON(ioapic == -1)) return -1; @@ -4284,6 +4266,7 @@ static int bad_ioapic(unsigned long address) void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) { int idx = 0; + int entries; if (bad_ioapic(address)) return; @@ -4302,9 +4285,17 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) * Build basic GSI lookup table to facilitate gsi->io_apic lookups * and to prevent reprogramming of IOAPIC pins (PCI GSIs). */ + entries = io_apic_get_redir_entries(idx); mp_gsi_routing[idx].gsi_base = gsi_base; - mp_gsi_routing[idx].gsi_end = gsi_base + - io_apic_get_redir_entries(idx); + mp_gsi_routing[idx].gsi_end = gsi_base + entries - 1; + + /* + * The number of IO-APIC IRQ registers (== #pins): + */ + nr_ioapic_registers[idx] = entries; + + if (mp_gsi_routing[idx].gsi_end >= gsi_top) + gsi_top = mp_gsi_routing[idx].gsi_end + 1; printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, " "GSI %d-%d\n", idx, mp_ioapics[idx].apicid, diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index 1edaf15c0b8..a43f71cb30f 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -401,13 +401,6 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) int cpu = smp_processor_id(); int rc = 0; - /* check for other users first */ - if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) - == NOTIFY_STOP) { - rc = 1; - touched = 1; - } - sum = get_timer_irqs(cpu); if (__get_cpu_var(nmi_touch)) { diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index c085d52dbaf..e46f98f36e3 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -735,9 +735,6 @@ void __init uv_system_init(void) uv_node_to_blade[nid] = blade; uv_cpu_to_blade[cpu] = blade; max_pnode = max(pnode, max_pnode); - - printk(KERN_DEBUG "UV: cpu %d, apicid 0x%x, pnode %d, nid %d, lcpu %d, blade %d\n", - cpu, apicid, pnode, nid, lcpu, blade); } /* Add blade/pnode info for nodes without cpus */ diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 031aa887b0e..4c9c67bf09b 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -140,7 +140,7 @@ * is now the way life works). * Fix thinko in suspend() (wrong return). * Notify drivers on critical suspend. - * Make kapmd absorb more idle time (Pavel Machek <pavel@suse.cz> + * Make kapmd absorb more idle time (Pavel Machek <pavel@ucw.cz> * modified by sfr). * Disable interrupts while we are suspended (Andy Henroid * <andy_henroid@yahoo.com> fixed by sfr). @@ -1224,7 +1224,7 @@ static void reinit_timer(void) #ifdef INIT_TIMER_AFTER_SUSPEND unsigned long flags; - spin_lock_irqsave(&i8253_lock, flags); + raw_spin_lock_irqsave(&i8253_lock, flags); /* set the clock to HZ */ outb_pit(0x34, PIT_MODE); /* binary, mode 2, LSB/MSB, ch 0 */ udelay(10); @@ -1232,7 +1232,7 @@ static void reinit_timer(void) udelay(10); outb_pit(LATCH >> 8, PIT_CH0); /* MSB */ udelay(10); - spin_unlock_irqrestore(&i8253_lock, flags); + raw_spin_unlock_irqrestore(&i8253_lock, flags); #endif } diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index c202b62f367..3f0ebe429a0 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -12,11 +12,11 @@ endif nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_common.o := $(nostackp) -obj-y := intel_cacheinfo.o addon_cpuid_features.o +obj-y := intel_cacheinfo.o scattered.o topology.o obj-y += proc.o capflags.o powerflags.o common.o -obj-y += vmware.o hypervisor.o sched.o +obj-y += vmware.o hypervisor.o sched.o mshyperv.o -obj-$(CONFIG_X86_32) += bugs.o cmpxchg.o +obj-$(CONFIG_X86_32) += bugs.o obj-$(CONFIG_X86_64) += bugs_64.o obj-$(CONFIG_CPU_SUP_INTEL) += intel.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e485825130d..60a57b13082 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -466,7 +466,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) } } - if (c->x86 == 0x10 || c->x86 == 0x11) + if (c->x86 >= 0x10) set_cpu_cap(c, X86_FEATURE_REP_GOOD); /* get apicid instead of initial apic id from cpuid */ @@ -529,7 +529,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) num_cache_leaves = 3; } - if (c->x86 >= 0xf && c->x86 <= 0x11) + if (c->x86 >= 0xf) set_cpu_cap(c, X86_FEATURE_K8); if (cpu_has_xmm2) { @@ -546,7 +546,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) fam10h_check_enable_mmcfg(); } - if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) { + if (c == &boot_cpu_data && c->x86 >= 0xf) { unsigned long long tseg; /* @@ -609,3 +609,74 @@ static const struct cpu_dev __cpuinitconst amd_cpu_dev = { }; cpu_dev_register(amd_cpu_dev); + +/* + * AMD errata checking + * + * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or + * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that + * have an OSVW id assigned, which it takes as first argument. Both take a + * variable number of family-specific model-stepping ranges created by + * AMD_MODEL_RANGE(). Each erratum also has to be declared as extern const + * int[] in arch/x86/include/asm/processor.h. + * + * Example: + * + * const int amd_erratum_319[] = + * AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2), + * AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0), + * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0)); + */ + +const int amd_erratum_400[] = + AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf), + AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf)); +EXPORT_SYMBOL_GPL(amd_erratum_400); + +const int amd_erratum_383[] = + AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); +EXPORT_SYMBOL_GPL(amd_erratum_383); + +bool cpu_has_amd_erratum(const int *erratum) +{ + struct cpuinfo_x86 *cpu = ¤t_cpu_data; + int osvw_id = *erratum++; + u32 range; + u32 ms; + + /* + * If called early enough that current_cpu_data hasn't been initialized + * yet, fall back to boot_cpu_data. + */ + if (cpu->x86 == 0) + cpu = &boot_cpu_data; + + if (cpu->x86_vendor != X86_VENDOR_AMD) + return false; + + if (osvw_id >= 0 && osvw_id < 65536 && + cpu_has(cpu, X86_FEATURE_OSVW)) { + u64 osvw_len; + + rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len); + if (osvw_id < osvw_len) { + u64 osvw_bits; + + rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6), + osvw_bits); + return osvw_bits & (1ULL << (osvw_id & 0x3f)); + } + } + + /* OSVW unavailable or ID unknown, match family-model-stepping range */ + ms = (cpu->x86_model << 8) | cpu->x86_mask; + while ((range = *erratum++)) + if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && + (ms >= AMD_MODEL_RANGE_START(range)) && + (ms <= AMD_MODEL_RANGE_END(range))) + return true; + + return false; +} + +EXPORT_SYMBOL_GPL(cpu_has_amd_erratum); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 01a26521239..c39576cb301 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -86,7 +86,7 @@ static void __init check_fpu(void) static void __init check_hlt(void) { - if (paravirt_enabled()) + if (boot_cpu_data.x86 >= 5 || paravirt_enabled()) return; printk(KERN_INFO "Checking 'hlt' instruction... "); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4868e4a951e..490dac63c2d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -140,10 +140,18 @@ EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); static int __init x86_xsave_setup(char *s) { setup_clear_cpu_cap(X86_FEATURE_XSAVE); + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); return 1; } __setup("noxsave", x86_xsave_setup); +static int __init x86_xsaveopt_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + return 1; +} +__setup("noxsaveopt", x86_xsaveopt_setup); + #ifdef CONFIG_X86_32 static int cachesize_override __cpuinitdata = -1; static int disable_x86_serial_nr __cpuinitdata = 1; @@ -551,6 +559,16 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[4] = excap; } + /* Additional Intel-defined flags: level 0x00000007 */ + if (c->cpuid_level >= 0x00000007) { + u32 eax, ebx, ecx, edx; + + cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); + + if (eax > 0) + c->x86_capability[9] = ebx; + } + /* AMD-defined flags: level 0x80000001 */ xlvl = cpuid_eax(0x80000000); c->extended_cpuid_level = xlvl; @@ -576,6 +594,7 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x80000007) c->x86_power = cpuid_edx(0x80000007); + init_scattered_cpuid_features(c); } static void __cpuinit identify_cpu_without_cpuid(struct cpuinfo_x86 *c) @@ -731,7 +750,6 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c) get_model_name(c); /* Default name */ - init_scattered_cpuid_features(c); detect_nopl(c); } @@ -1084,6 +1102,20 @@ static void clear_all_debug_regs(void) } } +#ifdef CONFIG_KGDB +/* + * Restore debug regs if using kgdbwait and you have a kernel debugger + * connection established. + */ +static void dbg_restore_debug_regs(void) +{ + if (unlikely(kgdb_connected && arch_kgdb_ops.correct_hw_break)) + arch_kgdb_ops.correct_hw_break(); +} +#else /* ! CONFIG_KGDB */ +#define dbg_restore_debug_regs() +#endif /* ! CONFIG_KGDB */ + /* * cpu_init() initializes state that is per-CPU. Some data is already * initialized (naturally) in the bootstrap process, such as the GDT @@ -1107,9 +1139,9 @@ void __cpuinit cpu_init(void) oist = &per_cpu(orig_ist, cpu); #ifdef CONFIG_NUMA - if (cpu != 0 && percpu_read(node_number) == 0 && - cpu_to_node(cpu) != NUMA_NO_NODE) - percpu_write(node_number, cpu_to_node(cpu)); + if (cpu != 0 && percpu_read(numa_node) == 0 && + early_cpu_to_node(cpu) != NUMA_NO_NODE) + set_numa_node(early_cpu_to_node(cpu)); #endif me = current; @@ -1174,20 +1206,11 @@ void __cpuinit cpu_init(void) load_TR_desc(); load_LDT(&init_mm.context); -#ifdef CONFIG_KGDB - /* - * If the kgdb is connected no debug regs should be altered. This - * is only applicable when KGDB and a KGDB I/O module are built - * into the kernel and you are using early debugging with - * kgdbwait. KGDB will control the kernel HW breakpoint registers. - */ - if (kgdb_connected && arch_kgdb_ops.correct_hw_break) - arch_kgdb_ops.correct_hw_break(); - else -#endif - clear_all_debug_regs(); + clear_all_debug_regs(); + dbg_restore_debug_regs(); fpu_init(); + xsave_init(); raw_local_save_flags(kernel_eflags); @@ -1239,23 +1262,16 @@ void __cpuinit cpu_init(void) #endif clear_all_debug_regs(); + dbg_restore_debug_regs(); /* * Force FPU initialization: */ - if (cpu_has_xsave) - current_thread_info()->status = TS_XSAVE; - else - current_thread_info()->status = 0; + current_thread_info()->status = 0; clear_used_math(); mxcsr_feature_mask_init(); - /* - * Boot processor to setup the FP and extended state context info. - */ - if (smp_processor_id() == boot_cpu_id) - init_thread_xstate(); - + fpu_init(); xsave_init(); } #endif diff --git a/arch/x86/kernel/cpu/cpufreq/Makefile b/arch/x86/kernel/cpu/cpufreq/Makefile index 1840c0a5170..bd54bf67e6f 100644 --- a/arch/x86/kernel/cpu/cpufreq/Makefile +++ b/arch/x86/kernel/cpu/cpufreq/Makefile @@ -2,8 +2,8 @@ # K8 systems. ACPI is preferred to all other hardware-specific drivers. # speedstep-* is preferred over p4-clockmod. -obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o -obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o +obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o mperf.o +obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o mperf.o obj-$(CONFIG_X86_PCC_CPUFREQ) += pcc-cpufreq.o obj-$(CONFIG_X86_POWERNOW_K6) += powernow-k6.o obj-$(CONFIG_X86_POWERNOW_K7) += powernow-k7.o diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 459168083b7..246cd3afbb5 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -34,7 +34,6 @@ #include <linux/compiler.h> #include <linux/dmi.h> #include <linux/slab.h> -#include <trace/events/power.h> #include <linux/acpi.h> #include <linux/io.h> @@ -46,6 +45,7 @@ #include <asm/msr.h> #include <asm/processor.h> #include <asm/cpufeature.h> +#include "mperf.h" #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ "acpi-cpufreq", msg) @@ -71,8 +71,6 @@ struct acpi_cpufreq_data { static DEFINE_PER_CPU(struct acpi_cpufreq_data *, acfreq_data); -static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf); - /* acpi_perf_data is a pointer to percpu data. */ static struct acpi_processor_performance *acpi_perf_data; @@ -240,45 +238,6 @@ static u32 get_cur_val(const struct cpumask *mask) return cmd.val; } -/* Called via smp_call_function_single(), on the target CPU */ -static void read_measured_perf_ctrs(void *_cur) -{ - struct aperfmperf *am = _cur; - - get_aperfmperf(am); -} - -/* - * Return the measured active (C0) frequency on this CPU since last call - * to this function. - * Input: cpu number - * Return: Average CPU frequency in terms of max frequency (zero on error) - * - * We use IA32_MPERF and IA32_APERF MSRs to get the measured performance - * over a period of time, while CPU is in C0 state. - * IA32_MPERF counts at the rate of max advertised frequency - * IA32_APERF counts at the rate of actual CPU frequency - * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and - * no meaning should be associated with absolute values of these MSRs. - */ -static unsigned int get_measured_perf(struct cpufreq_policy *policy, - unsigned int cpu) -{ - struct aperfmperf perf; - unsigned long ratio; - unsigned int retval; - - if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1)) - return 0; - - ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf); - per_cpu(acfreq_old_perf, cpu) = perf; - - retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT; - - return retval; -} - static unsigned int get_cur_freq_on_cpu(unsigned int cpu) { struct acpi_cpufreq_data *data = per_cpu(acfreq_data, cpu); @@ -364,8 +323,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, } } - trace_power_frequency(POWER_PSTATE, data->freq_table[next_state].frequency); - switch (data->cpu_feature) { case SYSTEM_INTEL_MSR_CAPABLE: cmd.type = SYSTEM_INTEL_MSR_CAPABLE; @@ -391,7 +348,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, freqs.old = perf->states[perf->state].core_frequency * 1000; freqs.new = data->freq_table[next_state].frequency; - for_each_cpu(i, cmd.mask) { + for_each_cpu(i, policy->cpus) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } @@ -407,7 +364,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, } } - for_each_cpu(i, cmd.mask) { + for_each_cpu(i, policy->cpus) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } @@ -702,7 +659,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) /* Check for APERF/MPERF support in hardware */ if (cpu_has(c, X86_FEATURE_APERFMPERF)) - acpi_cpufreq_driver.getavg = get_measured_perf; + acpi_cpufreq_driver.getavg = cpufreq_get_measured_perf; dprintk("CPU%u - ACPI performance management activated.\n", cpu); for (i = 0; i < perf->state_count; i++) diff --git a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c index 16e3483be9e..32974cf8423 100644 --- a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c +++ b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c @@ -169,12 +169,9 @@ static int gx_freq_mult[16] = { * Low Level chipset interface * ****************************************************************/ static struct pci_device_id gx_chipset_tbl[] __initdata = { - { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, - PCI_ANY_ID, PCI_ANY_ID }, - { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5520, - PCI_ANY_ID, PCI_ANY_ID }, - { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5510, - PCI_ANY_ID, PCI_ANY_ID }, + { PCI_VDEVICE(CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY), }, + { PCI_VDEVICE(CYRIX, PCI_DEVICE_ID_CYRIX_5520), }, + { PCI_VDEVICE(CYRIX, PCI_DEVICE_ID_CYRIX_5510), }, { 0, }, }; @@ -199,7 +196,7 @@ static __init struct pci_dev *gx_detect_chipset(void) } /* detect which companion chip is used */ - while ((gx_pci = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, gx_pci)) != NULL) { + for_each_pci_dev(gx_pci) { if ((pci_match_id(gx_chipset_tbl, gx_pci)) != NULL) return gx_pci; } diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c index 7e7eea4f826..03162dac627 100644 --- a/arch/x86/kernel/cpu/cpufreq/longhaul.c +++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c @@ -426,7 +426,7 @@ static int guess_fsb(int mult) } -static int __init longhaul_get_ranges(void) +static int __cpuinit longhaul_get_ranges(void) { unsigned int i, j, k = 0; unsigned int ratio; @@ -530,7 +530,7 @@ static int __init longhaul_get_ranges(void) } -static void __init longhaul_setup_voltagescaling(void) +static void __cpuinit longhaul_setup_voltagescaling(void) { union msr_longhaul longhaul; struct mV_pos minvid, maxvid, vid; @@ -784,7 +784,7 @@ static int longhaul_setup_southbridge(void) return 0; } -static int __init longhaul_cpu_init(struct cpufreq_policy *policy) +static int __cpuinit longhaul_cpu_init(struct cpufreq_policy *policy) { struct cpuinfo_x86 *c = &cpu_data(0); char *cpuname = NULL; diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.h b/arch/x86/kernel/cpu/cpufreq/longhaul.h index e2360a469f7..cbf48fbca88 100644 --- a/arch/x86/kernel/cpu/cpufreq/longhaul.h +++ b/arch/x86/kernel/cpu/cpufreq/longhaul.h @@ -56,7 +56,7 @@ union msr_longhaul { /* * VIA C3 Samuel 1 & Samuel 2 (stepping 0) */ -static const int __initdata samuel1_mults[16] = { +static const int __cpuinitdata samuel1_mults[16] = { -1, /* 0000 -> RESERVED */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -75,7 +75,7 @@ static const int __initdata samuel1_mults[16] = { -1, /* 1111 -> RESERVED */ }; -static const int __initdata samuel1_eblcr[16] = { +static const int __cpuinitdata samuel1_eblcr[16] = { 50, /* 0000 -> RESERVED */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -97,7 +97,7 @@ static const int __initdata samuel1_eblcr[16] = { /* * VIA C3 Samuel2 Stepping 1->15 */ -static const int __initdata samuel2_eblcr[16] = { +static const int __cpuinitdata samuel2_eblcr[16] = { 50, /* 0000 -> 5.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -119,7 +119,7 @@ static const int __initdata samuel2_eblcr[16] = { /* * VIA C3 Ezra */ -static const int __initdata ezra_mults[16] = { +static const int __cpuinitdata ezra_mults[16] = { 100, /* 0000 -> 10.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -138,7 +138,7 @@ static const int __initdata ezra_mults[16] = { 120, /* 1111 -> 12.0x */ }; -static const int __initdata ezra_eblcr[16] = { +static const int __cpuinitdata ezra_eblcr[16] = { 50, /* 0000 -> 5.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -160,7 +160,7 @@ static const int __initdata ezra_eblcr[16] = { /* * VIA C3 (Ezra-T) [C5M]. */ -static const int __initdata ezrat_mults[32] = { +static const int __cpuinitdata ezrat_mults[32] = { 100, /* 0000 -> 10.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -196,7 +196,7 @@ static const int __initdata ezrat_mults[32] = { -1, /* 1111 -> RESERVED (12.0x) */ }; -static const int __initdata ezrat_eblcr[32] = { +static const int __cpuinitdata ezrat_eblcr[32] = { 50, /* 0000 -> 5.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -235,7 +235,7 @@ static const int __initdata ezrat_eblcr[32] = { /* * VIA C3 Nehemiah */ -static const int __initdata nehemiah_mults[32] = { +static const int __cpuinitdata nehemiah_mults[32] = { 100, /* 0000 -> 10.0x */ -1, /* 0001 -> 16.0x */ 40, /* 0010 -> 4.0x */ @@ -270,7 +270,7 @@ static const int __initdata nehemiah_mults[32] = { -1, /* 1111 -> 12.0x */ }; -static const int __initdata nehemiah_eblcr[32] = { +static const int __cpuinitdata nehemiah_eblcr[32] = { 50, /* 0000 -> 5.0x */ 160, /* 0001 -> 16.0x */ 40, /* 0010 -> 4.0x */ @@ -315,7 +315,7 @@ struct mV_pos { unsigned short pos; }; -static const struct mV_pos __initdata vrm85_mV[32] = { +static const struct mV_pos __cpuinitdata vrm85_mV[32] = { {1250, 8}, {1200, 6}, {1150, 4}, {1100, 2}, {1050, 0}, {1800, 30}, {1750, 28}, {1700, 26}, {1650, 24}, {1600, 22}, {1550, 20}, {1500, 18}, @@ -326,14 +326,14 @@ static const struct mV_pos __initdata vrm85_mV[32] = { {1475, 17}, {1425, 15}, {1375, 13}, {1325, 11} }; -static const unsigned char __initdata mV_vrm85[32] = { +static const unsigned char __cpuinitdata mV_vrm85[32] = { 0x04, 0x14, 0x03, 0x13, 0x02, 0x12, 0x01, 0x11, 0x00, 0x10, 0x0f, 0x1f, 0x0e, 0x1e, 0x0d, 0x1d, 0x0c, 0x1c, 0x0b, 0x1b, 0x0a, 0x1a, 0x09, 0x19, 0x08, 0x18, 0x07, 0x17, 0x06, 0x16, 0x05, 0x15 }; -static const struct mV_pos __initdata mobilevrm_mV[32] = { +static const struct mV_pos __cpuinitdata mobilevrm_mV[32] = { {1750, 31}, {1700, 30}, {1650, 29}, {1600, 28}, {1550, 27}, {1500, 26}, {1450, 25}, {1400, 24}, {1350, 23}, {1300, 22}, {1250, 21}, {1200, 20}, @@ -344,7 +344,7 @@ static const struct mV_pos __initdata mobilevrm_mV[32] = { {675, 3}, {650, 2}, {625, 1}, {600, 0} }; -static const unsigned char __initdata mV_mobilevrm[32] = { +static const unsigned char __cpuinitdata mV_mobilevrm[32] = { 0x1f, 0x1e, 0x1d, 0x1c, 0x1b, 0x1a, 0x19, 0x18, 0x17, 0x16, 0x15, 0x14, 0x13, 0x12, 0x11, 0x10, 0x0f, 0x0e, 0x0d, 0x0c, 0x0b, 0x0a, 0x09, 0x08, diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/arch/x86/kernel/cpu/cpufreq/longrun.c index e7b559d74c5..fc09f142d94 100644 --- a/arch/x86/kernel/cpu/cpufreq/longrun.c +++ b/arch/x86/kernel/cpu/cpufreq/longrun.c @@ -165,8 +165,8 @@ static unsigned int longrun_get(unsigned int cpu) * TMTA rules: * performance_pctg = (target_freq - low_freq)/(high_freq - low_freq) */ -static unsigned int __init longrun_determine_freqs(unsigned int *low_freq, - unsigned int *high_freq) +static unsigned int __cpuinit longrun_determine_freqs(unsigned int *low_freq, + unsigned int *high_freq) { u32 msr_lo, msr_hi; u32 save_lo, save_hi; @@ -258,7 +258,7 @@ static unsigned int __init longrun_determine_freqs(unsigned int *low_freq, } -static int __init longrun_cpu_init(struct cpufreq_policy *policy) +static int __cpuinit longrun_cpu_init(struct cpufreq_policy *policy) { int result = 0; diff --git a/arch/x86/kernel/cpu/cpufreq/mperf.c b/arch/x86/kernel/cpu/cpufreq/mperf.c new file mode 100644 index 00000000000..911e193018a --- /dev/null +++ b/arch/x86/kernel/cpu/cpufreq/mperf.c @@ -0,0 +1,51 @@ +#include <linux/kernel.h> +#include <linux/smp.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/cpufreq.h> +#include <linux/slab.h> + +#include "mperf.h" + +static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf); + +/* Called via smp_call_function_single(), on the target CPU */ +static void read_measured_perf_ctrs(void *_cur) +{ + struct aperfmperf *am = _cur; + + get_aperfmperf(am); +} + +/* + * Return the measured active (C0) frequency on this CPU since last call + * to this function. + * Input: cpu number + * Return: Average CPU frequency in terms of max frequency (zero on error) + * + * We use IA32_MPERF and IA32_APERF MSRs to get the measured performance + * over a period of time, while CPU is in C0 state. + * IA32_MPERF counts at the rate of max advertised frequency + * IA32_APERF counts at the rate of actual CPU frequency + * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and + * no meaning should be associated with absolute values of these MSRs. + */ +unsigned int cpufreq_get_measured_perf(struct cpufreq_policy *policy, + unsigned int cpu) +{ + struct aperfmperf perf; + unsigned long ratio; + unsigned int retval; + + if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1)) + return 0; + + ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf); + per_cpu(acfreq_old_perf, cpu) = perf; + + retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT; + + return retval; +} +EXPORT_SYMBOL_GPL(cpufreq_get_measured_perf); +MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/cpufreq/mperf.h b/arch/x86/kernel/cpu/cpufreq/mperf.h new file mode 100644 index 00000000000..5dbf2950dc2 --- /dev/null +++ b/arch/x86/kernel/cpu/cpufreq/mperf.h @@ -0,0 +1,9 @@ +/* + * (c) 2010 Advanced Micro Devices, Inc. + * Your use of this code is subject to the terms and conditions of the + * GNU general public license version 2. See "COPYING" or + * http://www.gnu.org/licenses/gpl.html + */ + +unsigned int cpufreq_get_measured_perf(struct cpufreq_policy *policy, + unsigned int cpu); diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index 7b8a8ba67b0..bd1cac747f6 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -178,13 +178,8 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) } } - if (c->x86 != 0xF) { - if (!cpu_has(c, X86_FEATURE_EST)) - printk(KERN_WARNING PFX "Unknown CPU. " - "Please send an e-mail to " - "<cpufreq@vger.kernel.org>\n"); + if (c->x86 != 0xF) return 0; - } /* on P-4s, the TSC runs with constant frequency independent whether * throttling is active or not. */ diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c index ce7cde713e7..a36de5bbb62 100644 --- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c @@ -368,22 +368,16 @@ static int __init pcc_cpufreq_do_osc(acpi_handle *handle) return -ENODEV; out_obj = output.pointer; - if (out_obj->type != ACPI_TYPE_BUFFER) { - ret = -ENODEV; - goto out_free; - } + if (out_obj->type != ACPI_TYPE_BUFFER) + return -ENODEV; errors = *((u32 *)out_obj->buffer.pointer) & ~(1 << 0); - if (errors) { - ret = -ENODEV; - goto out_free; - } + if (errors) + return -ENODEV; supported = *((u32 *)(out_obj->buffer.pointer + 4)); - if (!(supported & 0x1)) { - ret = -ENODEV; - goto out_free; - } + if (!(supported & 0x1)) + return -ENODEV; out_free: kfree(output.pointer); @@ -397,13 +391,17 @@ static int __init pcc_cpufreq_probe(void) struct pcc_memory_resource *mem_resource; struct pcc_register_resource *reg_resource; union acpi_object *out_obj, *member; - acpi_handle handle, osc_handle; + acpi_handle handle, osc_handle, pcch_handle; int ret = 0; status = acpi_get_handle(NULL, "\\_SB", &handle); if (ACPI_FAILURE(status)) return -ENODEV; + status = acpi_get_handle(handle, "PCCH", &pcch_handle); + if (ACPI_FAILURE(status)) + return -ENODEV; + status = acpi_get_handle(handle, "_OSC", &osc_handle); if (ACPI_SUCCESS(status)) { ret = pcc_cpufreq_do_osc(&osc_handle); @@ -543,13 +541,13 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy) if (!pcch_virt_addr) { result = -1; - goto pcch_null; + goto out; } result = pcc_get_offset(cpu); if (result) { dprintk("init: PCCP evaluation failed\n"); - goto free; + goto out; } policy->max = policy->cpuinfo.max_freq = @@ -558,14 +556,15 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy) ioread32(&pcch_hdr->minimum_frequency) * 1000; policy->cur = pcc_get_freq(cpu); + if (!policy->cur) { + dprintk("init: Unable to get current CPU frequency\n"); + result = -EINVAL; + goto out; + } + dprintk("init: policy->max is %d, policy->min is %d\n", policy->max, policy->min); - - return 0; -free: - pcc_clear_mapping(); - free_percpu(pcc_cpu_info); -pcch_null: +out: return result; } diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c index 9a97116f89e..4a45fd6e41b 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c @@ -569,7 +569,7 @@ static int powernow_verify(struct cpufreq_policy *policy) * We will then get the same kind of behaviour already tested under * the "well-known" other OS. */ -static int __init fixup_sgtc(void) +static int __cpuinit fixup_sgtc(void) { unsigned int sgtc; unsigned int m; @@ -603,7 +603,7 @@ static unsigned int powernow_get(unsigned int cpu) } -static int __init acer_cpufreq_pst(const struct dmi_system_id *d) +static int __cpuinit acer_cpufreq_pst(const struct dmi_system_id *d) { printk(KERN_WARNING PFX "%s laptop with broken PST tables in BIOS detected.\n", @@ -621,7 +621,7 @@ static int __init acer_cpufreq_pst(const struct dmi_system_id *d) * A BIOS update is all that can save them. * Mention this, and disable cpufreq. */ -static struct dmi_system_id __initdata powernow_dmi_table[] = { +static struct dmi_system_id __cpuinitdata powernow_dmi_table[] = { { .callback = acer_cpufreq_pst, .ident = "Acer Aspire", @@ -633,7 +633,7 @@ static struct dmi_system_id __initdata powernow_dmi_table[] = { { } }; -static int __init powernow_cpu_init(struct cpufreq_policy *policy) +static int __cpuinit powernow_cpu_init(struct cpufreq_policy *policy) { union msr_fidvidstatus fidvidstatus; int result; diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index b6215b9798e..491977baf6c 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -1,6 +1,5 @@ - /* - * (c) 2003-2006 Advanced Micro Devices, Inc. + * (c) 2003-2010 Advanced Micro Devices, Inc. * Your use of this code is subject to the terms and conditions of the * GNU general public license version 2. See "COPYING" or * http://www.gnu.org/licenses/gpl.html @@ -10,7 +9,7 @@ * Based on the powernow-k7.c module written by Dave Jones. * (C) 2003 Dave Jones on behalf of SuSE Labs * (C) 2004 Dominik Brodowski <linux@brodo.de> - * (C) 2004 Pavel Machek <pavel@suse.cz> + * (C) 2004 Pavel Machek <pavel@ucw.cz> * Licensed under the terms of the GNU GPL License version 2. * Based upon datasheets & sample CPUs kindly provided by AMD. * @@ -46,6 +45,7 @@ #define PFX "powernow-k8: " #define VERSION "version 2.20.00" #include "powernow-k8.h" +#include "mperf.h" /* serialize freq changes */ static DEFINE_MUTEX(fidvid_mutex); @@ -54,6 +54,12 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data); static int cpu_family = CPU_OPTERON; +/* core performance boost */ +static bool cpb_capable, cpb_enabled; +static struct msr __percpu *msrs; + +static struct cpufreq_driver cpufreq_amd64_driver; + #ifndef CONFIG_SMP static inline const struct cpumask *cpu_core_mask(int cpu) { @@ -800,6 +806,8 @@ static int find_psb_table(struct powernow_k8_data *data) * www.amd.com */ printk(KERN_ERR FW_BUG PFX "No PSB or ACPI _PSS objects\n"); + printk(KERN_ERR PFX "Make sure that your BIOS is up to date" + " and Cool'N'Quiet support is enabled in BIOS setup\n"); return -ENODEV; } @@ -904,8 +912,8 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, { int i; u32 hi = 0, lo = 0; - rdmsr(MSR_PSTATE_CUR_LIMIT, hi, lo); - data->max_hw_pstate = (hi & HW_PSTATE_MAX_MASK) >> HW_PSTATE_MAX_SHIFT; + rdmsr(MSR_PSTATE_CUR_LIMIT, lo, hi); + data->max_hw_pstate = (lo & HW_PSTATE_MAX_MASK) >> HW_PSTATE_MAX_SHIFT; for (i = 0; i < data->acpi_data.state_count; i++) { u32 index; @@ -1017,13 +1025,12 @@ static int get_transition_latency(struct powernow_k8_data *data) } if (max_latency == 0) { /* - * Fam 11h always returns 0 as transition latency. - * This is intended and means "very fast". While cpufreq core - * and governors currently can handle that gracefully, better - * set it to 1 to avoid problems in the future. - * For all others it's a BIOS bug. + * Fam 11h and later may return 0 as transition latency. This + * is intended and means "very fast". While cpufreq core and + * governors currently can handle that gracefully, better set it + * to 1 to avoid problems in the future. */ - if (boot_cpu_data.x86 != 0x11) + if (boot_cpu_data.x86 < 0x11) printk(KERN_ERR FW_WARN PFX "Invalid zero transition " "latency\n"); max_latency = 1; @@ -1249,6 +1256,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) struct powernow_k8_data *data; struct init_on_cpu init_on_cpu; int rc; + struct cpuinfo_x86 *c = &cpu_data(pol->cpu); if (!cpu_online(pol->cpu)) return -ENODEV; @@ -1323,6 +1331,10 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) return -EINVAL; } + /* Check for APERF/MPERF support in hardware */ + if (cpu_has(c, X86_FEATURE_APERFMPERF)) + cpufreq_amd64_driver.getavg = cpufreq_get_measured_perf; + cpufreq_frequency_table_get_attr(data->powernow_table, pol->cpu); if (cpu_family == CPU_HW_PSTATE) @@ -1394,8 +1406,77 @@ out: return khz; } +static void _cpb_toggle_msrs(bool t) +{ + int cpu; + + get_online_cpus(); + + rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs); + + for_each_cpu(cpu, cpu_online_mask) { + struct msr *reg = per_cpu_ptr(msrs, cpu); + if (t) + reg->l &= ~BIT(25); + else + reg->l |= BIT(25); + } + wrmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs); + + put_online_cpus(); +} + +/* + * Switch on/off core performance boosting. + * + * 0=disable + * 1=enable. + */ +static void cpb_toggle(bool t) +{ + if (!cpb_capable) + return; + + if (t && !cpb_enabled) { + cpb_enabled = true; + _cpb_toggle_msrs(t); + printk(KERN_INFO PFX "Core Boosting enabled.\n"); + } else if (!t && cpb_enabled) { + cpb_enabled = false; + _cpb_toggle_msrs(t); + printk(KERN_INFO PFX "Core Boosting disabled.\n"); + } +} + +static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf, + size_t count) +{ + int ret = -EINVAL; + unsigned long val = 0; + + ret = strict_strtoul(buf, 10, &val); + if (!ret && (val == 0 || val == 1) && cpb_capable) + cpb_toggle(val); + else + return -EINVAL; + + return count; +} + +static ssize_t show_cpb(struct cpufreq_policy *policy, char *buf) +{ + return sprintf(buf, "%u\n", cpb_enabled); +} + +#define define_one_rw(_name) \ +static struct freq_attr _name = \ +__ATTR(_name, 0644, show_##_name, store_##_name) + +define_one_rw(cpb); + static struct freq_attr *powernow_k8_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, + &cpb, NULL, }; @@ -1411,10 +1492,51 @@ static struct cpufreq_driver cpufreq_amd64_driver = { .attr = powernow_k8_attr, }; +/* + * Clear the boost-disable flag on the CPU_DOWN path so that this cpu + * cannot block the remaining ones from boosting. On the CPU_UP path we + * simply keep the boost-disable flag in sync with the current global + * state. + */ +static int cpb_notify(struct notifier_block *nb, unsigned long action, + void *hcpu) +{ + unsigned cpu = (long)hcpu; + u32 lo, hi; + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + + if (!cpb_enabled) { + rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi); + lo |= BIT(25); + wrmsr_on_cpu(cpu, MSR_K7_HWCR, lo, hi); + } + break; + + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi); + lo &= ~BIT(25); + wrmsr_on_cpu(cpu, MSR_K7_HWCR, lo, hi); + break; + + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block cpb_nb = { + .notifier_call = cpb_notify, +}; + /* driver entry point for init */ static int __cpuinit powernowk8_init(void) { - unsigned int i, supported_cpus = 0; + unsigned int i, supported_cpus = 0, cpu; for_each_online_cpu(i) { int rc; @@ -1423,15 +1545,36 @@ static int __cpuinit powernowk8_init(void) supported_cpus++; } - if (supported_cpus == num_online_cpus()) { - printk(KERN_INFO PFX "Found %d %s " - "processors (%d cpu cores) (" VERSION ")\n", - num_online_nodes(), - boot_cpu_data.x86_model_id, supported_cpus); - return cpufreq_register_driver(&cpufreq_amd64_driver); + if (supported_cpus != num_online_cpus()) + return -ENODEV; + + printk(KERN_INFO PFX "Found %d %s (%d cpu cores) (" VERSION ")\n", + num_online_nodes(), boot_cpu_data.x86_model_id, supported_cpus); + + if (boot_cpu_has(X86_FEATURE_CPB)) { + + cpb_capable = true; + + register_cpu_notifier(&cpb_nb); + + msrs = msrs_alloc(); + if (!msrs) { + printk(KERN_ERR "%s: Error allocating msrs!\n", __func__); + return -ENOMEM; + } + + rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs); + + for_each_cpu(cpu, cpu_online_mask) { + struct msr *reg = per_cpu_ptr(msrs, cpu); + cpb_enabled |= !(!!(reg->l & BIT(25))); + } + + printk(KERN_INFO PFX "Core Performance Boosting: %s.\n", + (cpb_enabled ? "on" : "off")); } - return -ENODEV; + return cpufreq_register_driver(&cpufreq_amd64_driver); } /* driver entry point for term */ @@ -1439,6 +1582,13 @@ static void __exit powernowk8_exit(void) { dprintk("exit\n"); + if (boot_cpu_has(X86_FEATURE_CPB)) { + msrs_free(msrs); + msrs = NULL; + + unregister_cpu_notifier(&cpb_nb); + } + cpufreq_unregister_driver(&cpufreq_amd64_driver); } diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h index 02ce824073c..df3529b1c02 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h @@ -5,7 +5,6 @@ * http://www.gnu.org/licenses/gpl.html */ - enum pstate { HW_PSTATE_INVALID = 0xff, HW_PSTATE_0 = 0, @@ -55,7 +54,6 @@ struct powernow_k8_data { struct cpumask *available_cores; }; - /* processor's cpuid instruction support */ #define CPUID_PROCESSOR_SIGNATURE 1 /* function 1 */ #define CPUID_XFAM 0x0ff00000 /* extended family */ diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 08be922de33..8095f8611f8 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -21,37 +21,58 @@ * */ +#include <linux/module.h> #include <asm/processor.h> -#include <asm/vmware.h> #include <asm/hypervisor.h> -static inline void __cpuinit -detect_hypervisor_vendor(struct cpuinfo_x86 *c) +/* + * Hypervisor detect order. This is specified explicitly here because + * some hypervisors might implement compatibility modes for other + * hypervisors and therefore need to be detected in specific sequence. + */ +static const __initconst struct hypervisor_x86 * const hypervisors[] = { - if (vmware_platform()) - c->x86_hyper_vendor = X86_HYPER_VENDOR_VMWARE; - else - c->x86_hyper_vendor = X86_HYPER_VENDOR_NONE; -} + &x86_hyper_vmware, + &x86_hyper_ms_hyperv, +#ifdef CONFIG_XEN_PVHVM + &x86_hyper_xen_hvm, +#endif +}; -static inline void __cpuinit -hypervisor_set_feature_bits(struct cpuinfo_x86 *c) +const struct hypervisor_x86 *x86_hyper; +EXPORT_SYMBOL(x86_hyper); + +static inline void __init +detect_hypervisor_vendor(void) { - if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE) { - vmware_set_feature_bits(c); - return; + const struct hypervisor_x86 *h, * const *p; + + for (p = hypervisors; p < hypervisors + ARRAY_SIZE(hypervisors); p++) { + h = *p; + if (h->detect()) { + x86_hyper = h; + printk(KERN_INFO "Hypervisor detected: %s\n", h->name); + break; + } } } void __cpuinit init_hypervisor(struct cpuinfo_x86 *c) { - detect_hypervisor_vendor(c); - hypervisor_set_feature_bits(c); + if (x86_hyper && x86_hyper->set_cpu_features) + x86_hyper->set_cpu_features(c); } void __init init_hypervisor_platform(void) { + + detect_hypervisor_vendor(); + + if (!x86_hyper) + return; + init_hypervisor(&boot_cpu_data); - if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE) - vmware_platform_setup(); + + if (x86_hyper->init_platform) + x86_hyper->init_platform(); } diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 1366c7cfd48..85f69cdeae1 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -12,7 +12,6 @@ #include <asm/processor.h> #include <asm/pgtable.h> #include <asm/msr.h> -#include <asm/ds.h> #include <asm/bugs.h> #include <asm/cpu.h> @@ -373,12 +372,6 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON); } - if (c->cpuid_level > 6) { - unsigned ecx = cpuid_ecx(6); - if (ecx & 0x01) - set_cpu_cap(c, X86_FEATURE_APERFMPERF); - } - if (cpu_has_xmm2) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); if (cpu_has_ds) { @@ -388,7 +381,6 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_BTS); if (!(l1 & (1<<12))) set_cpu_cap(c, X86_FEATURE_PEBS); - ds_init_intel(c); } if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush) diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 95962a93f99..898c2f4eab8 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -148,13 +148,19 @@ union _cpuid4_leaf_ecx { u32 full; }; +struct amd_l3_cache { + struct pci_dev *dev; + bool can_disable; + unsigned indices; + u8 subcaches[4]; +}; + struct _cpuid4_info { union _cpuid4_leaf_eax eax; union _cpuid4_leaf_ebx ebx; union _cpuid4_leaf_ecx ecx; unsigned long size; - bool can_disable; - unsigned int l3_indices; + struct amd_l3_cache *l3; DECLARE_BITMAP(shared_cpu_map, NR_CPUS); }; @@ -164,8 +170,7 @@ struct _cpuid4_info_regs { union _cpuid4_leaf_ebx ebx; union _cpuid4_leaf_ecx ecx; unsigned long size; - bool can_disable; - unsigned int l3_indices; + struct amd_l3_cache *l3; }; unsigned short num_cache_leaves; @@ -302,124 +307,246 @@ struct _cache_attr { }; #ifdef CONFIG_CPU_SUP_AMD -static unsigned int __cpuinit amd_calc_l3_indices(void) + +/* + * L3 cache descriptors + */ +static struct amd_l3_cache **__cpuinitdata l3_caches; + +static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3) { - /* - * We're called over smp_call_function_single() and therefore - * are on the correct cpu. - */ - int cpu = smp_processor_id(); - int node = cpu_to_node(cpu); - struct pci_dev *dev = node_to_k8_nb_misc(node); unsigned int sc0, sc1, sc2, sc3; u32 val = 0; - pci_read_config_dword(dev, 0x1C4, &val); + pci_read_config_dword(l3->dev, 0x1C4, &val); /* calculate subcache sizes */ - sc0 = !(val & BIT(0)); - sc1 = !(val & BIT(4)); - sc2 = !(val & BIT(8)) + !(val & BIT(9)); - sc3 = !(val & BIT(12)) + !(val & BIT(13)); + l3->subcaches[0] = sc0 = !(val & BIT(0)); + l3->subcaches[1] = sc1 = !(val & BIT(4)); + l3->subcaches[2] = sc2 = !(val & BIT(8)) + !(val & BIT(9)); + l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13)); - return (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1; + l3->indices = (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1; } -static void __cpuinit -amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) +static struct amd_l3_cache * __cpuinit amd_init_l3_cache(int node) { - if (index < 3) + struct amd_l3_cache *l3; + struct pci_dev *dev = node_to_k8_nb_misc(node); + + l3 = kzalloc(sizeof(struct amd_l3_cache), GFP_ATOMIC); + if (!l3) { + printk(KERN_WARNING "Error allocating L3 struct\n"); + return NULL; + } + + l3->dev = dev; + + amd_calc_l3_indices(l3); + + return l3; +} + +static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, + int index) +{ + int node; + + if (boot_cpu_data.x86 != 0x10) return; - if (boot_cpu_data.x86 == 0x11) + if (index < 3) return; /* see errata #382 and #388 */ - if ((boot_cpu_data.x86 == 0x10) && - ((boot_cpu_data.x86_model < 0x8) || - (boot_cpu_data.x86_mask < 0x1))) + if (boot_cpu_data.x86_model < 0x8) return; + if ((boot_cpu_data.x86_model == 0x8 || + boot_cpu_data.x86_model == 0x9) + && + boot_cpu_data.x86_mask < 0x1) + return; + /* not in virtualized environments */ if (num_k8_northbridges == 0) return; - this_leaf->can_disable = true; - this_leaf->l3_indices = amd_calc_l3_indices(); + /* + * Strictly speaking, the amount in @size below is leaked since it is + * never freed but this is done only on shutdown so it doesn't matter. + */ + if (!l3_caches) { + int size = num_k8_northbridges * sizeof(struct amd_l3_cache *); + + l3_caches = kzalloc(size, GFP_ATOMIC); + if (!l3_caches) + return; + } + + node = amd_get_nb_id(smp_processor_id()); + + if (!l3_caches[node]) { + l3_caches[node] = amd_init_l3_cache(node); + l3_caches[node]->can_disable = true; + } + + WARN_ON(!l3_caches[node]); + + this_leaf->l3 = l3_caches[node]; } -static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf, - unsigned int index) +/* + * check whether a slot used for disabling an L3 index is occupied. + * @l3: L3 cache descriptor + * @slot: slot number (0..1) + * + * @returns: the disabled index if used or negative value if slot free. + */ +int amd_get_l3_disable_slot(struct amd_l3_cache *l3, unsigned slot) { - int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); - int node = amd_get_nb_id(cpu); - struct pci_dev *dev = node_to_k8_nb_misc(node); unsigned int reg = 0; - if (!this_leaf->can_disable) - return -EINVAL; + pci_read_config_dword(l3->dev, 0x1BC + slot * 4, ®); + + /* check whether this slot is activated already */ + if (reg & (3UL << 30)) + return reg & 0xfff; - if (!dev) + return -1; +} + +static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf, + unsigned int slot) +{ + int index; + + if (!this_leaf->l3 || !this_leaf->l3->can_disable) return -EINVAL; - pci_read_config_dword(dev, 0x1BC + index * 4, ®); - return sprintf(buf, "0x%08x\n", reg); + index = amd_get_l3_disable_slot(this_leaf->l3, slot); + if (index >= 0) + return sprintf(buf, "%d\n", index); + + return sprintf(buf, "FREE\n"); } -#define SHOW_CACHE_DISABLE(index) \ +#define SHOW_CACHE_DISABLE(slot) \ static ssize_t \ -show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf) \ +show_cache_disable_##slot(struct _cpuid4_info *this_leaf, char *buf) \ { \ - return show_cache_disable(this_leaf, buf, index); \ + return show_cache_disable(this_leaf, buf, slot); \ } SHOW_CACHE_DISABLE(0) SHOW_CACHE_DISABLE(1) -static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, - const char *buf, size_t count, unsigned int index) +static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu, + unsigned slot, unsigned long idx) { - int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); - int node = amd_get_nb_id(cpu); - struct pci_dev *dev = node_to_k8_nb_misc(node); - unsigned long val = 0; + int i; + + idx |= BIT(30); + + /* + * disable index in all 4 subcaches + */ + for (i = 0; i < 4; i++) { + u32 reg = idx | (i << 20); + + if (!l3->subcaches[i]) + continue; + + pci_write_config_dword(l3->dev, 0x1BC + slot * 4, reg); + + /* + * We need to WBINVD on a core on the node containing the L3 + * cache which indices we disable therefore a simple wbinvd() + * is not sufficient. + */ + wbinvd_on_cpu(cpu); + + reg |= BIT(31); + pci_write_config_dword(l3->dev, 0x1BC + slot * 4, reg); + } +} + +/* + * disable a L3 cache index by using a disable-slot + * + * @l3: L3 cache descriptor + * @cpu: A CPU on the node containing the L3 cache + * @slot: slot number (0..1) + * @index: index to disable + * + * @return: 0 on success, error status on failure + */ +int amd_set_l3_disable_slot(struct amd_l3_cache *l3, int cpu, unsigned slot, + unsigned long index) +{ + int ret = 0; #define SUBCACHE_MASK (3UL << 20) #define SUBCACHE_INDEX 0xfff - if (!this_leaf->can_disable) + /* + * check whether this slot is already used or + * the index is already disabled + */ + ret = amd_get_l3_disable_slot(l3, slot); + if (ret >= 0) return -EINVAL; + /* + * check whether the other slot has disabled the + * same index already + */ + if (index == amd_get_l3_disable_slot(l3, !slot)) + return -EINVAL; + + /* do not allow writes outside of allowed bits */ + if ((index & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) || + ((index & SUBCACHE_INDEX) > l3->indices)) + return -EINVAL; + + amd_l3_disable_index(l3, cpu, slot, index); + + return 0; +} + +static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, + const char *buf, size_t count, + unsigned int slot) +{ + unsigned long val = 0; + int cpu, err = 0; + if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!dev) + if (!this_leaf->l3 || !this_leaf->l3->can_disable) return -EINVAL; - if (strict_strtoul(buf, 10, &val) < 0) - return -EINVAL; + cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); - /* do not allow writes outside of allowed bits */ - if ((val & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) || - ((val & SUBCACHE_INDEX) > this_leaf->l3_indices)) + if (strict_strtoul(buf, 10, &val) < 0) return -EINVAL; - val |= BIT(30); - pci_write_config_dword(dev, 0x1BC + index * 4, val); - /* - * We need to WBINVD on a core on the node containing the L3 cache which - * indices we disable therefore a simple wbinvd() is not sufficient. - */ - wbinvd_on_cpu(cpu); - pci_write_config_dword(dev, 0x1BC + index * 4, val | BIT(31)); + err = amd_set_l3_disable_slot(this_leaf->l3, cpu, slot, val); + if (err) { + if (err == -EEXIST) + printk(KERN_WARNING "L3 disable slot %d in use!\n", + slot); + return err; + } return count; } -#define STORE_CACHE_DISABLE(index) \ +#define STORE_CACHE_DISABLE(slot) \ static ssize_t \ -store_cache_disable_##index(struct _cpuid4_info *this_leaf, \ +store_cache_disable_##slot(struct _cpuid4_info *this_leaf, \ const char *buf, size_t count) \ { \ - return store_cache_disable(this_leaf, buf, count, index); \ + return store_cache_disable(this_leaf, buf, count, slot); \ } STORE_CACHE_DISABLE(0) STORE_CACHE_DISABLE(1) @@ -431,7 +558,7 @@ static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644, #else /* CONFIG_CPU_SUP_AMD */ static void __cpuinit -amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) +amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, int index) { }; #endif /* CONFIG_CPU_SUP_AMD */ @@ -447,8 +574,7 @@ __cpuinit cpuid4_cache_lookup_regs(int index, if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { amd_cpuid4(index, &eax, &ebx, &ecx); - if (boot_cpu_data.x86 >= 0x10) - amd_check_l3_disable(index, this_leaf); + amd_check_l3_disable(this_leaf, index); } else { cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx); } @@ -705,6 +831,7 @@ static void __cpuinit free_cache_attributes(unsigned int cpu) for (i = 0; i < num_cache_leaves; i++) cache_remove_shared_cpu_map(cpu, i); + kfree(per_cpu(ici_cpuid4_info, cpu)->l3); kfree(per_cpu(ici_cpuid4_info, cpu)); per_cpu(ici_cpuid4_info, cpu) = NULL; } @@ -989,7 +1116,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) this_leaf = CPUID4_INFO_IDX(cpu, i); - if (this_leaf->can_disable) + if (this_leaf->l3 && this_leaf->l3->can_disable) ktype_cache.default_attrs = default_l3_attrs; else ktype_cache.default_attrs = default_attrs; diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile index 4ac6d48fe11..bb34b03af25 100644 --- a/arch/x86/kernel/cpu/mcheck/Makefile +++ b/arch/x86/kernel/cpu/mcheck/Makefile @@ -7,3 +7,5 @@ obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o obj-$(CONFIG_X86_MCE_INJECT) += mce-inject.o obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o + +obj-$(CONFIG_ACPI_APEI) += mce-apei.o diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c new file mode 100644 index 00000000000..745b54f9be8 --- /dev/null +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -0,0 +1,138 @@ +/* + * Bridge between MCE and APEI + * + * On some machine, corrected memory errors are reported via APEI + * generic hardware error source (GHES) instead of corrected Machine + * Check. These corrected memory errors can be reported to user space + * through /dev/mcelog via faking a corrected Machine Check, so that + * the error memory page can be offlined by /sbin/mcelog if the error + * count for one page is beyond the threshold. + * + * For fatal MCE, save MCE record into persistent storage via ERST, so + * that the MCE record can be logged after reboot via ERST. + * + * Copyright 2010 Intel Corp. + * Author: Huang Ying <ying.huang@intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version + * 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/kernel.h> +#include <linux/acpi.h> +#include <linux/cper.h> +#include <acpi/apei.h> +#include <asm/mce.h> + +#include "mce-internal.h" + +void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err) +{ + struct mce m; + + /* Only corrected MC is reported */ + if (!corrected) + return; + + mce_setup(&m); + m.bank = 1; + /* Fake a memory read corrected error with unknown channel */ + m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | 0x9f; + m.addr = mem_err->physical_addr; + mce_log(&m); + mce_notify_irq(); +} +EXPORT_SYMBOL_GPL(apei_mce_report_mem_error); + +#define CPER_CREATOR_MCE \ + UUID_LE(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c, \ + 0x64, 0x90, 0xb8, 0x9d) +#define CPER_SECTION_TYPE_MCE \ + UUID_LE(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96, \ + 0x04, 0x4a, 0x38, 0xfc) + +/* + * CPER specification (in UEFI specification 2.3 appendix N) requires + * byte-packed. + */ +struct cper_mce_record { + struct cper_record_header hdr; + struct cper_section_descriptor sec_hdr; + struct mce mce; +} __packed; + +int apei_write_mce(struct mce *m) +{ + struct cper_mce_record rcd; + + memset(&rcd, 0, sizeof(rcd)); + memcpy(rcd.hdr.signature, CPER_SIG_RECORD, CPER_SIG_SIZE); + rcd.hdr.revision = CPER_RECORD_REV; + rcd.hdr.signature_end = CPER_SIG_END; + rcd.hdr.section_count = 1; + rcd.hdr.error_severity = CPER_SER_FATAL; + /* timestamp, platform_id, partition_id are all invalid */ + rcd.hdr.validation_bits = 0; + rcd.hdr.record_length = sizeof(rcd); + rcd.hdr.creator_id = CPER_CREATOR_MCE; + rcd.hdr.notification_type = CPER_NOTIFY_MCE; + rcd.hdr.record_id = cper_next_record_id(); + rcd.hdr.flags = CPER_HW_ERROR_FLAGS_PREVERR; + + rcd.sec_hdr.section_offset = (void *)&rcd.mce - (void *)&rcd; + rcd.sec_hdr.section_length = sizeof(rcd.mce); + rcd.sec_hdr.revision = CPER_SEC_REV; + /* fru_id and fru_text is invalid */ + rcd.sec_hdr.validation_bits = 0; + rcd.sec_hdr.flags = CPER_SEC_PRIMARY; + rcd.sec_hdr.section_type = CPER_SECTION_TYPE_MCE; + rcd.sec_hdr.section_severity = CPER_SER_FATAL; + + memcpy(&rcd.mce, m, sizeof(*m)); + + return erst_write(&rcd.hdr); +} + +ssize_t apei_read_mce(struct mce *m, u64 *record_id) +{ + struct cper_mce_record rcd; + ssize_t len; + + len = erst_read_next(&rcd.hdr, sizeof(rcd)); + if (len <= 0) + return len; + /* Can not skip other records in storage via ERST unless clear them */ + else if (len != sizeof(rcd) || + uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE)) { + if (printk_ratelimit()) + pr_warning( + "MCE-APEI: Can not skip the unknown record in ERST"); + return -EIO; + } + + memcpy(m, &rcd.mce, sizeof(*m)); + *record_id = rcd.hdr.record_id; + + return sizeof(*m); +} + +/* Check whether there is record in ERST */ +int apei_check_mce(void) +{ + return erst_get_record_count(); +} + +int apei_clear_mce(u64 record_id) +{ + return erst_clear(record_id); +} diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 32996f9fab6..fefcc69ee8b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -28,3 +28,26 @@ extern int mce_ser; extern struct mce_bank *mce_banks; +#ifdef CONFIG_ACPI_APEI +int apei_write_mce(struct mce *m); +ssize_t apei_read_mce(struct mce *m, u64 *record_id); +int apei_check_mce(void); +int apei_clear_mce(u64 record_id); +#else +static inline int apei_write_mce(struct mce *m) +{ + return -EINVAL; +} +static inline ssize_t apei_read_mce(struct mce *m, u64 *record_id) +{ + return 0; +} +static inline int apei_check_mce(void) +{ + return 0; +} +static inline int apei_clear_mce(u64 record_id) +{ + return -EINVAL; +} +#endif diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8a6f0afa767..ed41562909f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -36,6 +36,7 @@ #include <linux/fs.h> #include <linux/mm.h> #include <linux/debugfs.h> +#include <linux/edac_mce.h> #include <asm/processor.h> #include <asm/hw_irq.h> @@ -50,7 +51,7 @@ static DEFINE_MUTEX(mce_read_mutex); #define rcu_dereference_check_mce(p) \ - rcu_dereference_check((p), \ + rcu_dereference_index_check((p), \ rcu_read_lock_sched_held() || \ lockdep_is_held(&mce_read_mutex)) @@ -106,8 +107,8 @@ EXPORT_SYMBOL_GPL(x86_mce_decoder_chain); static int default_decode_mce(struct notifier_block *nb, unsigned long val, void *data) { - pr_emerg("No human readable MCE decoding support on this CPU type.\n"); - pr_emerg("Run the message through 'mcelog --ascii' to decode.\n"); + pr_emerg(HW_ERR "No human readable MCE decoding support on this CPU type.\n"); + pr_emerg(HW_ERR "Run the message through 'mcelog --ascii' to decode.\n"); return NOTIFY_STOP; } @@ -169,6 +170,15 @@ void mce_log(struct mce *mce) entry = rcu_dereference_check_mce(mcelog.next); for (;;) { /* + * If edac_mce is enabled, it will check the error type + * and will process it, if it is a known error. + * Otherwise, the error will be sent through mcelog + * interface + */ + if (edac_mce_parse(mce)) + return; + + /* * When the buffer fills up discard new entries. * Assume that the earlier errors are the more * interesting ones: @@ -201,11 +211,11 @@ void mce_log(struct mce *mce) static void print_mce(struct mce *m) { - pr_emerg("CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n", + pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n", m->extcpu, m->mcgstatus, m->bank, m->status); if (m->ip) { - pr_emerg("RIP%s %02x:<%016Lx> ", + pr_emerg(HW_ERR "RIP%s %02x:<%016Lx> ", !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "", m->cs, m->ip); @@ -214,14 +224,14 @@ static void print_mce(struct mce *m) pr_cont("\n"); } - pr_emerg("TSC %llx ", m->tsc); + pr_emerg(HW_ERR "TSC %llx ", m->tsc); if (m->addr) pr_cont("ADDR %llx ", m->addr); if (m->misc) pr_cont("MISC %llx ", m->misc); pr_cont("\n"); - pr_emerg("PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n", + pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n", m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid); /* @@ -231,16 +241,6 @@ static void print_mce(struct mce *m) atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m); } -static void print_mce_head(void) -{ - pr_emerg("\nHARDWARE ERROR\n"); -} - -static void print_mce_tail(void) -{ - pr_emerg("This is not a software problem!\n"); -} - #define PANIC_TIMEOUT 5 /* 5 seconds */ static atomic_t mce_paniced; @@ -264,7 +264,7 @@ static void wait_for_panic(void) static void mce_panic(char *msg, struct mce *final, char *exp) { - int i; + int i, apei_err = 0; if (!fake_panic) { /* @@ -281,14 +281,16 @@ static void mce_panic(char *msg, struct mce *final, char *exp) if (atomic_inc_return(&mce_fake_paniced) > 1) return; } - print_mce_head(); /* First print corrected ones that are still unlogged */ for (i = 0; i < MCE_LOG_LEN; i++) { struct mce *m = &mcelog.entry[i]; if (!(m->status & MCI_STATUS_VAL)) continue; - if (!(m->status & MCI_STATUS_UC)) + if (!(m->status & MCI_STATUS_UC)) { print_mce(m); + if (!apei_err) + apei_err = apei_write_mce(m); + } } /* Now print uncorrected but with the final one last */ for (i = 0; i < MCE_LOG_LEN; i++) { @@ -297,22 +299,27 @@ static void mce_panic(char *msg, struct mce *final, char *exp) continue; if (!(m->status & MCI_STATUS_UC)) continue; - if (!final || memcmp(m, final, sizeof(struct mce))) + if (!final || memcmp(m, final, sizeof(struct mce))) { print_mce(m); + if (!apei_err) + apei_err = apei_write_mce(m); + } } - if (final) + if (final) { print_mce(final); + if (!apei_err) + apei_err = apei_write_mce(final); + } if (cpu_missing) - printk(KERN_EMERG "Some CPUs didn't answer in synchronization\n"); - print_mce_tail(); + pr_emerg(HW_ERR "Some CPUs didn't answer in synchronization\n"); if (exp) - printk(KERN_EMERG "Machine check: %s\n", exp); + pr_emerg(HW_ERR "Machine check: %s\n", exp); if (!fake_panic) { if (panic_timeout == 0) panic_timeout = mce_panic_timeout; panic(msg); } else - printk(KERN_EMERG "Fake kernel panic: %s\n", msg); + pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg); } /* Support code for software error injection */ @@ -539,7 +546,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) struct mce m; int i; - __get_cpu_var(mce_poll_count)++; + percpu_inc(mce_poll_count); mce_setup(&m); @@ -581,6 +588,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) */ if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) { mce_log(&m); + atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, &m); add_taint(TAINT_MACHINE_CHECK); } @@ -934,7 +942,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) atomic_inc(&mce_entry); - __get_cpu_var(mce_exception_count)++; + percpu_inc(mce_exception_count); if (notify_die(DIE_NMI, "machine check", regs, error_code, 18, SIGKILL) == NOTIFY_STOP) @@ -1201,7 +1209,7 @@ int mce_notify_irq(void) schedule_work(&mce_trigger_work); if (__ratelimit(&ratelimit)) - printk(KERN_INFO "Machine check events logged\n"); + pr_info(HW_ERR "Machine check events logged\n"); return 1; } @@ -1493,6 +1501,43 @@ static void collect_tscs(void *data) rdtscll(cpu_tsc[smp_processor_id()]); } +static int mce_apei_read_done; + +/* Collect MCE record of previous boot in persistent storage via APEI ERST. */ +static int __mce_read_apei(char __user **ubuf, size_t usize) +{ + int rc; + u64 record_id; + struct mce m; + + if (usize < sizeof(struct mce)) + return -EINVAL; + + rc = apei_read_mce(&m, &record_id); + /* Error or no more MCE record */ + if (rc <= 0) { + mce_apei_read_done = 1; + return rc; + } + rc = -EFAULT; + if (copy_to_user(*ubuf, &m, sizeof(struct mce))) + return rc; + /* + * In fact, we should have cleared the record after that has + * been flushed to the disk or sent to network in + * /sbin/mcelog, but we have no interface to support that now, + * so just clear it to avoid duplication. + */ + rc = apei_clear_mce(record_id); + if (rc) { + mce_apei_read_done = 1; + return rc; + } + *ubuf += sizeof(struct mce); + + return 0; +} + static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, loff_t *off) { @@ -1506,15 +1551,19 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, return -ENOMEM; mutex_lock(&mce_read_mutex); + + if (!mce_apei_read_done) { + err = __mce_read_apei(&buf, usize); + if (err || buf != ubuf) + goto out; + } + next = rcu_dereference_check_mce(mcelog.next); /* Only supports full reads right now */ - if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) { - mutex_unlock(&mce_read_mutex); - kfree(cpu_tsc); - - return -EINVAL; - } + err = -EINVAL; + if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) + goto out; err = 0; prev = 0; @@ -1562,10 +1611,15 @@ timeout: memset(&mcelog.entry[i], 0, sizeof(struct mce)); } } + + if (err) + err = -EFAULT; + +out: mutex_unlock(&mce_read_mutex); kfree(cpu_tsc); - return err ? -EFAULT : buf - ubuf; + return err ? err : buf - ubuf; } static unsigned int mce_poll(struct file *file, poll_table *wait) @@ -1573,6 +1627,8 @@ static unsigned int mce_poll(struct file *file, poll_table *wait) poll_wait(file, &mce_wait, wait); if (rcu_dereference_check_mce(mcelog.next)) return POLLIN | POLLRDNORM; + if (!mce_apei_read_done && apei_check_mce()) + return POLLIN | POLLRDNORM; return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 62b48e40920..6fcd0936194 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -95,19 +95,20 @@ static void cmci_discover(int banks, int boot) rdmsrl(MSR_IA32_MCx_CTL2(i), val); /* Already owned by someone else? */ - if (val & CMCI_EN) { + if (val & MCI_CTL2_CMCI_EN) { if (test_and_clear_bit(i, owned) && !boot) print_update("SHD", &hdr, i); __clear_bit(i, __get_cpu_var(mce_poll_banks)); continue; } - val |= CMCI_EN | CMCI_THRESHOLD; + val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; + val |= MCI_CTL2_CMCI_EN | CMCI_THRESHOLD; 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 & CMCI_EN) { + if (val & MCI_CTL2_CMCI_EN) { if (!test_and_set_bit(i, owned) && !boot) print_update("CMCI", &hdr, i); __clear_bit(i, __get_cpu_var(mce_poll_banks)); @@ -155,7 +156,7 @@ void cmci_clear(void) continue; /* Disable CMCI */ rdmsrl(MSR_IA32_MCx_CTL2(i), val); - val &= ~(CMCI_EN|CMCI_THRESHOLD_MASK); + val &= ~(MCI_CTL2_CMCI_EN|MCI_CTL2_CMCI_THRESHOLD_MASK); wrmsrl(MSR_IA32_MCx_CTL2(i), val); __clear_bit(i, __get_cpu_var(mce_banks_owned)); } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 81c499eceb2..c2a8b26d4fe 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -34,15 +34,25 @@ /* How long to wait between reporting thermal events */ #define CHECK_INTERVAL (300 * HZ) +#define THERMAL_THROTTLING_EVENT 0 +#define POWER_LIMIT_EVENT 1 + /* - * Current thermal throttling state: + * Current thermal event state: */ -struct thermal_state { - bool is_throttled; - +struct _thermal_state { + bool new_event; + int event; u64 next_check; - unsigned long throttle_count; - unsigned long last_throttle_count; + unsigned long count; + unsigned long last_count; +}; + +struct thermal_state { + struct _thermal_state core_throttle; + struct _thermal_state core_power_limit; + struct _thermal_state package_throttle; + struct _thermal_state package_power_limit; }; static DEFINE_PER_CPU(struct thermal_state, thermal_state); @@ -53,11 +63,13 @@ static u32 lvtthmr_init __read_mostly; #ifdef CONFIG_SYSFS #define define_therm_throt_sysdev_one_ro(_name) \ - static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL) + static SYSDEV_ATTR(_name, 0444, \ + therm_throt_sysdev_show_##_name, \ + NULL) \ -#define define_therm_throt_sysdev_show_func(name) \ +#define define_therm_throt_sysdev_show_func(event, name) \ \ -static ssize_t therm_throt_sysdev_show_##name( \ +static ssize_t therm_throt_sysdev_show_##event##_##name( \ struct sys_device *dev, \ struct sysdev_attribute *attr, \ char *buf) \ @@ -66,30 +78,42 @@ static ssize_t therm_throt_sysdev_show_##name( \ ssize_t ret; \ \ preempt_disable(); /* CPU hotplug */ \ - if (cpu_online(cpu)) \ + if (cpu_online(cpu)) { \ ret = sprintf(buf, "%lu\n", \ - per_cpu(thermal_state, cpu).name); \ - else \ + per_cpu(thermal_state, cpu).event.name); \ + } else \ ret = 0; \ preempt_enable(); \ \ return ret; \ } -define_therm_throt_sysdev_show_func(throttle_count); -define_therm_throt_sysdev_one_ro(throttle_count); +define_therm_throt_sysdev_show_func(core_throttle, count); +define_therm_throt_sysdev_one_ro(core_throttle_count); + +define_therm_throt_sysdev_show_func(core_power_limit, count); +define_therm_throt_sysdev_one_ro(core_power_limit_count); + +define_therm_throt_sysdev_show_func(package_throttle, count); +define_therm_throt_sysdev_one_ro(package_throttle_count); + +define_therm_throt_sysdev_show_func(package_power_limit, count); +define_therm_throt_sysdev_one_ro(package_power_limit_count); static struct attribute *thermal_throttle_attrs[] = { - &attr_throttle_count.attr, + &attr_core_throttle_count.attr, NULL }; -static struct attribute_group thermal_throttle_attr_group = { +static struct attribute_group thermal_attr_group = { .attrs = thermal_throttle_attrs, .name = "thermal_throttle" }; #endif /* CONFIG_SYSFS */ +#define CORE_LEVEL 0 +#define PACKAGE_LEVEL 1 + /*** * therm_throt_process - Process thermal throttling event from interrupt * @curr: Whether the condition is current or not (boolean), since the @@ -106,39 +130,70 @@ static struct attribute_group thermal_throttle_attr_group = { * 1 : Event should be logged further, and a message has been * printed to the syslog. */ -static int therm_throt_process(bool is_throttled) +static int therm_throt_process(bool new_event, int event, int level) { - struct thermal_state *state; - unsigned int this_cpu; - bool was_throttled; + struct _thermal_state *state; + unsigned int this_cpu = smp_processor_id(); + bool old_event; u64 now; + struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu); - this_cpu = smp_processor_id(); now = get_jiffies_64(); - state = &per_cpu(thermal_state, this_cpu); + if (level == CORE_LEVEL) { + if (event == THERMAL_THROTTLING_EVENT) + state = &pstate->core_throttle; + else if (event == POWER_LIMIT_EVENT) + state = &pstate->core_power_limit; + else + return 0; + } else if (level == PACKAGE_LEVEL) { + if (event == THERMAL_THROTTLING_EVENT) + state = &pstate->package_throttle; + else if (event == POWER_LIMIT_EVENT) + state = &pstate->package_power_limit; + else + return 0; + } else + return 0; - was_throttled = state->is_throttled; - state->is_throttled = is_throttled; + old_event = state->new_event; + state->new_event = new_event; - if (is_throttled) - state->throttle_count++; + if (new_event) + state->count++; if (time_before64(now, state->next_check) && - state->throttle_count != state->last_throttle_count) + state->count != state->last_count) return 0; state->next_check = now + CHECK_INTERVAL; - state->last_throttle_count = state->throttle_count; + state->last_count = state->count; /* if we just entered the thermal event */ - if (is_throttled) { - printk(KERN_CRIT "CPU%d: Temperature above threshold, cpu clock throttled (total events = %lu)\n", this_cpu, state->throttle_count); + if (new_event) { + if (event == THERMAL_THROTTLING_EVENT) + printk(KERN_CRIT "CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", + this_cpu, + level == CORE_LEVEL ? "Core" : "Package", + state->count); + else + printk(KERN_CRIT "CPU%d: %s power limit notification (total events = %lu)\n", + this_cpu, + level == CORE_LEVEL ? "Core" : "Package", + state->count); add_taint(TAINT_MACHINE_CHECK); return 1; } - if (was_throttled) { - printk(KERN_INFO "CPU%d: Temperature/speed normal\n", this_cpu); + if (old_event) { + if (event == THERMAL_THROTTLING_EVENT) + printk(KERN_INFO "CPU%d: %s temperature/speed normal\n", + this_cpu, + level == CORE_LEVEL ? "Core" : "Package"); + else + printk(KERN_INFO "CPU%d: %s power limit normal\n", + this_cpu, + level == CORE_LEVEL ? "Core" : "Package"); return 1; } @@ -149,13 +204,32 @@ static int therm_throt_process(bool is_throttled) /* Add/Remove thermal_throttle interface for CPU device: */ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev) { - return sysfs_create_group(&sys_dev->kobj, - &thermal_throttle_attr_group); + int err; + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + + err = sysfs_create_group(&sys_dev->kobj, &thermal_attr_group); + if (err) + return err; + + if (cpu_has(c, X86_FEATURE_PLN)) + err = sysfs_add_file_to_group(&sys_dev->kobj, + &attr_core_power_limit_count.attr, + thermal_attr_group.name); + if (cpu_has(c, X86_FEATURE_PTS)) + err = sysfs_add_file_to_group(&sys_dev->kobj, + &attr_package_throttle_count.attr, + thermal_attr_group.name); + if (cpu_has(c, X86_FEATURE_PLN)) + err = sysfs_add_file_to_group(&sys_dev->kobj, + &attr_package_power_limit_count.attr, + thermal_attr_group.name); + + return err; } static __cpuinit void thermal_throttle_remove_dev(struct sys_device *sys_dev) { - sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group); + sysfs_remove_group(&sys_dev->kobj, &thermal_attr_group); } /* Mutex protecting device creation against CPU hotplug: */ @@ -190,7 +264,7 @@ thermal_throttle_cpu_callback(struct notifier_block *nfb, mutex_unlock(&therm_cpu_lock); break; } - return err ? NOTIFY_BAD : NOTIFY_OK; + return notifier_from_errno(err); } static struct notifier_block thermal_throttle_cpu_notifier __cpuinitdata = @@ -226,14 +300,50 @@ device_initcall(thermal_throttle_init_device); #endif /* CONFIG_SYSFS */ +/* + * Set up the most two significant bit to notify mce log that this thermal + * event type. + * This is a temp solution. May be changed in the future with mce log + * infrasture. + */ +#define CORE_THROTTLED (0) +#define CORE_POWER_LIMIT ((__u64)1 << 62) +#define PACKAGE_THROTTLED ((__u64)2 << 62) +#define PACKAGE_POWER_LIMIT ((__u64)3 << 62) + /* Thermal transition interrupt handler */ static void intel_thermal_interrupt(void) { __u64 msr_val; + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); rdmsrl(MSR_IA32_THERM_STATUS, msr_val); - if (therm_throt_process((msr_val & THERM_STATUS_PROCHOT) != 0)) - mce_log_therm_throt_event(msr_val); + + if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT, + THERMAL_THROTTLING_EVENT, + CORE_LEVEL) != 0) + mce_log_therm_throt_event(CORE_THROTTLED | msr_val); + + if (cpu_has(c, X86_FEATURE_PLN)) + if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, + POWER_LIMIT_EVENT, + CORE_LEVEL) != 0) + mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val); + + if (cpu_has(c, X86_FEATURE_PTS)) { + rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val); + if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT, + THERMAL_THROTTLING_EVENT, + PACKAGE_LEVEL) != 0) + mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val); + if (cpu_has(c, X86_FEATURE_PLN)) + if (therm_throt_process(msr_val & + PACKAGE_THERM_STATUS_POWER_LIMIT, + POWER_LIMIT_EVENT, + PACKAGE_LEVEL) != 0) + mce_log_therm_throt_event(PACKAGE_POWER_LIMIT + | msr_val); + } } static void unexpected_thermal_interrupt(void) @@ -335,8 +445,26 @@ void intel_init_thermal(struct cpuinfo_x86 *c) apic_write(APIC_LVTTHMR, h); rdmsr(MSR_IA32_THERM_INTERRUPT, l, h); - wrmsr(MSR_IA32_THERM_INTERRUPT, - l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h); + if (cpu_has(c, X86_FEATURE_PLN)) + wrmsr(MSR_IA32_THERM_INTERRUPT, + l | (THERM_INT_LOW_ENABLE + | THERM_INT_HIGH_ENABLE | THERM_INT_PLN_ENABLE), h); + else + wrmsr(MSR_IA32_THERM_INTERRUPT, + l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h); + + if (cpu_has(c, X86_FEATURE_PTS)) { + rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h); + if (cpu_has(c, X86_FEATURE_PLN)) + wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, + l | (PACKAGE_THERM_INT_LOW_ENABLE + | PACKAGE_THERM_INT_HIGH_ENABLE + | PACKAGE_THERM_INT_PLN_ENABLE), h); + else + wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, + l | (PACKAGE_THERM_INT_LOW_ENABLE + | PACKAGE_THERM_INT_HIGH_ENABLE), h); + } smp_thermal_vector = intel_thermal_interrupt; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c new file mode 100644 index 00000000000..d944bf6c50e --- /dev/null +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -0,0 +1,56 @@ +/* + * HyperV Detection code. + * + * Copyright (C) 2010, Novell, Inc. + * Author : K. Y. Srinivasan <ksrinivasan@novell.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + */ + +#include <linux/types.h> +#include <linux/module.h> +#include <asm/processor.h> +#include <asm/hypervisor.h> +#include <asm/hyperv.h> +#include <asm/mshyperv.h> + +struct ms_hyperv_info ms_hyperv; +EXPORT_SYMBOL_GPL(ms_hyperv); + +static bool __init ms_hyperv_platform(void) +{ + u32 eax; + u32 hyp_signature[3]; + + if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return false; + + cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS, + &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]); + + return eax >= HYPERV_CPUID_MIN && + eax <= HYPERV_CPUID_MAX && + !memcmp("Microsoft Hv", hyp_signature, 12); +} + +static void __init ms_hyperv_init_platform(void) +{ + /* + * Extract the features and hints + */ + ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES); + ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); + + printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n", + ms_hyperv.features, ms_hyperv.hints); +} + +const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { + .name = "Microsoft HyperV", + .detect = ms_hyperv_platform, + .init_platform = ms_hyperv_init_platform, +}; +EXPORT_SYMBOL(x86_hyper_ms_hyperv); diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 06130b52f01..c5f59d07142 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -632,9 +632,9 @@ static void __init mtrr_print_out_one_result(int i) unsigned long gran_base, chunk_base, lose_base; char gran_factor, chunk_factor, lose_factor; - gran_base = to_size_factor(result[i].gran_sizek, &gran_factor), - chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor), - lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor), + gran_base = to_size_factor(result[i].gran_sizek, &gran_factor); + chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor); + lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor); pr_info("%sgran_size: %ld%c \tchunk_size: %ld%c \t", result[i].bad ? "*BAD*" : " ", diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fd31a441c61..7d28d7d0388 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -433,13 +433,12 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, { unsigned int mask_lo, mask_hi, base_lo, base_hi; unsigned int tmp, hi; - int cpu; /* * get_mtrr doesn't need to update mtrr_state, also it could be called * from any cpu, so try to print it out directly. */ - cpu = get_cpu(); + get_cpu(); rdmsr(MTRRphysMask_MSR(reg), mask_lo, mask_hi); diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 79556bd9b60..01c0f3ee6cc 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -35,6 +35,7 @@ #include <linux/types.h> /* FIXME: kvm_para.h needs this */ +#include <linux/stop_machine.h> #include <linux/kvm_para.h> #include <linux/uaccess.h> #include <linux/module.h> @@ -143,22 +144,28 @@ struct set_mtrr_data { mtrr_type smp_type; }; +static DEFINE_PER_CPU(struct cpu_stop_work, mtrr_work); + /** - * ipi_handler - Synchronisation handler. Executed by "other" CPUs. + * mtrr_work_handler - Synchronisation handler. Executed by "other" CPUs. * @info: pointer to mtrr configuration data * * Returns nothing. */ -static void ipi_handler(void *info) +static int mtrr_work_handler(void *info) { #ifdef CONFIG_SMP struct set_mtrr_data *data = info; unsigned long flags; + atomic_dec(&data->count); + while (!atomic_read(&data->gate)) + cpu_relax(); + local_irq_save(flags); atomic_dec(&data->count); - while (!atomic_read(&data->gate)) + while (atomic_read(&data->gate)) cpu_relax(); /* The master has cleared me to execute */ @@ -173,12 +180,13 @@ static void ipi_handler(void *info) } atomic_dec(&data->count); - while (atomic_read(&data->gate)) + while (!atomic_read(&data->gate)) cpu_relax(); atomic_dec(&data->count); local_irq_restore(flags); #endif + return 0; } static inline int types_compatible(mtrr_type type1, mtrr_type type2) @@ -198,7 +206,7 @@ static inline int types_compatible(mtrr_type type1, mtrr_type type2) * * This is kinda tricky, but fortunately, Intel spelled it out for us cleanly: * - * 1. Send IPI to do the following: + * 1. Queue work to do the following on all processors: * 2. Disable Interrupts * 3. Wait for all procs to do so * 4. Enter no-fill cache mode @@ -215,14 +223,17 @@ static inline int types_compatible(mtrr_type type1, mtrr_type type2) * 15. Enable interrupts. * * What does that mean for us? Well, first we set data.count to the number - * of CPUs. As each CPU disables interrupts, it'll decrement it once. We wait - * until it hits 0 and proceed. We set the data.gate flag and reset data.count. - * Meanwhile, they are waiting for that flag to be set. Once it's set, each + * of CPUs. As each CPU announces that it started the rendezvous handler by + * decrementing the count, We reset data.count and set the data.gate flag + * allowing all the cpu's to proceed with the work. As each cpu disables + * interrupts, it'll decrement data.count once. We wait until it hits 0 and + * proceed. We clear the data.gate flag and reset data.count. Meanwhile, they + * are waiting for that flag to be cleared. Once it's cleared, each * CPU goes through the transition of updating MTRRs. * The CPU vendors may each do it differently, * so we call mtrr_if->set() callback and let them take care of it. * When they're done, they again decrement data->count and wait for data.gate - * to be reset. + * to be set. * When we finish, we wait for data.count to hit 0 and toggle the data.gate flag * Everyone then enables interrupts and we all continue on. * @@ -234,6 +245,9 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ { struct set_mtrr_data data; unsigned long flags; + int cpu; + + preempt_disable(); data.smp_reg = reg; data.smp_base = base; @@ -246,10 +260,15 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ atomic_set(&data.gate, 0); /* Start the ball rolling on other CPUs */ - if (smp_call_function(ipi_handler, &data, 0) != 0) - panic("mtrr: timed out waiting for other CPUs\n"); + for_each_online_cpu(cpu) { + struct cpu_stop_work *work = &per_cpu(mtrr_work, cpu); + + if (cpu == smp_processor_id()) + continue; + + stop_one_cpu_nowait(cpu, mtrr_work_handler, &data, work); + } - local_irq_save(flags); while (atomic_read(&data.count)) cpu_relax(); @@ -259,6 +278,16 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ smp_wmb(); atomic_set(&data.gate, 1); + local_irq_save(flags); + + while (atomic_read(&data.count)) + cpu_relax(); + + /* Ok, reset count and toggle gate */ + atomic_set(&data.count, num_booting_cpus() - 1); + smp_wmb(); + atomic_set(&data.gate, 0); + /* Do our MTRR business */ /* @@ -279,7 +308,7 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ atomic_set(&data.count, num_booting_cpus() - 1); smp_wmb(); - atomic_set(&data.gate, 0); + atomic_set(&data.gate, 1); /* * Wait here for everyone to have seen the gate change @@ -289,6 +318,7 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ cpu_relax(); local_irq_restore(flags); + preempt_enable(); } /** diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index db5bdc8addf..f2da20fda02 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -31,46 +31,51 @@ #include <asm/nmi.h> #include <asm/compat.h> -static u64 perf_event_mask __read_mostly; +#if 0 +#undef wrmsrl +#define wrmsrl(msr, val) \ +do { \ + trace_printk("wrmsrl(%lx, %lx)\n", (unsigned long)(msr),\ + (unsigned long)(val)); \ + native_write_msr((msr), (u32)((u64)(val)), \ + (u32)((u64)(val) >> 32)); \ +} while (0) +#endif -/* The maximal number of PEBS events: */ -#define MAX_PEBS_EVENTS 4 +/* + * best effort, GUP based copy_from_user() that assumes IRQ or NMI context + */ +static unsigned long +copy_from_user_nmi(void *to, const void __user *from, unsigned long n) +{ + unsigned long offset, addr = (unsigned long)from; + int type = in_nmi() ? KM_NMI : KM_IRQ0; + unsigned long size, len = 0; + struct page *page; + void *map; + int ret; -/* The size of a BTS record in bytes: */ -#define BTS_RECORD_SIZE 24 + do { + ret = __get_user_pages_fast(addr, 1, 0, &page); + if (!ret) + break; -/* The size of a per-cpu BTS buffer in bytes: */ -#define BTS_BUFFER_SIZE (BTS_RECORD_SIZE * 2048) + offset = addr & (PAGE_SIZE - 1); + size = min(PAGE_SIZE - offset, n - len); -/* The BTS overflow threshold in bytes from the end of the buffer: */ -#define BTS_OVFL_TH (BTS_RECORD_SIZE * 128) + map = kmap_atomic(page, type); + memcpy(to, map+offset, size); + kunmap_atomic(map, type); + put_page(page); + len += size; + to += size; + addr += size; -/* - * Bits in the debugctlmsr controlling branch tracing. - */ -#define X86_DEBUGCTL_TR (1 << 6) -#define X86_DEBUGCTL_BTS (1 << 7) -#define X86_DEBUGCTL_BTINT (1 << 8) -#define X86_DEBUGCTL_BTS_OFF_OS (1 << 9) -#define X86_DEBUGCTL_BTS_OFF_USR (1 << 10) + } while (len < n); -/* - * A debug store configuration. - * - * We only support architectures that use 64bit fields. - */ -struct debug_store { - u64 bts_buffer_base; - u64 bts_index; - u64 bts_absolute_maximum; - u64 bts_interrupt_threshold; - u64 pebs_buffer_base; - u64 pebs_index; - u64 pebs_absolute_maximum; - u64 pebs_interrupt_threshold; - u64 pebs_event_reset[MAX_PEBS_EVENTS]; -}; + return len; +} struct event_constraint { union { @@ -89,18 +94,42 @@ struct amd_nb { struct event_constraint event_constraints[X86_PMC_IDX_MAX]; }; +#define MAX_LBR_ENTRIES 16 + struct cpu_hw_events { + /* + * Generic x86 PMC bits + */ struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */ unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; - unsigned long interrupts; int enabled; - struct debug_store *ds; int n_events; int n_added; + int n_txn; int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ u64 tags[X86_PMC_IDX_MAX]; struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ + + unsigned int group_flag; + + /* + * Intel DebugStore bits + */ + struct debug_store *ds; + u64 pebs_enabled; + + /* + * Intel LBR bits + */ + int lbr_users; + void *lbr_context; + struct perf_branch_stack lbr_stack; + struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; + + /* + * AMD specific bits + */ struct amd_nb *amd_nb; }; @@ -114,44 +143,75 @@ struct cpu_hw_events { #define EVENT_CONSTRAINT(c, n, m) \ __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n)) +/* + * Constraint on the Event code. + */ #define INTEL_EVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVTSEL_MASK) + EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT) +/* + * Constraint on the Event code + UMask + fixed-mask + * + * filter mask to validate fixed counter events. + * the following filters disqualify for fixed counters: + * - inv + * - edge + * - cnt-mask + * The other filters are supported by fixed counters. + * The any-thread option is supported starting with v3. + */ #define FIXED_EVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, (1ULL << (32+n)), INTEL_ARCH_FIXED_MASK) + EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK) + +/* + * Constraint on the Event code + UMask + */ +#define PEBS_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) #define EVENT_CONSTRAINT_END \ EVENT_CONSTRAINT(0, 0, 0) #define for_each_event_constraint(e, c) \ - for ((e) = (c); (e)->cmask; (e)++) + for ((e) = (c); (e)->weight; (e)++) + +union perf_capabilities { + struct { + u64 lbr_format : 6; + u64 pebs_trap : 1; + u64 pebs_arch_reg : 1; + u64 pebs_format : 4; + u64 smm_freeze : 1; + }; + u64 capabilities; +}; /* * struct x86_pmu - generic x86 pmu */ struct x86_pmu { + /* + * Generic x86 PMC bits + */ const char *name; int version; int (*handle_irq)(struct pt_regs *); void (*disable_all)(void); - void (*enable_all)(void); + void (*enable_all)(int added); void (*enable)(struct perf_event *); void (*disable)(struct perf_event *); + int (*hw_config)(struct perf_event *event); + int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); unsigned eventsel; unsigned perfctr; u64 (*event_map)(int); - u64 (*raw_event)(u64); int max_events; - int num_events; - int num_events_fixed; - int event_bits; - u64 event_mask; + int num_counters; + int num_counters_fixed; + int cntval_bits; + u64 cntval_mask; int apic; u64 max_period; - u64 intel_ctrl; - void (*enable_bts)(u64 config); - void (*disable_bts)(void); - struct event_constraint * (*get_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); @@ -159,11 +219,33 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); struct event_constraint *event_constraints; + void (*quirks)(void); + int perfctr_second_write; int (*cpu_prepare)(int cpu); void (*cpu_starting)(int cpu); void (*cpu_dying)(int cpu); void (*cpu_dead)(int cpu); + + /* + * Intel Arch Perfmon v2+ + */ + u64 intel_ctrl; + union perf_capabilities intel_cap; + + /* + * Intel DebugStore bits + */ + int bts, pebs; + int pebs_record_size; + void (*drain_pebs)(struct pt_regs *regs); + struct event_constraint *pebs_constraints; + + /* + * Intel LBR + */ + unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */ + int lbr_nr; /* hardware stack size */ }; static struct x86_pmu x86_pmu __read_mostly; @@ -198,7 +280,7 @@ static u64 x86_perf_event_update(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - int shift = 64 - x86_pmu.event_bits; + int shift = 64 - x86_pmu.cntval_bits; u64 prev_raw_count, new_raw_count; int idx = hwc->idx; s64 delta; @@ -214,10 +296,10 @@ x86_perf_event_update(struct perf_event *event) * count to the generic event atomically: */ again: - prev_raw_count = atomic64_read(&hwc->prev_count); + prev_raw_count = local64_read(&hwc->prev_count); rdmsrl(hwc->event_base + idx, new_raw_count); - if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count, + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) goto again; @@ -232,8 +314,8 @@ again: delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - atomic64_add(delta, &event->count); - atomic64_sub(delta, &hwc->period_left); + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); return new_raw_count; } @@ -241,33 +323,32 @@ again: static atomic_t active_events; static DEFINE_MUTEX(pmc_reserve_mutex); +#ifdef CONFIG_X86_LOCAL_APIC + static bool reserve_pmc_hardware(void) { -#ifdef CONFIG_X86_LOCAL_APIC int i; if (nmi_watchdog == NMI_LOCAL_APIC) disable_lapic_nmi_watchdog(); - for (i = 0; i < x86_pmu.num_events; i++) { + for (i = 0; i < x86_pmu.num_counters; i++) { if (!reserve_perfctr_nmi(x86_pmu.perfctr + i)) goto perfctr_fail; } - for (i = 0; i < x86_pmu.num_events; i++) { + for (i = 0; i < x86_pmu.num_counters; i++) { if (!reserve_evntsel_nmi(x86_pmu.eventsel + i)) goto eventsel_fail; } -#endif return true; -#ifdef CONFIG_X86_LOCAL_APIC eventsel_fail: for (i--; i >= 0; i--) release_evntsel_nmi(x86_pmu.eventsel + i); - i = x86_pmu.num_events; + i = x86_pmu.num_counters; perfctr_fail: for (i--; i >= 0; i--) @@ -277,128 +358,36 @@ perfctr_fail: enable_lapic_nmi_watchdog(); return false; -#endif } static void release_pmc_hardware(void) { -#ifdef CONFIG_X86_LOCAL_APIC int i; - for (i = 0; i < x86_pmu.num_events; i++) { + for (i = 0; i < x86_pmu.num_counters; i++) { release_perfctr_nmi(x86_pmu.perfctr + i); release_evntsel_nmi(x86_pmu.eventsel + i); } if (nmi_watchdog == NMI_LOCAL_APIC) enable_lapic_nmi_watchdog(); -#endif -} - -static inline bool bts_available(void) -{ - return x86_pmu.enable_bts != NULL; -} - -static void init_debug_store_on_cpu(int cpu) -{ - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; - - if (!ds) - return; - - wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, - (u32)((u64)(unsigned long)ds), - (u32)((u64)(unsigned long)ds >> 32)); -} - -static void fini_debug_store_on_cpu(int cpu) -{ - if (!per_cpu(cpu_hw_events, cpu).ds) - return; - - wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0); -} - -static void release_bts_hardware(void) -{ - int cpu; - - if (!bts_available()) - return; - - get_online_cpus(); - - for_each_online_cpu(cpu) - fini_debug_store_on_cpu(cpu); - - for_each_possible_cpu(cpu) { - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; - - if (!ds) - continue; - - per_cpu(cpu_hw_events, cpu).ds = NULL; - - kfree((void *)(unsigned long)ds->bts_buffer_base); - kfree(ds); - } - - put_online_cpus(); } -static int reserve_bts_hardware(void) -{ - int cpu, err = 0; - - if (!bts_available()) - return 0; - - get_online_cpus(); - - for_each_possible_cpu(cpu) { - struct debug_store *ds; - void *buffer; - - err = -ENOMEM; - buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL); - if (unlikely(!buffer)) - break; - - ds = kzalloc(sizeof(*ds), GFP_KERNEL); - if (unlikely(!ds)) { - kfree(buffer); - break; - } - - ds->bts_buffer_base = (u64)(unsigned long)buffer; - ds->bts_index = ds->bts_buffer_base; - ds->bts_absolute_maximum = - ds->bts_buffer_base + BTS_BUFFER_SIZE; - ds->bts_interrupt_threshold = - ds->bts_absolute_maximum - BTS_OVFL_TH; +#else - per_cpu(cpu_hw_events, cpu).ds = ds; - err = 0; - } +static bool reserve_pmc_hardware(void) { return true; } +static void release_pmc_hardware(void) {} - if (err) - release_bts_hardware(); - else { - for_each_online_cpu(cpu) - init_debug_store_on_cpu(cpu); - } - - put_online_cpus(); +#endif - return err; -} +static int reserve_ds_buffers(void); +static void release_ds_buffers(void); static void hw_perf_event_destroy(struct perf_event *event) { if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) { release_pmc_hardware(); - release_bts_hardware(); + release_ds_buffers(); mutex_unlock(&pmc_reserve_mutex); } } @@ -441,59 +430,16 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr) return 0; } -/* - * Setup the hardware configuration for a given attr_type - */ -static int __hw_perf_event_init(struct perf_event *event) +static int x86_setup_perfctr(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; u64 config; - int err; - - if (!x86_pmu_initialized()) - return -ENODEV; - - err = 0; - if (!atomic_inc_not_zero(&active_events)) { - mutex_lock(&pmc_reserve_mutex); - if (atomic_read(&active_events) == 0) { - if (!reserve_pmc_hardware()) - err = -EBUSY; - else - err = reserve_bts_hardware(); - } - if (!err) - atomic_inc(&active_events); - mutex_unlock(&pmc_reserve_mutex); - } - if (err) - return err; - - event->destroy = hw_perf_event_destroy; - - /* - * Generate PMC IRQs: - * (keep 'enabled' bit clear for now) - */ - hwc->config = ARCH_PERFMON_EVENTSEL_INT; - - hwc->idx = -1; - hwc->last_cpu = -1; - hwc->last_tag = ~0ULL; - - /* - * Count user and OS events unless requested not to. - */ - if (!attr->exclude_user) - hwc->config |= ARCH_PERFMON_EVENTSEL_USR; - if (!attr->exclude_kernel) - hwc->config |= ARCH_PERFMON_EVENTSEL_OS; if (!hwc->sample_period) { hwc->sample_period = x86_pmu.max_period; hwc->last_period = hwc->sample_period; - atomic64_set(&hwc->period_left, hwc->sample_period); + local64_set(&hwc->period_left, hwc->sample_period); } else { /* * If we have a PMU initialized but no APIC @@ -505,16 +451,8 @@ static int __hw_perf_event_init(struct perf_event *event) return -EOPNOTSUPP; } - /* - * Raw hw_event type provide the config in the hw_event structure - */ - if (attr->type == PERF_TYPE_RAW) { - hwc->config |= x86_pmu.raw_event(attr->config); - if ((hwc->config & ARCH_PERFMON_EVENTSEL_ANY) && - perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) - return -EACCES; + if (attr->type == PERF_TYPE_RAW) return 0; - } if (attr->type == PERF_TYPE_HW_CACHE) return set_ext_hw_attr(hwc, attr); @@ -539,11 +477,11 @@ static int __hw_perf_event_init(struct perf_event *event) if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) && (hwc->sample_period == 1)) { /* BTS is not supported by this architecture. */ - if (!bts_available()) + if (!x86_pmu.bts) return -EOPNOTSUPP; /* BTS is currently only allowed for user-mode. */ - if (hwc->config & ARCH_PERFMON_EVENTSEL_OS) + if (!attr->exclude_kernel) return -EOPNOTSUPP; } @@ -552,12 +490,87 @@ static int __hw_perf_event_init(struct perf_event *event) return 0; } +static int x86_pmu_hw_config(struct perf_event *event) +{ + if (event->attr.precise_ip) { + int precise = 0; + + /* Support for constant skid */ + if (x86_pmu.pebs) + precise++; + + /* Support for IP fixup */ + if (x86_pmu.lbr_nr) + precise++; + + if (event->attr.precise_ip > precise) + return -EOPNOTSUPP; + } + + /* + * Generate PMC IRQs: + * (keep 'enabled' bit clear for now) + */ + event->hw.config = ARCH_PERFMON_EVENTSEL_INT; + + /* + * Count user and OS events unless requested not to + */ + if (!event->attr.exclude_user) + event->hw.config |= ARCH_PERFMON_EVENTSEL_USR; + if (!event->attr.exclude_kernel) + event->hw.config |= ARCH_PERFMON_EVENTSEL_OS; + + if (event->attr.type == PERF_TYPE_RAW) + event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK; + + return x86_setup_perfctr(event); +} + +/* + * Setup the hardware configuration for a given attr_type + */ +static int __hw_perf_event_init(struct perf_event *event) +{ + int err; + + if (!x86_pmu_initialized()) + return -ENODEV; + + err = 0; + if (!atomic_inc_not_zero(&active_events)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_read(&active_events) == 0) { + if (!reserve_pmc_hardware()) + err = -EBUSY; + else { + err = reserve_ds_buffers(); + if (err) + release_pmc_hardware(); + } + } + if (!err) + atomic_inc(&active_events); + mutex_unlock(&pmc_reserve_mutex); + } + if (err) + return err; + + event->destroy = hw_perf_event_destroy; + + event->hw.idx = -1; + event->hw.last_cpu = -1; + event->hw.last_tag = ~0ULL; + + return x86_pmu.hw_config(event); +} + static void x86_pmu_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; - for (idx = 0; idx < x86_pmu.num_events; idx++) { + for (idx = 0; idx < x86_pmu.num_counters; idx++) { u64 val; if (!test_bit(idx, cpuc->active_mask)) @@ -587,12 +600,12 @@ void hw_perf_disable(void) x86_pmu.disable_all(); } -static void x86_pmu_enable_all(void) +static void x86_pmu_enable_all(int added) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; - for (idx = 0; idx < x86_pmu.num_events; idx++) { + for (idx = 0; idx < x86_pmu.num_counters; idx++) { struct perf_event *event = cpuc->events[idx]; u64 val; @@ -667,14 +680,14 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) * assign events to counters starting with most * constrained events. */ - wmax = x86_pmu.num_events; + wmax = x86_pmu.num_counters; /* * when fixed event counters are present, * wmax is incremented by 1 to account * for one more choice */ - if (x86_pmu.num_events_fixed) + if (x86_pmu.num_counters_fixed) wmax++; for (w = 1, num = n; num && w <= wmax; w++) { @@ -724,7 +737,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, struct perf_event *event; int n, max_count; - max_count = x86_pmu.num_events + x86_pmu.num_events_fixed; + max_count = x86_pmu.num_counters + x86_pmu.num_counters_fixed; /* current number of events already accepted */ n = cpuc->n_events; @@ -795,7 +808,7 @@ void hw_perf_enable(void) struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct perf_event *event; struct hw_perf_event *hwc; - int i; + int i, added = cpuc->n_added; if (!x86_pmu_initialized()) return; @@ -847,19 +860,20 @@ void hw_perf_enable(void) cpuc->enabled = 1; barrier(); - x86_pmu.enable_all(); + x86_pmu.enable_all(added); } -static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc) +static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, + u64 enable_mask) { - (void)checking_wrmsrl(hwc->config_base + hwc->idx, - hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE); + wrmsrl(hwc->config_base + hwc->idx, hwc->config | enable_mask); } static inline void x86_pmu_disable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - (void)checking_wrmsrl(hwc->config_base + hwc->idx, hwc->config); + + wrmsrl(hwc->config_base + hwc->idx, hwc->config); } static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); @@ -872,9 +886,9 @@ static int x86_perf_event_set_period(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - s64 left = atomic64_read(&hwc->period_left); + s64 left = local64_read(&hwc->period_left); s64 period = hwc->sample_period; - int err, ret = 0, idx = hwc->idx; + int ret = 0, idx = hwc->idx; if (idx == X86_PMC_IDX_FIXED_BTS) return 0; @@ -884,14 +898,14 @@ x86_perf_event_set_period(struct perf_event *event) */ if (unlikely(left <= -period)) { left = period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (unlikely(left <= 0)) { left += period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } @@ -910,10 +924,19 @@ x86_perf_event_set_period(struct perf_event *event) * The hw event starts counting from this event offset, * mark it to be able to extra future deltas: */ - atomic64_set(&hwc->prev_count, (u64)-left); + local64_set(&hwc->prev_count, (u64)-left); + + wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask); - err = checking_wrmsrl(hwc->event_base + idx, - (u64)(-left) & x86_pmu.event_mask); + /* + * Due to erratum on certan cpu we need + * a second write to be sure the register + * is updated properly + */ + if (x86_pmu.perfctr_second_write) { + wrmsrl(hwc->event_base + idx, + (u64)(-left) & x86_pmu.cntval_mask); + } perf_event_update_userpage(event); @@ -924,7 +947,8 @@ static void x86_pmu_enable_event(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); if (cpuc->enabled) - __x86_pmu_enable_event(&event->hw); + __x86_pmu_enable_event(&event->hw, + ARCH_PERFMON_EVENTSEL_ENABLE); } /* @@ -950,7 +974,15 @@ static int x86_pmu_enable(struct perf_event *event) if (n < 0) return n; - ret = x86_schedule_events(cpuc, n, assign); + /* + * If group events scheduling transaction was started, + * skip the schedulability test here, it will be peformed + * at commit time(->commit_txn) as a whole + */ + if (cpuc->group_flag & PERF_EVENT_TXN) + goto out; + + ret = x86_pmu.schedule_events(cpuc, n, assign); if (ret) return ret; /* @@ -959,8 +991,10 @@ static int x86_pmu_enable(struct perf_event *event) */ memcpy(cpuc->assign, assign, n*sizeof(int)); +out: cpuc->n_events = n; cpuc->n_added += n - n0; + cpuc->n_txn += n - n0; return 0; } @@ -991,11 +1025,12 @@ static void x86_pmu_unthrottle(struct perf_event *event) void perf_event_print_debug(void) { u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed; + u64 pebs; struct cpu_hw_events *cpuc; unsigned long flags; int cpu, idx; - if (!x86_pmu.num_events) + if (!x86_pmu.num_counters) return; local_irq_save(flags); @@ -1008,16 +1043,18 @@ void perf_event_print_debug(void) rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status); rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow); rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed); + rdmsrl(MSR_IA32_PEBS_ENABLE, pebs); pr_info("\n"); pr_info("CPU#%d: ctrl: %016llx\n", cpu, ctrl); pr_info("CPU#%d: status: %016llx\n", cpu, status); pr_info("CPU#%d: overflow: %016llx\n", cpu, overflow); pr_info("CPU#%d: fixed: %016llx\n", cpu, fixed); + pr_info("CPU#%d: pebs: %016llx\n", cpu, pebs); } - pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask); + pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask); - for (idx = 0; idx < x86_pmu.num_events; idx++) { + for (idx = 0; idx < x86_pmu.num_counters; idx++) { rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl); rdmsrl(x86_pmu.perfctr + idx, pmc_count); @@ -1030,7 +1067,7 @@ void perf_event_print_debug(void) pr_info("CPU#%d: gen-PMC%d left: %016llx\n", cpu, idx, prev_left); } - for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) { + for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) { rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count); pr_info("CPU#%d: fixed-PMC%d count: %016llx\n", @@ -1064,6 +1101,14 @@ static void x86_pmu_disable(struct perf_event *event) struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int i; + /* + * If we're called during a txn, we don't need to do anything. + * The events never got scheduled and ->cancel_txn will truncate + * the event_list. + */ + if (cpuc->group_flag & PERF_EVENT_TXN) + return; + x86_pmu_stop(event); for (i = 0; i < cpuc->n_events; i++) { @@ -1095,7 +1140,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) cpuc = &__get_cpu_var(cpu_hw_events); - for (idx = 0; idx < x86_pmu.num_events; idx++) { + for (idx = 0; idx < x86_pmu.num_counters; idx++) { if (!test_bit(idx, cpuc->active_mask)) continue; @@ -1103,7 +1148,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) hwc = &event->hw; val = x86_perf_event_update(event); - if (val & (1ULL << (x86_pmu.event_bits - 1))) + if (val & (1ULL << (x86_pmu.cntval_bits - 1))) continue; /* @@ -1146,7 +1191,6 @@ void set_perf_event_pending(void) void perf_events_lapic_init(void) { -#ifdef CONFIG_X86_LOCAL_APIC if (!x86_pmu.apic || !x86_pmu_initialized()) return; @@ -1154,7 +1198,6 @@ void perf_events_lapic_init(void) * Always use NMI for PMU */ apic_write(APIC_LVTPC, APIC_DM_NMI); -#endif } static int __kprobes @@ -1178,9 +1221,7 @@ perf_event_nmi_handler(struct notifier_block *self, regs = args->regs; -#ifdef CONFIG_X86_LOCAL_APIC apic_write(APIC_LVTPC, APIC_DM_NMI); -#endif /* * Can't rely on the handled return value to say it was our NMI, two * events could trigger 'simultaneously' raising two back-to-back NMIs. @@ -1217,118 +1258,11 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) return &unconstrained; } -static int x86_event_sched_in(struct perf_event *event, - struct perf_cpu_context *cpuctx) -{ - int ret = 0; - - event->state = PERF_EVENT_STATE_ACTIVE; - event->oncpu = smp_processor_id(); - event->tstamp_running += event->ctx->time - event->tstamp_stopped; - - if (!is_x86_event(event)) - ret = event->pmu->enable(event); - - if (!ret && !is_software_event(event)) - cpuctx->active_oncpu++; - - if (!ret && event->attr.exclusive) - cpuctx->exclusive = 1; - - return ret; -} - -static void x86_event_sched_out(struct perf_event *event, - struct perf_cpu_context *cpuctx) -{ - event->state = PERF_EVENT_STATE_INACTIVE; - event->oncpu = -1; - - if (!is_x86_event(event)) - event->pmu->disable(event); - - event->tstamp_running -= event->ctx->time - event->tstamp_stopped; - - if (!is_software_event(event)) - cpuctx->active_oncpu--; - - if (event->attr.exclusive || !cpuctx->active_oncpu) - cpuctx->exclusive = 0; -} - -/* - * Called to enable a whole group of events. - * Returns 1 if the group was enabled, or -EAGAIN if it could not be. - * Assumes the caller has disabled interrupts and has - * frozen the PMU with hw_perf_save_disable. - * - * called with PMU disabled. If successful and return value 1, - * then guaranteed to call perf_enable() and hw_perf_enable() - */ -int hw_perf_group_sched_in(struct perf_event *leader, - struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct perf_event *sub; - int assign[X86_PMC_IDX_MAX]; - int n0, n1, ret; - - /* n0 = total number of events */ - n0 = collect_events(cpuc, leader, true); - if (n0 < 0) - return n0; - - ret = x86_schedule_events(cpuc, n0, assign); - if (ret) - return ret; - - ret = x86_event_sched_in(leader, cpuctx); - if (ret) - return ret; - - n1 = 1; - list_for_each_entry(sub, &leader->sibling_list, group_entry) { - if (sub->state > PERF_EVENT_STATE_OFF) { - ret = x86_event_sched_in(sub, cpuctx); - if (ret) - goto undo; - ++n1; - } - } - /* - * copy new assignment, now we know it is possible - * will be used by hw_perf_enable() - */ - memcpy(cpuc->assign, assign, n0*sizeof(int)); - - cpuc->n_events = n0; - cpuc->n_added += n1; - ctx->nr_active += n1; - - /* - * 1 means successful and events are active - * This is not quite true because we defer - * actual activation until hw_perf_enable() but - * this way we* ensure caller won't try to enable - * individual events - */ - return 1; -undo: - x86_event_sched_out(leader, cpuctx); - n0 = 1; - list_for_each_entry(sub, &leader->sibling_list, group_entry) { - if (sub->state == PERF_EVENT_STATE_ACTIVE) { - x86_event_sched_out(sub, cpuctx); - if (++n0 == n1) - break; - } - } - return ret; -} - #include "perf_event_amd.c" #include "perf_event_p6.c" +#include "perf_event_p4.c" +#include "perf_event_intel_lbr.c" +#include "perf_event_intel_ds.c" #include "perf_event_intel.c" static int __cpuinit @@ -1402,48 +1336,50 @@ void __init init_hw_perf_events(void) pr_cont("%s PMU driver.\n", x86_pmu.name); - if (x86_pmu.num_events > X86_PMC_MAX_GENERIC) { + if (x86_pmu.quirks) + x86_pmu.quirks(); + + if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) { WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!", - x86_pmu.num_events, X86_PMC_MAX_GENERIC); - x86_pmu.num_events = X86_PMC_MAX_GENERIC; + x86_pmu.num_counters, X86_PMC_MAX_GENERIC); + x86_pmu.num_counters = X86_PMC_MAX_GENERIC; } - perf_event_mask = (1 << x86_pmu.num_events) - 1; - perf_max_events = x86_pmu.num_events; + x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1; + perf_max_events = x86_pmu.num_counters; - if (x86_pmu.num_events_fixed > X86_PMC_MAX_FIXED) { + if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) { WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!", - x86_pmu.num_events_fixed, X86_PMC_MAX_FIXED); - x86_pmu.num_events_fixed = X86_PMC_MAX_FIXED; + x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED); + x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED; } - perf_event_mask |= - ((1LL << x86_pmu.num_events_fixed)-1) << X86_PMC_IDX_FIXED; - x86_pmu.intel_ctrl = perf_event_mask; + x86_pmu.intel_ctrl |= + ((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED; perf_events_lapic_init(); register_die_notifier(&perf_event_nmi_notifier); unconstrained = (struct event_constraint) - __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_events) - 1, - 0, x86_pmu.num_events); + __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1, + 0, x86_pmu.num_counters); if (x86_pmu.event_constraints) { for_each_event_constraint(c, x86_pmu.event_constraints) { - if (c->cmask != INTEL_ARCH_FIXED_MASK) + if (c->cmask != X86_RAW_EVENT_MASK) continue; - c->idxmsk64 |= (1ULL << x86_pmu.num_events) - 1; - c->weight += x86_pmu.num_events; + c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; + c->weight += x86_pmu.num_counters; } } pr_info("... version: %d\n", x86_pmu.version); - pr_info("... bit width: %d\n", x86_pmu.event_bits); - pr_info("... generic registers: %d\n", x86_pmu.num_events); - pr_info("... value mask: %016Lx\n", x86_pmu.event_mask); + pr_info("... bit width: %d\n", x86_pmu.cntval_bits); + pr_info("... generic registers: %d\n", x86_pmu.num_counters); + pr_info("... value mask: %016Lx\n", x86_pmu.cntval_mask); pr_info("... max period: %016Lx\n", x86_pmu.max_period); - pr_info("... fixed-purpose events: %d\n", x86_pmu.num_events_fixed); - pr_info("... event mask: %016Lx\n", perf_event_mask); + pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed); + pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl); perf_cpu_notifier(x86_pmu_notifier); } @@ -1453,6 +1389,67 @@ static inline void x86_pmu_read(struct perf_event *event) x86_perf_event_update(event); } +/* + * Start group events scheduling transaction + * Set the flag to make pmu::enable() not perform the + * schedulability test, it will be performed at commit time + */ +static void x86_pmu_start_txn(const struct pmu *pmu) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + cpuc->group_flag |= PERF_EVENT_TXN; + cpuc->n_txn = 0; +} + +/* + * Stop group events scheduling transaction + * Clear the flag and pmu::enable() will perform the + * schedulability test. + */ +static void x86_pmu_cancel_txn(const struct pmu *pmu) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + cpuc->group_flag &= ~PERF_EVENT_TXN; + /* + * Truncate the collected events. + */ + cpuc->n_added -= cpuc->n_txn; + cpuc->n_events -= cpuc->n_txn; +} + +/* + * Commit group events scheduling transaction + * Perform the group schedulability test as a whole + * Return 0 if success + */ +static int x86_pmu_commit_txn(const struct pmu *pmu) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int assign[X86_PMC_IDX_MAX]; + int n, ret; + + n = cpuc->n_events; + + if (!x86_pmu_initialized()) + return -EAGAIN; + + ret = x86_pmu.schedule_events(cpuc, n, assign); + if (ret) + return ret; + + /* + * copy new assignment, now we know it is possible + * will be used by hw_perf_enable() + */ + memcpy(cpuc->assign, assign, n*sizeof(int)); + + cpuc->group_flag &= ~PERF_EVENT_TXN; + + return 0; +} + static const struct pmu pmu = { .enable = x86_pmu_enable, .disable = x86_pmu_disable, @@ -1460,9 +1457,38 @@ static const struct pmu pmu = { .stop = x86_pmu_stop, .read = x86_pmu_read, .unthrottle = x86_pmu_unthrottle, + .start_txn = x86_pmu_start_txn, + .cancel_txn = x86_pmu_cancel_txn, + .commit_txn = x86_pmu_commit_txn, }; /* + * validate that we can schedule this event + */ +static int validate_event(struct perf_event *event) +{ + struct cpu_hw_events *fake_cpuc; + struct event_constraint *c; + int ret = 0; + + fake_cpuc = kmalloc(sizeof(*fake_cpuc), GFP_KERNEL | __GFP_ZERO); + if (!fake_cpuc) + return -ENOMEM; + + c = x86_pmu.get_event_constraints(fake_cpuc, event); + + if (!c || !c->weight) + ret = -ENOSPC; + + if (x86_pmu.put_event_constraints) + x86_pmu.put_event_constraints(fake_cpuc, event); + + kfree(fake_cpuc); + + return ret; +} + +/* * validate a single event group * * validation include: @@ -1502,7 +1528,7 @@ static int validate_group(struct perf_event *event) fake_cpuc->n_events = n; - ret = x86_schedule_events(fake_cpuc, n, NULL); + ret = x86_pmu.schedule_events(fake_cpuc, n, NULL); out_free: kfree(fake_cpuc); @@ -1527,6 +1553,8 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) if (event->group_leader != event) err = validate_group(event); + else + err = validate_event(event); event->pmu = tmp; } @@ -1574,8 +1602,7 @@ static void backtrace_address(void *data, unsigned long addr, int reliable) { struct perf_callchain_entry *entry = data; - if (reliable) - callchain_store(entry, addr); + callchain_store(entry, addr); } static const struct stacktrace_ops backtrace_ops = { @@ -1586,8 +1613,6 @@ static const struct stacktrace_ops backtrace_ops = { .walk_stack = print_context_stack_bp, }; -#include "../dumpstack.h" - static void perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry) { @@ -1597,41 +1622,6 @@ perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry) dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry); } -/* - * best effort, GUP based copy_from_user() that assumes IRQ or NMI context - */ -static unsigned long -copy_from_user_nmi(void *to, const void __user *from, unsigned long n) -{ - unsigned long offset, addr = (unsigned long)from; - int type = in_nmi() ? KM_NMI : KM_IRQ0; - unsigned long size, len = 0; - struct page *page; - void *map; - int ret; - - do { - ret = __get_user_pages_fast(addr, 1, 0, &page); - if (!ret) - break; - - offset = addr & (PAGE_SIZE - 1); - size = min(PAGE_SIZE - offset, n - len); - - map = kmap_atomic(page, type); - memcpy(to, map+offset, size); - kunmap_atomic(map, type); - put_page(page); - - len += size; - to += size; - addr += size; - - } while (len < n); - - return len; -} - #ifdef CONFIG_COMPAT static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) @@ -1727,6 +1717,11 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) { struct perf_callchain_entry *entry; + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + /* TODO: We don't support guest os callchain now */ + return NULL; + } + if (in_nmi()) entry = &__get_cpu_var(pmc_nmi_entry); else @@ -1739,14 +1734,36 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return entry; } -void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip) +unsigned long perf_instruction_pointer(struct pt_regs *regs) { - regs->ip = ip; - /* - * perf_arch_fetch_caller_regs adds another call, we need to increment - * the skip level - */ - regs->bp = rewind_frame_pointer(skip + 1); - regs->cs = __KERNEL_CS; - local_save_flags(regs->flags); + unsigned long ip; + + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) + ip = perf_guest_cbs->get_guest_ip(); + else + ip = instruction_pointer(regs); + + return ip; +} + +unsigned long perf_misc_flags(struct pt_regs *regs) +{ + int misc = 0; + + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + if (perf_guest_cbs->is_user_mode()) + misc |= PERF_RECORD_MISC_GUEST_USER; + else + misc |= PERF_RECORD_MISC_GUEST_KERNEL; + } else { + if (user_mode(regs)) + misc |= PERF_RECORD_MISC_USER; + else + misc |= PERF_RECORD_MISC_KERNEL; + } + + if (regs->flags & PERF_EFLAGS_EXACT) + misc |= PERF_RECORD_MISC_EXACT_IP; + + return misc; } diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index db6f7d4056e..c2897b7b4a3 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -2,7 +2,7 @@ static DEFINE_RAW_SPINLOCK(amd_nb_lock); -static __initconst u64 amd_hw_cache_event_ids +static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -102,8 +102,8 @@ static const u64 amd_perfmon_event_map[] = [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0080, [PERF_COUNT_HW_CACHE_MISSES] = 0x0081, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, - [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, }; static u64 amd_pmu_event_map(int hw_event) @@ -111,22 +111,19 @@ static u64 amd_pmu_event_map(int hw_event) return amd_perfmon_event_map[hw_event]; } -static u64 amd_pmu_raw_event(u64 hw_event) +static int amd_pmu_hw_config(struct perf_event *event) { -#define K7_EVNTSEL_EVENT_MASK 0xF000000FFULL -#define K7_EVNTSEL_UNIT_MASK 0x00000FF00ULL -#define K7_EVNTSEL_EDGE_MASK 0x000040000ULL -#define K7_EVNTSEL_INV_MASK 0x000800000ULL -#define K7_EVNTSEL_REG_MASK 0x0FF000000ULL - -#define K7_EVNTSEL_MASK \ - (K7_EVNTSEL_EVENT_MASK | \ - K7_EVNTSEL_UNIT_MASK | \ - K7_EVNTSEL_EDGE_MASK | \ - K7_EVNTSEL_INV_MASK | \ - K7_EVNTSEL_REG_MASK) - - return hw_event & K7_EVNTSEL_MASK; + int ret = x86_pmu_hw_config(event); + + if (ret) + return ret; + + if (event->attr.type != PERF_TYPE_RAW) + return 0; + + event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK; + + return 0; } /* @@ -165,7 +162,7 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc, * be removed on one CPU at a time AND PMU is disabled * when we come here */ - for (i = 0; i < x86_pmu.num_events; i++) { + for (i = 0; i < x86_pmu.num_counters; i++) { if (nb->owners[i] == event) { cmpxchg(nb->owners+i, event, NULL); break; @@ -215,7 +212,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) struct hw_perf_event *hwc = &event->hw; struct amd_nb *nb = cpuc->amd_nb; struct perf_event *old = NULL; - int max = x86_pmu.num_events; + int max = x86_pmu.num_counters; int i, j, k = -1; /* @@ -293,7 +290,7 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id) /* * initialize all possible NB constraints */ - for (i = 0; i < x86_pmu.num_events; i++) { + for (i = 0; i < x86_pmu.num_counters; i++) { __set_bit(i, nb->event_constraints[i].idxmsk); nb->event_constraints[i].weight = 1; } @@ -371,21 +368,22 @@ static void amd_pmu_cpu_dead(int cpu) raw_spin_unlock(&amd_nb_lock); } -static __initconst struct x86_pmu amd_pmu = { +static __initconst const struct x86_pmu amd_pmu = { .name = "AMD", .handle_irq = x86_pmu_handle_irq, .disable_all = x86_pmu_disable_all, .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, .disable = x86_pmu_disable_event, + .hw_config = amd_pmu_hw_config, + .schedule_events = x86_schedule_events, .eventsel = MSR_K7_EVNTSEL0, .perfctr = MSR_K7_PERFCTR0, .event_map = amd_pmu_event_map, - .raw_event = amd_pmu_raw_event, .max_events = ARRAY_SIZE(amd_perfmon_event_map), - .num_events = 4, - .event_bits = 48, - .event_mask = (1ULL << 48) - 1, + .num_counters = 4, + .cntval_bits = 48, + .cntval_mask = (1ULL << 48) - 1, .apic = 1, /* use highest bit to detect overflow */ .max_period = (1ULL << 47) - 1, diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 9c794ac8783..214ac860ebe 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -72,6 +72,7 @@ static struct event_constraint intel_westmere_event_constraints[] = INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */ INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */ INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */ + INTEL_EVENT_CONSTRAINT(0xb3, 0x1), /* SNOOPQ_REQUEST_OUTSTANDING */ EVENT_CONSTRAINT_END }; @@ -88,7 +89,7 @@ static u64 intel_pmu_event_map(int hw_event) return intel_perfmon_event_map[hw_event]; } -static __initconst u64 westmere_hw_cache_event_ids +static __initconst const u64 westmere_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -179,7 +180,7 @@ static __initconst u64 westmere_hw_cache_event_ids }, }; -static __initconst u64 nehalem_hw_cache_event_ids +static __initconst const u64 nehalem_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -270,7 +271,7 @@ static __initconst u64 nehalem_hw_cache_event_ids }, }; -static __initconst u64 core2_hw_cache_event_ids +static __initconst const u64 core2_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -361,7 +362,7 @@ static __initconst u64 core2_hw_cache_event_ids }, }; -static __initconst u64 atom_hw_cache_event_ids +static __initconst const u64 atom_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -452,60 +453,6 @@ static __initconst u64 atom_hw_cache_event_ids }, }; -static u64 intel_pmu_raw_event(u64 hw_event) -{ -#define CORE_EVNTSEL_EVENT_MASK 0x000000FFULL -#define CORE_EVNTSEL_UNIT_MASK 0x0000FF00ULL -#define CORE_EVNTSEL_EDGE_MASK 0x00040000ULL -#define CORE_EVNTSEL_INV_MASK 0x00800000ULL -#define CORE_EVNTSEL_REG_MASK 0xFF000000ULL - -#define CORE_EVNTSEL_MASK \ - (INTEL_ARCH_EVTSEL_MASK | \ - INTEL_ARCH_UNIT_MASK | \ - INTEL_ARCH_EDGE_MASK | \ - INTEL_ARCH_INV_MASK | \ - INTEL_ARCH_CNT_MASK) - - return hw_event & CORE_EVNTSEL_MASK; -} - -static void intel_pmu_enable_bts(u64 config) -{ - unsigned long debugctlmsr; - - debugctlmsr = get_debugctlmsr(); - - debugctlmsr |= X86_DEBUGCTL_TR; - debugctlmsr |= X86_DEBUGCTL_BTS; - debugctlmsr |= X86_DEBUGCTL_BTINT; - - if (!(config & ARCH_PERFMON_EVENTSEL_OS)) - debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS; - - if (!(config & ARCH_PERFMON_EVENTSEL_USR)) - debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR; - - update_debugctlmsr(debugctlmsr); -} - -static void intel_pmu_disable_bts(void) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - unsigned long debugctlmsr; - - if (!cpuc->ds) - return; - - debugctlmsr = get_debugctlmsr(); - - debugctlmsr &= - ~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT | - X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR); - - update_debugctlmsr(debugctlmsr); -} - static void intel_pmu_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -514,12 +461,17 @@ static void intel_pmu_disable_all(void) if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) intel_pmu_disable_bts(); + + intel_pmu_pebs_disable_all(); + intel_pmu_lbr_disable_all(); } -static void intel_pmu_enable_all(void) +static void intel_pmu_enable_all(int added) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + intel_pmu_pebs_enable_all(); + intel_pmu_lbr_enable_all(); wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl); if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) { @@ -533,6 +485,42 @@ static void intel_pmu_enable_all(void) } } +/* + * Workaround for: + * Intel Errata AAK100 (model 26) + * Intel Errata AAP53 (model 30) + * Intel Errata BD53 (model 44) + * + * These chips need to be 'reset' when adding counters by programming + * the magic three (non counting) events 0x4300D2, 0x4300B1 and 0x4300B5 + * either in sequence on the same PMC or on different PMCs. + */ +static void intel_pmu_nhm_enable_all(int added) +{ + if (added) { + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int i; + + wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 0, 0x4300D2); + wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x4300B1); + wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x4300B5); + + wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x3); + wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0); + + for (i = 0; i < 3; i++) { + struct perf_event *event = cpuc->events[i]; + + if (!event) + continue; + + __x86_pmu_enable_event(&event->hw, + ARCH_PERFMON_EVENTSEL_ENABLE); + } + } + intel_pmu_enable_all(added); +} + static inline u64 intel_pmu_get_status(void) { u64 status; @@ -547,8 +535,7 @@ static inline void intel_pmu_ack_status(u64 ack) wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack); } -static inline void -intel_pmu_disable_fixed(struct hw_perf_event *hwc) +static void intel_pmu_disable_fixed(struct hw_perf_event *hwc) { int idx = hwc->idx - X86_PMC_IDX_FIXED; u64 ctrl_val, mask; @@ -557,71 +544,10 @@ intel_pmu_disable_fixed(struct hw_perf_event *hwc) rdmsrl(hwc->config_base, ctrl_val); ctrl_val &= ~mask; - (void)checking_wrmsrl(hwc->config_base, ctrl_val); -} - -static void intel_pmu_drain_bts_buffer(void) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct debug_store *ds = cpuc->ds; - struct bts_record { - u64 from; - u64 to; - u64 flags; - }; - struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS]; - struct bts_record *at, *top; - struct perf_output_handle handle; - struct perf_event_header header; - struct perf_sample_data data; - struct pt_regs regs; - - if (!event) - return; - - if (!ds) - return; - - at = (struct bts_record *)(unsigned long)ds->bts_buffer_base; - top = (struct bts_record *)(unsigned long)ds->bts_index; - - if (top <= at) - return; - - ds->bts_index = ds->bts_buffer_base; - - perf_sample_data_init(&data, 0); - - data.period = event->hw.last_period; - regs.ip = 0; - - /* - * Prepare a generic sample, i.e. fill in the invariant fields. - * We will overwrite the from and to address before we output - * the sample. - */ - perf_prepare_sample(&header, &data, event, ®s); - - if (perf_output_begin(&handle, event, - header.size * (top - at), 1, 1)) - return; - - for (; at < top; at++) { - data.ip = at->from; - data.addr = at->to; - - perf_output_sample(&handle, &header, &data, event); - } - - perf_output_end(&handle); - - /* There's new data available. */ - event->hw.interrupts++; - event->pending_kill = POLL_IN; + wrmsrl(hwc->config_base, ctrl_val); } -static inline void -intel_pmu_disable_event(struct perf_event *event) +static void intel_pmu_disable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -637,14 +563,15 @@ intel_pmu_disable_event(struct perf_event *event) } x86_pmu_disable_event(event); + + if (unlikely(event->attr.precise_ip)) + intel_pmu_pebs_disable(event); } -static inline void -intel_pmu_enable_fixed(struct hw_perf_event *hwc) +static void intel_pmu_enable_fixed(struct hw_perf_event *hwc) { int idx = hwc->idx - X86_PMC_IDX_FIXED; u64 ctrl_val, bits, mask; - int err; /* * Enable IRQ generation (0x8), @@ -669,7 +596,7 @@ intel_pmu_enable_fixed(struct hw_perf_event *hwc) rdmsrl(hwc->config_base, ctrl_val); ctrl_val &= ~mask; ctrl_val |= bits; - err = checking_wrmsrl(hwc->config_base, ctrl_val); + wrmsrl(hwc->config_base, ctrl_val); } static void intel_pmu_enable_event(struct perf_event *event) @@ -689,7 +616,10 @@ static void intel_pmu_enable_event(struct perf_event *event) return; } - __x86_pmu_enable_event(hwc); + if (unlikely(event->attr.precise_ip)) + intel_pmu_pebs_enable(event); + + __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); } /* @@ -708,20 +638,20 @@ static void intel_pmu_reset(void) unsigned long flags; int idx; - if (!x86_pmu.num_events) + if (!x86_pmu.num_counters) return; local_irq_save(flags); printk("clearing PMU state on CPU#%d\n", smp_processor_id()); - for (idx = 0; idx < x86_pmu.num_events; idx++) { + for (idx = 0; idx < x86_pmu.num_counters; idx++) { checking_wrmsrl(x86_pmu.eventsel + idx, 0ull); checking_wrmsrl(x86_pmu.perfctr + idx, 0ull); } - for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) { + for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull); - } + if (ds) ds->bts_index = ds->bts_buffer_base; @@ -747,7 +677,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) intel_pmu_drain_bts_buffer(); status = intel_pmu_get_status(); if (!status) { - intel_pmu_enable_all(); + intel_pmu_enable_all(0); return 0; } @@ -762,6 +692,15 @@ again: inc_irq_stat(apic_perf_irqs); ack = status; + + intel_pmu_lbr_read(); + + /* + * PEBS overflow sets bit 62 in the global status register + */ + if (__test_and_clear_bit(62, (unsigned long *)&status)) + x86_pmu.drain_pebs(regs); + for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { struct perf_event *event = cpuc->events[bit]; @@ -787,26 +726,22 @@ again: goto again; done: - intel_pmu_enable_all(); + intel_pmu_enable_all(0); return 1; } -static struct event_constraint bts_constraint = - EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0); - static struct event_constraint * -intel_special_constraints(struct perf_event *event) +intel_bts_constraints(struct perf_event *event) { - unsigned int hw_event; - - hw_event = event->hw.config & INTEL_ARCH_EVENT_MASK; + struct hw_perf_event *hwc = &event->hw; + unsigned int hw_event, bts_event; - if (unlikely((hw_event == - x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) && - (event->hw.sample_period == 1))) { + hw_event = hwc->config & INTEL_ARCH_EVENT_MASK; + bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS); + if (unlikely(hw_event == bts_event && hwc->sample_period == 1)) return &bts_constraint; - } + return NULL; } @@ -815,24 +750,53 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event { struct event_constraint *c; - c = intel_special_constraints(event); + c = intel_bts_constraints(event); + if (c) + return c; + + c = intel_pebs_constraints(event); if (c) return c; return x86_get_event_constraints(cpuc, event); } -static __initconst struct x86_pmu core_pmu = { +static int intel_pmu_hw_config(struct perf_event *event) +{ + int ret = x86_pmu_hw_config(event); + + if (ret) + return ret; + + if (event->attr.type != PERF_TYPE_RAW) + return 0; + + if (!(event->attr.config & ARCH_PERFMON_EVENTSEL_ANY)) + return 0; + + if (x86_pmu.version < 3) + return -EINVAL; + + if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) + return -EACCES; + + event->hw.config |= ARCH_PERFMON_EVENTSEL_ANY; + + return 0; +} + +static __initconst const struct x86_pmu core_pmu = { .name = "core", .handle_irq = x86_pmu_handle_irq, .disable_all = x86_pmu_disable_all, .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, .disable = x86_pmu_disable_event, + .hw_config = x86_pmu_hw_config, + .schedule_events = x86_schedule_events, .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, .perfctr = MSR_ARCH_PERFMON_PERFCTR0, .event_map = intel_pmu_event_map, - .raw_event = intel_pmu_raw_event, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, /* @@ -845,17 +809,32 @@ static __initconst struct x86_pmu core_pmu = { .event_constraints = intel_core_event_constraints, }; -static __initconst struct x86_pmu intel_pmu = { +static void intel_pmu_cpu_starting(int cpu) +{ + init_debug_store_on_cpu(cpu); + /* + * Deal with CPUs that don't clear their LBRs on power-up. + */ + intel_pmu_lbr_reset(); +} + +static void intel_pmu_cpu_dying(int cpu) +{ + fini_debug_store_on_cpu(cpu); +} + +static __initconst const struct x86_pmu intel_pmu = { .name = "Intel", .handle_irq = intel_pmu_handle_irq, .disable_all = intel_pmu_disable_all, .enable_all = intel_pmu_enable_all, .enable = intel_pmu_enable_event, .disable = intel_pmu_disable_event, + .hw_config = intel_pmu_hw_config, + .schedule_events = x86_schedule_events, .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, .perfctr = MSR_ARCH_PERFMON_PERFCTR0, .event_map = intel_pmu_event_map, - .raw_event = intel_pmu_raw_event, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, /* @@ -864,14 +843,38 @@ static __initconst struct x86_pmu intel_pmu = { * the generic event period: */ .max_period = (1ULL << 31) - 1, - .enable_bts = intel_pmu_enable_bts, - .disable_bts = intel_pmu_disable_bts, .get_event_constraints = intel_get_event_constraints, - .cpu_starting = init_debug_store_on_cpu, - .cpu_dying = fini_debug_store_on_cpu, + .cpu_starting = intel_pmu_cpu_starting, + .cpu_dying = intel_pmu_cpu_dying, }; +static void intel_clovertown_quirks(void) +{ + /* + * PEBS is unreliable due to: + * + * AJ67 - PEBS may experience CPL leaks + * AJ68 - PEBS PMI may be delayed by one event + * AJ69 - GLOBAL_STATUS[62] will only be set when DEBUGCTL[12] + * AJ106 - FREEZE_LBRS_ON_PMI doesn't work in combination with PEBS + * + * AJ67 could be worked around by restricting the OS/USR flags. + * AJ69 could be worked around by setting PMU_FREEZE_ON_PMI. + * + * AJ106 could possibly be worked around by not allowing LBR + * usage from PEBS, including the fixup. + * AJ68 could possibly be worked around by always programming + * a pebs_event_reset[0] value and coping with the lost events. + * + * But taken together it might just make sense to not enable PEBS on + * these chips. + */ + printk(KERN_WARNING "PEBS disabled due to CPU errata.\n"); + x86_pmu.pebs = 0; + x86_pmu.pebs_constraints = NULL; +} + static __init int intel_pmu_init(void) { union cpuid10_edx edx; @@ -881,12 +884,13 @@ static __init int intel_pmu_init(void) int version; if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { - /* check for P6 processor family */ - if (boot_cpu_data.x86 == 6) { - return p6_pmu_init(); - } else { + switch (boot_cpu_data.x86) { + case 0x6: + return p6_pmu_init(); + case 0xf: + return p4_pmu_init(); + } return -ENODEV; - } } /* @@ -904,16 +908,28 @@ static __init int intel_pmu_init(void) x86_pmu = intel_pmu; x86_pmu.version = version; - x86_pmu.num_events = eax.split.num_events; - x86_pmu.event_bits = eax.split.bit_width; - x86_pmu.event_mask = (1ULL << eax.split.bit_width) - 1; + x86_pmu.num_counters = eax.split.num_counters; + x86_pmu.cntval_bits = eax.split.bit_width; + x86_pmu.cntval_mask = (1ULL << eax.split.bit_width) - 1; /* * Quirk: v2 perfmon does not report fixed-purpose events, so * assume at least 3 events: */ if (version > 1) - x86_pmu.num_events_fixed = max((int)edx.split.num_events_fixed, 3); + x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3); + + /* + * v2 and above have a perf capabilities MSR + */ + if (version > 1) { + u64 capabilities; + + rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities); + x86_pmu.intel_cap.capabilities = capabilities; + } + + intel_ds_init(); /* * Install the hw-cache-events table: @@ -924,12 +940,15 @@ static __init int intel_pmu_init(void) break; case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ + x86_pmu.quirks = intel_clovertown_quirks; case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */ case 29: /* six-core 45 nm xeon "Dunnington" */ memcpy(hw_cache_event_ids, core2_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + intel_pmu_lbr_init_core(); + x86_pmu.event_constraints = intel_core2_event_constraints; pr_cont("Core2 events, "); break; @@ -940,13 +959,19 @@ static __init int intel_pmu_init(void) memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + intel_pmu_lbr_init_nhm(); + x86_pmu.event_constraints = intel_nehalem_event_constraints; - pr_cont("Nehalem/Corei7 events, "); + x86_pmu.enable_all = intel_pmu_nhm_enable_all; + pr_cont("Nehalem events, "); break; + case 28: /* Atom */ memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + intel_pmu_lbr_init_atom(); + x86_pmu.event_constraints = intel_gen_event_constraints; pr_cont("Atom events, "); break; @@ -956,7 +981,10 @@ static __init int intel_pmu_init(void) memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + intel_pmu_lbr_init_nhm(); + x86_pmu.event_constraints = intel_westmere_event_constraints; + x86_pmu.enable_all = intel_pmu_nhm_enable_all; pr_cont("Westmere events, "); break; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c new file mode 100644 index 00000000000..18018d1311c --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -0,0 +1,641 @@ +#ifdef CONFIG_CPU_SUP_INTEL + +/* The maximal number of PEBS events: */ +#define MAX_PEBS_EVENTS 4 + +/* The size of a BTS record in bytes: */ +#define BTS_RECORD_SIZE 24 + +#define BTS_BUFFER_SIZE (PAGE_SIZE << 4) +#define PEBS_BUFFER_SIZE PAGE_SIZE + +/* + * pebs_record_32 for p4 and core not supported + +struct pebs_record_32 { + u32 flags, ip; + u32 ax, bc, cx, dx; + u32 si, di, bp, sp; +}; + + */ + +struct pebs_record_core { + u64 flags, ip; + u64 ax, bx, cx, dx; + u64 si, di, bp, sp; + u64 r8, r9, r10, r11; + u64 r12, r13, r14, r15; +}; + +struct pebs_record_nhm { + u64 flags, ip; + u64 ax, bx, cx, dx; + u64 si, di, bp, sp; + u64 r8, r9, r10, r11; + u64 r12, r13, r14, r15; + u64 status, dla, dse, lat; +}; + +/* + * A debug store configuration. + * + * We only support architectures that use 64bit fields. + */ +struct debug_store { + u64 bts_buffer_base; + u64 bts_index; + u64 bts_absolute_maximum; + u64 bts_interrupt_threshold; + u64 pebs_buffer_base; + u64 pebs_index; + u64 pebs_absolute_maximum; + u64 pebs_interrupt_threshold; + u64 pebs_event_reset[MAX_PEBS_EVENTS]; +}; + +static void init_debug_store_on_cpu(int cpu) +{ + struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + + if (!ds) + return; + + wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, + (u32)((u64)(unsigned long)ds), + (u32)((u64)(unsigned long)ds >> 32)); +} + +static void fini_debug_store_on_cpu(int cpu) +{ + if (!per_cpu(cpu_hw_events, cpu).ds) + return; + + wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0); +} + +static void release_ds_buffers(void) +{ + int cpu; + + if (!x86_pmu.bts && !x86_pmu.pebs) + return; + + get_online_cpus(); + + for_each_online_cpu(cpu) + fini_debug_store_on_cpu(cpu); + + for_each_possible_cpu(cpu) { + struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + + if (!ds) + continue; + + per_cpu(cpu_hw_events, cpu).ds = NULL; + + kfree((void *)(unsigned long)ds->pebs_buffer_base); + kfree((void *)(unsigned long)ds->bts_buffer_base); + kfree(ds); + } + + put_online_cpus(); +} + +static int reserve_ds_buffers(void) +{ + int cpu, err = 0; + + if (!x86_pmu.bts && !x86_pmu.pebs) + return 0; + + get_online_cpus(); + + for_each_possible_cpu(cpu) { + struct debug_store *ds; + void *buffer; + int max, thresh; + + err = -ENOMEM; + ds = kzalloc(sizeof(*ds), GFP_KERNEL); + if (unlikely(!ds)) + break; + per_cpu(cpu_hw_events, cpu).ds = ds; + + if (x86_pmu.bts) { + buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL); + if (unlikely(!buffer)) + break; + + max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE; + thresh = max / 16; + + ds->bts_buffer_base = (u64)(unsigned long)buffer; + ds->bts_index = ds->bts_buffer_base; + ds->bts_absolute_maximum = ds->bts_buffer_base + + max * BTS_RECORD_SIZE; + ds->bts_interrupt_threshold = ds->bts_absolute_maximum - + thresh * BTS_RECORD_SIZE; + } + + if (x86_pmu.pebs) { + buffer = kzalloc(PEBS_BUFFER_SIZE, GFP_KERNEL); + if (unlikely(!buffer)) + break; + + max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size; + + ds->pebs_buffer_base = (u64)(unsigned long)buffer; + ds->pebs_index = ds->pebs_buffer_base; + ds->pebs_absolute_maximum = ds->pebs_buffer_base + + max * x86_pmu.pebs_record_size; + /* + * Always use single record PEBS + */ + ds->pebs_interrupt_threshold = ds->pebs_buffer_base + + x86_pmu.pebs_record_size; + } + + err = 0; + } + + if (err) + release_ds_buffers(); + else { + for_each_online_cpu(cpu) + init_debug_store_on_cpu(cpu); + } + + put_online_cpus(); + + return err; +} + +/* + * BTS + */ + +static struct event_constraint bts_constraint = + EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0); + +static void intel_pmu_enable_bts(u64 config) +{ + unsigned long debugctlmsr; + + debugctlmsr = get_debugctlmsr(); + + debugctlmsr |= DEBUGCTLMSR_TR; + debugctlmsr |= DEBUGCTLMSR_BTS; + debugctlmsr |= DEBUGCTLMSR_BTINT; + + if (!(config & ARCH_PERFMON_EVENTSEL_OS)) + debugctlmsr |= DEBUGCTLMSR_BTS_OFF_OS; + + if (!(config & ARCH_PERFMON_EVENTSEL_USR)) + debugctlmsr |= DEBUGCTLMSR_BTS_OFF_USR; + + update_debugctlmsr(debugctlmsr); +} + +static void intel_pmu_disable_bts(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + unsigned long debugctlmsr; + + if (!cpuc->ds) + return; + + debugctlmsr = get_debugctlmsr(); + + debugctlmsr &= + ~(DEBUGCTLMSR_TR | DEBUGCTLMSR_BTS | DEBUGCTLMSR_BTINT | + DEBUGCTLMSR_BTS_OFF_OS | DEBUGCTLMSR_BTS_OFF_USR); + + update_debugctlmsr(debugctlmsr); +} + +static void intel_pmu_drain_bts_buffer(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct bts_record { + u64 from; + u64 to; + u64 flags; + }; + struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS]; + struct bts_record *at, *top; + struct perf_output_handle handle; + struct perf_event_header header; + struct perf_sample_data data; + struct pt_regs regs; + + if (!event) + return; + + if (!ds) + return; + + at = (struct bts_record *)(unsigned long)ds->bts_buffer_base; + top = (struct bts_record *)(unsigned long)ds->bts_index; + + if (top <= at) + return; + + ds->bts_index = ds->bts_buffer_base; + + perf_sample_data_init(&data, 0); + data.period = event->hw.last_period; + regs.ip = 0; + + /* + * Prepare a generic sample, i.e. fill in the invariant fields. + * We will overwrite the from and to address before we output + * the sample. + */ + perf_prepare_sample(&header, &data, event, ®s); + + if (perf_output_begin(&handle, event, header.size * (top - at), 1, 1)) + return; + + for (; at < top; at++) { + data.ip = at->from; + data.addr = at->to; + + perf_output_sample(&handle, &header, &data, event); + } + + perf_output_end(&handle); + + /* There's new data available. */ + event->hw.interrupts++; + event->pending_kill = POLL_IN; +} + +/* + * PEBS + */ + +static struct event_constraint intel_core_pebs_events[] = { + PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INSTR_RETIRED.ANY */ + PEBS_EVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */ + PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ + PEBS_EVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ + PEBS_EVENT_CONSTRAINT(0x01cb, 0x1), /* MEM_LOAD_RETIRED.L1D_MISS */ + PEBS_EVENT_CONSTRAINT(0x02cb, 0x1), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */ + PEBS_EVENT_CONSTRAINT(0x04cb, 0x1), /* MEM_LOAD_RETIRED.L2_MISS */ + PEBS_EVENT_CONSTRAINT(0x08cb, 0x1), /* MEM_LOAD_RETIRED.L2_LINE_MISS */ + PEBS_EVENT_CONSTRAINT(0x10cb, 0x1), /* MEM_LOAD_RETIRED.DTLB_MISS */ + EVENT_CONSTRAINT_END +}; + +static struct event_constraint intel_nehalem_pebs_events[] = { + PEBS_EVENT_CONSTRAINT(0x00c0, 0xf), /* INSTR_RETIRED.ANY */ + PEBS_EVENT_CONSTRAINT(0xfec1, 0xf), /* X87_OPS_RETIRED.ANY */ + PEBS_EVENT_CONSTRAINT(0x00c5, 0xf), /* BR_INST_RETIRED.MISPRED */ + PEBS_EVENT_CONSTRAINT(0x1fc7, 0xf), /* SIMD_INST_RETURED.ANY */ + PEBS_EVENT_CONSTRAINT(0x01cb, 0xf), /* MEM_LOAD_RETIRED.L1D_MISS */ + PEBS_EVENT_CONSTRAINT(0x02cb, 0xf), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */ + PEBS_EVENT_CONSTRAINT(0x04cb, 0xf), /* MEM_LOAD_RETIRED.L2_MISS */ + PEBS_EVENT_CONSTRAINT(0x08cb, 0xf), /* MEM_LOAD_RETIRED.L2_LINE_MISS */ + PEBS_EVENT_CONSTRAINT(0x10cb, 0xf), /* MEM_LOAD_RETIRED.DTLB_MISS */ + EVENT_CONSTRAINT_END +}; + +static struct event_constraint * +intel_pebs_constraints(struct perf_event *event) +{ + struct event_constraint *c; + + if (!event->attr.precise_ip) + return NULL; + + if (x86_pmu.pebs_constraints) { + for_each_event_constraint(c, x86_pmu.pebs_constraints) { + if ((event->hw.config & c->cmask) == c->code) + return c; + } + } + + return &emptyconstraint; +} + +static void intel_pmu_pebs_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + + hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; + + cpuc->pebs_enabled |= 1ULL << hwc->idx; + WARN_ON_ONCE(cpuc->enabled); + + if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1) + intel_pmu_lbr_enable(event); +} + +static void intel_pmu_pebs_disable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + + cpuc->pebs_enabled &= ~(1ULL << hwc->idx); + if (cpuc->enabled) + wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); + + hwc->config |= ARCH_PERFMON_EVENTSEL_INT; + + if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1) + intel_pmu_lbr_disable(event); +} + +static void intel_pmu_pebs_enable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (cpuc->pebs_enabled) + wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); +} + +static void intel_pmu_pebs_disable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (cpuc->pebs_enabled) + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); +} + +#include <asm/insn.h> + +static inline bool kernel_ip(unsigned long ip) +{ +#ifdef CONFIG_X86_32 + return ip > PAGE_OFFSET; +#else + return (long)ip < 0; +#endif +} + +static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + unsigned long from = cpuc->lbr_entries[0].from; + unsigned long old_to, to = cpuc->lbr_entries[0].to; + unsigned long ip = regs->ip; + + /* + * We don't need to fixup if the PEBS assist is fault like + */ + if (!x86_pmu.intel_cap.pebs_trap) + return 1; + + /* + * No LBR entry, no basic block, no rewinding + */ + if (!cpuc->lbr_stack.nr || !from || !to) + return 0; + + /* + * Basic blocks should never cross user/kernel boundaries + */ + if (kernel_ip(ip) != kernel_ip(to)) + return 0; + + /* + * unsigned math, either ip is before the start (impossible) or + * the basic block is larger than 1 page (sanity) + */ + if ((ip - to) > PAGE_SIZE) + return 0; + + /* + * We sampled a branch insn, rewind using the LBR stack + */ + if (ip == to) { + regs->ip = from; + return 1; + } + + do { + struct insn insn; + u8 buf[MAX_INSN_SIZE]; + void *kaddr; + + old_to = to; + if (!kernel_ip(ip)) { + int bytes, size = MAX_INSN_SIZE; + + bytes = copy_from_user_nmi(buf, (void __user *)to, size); + if (bytes != size) + return 0; + + kaddr = buf; + } else + kaddr = (void *)to; + + kernel_insn_init(&insn, kaddr); + insn_get_length(&insn); + to += insn.length; + } while (to < ip); + + if (to == ip) { + regs->ip = old_to; + return 1; + } + + /* + * Even though we decoded the basic block, the instruction stream + * never matched the given IP, either the TO or the IP got corrupted. + */ + return 0; +} + +static int intel_pmu_save_and_restart(struct perf_event *event); + +static void __intel_pmu_pebs_event(struct perf_event *event, + struct pt_regs *iregs, void *__pebs) +{ + /* + * We cast to pebs_record_core since that is a subset of + * both formats and we don't use the other fields in this + * routine. + */ + struct pebs_record_core *pebs = __pebs; + struct perf_sample_data data; + struct pt_regs regs; + + if (!intel_pmu_save_and_restart(event)) + return; + + perf_sample_data_init(&data, 0); + data.period = event->hw.last_period; + + /* + * We use the interrupt regs as a base because the PEBS record + * does not contain a full regs set, specifically it seems to + * lack segment descriptors, which get used by things like + * user_mode(). + * + * In the simple case fix up only the IP and BP,SP regs, for + * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly. + * A possible PERF_SAMPLE_REGS will have to transfer all regs. + */ + regs = *iregs; + regs.ip = pebs->ip; + regs.bp = pebs->bp; + regs.sp = pebs->sp; + + if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s)) + regs.flags |= PERF_EFLAGS_EXACT; + else + regs.flags &= ~PERF_EFLAGS_EXACT; + + if (perf_event_overflow(event, 1, &data, ®s)) + x86_pmu_stop(event); +} + +static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct perf_event *event = cpuc->events[0]; /* PMC0 only */ + struct pebs_record_core *at, *top; + int n; + + if (!ds || !x86_pmu.pebs) + return; + + at = (struct pebs_record_core *)(unsigned long)ds->pebs_buffer_base; + top = (struct pebs_record_core *)(unsigned long)ds->pebs_index; + + /* + * Whatever else happens, drain the thing + */ + ds->pebs_index = ds->pebs_buffer_base; + + if (!test_bit(0, cpuc->active_mask)) + return; + + WARN_ON_ONCE(!event); + + if (!event->attr.precise_ip) + return; + + n = top - at; + if (n <= 0) + return; + + /* + * Should not happen, we program the threshold at 1 and do not + * set a reset value. + */ + WARN_ON_ONCE(n > 1); + at += n - 1; + + __intel_pmu_pebs_event(event, iregs, at); +} + +static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct pebs_record_nhm *at, *top; + struct perf_event *event = NULL; + u64 status = 0; + int bit, n; + + if (!ds || !x86_pmu.pebs) + return; + + at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; + top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; + + ds->pebs_index = ds->pebs_buffer_base; + + n = top - at; + if (n <= 0) + return; + + /* + * Should not happen, we program the threshold at 1 and do not + * set a reset value. + */ + WARN_ON_ONCE(n > MAX_PEBS_EVENTS); + + for ( ; at < top; at++) { + for_each_set_bit(bit, (unsigned long *)&at->status, MAX_PEBS_EVENTS) { + event = cpuc->events[bit]; + if (!test_bit(bit, cpuc->active_mask)) + continue; + + WARN_ON_ONCE(!event); + + if (!event->attr.precise_ip) + continue; + + if (__test_and_set_bit(bit, (unsigned long *)&status)) + continue; + + break; + } + + if (!event || bit >= MAX_PEBS_EVENTS) + continue; + + __intel_pmu_pebs_event(event, iregs, at); + } +} + +/* + * BTS, PEBS probe and setup + */ + +static void intel_ds_init(void) +{ + /* + * No support for 32bit formats + */ + if (!boot_cpu_has(X86_FEATURE_DTES64)) + return; + + x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS); + x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS); + if (x86_pmu.pebs) { + char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-'; + int format = x86_pmu.intel_cap.pebs_format; + + switch (format) { + case 0: + printk(KERN_CONT "PEBS fmt0%c, ", pebs_type); + x86_pmu.pebs_record_size = sizeof(struct pebs_record_core); + x86_pmu.drain_pebs = intel_pmu_drain_pebs_core; + x86_pmu.pebs_constraints = intel_core_pebs_events; + break; + + case 1: + printk(KERN_CONT "PEBS fmt1%c, ", pebs_type); + x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm); + x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; + x86_pmu.pebs_constraints = intel_nehalem_pebs_events; + break; + + default: + printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type); + x86_pmu.pebs = 0; + break; + } + } +} + +#else /* CONFIG_CPU_SUP_INTEL */ + +static int reserve_ds_buffers(void) +{ + return 0; +} + +static void release_ds_buffers(void) +{ +} + +#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c new file mode 100644 index 00000000000..d202c1bece1 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -0,0 +1,218 @@ +#ifdef CONFIG_CPU_SUP_INTEL + +enum { + LBR_FORMAT_32 = 0x00, + LBR_FORMAT_LIP = 0x01, + LBR_FORMAT_EIP = 0x02, + LBR_FORMAT_EIP_FLAGS = 0x03, +}; + +/* + * We only support LBR implementations that have FREEZE_LBRS_ON_PMI + * otherwise it becomes near impossible to get a reliable stack. + */ + +static void __intel_pmu_lbr_enable(void) +{ + u64 debugctl; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); +} + +static void __intel_pmu_lbr_disable(void) +{ + u64 debugctl; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); +} + +static void intel_pmu_lbr_reset_32(void) +{ + int i; + + for (i = 0; i < x86_pmu.lbr_nr; i++) + wrmsrl(x86_pmu.lbr_from + i, 0); +} + +static void intel_pmu_lbr_reset_64(void) +{ + int i; + + for (i = 0; i < x86_pmu.lbr_nr; i++) { + wrmsrl(x86_pmu.lbr_from + i, 0); + wrmsrl(x86_pmu.lbr_to + i, 0); + } +} + +static void intel_pmu_lbr_reset(void) +{ + if (!x86_pmu.lbr_nr) + return; + + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32) + intel_pmu_lbr_reset_32(); + else + intel_pmu_lbr_reset_64(); +} + +static void intel_pmu_lbr_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (!x86_pmu.lbr_nr) + return; + + WARN_ON_ONCE(cpuc->enabled); + + /* + * Reset the LBR stack if we changed task context to + * avoid data leaks. + */ + + if (event->ctx->task && cpuc->lbr_context != event->ctx) { + intel_pmu_lbr_reset(); + cpuc->lbr_context = event->ctx; + } + + cpuc->lbr_users++; +} + +static void intel_pmu_lbr_disable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (!x86_pmu.lbr_nr) + return; + + cpuc->lbr_users--; + WARN_ON_ONCE(cpuc->lbr_users < 0); + + if (cpuc->enabled && !cpuc->lbr_users) + __intel_pmu_lbr_disable(); +} + +static void intel_pmu_lbr_enable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (cpuc->lbr_users) + __intel_pmu_lbr_enable(); +} + +static void intel_pmu_lbr_disable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (cpuc->lbr_users) + __intel_pmu_lbr_disable(); +} + +static inline u64 intel_pmu_lbr_tos(void) +{ + u64 tos; + + rdmsrl(x86_pmu.lbr_tos, tos); + + return tos; +} + +static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) +{ + unsigned long mask = x86_pmu.lbr_nr - 1; + u64 tos = intel_pmu_lbr_tos(); + int i; + + for (i = 0; i < x86_pmu.lbr_nr; i++) { + unsigned long lbr_idx = (tos - i) & mask; + union { + struct { + u32 from; + u32 to; + }; + u64 lbr; + } msr_lastbranch; + + rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr); + + cpuc->lbr_entries[i].from = msr_lastbranch.from; + cpuc->lbr_entries[i].to = msr_lastbranch.to; + cpuc->lbr_entries[i].flags = 0; + } + cpuc->lbr_stack.nr = i; +} + +#define LBR_FROM_FLAG_MISPRED (1ULL << 63) + +/* + * Due to lack of segmentation in Linux the effective address (offset) + * is the same as the linear address, allowing us to merge the LIP and EIP + * LBR formats. + */ +static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) +{ + unsigned long mask = x86_pmu.lbr_nr - 1; + int lbr_format = x86_pmu.intel_cap.lbr_format; + u64 tos = intel_pmu_lbr_tos(); + int i; + + for (i = 0; i < x86_pmu.lbr_nr; i++) { + unsigned long lbr_idx = (tos - i) & mask; + u64 from, to, flags = 0; + + rdmsrl(x86_pmu.lbr_from + lbr_idx, from); + rdmsrl(x86_pmu.lbr_to + lbr_idx, to); + + if (lbr_format == LBR_FORMAT_EIP_FLAGS) { + flags = !!(from & LBR_FROM_FLAG_MISPRED); + from = (u64)((((s64)from) << 1) >> 1); + } + + cpuc->lbr_entries[i].from = from; + cpuc->lbr_entries[i].to = to; + cpuc->lbr_entries[i].flags = flags; + } + cpuc->lbr_stack.nr = i; +} + +static void intel_pmu_lbr_read(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (!cpuc->lbr_users) + return; + + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32) + intel_pmu_lbr_read_32(cpuc); + else + intel_pmu_lbr_read_64(cpuc); +} + +static void intel_pmu_lbr_init_core(void) +{ + x86_pmu.lbr_nr = 4; + x86_pmu.lbr_tos = 0x01c9; + x86_pmu.lbr_from = 0x40; + x86_pmu.lbr_to = 0x60; +} + +static void intel_pmu_lbr_init_nhm(void) +{ + x86_pmu.lbr_nr = 16; + x86_pmu.lbr_tos = 0x01c9; + x86_pmu.lbr_from = 0x680; + x86_pmu.lbr_to = 0x6c0; +} + +static void intel_pmu_lbr_init_atom(void) +{ + x86_pmu.lbr_nr = 8; + x86_pmu.lbr_tos = 0x01c9; + x86_pmu.lbr_from = 0x40; + x86_pmu.lbr_to = 0x60; +} + +#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c new file mode 100644 index 00000000000..107711bf0ee --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -0,0 +1,942 @@ +/* + * Netburst Perfomance Events (P4, old Xeon) + * + * Copyright (C) 2010 Parallels, Inc., Cyrill Gorcunov <gorcunov@openvz.org> + * Copyright (C) 2010 Intel Corporation, Lin Ming <ming.m.lin@intel.com> + * + * For licencing details see kernel-base/COPYING + */ + +#ifdef CONFIG_CPU_SUP_INTEL + +#include <asm/perf_event_p4.h> + +#define P4_CNTR_LIMIT 3 +/* + * array indices: 0,1 - HT threads, used with HT enabled cpu + */ +struct p4_event_bind { + unsigned int opcode; /* Event code and ESCR selector */ + unsigned int escr_msr[2]; /* ESCR MSR for this event */ + char cntr[2][P4_CNTR_LIMIT]; /* counter index (offset), -1 on abscence */ +}; + +struct p4_pebs_bind { + unsigned int metric_pebs; + unsigned int metric_vert; +}; + +/* it sets P4_PEBS_ENABLE_UOP_TAG as well */ +#define P4_GEN_PEBS_BIND(name, pebs, vert) \ + [P4_PEBS_METRIC__##name] = { \ + .metric_pebs = pebs | P4_PEBS_ENABLE_UOP_TAG, \ + .metric_vert = vert, \ + } + +/* + * note we have P4_PEBS_ENABLE_UOP_TAG always set here + * + * it's needed for mapping P4_PEBS_CONFIG_METRIC_MASK bits of + * event configuration to find out which values are to be + * written into MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT + * resgisters + */ +static struct p4_pebs_bind p4_pebs_bind_map[] = { + P4_GEN_PEBS_BIND(1stl_cache_load_miss_retired, 0x0000001, 0x0000001), + P4_GEN_PEBS_BIND(2ndl_cache_load_miss_retired, 0x0000002, 0x0000001), + P4_GEN_PEBS_BIND(dtlb_load_miss_retired, 0x0000004, 0x0000001), + P4_GEN_PEBS_BIND(dtlb_store_miss_retired, 0x0000004, 0x0000002), + P4_GEN_PEBS_BIND(dtlb_all_miss_retired, 0x0000004, 0x0000003), + P4_GEN_PEBS_BIND(tagged_mispred_branch, 0x0018000, 0x0000010), + P4_GEN_PEBS_BIND(mob_load_replay_retired, 0x0000200, 0x0000001), + P4_GEN_PEBS_BIND(split_load_retired, 0x0000400, 0x0000001), + P4_GEN_PEBS_BIND(split_store_retired, 0x0000400, 0x0000002), +}; + +/* + * Note that we don't use CCCR1 here, there is an + * exception for P4_BSQ_ALLOCATION but we just have + * no workaround + * + * consider this binding as resources which particular + * event may borrow, it doesn't contain EventMask, + * Tags and friends -- they are left to a caller + */ +static struct p4_event_bind p4_event_bind_map[] = { + [P4_EVENT_TC_DELIVER_MODE] = { + .opcode = P4_OPCODE(P4_EVENT_TC_DELIVER_MODE), + .escr_msr = { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 }, + .cntr = { {4, 5, -1}, {6, 7, -1} }, + }, + [P4_EVENT_BPU_FETCH_REQUEST] = { + .opcode = P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST), + .escr_msr = { MSR_P4_BPU_ESCR0, MSR_P4_BPU_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_ITLB_REFERENCE] = { + .opcode = P4_OPCODE(P4_EVENT_ITLB_REFERENCE), + .escr_msr = { MSR_P4_ITLB_ESCR0, MSR_P4_ITLB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_MEMORY_CANCEL] = { + .opcode = P4_OPCODE(P4_EVENT_MEMORY_CANCEL), + .escr_msr = { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_MEMORY_COMPLETE] = { + .opcode = P4_OPCODE(P4_EVENT_MEMORY_COMPLETE), + .escr_msr = { MSR_P4_SAAT_ESCR0 , MSR_P4_SAAT_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_LOAD_PORT_REPLAY] = { + .opcode = P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY), + .escr_msr = { MSR_P4_SAAT_ESCR0, MSR_P4_SAAT_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_STORE_PORT_REPLAY] = { + .opcode = P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY), + .escr_msr = { MSR_P4_SAAT_ESCR0 , MSR_P4_SAAT_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_MOB_LOAD_REPLAY] = { + .opcode = P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY), + .escr_msr = { MSR_P4_MOB_ESCR0, MSR_P4_MOB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_PAGE_WALK_TYPE] = { + .opcode = P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE), + .escr_msr = { MSR_P4_PMH_ESCR0, MSR_P4_PMH_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_BSQ_CACHE_REFERENCE] = { + .opcode = P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE), + .escr_msr = { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_IOQ_ALLOCATION] = { + .opcode = P4_OPCODE(P4_EVENT_IOQ_ALLOCATION), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_IOQ_ACTIVE_ENTRIES] = { /* shared ESCR */ + .opcode = P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES), + .escr_msr = { MSR_P4_FSB_ESCR1, MSR_P4_FSB_ESCR1 }, + .cntr = { {2, -1, -1}, {3, -1, -1} }, + }, + [P4_EVENT_FSB_DATA_ACTIVITY] = { + .opcode = P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_BSQ_ALLOCATION] = { /* shared ESCR, broken CCCR1 */ + .opcode = P4_OPCODE(P4_EVENT_BSQ_ALLOCATION), + .escr_msr = { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR0 }, + .cntr = { {0, -1, -1}, {1, -1, -1} }, + }, + [P4_EVENT_BSQ_ACTIVE_ENTRIES] = { /* shared ESCR */ + .opcode = P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES), + .escr_msr = { MSR_P4_BSU_ESCR1 , MSR_P4_BSU_ESCR1 }, + .cntr = { {2, -1, -1}, {3, -1, -1} }, + }, + [P4_EVENT_SSE_INPUT_ASSIST] = { + .opcode = P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_PACKED_SP_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_PACKED_SP_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_PACKED_DP_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_PACKED_DP_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_SCALAR_SP_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_SCALAR_SP_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_SCALAR_DP_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_SCALAR_DP_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_64BIT_MMX_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_64BIT_MMX_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_128BIT_MMX_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_128BIT_MMX_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_X87_FP_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_X87_FP_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_TC_MISC] = { + .opcode = P4_OPCODE(P4_EVENT_TC_MISC), + .escr_msr = { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 }, + .cntr = { {4, 5, -1}, {6, 7, -1} }, + }, + [P4_EVENT_GLOBAL_POWER_EVENTS] = { + .opcode = P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_TC_MS_XFER] = { + .opcode = P4_OPCODE(P4_EVENT_TC_MS_XFER), + .escr_msr = { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 }, + .cntr = { {4, 5, -1}, {6, 7, -1} }, + }, + [P4_EVENT_UOP_QUEUE_WRITES] = { + .opcode = P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES), + .escr_msr = { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 }, + .cntr = { {4, 5, -1}, {6, 7, -1} }, + }, + [P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE] = { + .opcode = P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE), + .escr_msr = { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR0 }, + .cntr = { {4, 5, -1}, {6, 7, -1} }, + }, + [P4_EVENT_RETIRED_BRANCH_TYPE] = { + .opcode = P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE), + .escr_msr = { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR1 }, + .cntr = { {4, 5, -1}, {6, 7, -1} }, + }, + [P4_EVENT_RESOURCE_STALL] = { + .opcode = P4_OPCODE(P4_EVENT_RESOURCE_STALL), + .escr_msr = { MSR_P4_ALF_ESCR0, MSR_P4_ALF_ESCR1 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_WC_BUFFER] = { + .opcode = P4_OPCODE(P4_EVENT_WC_BUFFER), + .escr_msr = { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_B2B_CYCLES] = { + .opcode = P4_OPCODE(P4_EVENT_B2B_CYCLES), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_BNR] = { + .opcode = P4_OPCODE(P4_EVENT_BNR), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_SNOOP] = { + .opcode = P4_OPCODE(P4_EVENT_SNOOP), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_RESPONSE] = { + .opcode = P4_OPCODE(P4_EVENT_RESPONSE), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_FRONT_END_EVENT] = { + .opcode = P4_OPCODE(P4_EVENT_FRONT_END_EVENT), + .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_EXECUTION_EVENT] = { + .opcode = P4_OPCODE(P4_EVENT_EXECUTION_EVENT), + .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_REPLAY_EVENT] = { + .opcode = P4_OPCODE(P4_EVENT_REPLAY_EVENT), + .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_INSTR_RETIRED] = { + .opcode = P4_OPCODE(P4_EVENT_INSTR_RETIRED), + .escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_UOPS_RETIRED] = { + .opcode = P4_OPCODE(P4_EVENT_UOPS_RETIRED), + .escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_UOP_TYPE] = { + .opcode = P4_OPCODE(P4_EVENT_UOP_TYPE), + .escr_msr = { MSR_P4_RAT_ESCR0, MSR_P4_RAT_ESCR1 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_BRANCH_RETIRED] = { + .opcode = P4_OPCODE(P4_EVENT_BRANCH_RETIRED), + .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_MISPRED_BRANCH_RETIRED] = { + .opcode = P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED), + .escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_X87_ASSIST] = { + .opcode = P4_OPCODE(P4_EVENT_X87_ASSIST), + .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_MACHINE_CLEAR] = { + .opcode = P4_OPCODE(P4_EVENT_MACHINE_CLEAR), + .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_INSTR_COMPLETED] = { + .opcode = P4_OPCODE(P4_EVENT_INSTR_COMPLETED), + .escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, +}; + +#define P4_GEN_CACHE_EVENT(event, bit, metric) \ + p4_config_pack_escr(P4_ESCR_EVENT(event) | \ + P4_ESCR_EMASK_BIT(event, bit)) | \ + p4_config_pack_cccr(metric | \ + P4_CCCR_ESEL(P4_OPCODE_ESEL(P4_OPCODE(event)))) + +static __initconst const u64 p4_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, + P4_PEBS_METRIC__1stl_cache_load_miss_retired), + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, + P4_PEBS_METRIC__2ndl_cache_load_miss_retired), + }, +}, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, + P4_PEBS_METRIC__dtlb_load_miss_retired), + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, + P4_PEBS_METRIC__dtlb_store_miss_retired), + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, HIT, + P4_PEBS_METRIC__none), + [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, MISS, + P4_PEBS_METRIC__none), + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + +static u64 p4_general_events[PERF_COUNT_HW_MAX] = { + /* non-halted CPU clocks */ + [PERF_COUNT_HW_CPU_CYCLES] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_GLOBAL_POWER_EVENTS) | + P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING)), + + /* + * retired instructions + * in a sake of simplicity we don't use the FSB tagging + */ + [PERF_COUNT_HW_INSTRUCTIONS] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_INSTR_RETIRED) | + P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG) | + P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, BOGUSNTAG)), + + /* cache hits */ + [PERF_COUNT_HW_CACHE_REFERENCES] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_BSQ_CACHE_REFERENCE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM)), + + /* cache misses */ + [PERF_COUNT_HW_CACHE_MISSES] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_BSQ_CACHE_REFERENCE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS)), + + /* branch instructions retired */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_RETIRED_BRANCH_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CALL) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT)), + + /* mispredicted branches retired */ + [PERF_COUNT_HW_BRANCH_MISSES] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_MISPRED_BRANCH_RETIRED) | + P4_ESCR_EMASK_BIT(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS)), + + /* bus ready clocks (cpu is driving #DRDY_DRV\#DRDY_OWN): */ + [PERF_COUNT_HW_BUS_CYCLES] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_FSB_DATA_ACTIVITY) | + P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV) | + P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN)) | + p4_config_pack_cccr(P4_CCCR_EDGE | P4_CCCR_COMPARE), +}; + +static struct p4_event_bind *p4_config_get_bind(u64 config) +{ + unsigned int evnt = p4_config_unpack_event(config); + struct p4_event_bind *bind = NULL; + + if (evnt < ARRAY_SIZE(p4_event_bind_map)) + bind = &p4_event_bind_map[evnt]; + + return bind; +} + +static u64 p4_pmu_event_map(int hw_event) +{ + struct p4_event_bind *bind; + unsigned int esel; + u64 config; + + config = p4_general_events[hw_event]; + bind = p4_config_get_bind(config); + esel = P4_OPCODE_ESEL(bind->opcode); + config |= p4_config_pack_cccr(P4_CCCR_ESEL(esel)); + + return config; +} + +static int p4_validate_raw_event(struct perf_event *event) +{ + unsigned int v; + + /* user data may have out-of-bound event index */ + v = p4_config_unpack_event(event->attr.config); + if (v >= ARRAY_SIZE(p4_event_bind_map)) { + pr_warning("P4 PMU: Unknown event code: %d\n", v); + return -EINVAL; + } + + /* + * it may have some screwed PEBS bits + */ + if (p4_config_pebs_has(event->attr.config, P4_PEBS_CONFIG_ENABLE)) { + pr_warning("P4 PMU: PEBS are not supported yet\n"); + return -EINVAL; + } + v = p4_config_unpack_metric(event->attr.config); + if (v >= ARRAY_SIZE(p4_pebs_bind_map)) { + pr_warning("P4 PMU: Unknown metric code: %d\n", v); + return -EINVAL; + } + + return 0; +} + +static int p4_hw_config(struct perf_event *event) +{ + int cpu = get_cpu(); + int rc = 0; + u32 escr, cccr; + + /* + * the reason we use cpu that early is that: if we get scheduled + * first time on the same cpu -- we will not need swap thread + * specific flags in config (and will save some cpu cycles) + */ + + cccr = p4_default_cccr_conf(cpu); + escr = p4_default_escr_conf(cpu, event->attr.exclude_kernel, + event->attr.exclude_user); + event->hw.config = p4_config_pack_escr(escr) | + p4_config_pack_cccr(cccr); + + if (p4_ht_active() && p4_ht_thread(cpu)) + event->hw.config = p4_set_ht_bit(event->hw.config); + + if (event->attr.type == PERF_TYPE_RAW) { + + rc = p4_validate_raw_event(event); + if (rc) + goto out; + + /* + * We don't control raw events so it's up to the caller + * to pass sane values (and we don't count the thread number + * on HT machine but allow HT-compatible specifics to be + * passed on) + * + * Note that for RAW events we allow user to use P4_CCCR_RESERVED + * bits since we keep additional info here (for cache events and etc) + * + * XXX: HT wide things should check perf_paranoid_cpu() && + * CAP_SYS_ADMIN + */ + event->hw.config |= event->attr.config & + (p4_config_pack_escr(P4_ESCR_MASK_HT) | + p4_config_pack_cccr(P4_CCCR_MASK_HT | P4_CCCR_RESERVED)); + } + + rc = x86_setup_perfctr(event); +out: + put_cpu(); + return rc; +} + +static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc) +{ + int overflow = 0; + u32 low, high; + + rdmsr(hwc->config_base + hwc->idx, low, high); + + /* we need to check high bit for unflagged overflows */ + if ((low & P4_CCCR_OVF) || !(high & (1 << 31))) { + overflow = 1; + (void)checking_wrmsrl(hwc->config_base + hwc->idx, + ((u64)low) & ~P4_CCCR_OVF); + } + + return overflow; +} + +static void p4_pmu_disable_pebs(void) +{ + /* + * FIXME + * + * It's still allowed that two threads setup same cache + * events so we can't simply clear metrics until we knew + * noone is depending on us, so we need kind of counter + * for "ReplayEvent" users. + * + * What is more complex -- RAW events, if user (for some + * reason) will pass some cache event metric with improper + * event opcode -- it's fine from hardware point of view + * but completely nonsence from "meaning" of such action. + * + * So at moment let leave metrics turned on forever -- it's + * ok for now but need to be revisited! + * + * (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)0); + * (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)0); + */ +} + +static inline void p4_pmu_disable_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + /* + * If event gets disabled while counter is in overflowed + * state we need to clear P4_CCCR_OVF, otherwise interrupt get + * asserted again and again + */ + (void)checking_wrmsrl(hwc->config_base + hwc->idx, + (u64)(p4_config_unpack_cccr(hwc->config)) & + ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED); +} + +static void p4_pmu_disable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int idx; + + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + struct perf_event *event = cpuc->events[idx]; + if (!test_bit(idx, cpuc->active_mask)) + continue; + p4_pmu_disable_event(event); + } + + p4_pmu_disable_pebs(); +} + +/* configuration must be valid */ +static void p4_pmu_enable_pebs(u64 config) +{ + struct p4_pebs_bind *bind; + unsigned int idx; + + BUILD_BUG_ON(P4_PEBS_METRIC__max > P4_PEBS_CONFIG_METRIC_MASK); + + idx = p4_config_unpack_metric(config); + if (idx == P4_PEBS_METRIC__none) + return; + + bind = &p4_pebs_bind_map[idx]; + + (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind->metric_pebs); + (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind->metric_vert); +} + +static void p4_pmu_enable_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + int thread = p4_ht_config_thread(hwc->config); + u64 escr_conf = p4_config_unpack_escr(p4_clear_ht_bit(hwc->config)); + unsigned int idx = p4_config_unpack_event(hwc->config); + struct p4_event_bind *bind; + u64 escr_addr, cccr; + + bind = &p4_event_bind_map[idx]; + escr_addr = (u64)bind->escr_msr[thread]; + + /* + * - we dont support cascaded counters yet + * - and counter 1 is broken (erratum) + */ + WARN_ON_ONCE(p4_is_event_cascaded(hwc->config)); + WARN_ON_ONCE(hwc->idx == 1); + + /* we need a real Event value */ + escr_conf &= ~P4_ESCR_EVENT_MASK; + escr_conf |= P4_ESCR_EVENT(P4_OPCODE_EVNT(bind->opcode)); + + cccr = p4_config_unpack_cccr(hwc->config); + + /* + * it could be Cache event so we need to write metrics + * into additional MSRs + */ + p4_pmu_enable_pebs(hwc->config); + + (void)checking_wrmsrl(escr_addr, escr_conf); + (void)checking_wrmsrl(hwc->config_base + hwc->idx, + (cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE); +} + +static void p4_pmu_enable_all(int added) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int idx; + + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + struct perf_event *event = cpuc->events[idx]; + if (!test_bit(idx, cpuc->active_mask)) + continue; + p4_pmu_enable_event(event); + } +} + +static int p4_pmu_handle_irq(struct pt_regs *regs) +{ + struct perf_sample_data data; + struct cpu_hw_events *cpuc; + struct perf_event *event; + struct hw_perf_event *hwc; + int idx, handled = 0; + u64 val; + + data.addr = 0; + data.raw = NULL; + + cpuc = &__get_cpu_var(cpu_hw_events); + + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + + if (!test_bit(idx, cpuc->active_mask)) + continue; + + event = cpuc->events[idx]; + hwc = &event->hw; + + WARN_ON_ONCE(hwc->idx != idx); + + /* it might be unflagged overflow */ + handled = p4_pmu_clear_cccr_ovf(hwc); + + val = x86_perf_event_update(event); + if (!handled && (val & (1ULL << (x86_pmu.cntval_bits - 1)))) + continue; + + /* event overflow for sure */ + data.period = event->hw.last_period; + + if (!x86_perf_event_set_period(event)) + continue; + if (perf_event_overflow(event, 1, &data, regs)) + p4_pmu_disable_event(event); + } + + if (handled) { + /* p4 quirk: unmask it again */ + apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED); + inc_irq_stat(apic_perf_irqs); + } + + return handled; +} + +/* + * swap thread specific fields according to a thread + * we are going to run on + */ +static void p4_pmu_swap_config_ts(struct hw_perf_event *hwc, int cpu) +{ + u32 escr, cccr; + + /* + * we either lucky and continue on same cpu or no HT support + */ + if (!p4_should_swap_ts(hwc->config, cpu)) + return; + + /* + * the event is migrated from an another logical + * cpu, so we need to swap thread specific flags + */ + + escr = p4_config_unpack_escr(hwc->config); + cccr = p4_config_unpack_cccr(hwc->config); + + if (p4_ht_thread(cpu)) { + cccr &= ~P4_CCCR_OVF_PMI_T0; + cccr |= P4_CCCR_OVF_PMI_T1; + if (escr & P4_ESCR_T0_OS) { + escr &= ~P4_ESCR_T0_OS; + escr |= P4_ESCR_T1_OS; + } + if (escr & P4_ESCR_T0_USR) { + escr &= ~P4_ESCR_T0_USR; + escr |= P4_ESCR_T1_USR; + } + hwc->config = p4_config_pack_escr(escr); + hwc->config |= p4_config_pack_cccr(cccr); + hwc->config |= P4_CONFIG_HT; + } else { + cccr &= ~P4_CCCR_OVF_PMI_T1; + cccr |= P4_CCCR_OVF_PMI_T0; + if (escr & P4_ESCR_T1_OS) { + escr &= ~P4_ESCR_T1_OS; + escr |= P4_ESCR_T0_OS; + } + if (escr & P4_ESCR_T1_USR) { + escr &= ~P4_ESCR_T1_USR; + escr |= P4_ESCR_T0_USR; + } + hwc->config = p4_config_pack_escr(escr); + hwc->config |= p4_config_pack_cccr(cccr); + hwc->config &= ~P4_CONFIG_HT; + } +} + +/* + * ESCR address hashing is tricky, ESCRs are not sequential + * in memory but all starts from MSR_P4_BSU_ESCR0 (0x03a0) and + * the metric between any ESCRs is laid in range [0xa0,0xe1] + * + * so we make ~70% filled hashtable + */ + +#define P4_ESCR_MSR_BASE 0x000003a0 +#define P4_ESCR_MSR_MAX 0x000003e1 +#define P4_ESCR_MSR_TABLE_SIZE (P4_ESCR_MSR_MAX - P4_ESCR_MSR_BASE + 1) +#define P4_ESCR_MSR_IDX(msr) (msr - P4_ESCR_MSR_BASE) +#define P4_ESCR_MSR_TABLE_ENTRY(msr) [P4_ESCR_MSR_IDX(msr)] = msr + +static const unsigned int p4_escr_table[P4_ESCR_MSR_TABLE_SIZE] = { + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_ALF_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_ALF_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_BPU_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_BPU_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_BSU_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_BSU_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_CRU_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_CRU_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_CRU_ESCR2), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_CRU_ESCR3), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_CRU_ESCR4), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_CRU_ESCR5), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_DAC_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_DAC_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_FIRM_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_FIRM_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_FLAME_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_FLAME_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_FSB_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_FSB_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_IQ_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_IQ_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_IS_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_IS_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_ITLB_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_ITLB_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_IX_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_IX_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_MOB_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_MOB_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_MS_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_MS_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_PMH_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_PMH_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_RAT_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_RAT_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_SAAT_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_SAAT_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_SSU_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_SSU_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_TBPU_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_TBPU_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_TC_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_TC_ESCR1), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_U2L_ESCR0), + P4_ESCR_MSR_TABLE_ENTRY(MSR_P4_U2L_ESCR1), +}; + +static int p4_get_escr_idx(unsigned int addr) +{ + unsigned int idx = P4_ESCR_MSR_IDX(addr); + + if (unlikely(idx >= P4_ESCR_MSR_TABLE_SIZE || + !p4_escr_table[idx] || + p4_escr_table[idx] != addr)) { + WARN_ONCE(1, "P4 PMU: Wrong address passed: %x\n", addr); + return -1; + } + + return idx; +} + +static int p4_next_cntr(int thread, unsigned long *used_mask, + struct p4_event_bind *bind) +{ + int i, j; + + for (i = 0; i < P4_CNTR_LIMIT; i++) { + j = bind->cntr[thread][i]; + if (j != -1 && !test_bit(j, used_mask)) + return j; + } + + return -1; +} + +static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) +{ + unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + unsigned long escr_mask[BITS_TO_LONGS(P4_ESCR_MSR_TABLE_SIZE)]; + int cpu = smp_processor_id(); + struct hw_perf_event *hwc; + struct p4_event_bind *bind; + unsigned int i, thread, num; + int cntr_idx, escr_idx; + + bitmap_zero(used_mask, X86_PMC_IDX_MAX); + bitmap_zero(escr_mask, P4_ESCR_MSR_TABLE_SIZE); + + for (i = 0, num = n; i < n; i++, num--) { + + hwc = &cpuc->event_list[i]->hw; + thread = p4_ht_thread(cpu); + bind = p4_config_get_bind(hwc->config); + escr_idx = p4_get_escr_idx(bind->escr_msr[thread]); + if (unlikely(escr_idx == -1)) + goto done; + + if (hwc->idx != -1 && !p4_should_swap_ts(hwc->config, cpu)) { + cntr_idx = hwc->idx; + if (assign) + assign[i] = hwc->idx; + goto reserve; + } + + cntr_idx = p4_next_cntr(thread, used_mask, bind); + if (cntr_idx == -1 || test_bit(escr_idx, escr_mask)) + goto done; + + p4_pmu_swap_config_ts(hwc, cpu); + if (assign) + assign[i] = cntr_idx; +reserve: + set_bit(cntr_idx, used_mask); + set_bit(escr_idx, escr_mask); + } + +done: + return num ? -ENOSPC : 0; +} + +static __initconst const struct x86_pmu p4_pmu = { + .name = "Netburst P4/Xeon", + .handle_irq = p4_pmu_handle_irq, + .disable_all = p4_pmu_disable_all, + .enable_all = p4_pmu_enable_all, + .enable = p4_pmu_enable_event, + .disable = p4_pmu_disable_event, + .eventsel = MSR_P4_BPU_CCCR0, + .perfctr = MSR_P4_BPU_PERFCTR0, + .event_map = p4_pmu_event_map, + .max_events = ARRAY_SIZE(p4_general_events), + .get_event_constraints = x86_get_event_constraints, + /* + * IF HT disabled we may need to use all + * ARCH_P4_MAX_CCCR counters simulaneously + * though leave it restricted at moment assuming + * HT is on + */ + .num_counters = ARCH_P4_MAX_CCCR, + .apic = 1, + .cntval_bits = 40, + .cntval_mask = (1ULL << 40) - 1, + .max_period = (1ULL << 39) - 1, + .hw_config = p4_hw_config, + .schedule_events = p4_pmu_schedule_events, + /* + * This handles erratum N15 in intel doc 249199-029, + * the counter may not be updated correctly on write + * so we need a second write operation to do the trick + * (the official workaround didn't work) + * + * the former idea is taken from OProfile code + */ + .perfctr_second_write = 1, +}; + +static __init int p4_pmu_init(void) +{ + unsigned int low, high; + + /* If we get stripped -- indexig fails */ + BUILD_BUG_ON(ARCH_P4_MAX_CCCR > X86_PMC_MAX_GENERIC); + + rdmsr(MSR_IA32_MISC_ENABLE, low, high); + if (!(low & (1 << 7))) { + pr_cont("unsupported Netburst CPU model %d ", + boot_cpu_data.x86_model); + return -ENODEV; + } + + memcpy(hw_cache_event_ids, p4_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + + pr_cont("Netburst events, "); + + x86_pmu = p4_pmu; + + return 0; +} + +#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index a330485d14d..34ba07be2cd 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -27,24 +27,6 @@ static u64 p6_pmu_event_map(int hw_event) */ #define P6_NOP_EVENT 0x0000002EULL -static u64 p6_pmu_raw_event(u64 hw_event) -{ -#define P6_EVNTSEL_EVENT_MASK 0x000000FFULL -#define P6_EVNTSEL_UNIT_MASK 0x0000FF00ULL -#define P6_EVNTSEL_EDGE_MASK 0x00040000ULL -#define P6_EVNTSEL_INV_MASK 0x00800000ULL -#define P6_EVNTSEL_REG_MASK 0xFF000000ULL - -#define P6_EVNTSEL_MASK \ - (P6_EVNTSEL_EVENT_MASK | \ - P6_EVNTSEL_UNIT_MASK | \ - P6_EVNTSEL_EDGE_MASK | \ - P6_EVNTSEL_INV_MASK | \ - P6_EVNTSEL_REG_MASK) - - return hw_event & P6_EVNTSEL_MASK; -} - static struct event_constraint p6_event_constraints[] = { INTEL_EVENT_CONSTRAINT(0xc1, 0x1), /* FLOPS */ @@ -66,7 +48,7 @@ static void p6_pmu_disable_all(void) wrmsrl(MSR_P6_EVNTSEL0, val); } -static void p6_pmu_enable_all(void) +static void p6_pmu_enable_all(int added) { unsigned long val; @@ -102,22 +84,23 @@ static void p6_pmu_enable_event(struct perf_event *event) (void)checking_wrmsrl(hwc->config_base + hwc->idx, val); } -static __initconst struct x86_pmu p6_pmu = { +static __initconst const struct x86_pmu p6_pmu = { .name = "p6", .handle_irq = x86_pmu_handle_irq, .disable_all = p6_pmu_disable_all, .enable_all = p6_pmu_enable_all, .enable = p6_pmu_enable_event, .disable = p6_pmu_disable_event, + .hw_config = x86_pmu_hw_config, + .schedule_events = x86_schedule_events, .eventsel = MSR_P6_EVNTSEL0, .perfctr = MSR_P6_PERFCTR0, .event_map = p6_pmu_event_map, - .raw_event = p6_pmu_raw_event, .max_events = ARRAY_SIZE(p6_perfmon_event_map), .apic = 1, .max_period = (1ULL << 31) - 1, .version = 0, - .num_events = 2, + .num_counters = 2, /* * Events have 40 bits implemented. However they are designed such * that bits [32-39] are sign extensions of bit 31. As such the @@ -125,8 +108,8 @@ static __initconst struct x86_pmu p6_pmu = { * * See IA-32 Intel Architecture Software developer manual Vol 3B */ - .event_bits = 32, - .event_mask = (1ULL << 32) - 1, + .cntval_bits = 32, + .cntval_mask = (1ULL << 32) - 1, .get_event_constraints = x86_get_event_constraints, .event_constraints = p6_event_constraints, }; diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c new file mode 100644 index 00000000000..34b4dad6f0b --- /dev/null +++ b/arch/x86/kernel/cpu/scattered.c @@ -0,0 +1,63 @@ +/* + * Routines to indentify additional cpu features that are scattered in + * cpuid space. + */ +#include <linux/cpu.h> + +#include <asm/pat.h> +#include <asm/processor.h> + +#include <asm/apic.h> + +struct cpuid_bit { + u16 feature; + u8 reg; + u8 bit; + u32 level; + u32 sub_leaf; +}; + +enum cpuid_regs { + CR_EAX = 0, + CR_ECX, + CR_EDX, + CR_EBX +}; + +void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) +{ + u32 max_level; + u32 regs[4]; + const struct cpuid_bit *cb; + + static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { + { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 }, + { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, + { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, + { X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 }, + { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, + { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, + { X86_FEATURE_XSAVEOPT, CR_EAX, 0, 0x0000000d, 1 }, + { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, + { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a, 0 }, + { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a, 0 }, + { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a, 0 }, + { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a, 0 }, + { 0, 0, 0, 0, 0 } + }; + + for (cb = cpuid_bits; cb->feature; cb++) { + + /* Verify that the level is valid */ + max_level = cpuid_eax(cb->level & 0xffff0000); + if (max_level < cb->level || + max_level > (cb->level | 0xffff)) + continue; + + cpuid_count(cb->level, cb->sub_leaf, ®s[CR_EAX], + ®s[CR_EBX], ®s[CR_ECX], ®s[CR_EDX]); + + if (regs[cb->reg] & (1 << cb->bit)) + set_cpu_cap(c, cb->feature); + } +} diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/topology.c index 97ad79cdf68..4397e987a1c 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/topology.c @@ -1,60 +1,14 @@ /* - * Routines to indentify additional cpu features that are scattered in - * cpuid space. + * Check for extended topology enumeration cpuid leaf 0xb and if it + * exists, use it for populating initial_apicid and cpu topology + * detection. */ -#include <linux/cpu.h> +#include <linux/cpu.h> +#include <asm/apic.h> #include <asm/pat.h> #include <asm/processor.h> -#include <asm/apic.h> - -struct cpuid_bit { - u16 feature; - u8 reg; - u8 bit; - u32 level; -}; - -enum cpuid_regs { - CR_EAX = 0, - CR_ECX, - CR_EDX, - CR_EBX -}; - -void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) -{ - u32 max_level; - u32 regs[4]; - const struct cpuid_bit *cb; - - static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { - { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 }, - { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006 }, - { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a }, - { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a }, - { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a }, - { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a }, - { 0, 0, 0, 0 } - }; - - for (cb = cpuid_bits; cb->feature; cb++) { - - /* Verify that the level is valid */ - max_level = cpuid_eax(cb->level & 0xffff0000); - if (max_level < cb->level || - max_level > (cb->level | 0xffff)) - continue; - - cpuid(cb->level, ®s[CR_EAX], ®s[CR_EBX], - ®s[CR_ECX], ®s[CR_EDX]); - - if (regs[cb->reg] & (1 << cb->bit)) - set_cpu_cap(c, cb->feature); - } -} - /* leaf 0xb SMT level */ #define SMT_LEVEL 0 diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index dfdb4dba232..227b0448960 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -24,8 +24,8 @@ #include <linux/dmi.h> #include <linux/module.h> #include <asm/div64.h> -#include <asm/vmware.h> #include <asm/x86_init.h> +#include <asm/hypervisor.h> #define CPUID_VMWARE_INFO_LEAF 0x40000000 #define VMWARE_HYPERVISOR_MAGIC 0x564D5868 @@ -51,7 +51,7 @@ static inline int __vmware_platform(void) static unsigned long vmware_get_tsc_khz(void) { - uint64_t tsc_hz; + uint64_t tsc_hz, lpj; uint32_t eax, ebx, ecx, edx; VMWARE_PORT(GETHZ, eax, ebx, ecx, edx); @@ -62,10 +62,17 @@ static unsigned long vmware_get_tsc_khz(void) printk(KERN_INFO "TSC freq read from hypervisor : %lu.%03lu MHz\n", (unsigned long) tsc_hz / 1000, (unsigned long) tsc_hz % 1000); + + if (!preset_lpj) { + lpj = ((u64)tsc_hz * 1000); + do_div(lpj, HZ); + preset_lpj = lpj; + } + return tsc_hz; } -void __init vmware_platform_setup(void) +static void __init vmware_platform_setup(void) { uint32_t eax, ebx, ecx, edx; @@ -83,26 +90,22 @@ void __init vmware_platform_setup(void) * serial key should be enough, as this will always have a VMware * specific string when running under VMware hypervisor. */ -int vmware_platform(void) +static bool __init vmware_platform(void) { if (cpu_has_hypervisor) { - unsigned int eax, ebx, ecx, edx; - char hyper_vendor_id[13]; - - cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &ebx, &ecx, &edx); - memcpy(hyper_vendor_id + 0, &ebx, 4); - memcpy(hyper_vendor_id + 4, &ecx, 4); - memcpy(hyper_vendor_id + 8, &edx, 4); - hyper_vendor_id[12] = '\0'; - if (!strcmp(hyper_vendor_id, "VMwareVMware")) - return 1; + unsigned int eax; + unsigned int hyper_vendor_id[3]; + + cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &hyper_vendor_id[0], + &hyper_vendor_id[1], &hyper_vendor_id[2]); + if (!memcmp(hyper_vendor_id, "VMwareVMware", 12)) + return true; } else if (dmi_available && dmi_name_in_serial("VMware") && __vmware_platform()) - return 1; + return true; - return 0; + return false; } -EXPORT_SYMBOL(vmware_platform); /* * VMware hypervisor takes care of exporting a reliable TSC to the guest. @@ -116,8 +119,16 @@ EXPORT_SYMBOL(vmware_platform); * so that the kernel could just trust the hypervisor with providing a * reliable virtual TSC that is suitable for timekeeping. */ -void __cpuinit vmware_set_feature_bits(struct cpuinfo_x86 *c) +static void __cpuinit vmware_set_cpu_features(struct cpuinfo_x86 *c) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE); } + +const __refconst struct hypervisor_x86 x86_hyper_vmware = { + .name = "VMware", + .detect = vmware_platform, + .set_cpu_features = vmware_set_cpu_features, + .init_platform = vmware_platform_setup, +}; +EXPORT_SYMBOL(x86_hyper_vmware); diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 8b862d5900f..1b7b31ab7d8 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -170,7 +170,7 @@ static int __cpuinit cpuid_class_cpu_callback(struct notifier_block *nfb, cpuid_device_destroy(cpu); break; } - return err ? NOTIFY_BAD : NOTIFY_OK; + return notifier_from_errno(err); } static struct notifier_block __refdata cpuid_class_cpu_notifier = diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c deleted file mode 100644 index 1c47390dd0e..00000000000 --- a/arch/x86/kernel/ds.c +++ /dev/null @@ -1,1437 +0,0 @@ -/* - * Debug Store support - * - * This provides a low-level interface to the hardware's Debug Store - * feature that is used for branch trace store (BTS) and - * precise-event based sampling (PEBS). - * - * It manages: - * - DS and BTS hardware configuration - * - buffer overflow handling (to be done) - * - buffer access - * - * It does not do: - * - security checking (is the caller allowed to trace the task) - * - buffer allocation (memory accounting) - * - * - * Copyright (C) 2007-2009 Intel Corporation. - * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009 - */ - -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/mm.h> -#include <linux/trace_clock.h> - -#include <asm/ds.h> - -#include "ds_selftest.h" - -/* - * The configuration for a particular DS hardware implementation: - */ -struct ds_configuration { - /* The name of the configuration: */ - const char *name; - - /* The size of pointer-typed fields in DS, BTS, and PEBS: */ - unsigned char sizeof_ptr_field; - - /* The size of a BTS/PEBS record in bytes: */ - unsigned char sizeof_rec[2]; - - /* The number of pebs counter reset values in the DS structure. */ - unsigned char nr_counter_reset; - - /* Control bit-masks indexed by enum ds_feature: */ - unsigned long ctl[dsf_ctl_max]; -}; -static struct ds_configuration ds_cfg __read_mostly; - - -/* Maximal size of a DS configuration: */ -#define MAX_SIZEOF_DS 0x80 - -/* Maximal size of a BTS record: */ -#define MAX_SIZEOF_BTS (3 * 8) - -/* BTS and PEBS buffer alignment: */ -#define DS_ALIGNMENT (1 << 3) - -/* Number of buffer pointers in DS: */ -#define NUM_DS_PTR_FIELDS 8 - -/* Size of a pebs reset value in DS: */ -#define PEBS_RESET_FIELD_SIZE 8 - -/* Mask of control bits in the DS MSR register: */ -#define BTS_CONTROL \ - ( ds_cfg.ctl[dsf_bts] | \ - ds_cfg.ctl[dsf_bts_kernel] | \ - ds_cfg.ctl[dsf_bts_user] | \ - ds_cfg.ctl[dsf_bts_overflow] ) - -/* - * A BTS or PEBS tracer. - * - * This holds the configuration of the tracer and serves as a handle - * to identify tracers. - */ -struct ds_tracer { - /* The DS context (partially) owned by this tracer. */ - struct ds_context *context; - /* The buffer provided on ds_request() and its size in bytes. */ - void *buffer; - size_t size; -}; - -struct bts_tracer { - /* The common DS part: */ - struct ds_tracer ds; - - /* The trace including the DS configuration: */ - struct bts_trace trace; - - /* Buffer overflow notification function: */ - bts_ovfl_callback_t ovfl; - - /* Active flags affecting trace collection. */ - unsigned int flags; -}; - -struct pebs_tracer { - /* The common DS part: */ - struct ds_tracer ds; - - /* The trace including the DS configuration: */ - struct pebs_trace trace; - - /* Buffer overflow notification function: */ - pebs_ovfl_callback_t ovfl; -}; - -/* - * Debug Store (DS) save area configuration (see Intel64 and IA32 - * Architectures Software Developer's Manual, section 18.5) - * - * The DS configuration consists of the following fields; different - * architetures vary in the size of those fields. - * - * - double-word aligned base linear address of the BTS buffer - * - write pointer into the BTS buffer - * - end linear address of the BTS buffer (one byte beyond the end of - * the buffer) - * - interrupt pointer into BTS buffer - * (interrupt occurs when write pointer passes interrupt pointer) - * - double-word aligned base linear address of the PEBS buffer - * - write pointer into the PEBS buffer - * - end linear address of the PEBS buffer (one byte beyond the end of - * the buffer) - * - interrupt pointer into PEBS buffer - * (interrupt occurs when write pointer passes interrupt pointer) - * - value to which counter is reset following counter overflow - * - * Later architectures use 64bit pointers throughout, whereas earlier - * architectures use 32bit pointers in 32bit mode. - * - * - * We compute the base address for the first 8 fields based on: - * - the field size stored in the DS configuration - * - the relative field position - * - an offset giving the start of the respective region - * - * This offset is further used to index various arrays holding - * information for BTS and PEBS at the respective index. - * - * On later 32bit processors, we only access the lower 32bit of the - * 64bit pointer fields. The upper halves will be zeroed out. - */ - -enum ds_field { - ds_buffer_base = 0, - ds_index, - ds_absolute_maximum, - ds_interrupt_threshold, -}; - -enum ds_qualifier { - ds_bts = 0, - ds_pebs -}; - -static inline unsigned long -ds_get(const unsigned char *base, enum ds_qualifier qual, enum ds_field field) -{ - base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual))); - return *(unsigned long *)base; -} - -static inline void -ds_set(unsigned char *base, enum ds_qualifier qual, enum ds_field field, - unsigned long value) -{ - base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual))); - (*(unsigned long *)base) = value; -} - - -/* - * Locking is done only for allocating BTS or PEBS resources. - */ -static DEFINE_SPINLOCK(ds_lock); - -/* - * We either support (system-wide) per-cpu or per-thread allocation. - * We distinguish the two based on the task_struct pointer, where a - * NULL pointer indicates per-cpu allocation for the current cpu. - * - * Allocations are use-counted. As soon as resources are allocated, - * further allocations must be of the same type (per-cpu or - * per-thread). We model this by counting allocations (i.e. the number - * of tracers of a certain type) for one type negatively: - * =0 no tracers - * >0 number of per-thread tracers - * <0 number of per-cpu tracers - * - * Tracers essentially gives the number of ds contexts for a certain - * type of allocation. - */ -static atomic_t tracers = ATOMIC_INIT(0); - -static inline int get_tracer(struct task_struct *task) -{ - int error; - - spin_lock_irq(&ds_lock); - - if (task) { - error = -EPERM; - if (atomic_read(&tracers) < 0) - goto out; - atomic_inc(&tracers); - } else { - error = -EPERM; - if (atomic_read(&tracers) > 0) - goto out; - atomic_dec(&tracers); - } - - error = 0; -out: - spin_unlock_irq(&ds_lock); - return error; -} - -static inline void put_tracer(struct task_struct *task) -{ - if (task) - atomic_dec(&tracers); - else - atomic_inc(&tracers); -} - -/* - * The DS context is either attached to a thread or to a cpu: - * - in the former case, the thread_struct contains a pointer to the - * attached context. - * - in the latter case, we use a static array of per-cpu context - * pointers. - * - * Contexts are use-counted. They are allocated on first access and - * deallocated when the last user puts the context. - */ -struct ds_context { - /* The DS configuration; goes into MSR_IA32_DS_AREA: */ - unsigned char ds[MAX_SIZEOF_DS]; - - /* The owner of the BTS and PEBS configuration, respectively: */ - struct bts_tracer *bts_master; - struct pebs_tracer *pebs_master; - - /* Use count: */ - unsigned long count; - - /* Pointer to the context pointer field: */ - struct ds_context **this; - - /* The traced task; NULL for cpu tracing: */ - struct task_struct *task; - - /* The traced cpu; only valid if task is NULL: */ - int cpu; -}; - -static DEFINE_PER_CPU(struct ds_context *, cpu_ds_context); - - -static struct ds_context *ds_get_context(struct task_struct *task, int cpu) -{ - struct ds_context **p_context = - (task ? &task->thread.ds_ctx : &per_cpu(cpu_ds_context, cpu)); - struct ds_context *context = NULL; - struct ds_context *new_context = NULL; - - /* Chances are small that we already have a context. */ - new_context = kzalloc(sizeof(*new_context), GFP_KERNEL); - if (!new_context) - return NULL; - - spin_lock_irq(&ds_lock); - - context = *p_context; - if (likely(!context)) { - context = new_context; - - context->this = p_context; - context->task = task; - context->cpu = cpu; - context->count = 0; - - *p_context = context; - } - - context->count++; - - spin_unlock_irq(&ds_lock); - - if (context != new_context) - kfree(new_context); - - return context; -} - -static void ds_put_context(struct ds_context *context) -{ - struct task_struct *task; - unsigned long irq; - - if (!context) - return; - - spin_lock_irqsave(&ds_lock, irq); - - if (--context->count) { - spin_unlock_irqrestore(&ds_lock, irq); - return; - } - - *(context->this) = NULL; - - task = context->task; - - if (task) - clear_tsk_thread_flag(task, TIF_DS_AREA_MSR); - - /* - * We leave the (now dangling) pointer to the DS configuration in - * the DS_AREA msr. This is as good or as bad as replacing it with - * NULL - the hardware would crash if we enabled tracing. - * - * This saves us some problems with having to write an msr on a - * different cpu while preventing others from doing the same for the - * next context for that same cpu. - */ - - spin_unlock_irqrestore(&ds_lock, irq); - - /* The context might still be in use for context switching. */ - if (task && (task != current)) - wait_task_context_switch(task); - - kfree(context); -} - -static void ds_install_ds_area(struct ds_context *context) -{ - unsigned long ds; - - ds = (unsigned long)context->ds; - - /* - * There is a race between the bts master and the pebs master. - * - * The thread/cpu access is synchronized via get/put_cpu() for - * task tracing and via wrmsr_on_cpu for cpu tracing. - * - * If bts and pebs are collected for the same task or same cpu, - * the same confiuration is written twice. - */ - if (context->task) { - get_cpu(); - if (context->task == current) - wrmsrl(MSR_IA32_DS_AREA, ds); - set_tsk_thread_flag(context->task, TIF_DS_AREA_MSR); - put_cpu(); - } else - wrmsr_on_cpu(context->cpu, MSR_IA32_DS_AREA, - (u32)((u64)ds), (u32)((u64)ds >> 32)); -} - -/* - * Call the tracer's callback on a buffer overflow. - * - * context: the ds context - * qual: the buffer type - */ -static void ds_overflow(struct ds_context *context, enum ds_qualifier qual) -{ - switch (qual) { - case ds_bts: - if (context->bts_master && - context->bts_master->ovfl) - context->bts_master->ovfl(context->bts_master); - break; - case ds_pebs: - if (context->pebs_master && - context->pebs_master->ovfl) - context->pebs_master->ovfl(context->pebs_master); - break; - } -} - - -/* - * Write raw data into the BTS or PEBS buffer. - * - * The remainder of any partially written record is zeroed out. - * - * context: the DS context - * qual: the buffer type - * record: the data to write - * size: the size of the data - */ -static int ds_write(struct ds_context *context, enum ds_qualifier qual, - const void *record, size_t size) -{ - int bytes_written = 0; - - if (!record) - return -EINVAL; - - while (size) { - unsigned long base, index, end, write_end, int_th; - unsigned long write_size, adj_write_size; - - /* - * Write as much as possible without producing an - * overflow interrupt. - * - * Interrupt_threshold must either be - * - bigger than absolute_maximum or - * - point to a record between buffer_base and absolute_maximum - * - * Index points to a valid record. - */ - base = ds_get(context->ds, qual, ds_buffer_base); - index = ds_get(context->ds, qual, ds_index); - end = ds_get(context->ds, qual, ds_absolute_maximum); - int_th = ds_get(context->ds, qual, ds_interrupt_threshold); - - write_end = min(end, int_th); - - /* - * If we are already beyond the interrupt threshold, - * we fill the entire buffer. - */ - if (write_end <= index) - write_end = end; - - if (write_end <= index) - break; - - write_size = min((unsigned long) size, write_end - index); - memcpy((void *)index, record, write_size); - - record = (const char *)record + write_size; - size -= write_size; - bytes_written += write_size; - - adj_write_size = write_size / ds_cfg.sizeof_rec[qual]; - adj_write_size *= ds_cfg.sizeof_rec[qual]; - - /* Zero out trailing bytes. */ - memset((char *)index + write_size, 0, - adj_write_size - write_size); - index += adj_write_size; - - if (index >= end) - index = base; - ds_set(context->ds, qual, ds_index, index); - - if (index >= int_th) - ds_overflow(context, qual); - } - - return bytes_written; -} - - -/* - * Branch Trace Store (BTS) uses the following format. Different - * architectures vary in the size of those fields. - * - source linear address - * - destination linear address - * - flags - * - * Later architectures use 64bit pointers throughout, whereas earlier - * architectures use 32bit pointers in 32bit mode. - * - * We compute the base address for the fields based on: - * - the field size stored in the DS configuration - * - the relative field position - * - * In order to store additional information in the BTS buffer, we use - * a special source address to indicate that the record requires - * special interpretation. - * - * Netburst indicated via a bit in the flags field whether the branch - * was predicted; this is ignored. - * - * We use two levels of abstraction: - * - the raw data level defined here - * - an arch-independent level defined in ds.h - */ - -enum bts_field { - bts_from, - bts_to, - bts_flags, - - bts_qual = bts_from, - bts_clock = bts_to, - bts_pid = bts_flags, - - bts_qual_mask = (bts_qual_max - 1), - bts_escape = ((unsigned long)-1 & ~bts_qual_mask) -}; - -static inline unsigned long bts_get(const char *base, unsigned long field) -{ - base += (ds_cfg.sizeof_ptr_field * field); - return *(unsigned long *)base; -} - -static inline void bts_set(char *base, unsigned long field, unsigned long val) -{ - base += (ds_cfg.sizeof_ptr_field * field); - (*(unsigned long *)base) = val; -} - - -/* - * The raw BTS data is architecture dependent. - * - * For higher-level users, we give an arch-independent view. - * - ds.h defines struct bts_struct - * - bts_read translates one raw bts record into a bts_struct - * - bts_write translates one bts_struct into the raw format and - * writes it into the top of the parameter tracer's buffer. - * - * return: bytes read/written on success; -Eerrno, otherwise - */ -static int -bts_read(struct bts_tracer *tracer, const void *at, struct bts_struct *out) -{ - if (!tracer) - return -EINVAL; - - if (at < tracer->trace.ds.begin) - return -EINVAL; - - if (tracer->trace.ds.end < (at + tracer->trace.ds.size)) - return -EINVAL; - - memset(out, 0, sizeof(*out)); - if ((bts_get(at, bts_qual) & ~bts_qual_mask) == bts_escape) { - out->qualifier = (bts_get(at, bts_qual) & bts_qual_mask); - out->variant.event.clock = bts_get(at, bts_clock); - out->variant.event.pid = bts_get(at, bts_pid); - } else { - out->qualifier = bts_branch; - out->variant.lbr.from = bts_get(at, bts_from); - out->variant.lbr.to = bts_get(at, bts_to); - - if (!out->variant.lbr.from && !out->variant.lbr.to) - out->qualifier = bts_invalid; - } - - return ds_cfg.sizeof_rec[ds_bts]; -} - -static int bts_write(struct bts_tracer *tracer, const struct bts_struct *in) -{ - unsigned char raw[MAX_SIZEOF_BTS]; - - if (!tracer) - return -EINVAL; - - if (MAX_SIZEOF_BTS < ds_cfg.sizeof_rec[ds_bts]) - return -EOVERFLOW; - - switch (in->qualifier) { - case bts_invalid: - bts_set(raw, bts_from, 0); - bts_set(raw, bts_to, 0); - bts_set(raw, bts_flags, 0); - break; - case bts_branch: - bts_set(raw, bts_from, in->variant.lbr.from); - bts_set(raw, bts_to, in->variant.lbr.to); - bts_set(raw, bts_flags, 0); - break; - case bts_task_arrives: - case bts_task_departs: - bts_set(raw, bts_qual, (bts_escape | in->qualifier)); - bts_set(raw, bts_clock, in->variant.event.clock); - bts_set(raw, bts_pid, in->variant.event.pid); - break; - default: - return -EINVAL; - } - - return ds_write(tracer->ds.context, ds_bts, raw, - ds_cfg.sizeof_rec[ds_bts]); -} - - -static void ds_write_config(struct ds_context *context, - struct ds_trace *cfg, enum ds_qualifier qual) -{ - unsigned char *ds = context->ds; - - ds_set(ds, qual, ds_buffer_base, (unsigned long)cfg->begin); - ds_set(ds, qual, ds_index, (unsigned long)cfg->top); - ds_set(ds, qual, ds_absolute_maximum, (unsigned long)cfg->end); - ds_set(ds, qual, ds_interrupt_threshold, (unsigned long)cfg->ith); -} - -static void ds_read_config(struct ds_context *context, - struct ds_trace *cfg, enum ds_qualifier qual) -{ - unsigned char *ds = context->ds; - - cfg->begin = (void *)ds_get(ds, qual, ds_buffer_base); - cfg->top = (void *)ds_get(ds, qual, ds_index); - cfg->end = (void *)ds_get(ds, qual, ds_absolute_maximum); - cfg->ith = (void *)ds_get(ds, qual, ds_interrupt_threshold); -} - -static void ds_init_ds_trace(struct ds_trace *trace, enum ds_qualifier qual, - void *base, size_t size, size_t ith, - unsigned int flags) { - unsigned long buffer, adj; - - /* - * Adjust the buffer address and size to meet alignment - * constraints: - * - buffer is double-word aligned - * - size is multiple of record size - * - * We checked the size at the very beginning; we have enough - * space to do the adjustment. - */ - buffer = (unsigned long)base; - - adj = ALIGN(buffer, DS_ALIGNMENT) - buffer; - buffer += adj; - size -= adj; - - trace->n = size / ds_cfg.sizeof_rec[qual]; - trace->size = ds_cfg.sizeof_rec[qual]; - - size = (trace->n * trace->size); - - trace->begin = (void *)buffer; - trace->top = trace->begin; - trace->end = (void *)(buffer + size); - /* - * The value for 'no threshold' is -1, which will set the - * threshold outside of the buffer, just like we want it. - */ - ith *= ds_cfg.sizeof_rec[qual]; - trace->ith = (void *)(buffer + size - ith); - - trace->flags = flags; -} - - -static int ds_request(struct ds_tracer *tracer, struct ds_trace *trace, - enum ds_qualifier qual, struct task_struct *task, - int cpu, void *base, size_t size, size_t th) -{ - struct ds_context *context; - int error; - size_t req_size; - - error = -EOPNOTSUPP; - if (!ds_cfg.sizeof_rec[qual]) - goto out; - - error = -EINVAL; - if (!base) - goto out; - - req_size = ds_cfg.sizeof_rec[qual]; - /* We might need space for alignment adjustments. */ - if (!IS_ALIGNED((unsigned long)base, DS_ALIGNMENT)) - req_size += DS_ALIGNMENT; - - error = -EINVAL; - if (size < req_size) - goto out; - - if (th != (size_t)-1) { - th *= ds_cfg.sizeof_rec[qual]; - - error = -EINVAL; - if (size <= th) - goto out; - } - - tracer->buffer = base; - tracer->size = size; - - error = -ENOMEM; - context = ds_get_context(task, cpu); - if (!context) - goto out; - tracer->context = context; - - /* - * Defer any tracer-specific initialization work for the context until - * context ownership has been clarified. - */ - - error = 0; - out: - return error; -} - -static struct bts_tracer *ds_request_bts(struct task_struct *task, int cpu, - void *base, size_t size, - bts_ovfl_callback_t ovfl, size_t th, - unsigned int flags) -{ - struct bts_tracer *tracer; - int error; - - /* Buffer overflow notification is not yet implemented. */ - error = -EOPNOTSUPP; - if (ovfl) - goto out; - - error = get_tracer(task); - if (error < 0) - goto out; - - error = -ENOMEM; - tracer = kzalloc(sizeof(*tracer), GFP_KERNEL); - if (!tracer) - goto out_put_tracer; - tracer->ovfl = ovfl; - - /* Do some more error checking and acquire a tracing context. */ - error = ds_request(&tracer->ds, &tracer->trace.ds, - ds_bts, task, cpu, base, size, th); - if (error < 0) - goto out_tracer; - - /* Claim the bts part of the tracing context we acquired above. */ - spin_lock_irq(&ds_lock); - - error = -EPERM; - if (tracer->ds.context->bts_master) - goto out_unlock; - tracer->ds.context->bts_master = tracer; - - spin_unlock_irq(&ds_lock); - - /* - * Now that we own the bts part of the context, let's complete the - * initialization for that part. - */ - ds_init_ds_trace(&tracer->trace.ds, ds_bts, base, size, th, flags); - ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts); - ds_install_ds_area(tracer->ds.context); - - tracer->trace.read = bts_read; - tracer->trace.write = bts_write; - - /* Start tracing. */ - ds_resume_bts(tracer); - - return tracer; - - out_unlock: - spin_unlock_irq(&ds_lock); - ds_put_context(tracer->ds.context); - out_tracer: - kfree(tracer); - out_put_tracer: - put_tracer(task); - out: - return ERR_PTR(error); -} - -struct bts_tracer *ds_request_bts_task(struct task_struct *task, - void *base, size_t size, - bts_ovfl_callback_t ovfl, - size_t th, unsigned int flags) -{ - return ds_request_bts(task, 0, base, size, ovfl, th, flags); -} - -struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size, - bts_ovfl_callback_t ovfl, - size_t th, unsigned int flags) -{ - return ds_request_bts(NULL, cpu, base, size, ovfl, th, flags); -} - -static struct pebs_tracer *ds_request_pebs(struct task_struct *task, int cpu, - void *base, size_t size, - pebs_ovfl_callback_t ovfl, size_t th, - unsigned int flags) -{ - struct pebs_tracer *tracer; - int error; - - /* Buffer overflow notification is not yet implemented. */ - error = -EOPNOTSUPP; - if (ovfl) - goto out; - - error = get_tracer(task); - if (error < 0) - goto out; - - error = -ENOMEM; - tracer = kzalloc(sizeof(*tracer), GFP_KERNEL); - if (!tracer) - goto out_put_tracer; - tracer->ovfl = ovfl; - - /* Do some more error checking and acquire a tracing context. */ - error = ds_request(&tracer->ds, &tracer->trace.ds, - ds_pebs, task, cpu, base, size, th); - if (error < 0) - goto out_tracer; - - /* Claim the pebs part of the tracing context we acquired above. */ - spin_lock_irq(&ds_lock); - - error = -EPERM; - if (tracer->ds.context->pebs_master) - goto out_unlock; - tracer->ds.context->pebs_master = tracer; - - spin_unlock_irq(&ds_lock); - - /* - * Now that we own the pebs part of the context, let's complete the - * initialization for that part. - */ - ds_init_ds_trace(&tracer->trace.ds, ds_pebs, base, size, th, flags); - ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs); - ds_install_ds_area(tracer->ds.context); - - /* Start tracing. */ - ds_resume_pebs(tracer); - - return tracer; - - out_unlock: - spin_unlock_irq(&ds_lock); - ds_put_context(tracer->ds.context); - out_tracer: - kfree(tracer); - out_put_tracer: - put_tracer(task); - out: - return ERR_PTR(error); -} - -struct pebs_tracer *ds_request_pebs_task(struct task_struct *task, - void *base, size_t size, - pebs_ovfl_callback_t ovfl, - size_t th, unsigned int flags) -{ - return ds_request_pebs(task, 0, base, size, ovfl, th, flags); -} - -struct pebs_tracer *ds_request_pebs_cpu(int cpu, void *base, size_t size, - pebs_ovfl_callback_t ovfl, - size_t th, unsigned int flags) -{ - return ds_request_pebs(NULL, cpu, base, size, ovfl, th, flags); -} - -static void ds_free_bts(struct bts_tracer *tracer) -{ - struct task_struct *task; - - task = tracer->ds.context->task; - - WARN_ON_ONCE(tracer->ds.context->bts_master != tracer); - tracer->ds.context->bts_master = NULL; - - /* Make sure tracing stopped and the tracer is not in use. */ - if (task && (task != current)) - wait_task_context_switch(task); - - ds_put_context(tracer->ds.context); - put_tracer(task); - - kfree(tracer); -} - -void ds_release_bts(struct bts_tracer *tracer) -{ - might_sleep(); - - if (!tracer) - return; - - ds_suspend_bts(tracer); - ds_free_bts(tracer); -} - -int ds_release_bts_noirq(struct bts_tracer *tracer) -{ - struct task_struct *task; - unsigned long irq; - int error; - - if (!tracer) - return 0; - - task = tracer->ds.context->task; - - local_irq_save(irq); - - error = -EPERM; - if (!task && - (tracer->ds.context->cpu != smp_processor_id())) - goto out; - - error = -EPERM; - if (task && (task != current)) - goto out; - - ds_suspend_bts_noirq(tracer); - ds_free_bts(tracer); - - error = 0; - out: - local_irq_restore(irq); - return error; -} - -static void update_task_debugctlmsr(struct task_struct *task, - unsigned long debugctlmsr) -{ - task->thread.debugctlmsr = debugctlmsr; - - get_cpu(); - if (task == current) - update_debugctlmsr(debugctlmsr); - put_cpu(); -} - -void ds_suspend_bts(struct bts_tracer *tracer) -{ - struct task_struct *task; - unsigned long debugctlmsr; - int cpu; - - if (!tracer) - return; - - tracer->flags = 0; - - task = tracer->ds.context->task; - cpu = tracer->ds.context->cpu; - - WARN_ON(!task && irqs_disabled()); - - debugctlmsr = (task ? - task->thread.debugctlmsr : - get_debugctlmsr_on_cpu(cpu)); - debugctlmsr &= ~BTS_CONTROL; - - if (task) - update_task_debugctlmsr(task, debugctlmsr); - else - update_debugctlmsr_on_cpu(cpu, debugctlmsr); -} - -int ds_suspend_bts_noirq(struct bts_tracer *tracer) -{ - struct task_struct *task; - unsigned long debugctlmsr, irq; - int cpu, error = 0; - - if (!tracer) - return 0; - - tracer->flags = 0; - - task = tracer->ds.context->task; - cpu = tracer->ds.context->cpu; - - local_irq_save(irq); - - error = -EPERM; - if (!task && (cpu != smp_processor_id())) - goto out; - - debugctlmsr = (task ? - task->thread.debugctlmsr : - get_debugctlmsr()); - debugctlmsr &= ~BTS_CONTROL; - - if (task) - update_task_debugctlmsr(task, debugctlmsr); - else - update_debugctlmsr(debugctlmsr); - - error = 0; - out: - local_irq_restore(irq); - return error; -} - -static unsigned long ds_bts_control(struct bts_tracer *tracer) -{ - unsigned long control; - - control = ds_cfg.ctl[dsf_bts]; - if (!(tracer->trace.ds.flags & BTS_KERNEL)) - control |= ds_cfg.ctl[dsf_bts_kernel]; - if (!(tracer->trace.ds.flags & BTS_USER)) - control |= ds_cfg.ctl[dsf_bts_user]; - - return control; -} - -void ds_resume_bts(struct bts_tracer *tracer) -{ - struct task_struct *task; - unsigned long debugctlmsr; - int cpu; - - if (!tracer) - return; - - tracer->flags = tracer->trace.ds.flags; - - task = tracer->ds.context->task; - cpu = tracer->ds.context->cpu; - - WARN_ON(!task && irqs_disabled()); - - debugctlmsr = (task ? - task->thread.debugctlmsr : - get_debugctlmsr_on_cpu(cpu)); - debugctlmsr |= ds_bts_control(tracer); - - if (task) - update_task_debugctlmsr(task, debugctlmsr); - else - update_debugctlmsr_on_cpu(cpu, debugctlmsr); -} - -int ds_resume_bts_noirq(struct bts_tracer *tracer) -{ - struct task_struct *task; - unsigned long debugctlmsr, irq; - int cpu, error = 0; - - if (!tracer) - return 0; - - tracer->flags = tracer->trace.ds.flags; - - task = tracer->ds.context->task; - cpu = tracer->ds.context->cpu; - - local_irq_save(irq); - - error = -EPERM; - if (!task && (cpu != smp_processor_id())) - goto out; - - debugctlmsr = (task ? - task->thread.debugctlmsr : - get_debugctlmsr()); - debugctlmsr |= ds_bts_control(tracer); - - if (task) - update_task_debugctlmsr(task, debugctlmsr); - else - update_debugctlmsr(debugctlmsr); - - error = 0; - out: - local_irq_restore(irq); - return error; -} - -static void ds_free_pebs(struct pebs_tracer *tracer) -{ - struct task_struct *task; - - task = tracer->ds.context->task; - - WARN_ON_ONCE(tracer->ds.context->pebs_master != tracer); - tracer->ds.context->pebs_master = NULL; - - ds_put_context(tracer->ds.context); - put_tracer(task); - - kfree(tracer); -} - -void ds_release_pebs(struct pebs_tracer *tracer) -{ - might_sleep(); - - if (!tracer) - return; - - ds_suspend_pebs(tracer); - ds_free_pebs(tracer); -} - -int ds_release_pebs_noirq(struct pebs_tracer *tracer) -{ - struct task_struct *task; - unsigned long irq; - int error; - - if (!tracer) - return 0; - - task = tracer->ds.context->task; - - local_irq_save(irq); - - error = -EPERM; - if (!task && - (tracer->ds.context->cpu != smp_processor_id())) - goto out; - - error = -EPERM; - if (task && (task != current)) - goto out; - - ds_suspend_pebs_noirq(tracer); - ds_free_pebs(tracer); - - error = 0; - out: - local_irq_restore(irq); - return error; -} - -void ds_suspend_pebs(struct pebs_tracer *tracer) -{ - -} - -int ds_suspend_pebs_noirq(struct pebs_tracer *tracer) -{ - return 0; -} - -void ds_resume_pebs(struct pebs_tracer *tracer) -{ - -} - -int ds_resume_pebs_noirq(struct pebs_tracer *tracer) -{ - return 0; -} - -const struct bts_trace *ds_read_bts(struct bts_tracer *tracer) -{ - if (!tracer) - return NULL; - - ds_read_config(tracer->ds.context, &tracer->trace.ds, ds_bts); - return &tracer->trace; -} - -const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer) -{ - if (!tracer) - return NULL; - - ds_read_config(tracer->ds.context, &tracer->trace.ds, ds_pebs); - - tracer->trace.counters = ds_cfg.nr_counter_reset; - memcpy(tracer->trace.counter_reset, - tracer->ds.context->ds + - (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field), - ds_cfg.nr_counter_reset * PEBS_RESET_FIELD_SIZE); - - return &tracer->trace; -} - -int ds_reset_bts(struct bts_tracer *tracer) -{ - if (!tracer) - return -EINVAL; - - tracer->trace.ds.top = tracer->trace.ds.begin; - - ds_set(tracer->ds.context->ds, ds_bts, ds_index, - (unsigned long)tracer->trace.ds.top); - - return 0; -} - -int ds_reset_pebs(struct pebs_tracer *tracer) -{ - if (!tracer) - return -EINVAL; - - tracer->trace.ds.top = tracer->trace.ds.begin; - - ds_set(tracer->ds.context->ds, ds_pebs, ds_index, - (unsigned long)tracer->trace.ds.top); - - return 0; -} - -int ds_set_pebs_reset(struct pebs_tracer *tracer, - unsigned int counter, u64 value) -{ - if (!tracer) - return -EINVAL; - - if (ds_cfg.nr_counter_reset < counter) - return -EINVAL; - - *(u64 *)(tracer->ds.context->ds + - (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field) + - (counter * PEBS_RESET_FIELD_SIZE)) = value; - - return 0; -} - -static const struct ds_configuration ds_cfg_netburst = { - .name = "Netburst", - .ctl[dsf_bts] = (1 << 2) | (1 << 3), - .ctl[dsf_bts_kernel] = (1 << 5), - .ctl[dsf_bts_user] = (1 << 6), - .nr_counter_reset = 1, -}; -static const struct ds_configuration ds_cfg_pentium_m = { - .name = "Pentium M", - .ctl[dsf_bts] = (1 << 6) | (1 << 7), - .nr_counter_reset = 1, -}; -static const struct ds_configuration ds_cfg_core2_atom = { - .name = "Core 2/Atom", - .ctl[dsf_bts] = (1 << 6) | (1 << 7), - .ctl[dsf_bts_kernel] = (1 << 9), - .ctl[dsf_bts_user] = (1 << 10), - .nr_counter_reset = 1, -}; -static const struct ds_configuration ds_cfg_core_i7 = { - .name = "Core i7", - .ctl[dsf_bts] = (1 << 6) | (1 << 7), - .ctl[dsf_bts_kernel] = (1 << 9), - .ctl[dsf_bts_user] = (1 << 10), - .nr_counter_reset = 4, -}; - -static void -ds_configure(const struct ds_configuration *cfg, - struct cpuinfo_x86 *cpu) -{ - unsigned long nr_pebs_fields = 0; - - printk(KERN_INFO "[ds] using %s configuration\n", cfg->name); - -#ifdef __i386__ - nr_pebs_fields = 10; -#else - nr_pebs_fields = 18; -#endif - - /* - * Starting with version 2, architectural performance - * monitoring supports a format specifier. - */ - if ((cpuid_eax(0xa) & 0xff) > 1) { - unsigned long perf_capabilities, format; - - rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_capabilities); - - format = (perf_capabilities >> 8) & 0xf; - - switch (format) { - case 0: - nr_pebs_fields = 18; - break; - case 1: - nr_pebs_fields = 22; - break; - default: - printk(KERN_INFO - "[ds] unknown PEBS format: %lu\n", format); - nr_pebs_fields = 0; - break; - } - } - - memset(&ds_cfg, 0, sizeof(ds_cfg)); - ds_cfg = *cfg; - - ds_cfg.sizeof_ptr_field = - (cpu_has(cpu, X86_FEATURE_DTES64) ? 8 : 4); - - ds_cfg.sizeof_rec[ds_bts] = ds_cfg.sizeof_ptr_field * 3; - ds_cfg.sizeof_rec[ds_pebs] = ds_cfg.sizeof_ptr_field * nr_pebs_fields; - - if (!cpu_has(cpu, X86_FEATURE_BTS)) { - ds_cfg.sizeof_rec[ds_bts] = 0; - printk(KERN_INFO "[ds] bts not available\n"); - } - if (!cpu_has(cpu, X86_FEATURE_PEBS)) { - ds_cfg.sizeof_rec[ds_pebs] = 0; - printk(KERN_INFO "[ds] pebs not available\n"); - } - - printk(KERN_INFO "[ds] sizes: address: %u bit, ", - 8 * ds_cfg.sizeof_ptr_field); - printk("bts/pebs record: %u/%u bytes\n", - ds_cfg.sizeof_rec[ds_bts], ds_cfg.sizeof_rec[ds_pebs]); - - WARN_ON_ONCE(MAX_PEBS_COUNTERS < ds_cfg.nr_counter_reset); -} - -void __cpuinit ds_init_intel(struct cpuinfo_x86 *c) -{ - /* Only configure the first cpu. Others are identical. */ - if (ds_cfg.name) - return; - - switch (c->x86) { - case 0x6: - switch (c->x86_model) { - case 0x9: - case 0xd: /* Pentium M */ - ds_configure(&ds_cfg_pentium_m, c); - break; - case 0xf: - case 0x17: /* Core2 */ - case 0x1c: /* Atom */ - ds_configure(&ds_cfg_core2_atom, c); - break; - case 0x1a: /* Core i7 */ - ds_configure(&ds_cfg_core_i7, c); - break; - default: - /* Sorry, don't know about them. */ - break; - } - break; - case 0xf: - switch (c->x86_model) { - case 0x0: - case 0x1: - case 0x2: /* Netburst */ - ds_configure(&ds_cfg_netburst, c); - break; - default: - /* Sorry, don't know about them. */ - break; - } - break; - default: - /* Sorry, don't know about them. */ - break; - } -} - -static inline void ds_take_timestamp(struct ds_context *context, - enum bts_qualifier qualifier, - struct task_struct *task) -{ - struct bts_tracer *tracer = context->bts_master; - struct bts_struct ts; - - /* Prevent compilers from reading the tracer pointer twice. */ - barrier(); - - if (!tracer || !(tracer->flags & BTS_TIMESTAMPS)) - return; - - memset(&ts, 0, sizeof(ts)); - ts.qualifier = qualifier; - ts.variant.event.clock = trace_clock_global(); - ts.variant.event.pid = task->pid; - - bts_write(tracer, &ts); -} - -/* - * Change the DS configuration from tracing prev to tracing next. - */ -void ds_switch_to(struct task_struct *prev, struct task_struct *next) -{ - struct ds_context *prev_ctx = prev->thread.ds_ctx; - struct ds_context *next_ctx = next->thread.ds_ctx; - unsigned long debugctlmsr = next->thread.debugctlmsr; - - /* Make sure all data is read before we start. */ - barrier(); - - if (prev_ctx) { - update_debugctlmsr(0); - - ds_take_timestamp(prev_ctx, bts_task_departs, prev); - } - - if (next_ctx) { - ds_take_timestamp(next_ctx, bts_task_arrives, next); - - wrmsrl(MSR_IA32_DS_AREA, (unsigned long)next_ctx->ds); - } - - update_debugctlmsr(debugctlmsr); -} - -static __init int ds_selftest(void) -{ - if (ds_cfg.sizeof_rec[ds_bts]) { - int error; - - error = ds_selftest_bts(); - if (error) { - WARN(1, "[ds] selftest failed. disabling bts.\n"); - ds_cfg.sizeof_rec[ds_bts] = 0; - } - } - - if (ds_cfg.sizeof_rec[ds_pebs]) { - int error; - - error = ds_selftest_pebs(); - if (error) { - WARN(1, "[ds] selftest failed. disabling pebs.\n"); - ds_cfg.sizeof_rec[ds_pebs] = 0; - } - } - - return 0; -} -device_initcall(ds_selftest); diff --git a/arch/x86/kernel/ds_selftest.c b/arch/x86/kernel/ds_selftest.c deleted file mode 100644 index 6bc7c199ab9..00000000000 --- a/arch/x86/kernel/ds_selftest.c +++ /dev/null @@ -1,408 +0,0 @@ -/* - * Debug Store support - selftest - * - * - * Copyright (C) 2009 Intel Corporation. - * Markus Metzger <markus.t.metzger@intel.com>, 2009 - */ - -#include "ds_selftest.h" - -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/smp.h> -#include <linux/cpu.h> - -#include <asm/ds.h> - - -#define BUFFER_SIZE 521 /* Intentionally chose an odd size. */ -#define SMALL_BUFFER_SIZE 24 /* A single bts entry. */ - -struct ds_selftest_bts_conf { - struct bts_tracer *tracer; - int error; - int (*suspend)(struct bts_tracer *); - int (*resume)(struct bts_tracer *); -}; - -static int ds_selftest_bts_consistency(const struct bts_trace *trace) -{ - int error = 0; - - if (!trace) { - printk(KERN_CONT "failed to access trace..."); - /* Bail out. Other tests are pointless. */ - return -1; - } - - if (!trace->read) { - printk(KERN_CONT "bts read not available..."); - error = -1; - } - - /* Do some sanity checks on the trace configuration. */ - if (!trace->ds.n) { - printk(KERN_CONT "empty bts buffer..."); - error = -1; - } - if (!trace->ds.size) { - printk(KERN_CONT "bad bts trace setup..."); - error = -1; - } - if (trace->ds.end != - (char *)trace->ds.begin + (trace->ds.n * trace->ds.size)) { - printk(KERN_CONT "bad bts buffer setup..."); - error = -1; - } - /* - * We allow top in [begin; end], since its not clear when the - * overflow adjustment happens: after the increment or before the - * write. - */ - if ((trace->ds.top < trace->ds.begin) || - (trace->ds.end < trace->ds.top)) { - printk(KERN_CONT "bts top out of bounds..."); - error = -1; - } - - return error; -} - -static int ds_selftest_bts_read(struct bts_tracer *tracer, - const struct bts_trace *trace, - const void *from, const void *to) -{ - const unsigned char *at; - - /* - * Check a few things which do not belong to this test. - * They should be covered by other tests. - */ - if (!trace) - return -1; - - if (!trace->read) - return -1; - - if (to < from) - return -1; - - if (from < trace->ds.begin) - return -1; - - if (trace->ds.end < to) - return -1; - - if (!trace->ds.size) - return -1; - - /* Now to the test itself. */ - for (at = from; (void *)at < to; at += trace->ds.size) { - struct bts_struct bts; - unsigned long index; - int error; - - if (((void *)at - trace->ds.begin) % trace->ds.size) { - printk(KERN_CONT - "read from non-integer index..."); - return -1; - } - index = ((void *)at - trace->ds.begin) / trace->ds.size; - - memset(&bts, 0, sizeof(bts)); - error = trace->read(tracer, at, &bts); - if (error < 0) { - printk(KERN_CONT - "error reading bts trace at [%lu] (0x%p)...", - index, at); - return error; - } - - switch (bts.qualifier) { - case BTS_BRANCH: - break; - default: - printk(KERN_CONT - "unexpected bts entry %llu at [%lu] (0x%p)...", - bts.qualifier, index, at); - return -1; - } - } - - return 0; -} - -static void ds_selftest_bts_cpu(void *arg) -{ - struct ds_selftest_bts_conf *conf = arg; - const struct bts_trace *trace; - void *top; - - if (IS_ERR(conf->tracer)) { - conf->error = PTR_ERR(conf->tracer); - conf->tracer = NULL; - - printk(KERN_CONT - "initialization failed (err: %d)...", conf->error); - return; - } - - /* We should meanwhile have enough trace. */ - conf->error = conf->suspend(conf->tracer); - if (conf->error < 0) - return; - - /* Let's see if we can access the trace. */ - trace = ds_read_bts(conf->tracer); - - conf->error = ds_selftest_bts_consistency(trace); - if (conf->error < 0) - return; - - /* If everything went well, we should have a few trace entries. */ - if (trace->ds.top == trace->ds.begin) { - /* - * It is possible but highly unlikely that we got a - * buffer overflow and end up at exactly the same - * position we started from. - * Let's issue a warning, but continue. - */ - printk(KERN_CONT "no trace/overflow..."); - } - - /* Let's try to read the trace we collected. */ - conf->error = - ds_selftest_bts_read(conf->tracer, trace, - trace->ds.begin, trace->ds.top); - if (conf->error < 0) - return; - - /* - * Let's read the trace again. - * Since we suspended tracing, we should get the same result. - */ - top = trace->ds.top; - - trace = ds_read_bts(conf->tracer); - conf->error = ds_selftest_bts_consistency(trace); - if (conf->error < 0) - return; - - if (top != trace->ds.top) { - printk(KERN_CONT "suspend not working..."); - conf->error = -1; - return; - } - - /* Let's collect some more trace - see if resume is working. */ - conf->error = conf->resume(conf->tracer); - if (conf->error < 0) - return; - - conf->error = conf->suspend(conf->tracer); - if (conf->error < 0) - return; - - trace = ds_read_bts(conf->tracer); - - conf->error = ds_selftest_bts_consistency(trace); - if (conf->error < 0) - return; - - if (trace->ds.top == top) { - /* - * It is possible but highly unlikely that we got a - * buffer overflow and end up at exactly the same - * position we started from. - * Let's issue a warning and check the full trace. - */ - printk(KERN_CONT - "no resume progress/overflow..."); - - conf->error = - ds_selftest_bts_read(conf->tracer, trace, - trace->ds.begin, trace->ds.end); - } else if (trace->ds.top < top) { - /* - * We had a buffer overflow - the entire buffer should - * contain trace records. - */ - conf->error = - ds_selftest_bts_read(conf->tracer, trace, - trace->ds.begin, trace->ds.end); - } else { - /* - * It is quite likely that the buffer did not overflow. - * Let's just check the delta trace. - */ - conf->error = - ds_selftest_bts_read(conf->tracer, trace, top, - trace->ds.top); - } - if (conf->error < 0) - return; - - conf->error = 0; -} - -static int ds_suspend_bts_wrap(struct bts_tracer *tracer) -{ - ds_suspend_bts(tracer); - return 0; -} - -static int ds_resume_bts_wrap(struct bts_tracer *tracer) -{ - ds_resume_bts(tracer); - return 0; -} - -static void ds_release_bts_noirq_wrap(void *tracer) -{ - (void)ds_release_bts_noirq(tracer); -} - -static int ds_selftest_bts_bad_release_noirq(int cpu, - struct bts_tracer *tracer) -{ - int error = -EPERM; - - /* Try to release the tracer on the wrong cpu. */ - get_cpu(); - if (cpu != smp_processor_id()) { - error = ds_release_bts_noirq(tracer); - if (error != -EPERM) - printk(KERN_CONT "release on wrong cpu..."); - } - put_cpu(); - - return error ? 0 : -1; -} - -static int ds_selftest_bts_bad_request_cpu(int cpu, void *buffer) -{ - struct bts_tracer *tracer; - int error; - - /* Try to request cpu tracing while task tracing is active. */ - tracer = ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE, NULL, - (size_t)-1, BTS_KERNEL); - error = PTR_ERR(tracer); - if (!IS_ERR(tracer)) { - ds_release_bts(tracer); - error = 0; - } - - if (error != -EPERM) - printk(KERN_CONT "cpu/task tracing overlap..."); - - return error ? 0 : -1; -} - -static int ds_selftest_bts_bad_request_task(void *buffer) -{ - struct bts_tracer *tracer; - int error; - - /* Try to request cpu tracing while task tracing is active. */ - tracer = ds_request_bts_task(current, buffer, BUFFER_SIZE, NULL, - (size_t)-1, BTS_KERNEL); - error = PTR_ERR(tracer); - if (!IS_ERR(tracer)) { - error = 0; - ds_release_bts(tracer); - } - - if (error != -EPERM) - printk(KERN_CONT "task/cpu tracing overlap..."); - - return error ? 0 : -1; -} - -int ds_selftest_bts(void) -{ - struct ds_selftest_bts_conf conf; - unsigned char buffer[BUFFER_SIZE], *small_buffer; - unsigned long irq; - int cpu; - - printk(KERN_INFO "[ds] bts selftest..."); - conf.error = 0; - - small_buffer = (unsigned char *)ALIGN((unsigned long)buffer, 8) + 8; - - get_online_cpus(); - for_each_online_cpu(cpu) { - conf.suspend = ds_suspend_bts_wrap; - conf.resume = ds_resume_bts_wrap; - conf.tracer = - ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE, - NULL, (size_t)-1, BTS_KERNEL); - ds_selftest_bts_cpu(&conf); - if (conf.error >= 0) - conf.error = ds_selftest_bts_bad_request_task(buffer); - ds_release_bts(conf.tracer); - if (conf.error < 0) - goto out; - - conf.suspend = ds_suspend_bts_noirq; - conf.resume = ds_resume_bts_noirq; - conf.tracer = - ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE, - NULL, (size_t)-1, BTS_KERNEL); - smp_call_function_single(cpu, ds_selftest_bts_cpu, &conf, 1); - if (conf.error >= 0) { - conf.error = - ds_selftest_bts_bad_release_noirq(cpu, - conf.tracer); - /* We must not release the tracer twice. */ - if (conf.error < 0) - conf.tracer = NULL; - } - if (conf.error >= 0) - conf.error = ds_selftest_bts_bad_request_task(buffer); - smp_call_function_single(cpu, ds_release_bts_noirq_wrap, - conf.tracer, 1); - if (conf.error < 0) - goto out; - } - - conf.suspend = ds_suspend_bts_wrap; - conf.resume = ds_resume_bts_wrap; - conf.tracer = - ds_request_bts_task(current, buffer, BUFFER_SIZE, - NULL, (size_t)-1, BTS_KERNEL); - ds_selftest_bts_cpu(&conf); - if (conf.error >= 0) - conf.error = ds_selftest_bts_bad_request_cpu(0, buffer); - ds_release_bts(conf.tracer); - if (conf.error < 0) - goto out; - - conf.suspend = ds_suspend_bts_noirq; - conf.resume = ds_resume_bts_noirq; - conf.tracer = - ds_request_bts_task(current, small_buffer, SMALL_BUFFER_SIZE, - NULL, (size_t)-1, BTS_KERNEL); - local_irq_save(irq); - ds_selftest_bts_cpu(&conf); - if (conf.error >= 0) - conf.error = ds_selftest_bts_bad_request_cpu(0, buffer); - ds_release_bts_noirq(conf.tracer); - local_irq_restore(irq); - if (conf.error < 0) - goto out; - - conf.error = 0; - out: - put_online_cpus(); - printk(KERN_CONT "%s.\n", (conf.error ? "failed" : "passed")); - - return conf.error; -} - -int ds_selftest_pebs(void) -{ - return 0; -} diff --git a/arch/x86/kernel/ds_selftest.h b/arch/x86/kernel/ds_selftest.h deleted file mode 100644 index 2ba8745c666..00000000000 --- a/arch/x86/kernel/ds_selftest.h +++ /dev/null @@ -1,15 +0,0 @@ -/* - * Debug Store support - selftest - * - * - * Copyright (C) 2009 Intel Corporation. - * Markus Metzger <markus.t.metzger@intel.com>, 2009 - */ - -#ifdef CONFIG_X86_DS_SELFTEST -extern int ds_selftest_bts(void); -extern int ds_selftest_pebs(void); -#else -static inline int ds_selftest_bts(void) { return 0; } -static inline int ds_selftest_pebs(void) { return 0; } -#endif diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 6d817554780..6e8752c1bd5 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -18,7 +18,6 @@ #include <asm/stacktrace.h> -#include "dumpstack.h" int panic_on_unrecovered_nmi; int panic_on_io_nmi; @@ -224,11 +223,6 @@ unsigned __kprobes long oops_begin(void) int cpu; unsigned long flags; - /* notify the hw-branch tracer so it may disable tracing and - add the last trace to the trace buffer - - the earlier this happens, the more useful the trace. */ - trace_hw_branch_oops(); - oops_enter(); /* racy, but better than risking deadlock. */ diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h deleted file mode 100644 index e1a93be4fd4..00000000000 --- a/arch/x86/kernel/dumpstack.h +++ /dev/null @@ -1,56 +0,0 @@ -/* - * Copyright (C) 1991, 1992 Linus Torvalds - * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs - */ - -#ifndef DUMPSTACK_H -#define DUMPSTACK_H - -#ifdef CONFIG_X86_32 -#define STACKSLOTS_PER_LINE 8 -#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :) -#else -#define STACKSLOTS_PER_LINE 4 -#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) -#endif - -#include <linux/uaccess.h> - -extern void -show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl); - -extern void -show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl); - -extern unsigned int code_bytes; - -/* The form of the top of the frame on the stack */ -struct stack_frame { - struct stack_frame *next_frame; - unsigned long return_address; -}; - -struct stack_frame_ia32 { - u32 next_frame; - u32 return_address; -}; - -static inline unsigned long rewind_frame_pointer(int n) -{ - struct stack_frame *frame; - - get_bp(frame); - -#ifdef CONFIG_FRAME_POINTER - while (n--) { - if (probe_kernel_address(&frame->next_frame, frame)) - break; - } -#endif - - return (unsigned long)frame; -} - -#endif /* DUMPSTACK_H */ diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 11540a189d9..0f6376ffa2d 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -16,8 +16,6 @@ #include <asm/stacktrace.h> -#include "dumpstack.h" - void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 272c9f1f05f..57a21f11c79 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -16,7 +16,6 @@ #include <asm/stacktrace.h> -#include "dumpstack.h" #define N_EXCEPTION_STACKS_END \ (N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 7bca3c6a02f..0d6fc71bedb 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -729,7 +729,7 @@ static int __init e820_mark_nvs_memory(void) struct e820entry *ei = &e820.map[i]; if (ei->type == E820_NVS) - hibernate_nvs_register(ei->addr, ei->size); + suspend_nvs_register(ei->addr, ei->size); } return 0; diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index ebdb85cf268..e5cc7e82e60 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -18,6 +18,7 @@ #include <asm/apic.h> #include <asm/iommu.h> #include <asm/gart.h> +#include <asm/hpet.h> static void __init fix_hypertransport_config(int num, int slot, int func) { @@ -191,6 +192,21 @@ static void __init ati_bugs_contd(int num, int slot, int func) } #endif +/* + * Force the read back of the CMP register in hpet_next_event() + * to work around the problem that the CMP register write seems to be + * delayed. See hpet_next_event() for details. + * + * We do this on all SMBUS incarnations for now until we have more + * information about the affected chipsets. + */ +static void __init ati_hpet_bugs(int num, int slot, int func) +{ +#ifdef CONFIG_HPET_TIMER + hpet_readback_cmp = 1; +#endif +} + #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 #define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED) @@ -220,6 +236,8 @@ static struct chipset early_qrk[] __initdata = { PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs }, { PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd }, + { PCI_VENDOR_ID_ATI, PCI_ANY_ID, + PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_hpet_bugs }, {} }; diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index b9c830c12b4..fa99bae75ac 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -41,6 +41,14 @@ static void early_vga_write(struct console *con, const char *str, unsigned n) writew(0x720, VGABASE + 2*(max_xpos*j + i)); current_ypos = max_ypos-1; } +#ifdef CONFIG_KGDB_KDB + if (c == '\b') { + if (current_xpos > 0) + current_xpos--; + } else if (c == '\r') { + current_xpos = 0; + } else +#endif if (c == '\n') { current_xpos = 0; current_ypos++; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 44a8e0dc673..227d00920d2 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -53,6 +53,7 @@ #include <asm/processor-flags.h> #include <asm/ftrace.h> #include <asm/irq_vectors.h> +#include <asm/cpufeature.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> @@ -610,14 +611,14 @@ ldt_ss: * compensating for the offset by changing to the ESPFIX segment with * a base address that matches for the difference. */ +#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8) mov %esp, %edx /* load kernel esp */ mov PT_OLDESP(%esp), %eax /* load userspace esp */ mov %dx, %ax /* eax: new kernel esp */ sub %eax, %edx /* offset (low word is 0) */ - PER_CPU(gdt_page, %ebx) shr $16, %edx - mov %dl, GDT_ENTRY_ESPFIX_SS * 8 + 4(%ebx) /* bits 16..23 */ - mov %dh, GDT_ENTRY_ESPFIX_SS * 8 + 7(%ebx) /* bits 24..31 */ + mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */ + mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */ pushl $__ESPFIX_SS CFI_ADJUST_CFA_OFFSET 4 push %eax /* new kernel esp */ @@ -790,9 +791,8 @@ ptregs_clone: * normal stack and adjusts ESP with the matching offset. */ /* fixup the stack */ - PER_CPU(gdt_page, %ebx) - mov GDT_ENTRY_ESPFIX_SS * 8 + 4(%ebx), %al /* bits 16..23 */ - mov GDT_ENTRY_ESPFIX_SS * 8 + 7(%ebx), %ah /* bits 24..31 */ + mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ + mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ shl $16, %eax addl %esp, %eax /* the adjusted stack pointer */ pushl $__KERNEL_DS @@ -905,7 +905,25 @@ ENTRY(simd_coprocessor_error) RING0_INT_FRAME pushl $0 CFI_ADJUST_CFA_OFFSET 4 +#ifdef CONFIG_X86_INVD_BUG + /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ +661: pushl $do_general_protection +662: +.section .altinstructions,"a" + .balign 4 + .long 661b + .long 663f + .word X86_FEATURE_XMM + .byte 662b-661b + .byte 664f-663f +.previous +.section .altinstr_replacement,"ax" +663: pushl $do_simd_coprocessor_error +664: +.previous +#else pushl $do_simd_coprocessor_error +#endif CFI_ADJUST_CFA_OFFSET 4 jmp error_code CFI_ENDPROC @@ -1147,6 +1165,9 @@ ENTRY(xen_failsafe_callback) .previous ENDPROC(xen_failsafe_callback) +BUILD_INTERRUPT3(xen_hvm_callback_vector, XEN_HVM_EVTCHN_CALLBACK, + xen_evtchn_do_upcall) + #endif /* CONFIG_XEN */ #ifdef CONFIG_FUNCTION_TRACER diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 0697ff13983..c5ea5cdbe7b 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -571,8 +571,8 @@ auditsys: * masked off. */ sysret_audit: - movq %rax,%rsi /* second arg, syscall return value */ - cmpq $0,%rax /* is it < 0? */ + movq RAX-ARGOFFSET(%rsp),%rsi /* second arg, syscall return value */ + cmpq $0,%rsi /* is it < 0? */ setl %al /* 1 if so, 0 if not */ movzbl %al,%edi /* zero-extend that into %edi */ inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */ @@ -1065,6 +1065,7 @@ ENTRY(\sym) END(\sym) .endm +#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8) .macro paranoidzeroentry_ist sym do_sym ist ENTRY(\sym) INTR_FRAME @@ -1076,10 +1077,9 @@ ENTRY(\sym) TRACE_IRQS_OFF movq %rsp,%rdi /* pt_regs pointer */ xorl %esi,%esi /* no error code */ - PER_CPU(init_tss, %r12) - subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%r12) + subq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist) call \do_sym - addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%r12) + addq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist) jmp paranoid_exit /* %ebx: no swapgs flag */ CFI_ENDPROC END(\sym) @@ -1329,6 +1329,9 @@ ENTRY(xen_failsafe_callback) CFI_ENDPROC END(xen_failsafe_callback) +apicinterrupt XEN_HVM_EVTCHN_CALLBACK \ + xen_hvm_callback_vector xen_evtchn_do_upcall + #endif /* CONFIG_XEN */ /* diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index b2e24603739..784360c0625 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -20,7 +20,7 @@ static void __init i386_default_early_setup(void) { - /* Initilize 32bit specific setup functions */ + /* Initialize 32bit specific setup functions */ x86_init.resources.probe_roms = probe_roms; x86_init.resources.reserve_resources = i386_reserve_resources; x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 37c3d4b17d8..ff4c453e13f 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -131,6 +131,12 @@ ENTRY(startup_32) movsl 1: +#ifdef CONFIG_OLPC_OPENFIRMWARE + /* save OFW's pgdir table for later use when calling into OFW */ + movl %cr3, %eax + movl %eax, pa(olpc_ofw_pgd) +#endif + #ifdef CONFIG_PARAVIRT /* This is can only trip for a broken bootloader... */ cmpw $0x207, pa(boot_params + BP_version) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 3d1e6f16b7a..239046bd447 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -234,9 +234,8 @@ ENTRY(secondary_startup_64) * init data section till per cpu areas are set up. */ movl $MSR_GS_BASE,%ecx - movq initial_gs(%rip),%rax - movq %rax,%rdx - shrq $32,%rdx + movl initial_gs(%rip),%eax + movl initial_gs+4(%rip),%edx wrmsr /* esi is pointer to real mode structure with interesting info. diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 23b4ecdffa9..33dbcc4ec5f 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -16,7 +16,6 @@ #include <asm/hpet.h> #define HPET_MASK CLOCKSOURCE_MASK(32) -#define HPET_SHIFT 22 /* FSEC = 10^-15 NSEC = 10^-9 */ @@ -36,6 +35,7 @@ unsigned long hpet_address; u8 hpet_blockid; /* OS timer block num */ u8 hpet_msi_disable; +u8 hpet_readback_cmp; #ifdef CONFIG_PCI_MSI static unsigned long hpet_num_timers; @@ -395,19 +395,23 @@ static int hpet_next_event(unsigned long delta, * at that point and we would wait for the next hpet interrupt * forever. We found out that reading the CMP register back * forces the transfer so we can rely on the comparison with - * the counter register below. If the read back from the - * compare register does not match the value we programmed - * then we might have a real hardware problem. We can not do - * much about it here, but at least alert the user/admin with - * a prominent warning. - * An erratum on some chipsets (ICH9,..), results in comparator read - * immediately following a write returning old value. Workaround - * for this is to read this value second time, when first - * read returns old value. + * the counter register below. + * + * That works fine on those ATI chipsets, but on newer Intel + * chipsets (ICH9...) this triggers due to an erratum: Reading + * the comparator immediately following a write is returning + * the old value. + * + * We restrict the read back to the affected ATI chipsets (set + * by quirks) and also run it with hpet=verbose for debugging + * purposes. */ - if (unlikely((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt)) { - WARN_ONCE(hpet_readl(HPET_Tn_CMP(timer)) != cnt, - KERN_WARNING "hpet: compare register read back failed.\n"); + if (hpet_readback_cmp || hpet_verbose) { + u32 cmp = hpet_readl(HPET_Tn_CMP(timer)); + + if (cmp != cnt) + printk_once(KERN_WARNING + "hpet: compare register read back failed.\n"); } return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0; @@ -782,7 +786,6 @@ static struct clocksource clocksource_hpet = { .rating = 250, .read = read_hpet, .mask = HPET_MASK, - .shift = HPET_SHIFT, .flags = CLOCK_SOURCE_IS_CONTINUOUS, .resume = hpet_resume_counter, #ifdef CONFIG_X86_64 @@ -793,6 +796,7 @@ static struct clocksource clocksource_hpet = { static int hpet_clocksource_register(void) { u64 start, now; + u64 hpet_freq; cycle_t t1; /* Start the counter */ @@ -827,9 +831,15 @@ static int hpet_clocksource_register(void) * mult = (hpet_period * 2^shift)/10^6 * mult = (hpet_period << shift)/FSEC_PER_NSEC */ - clocksource_hpet.mult = div_sc(hpet_period, FSEC_PER_NSEC, HPET_SHIFT); - clocksource_register(&clocksource_hpet); + /* Need to convert hpet_period (fsec/cyc) to cyc/sec: + * + * cyc/sec = FSEC_PER_SEC/hpet_period(fsec/cyc) + * cyc/sec = (FSEC_PER_NSEC * NSEC_PER_SEC)/hpet_period + */ + hpet_freq = FSEC_PER_NSEC * NSEC_PER_SEC; + do_div(hpet_freq, hpet_period); + clocksource_register_hz(&clocksource_hpet, (u32)hpet_freq); return 0; } @@ -959,7 +969,7 @@ fs_initcall(hpet_late_init); void hpet_disable(void) { - if (is_hpet_capable()) { + if (is_hpet_capable() && hpet_virt_address) { unsigned int cfg = hpet_readl(HPET_CFG); if (hpet_legacy_int_enabled) { diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index d6cc065f519..a474ec37c32 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -189,25 +189,16 @@ static int get_hbp_len(u8 hbp_len) } /* - * Check for virtual address in user space. - */ -int arch_check_va_in_userspace(unsigned long va, u8 hbp_len) -{ - unsigned int len; - - len = get_hbp_len(hbp_len); - - return (va <= TASK_SIZE - len); -} - -/* * Check for virtual address in kernel space. */ -static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len) +int arch_check_bp_in_kernelspace(struct perf_event *bp) { unsigned int len; + unsigned long va; + struct arch_hw_breakpoint *info = counter_arch_bp(bp); - len = get_hbp_len(hbp_len); + va = info->address; + len = get_hbp_len(info->len); return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -217,6 +208,9 @@ int arch_bp_generic_fields(int x86_len, int x86_type, { /* Len */ switch (x86_len) { + case X86_BREAKPOINT_LEN_X: + *gen_len = sizeof(long); + break; case X86_BREAKPOINT_LEN_1: *gen_len = HW_BREAKPOINT_LEN_1; break; @@ -260,6 +254,29 @@ static int arch_build_bp_info(struct perf_event *bp) info->address = bp->attr.bp_addr; + /* Type */ + switch (bp->attr.bp_type) { + case HW_BREAKPOINT_W: + info->type = X86_BREAKPOINT_WRITE; + break; + case HW_BREAKPOINT_W | HW_BREAKPOINT_R: + info->type = X86_BREAKPOINT_RW; + break; + case HW_BREAKPOINT_X: + info->type = X86_BREAKPOINT_EXECUTE; + /* + * x86 inst breakpoints need to have a specific undefined len. + * But we still need to check userspace is not trying to setup + * an unsupported length, to get a range breakpoint for example. + */ + if (bp->attr.bp_len == sizeof(long)) { + info->len = X86_BREAKPOINT_LEN_X; + return 0; + } + default: + return -EINVAL; + } + /* Len */ switch (bp->attr.bp_len) { case HW_BREAKPOINT_LEN_1: @@ -280,28 +297,12 @@ static int arch_build_bp_info(struct perf_event *bp) return -EINVAL; } - /* Type */ - switch (bp->attr.bp_type) { - case HW_BREAKPOINT_W: - info->type = X86_BREAKPOINT_WRITE; - break; - case HW_BREAKPOINT_W | HW_BREAKPOINT_R: - info->type = X86_BREAKPOINT_RW; - break; - case HW_BREAKPOINT_X: - info->type = X86_BREAKPOINT_EXECUTE; - break; - default: - return -EINVAL; - } - return 0; } /* * Validate the arch-specific HW Breakpoint register settings */ -int arch_validate_hwbkpt_settings(struct perf_event *bp, - struct task_struct *tsk) +int arch_validate_hwbkpt_settings(struct perf_event *bp) { struct arch_hw_breakpoint *info = counter_arch_bp(bp); unsigned int align; @@ -314,17 +315,10 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp, ret = -EINVAL; - if (info->type == X86_BREAKPOINT_EXECUTE) - /* - * Ptrace-refactoring code - * For now, we'll allow instruction breakpoint only for user-space - * addresses - */ - if ((!arch_check_va_in_userspace(info->address, info->len)) && - info->len != X86_BREAKPOINT_EXECUTE) - return ret; - switch (info->len) { + case X86_BREAKPOINT_LEN_X: + align = sizeof(long) -1; + break; case X86_BREAKPOINT_LEN_1: align = 0; break; @@ -350,15 +344,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp, if (info->address & align) return -EINVAL; - /* Check that the virtual address is in the proper range */ - if (tsk) { - if (!arch_check_va_in_userspace(info->address, info->len)) - return -EFAULT; - } else { - if (!arch_check_va_in_kernelspace(info->address, info->len)) - return -EFAULT; - } - return 0; } @@ -495,6 +480,13 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args) perf_bp_event(bp, args->regs); + /* + * Set up resume flag to avoid breakpoint recursion when + * returning back to origin. + */ + if (bp->hw.info.type == X86_BREAKPOINT_EXECUTE) + args->regs->flags |= X86_EFLAGS_RF; + rcu_read_unlock(); } /* diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 54c31c28548..1f11f5ce668 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -59,18 +59,18 @@ void __cpuinit mxcsr_feature_mask_init(void) stts(); } -void __cpuinit init_thread_xstate(void) +static void __cpuinit init_thread_xstate(void) { + /* + * Note that xstate_size might be overwriten later during + * xsave_init(). + */ + if (!HAVE_HWFP) { xstate_size = sizeof(struct i387_soft_struct); return; } - if (cpu_has_xsave) { - xsave_cntxt_init(); - return; - } - if (cpu_has_fxsr) xstate_size = sizeof(struct i387_fxsave_struct); #ifdef CONFIG_X86_32 @@ -84,6 +84,7 @@ void __cpuinit init_thread_xstate(void) * Called at bootup to set up the initial FPU state that is later cloned * into all processes. */ + void __cpuinit fpu_init(void) { unsigned long oldcr0 = read_cr0(); @@ -93,74 +94,77 @@ void __cpuinit fpu_init(void) write_cr0(oldcr0 & ~(X86_CR0_TS|X86_CR0_EM)); /* clear TS and EM */ - /* - * Boot processor to setup the FP and extended state context info. - */ if (!smp_processor_id()) init_thread_xstate(); - xsave_init(); mxcsr_feature_mask_init(); /* clean state in init */ - if (cpu_has_xsave) - current_thread_info()->status = TS_XSAVE; - else - current_thread_info()->status = 0; + current_thread_info()->status = 0; clear_used_math(); } -#endif /* CONFIG_X86_64 */ -/* - * The _current_ task is using the FPU for the first time - * so initialize it and set the mxcsr to its default - * value at reset if we support XMM instructions and then - * remeber the current task has used the FPU. - */ -int init_fpu(struct task_struct *tsk) +#else /* CONFIG_X86_64 */ + +void __cpuinit fpu_init(void) { - if (tsk_used_math(tsk)) { - if (HAVE_HWFP && tsk == current) - unlazy_fpu(tsk); - return 0; - } + if (!smp_processor_id()) + init_thread_xstate(); +} - /* - * Memory allocation at the first usage of the FPU and other state. - */ - if (!tsk->thread.xstate) { - tsk->thread.xstate = kmem_cache_alloc(task_xstate_cachep, - GFP_KERNEL); - if (!tsk->thread.xstate) - return -ENOMEM; - } +#endif /* CONFIG_X86_32 */ +void fpu_finit(struct fpu *fpu) +{ #ifdef CONFIG_X86_32 if (!HAVE_HWFP) { - memset(tsk->thread.xstate, 0, xstate_size); - finit_task(tsk); - set_stopped_child_used_math(tsk); - return 0; + finit_soft_fpu(&fpu->state->soft); + return; } #endif if (cpu_has_fxsr) { - struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave; + struct i387_fxsave_struct *fx = &fpu->state->fxsave; memset(fx, 0, xstate_size); fx->cwd = 0x37f; if (cpu_has_xmm) fx->mxcsr = MXCSR_DEFAULT; } else { - struct i387_fsave_struct *fp = &tsk->thread.xstate->fsave; + struct i387_fsave_struct *fp = &fpu->state->fsave; memset(fp, 0, xstate_size); fp->cwd = 0xffff037fu; fp->swd = 0xffff0000u; fp->twd = 0xffffffffu; fp->fos = 0xffff0000u; } +} +EXPORT_SYMBOL_GPL(fpu_finit); + +/* + * The _current_ task is using the FPU for the first time + * so initialize it and set the mxcsr to its default + * value at reset if we support XMM instructions and then + * remeber the current task has used the FPU. + */ +int init_fpu(struct task_struct *tsk) +{ + int ret; + + if (tsk_used_math(tsk)) { + if (HAVE_HWFP && tsk == current) + unlazy_fpu(tsk); + return 0; + } + /* - * Only the device not available exception or ptrace can call init_fpu. + * Memory allocation at the first usage of the FPU and other state. */ + ret = fpu_alloc(&tsk->thread.fpu); + if (ret) + return ret; + + fpu_finit(&tsk->thread.fpu); + set_stopped_child_used_math(tsk); return 0; } @@ -193,8 +197,10 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; + sanitize_i387_state(target); + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.xstate->fxsave, 0, -1); + &target->thread.fpu.state->fxsave, 0, -1); } int xfpregs_set(struct task_struct *target, const struct user_regset *regset, @@ -210,20 +216,22 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; + sanitize_i387_state(target); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.xstate->fxsave, 0, -1); + &target->thread.fpu.state->fxsave, 0, -1); /* * mxcsr reserved bits must be masked to zero for security reasons. */ - target->thread.xstate->fxsave.mxcsr &= mxcsr_feature_mask; + target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask; /* * update the header bits in the xsave header, indicating the * presence of FP and SSE state. */ if (cpu_has_xsave) - target->thread.xstate->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE; + target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE; return ret; } @@ -246,14 +254,14 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, * memory layout in the thread struct, so that we can copy the entire * xstateregs to the user using one user_regset_copyout(). */ - memcpy(&target->thread.xstate->fxsave.sw_reserved, + memcpy(&target->thread.fpu.state->fxsave.sw_reserved, xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes)); /* * Copy the xstate memory layout. */ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.xstate->xsave, 0, -1); + &target->thread.fpu.state->xsave, 0, -1); return ret; } @@ -272,14 +280,14 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, return ret; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.xstate->xsave, 0, -1); + &target->thread.fpu.state->xsave, 0, -1); /* * mxcsr reserved bits must be masked to zero for security reasons. */ - target->thread.xstate->fxsave.mxcsr &= mxcsr_feature_mask; + target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask; - xsave_hdr = &target->thread.xstate->xsave.xsave_hdr; + xsave_hdr = &target->thread.fpu.state->xsave.xsave_hdr; xsave_hdr->xstate_bv &= pcntxt_mask; /* @@ -365,7 +373,7 @@ static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave) static void convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) { - struct i387_fxsave_struct *fxsave = &tsk->thread.xstate->fxsave; + struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; struct _fpreg *to = (struct _fpreg *) &env->st_space[0]; struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0]; int i; @@ -405,7 +413,7 @@ static void convert_to_fxsr(struct task_struct *tsk, const struct user_i387_ia32_struct *env) { - struct i387_fxsave_struct *fxsave = &tsk->thread.xstate->fxsave; + struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; struct _fpreg *from = (struct _fpreg *) &env->st_space[0]; struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0]; int i; @@ -445,10 +453,12 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, if (!cpu_has_fxsr) { return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.xstate->fsave, 0, + &target->thread.fpu.state->fsave, 0, -1); } + sanitize_i387_state(target); + if (kbuf && pos == 0 && count == sizeof(env)) { convert_from_fxsr(kbuf, target); return 0; @@ -470,12 +480,14 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; + sanitize_i387_state(target); + if (!HAVE_HWFP) return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); if (!cpu_has_fxsr) { return user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.xstate->fsave, 0, -1); + &target->thread.fpu.state->fsave, 0, -1); } if (pos > 0 || count < sizeof(env)) @@ -490,7 +502,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, * presence of FP. */ if (cpu_has_xsave) - target->thread.xstate->xsave.xsave_hdr.xstate_bv |= XSTATE_FP; + target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FP; return ret; } @@ -501,7 +513,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf) { struct task_struct *tsk = current; - struct i387_fsave_struct *fp = &tsk->thread.xstate->fsave; + struct i387_fsave_struct *fp = &tsk->thread.fpu.state->fsave; fp->status = fp->swd; if (__copy_to_user(buf, fp, sizeof(struct i387_fsave_struct))) @@ -512,7 +524,7 @@ static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf) static int save_i387_fxsave(struct _fpstate_ia32 __user *buf) { struct task_struct *tsk = current; - struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave; + struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave; struct user_i387_ia32_struct env; int err = 0; @@ -536,6 +548,9 @@ static int save_i387_xsave(void __user *buf) struct _fpstate_ia32 __user *fx = buf; int err = 0; + + sanitize_i387_state(tsk); + /* * For legacy compatible, we always set FP/SSE bits in the bit * vector while saving the state to the user context. @@ -547,7 +562,7 @@ static int save_i387_xsave(void __user *buf) * header as well as change any contents in the memory layout. * xrestore as part of sigreturn will capture all the changes. */ - tsk->thread.xstate->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE; + tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE; if (save_i387_fxsave(fx) < 0) return -1; @@ -599,7 +614,7 @@ static inline int restore_i387_fsave(struct _fpstate_ia32 __user *buf) { struct task_struct *tsk = current; - return __copy_from_user(&tsk->thread.xstate->fsave, buf, + return __copy_from_user(&tsk->thread.fpu.state->fsave, buf, sizeof(struct i387_fsave_struct)); } @@ -610,10 +625,10 @@ static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf, struct user_i387_ia32_struct env; int err; - err = __copy_from_user(&tsk->thread.xstate->fxsave, &buf->_fxsr_env[0], + err = __copy_from_user(&tsk->thread.fpu.state->fxsave, &buf->_fxsr_env[0], size); /* mxcsr reserved bits must be masked to zero for security reasons */ - tsk->thread.xstate->fxsave.mxcsr &= mxcsr_feature_mask; + tsk->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask; if (err || __copy_from_user(&env, buf, sizeof(env))) return 1; convert_to_fxsr(tsk, &env); @@ -629,7 +644,7 @@ static int restore_i387_xsave(void __user *buf) struct i387_fxsave_struct __user *fx = (struct i387_fxsave_struct __user *) &fx_user->_fxsr_env[0]; struct xsave_hdr_struct *xsave_hdr = - ¤t->thread.xstate->xsave.xsave_hdr; + ¤t->thread.fpu.state->xsave.xsave_hdr; u64 mask; int err; diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 23c167925a5..2dfd3159744 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -16,7 +16,7 @@ #include <asm/hpet.h> #include <asm/smp.h> -DEFINE_SPINLOCK(i8253_lock); +DEFINE_RAW_SPINLOCK(i8253_lock); EXPORT_SYMBOL(i8253_lock); /* @@ -33,7 +33,7 @@ struct clock_event_device *global_clock_event; static void init_pit_timer(enum clock_event_mode mode, struct clock_event_device *evt) { - spin_lock(&i8253_lock); + raw_spin_lock(&i8253_lock); switch (mode) { case CLOCK_EVT_MODE_PERIODIC: @@ -62,7 +62,7 @@ static void init_pit_timer(enum clock_event_mode mode, /* Nothing to do here */ break; } - spin_unlock(&i8253_lock); + raw_spin_unlock(&i8253_lock); } /* @@ -72,10 +72,10 @@ static void init_pit_timer(enum clock_event_mode mode, */ static int pit_next_event(unsigned long delta, struct clock_event_device *evt) { - spin_lock(&i8253_lock); + raw_spin_lock(&i8253_lock); outb_pit(delta & 0xff , PIT_CH0); /* LSB */ outb_pit(delta >> 8 , PIT_CH0); /* MSB */ - spin_unlock(&i8253_lock); + raw_spin_unlock(&i8253_lock); return 0; } @@ -130,7 +130,7 @@ static cycle_t pit_read(struct clocksource *cs) int count; u32 jifs; - spin_lock_irqsave(&i8253_lock, flags); + raw_spin_lock_irqsave(&i8253_lock, flags); /* * Although our caller may have the read side of xtime_lock, * this is now a seqlock, and we are cheating in this routine @@ -176,7 +176,7 @@ static cycle_t pit_read(struct clocksource *cs) old_count = count; old_jifs = jifs; - spin_unlock_irqrestore(&i8253_lock, flags); + raw_spin_unlock_irqrestore(&i8253_lock, flags); count = (LATCH - 1) - count; diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 7c9f02c130f..cafa7c80ac9 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -276,16 +276,6 @@ static struct sys_device device_i8259A = { .cls = &i8259_sysdev_class, }; -static int __init i8259A_init_sysfs(void) -{ - int error = sysdev_class_register(&i8259_sysdev_class); - if (!error) - error = sysdev_register(&device_i8259A); - return error; -} - -device_initcall(i8259A_init_sysfs); - static void mask_8259A(void) { unsigned long flags; @@ -407,3 +397,18 @@ struct legacy_pic default_legacy_pic = { }; struct legacy_pic *legacy_pic = &default_legacy_pic; + +static int __init i8259A_init_sysfs(void) +{ + int error; + + if (legacy_pic != &default_legacy_pic) + return 0; + + error = sysdev_class_register(&i8259_sysdev_class); + if (!error) + error = sysdev_register(&device_i8259A); + return error; +} + +device_initcall(i8259A_init_sysfs); diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c index 3a54dcb9cd0..43e9ccf4494 100644 --- a/arch/x86/kernel/init_task.c +++ b/arch/x86/kernel/init_task.c @@ -34,7 +34,7 @@ EXPORT_SYMBOL(init_task); /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, * no more per-task TSS's. The TSS size is kept cacheline-aligned - * so they are allowed to end up in the .data.cacheline_aligned + * so they are allowed to end up in the .data..cacheline_aligned * section. Since TSS's are completely CPU-local, we want them * on exact cacheline boundaries, to eliminate cacheline ping-pong. */ diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 0ed2d300cd4..990ae7cfc57 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -60,7 +60,7 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id) outb(0, 0xF0); if (ignore_fpu_irq || !boot_cpu_data.hard_math) return IRQ_NONE; - math_error((void __user *)get_irq_regs()->ip); + math_error(get_irq_regs(), 0, 16); return IRQ_HANDLED; } diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index b2258ca9100..ef10940e1af 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -47,69 +47,96 @@ #include <asm/debugreg.h> #include <asm/apicdef.h> #include <asm/system.h> - #include <asm/apic.h> -/* - * Put the error code here just in case the user cares: - */ -static int gdb_x86errcode; - -/* - * Likewise, the vector number here (since GDB only gets the signal - * number through the usual means, and that's not very specific): - */ -static int gdb_x86vector = -1; - -/** - * pt_regs_to_gdb_regs - Convert ptrace regs to GDB regs - * @gdb_regs: A pointer to hold the registers in the order GDB wants. - * @regs: The &struct pt_regs of the current process. - * - * Convert the pt_regs in @regs into the format for registers that - * GDB expects, stored in @gdb_regs. - */ -void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) +struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { -#ifndef CONFIG_X86_32 - u32 *gdb_regs32 = (u32 *)gdb_regs; +#ifdef CONFIG_X86_32 + { "ax", 4, offsetof(struct pt_regs, ax) }, + { "cx", 4, offsetof(struct pt_regs, cx) }, + { "dx", 4, offsetof(struct pt_regs, dx) }, + { "bx", 4, offsetof(struct pt_regs, bx) }, + { "sp", 4, offsetof(struct pt_regs, sp) }, + { "bp", 4, offsetof(struct pt_regs, bp) }, + { "si", 4, offsetof(struct pt_regs, si) }, + { "di", 4, offsetof(struct pt_regs, di) }, + { "ip", 4, offsetof(struct pt_regs, ip) }, + { "flags", 4, offsetof(struct pt_regs, flags) }, + { "cs", 4, offsetof(struct pt_regs, cs) }, + { "ss", 4, offsetof(struct pt_regs, ss) }, + { "ds", 4, offsetof(struct pt_regs, ds) }, + { "es", 4, offsetof(struct pt_regs, es) }, + { "fs", 4, -1 }, + { "gs", 4, -1 }, +#else + { "ax", 8, offsetof(struct pt_regs, ax) }, + { "bx", 8, offsetof(struct pt_regs, bx) }, + { "cx", 8, offsetof(struct pt_regs, cx) }, + { "dx", 8, offsetof(struct pt_regs, dx) }, + { "si", 8, offsetof(struct pt_regs, dx) }, + { "di", 8, offsetof(struct pt_regs, di) }, + { "bp", 8, offsetof(struct pt_regs, bp) }, + { "sp", 8, offsetof(struct pt_regs, sp) }, + { "r8", 8, offsetof(struct pt_regs, r8) }, + { "r9", 8, offsetof(struct pt_regs, r9) }, + { "r10", 8, offsetof(struct pt_regs, r10) }, + { "r11", 8, offsetof(struct pt_regs, r11) }, + { "r12", 8, offsetof(struct pt_regs, r12) }, + { "r13", 8, offsetof(struct pt_regs, r13) }, + { "r14", 8, offsetof(struct pt_regs, r14) }, + { "r15", 8, offsetof(struct pt_regs, r15) }, + { "ip", 8, offsetof(struct pt_regs, ip) }, + { "flags", 4, offsetof(struct pt_regs, flags) }, + { "cs", 4, offsetof(struct pt_regs, cs) }, + { "ss", 4, offsetof(struct pt_regs, ss) }, #endif - gdb_regs[GDB_AX] = regs->ax; - gdb_regs[GDB_BX] = regs->bx; - gdb_regs[GDB_CX] = regs->cx; - gdb_regs[GDB_DX] = regs->dx; - gdb_regs[GDB_SI] = regs->si; - gdb_regs[GDB_DI] = regs->di; - gdb_regs[GDB_BP] = regs->bp; - gdb_regs[GDB_PC] = regs->ip; +}; + +int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) +{ + if ( #ifdef CONFIG_X86_32 - gdb_regs[GDB_PS] = regs->flags; - gdb_regs[GDB_DS] = regs->ds; - gdb_regs[GDB_ES] = regs->es; - gdb_regs[GDB_CS] = regs->cs; - gdb_regs[GDB_FS] = 0xFFFF; - gdb_regs[GDB_GS] = 0xFFFF; - if (user_mode_vm(regs)) { - gdb_regs[GDB_SS] = regs->ss; - gdb_regs[GDB_SP] = regs->sp; - } else { - gdb_regs[GDB_SS] = __KERNEL_DS; - gdb_regs[GDB_SP] = kernel_stack_pointer(regs); + regno == GDB_SS || regno == GDB_FS || regno == GDB_GS || +#endif + regno == GDB_SP || regno == GDB_ORIG_AX) + return 0; + + if (dbg_reg_def[regno].offset != -1) + memcpy((void *)regs + dbg_reg_def[regno].offset, mem, + dbg_reg_def[regno].size); + return 0; +} + +char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) +{ + if (regno == GDB_ORIG_AX) { + memcpy(mem, ®s->orig_ax, sizeof(regs->orig_ax)); + return "orig_ax"; } -#else - gdb_regs[GDB_R8] = regs->r8; - gdb_regs[GDB_R9] = regs->r9; - gdb_regs[GDB_R10] = regs->r10; - gdb_regs[GDB_R11] = regs->r11; - gdb_regs[GDB_R12] = regs->r12; - gdb_regs[GDB_R13] = regs->r13; - gdb_regs[GDB_R14] = regs->r14; - gdb_regs[GDB_R15] = regs->r15; - gdb_regs32[GDB_PS] = regs->flags; - gdb_regs32[GDB_CS] = regs->cs; - gdb_regs32[GDB_SS] = regs->ss; - gdb_regs[GDB_SP] = kernel_stack_pointer(regs); + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return NULL; + + if (dbg_reg_def[regno].offset != -1) + memcpy(mem, (void *)regs + dbg_reg_def[regno].offset, + dbg_reg_def[regno].size); + + switch (regno) { +#ifdef CONFIG_X86_32 + case GDB_SS: + if (!user_mode_vm(regs)) + *(unsigned long *)mem = __KERNEL_DS; + break; + case GDB_SP: + if (!user_mode_vm(regs)) + *(unsigned long *)mem = kernel_stack_pointer(regs); + break; + case GDB_GS: + case GDB_FS: + *(unsigned long *)mem = 0xFFFF; + break; #endif + } + return dbg_reg_def[regno].name; } /** @@ -162,66 +189,35 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) gdb_regs[GDB_SP] = p->thread.sp; } -/** - * gdb_regs_to_pt_regs - Convert GDB regs to ptrace regs. - * @gdb_regs: A pointer to hold the registers we've received from GDB. - * @regs: A pointer to a &struct pt_regs to hold these values in. - * - * Convert the GDB regs in @gdb_regs into the pt_regs, and store them - * in @regs. - */ -void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) -{ -#ifndef CONFIG_X86_32 - u32 *gdb_regs32 = (u32 *)gdb_regs; -#endif - regs->ax = gdb_regs[GDB_AX]; - regs->bx = gdb_regs[GDB_BX]; - regs->cx = gdb_regs[GDB_CX]; - regs->dx = gdb_regs[GDB_DX]; - regs->si = gdb_regs[GDB_SI]; - regs->di = gdb_regs[GDB_DI]; - regs->bp = gdb_regs[GDB_BP]; - regs->ip = gdb_regs[GDB_PC]; -#ifdef CONFIG_X86_32 - regs->flags = gdb_regs[GDB_PS]; - regs->ds = gdb_regs[GDB_DS]; - regs->es = gdb_regs[GDB_ES]; - regs->cs = gdb_regs[GDB_CS]; -#else - regs->r8 = gdb_regs[GDB_R8]; - regs->r9 = gdb_regs[GDB_R9]; - regs->r10 = gdb_regs[GDB_R10]; - regs->r11 = gdb_regs[GDB_R11]; - regs->r12 = gdb_regs[GDB_R12]; - regs->r13 = gdb_regs[GDB_R13]; - regs->r14 = gdb_regs[GDB_R14]; - regs->r15 = gdb_regs[GDB_R15]; - regs->flags = gdb_regs32[GDB_PS]; - regs->cs = gdb_regs32[GDB_CS]; - regs->ss = gdb_regs32[GDB_SS]; -#endif -} - static struct hw_breakpoint { unsigned enabled; unsigned long addr; int len; int type; struct perf_event **pev; -} breakinfo[4]; +} breakinfo[HBP_NUM]; + +static unsigned long early_dr7; static void kgdb_correct_hw_break(void) { int breakno; - for (breakno = 0; breakno < 4; breakno++) { + for (breakno = 0; breakno < HBP_NUM; breakno++) { struct perf_event *bp; struct arch_hw_breakpoint *info; int val; int cpu = raw_smp_processor_id(); if (!breakinfo[breakno].enabled) continue; + if (dbg_is_early) { + set_debugreg(breakinfo[breakno].addr, breakno); + early_dr7 |= encode_dr7(breakno, + breakinfo[breakno].len, + breakinfo[breakno].type); + set_debugreg(early_dr7, 7); + continue; + } bp = *per_cpu_ptr(breakinfo[breakno].pev, cpu); info = counter_arch_bp(bp); if (bp->attr.disabled != 1) @@ -236,7 +232,8 @@ static void kgdb_correct_hw_break(void) if (!val) bp->attr.disabled = 0; } - hw_breakpoint_restore(); + if (!dbg_is_early) + hw_breakpoint_restore(); } static int hw_break_reserve_slot(int breakno) @@ -245,6 +242,9 @@ static int hw_break_reserve_slot(int breakno) int cnt = 0; struct perf_event **pevent; + if (dbg_is_early) + return 0; + for_each_online_cpu(cpu) { cnt++; pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu); @@ -270,6 +270,9 @@ static int hw_break_release_slot(int breakno) struct perf_event **pevent; int cpu; + if (dbg_is_early) + return 0; + for_each_online_cpu(cpu) { pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu); if (dbg_release_bp_slot(*pevent)) @@ -287,10 +290,10 @@ kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) { int i; - for (i = 0; i < 4; i++) + for (i = 0; i < HBP_NUM; i++) if (breakinfo[i].addr == addr && breakinfo[i].enabled) break; - if (i == 4) + if (i == HBP_NUM) return -1; if (hw_break_release_slot(i)) { @@ -308,13 +311,17 @@ static void kgdb_remove_all_hw_break(void) int cpu = raw_smp_processor_id(); struct perf_event *bp; - for (i = 0; i < 4; i++) { + for (i = 0; i < HBP_NUM; i++) { if (!breakinfo[i].enabled) continue; bp = *per_cpu_ptr(breakinfo[i].pev, cpu); if (bp->attr.disabled == 1) continue; - arch_uninstall_hw_breakpoint(bp); + if (dbg_is_early) + early_dr7 &= ~encode_dr7(i, breakinfo[i].len, + breakinfo[i].type); + else + arch_uninstall_hw_breakpoint(bp); bp->attr.disabled = 1; } } @@ -324,10 +331,10 @@ kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) { int i; - for (i = 0; i < 4; i++) + for (i = 0; i < HBP_NUM; i++) if (!breakinfo[i].enabled) break; - if (i == 4) + if (i == HBP_NUM) return -1; switch (bptype) { @@ -388,9 +395,14 @@ void kgdb_disable_hw_debug(struct pt_regs *regs) /* Disable hardware debugging while we are in kgdb: */ set_debugreg(0UL, 7); - for (i = 0; i < 4; i++) { + for (i = 0; i < HBP_NUM; i++) { if (!breakinfo[i].enabled) continue; + if (dbg_is_early) { + early_dr7 &= ~encode_dr7(i, breakinfo[i].len, + breakinfo[i].type); + continue; + } bp = *per_cpu_ptr(breakinfo[i].pev, cpu); if (bp->attr.disabled == 1) continue; @@ -399,23 +411,6 @@ void kgdb_disable_hw_debug(struct pt_regs *regs) } } -/** - * kgdb_post_primary_code - Save error vector/code numbers. - * @regs: Original pt_regs. - * @e_vector: Original error vector. - * @err_code: Original error code. - * - * This is needed on architectures which support SMP and KGDB. - * This function is called after all the slave cpus have been put - * to a know spin state and the primary CPU has control over KGDB. - */ -void kgdb_post_primary_code(struct pt_regs *regs, int e_vector, int err_code) -{ - /* primary processor is completely in the debugger */ - gdb_x86vector = e_vector; - gdb_x86errcode = err_code; -} - #ifdef CONFIG_SMP /** * kgdb_roundup_cpus - Get other CPUs into a holding pattern @@ -461,7 +456,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, { unsigned long addr; char *ptr; - int newPC; switch (remcomInBuffer[0]) { case 'c': @@ -472,8 +466,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, linux_regs->ip = addr; case 'D': case 'k': - newPC = linux_regs->ip; - /* clear the trace bit */ linux_regs->flags &= ~X86_EFLAGS_TF; atomic_set(&kgdb_cpu_doing_single_step, -1); @@ -567,7 +559,7 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd) return NOTIFY_DONE; } - if (kgdb_handle_exception(args->trapnr, args->signr, args->err, regs)) + if (kgdb_handle_exception(args->trapnr, args->signr, cmd, regs)) return NOTIFY_DONE; /* Must touch watchdog before return to normal operation */ @@ -575,6 +567,24 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd) return NOTIFY_STOP; } +int kgdb_ll_trap(int cmd, const char *str, + struct pt_regs *regs, long err, int trap, int sig) +{ + struct die_args args = { + .regs = regs, + .str = str, + .err = err, + .trapnr = trap, + .signr = sig, + + }; + + if (!kgdb_io_module_registered) + return NOTIFY_DONE; + + return __kgdb_notify(&args, cmd); +} + static int kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr) { @@ -605,14 +615,21 @@ static struct notifier_block kgdb_notifier = { */ int kgdb_arch_init(void) { + return register_die_notifier(&kgdb_notifier); +} + +static void kgdb_hw_overflow_handler(struct perf_event *event, int nmi, + struct perf_sample_data *data, struct pt_regs *regs) +{ + kgdb_ll_trap(DIE_DEBUG, "debug", regs, 0, 0, SIGTRAP); +} + +void kgdb_arch_late(void) +{ int i, cpu; - int ret; struct perf_event_attr attr; struct perf_event **pevent; - ret = register_die_notifier(&kgdb_notifier); - if (ret != 0) - return ret; /* * Pre-allocate the hw breakpoint structions in the non-atomic * portion of kgdb because this operation requires mutexs to @@ -623,24 +640,27 @@ int kgdb_arch_init(void) attr.bp_len = HW_BREAKPOINT_LEN_1; attr.bp_type = HW_BREAKPOINT_W; attr.disabled = 1; - for (i = 0; i < 4; i++) { + for (i = 0; i < HBP_NUM; i++) { + if (breakinfo[i].pev) + continue; breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL); if (IS_ERR(breakinfo[i].pev)) { - printk(KERN_ERR "kgdb: Could not allocate hw breakpoints\n"); + printk(KERN_ERR "kgdb: Could not allocate hw" + "breakpoints\nDisabling the kernel debugger\n"); breakinfo[i].pev = NULL; kgdb_arch_exit(); - return -1; + return; } for_each_online_cpu(cpu) { pevent = per_cpu_ptr(breakinfo[i].pev, cpu); pevent[0]->hw.sample_period = 1; + pevent[0]->overflow_handler = kgdb_hw_overflow_handler; if (pevent[0]->destroy != NULL) { pevent[0]->destroy = NULL; release_bp_slot(*pevent); } } } - return ret; } /** @@ -690,6 +710,11 @@ unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs) return instruction_pointer(regs); } +void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip) +{ + regs->ip = ip; +} + struct kgdb_arch arch_kgdb_ops = { /* Breakpoint instruction: */ .gdb_bpt_instr = { 0xcc }, diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 1658efdfb4e..1bfb6cf4dd5 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -126,16 +126,22 @@ static void __kprobes synthesize_reljump(void *from, void *to) } /* - * Check for the REX prefix which can only exist on X86_64 - * X86_32 always returns 0 + * Skip the prefixes of the instruction. */ -static int __kprobes is_REX_prefix(kprobe_opcode_t *insn) +static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn) { + insn_attr_t attr; + + attr = inat_get_opcode_attribute((insn_byte_t)*insn); + while (inat_is_legacy_prefix(attr)) { + insn++; + attr = inat_get_opcode_attribute((insn_byte_t)*insn); + } #ifdef CONFIG_X86_64 - if ((*insn & 0xf0) == 0x40) - return 1; + if (inat_is_rex_prefix(attr)) + insn++; #endif - return 0; + return insn; } /* @@ -272,6 +278,9 @@ static int __kprobes can_probe(unsigned long paddr) */ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) { + /* Skip prefixes */ + insn = skip_prefixes(insn); + switch (*insn) { case 0xfa: /* cli */ case 0xfb: /* sti */ @@ -280,13 +289,6 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) return 1; } - /* - * on X86_64, 0x40-0x4f are REX prefixes so we need to look - * at the next byte instead.. but of course not recurse infinitely - */ - if (is_REX_prefix(insn)) - return is_IF_modifier(++insn); - return 0; } @@ -422,14 +424,22 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, static void __kprobes clear_btf(void) { - if (test_thread_flag(TIF_DEBUGCTLMSR)) - update_debugctlmsr(0); + if (test_thread_flag(TIF_BLOCKSTEP)) { + unsigned long debugctl = get_debugctlmsr(); + + debugctl &= ~DEBUGCTLMSR_BTF; + update_debugctlmsr(debugctl); + } } static void __kprobes restore_btf(void) { - if (test_thread_flag(TIF_DEBUGCTLMSR)) - update_debugctlmsr(current->thread.debugctlmsr); + if (test_thread_flag(TIF_BLOCKSTEP)) { + unsigned long debugctl = get_debugctlmsr(); + + debugctl |= DEBUGCTLMSR_BTF; + update_debugctlmsr(debugctl); + } } void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, @@ -632,8 +642,8 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) /* Skip cs, ip, orig_ax and gs. */ \ " subl $16, %esp\n" \ " pushl %fs\n" \ - " pushl %ds\n" \ " pushl %es\n" \ + " pushl %ds\n" \ " pushl %eax\n" \ " pushl %ebp\n" \ " pushl %edi\n" \ @@ -795,9 +805,8 @@ static void __kprobes resume_execution(struct kprobe *p, unsigned long orig_ip = (unsigned long)p->addr; kprobe_opcode_t *insn = p->ainsn.insn; - /*skip the REX prefix*/ - if (is_REX_prefix(insn)) - insn++; + /* Skip prefixes */ + insn = skip_prefixes(insn); regs->flags &= ~X86_EFLAGS_TF; switch (*insn) { diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index feaeb0d3aa4..eb9b76c716c 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -29,6 +29,8 @@ #define KVM_SCALE 22 static int kvmclock = 1; +static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; +static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK; static int parse_no_kvmclock(char *arg) { @@ -54,7 +56,8 @@ static unsigned long kvm_get_wallclock(void) low = (int)__pa_symbol(&wall_clock); high = ((u64)__pa_symbol(&wall_clock) >> 32); - native_write_msr(MSR_KVM_WALL_CLOCK, low, high); + + native_write_msr(msr_kvm_wall_clock, low, high); vcpu_time = &get_cpu_var(hv_clock); pvclock_read_wallclock(&wall_clock, vcpu_time, &ts); @@ -130,7 +133,8 @@ static int kvm_register_clock(char *txt) high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32); printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n", cpu, high, low, txt); - return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high); + + return native_write_msr_safe(msr_kvm_system_time, low, high); } #ifdef CONFIG_X86_LOCAL_APIC @@ -165,14 +169,14 @@ static void __init kvm_smp_prepare_boot_cpu(void) #ifdef CONFIG_KEXEC static void kvm_crash_shutdown(struct pt_regs *regs) { - native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0); + native_write_msr(msr_kvm_system_time, 0, 0); native_machine_crash_shutdown(regs); } #endif static void kvm_shutdown(void) { - native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0); + native_write_msr(msr_kvm_system_time, 0, 0); native_machine_shutdown(); } @@ -181,27 +185,37 @@ void __init kvmclock_init(void) if (!kvm_para_available()) return; - if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { - if (kvm_register_clock("boot clock")) - return; - pv_time_ops.sched_clock = kvm_clock_read; - x86_platform.calibrate_tsc = kvm_get_tsc_khz; - x86_platform.get_wallclock = kvm_get_wallclock; - x86_platform.set_wallclock = kvm_set_wallclock; + if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) { + msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW; + msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW; + } else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE))) + return; + + printk(KERN_INFO "kvm-clock: Using msrs %x and %x", + msr_kvm_system_time, msr_kvm_wall_clock); + + if (kvm_register_clock("boot clock")) + return; + pv_time_ops.sched_clock = kvm_clock_read; + x86_platform.calibrate_tsc = kvm_get_tsc_khz; + x86_platform.get_wallclock = kvm_get_wallclock; + x86_platform.set_wallclock = kvm_set_wallclock; #ifdef CONFIG_X86_LOCAL_APIC - x86_cpuinit.setup_percpu_clockev = - kvm_setup_secondary_clock; + x86_cpuinit.setup_percpu_clockev = + kvm_setup_secondary_clock; #endif #ifdef CONFIG_SMP - smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; + smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; #endif - machine_ops.shutdown = kvm_shutdown; + machine_ops.shutdown = kvm_shutdown; #ifdef CONFIG_KEXEC - machine_ops.crash_shutdown = kvm_crash_shutdown; + machine_ops.crash_shutdown = kvm_crash_shutdown; #endif - kvm_get_preset_lpj(); - clocksource_register(&kvm_clock); - pv_info.paravirt_enabled = 1; - pv_info.name = "KVM"; - } + kvm_get_preset_lpj(); + clocksource_register(&kvm_clock); + pv_info.paravirt_enabled = 1; + pv_info.name = "KVM"; + + if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) + pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); } diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index cceb5bc3c3c..fa6551d36c1 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -201,9 +201,9 @@ static int do_microcode_update(const void __user *buf, size_t size) return error; } -static int microcode_open(struct inode *unused1, struct file *unused2) +static int microcode_open(struct inode *inode, struct file *file) { - return capable(CAP_SYS_RAWIO) ? 0 : -EPERM; + return capable(CAP_SYS_RAWIO) ? nonseekable_open(inode, file) : -EPERM; } static ssize_t microcode_write(struct file *file, const char __user *buf, @@ -260,6 +260,7 @@ static void microcode_dev_exit(void) } MODULE_ALIAS_MISCDEV(MICROCODE_MINOR); +MODULE_ALIAS("devname:cpu/microcode"); #else #define microcode_dev_init() 0 #define microcode_dev_exit() do { } while (0) diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index 85a343e2893..356170262a9 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -343,10 +343,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, int (*get_ucode_data)(void *, const void *, size_t)) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - u8 *ucode_ptr = data, *new_mc = NULL, *mc; + u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL; int new_rev = uci->cpu_sig.rev; unsigned int leftover = size; enum ucode_state state = UCODE_OK; + unsigned int curr_mc_size = 0; while (leftover) { struct microcode_header_intel mc_header; @@ -361,9 +362,15 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, break; } - mc = vmalloc(mc_size); - if (!mc) - break; + /* For performance reasons, reuse mc area when possible */ + if (!mc || mc_size > curr_mc_size) { + if (mc) + vfree(mc); + mc = vmalloc(mc_size); + if (!mc) + break; + curr_mc_size = mc_size; + } if (get_ucode_data(mc, ucode_ptr, mc_size) || microcode_sanity_check(mc) < 0) { @@ -376,13 +383,16 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, vfree(new_mc); new_rev = mc_header.rev; new_mc = mc; - } else - vfree(mc); + mc = NULL; /* trigger new vmalloc */ + } ucode_ptr += mc_size; leftover -= mc_size; } + if (mc) + vfree(mc); + if (leftover) { if (new_mc) vfree(new_mc); diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index e81030f71a8..d86dbf7e54b 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -115,21 +115,6 @@ static void __init MP_bus_info(struct mpc_bus *m) printk(KERN_WARNING "Unknown bustype %s - ignoring\n", str); } -static int bad_ioapic(unsigned long address) -{ - if (nr_ioapics >= MAX_IO_APICS) { - printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded " - "(found %d)\n", MAX_IO_APICS, nr_ioapics); - panic("Recompile kernel with bigger MAX_IO_APICS!\n"); - } - if (!address) { - printk(KERN_ERR "WARNING: Bogus (zero) I/O APIC address" - " found in table, skipping!\n"); - return 1; - } - return 0; -} - static void __init MP_ioapic_info(struct mpc_ioapic *m) { if (!(m->flags & MPC_APIC_USABLE)) @@ -138,15 +123,7 @@ static void __init MP_ioapic_info(struct mpc_ioapic *m) printk(KERN_INFO "I/O APIC #%d Version %d at 0x%X.\n", m->apicid, m->apicver, m->apicaddr); - if (bad_ioapic(m->apicaddr)) - return; - - mp_ioapics[nr_ioapics].apicaddr = m->apicaddr; - mp_ioapics[nr_ioapics].apicid = m->apicid; - mp_ioapics[nr_ioapics].type = m->type; - mp_ioapics[nr_ioapics].apicver = m->apicver; - mp_ioapics[nr_ioapics].flags = m->flags; - nr_ioapics++; + mp_register_ioapic(m->apicid, m->apicaddr, gsi_top); } static void print_MP_intsrc_info(struct mpc_intsrc *m) diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c index 0aad8670858..79ae68154e8 100644 --- a/arch/x86/kernel/mrst.c +++ b/arch/x86/kernel/mrst.c @@ -25,8 +25,34 @@ #include <asm/i8259.h> #include <asm/apb_timer.h> +/* + * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock, + * cmdline option x86_mrst_timer can be used to override the configuration + * to prefer one or the other. + * at runtime, there are basically three timer configurations: + * 1. per cpu apbt clock only + * 2. per cpu always-on lapic clocks only, this is Penwell/Medfield only + * 3. per cpu lapic clock (C3STOP) and one apbt clock, with broadcast. + * + * by default (without cmdline option), platform code first detects cpu type + * to see if we are on lincroft or penwell, then set up both lapic or apbt + * clocks accordingly. + * i.e. by default, medfield uses configuration #2, moorestown uses #1. + * config #3 is supported but not recommended on medfield. + * + * rating and feature summary: + * lapic (with C3STOP) --------- 100 + * apbt (always-on) ------------ 110 + * lapic (always-on,ARAT) ------ 150 + */ + +__cpuinitdata enum mrst_timer_options mrst_timer_options; + static u32 sfi_mtimer_usage[SFI_MTMR_MAX_NUM]; static struct sfi_timer_table_entry sfi_mtimer_array[SFI_MTMR_MAX_NUM]; +enum mrst_cpu_type __mrst_cpu_chip; +EXPORT_SYMBOL_GPL(__mrst_cpu_chip); + int sfi_mtimer_num; struct sfi_rtc_table_entry sfi_mrtc_array[SFI_MRTC_MAX]; @@ -167,18 +193,6 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table) return 0; } -/* - * the secondary clock in Moorestown can be APBT or LAPIC clock, default to - * APBT but cmdline option can also override it. - */ -static void __cpuinit mrst_setup_secondary_clock(void) -{ - /* restore default lapic clock if disabled by cmdline */ - if (disable_apbt_percpu) - return setup_secondary_APIC_clock(); - apbt_setup_secondary_clock(); -} - static unsigned long __init mrst_calibrate_tsc(void) { unsigned long flags, fast_calibrate; @@ -195,6 +209,21 @@ static unsigned long __init mrst_calibrate_tsc(void) void __init mrst_time_init(void) { + switch (mrst_timer_options) { + case MRST_TIMER_APBT_ONLY: + break; + case MRST_TIMER_LAPIC_APBT: + x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; + x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; + break; + default: + if (!boot_cpu_has(X86_FEATURE_ARAT)) + break; + x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; + x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; + return; + } + /* we need at least one APB timer */ sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr); pre_init_apic_IRQ0(); apbt_time_init(); @@ -205,16 +234,27 @@ void __init mrst_rtc_init(void) sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc); } -/* - * if we use per cpu apb timer, the bootclock already setup. if we use lapic - * timer and one apbt timer for broadcast, we need to set up lapic boot clock. - */ -static void __init mrst_setup_boot_clock(void) +void __cpuinit mrst_arch_setup(void) { - pr_info("%s: per cpu apbt flag %d \n", __func__, disable_apbt_percpu); - if (disable_apbt_percpu) - setup_boot_APIC_clock(); -}; + if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27) + __mrst_cpu_chip = MRST_CPU_CHIP_PENWELL; + else if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x26) + __mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; + else { + pr_err("Unknown Moorestown CPU (%d:%d), default to Lincroft\n", + boot_cpu_data.x86, boot_cpu_data.x86_model); + __mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; + } + pr_debug("Moorestown CPU %s identified\n", + (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT) ? + "Lincroft" : "Penwell"); +} + +/* MID systems don't have i8042 controller */ +static int mrst_i8042_detect(void) +{ + return 0; +} /* * Moorestown specific x86_init function overrides and early setup @@ -226,15 +266,46 @@ void __init x86_mrst_early_setup(void) x86_init.resources.reserve_resources = x86_init_noop; x86_init.timers.timer_init = mrst_time_init; - x86_init.timers.setup_percpu_clockev = mrst_setup_boot_clock; + x86_init.timers.setup_percpu_clockev = x86_init_noop; x86_init.irqs.pre_vector_init = x86_init_noop; - x86_cpuinit.setup_percpu_clockev = mrst_setup_secondary_clock; + x86_init.oem.arch_setup = mrst_arch_setup; + + x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock; x86_platform.calibrate_tsc = mrst_calibrate_tsc; + x86_platform.i8042_detect = mrst_i8042_detect; x86_init.pci.init = pci_mrst_init; x86_init.pci.fixup_irqs = x86_init_noop; legacy_pic = &null_legacy_pic; + + /* 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; + +} + +/* + * if user does not want to use per CPU apb timer, just give it a lower rating + * than local apic timer and skip the late per cpu timer init. + */ +static inline int __init setup_x86_mrst_timer(char *arg) +{ + if (!arg) + return -EINVAL; + + if (strcmp("apbt_only", arg) == 0) + mrst_timer_options = MRST_TIMER_APBT_ONLY; + else if (strcmp("lapic_and_apbt", arg) == 0) + mrst_timer_options = MRST_TIMER_LAPIC_APBT; + else { + pr_warning("X86 MRST timer option %s not recognised" + " use x86_mrst_timer=apbt_only or lapic_and_apbt\n", + arg); + return -EINVAL; + } + return 0; } +__setup("x86_mrst_timer=", setup_x86_mrst_timer); diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 4d4468e9f47..7bf2dc4c8f7 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -230,7 +230,7 @@ static int __cpuinit msr_class_cpu_callback(struct notifier_block *nfb, msr_device_destroy(cpu); break; } - return err ? NOTIFY_BAD : NOTIFY_OK; + return notifier_from_errno(err); } static struct notifier_block __refdata msr_class_cpu_notifier = { diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c index 8297160c41b..0e0cdde519b 100644 --- a/arch/x86/kernel/olpc.c +++ b/arch/x86/kernel/olpc.c @@ -21,10 +21,7 @@ #include <asm/geode.h> #include <asm/setup.h> #include <asm/olpc.h> - -#ifdef CONFIG_OPEN_FIRMWARE -#include <asm/ofw.h> -#endif +#include <asm/olpc_ofw.h> struct olpc_platform_t olpc_platform_info; EXPORT_SYMBOL_GPL(olpc_platform_info); @@ -145,7 +142,7 @@ restart: * The OBF flag will sometimes misbehave due to what we believe * is a hardware quirk.. */ - printk(KERN_DEBUG "olpc-ec: running cmd 0x%x\n", cmd); + pr_devel("olpc-ec: running cmd 0x%x\n", cmd); outb(cmd, 0x6c); if (wait_on_ibf(0x6c, 0)) { @@ -162,8 +159,7 @@ restart: " EC accept data!\n"); goto err; } - printk(KERN_DEBUG "olpc-ec: sending cmd arg 0x%x\n", - inbuf[i]); + pr_devel("olpc-ec: sending cmd arg 0x%x\n", inbuf[i]); outb(inbuf[i], 0x68); } } @@ -176,8 +172,7 @@ restart: goto restart; } outbuf[i] = inb(0x68); - printk(KERN_DEBUG "olpc-ec: received 0x%x\n", - outbuf[i]); + pr_devel("olpc-ec: received 0x%x\n", outbuf[i]); } } @@ -188,14 +183,15 @@ err: } EXPORT_SYMBOL_GPL(olpc_ec_cmd); -#ifdef CONFIG_OPEN_FIRMWARE +#ifdef CONFIG_OLPC_OPENFIRMWARE static void __init platform_detect(void) { size_t propsize; __be32 rev; + const void *args[] = { NULL, "board-revision-int", &rev, (void *)4 }; + void *res[] = { &propsize }; - if (ofw("getprop", 4, 1, NULL, "board-revision-int", &rev, 4, - &propsize) || propsize != 4) { + if (olpc_ofw("getprop", args, res) || propsize != 4) { printk(KERN_ERR "ofw: getprop call failed!\n"); rev = cpu_to_be32(0); } diff --git a/arch/x86/kernel/olpc_ofw.c b/arch/x86/kernel/olpc_ofw.c new file mode 100644 index 00000000000..3218aa71ab5 --- /dev/null +++ b/arch/x86/kernel/olpc_ofw.c @@ -0,0 +1,106 @@ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <asm/page.h> +#include <asm/setup.h> +#include <asm/io.h> +#include <asm/pgtable.h> +#include <asm/olpc_ofw.h> + +/* address of OFW callback interface; will be NULL if OFW isn't found */ +static int (*olpc_ofw_cif)(int *); + +/* page dir entry containing OFW's pgdir table; filled in by head_32.S */ +u32 olpc_ofw_pgd __initdata; + +static DEFINE_SPINLOCK(ofw_lock); + +#define MAXARGS 10 + +void __init setup_olpc_ofw_pgd(void) +{ + pgd_t *base, *ofw_pde; + + if (!olpc_ofw_cif) + return; + + /* fetch OFW's PDE */ + base = early_ioremap(olpc_ofw_pgd, sizeof(olpc_ofw_pgd) * PTRS_PER_PGD); + if (!base) { + printk(KERN_ERR "failed to remap OFW's pgd - disabling OFW!\n"); + olpc_ofw_cif = NULL; + return; + } + ofw_pde = &base[OLPC_OFW_PDE_NR]; + + /* install OFW's PDE permanently into the kernel's pgtable */ + set_pgd(&swapper_pg_dir[OLPC_OFW_PDE_NR], *ofw_pde); + /* implicit optimization barrier here due to uninline function return */ + + early_iounmap(base, sizeof(olpc_ofw_pgd) * PTRS_PER_PGD); +} + +int __olpc_ofw(const char *name, int nr_args, const void **args, int nr_res, + void **res) +{ + int ofw_args[MAXARGS + 3]; + unsigned long flags; + int ret, i, *p; + + BUG_ON(nr_args + nr_res > MAXARGS); + + if (!olpc_ofw_cif) + return -EIO; + + ofw_args[0] = (int)name; + ofw_args[1] = nr_args; + ofw_args[2] = nr_res; + + p = &ofw_args[3]; + for (i = 0; i < nr_args; i++, p++) + *p = (int)args[i]; + + /* call into ofw */ + spin_lock_irqsave(&ofw_lock, flags); + ret = olpc_ofw_cif(ofw_args); + spin_unlock_irqrestore(&ofw_lock, flags); + + if (!ret) { + for (i = 0; i < nr_res; i++, p++) + *((int *)res[i]) = *p; + } + + return ret; +} +EXPORT_SYMBOL_GPL(__olpc_ofw); + +/* OFW cif _should_ be above this address */ +#define OFW_MIN 0xff000000 + +/* OFW starts on a 1MB boundary */ +#define OFW_BOUND (1<<20) + +void __init olpc_ofw_detect(void) +{ + struct olpc_ofw_header *hdr = &boot_params.olpc_ofw_header; + unsigned long start; + + /* ensure OFW booted us by checking for "OFW " string */ + if (hdr->ofw_magic != OLPC_OFW_SIG) + return; + + olpc_ofw_cif = (int (*)(int *))hdr->cif_handler; + + if ((unsigned long)olpc_ofw_cif < OFW_MIN) { + printk(KERN_ERR "OFW detected, but cif has invalid address 0x%lx - disabling.\n", + (unsigned long)olpc_ofw_cif); + olpc_ofw_cif = NULL; + return; + } + + /* determine where OFW starts in memory */ + start = round_down((unsigned long)olpc_ofw_cif, OFW_BOUND); + printk(KERN_INFO "OFW detected in memory, cif @ 0x%lx (reserving top %ldMB)\n", + (unsigned long)olpc_ofw_cif, (-start) >> 20); + reserve_top_address(-start); +} diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index fb99f7edb34..078d4ec1a9d 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -103,11 +103,16 @@ int use_calgary __read_mostly = 0; #define PMR_SOFTSTOPFAULT 0x40000000 #define PMR_HARDSTOP 0x20000000 -#define MAX_NUM_OF_PHBS 8 /* how many PHBs in total? */ -#define MAX_NUM_CHASSIS 8 /* max number of chassis */ -/* MAX_PHB_BUS_NUM is the maximal possible dev->bus->number */ -#define MAX_PHB_BUS_NUM (MAX_NUM_OF_PHBS * MAX_NUM_CHASSIS * 2) -#define PHBS_PER_CALGARY 4 +/* + * The maximum PHB bus number. + * x3950M2 (rare): 8 chassis, 48 PHBs per chassis = 384 + * x3950M2: 4 chassis, 48 PHBs per chassis = 192 + * x3950 (PCIE): 8 chassis, 32 PHBs per chassis = 256 + * x3950 (PCIX): 8 chassis, 16 PHBs per chassis = 128 + */ +#define MAX_PHB_BUS_NUM 256 + +#define PHBS_PER_CALGARY 4 /* register offsets in Calgary's internal register space */ static const unsigned long tar_offsets[] = { @@ -1051,8 +1056,6 @@ static int __init calgary_init_one(struct pci_dev *dev) struct iommu_table *tbl; int ret; - BUG_ON(dev->bus->number >= MAX_PHB_BUS_NUM); - bbar = busno_to_bbar(dev->bus->number); ret = calgary_setup_tar(dev, bbar); if (ret) diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 7d2829dde20..a5bc528d432 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -31,8 +31,6 @@ static struct dma_map_ops swiotlb_dma_ops = { .free_coherent = swiotlb_free_coherent, .sync_single_for_cpu = swiotlb_sync_single_for_cpu, .sync_single_for_device = swiotlb_sync_single_for_device, - .sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu, - .sync_single_range_for_device = swiotlb_sync_single_range_for_device, .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, .sync_sg_for_device = swiotlb_sync_sg_for_device, .map_sg = swiotlb_map_sg_attrs, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 0415c3ef91b..d401f1d2d06 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -20,7 +20,6 @@ #include <asm/idle.h> #include <asm/uaccess.h> #include <asm/i387.h> -#include <asm/ds.h> #include <asm/debugreg.h> unsigned long idle_halt; @@ -29,29 +28,26 @@ unsigned long idle_nomwait; EXPORT_SYMBOL(idle_nomwait); struct kmem_cache *task_xstate_cachep; +EXPORT_SYMBOL_GPL(task_xstate_cachep); int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { + int ret; + *dst = *src; - if (src->thread.xstate) { - dst->thread.xstate = kmem_cache_alloc(task_xstate_cachep, - GFP_KERNEL); - if (!dst->thread.xstate) - return -ENOMEM; - WARN_ON((unsigned long)dst->thread.xstate & 15); - memcpy(dst->thread.xstate, src->thread.xstate, xstate_size); + if (fpu_allocated(&src->thread.fpu)) { + memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu)); + ret = fpu_alloc(&dst->thread.fpu); + if (ret) + return ret; + fpu_copy(&dst->thread.fpu, &src->thread.fpu); } return 0; } void free_thread_xstate(struct task_struct *tsk) { - if (tsk->thread.xstate) { - kmem_cache_free(task_xstate_cachep, tsk->thread.xstate); - tsk->thread.xstate = NULL; - } - - WARN(tsk->thread.ds_ctx, "leaking DS context\n"); + fpu_free(&tsk->thread.fpu); } void free_thread_info(struct thread_info *ti) @@ -198,11 +194,16 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, prev = &prev_p->thread; next = &next_p->thread; - if (test_tsk_thread_flag(next_p, TIF_DS_AREA_MSR) || - test_tsk_thread_flag(prev_p, TIF_DS_AREA_MSR)) - ds_switch_to(prev_p, next_p); - else if (next->debugctlmsr != prev->debugctlmsr) - update_debugctlmsr(next->debugctlmsr); + if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^ + test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) { + unsigned long debugctl = get_debugctlmsr(); + + debugctl &= ~DEBUGCTLMSR_BTF; + if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) + debugctl |= DEBUGCTLMSR_BTF; + + update_debugctlmsr(debugctl); + } if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ test_tsk_thread_flag(next_p, TIF_NOTSC)) { @@ -371,7 +372,7 @@ static inline int hlt_use_halt(void) void default_idle(void) { if (hlt_use_halt()) { - trace_power_start(POWER_CSTATE, 1); + trace_power_start(POWER_CSTATE, 1, smp_processor_id()); current_thread_info()->status &= ~TS_POLLING; /* * TS_POLLING-cleared state must be visible before we @@ -441,7 +442,7 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait); */ void mwait_idle_with_hints(unsigned long ax, unsigned long cx) { - trace_power_start(POWER_CSTATE, (ax>>4)+1); + trace_power_start(POWER_CSTATE, (ax>>4)+1, smp_processor_id()); if (!need_resched()) { if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -457,7 +458,7 @@ void mwait_idle_with_hints(unsigned long ax, unsigned long cx) static void mwait_idle(void) { if (!need_resched()) { - trace_power_start(POWER_CSTATE, 1); + trace_power_start(POWER_CSTATE, 1, smp_processor_id()); if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -478,7 +479,7 @@ static void mwait_idle(void) */ static void poll_idle(void) { - trace_power_start(POWER_CSTATE, 0); + trace_power_start(POWER_CSTATE, 0, smp_processor_id()); local_irq_enable(); while (!need_resched()) cpu_relax(); @@ -525,44 +526,10 @@ static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c) return (edx & MWAIT_EDX_C1); } -/* - * Check for AMD CPUs, where APIC timer interrupt does not wake up CPU from C1e. - * For more information see - * - Erratum #400 for NPT family 0xf and family 0x10 CPUs - * - Erratum #365 for family 0x11 (not affected because C1e not in use) - */ -static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c) -{ - u64 val; - if (c->x86_vendor != X86_VENDOR_AMD) - goto no_c1e_idle; - - /* Family 0x0f models < rev F do not have C1E */ - if (c->x86 == 0x0F && c->x86_model >= 0x40) - return 1; - - if (c->x86 == 0x10) { - /* - * check OSVW bit for CPUs that are not affected - * by erratum #400 - */ - if (cpu_has(c, X86_FEATURE_OSVW)) { - rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val); - if (val >= 2) { - rdmsrl(MSR_AMD64_OSVW_STATUS, val); - if (!(val & BIT(1))) - goto no_c1e_idle; - } - } - return 1; - } - -no_c1e_idle: - return 0; -} +bool c1e_detected; +EXPORT_SYMBOL(c1e_detected); static cpumask_var_t c1e_mask; -static int c1e_detected; void c1e_remove_cpu(int cpu) { @@ -584,12 +551,12 @@ static void c1e_idle(void) u32 lo, hi; rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi); + if (lo & K8_INTP_C1E_ACTIVE_MASK) { - c1e_detected = 1; + c1e_detected = true; if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) mark_tsc_unstable("TSC halt in AMD C1E"); printk(KERN_INFO "System has AMD C1E enabled\n"); - set_cpu_cap(&boot_cpu_data, X86_FEATURE_AMDC1E); } } @@ -638,7 +605,8 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) */ printk(KERN_INFO "using mwait in idle threads.\n"); pm_idle = mwait_idle; - } else if (check_c1e_idle(c)) { + } else if (cpu_has_amd_erratum(amd_erratum_400)) { + /* E400: APIC timer interrupt does not wake up CPU from C1e */ printk(KERN_INFO "using C1E aware idle routine\n"); pm_idle = c1e_idle; } else diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index f6c62667e30..96586c3cbbb 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -55,9 +55,10 @@ #include <asm/cpu.h> #include <asm/idle.h> #include <asm/syscalls.h> -#include <asm/ds.h> #include <asm/debugreg.h> +#include <trace/events/power.h> + asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); /* @@ -112,6 +113,8 @@ void cpu_idle(void) stop_critical_timings(); pm_idle(); start_critical_timings(); + + trace_power_end(smp_processor_id()); } tick_nohz_restart_sched_tick(); preempt_enable_no_resched(); @@ -238,13 +241,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, kfree(p->thread.io_bitmap_ptr); p->thread.io_bitmap_max = 0; } - - clear_tsk_thread_flag(p, TIF_DS_AREA_MSR); - p->thread.ds_ctx = NULL; - - clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR); - p->thread.debugctlmsr = 0; - return err; } @@ -317,7 +313,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* we're going to use this soon, after a few expensive things */ if (preload_fpu) - prefetch(next->xstate); + prefetch(next->fpu.state); /* * Reload esp0. diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 17cb3295cbf..3d9ea531ddd 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -49,9 +49,10 @@ #include <asm/ia32.h> #include <asm/idle.h> #include <asm/syscalls.h> -#include <asm/ds.h> #include <asm/debugreg.h> +#include <trace/events/power.h> + asmlinkage extern void ret_from_fork(void); DEFINE_PER_CPU(unsigned long, old_rsp); @@ -139,6 +140,9 @@ void cpu_idle(void) stop_critical_timings(); pm_idle(); start_critical_timings(); + + trace_power_end(smp_processor_id()); + /* In many cases the interrupt that ended idle has already called exit_idle. But some idle loops can be woken up without interrupt. */ @@ -313,13 +317,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, if (err) goto out; } - - clear_tsk_thread_flag(p, TIF_DS_AREA_MSR); - p->thread.ds_ctx = NULL; - - clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR); - p->thread.debugctlmsr = 0; - err = 0; out: if (err && p->thread.io_bitmap_ptr) { @@ -396,7 +393,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* we're going to use this soon, after a few expensive things */ if (preload_fpu) - prefetch(next->xstate); + prefetch(next->fpu.state); /* * Reload esp0, LDT and the page table pointer: diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 2e9b55027b7..70c4872cd8a 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -2,9 +2,6 @@ /* * Pentium III FXSR, SSE support * Gareth Hughes <gareth@valinux.com>, May 2000 - * - * BTS tracing - * Markus Metzger <markus.t.metzger@intel.com>, Dec 2007 */ #include <linux/kernel.h> @@ -22,7 +19,6 @@ #include <linux/audit.h> #include <linux/seccomp.h> #include <linux/signal.h> -#include <linux/workqueue.h> #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> @@ -36,7 +32,6 @@ #include <asm/desc.h> #include <asm/prctl.h> #include <asm/proto.h> -#include <asm/ds.h> #include <asm/hw_breakpoint.h> #include "tls.h" @@ -693,7 +688,7 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr, struct perf_event_attr attr; if (!t->ptrace_bps[nr]) { - hw_breakpoint_init(&attr); + ptrace_breakpoint_init(&attr); /* * Put stub len and type to register (reserve) an inactive but * correct bp @@ -789,342 +784,6 @@ static int ioperm_get(struct task_struct *target, 0, IO_BITMAP_BYTES); } -#ifdef CONFIG_X86_PTRACE_BTS -/* - * A branch trace store context. - * - * Contexts may only be installed by ptrace_bts_config() and only for - * ptraced tasks. - * - * Contexts are destroyed when the tracee is detached from the tracer. - * The actual destruction work requires interrupts enabled, so the - * work is deferred and will be scheduled during __ptrace_unlink(). - * - * Contexts hold an additional task_struct reference on the traced - * task, as well as a reference on the tracer's mm. - * - * Ptrace already holds a task_struct for the duration of ptrace operations, - * but since destruction is deferred, it may be executed after both - * tracer and tracee exited. - */ -struct bts_context { - /* The branch trace handle. */ - struct bts_tracer *tracer; - - /* The buffer used to store the branch trace and its size. */ - void *buffer; - unsigned int size; - - /* The mm that paid for the above buffer. */ - struct mm_struct *mm; - - /* The task this context belongs to. */ - struct task_struct *task; - - /* The signal to send on a bts buffer overflow. */ - unsigned int bts_ovfl_signal; - - /* The work struct to destroy a context. */ - struct work_struct work; -}; - -static int alloc_bts_buffer(struct bts_context *context, unsigned int size) -{ - void *buffer = NULL; - int err = -ENOMEM; - - err = account_locked_memory(current->mm, current->signal->rlim, size); - if (err < 0) - return err; - - buffer = kzalloc(size, GFP_KERNEL); - if (!buffer) - goto out_refund; - - context->buffer = buffer; - context->size = size; - context->mm = get_task_mm(current); - - return 0; - - out_refund: - refund_locked_memory(current->mm, size); - return err; -} - -static inline void free_bts_buffer(struct bts_context *context) -{ - if (!context->buffer) - return; - - kfree(context->buffer); - context->buffer = NULL; - - refund_locked_memory(context->mm, context->size); - context->size = 0; - - mmput(context->mm); - context->mm = NULL; -} - -static void free_bts_context_work(struct work_struct *w) -{ - struct bts_context *context; - - context = container_of(w, struct bts_context, work); - - ds_release_bts(context->tracer); - put_task_struct(context->task); - free_bts_buffer(context); - kfree(context); -} - -static inline void free_bts_context(struct bts_context *context) -{ - INIT_WORK(&context->work, free_bts_context_work); - schedule_work(&context->work); -} - -static inline struct bts_context *alloc_bts_context(struct task_struct *task) -{ - struct bts_context *context = kzalloc(sizeof(*context), GFP_KERNEL); - if (context) { - context->task = task; - task->bts = context; - - get_task_struct(task); - } - - return context; -} - -static int ptrace_bts_read_record(struct task_struct *child, size_t index, - struct bts_struct __user *out) -{ - struct bts_context *context; - const struct bts_trace *trace; - struct bts_struct bts; - const unsigned char *at; - int error; - - context = child->bts; - if (!context) - return -ESRCH; - - trace = ds_read_bts(context->tracer); - if (!trace) - return -ESRCH; - - at = trace->ds.top - ((index + 1) * trace->ds.size); - if ((void *)at < trace->ds.begin) - at += (trace->ds.n * trace->ds.size); - - if (!trace->read) - return -EOPNOTSUPP; - - error = trace->read(context->tracer, at, &bts); - if (error < 0) - return error; - - if (copy_to_user(out, &bts, sizeof(bts))) - return -EFAULT; - - return sizeof(bts); -} - -static int ptrace_bts_drain(struct task_struct *child, - long size, - struct bts_struct __user *out) -{ - struct bts_context *context; - const struct bts_trace *trace; - const unsigned char *at; - int error, drained = 0; - - context = child->bts; - if (!context) - return -ESRCH; - - trace = ds_read_bts(context->tracer); - if (!trace) - return -ESRCH; - - if (!trace->read) - return -EOPNOTSUPP; - - if (size < (trace->ds.top - trace->ds.begin)) - return -EIO; - - for (at = trace->ds.begin; (void *)at < trace->ds.top; - out++, drained++, at += trace->ds.size) { - struct bts_struct bts; - - error = trace->read(context->tracer, at, &bts); - if (error < 0) - return error; - - if (copy_to_user(out, &bts, sizeof(bts))) - return -EFAULT; - } - - memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size); - - error = ds_reset_bts(context->tracer); - if (error < 0) - return error; - - return drained; -} - -static int ptrace_bts_config(struct task_struct *child, - long cfg_size, - const struct ptrace_bts_config __user *ucfg) -{ - struct bts_context *context; - struct ptrace_bts_config cfg; - unsigned int flags = 0; - - if (cfg_size < sizeof(cfg)) - return -EIO; - - if (copy_from_user(&cfg, ucfg, sizeof(cfg))) - return -EFAULT; - - context = child->bts; - if (!context) - context = alloc_bts_context(child); - if (!context) - return -ENOMEM; - - if (cfg.flags & PTRACE_BTS_O_SIGNAL) { - if (!cfg.signal) - return -EINVAL; - - return -EOPNOTSUPP; - context->bts_ovfl_signal = cfg.signal; - } - - ds_release_bts(context->tracer); - context->tracer = NULL; - - if ((cfg.flags & PTRACE_BTS_O_ALLOC) && (cfg.size != context->size)) { - int err; - - free_bts_buffer(context); - if (!cfg.size) - return 0; - - err = alloc_bts_buffer(context, cfg.size); - if (err < 0) - return err; - } - - if (cfg.flags & PTRACE_BTS_O_TRACE) - flags |= BTS_USER; - - if (cfg.flags & PTRACE_BTS_O_SCHED) - flags |= BTS_TIMESTAMPS; - - context->tracer = - ds_request_bts_task(child, context->buffer, context->size, - NULL, (size_t)-1, flags); - if (unlikely(IS_ERR(context->tracer))) { - int error = PTR_ERR(context->tracer); - - free_bts_buffer(context); - context->tracer = NULL; - return error; - } - - return sizeof(cfg); -} - -static int ptrace_bts_status(struct task_struct *child, - long cfg_size, - struct ptrace_bts_config __user *ucfg) -{ - struct bts_context *context; - const struct bts_trace *trace; - struct ptrace_bts_config cfg; - - context = child->bts; - if (!context) - return -ESRCH; - - if (cfg_size < sizeof(cfg)) - return -EIO; - - trace = ds_read_bts(context->tracer); - if (!trace) - return -ESRCH; - - memset(&cfg, 0, sizeof(cfg)); - cfg.size = trace->ds.end - trace->ds.begin; - cfg.signal = context->bts_ovfl_signal; - cfg.bts_size = sizeof(struct bts_struct); - - if (cfg.signal) - cfg.flags |= PTRACE_BTS_O_SIGNAL; - - if (trace->ds.flags & BTS_USER) - cfg.flags |= PTRACE_BTS_O_TRACE; - - if (trace->ds.flags & BTS_TIMESTAMPS) - cfg.flags |= PTRACE_BTS_O_SCHED; - - if (copy_to_user(ucfg, &cfg, sizeof(cfg))) - return -EFAULT; - - return sizeof(cfg); -} - -static int ptrace_bts_clear(struct task_struct *child) -{ - struct bts_context *context; - const struct bts_trace *trace; - - context = child->bts; - if (!context) - return -ESRCH; - - trace = ds_read_bts(context->tracer); - if (!trace) - return -ESRCH; - - memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size); - - return ds_reset_bts(context->tracer); -} - -static int ptrace_bts_size(struct task_struct *child) -{ - struct bts_context *context; - const struct bts_trace *trace; - - context = child->bts; - if (!context) - return -ESRCH; - - trace = ds_read_bts(context->tracer); - if (!trace) - return -ESRCH; - - return (trace->ds.top - trace->ds.begin) / trace->ds.size; -} - -/* - * Called from __ptrace_unlink() after the child has been moved back - * to its original parent. - */ -void ptrace_bts_untrace(struct task_struct *child) -{ - if (unlikely(child->bts)) { - free_bts_context(child->bts); - child->bts = NULL; - } -} -#endif /* CONFIG_X86_PTRACE_BTS */ - /* * Called by kernel/ptrace.c when detaching.. * @@ -1252,39 +911,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) break; #endif - /* - * These bits need more cooking - not enabled yet: - */ -#ifdef CONFIG_X86_PTRACE_BTS - case PTRACE_BTS_CONFIG: - ret = ptrace_bts_config - (child, data, (struct ptrace_bts_config __user *)addr); - break; - - case PTRACE_BTS_STATUS: - ret = ptrace_bts_status - (child, data, (struct ptrace_bts_config __user *)addr); - break; - - case PTRACE_BTS_SIZE: - ret = ptrace_bts_size(child); - break; - - case PTRACE_BTS_GET: - ret = ptrace_bts_read_record - (child, data, (struct bts_struct __user *) addr); - break; - - case PTRACE_BTS_CLEAR: - ret = ptrace_bts_clear(child); - break; - - case PTRACE_BTS_DRAIN: - ret = ptrace_bts_drain - (child, data, (struct bts_struct __user *) addr); - break; -#endif /* CONFIG_X86_PTRACE_BTS */ - default: ret = ptrace_request(child, request, addr, data); break; @@ -1544,14 +1170,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, case PTRACE_GET_THREAD_AREA: case PTRACE_SET_THREAD_AREA: -#ifdef CONFIG_X86_PTRACE_BTS - case PTRACE_BTS_CONFIG: - case PTRACE_BTS_STATUS: - case PTRACE_BTS_SIZE: - case PTRACE_BTS_GET: - case PTRACE_BTS_CLEAR: - case PTRACE_BTS_DRAIN: -#endif /* CONFIG_X86_PTRACE_BTS */ return arch_ptrace(child, request, addr, data); default: diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 03801f2f761..239427ca02a 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -31,8 +31,16 @@ struct pvclock_shadow_time { u32 tsc_to_nsec_mul; int tsc_shift; u32 version; + u8 flags; }; +static u8 valid_flags __read_mostly = 0; + +void pvclock_set_flags(u8 flags) +{ + valid_flags = flags; +} + /* * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, * yielding a 64-bit result. @@ -91,6 +99,7 @@ static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst, dst->system_timestamp = src->system_time; dst->tsc_to_nsec_mul = src->tsc_to_system_mul; dst->tsc_shift = src->tsc_shift; + dst->flags = src->flags; rmb(); /* test version after fetching data */ } while ((src->version & 1) || (dst->version != src->version)); @@ -109,11 +118,14 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src) return pv_tsc_khz; } +static atomic64_t last_value = ATOMIC64_INIT(0); + cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) { struct pvclock_shadow_time shadow; unsigned version; cycle_t ret, offset; + u64 last; do { version = pvclock_get_time_values(&shadow, src); @@ -123,6 +135,31 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) barrier(); } while (version != src->version); + if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) && + (shadow.flags & PVCLOCK_TSC_STABLE_BIT)) + return ret; + + /* + * Assumption here is that last_value, a global accumulator, always goes + * forward. If we are less than that, we should not be much smaller. + * We assume there is an error marging we're inside, and then the correction + * does not sacrifice accuracy. + * + * For reads: global may have changed between test and return, + * but this means someone else updated poked the clock at a later time. + * We just need to make sure we are not seeing a backwards event. + * + * For updates: last_value = ret is not enough, since two vcpus could be + * updating at the same time, and one of them could be slightly behind, + * making the assumption that last_value always go forward fail to hold. + */ + last = atomic64_read(&last_value); + do { + if (ret < last) + return last; + last = atomic64_cmpxchg(&last_value, last, ret); + } while (unlikely(last != ret)); + return ret; } diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 12e9feaa2f7..939b9e98245 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -495,6 +495,9 @@ void force_hpet_resume(void) /* * HPET MSI on some boards (ATI SB700/SB800) has side effect on * floppy DMA. Disable HPET MSI on such platforms. + * See erratum #27 (Misinterpreted MSI Requests May Result in + * Corrupted LPC DMA Data) in AMD Publication #46837, + * "SB700 Family Product Errata", Rev. 1.0, March 2010. */ static void force_disable_hpet_msi(struct pci_dev *unused) { diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 8e1aac86b50..e3af342fe83 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -228,6 +228,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T5400"), }, }, + { /* Handle problems with rebooting on Dell T7400's */ + .callback = set_bios_reboot, + .ident = "Dell Precision T7400", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T7400"), + }, + }, { /* Handle problems with rebooting on HP laptops */ .callback = set_bios_reboot, .ident = "HP Compaq Laptop", diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c4851eff57b..b008e788320 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -102,6 +102,7 @@ #include <asm/paravirt.h> #include <asm/hypervisor.h> +#include <asm/olpc_ofw.h> #include <asm/percpu.h> #include <asm/topology.h> @@ -676,6 +677,17 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "DG45FC"), }, }, + /* + * The Dell Inspiron Mini 1012 has DMI_BIOS_VENDOR = "Dell Inc.", so + * match on the product name. + */ + { + .callback = dmi_low_memory_corruption, + .ident = "Phoenix BIOS", + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1012"), + }, + }, #endif {} }; @@ -725,9 +737,15 @@ void __init setup_arch(char **cmdline_p) /* VMI may relocate the fixmap; do this before touching ioremap area */ vmi_init(); + /* OFW also may relocate the fixmap */ + olpc_ofw_detect(); + + early_trap_init(); early_cpu_init(); early_ioremap_init(); + setup_olpc_ofw_pgd(); + ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev); screen_info = boot_params.screen_info; edid_info = boot_params.edid_info; diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index ef6370b00e7..a60df9ae645 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -21,12 +21,6 @@ #include <asm/cpu.h> #include <asm/stackprotector.h> -#ifdef CONFIG_DEBUG_PER_CPU_MAPS -# define DBG(fmt, ...) pr_dbg(fmt, ##__VA_ARGS__) -#else -# define DBG(fmt, ...) do { if (0) pr_dbg(fmt, ##__VA_ARGS__); } while (0) -#endif - DEFINE_PER_CPU(int, cpu_number); EXPORT_PER_CPU_SYMBOL(cpu_number); @@ -244,10 +238,19 @@ void __init setup_per_cpu_areas(void) #ifdef CONFIG_NUMA per_cpu(x86_cpu_to_node_map, cpu) = early_per_cpu_map(x86_cpu_to_node_map, cpu); + /* + * Ensure that the boot cpu numa_node is correct when the boot + * cpu is on a node that doesn't have memory installed. + * Also cpu_up() will call cpu_to_node() for APs when + * MEMORY_HOTPLUG is defined, before per_cpu(numa_node) is set + * up later with c_init aka intel_init/amd_init. + * So set them all (boot cpu and all APs). + */ + set_cpu_numa_node(cpu, early_cpu_to_node(cpu)); #endif #endif /* - * Up to this point, the boot CPU has been using .data.init + * Up to this point, the boot CPU has been using .init.data * area. Reload any changed state for the boot CPU. */ if (cpu == boot_cpu_id) @@ -263,14 +266,6 @@ void __init setup_per_cpu_areas(void) early_per_cpu_ptr(x86_cpu_to_node_map) = NULL; #endif -#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA) - /* - * make sure boot cpu node_number is right, when boot cpu is on the - * node that doesn't have mem installed - */ - per_cpu(node_number, boot_cpu_id) = cpu_to_node(boot_cpu_id); -#endif - /* Setup node to cpumask map */ setup_node_to_cpumask_map(); diff --git a/arch/x86/kernel/sfi.c b/arch/x86/kernel/sfi.c index 34e09938265..cb22acf3ed0 100644 --- a/arch/x86/kernel/sfi.c +++ b/arch/x86/kernel/sfi.c @@ -81,7 +81,6 @@ static int __init sfi_parse_cpus(struct sfi_table_header *table) #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC -static u32 gsi_base; static int __init sfi_parse_ioapic(struct sfi_table_header *table) { @@ -94,8 +93,7 @@ static int __init sfi_parse_ioapic(struct sfi_table_header *table) pentry = (struct sfi_apic_table_entry *)sb->pentry; for (i = 0; i < num; i++) { - mp_register_ioapic(i, pentry->phys_addr, gsi_base); - gsi_base += io_apic_get_redir_entries(i); + mp_register_ioapic(i, pentry->phys_addr, gsi_top); pentry++; } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 763d815e27a..a5e928b0cb5 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -686,7 +686,7 @@ static void __cpuinit do_fork_idle(struct work_struct *work) static void __cpuinit announce_cpu(int cpu, int apicid) { static int current_node = -1; - int node = cpu_to_node(cpu); + int node = early_cpu_to_node(cpu); if (system_state == SYSTEM_BOOTING) { if (node != current_node) { @@ -735,12 +735,8 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) goto do_rest; } - if (!keventd_up() || current_is_keventd()) - c_idle.work.func(&c_idle.work); - else { - schedule_work(&c_idle.work); - wait_for_completion(&c_idle.done); - } + schedule_work(&c_idle.work); + wait_for_completion(&c_idle.done); if (IS_ERR(c_idle.idle)) { printk("failed fork for CPU %d\n", cpu); @@ -816,6 +812,13 @@ do_rest: if (cpumask_test_cpu(cpu, cpu_callin_mask)) break; /* It has booted */ udelay(100); + /* + * Allow other tasks to run while we wait for the + * AP to come online. This also gives a chance + * for the MTRR work(triggered by the AP coming online) + * to be completed in the stop machine context. + */ + schedule(); } if (cpumask_test_cpu(cpu, cpu_callin_mask)) @@ -1215,9 +1218,17 @@ __init void prefill_possible_map(void) if (!num_processors) num_processors = 1; - if (setup_possible_cpus == -1) - possible = num_processors + disabled_cpus; - else + i = setup_max_cpus ?: 1; + if (setup_possible_cpus == -1) { + possible = num_processors; +#ifdef CONFIG_HOTPLUG_CPU + if (setup_max_cpus) + possible += disabled_cpus; +#else + if (possible > i) + possible = i; +#endif + } else possible = setup_possible_cpus; total_cpus = max_t(int, possible, num_processors + disabled_cpus); @@ -1230,11 +1241,23 @@ __init void prefill_possible_map(void) possible = nr_cpu_ids; } +#ifdef CONFIG_HOTPLUG_CPU + if (!setup_max_cpus) +#endif + if (possible > i) { + printk(KERN_WARNING + "%d Processors exceeds max_cpus limit of %u\n", + possible, setup_max_cpus); + possible = i; + } + printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n", possible, max_t(int, possible - num_processors, 0)); for (i = 0; i < possible; i++) set_cpu_possible(i, true); + for (; i < NR_CPUS; i++) + set_cpu_possible(i, false); nr_cpu_ids = possible; } diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 922eefbb3f6..b53c525368a 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -23,11 +23,16 @@ static int save_stack_stack(void *data, char *name) return 0; } -static void save_stack_address(void *data, unsigned long addr, int reliable) +static void +__save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched) { struct stack_trace *trace = data; +#ifdef CONFIG_FRAME_POINTER if (!reliable) return; +#endif + if (nosched && in_sched_functions(addr)) + return; if (trace->skip > 0) { trace->skip--; return; @@ -36,20 +41,15 @@ static void save_stack_address(void *data, unsigned long addr, int reliable) trace->entries[trace->nr_entries++] = addr; } +static void save_stack_address(void *data, unsigned long addr, int reliable) +{ + return __save_stack_address(data, addr, reliable, false); +} + static void save_stack_address_nosched(void *data, unsigned long addr, int reliable) { - struct stack_trace *trace = (struct stack_trace *)data; - if (!reliable) - return; - if (in_sched_functions(addr)) - return; - if (trace->skip > 0) { - trace->skip--; - return; - } - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = addr; + return __save_stack_address(data, addr, reliable, true); } static const struct stacktrace_ops save_stack_ops = { @@ -96,12 +96,13 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk); /* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */ -struct stack_frame { +struct stack_frame_user { const void __user *next_fp; unsigned long ret_addr; }; -static int copy_stack_frame(const void __user *fp, struct stack_frame *frame) +static int +copy_stack_frame(const void __user *fp, struct stack_frame_user *frame) { int ret; @@ -126,7 +127,7 @@ static inline void __save_stack_trace_user(struct stack_trace *trace) trace->entries[trace->nr_entries++] = regs->ip; while (trace->nr_entries < trace->max_entries) { - struct stack_frame frame; + struct stack_frame_user frame; frame.next_fp = NULL; frame.ret_addr = 0; diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 3149032ff10..58de45ee08b 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -158,22 +158,6 @@ static int enable_single_step(struct task_struct *child) } /* - * Install this value in MSR_IA32_DEBUGCTLMSR whenever child is running. - */ -static void write_debugctlmsr(struct task_struct *child, unsigned long val) -{ - if (child->thread.debugctlmsr == val) - return; - - child->thread.debugctlmsr = val; - - if (child != current) - return; - - update_debugctlmsr(val); -} - -/* * Enable single or block step. */ static void enable_step(struct task_struct *child, bool block) @@ -186,15 +170,17 @@ static void enable_step(struct task_struct *child, bool block) * that uses user-mode single stepping itself. */ if (enable_single_step(child) && block) { - set_tsk_thread_flag(child, TIF_DEBUGCTLMSR); - write_debugctlmsr(child, - child->thread.debugctlmsr | DEBUGCTLMSR_BTF); - } else { - write_debugctlmsr(child, - child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF); - - if (!child->thread.debugctlmsr) - clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); + 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); } } @@ -213,11 +199,13 @@ void user_disable_single_step(struct task_struct *child) /* * Make sure block stepping (BTF) is disabled. */ - write_debugctlmsr(child, - child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF); + if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) { + unsigned long debugctl = get_debugctlmsr(); - if (!child->thread.debugctlmsr) - clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); + debugctl &= ~DEBUGCTLMSR_BTF; + update_debugctlmsr(debugctl); + clear_tsk_thread_flag(child, TIF_BLOCKSTEP); + } /* Always clear TIF_SINGLESTEP... */ clear_tsk_thread_flag(child, TIF_SINGLESTEP); diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 8b372934121..b35786dc9b8 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -337,3 +337,6 @@ ENTRY(sys_call_table) .long sys_rt_tgsigqueueinfo /* 335 */ .long sys_perf_event_open .long sys_recvmmsg + .long sys_fanotify_init + .long sys_fanotify_mark + .long sys_prlimit64 /* 340 */ diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 86c9f91b48a..c2f1b26141e 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -46,6 +46,7 @@ /* Global pointer to shared data; NULL means no measured launch. */ struct tboot *tboot __read_mostly; +EXPORT_SYMBOL(tboot); /* timeout for APs (in secs) to enter wait-for-SIPI state during shutdown */ #define AP_WAIT_TIMEOUT 1 @@ -175,6 +176,9 @@ static void add_mac_region(phys_addr_t start, unsigned long size) struct tboot_mac_region *mr; phys_addr_t end = start + size; + if (tboot->num_mac_regions >= MAX_TB_MAC_REGIONS) + panic("tboot: Too many MAC regions\n"); + if (start && size) { mr = &tboot->mac_regions[tboot->num_mac_regions++]; mr->start = round_down(start, PAGE_SIZE); @@ -184,18 +188,17 @@ static void add_mac_region(phys_addr_t start, unsigned long size) static int tboot_setup_sleep(void) { + int i; + tboot->num_mac_regions = 0; - /* S3 resume code */ - add_mac_region(acpi_wakeup_address, WAKEUP_SIZE); + for (i = 0; i < e820.nr_map; i++) { + if ((e820.map[i].type != E820_RAM) + && (e820.map[i].type != E820_RESERVED_KERN)) + continue; -#ifdef CONFIG_X86_TRAMPOLINE - /* AP trampoline code */ - add_mac_region(virt_to_phys(trampoline_base), TRAMPOLINE_SIZE); -#endif - - /* kernel code + data + bss */ - add_mac_region(virt_to_phys(_text), _end - _text); + add_mac_region(e820.map[i].addr, e820.map[i].size); + } tboot->acpi_sinfo.kernel_s3_resume_vector = acpi_wakeup_address; diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index 17b03dd3a6b..7fea555929e 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -1,7 +1,7 @@ /* * SGI UltraViolet TLB flush routines. * - * (c) 2008 Cliff Wickman <cpw@sgi.com>, SGI. + * (c) 2008-2010 Cliff Wickman <cpw@sgi.com>, SGI. * * This code is released under the GNU General Public License version 2 or * later. @@ -20,42 +20,67 @@ #include <asm/idle.h> #include <asm/tsc.h> #include <asm/irq_vectors.h> +#include <asm/timer.h> -static struct bau_control **uv_bau_table_bases __read_mostly; -static int uv_bau_retry_limit __read_mostly; +struct msg_desc { + struct bau_payload_queue_entry *msg; + int msg_slot; + int sw_ack_slot; + struct bau_payload_queue_entry *va_queue_first; + struct bau_payload_queue_entry *va_queue_last; +}; -/* base pnode in this partition */ -static int uv_partition_base_pnode __read_mostly; +#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x000000000bUL + +static int uv_bau_max_concurrent __read_mostly; + +static int nobau; +static int __init setup_nobau(char *arg) +{ + nobau = 1; + return 0; +} +early_param("nobau", setup_nobau); -static unsigned long uv_mmask __read_mostly; +/* base pnode in this partition */ +static int uv_partition_base_pnode __read_mostly; +/* position of pnode (which is nasid>>1): */ +static int uv_nshift __read_mostly; +static unsigned long uv_mmask __read_mostly; static DEFINE_PER_CPU(struct ptc_stats, ptcstats); static DEFINE_PER_CPU(struct bau_control, bau_control); +static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask); + +struct reset_args { + int sender; +}; /* - * Determine the first node on a blade. + * Determine the first node on a uvhub. 'Nodes' are used for kernel + * memory allocation. */ -static int __init blade_to_first_node(int blade) +static int __init uvhub_to_first_node(int uvhub) { int node, b; for_each_online_node(node) { b = uv_node_to_blade_id(node); - if (blade == b) + if (uvhub == b) return node; } - return -1; /* shouldn't happen */ + return -1; } /* - * Determine the apicid of the first cpu on a blade. + * Determine the apicid of the first cpu on a uvhub. */ -static int __init blade_to_first_apicid(int blade) +static int __init uvhub_to_first_apicid(int uvhub) { int cpu; for_each_present_cpu(cpu) - if (blade == uv_cpu_to_blade_id(cpu)) + if (uvhub == uv_cpu_to_blade_id(cpu)) return per_cpu(x86_cpu_to_apicid, cpu); return -1; } @@ -68,195 +93,459 @@ static int __init blade_to_first_apicid(int blade) * clear of the Timeout bit (as well) will free the resource. No reply will * be sent (the hardware will only do one reply per message). */ -static void uv_reply_to_message(int resource, - struct bau_payload_queue_entry *msg, - struct bau_msg_status *msp) +static inline void uv_reply_to_message(struct msg_desc *mdp, + struct bau_control *bcp) { unsigned long dw; + struct bau_payload_queue_entry *msg; - dw = (1 << (resource + UV_SW_ACK_NPENDING)) | (1 << resource); + msg = mdp->msg; + if (!msg->canceled) { + dw = (msg->sw_ack_vector << UV_SW_ACK_NPENDING) | + msg->sw_ack_vector; + uv_write_local_mmr( + UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, dw); + } msg->replied_to = 1; msg->sw_ack_vector = 0; - if (msp) - msp->seen_by.bits = 0; - uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, dw); } /* - * Do all the things a cpu should do for a TLB shootdown message. - * Other cpu's may come here at the same time for this message. + * Process the receipt of a RETRY message */ -static void uv_bau_process_message(struct bau_payload_queue_entry *msg, - int msg_slot, int sw_ack_slot) +static inline void uv_bau_process_retry_msg(struct msg_desc *mdp, + struct bau_control *bcp) { - unsigned long this_cpu_mask; - struct bau_msg_status *msp; - int cpu; + int i; + int cancel_count = 0; + int slot2; + unsigned long msg_res; + unsigned long mmr = 0; + struct bau_payload_queue_entry *msg; + struct bau_payload_queue_entry *msg2; + struct ptc_stats *stat; - msp = __get_cpu_var(bau_control).msg_statuses + msg_slot; - cpu = uv_blade_processor_id(); - msg->number_of_cpus = - uv_blade_nr_online_cpus(uv_node_to_blade_id(numa_node_id())); - this_cpu_mask = 1UL << cpu; - if (msp->seen_by.bits & this_cpu_mask) - return; - atomic_or_long(&msp->seen_by.bits, this_cpu_mask); + msg = mdp->msg; + stat = &per_cpu(ptcstats, bcp->cpu); + stat->d_retries++; + /* + * cancel any message from msg+1 to the retry itself + */ + for (msg2 = msg+1, i = 0; i < DEST_Q_SIZE; msg2++, i++) { + if (msg2 > mdp->va_queue_last) + msg2 = mdp->va_queue_first; + if (msg2 == msg) + break; + + /* same conditions for cancellation as uv_do_reset */ + if ((msg2->replied_to == 0) && (msg2->canceled == 0) && + (msg2->sw_ack_vector) && ((msg2->sw_ack_vector & + msg->sw_ack_vector) == 0) && + (msg2->sending_cpu == msg->sending_cpu) && + (msg2->msg_type != MSG_NOOP)) { + slot2 = msg2 - mdp->va_queue_first; + mmr = uv_read_local_mmr + (UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE); + msg_res = ((msg2->sw_ack_vector << 8) | + msg2->sw_ack_vector); + /* + * This is a message retry; clear the resources held + * by the previous message only if they timed out. + * If it has not timed out we have an unexpected + * situation to report. + */ + if (mmr & (msg_res << 8)) { + /* + * is the resource timed out? + * make everyone ignore the cancelled message. + */ + msg2->canceled = 1; + stat->d_canceled++; + cancel_count++; + uv_write_local_mmr( + UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, + (msg_res << 8) | msg_res); + } else + printk(KERN_INFO "note bau retry: no effect\n"); + } + } + if (!cancel_count) + stat->d_nocanceled++; +} - if (msg->replied_to == 1) - return; +/* + * Do all the things a cpu should do for a TLB shootdown message. + * Other cpu's may come here at the same time for this message. + */ +static void uv_bau_process_message(struct msg_desc *mdp, + struct bau_control *bcp) +{ + int msg_ack_count; + short socket_ack_count = 0; + struct ptc_stats *stat; + struct bau_payload_queue_entry *msg; + struct bau_control *smaster = bcp->socket_master; + /* + * This must be a normal message, or retry of a normal message + */ + msg = mdp->msg; + stat = &per_cpu(ptcstats, bcp->cpu); if (msg->address == TLB_FLUSH_ALL) { local_flush_tlb(); - __get_cpu_var(ptcstats).alltlb++; + stat->d_alltlb++; } else { __flush_tlb_one(msg->address); - __get_cpu_var(ptcstats).onetlb++; + stat->d_onetlb++; } + stat->d_requestee++; + + /* + * One cpu on each uvhub has the additional job on a RETRY + * of releasing the resource held by the message that is + * being retried. That message is identified by sending + * cpu number. + */ + if (msg->msg_type == MSG_RETRY && bcp == bcp->uvhub_master) + uv_bau_process_retry_msg(mdp, bcp); - __get_cpu_var(ptcstats).requestee++; + /* + * This is a sw_ack message, so we have to reply to it. + * Count each responding cpu on the socket. This avoids + * pinging the count's cache line back and forth between + * the sockets. + */ + socket_ack_count = atomic_add_short_return(1, (struct atomic_short *) + &smaster->socket_acknowledge_count[mdp->msg_slot]); + if (socket_ack_count == bcp->cpus_in_socket) { + /* + * Both sockets dump their completed count total into + * the message's count. + */ + smaster->socket_acknowledge_count[mdp->msg_slot] = 0; + msg_ack_count = atomic_add_short_return(socket_ack_count, + (struct atomic_short *)&msg->acknowledge_count); + + if (msg_ack_count == bcp->cpus_in_uvhub) { + /* + * All cpus in uvhub saw it; reply + */ + uv_reply_to_message(mdp, bcp); + } + } - atomic_inc_short(&msg->acknowledge_count); - if (msg->number_of_cpus == msg->acknowledge_count) - uv_reply_to_message(sw_ack_slot, msg, msp); + return; } /* - * Examine the payload queue on one distribution node to see - * which messages have not been seen, and which cpu(s) have not seen them. + * Determine the first cpu on a uvhub. + */ +static int uvhub_to_first_cpu(int uvhub) +{ + int cpu; + for_each_present_cpu(cpu) + if (uvhub == uv_cpu_to_blade_id(cpu)) + return cpu; + return -1; +} + +/* + * Last resort when we get a large number of destination timeouts is + * to clear resources held by a given cpu. + * Do this with IPI so that all messages in the BAU message queue + * can be identified by their nonzero sw_ack_vector field. * - * Returns the number of cpu's that have not responded. + * This is entered for a single cpu on the uvhub. + * The sender want's this uvhub to free a specific message's + * sw_ack resources. */ -static int uv_examine_destination(struct bau_control *bau_tablesp, int sender) +static void +uv_do_reset(void *ptr) { - struct bau_payload_queue_entry *msg; - struct bau_msg_status *msp; - int count = 0; int i; - int j; + int slot; + int count = 0; + unsigned long mmr; + unsigned long msg_res; + struct bau_control *bcp; + struct reset_args *rap; + struct bau_payload_queue_entry *msg; + struct ptc_stats *stat; - for (msg = bau_tablesp->va_queue_first, i = 0; i < DEST_Q_SIZE; - msg++, i++) { - if ((msg->sending_cpu == sender) && (!msg->replied_to)) { - msp = bau_tablesp->msg_statuses + i; - printk(KERN_DEBUG - "blade %d: address:%#lx %d of %d, not cpu(s): ", - i, msg->address, msg->acknowledge_count, - msg->number_of_cpus); - for (j = 0; j < msg->number_of_cpus; j++) { - if (!((1L << j) & msp->seen_by.bits)) { - count++; - printk("%d ", j); - } + bcp = &per_cpu(bau_control, smp_processor_id()); + rap = (struct reset_args *)ptr; + stat = &per_cpu(ptcstats, bcp->cpu); + stat->d_resets++; + + /* + * We're looking for the given sender, and + * will free its sw_ack resource. + * If all cpu's finally responded after the timeout, its + * message 'replied_to' was set. + */ + for (msg = bcp->va_queue_first, i = 0; i < DEST_Q_SIZE; msg++, i++) { + /* uv_do_reset: same conditions for cancellation as + uv_bau_process_retry_msg() */ + if ((msg->replied_to == 0) && + (msg->canceled == 0) && + (msg->sending_cpu == rap->sender) && + (msg->sw_ack_vector) && + (msg->msg_type != MSG_NOOP)) { + /* + * make everyone else ignore this message + */ + msg->canceled = 1; + slot = msg - bcp->va_queue_first; + count++; + /* + * only reset the resource if it is still pending + */ + mmr = uv_read_local_mmr + (UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE); + msg_res = ((msg->sw_ack_vector << 8) | + msg->sw_ack_vector); + if (mmr & msg_res) { + stat->d_rcanceled++; + uv_write_local_mmr( + UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, + msg_res); } - printk("\n"); } } - return count; + return; } /* - * Examine the payload queue on all the distribution nodes to see - * which messages have not been seen, and which cpu(s) have not seen them. - * - * Returns the number of cpu's that have not responded. + * Use IPI to get all target uvhubs to release resources held by + * a given sending cpu number. */ -static int uv_examine_destinations(struct bau_target_nodemask *distribution) +static void uv_reset_with_ipi(struct bau_target_uvhubmask *distribution, + int sender) { - int sender; - int i; - int count = 0; + int uvhub; + int cpu; + cpumask_t mask; + struct reset_args reset_args; + + reset_args.sender = sender; - sender = smp_processor_id(); - for (i = 0; i < sizeof(struct bau_target_nodemask) * BITSPERBYTE; i++) { - if (!bau_node_isset(i, distribution)) + cpus_clear(mask); + /* find a single cpu for each uvhub in this distribution mask */ + for (uvhub = 0; + uvhub < sizeof(struct bau_target_uvhubmask) * BITSPERBYTE; + uvhub++) { + if (!bau_uvhub_isset(uvhub, distribution)) continue; - count += uv_examine_destination(uv_bau_table_bases[i], sender); + /* find a cpu for this uvhub */ + cpu = uvhub_to_first_cpu(uvhub); + cpu_set(cpu, mask); } - return count; + /* IPI all cpus; Preemption is already disabled */ + smp_call_function_many(&mask, uv_do_reset, (void *)&reset_args, 1); + return; +} + +static inline unsigned long +cycles_2_us(unsigned long long cyc) +{ + unsigned long long ns; + unsigned long us; + ns = (cyc * per_cpu(cyc2ns, smp_processor_id())) + >> CYC2NS_SCALE_FACTOR; + us = ns / 1000; + return us; } /* - * wait for completion of a broadcast message - * - * return COMPLETE, RETRY or GIVEUP + * wait for all cpus on this hub to finish their sends and go quiet + * leaves uvhub_quiesce set so that no new broadcasts are started by + * bau_flush_send_and_wait() + */ +static inline void +quiesce_local_uvhub(struct bau_control *hmaster) +{ + atomic_add_short_return(1, (struct atomic_short *) + &hmaster->uvhub_quiesce); +} + +/* + * mark this quiet-requestor as done + */ +static inline void +end_uvhub_quiesce(struct bau_control *hmaster) +{ + atomic_add_short_return(-1, (struct atomic_short *) + &hmaster->uvhub_quiesce); +} + +/* + * Wait for completion of a broadcast software ack message + * return COMPLETE, RETRY(PLUGGED or TIMEOUT) or GIVEUP */ static int uv_wait_completion(struct bau_desc *bau_desc, - unsigned long mmr_offset, int right_shift) + unsigned long mmr_offset, int right_shift, int this_cpu, + struct bau_control *bcp, struct bau_control *smaster, long try) { - int exams = 0; - long destination_timeouts = 0; - long source_timeouts = 0; + int relaxes = 0; unsigned long descriptor_status; + unsigned long mmr; + unsigned long mask; + cycles_t ttime; + cycles_t timeout_time; + struct ptc_stats *stat = &per_cpu(ptcstats, this_cpu); + struct bau_control *hmaster; + + hmaster = bcp->uvhub_master; + timeout_time = get_cycles() + bcp->timeout_interval; + /* spin on the status MMR, waiting for it to go idle */ while ((descriptor_status = (((unsigned long) uv_read_local_mmr(mmr_offset) >> right_shift) & UV_ACT_STATUS_MASK)) != DESC_STATUS_IDLE) { - if (descriptor_status == DESC_STATUS_SOURCE_TIMEOUT) { - source_timeouts++; - if (source_timeouts > SOURCE_TIMEOUT_LIMIT) - source_timeouts = 0; - __get_cpu_var(ptcstats).s_retry++; - return FLUSH_RETRY; - } /* - * spin here looking for progress at the destinations + * Our software ack messages may be blocked because there are + * no swack resources available. As long as none of them + * has timed out hardware will NACK our message and its + * state will stay IDLE. */ - if (descriptor_status == DESC_STATUS_DESTINATION_TIMEOUT) { - destination_timeouts++; - if (destination_timeouts > DESTINATION_TIMEOUT_LIMIT) { - /* - * returns number of cpus not responding - */ - if (uv_examine_destinations - (&bau_desc->distribution) == 0) { - __get_cpu_var(ptcstats).d_retry++; - return FLUSH_RETRY; - } - exams++; - if (exams >= uv_bau_retry_limit) { - printk(KERN_DEBUG - "uv_flush_tlb_others"); - printk("giving up on cpu %d\n", - smp_processor_id()); + if (descriptor_status == DESC_STATUS_SOURCE_TIMEOUT) { + stat->s_stimeout++; + return FLUSH_GIVEUP; + } else if (descriptor_status == + DESC_STATUS_DESTINATION_TIMEOUT) { + stat->s_dtimeout++; + ttime = get_cycles(); + + /* + * Our retries may be blocked by all destination + * swack resources being consumed, and a timeout + * pending. In that case hardware returns the + * ERROR that looks like a destination timeout. + */ + if (cycles_2_us(ttime - bcp->send_message) < BIOS_TO) { + bcp->conseccompletes = 0; + return FLUSH_RETRY_PLUGGED; + } + + bcp->conseccompletes = 0; + return FLUSH_RETRY_TIMEOUT; + } else { + /* + * descriptor_status is still BUSY + */ + cpu_relax(); + relaxes++; + if (relaxes >= 10000) { + relaxes = 0; + if (get_cycles() > timeout_time) { + quiesce_local_uvhub(hmaster); + + /* single-thread the register change */ + spin_lock(&hmaster->masks_lock); + mmr = uv_read_local_mmr(mmr_offset); + mask = 0UL; + mask |= (3UL < right_shift); + mask = ~mask; + mmr &= mask; + uv_write_local_mmr(mmr_offset, mmr); + spin_unlock(&hmaster->masks_lock); + end_uvhub_quiesce(hmaster); + stat->s_busy++; return FLUSH_GIVEUP; } - /* - * delays can hang the simulator - udelay(1000); - */ - destination_timeouts = 0; } } - cpu_relax(); } + bcp->conseccompletes++; return FLUSH_COMPLETE; } +static inline cycles_t +sec_2_cycles(unsigned long sec) +{ + unsigned long ns; + cycles_t cyc; + + ns = sec * 1000000000; + cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id())); + return cyc; +} + +/* + * conditionally add 1 to *v, unless *v is >= u + * return 0 if we cannot add 1 to *v because it is >= u + * return 1 if we can add 1 to *v because it is < u + * the add is atomic + * + * This is close to atomic_add_unless(), but this allows the 'u' value + * to be lowered below the current 'v'. atomic_add_unless can only stop + * on equal. + */ +static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u) +{ + spin_lock(lock); + if (atomic_read(v) >= u) { + spin_unlock(lock); + return 0; + } + atomic_inc(v); + spin_unlock(lock); + return 1; +} + /** * uv_flush_send_and_wait * - * Send a broadcast and wait for a broadcast message to complete. + * Send a broadcast and wait for it to complete. * - * The flush_mask contains the cpus the broadcast was sent to. + * The flush_mask contains the cpus the broadcast is to be sent to, plus + * cpus that are on the local uvhub. * - * Returns NULL if all remote flushing was done. The mask is zeroed. + * Returns NULL if all flushing represented in the mask was done. The mask + * is zeroed. * Returns @flush_mask if some remote flushing remains to be done. The - * mask will have some bits still set. + * mask will have some bits still set, representing any cpus on the local + * uvhub (not current cpu) and any on remote uvhubs if the broadcast failed. */ -const struct cpumask *uv_flush_send_and_wait(int cpu, int this_pnode, - struct bau_desc *bau_desc, - struct cpumask *flush_mask) +const struct cpumask *uv_flush_send_and_wait(struct bau_desc *bau_desc, + struct cpumask *flush_mask, + struct bau_control *bcp) { - int completion_status = 0; int right_shift; - int tries = 0; - int pnode; + int uvhub; int bit; + int completion_status = 0; + int seq_number = 0; + long try = 0; + int cpu = bcp->uvhub_cpu; + int this_cpu = bcp->cpu; + int this_uvhub = bcp->uvhub; unsigned long mmr_offset; unsigned long index; cycles_t time1; cycles_t time2; + struct ptc_stats *stat = &per_cpu(ptcstats, bcp->cpu); + struct bau_control *smaster = bcp->socket_master; + struct bau_control *hmaster = bcp->uvhub_master; + + /* + * Spin here while there are hmaster->max_concurrent or more active + * descriptors. This is the per-uvhub 'throttle'. + */ + if (!atomic_inc_unless_ge(&hmaster->uvhub_lock, + &hmaster->active_descriptor_count, + hmaster->max_concurrent)) { + stat->s_throttles++; + do { + cpu_relax(); + } while (!atomic_inc_unless_ge(&hmaster->uvhub_lock, + &hmaster->active_descriptor_count, + hmaster->max_concurrent)); + } + + while (hmaster->uvhub_quiesce) + cpu_relax(); if (cpu < UV_CPUS_PER_ACT_STATUS) { mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; @@ -268,24 +557,108 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_pnode, } time1 = get_cycles(); do { - tries++; + /* + * Every message from any given cpu gets a unique message + * sequence number. But retries use that same number. + * Our message may have timed out at the destination because + * all sw-ack resources are in use and there is a timeout + * pending there. In that case, our last send never got + * placed into the queue and we need to persist until it + * does. + * + * Make any retry a type MSG_RETRY so that the destination will + * free any resource held by a previous message from this cpu. + */ + if (try == 0) { + /* use message type set by the caller the first time */ + seq_number = bcp->message_number++; + } else { + /* use RETRY type on all the rest; same sequence */ + bau_desc->header.msg_type = MSG_RETRY; + stat->s_retry_messages++; + } + bau_desc->header.sequence = seq_number; index = (1UL << UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT) | - cpu; + bcp->uvhub_cpu; + bcp->send_message = get_cycles(); + uv_write_local_mmr(UVH_LB_BAU_SB_ACTIVATION_CONTROL, index); + + try++; completion_status = uv_wait_completion(bau_desc, mmr_offset, - right_shift); - } while (completion_status == FLUSH_RETRY); + right_shift, this_cpu, bcp, smaster, try); + + if (completion_status == FLUSH_RETRY_PLUGGED) { + /* + * Our retries may be blocked by all destination swack + * resources being consumed, and a timeout pending. In + * that case hardware immediately returns the ERROR + * that looks like a destination timeout. + */ + udelay(TIMEOUT_DELAY); + bcp->plugged_tries++; + if (bcp->plugged_tries >= PLUGSB4RESET) { + bcp->plugged_tries = 0; + quiesce_local_uvhub(hmaster); + spin_lock(&hmaster->queue_lock); + uv_reset_with_ipi(&bau_desc->distribution, + this_cpu); + spin_unlock(&hmaster->queue_lock); + end_uvhub_quiesce(hmaster); + bcp->ipi_attempts++; + stat->s_resets_plug++; + } + } else if (completion_status == FLUSH_RETRY_TIMEOUT) { + hmaster->max_concurrent = 1; + bcp->timeout_tries++; + udelay(TIMEOUT_DELAY); + if (bcp->timeout_tries >= TIMEOUTSB4RESET) { + bcp->timeout_tries = 0; + quiesce_local_uvhub(hmaster); + spin_lock(&hmaster->queue_lock); + uv_reset_with_ipi(&bau_desc->distribution, + this_cpu); + spin_unlock(&hmaster->queue_lock); + end_uvhub_quiesce(hmaster); + bcp->ipi_attempts++; + stat->s_resets_timeout++; + } + } + if (bcp->ipi_attempts >= 3) { + bcp->ipi_attempts = 0; + completion_status = FLUSH_GIVEUP; + break; + } + cpu_relax(); + } while ((completion_status == FLUSH_RETRY_PLUGGED) || + (completion_status == FLUSH_RETRY_TIMEOUT)); time2 = get_cycles(); - __get_cpu_var(ptcstats).sflush += (time2 - time1); - if (tries > 1) - __get_cpu_var(ptcstats).retriesok++; - if (completion_status == FLUSH_GIVEUP) { + if ((completion_status == FLUSH_COMPLETE) && (bcp->conseccompletes > 5) + && (hmaster->max_concurrent < hmaster->max_concurrent_constant)) + hmaster->max_concurrent++; + + /* + * hold any cpu not timing out here; no other cpu currently held by + * the 'throttle' should enter the activation code + */ + while (hmaster->uvhub_quiesce) + cpu_relax(); + atomic_dec(&hmaster->active_descriptor_count); + + /* guard against cycles wrap */ + if (time2 > time1) + stat->s_time += (time2 - time1); + else + stat->s_requestor--; /* don't count this one */ + if (completion_status == FLUSH_COMPLETE && try > 1) + stat->s_retriesok++; + else if (completion_status == FLUSH_GIVEUP) { /* * Cause the caller to do an IPI-style TLB shootdown on - * the cpu's, all of which are still in the mask. + * the target cpu's, all of which are still in the mask. */ - __get_cpu_var(ptcstats).ptc_i++; + stat->s_giveup++; return flush_mask; } @@ -294,18 +667,17 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_pnode, * use the IPI method of shootdown on them. */ for_each_cpu(bit, flush_mask) { - pnode = uv_cpu_to_pnode(bit); - if (pnode == this_pnode) + uvhub = uv_cpu_to_blade_id(bit); + if (uvhub == this_uvhub) continue; cpumask_clear_cpu(bit, flush_mask); } if (!cpumask_empty(flush_mask)) return flush_mask; + return NULL; } -static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask); - /** * uv_flush_tlb_others - globally purge translation cache of a virtual * address or all TLB's @@ -322,8 +694,8 @@ static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask); * The caller has derived the cpumask from the mm_struct. This function * is called only if there are bits set in the mask. (e.g. flush_tlb_page()) * - * The cpumask is converted into a nodemask of the nodes containing - * the cpus. + * The cpumask is converted into a uvhubmask of the uvhubs containing + * those cpus. * * Note that this function should be called with preemption disabled. * @@ -335,52 +707,82 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long va, unsigned int cpu) { - struct cpumask *flush_mask = __get_cpu_var(uv_flush_tlb_mask); - int i; - int bit; - int pnode; - int uv_cpu; - int this_pnode; + int remotes; + int tcpu; + int uvhub; int locals = 0; struct bau_desc *bau_desc; + struct cpumask *flush_mask; + struct ptc_stats *stat; + struct bau_control *bcp; - cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu)); + if (nobau) + return cpumask; - uv_cpu = uv_blade_processor_id(); - this_pnode = uv_hub_info->pnode; - bau_desc = __get_cpu_var(bau_control).descriptor_base; - bau_desc += UV_ITEMS_PER_DESCRIPTOR * uv_cpu; + bcp = &per_cpu(bau_control, cpu); + /* + * Each sending cpu has a per-cpu mask which it fills from the caller's + * cpu mask. Only remote cpus are converted to uvhubs and copied. + */ + flush_mask = (struct cpumask *)per_cpu(uv_flush_tlb_mask, cpu); + /* + * copy cpumask to flush_mask, removing current cpu + * (current cpu should already have been flushed by the caller and + * should never be returned if we return flush_mask) + */ + cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu)); + if (cpu_isset(cpu, *cpumask)) + locals++; /* current cpu was targeted */ - bau_nodes_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE); + bau_desc = bcp->descriptor_base; + bau_desc += UV_ITEMS_PER_DESCRIPTOR * bcp->uvhub_cpu; - i = 0; - for_each_cpu(bit, flush_mask) { - pnode = uv_cpu_to_pnode(bit); - BUG_ON(pnode > (UV_DISTRIBUTION_SIZE - 1)); - if (pnode == this_pnode) { + bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE); + remotes = 0; + for_each_cpu(tcpu, flush_mask) { + uvhub = uv_cpu_to_blade_id(tcpu); + if (uvhub == bcp->uvhub) { locals++; continue; } - bau_node_set(pnode - uv_partition_base_pnode, - &bau_desc->distribution); - i++; + bau_uvhub_set(uvhub, &bau_desc->distribution); + remotes++; } - if (i == 0) { + if (remotes == 0) { /* - * no off_node flushing; return status for local node + * No off_hub flushing; return status for local hub. + * Return the caller's mask if all were local (the current + * cpu may be in that mask). */ if (locals) - return flush_mask; + return cpumask; else return NULL; } - __get_cpu_var(ptcstats).requestor++; - __get_cpu_var(ptcstats).ntargeted += i; + stat = &per_cpu(ptcstats, cpu); + stat->s_requestor++; + stat->s_ntargcpu += remotes; + remotes = bau_uvhub_weight(&bau_desc->distribution); + stat->s_ntarguvhub += remotes; + if (remotes >= 16) + stat->s_ntarguvhub16++; + else if (remotes >= 8) + stat->s_ntarguvhub8++; + else if (remotes >= 4) + stat->s_ntarguvhub4++; + else if (remotes >= 2) + stat->s_ntarguvhub2++; + else + stat->s_ntarguvhub1++; bau_desc->payload.address = va; bau_desc->payload.sending_cpu = cpu; - return uv_flush_send_and_wait(uv_cpu, this_pnode, bau_desc, flush_mask); + /* + * uv_flush_send_and_wait returns null if all cpu's were messaged, or + * the adjusted flush_mask if any cpu's were not messaged. + */ + return uv_flush_send_and_wait(bau_desc, flush_mask, bcp); } /* @@ -389,87 +791,70 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, * * We received a broadcast assist message. * - * Interrupts may have been disabled; this interrupt could represent + * Interrupts are disabled; this interrupt could represent * the receipt of several messages. * - * All cores/threads on this node get this interrupt. - * The last one to see it does the s/w ack. + * All cores/threads on this hub get this interrupt. + * The last one to see it does the software ack. * (the resource will not be freed until noninterruptable cpus see this - * interrupt; hardware will timeout the s/w ack and reply ERROR) + * interrupt; hardware may timeout the s/w ack and reply ERROR) */ void uv_bau_message_interrupt(struct pt_regs *regs) { - struct bau_payload_queue_entry *va_queue_first; - struct bau_payload_queue_entry *va_queue_last; - struct bau_payload_queue_entry *msg; - struct pt_regs *old_regs = set_irq_regs(regs); - cycles_t time1; - cycles_t time2; - int msg_slot; - int sw_ack_slot; - int fw; int count = 0; - unsigned long local_pnode; - - ack_APIC_irq(); - exit_idle(); - irq_enter(); - - time1 = get_cycles(); - - local_pnode = uv_blade_to_pnode(uv_numa_blade_id()); - - va_queue_first = __get_cpu_var(bau_control).va_queue_first; - va_queue_last = __get_cpu_var(bau_control).va_queue_last; - - msg = __get_cpu_var(bau_control).bau_msg_head; + cycles_t time_start; + struct bau_payload_queue_entry *msg; + struct bau_control *bcp; + struct ptc_stats *stat; + struct msg_desc msgdesc; + + time_start = get_cycles(); + bcp = &per_cpu(bau_control, smp_processor_id()); + stat = &per_cpu(ptcstats, smp_processor_id()); + msgdesc.va_queue_first = bcp->va_queue_first; + msgdesc.va_queue_last = bcp->va_queue_last; + msg = bcp->bau_msg_head; while (msg->sw_ack_vector) { count++; - fw = msg->sw_ack_vector; - msg_slot = msg - va_queue_first; - sw_ack_slot = ffs(fw) - 1; - - uv_bau_process_message(msg, msg_slot, sw_ack_slot); - + msgdesc.msg_slot = msg - msgdesc.va_queue_first; + msgdesc.sw_ack_slot = ffs(msg->sw_ack_vector) - 1; + msgdesc.msg = msg; + uv_bau_process_message(&msgdesc, bcp); msg++; - if (msg > va_queue_last) - msg = va_queue_first; - __get_cpu_var(bau_control).bau_msg_head = msg; + if (msg > msgdesc.va_queue_last) + msg = msgdesc.va_queue_first; + bcp->bau_msg_head = msg; } + stat->d_time += (get_cycles() - time_start); if (!count) - __get_cpu_var(ptcstats).nomsg++; + stat->d_nomsg++; else if (count > 1) - __get_cpu_var(ptcstats).multmsg++; - - time2 = get_cycles(); - __get_cpu_var(ptcstats).dflush += (time2 - time1); - - irq_exit(); - set_irq_regs(old_regs); + stat->d_multmsg++; + ack_APIC_irq(); } /* * uv_enable_timeouts * - * Each target blade (i.e. blades that have cpu's) needs to have + * Each target uvhub (i.e. a uvhub that has no cpu's) needs to have * shootdown message timeouts enabled. The timeout does not cause * an interrupt, but causes an error message to be returned to * the sender. */ static void uv_enable_timeouts(void) { - int blade; - int nblades; + int uvhub; + int nuvhubs; int pnode; unsigned long mmr_image; - nblades = uv_num_possible_blades(); + nuvhubs = uv_num_possible_blades(); - for (blade = 0; blade < nblades; blade++) { - if (!uv_blade_nr_possible_cpus(blade)) + for (uvhub = 0; uvhub < nuvhubs; uvhub++) { + if (!uv_blade_nr_possible_cpus(uvhub)) continue; - pnode = uv_blade_to_pnode(blade); + pnode = uv_blade_to_pnode(uvhub); mmr_image = uv_read_global_mmr64(pnode, UVH_LB_BAU_MISC_CONTROL); /* @@ -479,16 +864,16 @@ static void uv_enable_timeouts(void) * To program the period, the SOFT_ACK_MODE must be off. */ mmr_image &= ~((unsigned long)1 << - UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT); + UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT); uv_write_global_mmr64 (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); /* * Set the 4-bit period. */ mmr_image &= ~((unsigned long)0xf << - UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT); + UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT); mmr_image |= (UV_INTD_SOFT_ACK_TIMEOUT_PERIOD << - UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT); + UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT); uv_write_global_mmr64 (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); /* @@ -497,7 +882,7 @@ static void uv_enable_timeouts(void) * indicated in bits 2:0 (7 causes all of them to timeout). */ mmr_image |= ((unsigned long)1 << - UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT); + UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT); uv_write_global_mmr64 (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); } @@ -522,9 +907,20 @@ static void uv_ptc_seq_stop(struct seq_file *file, void *data) { } +static inline unsigned long long +millisec_2_cycles(unsigned long millisec) +{ + unsigned long ns; + unsigned long long cyc; + + ns = millisec * 1000; + cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id())); + return cyc; +} + /* - * Display the statistics thru /proc - * data points to the cpu number + * Display the statistics thru /proc. + * 'data' points to the cpu number */ static int uv_ptc_seq_show(struct seq_file *file, void *data) { @@ -535,78 +931,155 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data) if (!cpu) { seq_printf(file, - "# cpu requestor requestee one all sretry dretry ptc_i "); + "# cpu sent stime numuvhubs numuvhubs16 numuvhubs8 "); seq_printf(file, - "sw_ack sflush dflush sok dnomsg dmult starget\n"); + "numuvhubs4 numuvhubs2 numuvhubs1 numcpus dto "); + seq_printf(file, + "retries rok resetp resett giveup sto bz throt "); + seq_printf(file, + "sw_ack recv rtime all "); + seq_printf(file, + "one mult none retry canc nocan reset rcan\n"); } if (cpu < num_possible_cpus() && cpu_online(cpu)) { stat = &per_cpu(ptcstats, cpu); - seq_printf(file, "cpu %d %ld %ld %ld %ld %ld %ld %ld ", - cpu, stat->requestor, - stat->requestee, stat->onetlb, stat->alltlb, - stat->s_retry, stat->d_retry, stat->ptc_i); - seq_printf(file, "%lx %ld %ld %ld %ld %ld %ld\n", + /* source side statistics */ + seq_printf(file, + "cpu %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ", + cpu, stat->s_requestor, cycles_2_us(stat->s_time), + stat->s_ntarguvhub, stat->s_ntarguvhub16, + stat->s_ntarguvhub8, stat->s_ntarguvhub4, + stat->s_ntarguvhub2, stat->s_ntarguvhub1, + stat->s_ntargcpu, stat->s_dtimeout); + seq_printf(file, "%ld %ld %ld %ld %ld %ld %ld %ld ", + stat->s_retry_messages, stat->s_retriesok, + stat->s_resets_plug, stat->s_resets_timeout, + stat->s_giveup, stat->s_stimeout, + stat->s_busy, stat->s_throttles); + /* destination side statistics */ + seq_printf(file, + "%lx %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld\n", uv_read_global_mmr64(uv_cpu_to_pnode(cpu), UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE), - stat->sflush, stat->dflush, - stat->retriesok, stat->nomsg, - stat->multmsg, stat->ntargeted); + stat->d_requestee, cycles_2_us(stat->d_time), + stat->d_alltlb, stat->d_onetlb, stat->d_multmsg, + stat->d_nomsg, stat->d_retries, stat->d_canceled, + stat->d_nocanceled, stat->d_resets, + stat->d_rcanceled); } return 0; } /* + * -1: resetf the statistics * 0: display meaning of the statistics - * >0: retry limit + * >0: maximum concurrent active descriptors per uvhub (throttle) */ static ssize_t uv_ptc_proc_write(struct file *file, const char __user *user, size_t count, loff_t *data) { - long newmode; + int cpu; + long input_arg; char optstr[64]; + struct ptc_stats *stat; + struct bau_control *bcp; if (count == 0 || count > sizeof(optstr)) return -EINVAL; if (copy_from_user(optstr, user, count)) return -EFAULT; optstr[count - 1] = '\0'; - if (strict_strtoul(optstr, 10, &newmode) < 0) { + if (strict_strtol(optstr, 10, &input_arg) < 0) { printk(KERN_DEBUG "%s is invalid\n", optstr); return -EINVAL; } - if (newmode == 0) { + if (input_arg == 0) { printk(KERN_DEBUG "# cpu: cpu number\n"); + printk(KERN_DEBUG "Sender statistics:\n"); + printk(KERN_DEBUG + "sent: number of shootdown messages sent\n"); + printk(KERN_DEBUG + "stime: time spent sending messages\n"); + printk(KERN_DEBUG + "numuvhubs: number of hubs targeted with shootdown\n"); + printk(KERN_DEBUG + "numuvhubs16: number times 16 or more hubs targeted\n"); + printk(KERN_DEBUG + "numuvhubs8: number times 8 or more hubs targeted\n"); + printk(KERN_DEBUG + "numuvhubs4: number times 4 or more hubs targeted\n"); + printk(KERN_DEBUG + "numuvhubs2: number times 2 or more hubs targeted\n"); + printk(KERN_DEBUG + "numuvhubs1: number times 1 hub targeted\n"); + printk(KERN_DEBUG + "numcpus: number of cpus targeted with shootdown\n"); + printk(KERN_DEBUG + "dto: number of destination timeouts\n"); + printk(KERN_DEBUG + "retries: destination timeout retries sent\n"); + printk(KERN_DEBUG + "rok: : destination timeouts successfully retried\n"); + printk(KERN_DEBUG + "resetp: ipi-style resource resets for plugs\n"); + printk(KERN_DEBUG + "resett: ipi-style resource resets for timeouts\n"); + printk(KERN_DEBUG + "giveup: fall-backs to ipi-style shootdowns\n"); + printk(KERN_DEBUG + "sto: number of source timeouts\n"); + printk(KERN_DEBUG + "bz: number of stay-busy's\n"); + printk(KERN_DEBUG + "throt: number times spun in throttle\n"); + printk(KERN_DEBUG "Destination side statistics:\n"); printk(KERN_DEBUG - "requestor: times this cpu was the flush requestor\n"); + "sw_ack: image of UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE\n"); printk(KERN_DEBUG - "requestee: times this cpu was requested to flush its TLBs\n"); + "recv: shootdown messages received\n"); printk(KERN_DEBUG - "one: times requested to flush a single address\n"); + "rtime: time spent processing messages\n"); printk(KERN_DEBUG - "all: times requested to flush all TLB's\n"); + "all: shootdown all-tlb messages\n"); printk(KERN_DEBUG - "sretry: number of retries of source-side timeouts\n"); + "one: shootdown one-tlb messages\n"); printk(KERN_DEBUG - "dretry: number of retries of destination-side timeouts\n"); + "mult: interrupts that found multiple messages\n"); printk(KERN_DEBUG - "ptc_i: times UV fell through to IPI-style flushes\n"); + "none: interrupts that found no messages\n"); printk(KERN_DEBUG - "sw_ack: image of UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE\n"); + "retry: number of retry messages processed\n"); printk(KERN_DEBUG - "sflush_us: cycles spent in uv_flush_tlb_others()\n"); + "canc: number messages canceled by retries\n"); printk(KERN_DEBUG - "dflush_us: cycles spent in handling flush requests\n"); - printk(KERN_DEBUG "sok: successes on retry\n"); - printk(KERN_DEBUG "dnomsg: interrupts with no message\n"); + "nocan: number retries that found nothing to cancel\n"); printk(KERN_DEBUG - "dmult: interrupts with multiple messages\n"); - printk(KERN_DEBUG "starget: nodes targeted\n"); + "reset: number of ipi-style reset requests processed\n"); + printk(KERN_DEBUG + "rcan: number messages canceled by reset requests\n"); + } else if (input_arg == -1) { + for_each_present_cpu(cpu) { + stat = &per_cpu(ptcstats, cpu); + memset(stat, 0, sizeof(struct ptc_stats)); + } } else { - uv_bau_retry_limit = newmode; - printk(KERN_DEBUG "timeout retry limit:%d\n", - uv_bau_retry_limit); + uv_bau_max_concurrent = input_arg; + bcp = &per_cpu(bau_control, smp_processor_id()); + if (uv_bau_max_concurrent < 1 || + uv_bau_max_concurrent > bcp->cpus_in_uvhub) { + printk(KERN_DEBUG + "Error: BAU max concurrent %d; %d is invalid\n", + bcp->max_concurrent, uv_bau_max_concurrent); + return -EINVAL; + } + printk(KERN_DEBUG "Set BAU max concurrent:%d\n", + uv_bau_max_concurrent); + for_each_present_cpu(cpu) { + bcp = &per_cpu(bau_control, cpu); + bcp->max_concurrent = uv_bau_max_concurrent; + } } return count; @@ -650,79 +1123,30 @@ static int __init uv_ptc_init(void) } /* - * begin the initialization of the per-blade control structures - */ -static struct bau_control * __init uv_table_bases_init(int blade, int node) -{ - int i; - struct bau_msg_status *msp; - struct bau_control *bau_tabp; - - bau_tabp = - kmalloc_node(sizeof(struct bau_control), GFP_KERNEL, node); - BUG_ON(!bau_tabp); - - bau_tabp->msg_statuses = - kmalloc_node(sizeof(struct bau_msg_status) * - DEST_Q_SIZE, GFP_KERNEL, node); - BUG_ON(!bau_tabp->msg_statuses); - - for (i = 0, msp = bau_tabp->msg_statuses; i < DEST_Q_SIZE; i++, msp++) - bau_cpubits_clear(&msp->seen_by, (int) - uv_blade_nr_possible_cpus(blade)); - - uv_bau_table_bases[blade] = bau_tabp; - - return bau_tabp; -} - -/* - * finish the initialization of the per-blade control structures - */ -static void __init -uv_table_bases_finish(int blade, - struct bau_control *bau_tablesp, - struct bau_desc *adp) -{ - struct bau_control *bcp; - int cpu; - - for_each_present_cpu(cpu) { - if (blade != uv_cpu_to_blade_id(cpu)) - continue; - - bcp = (struct bau_control *)&per_cpu(bau_control, cpu); - bcp->bau_msg_head = bau_tablesp->va_queue_first; - bcp->va_queue_first = bau_tablesp->va_queue_first; - bcp->va_queue_last = bau_tablesp->va_queue_last; - bcp->msg_statuses = bau_tablesp->msg_statuses; - bcp->descriptor_base = adp; - } -} - -/* * initialize the sending side's sending buffers */ -static struct bau_desc * __init +static void uv_activation_descriptor_init(int node, int pnode) { int i; + int cpu; unsigned long pa; unsigned long m; unsigned long n; - struct bau_desc *adp; - struct bau_desc *ad2; + struct bau_desc *bau_desc; + struct bau_desc *bd2; + struct bau_control *bcp; /* * each bau_desc is 64 bytes; there are 8 (UV_ITEMS_PER_DESCRIPTOR) - * per cpu; and up to 32 (UV_ADP_SIZE) cpu's per blade + * per cpu; and up to 32 (UV_ADP_SIZE) cpu's per uvhub */ - adp = (struct bau_desc *)kmalloc_node(sizeof(struct bau_desc)* + bau_desc = (struct bau_desc *)kmalloc_node(sizeof(struct bau_desc)* UV_ADP_SIZE*UV_ITEMS_PER_DESCRIPTOR, GFP_KERNEL, node); - BUG_ON(!adp); + BUG_ON(!bau_desc); - pa = uv_gpa(adp); /* need the real nasid*/ - n = uv_gpa_to_pnode(pa); + pa = uv_gpa(bau_desc); /* need the real nasid*/ + n = pa >> uv_nshift; m = pa & uv_mmask; uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE, @@ -731,96 +1155,188 @@ uv_activation_descriptor_init(int node, int pnode) /* * initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each * cpu even though we only use the first one; one descriptor can - * describe a broadcast to 256 nodes. + * describe a broadcast to 256 uv hubs. */ - for (i = 0, ad2 = adp; i < (UV_ADP_SIZE*UV_ITEMS_PER_DESCRIPTOR); - i++, ad2++) { - memset(ad2, 0, sizeof(struct bau_desc)); - ad2->header.sw_ack_flag = 1; + for (i = 0, bd2 = bau_desc; i < (UV_ADP_SIZE*UV_ITEMS_PER_DESCRIPTOR); + i++, bd2++) { + memset(bd2, 0, sizeof(struct bau_desc)); + bd2->header.sw_ack_flag = 1; /* - * base_dest_nodeid is the first node in the partition, so - * the bit map will indicate partition-relative node numbers. - * note that base_dest_nodeid is actually a nasid. + * base_dest_nodeid is the nasid (pnode<<1) of the first uvhub + * in the partition. The bit map will indicate uvhub numbers, + * which are 0-N in a partition. Pnodes are unique system-wide. */ - ad2->header.base_dest_nodeid = uv_partition_base_pnode << 1; - ad2->header.dest_subnodeid = 0x10; /* the LB */ - ad2->header.command = UV_NET_ENDPOINT_INTD; - ad2->header.int_both = 1; + bd2->header.base_dest_nodeid = uv_partition_base_pnode << 1; + bd2->header.dest_subnodeid = 0x10; /* the LB */ + bd2->header.command = UV_NET_ENDPOINT_INTD; + bd2->header.int_both = 1; /* * all others need to be set to zero: * fairness chaining multilevel count replied_to */ } - return adp; + for_each_present_cpu(cpu) { + if (pnode != uv_blade_to_pnode(uv_cpu_to_blade_id(cpu))) + continue; + bcp = &per_cpu(bau_control, cpu); + bcp->descriptor_base = bau_desc; + } } /* * initialize the destination side's receiving buffers + * entered for each uvhub in the partition + * - node is first node (kernel memory notion) on the uvhub + * - pnode is the uvhub's physical identifier */ -static struct bau_payload_queue_entry * __init -uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp) +static void +uv_payload_queue_init(int node, int pnode) { - struct bau_payload_queue_entry *pqp; - unsigned long pa; int pn; + int cpu; char *cp; + unsigned long pa; + struct bau_payload_queue_entry *pqp; + struct bau_payload_queue_entry *pqp_malloc; + struct bau_control *bcp; pqp = (struct bau_payload_queue_entry *) kmalloc_node( (DEST_Q_SIZE + 1) * sizeof(struct bau_payload_queue_entry), GFP_KERNEL, node); BUG_ON(!pqp); + pqp_malloc = pqp; cp = (char *)pqp + 31; pqp = (struct bau_payload_queue_entry *)(((unsigned long)cp >> 5) << 5); - bau_tablesp->va_queue_first = pqp; + + for_each_present_cpu(cpu) { + if (pnode != uv_cpu_to_pnode(cpu)) + continue; + /* for every cpu on this pnode: */ + bcp = &per_cpu(bau_control, cpu); + bcp->va_queue_first = pqp; + bcp->bau_msg_head = pqp; + bcp->va_queue_last = pqp + (DEST_Q_SIZE - 1); + } /* * need the pnode of where the memory was really allocated */ pa = uv_gpa(pqp); - pn = uv_gpa_to_pnode(pa); + pn = pa >> uv_nshift; uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST, ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) | uv_physnodeaddr(pqp)); uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL, uv_physnodeaddr(pqp)); - bau_tablesp->va_queue_last = pqp + (DEST_Q_SIZE - 1); uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST, (unsigned long) - uv_physnodeaddr(bau_tablesp->va_queue_last)); + uv_physnodeaddr(pqp + (DEST_Q_SIZE - 1))); + /* in effect, all msg_type's are set to MSG_NOOP */ memset(pqp, 0, sizeof(struct bau_payload_queue_entry) * DEST_Q_SIZE); - - return pqp; } /* - * Initialization of each UV blade's structures + * Initialization of each UV hub's structures */ -static int __init uv_init_blade(int blade) +static void __init uv_init_uvhub(int uvhub, int vector) { int node; int pnode; - unsigned long pa; unsigned long apicid; - struct bau_desc *adp; - struct bau_payload_queue_entry *pqp; - struct bau_control *bau_tablesp; - - node = blade_to_first_node(blade); - bau_tablesp = uv_table_bases_init(blade, node); - pnode = uv_blade_to_pnode(blade); - adp = uv_activation_descriptor_init(node, pnode); - pqp = uv_payload_queue_init(node, pnode, bau_tablesp); - uv_table_bases_finish(blade, bau_tablesp, adp); + + node = uvhub_to_first_node(uvhub); + pnode = uv_blade_to_pnode(uvhub); + uv_activation_descriptor_init(node, pnode); + uv_payload_queue_init(node, pnode); /* * the below initialization can't be in firmware because the * messaging IRQ will be determined by the OS */ - apicid = blade_to_first_apicid(blade); - pa = uv_read_global_mmr64(pnode, UVH_BAU_DATA_CONFIG); + apicid = uvhub_to_first_apicid(uvhub); uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, - ((apicid << 32) | UV_BAU_MESSAGE)); - return 0; + ((apicid << 32) | vector)); +} + +/* + * initialize the bau_control structure for each cpu + */ +static void uv_init_per_cpu(int nuvhubs) +{ + int i, j, k; + int cpu; + int pnode; + int uvhub; + short socket = 0; + struct bau_control *bcp; + struct uvhub_desc *bdp; + struct socket_desc *sdp; + struct bau_control *hmaster = NULL; + struct bau_control *smaster = NULL; + struct socket_desc { + short num_cpus; + short cpu_number[16]; + }; + struct uvhub_desc { + short num_sockets; + short num_cpus; + short uvhub; + short pnode; + struct socket_desc socket[2]; + }; + struct uvhub_desc *uvhub_descs; + + uvhub_descs = (struct uvhub_desc *) + kmalloc(nuvhubs * sizeof(struct uvhub_desc), GFP_KERNEL); + memset(uvhub_descs, 0, nuvhubs * sizeof(struct uvhub_desc)); + for_each_present_cpu(cpu) { + bcp = &per_cpu(bau_control, cpu); + memset(bcp, 0, sizeof(struct bau_control)); + spin_lock_init(&bcp->masks_lock); + bcp->max_concurrent = uv_bau_max_concurrent; + pnode = uv_cpu_hub_info(cpu)->pnode; + uvhub = uv_cpu_hub_info(cpu)->numa_blade_id; + bdp = &uvhub_descs[uvhub]; + bdp->num_cpus++; + bdp->uvhub = uvhub; + bdp->pnode = pnode; + /* time interval to catch a hardware stay-busy bug */ + bcp->timeout_interval = millisec_2_cycles(3); + /* kludge: assume uv_hub.h is constant */ + socket = (cpu_physical_id(cpu)>>5)&1; + if (socket >= bdp->num_sockets) + bdp->num_sockets = socket+1; + sdp = &bdp->socket[socket]; + sdp->cpu_number[sdp->num_cpus] = cpu; + sdp->num_cpus++; + } + socket = 0; + for_each_possible_blade(uvhub) { + bdp = &uvhub_descs[uvhub]; + for (i = 0; i < bdp->num_sockets; i++) { + sdp = &bdp->socket[i]; + for (j = 0; j < sdp->num_cpus; j++) { + cpu = sdp->cpu_number[j]; + bcp = &per_cpu(bau_control, cpu); + bcp->cpu = cpu; + if (j == 0) { + smaster = bcp; + if (i == 0) + hmaster = bcp; + } + bcp->cpus_in_uvhub = bdp->num_cpus; + bcp->cpus_in_socket = sdp->num_cpus; + bcp->socket_master = smaster; + bcp->uvhub_master = hmaster; + for (k = 0; k < DEST_Q_SIZE; k++) + bcp->socket_acknowledge_count[k] = 0; + bcp->uvhub_cpu = + uv_cpu_hub_info(cpu)->blade_processor_id; + } + socket++; + } + } + kfree(uvhub_descs); } /* @@ -828,38 +1344,54 @@ static int __init uv_init_blade(int blade) */ static int __init uv_bau_init(void) { - int blade; - int nblades; + int uvhub; + int pnode; + int nuvhubs; int cur_cpu; + int vector; + unsigned long mmr; if (!is_uv_system()) return 0; + if (nobau) + return 0; + for_each_possible_cpu(cur_cpu) zalloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu), GFP_KERNEL, cpu_to_node(cur_cpu)); - uv_bau_retry_limit = 1; + uv_bau_max_concurrent = MAX_BAU_CONCURRENT; + uv_nshift = uv_hub_info->m_val; uv_mmask = (1UL << uv_hub_info->m_val) - 1; - nblades = uv_num_possible_blades(); + nuvhubs = uv_num_possible_blades(); - uv_bau_table_bases = (struct bau_control **) - kmalloc(nblades * sizeof(struct bau_control *), GFP_KERNEL); - BUG_ON(!uv_bau_table_bases); + uv_init_per_cpu(nuvhubs); uv_partition_base_pnode = 0x7fffffff; - for (blade = 0; blade < nblades; blade++) - if (uv_blade_nr_possible_cpus(blade) && - (uv_blade_to_pnode(blade) < uv_partition_base_pnode)) - uv_partition_base_pnode = uv_blade_to_pnode(blade); - for (blade = 0; blade < nblades; blade++) - if (uv_blade_nr_possible_cpus(blade)) - uv_init_blade(blade); - - alloc_intr_gate(UV_BAU_MESSAGE, uv_bau_message_intr1); + for (uvhub = 0; uvhub < nuvhubs; uvhub++) + if (uv_blade_nr_possible_cpus(uvhub) && + (uv_blade_to_pnode(uvhub) < uv_partition_base_pnode)) + uv_partition_base_pnode = uv_blade_to_pnode(uvhub); + + vector = UV_BAU_MESSAGE; + for_each_possible_blade(uvhub) + if (uv_blade_nr_possible_cpus(uvhub)) + uv_init_uvhub(uvhub, vector); + uv_enable_timeouts(); + alloc_intr_gate(vector, uv_bau_message_intr1); + + for_each_possible_blade(uvhub) { + pnode = uv_blade_to_pnode(uvhub); + /* INIT the bau */ + uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_ACTIVATION_CONTROL, + ((unsigned long)1 << 63)); + mmr = 1; /* should be 1 to broadcast to both sockets */ + uv_write_global_mmr64(pnode, UVH_BAU_DATA_BROADCAST, mmr); + } return 0; } -__initcall(uv_bau_init); -__initcall(uv_ptc_init); +core_initcall(uv_bau_init); +core_initcall(uv_ptc_init); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1168e445418..60788dee0f8 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -15,6 +15,7 @@ #include <linux/kprobes.h> #include <linux/uaccess.h> #include <linux/kdebug.h> +#include <linux/kgdb.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/ptrace.h> @@ -108,15 +109,6 @@ static inline void preempt_conditional_cli(struct pt_regs *regs) dec_preempt_count(); } -#ifdef CONFIG_X86_32 -static inline void -die_if_kernel(const char *str, struct pt_regs *regs, long err) -{ - if (!user_mode_vm(regs)) - die(str, regs, err); -} -#endif - static void __kprobes do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, long error_code, siginfo_t *info) @@ -400,7 +392,13 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT) == NOTIFY_STOP) return; + #ifdef CONFIG_X86_LOCAL_APIC + if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) + == NOTIFY_STOP) + return; + +#ifndef CONFIG_LOCKUP_DETECTOR /* * Ok, so this is none of the documented NMI sources, * so it must be the NMI watchdog. @@ -408,6 +406,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) if (nmi_watchdog_tick(regs, reason)) return; if (!do_nmi_callback(regs, cpu)) +#endif /* !CONFIG_LOCKUP_DETECTOR */ unknown_nmi_error(reason, regs); #else unknown_nmi_error(reason, regs); @@ -460,6 +459,11 @@ void restart_nmi(void) /* May run on IST stack. */ dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code) { +#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP + if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) + == NOTIFY_STOP) + return; +#endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */ #ifdef CONFIG_KPROBES if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) @@ -529,6 +533,7 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) { struct task_struct *tsk = current; + int user_icebp = 0; unsigned long dr6; int si_code; @@ -537,17 +542,25 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) /* Filter out all the reserved bits which are preset to 1 */ dr6 &= ~DR6_RESERVED; + /* + * If dr6 has no reason to give us about the origin of this trap, + * then it's very likely the result of an icebp/int01 trap. + * User wants a sigtrap for that. + */ + if (!dr6 && user_mode(regs)) + user_icebp = 1; + /* Catch kmemcheck conditions first of all! */ if ((dr6 & DR_STEP) && kmemcheck_trap(regs)) return; /* DR6 may or may not be cleared by the CPU */ set_debugreg(0, 6); + /* * The processor cleared BTF, so don't mark that we need it set. */ - clear_tsk_thread_flag(tsk, TIF_DEBUGCTLMSR); - tsk->thread.debugctlmsr = 0; + clear_tsk_thread_flag(tsk, TIF_BLOCKSTEP); /* Store the virtualized DR6 value */ tsk->thread.debugreg6 = dr6; @@ -578,62 +591,74 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) regs->flags &= ~X86_EFLAGS_TF; } si_code = get_si_code(tsk->thread.debugreg6); - if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS)) + if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) send_sigtrap(tsk, regs, error_code, si_code); preempt_conditional_cli(regs); return; } -#ifdef CONFIG_X86_64 -static int kernel_math_error(struct pt_regs *regs, const char *str, int trapnr) -{ - if (fixup_exception(regs)) - return 1; - - notify_die(DIE_GPF, str, regs, 0, trapnr, SIGFPE); - /* Illegal floating point operation in the kernel */ - current->thread.trap_no = trapnr; - die(str, regs, 0); - return 0; -} -#endif - /* * Note that we play around with the 'TS' bit in an attempt to get * the correct behaviour even in the presence of the asynchronous * IRQ13 behaviour */ -void math_error(void __user *ip) +void math_error(struct pt_regs *regs, int error_code, int trapnr) { - struct task_struct *task; + struct task_struct *task = current; siginfo_t info; - unsigned short cwd, swd, err; + unsigned short err; + char *str = (trapnr == 16) ? "fpu exception" : "simd exception"; + + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP) + return; + conditional_sti(regs); + + if (!user_mode_vm(regs)) + { + if (!fixup_exception(regs)) { + task->thread.error_code = error_code; + task->thread.trap_no = trapnr; + die(str, regs, error_code); + } + return; + } /* * Save the info for the exception handler and clear the error. */ - task = current; save_init_fpu(task); - task->thread.trap_no = 16; - task->thread.error_code = 0; + task->thread.trap_no = trapnr; + task->thread.error_code = error_code; info.si_signo = SIGFPE; info.si_errno = 0; - info.si_addr = ip; - /* - * (~cwd & swd) will mask out exceptions that are not set to unmasked - * status. 0x3f is the exception bits in these regs, 0x200 is the - * C1 reg you need in case of a stack fault, 0x040 is the stack - * fault bit. We should only be taking one exception at a time, - * so if this combination doesn't produce any single exception, - * then we have a bad program that isn't synchronizing its FPU usage - * and it will suffer the consequences since we won't be able to - * fully reproduce the context of the exception - */ - cwd = get_fpu_cwd(task); - swd = get_fpu_swd(task); + info.si_addr = (void __user *)regs->ip; + if (trapnr == 16) { + unsigned short cwd, swd; + /* + * (~cwd & swd) will mask out exceptions that are not set to unmasked + * status. 0x3f is the exception bits in these regs, 0x200 is the + * C1 reg you need in case of a stack fault, 0x040 is the stack + * fault bit. We should only be taking one exception at a time, + * so if this combination doesn't produce any single exception, + * then we have a bad program that isn't synchronizing its FPU usage + * and it will suffer the consequences since we won't be able to + * fully reproduce the context of the exception + */ + cwd = get_fpu_cwd(task); + swd = get_fpu_swd(task); - err = swd & ~cwd; + err = swd & ~cwd; + } else { + /* + * The SIMD FPU exceptions are handled a little differently, as there + * is only a single status/control register. Thus, to determine which + * unmasked exception was caught we must mask the exception mask bits + * at 0x1f80, and then use these to mask the exception bits at 0x3f. + */ + unsigned short mxcsr = get_fpu_mxcsr(task); + err = ~(mxcsr >> 7) & mxcsr; + } if (err & 0x001) { /* Invalid op */ /* @@ -662,97 +687,17 @@ void math_error(void __user *ip) dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) { - conditional_sti(regs); - #ifdef CONFIG_X86_32 ignore_fpu_irq = 1; -#else - if (!user_mode(regs) && - kernel_math_error(regs, "kernel x87 math error", 16)) - return; #endif - math_error((void __user *)regs->ip); -} - -static void simd_math_error(void __user *ip) -{ - struct task_struct *task; - siginfo_t info; - unsigned short mxcsr; - - /* - * Save the info for the exception handler and clear the error. - */ - task = current; - save_init_fpu(task); - task->thread.trap_no = 19; - task->thread.error_code = 0; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_code = __SI_FAULT; - info.si_addr = ip; - /* - * The SIMD FPU exceptions are handled a little differently, as there - * is only a single status/control register. Thus, to determine which - * unmasked exception was caught we must mask the exception mask bits - * at 0x1f80, and then use these to mask the exception bits at 0x3f. - */ - mxcsr = get_fpu_mxcsr(task); - switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) { - case 0x000: - default: - break; - case 0x001: /* Invalid Op */ - info.si_code = FPE_FLTINV; - break; - case 0x002: /* Denormalize */ - case 0x010: /* Underflow */ - info.si_code = FPE_FLTUND; - break; - case 0x004: /* Zero Divide */ - info.si_code = FPE_FLTDIV; - break; - case 0x008: /* Overflow */ - info.si_code = FPE_FLTOVF; - break; - case 0x020: /* Precision */ - info.si_code = FPE_FLTRES; - break; - } - force_sig_info(SIGFPE, &info, task); + math_error(regs, error_code, 16); } dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { - conditional_sti(regs); - -#ifdef CONFIG_X86_32 - if (cpu_has_xmm) { - /* Handle SIMD FPU exceptions on PIII+ processors. */ - ignore_fpu_irq = 1; - simd_math_error((void __user *)regs->ip); - return; - } - /* - * Handle strange cache flush from user space exception - * in all other cases. This is undocumented behaviour. - */ - if (regs->flags & X86_VM_MASK) { - handle_vm86_fault((struct kernel_vm86_regs *)regs, error_code); - return; - } - current->thread.trap_no = 19; - current->thread.error_code = error_code; - die_if_kernel("cache flush denied", regs, error_code); - force_sig(SIGSEGV, current); -#else - if (!user_mode(regs) && - kernel_math_error(regs, "kernel simd math error", 19)) - return; - simd_math_error((void __user *)regs->ip); -#endif + math_error(regs, error_code, 19); } dotraplinkage void @@ -879,6 +824,16 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) } #endif +/* Set of traps needed for early debugging. */ +void __init early_trap_init(void) +{ + set_intr_gate_ist(1, &debug, DEBUG_STACK); + /* int3 can be called from all */ + set_system_intr_gate_ist(3, &int3, DEBUG_STACK); + set_intr_gate(14, &page_fault); + load_idt(&idt_descr); +} + void __init trap_init(void) { int i; @@ -892,10 +847,7 @@ void __init trap_init(void) #endif set_intr_gate(0, ÷_error); - set_intr_gate_ist(1, &debug, DEBUG_STACK); set_intr_gate_ist(2, &nmi, NMI_STACK); - /* int3 can be called from all */ - set_system_intr_gate_ist(3, &int3, DEBUG_STACK); /* int4 can be called from all */ set_system_intr_gate(4, &overflow); set_intr_gate(5, &bounds); @@ -911,7 +863,6 @@ void __init trap_init(void) set_intr_gate(11, &segment_not_present); set_intr_gate_ist(12, &stack_segment, STACKFAULT_STACK); set_intr_gate(13, &general_protection); - set_intr_gate(14, &page_fault); set_intr_gate(15, &spurious_interrupt_bug); set_intr_gate(16, &coprocessor_error); set_intr_gate(17, &alignment_check); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 9faf91ae184..ce8e5023933 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -751,7 +751,6 @@ static struct clocksource clocksource_tsc = { .read = read_tsc, .resume = resume_tsc, .mask = CLOCKSOURCE_MASK(64), - .shift = 22, .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_MUST_VERIFY, #ifdef CONFIG_X86_64 @@ -845,8 +844,6 @@ __cpuinit int unsynchronized_tsc(void) static void __init init_tsc_clocksource(void) { - clocksource_tsc.mult = clocksource_khz2mult(tsc_khz, - clocksource_tsc.shift); if (tsc_clocksource_reliable) clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; /* lower the rating if we already know its unstable: */ @@ -854,7 +851,7 @@ static void __init init_tsc_clocksource(void) clocksource_tsc.rating = 0; clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; } - clocksource_register(&clocksource_tsc); + clocksource_register_khz(&clocksource_tsc, tsc_khz); } #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/uv_irq.c b/arch/x86/kernel/uv_irq.c index 1d40336b030..1132129db79 100644 --- a/arch/x86/kernel/uv_irq.c +++ b/arch/x86/kernel/uv_irq.c @@ -44,7 +44,7 @@ static void uv_ack_apic(unsigned int irq) ack_APIC_irq(); } -struct irq_chip uv_irq_chip = { +static struct irq_chip uv_irq_chip = { .name = "UV-CORE", .startup = uv_noop_ret, .shutdown = uv_noop, @@ -141,7 +141,7 @@ int uv_irq_2_mmr_info(int irq, unsigned long *offset, int *pnode) */ static int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, - unsigned long mmr_offset, int restrict) + unsigned long mmr_offset, int limit) { const struct cpumask *eligible_cpu = cpumask_of(cpu); struct irq_desc *desc = irq_to_desc(irq); @@ -160,7 +160,7 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, if (err != 0) return err; - if (restrict == UV_AFFINITY_CPU) + if (limit == UV_AFFINITY_CPU) desc->status |= IRQ_NO_BALANCING; else desc->status |= IRQ_MOVE_PCNTXT; @@ -214,7 +214,7 @@ static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask) unsigned long mmr_value; struct uv_IO_APIC_route_entry *entry; unsigned long mmr_offset; - unsigned mmr_pnode; + int mmr_pnode; if (set_desc_affinity(desc, mask, &dest)) return -1; @@ -248,7 +248,7 @@ static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask) * interrupt is raised. */ int uv_setup_irq(char *irq_name, int cpu, int mmr_blade, - unsigned long mmr_offset, int restrict) + unsigned long mmr_offset, int limit) { int irq, ret; @@ -258,7 +258,7 @@ int uv_setup_irq(char *irq_name, int cpu, int mmr_blade, return -EBUSY; ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset, - restrict); + limit); if (ret == irq) uv_set_irq_2_mmr_info(irq, mmr_offset, mmr_blade); else diff --git a/arch/x86/kernel/verify_cpu_64.S b/arch/x86/kernel/verify_cpu_64.S index 45b6f8a975a..56a8c2a867d 100644 --- a/arch/x86/kernel/verify_cpu_64.S +++ b/arch/x86/kernel/verify_cpu_64.S @@ -31,6 +31,7 @@ */ #include <asm/cpufeature.h> +#include <asm/msr-index.h> verify_cpu: pushfl # Save caller passed flags @@ -88,7 +89,7 @@ verify_cpu_sse_test: je verify_cpu_sse_ok test %di,%di jz verify_cpu_no_longmode # only try to force SSE on AMD - movl $0xc0010015,%ecx # HWCR + movl $MSR_K7_HWCR,%ecx rdmsr btr $15,%eax # enable SSE wrmsr diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 2cc249718c4..d0bb52296fa 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -97,7 +97,7 @@ SECTIONS HEAD_TEXT #ifdef CONFIG_X86_32 . = ALIGN(PAGE_SIZE); - *(.text.page_aligned) + *(.text..page_aligned) #endif . = ALIGN(8); _stext = .; @@ -305,7 +305,7 @@ SECTIONS . = ALIGN(PAGE_SIZE); .bss : AT(ADDR(.bss) - LOAD_OFFSET) { __bss_start = .; - *(.bss.page_aligned) + *(.bss..page_aligned) *(.bss) . = ALIGN(4); __bss_stop = .; diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 1c0c6ab9c60..dcbb28c4b69 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -73,8 +73,8 @@ void update_vsyscall_tz(void) write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); } -void update_vsyscall(struct timespec *wall_time, struct clocksource *clock, - u32 mult) +void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, + struct clocksource *clock, u32 mult) { unsigned long flags; @@ -87,7 +87,7 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock, vsyscall_gtod_data.clock.shift = clock->shift; vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec; vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec; - vsyscall_gtod_data.wall_to_monotonic = wall_to_monotonic; + vsyscall_gtod_data.wall_to_monotonic = *wtm; vsyscall_gtod_data.wall_time_coarse = __current_kernel_time(); write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); } @@ -169,13 +169,18 @@ int __vsyscall(0) vgettimeofday(struct timeval * tv, struct timezone * tz) * unlikely */ time_t __vsyscall(1) vtime(time_t *t) { - struct timeval tv; + unsigned seq; time_t result; if (unlikely(!__vsyscall_gtod_data.sysctl_enabled)) return time_syscall(t); - vgettimeofday(&tv, NULL); - result = tv.tv_sec; + do { + seq = read_seqbegin(&__vsyscall_gtod_data.lock); + + result = __vsyscall_gtod_data.wall_time_sec; + + } while (read_seqretry(&__vsyscall_gtod_data.lock, seq)); + if (t) *t = result; return result; diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 693920b2249..1b950d151e5 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -54,7 +54,6 @@ EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(__memcpy); EXPORT_SYMBOL(empty_zero_page); -EXPORT_SYMBOL(init_level4_pgt); #ifndef CONFIG_PARAVIRT EXPORT_SYMBOL(native_load_gs_index); #endif diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 61a1e8c7e19..cd6da6bf3ec 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -5,6 +5,7 @@ */ #include <linux/init.h> #include <linux/ioport.h> +#include <linux/module.h> #include <asm/bios_ebda.h> #include <asm/paravirt.h> @@ -85,6 +86,7 @@ struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = { }; static void default_nmi_init(void) { }; +static int default_i8042_detect(void) { return 1; }; struct x86_platform_ops x86_platform = { .calibrate_tsc = native_calibrate_tsc, @@ -92,5 +94,8 @@ struct x86_platform_ops x86_platform = { .set_wallclock = mach_set_rtc_mmss, .iommu_shutdown = iommu_shutdown_noop, .is_untracked_pat_range = is_ISA_range, - .nmi_init = default_nmi_init + .nmi_init = default_nmi_init, + .i8042_detect = default_i8042_detect }; + +EXPORT_SYMBOL_GPL(x86_platform); diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 782c3a362ec..9c253bd65e2 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -16,11 +16,88 @@ */ u64 pcntxt_mask; +/* + * Represents init state for the supported extended state. + */ +static struct xsave_struct *init_xstate_buf; + struct _fpx_sw_bytes fx_sw_reserved; #ifdef CONFIG_IA32_EMULATION struct _fpx_sw_bytes fx_sw_reserved_ia32; #endif +static unsigned int *xstate_offsets, *xstate_sizes, xstate_features; + +/* + * If a processor implementation discern that a processor state component is + * in its initialized state it may modify the corresponding bit in the + * xsave_hdr.xstate_bv as '0', with out modifying the corresponding memory + * layout in the case of xsaveopt. While presenting the xstate information to + * the user, we always ensure that the memory layout of a feature will be in + * the init state if the corresponding header bit is zero. This is to ensure + * that the user doesn't see some stale state in the memory layout during + * signal handling, debugging etc. + */ +void __sanitize_i387_state(struct task_struct *tsk) +{ + u64 xstate_bv; + int feature_bit = 0x2; + struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave; + + if (!fx) + return; + + BUG_ON(task_thread_info(tsk)->status & TS_USEDFPU); + + xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv; + + /* + * None of the feature bits are in init state. So nothing else + * to do for us, as the memory layout is upto date. + */ + if ((xstate_bv & pcntxt_mask) == pcntxt_mask) + return; + + /* + * FP is in init state + */ + if (!(xstate_bv & XSTATE_FP)) { + fx->cwd = 0x37f; + fx->swd = 0; + fx->twd = 0; + fx->fop = 0; + fx->rip = 0; + fx->rdp = 0; + memset(&fx->st_space[0], 0, 128); + } + + /* + * SSE is in init state + */ + if (!(xstate_bv & XSTATE_SSE)) + memset(&fx->xmm_space[0], 0, 256); + + xstate_bv = (pcntxt_mask & ~xstate_bv) >> 2; + + /* + * Update all the other memory layouts for which the corresponding + * header bit is in the init state. + */ + while (xstate_bv) { + if (xstate_bv & 0x1) { + int offset = xstate_offsets[feature_bit]; + int size = xstate_sizes[feature_bit]; + + memcpy(((void *) fx) + offset, + ((void *) init_xstate_buf) + offset, + size); + } + + xstate_bv >>= 1; + feature_bit++; + } +} + /* * Check for the presence of extended state information in the * user fpstate pointer in the sigcontext. @@ -36,15 +113,14 @@ int check_for_xstate(struct i387_fxsave_struct __user *buf, err = __copy_from_user(fx_sw_user, &buf->sw_reserved[0], sizeof(struct _fpx_sw_bytes)); - if (err) - return err; + return -EFAULT; /* * First Magic check failed. */ if (fx_sw_user->magic1 != FP_XSTATE_MAGIC1) - return -1; + return -EINVAL; /* * Check for error scenarios. @@ -52,19 +128,21 @@ int check_for_xstate(struct i387_fxsave_struct __user *buf, if (fx_sw_user->xstate_size < min_xstate_size || fx_sw_user->xstate_size > xstate_size || fx_sw_user->xstate_size > fx_sw_user->extended_size) - return -1; + return -EINVAL; err = __get_user(magic2, (__u32 *) (((void *)fpstate) + fx_sw_user->extended_size - FP_XSTATE_MAGIC2_SIZE)); + if (err) + return err; /* * Check for the presence of second magic word at the end of memory * layout. This detects the case where the user just copied the legacy * fpstate layout with out copying the extended state information * in the memory layout. */ - if (err || magic2 != FP_XSTATE_MAGIC2) - return -1; + if (magic2 != FP_XSTATE_MAGIC2) + return -EFAULT; return 0; } @@ -91,15 +169,7 @@ int save_i387_xstate(void __user *buf) return 0; if (task_thread_info(tsk)->status & TS_USEDFPU) { - /* - * Start with clearing the user buffer. This will present a - * clean context for the bytes not touched by the fxsave/xsave. - */ - err = __clear_user(buf, sig_xstate_size); - if (err) - return err; - - if (task_thread_info(tsk)->status & TS_XSAVE) + if (use_xsave()) err = xsave_user(buf); else err = fxsave_user(buf); @@ -109,14 +179,15 @@ int save_i387_xstate(void __user *buf) task_thread_info(tsk)->status &= ~TS_USEDFPU; stts(); } else { - if (__copy_to_user(buf, &tsk->thread.xstate->fxsave, + sanitize_i387_state(tsk); + if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave, xstate_size)) return -1; } clear_used_math(); /* trigger finit */ - if (task_thread_info(tsk)->status & TS_XSAVE) { + if (use_xsave()) { struct _fpstate __user *fx = buf; struct _xstate __user *x = buf; u64 xstate_bv; @@ -184,8 +255,8 @@ static int restore_user_xstate(void __user *buf) * init the state skipped by the user. */ mask = pcntxt_mask & ~mask; - - xrstor_state(init_xstate_buf, mask); + if (unlikely(mask)) + xrstor_state(init_xstate_buf, mask); return 0; @@ -225,7 +296,7 @@ int restore_i387_xstate(void __user *buf) clts(); task_thread_info(current)->status |= TS_USEDFPU; } - if (task_thread_info(tsk)->status & TS_XSAVE) + if (use_xsave()) err = restore_user_xstate(buf); else err = fxrstor_checking((__force struct i387_fxsave_struct *) @@ -274,11 +345,6 @@ static void prepare_fx_sw_frame(void) #endif } -/* - * Represents init state for the supported extended state. - */ -struct xsave_struct *init_xstate_buf; - #ifdef CONFIG_X86_64 unsigned int sig_xstate_size = sizeof(struct _fpstate); #endif @@ -286,37 +352,77 @@ unsigned int sig_xstate_size = sizeof(struct _fpstate); /* * Enable the extended processor state save/restore feature */ -void __cpuinit xsave_init(void) +static inline void xstate_enable(void) { - if (!cpu_has_xsave) - return; - set_in_cr4(X86_CR4_OSXSAVE); - - /* - * Enable all the features that the HW is capable of - * and the Linux kernel is aware of. - */ xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask); } /* + * Record the offsets and sizes of different state managed by the xsave + * memory layout. + */ +static void __init setup_xstate_features(void) +{ + int eax, ebx, ecx, edx, leaf = 0x2; + + xstate_features = fls64(pcntxt_mask); + xstate_offsets = alloc_bootmem(xstate_features * sizeof(int)); + xstate_sizes = alloc_bootmem(xstate_features * sizeof(int)); + + do { + cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx); + + if (eax == 0) + break; + + xstate_offsets[leaf] = ebx; + xstate_sizes[leaf] = eax; + + leaf++; + } while (1); +} + +/* * setup the xstate image representing the init state */ static void __init setup_xstate_init(void) { + setup_xstate_features(); + + /* + * Setup init_xstate_buf to represent the init state of + * all the features managed by the xsave + */ init_xstate_buf = alloc_bootmem(xstate_size); init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT; + + clts(); + /* + * Init all the features state with header_bv being 0x0 + */ + xrstor_state(init_xstate_buf, -1); + /* + * Dump the init state again. This is to identify the init state + * of any feature which is not represented by all zero's. + */ + xsave_state(init_xstate_buf, -1); + stts(); } /* * Enable and initialize the xsave feature. */ -void __ref xsave_cntxt_init(void) +static void __init xstate_enable_boot_cpu(void) { unsigned int eax, ebx, ecx, edx; - cpuid_count(0xd, 0, &eax, &ebx, &ecx, &edx); + if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { + WARN(1, KERN_ERR "XSTATE_CPUID missing\n"); + return; + } + + cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); pcntxt_mask = eax + ((u64)edx << 32); if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) { @@ -329,12 +435,13 @@ void __ref xsave_cntxt_init(void) * Support only the state known to OS. */ pcntxt_mask = pcntxt_mask & XCNTXT_MASK; - xsave_init(); + + xstate_enable(); /* * Recompute the context size for enabled features */ - cpuid_count(0xd, 0, &eax, &ebx, &ecx, &edx); + cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); xstate_size = ebx; update_regset_xstate_info(xstate_size, pcntxt_mask); @@ -346,3 +453,23 @@ void __ref xsave_cntxt_init(void) "cntxt size 0x%x\n", pcntxt_mask, xstate_size); } + +/* + * For the very first instance, this calls xstate_enable_boot_cpu(); + * for all subsequent instances, this calls xstate_enable(). + * + * This is somewhat obfuscated due to the lack of powerful enough + * overrides for the section checks. + */ +void __cpuinit xsave_init(void) +{ + static __refdata void (*next_func)(void) = xstate_enable_boot_cpu; + void (*this_func)(void); + + if (!cpu_has_xsave) + return; + + this_func = next_func; + next_func = xstate_enable; + this_func(); +} diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 4dade6ac082..b38bd8b92aa 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -9,6 +9,7 @@ * privileged instructions: * * Copyright (C) 2006 Qumranet + * Copyright 2010 Red Hat, Inc. and/or its affilates. * * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> @@ -33,6 +34,7 @@ #include <asm/kvm_emulate.h> #include "x86.h" +#include "tss.h" /* * Opcode effective-address decode tables. @@ -50,6 +52,8 @@ #define DstReg (2<<1) /* Register operand. */ #define DstMem (3<<1) /* Memory operand. */ #define DstAcc (4<<1) /* Destination Accumulator */ +#define DstDI (5<<1) /* Destination is in ES:(E)DI */ +#define DstMem64 (6<<1) /* 64bit memory operand */ #define DstMask (7<<1) /* Source operand type. */ #define SrcNone (0<<4) /* No source operand. */ @@ -63,6 +67,10 @@ #define SrcOne (7<<4) /* Implied '1' */ #define SrcImmUByte (8<<4) /* 8-bit unsigned immediate operand. */ #define SrcImmU (9<<4) /* Immediate operand, unsigned */ +#define SrcSI (0xa<<4) /* Source is in the DS:RSI */ +#define SrcImmFAddr (0xb<<4) /* Source is immediate far address */ +#define SrcMemFAddr (0xc<<4) /* Source is far address in memory */ +#define SrcAcc (0xd<<4) /* Source Accumulator */ #define SrcMask (0xf<<4) /* Generic ModRM decode. */ #define ModRM (1<<8) @@ -84,7 +92,6 @@ #define Src2CL (1<<29) #define Src2ImmByte (2<<29) #define Src2One (3<<29) -#define Src2Imm16 (4<<29) #define Src2Mask (7<<29) enum { @@ -117,15 +124,15 @@ static u32 opcode_table[256] = { /* 0x20 - 0x27 */ ByteOp | DstMem | SrcReg | ModRM | Lock, DstMem | SrcReg | ModRM | Lock, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - DstAcc | SrcImmByte, DstAcc | SrcImm, 0, 0, + ByteOp | DstAcc | SrcImmByte, DstAcc | SrcImm, 0, 0, /* 0x28 - 0x2F */ ByteOp | DstMem | SrcReg | ModRM | Lock, DstMem | SrcReg | ModRM | Lock, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, + ByteOp | DstAcc | SrcImmByte, DstAcc | SrcImm, 0, 0, /* 0x30 - 0x37 */ ByteOp | DstMem | SrcReg | ModRM | Lock, DstMem | SrcReg | ModRM | Lock, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, + ByteOp | DstAcc | SrcImmByte, DstAcc | SrcImm, 0, 0, /* 0x38 - 0x3F */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, @@ -147,8 +154,8 @@ static u32 opcode_table[256] = { 0, 0, 0, 0, /* 0x68 - 0x6F */ SrcImm | Mov | Stack, 0, SrcImmByte | Mov | Stack, 0, - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* insb, insw/insd */ - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* outsb, outsw/outsd */ + DstDI | ByteOp | Mov | String, DstDI | Mov | String, /* insb, insw/insd */ + SrcSI | ByteOp | ImplicitOps | String, SrcSI | ImplicitOps | String, /* outsb, outsw/outsd */ /* 0x70 - 0x77 */ SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, @@ -163,22 +170,22 @@ static u32 opcode_table[256] = { /* 0x88 - 0x8F */ ByteOp | DstMem | SrcReg | ModRM | Mov, DstMem | SrcReg | ModRM | Mov, ByteOp | DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, - DstMem | SrcReg | ModRM | Mov, ModRM | DstReg, - DstReg | SrcMem | ModRM | Mov, Group | Group1A, + DstMem | SrcNone | ModRM | Mov, ModRM | DstReg, + ImplicitOps | SrcMem16 | ModRM, Group | Group1A, /* 0x90 - 0x97 */ DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, /* 0x98 - 0x9F */ - 0, 0, SrcImm | Src2Imm16 | No64, 0, + 0, 0, SrcImmFAddr | No64, 0, ImplicitOps | Stack, ImplicitOps | Stack, 0, 0, /* 0xA0 - 0xA7 */ - ByteOp | DstReg | SrcMem | Mov | MemAbs, DstReg | SrcMem | Mov | MemAbs, - ByteOp | DstMem | SrcReg | Mov | MemAbs, DstMem | SrcReg | Mov | MemAbs, - ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String, - ByteOp | ImplicitOps | String, ImplicitOps | String, + ByteOp | DstAcc | SrcMem | Mov | MemAbs, DstAcc | SrcMem | Mov | MemAbs, + ByteOp | DstMem | SrcAcc | Mov | MemAbs, DstMem | SrcAcc | Mov | MemAbs, + ByteOp | SrcSI | DstDI | Mov | String, SrcSI | DstDI | Mov | String, + ByteOp | SrcSI | DstDI | String, SrcSI | DstDI | String, /* 0xA8 - 0xAF */ - 0, 0, ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String, - ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String, - ByteOp | ImplicitOps | String, ImplicitOps | String, + DstAcc | SrcImmByte | ByteOp, DstAcc | SrcImm, ByteOp | DstDI | Mov | String, DstDI | Mov | String, + ByteOp | SrcSI | DstAcc | Mov | String, SrcSI | DstAcc | Mov | String, + ByteOp | DstDI | String, DstDI | String, /* 0xB0 - 0xB7 */ ByteOp | DstReg | SrcImm | Mov, ByteOp | DstReg | SrcImm | Mov, ByteOp | DstReg | SrcImm | Mov, ByteOp | DstReg | SrcImm | Mov, @@ -204,13 +211,13 @@ static u32 opcode_table[256] = { 0, 0, 0, 0, 0, 0, 0, 0, /* 0xE0 - 0xE7 */ 0, 0, 0, 0, - ByteOp | SrcImmUByte, SrcImmUByte, - ByteOp | SrcImmUByte, SrcImmUByte, + ByteOp | SrcImmUByte | DstAcc, SrcImmUByte | DstAcc, + ByteOp | SrcImmUByte | DstAcc, SrcImmUByte | DstAcc, /* 0xE8 - 0xEF */ SrcImm | Stack, SrcImm | ImplicitOps, - SrcImmU | Src2Imm16 | No64, SrcImmByte | ImplicitOps, - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, + SrcImmFAddr | No64, SrcImmByte | ImplicitOps, + SrcNone | ByteOp | DstAcc, SrcNone | DstAcc, + SrcNone | ByteOp | DstAcc, SrcNone | DstAcc, /* 0xF0 - 0xF7 */ 0, 0, 0, 0, ImplicitOps | Priv, ImplicitOps, Group | Group3_Byte, Group | Group3, @@ -330,20 +337,21 @@ static u32 group_table[] = { [Group1A*8] = DstMem | SrcNone | ModRM | Mov | Stack, 0, 0, 0, 0, 0, 0, 0, [Group3_Byte*8] = - ByteOp | SrcImm | DstMem | ModRM, 0, + ByteOp | SrcImm | DstMem | ModRM, ByteOp | SrcImm | DstMem | ModRM, ByteOp | DstMem | SrcNone | ModRM, ByteOp | DstMem | SrcNone | ModRM, 0, 0, 0, 0, [Group3*8] = - DstMem | SrcImm | ModRM, 0, + DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM, DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM, 0, 0, 0, 0, [Group4*8] = - ByteOp | DstMem | SrcNone | ModRM, ByteOp | DstMem | SrcNone | ModRM, + ByteOp | DstMem | SrcNone | ModRM | Lock, ByteOp | DstMem | SrcNone | ModRM | Lock, 0, 0, 0, 0, 0, 0, [Group5*8] = - DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM, + DstMem | SrcNone | ModRM | Lock, DstMem | SrcNone | ModRM | Lock, + SrcMem | ModRM | Stack, 0, + SrcMem | ModRM | Stack, SrcMemFAddr | ModRM | ImplicitOps, SrcMem | ModRM | Stack, 0, - SrcMem | ModRM | Stack, 0, SrcMem | ModRM | Stack, 0, [Group7*8] = 0, 0, ModRM | SrcMem | Priv, ModRM | SrcMem | Priv, SrcNone | ModRM | DstMem | Mov, 0, @@ -353,14 +361,14 @@ static u32 group_table[] = { DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM | Lock, DstMem | SrcImmByte | ModRM | Lock, DstMem | SrcImmByte | ModRM | Lock, [Group9*8] = - 0, ImplicitOps | ModRM | Lock, 0, 0, 0, 0, 0, 0, + 0, DstMem64 | ModRM | Lock, 0, 0, 0, 0, 0, 0, }; static u32 group2_table[] = { [Group7*8] = - SrcNone | ModRM | Priv, 0, 0, SrcNone | ModRM, + SrcNone | ModRM | Priv, 0, 0, SrcNone | ModRM | Priv, SrcNone | ModRM | DstMem | Mov, 0, - SrcMem16 | ModRM | Mov, 0, + SrcMem16 | ModRM | Mov | Priv, 0, [Group9*8] = 0, 0, 0, 0, 0, 0, 0, 0, }; @@ -562,12 +570,19 @@ static u32 group2_table[] = { #define insn_fetch(_type, _size, _eip) \ ({ unsigned long _x; \ rc = do_insn_fetch(ctxt, ops, (_eip), &_x, (_size)); \ - if (rc != 0) \ + if (rc != X86EMUL_CONTINUE) \ goto done; \ (_eip) += (_size); \ (_type)_x; \ }) +#define insn_fetch_arr(_arr, _size, _eip) \ +({ rc = do_insn_fetch(ctxt, ops, (_eip), _arr, (_size)); \ + if (rc != X86EMUL_CONTINUE) \ + goto done; \ + (_eip) += (_size); \ +}) + static inline unsigned long ad_mask(struct decode_cache *c) { return (1UL << (c->ad_bytes << 3)) - 1; @@ -609,69 +624,104 @@ static void set_seg_override(struct decode_cache *c, int seg) c->seg_override = seg; } -static unsigned long seg_base(struct x86_emulate_ctxt *ctxt, int seg) +static unsigned long seg_base(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, int seg) { if (ctxt->mode == X86EMUL_MODE_PROT64 && seg < VCPU_SREG_FS) return 0; - return kvm_x86_ops->get_segment_base(ctxt->vcpu, seg); + return ops->get_cached_segment_base(seg, ctxt->vcpu); } static unsigned long seg_override_base(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, struct decode_cache *c) { if (!c->has_seg_override) return 0; - return seg_base(ctxt, c->seg_override); + return seg_base(ctxt, ops, c->seg_override); +} + +static unsigned long es_base(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + return seg_base(ctxt, ops, VCPU_SREG_ES); +} + +static unsigned long ss_base(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + return seg_base(ctxt, ops, VCPU_SREG_SS); +} + +static void emulate_exception(struct x86_emulate_ctxt *ctxt, int vec, + u32 error, bool valid) +{ + ctxt->exception = vec; + ctxt->error_code = error; + ctxt->error_code_valid = valid; + ctxt->restart = false; } -static unsigned long es_base(struct x86_emulate_ctxt *ctxt) +static void emulate_gp(struct x86_emulate_ctxt *ctxt, int err) { - return seg_base(ctxt, VCPU_SREG_ES); + emulate_exception(ctxt, GP_VECTOR, err, true); } -static unsigned long ss_base(struct x86_emulate_ctxt *ctxt) +static void emulate_pf(struct x86_emulate_ctxt *ctxt, unsigned long addr, + int err) { - return seg_base(ctxt, VCPU_SREG_SS); + ctxt->cr2 = addr; + emulate_exception(ctxt, PF_VECTOR, err, true); +} + +static void emulate_ud(struct x86_emulate_ctxt *ctxt) +{ + emulate_exception(ctxt, UD_VECTOR, 0, false); +} + +static void emulate_ts(struct x86_emulate_ctxt *ctxt, int err) +{ + emulate_exception(ctxt, TS_VECTOR, err, true); } static int do_fetch_insn_byte(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, - unsigned long linear, u8 *dest) + unsigned long eip, u8 *dest) { struct fetch_cache *fc = &ctxt->decode.fetch; int rc; - int size; + int size, cur_size; - if (linear < fc->start || linear >= fc->end) { - size = min(15UL, PAGE_SIZE - offset_in_page(linear)); - rc = ops->fetch(linear, fc->data, size, ctxt->vcpu, NULL); - if (rc) + if (eip == fc->end) { + cur_size = fc->end - fc->start; + size = min(15UL - cur_size, PAGE_SIZE - offset_in_page(eip)); + rc = ops->fetch(ctxt->cs_base + eip, fc->data + cur_size, + size, ctxt->vcpu, NULL); + if (rc != X86EMUL_CONTINUE) return rc; - fc->start = linear; - fc->end = linear + size; + fc->end += size; } - *dest = fc->data[linear - fc->start]; - return 0; + *dest = fc->data[eip - fc->start]; + return X86EMUL_CONTINUE; } static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, unsigned long eip, void *dest, unsigned size) { - int rc = 0; + int rc; /* x86 instructions are limited to 15 bytes. */ - if (eip + size - ctxt->decode.eip_orig > 15) + if (eip + size - ctxt->eip > 15) return X86EMUL_UNHANDLEABLE; - eip += ctxt->cs_base; while (size--) { rc = do_fetch_insn_byte(ctxt, ops, eip++, dest++); - if (rc) + if (rc != X86EMUL_CONTINUE) return rc; } - return 0; + return X86EMUL_CONTINUE; } /* @@ -702,7 +752,7 @@ static int read_descriptor(struct x86_emulate_ctxt *ctxt, *address = 0; rc = ops->read_std((unsigned long)ptr, (unsigned long *)size, 2, ctxt->vcpu, NULL); - if (rc) + if (rc != X86EMUL_CONTINUE) return rc; rc = ops->read_std((unsigned long)ptr + 2, address, op_bytes, ctxt->vcpu, NULL); @@ -782,7 +832,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, struct decode_cache *c = &ctxt->decode; u8 sib; int index_reg = 0, base_reg = 0, scale; - int rc = 0; + int rc = X86EMUL_CONTINUE; if (c->rex_prefix) { c->modrm_reg = (c->rex_prefix & 4) << 1; /* REX.R */ @@ -895,7 +945,7 @@ static int decode_abs(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc = 0; + int rc = X86EMUL_CONTINUE; switch (c->ad_bytes) { case 2: @@ -916,16 +966,17 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc = 0; + int rc = X86EMUL_CONTINUE; int mode = ctxt->mode; int def_op_bytes, def_ad_bytes, group; - /* Shadow copy of register state. Committed on successful emulation. */ - memset(c, 0, sizeof(struct decode_cache)); - c->eip = c->eip_orig = kvm_rip_read(ctxt->vcpu); - ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS); - memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); + /* we cannot decode insn before we complete previous rep insn */ + WARN_ON(ctxt->restart); + + c->eip = ctxt->eip; + c->fetch.start = c->fetch.end = c->eip; + ctxt->cs_base = seg_base(ctxt, ops, VCPU_SREG_CS); switch (mode) { case X86EMUL_MODE_REAL: @@ -1015,11 +1066,6 @@ done_prefixes: } } - if (mode == X86EMUL_MODE_PROT64 && (c->d & No64)) { - kvm_report_emulation_failure(ctxt->vcpu, "invalid x86/64 instruction"); - return -1; - } - if (c->d & Group) { group = c->d & GroupMask; c->modrm = insn_fetch(u8, 1, c->eip); @@ -1046,17 +1092,21 @@ done_prefixes: rc = decode_modrm(ctxt, ops); else if (c->d & MemAbs) rc = decode_abs(ctxt, ops); - if (rc) + if (rc != X86EMUL_CONTINUE) goto done; if (!c->has_seg_override) set_seg_override(c, VCPU_SREG_DS); if (!(!c->twobyte && c->b == 0x8d)) - c->modrm_ea += seg_override_base(ctxt, c); + c->modrm_ea += seg_override_base(ctxt, ops, c); if (c->ad_bytes != 8) c->modrm_ea = (u32)c->modrm_ea; + + if (c->rip_relative) + c->modrm_ea += c->eip; + /* * Decode and fetch the source operand: register, memory * or immediate. @@ -1091,6 +1141,8 @@ done_prefixes: break; } c->src.type = OP_MEM; + c->src.ptr = (unsigned long *)c->modrm_ea; + c->src.val = 0; break; case SrcImm: case SrcImmU: @@ -1135,10 +1187,48 @@ done_prefixes: else c->src.val = insn_fetch(u8, 1, c->eip); break; + case SrcAcc: + c->src.type = OP_REG; + c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->src.ptr = &c->regs[VCPU_REGS_RAX]; + switch (c->src.bytes) { + case 1: + c->src.val = *(u8 *)c->src.ptr; + break; + case 2: + c->src.val = *(u16 *)c->src.ptr; + break; + case 4: + c->src.val = *(u32 *)c->src.ptr; + break; + case 8: + c->src.val = *(u64 *)c->src.ptr; + break; + } + break; case SrcOne: c->src.bytes = 1; c->src.val = 1; break; + case SrcSI: + c->src.type = OP_MEM; + c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->src.ptr = (unsigned long *) + register_address(c, seg_override_base(ctxt, ops, c), + c->regs[VCPU_REGS_RSI]); + c->src.val = 0; + break; + case SrcImmFAddr: + c->src.type = OP_IMM; + c->src.ptr = (unsigned long *)c->eip; + c->src.bytes = c->op_bytes + 2; + insn_fetch_arr(c->src.valptr, c->src.bytes, c->eip); + break; + case SrcMemFAddr: + c->src.type = OP_MEM; + c->src.ptr = (unsigned long *)c->modrm_ea; + c->src.bytes = c->op_bytes + 2; + break; } /* @@ -1158,12 +1248,6 @@ done_prefixes: c->src2.bytes = 1; c->src2.val = insn_fetch(u8, 1, c->eip); break; - case Src2Imm16: - c->src2.type = OP_IMM; - c->src2.ptr = (unsigned long *)c->eip; - c->src2.bytes = 2; - c->src2.val = insn_fetch(u16, 2, c->eip); - break; case Src2One: c->src2.bytes = 1; c->src2.val = 1; @@ -1180,6 +1264,7 @@ done_prefixes: c->twobyte && (c->b == 0xb6 || c->b == 0xb7)); break; case DstMem: + case DstMem64: if ((c->d & ModRM) && c->modrm_mod == 3) { c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; c->dst.type = OP_REG; @@ -1188,12 +1273,24 @@ done_prefixes: break; } c->dst.type = OP_MEM; + c->dst.ptr = (unsigned long *)c->modrm_ea; + if ((c->d & DstMask) == DstMem64) + c->dst.bytes = 8; + else + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->dst.val = 0; + if (c->d & BitOp) { + unsigned long mask = ~(c->dst.bytes * 8 - 1); + + c->dst.ptr = (void *)c->dst.ptr + + (c->src.val & mask) / 8; + } break; case DstAcc: c->dst.type = OP_REG; - c->dst.bytes = c->op_bytes; + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; c->dst.ptr = &c->regs[VCPU_REGS_RAX]; - switch (c->op_bytes) { + switch (c->dst.bytes) { case 1: c->dst.val = *(u8 *)c->dst.ptr; break; @@ -1203,19 +1300,339 @@ done_prefixes: case 4: c->dst.val = *(u32 *)c->dst.ptr; break; + case 8: + c->dst.val = *(u64 *)c->dst.ptr; + break; } c->dst.orig_val = c->dst.val; break; + case DstDI: + c->dst.type = OP_MEM; + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->dst.ptr = (unsigned long *) + register_address(c, es_base(ctxt, ops), + c->regs[VCPU_REGS_RDI]); + c->dst.val = 0; + break; } - if (c->rip_relative) - c->modrm_ea += c->eip; - done: return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0; } -static inline void emulate_push(struct x86_emulate_ctxt *ctxt) +static int read_emulated(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + unsigned long addr, void *dest, unsigned size) +{ + int rc; + struct read_cache *mc = &ctxt->decode.mem_read; + u32 err; + + while (size) { + int n = min(size, 8u); + size -= n; + if (mc->pos < mc->end) + goto read_cached; + + rc = ops->read_emulated(addr, mc->data + mc->end, n, &err, + ctxt->vcpu); + if (rc == X86EMUL_PROPAGATE_FAULT) + emulate_pf(ctxt, addr, err); + if (rc != X86EMUL_CONTINUE) + return rc; + mc->end += n; + + read_cached: + memcpy(dest, mc->data + mc->pos, n); + mc->pos += n; + dest += n; + addr += n; + } + return X86EMUL_CONTINUE; +} + +static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + unsigned int size, unsigned short port, + void *dest) +{ + struct read_cache *rc = &ctxt->decode.io_read; + + if (rc->pos == rc->end) { /* refill pio read ahead */ + struct decode_cache *c = &ctxt->decode; + unsigned int in_page, n; + unsigned int count = c->rep_prefix ? + address_mask(c, c->regs[VCPU_REGS_RCX]) : 1; + in_page = (ctxt->eflags & EFLG_DF) ? + offset_in_page(c->regs[VCPU_REGS_RDI]) : + PAGE_SIZE - offset_in_page(c->regs[VCPU_REGS_RDI]); + n = min(min(in_page, (unsigned int)sizeof(rc->data)) / size, + count); + if (n == 0) + n = 1; + rc->pos = rc->end = 0; + if (!ops->pio_in_emulated(size, port, rc->data, n, ctxt->vcpu)) + return 0; + rc->end = n * size; + } + + memcpy(dest, rc->data + rc->pos, size); + rc->pos += size; + return 1; +} + +static u32 desc_limit_scaled(struct desc_struct *desc) +{ + u32 limit = get_desc_limit(desc); + + return desc->g ? (limit << 12) | 0xfff : limit; +} + +static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 selector, struct desc_ptr *dt) +{ + if (selector & 1 << 2) { + struct desc_struct desc; + memset (dt, 0, sizeof *dt); + if (!ops->get_cached_descriptor(&desc, VCPU_SREG_LDTR, ctxt->vcpu)) + return; + + dt->size = desc_limit_scaled(&desc); /* what if limit > 65535? */ + dt->address = get_desc_base(&desc); + } else + ops->get_gdt(dt, ctxt->vcpu); +} + +/* allowed just for 8 bytes segments */ +static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 selector, struct desc_struct *desc) +{ + struct desc_ptr dt; + u16 index = selector >> 3; + int ret; + u32 err; + ulong addr; + + get_descriptor_table_ptr(ctxt, ops, selector, &dt); + + if (dt.size < index * 8 + 7) { + emulate_gp(ctxt, selector & 0xfffc); + return X86EMUL_PROPAGATE_FAULT; + } + addr = dt.address + index * 8; + ret = ops->read_std(addr, desc, sizeof *desc, ctxt->vcpu, &err); + if (ret == X86EMUL_PROPAGATE_FAULT) + emulate_pf(ctxt, addr, err); + + return ret; +} + +/* allowed just for 8 bytes segments */ +static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 selector, struct desc_struct *desc) +{ + struct desc_ptr dt; + u16 index = selector >> 3; + u32 err; + ulong addr; + int ret; + + get_descriptor_table_ptr(ctxt, ops, selector, &dt); + + if (dt.size < index * 8 + 7) { + emulate_gp(ctxt, selector & 0xfffc); + return X86EMUL_PROPAGATE_FAULT; + } + + addr = dt.address + index * 8; + ret = ops->write_std(addr, desc, sizeof *desc, ctxt->vcpu, &err); + if (ret == X86EMUL_PROPAGATE_FAULT) + emulate_pf(ctxt, addr, err); + + return ret; +} + +static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 selector, int seg) +{ + struct desc_struct seg_desc; + u8 dpl, rpl, cpl; + unsigned err_vec = GP_VECTOR; + u32 err_code = 0; + bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */ + int ret; + + memset(&seg_desc, 0, sizeof seg_desc); + + if ((seg <= VCPU_SREG_GS && ctxt->mode == X86EMUL_MODE_VM86) + || ctxt->mode == X86EMUL_MODE_REAL) { + /* set real mode segment descriptor */ + set_desc_base(&seg_desc, selector << 4); + set_desc_limit(&seg_desc, 0xffff); + seg_desc.type = 3; + seg_desc.p = 1; + seg_desc.s = 1; + goto load; + } + + /* NULL selector is not valid for TR, CS and SS */ + if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || seg == VCPU_SREG_TR) + && null_selector) + goto exception; + + /* TR should be in GDT only */ + if (seg == VCPU_SREG_TR && (selector & (1 << 2))) + goto exception; + + if (null_selector) /* for NULL selector skip all following checks */ + goto load; + + ret = read_segment_descriptor(ctxt, ops, selector, &seg_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + + err_code = selector & 0xfffc; + err_vec = GP_VECTOR; + + /* can't load system descriptor into segment selecor */ + if (seg <= VCPU_SREG_GS && !seg_desc.s) + goto exception; + + if (!seg_desc.p) { + err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR; + goto exception; + } + + rpl = selector & 3; + dpl = seg_desc.dpl; + cpl = ops->cpl(ctxt->vcpu); + + switch (seg) { + case VCPU_SREG_SS: + /* + * segment is not a writable data segment or segment + * selector's RPL != CPL or segment selector's RPL != CPL + */ + if (rpl != cpl || (seg_desc.type & 0xa) != 0x2 || dpl != cpl) + goto exception; + break; + case VCPU_SREG_CS: + if (!(seg_desc.type & 8)) + goto exception; + + if (seg_desc.type & 4) { + /* conforming */ + if (dpl > cpl) + goto exception; + } else { + /* nonconforming */ + if (rpl > cpl || dpl != cpl) + goto exception; + } + /* CS(RPL) <- CPL */ + selector = (selector & 0xfffc) | cpl; + break; + case VCPU_SREG_TR: + if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9)) + goto exception; + break; + case VCPU_SREG_LDTR: + if (seg_desc.s || seg_desc.type != 2) + goto exception; + break; + default: /* DS, ES, FS, or GS */ + /* + * segment is not a data or readable code segment or + * ((segment is a data or nonconforming code segment) + * and (both RPL and CPL > DPL)) + */ + if ((seg_desc.type & 0xa) == 0x8 || + (((seg_desc.type & 0xc) != 0xc) && + (rpl > dpl && cpl > dpl))) + goto exception; + break; + } + + if (seg_desc.s) { + /* mark segment as accessed */ + seg_desc.type |= 1; + ret = write_segment_descriptor(ctxt, ops, selector, &seg_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + } +load: + ops->set_segment_selector(selector, seg, ctxt->vcpu); + ops->set_cached_descriptor(&seg_desc, seg, ctxt->vcpu); + return X86EMUL_CONTINUE; +exception: + emulate_exception(ctxt, err_vec, err_code, true); + return X86EMUL_PROPAGATE_FAULT; +} + +static inline int writeback(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + int rc; + struct decode_cache *c = &ctxt->decode; + u32 err; + + switch (c->dst.type) { + case OP_REG: + /* The 4-byte case *is* correct: + * in 64-bit mode we zero-extend. + */ + switch (c->dst.bytes) { + case 1: + *(u8 *)c->dst.ptr = (u8)c->dst.val; + break; + case 2: + *(u16 *)c->dst.ptr = (u16)c->dst.val; + break; + case 4: + *c->dst.ptr = (u32)c->dst.val; + break; /* 64b: zero-ext */ + case 8: + *c->dst.ptr = c->dst.val; + break; + } + break; + case OP_MEM: + if (c->lock_prefix) + rc = ops->cmpxchg_emulated( + (unsigned long)c->dst.ptr, + &c->dst.orig_val, + &c->dst.val, + c->dst.bytes, + &err, + ctxt->vcpu); + else + rc = ops->write_emulated( + (unsigned long)c->dst.ptr, + &c->dst.val, + c->dst.bytes, + &err, + ctxt->vcpu); + if (rc == X86EMUL_PROPAGATE_FAULT) + emulate_pf(ctxt, + (unsigned long)c->dst.ptr, err); + if (rc != X86EMUL_CONTINUE) + return rc; + break; + case OP_NONE: + /* no writeback */ + break; + default: + break; + } + return X86EMUL_CONTINUE; +} + +static inline void emulate_push(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; @@ -1223,7 +1640,7 @@ static inline void emulate_push(struct x86_emulate_ctxt *ctxt) c->dst.bytes = c->op_bytes; c->dst.val = c->src.val; register_address_increment(c, &c->regs[VCPU_REGS_RSP], -c->op_bytes); - c->dst.ptr = (void *) register_address(c, ss_base(ctxt), + c->dst.ptr = (void *) register_address(c, ss_base(ctxt, ops), c->regs[VCPU_REGS_RSP]); } @@ -1234,9 +1651,9 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt, struct decode_cache *c = &ctxt->decode; int rc; - rc = ops->read_emulated(register_address(c, ss_base(ctxt), - c->regs[VCPU_REGS_RSP]), - dest, len, ctxt->vcpu); + rc = read_emulated(ctxt, ops, register_address(c, ss_base(ctxt, ops), + c->regs[VCPU_REGS_RSP]), + dest, len); if (rc != X86EMUL_CONTINUE) return rc; @@ -1251,7 +1668,7 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt, int rc; unsigned long val, change_mask; int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; - int cpl = kvm_x86_ops->get_cpl(ctxt->vcpu); + int cpl = ops->cpl(ctxt->vcpu); rc = emulate_pop(ctxt, ops, &val, len); if (rc != X86EMUL_CONTINUE) @@ -1271,7 +1688,7 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt, break; case X86EMUL_MODE_VM86: if (iopl < 3) { - kvm_inject_gp(ctxt->vcpu, 0); + emulate_gp(ctxt, 0); return X86EMUL_PROPAGATE_FAULT; } change_mask |= EFLG_IF; @@ -1287,15 +1704,14 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt, return rc; } -static void emulate_push_sreg(struct x86_emulate_ctxt *ctxt, int seg) +static void emulate_push_sreg(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, int seg) { struct decode_cache *c = &ctxt->decode; - struct kvm_segment segment; - kvm_x86_ops->get_segment(ctxt->vcpu, &segment, seg); + c->src.val = ops->get_segment_selector(seg, ctxt->vcpu); - c->src.val = segment.selector; - emulate_push(ctxt); + emulate_push(ctxt, ops); } static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, @@ -1306,33 +1722,45 @@ static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, int rc; rc = emulate_pop(ctxt, ops, &selector, c->op_bytes); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) return rc; - rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)selector, seg); + rc = load_segment_descriptor(ctxt, ops, (u16)selector, seg); return rc; } -static void emulate_pusha(struct x86_emulate_ctxt *ctxt) +static int emulate_pusha(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; unsigned long old_esp = c->regs[VCPU_REGS_RSP]; + int rc = X86EMUL_CONTINUE; int reg = VCPU_REGS_RAX; while (reg <= VCPU_REGS_RDI) { (reg == VCPU_REGS_RSP) ? (c->src.val = old_esp) : (c->src.val = c->regs[reg]); - emulate_push(ctxt); + emulate_push(ctxt, ops); + + rc = writeback(ctxt, ops); + if (rc != X86EMUL_CONTINUE) + return rc; + ++reg; } + + /* Disable writeback. */ + c->dst.type = OP_NONE; + + return rc; } static int emulate_popa(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc = 0; + int rc = X86EMUL_CONTINUE; int reg = VCPU_REGS_RDI; while (reg >= VCPU_REGS_RAX) { @@ -1343,7 +1771,7 @@ static int emulate_popa(struct x86_emulate_ctxt *ctxt, } rc = emulate_pop(ctxt, ops, &c->regs[reg], c->op_bytes); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) break; --reg; } @@ -1354,12 +1782,8 @@ static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc; - rc = emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes); - if (rc != 0) - return rc; - return 0; + return emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes); } static inline void emulate_grp2(struct x86_emulate_ctxt *ctxt) @@ -1395,7 +1819,6 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc = 0; switch (c->modrm_reg) { case 0 ... 1: /* test */ @@ -1408,11 +1831,9 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt, emulate_1op("neg", c->dst, ctxt->eflags); break; default: - DPRINTF("Cannot emulate %02x\n", c->b); - rc = X86EMUL_UNHANDLEABLE; - break; + return 0; } - return rc; + return 1; } static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt, @@ -1432,30 +1853,24 @@ static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt, old_eip = c->eip; c->eip = c->src.val; c->src.val = old_eip; - emulate_push(ctxt); + emulate_push(ctxt, ops); break; } case 4: /* jmp abs */ c->eip = c->src.val; break; case 6: /* push */ - emulate_push(ctxt); + emulate_push(ctxt, ops); break; } - return 0; + return X86EMUL_CONTINUE; } static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops, - unsigned long memop) + struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - u64 old, new; - int rc; - - rc = ops->read_emulated(memop, &old, 8, ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - return rc; + u64 old = c->dst.orig_val; if (((u32) (old >> 0) != (u32) c->regs[VCPU_REGS_RAX]) || ((u32) (old >> 32) != (u32) c->regs[VCPU_REGS_RDX])) { @@ -1463,17 +1878,13 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt, c->regs[VCPU_REGS_RAX] = (u32) (old >> 0); c->regs[VCPU_REGS_RDX] = (u32) (old >> 32); ctxt->eflags &= ~EFLG_ZF; - } else { - new = ((u64)c->regs[VCPU_REGS_RCX] << 32) | + c->dst.val = ((u64)c->regs[VCPU_REGS_RCX] << 32) | (u32) c->regs[VCPU_REGS_RBX]; - rc = ops->cmpxchg_emulated(memop, &old, &new, 8, ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - return rc; ctxt->eflags |= EFLG_ZF; } - return 0; + return X86EMUL_CONTINUE; } static int emulate_ret_far(struct x86_emulate_ctxt *ctxt, @@ -1484,153 +1895,93 @@ static int emulate_ret_far(struct x86_emulate_ctxt *ctxt, unsigned long cs; rc = emulate_pop(ctxt, ops, &c->eip, c->op_bytes); - if (rc) + if (rc != X86EMUL_CONTINUE) return rc; if (c->op_bytes == 4) c->eip = (u32)c->eip; rc = emulate_pop(ctxt, ops, &cs, c->op_bytes); - if (rc) + if (rc != X86EMUL_CONTINUE) return rc; - rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)cs, VCPU_SREG_CS); + rc = load_segment_descriptor(ctxt, ops, (u16)cs, VCPU_SREG_CS); return rc; } -static inline int writeback(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops) -{ - int rc; - struct decode_cache *c = &ctxt->decode; - - switch (c->dst.type) { - case OP_REG: - /* The 4-byte case *is* correct: - * in 64-bit mode we zero-extend. - */ - switch (c->dst.bytes) { - case 1: - *(u8 *)c->dst.ptr = (u8)c->dst.val; - break; - case 2: - *(u16 *)c->dst.ptr = (u16)c->dst.val; - break; - case 4: - *c->dst.ptr = (u32)c->dst.val; - break; /* 64b: zero-ext */ - case 8: - *c->dst.ptr = c->dst.val; - break; - } - break; - case OP_MEM: - if (c->lock_prefix) - rc = ops->cmpxchg_emulated( - (unsigned long)c->dst.ptr, - &c->dst.orig_val, - &c->dst.val, - c->dst.bytes, - ctxt->vcpu); - else - rc = ops->write_emulated( - (unsigned long)c->dst.ptr, - &c->dst.val, - c->dst.bytes, - ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - return rc; - break; - case OP_NONE: - /* no writeback */ - break; - default: - break; - } - return 0; -} - -static void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask) -{ - u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(ctxt->vcpu, mask); - /* - * an sti; sti; sequence only disable interrupts for the first - * instruction. So, if the last instruction, be it emulated or - * not, left the system with the INT_STI flag enabled, it - * means that the last instruction is an sti. We should not - * leave the flag on in this case. The same goes for mov ss - */ - if (!(int_shadow & mask)) - ctxt->interruptibility = mask; -} - static inline void setup_syscalls_segments(struct x86_emulate_ctxt *ctxt, - struct kvm_segment *cs, struct kvm_segment *ss) + struct x86_emulate_ops *ops, struct desc_struct *cs, + struct desc_struct *ss) { - memset(cs, 0, sizeof(struct kvm_segment)); - kvm_x86_ops->get_segment(ctxt->vcpu, cs, VCPU_SREG_CS); - memset(ss, 0, sizeof(struct kvm_segment)); + memset(cs, 0, sizeof(struct desc_struct)); + ops->get_cached_descriptor(cs, VCPU_SREG_CS, ctxt->vcpu); + memset(ss, 0, sizeof(struct desc_struct)); cs->l = 0; /* will be adjusted later */ - cs->base = 0; /* flat segment */ + set_desc_base(cs, 0); /* flat segment */ cs->g = 1; /* 4kb granularity */ - cs->limit = 0xffffffff; /* 4GB limit */ + set_desc_limit(cs, 0xfffff); /* 4GB limit */ cs->type = 0x0b; /* Read, Execute, Accessed */ cs->s = 1; cs->dpl = 0; /* will be adjusted later */ - cs->present = 1; - cs->db = 1; + cs->p = 1; + cs->d = 1; - ss->unusable = 0; - ss->base = 0; /* flat segment */ - ss->limit = 0xffffffff; /* 4GB limit */ + set_desc_base(ss, 0); /* flat segment */ + set_desc_limit(ss, 0xfffff); /* 4GB limit */ ss->g = 1; /* 4kb granularity */ ss->s = 1; ss->type = 0x03; /* Read/Write, Accessed */ - ss->db = 1; /* 32bit stack segment */ + ss->d = 1; /* 32bit stack segment */ ss->dpl = 0; - ss->present = 1; + ss->p = 1; } static int -emulate_syscall(struct x86_emulate_ctxt *ctxt) +emulate_syscall(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - struct kvm_segment cs, ss; + struct desc_struct cs, ss; u64 msr_data; + u16 cs_sel, ss_sel; /* syscall is not available in real mode */ - if (ctxt->mode == X86EMUL_MODE_REAL || ctxt->mode == X86EMUL_MODE_VM86) - return X86EMUL_UNHANDLEABLE; + if (ctxt->mode == X86EMUL_MODE_REAL || + ctxt->mode == X86EMUL_MODE_VM86) { + emulate_ud(ctxt); + return X86EMUL_PROPAGATE_FAULT; + } - setup_syscalls_segments(ctxt, &cs, &ss); + setup_syscalls_segments(ctxt, ops, &cs, &ss); - kvm_x86_ops->get_msr(ctxt->vcpu, MSR_STAR, &msr_data); + ops->get_msr(ctxt->vcpu, MSR_STAR, &msr_data); msr_data >>= 32; - cs.selector = (u16)(msr_data & 0xfffc); - ss.selector = (u16)(msr_data + 8); + cs_sel = (u16)(msr_data & 0xfffc); + ss_sel = (u16)(msr_data + 8); if (is_long_mode(ctxt->vcpu)) { - cs.db = 0; + cs.d = 0; cs.l = 1; } - kvm_x86_ops->set_segment(ctxt->vcpu, &cs, VCPU_SREG_CS); - kvm_x86_ops->set_segment(ctxt->vcpu, &ss, VCPU_SREG_SS); + ops->set_cached_descriptor(&cs, VCPU_SREG_CS, ctxt->vcpu); + ops->set_segment_selector(cs_sel, VCPU_SREG_CS, ctxt->vcpu); + ops->set_cached_descriptor(&ss, VCPU_SREG_SS, ctxt->vcpu); + ops->set_segment_selector(ss_sel, VCPU_SREG_SS, ctxt->vcpu); c->regs[VCPU_REGS_RCX] = c->eip; if (is_long_mode(ctxt->vcpu)) { #ifdef CONFIG_X86_64 c->regs[VCPU_REGS_R11] = ctxt->eflags & ~EFLG_RF; - kvm_x86_ops->get_msr(ctxt->vcpu, - ctxt->mode == X86EMUL_MODE_PROT64 ? - MSR_LSTAR : MSR_CSTAR, &msr_data); + ops->get_msr(ctxt->vcpu, + ctxt->mode == X86EMUL_MODE_PROT64 ? + MSR_LSTAR : MSR_CSTAR, &msr_data); c->eip = msr_data; - kvm_x86_ops->get_msr(ctxt->vcpu, MSR_SYSCALL_MASK, &msr_data); + ops->get_msr(ctxt->vcpu, MSR_SYSCALL_MASK, &msr_data); ctxt->eflags &= ~(msr_data | EFLG_RF); #endif } else { /* legacy mode */ - kvm_x86_ops->get_msr(ctxt->vcpu, MSR_STAR, &msr_data); + ops->get_msr(ctxt->vcpu, MSR_STAR, &msr_data); c->eip = (u32)msr_data; ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF); @@ -1640,81 +1991,87 @@ emulate_syscall(struct x86_emulate_ctxt *ctxt) } static int -emulate_sysenter(struct x86_emulate_ctxt *ctxt) +emulate_sysenter(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - struct kvm_segment cs, ss; + struct desc_struct cs, ss; u64 msr_data; + u16 cs_sel, ss_sel; /* inject #GP if in real mode */ if (ctxt->mode == X86EMUL_MODE_REAL) { - kvm_inject_gp(ctxt->vcpu, 0); - return X86EMUL_UNHANDLEABLE; + emulate_gp(ctxt, 0); + return X86EMUL_PROPAGATE_FAULT; } /* XXX sysenter/sysexit have not been tested in 64bit mode. * Therefore, we inject an #UD. */ - if (ctxt->mode == X86EMUL_MODE_PROT64) - return X86EMUL_UNHANDLEABLE; + if (ctxt->mode == X86EMUL_MODE_PROT64) { + emulate_ud(ctxt); + return X86EMUL_PROPAGATE_FAULT; + } - setup_syscalls_segments(ctxt, &cs, &ss); + setup_syscalls_segments(ctxt, ops, &cs, &ss); - kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_CS, &msr_data); + ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_CS, &msr_data); switch (ctxt->mode) { case X86EMUL_MODE_PROT32: if ((msr_data & 0xfffc) == 0x0) { - kvm_inject_gp(ctxt->vcpu, 0); + emulate_gp(ctxt, 0); return X86EMUL_PROPAGATE_FAULT; } break; case X86EMUL_MODE_PROT64: if (msr_data == 0x0) { - kvm_inject_gp(ctxt->vcpu, 0); + emulate_gp(ctxt, 0); return X86EMUL_PROPAGATE_FAULT; } break; } ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF); - cs.selector = (u16)msr_data; - cs.selector &= ~SELECTOR_RPL_MASK; - ss.selector = cs.selector + 8; - ss.selector &= ~SELECTOR_RPL_MASK; + cs_sel = (u16)msr_data; + cs_sel &= ~SELECTOR_RPL_MASK; + ss_sel = cs_sel + 8; + ss_sel &= ~SELECTOR_RPL_MASK; if (ctxt->mode == X86EMUL_MODE_PROT64 || is_long_mode(ctxt->vcpu)) { - cs.db = 0; + cs.d = 0; cs.l = 1; } - kvm_x86_ops->set_segment(ctxt->vcpu, &cs, VCPU_SREG_CS); - kvm_x86_ops->set_segment(ctxt->vcpu, &ss, VCPU_SREG_SS); + ops->set_cached_descriptor(&cs, VCPU_SREG_CS, ctxt->vcpu); + ops->set_segment_selector(cs_sel, VCPU_SREG_CS, ctxt->vcpu); + ops->set_cached_descriptor(&ss, VCPU_SREG_SS, ctxt->vcpu); + ops->set_segment_selector(ss_sel, VCPU_SREG_SS, ctxt->vcpu); - kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_EIP, &msr_data); + ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_EIP, &msr_data); c->eip = msr_data; - kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_ESP, &msr_data); + ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_ESP, &msr_data); c->regs[VCPU_REGS_RSP] = msr_data; return X86EMUL_CONTINUE; } static int -emulate_sysexit(struct x86_emulate_ctxt *ctxt) +emulate_sysexit(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - struct kvm_segment cs, ss; + struct desc_struct cs, ss; u64 msr_data; int usermode; + u16 cs_sel, ss_sel; /* inject #GP if in real mode or Virtual 8086 mode */ if (ctxt->mode == X86EMUL_MODE_REAL || ctxt->mode == X86EMUL_MODE_VM86) { - kvm_inject_gp(ctxt->vcpu, 0); - return X86EMUL_UNHANDLEABLE; + emulate_gp(ctxt, 0); + return X86EMUL_PROPAGATE_FAULT; } - setup_syscalls_segments(ctxt, &cs, &ss); + setup_syscalls_segments(ctxt, ops, &cs, &ss); if ((c->rex_prefix & 0x8) != 0x0) usermode = X86EMUL_MODE_PROT64; @@ -1723,40 +2080,43 @@ emulate_sysexit(struct x86_emulate_ctxt *ctxt) cs.dpl = 3; ss.dpl = 3; - kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_CS, &msr_data); + ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_CS, &msr_data); switch (usermode) { case X86EMUL_MODE_PROT32: - cs.selector = (u16)(msr_data + 16); + cs_sel = (u16)(msr_data + 16); if ((msr_data & 0xfffc) == 0x0) { - kvm_inject_gp(ctxt->vcpu, 0); + emulate_gp(ctxt, 0); return X86EMUL_PROPAGATE_FAULT; } - ss.selector = (u16)(msr_data + 24); + ss_sel = (u16)(msr_data + 24); break; case X86EMUL_MODE_PROT64: - cs.selector = (u16)(msr_data + 32); + cs_sel = (u16)(msr_data + 32); if (msr_data == 0x0) { - kvm_inject_gp(ctxt->vcpu, 0); + emulate_gp(ctxt, 0); return X86EMUL_PROPAGATE_FAULT; } - ss.selector = cs.selector + 8; - cs.db = 0; + ss_sel = cs_sel + 8; + cs.d = 0; cs.l = 1; break; } - cs.selector |= SELECTOR_RPL_MASK; - ss.selector |= SELECTOR_RPL_MASK; + cs_sel |= SELECTOR_RPL_MASK; + ss_sel |= SELECTOR_RPL_MASK; - kvm_x86_ops->set_segment(ctxt->vcpu, &cs, VCPU_SREG_CS); - kvm_x86_ops->set_segment(ctxt->vcpu, &ss, VCPU_SREG_SS); + ops->set_cached_descriptor(&cs, VCPU_SREG_CS, ctxt->vcpu); + ops->set_segment_selector(cs_sel, VCPU_SREG_CS, ctxt->vcpu); + ops->set_cached_descriptor(&ss, VCPU_SREG_SS, ctxt->vcpu); + ops->set_segment_selector(ss_sel, VCPU_SREG_SS, ctxt->vcpu); - c->eip = ctxt->vcpu->arch.regs[VCPU_REGS_RDX]; - c->regs[VCPU_REGS_RSP] = ctxt->vcpu->arch.regs[VCPU_REGS_RCX]; + c->eip = c->regs[VCPU_REGS_RDX]; + c->regs[VCPU_REGS_RSP] = c->regs[VCPU_REGS_RCX]; return X86EMUL_CONTINUE; } -static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt) +static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) { int iopl; if (ctxt->mode == X86EMUL_MODE_REAL) @@ -1764,32 +2124,32 @@ static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt) if (ctxt->mode == X86EMUL_MODE_VM86) return true; iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; - return kvm_x86_ops->get_cpl(ctxt->vcpu) > iopl; + return ops->cpl(ctxt->vcpu) > iopl; } static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, u16 port, u16 len) { - struct kvm_segment tr_seg; + struct desc_struct tr_seg; int r; u16 io_bitmap_ptr; u8 perm, bit_idx = port & 0x7; unsigned mask = (1 << len) - 1; - kvm_get_segment(ctxt->vcpu, &tr_seg, VCPU_SREG_TR); - if (tr_seg.unusable) + ops->get_cached_descriptor(&tr_seg, VCPU_SREG_TR, ctxt->vcpu); + if (!tr_seg.p) return false; - if (tr_seg.limit < 103) + if (desc_limit_scaled(&tr_seg) < 103) return false; - r = ops->read_std(tr_seg.base + 102, &io_bitmap_ptr, 2, ctxt->vcpu, - NULL); + r = ops->read_std(get_desc_base(&tr_seg) + 102, &io_bitmap_ptr, 2, + ctxt->vcpu, NULL); if (r != X86EMUL_CONTINUE) return false; - if (io_bitmap_ptr + port/8 > tr_seg.limit) + if (io_bitmap_ptr + port/8 > desc_limit_scaled(&tr_seg)) return false; - r = ops->read_std(tr_seg.base + io_bitmap_ptr + port/8, &perm, 1, - ctxt->vcpu, NULL); + r = ops->read_std(get_desc_base(&tr_seg) + io_bitmap_ptr + port/8, + &perm, 1, ctxt->vcpu, NULL); if (r != X86EMUL_CONTINUE) return false; if ((perm >> bit_idx) & mask) @@ -1801,52 +2161,435 @@ static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, u16 port, u16 len) { - if (emulator_bad_iopl(ctxt)) + if (emulator_bad_iopl(ctxt, ops)) if (!emulator_io_port_access_allowed(ctxt, ops, port, len)) return false; return true; } +static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + struct tss_segment_16 *tss) +{ + struct decode_cache *c = &ctxt->decode; + + tss->ip = c->eip; + tss->flag = ctxt->eflags; + tss->ax = c->regs[VCPU_REGS_RAX]; + tss->cx = c->regs[VCPU_REGS_RCX]; + tss->dx = c->regs[VCPU_REGS_RDX]; + tss->bx = c->regs[VCPU_REGS_RBX]; + tss->sp = c->regs[VCPU_REGS_RSP]; + tss->bp = c->regs[VCPU_REGS_RBP]; + tss->si = c->regs[VCPU_REGS_RSI]; + tss->di = c->regs[VCPU_REGS_RDI]; + + tss->es = ops->get_segment_selector(VCPU_SREG_ES, ctxt->vcpu); + tss->cs = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu); + tss->ss = ops->get_segment_selector(VCPU_SREG_SS, ctxt->vcpu); + tss->ds = ops->get_segment_selector(VCPU_SREG_DS, ctxt->vcpu); + tss->ldt = ops->get_segment_selector(VCPU_SREG_LDTR, ctxt->vcpu); +} + +static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + struct tss_segment_16 *tss) +{ + struct decode_cache *c = &ctxt->decode; + int ret; + + c->eip = tss->ip; + ctxt->eflags = tss->flag | 2; + c->regs[VCPU_REGS_RAX] = tss->ax; + c->regs[VCPU_REGS_RCX] = tss->cx; + c->regs[VCPU_REGS_RDX] = tss->dx; + c->regs[VCPU_REGS_RBX] = tss->bx; + c->regs[VCPU_REGS_RSP] = tss->sp; + c->regs[VCPU_REGS_RBP] = tss->bp; + c->regs[VCPU_REGS_RSI] = tss->si; + c->regs[VCPU_REGS_RDI] = tss->di; + + /* + * SDM says that segment selectors are loaded before segment + * descriptors + */ + ops->set_segment_selector(tss->ldt, VCPU_SREG_LDTR, ctxt->vcpu); + ops->set_segment_selector(tss->es, VCPU_SREG_ES, ctxt->vcpu); + ops->set_segment_selector(tss->cs, VCPU_SREG_CS, ctxt->vcpu); + ops->set_segment_selector(tss->ss, VCPU_SREG_SS, ctxt->vcpu); + ops->set_segment_selector(tss->ds, VCPU_SREG_DS, ctxt->vcpu); + + /* + * Now load segment descriptors. If fault happenes at this stage + * it is handled in a context of new task + */ + ret = load_segment_descriptor(ctxt, ops, tss->ldt, VCPU_SREG_LDTR); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->es, VCPU_SREG_ES); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->cs, VCPU_SREG_CS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->ss, VCPU_SREG_SS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->ds, VCPU_SREG_DS); + if (ret != X86EMUL_CONTINUE) + return ret; + + return X86EMUL_CONTINUE; +} + +static int task_switch_16(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 tss_selector, u16 old_tss_sel, + ulong old_tss_base, struct desc_struct *new_desc) +{ + struct tss_segment_16 tss_seg; + int ret; + u32 err, new_tss_base = get_desc_base(new_desc); + + ret = ops->read_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + emulate_pf(ctxt, old_tss_base, err); + return ret; + } + + save_state_to_tss16(ctxt, ops, &tss_seg); + + ret = ops->write_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + emulate_pf(ctxt, old_tss_base, err); + return ret; + } + + ret = ops->read_std(new_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + emulate_pf(ctxt, new_tss_base, err); + return ret; + } + + if (old_tss_sel != 0xffff) { + tss_seg.prev_task_link = old_tss_sel; + + ret = ops->write_std(new_tss_base, + &tss_seg.prev_task_link, + sizeof tss_seg.prev_task_link, + ctxt->vcpu, &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + emulate_pf(ctxt, new_tss_base, err); + return ret; + } + } + + return load_state_from_tss16(ctxt, ops, &tss_seg); +} + +static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + struct tss_segment_32 *tss) +{ + struct decode_cache *c = &ctxt->decode; + + tss->cr3 = ops->get_cr(3, ctxt->vcpu); + tss->eip = c->eip; + tss->eflags = ctxt->eflags; + tss->eax = c->regs[VCPU_REGS_RAX]; + tss->ecx = c->regs[VCPU_REGS_RCX]; + tss->edx = c->regs[VCPU_REGS_RDX]; + tss->ebx = c->regs[VCPU_REGS_RBX]; + tss->esp = c->regs[VCPU_REGS_RSP]; + tss->ebp = c->regs[VCPU_REGS_RBP]; + tss->esi = c->regs[VCPU_REGS_RSI]; + tss->edi = c->regs[VCPU_REGS_RDI]; + + tss->es = ops->get_segment_selector(VCPU_SREG_ES, ctxt->vcpu); + tss->cs = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu); + tss->ss = ops->get_segment_selector(VCPU_SREG_SS, ctxt->vcpu); + tss->ds = ops->get_segment_selector(VCPU_SREG_DS, ctxt->vcpu); + tss->fs = ops->get_segment_selector(VCPU_SREG_FS, ctxt->vcpu); + tss->gs = ops->get_segment_selector(VCPU_SREG_GS, ctxt->vcpu); + tss->ldt_selector = ops->get_segment_selector(VCPU_SREG_LDTR, ctxt->vcpu); +} + +static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + struct tss_segment_32 *tss) +{ + struct decode_cache *c = &ctxt->decode; + int ret; + + if (ops->set_cr(3, tss->cr3, ctxt->vcpu)) { + emulate_gp(ctxt, 0); + return X86EMUL_PROPAGATE_FAULT; + } + c->eip = tss->eip; + ctxt->eflags = tss->eflags | 2; + c->regs[VCPU_REGS_RAX] = tss->eax; + c->regs[VCPU_REGS_RCX] = tss->ecx; + c->regs[VCPU_REGS_RDX] = tss->edx; + c->regs[VCPU_REGS_RBX] = tss->ebx; + c->regs[VCPU_REGS_RSP] = tss->esp; + c->regs[VCPU_REGS_RBP] = tss->ebp; + c->regs[VCPU_REGS_RSI] = tss->esi; + c->regs[VCPU_REGS_RDI] = tss->edi; + + /* + * SDM says that segment selectors are loaded before segment + * descriptors + */ + ops->set_segment_selector(tss->ldt_selector, VCPU_SREG_LDTR, ctxt->vcpu); + ops->set_segment_selector(tss->es, VCPU_SREG_ES, ctxt->vcpu); + ops->set_segment_selector(tss->cs, VCPU_SREG_CS, ctxt->vcpu); + ops->set_segment_selector(tss->ss, VCPU_SREG_SS, ctxt->vcpu); + ops->set_segment_selector(tss->ds, VCPU_SREG_DS, ctxt->vcpu); + ops->set_segment_selector(tss->fs, VCPU_SREG_FS, ctxt->vcpu); + ops->set_segment_selector(tss->gs, VCPU_SREG_GS, ctxt->vcpu); + + /* + * Now load segment descriptors. If fault happenes at this stage + * it is handled in a context of new task + */ + ret = load_segment_descriptor(ctxt, ops, tss->ldt_selector, VCPU_SREG_LDTR); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->es, VCPU_SREG_ES); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->cs, VCPU_SREG_CS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->ss, VCPU_SREG_SS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->ds, VCPU_SREG_DS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->fs, VCPU_SREG_FS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->gs, VCPU_SREG_GS); + if (ret != X86EMUL_CONTINUE) + return ret; + + return X86EMUL_CONTINUE; +} + +static int task_switch_32(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 tss_selector, u16 old_tss_sel, + ulong old_tss_base, struct desc_struct *new_desc) +{ + struct tss_segment_32 tss_seg; + int ret; + u32 err, new_tss_base = get_desc_base(new_desc); + + ret = ops->read_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + emulate_pf(ctxt, old_tss_base, err); + return ret; + } + + save_state_to_tss32(ctxt, ops, &tss_seg); + + ret = ops->write_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + emulate_pf(ctxt, old_tss_base, err); + return ret; + } + + ret = ops->read_std(new_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + emulate_pf(ctxt, new_tss_base, err); + return ret; + } + + if (old_tss_sel != 0xffff) { + tss_seg.prev_task_link = old_tss_sel; + + ret = ops->write_std(new_tss_base, + &tss_seg.prev_task_link, + sizeof tss_seg.prev_task_link, + ctxt->vcpu, &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + emulate_pf(ctxt, new_tss_base, err); + return ret; + } + } + + return load_state_from_tss32(ctxt, ops, &tss_seg); +} + +static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 tss_selector, int reason, + bool has_error_code, u32 error_code) +{ + struct desc_struct curr_tss_desc, next_tss_desc; + int ret; + u16 old_tss_sel = ops->get_segment_selector(VCPU_SREG_TR, ctxt->vcpu); + ulong old_tss_base = + ops->get_cached_segment_base(VCPU_SREG_TR, ctxt->vcpu); + u32 desc_limit; + + /* FIXME: old_tss_base == ~0 ? */ + + ret = read_segment_descriptor(ctxt, ops, tss_selector, &next_tss_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = read_segment_descriptor(ctxt, ops, old_tss_sel, &curr_tss_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + + /* FIXME: check that next_tss_desc is tss */ + + if (reason != TASK_SWITCH_IRET) { + if ((tss_selector & 3) > next_tss_desc.dpl || + ops->cpl(ctxt->vcpu) > next_tss_desc.dpl) { + emulate_gp(ctxt, 0); + return X86EMUL_PROPAGATE_FAULT; + } + } + + desc_limit = desc_limit_scaled(&next_tss_desc); + if (!next_tss_desc.p || + ((desc_limit < 0x67 && (next_tss_desc.type & 8)) || + desc_limit < 0x2b)) { + emulate_ts(ctxt, tss_selector & 0xfffc); + return X86EMUL_PROPAGATE_FAULT; + } + + if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) { + curr_tss_desc.type &= ~(1 << 1); /* clear busy flag */ + write_segment_descriptor(ctxt, ops, old_tss_sel, + &curr_tss_desc); + } + + if (reason == TASK_SWITCH_IRET) + ctxt->eflags = ctxt->eflags & ~X86_EFLAGS_NT; + + /* set back link to prev task only if NT bit is set in eflags + note that old_tss_sel is not used afetr this point */ + if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE) + old_tss_sel = 0xffff; + + if (next_tss_desc.type & 8) + ret = task_switch_32(ctxt, ops, tss_selector, old_tss_sel, + old_tss_base, &next_tss_desc); + else + ret = task_switch_16(ctxt, ops, tss_selector, old_tss_sel, + old_tss_base, &next_tss_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + + if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) + ctxt->eflags = ctxt->eflags | X86_EFLAGS_NT; + + if (reason != TASK_SWITCH_IRET) { + next_tss_desc.type |= (1 << 1); /* set busy flag */ + write_segment_descriptor(ctxt, ops, tss_selector, + &next_tss_desc); + } + + ops->set_cr(0, ops->get_cr(0, ctxt->vcpu) | X86_CR0_TS, ctxt->vcpu); + ops->set_cached_descriptor(&next_tss_desc, VCPU_SREG_TR, ctxt->vcpu); + ops->set_segment_selector(tss_selector, VCPU_SREG_TR, ctxt->vcpu); + + if (has_error_code) { + struct decode_cache *c = &ctxt->decode; + + c->op_bytes = c->ad_bytes = (next_tss_desc.type & 8) ? 4 : 2; + c->lock_prefix = 0; + c->src.val = (unsigned long) error_code; + emulate_push(ctxt, ops); + } + + return ret; +} + +int emulator_task_switch(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 tss_selector, int reason, + bool has_error_code, u32 error_code) +{ + struct decode_cache *c = &ctxt->decode; + int rc; + + c->eip = ctxt->eip; + c->dst.type = OP_NONE; + + rc = emulator_do_task_switch(ctxt, ops, tss_selector, reason, + has_error_code, error_code); + + if (rc == X86EMUL_CONTINUE) { + rc = writeback(ctxt, ops); + if (rc == X86EMUL_CONTINUE) + ctxt->eip = c->eip; + } + + return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0; +} + +static void string_addr_inc(struct x86_emulate_ctxt *ctxt, unsigned long base, + int reg, struct operand *op) +{ + struct decode_cache *c = &ctxt->decode; + int df = (ctxt->eflags & EFLG_DF) ? -1 : 1; + + register_address_increment(c, &c->regs[reg], df * op->bytes); + op->ptr = (unsigned long *)register_address(c, base, c->regs[reg]); +} + int x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { - unsigned long memop = 0; u64 msr_data; - unsigned long saved_eip = 0; struct decode_cache *c = &ctxt->decode; - unsigned int port; - int io_dir_in; - int rc = 0; + int rc = X86EMUL_CONTINUE; + int saved_dst_type = c->dst.type; - ctxt->interruptibility = 0; + ctxt->decode.mem_read.pos = 0; - /* Shadow copy of register state. Committed on successful emulation. - * NOTE: we can copy them from vcpu as x86_decode_insn() doesn't - * modify them. - */ - - memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); - saved_eip = c->eip; + if (ctxt->mode == X86EMUL_MODE_PROT64 && (c->d & No64)) { + emulate_ud(ctxt); + goto done; + } /* LOCK prefix is allowed only with some instructions */ - if (c->lock_prefix && !(c->d & Lock)) { - kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + if (c->lock_prefix && (!(c->d & Lock) || c->dst.type != OP_MEM)) { + emulate_ud(ctxt); goto done; } /* Privileged instruction can be executed only in CPL=0 */ - if ((c->d & Priv) && kvm_x86_ops->get_cpl(ctxt->vcpu)) { - kvm_inject_gp(ctxt->vcpu, 0); + if ((c->d & Priv) && ops->cpl(ctxt->vcpu)) { + emulate_gp(ctxt, 0); goto done; } - if (((c->d & ModRM) && (c->modrm_mod != 3)) || (c->d & MemAbs)) - memop = c->modrm_ea; - if (c->rep_prefix && (c->d & String)) { + ctxt->restart = true; /* All REP prefixes have the same first termination condition */ - if (c->regs[VCPU_REGS_RCX] == 0) { - kvm_rip_write(ctxt->vcpu, c->eip); + if (address_mask(c, c->regs[VCPU_REGS_RCX]) == 0) { + string_done: + ctxt->restart = false; + ctxt->eip = c->eip; goto done; } /* The second termination condition only applies for REPE @@ -1857,57 +2600,42 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) * - if REPNE/REPNZ and ZF = 1 then done */ if ((c->b == 0xa6) || (c->b == 0xa7) || - (c->b == 0xae) || (c->b == 0xaf)) { + (c->b == 0xae) || (c->b == 0xaf)) { if ((c->rep_prefix == REPE_PREFIX) && - ((ctxt->eflags & EFLG_ZF) == 0)) { - kvm_rip_write(ctxt->vcpu, c->eip); - goto done; - } + ((ctxt->eflags & EFLG_ZF) == 0)) + goto string_done; if ((c->rep_prefix == REPNE_PREFIX) && - ((ctxt->eflags & EFLG_ZF) == EFLG_ZF)) { - kvm_rip_write(ctxt->vcpu, c->eip); - goto done; - } + ((ctxt->eflags & EFLG_ZF) == EFLG_ZF)) + goto string_done; } - c->regs[VCPU_REGS_RCX]--; - c->eip = kvm_rip_read(ctxt->vcpu); + c->eip = ctxt->eip; } if (c->src.type == OP_MEM) { - c->src.ptr = (unsigned long *)memop; - c->src.val = 0; - rc = ops->read_emulated((unsigned long)c->src.ptr, - &c->src.val, - c->src.bytes, - ctxt->vcpu); + rc = read_emulated(ctxt, ops, (unsigned long)c->src.ptr, + c->src.valptr, c->src.bytes); if (rc != X86EMUL_CONTINUE) goto done; c->src.orig_val = c->src.val; } + if (c->src2.type == OP_MEM) { + rc = read_emulated(ctxt, ops, (unsigned long)c->src2.ptr, + &c->src2.val, c->src2.bytes); + if (rc != X86EMUL_CONTINUE) + goto done; + } + if ((c->d & DstMask) == ImplicitOps) goto special_insn; - if (c->dst.type == OP_MEM) { - c->dst.ptr = (unsigned long *)memop; - c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->dst.val = 0; - if (c->d & BitOp) { - unsigned long mask = ~(c->dst.bytes * 8 - 1); - - c->dst.ptr = (void *)c->dst.ptr + - (c->src.val & mask) / 8; - } - if (!(c->d & Mov)) { - /* optimisation - avoid slow emulated read */ - rc = ops->read_emulated((unsigned long)c->dst.ptr, - &c->dst.val, - c->dst.bytes, - ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - goto done; - } + if ((c->dst.type == OP_MEM) && !(c->d & Mov)) { + /* optimisation - avoid slow emulated read if Mov */ + rc = read_emulated(ctxt, ops, (unsigned long)c->dst.ptr, + &c->dst.val, c->dst.bytes); + if (rc != X86EMUL_CONTINUE) + goto done; } c->dst.orig_val = c->dst.val; @@ -1922,11 +2650,11 @@ special_insn: emulate_2op_SrcV("add", c->src, c->dst, ctxt->eflags); break; case 0x06: /* push es */ - emulate_push_sreg(ctxt, VCPU_SREG_ES); + emulate_push_sreg(ctxt, ops, VCPU_SREG_ES); break; case 0x07: /* pop es */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_ES); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0x08 ... 0x0d: @@ -1934,18 +2662,18 @@ special_insn: emulate_2op_SrcV("or", c->src, c->dst, ctxt->eflags); break; case 0x0e: /* push cs */ - emulate_push_sreg(ctxt, VCPU_SREG_CS); + emulate_push_sreg(ctxt, ops, VCPU_SREG_CS); break; case 0x10 ... 0x15: adc: /* adc */ emulate_2op_SrcV("adc", c->src, c->dst, ctxt->eflags); break; case 0x16: /* push ss */ - emulate_push_sreg(ctxt, VCPU_SREG_SS); + emulate_push_sreg(ctxt, ops, VCPU_SREG_SS); break; case 0x17: /* pop ss */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_SS); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0x18 ... 0x1d: @@ -1953,11 +2681,11 @@ special_insn: emulate_2op_SrcV("sbb", c->src, c->dst, ctxt->eflags); break; case 0x1e: /* push ds */ - emulate_push_sreg(ctxt, VCPU_SREG_DS); + emulate_push_sreg(ctxt, ops, VCPU_SREG_DS); break; case 0x1f: /* pop ds */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_DS); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0x20 ... 0x25: @@ -1983,20 +2711,22 @@ special_insn: emulate_1op("dec", c->dst, ctxt->eflags); break; case 0x50 ... 0x57: /* push reg */ - emulate_push(ctxt); + emulate_push(ctxt, ops); break; case 0x58 ... 0x5f: /* pop reg */ pop_instruction: rc = emulate_pop(ctxt, ops, &c->dst.val, c->op_bytes); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0x60: /* pusha */ - emulate_pusha(ctxt); + rc = emulate_pusha(ctxt, ops); + if (rc != X86EMUL_CONTINUE) + goto done; break; case 0x61: /* popa */ rc = emulate_popa(ctxt, ops); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0x63: /* movsxd */ @@ -2006,51 +2736,33 @@ special_insn: break; case 0x68: /* push imm */ case 0x6a: /* push imm8 */ - emulate_push(ctxt); + emulate_push(ctxt, ops); break; case 0x6c: /* insb */ case 0x6d: /* insw/insd */ + c->dst.bytes = min(c->dst.bytes, 4u); if (!emulator_io_permited(ctxt, ops, c->regs[VCPU_REGS_RDX], - (c->d & ByteOp) ? 1 : c->op_bytes)) { - kvm_inject_gp(ctxt->vcpu, 0); + c->dst.bytes)) { + emulate_gp(ctxt, 0); goto done; } - if (kvm_emulate_pio_string(ctxt->vcpu, - 1, - (c->d & ByteOp) ? 1 : c->op_bytes, - c->rep_prefix ? - address_mask(c, c->regs[VCPU_REGS_RCX]) : 1, - (ctxt->eflags & EFLG_DF), - register_address(c, es_base(ctxt), - c->regs[VCPU_REGS_RDI]), - c->rep_prefix, - c->regs[VCPU_REGS_RDX]) == 0) { - c->eip = saved_eip; - return -1; - } - return 0; + if (!pio_in_emulated(ctxt, ops, c->dst.bytes, + c->regs[VCPU_REGS_RDX], &c->dst.val)) + goto done; /* IO is needed, skip writeback */ + break; case 0x6e: /* outsb */ case 0x6f: /* outsw/outsd */ + c->src.bytes = min(c->src.bytes, 4u); if (!emulator_io_permited(ctxt, ops, c->regs[VCPU_REGS_RDX], - (c->d & ByteOp) ? 1 : c->op_bytes)) { - kvm_inject_gp(ctxt->vcpu, 0); + c->src.bytes)) { + emulate_gp(ctxt, 0); goto done; } - if (kvm_emulate_pio_string(ctxt->vcpu, - 0, - (c->d & ByteOp) ? 1 : c->op_bytes, - c->rep_prefix ? - address_mask(c, c->regs[VCPU_REGS_RCX]) : 1, - (ctxt->eflags & EFLG_DF), - register_address(c, - seg_override_base(ctxt, c), - c->regs[VCPU_REGS_RSI]), - c->rep_prefix, - c->regs[VCPU_REGS_RDX]) == 0) { - c->eip = saved_eip; - return -1; - } - return 0; + ops->pio_out_emulated(c->src.bytes, c->regs[VCPU_REGS_RDX], + &c->src.val, 1, ctxt->vcpu); + + c->dst.type = OP_NONE; /* nothing to writeback */ + break; case 0x70 ... 0x7f: /* jcc (short) */ if (test_cc(c->b, ctxt->eflags)) jmp_rel(c, c->src.val); @@ -2076,6 +2788,7 @@ special_insn: } break; case 0x84 ... 0x85: + test: emulate_2op_SrcV("test", c->src, c->dst, ctxt->eflags); break; case 0x86 ... 0x87: /* xchg */ @@ -2104,19 +2817,13 @@ special_insn: break; case 0x88 ... 0x8b: /* mov */ goto mov; - case 0x8c: { /* mov r/m, sreg */ - struct kvm_segment segreg; - - if (c->modrm_reg <= 5) - kvm_get_segment(ctxt->vcpu, &segreg, c->modrm_reg); - else { - printk(KERN_INFO "0x8c: Invalid segreg in modrm byte 0x%02x\n", - c->modrm); - goto cannot_emulate; + case 0x8c: /* mov r/m, sreg */ + if (c->modrm_reg > VCPU_SREG_GS) { + emulate_ud(ctxt); + goto done; } - c->dst.val = segreg.selector; + c->dst.val = ops->get_segment_selector(c->modrm_reg, ctxt->vcpu); break; - } case 0x8d: /* lea r16/r32, m */ c->dst.val = c->modrm_ea; break; @@ -2127,37 +2834,37 @@ special_insn: if (c->modrm_reg == VCPU_SREG_CS || c->modrm_reg > VCPU_SREG_GS) { - kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + emulate_ud(ctxt); goto done; } if (c->modrm_reg == VCPU_SREG_SS) - toggle_interruptibility(ctxt, X86_SHADOW_INT_MOV_SS); + ctxt->interruptibility = KVM_X86_SHADOW_INT_MOV_SS; - rc = kvm_load_segment_descriptor(ctxt->vcpu, sel, c->modrm_reg); + rc = load_segment_descriptor(ctxt, ops, sel, c->modrm_reg); c->dst.type = OP_NONE; /* Disable writeback. */ break; } case 0x8f: /* pop (sole member of Grp1a) */ rc = emulate_grp1a(ctxt, ops); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0x90: /* nop / xchg r8,rax */ - if (!(c->rex_prefix & 1)) { /* nop */ - c->dst.type = OP_NONE; + if (c->dst.ptr == (unsigned long *)&c->regs[VCPU_REGS_RAX]) { + c->dst.type = OP_NONE; /* nop */ break; } case 0x91 ... 0x97: /* xchg reg,rax */ - c->src.type = c->dst.type = OP_REG; - c->src.bytes = c->dst.bytes = c->op_bytes; + c->src.type = OP_REG; + c->src.bytes = c->op_bytes; c->src.ptr = (unsigned long *) &c->regs[VCPU_REGS_RAX]; c->src.val = *(c->src.ptr); goto xchg; case 0x9c: /* pushf */ c->src.val = (unsigned long) ctxt->eflags; - emulate_push(ctxt); + emulate_push(ctxt, ops); break; case 0x9d: /* popf */ c->dst.type = OP_REG; @@ -2167,97 +2874,20 @@ special_insn: if (rc != X86EMUL_CONTINUE) goto done; break; - case 0xa0 ... 0xa1: /* mov */ - c->dst.ptr = (unsigned long *)&c->regs[VCPU_REGS_RAX]; - c->dst.val = c->src.val; - break; - case 0xa2 ... 0xa3: /* mov */ - c->dst.val = (unsigned long)c->regs[VCPU_REGS_RAX]; - break; + case 0xa0 ... 0xa3: /* mov */ case 0xa4 ... 0xa5: /* movs */ - c->dst.type = OP_MEM; - c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->dst.ptr = (unsigned long *)register_address(c, - es_base(ctxt), - c->regs[VCPU_REGS_RDI]); - rc = ops->read_emulated(register_address(c, - seg_override_base(ctxt, c), - c->regs[VCPU_REGS_RSI]), - &c->dst.val, - c->dst.bytes, ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - goto done; - register_address_increment(c, &c->regs[VCPU_REGS_RSI], - (ctxt->eflags & EFLG_DF) ? -c->dst.bytes - : c->dst.bytes); - register_address_increment(c, &c->regs[VCPU_REGS_RDI], - (ctxt->eflags & EFLG_DF) ? -c->dst.bytes - : c->dst.bytes); - break; + goto mov; case 0xa6 ... 0xa7: /* cmps */ - c->src.type = OP_NONE; /* Disable writeback. */ - c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->src.ptr = (unsigned long *)register_address(c, - seg_override_base(ctxt, c), - c->regs[VCPU_REGS_RSI]); - rc = ops->read_emulated((unsigned long)c->src.ptr, - &c->src.val, - c->src.bytes, - ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - goto done; - c->dst.type = OP_NONE; /* Disable writeback. */ - c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->dst.ptr = (unsigned long *)register_address(c, - es_base(ctxt), - c->regs[VCPU_REGS_RDI]); - rc = ops->read_emulated((unsigned long)c->dst.ptr, - &c->dst.val, - c->dst.bytes, - ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - goto done; - DPRINTF("cmps: mem1=0x%p mem2=0x%p\n", c->src.ptr, c->dst.ptr); - - emulate_2op_SrcV("cmp", c->src, c->dst, ctxt->eflags); - - register_address_increment(c, &c->regs[VCPU_REGS_RSI], - (ctxt->eflags & EFLG_DF) ? -c->src.bytes - : c->src.bytes); - register_address_increment(c, &c->regs[VCPU_REGS_RDI], - (ctxt->eflags & EFLG_DF) ? -c->dst.bytes - : c->dst.bytes); - - break; + goto cmp; + case 0xa8 ... 0xa9: /* test ax, imm */ + goto test; case 0xaa ... 0xab: /* stos */ - c->dst.type = OP_MEM; - c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->dst.ptr = (unsigned long *)register_address(c, - es_base(ctxt), - c->regs[VCPU_REGS_RDI]); c->dst.val = c->regs[VCPU_REGS_RAX]; - register_address_increment(c, &c->regs[VCPU_REGS_RDI], - (ctxt->eflags & EFLG_DF) ? -c->dst.bytes - : c->dst.bytes); break; case 0xac ... 0xad: /* lods */ - c->dst.type = OP_REG; - c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->dst.ptr = (unsigned long *)&c->regs[VCPU_REGS_RAX]; - rc = ops->read_emulated(register_address(c, - seg_override_base(ctxt, c), - c->regs[VCPU_REGS_RSI]), - &c->dst.val, - c->dst.bytes, - ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - goto done; - register_address_increment(c, &c->regs[VCPU_REGS_RSI], - (ctxt->eflags & EFLG_DF) ? -c->dst.bytes - : c->dst.bytes); - break; + goto mov; case 0xae ... 0xaf: /* scas */ DPRINTF("Urk! I don't handle SCAS.\n"); goto cannot_emulate; @@ -2277,7 +2907,7 @@ special_insn: break; case 0xcb: /* ret far */ rc = emulate_ret_far(ctxt, ops); - if (rc) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0xd0 ... 0xd1: /* Grp2 */ @@ -2290,30 +2920,31 @@ special_insn: break; case 0xe4: /* inb */ case 0xe5: /* in */ - port = c->src.val; - io_dir_in = 1; - goto do_io; + goto do_io_in; case 0xe6: /* outb */ case 0xe7: /* out */ - port = c->src.val; - io_dir_in = 0; - goto do_io; + goto do_io_out; case 0xe8: /* call (near) */ { long int rel = c->src.val; c->src.val = (unsigned long) c->eip; jmp_rel(c, rel); - emulate_push(ctxt); + emulate_push(ctxt, ops); break; } case 0xe9: /* jmp rel */ goto jmp; - case 0xea: /* jmp far */ - if (kvm_load_segment_descriptor(ctxt->vcpu, c->src2.val, - VCPU_SREG_CS)) + case 0xea: { /* jmp far */ + unsigned short sel; + jump_far: + memcpy(&sel, c->src.valptr + c->op_bytes, 2); + + if (load_segment_descriptor(ctxt, ops, sel, VCPU_SREG_CS)) goto done; - c->eip = c->src.val; + c->eip = 0; + memcpy(&c->eip, c->src.valptr, c->op_bytes); break; + } case 0xeb: jmp: /* jmp rel short */ jmp_rel(c, c->src.val); @@ -2321,25 +2952,29 @@ special_insn: break; case 0xec: /* in al,dx */ case 0xed: /* in (e/r)ax,dx */ - port = c->regs[VCPU_REGS_RDX]; - io_dir_in = 1; - goto do_io; - case 0xee: /* out al,dx */ - case 0xef: /* out (e/r)ax,dx */ - port = c->regs[VCPU_REGS_RDX]; - io_dir_in = 0; - do_io: - if (!emulator_io_permited(ctxt, ops, port, - (c->d & ByteOp) ? 1 : c->op_bytes)) { - kvm_inject_gp(ctxt->vcpu, 0); + c->src.val = c->regs[VCPU_REGS_RDX]; + do_io_in: + c->dst.bytes = min(c->dst.bytes, 4u); + if (!emulator_io_permited(ctxt, ops, c->src.val, c->dst.bytes)) { + emulate_gp(ctxt, 0); goto done; } - if (kvm_emulate_pio(ctxt->vcpu, io_dir_in, - (c->d & ByteOp) ? 1 : c->op_bytes, - port) != 0) { - c->eip = saved_eip; - goto cannot_emulate; + if (!pio_in_emulated(ctxt, ops, c->dst.bytes, c->src.val, + &c->dst.val)) + goto done; /* IO is needed */ + break; + case 0xee: /* out dx,al */ + case 0xef: /* out dx,(e/r)ax */ + c->src.val = c->regs[VCPU_REGS_RDX]; + do_io_out: + c->dst.bytes = min(c->dst.bytes, 4u); + if (!emulator_io_permited(ctxt, ops, c->src.val, c->dst.bytes)) { + emulate_gp(ctxt, 0); + goto done; } + ops->pio_out_emulated(c->dst.bytes, c->src.val, &c->dst.val, 1, + ctxt->vcpu); + c->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xf4: /* hlt */ ctxt->vcpu->arch.halt_request = 1; @@ -2350,27 +2985,28 @@ special_insn: c->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xf6 ... 0xf7: /* Grp3 */ - rc = emulate_grp3(ctxt, ops); - if (rc != 0) - goto done; + if (!emulate_grp3(ctxt, ops)) + goto cannot_emulate; break; case 0xf8: /* clc */ ctxt->eflags &= ~EFLG_CF; c->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xfa: /* cli */ - if (emulator_bad_iopl(ctxt)) - kvm_inject_gp(ctxt->vcpu, 0); - else { + if (emulator_bad_iopl(ctxt, ops)) { + emulate_gp(ctxt, 0); + goto done; + } else { ctxt->eflags &= ~X86_EFLAGS_IF; c->dst.type = OP_NONE; /* Disable writeback. */ } break; case 0xfb: /* sti */ - if (emulator_bad_iopl(ctxt)) - kvm_inject_gp(ctxt->vcpu, 0); - else { - toggle_interruptibility(ctxt, X86_SHADOW_INT_STI); + if (emulator_bad_iopl(ctxt, ops)) { + emulate_gp(ctxt, 0); + goto done; + } else { + ctxt->interruptibility = KVM_X86_SHADOW_INT_STI; ctxt->eflags |= X86_EFLAGS_IF; c->dst.type = OP_NONE; /* Disable writeback. */ } @@ -2383,28 +3019,57 @@ special_insn: ctxt->eflags |= EFLG_DF; c->dst.type = OP_NONE; /* Disable writeback. */ break; - case 0xfe ... 0xff: /* Grp4/Grp5 */ + case 0xfe: /* Grp4 */ + grp45: rc = emulate_grp45(ctxt, ops); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; + case 0xff: /* Grp5 */ + if (c->modrm_reg == 5) + goto jump_far; + goto grp45; } writeback: rc = writeback(ctxt, ops); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; - /* Commit shadow register state. */ - memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs); - kvm_rip_write(ctxt->vcpu, c->eip); + /* + * restore dst type in case the decoding will be reused + * (happens for string instruction ) + */ + c->dst.type = saved_dst_type; -done: - if (rc == X86EMUL_UNHANDLEABLE) { - c->eip = saved_eip; - return -1; + if ((c->d & SrcMask) == SrcSI) + string_addr_inc(ctxt, seg_override_base(ctxt, ops, c), + VCPU_REGS_RSI, &c->src); + + if ((c->d & DstMask) == DstDI) + string_addr_inc(ctxt, es_base(ctxt, ops), VCPU_REGS_RDI, + &c->dst); + + if (c->rep_prefix && (c->d & String)) { + struct read_cache *rc = &ctxt->decode.io_read; + register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1); + /* + * Re-enter guest when pio read ahead buffer is empty or, + * if it is not used, after each 1024 iteration. + */ + if ((rc->end == 0 && !(c->regs[VCPU_REGS_RCX] & 0x3ff)) || + (rc->end != 0 && rc->end == rc->pos)) + ctxt->restart = false; } - return 0; + /* + * reset read cache here in case string instruction is restared + * without decoding + */ + ctxt->decode.mem_read.end = 0; + ctxt->eip = c->eip; + +done: + return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0; twobyte_insn: switch (c->b) { @@ -2418,18 +3083,18 @@ twobyte_insn: goto cannot_emulate; rc = kvm_fix_hypercall(ctxt->vcpu); - if (rc) + if (rc != X86EMUL_CONTINUE) goto done; /* Let the processor re-execute the fixed hypercall */ - c->eip = kvm_rip_read(ctxt->vcpu); + c->eip = ctxt->eip; /* Disable writeback. */ c->dst.type = OP_NONE; break; case 2: /* lgdt */ rc = read_descriptor(ctxt, ops, c->src.ptr, &size, &address, c->op_bytes); - if (rc) + if (rc != X86EMUL_CONTINUE) goto done; realmode_lgdt(ctxt->vcpu, size, address); /* Disable writeback. */ @@ -2440,7 +3105,7 @@ twobyte_insn: switch (c->modrm_rm) { case 1: rc = kvm_fix_hypercall(ctxt->vcpu); - if (rc) + if (rc != X86EMUL_CONTINUE) goto done; break; default: @@ -2450,7 +3115,7 @@ twobyte_insn: rc = read_descriptor(ctxt, ops, c->src.ptr, &size, &address, c->op_bytes); - if (rc) + if (rc != X86EMUL_CONTINUE) goto done; realmode_lidt(ctxt->vcpu, size, address); } @@ -2459,15 +3124,18 @@ twobyte_insn: break; case 4: /* smsw */ c->dst.bytes = 2; - c->dst.val = realmode_get_cr(ctxt->vcpu, 0); + c->dst.val = ops->get_cr(0, ctxt->vcpu); break; case 6: /* lmsw */ - realmode_lmsw(ctxt->vcpu, (u16)c->src.val, - &ctxt->eflags); + ops->set_cr(0, (ops->get_cr(0, ctxt->vcpu) & ~0x0ful) | + (c->src.val & 0x0f), ctxt->vcpu); c->dst.type = OP_NONE; break; + case 5: /* not defined */ + emulate_ud(ctxt); + goto done; case 7: /* invlpg*/ - emulate_invlpg(ctxt->vcpu, memop); + emulate_invlpg(ctxt->vcpu, c->modrm_ea); /* Disable writeback. */ c->dst.type = OP_NONE; break; @@ -2476,7 +3144,7 @@ twobyte_insn: } break; case 0x05: /* syscall */ - rc = emulate_syscall(ctxt); + rc = emulate_syscall(ctxt, ops); if (rc != X86EMUL_CONTINUE) goto done; else @@ -2486,61 +3154,75 @@ twobyte_insn: emulate_clts(ctxt->vcpu); c->dst.type = OP_NONE; break; - case 0x08: /* invd */ case 0x09: /* wbinvd */ + kvm_emulate_wbinvd(ctxt->vcpu); + c->dst.type = OP_NONE; + break; + case 0x08: /* invd */ case 0x0d: /* GrpP (prefetch) */ case 0x18: /* Grp16 (prefetch/nop) */ c->dst.type = OP_NONE; break; case 0x20: /* mov cr, reg */ - if (c->modrm_mod != 3) - goto cannot_emulate; - c->regs[c->modrm_rm] = - realmode_get_cr(ctxt->vcpu, c->modrm_reg); + switch (c->modrm_reg) { + case 1: + case 5 ... 7: + case 9 ... 15: + emulate_ud(ctxt); + goto done; + } + c->regs[c->modrm_rm] = ops->get_cr(c->modrm_reg, ctxt->vcpu); c->dst.type = OP_NONE; /* no writeback */ break; case 0x21: /* mov from dr to reg */ - if (c->modrm_mod != 3) - goto cannot_emulate; - rc = emulator_get_dr(ctxt, c->modrm_reg, &c->regs[c->modrm_rm]); - if (rc) - goto cannot_emulate; + if ((ops->get_cr(4, ctxt->vcpu) & X86_CR4_DE) && + (c->modrm_reg == 4 || c->modrm_reg == 5)) { + emulate_ud(ctxt); + goto done; + } + ops->get_dr(c->modrm_reg, &c->regs[c->modrm_rm], ctxt->vcpu); c->dst.type = OP_NONE; /* no writeback */ break; case 0x22: /* mov reg, cr */ - if (c->modrm_mod != 3) - goto cannot_emulate; - realmode_set_cr(ctxt->vcpu, - c->modrm_reg, c->modrm_val, &ctxt->eflags); + if (ops->set_cr(c->modrm_reg, c->modrm_val, ctxt->vcpu)) { + emulate_gp(ctxt, 0); + goto done; + } c->dst.type = OP_NONE; break; case 0x23: /* mov from reg to dr */ - if (c->modrm_mod != 3) - goto cannot_emulate; - rc = emulator_set_dr(ctxt, c->modrm_reg, - c->regs[c->modrm_rm]); - if (rc) - goto cannot_emulate; + if ((ops->get_cr(4, ctxt->vcpu) & X86_CR4_DE) && + (c->modrm_reg == 4 || c->modrm_reg == 5)) { + emulate_ud(ctxt); + goto done; + } + + if (ops->set_dr(c->modrm_reg, c->regs[c->modrm_rm] & + ((ctxt->mode == X86EMUL_MODE_PROT64) ? + ~0ULL : ~0U), ctxt->vcpu) < 0) { + /* #UD condition is already handled by the code above */ + emulate_gp(ctxt, 0); + goto done; + } + c->dst.type = OP_NONE; /* no writeback */ break; case 0x30: /* wrmsr */ msr_data = (u32)c->regs[VCPU_REGS_RAX] | ((u64)c->regs[VCPU_REGS_RDX] << 32); - rc = kvm_set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data); - if (rc) { - kvm_inject_gp(ctxt->vcpu, 0); - c->eip = kvm_rip_read(ctxt->vcpu); + if (ops->set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data)) { + emulate_gp(ctxt, 0); + goto done; } rc = X86EMUL_CONTINUE; c->dst.type = OP_NONE; break; case 0x32: /* rdmsr */ - rc = kvm_get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data); - if (rc) { - kvm_inject_gp(ctxt->vcpu, 0); - c->eip = kvm_rip_read(ctxt->vcpu); + if (ops->get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data)) { + emulate_gp(ctxt, 0); + goto done; } else { c->regs[VCPU_REGS_RAX] = (u32)msr_data; c->regs[VCPU_REGS_RDX] = msr_data >> 32; @@ -2549,14 +3231,14 @@ twobyte_insn: c->dst.type = OP_NONE; break; case 0x34: /* sysenter */ - rc = emulate_sysenter(ctxt); + rc = emulate_sysenter(ctxt, ops); if (rc != X86EMUL_CONTINUE) goto done; else goto writeback; break; case 0x35: /* sysexit */ - rc = emulate_sysexit(ctxt); + rc = emulate_sysexit(ctxt, ops); if (rc != X86EMUL_CONTINUE) goto done; else @@ -2573,11 +3255,11 @@ twobyte_insn: c->dst.type = OP_NONE; break; case 0xa0: /* push fs */ - emulate_push_sreg(ctxt, VCPU_SREG_FS); + emulate_push_sreg(ctxt, ops, VCPU_SREG_FS); break; case 0xa1: /* pop fs */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_FS); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0xa3: @@ -2592,11 +3274,11 @@ twobyte_insn: emulate_2op_cl("shld", c->src2, c->src, c->dst, ctxt->eflags); break; case 0xa8: /* push gs */ - emulate_push_sreg(ctxt, VCPU_SREG_GS); + emulate_push_sreg(ctxt, ops, VCPU_SREG_GS); break; case 0xa9: /* pop gs */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_GS); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0xab: @@ -2668,16 +3350,14 @@ twobyte_insn: (u64) c->src.val; break; case 0xc7: /* Grp9 (cmpxchg8b) */ - rc = emulate_grp9(ctxt, ops, memop); - if (rc != 0) + rc = emulate_grp9(ctxt, ops); + if (rc != X86EMUL_CONTINUE) goto done; - c->dst.type = OP_NONE; break; } goto writeback; cannot_emulate: DPRINTF("Cannot emulate %02x\n", c->b); - c->eip = saved_eip; return -1; } diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 0150affad25..0fd6378981f 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -5,6 +5,7 @@ * Copyright (c) 2006 Intel Corporation * Copyright (c) 2007 Keir Fraser, XenSource Inc * Copyright (c) 2008 Intel Corporation + * Copyright 2009 Red Hat, Inc. and/or its affilates. * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal @@ -33,6 +34,7 @@ #include <linux/kvm_host.h> #include <linux/slab.h> +#include <linux/workqueue.h> #include "irq.h" #include "i8254.h" @@ -243,11 +245,22 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian) { struct kvm_kpit_state *ps = container_of(kian, struct kvm_kpit_state, irq_ack_notifier); - raw_spin_lock(&ps->inject_lock); - if (atomic_dec_return(&ps->pit_timer.pending) < 0) + int value; + + spin_lock(&ps->inject_lock); + value = atomic_dec_return(&ps->pit_timer.pending); + if (value < 0) + /* spurious acks can be generated if, for example, the + * PIC is being reset. Handle it gracefully here + */ atomic_inc(&ps->pit_timer.pending); + else if (value > 0) + /* in this case, we had multiple outstanding pit interrupts + * that we needed to inject. Reinject + */ + queue_work(ps->pit->wq, &ps->pit->expired); ps->irq_ack = 1; - raw_spin_unlock(&ps->inject_lock); + spin_unlock(&ps->inject_lock); } void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) @@ -263,10 +276,10 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } -static void destroy_pit_timer(struct kvm_timer *pt) +static void destroy_pit_timer(struct kvm_pit *pit) { - pr_debug("execute del timer!\n"); - hrtimer_cancel(&pt->timer); + hrtimer_cancel(&pit->pit_state.pit_timer.timer); + cancel_work_sync(&pit->expired); } static bool kpit_is_periodic(struct kvm_timer *ktimer) @@ -280,6 +293,60 @@ static struct kvm_timer_ops kpit_ops = { .is_periodic = kpit_is_periodic, }; +static void pit_do_work(struct work_struct *work) +{ + struct kvm_pit *pit = container_of(work, struct kvm_pit, expired); + struct kvm *kvm = pit->kvm; + struct kvm_vcpu *vcpu; + int i; + struct kvm_kpit_state *ps = &pit->pit_state; + int inject = 0; + + /* Try to inject pending interrupts when + * last one has been acked. + */ + spin_lock(&ps->inject_lock); + if (ps->irq_ack) { + ps->irq_ack = 0; + inject = 1; + } + spin_unlock(&ps->inject_lock); + if (inject) { + kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1); + kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0); + + /* + * Provides NMI watchdog support via Virtual Wire mode. + * The route is: PIT -> PIC -> LVT0 in NMI mode. + * + * Note: Our Virtual Wire implementation is simplified, only + * propagating PIT interrupts to all VCPUs when they have set + * LVT0 to NMI delivery. Other PIC interrupts are just sent to + * VCPU0, and only if its LVT0 is in EXTINT mode. + */ + if (kvm->arch.vapics_in_nmi_mode > 0) + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_apic_nmi_wd_deliver(vcpu); + } +} + +static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) +{ + struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); + struct kvm_pit *pt = ktimer->kvm->arch.vpit; + + if (ktimer->reinject || !atomic_read(&ktimer->pending)) { + atomic_inc(&ktimer->pending); + queue_work(pt->wq, &pt->expired); + } + + if (ktimer->t_ops->is_periodic(ktimer)) { + hrtimer_add_expires_ns(&ktimer->timer, ktimer->period); + return HRTIMER_RESTART; + } else + return HRTIMER_NORESTART; +} + static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period) { struct kvm_timer *pt = &ps->pit_timer; @@ -291,13 +358,13 @@ static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period) /* TODO The new value only affected after the retriggered */ hrtimer_cancel(&pt->timer); + cancel_work_sync(&ps->pit->expired); pt->period = interval; ps->is_periodic = is_period; - pt->timer.function = kvm_timer_fn; + pt->timer.function = pit_timer_fn; pt->t_ops = &kpit_ops; pt->kvm = ps->pit->kvm; - pt->vcpu = pt->kvm->bsp_vcpu; atomic_set(&pt->pending, 0); ps->irq_ack = 1; @@ -346,7 +413,7 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val) } break; default: - destroy_pit_timer(&ps->pit_timer); + destroy_pit_timer(kvm->arch.vpit); } } @@ -625,7 +692,15 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) mutex_init(&pit->pit_state.lock); mutex_lock(&pit->pit_state.lock); - raw_spin_lock_init(&pit->pit_state.inject_lock); + spin_lock_init(&pit->pit_state.inject_lock); + + pit->wq = create_singlethread_workqueue("kvm-pit-wq"); + if (!pit->wq) { + mutex_unlock(&pit->pit_state.lock); + kfree(pit); + return NULL; + } + INIT_WORK(&pit->expired, pit_do_work); kvm->arch.vpit = pit; pit->kvm = kvm; @@ -677,6 +752,9 @@ void kvm_free_pit(struct kvm *kvm) struct hrtimer *timer; if (kvm->arch.vpit) { + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &kvm->arch.vpit->dev); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &kvm->arch.vpit->speaker_dev); kvm_unregister_irq_mask_notifier(kvm, 0, &kvm->arch.vpit->mask_notifier); kvm_unregister_irq_ack_notifier(kvm, @@ -684,54 +762,10 @@ void kvm_free_pit(struct kvm *kvm) mutex_lock(&kvm->arch.vpit->pit_state.lock); timer = &kvm->arch.vpit->pit_state.pit_timer.timer; hrtimer_cancel(timer); + cancel_work_sync(&kvm->arch.vpit->expired); kvm_free_irq_source_id(kvm, kvm->arch.vpit->irq_source_id); mutex_unlock(&kvm->arch.vpit->pit_state.lock); + destroy_workqueue(kvm->arch.vpit->wq); kfree(kvm->arch.vpit); } } - -static void __inject_pit_timer_intr(struct kvm *kvm) -{ - struct kvm_vcpu *vcpu; - int i; - - kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1); - kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0); - - /* - * Provides NMI watchdog support via Virtual Wire mode. - * The route is: PIT -> PIC -> LVT0 in NMI mode. - * - * Note: Our Virtual Wire implementation is simplified, only - * propagating PIT interrupts to all VCPUs when they have set - * LVT0 to NMI delivery. Other PIC interrupts are just sent to - * VCPU0, and only if its LVT0 is in EXTINT mode. - */ - if (kvm->arch.vapics_in_nmi_mode > 0) - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_apic_nmi_wd_deliver(vcpu); -} - -void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu) -{ - struct kvm_pit *pit = vcpu->kvm->arch.vpit; - struct kvm *kvm = vcpu->kvm; - struct kvm_kpit_state *ps; - - if (pit) { - int inject = 0; - ps = &pit->pit_state; - - /* Try to inject pending interrupts when - * last one has been acked. - */ - raw_spin_lock(&ps->inject_lock); - if (atomic_read(&ps->pit_timer.pending) && ps->irq_ack) { - ps->irq_ack = 0; - inject = 1; - } - raw_spin_unlock(&ps->inject_lock); - if (inject) - __inject_pit_timer_intr(kvm); - } -} diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index 900d6b0ba7c..46d08ca0b48 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -27,7 +27,7 @@ struct kvm_kpit_state { u32 speaker_data_on; struct mutex lock; struct kvm_pit *pit; - raw_spinlock_t inject_lock; + spinlock_t inject_lock; unsigned long irq_ack; struct kvm_irq_ack_notifier irq_ack_notifier; }; @@ -40,6 +40,8 @@ struct kvm_pit { struct kvm_kpit_state pit_state; int irq_source_id; struct kvm_irq_mask_notifier mask_notifier; + struct workqueue_struct *wq; + struct work_struct expired; }; #define KVM_PIT_BASE_ADDRESS 0x40 diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index a790fa128a9..8d10c063d7f 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -3,6 +3,7 @@ * * Copyright (c) 2003-2004 Fabrice Bellard * Copyright (c) 2007 Intel Corporation + * Copyright 2009 Red Hat, Inc. and/or its affilates. * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal @@ -33,6 +34,40 @@ #include <linux/kvm_host.h> #include "trace.h" +static void pic_irq_request(struct kvm *kvm, int level); + +static void pic_lock(struct kvm_pic *s) + __acquires(&s->lock) +{ + raw_spin_lock(&s->lock); +} + +static void pic_unlock(struct kvm_pic *s) + __releases(&s->lock) +{ + bool wakeup = s->wakeup_needed; + struct kvm_vcpu *vcpu, *found = NULL; + int i; + + s->wakeup_needed = false; + + raw_spin_unlock(&s->lock); + + if (wakeup) { + kvm_for_each_vcpu(i, vcpu, s->kvm) { + if (kvm_apic_accept_pic_intr(vcpu)) { + found = vcpu; + break; + } + } + + if (!found) + found = s->kvm->bsp_vcpu; + + kvm_vcpu_kick(found); + } +} + static void pic_clear_isr(struct kvm_kpic_state *s, int irq) { s->isr &= ~(1 << irq); @@ -45,19 +80,19 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq) * Other interrupt may be delivered to PIC while lock is dropped but * it should be safe since PIC state is already updated at this stage. */ - raw_spin_unlock(&s->pics_state->lock); + pic_unlock(s->pics_state); kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq); - raw_spin_lock(&s->pics_state->lock); + pic_lock(s->pics_state); } void kvm_pic_clear_isr_ack(struct kvm *kvm) { struct kvm_pic *s = pic_irqchip(kvm); - raw_spin_lock(&s->lock); + pic_lock(s); s->pics[0].isr_ack = 0xff; s->pics[1].isr_ack = 0xff; - raw_spin_unlock(&s->lock); + pic_unlock(s); } /* @@ -150,17 +185,14 @@ static void pic_update_irq(struct kvm_pic *s) pic_set_irq1(&s->pics[0], 2, 0); } irq = pic_get_irq(&s->pics[0]); - if (irq >= 0) - s->irq_request(s->irq_request_opaque, 1); - else - s->irq_request(s->irq_request_opaque, 0); + pic_irq_request(s->kvm, irq >= 0); } void kvm_pic_update_irq(struct kvm_pic *s) { - raw_spin_lock(&s->lock); + pic_lock(s); pic_update_irq(s); - raw_spin_unlock(&s->lock); + pic_unlock(s); } int kvm_pic_set_irq(void *opaque, int irq, int level) @@ -168,14 +200,14 @@ int kvm_pic_set_irq(void *opaque, int irq, int level) struct kvm_pic *s = opaque; int ret = -1; - raw_spin_lock(&s->lock); + pic_lock(s); if (irq >= 0 && irq < PIC_NUM_PINS) { ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); pic_update_irq(s); trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr, s->pics[irq >> 3].imr, ret == 0); } - raw_spin_unlock(&s->lock); + pic_unlock(s); return ret; } @@ -205,7 +237,7 @@ int kvm_pic_read_irq(struct kvm *kvm) int irq, irq2, intno; struct kvm_pic *s = pic_irqchip(kvm); - raw_spin_lock(&s->lock); + pic_lock(s); irq = pic_get_irq(&s->pics[0]); if (irq >= 0) { pic_intack(&s->pics[0], irq); @@ -230,7 +262,7 @@ int kvm_pic_read_irq(struct kvm *kvm) intno = s->pics[0].irq_base + irq; } pic_update_irq(s); - raw_spin_unlock(&s->lock); + pic_unlock(s); return intno; } @@ -238,8 +270,7 @@ int kvm_pic_read_irq(struct kvm *kvm) void kvm_pic_reset(struct kvm_kpic_state *s) { int irq; - struct kvm *kvm = s->pics_state->irq_request_opaque; - struct kvm_vcpu *vcpu0 = kvm->bsp_vcpu; + struct kvm_vcpu *vcpu0 = s->pics_state->kvm->bsp_vcpu; u8 irr = s->irr, isr = s->imr; s->last_irr = 0; @@ -278,8 +309,7 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) /* * deassert a pending interrupt */ - s->pics_state->irq_request(s->pics_state-> - irq_request_opaque, 0); + pic_irq_request(s->pics_state->kvm, 0); s->init_state = 1; s->init4 = val & 1; if (val & 0x02) @@ -333,10 +363,20 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) } } else switch (s->init_state) { - case 0: /* normal mode */ + case 0: { /* normal mode */ + u8 imr_diff = s->imr ^ val, + off = (s == &s->pics_state->pics[0]) ? 0 : 8; s->imr = val; + for (irq = 0; irq < PIC_NUM_PINS/2; irq++) + if (imr_diff & (1 << irq)) + kvm_fire_mask_notifiers( + s->pics_state->kvm, + SELECT_PIC(irq + off), + irq + off, + !!(s->imr & (1 << irq))); pic_update_irq(s->pics_state); break; + } case 1: s->irq_base = val & 0xf8; s->init_state = 2; @@ -444,7 +484,7 @@ static int picdev_write(struct kvm_io_device *this, printk(KERN_ERR "PIC: non byte write\n"); return 0; } - raw_spin_lock(&s->lock); + pic_lock(s); switch (addr) { case 0x20: case 0x21: @@ -457,7 +497,7 @@ static int picdev_write(struct kvm_io_device *this, elcr_ioport_write(&s->pics[addr & 1], addr, data); break; } - raw_spin_unlock(&s->lock); + pic_unlock(s); return 0; } @@ -474,7 +514,7 @@ static int picdev_read(struct kvm_io_device *this, printk(KERN_ERR "PIC: non byte read\n"); return 0; } - raw_spin_lock(&s->lock); + pic_lock(s); switch (addr) { case 0x20: case 0x21: @@ -488,16 +528,15 @@ static int picdev_read(struct kvm_io_device *this, break; } *(unsigned char *)val = data; - raw_spin_unlock(&s->lock); + pic_unlock(s); return 0; } /* * callback when PIC0 irq status changed */ -static void pic_irq_request(void *opaque, int level) +static void pic_irq_request(struct kvm *kvm, int level) { - struct kvm *kvm = opaque; struct kvm_vcpu *vcpu = kvm->bsp_vcpu; struct kvm_pic *s = pic_irqchip(kvm); int irq = pic_get_irq(&s->pics[0]); @@ -505,7 +544,7 @@ static void pic_irq_request(void *opaque, int level) s->output = level; if (vcpu && level && (s->pics[0].isr_ack & (1 << irq))) { s->pics[0].isr_ack &= ~(1 << irq); - kvm_vcpu_kick(vcpu); + s->wakeup_needed = true; } } @@ -526,8 +565,6 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm) s->kvm = kvm; s->pics[0].elcr_mask = 0xf8; s->pics[1].elcr_mask = 0xde; - s->irq_request = pic_irq_request; - s->irq_request_opaque = kvm; s->pics[0].pics_state = s; s->pics[1].pics_state = s; diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 96dfbb6ad2a..2095a049835 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -1,6 +1,7 @@ /* * irq.c: API for in kernel interrupt controller * Copyright (c) 2007, Intel Corporation. + * Copyright 2009 Red Hat, Inc. and/or its affilates. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -89,7 +90,6 @@ EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) { kvm_inject_apic_timer_irqs(vcpu); - kvm_inject_pit_timer_irqs(vcpu); /* TODO: PIT, RTC etc. */ } EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs); diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 34b15915754..ffed06871c5 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -38,8 +38,6 @@ struct kvm; struct kvm_vcpu; -typedef void irq_request_func(void *opaque, int level); - struct kvm_kpic_state { u8 last_irr; /* edge detection */ u8 irr; /* interrupt request register */ @@ -63,11 +61,10 @@ struct kvm_kpic_state { struct kvm_pic { raw_spinlock_t lock; + bool wakeup_needed; unsigned pending_acks; struct kvm *kvm; struct kvm_kpic_state pics[2]; /* 0 is master pic, 1 is slave pic */ - irq_request_func *irq_request; - void *irq_request_opaque; int output; /* intr from master PIC */ struct kvm_io_device dev; void (*ack_notifier)(void *opaque, int irq); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index cff851cf532..6491ac8e755 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -36,6 +36,8 @@ static inline void kvm_rip_write(struct kvm_vcpu *vcpu, unsigned long val) static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) { + might_sleep(); /* on svm */ + if (!test_bit(VCPU_EXREG_PDPTR, (unsigned long *)&vcpu->arch.regs_avail)) kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_PDPTR); @@ -69,4 +71,10 @@ static inline ulong kvm_read_cr4(struct kvm_vcpu *vcpu) return kvm_read_cr4_bits(vcpu, ~0UL); } +static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu) +{ + return (kvm_register_read(vcpu, VCPU_REGS_RAX) & -1u) + | ((u64)(kvm_register_read(vcpu, VCPU_REGS_RDX) & -1u) << 32); +} + #endif diff --git a/arch/x86/kvm/kvm_timer.h b/arch/x86/kvm/kvm_timer.h index 55c7524dda5..64bc6ea78d9 100644 --- a/arch/x86/kvm/kvm_timer.h +++ b/arch/x86/kvm/kvm_timer.h @@ -10,9 +10,7 @@ struct kvm_timer { }; struct kvm_timer_ops { - bool (*is_periodic)(struct kvm_timer *); + bool (*is_periodic)(struct kvm_timer *); }; - enum hrtimer_restart kvm_timer_fn(struct hrtimer *data); - diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 1eb7a4ae0c9..77d8c0f4817 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -5,6 +5,7 @@ * Copyright (C) 2006 Qumranet, Inc. * Copyright (C) 2007 Novell * Copyright (C) 2007 Intel + * Copyright 2009 Red Hat, Inc. and/or its affilates. * * Authors: * Dor Laor <dor.laor@qumranet.com> @@ -328,7 +329,7 @@ int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, "dest_mode 0x%x, short_hand 0x%x\n", target, source, dest, dest_mode, short_hand); - ASSERT(!target); + ASSERT(target); switch (short_hand) { case APIC_DEST_NOSHORT: if (dest_mode == 0) @@ -533,7 +534,7 @@ static void __report_tpr_access(struct kvm_lapic *apic, bool write) struct kvm_vcpu *vcpu = apic->vcpu; struct kvm_run *run = vcpu->run; - set_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests); + kvm_make_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu); run->tpr_access.rip = kvm_rip_read(vcpu); run->tpr_access.is_write = write; } @@ -1106,13 +1107,11 @@ int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) u32 lvt0 = apic_get_reg(vcpu->arch.apic, APIC_LVT0); int r = 0; - if (kvm_vcpu_is_bsp(vcpu)) { - if (!apic_hw_enabled(vcpu->arch.apic)) - r = 1; - if ((lvt0 & APIC_LVT_MASKED) == 0 && - GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT) - r = 1; - } + if (!apic_hw_enabled(vcpu->arch.apic)) + r = 1; + if ((lvt0 & APIC_LVT_MASKED) == 0 && + GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT) + r = 1; return r; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 19a8906bcaa..311f6dad895 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -7,6 +7,7 @@ * MMU support * * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affilates. * * Authors: * Yaniv Kamay <yaniv@qumranet.com> @@ -32,6 +33,7 @@ #include <linux/compiler.h> #include <linux/srcu.h> #include <linux/slab.h> +#include <linux/uaccess.h> #include <asm/page.h> #include <asm/cmpxchg.h> @@ -90,8 +92,6 @@ module_param(oos_shadow, bool, 0644); #define PT_FIRST_AVAIL_BITS_SHIFT 9 #define PT64_SECOND_AVAIL_BITS_SHIFT 52 -#define VALID_PAGE(x) ((x) != INVALID_PAGE) - #define PT64_LEVEL_BITS 9 #define PT64_LEVEL_SHIFT(level) \ @@ -148,7 +148,6 @@ module_param(oos_shadow, bool, 0644); #include <trace/events/kvm.h> -#undef TRACE_INCLUDE_FILE #define CREATE_TRACE_POINTS #include "mmutrace.h" @@ -174,12 +173,7 @@ struct kvm_shadow_walk_iterator { shadow_walk_okay(&(_walker)); \ shadow_walk_next(&(_walker))) - -struct kvm_unsync_walk { - int (*entry) (struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk); -}; - -typedef int (*mmu_parent_walk_fn) (struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp); +typedef void (*mmu_parent_walk_fn) (struct kvm_mmu_page *sp, u64 *spte); static struct kmem_cache *pte_chain_cache; static struct kmem_cache *rmap_desc_cache; @@ -223,7 +217,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); -static int is_write_protection(struct kvm_vcpu *vcpu) +static bool is_write_protection(struct kvm_vcpu *vcpu) { return kvm_read_cr0_bits(vcpu, X86_CR0_WP); } @@ -287,13 +281,38 @@ static gfn_t pse36_gfn_delta(u32 gpte) static void __set_spte(u64 *sptep, u64 spte) { + set_64bit(sptep, spte); +} + +static u64 __xchg_spte(u64 *sptep, u64 new_spte) +{ #ifdef CONFIG_X86_64 - set_64bit((unsigned long *)sptep, spte); + return xchg(sptep, new_spte); #else - set_64bit((unsigned long long *)sptep, spte); + u64 old_spte; + + do { + old_spte = *sptep; + } while (cmpxchg64(sptep, old_spte, new_spte) != old_spte); + + return old_spte; #endif } +static void update_spte(u64 *sptep, u64 new_spte) +{ + u64 old_spte; + + if (!shadow_accessed_mask || (new_spte & shadow_accessed_mask) || + !is_rmap_spte(*sptep)) + __set_spte(sptep, new_spte); + else { + old_spte = __xchg_spte(sptep, new_spte); + if (old_spte & shadow_accessed_mask) + mark_page_accessed(pfn_to_page(spte_to_pfn(old_spte))); + } +} + static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, struct kmem_cache *base_cache, int min) { @@ -310,10 +329,11 @@ static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, return 0; } -static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc) +static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc, + struct kmem_cache *cache) { while (mc->nobjs) - kfree(mc->objects[--mc->nobjs]); + kmem_cache_free(cache, mc->objects[--mc->nobjs]); } static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, @@ -327,7 +347,6 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, page = alloc_page(GFP_KERNEL); if (!page) return -ENOMEM; - set_page_private(page, 0); cache->objects[cache->nobjs++] = page_address(page); } return 0; @@ -362,10 +381,11 @@ out: static void mmu_free_memory_caches(struct kvm_vcpu *vcpu) { - mmu_free_memory_cache(&vcpu->arch.mmu_pte_chain_cache); - mmu_free_memory_cache(&vcpu->arch.mmu_rmap_desc_cache); + mmu_free_memory_cache(&vcpu->arch.mmu_pte_chain_cache, pte_chain_cache); + mmu_free_memory_cache(&vcpu->arch.mmu_rmap_desc_cache, rmap_desc_cache); mmu_free_memory_cache_page(&vcpu->arch.mmu_page_cache); - mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache); + mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache, + mmu_page_header_cache); } static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc, @@ -386,7 +406,7 @@ static struct kvm_pte_chain *mmu_alloc_pte_chain(struct kvm_vcpu *vcpu) static void mmu_free_pte_chain(struct kvm_pte_chain *pc) { - kfree(pc); + kmem_cache_free(pte_chain_cache, pc); } static struct kvm_rmap_desc *mmu_alloc_rmap_desc(struct kvm_vcpu *vcpu) @@ -397,7 +417,23 @@ static struct kvm_rmap_desc *mmu_alloc_rmap_desc(struct kvm_vcpu *vcpu) static void mmu_free_rmap_desc(struct kvm_rmap_desc *rd) { - kfree(rd); + kmem_cache_free(rmap_desc_cache, rd); +} + +static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index) +{ + if (!sp->role.direct) + return sp->gfns[index]; + + return sp->gfn + (index << ((sp->role.level - 1) * PT64_LEVEL_BITS)); +} + +static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn) +{ + if (sp->role.direct) + BUG_ON(gfn != kvm_mmu_page_get_gfn(sp, index)); + else + sp->gfns[index] = gfn; } /* @@ -410,8 +446,8 @@ static int *slot_largepage_idx(gfn_t gfn, { unsigned long idx; - idx = (gfn / KVM_PAGES_PER_HPAGE(level)) - - (slot->base_gfn / KVM_PAGES_PER_HPAGE(level)); + idx = (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - + (slot->base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); return &slot->lpage_info[level - 2][idx].write_count; } @@ -421,9 +457,7 @@ static void account_shadowed(struct kvm *kvm, gfn_t gfn) int *write_count; int i; - gfn = unalias_gfn(kvm, gfn); - - slot = gfn_to_memslot_unaliased(kvm, gfn); + slot = gfn_to_memslot(kvm, gfn); for (i = PT_DIRECTORY_LEVEL; i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { write_count = slot_largepage_idx(gfn, slot, i); @@ -437,10 +471,9 @@ static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn) int *write_count; int i; - gfn = unalias_gfn(kvm, gfn); + slot = gfn_to_memslot(kvm, gfn); for (i = PT_DIRECTORY_LEVEL; i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - slot = gfn_to_memslot_unaliased(kvm, gfn); write_count = slot_largepage_idx(gfn, slot, i); *write_count -= 1; WARN_ON(*write_count < 0); @@ -454,8 +487,7 @@ static int has_wrprotected_page(struct kvm *kvm, struct kvm_memory_slot *slot; int *largepage_idx; - gfn = unalias_gfn(kvm, gfn); - slot = gfn_to_memslot_unaliased(kvm, gfn); + slot = gfn_to_memslot(kvm, gfn); if (slot) { largepage_idx = slot_largepage_idx(gfn, slot, level); return *largepage_idx; @@ -508,7 +540,6 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) /* * Take gfn and return the reverse mapping to it. - * Note: gfn must be unaliased before this function get called */ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level) @@ -520,8 +551,8 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level) if (likely(level == PT_PAGE_TABLE_LEVEL)) return &slot->rmap[gfn - slot->base_gfn]; - idx = (gfn / KVM_PAGES_PER_HPAGE(level)) - - (slot->base_gfn / KVM_PAGES_PER_HPAGE(level)); + idx = (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - + (slot->base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); return &slot->lpage_info[level - 2][idx].rmap_pde; } @@ -548,9 +579,8 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) if (!is_rmap_spte(*spte)) return count; - gfn = unalias_gfn(vcpu->kvm, gfn); sp = page_header(__pa(spte)); - sp->gfns[spte - sp->spt] = gfn; + kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn); rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); if (!*rmapp) { rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte); @@ -607,19 +637,13 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) struct kvm_rmap_desc *desc; struct kvm_rmap_desc *prev_desc; struct kvm_mmu_page *sp; - pfn_t pfn; + gfn_t gfn; unsigned long *rmapp; int i; - if (!is_rmap_spte(*spte)) - return; sp = page_header(__pa(spte)); - pfn = spte_to_pfn(*spte); - if (*spte & shadow_accessed_mask) - kvm_set_pfn_accessed(pfn); - if (is_writable_pte(*spte)) - kvm_set_pfn_dirty(pfn); - rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], sp->role.level); + gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt); + rmapp = gfn_to_rmap(kvm, gfn, sp->role.level); if (!*rmapp) { printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte); BUG(); @@ -651,10 +675,35 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) } } +static void set_spte_track_bits(u64 *sptep, u64 new_spte) +{ + pfn_t pfn; + u64 old_spte = *sptep; + + if (!shadow_accessed_mask || !is_shadow_present_pte(old_spte) || + old_spte & shadow_accessed_mask) { + __set_spte(sptep, new_spte); + } else + old_spte = __xchg_spte(sptep, new_spte); + + if (!is_rmap_spte(old_spte)) + return; + pfn = spte_to_pfn(old_spte); + if (!shadow_accessed_mask || old_spte & shadow_accessed_mask) + kvm_set_pfn_accessed(pfn); + if (is_writable_pte(old_spte)) + kvm_set_pfn_dirty(pfn); +} + +static void drop_spte(struct kvm *kvm, u64 *sptep, u64 new_spte) +{ + set_spte_track_bits(sptep, new_spte); + rmap_remove(kvm, sptep); +} + static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte) { struct kvm_rmap_desc *desc; - struct kvm_rmap_desc *prev_desc; u64 *prev_spte; int i; @@ -666,7 +715,6 @@ static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte) return NULL; } desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul); - prev_desc = NULL; prev_spte = NULL; while (desc) { for (i = 0; i < RMAP_EXT && desc->sptes[i]; ++i) { @@ -685,7 +733,6 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) u64 *spte; int i, write_protected = 0; - gfn = unalias_gfn(kvm, gfn); rmapp = gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL); spte = rmap_next(kvm, rmapp, NULL); @@ -694,7 +741,7 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) BUG_ON(!(*spte & PT_PRESENT_MASK)); rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte); if (is_writable_pte(*spte)) { - __set_spte(spte, *spte & ~PT_WRITABLE_MASK); + update_spte(spte, *spte & ~PT_WRITABLE_MASK); write_protected = 1; } spte = rmap_next(kvm, rmapp, spte); @@ -718,9 +765,9 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)); pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn); if (is_writable_pte(*spte)) { - rmap_remove(kvm, spte); + drop_spte(kvm, spte, + shadow_trap_nonpresent_pte); --kvm->stat.lpages; - __set_spte(spte, shadow_trap_nonpresent_pte); spte = NULL; write_protected = 1; } @@ -740,8 +787,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, while ((spte = rmap_next(kvm, rmapp, NULL))) { BUG_ON(!(*spte & PT_PRESENT_MASK)); rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", spte, *spte); - rmap_remove(kvm, spte); - __set_spte(spte, shadow_trap_nonpresent_pte); + drop_spte(kvm, spte, shadow_trap_nonpresent_pte); need_tlb_flush = 1; } return need_tlb_flush; @@ -763,8 +809,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", spte, *spte); need_flush = 1; if (pte_write(*ptep)) { - rmap_remove(kvm, spte); - __set_spte(spte, shadow_trap_nonpresent_pte); + drop_spte(kvm, spte, shadow_trap_nonpresent_pte); spte = rmap_next(kvm, rmapp, NULL); } else { new_spte = *spte &~ (PT64_BASE_ADDR_MASK); @@ -772,9 +817,8 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, new_spte &= ~PT_WRITABLE_MASK; new_spte &= ~SPTE_HOST_WRITEABLE; - if (is_writable_pte(*spte)) - kvm_set_pfn_dirty(spte_to_pfn(*spte)); - __set_spte(spte, new_spte); + new_spte &= ~shadow_accessed_mask; + set_spte_track_bits(spte, new_spte); spte = rmap_next(kvm, rmapp, spte); } } @@ -794,7 +838,7 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, int retval = 0; struct kvm_memslots *slots; - slots = rcu_dereference(kvm->memslots); + slots = kvm_memslots(kvm); for (i = 0; i < slots->nmemslots; i++) { struct kvm_memory_slot *memslot = &slots->memslots[i]; @@ -808,8 +852,12 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, ret = handler(kvm, &memslot->rmap[gfn_offset], data); for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) { - int idx = gfn_offset; - idx /= KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL + j); + unsigned long idx; + int sh; + + sh = KVM_HPAGE_GFN_SHIFT(PT_DIRECTORY_LEVEL+j); + idx = ((memslot->base_gfn+gfn_offset) >> sh) - + (memslot->base_gfn >> sh); ret |= handler(kvm, &memslot->lpage_info[j][idx].rmap_pde, data); @@ -872,7 +920,6 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) sp = page_header(__pa(spte)); - gfn = unalias_gfn(vcpu->kvm, gfn); rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); kvm_unmap_rmapp(vcpu->kvm, rmapp, 0); @@ -903,10 +950,12 @@ static int is_empty_shadow_page(u64 *spt) static void kvm_mmu_free_page(struct kvm *kvm, struct kvm_mmu_page *sp) { ASSERT(is_empty_shadow_page(sp->spt)); + hlist_del(&sp->hash_link); list_del(&sp->link); __free_page(virt_to_page(sp->spt)); - __free_page(virt_to_page(sp->gfns)); - kfree(sp); + if (!sp->role.direct) + __free_page(virt_to_page(sp->gfns)); + kmem_cache_free(mmu_page_header_cache, sp); ++kvm->arch.n_free_mmu_pages; } @@ -916,16 +965,17 @@ static unsigned kvm_page_table_hashfn(gfn_t gfn) } static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, - u64 *parent_pte) + u64 *parent_pte, int direct) { struct kvm_mmu_page *sp; sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache, sizeof *sp); sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE); - sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE); + if (!direct) + sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, + PAGE_SIZE); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); - INIT_LIST_HEAD(&sp->oos_link); bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS); sp->multimapped = 0; sp->parent_pte = parent_pte; @@ -1008,9 +1058,7 @@ static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp, BUG(); } - -static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - mmu_parent_walk_fn fn) +static void mmu_parent_walk(struct kvm_mmu_page *sp, mmu_parent_walk_fn fn) { struct kvm_pte_chain *pte_chain; struct hlist_node *node; @@ -1019,64 +1067,37 @@ static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (!sp->multimapped && sp->parent_pte) { parent_sp = page_header(__pa(sp->parent_pte)); - fn(vcpu, parent_sp); - mmu_parent_walk(vcpu, parent_sp, fn); + fn(parent_sp, sp->parent_pte); return; } + hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link) for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) { - if (!pte_chain->parent_ptes[i]) + u64 *spte = pte_chain->parent_ptes[i]; + + if (!spte) break; - parent_sp = page_header(__pa(pte_chain->parent_ptes[i])); - fn(vcpu, parent_sp); - mmu_parent_walk(vcpu, parent_sp, fn); + parent_sp = page_header(__pa(spte)); + fn(parent_sp, spte); } } -static void kvm_mmu_update_unsync_bitmap(u64 *spte) +static void mark_unsync(struct kvm_mmu_page *sp, u64 *spte); +static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp) { - unsigned int index; - struct kvm_mmu_page *sp = page_header(__pa(spte)); - - index = spte - sp->spt; - if (!__test_and_set_bit(index, sp->unsync_child_bitmap)) - sp->unsync_children++; - WARN_ON(!sp->unsync_children); + mmu_parent_walk(sp, mark_unsync); } -static void kvm_mmu_update_parents_unsync(struct kvm_mmu_page *sp) +static void mark_unsync(struct kvm_mmu_page *sp, u64 *spte) { - struct kvm_pte_chain *pte_chain; - struct hlist_node *node; - int i; + unsigned int index; - if (!sp->parent_pte) + index = spte - sp->spt; + if (__test_and_set_bit(index, sp->unsync_child_bitmap)) return; - - if (!sp->multimapped) { - kvm_mmu_update_unsync_bitmap(sp->parent_pte); + if (sp->unsync_children++) return; - } - - hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link) - for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) { - if (!pte_chain->parent_ptes[i]) - break; - kvm_mmu_update_unsync_bitmap(pte_chain->parent_ptes[i]); - } -} - -static int unsync_walk_fn(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) -{ - kvm_mmu_update_parents_unsync(sp); - return 1; -} - -static void kvm_mmu_mark_parents_unsync(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp) -{ - mmu_parent_walk(vcpu, sp, unsync_walk_fn); - kvm_mmu_update_parents_unsync(sp); + kvm_mmu_mark_parents_unsync(sp); } static void nonpaging_prefetch_page(struct kvm_vcpu *vcpu, @@ -1089,7 +1110,7 @@ static void nonpaging_prefetch_page(struct kvm_vcpu *vcpu, } static int nonpaging_sync_page(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp) + struct kvm_mmu_page *sp, bool clear_unsync) { return 1; } @@ -1135,35 +1156,40 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp, int i, ret, nr_unsync_leaf = 0; for_each_unsync_children(sp->unsync_child_bitmap, i) { + struct kvm_mmu_page *child; u64 ent = sp->spt[i]; - if (is_shadow_present_pte(ent) && !is_large_pte(ent)) { - struct kvm_mmu_page *child; - child = page_header(ent & PT64_BASE_ADDR_MASK); - - if (child->unsync_children) { - if (mmu_pages_add(pvec, child, i)) - return -ENOSPC; - - ret = __mmu_unsync_walk(child, pvec); - if (!ret) - __clear_bit(i, sp->unsync_child_bitmap); - else if (ret > 0) - nr_unsync_leaf += ret; - else - return ret; - } + if (!is_shadow_present_pte(ent) || is_large_pte(ent)) + goto clear_child_bitmap; + + child = page_header(ent & PT64_BASE_ADDR_MASK); + + if (child->unsync_children) { + if (mmu_pages_add(pvec, child, i)) + return -ENOSPC; + + ret = __mmu_unsync_walk(child, pvec); + if (!ret) + goto clear_child_bitmap; + else if (ret > 0) + nr_unsync_leaf += ret; + else + return ret; + } else if (child->unsync) { + nr_unsync_leaf++; + if (mmu_pages_add(pvec, child, i)) + return -ENOSPC; + } else + goto clear_child_bitmap; - if (child->unsync) { - nr_unsync_leaf++; - if (mmu_pages_add(pvec, child, i)) - return -ENOSPC; - } - } + continue; + +clear_child_bitmap: + __clear_bit(i, sp->unsync_child_bitmap); + sp->unsync_children--; + WARN_ON((int)sp->unsync_children < 0); } - if (find_first_bit(sp->unsync_child_bitmap, 512) == 512) - sp->unsync_children = 0; return nr_unsync_leaf; } @@ -1178,48 +1204,44 @@ static int mmu_unsync_walk(struct kvm_mmu_page *sp, return __mmu_unsync_walk(sp, pvec); } -static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn) -{ - unsigned index; - struct hlist_head *bucket; - struct kvm_mmu_page *sp; - struct hlist_node *node; - - pgprintk("%s: looking for gfn %lx\n", __func__, gfn); - index = kvm_page_table_hashfn(gfn); - bucket = &kvm->arch.mmu_page_hash[index]; - hlist_for_each_entry(sp, node, bucket, hash_link) - if (sp->gfn == gfn && !sp->role.direct - && !sp->role.invalid) { - pgprintk("%s: found role %x\n", - __func__, sp->role.word); - return sp; - } - return NULL; -} - static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) { WARN_ON(!sp->unsync); + trace_kvm_mmu_sync_page(sp); sp->unsync = 0; --kvm->stat.mmu_unsync; } -static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp); +static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, + struct list_head *invalid_list); +static void kvm_mmu_commit_zap_page(struct kvm *kvm, + struct list_head *invalid_list); + +#define for_each_gfn_sp(kvm, sp, gfn, pos) \ + hlist_for_each_entry(sp, pos, \ + &(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link) \ + if ((sp)->gfn != (gfn)) {} else + +#define for_each_gfn_indirect_valid_sp(kvm, sp, gfn, pos) \ + hlist_for_each_entry(sp, pos, \ + &(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link) \ + if ((sp)->gfn != (gfn) || (sp)->role.direct || \ + (sp)->role.invalid) {} else -static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +/* @sp->gfn should be write-protected at the call site */ +static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + struct list_head *invalid_list, bool clear_unsync) { - if (sp->role.glevels != vcpu->arch.mmu.root_level) { - kvm_mmu_zap_page(vcpu->kvm, sp); + if (sp->role.cr4_pae != !!is_pae(vcpu)) { + kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); return 1; } - trace_kvm_mmu_sync_page(sp); - if (rmap_write_protect(vcpu->kvm, sp->gfn)) - kvm_flush_remote_tlbs(vcpu->kvm); - kvm_unlink_unsync_page(vcpu->kvm, sp); - if (vcpu->arch.mmu.sync_page(vcpu, sp)) { - kvm_mmu_zap_page(vcpu->kvm, sp); + if (clear_unsync) + kvm_unlink_unsync_page(vcpu->kvm, sp); + + if (vcpu->arch.mmu.sync_page(vcpu, sp, clear_unsync)) { + kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); return 1; } @@ -1227,6 +1249,52 @@ static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) return 0; } +static int kvm_sync_page_transient(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp) +{ + LIST_HEAD(invalid_list); + int ret; + + ret = __kvm_sync_page(vcpu, sp, &invalid_list, false); + if (ret) + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); + + return ret; +} + +static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + struct list_head *invalid_list) +{ + return __kvm_sync_page(vcpu, sp, invalid_list, true); +} + +/* @gfn should be write-protected at the call site */ +static void kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + struct kvm_mmu_page *s; + struct hlist_node *node; + LIST_HEAD(invalid_list); + bool flush = false; + + for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) { + if (!s->unsync) + continue; + + WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL); + if ((s->role.cr4_pae != !!is_pae(vcpu)) || + (vcpu->arch.mmu.sync_page(vcpu, s, true))) { + kvm_mmu_prepare_zap_page(vcpu->kvm, s, &invalid_list); + continue; + } + kvm_unlink_unsync_page(vcpu->kvm, s); + flush = true; + } + + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); + if (flush) + kvm_mmu_flush_tlb(vcpu); +} + struct mmu_page_path { struct kvm_mmu_page *parent[PT64_ROOT_LEVEL-1]; unsigned int idx[PT64_ROOT_LEVEL-1]; @@ -1293,6 +1361,7 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp; struct mmu_page_path parents; struct kvm_mmu_pages pages; + LIST_HEAD(invalid_list); kvm_mmu_pages_init(parent, &parents, &pages); while (mmu_unsync_walk(parent, &pages)) { @@ -1305,9 +1374,10 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, kvm_flush_remote_tlbs(vcpu->kvm); for_each_sp(pages, sp, parents, i) { - kvm_sync_page(vcpu, sp); + kvm_sync_page(vcpu, sp, &invalid_list); mmu_pages_clear_parents(&parents); } + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); cond_resched_lock(&vcpu->kvm->mmu_lock); kvm_mmu_pages_init(parent, &parents, &pages); } @@ -1322,50 +1392,56 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, u64 *parent_pte) { union kvm_mmu_page_role role; - unsigned index; unsigned quadrant; - struct hlist_head *bucket; struct kvm_mmu_page *sp; - struct hlist_node *node, *tmp; + struct hlist_node *node; + bool need_sync = false; role = vcpu->arch.mmu.base_role; role.level = level; role.direct = direct; + if (role.direct) + role.cr4_pae = 0; role.access = access; - if (vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) { + if (!tdp_enabled && vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) { quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level)); quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; role.quadrant = quadrant; } - index = kvm_page_table_hashfn(gfn); - bucket = &vcpu->kvm->arch.mmu_page_hash[index]; - hlist_for_each_entry_safe(sp, node, tmp, bucket, hash_link) - if (sp->gfn == gfn) { - if (sp->unsync) - if (kvm_sync_page(vcpu, sp)) - continue; + for_each_gfn_sp(vcpu->kvm, sp, gfn, node) { + if (!need_sync && sp->unsync) + need_sync = true; - if (sp->role.word != role.word) - continue; + if (sp->role.word != role.word) + continue; - mmu_page_add_parent_pte(vcpu, sp, parent_pte); - if (sp->unsync_children) { - set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests); - kvm_mmu_mark_parents_unsync(vcpu, sp); - } - trace_kvm_mmu_get_page(sp, false); - return sp; - } + if (sp->unsync && kvm_sync_page_transient(vcpu, sp)) + break; + + mmu_page_add_parent_pte(vcpu, sp, parent_pte); + if (sp->unsync_children) { + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + kvm_mmu_mark_parents_unsync(sp); + } else if (sp->unsync) + kvm_mmu_mark_parents_unsync(sp); + + trace_kvm_mmu_get_page(sp, false); + return sp; + } ++vcpu->kvm->stat.mmu_cache_miss; - sp = kvm_mmu_alloc_page(vcpu, parent_pte); + sp = kvm_mmu_alloc_page(vcpu, parent_pte, direct); if (!sp) return sp; sp->gfn = gfn; sp->role = role; - hlist_add_head(&sp->hash_link, bucket); + hlist_add_head(&sp->hash_link, + &vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]); if (!direct) { if (rmap_write_protect(vcpu->kvm, gfn)) kvm_flush_remote_tlbs(vcpu->kvm); + if (level > PT_PAGE_TABLE_LEVEL && need_sync) + kvm_sync_pages(vcpu, gfn); + account_shadowed(vcpu->kvm, gfn); } if (shadow_trap_nonpresent_pte != shadow_notrap_nonpresent_pte) @@ -1412,6 +1488,47 @@ static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator) --iterator->level; } +static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp) +{ + u64 spte; + + spte = __pa(sp->spt) + | PT_PRESENT_MASK | PT_ACCESSED_MASK + | PT_WRITABLE_MASK | PT_USER_MASK; + __set_spte(sptep, spte); +} + +static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) +{ + if (is_large_pte(*sptep)) { + drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte); + kvm_flush_remote_tlbs(vcpu->kvm); + } +} + +static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, + unsigned direct_access) +{ + if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) { + struct kvm_mmu_page *child; + + /* + * For the direct sp, if the guest pte's dirty bit + * changed form clean to dirty, it will corrupt the + * sp's access: allow writable in the read-only sp, + * so we should update the spte at this point to get + * a new sp with the correct access. + */ + child = page_header(*sptep & PT64_BASE_ADDR_MASK); + if (child->role.access == direct_access) + return; + + mmu_page_remove_parent_pte(child, sptep); + __set_spte(sptep, shadow_trap_nonpresent_pte); + kvm_flush_remote_tlbs(vcpu->kvm); + } +} + static void kvm_mmu_page_unlink_children(struct kvm *kvm, struct kvm_mmu_page *sp) { @@ -1432,7 +1549,8 @@ static void kvm_mmu_page_unlink_children(struct kvm *kvm, } else { if (is_large_pte(ent)) --kvm->stat.lpages; - rmap_remove(kvm, &pt[i]); + drop_spte(kvm, &pt[i], + shadow_trap_nonpresent_pte); } } pt[i] = shadow_trap_nonpresent_pte; @@ -1474,7 +1592,8 @@ static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) } static int mmu_zap_unsync_children(struct kvm *kvm, - struct kvm_mmu_page *parent) + struct kvm_mmu_page *parent, + struct list_head *invalid_list) { int i, zapped = 0; struct mmu_page_path parents; @@ -1488,7 +1607,7 @@ static int mmu_zap_unsync_children(struct kvm *kvm, struct kvm_mmu_page *sp; for_each_sp(pages, sp, parents, i) { - kvm_mmu_zap_page(kvm, sp); + kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); mmu_pages_clear_parents(&parents); zapped++; } @@ -1498,32 +1617,52 @@ static int mmu_zap_unsync_children(struct kvm *kvm, return zapped; } -static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) +static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, + struct list_head *invalid_list) { int ret; - trace_kvm_mmu_zap_page(sp); + trace_kvm_mmu_prepare_zap_page(sp); ++kvm->stat.mmu_shadow_zapped; - ret = mmu_zap_unsync_children(kvm, sp); + ret = mmu_zap_unsync_children(kvm, sp, invalid_list); kvm_mmu_page_unlink_children(kvm, sp); kvm_mmu_unlink_parents(kvm, sp); - kvm_flush_remote_tlbs(kvm); if (!sp->role.invalid && !sp->role.direct) unaccount_shadowed(kvm, sp->gfn); if (sp->unsync) kvm_unlink_unsync_page(kvm, sp); if (!sp->root_count) { - hlist_del(&sp->hash_link); - kvm_mmu_free_page(kvm, sp); + /* Count self */ + ret++; + list_move(&sp->link, invalid_list); } else { - sp->role.invalid = 1; list_move(&sp->link, &kvm->arch.active_mmu_pages); kvm_reload_remote_mmus(kvm); } + + sp->role.invalid = 1; kvm_mmu_reset_last_pte_updated(kvm); return ret; } +static void kvm_mmu_commit_zap_page(struct kvm *kvm, + struct list_head *invalid_list) +{ + struct kvm_mmu_page *sp; + + if (list_empty(invalid_list)) + return; + + kvm_flush_remote_tlbs(kvm); + + do { + sp = list_first_entry(invalid_list, struct kvm_mmu_page, link); + WARN_ON(!sp->role.invalid || sp->root_count); + kvm_mmu_free_page(kvm, sp); + } while (!list_empty(invalid_list)); + +} + /* * Changing the number of mmu pages allocated to the vm * Note: if kvm_nr_mmu_pages is too small, you will get dead lock @@ -1531,6 +1670,7 @@ static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages) { int used_pages; + LIST_HEAD(invalid_list); used_pages = kvm->arch.n_alloc_mmu_pages - kvm->arch.n_free_mmu_pages; used_pages = max(0, used_pages); @@ -1548,9 +1688,10 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages) page = container_of(kvm->arch.active_mmu_pages.prev, struct kvm_mmu_page, link); - used_pages -= kvm_mmu_zap_page(kvm, page); - used_pages--; + used_pages -= kvm_mmu_prepare_zap_page(kvm, page, + &invalid_list); } + kvm_mmu_commit_zap_page(kvm, &invalid_list); kvm_nr_mmu_pages = used_pages; kvm->arch.n_free_mmu_pages = 0; } @@ -1563,45 +1704,36 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages) static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) { - unsigned index; - struct hlist_head *bucket; struct kvm_mmu_page *sp; - struct hlist_node *node, *n; + struct hlist_node *node; + LIST_HEAD(invalid_list); int r; pgprintk("%s: looking for gfn %lx\n", __func__, gfn); r = 0; - index = kvm_page_table_hashfn(gfn); - bucket = &kvm->arch.mmu_page_hash[index]; - hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) - if (sp->gfn == gfn && !sp->role.direct) { - pgprintk("%s: gfn %lx role %x\n", __func__, gfn, - sp->role.word); - r = 1; - if (kvm_mmu_zap_page(kvm, sp)) - n = bucket->first; - } + + for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) { + pgprintk("%s: gfn %lx role %x\n", __func__, gfn, + sp->role.word); + r = 1; + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + } + kvm_mmu_commit_zap_page(kvm, &invalid_list); return r; } static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) { - unsigned index; - struct hlist_head *bucket; struct kvm_mmu_page *sp; - struct hlist_node *node, *nn; - - index = kvm_page_table_hashfn(gfn); - bucket = &kvm->arch.mmu_page_hash[index]; - hlist_for_each_entry_safe(sp, node, nn, bucket, hash_link) { - if (sp->gfn == gfn && !sp->role.direct - && !sp->role.invalid) { - pgprintk("%s: zap %lx %x\n", - __func__, gfn, sp->role.word); - if (kvm_mmu_zap_page(kvm, sp)) - nn = bucket->first; - } + struct hlist_node *node; + LIST_HEAD(invalid_list); + + for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) { + pgprintk("%s: zap %lx %x\n", + __func__, gfn, sp->role.word); + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); } + kvm_mmu_commit_zap_page(kvm, &invalid_list); } static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn) @@ -1626,20 +1758,6 @@ static void mmu_convert_notrap(struct kvm_mmu_page *sp) } } -struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva) -{ - struct page *page; - - gpa_t gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); - - if (gpa == UNMAPPED_GVA) - return NULL; - - page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); - - return page; -} - /* * The function is based on mtrr_type_lookup() in * arch/x86/kernel/cpu/mtrr/generic.c @@ -1745,47 +1863,51 @@ u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) } EXPORT_SYMBOL_GPL(kvm_get_guest_memory_type); -static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { - unsigned index; - struct hlist_head *bucket; - struct kvm_mmu_page *s; - struct hlist_node *node, *n; - trace_kvm_mmu_unsync_page(sp); - index = kvm_page_table_hashfn(sp->gfn); - bucket = &vcpu->kvm->arch.mmu_page_hash[index]; - /* don't unsync if pagetable is shadowed with multiple roles */ - hlist_for_each_entry_safe(s, node, n, bucket, hash_link) { - if (s->gfn != sp->gfn || s->role.direct) - continue; - if (s->role.word != sp->role.word) - return 1; - } ++vcpu->kvm->stat.mmu_unsync; sp->unsync = 1; - kvm_mmu_mark_parents_unsync(vcpu, sp); - + kvm_mmu_mark_parents_unsync(sp); mmu_convert_notrap(sp); - return 0; +} + +static void kvm_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + struct kvm_mmu_page *s; + struct hlist_node *node; + + for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) { + if (s->unsync) + continue; + WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL); + __kvm_unsync_page(vcpu, s); + } } static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) { - struct kvm_mmu_page *shadow; + struct kvm_mmu_page *s; + struct hlist_node *node; + bool need_unsync = false; - shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn); - if (shadow) { - if (shadow->role.level != PT_PAGE_TABLE_LEVEL) + for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) { + if (!can_unsync) return 1; - if (shadow->unsync) - return 0; - if (can_unsync && oos_shadow) - return kvm_unsync_page(vcpu, shadow); - return 1; + + if (s->role.level != PT_PAGE_TABLE_LEVEL) + return 1; + + if (!need_unsync && !s->unsync) { + if (!oos_shadow) + return 1; + need_unsync = true; + } } + if (need_unsync) + kvm_unsync_pages(vcpu, gfn); return 0; } @@ -1826,17 +1948,21 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= (u64)pfn << PAGE_SHIFT; if ((pte_access & ACC_WRITE_MASK) - || (write_fault && !is_write_protection(vcpu) && !user_fault)) { + || (!tdp_enabled && write_fault && !is_write_protection(vcpu) + && !user_fault)) { if (level > PT_PAGE_TABLE_LEVEL && has_wrprotected_page(vcpu->kvm, gfn, level)) { ret = 1; - spte = shadow_trap_nonpresent_pte; - goto set_pte; + drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte); + goto done; } spte |= PT_WRITABLE_MASK; + if (!tdp_enabled && !(pte_access & ACC_WRITE_MASK)) + spte &= ~PT_USER_MASK; + /* * Optimization: for pte sync, if spte was writable the hash * lookup is unnecessary (and expensive). Write protection @@ -1860,7 +1986,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, mark_page_dirty(vcpu->kvm, gfn); set_pte: - __set_spte(sptep, spte); + if (is_writable_pte(*sptep) && !is_writable_pte(spte)) + kvm_set_pfn_dirty(pfn); + update_spte(sptep, spte); +done: return ret; } @@ -1872,7 +2001,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, bool reset_host_protection) { int was_rmapped = 0; - int was_writable = is_writable_pte(*sptep); int rmap_count; pgprintk("%s: spte %llx access %x write_fault %d" @@ -1892,10 +2020,13 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, child = page_header(pte & PT64_BASE_ADDR_MASK); mmu_page_remove_parent_pte(child, sptep); + __set_spte(sptep, shadow_trap_nonpresent_pte); + kvm_flush_remote_tlbs(vcpu->kvm); } else if (pfn != spte_to_pfn(*sptep)) { pgprintk("hfn old %lx new %lx\n", spte_to_pfn(*sptep), pfn); - rmap_remove(vcpu->kvm, sptep); + drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte); + kvm_flush_remote_tlbs(vcpu->kvm); } else was_rmapped = 1; } @@ -1905,7 +2036,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, reset_host_protection)) { if (write_fault) *ptwrite = 1; - kvm_x86_ops->tlb_flush(vcpu); + kvm_mmu_flush_tlb(vcpu); } pgprintk("%s: setting spte %llx\n", __func__, *sptep); @@ -1919,15 +2050,10 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, page_header_update_slot(vcpu->kvm, sptep, gfn); if (!was_rmapped) { rmap_count = rmap_add(vcpu, sptep, gfn); - kvm_release_pfn_clean(pfn); if (rmap_count > RMAP_RECYCLE_THRESHOLD) rmap_recycle(vcpu, sptep, gfn); - } else { - if (was_writable) - kvm_release_pfn_dirty(pfn); - else - kvm_release_pfn_clean(pfn); } + kvm_release_pfn_clean(pfn); if (speculative) { vcpu->arch.last_pte_updated = sptep; vcpu->arch.last_pte_gfn = gfn; @@ -1956,7 +2082,10 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, } if (*iterator.sptep == shadow_trap_nonpresent_pte) { - pseudo_gfn = (iterator.addr & PT64_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT; + u64 base_addr = iterator.addr; + + base_addr &= PT64_LVL_ADDR_MASK(iterator.level); + pseudo_gfn = base_addr >> PAGE_SHIFT; sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr, iterator.level - 1, 1, ACC_ALL, iterator.sptep); @@ -1975,6 +2104,29 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, return pt_write; } +static void kvm_send_hwpoison_signal(struct kvm *kvm, gfn_t gfn) +{ + char buf[1]; + void __user *hva; + int r; + + /* Touch the page, so send SIGBUS */ + hva = (void __user *)gfn_to_hva(kvm, gfn); + r = copy_from_user(buf, hva, 1); +} + +static int kvm_handle_bad_page(struct kvm *kvm, gfn_t gfn, pfn_t pfn) +{ + kvm_release_pfn_clean(pfn); + if (is_hwpoison_pfn(pfn)) { + kvm_send_hwpoison_signal(kvm, gfn); + return 0; + } else if (is_fault_pfn(pfn)) + return -EFAULT; + + return 1; +} + static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) { int r; @@ -1998,10 +2150,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) pfn = gfn_to_pfn(vcpu->kvm, gfn); /* mmio */ - if (is_error_pfn(pfn)) { - kvm_release_pfn_clean(pfn); - return 1; - } + if (is_error_pfn(pfn)) + return kvm_handle_bad_page(vcpu->kvm, gfn, pfn); spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu, mmu_seq)) @@ -2024,6 +2174,7 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) { int i; struct kvm_mmu_page *sp; + LIST_HEAD(invalid_list); if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; @@ -2033,8 +2184,10 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) sp = page_header(root); --sp->root_count; - if (!sp->root_count && sp->role.invalid) - kvm_mmu_zap_page(vcpu->kvm, sp); + if (!sp->root_count && sp->role.invalid) { + kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); + } vcpu->arch.mmu.root_hpa = INVALID_PAGE; spin_unlock(&vcpu->kvm->mmu_lock); return; @@ -2047,10 +2200,12 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) sp = page_header(root); --sp->root_count; if (!sp->root_count && sp->role.invalid) - kvm_mmu_zap_page(vcpu->kvm, sp); + kvm_mmu_prepare_zap_page(vcpu->kvm, sp, + &invalid_list); } vcpu->arch.mmu.pae_root[i] = INVALID_PAGE; } + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); spin_unlock(&vcpu->kvm->mmu_lock); vcpu->arch.mmu.root_hpa = INVALID_PAGE; } @@ -2060,7 +2215,7 @@ static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn) int ret = 0; if (!kvm_is_visible_gfn(vcpu->kvm, root_gfn)) { - set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests); + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); ret = 1; } @@ -2081,21 +2236,24 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu) hpa_t root = vcpu->arch.mmu.root_hpa; ASSERT(!VALID_PAGE(root)); - if (tdp_enabled) - direct = 1; if (mmu_check_root(vcpu, root_gfn)) return 1; + if (tdp_enabled) { + direct = 1; + root_gfn = 0; + } + spin_lock(&vcpu->kvm->mmu_lock); + kvm_mmu_free_some_pages(vcpu); sp = kvm_mmu_get_page(vcpu, root_gfn, 0, PT64_ROOT_LEVEL, direct, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; + spin_unlock(&vcpu->kvm->mmu_lock); vcpu->arch.mmu.root_hpa = root; return 0; } direct = !is_paging(vcpu); - if (tdp_enabled) - direct = 1; for (i = 0; i < 4; ++i) { hpa_t root = vcpu->arch.mmu.pae_root[i]; @@ -2111,11 +2269,19 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu) root_gfn = 0; if (mmu_check_root(vcpu, root_gfn)) return 1; + if (tdp_enabled) { + direct = 1; + root_gfn = i << 30; + } + spin_lock(&vcpu->kvm->mmu_lock); + kvm_mmu_free_some_pages(vcpu); sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL, direct, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; + spin_unlock(&vcpu->kvm->mmu_lock); + vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK; } vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root); @@ -2204,10 +2370,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); pfn = gfn_to_pfn(vcpu->kvm, gfn); - if (is_error_pfn(pfn)) { - kvm_release_pfn_clean(pfn); - return 1; - } + if (is_error_pfn(pfn)) + return kvm_handle_bad_page(vcpu->kvm, gfn, pfn); spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu, mmu_seq)) goto out_unlock; @@ -2249,7 +2413,7 @@ static int nonpaging_init_context(struct kvm_vcpu *vcpu) void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; - kvm_x86_ops->tlb_flush(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } static void paging_new_cr3(struct kvm_vcpu *vcpu) @@ -2299,13 +2463,19 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level) /* no rsvd bits for 2 level 4K page table entries */ context->rsvd_bits_mask[0][1] = 0; context->rsvd_bits_mask[0][0] = 0; + context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + + if (!is_pse(vcpu)) { + context->rsvd_bits_mask[1][1] = 0; + break; + } + if (is_cpuid_PSE36()) /* 36bits PSE 4MB page */ context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21); else /* 32 bits PSE 4MB page */ context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21); - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0]; break; case PT32E_ROOT_LEVEL: context->rsvd_bits_mask[0][2] = @@ -2318,7 +2488,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level) context->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62) | rsvd_bits(13, 20); /* large page */ - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0]; + context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; break; case PT64_ROOT_LEVEL: context->rsvd_bits_mask[0][3] = exb_bit_rsvd | @@ -2336,7 +2506,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level) context->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 20); /* large page */ - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0]; + context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; break; } } @@ -2438,7 +2608,8 @@ static int init_kvm_softmmu(struct kvm_vcpu *vcpu) else r = paging32_init_context(vcpu); - vcpu->arch.mmu.base_role.glevels = vcpu->arch.mmu.root_level; + vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu); + vcpu->arch.mmu.base_role.cr0_wp = is_write_protection(vcpu); return r; } @@ -2456,10 +2627,9 @@ static int init_kvm_mmu(struct kvm_vcpu *vcpu) static void destroy_kvm_mmu(struct kvm_vcpu *vcpu) { ASSERT(vcpu); - if (VALID_PAGE(vcpu->arch.mmu.root_hpa)) { + if (VALID_PAGE(vcpu->arch.mmu.root_hpa)) + /* mmu.free() should set root_hpa = INVALID_PAGE */ vcpu->arch.mmu.free(vcpu); - vcpu->arch.mmu.root_hpa = INVALID_PAGE; - } } int kvm_mmu_reset_context(struct kvm_vcpu *vcpu) @@ -2476,9 +2646,8 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) r = mmu_topup_memory_caches(vcpu); if (r) goto out; - spin_lock(&vcpu->kvm->mmu_lock); - kvm_mmu_free_some_pages(vcpu); r = mmu_alloc_roots(vcpu); + spin_lock(&vcpu->kvm->mmu_lock); mmu_sync_roots(vcpu); spin_unlock(&vcpu->kvm->mmu_lock); if (r) @@ -2505,7 +2674,7 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu, pte = *spte; if (is_shadow_present_pte(pte)) { if (is_last_spte(pte, sp->role.level)) - rmap_remove(vcpu->kvm, spte); + drop_spte(vcpu->kvm, spte, shadow_trap_nonpresent_pte); else { child = page_header(pte & PT64_BASE_ADDR_MASK); mmu_page_remove_parent_pte(child, spte); @@ -2526,8 +2695,11 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, return; } + if (is_rsvd_bits_set(vcpu, *(u64 *)new, PT_PAGE_TABLE_LEVEL)) + return; + ++vcpu->kvm->stat.mmu_pte_updated; - if (sp->role.glevels == PT32_ROOT_LEVEL) + if (!sp->role.cr4_pae) paging32_update_pte(vcpu, sp, spte, new); else paging64_update_pte(vcpu, sp, spte, new); @@ -2546,11 +2718,15 @@ static bool need_remote_flush(u64 old, u64 new) return (old & ~new & PT64_PERM_MASK) != 0; } -static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, u64 old, u64 new) +static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page, + bool remote_flush, bool local_flush) { - if (need_remote_flush(old, new)) + if (zap_page) + return; + + if (remote_flush) kvm_flush_remote_tlbs(vcpu->kvm); - else + else if (local_flush) kvm_mmu_flush_tlb(vcpu); } @@ -2562,36 +2738,11 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu) } static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes) + u64 gpte) { gfn_t gfn; - int r; - u64 gpte = 0; pfn_t pfn; - if (bytes != 4 && bytes != 8) - return; - - /* - * Assume that the pte write on a page table of the same type - * as the current vcpu paging mode. This is nearly always true - * (might be false while changing modes). Note it is verified later - * by update_pte(). - */ - if (is_pae(vcpu)) { - /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ - if ((bytes == 4) && (gpa % 4 == 0)) { - r = kvm_read_guest(vcpu->kvm, gpa & ~(u64)7, &gpte, 8); - if (r) - return; - memcpy((void *)&gpte + (gpa % 8), new, 4); - } else if ((bytes == 8) && (gpa % 8 == 0)) { - memcpy((void *)&gpte, new, 8); - } - } else { - if ((bytes == 4) && (gpa % 4 == 0)) - memcpy((void *)&gpte, new, 4); - } if (!is_present_gpte(gpte)) return; gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; @@ -2625,10 +2776,10 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, bool guest_initiated) { gfn_t gfn = gpa >> PAGE_SHIFT; + union kvm_mmu_page_role mask = { .word = 0 }; struct kvm_mmu_page *sp; - struct hlist_node *node, *n; - struct hlist_head *bucket; - unsigned index; + struct hlist_node *node; + LIST_HEAD(invalid_list); u64 entry, gentry; u64 *spte; unsigned offset = offset_in_page(gpa); @@ -2640,10 +2791,49 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, int flooded = 0; int npte; int r; + int invlpg_counter; + bool remote_flush, local_flush, zap_page; + + zap_page = remote_flush = local_flush = false; pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); - mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes); + + invlpg_counter = atomic_read(&vcpu->kvm->arch.invlpg_counter); + + /* + * Assume that the pte write on a page table of the same type + * as the current vcpu paging mode. This is nearly always true + * (might be false while changing modes). Note it is verified later + * by update_pte(). + */ + if ((is_pae(vcpu) && bytes == 4) || !new) { + /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ + if (is_pae(vcpu)) { + gpa &= ~(gpa_t)7; + bytes = 8; + } + r = kvm_read_guest(vcpu->kvm, gpa, &gentry, min(bytes, 8)); + if (r) + gentry = 0; + new = (const u8 *)&gentry; + } + + switch (bytes) { + case 4: + gentry = *(const u32 *)new; + break; + case 8: + gentry = *(const u64 *)new; + break; + default: + gentry = 0; + break; + } + + mmu_guess_page_from_pte_write(vcpu, gpa, gentry); spin_lock(&vcpu->kvm->mmu_lock); + if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter) + gentry = 0; kvm_mmu_access_page(vcpu, gfn); kvm_mmu_free_some_pages(vcpu); ++vcpu->kvm->stat.mmu_pte_write; @@ -2660,12 +2850,10 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, vcpu->arch.last_pte_updated = NULL; } } - index = kvm_page_table_hashfn(gfn); - bucket = &vcpu->kvm->arch.mmu_page_hash[index]; - hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) { - if (sp->gfn != gfn || sp->role.direct || sp->role.invalid) - continue; - pte_size = sp->role.glevels == PT32_ROOT_LEVEL ? 4 : 8; + + mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; + for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) { + pte_size = sp->role.cr4_pae ? 8 : 4; misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); misaligned |= bytes < 4; if (misaligned || flooded) { @@ -2681,15 +2869,15 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, */ pgprintk("misaligned: gpa %llx bytes %d role %x\n", gpa, bytes, sp->role.word); - if (kvm_mmu_zap_page(vcpu->kvm, sp)) - n = bucket->first; + zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp, + &invalid_list); ++vcpu->kvm->stat.mmu_flooded; continue; } page_offset = offset; level = sp->role.level; npte = 1; - if (sp->role.glevels == PT32_ROOT_LEVEL) { + if (!sp->role.cr4_pae) { page_offset <<= 1; /* 32->64 */ /* * A 32-bit pde maps 4MB while the shadow pdes map @@ -2706,25 +2894,22 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, if (quadrant != sp->role.quadrant) continue; } + local_flush = true; spte = &sp->spt[page_offset / sizeof(*spte)]; - if ((gpa & (pte_size - 1)) || (bytes < pte_size)) { - gentry = 0; - r = kvm_read_guest_atomic(vcpu->kvm, - gpa & ~(u64)(pte_size - 1), - &gentry, pte_size); - new = (const void *)&gentry; - if (r < 0) - new = NULL; - } while (npte--) { entry = *spte; mmu_pte_write_zap_pte(vcpu, sp, spte); - if (new) - mmu_pte_write_new_pte(vcpu, sp, spte, new); - mmu_pte_write_flush_tlb(vcpu, entry, *spte); + if (gentry && + !((sp->role.word ^ vcpu->arch.mmu.base_role.word) + & mask.word)) + mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); + if (!remote_flush && need_remote_flush(entry, *spte)) + remote_flush = true; ++spte; } } + mmu_pte_write_flush_tlb(vcpu, zap_page, remote_flush, local_flush); + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); kvm_mmu_audit(vcpu, "post pte write"); spin_unlock(&vcpu->kvm->mmu_lock); if (!is_error_pfn(vcpu->arch.update_pte.pfn)) { @@ -2752,15 +2937,21 @@ EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) { - while (vcpu->kvm->arch.n_free_mmu_pages < KVM_REFILL_PAGES && + int free_pages; + LIST_HEAD(invalid_list); + + free_pages = vcpu->kvm->arch.n_free_mmu_pages; + while (free_pages < KVM_REFILL_PAGES && !list_empty(&vcpu->kvm->arch.active_mmu_pages)) { struct kvm_mmu_page *sp; sp = container_of(vcpu->kvm->arch.active_mmu_pages.prev, struct kvm_mmu_page, link); - kvm_mmu_zap_page(vcpu->kvm, sp); + free_pages += kvm_mmu_prepare_zap_page(vcpu->kvm, sp, + &invalid_list); ++vcpu->kvm->stat.mmu_recycled; } + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); } int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code) @@ -2788,11 +2979,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code) return 1; case EMULATE_DO_MMIO: ++vcpu->stat.mmio_exits; - return 0; + /* fall through */ case EMULATE_FAIL: - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; return 0; default: BUG(); @@ -2889,7 +3077,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) pt = sp->spt; for (i = 0; i < PT64_ENT_PER_PAGE; ++i) /* avoid RMW */ - if (pt[i] & PT_WRITABLE_MASK) + if (is_writable_pte(pt[i])) pt[i] &= ~PT_WRITABLE_MASK; } kvm_flush_remote_tlbs(kvm); @@ -2898,27 +3086,29 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) void kvm_mmu_zap_all(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; + LIST_HEAD(invalid_list); spin_lock(&kvm->mmu_lock); +restart: list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) - if (kvm_mmu_zap_page(kvm, sp)) - node = container_of(kvm->arch.active_mmu_pages.next, - struct kvm_mmu_page, link); - spin_unlock(&kvm->mmu_lock); + if (kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list)) + goto restart; - kvm_flush_remote_tlbs(kvm); + kvm_mmu_commit_zap_page(kvm, &invalid_list); + spin_unlock(&kvm->mmu_lock); } -static void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm) +static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm, + struct list_head *invalid_list) { struct kvm_mmu_page *page; page = container_of(kvm->arch.active_mmu_pages.prev, struct kvm_mmu_page, link); - kvm_mmu_zap_page(kvm, page); + return kvm_mmu_prepare_zap_page(kvm, page, invalid_list); } -static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask) +static int mmu_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) { struct kvm *kvm; struct kvm *kvm_freed = NULL; @@ -2927,7 +3117,8 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask) spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { - int npages, idx; + int npages, idx, freed_pages; + LIST_HEAD(invalid_list); idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); @@ -2935,12 +3126,14 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask) kvm->arch.n_free_mmu_pages; cache_count += npages; if (!kvm_freed && nr_to_scan > 0 && npages > 0) { - kvm_mmu_remove_one_alloc_mmu_page(kvm); - cache_count--; + freed_pages = kvm_mmu_remove_some_alloc_mmu_pages(kvm, + &invalid_list); + cache_count -= freed_pages; kvm_freed = kvm; } nr_to_scan--; + kvm_mmu_commit_zap_page(kvm, &invalid_list); spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); } @@ -3011,7 +3204,8 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) unsigned int nr_pages = 0; struct kvm_memslots *slots; - slots = rcu_dereference(kvm->memslots); + slots = kvm_memslots(kvm); + for (i = 0; i < slots->nmemslots; i++) nr_pages += slots->memslots[i].npages; @@ -3065,7 +3259,7 @@ static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu, static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu) { - kvm_set_cr3(vcpu, vcpu->arch.cr3); + (void)kvm_set_cr3(vcpu, vcpu->arch.cr3); return 1; } @@ -3174,8 +3368,7 @@ static gva_t canonicalize(gva_t gva) } -typedef void (*inspect_spte_fn) (struct kvm *kvm, struct kvm_mmu_page *sp, - u64 *sptep); +typedef void (*inspect_spte_fn) (struct kvm *kvm, u64 *sptep); static void __mmu_spte_walk(struct kvm *kvm, struct kvm_mmu_page *sp, inspect_spte_fn fn) @@ -3191,7 +3384,7 @@ static void __mmu_spte_walk(struct kvm *kvm, struct kvm_mmu_page *sp, child = page_header(ent & PT64_BASE_ADDR_MASK); __mmu_spte_walk(kvm, child, fn); } else - fn(kvm, sp, &sp->spt[i]); + fn(kvm, &sp->spt[i]); } } } @@ -3282,11 +3475,13 @@ static void audit_mappings(struct kvm_vcpu *vcpu) static int count_rmaps(struct kvm_vcpu *vcpu) { + struct kvm *kvm = vcpu->kvm; + struct kvm_memslots *slots; int nmaps = 0; int i, j, k, idx; idx = srcu_read_lock(&kvm->srcu); - slots = rcu_dereference(kvm->memslots); + slots = kvm_memslots(kvm); for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { struct kvm_memory_slot *m = &slots->memslots[i]; struct kvm_rmap_desc *d; @@ -3315,15 +3510,15 @@ static int count_rmaps(struct kvm_vcpu *vcpu) return nmaps; } -void inspect_spte_has_rmap(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *sptep) +void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) { unsigned long *rmapp; struct kvm_mmu_page *rev_sp; gfn_t gfn; - if (*sptep & PT_WRITABLE_MASK) { + if (is_writable_pte(*sptep)) { rev_sp = page_header(__pa(sptep)); - gfn = rev_sp->gfns[sptep - rev_sp->spt]; + gfn = kvm_mmu_page_get_gfn(rev_sp, sptep - rev_sp->spt); if (!gfn_to_memslot(kvm, gfn)) { if (!printk_ratelimit()) @@ -3331,14 +3526,13 @@ void inspect_spte_has_rmap(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *sptep) printk(KERN_ERR "%s: no memslot for gfn %ld\n", audit_msg, gfn); printk(KERN_ERR "%s: index %ld of sp (gfn=%lx)\n", - audit_msg, sptep - rev_sp->spt, + audit_msg, (long int)(sptep - rev_sp->spt), rev_sp->gfn); dump_stack(); return; } - rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt], - is_large_pte(*sptep)); + rmapp = gfn_to_rmap(kvm, gfn, rev_sp->role.level); if (!*rmapp) { if (!printk_ratelimit()) return; @@ -3371,9 +3565,9 @@ static void check_writable_mappings_rmap(struct kvm_vcpu *vcpu) if (!(ent & PT_PRESENT_MASK)) continue; - if (!(ent & PT_WRITABLE_MASK)) + if (!is_writable_pte(ent)) continue; - inspect_spte_has_rmap(vcpu->kvm, sp, &pt[i]); + inspect_spte_has_rmap(vcpu->kvm, &pt[i]); } } return; @@ -3399,13 +3593,12 @@ static void audit_write_protection(struct kvm_vcpu *vcpu) if (sp->unsync) continue; - gfn = unalias_gfn(vcpu->kvm, sp->gfn); - slot = gfn_to_memslot_unaliased(vcpu->kvm, sp->gfn); + slot = gfn_to_memslot(vcpu->kvm, sp->gfn); rmapp = &slot->rmap[gfn - slot->base_gfn]; spte = rmap_next(vcpu->kvm, rmapp, NULL); while (spte) { - if (*spte & PT_WRITABLE_MASK) + if (is_writable_pte(*spte)) printk(KERN_ERR "%s: (%s) shadow page has " "writable mappings: gfn %lx role %x\n", __func__, audit_msg, sp->gfn, diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 3e4a5c6ca2a..3aab0f0930e 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -6,14 +6,12 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvmmmu -#define TRACE_INCLUDE_PATH . -#define TRACE_INCLUDE_FILE mmutrace #define KVM_MMU_PAGE_FIELDS \ __field(__u64, gfn) \ __field(__u32, role) \ __field(__u32, root_count) \ - __field(__u32, unsync) + __field(bool, unsync) #define KVM_MMU_PAGE_ASSIGN(sp) \ __entry->gfn = sp->gfn; \ @@ -30,14 +28,14 @@ \ role.word = __entry->role; \ \ - trace_seq_printf(p, "sp gfn %llx %u/%u q%u%s %s%s %spge" \ + trace_seq_printf(p, "sp gfn %llx %u%s q%u%s %s%s" \ " %snxe root %u %s%c", \ - __entry->gfn, role.level, role.glevels, \ + __entry->gfn, role.level, \ + role.cr4_pae ? " pae" : "", \ role.quadrant, \ role.direct ? " direct" : "", \ access_str[role.access], \ role.invalid ? " invalid" : "", \ - role.cr4_pge ? "" : "!", \ role.nxe ? "" : "!", \ __entry->root_count, \ __entry->unsync ? "unsync" : "sync", 0); \ @@ -94,15 +92,15 @@ TRACE_EVENT( TP_printk("pte %llx level %u", __entry->pte, __entry->level) ); -/* We set a pte accessed bit */ -TRACE_EVENT( - kvm_mmu_set_accessed_bit, +DECLARE_EVENT_CLASS(kvm_mmu_set_bit_class, + TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size), + TP_ARGS(table_gfn, index, size), TP_STRUCT__entry( __field(__u64, gpa) - ), + ), TP_fast_assign( __entry->gpa = ((u64)table_gfn << PAGE_SHIFT) @@ -112,22 +110,20 @@ TRACE_EVENT( TP_printk("gpa %llx", __entry->gpa) ); -/* We set a pte dirty bit */ -TRACE_EVENT( - kvm_mmu_set_dirty_bit, +/* We set a pte accessed bit */ +DEFINE_EVENT(kvm_mmu_set_bit_class, kvm_mmu_set_accessed_bit, + TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size), - TP_ARGS(table_gfn, index, size), - TP_STRUCT__entry( - __field(__u64, gpa) - ), + TP_ARGS(table_gfn, index, size) +); - TP_fast_assign( - __entry->gpa = ((u64)table_gfn << PAGE_SHIFT) - + index * size; - ), +/* We set a pte dirty bit */ +DEFINE_EVENT(kvm_mmu_set_bit_class, kvm_mmu_set_dirty_bit, - TP_printk("gpa %llx", __entry->gpa) + TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size), + + TP_ARGS(table_gfn, index, size) ); TRACE_EVENT( @@ -166,55 +162,45 @@ TRACE_EVENT( __entry->created ? "new" : "existing") ); -TRACE_EVENT( - kvm_mmu_sync_page, +DECLARE_EVENT_CLASS(kvm_mmu_page_class, + TP_PROTO(struct kvm_mmu_page *sp), TP_ARGS(sp), TP_STRUCT__entry( KVM_MMU_PAGE_FIELDS - ), + ), TP_fast_assign( KVM_MMU_PAGE_ASSIGN(sp) - ), + ), TP_printk("%s", KVM_MMU_PAGE_PRINTK()) ); -TRACE_EVENT( - kvm_mmu_unsync_page, +DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_sync_page, TP_PROTO(struct kvm_mmu_page *sp), - TP_ARGS(sp), - - TP_STRUCT__entry( - KVM_MMU_PAGE_FIELDS - ), - TP_fast_assign( - KVM_MMU_PAGE_ASSIGN(sp) - ), - - TP_printk("%s", KVM_MMU_PAGE_PRINTK()) + TP_ARGS(sp) ); -TRACE_EVENT( - kvm_mmu_zap_page, +DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_unsync_page, TP_PROTO(struct kvm_mmu_page *sp), - TP_ARGS(sp), - TP_STRUCT__entry( - KVM_MMU_PAGE_FIELDS - ), + TP_ARGS(sp) +); - TP_fast_assign( - KVM_MMU_PAGE_ASSIGN(sp) - ), +DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_prepare_zap_page, + TP_PROTO(struct kvm_mmu_page *sp), - TP_printk("%s", KVM_MMU_PAGE_PRINTK()) + TP_ARGS(sp) ); - #endif /* _TRACE_KVMMMU_H */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE mmutrace + /* This part must be outside protection */ #include <trace/define_trace.h> diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 81eab9a50e6..51ef9097960 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -7,6 +7,7 @@ * MMU support * * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affilates. * * Authors: * Yaniv Kamay <yaniv@qumranet.com> @@ -118,21 +119,25 @@ static int FNAME(walk_addr)(struct guest_walker *walker, { pt_element_t pte; gfn_t table_gfn; - unsigned index, pt_access, pte_access; + unsigned index, pt_access, uninitialized_var(pte_access); gpa_t pte_gpa; - int rsvd_fault = 0; + bool eperm, present, rsvd_fault; trace_kvm_mmu_pagetable_walk(addr, write_fault, user_fault, fetch_fault); walk: + present = true; + eperm = rsvd_fault = false; walker->level = vcpu->arch.mmu.root_level; pte = vcpu->arch.cr3; #if PTTYPE == 64 if (!is_long_mode(vcpu)) { pte = kvm_pdptr_read(vcpu, (addr >> 30) & 3); trace_kvm_mmu_paging_element(pte, walker->level); - if (!is_present_gpte(pte)) - goto not_present; + if (!is_present_gpte(pte)) { + present = false; + goto error; + } --walker->level; } #endif @@ -150,37 +155,42 @@ walk: walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; - if (kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte))) - goto not_present; + if (kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte))) { + present = false; + break; + } trace_kvm_mmu_paging_element(pte, walker->level); - if (!is_present_gpte(pte)) - goto not_present; + if (!is_present_gpte(pte)) { + present = false; + break; + } - rsvd_fault = is_rsvd_bits_set(vcpu, pte, walker->level); - if (rsvd_fault) - goto access_error; + if (is_rsvd_bits_set(vcpu, pte, walker->level)) { + rsvd_fault = true; + break; + } if (write_fault && !is_writable_pte(pte)) if (user_fault || is_write_protection(vcpu)) - goto access_error; + eperm = true; if (user_fault && !(pte & PT_USER_MASK)) - goto access_error; + eperm = true; #if PTTYPE == 64 - if (fetch_fault && is_nx(vcpu) && (pte & PT64_NX_MASK)) - goto access_error; + if (fetch_fault && (pte & PT64_NX_MASK)) + eperm = true; #endif - if (!(pte & PT_ACCESSED_MASK)) { + if (!eperm && !rsvd_fault && !(pte & PT_ACCESSED_MASK)) { trace_kvm_mmu_set_accessed_bit(table_gfn, index, sizeof(pte)); - mark_page_dirty(vcpu->kvm, table_gfn); if (FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, index, pte, pte|PT_ACCESSED_MASK)) goto walk; + mark_page_dirty(vcpu->kvm, table_gfn); pte |= PT_ACCESSED_MASK; } @@ -190,10 +200,10 @@ walk: if ((walker->level == PT_PAGE_TABLE_LEVEL) || ((walker->level == PT_DIRECTORY_LEVEL) && - (pte & PT_PAGE_SIZE_MASK) && + is_large_pte(pte) && (PTTYPE == 64 || is_pse(vcpu))) || ((walker->level == PT_PDPE_LEVEL) && - (pte & PT_PAGE_SIZE_MASK) && + is_large_pte(pte) && is_long_mode(vcpu))) { int lvl = walker->level; @@ -213,15 +223,18 @@ walk: --walker->level; } + if (!present || eperm || rsvd_fault) + goto error; + if (write_fault && !is_dirty_gpte(pte)) { bool ret; trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte)); - mark_page_dirty(vcpu->kvm, table_gfn); ret = FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, index, pte, pte|PT_DIRTY_MASK); if (ret) goto walk; + mark_page_dirty(vcpu->kvm, table_gfn); pte |= PT_DIRTY_MASK; walker->ptes[walker->level - 1] = pte; } @@ -229,22 +242,18 @@ walk: walker->pt_access = pt_access; walker->pte_access = pte_access; pgprintk("%s: pte %llx pte_access %x pt_access %x\n", - __func__, (u64)pte, pt_access, pte_access); + __func__, (u64)pte, pte_access, pt_access); return 1; -not_present: +error: walker->error_code = 0; - goto err; - -access_error: - walker->error_code = PFERR_PRESENT_MASK; - -err: + if (present) + walker->error_code |= PFERR_PRESENT_MASK; if (write_fault) walker->error_code |= PFERR_WRITE_MASK; if (user_fault) walker->error_code |= PFERR_USER_MASK; - if (fetch_fault) + if (fetch_fault && is_nx(vcpu)) walker->error_code |= PFERR_FETCH_MASK; if (rsvd_fault) walker->error_code |= PFERR_RSVD_MASK; @@ -252,21 +261,27 @@ err: return 0; } -static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, +static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, const void *pte) { pt_element_t gpte; unsigned pte_access; pfn_t pfn; + u64 new_spte; gpte = *(const pt_element_t *)pte; if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) { - if (!is_present_gpte(gpte)) - __set_spte(spte, shadow_notrap_nonpresent_pte); + if (!is_present_gpte(gpte)) { + if (sp->unsync) + new_spte = shadow_trap_nonpresent_pte; + else + new_spte = shadow_notrap_nonpresent_pte; + __set_spte(spte, new_spte); + } return; } pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte); - pte_access = page->role.access & FNAME(gpte_access)(vcpu, gpte); + pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte); if (gpte_to_gfn(gpte) != vcpu->arch.update_pte.gfn) return; pfn = vcpu->arch.update_pte.pfn; @@ -279,11 +294,22 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, * we call mmu_set_spte() with reset_host_protection = true beacuse that * vcpu->arch.update_pte.pfn was fetched from get_user_pages(write = 1). */ - mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0, - gpte & PT_DIRTY_MASK, NULL, PT_PAGE_TABLE_LEVEL, + mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0, + is_dirty_gpte(gpte), NULL, PT_PAGE_TABLE_LEVEL, gpte_to_gfn(gpte), pfn, true, true); } +static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu, + struct guest_walker *gw, int level) +{ + int r; + pt_element_t curr_pte; + + r = kvm_read_guest_atomic(vcpu->kvm, gw->pte_gpa[level - 1], + &curr_pte, sizeof(curr_pte)); + return r || curr_pte != gw->ptes[level - 1]; +} + /* * Fetch a shadow pte for a specific level in the paging hierarchy. */ @@ -293,74 +319,86 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, int *ptwrite, pfn_t pfn) { unsigned access = gw->pt_access; - struct kvm_mmu_page *shadow_page; - u64 spte, *sptep = NULL; - int direct; - gfn_t table_gfn; - int r; - int level; - pt_element_t curr_pte; - struct kvm_shadow_walk_iterator iterator; + struct kvm_mmu_page *sp = NULL; + bool dirty = is_dirty_gpte(gw->ptes[gw->level - 1]); + int top_level; + unsigned direct_access; + struct kvm_shadow_walk_iterator it; if (!is_present_gpte(gw->ptes[gw->level - 1])) return NULL; - for_each_shadow_entry(vcpu, addr, iterator) { - level = iterator.level; - sptep = iterator.sptep; - if (iterator.level == hlevel) { - mmu_set_spte(vcpu, sptep, access, - gw->pte_access & access, - user_fault, write_fault, - gw->ptes[gw->level-1] & PT_DIRTY_MASK, - ptwrite, level, - gw->gfn, pfn, false, true); - break; - } + direct_access = gw->pt_access & gw->pte_access; + if (!dirty) + direct_access &= ~ACC_WRITE_MASK; - if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) - continue; + top_level = vcpu->arch.mmu.root_level; + if (top_level == PT32E_ROOT_LEVEL) + top_level = PT32_ROOT_LEVEL; + /* + * Verify that the top-level gpte is still there. Since the page + * is a root page, it is either write protected (and cannot be + * changed from now on) or it is invalid (in which case, we don't + * really care if it changes underneath us after this point). + */ + if (FNAME(gpte_changed)(vcpu, gw, top_level)) + goto out_gpte_changed; - if (is_large_pte(*sptep)) { - rmap_remove(vcpu->kvm, sptep); - __set_spte(sptep, shadow_trap_nonpresent_pte); - kvm_flush_remote_tlbs(vcpu->kvm); - } + for (shadow_walk_init(&it, vcpu, addr); + shadow_walk_okay(&it) && it.level > gw->level; + shadow_walk_next(&it)) { + gfn_t table_gfn; - if (level <= gw->level) { - int delta = level - gw->level + 1; - direct = 1; - if (!is_dirty_gpte(gw->ptes[level - delta])) - access &= ~ACC_WRITE_MASK; - table_gfn = gpte_to_gfn(gw->ptes[level - delta]); - /* advance table_gfn when emulating 1gb pages with 4k */ - if (delta == 0) - table_gfn += PT_INDEX(addr, level); - } else { - direct = 0; - table_gfn = gw->table_gfn[level - 2]; - } - shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1, - direct, access, sptep); - if (!direct) { - r = kvm_read_guest_atomic(vcpu->kvm, - gw->pte_gpa[level - 2], - &curr_pte, sizeof(curr_pte)); - if (r || curr_pte != gw->ptes[level - 2]) { - kvm_mmu_put_page(shadow_page, sptep); - kvm_release_pfn_clean(pfn); - sptep = NULL; - break; - } + drop_large_spte(vcpu, it.sptep); + + sp = NULL; + if (!is_shadow_present_pte(*it.sptep)) { + table_gfn = gw->table_gfn[it.level - 2]; + sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1, + false, access, it.sptep); } - spte = __pa(shadow_page->spt) - | PT_PRESENT_MASK | PT_ACCESSED_MASK - | PT_WRITABLE_MASK | PT_USER_MASK; - *sptep = spte; + /* + * Verify that the gpte in the page we've just write + * protected is still there. + */ + if (FNAME(gpte_changed)(vcpu, gw, it.level - 1)) + goto out_gpte_changed; + + if (sp) + link_shadow_page(it.sptep, sp); + } + + for (; + shadow_walk_okay(&it) && it.level > hlevel; + shadow_walk_next(&it)) { + gfn_t direct_gfn; + + validate_direct_spte(vcpu, it.sptep, direct_access); + + drop_large_spte(vcpu, it.sptep); + + if (is_shadow_present_pte(*it.sptep)) + continue; + + direct_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + + sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1, + true, direct_access, it.sptep); + link_shadow_page(it.sptep, sp); } - return sptep; + mmu_set_spte(vcpu, it.sptep, access, gw->pte_access & access, + user_fault, write_fault, dirty, ptwrite, it.level, + gw->gfn, pfn, false, true); + + return it.sptep; + +out_gpte_changed: + if (sp) + kvm_mmu_put_page(sp, it.sptep); + kvm_release_pfn_clean(pfn); + return NULL; } /* @@ -424,11 +462,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, pfn = gfn_to_pfn(vcpu->kvm, walker.gfn); /* mmio */ - if (is_error_pfn(pfn)) { - pgprintk("gfn %lx is mmio\n", walker.gfn); - kvm_release_pfn_clean(pfn); - return 1; - } + if (is_error_pfn(pfn)) + return kvm_handle_bad_page(vcpu->kvm, walker.gfn, pfn); spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu, mmu_seq)) @@ -436,6 +471,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, kvm_mmu_free_some_pages(vcpu); sptep = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault, level, &write_pt, pfn); + (void)sptep; pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __func__, sptep, *sptep, write_pt); @@ -457,6 +493,8 @@ out_unlock: static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) { struct kvm_shadow_walk_iterator iterator; + struct kvm_mmu_page *sp; + gpa_t pte_gpa = -1; int level; u64 *sptep; int need_flush = 0; @@ -467,27 +505,48 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) level = iterator.level; sptep = iterator.sptep; - if (level == PT_PAGE_TABLE_LEVEL || - ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) || - ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) { + sp = page_header(__pa(sptep)); + if (is_last_spte(*sptep, level)) { + int offset, shift; + + if (!sp->unsync) + break; + + shift = PAGE_SHIFT - + (PT_LEVEL_BITS - PT64_LEVEL_BITS) * level; + offset = sp->role.quadrant << shift; + + pte_gpa = (sp->gfn << PAGE_SHIFT) + offset; + pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t); if (is_shadow_present_pte(*sptep)) { - rmap_remove(vcpu->kvm, sptep); if (is_large_pte(*sptep)) --vcpu->kvm->stat.lpages; + drop_spte(vcpu->kvm, sptep, + shadow_trap_nonpresent_pte); need_flush = 1; - } - __set_spte(sptep, shadow_trap_nonpresent_pte); + } else + __set_spte(sptep, shadow_trap_nonpresent_pte); break; } - if (!is_shadow_present_pte(*sptep)) + if (!is_shadow_present_pte(*sptep) || !sp->unsync_children) break; } if (need_flush) kvm_flush_remote_tlbs(vcpu->kvm); + + atomic_inc(&vcpu->kvm->arch.invlpg_counter); + spin_unlock(&vcpu->kvm->mmu_lock); + + if (pte_gpa == -1) + return; + + if (mmu_topup_memory_caches(vcpu)) + return; + kvm_mmu_pte_write(vcpu, pte_gpa, NULL, sizeof(pt_element_t), 0); } static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, @@ -545,44 +604,50 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu, * Using the cached information from sp->gfns is safe because: * - The spte has a reference to the struct page, so the pfn for a given gfn * can't change unless all sptes pointing to it are nuked first. - * - Alias changes zap the entire shadow cache. */ -static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + bool clear_unsync) { int i, offset, nr_present; bool reset_host_protection; + gpa_t first_pte_gpa; offset = nr_present = 0; + /* direct kvm_mmu_page can not be unsync. */ + BUG_ON(sp->role.direct); + if (PTTYPE == 32) offset = sp->role.quadrant << PT64_LEVEL_BITS; + first_pte_gpa = gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t); + for (i = 0; i < PT64_ENT_PER_PAGE; i++) { unsigned pte_access; pt_element_t gpte; gpa_t pte_gpa; - gfn_t gfn = sp->gfns[i]; + gfn_t gfn; if (!is_shadow_present_pte(sp->spt[i])) continue; - pte_gpa = gfn_to_gpa(sp->gfn); - pte_gpa += (i+offset) * sizeof(pt_element_t); + pte_gpa = first_pte_gpa + i * sizeof(pt_element_t); if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, sizeof(pt_element_t))) return -EINVAL; - if (gpte_to_gfn(gpte) != gfn || !is_present_gpte(gpte) || - !(gpte & PT_ACCESSED_MASK)) { + gfn = gpte_to_gfn(gpte); + if (is_rsvd_bits_set(vcpu, gpte, PT_PAGE_TABLE_LEVEL) + || gfn != sp->gfns[i] || !is_present_gpte(gpte) + || !(gpte & PT_ACCESSED_MASK)) { u64 nonpresent; - rmap_remove(vcpu->kvm, &sp->spt[i]); - if (is_present_gpte(gpte)) + if (is_present_gpte(gpte) || !clear_unsync) nonpresent = shadow_trap_nonpresent_pte; else nonpresent = shadow_notrap_nonpresent_pte; - __set_spte(&sp->spt[i], nonpresent); + drop_spte(vcpu->kvm, &sp->spt[i], nonpresent); continue; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 737361fcd50..bc5b9b8d4a3 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -4,6 +4,7 @@ * AMD SVM support * * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affilates. * * Authors: * Yaniv Kamay <yaniv@qumranet.com> @@ -28,6 +29,7 @@ #include <linux/ftrace_event.h> #include <linux/slab.h> +#include <asm/tlbflush.h> #include <asm/desc.h> #include <asm/virtext.h> @@ -44,10 +46,11 @@ MODULE_LICENSE("GPL"); #define SEG_TYPE_LDT 2 #define SEG_TYPE_BUSY_TSS16 3 -#define SVM_FEATURE_NPT (1 << 0) -#define SVM_FEATURE_LBRV (1 << 1) -#define SVM_FEATURE_SVML (1 << 2) -#define SVM_FEATURE_PAUSE_FILTER (1 << 10) +#define SVM_FEATURE_NPT (1 << 0) +#define SVM_FEATURE_LBRV (1 << 1) +#define SVM_FEATURE_SVML (1 << 2) +#define SVM_FEATURE_NRIP (1 << 3) +#define SVM_FEATURE_PAUSE_FILTER (1 << 10) #define NESTED_EXIT_HOST 0 /* Exit handled on host level */ #define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */ @@ -55,6 +58,8 @@ MODULE_LICENSE("GPL"); #define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) +static bool erratum_383_found __read_mostly; + static const u32 host_save_user_msrs[] = { #ifdef CONFIG_X86_64 MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, @@ -70,6 +75,7 @@ struct kvm_vcpu; struct nested_state { struct vmcb *hsave; u64 hsave_msr; + u64 vm_cr_msr; u64 vmcb; /* These are the merged vectors */ @@ -77,6 +83,7 @@ struct nested_state { /* gpa pointers to the real vectors */ u64 vmcb_msrpm; + u64 vmcb_iopm; /* A VMEXIT is required but not yet emulated */ bool exit_required; @@ -91,6 +98,9 @@ struct nested_state { }; +#define MSRPM_OFFSETS 16 +static u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; + struct vcpu_svm { struct kvm_vcpu vcpu; struct vmcb *vmcb; @@ -110,13 +120,39 @@ struct vcpu_svm { struct nested_state nested; bool nmi_singlestep; + + unsigned int3_injected; + unsigned long int3_rip; +}; + +#define MSR_INVALID 0xffffffffU + +static struct svm_direct_access_msrs { + u32 index; /* Index of the MSR */ + bool always; /* True if intercept is always on */ +} direct_access_msrs[] = { + { .index = MSR_STAR, .always = true }, + { .index = MSR_IA32_SYSENTER_CS, .always = true }, +#ifdef CONFIG_X86_64 + { .index = MSR_GS_BASE, .always = true }, + { .index = MSR_FS_BASE, .always = true }, + { .index = MSR_KERNEL_GS_BASE, .always = true }, + { .index = MSR_LSTAR, .always = true }, + { .index = MSR_CSTAR, .always = true }, + { .index = MSR_SYSCALL_MASK, .always = true }, +#endif + { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, + { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, + { .index = MSR_IA32_LASTINTFROMIP, .always = false }, + { .index = MSR_IA32_LASTINTTOIP, .always = false }, + { .index = MSR_INVALID, .always = false }, }; /* enable NPT for AMD64 and X86 with PAE */ #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) static bool npt_enabled = true; #else -static bool npt_enabled = false; +static bool npt_enabled; #endif static int npt = 1; @@ -129,6 +165,7 @@ static void svm_flush_tlb(struct kvm_vcpu *vcpu); static void svm_complete_interrupts(struct vcpu_svm *svm); static int nested_svm_exit_handled(struct vcpu_svm *svm); +static int nested_svm_intercept(struct vcpu_svm *svm); static int nested_svm_vmexit(struct vcpu_svm *svm); static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); @@ -163,8 +200,8 @@ static unsigned long iopm_base; struct kvm_ldttss_desc { u16 limit0; u16 base0; - unsigned base1 : 8, type : 5, dpl : 2, p : 1; - unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8; + unsigned base1:8, type:5, dpl:2, p:1; + unsigned limit1:4, zero0:3, g:1, base2:8; u32 base3; u32 zero1; } __attribute__((packed)); @@ -194,6 +231,27 @@ static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; #define MSRS_RANGE_SIZE 2048 #define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2) +static u32 svm_msrpm_offset(u32 msr) +{ + u32 offset; + int i; + + for (i = 0; i < NUM_MSR_MAPS; i++) { + if (msr < msrpm_ranges[i] || + msr >= msrpm_ranges[i] + MSRS_IN_RANGE) + continue; + + offset = (msr - msrpm_ranges[i]) / 4; /* 4 msrs per u8 */ + offset += (i * MSRS_RANGE_SIZE); /* add range offset */ + + /* Now we have the u8 offset - but need the u32 offset */ + return offset / 4; + } + + /* MSR not in any range */ + return MSR_INVALID; +} + #define MAX_INST_SIZE 15 static inline u32 svm_has(u32 feat) @@ -213,7 +271,7 @@ static inline void stgi(void) static inline void invlpga(unsigned long addr, u32 asid) { - asm volatile (__ex(SVM_INVLPGA) :: "a"(addr), "c"(asid)); + asm volatile (__ex(SVM_INVLPGA) : : "a"(addr), "c"(asid)); } static inline void force_new_asid(struct kvm_vcpu *vcpu) @@ -228,28 +286,11 @@ static inline void flush_guest_tlb(struct kvm_vcpu *vcpu) static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) { + vcpu->arch.efer = efer; if (!npt_enabled && !(efer & EFER_LMA)) efer &= ~EFER_LME; to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; - vcpu->arch.efer = efer; -} - -static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, - bool has_error_code, u32 error_code) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - /* If we are within a nested VM we'd better #VMEXIT and let the - guest handle the exception */ - if (nested_svm_check_exception(svm, nr, has_error_code, error_code)) - return; - - svm->vmcb->control.event_inj = nr - | SVM_EVTINJ_VALID - | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0) - | SVM_EVTINJ_TYPE_EXEPT; - svm->vmcb->control.event_inj_err = error_code; } static int is_external_interrupt(u32 info) @@ -264,7 +305,7 @@ static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) u32 ret = 0; if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) - ret |= X86_SHADOW_INT_STI | X86_SHADOW_INT_MOV_SS; + ret |= KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS; return ret & mask; } @@ -283,6 +324,9 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + if (svm->vmcb->control.next_rip != 0) + svm->next_rip = svm->vmcb->control.next_rip; + if (!svm->next_rip) { if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) != EMULATE_DONE) @@ -297,6 +341,67 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) svm_set_interrupt_shadow(vcpu, 0); } +static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, + bool has_error_code, u32 error_code, + bool reinject) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * If we are within a nested VM we'd better #VMEXIT and let the guest + * handle the exception + */ + if (!reinject && + nested_svm_check_exception(svm, nr, has_error_code, error_code)) + return; + + if (nr == BP_VECTOR && !svm_has(SVM_FEATURE_NRIP)) { + unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu); + + /* + * For guest debugging where we have to reinject #BP if some + * INT3 is guest-owned: + * Emulate nRIP by moving RIP forward. Will fail if injection + * raises a fault that is not intercepted. Still better than + * failing in all cases. + */ + skip_emulated_instruction(&svm->vcpu); + rip = kvm_rip_read(&svm->vcpu); + svm->int3_rip = rip + svm->vmcb->save.cs.base; + svm->int3_injected = rip - old_rip; + } + + svm->vmcb->control.event_inj = nr + | SVM_EVTINJ_VALID + | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0) + | SVM_EVTINJ_TYPE_EXEPT; + svm->vmcb->control.event_inj_err = error_code; +} + +static void svm_init_erratum_383(void) +{ + u32 low, high; + int err; + u64 val; + + if (!cpu_has_amd_erratum(amd_erratum_383)) + return; + + /* Use _safe variants to not break nested virtualization */ + val = native_read_msr_safe(MSR_AMD64_DC_CFG, &err); + if (err) + return; + + val |= (1ULL << 47); + + low = lower_32_bits(val); + high = upper_32_bits(val); + + native_write_msr_safe(MSR_AMD64_DC_CFG, low, high); + + erratum_383_found = true; +} + static int has_svm(void) { const char *msg; @@ -319,7 +424,7 @@ static int svm_hardware_enable(void *garbage) struct svm_cpu_data *sd; uint64_t efer; - struct descriptor_table gdt_descr; + struct desc_ptr gdt_descr; struct desc_struct *gdt; int me = raw_smp_processor_id(); @@ -344,14 +449,16 @@ static int svm_hardware_enable(void *garbage) sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; sd->next_asid = sd->max_asid + 1; - kvm_get_gdt(&gdt_descr); - gdt = (struct desc_struct *)gdt_descr.base; + native_store_gdt(&gdt_descr); + gdt = (struct desc_struct *)gdt_descr.address; sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); wrmsrl(MSR_EFER, efer | EFER_SVME); wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT); + svm_init_erratum_383(); + return 0; } @@ -391,42 +498,98 @@ err_1: } +static bool valid_msr_intercept(u32 index) +{ + int i; + + for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) + if (direct_access_msrs[i].index == index) + return true; + + return false; +} + static void set_msr_interception(u32 *msrpm, unsigned msr, int read, int write) { + u8 bit_read, bit_write; + unsigned long tmp; + u32 offset; + + /* + * If this warning triggers extend the direct_access_msrs list at the + * beginning of the file + */ + WARN_ON(!valid_msr_intercept(msr)); + + offset = svm_msrpm_offset(msr); + bit_read = 2 * (msr & 0x0f); + bit_write = 2 * (msr & 0x0f) + 1; + tmp = msrpm[offset]; + + BUG_ON(offset == MSR_INVALID); + + read ? clear_bit(bit_read, &tmp) : set_bit(bit_read, &tmp); + write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp); + + msrpm[offset] = tmp; +} + +static void svm_vcpu_init_msrpm(u32 *msrpm) +{ int i; - for (i = 0; i < NUM_MSR_MAPS; i++) { - if (msr >= msrpm_ranges[i] && - msr < msrpm_ranges[i] + MSRS_IN_RANGE) { - u32 msr_offset = (i * MSRS_IN_RANGE + msr - - msrpm_ranges[i]) * 2; - - u32 *base = msrpm + (msr_offset / 32); - u32 msr_shift = msr_offset % 32; - u32 mask = ((write) ? 0 : 2) | ((read) ? 0 : 1); - *base = (*base & ~(0x3 << msr_shift)) | - (mask << msr_shift); + memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER)); + + for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) { + if (!direct_access_msrs[i].always) + continue; + + set_msr_interception(msrpm, direct_access_msrs[i].index, 1, 1); + } +} + +static void add_msr_offset(u32 offset) +{ + int i; + + for (i = 0; i < MSRPM_OFFSETS; ++i) { + + /* Offset already in list? */ + if (msrpm_offsets[i] == offset) return; - } + + /* Slot used by another offset? */ + if (msrpm_offsets[i] != MSR_INVALID) + continue; + + /* Add offset to list */ + msrpm_offsets[i] = offset; + + return; } + + /* + * If this BUG triggers the msrpm_offsets table has an overflow. Just + * increase MSRPM_OFFSETS in this case. + */ BUG(); } -static void svm_vcpu_init_msrpm(u32 *msrpm) +static void init_msrpm_offsets(void) { - memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER)); + int i; -#ifdef CONFIG_X86_64 - set_msr_interception(msrpm, MSR_GS_BASE, 1, 1); - set_msr_interception(msrpm, MSR_FS_BASE, 1, 1); - set_msr_interception(msrpm, MSR_KERNEL_GS_BASE, 1, 1); - set_msr_interception(msrpm, MSR_LSTAR, 1, 1); - set_msr_interception(msrpm, MSR_CSTAR, 1, 1); - set_msr_interception(msrpm, MSR_SYSCALL_MASK, 1, 1); -#endif - set_msr_interception(msrpm, MSR_K6_STAR, 1, 1); - set_msr_interception(msrpm, MSR_IA32_SYSENTER_CS, 1, 1); + memset(msrpm_offsets, 0xff, sizeof(msrpm_offsets)); + + for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) { + u32 offset; + + offset = svm_msrpm_offset(direct_access_msrs[i].index); + BUG_ON(offset == MSR_INVALID); + + add_msr_offset(offset); + } } static void svm_enable_lbrv(struct vcpu_svm *svm) @@ -467,6 +630,8 @@ static __init int svm_hardware_setup(void) memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER)); iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; + init_msrpm_offsets(); + if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); @@ -475,7 +640,7 @@ static __init int svm_hardware_setup(void) if (nested) { printk(KERN_INFO "kvm: Nested Virtualization enabled\n"); - kvm_enable_efer_bits(EFER_SVME); + kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE); } for_each_possible_cpu(cpu) { @@ -523,7 +688,7 @@ static void init_seg(struct vmcb_seg *seg) { seg->selector = 0; seg->attrib = SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK | - SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */ + SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */ seg->limit = 0xffff; seg->base = 0; } @@ -543,16 +708,16 @@ static void init_vmcb(struct vcpu_svm *svm) svm->vcpu.fpu_active = 1; - control->intercept_cr_read = INTERCEPT_CR0_MASK | + control->intercept_cr_read = INTERCEPT_CR0_MASK | INTERCEPT_CR3_MASK | INTERCEPT_CR4_MASK; - control->intercept_cr_write = INTERCEPT_CR0_MASK | + control->intercept_cr_write = INTERCEPT_CR0_MASK | INTERCEPT_CR3_MASK | INTERCEPT_CR4_MASK | INTERCEPT_CR8_MASK; - control->intercept_dr_read = INTERCEPT_DR0_MASK | + control->intercept_dr_read = INTERCEPT_DR0_MASK | INTERCEPT_DR1_MASK | INTERCEPT_DR2_MASK | INTERCEPT_DR3_MASK | @@ -561,7 +726,7 @@ static void init_vmcb(struct vcpu_svm *svm) INTERCEPT_DR6_MASK | INTERCEPT_DR7_MASK; - control->intercept_dr_write = INTERCEPT_DR0_MASK | + control->intercept_dr_write = INTERCEPT_DR0_MASK | INTERCEPT_DR1_MASK | INTERCEPT_DR2_MASK | INTERCEPT_DR3_MASK | @@ -575,7 +740,7 @@ static void init_vmcb(struct vcpu_svm *svm) (1 << MC_VECTOR); - control->intercept = (1ULL << INTERCEPT_INTR) | + control->intercept = (1ULL << INTERCEPT_INTR) | (1ULL << INTERCEPT_NMI) | (1ULL << INTERCEPT_SMI) | (1ULL << INTERCEPT_SELECTIVE_CR0) | @@ -636,11 +801,12 @@ static void init_vmcb(struct vcpu_svm *svm) save->rip = 0x0000fff0; svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; - /* This is the guest-visible cr0 value. + /* + * This is the guest-visible cr0 value. * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0. */ svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; - kvm_set_cr0(&svm->vcpu, svm->vcpu.arch.cr0); + (void)kvm_set_cr0(&svm->vcpu, svm->vcpu.arch.cr0); save->cr4 = X86_CR4_PAE; /* rdx = ?? */ @@ -729,6 +895,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm_vcpu_init_msrpm(svm->msrpm); svm->nested.msrpm = page_address(nested_msrpm_pages); + svm_vcpu_init_msrpm(svm->nested.msrpm); svm->vmcb = page_address(page); clear_page(svm->vmcb); @@ -736,13 +903,18 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->asid_generation = 0; init_vmcb(svm); - fx_init(&svm->vcpu); + err = fx_init(&svm->vcpu); + if (err) + goto free_page4; + svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_bsp(&svm->vcpu)) svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; return &svm->vcpu; +free_page4: + __free_page(hsave_page); free_page3: __free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER); free_page2: @@ -882,7 +1054,8 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1; var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1; - /* AMD's VMCB does not have an explicit unusable field, so emulate it + /* + * AMD's VMCB does not have an explicit unusable field, so emulate it * for cross vendor migration purposes by "not present" */ var->unusable = !var->present || (var->type == 0); @@ -918,7 +1091,8 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, var->type |= 0x1; break; case VCPU_SREG_SS: - /* On AMD CPUs sometimes the DB bit in the segment + /* + * On AMD CPUs sometimes the DB bit in the segment * descriptor is left as 1, although the whole segment has * been made unusable. Clear it here to pass an Intel VMX * entry check when cross vendor migrating. @@ -936,36 +1110,36 @@ static int svm_get_cpl(struct kvm_vcpu *vcpu) return save->cpl; } -static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void svm_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { struct vcpu_svm *svm = to_svm(vcpu); - dt->limit = svm->vmcb->save.idtr.limit; - dt->base = svm->vmcb->save.idtr.base; + dt->size = svm->vmcb->save.idtr.limit; + dt->address = svm->vmcb->save.idtr.base; } -static void svm_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void svm_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->save.idtr.limit = dt->limit; - svm->vmcb->save.idtr.base = dt->base ; + svm->vmcb->save.idtr.limit = dt->size; + svm->vmcb->save.idtr.base = dt->address ; } -static void svm_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void svm_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { struct vcpu_svm *svm = to_svm(vcpu); - dt->limit = svm->vmcb->save.gdtr.limit; - dt->base = svm->vmcb->save.gdtr.base; + dt->size = svm->vmcb->save.gdtr.limit; + dt->address = svm->vmcb->save.gdtr.base; } -static void svm_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->save.gdtr.limit = dt->limit; - svm->vmcb->save.gdtr.base = dt->base ; + svm->vmcb->save.gdtr.limit = dt->size; + svm->vmcb->save.gdtr.base = dt->address ; } static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) @@ -978,6 +1152,7 @@ static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) static void update_cr0_intercept(struct vcpu_svm *svm) { + struct vmcb *vmcb = svm->vmcb; ulong gcr0 = svm->vcpu.arch.cr0; u64 *hcr0 = &svm->vmcb->save.cr0; @@ -989,11 +1164,25 @@ static void update_cr0_intercept(struct vcpu_svm *svm) if (gcr0 == *hcr0 && svm->vcpu.fpu_active) { - svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK; - svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK; + vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK; + vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK; + if (is_nested(svm)) { + struct vmcb *hsave = svm->nested.hsave; + + hsave->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK; + hsave->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK; + vmcb->control.intercept_cr_read |= svm->nested.intercept_cr_read; + vmcb->control.intercept_cr_write |= svm->nested.intercept_cr_write; + } } else { svm->vmcb->control.intercept_cr_read |= INTERCEPT_CR0_MASK; svm->vmcb->control.intercept_cr_write |= INTERCEPT_CR0_MASK; + if (is_nested(svm)) { + struct vmcb *hsave = svm->nested.hsave; + + hsave->control.intercept_cr_read |= INTERCEPT_CR0_MASK; + hsave->control.intercept_cr_write |= INTERCEPT_CR0_MASK; + } } } @@ -1001,6 +1190,27 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_svm *svm = to_svm(vcpu); + if (is_nested(svm)) { + /* + * We are here because we run in nested mode, the host kvm + * intercepts cr0 writes but the l1 hypervisor does not. + * But the L1 hypervisor may intercept selective cr0 writes. + * This needs to be checked here. + */ + unsigned long old, new; + + /* Remove bits that would trigger a real cr0 write intercept */ + old = vcpu->arch.cr0 & SVM_CR0_SELECTIVE_MASK; + new = cr0 & SVM_CR0_SELECTIVE_MASK; + + if (old == new) { + /* cr0 write with ts and mp unchanged */ + svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE; + if (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE) + return; + } + } + #ifdef CONFIG_X86_64 if (vcpu->arch.efer & EFER_LME) { if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { @@ -1134,70 +1344,11 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) svm->vmcb->control.asid = sd->next_asid++; } -static int svm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *dest) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - switch (dr) { - case 0 ... 3: - *dest = vcpu->arch.db[dr]; - break; - case 4: - if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) - return EMULATE_FAIL; /* will re-inject UD */ - /* fall through */ - case 6: - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) - *dest = vcpu->arch.dr6; - else - *dest = svm->vmcb->save.dr6; - break; - case 5: - if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) - return EMULATE_FAIL; /* will re-inject UD */ - /* fall through */ - case 7: - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) - *dest = vcpu->arch.dr7; - else - *dest = svm->vmcb->save.dr7; - break; - } - - return EMULATE_DONE; -} - -static int svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value) +static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value) { struct vcpu_svm *svm = to_svm(vcpu); - switch (dr) { - case 0 ... 3: - vcpu->arch.db[dr] = value; - if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) - vcpu->arch.eff_db[dr] = value; - break; - case 4: - if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) - return EMULATE_FAIL; /* will re-inject UD */ - /* fall through */ - case 6: - vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1; - break; - case 5: - if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) - return EMULATE_FAIL; /* will re-inject UD */ - /* fall through */ - case 7: - vcpu->arch.dr7 = (value & DR7_VOLATILE) | DR7_FIXED_1; - if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { - svm->vmcb->save.dr7 = vcpu->arch.dr7; - vcpu->arch.switch_db_regs = (value & DR7_BP_EN_MASK); - } - break; - } - - return EMULATE_DONE; + svm->vmcb->save.dr7 = value; } static int pf_interception(struct vcpu_svm *svm) @@ -1234,7 +1385,7 @@ static int db_interception(struct vcpu_svm *svm) } if (svm->vcpu.guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)){ + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) { kvm_run->exit_reason = KVM_EXIT_DEBUG; kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; @@ -1268,7 +1419,22 @@ static int ud_interception(struct vcpu_svm *svm) static void svm_fpu_activate(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); + u32 excp; + + if (is_nested(svm)) { + u32 h_excp, n_excp; + + h_excp = svm->nested.hsave->control.intercept_exceptions; + n_excp = svm->nested.intercept_exceptions; + h_excp &= ~(1 << NM_VECTOR); + excp = h_excp | n_excp; + } else { + excp = svm->vmcb->control.intercept_exceptions; + excp &= ~(1 << NM_VECTOR); + } + + svm->vmcb->control.intercept_exceptions = excp; + svm->vcpu.fpu_active = 1; update_cr0_intercept(svm); } @@ -1279,8 +1445,59 @@ static int nm_interception(struct vcpu_svm *svm) return 1; } -static int mc_interception(struct vcpu_svm *svm) +static bool is_erratum_383(void) +{ + int err, i; + u64 value; + + if (!erratum_383_found) + return false; + + value = native_read_msr_safe(MSR_IA32_MC0_STATUS, &err); + if (err) + return false; + + /* Bit 62 may or may not be set for this mce */ + value &= ~(1ULL << 62); + + if (value != 0xb600000000010015ULL) + return false; + + /* Clear MCi_STATUS registers */ + for (i = 0; i < 6; ++i) + native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0, 0); + + value = native_read_msr_safe(MSR_IA32_MCG_STATUS, &err); + if (!err) { + u32 low, high; + + value &= ~(1ULL << 2); + low = lower_32_bits(value); + high = upper_32_bits(value); + + native_write_msr_safe(MSR_IA32_MCG_STATUS, low, high); + } + + /* Flush tlb to evict multi-match entries */ + __flush_tlb_all(); + + return true; +} + +static void svm_handle_mce(struct vcpu_svm *svm) { + if (is_erratum_383()) { + /* + * Erratum 383 triggered. Guest state is corrupt so kill the + * guest. + */ + pr_err("KVM: Guest triggered AMD Erratum 383\n"); + + kvm_make_request(KVM_REQ_TRIPLE_FAULT, &svm->vcpu); + + return; + } + /* * On an #MC intercept the MCE handler is not called automatically in * the host. So do it by hand here. @@ -1289,6 +1506,11 @@ static int mc_interception(struct vcpu_svm *svm) "int $0x12\n"); /* not sure if we ever come back to this point */ + return; +} + +static int mc_interception(struct vcpu_svm *svm) +{ return 1; } @@ -1309,29 +1531,23 @@ static int shutdown_interception(struct vcpu_svm *svm) static int io_interception(struct vcpu_svm *svm) { + struct kvm_vcpu *vcpu = &svm->vcpu; u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */ int size, in, string; unsigned port; ++svm->vcpu.stat.io_exits; - - svm->next_rip = svm->vmcb->control.exit_info_2; - string = (io_info & SVM_IOIO_STR_MASK) != 0; - - if (string) { - if (emulate_instruction(&svm->vcpu, - 0, 0, 0) == EMULATE_DO_MMIO) - return 0; - return 1; - } - in = (io_info & SVM_IOIO_TYPE_MASK) != 0; + if (string || in) + return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE; + port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; - + svm->next_rip = svm->vmcb->control.exit_info_2; skip_emulated_instruction(&svm->vcpu); - return kvm_emulate_pio(&svm->vcpu, in, size, port); + + return kvm_fast_pio_out(vcpu, size, port); } static int nmi_interception(struct vcpu_svm *svm) @@ -1384,6 +1600,8 @@ static int nested_svm_check_permissions(struct vcpu_svm *svm) static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code) { + int vmexit; + if (!is_nested(svm)) return 0; @@ -1392,21 +1610,28 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, svm->vmcb->control.exit_info_1 = error_code; svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; - return nested_svm_exit_handled(svm); + vmexit = nested_svm_intercept(svm); + if (vmexit == NESTED_EXIT_DONE) + svm->nested.exit_required = true; + + return vmexit; } -static inline int nested_svm_intr(struct vcpu_svm *svm) +/* This function returns true if it is save to enable the irq window */ +static inline bool nested_svm_intr(struct vcpu_svm *svm) { if (!is_nested(svm)) - return 0; + return true; if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) - return 0; + return true; if (!(svm->vcpu.arch.hflags & HF_HIF_MASK)) - return 0; + return false; - svm->vmcb->control.exit_code = SVM_EXIT_INTR; + svm->vmcb->control.exit_code = SVM_EXIT_INTR; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; if (svm->nested.intercept & 1ULL) { /* @@ -1417,21 +1642,40 @@ static inline int nested_svm_intr(struct vcpu_svm *svm) */ svm->nested.exit_required = true; trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); - return 1; + return false; } - return 0; + return true; +} + +/* This function returns true if it is save to enable the nmi window */ +static inline bool nested_svm_nmi(struct vcpu_svm *svm) +{ + if (!is_nested(svm)) + return true; + + if (!(svm->nested.intercept & (1ULL << INTERCEPT_NMI))) + return true; + + svm->vmcb->control.exit_code = SVM_EXIT_NMI; + svm->nested.exit_required = true; + + return false; } -static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, enum km_type idx) +static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page) { struct page *page; + might_sleep(); + page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT); if (is_error_page(page)) goto error; - return kmap_atomic(page, idx); + *_page = page; + + return kmap(page); error: kvm_release_page_clean(page); @@ -1440,61 +1684,55 @@ error: return NULL; } -static void nested_svm_unmap(void *addr, enum km_type idx) +static void nested_svm_unmap(struct page *page) { - struct page *page; + kunmap(page); + kvm_release_page_dirty(page); +} - if (!addr) - return; +static int nested_svm_intercept_ioio(struct vcpu_svm *svm) +{ + unsigned port; + u8 val, bit; + u64 gpa; - page = kmap_atomic_to_page(addr); + if (!(svm->nested.intercept & (1ULL << INTERCEPT_IOIO_PROT))) + return NESTED_EXIT_HOST; - kunmap_atomic(addr, idx); - kvm_release_page_dirty(page); + port = svm->vmcb->control.exit_info_1 >> 16; + gpa = svm->nested.vmcb_iopm + (port / 8); + bit = port % 8; + val = 0; + + if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, 1)) + val &= (1 << bit); + + return val ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; } -static bool nested_svm_exit_handled_msr(struct vcpu_svm *svm) +static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) { - u32 param = svm->vmcb->control.exit_info_1 & 1; - u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; - bool ret = false; - u32 t0, t1; - u8 *msrpm; + u32 offset, msr, value; + int write, mask; if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT))) - return false; + return NESTED_EXIT_HOST; - msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0); + msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + offset = svm_msrpm_offset(msr); + write = svm->vmcb->control.exit_info_1 & 1; + mask = 1 << ((2 * (msr & 0xf)) + write); - if (!msrpm) - goto out; + if (offset == MSR_INVALID) + return NESTED_EXIT_DONE; - switch (msr) { - case 0 ... 0x1fff: - t0 = (msr * 2) % 8; - t1 = msr / 8; - break; - case 0xc0000000 ... 0xc0001fff: - t0 = (8192 + msr - 0xc0000000) * 2; - t1 = (t0 / 8); - t0 %= 8; - break; - case 0xc0010000 ... 0xc0011fff: - t0 = (16384 + msr - 0xc0010000) * 2; - t1 = (t0 / 8); - t0 %= 8; - break; - default: - ret = true; - goto out; - } - - ret = msrpm[t1] & ((1 << param) << t0); + /* Offset is in 32 bit units but need in 8 bit units */ + offset *= 4; -out: - nested_svm_unmap(msrpm, KM_USER0); + if (kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + offset, &value, 4)) + return NESTED_EXIT_DONE; - return ret; + return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; } static int nested_svm_exit_special(struct vcpu_svm *svm) @@ -1504,17 +1742,21 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) switch (exit_code) { case SVM_EXIT_INTR: case SVM_EXIT_NMI: + case SVM_EXIT_EXCP_BASE + MC_VECTOR: return NESTED_EXIT_HOST; - /* For now we are always handling NPFs when using them */ case SVM_EXIT_NPF: + /* For now we are always handling NPFs when using them */ if (npt_enabled) return NESTED_EXIT_HOST; break; - /* When we're shadowing, trap PFs */ case SVM_EXIT_EXCP_BASE + PF_VECTOR: + /* When we're shadowing, trap PFs */ if (!npt_enabled) return NESTED_EXIT_HOST; break; + case SVM_EXIT_EXCP_BASE + NM_VECTOR: + nm_interception(svm); + break; default: break; } @@ -1525,7 +1767,7 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) /* * If this function returns true, this #vmexit was already handled */ -static int nested_svm_exit_handled(struct vcpu_svm *svm) +static int nested_svm_intercept(struct vcpu_svm *svm) { u32 exit_code = svm->vmcb->control.exit_code; int vmexit = NESTED_EXIT_HOST; @@ -1534,6 +1776,9 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm) case SVM_EXIT_MSR: vmexit = nested_svm_exit_handled_msr(svm); break; + case SVM_EXIT_IOIO: + vmexit = nested_svm_intercept_ioio(svm); + break; case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: { u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0); if (svm->nested.intercept_cr_read & cr_bits) @@ -1564,6 +1809,10 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm) vmexit = NESTED_EXIT_DONE; break; } + case SVM_EXIT_ERR: { + vmexit = NESTED_EXIT_DONE; + break; + } default: { u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR); if (svm->nested.intercept & exit_bits) @@ -1571,9 +1820,17 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm) } } - if (vmexit == NESTED_EXIT_DONE) { + return vmexit; +} + +static int nested_svm_exit_handled(struct vcpu_svm *svm) +{ + int vmexit; + + vmexit = nested_svm_intercept(svm); + + if (vmexit == NESTED_EXIT_DONE) nested_svm_vmexit(svm); - } return vmexit; } @@ -1615,6 +1872,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) struct vmcb *nested_vmcb; struct vmcb *hsave = svm->nested.hsave; struct vmcb *vmcb = svm->vmcb; + struct page *page; trace_kvm_nested_vmexit_inject(vmcb->control.exit_code, vmcb->control.exit_info_1, @@ -1622,10 +1880,13 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) vmcb->control.exit_int_info, vmcb->control.exit_int_info_err); - nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, KM_USER0); + nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, &page); if (!nested_vmcb) return 1; + /* Exit nested SVM mode */ + svm->nested.vmcb = 0; + /* Give the current vmcb to the guest */ disable_gif(svm); @@ -1635,9 +1896,10 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) nested_vmcb->save.ds = vmcb->save.ds; nested_vmcb->save.gdtr = vmcb->save.gdtr; nested_vmcb->save.idtr = vmcb->save.idtr; - if (npt_enabled) - nested_vmcb->save.cr3 = vmcb->save.cr3; + nested_vmcb->save.cr0 = kvm_read_cr0(&svm->vcpu); + nested_vmcb->save.cr3 = svm->vcpu.arch.cr3; nested_vmcb->save.cr2 = vmcb->save.cr2; + nested_vmcb->save.cr4 = svm->vcpu.arch.cr4; nested_vmcb->save.rflags = vmcb->save.rflags; nested_vmcb->save.rip = vmcb->save.rip; nested_vmcb->save.rsp = vmcb->save.rsp; @@ -1700,7 +1962,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) svm->vmcb->save.cr3 = hsave->save.cr3; svm->vcpu.arch.cr3 = hsave->save.cr3; } else { - kvm_set_cr3(&svm->vcpu, hsave->save.cr3); + (void)kvm_set_cr3(&svm->vcpu, hsave->save.cr3); } kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, hsave->save.rax); kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, hsave->save.rsp); @@ -1709,10 +1971,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) svm->vmcb->save.cpl = 0; svm->vmcb->control.exit_int_info = 0; - /* Exit nested SVM mode */ - svm->nested.vmcb = 0; - - nested_svm_unmap(nested_vmcb, KM_USER0); + nested_svm_unmap(page); kvm_mmu_reset_context(&svm->vcpu); kvm_mmu_load(&svm->vcpu); @@ -1722,19 +1981,33 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { - u32 *nested_msrpm; + /* + * This function merges the msr permission bitmaps of kvm and the + * nested vmcb. It is omptimized in that it only merges the parts where + * the kvm msr permission bitmap may contain zero bits + */ int i; - nested_msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0); - if (!nested_msrpm) - return false; + if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT))) + return true; - for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++) - svm->nested.msrpm[i] = svm->msrpm[i] | nested_msrpm[i]; + for (i = 0; i < MSRPM_OFFSETS; i++) { + u32 value, p; + u64 offset; - svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm); + if (msrpm_offsets[i] == 0xffffffff) + break; + + p = msrpm_offsets[i]; + offset = svm->nested.vmcb_msrpm + (p * 4); - nested_svm_unmap(nested_msrpm, KM_USER0); + if (kvm_read_guest(svm->vcpu.kvm, offset, &value, 4)) + return false; + + svm->nested.msrpm[p] = svm->msrpm[p] | value; + } + + svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm); return true; } @@ -1744,26 +2017,34 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) struct vmcb *nested_vmcb; struct vmcb *hsave = svm->nested.hsave; struct vmcb *vmcb = svm->vmcb; + struct page *page; + u64 vmcb_gpa; - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0); + vmcb_gpa = svm->vmcb->save.rax; + + nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); if (!nested_vmcb) return false; - /* nested_vmcb is our indicator if nested SVM is activated */ - svm->nested.vmcb = svm->vmcb->save.rax; - - trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb, + trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, vmcb_gpa, nested_vmcb->save.rip, nested_vmcb->control.int_ctl, nested_vmcb->control.event_inj, nested_vmcb->control.nested_ctl); + trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr_read, + nested_vmcb->control.intercept_cr_write, + nested_vmcb->control.intercept_exceptions, + nested_vmcb->control.intercept); + /* Clear internal status */ kvm_clear_exception_queue(&svm->vcpu); kvm_clear_interrupt_queue(&svm->vcpu); - /* Save the old vmcb, so we don't need to pick what we save, but - can restore everything when a VMEXIT occurs */ + /* + * Save the old vmcb, so we don't need to pick what we save, but can + * restore everything when a VMEXIT occurs + */ hsave->save.es = vmcb->save.es; hsave->save.cs = vmcb->save.cs; hsave->save.ss = vmcb->save.ss; @@ -1803,14 +2084,17 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) if (npt_enabled) { svm->vmcb->save.cr3 = nested_vmcb->save.cr3; svm->vcpu.arch.cr3 = nested_vmcb->save.cr3; - } else { - kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3); - kvm_mmu_reset_context(&svm->vcpu); - } + } else + (void)kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3); + + /* Guest paging mode is active - reset mmu */ + kvm_mmu_reset_context(&svm->vcpu); + svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2; kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax); kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp); kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip); + /* In case we don't even reach vcpu_run, the fields are not updated */ svm->vmcb->save.rax = nested_vmcb->save.rax; svm->vmcb->save.rsp = nested_vmcb->save.rsp; @@ -1819,22 +2103,8 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) svm->vmcb->save.dr6 = nested_vmcb->save.dr6; svm->vmcb->save.cpl = nested_vmcb->save.cpl; - /* We don't want a nested guest to be more powerful than the guest, - so all intercepts are ORed */ - svm->vmcb->control.intercept_cr_read |= - nested_vmcb->control.intercept_cr_read; - svm->vmcb->control.intercept_cr_write |= - nested_vmcb->control.intercept_cr_write; - svm->vmcb->control.intercept_dr_read |= - nested_vmcb->control.intercept_dr_read; - svm->vmcb->control.intercept_dr_write |= - nested_vmcb->control.intercept_dr_write; - svm->vmcb->control.intercept_exceptions |= - nested_vmcb->control.intercept_exceptions; - - svm->vmcb->control.intercept |= nested_vmcb->control.intercept; - - svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa; + svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL; + svm->nested.vmcb_iopm = nested_vmcb->control.iopm_base_pa & ~0x0fffULL; /* cache intercepts */ svm->nested.intercept_cr_read = nested_vmcb->control.intercept_cr_read; @@ -1851,13 +2121,43 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) else svm->vcpu.arch.hflags &= ~HF_VINTR_MASK; + if (svm->vcpu.arch.hflags & HF_VINTR_MASK) { + /* We only want the cr8 intercept bits of the guest */ + svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR8_MASK; + svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK; + } + + /* We don't want to see VMMCALLs from a nested guest */ + svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VMMCALL); + + /* + * We don't want a nested guest to be more powerful than the guest, so + * all intercepts are ORed + */ + svm->vmcb->control.intercept_cr_read |= + nested_vmcb->control.intercept_cr_read; + svm->vmcb->control.intercept_cr_write |= + nested_vmcb->control.intercept_cr_write; + svm->vmcb->control.intercept_dr_read |= + nested_vmcb->control.intercept_dr_read; + svm->vmcb->control.intercept_dr_write |= + nested_vmcb->control.intercept_dr_write; + svm->vmcb->control.intercept_exceptions |= + nested_vmcb->control.intercept_exceptions; + + svm->vmcb->control.intercept |= nested_vmcb->control.intercept; + + svm->vmcb->control.lbr_ctl = nested_vmcb->control.lbr_ctl; svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; svm->vmcb->control.int_state = nested_vmcb->control.int_state; svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset; svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; - nested_svm_unmap(nested_vmcb, KM_USER0); + nested_svm_unmap(page); + + /* nested_vmcb is our indicator if nested SVM is activated */ + svm->nested.vmcb = vmcb_gpa; enable_gif(svm); @@ -1883,6 +2183,7 @@ static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) static int vmload_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; + struct page *page; if (nested_svm_check_permissions(svm)) return 1; @@ -1890,12 +2191,12 @@ static int vmload_interception(struct vcpu_svm *svm) svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0); + nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); if (!nested_vmcb) return 1; nested_svm_vmloadsave(nested_vmcb, svm->vmcb); - nested_svm_unmap(nested_vmcb, KM_USER0); + nested_svm_unmap(page); return 1; } @@ -1903,6 +2204,7 @@ static int vmload_interception(struct vcpu_svm *svm) static int vmsave_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; + struct page *page; if (nested_svm_check_permissions(svm)) return 1; @@ -1910,12 +2212,12 @@ static int vmsave_interception(struct vcpu_svm *svm) svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0); + nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); if (!nested_vmcb) return 1; nested_svm_vmloadsave(svm->vmcb, nested_vmcb); - nested_svm_unmap(nested_vmcb, KM_USER0); + nested_svm_unmap(page); return 1; } @@ -2018,6 +2320,8 @@ static int task_switch_interception(struct vcpu_svm *svm) svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK; uint32_t idt_v = svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID; + bool has_error_code = false; + u32 error_code = 0; tss_selector = (u16)svm->vmcb->control.exit_info_1; @@ -2038,6 +2342,12 @@ static int task_switch_interception(struct vcpu_svm *svm) svm->vcpu.arch.nmi_injected = false; break; case SVM_EXITINTINFO_TYPE_EXEPT: + if (svm->vmcb->control.exit_info_2 & + (1ULL << SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE)) { + has_error_code = true; + error_code = + (u32)svm->vmcb->control.exit_info_2; + } kvm_clear_exception_queue(&svm->vcpu); break; case SVM_EXITINTINFO_TYPE_INTR: @@ -2054,7 +2364,14 @@ static int task_switch_interception(struct vcpu_svm *svm) (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) skip_emulated_instruction(&svm->vcpu); - return kvm_task_switch(&svm->vcpu, tss_selector, reason); + if (kvm_task_switch(&svm->vcpu, tss_selector, reason, + has_error_code, error_code) == EMULATE_FAIL) { + svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + svm->vcpu.run->internal.ndata = 0; + return 0; + } + return 1; } static int cpuid_interception(struct vcpu_svm *svm) @@ -2074,16 +2391,12 @@ static int iret_interception(struct vcpu_svm *svm) static int invlpg_interception(struct vcpu_svm *svm) { - if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE) - pr_unimpl(&svm->vcpu, "%s: failed\n", __func__); - return 1; + return emulate_instruction(&svm->vcpu, 0, 0, 0) == EMULATE_DONE; } static int emulate_on_interception(struct vcpu_svm *svm) { - if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE) - pr_unimpl(&svm->vcpu, "%s: failed\n", __func__); - return 1; + return emulate_instruction(&svm->vcpu, 0, 0, 0) == EMULATE_DONE; } static int cr8_write_interception(struct vcpu_svm *svm) @@ -2119,7 +2432,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) *data = tsc_offset + native_read_tsc(); break; } - case MSR_K6_STAR: + case MSR_STAR: *data = svm->vmcb->save.star; break; #ifdef CONFIG_X86_64 @@ -2145,9 +2458,11 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) case MSR_IA32_SYSENTER_ESP: *data = svm->sysenter_esp; break; - /* Nobody will change the following 5 values in the VMCB so - we can safely return them on rdmsr. They will always be 0 - until LBRV is implemented. */ + /* + * Nobody will change the following 5 values in the VMCB so we can + * safely return them on rdmsr. They will always be 0 until LBRV is + * implemented. + */ case MSR_IA32_DEBUGCTLMSR: *data = svm->vmcb->save.dbgctl; break; @@ -2167,7 +2482,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) *data = svm->nested.hsave_msr; break; case MSR_VM_CR: - *data = 0; + *data = svm->nested.vm_cr_msr; break; case MSR_IA32_UCODE_REV: *data = 0x01000065; @@ -2197,6 +2512,31 @@ static int rdmsr_interception(struct vcpu_svm *svm) return 1; } +static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int svm_dis, chg_mask; + + if (data & ~SVM_VM_CR_VALID_MASK) + return 1; + + chg_mask = SVM_VM_CR_VALID_MASK; + + if (svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK) + chg_mask &= ~(SVM_VM_CR_SVM_LOCK_MASK | SVM_VM_CR_SVM_DIS_MASK); + + svm->nested.vm_cr_msr &= ~chg_mask; + svm->nested.vm_cr_msr |= (data & chg_mask); + + svm_dis = svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK; + + /* check for svm_disable while efer.svme is set */ + if (svm_dis && (vcpu->arch.efer & EFER_SVME)) + return 1; + + return 0; +} + static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) { struct vcpu_svm *svm = to_svm(vcpu); @@ -2216,7 +2556,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) break; } - case MSR_K6_STAR: + case MSR_STAR: svm->vmcb->save.star = data; break; #ifdef CONFIG_X86_64 @@ -2263,6 +2603,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) svm->nested.hsave_msr = data; break; case MSR_VM_CR: + return svm_set_vm_cr(vcpu, data); case MSR_VM_IGNNE: pr_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; @@ -2326,16 +2667,16 @@ static int pause_interception(struct vcpu_svm *svm) } static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { - [SVM_EXIT_READ_CR0] = emulate_on_interception, - [SVM_EXIT_READ_CR3] = emulate_on_interception, - [SVM_EXIT_READ_CR4] = emulate_on_interception, - [SVM_EXIT_READ_CR8] = emulate_on_interception, + [SVM_EXIT_READ_CR0] = emulate_on_interception, + [SVM_EXIT_READ_CR3] = emulate_on_interception, + [SVM_EXIT_READ_CR4] = emulate_on_interception, + [SVM_EXIT_READ_CR8] = emulate_on_interception, [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, - [SVM_EXIT_WRITE_CR0] = emulate_on_interception, - [SVM_EXIT_WRITE_CR3] = emulate_on_interception, - [SVM_EXIT_WRITE_CR4] = emulate_on_interception, - [SVM_EXIT_WRITE_CR8] = cr8_write_interception, - [SVM_EXIT_READ_DR0] = emulate_on_interception, + [SVM_EXIT_WRITE_CR0] = emulate_on_interception, + [SVM_EXIT_WRITE_CR3] = emulate_on_interception, + [SVM_EXIT_WRITE_CR4] = emulate_on_interception, + [SVM_EXIT_WRITE_CR8] = cr8_write_interception, + [SVM_EXIT_READ_DR0] = emulate_on_interception, [SVM_EXIT_READ_DR1] = emulate_on_interception, [SVM_EXIT_READ_DR2] = emulate_on_interception, [SVM_EXIT_READ_DR3] = emulate_on_interception, @@ -2354,15 +2695,14 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception, [SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception, [SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception, - [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, - [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, - [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, - [SVM_EXIT_INTR] = intr_interception, + [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, + [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, + [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, + [SVM_EXIT_INTR] = intr_interception, [SVM_EXIT_NMI] = nmi_interception, [SVM_EXIT_SMI] = nop_on_interception, [SVM_EXIT_INIT] = nop_on_interception, [SVM_EXIT_VINTR] = interrupt_window_interception, - /* [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, */ [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, [SVM_EXIT_INVD] = emulate_on_interception, @@ -2370,7 +2710,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, [SVM_EXIT_INVLPGA] = invlpga_interception, - [SVM_EXIT_IOIO] = io_interception, + [SVM_EXIT_IOIO] = io_interception, [SVM_EXIT_MSR] = msr_interception, [SVM_EXIT_TASK_SWITCH] = task_switch_interception, [SVM_EXIT_SHUTDOWN] = shutdown_interception, @@ -2387,13 +2727,111 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_NPF] = pf_interception, }; +void dump_vmcb(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_control_area *control = &svm->vmcb->control; + struct vmcb_save_area *save = &svm->vmcb->save; + + pr_err("VMCB Control Area:\n"); + pr_err("cr_read: %04x\n", control->intercept_cr_read); + pr_err("cr_write: %04x\n", control->intercept_cr_write); + pr_err("dr_read: %04x\n", control->intercept_dr_read); + pr_err("dr_write: %04x\n", control->intercept_dr_write); + pr_err("exceptions: %08x\n", control->intercept_exceptions); + pr_err("intercepts: %016llx\n", control->intercept); + pr_err("pause filter count: %d\n", control->pause_filter_count); + pr_err("iopm_base_pa: %016llx\n", control->iopm_base_pa); + pr_err("msrpm_base_pa: %016llx\n", control->msrpm_base_pa); + pr_err("tsc_offset: %016llx\n", control->tsc_offset); + pr_err("asid: %d\n", control->asid); + pr_err("tlb_ctl: %d\n", control->tlb_ctl); + pr_err("int_ctl: %08x\n", control->int_ctl); + pr_err("int_vector: %08x\n", control->int_vector); + pr_err("int_state: %08x\n", control->int_state); + pr_err("exit_code: %08x\n", control->exit_code); + pr_err("exit_info1: %016llx\n", control->exit_info_1); + pr_err("exit_info2: %016llx\n", control->exit_info_2); + pr_err("exit_int_info: %08x\n", control->exit_int_info); + pr_err("exit_int_info_err: %08x\n", control->exit_int_info_err); + pr_err("nested_ctl: %lld\n", control->nested_ctl); + pr_err("nested_cr3: %016llx\n", control->nested_cr3); + pr_err("event_inj: %08x\n", control->event_inj); + pr_err("event_inj_err: %08x\n", control->event_inj_err); + pr_err("lbr_ctl: %lld\n", control->lbr_ctl); + pr_err("next_rip: %016llx\n", control->next_rip); + pr_err("VMCB State Save Area:\n"); + pr_err("es: s: %04x a: %04x l: %08x b: %016llx\n", + save->es.selector, save->es.attrib, + save->es.limit, save->es.base); + pr_err("cs: s: %04x a: %04x l: %08x b: %016llx\n", + save->cs.selector, save->cs.attrib, + save->cs.limit, save->cs.base); + pr_err("ss: s: %04x a: %04x l: %08x b: %016llx\n", + save->ss.selector, save->ss.attrib, + save->ss.limit, save->ss.base); + pr_err("ds: s: %04x a: %04x l: %08x b: %016llx\n", + save->ds.selector, save->ds.attrib, + save->ds.limit, save->ds.base); + pr_err("fs: s: %04x a: %04x l: %08x b: %016llx\n", + save->fs.selector, save->fs.attrib, + save->fs.limit, save->fs.base); + pr_err("gs: s: %04x a: %04x l: %08x b: %016llx\n", + save->gs.selector, save->gs.attrib, + save->gs.limit, save->gs.base); + pr_err("gdtr: s: %04x a: %04x l: %08x b: %016llx\n", + save->gdtr.selector, save->gdtr.attrib, + save->gdtr.limit, save->gdtr.base); + pr_err("ldtr: s: %04x a: %04x l: %08x b: %016llx\n", + save->ldtr.selector, save->ldtr.attrib, + save->ldtr.limit, save->ldtr.base); + pr_err("idtr: s: %04x a: %04x l: %08x b: %016llx\n", + save->idtr.selector, save->idtr.attrib, + save->idtr.limit, save->idtr.base); + pr_err("tr: s: %04x a: %04x l: %08x b: %016llx\n", + save->tr.selector, save->tr.attrib, + save->tr.limit, save->tr.base); + pr_err("cpl: %d efer: %016llx\n", + save->cpl, save->efer); + pr_err("cr0: %016llx cr2: %016llx\n", + save->cr0, save->cr2); + pr_err("cr3: %016llx cr4: %016llx\n", + save->cr3, save->cr4); + pr_err("dr6: %016llx dr7: %016llx\n", + save->dr6, save->dr7); + pr_err("rip: %016llx rflags: %016llx\n", + save->rip, save->rflags); + pr_err("rsp: %016llx rax: %016llx\n", + save->rsp, save->rax); + pr_err("star: %016llx lstar: %016llx\n", + save->star, save->lstar); + pr_err("cstar: %016llx sfmask: %016llx\n", + save->cstar, save->sfmask); + pr_err("kernel_gs_base: %016llx sysenter_cs: %016llx\n", + save->kernel_gs_base, save->sysenter_cs); + pr_err("sysenter_esp: %016llx sysenter_eip: %016llx\n", + save->sysenter_esp, save->sysenter_eip); + pr_err("gpat: %016llx dbgctl: %016llx\n", + save->g_pat, save->dbgctl); + pr_err("br_from: %016llx br_to: %016llx\n", + save->br_from, save->br_to); + pr_err("excp_from: %016llx excp_to: %016llx\n", + save->last_excp_from, save->last_excp_to); + +} + static int handle_exit(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; - trace_kvm_exit(exit_code, svm->vmcb->save.rip); + trace_kvm_exit(exit_code, vcpu); + + if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK)) + vcpu->arch.cr0 = svm->vmcb->save.cr0; + if (npt_enabled) + vcpu->arch.cr3 = svm->vmcb->save.cr3; if (unlikely(svm->nested.exit_required)) { nested_svm_vmexit(svm); @@ -2422,15 +2860,12 @@ static int handle_exit(struct kvm_vcpu *vcpu) svm_complete_interrupts(svm); - if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK)) - vcpu->arch.cr0 = svm->vmcb->save.cr0; - if (npt_enabled) - vcpu->arch.cr3 = svm->vmcb->save.cr3; - if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) { kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; kvm_run->fail_entry.hardware_entry_failure_reason = svm->vmcb->control.exit_code; + pr_err("KVM: FAILED VMRUN WITH VMCB:\n"); + dump_vmcb(vcpu); return 0; } @@ -2487,9 +2922,6 @@ static inline void svm_inject_irq(struct vcpu_svm *svm, int irq) { struct vmcb_control_area *control; - trace_kvm_inj_virq(irq); - - ++svm->vcpu.stat.irq_injections; control = &svm->vmcb->control; control->int_vector = irq; control->int_ctl &= ~V_INTR_PRIO_MASK; @@ -2503,6 +2935,9 @@ static void svm_set_irq(struct kvm_vcpu *vcpu) BUG_ON(!(gif_set(svm))); + trace_kvm_inj_virq(vcpu->arch.interrupt.nr); + ++vcpu->stat.irq_injections; + svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR; } @@ -2511,6 +2946,9 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); + if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK)) + return; + if (irr == -1) return; @@ -2522,8 +2960,12 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - return !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) && - !(svm->vcpu.arch.hflags & HF_NMI_MASK); + int ret; + ret = !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) && + !(svm->vcpu.arch.hflags & HF_NMI_MASK); + ret = ret && gif_set(svm) && nested_svm_nmi(svm); + + return ret; } static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) @@ -2568,13 +3010,13 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - nested_svm_intr(svm); - - /* In case GIF=0 we can't rely on the CPU to tell us when - * GIF becomes 1, because that's a separate STGI/VMRUN intercept. - * The next time we get that intercept, this function will be - * called again though and we'll get the vintr intercept. */ - if (gif_set(svm)) { + /* + * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes + * 1, because that's a separate STGI/VMRUN intercept. The next time we + * get that intercept, this function will be called again though and + * we'll get the vintr intercept. + */ + if (gif_set(svm) && nested_svm_intr(svm)) { svm_set_vintr(svm); svm_inject_irq(svm, 0x0); } @@ -2588,9 +3030,10 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) == HF_NMI_MASK) return; /* IRET will cause a vm exit */ - /* Something prevents NMI from been injected. Single step over - possible problem (IRET or exception injection or interrupt - shadow) */ + /* + * Something prevents NMI from been injected. Single step over possible + * problem (IRET or exception injection or interrupt shadow) + */ svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); update_db_intercept(vcpu); @@ -2614,6 +3057,9 @@ static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK)) + return; + if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR8_MASK)) { int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK; kvm_set_cr8(vcpu, cr8); @@ -2625,6 +3071,9 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); u64 cr8; + if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK)) + return; + cr8 = kvm_get_cr8(vcpu); svm->vmcb->control.int_ctl &= ~V_TPR_MASK; svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK; @@ -2635,6 +3084,9 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) u8 vector; int type; u32 exitintinfo = svm->vmcb->control.exit_int_info; + unsigned int3_injected = svm->int3_injected; + + svm->int3_injected = 0; if (svm->vcpu.arch.hflags & HF_IRET_MASK) svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK); @@ -2654,18 +3106,25 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) svm->vcpu.arch.nmi_injected = true; break; case SVM_EXITINTINFO_TYPE_EXEPT: - /* In case of software exception do not reinject an exception - vector, but re-execute and instruction instead */ - if (is_nested(svm)) - break; - if (kvm_exception_is_soft(vector)) + /* + * In case of software exceptions, do not reinject the vector, + * but re-execute the instruction instead. Rewind RIP first + * if we emulated INT3 before. + */ + if (kvm_exception_is_soft(vector)) { + if (vector == BP_VECTOR && int3_injected && + kvm_is_linear_rip(&svm->vcpu, svm->int3_rip)) + kvm_rip_write(&svm->vcpu, + kvm_rip_read(&svm->vcpu) - + int3_injected); break; + } if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) { u32 err = svm->vmcb->control.exit_int_info_err; - kvm_queue_exception_e(&svm->vcpu, vector, err); + kvm_requeue_exception_e(&svm->vcpu, vector, err); } else - kvm_queue_exception(&svm->vcpu, vector); + kvm_requeue_exception(&svm->vcpu, vector); break; case SVM_EXITINTINFO_TYPE_INTR: kvm_queue_interrupt(&svm->vcpu, vector, false); @@ -2688,6 +3147,10 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) u16 gs_selector; u16 ldt_selector; + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; + svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; + svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; + /* * A vmexit emulation is required before the vcpu can be executed * again. @@ -2695,10 +3158,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->nested.exit_required)) return; - svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; - svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; - svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; - pre_svm_run(svm); sync_lapic_to_cr8(vcpu); @@ -2811,6 +3270,14 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR); vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR); } + + /* + * We need to handle MC intercepts here before the vcpu has a chance to + * change the physical cpu + */ + if (unlikely(svm->vmcb->control.exit_code == + SVM_EXIT_EXCP_BASE + MC_VECTOR)) + svm_handle_mce(svm); } #undef R @@ -2879,25 +3346,39 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) { } +static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) +{ + switch (func) { + case 0x8000000A: + entry->eax = 1; /* SVM revision 1 */ + entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper + ASID emulation to nested SVM */ + entry->ecx = 0; /* Reserved */ + entry->edx = 0; /* Do not support any additional features */ + + break; + } +} + static const struct trace_print_flags svm_exit_reasons_str[] = { - { 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_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" }, @@ -2942,12 +3423,19 @@ static bool svm_rdtscp_supported(void) return false; } +static bool svm_has_wbinvd_exit(void) +{ + return true; +} + static void svm_fpu_deactivate(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - update_cr0_intercept(svm); svm->vmcb->control.intercept_exceptions |= 1 << NM_VECTOR; + if (is_nested(svm)) + svm->nested.hsave->control.intercept_exceptions |= 1 << NM_VECTOR; + update_cr0_intercept(svm); } static struct kvm_x86_ops svm_x86_ops = { @@ -2986,8 +3474,7 @@ static struct kvm_x86_ops svm_x86_ops = { .set_idt = svm_set_idt, .get_gdt = svm_get_gdt, .set_gdt = svm_set_gdt, - .get_dr = svm_get_dr, - .set_dr = svm_set_dr, + .set_dr7 = svm_set_dr7, .cache_reg = svm_cache_reg, .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, @@ -3023,12 +3510,16 @@ static struct kvm_x86_ops svm_x86_ops = { .cpuid_update = svm_cpuid_update, .rdtscp_supported = svm_rdtscp_supported, + + .set_supported_cpuid = svm_set_supported_cpuid, + + .has_wbinvd_exit = svm_has_wbinvd_exit, }; static int __init svm_init(void) { return kvm_init(&svm_x86_ops, sizeof(struct vcpu_svm), - THIS_MODULE); + __alignof__(struct vcpu_svm), THIS_MODULE); } static void __exit svm_exit(void) diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c index eea40439066..e16a0dbe74d 100644 --- a/arch/x86/kvm/timer.c +++ b/arch/x86/kvm/timer.c @@ -1,3 +1,17 @@ +/* + * Kernel-based Virtual Machine driver for Linux + * + * This module enables machines with Intel VT-x extensions to run virtual + * machines without emulation or binary translation. + * + * timer support + * + * Copyright 2010 Red Hat, Inc. and/or its affilates. + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + #include <linux/kvm_host.h> #include <linux/kvm.h> #include <linux/hrtimer.h> @@ -12,12 +26,13 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer) /* * There is a race window between reading and incrementing, but we do * not care about potentially loosing timer events in the !reinject - * case anyway. + * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked + * in vcpu_enter_guest. */ if (ktimer->reinject || !atomic_read(&ktimer->pending)) { atomic_inc(&ktimer->pending); /* FIXME: this code should not know anything about vcpus */ - set_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests); + kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu); } if (waitqueue_active(q)) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 6ad30a29f04..a6544b8e7c0 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -5,8 +5,6 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm -#define TRACE_INCLUDE_PATH arch/x86/kvm -#define TRACE_INCLUDE_FILE trace /* * Tracepoint for guest mode entry. @@ -184,8 +182,8 @@ TRACE_EVENT(kvm_apic, * Tracepoint for kvm guest exit: */ TRACE_EVENT(kvm_exit, - TP_PROTO(unsigned int exit_reason, unsigned long guest_rip), - TP_ARGS(exit_reason, guest_rip), + TP_PROTO(unsigned int exit_reason, struct kvm_vcpu *vcpu), + TP_ARGS(exit_reason, vcpu), TP_STRUCT__entry( __field( unsigned int, exit_reason ) @@ -194,7 +192,7 @@ TRACE_EVENT(kvm_exit, TP_fast_assign( __entry->exit_reason = exit_reason; - __entry->guest_rip = guest_rip; + __entry->guest_rip = kvm_rip_read(vcpu); ), TP_printk("reason %s rip 0x%lx", @@ -221,6 +219,38 @@ TRACE_EVENT(kvm_inj_virq, TP_printk("irq %u", __entry->irq) ); +#define EXS(x) { x##_VECTOR, "#" #x } + +#define kvm_trace_sym_exc \ + EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM), \ + EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF), \ + EXS(MF), EXS(MC) + +/* + * Tracepoint for kvm interrupt injection: + */ +TRACE_EVENT(kvm_inj_exception, + TP_PROTO(unsigned exception, bool has_error, unsigned error_code), + TP_ARGS(exception, has_error, error_code), + + TP_STRUCT__entry( + __field( u8, exception ) + __field( u8, has_error ) + __field( u32, error_code ) + ), + + TP_fast_assign( + __entry->exception = exception; + __entry->has_error = has_error; + __entry->error_code = error_code; + ), + + TP_printk("%s (0x%x)", + __print_symbolic(__entry->exception, kvm_trace_sym_exc), + /* FIXME: don't print error_code if not present */ + __entry->has_error ? __entry->error_code : 0) +); + /* * Tracepoint for page fault. */ @@ -413,12 +443,34 @@ TRACE_EVENT(kvm_nested_vmrun, ), TP_printk("rip: 0x%016llx vmcb: 0x%016llx nrip: 0x%016llx int_ctl: 0x%08x " - "event_inj: 0x%08x npt: %s\n", + "event_inj: 0x%08x npt: %s", __entry->rip, __entry->vmcb, __entry->nested_rip, __entry->int_ctl, __entry->event_inj, __entry->npt ? "on" : "off") ); +TRACE_EVENT(kvm_nested_intercepts, + TP_PROTO(__u16 cr_read, __u16 cr_write, __u32 exceptions, __u64 intercept), + TP_ARGS(cr_read, cr_write, exceptions, intercept), + + TP_STRUCT__entry( + __field( __u16, cr_read ) + __field( __u16, cr_write ) + __field( __u32, exceptions ) + __field( __u64, intercept ) + ), + + TP_fast_assign( + __entry->cr_read = cr_read; + __entry->cr_write = cr_write; + __entry->exceptions = exceptions; + __entry->intercept = intercept; + ), + + TP_printk("cr_read: %04x cr_write: %04x excp: %08x intercept: %016llx", + __entry->cr_read, __entry->cr_write, __entry->exceptions, + __entry->intercept) +); /* * Tracepoint for #VMEXIT while nested */ @@ -447,7 +499,7 @@ TRACE_EVENT(kvm_nested_vmexit, __entry->exit_int_info_err = exit_int_info_err; ), TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx " - "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n", + "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", __entry->rip, ftrace_print_symbols_seq(p, __entry->exit_code, kvm_x86_ops->exit_reasons_str), @@ -482,7 +534,7 @@ TRACE_EVENT(kvm_nested_vmexit_inject, ), TP_printk("reason: %s ext_inf1: 0x%016llx " - "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n", + "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", ftrace_print_symbols_seq(p, __entry->exit_code, kvm_x86_ops->exit_reasons_str), __entry->exit_info1, __entry->exit_info2, @@ -504,7 +556,7 @@ TRACE_EVENT(kvm_nested_intr_vmexit, __entry->rip = rip ), - TP_printk("rip: 0x%016llx\n", __entry->rip) + TP_printk("rip: 0x%016llx", __entry->rip) ); /* @@ -526,7 +578,7 @@ TRACE_EVENT(kvm_invlpga, __entry->address = address; ), - TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx\n", + TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx", __entry->rip, __entry->asid, __entry->address) ); @@ -547,11 +599,102 @@ TRACE_EVENT(kvm_skinit, __entry->slb = slb; ), - TP_printk("rip: 0x%016llx slb: 0x%08x\n", + TP_printk("rip: 0x%016llx slb: 0x%08x", __entry->rip, __entry->slb) ); +#define __print_insn(insn, ilen) ({ \ + int i; \ + const char *ret = p->buffer + p->len; \ + \ + for (i = 0; i < ilen; ++i) \ + trace_seq_printf(p, " %02x", insn[i]); \ + trace_seq_printf(p, "%c", 0); \ + ret; \ + }) + +#define KVM_EMUL_INSN_F_CR0_PE (1 << 0) +#define KVM_EMUL_INSN_F_EFL_VM (1 << 1) +#define KVM_EMUL_INSN_F_CS_D (1 << 2) +#define KVM_EMUL_INSN_F_CS_L (1 << 3) + +#define kvm_trace_symbol_emul_flags \ + { 0, "real" }, \ + { KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_EFL_VM, "vm16" }, \ + { KVM_EMUL_INSN_F_CR0_PE, "prot16" }, \ + { KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_CS_D, "prot32" }, \ + { KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_CS_L, "prot64" } + +#define kei_decode_mode(mode) ({ \ + u8 flags = 0xff; \ + switch (mode) { \ + case X86EMUL_MODE_REAL: \ + flags = 0; \ + break; \ + case X86EMUL_MODE_VM86: \ + flags = KVM_EMUL_INSN_F_EFL_VM; \ + break; \ + case X86EMUL_MODE_PROT16: \ + flags = KVM_EMUL_INSN_F_CR0_PE; \ + break; \ + case X86EMUL_MODE_PROT32: \ + flags = KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_CS_D; \ + break; \ + case X86EMUL_MODE_PROT64: \ + flags = KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_CS_L; \ + break; \ + } \ + flags; \ + }) + +TRACE_EVENT(kvm_emulate_insn, + TP_PROTO(struct kvm_vcpu *vcpu, __u8 failed), + TP_ARGS(vcpu, failed), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u32, csbase ) + __field( __u8, len ) + __array( __u8, insn, 15 ) + __field( __u8, flags ) + __field( __u8, failed ) + ), + + TP_fast_assign( + __entry->rip = vcpu->arch.emulate_ctxt.decode.fetch.start; + __entry->csbase = kvm_x86_ops->get_segment_base(vcpu, VCPU_SREG_CS); + __entry->len = vcpu->arch.emulate_ctxt.decode.eip + - vcpu->arch.emulate_ctxt.decode.fetch.start; + memcpy(__entry->insn, + vcpu->arch.emulate_ctxt.decode.fetch.data, + 15); + __entry->flags = kei_decode_mode(vcpu->arch.emulate_ctxt.mode); + __entry->failed = failed; + ), + + TP_printk("%x:%llx:%s (%s)%s", + __entry->csbase, __entry->rip, + __print_insn(__entry->insn, __entry->len), + __print_symbolic(__entry->flags, + kvm_trace_symbol_emul_flags), + __entry->failed ? " failed" : "" + ) + ); + +#define trace_kvm_emulate_insn_start(vcpu) trace_kvm_emulate_insn(vcpu, 0) +#define trace_kvm_emulate_insn_failed(vcpu) trace_kvm_emulate_insn(vcpu, 1) + #endif /* _TRACE_KVM_H */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH arch/x86/kvm +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + /* This part must be outside protection */ #include <trace/define_trace.h> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 2f8db0ec8ae..49b25eee25a 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -5,6 +5,7 @@ * machines without emulation or binary translation. * * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affilates. * * Authors: * Avi Kivity <avi@qumranet.com> @@ -27,6 +28,7 @@ #include <linux/moduleparam.h> #include <linux/ftrace_event.h> #include <linux/slab.h> +#include <linux/tboot.h> #include "kvm_cache_regs.h" #include "x86.h" @@ -35,6 +37,8 @@ #include <asm/vmx.h> #include <asm/virtext.h> #include <asm/mce.h> +#include <asm/i387.h> +#include <asm/xcr.h> #include "trace.h" @@ -62,6 +66,9 @@ module_param_named(unrestricted_guest, static int __read_mostly emulate_invalid_guest_state = 0; module_param(emulate_invalid_guest_state, bool, S_IRUGO); +static int __read_mostly vmm_exclusive = 1; +module_param(vmm_exclusive, bool, S_IRUGO); + #define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST \ (X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD) #define KVM_GUEST_CR0_MASK \ @@ -98,6 +105,8 @@ module_param(ple_gap, int, S_IRUGO); static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW; module_param(ple_window, int, S_IRUGO); +#define NR_AUTOLOAD_MSRS 1 + struct vmcs { u32 revision_id; u32 abort; @@ -125,6 +134,11 @@ struct vcpu_vmx { u64 msr_guest_kernel_gs_base; #endif struct vmcs *vmcs; + struct msr_autoload { + unsigned nr; + struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS]; + struct vmx_msr_entry host[NR_AUTOLOAD_MSRS]; + } msr_autoload; struct { int loaded; u16 fs_sel, gs_sel, ldt_sel; @@ -165,10 +179,13 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) static int init_rmode(struct kvm *kvm); static u64 construct_eptp(unsigned long root_hpa); +static void kvm_cpu_vmxon(u64 addr); +static void kvm_cpu_vmxoff(void); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); static DEFINE_PER_CPU(struct list_head, vcpus_on_cpu); +static DEFINE_PER_CPU(struct desc_ptr, host_gdt); static unsigned long *vmx_io_bitmap_a; static unsigned long *vmx_io_bitmap_b; @@ -223,67 +240,67 @@ static u64 host_efer; static void ept_save_pdptrs(struct kvm_vcpu *vcpu); /* - * Keep MSR_K6_STAR at the end, as setup_msrs() will try to optimize it + * Keep MSR_STAR at the end, as setup_msrs() will try to optimize it * away by decrementing the array size. */ static const u32 vmx_msr_index[] = { #ifdef CONFIG_X86_64 MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, #endif - MSR_EFER, MSR_TSC_AUX, MSR_K6_STAR, + MSR_EFER, MSR_TSC_AUX, MSR_STAR, }; #define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index) -static inline int is_page_fault(u32 intr_info) +static inline bool is_page_fault(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK); } -static inline int is_no_device(u32 intr_info) +static inline bool is_no_device(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK); } -static inline int is_invalid_opcode(u32 intr_info) +static inline bool is_invalid_opcode(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK); } -static inline int is_external_interrupt(u32 intr_info) +static inline bool is_external_interrupt(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK); } -static inline int is_machine_check(u32 intr_info) +static inline bool is_machine_check(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK); } -static inline int cpu_has_vmx_msr_bitmap(void) +static inline bool cpu_has_vmx_msr_bitmap(void) { return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS; } -static inline int cpu_has_vmx_tpr_shadow(void) +static inline bool cpu_has_vmx_tpr_shadow(void) { return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW; } -static inline int vm_need_tpr_shadow(struct kvm *kvm) +static inline bool vm_need_tpr_shadow(struct kvm *kvm) { return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm)); } -static inline int cpu_has_secondary_exec_ctrls(void) +static inline bool cpu_has_secondary_exec_ctrls(void) { return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; @@ -303,84 +320,105 @@ static inline bool cpu_has_vmx_flexpriority(void) static inline bool cpu_has_vmx_ept_execute_only(void) { - return !!(vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT); + return vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT; } static inline bool cpu_has_vmx_eptp_uncacheable(void) { - return !!(vmx_capability.ept & VMX_EPTP_UC_BIT); + return vmx_capability.ept & VMX_EPTP_UC_BIT; } static inline bool cpu_has_vmx_eptp_writeback(void) { - return !!(vmx_capability.ept & VMX_EPTP_WB_BIT); + return vmx_capability.ept & VMX_EPTP_WB_BIT; } static inline bool cpu_has_vmx_ept_2m_page(void) { - return !!(vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT); + return vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT; } static inline bool cpu_has_vmx_ept_1g_page(void) { - return !!(vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT); + return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT; +} + +static inline bool cpu_has_vmx_ept_4levels(void) +{ + return vmx_capability.ept & VMX_EPT_PAGE_WALK_4_BIT; +} + +static inline bool cpu_has_vmx_invept_individual_addr(void) +{ + return vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT; +} + +static inline bool cpu_has_vmx_invept_context(void) +{ + return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT; } -static inline int cpu_has_vmx_invept_individual_addr(void) +static inline bool cpu_has_vmx_invept_global(void) { - return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT); + return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT; } -static inline int cpu_has_vmx_invept_context(void) +static inline bool cpu_has_vmx_invvpid_single(void) { - return !!(vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT); + return vmx_capability.vpid & VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT; } -static inline int cpu_has_vmx_invept_global(void) +static inline bool cpu_has_vmx_invvpid_global(void) { - return !!(vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT); + return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT; } -static inline int cpu_has_vmx_ept(void) +static inline bool cpu_has_vmx_ept(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_EPT; } -static inline int cpu_has_vmx_unrestricted_guest(void) +static inline bool cpu_has_vmx_unrestricted_guest(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_UNRESTRICTED_GUEST; } -static inline int cpu_has_vmx_ple(void) +static inline bool cpu_has_vmx_ple(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PAUSE_LOOP_EXITING; } -static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm) +static inline bool vm_need_virtualize_apic_accesses(struct kvm *kvm) { return flexpriority_enabled && irqchip_in_kernel(kvm); } -static inline int cpu_has_vmx_vpid(void) +static inline bool cpu_has_vmx_vpid(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_VPID; } -static inline int cpu_has_vmx_rdtscp(void) +static inline bool cpu_has_vmx_rdtscp(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_RDTSCP; } -static inline int cpu_has_virtual_nmis(void) +static inline bool cpu_has_virtual_nmis(void) { return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS; } +static inline bool cpu_has_vmx_wbinvd_exit(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_WBINVD_EXITING; +} + static inline bool report_flexpriority(void) { return flexpriority_enabled; @@ -445,6 +483,19 @@ static void vmcs_clear(struct vmcs *vmcs) vmcs, phys_addr); } +static void vmcs_load(struct vmcs *vmcs) +{ + u64 phys_addr = __pa(vmcs); + u8 error; + + asm volatile (__ex(ASM_VMX_VMPTRLD_RAX) "; setna %0" + : "=g"(error) : "a"(&phys_addr), "m"(phys_addr) + : "cc", "memory"); + if (error) + printk(KERN_ERR "kvm: vmptrld %p/%llx fail\n", + vmcs, phys_addr); +} + static void __vcpu_clear(void *arg) { struct vcpu_vmx *vmx = arg; @@ -467,12 +518,27 @@ static void vcpu_clear(struct vcpu_vmx *vmx) smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear, vmx, 1); } -static inline void vpid_sync_vcpu_all(struct vcpu_vmx *vmx) +static inline void vpid_sync_vcpu_single(struct vcpu_vmx *vmx) { if (vmx->vpid == 0) return; - __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0); + if (cpu_has_vmx_invvpid_single()) + __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0); +} + +static inline void vpid_sync_vcpu_global(void) +{ + if (cpu_has_vmx_invvpid_global()) + __invvpid(VMX_VPID_EXTENT_ALL_CONTEXT, 0, 0); +} + +static inline void vpid_sync_context(struct vcpu_vmx *vmx) +{ + if (cpu_has_vmx_invvpid_single()) + vpid_sync_vcpu_single(vmx); + else + vpid_sync_vcpu_global(); } static inline void ept_sync_global(void) @@ -595,16 +661,56 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) vmcs_write32(EXCEPTION_BITMAP, eb); } +static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) +{ + unsigned i; + struct msr_autoload *m = &vmx->msr_autoload; + + for (i = 0; i < m->nr; ++i) + if (m->guest[i].index == msr) + break; + + if (i == m->nr) + return; + --m->nr; + m->guest[i] = m->guest[m->nr]; + m->host[i] = m->host[m->nr]; + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr); + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr); +} + +static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, + u64 guest_val, u64 host_val) +{ + unsigned i; + struct msr_autoload *m = &vmx->msr_autoload; + + for (i = 0; i < m->nr; ++i) + if (m->guest[i].index == msr) + break; + + if (i == m->nr) { + ++m->nr; + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr); + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr); + } + + m->guest[i].index = msr; + m->guest[i].value = guest_val; + m->host[i].index = msr; + m->host[i].value = host_val; +} + static void reload_tss(void) { /* * VT restores TR but not its size. Useless. */ - struct descriptor_table gdt; + struct desc_ptr gdt; struct desc_struct *descs; - kvm_get_gdt(&gdt); - descs = (void *)gdt.base; + native_store_gdt(&gdt); + descs = (void *)gdt.address; descs[GDT_ENTRY_TSS].type = 9; /* available TSS */ load_TR_desc(); } @@ -631,9 +737,57 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) guest_efer |= host_efer & ignore_bits; vmx->guest_msrs[efer_offset].data = guest_efer; vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + + clear_atomic_switch_msr(vmx, MSR_EFER); + /* On ept, can't emulate nx, and must switch nx atomically */ + if (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX)) { + guest_efer = vmx->vcpu.arch.efer; + if (!(guest_efer & EFER_LMA)) + guest_efer &= ~EFER_LME; + add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer); + return false; + } + return true; } +static unsigned long segment_base(u16 selector) +{ + struct desc_ptr gdt; + struct desc_struct *d; + unsigned long table_base; + unsigned long v; + + if (!(selector & ~3)) + return 0; + + native_store_gdt(&gdt); + table_base = gdt.address; + + if (selector & 4) { /* from ldt */ + u16 ldt_selector = kvm_read_ldt(); + + if (!(ldt_selector & ~3)) + return 0; + + table_base = segment_base(ldt_selector); + } + d = (struct desc_struct *)(table_base + (selector & ~7)); + v = get_desc_base(d); +#ifdef CONFIG_X86_64 + if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) + v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32; +#endif + return v; +} + +static inline unsigned long kvm_read_tr_base(void) +{ + u16 tr; + asm("str %0" : "=g"(tr)); + return segment_base(tr); +} + static void vmx_save_host_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -716,6 +870,9 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); } #endif + if (current_thread_info()->status & TS_USEDFPU) + clts(); + load_gdt(&__get_cpu_var(host_gdt)); } static void vmx_load_host_state(struct vcpu_vmx *vmx) @@ -732,43 +889,38 @@ static void vmx_load_host_state(struct vcpu_vmx *vmx) static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - u64 phys_addr = __pa(vmx->vmcs); u64 tsc_this, delta, new_offset; + u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); - if (vcpu->cpu != cpu) { + if (!vmm_exclusive) + kvm_cpu_vmxon(phys_addr); + else if (vcpu->cpu != cpu) vcpu_clear(vmx); - kvm_migrate_timers(vcpu); - set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests); - local_irq_disable(); - list_add(&vmx->local_vcpus_link, - &per_cpu(vcpus_on_cpu, cpu)); - local_irq_enable(); - } if (per_cpu(current_vmcs, cpu) != vmx->vmcs) { - u8 error; - per_cpu(current_vmcs, cpu) = vmx->vmcs; - asm volatile (__ex(ASM_VMX_VMPTRLD_RAX) "; setna %0" - : "=g"(error) : "a"(&phys_addr), "m"(phys_addr) - : "cc"); - if (error) - printk(KERN_ERR "kvm: vmptrld %p/%llx fail\n", - vmx->vmcs, phys_addr); + vmcs_load(vmx->vmcs); } if (vcpu->cpu != cpu) { - struct descriptor_table dt; + struct desc_ptr dt; unsigned long sysenter_esp; + kvm_migrate_timers(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + local_irq_disable(); + list_add(&vmx->local_vcpus_link, + &per_cpu(vcpus_on_cpu, cpu)); + local_irq_enable(); + vcpu->cpu = cpu; /* * Linux uses per-cpu TSS and GDT, so set these when switching * processors. */ vmcs_writel(HOST_TR_BASE, kvm_read_tr_base()); /* 22.2.4 */ - kvm_get_gdt(&dt); - vmcs_writel(HOST_GDTR_BASE, dt.base); /* 22.2.4 */ + native_store_gdt(&dt); + vmcs_writel(HOST_GDTR_BASE, dt.address); /* 22.2.4 */ rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ @@ -788,6 +940,10 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void vmx_vcpu_put(struct kvm_vcpu *vcpu) { __vmx_load_host_state(to_vmx(vcpu)); + if (!vmm_exclusive) { + __vcpu_clear(to_vmx(vcpu)); + kvm_cpu_vmxoff(); + } } static void vmx_fpu_activate(struct kvm_vcpu *vcpu) @@ -846,9 +1002,9 @@ static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) int ret = 0; if (interruptibility & GUEST_INTR_STATE_STI) - ret |= X86_SHADOW_INT_STI; + ret |= KVM_X86_SHADOW_INT_STI; if (interruptibility & GUEST_INTR_STATE_MOV_SS) - ret |= X86_SHADOW_INT_MOV_SS; + ret |= KVM_X86_SHADOW_INT_MOV_SS; return ret & mask; } @@ -860,9 +1016,9 @@ static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS); - if (mask & X86_SHADOW_INT_MOV_SS) + if (mask & KVM_X86_SHADOW_INT_MOV_SS) interruptibility |= GUEST_INTR_STATE_MOV_SS; - if (mask & X86_SHADOW_INT_STI) + else if (mask & KVM_X86_SHADOW_INT_STI) interruptibility |= GUEST_INTR_STATE_STI; if ((interruptibility != interruptibility_old)) @@ -882,7 +1038,8 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) } static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, - bool has_error_code, u32 error_code) + bool has_error_code, u32 error_code, + bool reinject) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 intr_info = nr | INTR_INFO_VALID_MASK; @@ -960,10 +1117,10 @@ static void setup_msrs(struct vcpu_vmx *vmx) if (index >= 0 && vmx->rdtscp_enabled) move_msr_up(vmx, index, save_nmsrs++); /* - * MSR_K6_STAR is only needed on long mode guests, and only + * MSR_STAR is only needed on long mode guests, and only * if efer.sce is enabled. */ - index = __find_msr_index(vmx, MSR_K6_STAR); + index = __find_msr_index(vmx, MSR_STAR); if ((index >= 0) && (vmx->vcpu.arch.efer & EFER_SCE)) move_msr_up(vmx, index, save_nmsrs++); } @@ -1176,37 +1333,55 @@ static __init int vmx_disabled_by_bios(void) u64 msr; rdmsrl(MSR_IA32_FEATURE_CONTROL, msr); - return (msr & (FEATURE_CONTROL_LOCKED | - FEATURE_CONTROL_VMXON_ENABLED)) - == FEATURE_CONTROL_LOCKED; + if (msr & FEATURE_CONTROL_LOCKED) { + if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX) + && tboot_enabled()) + return 1; + if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX) + && !tboot_enabled()) + return 1; + } + + return 0; /* locked but not enabled */ } +static void kvm_cpu_vmxon(u64 addr) +{ + asm volatile (ASM_VMX_VMXON_RAX + : : "a"(&addr), "m"(addr) + : "memory", "cc"); +} + static int hardware_enable(void *garbage) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); - u64 old; + u64 old, test_bits; if (read_cr4() & X86_CR4_VMXE) return -EBUSY; INIT_LIST_HEAD(&per_cpu(vcpus_on_cpu, cpu)); rdmsrl(MSR_IA32_FEATURE_CONTROL, old); - if ((old & (FEATURE_CONTROL_LOCKED | - FEATURE_CONTROL_VMXON_ENABLED)) - != (FEATURE_CONTROL_LOCKED | - FEATURE_CONTROL_VMXON_ENABLED)) + + test_bits = FEATURE_CONTROL_LOCKED; + test_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; + if (tboot_enabled()) + test_bits |= FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX; + + if ((old & test_bits) != test_bits) { /* enable and lock */ - wrmsrl(MSR_IA32_FEATURE_CONTROL, old | - FEATURE_CONTROL_LOCKED | - FEATURE_CONTROL_VMXON_ENABLED); + wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits); + } write_cr4(read_cr4() | X86_CR4_VMXE); /* FIXME: not cpu hotplug safe */ - asm volatile (ASM_VMX_VMXON_RAX - : : "a"(&phys_addr), "m"(phys_addr) - : "memory", "cc"); - ept_sync_global(); + if (vmm_exclusive) { + kvm_cpu_vmxon(phys_addr); + ept_sync_global(); + } + + store_gdt(&__get_cpu_var(host_gdt)); return 0; } @@ -1228,13 +1403,15 @@ static void vmclear_local_vcpus(void) static void kvm_cpu_vmxoff(void) { asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc"); - write_cr4(read_cr4() & ~X86_CR4_VMXE); } static void hardware_disable(void *garbage) { - vmclear_local_vcpus(); - kvm_cpu_vmxoff(); + if (vmm_exclusive) { + vmclear_local_vcpus(); + kvm_cpu_vmxoff(); + } + write_cr4(read_cr4() & ~X86_CR4_VMXE); } static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, @@ -1433,7 +1610,8 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_vpid()) enable_vpid = 0; - if (!cpu_has_vmx_ept()) { + if (!cpu_has_vmx_ept() || + !cpu_has_vmx_ept_4levels()) { enable_ept = 0; enable_unrestricted_guest = 0; } @@ -1521,8 +1699,8 @@ static gva_t rmode_tss_base(struct kvm *kvm) struct kvm_memslots *slots; gfn_t base_gfn; - slots = rcu_dereference(kvm->memslots); - base_gfn = kvm->memslots->memslots[0].base_gfn + + slots = kvm_memslots(kvm); + base_gfn = slots->memslots[0].base_gfn + kvm->memslots->memslots[0].npages - 3; return base_gfn << PAGE_SHIFT; } @@ -1638,26 +1816,27 @@ static void enter_lmode(struct kvm_vcpu *vcpu) (guest_tr_ar & ~AR_TYPE_MASK) | AR_TYPE_BUSY_64_TSS); } - vcpu->arch.efer |= EFER_LMA; - vmx_set_efer(vcpu, vcpu->arch.efer); + vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA); } static void exit_lmode(struct kvm_vcpu *vcpu) { - vcpu->arch.efer &= ~EFER_LMA; - vmcs_write32(VM_ENTRY_CONTROLS, vmcs_read32(VM_ENTRY_CONTROLS) & ~VM_ENTRY_IA32E_MODE); + vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA); } #endif static void vmx_flush_tlb(struct kvm_vcpu *vcpu) { - vpid_sync_vcpu_all(to_vmx(vcpu)); - if (enable_ept) + vpid_sync_context(to_vmx(vcpu)); + if (enable_ept) { + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + return; ept_sync_context(construct_eptp(vcpu->arch.mmu.root_hpa)); + } } static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) @@ -1934,28 +2113,28 @@ static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) *l = (ar >> 13) & 1; } -static void vmx_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { - dt->limit = vmcs_read32(GUEST_IDTR_LIMIT); - dt->base = vmcs_readl(GUEST_IDTR_BASE); + dt->size = vmcs_read32(GUEST_IDTR_LIMIT); + dt->address = vmcs_readl(GUEST_IDTR_BASE); } -static void vmx_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { - vmcs_write32(GUEST_IDTR_LIMIT, dt->limit); - vmcs_writel(GUEST_IDTR_BASE, dt->base); + vmcs_write32(GUEST_IDTR_LIMIT, dt->size); + vmcs_writel(GUEST_IDTR_BASE, dt->address); } -static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { - dt->limit = vmcs_read32(GUEST_GDTR_LIMIT); - dt->base = vmcs_readl(GUEST_GDTR_BASE); + dt->size = vmcs_read32(GUEST_GDTR_LIMIT); + dt->address = vmcs_readl(GUEST_GDTR_BASE); } -static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { - vmcs_write32(GUEST_GDTR_LIMIT, dt->limit); - vmcs_writel(GUEST_GDTR_BASE, dt->base); + vmcs_write32(GUEST_GDTR_LIMIT, dt->size); + vmcs_writel(GUEST_GDTR_BASE, dt->address); } static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg) @@ -2296,6 +2475,16 @@ static void allocate_vpid(struct vcpu_vmx *vmx) spin_unlock(&vmx_vpid_lock); } +static void free_vpid(struct vcpu_vmx *vmx) +{ + if (!enable_vpid) + return; + spin_lock(&vmx_vpid_lock); + if (vmx->vpid != 0) + __clear_bit(vmx->vpid, vmx_vpid_bitmap); + spin_unlock(&vmx_vpid_lock); +} + static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr) { int f = sizeof(unsigned long); @@ -2334,7 +2523,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) u32 junk; u64 host_pat, tsc_this, tsc_base; unsigned long a; - struct descriptor_table dt; + struct desc_ptr dt; int i; unsigned long kvm_vmx_return; u32 exec_control; @@ -2393,7 +2582,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf); vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */ - vmcs_writel(HOST_CR0, read_cr0()); /* 22.2.3 */ + vmcs_writel(HOST_CR0, read_cr0() | X86_CR0_TS); /* 22.2.3 */ vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */ vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */ @@ -2415,14 +2604,16 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */ - kvm_get_idt(&dt); - vmcs_writel(HOST_IDTR_BASE, dt.base); /* 22.2.4 */ + native_store_idt(&dt); + vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */ asm("mov $.Lkvm_vmx_return, %0" : "=r"(kvm_vmx_return)); vmcs_writel(HOST_RIP, kvm_vmx_return); /* 22.2.5 */ vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0); + vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host)); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); + vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest)); rdmsr(MSR_IA32_SYSENTER_CS, host_sysenter_cs, junk); vmcs_write32(HOST_IA32_SYSENTER_CS, host_sysenter_cs); @@ -2483,21 +2674,27 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) static int init_rmode(struct kvm *kvm) { + int idx, ret = 0; + + idx = srcu_read_lock(&kvm->srcu); if (!init_rmode_tss(kvm)) - return 0; + goto exit; if (!init_rmode_identity_map(kvm)) - return 0; - return 1; + goto exit; + + ret = 1; +exit: + srcu_read_unlock(&kvm->srcu, idx); + return ret; } static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 msr; - int ret, idx; + int ret; vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)); - idx = srcu_read_lock(&vcpu->kvm->srcu); if (!init_rmode(vmx->vcpu.kvm)) { ret = -ENOMEM; goto out; @@ -2514,7 +2711,9 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) msr |= MSR_IA32_APICBASE_BSP; kvm_set_apic_base(&vmx->vcpu, msr); - fx_init(&vmx->vcpu); + ret = fx_init(&vmx->vcpu); + if (ret != 0) + goto out; seg_setup(VCPU_SREG_CS); /* @@ -2597,7 +2796,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx_fpu_activate(&vmx->vcpu); update_exception_bitmap(&vmx->vcpu); - vpid_sync_vcpu_all(vmx); + vpid_sync_context(vmx); ret = 0; @@ -2605,7 +2804,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->emulation_required = 0; out: - srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; } @@ -2710,9 +2908,7 @@ static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) { if (!cpu_has_virtual_nmis()) return to_vmx(vcpu)->soft_vnmi_blocked; - else - return !!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - GUEST_INTR_STATE_NMI); + return vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI; } static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) @@ -2947,22 +3143,20 @@ static int handle_io(struct kvm_vcpu *vcpu) int size, in, string; unsigned port; - ++vcpu->stat.io_exits; exit_qualification = vmcs_readl(EXIT_QUALIFICATION); string = (exit_qualification & 16) != 0; + in = (exit_qualification & 8) != 0; - if (string) { - if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO) - return 0; - return 1; - } + ++vcpu->stat.io_exits; - size = (exit_qualification & 7) + 1; - in = (exit_qualification & 8) != 0; - port = exit_qualification >> 16; + if (string || in) + return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE; + port = exit_qualification >> 16; + size = (exit_qualification & 7) + 1; skip_emulated_instruction(vcpu); - return kvm_emulate_pio(vcpu, in, size, port); + + return kvm_fast_pio_out(vcpu, size, port); } static void @@ -2976,11 +3170,20 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) hypercall[2] = 0xc1; } +static void complete_insn_gp(struct kvm_vcpu *vcpu, int err) +{ + if (err) + kvm_inject_gp(vcpu, 0); + else + skip_emulated_instruction(vcpu); +} + static int handle_cr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification, val; int cr; int reg; + int err; exit_qualification = vmcs_readl(EXIT_QUALIFICATION); cr = exit_qualification & 15; @@ -2991,16 +3194,16 @@ static int handle_cr(struct kvm_vcpu *vcpu) trace_kvm_cr_write(cr, val); switch (cr) { case 0: - kvm_set_cr0(vcpu, val); - skip_emulated_instruction(vcpu); + err = kvm_set_cr0(vcpu, val); + complete_insn_gp(vcpu, err); return 1; case 3: - kvm_set_cr3(vcpu, val); - skip_emulated_instruction(vcpu); + err = kvm_set_cr3(vcpu, val); + complete_insn_gp(vcpu, err); return 1; case 4: - kvm_set_cr4(vcpu, val); - skip_emulated_instruction(vcpu); + err = kvm_set_cr4(vcpu, val); + complete_insn_gp(vcpu, err); return 1; case 8: { u8 cr8_prev = kvm_get_cr8(vcpu); @@ -3053,19 +3256,9 @@ static int handle_cr(struct kvm_vcpu *vcpu) return 0; } -static int check_dr_alias(struct kvm_vcpu *vcpu) -{ - if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) { - kvm_queue_exception(vcpu, UD_VECTOR); - return -1; - } - return 0; -} - static int handle_dr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; - unsigned long val; int dr, reg; /* Do not handle if the CPL > 0, will trigger GP on re-entry */ @@ -3100,67 +3293,20 @@ static int handle_dr(struct kvm_vcpu *vcpu) dr = exit_qualification & DEBUG_REG_ACCESS_NUM; reg = DEBUG_REG_ACCESS_REG(exit_qualification); if (exit_qualification & TYPE_MOV_FROM_DR) { - switch (dr) { - case 0 ... 3: - val = vcpu->arch.db[dr]; - break; - case 4: - if (check_dr_alias(vcpu) < 0) - return 1; - /* fall through */ - case 6: - val = vcpu->arch.dr6; - break; - case 5: - if (check_dr_alias(vcpu) < 0) - return 1; - /* fall through */ - default: /* 7 */ - val = vcpu->arch.dr7; - break; - } - kvm_register_write(vcpu, reg, val); - } else { - val = vcpu->arch.regs[reg]; - switch (dr) { - case 0 ... 3: - vcpu->arch.db[dr] = val; - if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) - vcpu->arch.eff_db[dr] = val; - break; - case 4: - if (check_dr_alias(vcpu) < 0) - return 1; - /* fall through */ - case 6: - if (val & 0xffffffff00000000ULL) { - kvm_inject_gp(vcpu, 0); - return 1; - } - vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1; - break; - case 5: - if (check_dr_alias(vcpu) < 0) - return 1; - /* fall through */ - default: /* 7 */ - if (val & 0xffffffff00000000ULL) { - kvm_inject_gp(vcpu, 0); - return 1; - } - vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; - if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { - vmcs_writel(GUEST_DR7, vcpu->arch.dr7); - vcpu->arch.switch_db_regs = - (val & DR7_BP_EN_MASK); - } - break; - } - } + unsigned long val; + if (!kvm_get_dr(vcpu, dr, &val)) + kvm_register_write(vcpu, reg, val); + } else + kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg]); skip_emulated_instruction(vcpu); return 1; } +static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) +{ + vmcs_writel(GUEST_DR7, val); +} + static int handle_cpuid(struct kvm_vcpu *vcpu) { kvm_emulate_cpuid(vcpu); @@ -3264,34 +3410,31 @@ static int handle_invlpg(struct kvm_vcpu *vcpu) static int handle_wbinvd(struct kvm_vcpu *vcpu) { skip_emulated_instruction(vcpu); - /* TODO: Add support for VT-d/pass-through device */ + kvm_emulate_wbinvd(vcpu); return 1; } -static int handle_apic_access(struct kvm_vcpu *vcpu) +static int handle_xsetbv(struct kvm_vcpu *vcpu) { - unsigned long exit_qualification; - enum emulation_result er; - unsigned long offset; + u64 new_bv = kvm_read_edx_eax(vcpu); + u32 index = kvm_register_read(vcpu, VCPU_REGS_RCX); - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - offset = exit_qualification & 0xffful; - - er = emulate_instruction(vcpu, 0, 0, 0); - - if (er != EMULATE_DONE) { - printk(KERN_ERR - "Fail to handle apic access vmexit! Offset is 0x%lx\n", - offset); - return -ENOEXEC; - } + if (kvm_set_xcr(vcpu, index, new_bv) == 0) + skip_emulated_instruction(vcpu); return 1; } +static int handle_apic_access(struct kvm_vcpu *vcpu) +{ + return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE; +} + static int handle_task_switch(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qualification; + bool has_error_code = false; + u32 error_code = 0; u16 tss_selector; int reason, type, idt_v; @@ -3314,6 +3457,13 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) kvm_clear_interrupt_queue(vcpu); break; case INTR_TYPE_HARD_EXCEPTION: + if (vmx->idt_vectoring_info & + VECTORING_INFO_DELIVER_CODE_MASK) { + has_error_code = true; + error_code = + vmcs_read32(IDT_VECTORING_ERROR_CODE); + } + /* fall through */ case INTR_TYPE_SOFT_EXCEPTION: kvm_clear_exception_queue(vcpu); break; @@ -3328,8 +3478,13 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) type != INTR_TYPE_NMI_INTR)) skip_emulated_instruction(vcpu); - if (!kvm_task_switch(vcpu, tss_selector, reason)) + if (kvm_task_switch(vcpu, tss_selector, reason, + has_error_code, error_code) == EMULATE_FAIL) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; return 0; + } /* clear all local breakpoint enable flags */ vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55); @@ -3483,13 +3638,8 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) goto out; } - if (err != EMULATE_DONE) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; - ret = 0; - goto out; - } + if (err != EMULATE_DONE) + return 0; if (signal_pending(current)) goto out; @@ -3552,6 +3702,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold, [EXIT_REASON_APIC_ACCESS] = handle_apic_access, [EXIT_REASON_WBINVD] = handle_wbinvd, + [EXIT_REASON_XSETBV] = handle_xsetbv, [EXIT_REASON_TASK_SWITCH] = handle_task_switch, [EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check, [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, @@ -3574,7 +3725,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; - trace_kvm_exit(exit_reason, kvm_rip_read(vcpu)); + trace_kvm_exit(exit_reason, vcpu); /* If guest state is invalid, start emulating */ if (vmx->emulation_required && emulate_invalid_guest_state) @@ -3585,6 +3736,13 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) if (enable_ept && is_paging(vcpu)) vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); + if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { + vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; + vcpu->run->fail_entry.hardware_entry_failure_reason + = exit_reason; + return 0; + } + if (unlikely(vmx->fail)) { vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; vcpu->run->fail_entry.hardware_entry_failure_reason @@ -3659,8 +3817,11 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx) /* We need to handle NMIs before interrupts are enabled */ if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR && - (exit_intr_info & INTR_INFO_VALID_MASK)) + (exit_intr_info & INTR_INFO_VALID_MASK)) { + kvm_before_handle_nmi(&vmx->vcpu); asm("int $2"); + kvm_after_handle_nmi(&vmx->vcpu); + } idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK; @@ -3787,11 +3948,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); - /* - * Loading guest fpu may have cleared host cr0.ts - */ - vmcs_writel(HOST_CR0, read_cr0()); - asm( /* Store host registers */ "push %%"R"dx; push %%"R"bp;" @@ -3920,16 +4076,26 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - spin_lock(&vmx_vpid_lock); - if (vmx->vpid != 0) - __clear_bit(vmx->vpid, vmx_vpid_bitmap); - spin_unlock(&vmx_vpid_lock); + free_vpid(vmx); vmx_free_vmcs(vcpu); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vmx); } +static inline void vmcs_init(struct vmcs *vmcs) +{ + u64 phys_addr = __pa(per_cpu(vmxarea, raw_smp_processor_id())); + + if (!vmm_exclusive) + kvm_cpu_vmxon(phys_addr); + + vmcs_clear(vmcs); + + if (!vmm_exclusive) + kvm_cpu_vmxoff(); +} + static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) { int err; @@ -3955,7 +4121,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx->vmcs) goto free_msrs; - vmcs_clear(vmx->vmcs); + vmcs_init(vmx->vmcs); cpu = get_cpu(); vmx_vcpu_load(&vmx->vcpu, cpu); @@ -3985,6 +4151,7 @@ free_msrs: uninit_vcpu: kvm_vcpu_uninit(&vmx->vcpu); free_vcpu: + free_vpid(vmx); kmem_cache_free(kvm_vcpu_cache, vmx); return ERR_PTR(err); } @@ -4115,6 +4282,10 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) } } +static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) +{ +} + static struct kvm_x86_ops vmx_x86_ops = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -4151,6 +4322,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .set_idt = vmx_set_idt, .get_gdt = vmx_get_gdt, .set_gdt = vmx_set_gdt, + .set_dr7 = vmx_set_dr7, .cache_reg = vmx_cache_reg, .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, @@ -4186,6 +4358,10 @@ static struct kvm_x86_ops vmx_x86_ops = { .cpuid_update = vmx_cpuid_update, .rdtscp_supported = vmx_rdtscp_supported, + + .set_supported_cpuid = vmx_set_supported_cpuid, + + .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, }; static int __init vmx_init(void) @@ -4233,7 +4409,8 @@ static int __init vmx_init(void) set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ - r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE); + r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), + __alignof__(struct vcpu_vmx), THIS_MODULE); if (r) goto out3; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c4f35b545c1..25f19078b32 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6,6 +6,7 @@ * Copyright (C) 2006 Qumranet, Inc. * Copyright (C) 2008 Qumranet, Inc. * Copyright IBM Corporation, 2008 + * Copyright 2010 Red Hat, Inc. and/or its affilates. * * Authors: * Avi Kivity <avi@qumranet.com> @@ -40,17 +41,20 @@ #include <linux/user-return-notifier.h> #include <linux/srcu.h> #include <linux/slab.h> +#include <linux/perf_event.h> +#include <linux/uaccess.h> #include <trace/events/kvm.h> -#undef TRACE_INCLUDE_FILE + #define CREATE_TRACE_POINTS #include "trace.h" #include <asm/debugreg.h> -#include <asm/uaccess.h> #include <asm/msr.h> #include <asm/desc.h> #include <asm/mtrr.h> #include <asm/mce.h> +#include <asm/i387.h> +#include <asm/xcr.h> #define MAX_IO_MSRS 256 #define CR0_RESERVED_BITS \ @@ -61,6 +65,7 @@ (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \ + | X86_CR4_OSXSAVE \ | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE)) #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) @@ -146,6 +151,13 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; +u64 __read_mostly host_xcr0; + +static inline u32 bit(int bitno) +{ + return 1 << (bitno & 31); +} + static void kvm_on_user_return(struct user_return_notifier *urn) { unsigned slot; @@ -223,34 +235,6 @@ static void drop_user_return_notifiers(void *ignore) kvm_on_user_return(&smsr->urn); } -unsigned long segment_base(u16 selector) -{ - struct descriptor_table gdt; - struct desc_struct *d; - unsigned long table_base; - unsigned long v; - - if (selector == 0) - return 0; - - kvm_get_gdt(&gdt); - table_base = gdt.base; - - if (selector & 4) { /* from ldt */ - u16 ldt_selector = kvm_read_ldt(); - - table_base = segment_base(ldt_selector); - } - d = (struct desc_struct *)(table_base + (selector & ~7)); - v = get_desc_base(d); -#ifdef CONFIG_X86_64 - if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) - v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32; -#endif - return v; -} -EXPORT_SYMBOL_GPL(segment_base); - u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) { if (irqchip_in_kernel(vcpu->kvm)) @@ -292,7 +276,8 @@ static int exception_class(int vector) } static void kvm_multiple_exception(struct kvm_vcpu *vcpu, - unsigned nr, bool has_error, u32 error_code) + unsigned nr, bool has_error, u32 error_code, + bool reinject) { u32 prev_nr; int class1, class2; @@ -303,6 +288,7 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, vcpu->arch.exception.has_error_code = has_error; vcpu->arch.exception.nr = nr; vcpu->arch.exception.error_code = error_code; + vcpu->arch.exception.reinject = reinject; return; } @@ -310,7 +296,7 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, prev_nr = vcpu->arch.exception.nr; if (prev_nr == DF_VECTOR) { /* triple fault -> shutdown */ - set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests); + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return; } class1 = exception_class(prev_nr); @@ -331,10 +317,16 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr) { - kvm_multiple_exception(vcpu, nr, false, 0); + kvm_multiple_exception(vcpu, nr, false, 0, false); } EXPORT_SYMBOL_GPL(kvm_queue_exception); +void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr) +{ + kvm_multiple_exception(vcpu, nr, false, 0, true); +} +EXPORT_SYMBOL_GPL(kvm_requeue_exception); + void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr, u32 error_code) { @@ -351,10 +343,16 @@ EXPORT_SYMBOL_GPL(kvm_inject_nmi); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) { - kvm_multiple_exception(vcpu, nr, true, error_code); + kvm_multiple_exception(vcpu, nr, true, error_code, false); } EXPORT_SYMBOL_GPL(kvm_queue_exception_e); +void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) +{ + kvm_multiple_exception(vcpu, nr, true, error_code, true); +} +EXPORT_SYMBOL_GPL(kvm_requeue_exception_e); + /* * Checks if cpl <= required_cpl; if true, return true. Otherwise queue * a #GP and return false. @@ -427,123 +425,163 @@ out: return changed; } -void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { + unsigned long old_cr0 = kvm_read_cr0(vcpu); + unsigned long update_bits = X86_CR0_PG | X86_CR0_WP | + X86_CR0_CD | X86_CR0_NW; + cr0 |= X86_CR0_ET; #ifdef CONFIG_X86_64 - if (cr0 & 0xffffffff00000000UL) { - kvm_inject_gp(vcpu, 0); - return; - } + if (cr0 & 0xffffffff00000000UL) + return 1; #endif cr0 &= ~CR0_RESERVED_BITS; - if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) { - kvm_inject_gp(vcpu, 0); - return; - } + if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) + return 1; - if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) { - kvm_inject_gp(vcpu, 0); - return; - } + if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) + return 1; if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { #ifdef CONFIG_X86_64 if ((vcpu->arch.efer & EFER_LME)) { int cs_db, cs_l; - if (!is_pae(vcpu)) { - kvm_inject_gp(vcpu, 0); - return; - } + if (!is_pae(vcpu)) + return 1; kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - if (cs_l) { - kvm_inject_gp(vcpu, 0); - return; - - } + if (cs_l) + return 1; } else #endif - if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3)) { - kvm_inject_gp(vcpu, 0); - return; - } - + if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3)) + return 1; } kvm_x86_ops->set_cr0(vcpu, cr0); - vcpu->arch.cr0 = cr0; - kvm_mmu_reset_context(vcpu); - return; + if ((cr0 ^ old_cr0) & update_bits) + kvm_mmu_reset_context(vcpu); + return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr0); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) { - kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0ful) | (msw & 0x0f)); + (void)kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f)); } EXPORT_SYMBOL_GPL(kvm_lmsw); -void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { - unsigned long old_cr4 = kvm_read_cr4(vcpu); - unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE; + u64 xcr0; - if (cr4 & CR4_RESERVED_BITS) { + /* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now */ + if (index != XCR_XFEATURE_ENABLED_MASK) + return 1; + xcr0 = xcr; + if (kvm_x86_ops->get_cpl(vcpu) != 0) + return 1; + if (!(xcr0 & XSTATE_FP)) + return 1; + if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE)) + return 1; + if (xcr0 & ~host_xcr0) + return 1; + vcpu->arch.xcr0 = xcr0; + vcpu->guest_xcr0_loaded = 0; + return 0; +} + +int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) +{ + if (__kvm_set_xcr(vcpu, index, xcr)) { kvm_inject_gp(vcpu, 0); + return 1; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_set_xcr); + +static bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + return best && (best->ecx & bit(X86_FEATURE_XSAVE)); +} + +static void update_cpuid(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + if (!best) return; + + /* Update OSXSAVE bit */ + if (cpu_has_xsave && best->function == 0x1) { + best->ecx &= ~(bit(X86_FEATURE_OSXSAVE)); + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) + best->ecx |= bit(X86_FEATURE_OSXSAVE); } +} + +int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + unsigned long old_cr4 = kvm_read_cr4(vcpu); + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE; + + if (cr4 & CR4_RESERVED_BITS) + return 1; + + if (!guest_cpuid_has_xsave(vcpu) && (cr4 & X86_CR4_OSXSAVE)) + return 1; if (is_long_mode(vcpu)) { - if (!(cr4 & X86_CR4_PAE)) { - kvm_inject_gp(vcpu, 0); - return; - } + if (!(cr4 & X86_CR4_PAE)) + return 1; } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) && ((cr4 ^ old_cr4) & pdptr_bits) - && !load_pdptrs(vcpu, vcpu->arch.cr3)) { - kvm_inject_gp(vcpu, 0); - return; - } + && !load_pdptrs(vcpu, vcpu->arch.cr3)) + return 1; + + if (cr4 & X86_CR4_VMXE) + return 1; - if (cr4 & X86_CR4_VMXE) { - kvm_inject_gp(vcpu, 0); - return; - } kvm_x86_ops->set_cr4(vcpu, cr4); - vcpu->arch.cr4 = cr4; - vcpu->arch.mmu.base_role.cr4_pge = (cr4 & X86_CR4_PGE) && !tdp_enabled; - kvm_mmu_reset_context(vcpu); + + if ((cr4 ^ old_cr4) & pdptr_bits) + kvm_mmu_reset_context(vcpu); + + if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE) + update_cpuid(vcpu); + + return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr4); -void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) +int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { if (cr3 == vcpu->arch.cr3 && !pdptrs_changed(vcpu)) { kvm_mmu_sync_roots(vcpu); kvm_mmu_flush_tlb(vcpu); - return; + return 0; } if (is_long_mode(vcpu)) { - if (cr3 & CR3_L_MODE_RESERVED_BITS) { - kvm_inject_gp(vcpu, 0); - return; - } + if (cr3 & CR3_L_MODE_RESERVED_BITS) + return 1; } else { if (is_pae(vcpu)) { - if (cr3 & CR3_PAE_RESERVED_BITS) { - kvm_inject_gp(vcpu, 0); - return; - } - if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) { - kvm_inject_gp(vcpu, 0); - return; - } + if (cr3 & CR3_PAE_RESERVED_BITS) + return 1; + if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) + return 1; } /* * We don't check reserved bits in nonpae mode, because @@ -561,24 +599,28 @@ void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) * to debug) behavior on the guest side. */ if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT))) - kvm_inject_gp(vcpu, 0); - else { - vcpu->arch.cr3 = cr3; - vcpu->arch.mmu.new_cr3(vcpu); - } + return 1; + vcpu->arch.cr3 = cr3; + vcpu->arch.mmu.new_cr3(vcpu); + return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr3); -void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) +int __kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) { - if (cr8 & CR8_RESERVED_BITS) { - kvm_inject_gp(vcpu, 0); - return; - } + if (cr8 & CR8_RESERVED_BITS) + return 1; if (irqchip_in_kernel(vcpu->kvm)) kvm_lapic_set_tpr(vcpu, cr8); else vcpu->arch.cr8 = cr8; + return 0; +} + +void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) +{ + if (__kvm_set_cr8(vcpu, cr8)) + kvm_inject_gp(vcpu, 0); } EXPORT_SYMBOL_GPL(kvm_set_cr8); @@ -591,11 +633,90 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_get_cr8); -static inline u32 bit(int bitno) +static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) { - return 1 << (bitno & 31); + switch (dr) { + case 0 ... 3: + vcpu->arch.db[dr] = val; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + vcpu->arch.eff_db[dr] = val; + break; + case 4: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; /* #UD */ + /* fall through */ + case 6: + if (val & 0xffffffff00000000ULL) + return -1; /* #GP */ + vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1; + break; + case 5: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; /* #UD */ + /* fall through */ + default: /* 7 */ + if (val & 0xffffffff00000000ULL) + return -1; /* #GP */ + vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { + kvm_x86_ops->set_dr7(vcpu, vcpu->arch.dr7); + vcpu->arch.switch_db_regs = (val & DR7_BP_EN_MASK); + } + break; + } + + return 0; +} + +int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) +{ + int res; + + res = __kvm_set_dr(vcpu, dr, val); + if (res > 0) + kvm_queue_exception(vcpu, UD_VECTOR); + else if (res < 0) + kvm_inject_gp(vcpu, 0); + + return res; +} +EXPORT_SYMBOL_GPL(kvm_set_dr); + +static int _kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +{ + switch (dr) { + case 0 ... 3: + *val = vcpu->arch.db[dr]; + break; + case 4: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; + /* fall through */ + case 6: + *val = vcpu->arch.dr6; + break; + case 5: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; + /* fall through */ + default: /* 7 */ + *val = vcpu->arch.dr7; + break; + } + + return 0; } +int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +{ + if (_kvm_get_dr(vcpu, dr, val)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_get_dr); + /* * List of msr numbers which we expose to userspace through KVM_GET_MSRS * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. @@ -605,13 +726,14 @@ static inline u32 bit(int bitno) * kvm-specific. Those are put in the beginning of the list. */ -#define KVM_SAVE_MSRS_BEGIN 5 +#define KVM_SAVE_MSRS_BEGIN 7 static u32 msrs_to_save[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, HV_X64_MSR_APIC_ASSIST_PAGE, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, - MSR_K6_STAR, + MSR_STAR, #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif @@ -622,50 +744,50 @@ static unsigned num_msrs_to_save; static u32 emulated_msrs[] = { MSR_IA32_MISC_ENABLE, + MSR_IA32_MCG_STATUS, + MSR_IA32_MCG_CTL, }; -static void set_efer(struct kvm_vcpu *vcpu, u64 efer) +static int set_efer(struct kvm_vcpu *vcpu, u64 efer) { - if (efer & efer_reserved_bits) { - kvm_inject_gp(vcpu, 0); - return; - } + u64 old_efer = vcpu->arch.efer; + + if (efer & efer_reserved_bits) + return 1; if (is_paging(vcpu) - && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) { - kvm_inject_gp(vcpu, 0); - return; - } + && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) + return 1; if (efer & EFER_FFXSR) { struct kvm_cpuid_entry2 *feat; feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); - if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) { - kvm_inject_gp(vcpu, 0); - return; - } + if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) + return 1; } if (efer & EFER_SVME) { struct kvm_cpuid_entry2 *feat; feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); - if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) { - kvm_inject_gp(vcpu, 0); - return; - } + if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) + return 1; } - kvm_x86_ops->set_efer(vcpu, efer); - efer &= ~EFER_LMA; efer |= vcpu->arch.efer & EFER_LMA; - vcpu->arch.efer = efer; + kvm_x86_ops->set_efer(vcpu, efer); vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled; kvm_mmu_reset_context(vcpu); + + /* Update reserved bits */ + if ((efer ^ old_efer) & EFER_NX) + kvm_mmu_reset_context(vcpu); + + return 0; } void kvm_enable_efer_bits(u64 mask) @@ -695,14 +817,22 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) { - static int version; + int version; + int r; struct pvclock_wall_clock wc; struct timespec boot; if (!wall_clock) return; - version++; + r = kvm_read_guest(kvm, wall_clock, &version, sizeof(version)); + if (r) + return; + + if (version & 1) + ++version; /* first time write, random junk */ + + ++version; kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); @@ -795,6 +925,8 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) vcpu->hv_clock.system_time = ts.tv_nsec + (NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset; + vcpu->hv_clock.flags = 0; + /* * The interface expects us to write an even number signaling that the * update is finished. Since the guest won't see the intermediate @@ -818,7 +950,7 @@ static int kvm_request_guest_time_update(struct kvm_vcpu *v) if (!vcpu->time_page) return 0; - set_bit(KVM_REQ_KVMCLOCK_UPDATE, &v->requests); + kvm_make_request(KVM_REQ_KVMCLOCK_UPDATE, v); return 1; } @@ -1086,10 +1218,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) { switch (msr) { case MSR_EFER: - set_efer(vcpu, data); - break; + return set_efer(vcpu, data); case MSR_K7_HWCR: data &= ~(u64)0x40; /* ignore flush filter disable */ + data &= ~(u64)0x100; /* ignore ignne emulation enable */ if (data != 0) { pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", data); @@ -1132,10 +1264,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) case MSR_IA32_MISC_ENABLE: vcpu->arch.ia32_misc_enable_msr = data; break; + case MSR_KVM_WALL_CLOCK_NEW: case MSR_KVM_WALL_CLOCK: vcpu->kvm->arch.wall_clock = data; kvm_write_wall_clock(vcpu->kvm, data); break; + case MSR_KVM_SYSTEM_TIME_NEW: case MSR_KVM_SYSTEM_TIME: { if (vcpu->arch.time_page) { kvm_release_page_dirty(vcpu->arch.time_page); @@ -1407,9 +1541,11 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) data = vcpu->arch.efer; break; case MSR_KVM_WALL_CLOCK: + case MSR_KVM_WALL_CLOCK_NEW: data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_SYSTEM_TIME: + case MSR_KVM_SYSTEM_TIME_NEW: data = vcpu->arch.time; break; case MSR_IA32_P5_MC_ADDR: @@ -1456,16 +1592,12 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, { int i, idx; - vcpu_load(vcpu); - idx = srcu_read_lock(&vcpu->kvm->srcu); for (i = 0; i < msrs->nmsrs; ++i) if (do_msr(vcpu, entries[i].index, &entries[i].data)) break; srcu_read_unlock(&vcpu->kvm->srcu, idx); - vcpu_put(vcpu); - return i; } @@ -1494,7 +1626,7 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, r = -ENOMEM; size = sizeof(struct kvm_msr_entry) * msrs.nmsrs; - entries = vmalloc(size); + entries = kmalloc(size, GFP_KERNEL); if (!entries) goto out; @@ -1513,7 +1645,7 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, r = n; out_free: - vfree(entries); + kfree(entries); out: return r; } @@ -1548,7 +1680,9 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: case KVM_CAP_PCI_SEGMENT: + case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: + case KVM_CAP_XSAVE: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -1572,6 +1706,9 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_MCE: r = KVM_MAX_MCE_BANKS; break; + case KVM_CAP_XCRS: + r = cpu_has_xsave; + break; default: r = 0; break; @@ -1648,8 +1785,28 @@ out: return r; } +static void wbinvd_ipi(void *garbage) +{ + wbinvd(); +} + +static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu) +{ + return vcpu->kvm->arch.iommu_domain && + !(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY); +} + void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { + /* Address WBINVD may be executed by guest */ + if (need_emulate_wbinvd(vcpu)) { + if (kvm_x86_ops->has_wbinvd_exit()) + cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); + else if (vcpu->cpu != -1 && vcpu->cpu != cpu) + smp_call_function_single(vcpu->cpu, + wbinvd_ipi, NULL, 1); + } + kvm_x86_ops->vcpu_load(vcpu, cpu); if (unlikely(per_cpu(cpu_tsc_khz, cpu) == 0)) { unsigned long khz = cpufreq_quick_get(cpu); @@ -1662,8 +1819,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { - kvm_put_guest_fpu(vcpu); kvm_x86_ops->vcpu_put(vcpu); + kvm_put_guest_fpu(vcpu); } static int is_efer_nx(void) @@ -1712,7 +1869,6 @@ static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, if (copy_from_user(cpuid_entries, entries, cpuid->nent * sizeof(struct kvm_cpuid_entry))) goto out_free; - vcpu_load(vcpu); for (i = 0; i < cpuid->nent; i++) { vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function; vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax; @@ -1730,7 +1886,7 @@ static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, r = 0; kvm_apic_set_version(vcpu); kvm_x86_ops->cpuid_update(vcpu); - vcpu_put(vcpu); + update_cpuid(vcpu); out_free: vfree(cpuid_entries); @@ -1751,11 +1907,10 @@ static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, if (copy_from_user(&vcpu->arch.cpuid_entries, entries, cpuid->nent * sizeof(struct kvm_cpuid_entry2))) goto out; - vcpu_load(vcpu); vcpu->arch.cpuid_nent = cpuid->nent; kvm_apic_set_version(vcpu); kvm_x86_ops->cpuid_update(vcpu); - vcpu_put(vcpu); + update_cpuid(vcpu); return 0; out: @@ -1830,13 +1985,13 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW); /* cpuid 1.ecx */ const u32 kvm_supported_word4_x86_features = - F(XMM3) | 0 /* Reserved, DTES64, MONITOR */ | + F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | 0 /* DS-CPL, VMX, SMX, EST */ | 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | 0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ | 0 /* Reserved, DCA */ | F(XMM4_1) | F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | - 0 /* Reserved, XSAVE, OSXSAVE */; + 0 /* Reserved, AES */ | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX); /* cpuid 0x80000001.ecx */ const u32 kvm_supported_word6_x86_features = F(LAHF_LM) | F(CMP_LEGACY) | F(SVM) | 0 /* ExtApicSpace */ | @@ -1851,7 +2006,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, switch (function) { case 0: - entry->eax = min(entry->eax, (u32)0xb); + entry->eax = min(entry->eax, (u32)0xd); break; case 1: entry->edx &= kvm_supported_word0_x86_features; @@ -1909,6 +2064,38 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, } break; } + case 0xd: { + int i; + + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + for (i = 1; *nent < maxnent; ++i) { + if (entry[i - 1].eax == 0 && i != 2) + break; + do_cpuid_1_ent(&entry[i], function, i); + entry[i].flags |= + KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + ++*nent; + } + break; + } + case KVM_CPUID_SIGNATURE: { + char signature[12] = "KVMKVMKVM\0\0"; + u32 *sigptr = (u32 *)signature; + entry->eax = 0; + entry->ebx = sigptr[0]; + entry->ecx = sigptr[1]; + entry->edx = sigptr[2]; + break; + } + case KVM_CPUID_FEATURES: + entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) | + (1 << KVM_FEATURE_NOP_IO_DELAY) | + (1 << KVM_FEATURE_CLOCKSOURCE2) | + (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT); + entry->ebx = 0; + entry->ecx = 0; + entry->edx = 0; + break; case 0x80000000: entry->eax = min(entry->eax, 0x8000001a); break; @@ -1917,6 +2104,9 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx &= kvm_supported_word6_x86_features; break; } + + kvm_x86_ops->set_supported_cpuid(function, entry); + put_cpu(); } @@ -1952,6 +2142,23 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func) do_cpuid_ent(&cpuid_entries[nent], func, 0, &nent, cpuid->nent); + + + + r = -E2BIG; + if (nent >= cpuid->nent) + goto out_free; + + do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_SIGNATURE, 0, &nent, + cpuid->nent); + + r = -E2BIG; + if (nent >= cpuid->nent) + goto out_free; + + do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_FEATURES, 0, &nent, + cpuid->nent); + r = -E2BIG; if (nent >= cpuid->nent) goto out_free; @@ -1972,9 +2179,7 @@ out: static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - vcpu_load(vcpu); memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s); - vcpu_put(vcpu); return 0; } @@ -1982,11 +2187,9 @@ static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - vcpu_load(vcpu); memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s); kvm_apic_post_state_restore(vcpu); update_cr8_intercept(vcpu); - vcpu_put(vcpu); return 0; } @@ -1998,20 +2201,15 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, return -EINVAL; if (irqchip_in_kernel(vcpu->kvm)) return -ENXIO; - vcpu_load(vcpu); kvm_queue_interrupt(vcpu, irq->irq, false); - vcpu_put(vcpu); - return 0; } static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu) { - vcpu_load(vcpu); kvm_inject_nmi(vcpu); - vcpu_put(vcpu); return 0; } @@ -2077,7 +2275,7 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, printk(KERN_DEBUG "kvm: set_mce: " "injects mce exception while " "previous one is in progress!\n"); - set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests); + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return 0; } if (banks[1] & MCI_STATUS_VAL) @@ -2102,16 +2300,20 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { - vcpu_load(vcpu); - - events->exception.injected = vcpu->arch.exception.pending; + events->exception.injected = + vcpu->arch.exception.pending && + !kvm_exception_is_soft(vcpu->arch.exception.nr); events->exception.nr = vcpu->arch.exception.nr; events->exception.has_error_code = vcpu->arch.exception.has_error_code; events->exception.error_code = vcpu->arch.exception.error_code; - events->interrupt.injected = vcpu->arch.interrupt.pending; + events->interrupt.injected = + vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft; events->interrupt.nr = vcpu->arch.interrupt.nr; - events->interrupt.soft = vcpu->arch.interrupt.soft; + events->interrupt.soft = 0; + events->interrupt.shadow = + kvm_x86_ops->get_interrupt_shadow(vcpu, + KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI); events->nmi.injected = vcpu->arch.nmi_injected; events->nmi.pending = vcpu->arch.nmi_pending; @@ -2120,20 +2322,18 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->sipi_vector = vcpu->arch.sipi_vector; events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING - | KVM_VCPUEVENT_VALID_SIPI_VECTOR); - - vcpu_put(vcpu); + | KVM_VCPUEVENT_VALID_SIPI_VECTOR + | KVM_VCPUEVENT_VALID_SHADOW); } static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING - | KVM_VCPUEVENT_VALID_SIPI_VECTOR)) + | KVM_VCPUEVENT_VALID_SIPI_VECTOR + | KVM_VCPUEVENT_VALID_SHADOW)) return -EINVAL; - vcpu_load(vcpu); - vcpu->arch.exception.pending = events->exception.injected; vcpu->arch.exception.nr = events->exception.nr; vcpu->arch.exception.has_error_code = events->exception.has_error_code; @@ -2144,6 +2344,9 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.interrupt.soft = events->interrupt.soft; if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm)) kvm_pic_clear_isr_ack(vcpu->kvm); + if (events->flags & KVM_VCPUEVENT_VALID_SHADOW) + kvm_x86_ops->set_interrupt_shadow(vcpu, + events->interrupt.shadow); vcpu->arch.nmi_injected = events->nmi.injected; if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) @@ -2153,34 +2356,131 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR) vcpu->arch.sipi_vector = events->sipi_vector; - vcpu_put(vcpu); + return 0; +} + +static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, + struct kvm_debugregs *dbgregs) +{ + memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); + dbgregs->dr6 = vcpu->arch.dr6; + dbgregs->dr7 = vcpu->arch.dr7; + dbgregs->flags = 0; +} + +static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, + struct kvm_debugregs *dbgregs) +{ + if (dbgregs->flags) + return -EINVAL; + + memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); + vcpu->arch.dr6 = dbgregs->dr6; + vcpu->arch.dr7 = dbgregs->dr7; return 0; } +static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) +{ + if (cpu_has_xsave) + memcpy(guest_xsave->region, + &vcpu->arch.guest_fpu.state->xsave, + sizeof(struct xsave_struct)); + else { + memcpy(guest_xsave->region, + &vcpu->arch.guest_fpu.state->fxsave, + sizeof(struct i387_fxsave_struct)); + *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] = + XSTATE_FPSSE; + } +} + +static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) +{ + u64 xstate_bv = + *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; + + if (cpu_has_xsave) + memcpy(&vcpu->arch.guest_fpu.state->xsave, + guest_xsave->region, sizeof(struct xsave_struct)); + else { + if (xstate_bv & ~XSTATE_FPSSE) + return -EINVAL; + memcpy(&vcpu->arch.guest_fpu.state->fxsave, + guest_xsave->region, sizeof(struct i387_fxsave_struct)); + } + return 0; +} + +static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, + struct kvm_xcrs *guest_xcrs) +{ + if (!cpu_has_xsave) { + guest_xcrs->nr_xcrs = 0; + return; + } + + guest_xcrs->nr_xcrs = 1; + guest_xcrs->flags = 0; + guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK; + guest_xcrs->xcrs[0].value = vcpu->arch.xcr0; +} + +static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, + struct kvm_xcrs *guest_xcrs) +{ + int i, r = 0; + + if (!cpu_has_xsave) + return -EINVAL; + + if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags) + return -EINVAL; + + for (i = 0; i < guest_xcrs->nr_xcrs; i++) + /* Only support XCR0 currently */ + if (guest_xcrs->xcrs[0].xcr == XCR_XFEATURE_ENABLED_MASK) { + r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK, + guest_xcrs->xcrs[0].value); + break; + } + if (r) + r = -EINVAL; + return r; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; int r; - struct kvm_lapic_state *lapic = NULL; + union { + struct kvm_lapic_state *lapic; + struct kvm_xsave *xsave; + struct kvm_xcrs *xcrs; + void *buffer; + } u; + u.buffer = NULL; switch (ioctl) { case KVM_GET_LAPIC: { r = -EINVAL; if (!vcpu->arch.apic) goto out; - lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); + u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); r = -ENOMEM; - if (!lapic) + if (!u.lapic) goto out; - r = kvm_vcpu_ioctl_get_lapic(vcpu, lapic); + r = kvm_vcpu_ioctl_get_lapic(vcpu, u.lapic); if (r) goto out; r = -EFAULT; - if (copy_to_user(argp, lapic, sizeof(struct kvm_lapic_state))) + if (copy_to_user(argp, u.lapic, sizeof(struct kvm_lapic_state))) goto out; r = 0; break; @@ -2189,14 +2489,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; if (!vcpu->arch.apic) goto out; - lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); + u.lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); r = -ENOMEM; - if (!lapic) + if (!u.lapic) goto out; r = -EFAULT; - if (copy_from_user(lapic, argp, sizeof(struct kvm_lapic_state))) + if (copy_from_user(u.lapic, argp, sizeof(struct kvm_lapic_state))) goto out; - r = kvm_vcpu_ioctl_set_lapic(vcpu, lapic); + r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic); if (r) goto out; r = 0; @@ -2336,11 +2636,90 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); break; } + case KVM_GET_DEBUGREGS: { + struct kvm_debugregs dbgregs; + + kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs); + + r = -EFAULT; + if (copy_to_user(argp, &dbgregs, + sizeof(struct kvm_debugregs))) + break; + r = 0; + break; + } + case KVM_SET_DEBUGREGS: { + struct kvm_debugregs dbgregs; + + r = -EFAULT; + if (copy_from_user(&dbgregs, argp, + sizeof(struct kvm_debugregs))) + break; + + r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs); + break; + } + case KVM_GET_XSAVE: { + u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL); + r = -ENOMEM; + if (!u.xsave) + break; + + kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave); + + r = -EFAULT; + if (copy_to_user(argp, u.xsave, sizeof(struct kvm_xsave))) + break; + r = 0; + break; + } + case KVM_SET_XSAVE: { + u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL); + r = -ENOMEM; + if (!u.xsave) + break; + + r = -EFAULT; + if (copy_from_user(u.xsave, argp, sizeof(struct kvm_xsave))) + break; + + r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave); + break; + } + case KVM_GET_XCRS: { + u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL); + r = -ENOMEM; + if (!u.xcrs) + break; + + kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs); + + r = -EFAULT; + if (copy_to_user(argp, u.xcrs, + sizeof(struct kvm_xcrs))) + break; + r = 0; + break; + } + case KVM_SET_XCRS: { + u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL); + r = -ENOMEM; + if (!u.xcrs) + break; + + r = -EFAULT; + if (copy_from_user(u.xcrs, argp, + sizeof(struct kvm_xcrs))) + break; + + r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs); + break; + } default: r = -EINVAL; } out: - kfree(lapic); + kfree(u.buffer); return r; } @@ -2383,115 +2762,6 @@ static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) return kvm->arch.n_alloc_mmu_pages; } -gfn_t unalias_gfn_instantiation(struct kvm *kvm, gfn_t gfn) -{ - int i; - struct kvm_mem_alias *alias; - struct kvm_mem_aliases *aliases; - - aliases = rcu_dereference(kvm->arch.aliases); - - for (i = 0; i < aliases->naliases; ++i) { - alias = &aliases->aliases[i]; - if (alias->flags & KVM_ALIAS_INVALID) - continue; - if (gfn >= alias->base_gfn - && gfn < alias->base_gfn + alias->npages) - return alias->target_gfn + gfn - alias->base_gfn; - } - return gfn; -} - -gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) -{ - int i; - struct kvm_mem_alias *alias; - struct kvm_mem_aliases *aliases; - - aliases = rcu_dereference(kvm->arch.aliases); - - for (i = 0; i < aliases->naliases; ++i) { - alias = &aliases->aliases[i]; - if (gfn >= alias->base_gfn - && gfn < alias->base_gfn + alias->npages) - return alias->target_gfn + gfn - alias->base_gfn; - } - return gfn; -} - -/* - * Set a new alias region. Aliases map a portion of physical memory into - * another portion. This is useful for memory windows, for example the PC - * VGA region. - */ -static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, - struct kvm_memory_alias *alias) -{ - int r, n; - struct kvm_mem_alias *p; - struct kvm_mem_aliases *aliases, *old_aliases; - - r = -EINVAL; - /* General sanity checks */ - if (alias->memory_size & (PAGE_SIZE - 1)) - goto out; - if (alias->guest_phys_addr & (PAGE_SIZE - 1)) - goto out; - if (alias->slot >= KVM_ALIAS_SLOTS) - goto out; - if (alias->guest_phys_addr + alias->memory_size - < alias->guest_phys_addr) - goto out; - if (alias->target_phys_addr + alias->memory_size - < alias->target_phys_addr) - goto out; - - r = -ENOMEM; - aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL); - if (!aliases) - goto out; - - mutex_lock(&kvm->slots_lock); - - /* invalidate any gfn reference in case of deletion/shrinking */ - memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases)); - aliases->aliases[alias->slot].flags |= KVM_ALIAS_INVALID; - old_aliases = kvm->arch.aliases; - rcu_assign_pointer(kvm->arch.aliases, aliases); - synchronize_srcu_expedited(&kvm->srcu); - kvm_mmu_zap_all(kvm); - kfree(old_aliases); - - r = -ENOMEM; - aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL); - if (!aliases) - goto out_unlock; - - memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases)); - - p = &aliases->aliases[alias->slot]; - p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT; - p->npages = alias->memory_size >> PAGE_SHIFT; - p->target_gfn = alias->target_phys_addr >> PAGE_SHIFT; - p->flags &= ~(KVM_ALIAS_INVALID); - - for (n = KVM_ALIAS_SLOTS; n > 0; --n) - if (aliases->aliases[n - 1].npages) - break; - aliases->naliases = n; - - old_aliases = kvm->arch.aliases; - rcu_assign_pointer(kvm->arch.aliases, aliases); - synchronize_srcu_expedited(&kvm->srcu); - kfree(old_aliases); - r = 0; - -out_unlock: - mutex_unlock(&kvm->slots_lock); -out: - return r; -} - static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) { int r; @@ -2620,7 +2890,6 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot; unsigned long n; unsigned long is_dirty = 0; - unsigned long *dirty_bitmap = NULL; mutex_lock(&kvm->slots_lock); @@ -2635,27 +2904,30 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, n = kvm_dirty_bitmap_bytes(memslot); - r = -ENOMEM; - dirty_bitmap = vmalloc(n); - if (!dirty_bitmap) - goto out; - memset(dirty_bitmap, 0, n); - for (i = 0; !is_dirty && i < n/sizeof(long); i++) is_dirty = memslot->dirty_bitmap[i]; /* If nothing is dirty, don't bother messing with page tables. */ if (is_dirty) { struct kvm_memslots *slots, *old_slots; + unsigned long *dirty_bitmap; spin_lock(&kvm->mmu_lock); kvm_mmu_slot_remove_write_access(kvm, log->slot); spin_unlock(&kvm->mmu_lock); - slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); - if (!slots) - goto out_free; + r = -ENOMEM; + dirty_bitmap = vmalloc(n); + if (!dirty_bitmap) + goto out; + memset(dirty_bitmap, 0, n); + r = -ENOMEM; + slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + if (!slots) { + vfree(dirty_bitmap); + goto out; + } memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); slots->memslots[log->slot].dirty_bitmap = dirty_bitmap; @@ -2664,13 +2936,20 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, synchronize_srcu_expedited(&kvm->srcu); dirty_bitmap = old_slots->memslots[log->slot].dirty_bitmap; kfree(old_slots); + + r = -EFAULT; + if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n)) { + vfree(dirty_bitmap); + goto out; + } + vfree(dirty_bitmap); + } else { + r = -EFAULT; + if (clear_user(log->dirty_bitmap, n)) + goto out; } r = 0; - if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n)) - r = -EFAULT; -out_free: - vfree(dirty_bitmap); out: mutex_unlock(&kvm->slots_lock); return r; @@ -2690,7 +2969,6 @@ long kvm_arch_vm_ioctl(struct file *filp, union { struct kvm_pit_state ps; struct kvm_pit_state2 ps2; - struct kvm_memory_alias alias; struct kvm_pit_config pit_config; } u; @@ -2711,22 +2989,6 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; break; } - case KVM_SET_MEMORY_REGION: { - struct kvm_memory_region kvm_mem; - struct kvm_userspace_memory_region kvm_userspace_mem; - - r = -EFAULT; - if (copy_from_user(&kvm_mem, argp, sizeof kvm_mem)) - goto out; - kvm_userspace_mem.slot = kvm_mem.slot; - kvm_userspace_mem.flags = kvm_mem.flags; - kvm_userspace_mem.guest_phys_addr = kvm_mem.guest_phys_addr; - kvm_userspace_mem.memory_size = kvm_mem.memory_size; - r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 0); - if (r) - goto out; - break; - } case KVM_SET_NR_MMU_PAGES: r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg); if (r) @@ -2735,14 +2997,6 @@ long kvm_arch_vm_ioctl(struct file *filp, case KVM_GET_NR_MMU_PAGES: r = kvm_vm_ioctl_get_nr_mmu_pages(kvm); break; - case KVM_SET_MEMORY_ALIAS: - r = -EFAULT; - if (copy_from_user(&u.alias, argp, sizeof(struct kvm_memory_alias))) - goto out; - r = kvm_vm_ioctl_set_memory_alias(kvm, &u.alias); - if (r) - goto out; - break; case KVM_CREATE_IRQCHIP: { struct kvm_pic *vpic; @@ -2803,11 +3057,13 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&irq_event, argp, sizeof irq_event)) goto out; + r = -ENXIO; if (irqchip_in_kernel(kvm)) { __s32 status; status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); if (ioctl == KVM_IRQ_LINE_STATUS) { + r = -EFAULT; irq_event.status = status; if (copy_to_user(argp, &irq_event, sizeof irq_event)) @@ -3023,6 +3279,18 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) return kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, len, v); } +static void kvm_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + kvm_x86_ops->set_segment(vcpu, var, seg); +} + +void kvm_get_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + kvm_x86_ops->get_segment(vcpu, var, seg); +} + gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error) { u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; @@ -3068,7 +3336,7 @@ static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, } ret = kvm_read_guest(vcpu->kvm, gpa, data, toread); if (ret < 0) { - r = X86EMUL_UNHANDLEABLE; + r = X86EMUL_IO_NEEDED; goto out; } @@ -3103,14 +3371,17 @@ static int kvm_read_guest_virt_system(gva_t addr, void *val, unsigned int bytes, return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, error); } -static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes, - struct kvm_vcpu *vcpu, u32 *error) +static int kvm_write_guest_virt_system(gva_t addr, void *val, + unsigned int bytes, + struct kvm_vcpu *vcpu, + u32 *error) { void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, error); + gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr, + PFERR_WRITE_MASK, error); unsigned offset = addr & (PAGE_SIZE-1); unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; @@ -3121,7 +3392,7 @@ static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes, } ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite); if (ret < 0) { - r = X86EMUL_UNHANDLEABLE; + r = X86EMUL_IO_NEEDED; goto out; } @@ -3133,14 +3404,13 @@ out: return r; } - static int emulator_read_emulated(unsigned long addr, void *val, unsigned int bytes, + unsigned int *error_code, struct kvm_vcpu *vcpu) { gpa_t gpa; - u32 error_code; if (vcpu->mmio_read_completed) { memcpy(val, vcpu->mmio_data, bytes); @@ -3150,12 +3420,10 @@ static int emulator_read_emulated(unsigned long addr, return X86EMUL_CONTINUE; } - gpa = kvm_mmu_gva_to_gpa_read(vcpu, addr, &error_code); + gpa = kvm_mmu_gva_to_gpa_read(vcpu, addr, error_code); - if (gpa == UNMAPPED_GVA) { - kvm_inject_page_fault(vcpu, addr, error_code); + if (gpa == UNMAPPED_GVA) return X86EMUL_PROPAGATE_FAULT; - } /* For APIC access vmexit */ if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) @@ -3177,11 +3445,12 @@ mmio: trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0); vcpu->mmio_needed = 1; - vcpu->mmio_phys_addr = gpa; - vcpu->mmio_size = bytes; - vcpu->mmio_is_write = 0; + vcpu->run->exit_reason = KVM_EXIT_MMIO; + vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa; + vcpu->run->mmio.len = vcpu->mmio_size = bytes; + vcpu->run->mmio.is_write = vcpu->mmio_is_write = 0; - return X86EMUL_UNHANDLEABLE; + return X86EMUL_IO_NEEDED; } int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, @@ -3199,17 +3468,15 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, static int emulator_write_emulated_onepage(unsigned long addr, const void *val, unsigned int bytes, + unsigned int *error_code, struct kvm_vcpu *vcpu) { gpa_t gpa; - u32 error_code; - gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, &error_code); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, error_code); - if (gpa == UNMAPPED_GVA) { - kvm_inject_page_fault(vcpu, addr, error_code); + if (gpa == UNMAPPED_GVA) return X86EMUL_PROPAGATE_FAULT; - } /* For APIC access vmexit */ if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) @@ -3227,72 +3494,185 @@ mmio: return X86EMUL_CONTINUE; vcpu->mmio_needed = 1; - vcpu->mmio_phys_addr = gpa; - vcpu->mmio_size = bytes; - vcpu->mmio_is_write = 1; - memcpy(vcpu->mmio_data, val, bytes); + vcpu->run->exit_reason = KVM_EXIT_MMIO; + vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa; + vcpu->run->mmio.len = vcpu->mmio_size = bytes; + vcpu->run->mmio.is_write = vcpu->mmio_is_write = 1; + memcpy(vcpu->run->mmio.data, val, bytes); return X86EMUL_CONTINUE; } int emulator_write_emulated(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) + const void *val, + unsigned int bytes, + unsigned int *error_code, + struct kvm_vcpu *vcpu) { /* Crossing a page boundary? */ if (((addr + bytes - 1) ^ addr) & PAGE_MASK) { int rc, now; now = -addr & ~PAGE_MASK; - rc = emulator_write_emulated_onepage(addr, val, now, vcpu); + rc = emulator_write_emulated_onepage(addr, val, now, error_code, + vcpu); if (rc != X86EMUL_CONTINUE) return rc; addr += now; val += now; bytes -= now; } - return emulator_write_emulated_onepage(addr, val, bytes, vcpu); + return emulator_write_emulated_onepage(addr, val, bytes, error_code, + vcpu); } -EXPORT_SYMBOL_GPL(emulator_write_emulated); + +#define CMPXCHG_TYPE(t, ptr, old, new) \ + (cmpxchg((t *)(ptr), *(t *)(old), *(t *)(new)) == *(t *)(old)) + +#ifdef CONFIG_X86_64 +# define CMPXCHG64(ptr, old, new) CMPXCHG_TYPE(u64, ptr, old, new) +#else +# define CMPXCHG64(ptr, old, new) \ + (cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old)) +#endif static int emulator_cmpxchg_emulated(unsigned long addr, const void *old, const void *new, unsigned int bytes, + unsigned int *error_code, struct kvm_vcpu *vcpu) { - printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); -#ifndef CONFIG_X86_64 - /* guests cmpxchg8b have to be emulated atomically */ - if (bytes == 8) { - gpa_t gpa; - struct page *page; - char *kaddr; - u64 val; + gpa_t gpa; + struct page *page; + char *kaddr; + bool exchanged; - gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL); + /* guests cmpxchg8b have to be emulated atomically */ + if (bytes > 8 || (bytes & (bytes - 1))) + goto emul_write; - if (gpa == UNMAPPED_GVA || - (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) - goto emul_write; + gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL); - if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) - goto emul_write; + if (gpa == UNMAPPED_GVA || + (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + goto emul_write; - val = *(u64 *)new; + if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) + goto emul_write; - page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + if (is_error_page(page)) { + kvm_release_page_clean(page); + goto emul_write; + } - kaddr = kmap_atomic(page, KM_USER0); - set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val); - kunmap_atomic(kaddr, KM_USER0); - kvm_release_page_dirty(page); + kaddr = kmap_atomic(page, KM_USER0); + kaddr += offset_in_page(gpa); + switch (bytes) { + case 1: + exchanged = CMPXCHG_TYPE(u8, kaddr, old, new); + break; + case 2: + exchanged = CMPXCHG_TYPE(u16, kaddr, old, new); + break; + case 4: + exchanged = CMPXCHG_TYPE(u32, kaddr, old, new); + break; + case 8: + exchanged = CMPXCHG64(kaddr, old, new); + break; + default: + BUG(); } + kunmap_atomic(kaddr, KM_USER0); + kvm_release_page_dirty(page); + + if (!exchanged) + return X86EMUL_CMPXCHG_FAILED; + + kvm_mmu_pte_write(vcpu, gpa, new, bytes, 1); + + return X86EMUL_CONTINUE; + emul_write: -#endif + printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); + + return emulator_write_emulated(addr, new, bytes, error_code, vcpu); +} + +static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) +{ + /* TODO: String I/O for in kernel device */ + int r; - return emulator_write_emulated(addr, new, bytes, vcpu); + if (vcpu->arch.pio.in) + r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port, + vcpu->arch.pio.size, pd); + else + r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, + vcpu->arch.pio.port, vcpu->arch.pio.size, + pd); + return r; +} + + +static int emulator_pio_in_emulated(int size, unsigned short port, void *val, + unsigned int count, struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.pio.count) + goto data_avail; + + trace_kvm_pio(1, port, size, 1); + + vcpu->arch.pio.port = port; + vcpu->arch.pio.in = 1; + vcpu->arch.pio.count = count; + vcpu->arch.pio.size = size; + + if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { + data_avail: + memcpy(val, vcpu->arch.pio_data, size * count); + vcpu->arch.pio.count = 0; + return 1; + } + + vcpu->run->exit_reason = KVM_EXIT_IO; + vcpu->run->io.direction = KVM_EXIT_IO_IN; + vcpu->run->io.size = size; + vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; + vcpu->run->io.count = count; + vcpu->run->io.port = port; + + return 0; +} + +static int emulator_pio_out_emulated(int size, unsigned short port, + const void *val, unsigned int count, + struct kvm_vcpu *vcpu) +{ + trace_kvm_pio(0, port, size, 1); + + vcpu->arch.pio.port = port; + vcpu->arch.pio.in = 0; + vcpu->arch.pio.count = count; + vcpu->arch.pio.size = size; + + memcpy(vcpu->arch.pio_data, val, size * count); + + if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { + vcpu->arch.pio.count = 0; + return 1; + } + + vcpu->run->exit_reason = KVM_EXIT_IO; + vcpu->run->io.direction = KVM_EXIT_IO_OUT; + vcpu->run->io.size = size; + vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; + vcpu->run->io.count = count; + vcpu->run->io.port = port; + + return 0; } static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) @@ -3306,6 +3686,21 @@ int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address) return X86EMUL_CONTINUE; } +int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) +{ + if (!need_emulate_wbinvd(vcpu)) + return X86EMUL_CONTINUE; + + if (kvm_x86_ops->has_wbinvd_exit()) { + smp_call_function_many(vcpu->arch.wbinvd_dirty_mask, + wbinvd_ipi, NULL, 1); + cpumask_clear(vcpu->arch.wbinvd_dirty_mask); + } + wbinvd(); + return X86EMUL_CONTINUE; +} +EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd); + int emulate_clts(struct kvm_vcpu *vcpu) { kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); @@ -3313,42 +3708,188 @@ int emulate_clts(struct kvm_vcpu *vcpu) return X86EMUL_CONTINUE; } -int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) +int emulator_get_dr(int dr, unsigned long *dest, struct kvm_vcpu *vcpu) { - return kvm_x86_ops->get_dr(ctxt->vcpu, dr, dest); + return _kvm_get_dr(vcpu, dr, dest); } -int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) +int emulator_set_dr(int dr, unsigned long value, struct kvm_vcpu *vcpu) { - unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U; - return kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask); + return __kvm_set_dr(vcpu, dr, value); } -void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) +static u64 mk_cr_64(u64 curr_cr, u32 new_val) { - u8 opcodes[4]; - unsigned long rip = kvm_rip_read(vcpu); - unsigned long rip_linear; + return (curr_cr & ~((1ULL << 32) - 1)) | new_val; +} - if (!printk_ratelimit()) - return; +static unsigned long emulator_get_cr(int cr, struct kvm_vcpu *vcpu) +{ + unsigned long value; - rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS); + switch (cr) { + case 0: + value = kvm_read_cr0(vcpu); + break; + case 2: + value = vcpu->arch.cr2; + break; + case 3: + value = vcpu->arch.cr3; + break; + case 4: + value = kvm_read_cr4(vcpu); + break; + case 8: + value = kvm_get_cr8(vcpu); + break; + default: + vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); + return 0; + } + + return value; +} + +static int emulator_set_cr(int cr, unsigned long val, struct kvm_vcpu *vcpu) +{ + int res = 0; - kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu, NULL); + switch (cr) { + case 0: + res = kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val)); + break; + case 2: + vcpu->arch.cr2 = val; + break; + case 3: + res = kvm_set_cr3(vcpu, val); + break; + case 4: + res = kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val)); + break; + case 8: + res = __kvm_set_cr8(vcpu, val & 0xfUL); + break; + default: + vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); + res = -1; + } - printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n", - context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]); + return res; +} + +static int emulator_get_cpl(struct kvm_vcpu *vcpu) +{ + return kvm_x86_ops->get_cpl(vcpu); +} + +static void emulator_get_gdt(struct desc_ptr *dt, struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->get_gdt(vcpu, dt); +} + +static unsigned long emulator_get_cached_segment_base(int seg, + struct kvm_vcpu *vcpu) +{ + return get_segment_base(vcpu, seg); +} + +static bool emulator_get_cached_descriptor(struct desc_struct *desc, int seg, + struct kvm_vcpu *vcpu) +{ + struct kvm_segment var; + + kvm_get_segment(vcpu, &var, seg); + + if (var.unusable) + return false; + + if (var.g) + var.limit >>= 12; + set_desc_limit(desc, var.limit); + set_desc_base(desc, (unsigned long)var.base); + desc->type = var.type; + desc->s = var.s; + desc->dpl = var.dpl; + desc->p = var.present; + desc->avl = var.avl; + desc->l = var.l; + desc->d = var.db; + desc->g = var.g; + + return true; +} + +static void emulator_set_cached_descriptor(struct desc_struct *desc, int seg, + struct kvm_vcpu *vcpu) +{ + struct kvm_segment var; + + /* needed to preserve selector */ + kvm_get_segment(vcpu, &var, seg); + + var.base = get_desc_base(desc); + var.limit = get_desc_limit(desc); + if (desc->g) + var.limit = (var.limit << 12) | 0xfff; + var.type = desc->type; + var.present = desc->p; + var.dpl = desc->dpl; + var.db = desc->d; + var.s = desc->s; + var.l = desc->l; + var.g = desc->g; + var.avl = desc->avl; + var.present = desc->p; + var.unusable = !var.present; + var.padding = 0; + + kvm_set_segment(vcpu, &var, seg); + return; +} + +static u16 emulator_get_segment_selector(int seg, struct kvm_vcpu *vcpu) +{ + struct kvm_segment kvm_seg; + + kvm_get_segment(vcpu, &kvm_seg, seg); + return kvm_seg.selector; +} + +static void emulator_set_segment_selector(u16 sel, int seg, + struct kvm_vcpu *vcpu) +{ + struct kvm_segment kvm_seg; + + kvm_get_segment(vcpu, &kvm_seg, seg); + kvm_seg.selector = sel; + kvm_set_segment(vcpu, &kvm_seg, seg); } -EXPORT_SYMBOL_GPL(kvm_report_emulation_failure); static struct x86_emulate_ops emulate_ops = { .read_std = kvm_read_guest_virt_system, + .write_std = kvm_write_guest_virt_system, .fetch = kvm_fetch_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, .cmpxchg_emulated = emulator_cmpxchg_emulated, + .pio_in_emulated = emulator_pio_in_emulated, + .pio_out_emulated = emulator_pio_out_emulated, + .get_cached_descriptor = emulator_get_cached_descriptor, + .set_cached_descriptor = emulator_set_cached_descriptor, + .get_segment_selector = emulator_get_segment_selector, + .set_segment_selector = emulator_set_segment_selector, + .get_cached_segment_base = emulator_get_cached_segment_base, + .get_gdt = emulator_get_gdt, + .get_cr = emulator_get_cr, + .set_cr = emulator_set_cr, + .cpl = emulator_get_cpl, + .get_dr = emulator_get_dr, + .set_dr = emulator_set_dr, + .set_msr = kvm_set_msr, + .get_msr = kvm_get_msr, }; static void cache_all_regs(struct kvm_vcpu *vcpu) @@ -3359,14 +3900,75 @@ static void cache_all_regs(struct kvm_vcpu *vcpu) vcpu->arch.regs_dirty = ~0; } +static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) +{ + u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(vcpu, mask); + /* + * an sti; sti; sequence only disable interrupts for the first + * instruction. So, if the last instruction, be it emulated or + * not, left the system with the INT_STI flag enabled, it + * means that the last instruction is an sti. We should not + * leave the flag on in this case. The same goes for mov ss + */ + if (!(int_shadow & mask)) + kvm_x86_ops->set_interrupt_shadow(vcpu, mask); +} + +static void inject_emulated_exception(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + if (ctxt->exception == PF_VECTOR) + kvm_inject_page_fault(vcpu, ctxt->cr2, ctxt->error_code); + else if (ctxt->error_code_valid) + kvm_queue_exception_e(vcpu, ctxt->exception, ctxt->error_code); + else + kvm_queue_exception(vcpu, ctxt->exception); +} + +static int handle_emulation_failure(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.insn_emulation_fail; + trace_kvm_emulate_insn_failed(vcpu); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + kvm_queue_exception(vcpu, UD_VECTOR); + return EMULATE_FAIL; +} + +static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva) +{ + gpa_t gpa; + + if (tdp_enabled) + return false; + + /* + * if emulation was due to access to shadowed page table + * and it failed try to unshadow page and re-entetr the + * guest to let CPU execute the instruction. + */ + if (kvm_mmu_unprotect_page_virt(vcpu, gva)) + return true; + + gpa = kvm_mmu_gva_to_gpa_system(vcpu, gva, NULL); + + if (gpa == UNMAPPED_GVA) + return true; /* let cpu generate fault */ + + if (!kvm_is_error_hva(gfn_to_hva(vcpu->kvm, gpa >> PAGE_SHIFT))) + return true; + + return false; +} + int emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, u16 error_code, int emulation_type) { - int r, shadow_mask; - struct decode_cache *c; - struct kvm_run *run = vcpu->run; + int r; + struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode; kvm_clear_exception_queue(vcpu); vcpu->arch.mmio_fault_cr2 = cr2; @@ -3378,27 +3980,29 @@ int emulate_instruction(struct kvm_vcpu *vcpu, */ cache_all_regs(vcpu); - vcpu->mmio_is_write = 0; - vcpu->arch.pio.string = 0; - if (!(emulation_type & EMULTYPE_NO_DECODE)) { int cs_db, cs_l; kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); vcpu->arch.emulate_ctxt.vcpu = vcpu; - vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu); + vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); + vcpu->arch.emulate_ctxt.eip = kvm_rip_read(vcpu); vcpu->arch.emulate_ctxt.mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 : cs_l ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; + memset(c, 0, sizeof(struct decode_cache)); + memcpy(c->regs, vcpu->arch.regs, sizeof c->regs); + vcpu->arch.emulate_ctxt.interruptibility = 0; + vcpu->arch.emulate_ctxt.exception = -1; r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops); + trace_kvm_emulate_insn_start(vcpu); /* Only allow emulation of specific instructions on #UD * (namely VMMCALL, sysenter, sysexit, syscall)*/ - c = &vcpu->arch.emulate_ctxt.decode; if (emulation_type & EMULTYPE_TRAP_UD) { if (!c->twobyte) return EMULATE_FAIL; @@ -3426,10 +4030,11 @@ int emulate_instruction(struct kvm_vcpu *vcpu, ++vcpu->stat.insn_emulation; if (r) { - ++vcpu->stat.insn_emulation_fail; - if (kvm_mmu_unprotect_page_virt(vcpu, cr2)) + if (reexecute_instruction(vcpu, cr2)) return EMULATE_DONE; - return EMULATE_FAIL; + if (emulation_type & EMULTYPE_SKIP) + return EMULATE_FAIL; + return handle_emulation_failure(vcpu); } } @@ -3438,241 +4043,58 @@ int emulate_instruction(struct kvm_vcpu *vcpu, return EMULATE_DONE; } + /* this is needed for vmware backdor interface to work since it + changes registers values during IO operation */ + memcpy(c->regs, vcpu->arch.regs, sizeof c->regs); + +restart: r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops); - shadow_mask = vcpu->arch.emulate_ctxt.interruptibility; - if (r == 0) - kvm_x86_ops->set_interrupt_shadow(vcpu, shadow_mask); + if (r) { /* emulation failed */ + if (reexecute_instruction(vcpu, cr2)) + return EMULATE_DONE; - if (vcpu->arch.pio.string) - return EMULATE_DO_MMIO; + return handle_emulation_failure(vcpu); + } - if ((r || vcpu->mmio_is_write) && run) { - run->exit_reason = KVM_EXIT_MMIO; - run->mmio.phys_addr = vcpu->mmio_phys_addr; - memcpy(run->mmio.data, vcpu->mmio_data, 8); - run->mmio.len = vcpu->mmio_size; - run->mmio.is_write = vcpu->mmio_is_write; + toggle_interruptibility(vcpu, vcpu->arch.emulate_ctxt.interruptibility); + kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + memcpy(vcpu->arch.regs, c->regs, sizeof c->regs); + kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip); + + if (vcpu->arch.emulate_ctxt.exception >= 0) { + inject_emulated_exception(vcpu); + return EMULATE_DONE; } - if (r) { - if (kvm_mmu_unprotect_page_virt(vcpu, cr2)) - return EMULATE_DONE; - if (!vcpu->mmio_needed) { - kvm_report_emulation_failure(vcpu, "mmio"); - return EMULATE_FAIL; - } + if (vcpu->arch.pio.count) { + if (!vcpu->arch.pio.in) + vcpu->arch.pio.count = 0; return EMULATE_DO_MMIO; } - kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); - - if (vcpu->mmio_is_write) { - vcpu->mmio_needed = 0; + if (vcpu->mmio_needed) { + if (vcpu->mmio_is_write) + vcpu->mmio_needed = 0; return EMULATE_DO_MMIO; } + if (vcpu->arch.emulate_ctxt.restart) + goto restart; + return EMULATE_DONE; } EXPORT_SYMBOL_GPL(emulate_instruction); -static int pio_copy_data(struct kvm_vcpu *vcpu) +int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) { - void *p = vcpu->arch.pio_data; - gva_t q = vcpu->arch.pio.guest_gva; - unsigned bytes; - int ret; - u32 error_code; - - bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count; - if (vcpu->arch.pio.in) - ret = kvm_write_guest_virt(q, p, bytes, vcpu, &error_code); - else - ret = kvm_read_guest_virt(q, p, bytes, vcpu, &error_code); - - if (ret == X86EMUL_PROPAGATE_FAULT) - kvm_inject_page_fault(vcpu, q, error_code); - + unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX); + int ret = emulator_pio_out_emulated(size, port, &val, 1, vcpu); + /* do not return to emulator after return from userspace */ + vcpu->arch.pio.count = 0; return ret; } - -int complete_pio(struct kvm_vcpu *vcpu) -{ - struct kvm_pio_request *io = &vcpu->arch.pio; - long delta; - int r; - unsigned long val; - - if (!io->string) { - if (io->in) { - val = kvm_register_read(vcpu, VCPU_REGS_RAX); - memcpy(&val, vcpu->arch.pio_data, io->size); - kvm_register_write(vcpu, VCPU_REGS_RAX, val); - } - } else { - if (io->in) { - r = pio_copy_data(vcpu); - if (r) - goto out; - } - - delta = 1; - if (io->rep) { - delta *= io->cur_count; - /* - * The size of the register should really depend on - * current address size. - */ - val = kvm_register_read(vcpu, VCPU_REGS_RCX); - val -= delta; - kvm_register_write(vcpu, VCPU_REGS_RCX, val); - } - if (io->down) - delta = -delta; - delta *= io->size; - if (io->in) { - val = kvm_register_read(vcpu, VCPU_REGS_RDI); - val += delta; - kvm_register_write(vcpu, VCPU_REGS_RDI, val); - } else { - val = kvm_register_read(vcpu, VCPU_REGS_RSI); - val += delta; - kvm_register_write(vcpu, VCPU_REGS_RSI, val); - } - } -out: - io->count -= io->cur_count; - io->cur_count = 0; - - return 0; -} - -static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) -{ - /* TODO: String I/O for in kernel device */ - int r; - - if (vcpu->arch.pio.in) - r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port, - vcpu->arch.pio.size, pd); - else - r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, - vcpu->arch.pio.port, vcpu->arch.pio.size, - pd); - return r; -} - -static int pio_string_write(struct kvm_vcpu *vcpu) -{ - struct kvm_pio_request *io = &vcpu->arch.pio; - void *pd = vcpu->arch.pio_data; - int i, r = 0; - - for (i = 0; i < io->cur_count; i++) { - if (kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, - io->port, io->size, pd)) { - r = -EOPNOTSUPP; - break; - } - pd += io->size; - } - return r; -} - -int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port) -{ - unsigned long val; - - trace_kvm_pio(!in, port, size, 1); - - vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; - vcpu->run->io.size = vcpu->arch.pio.size = size; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = 1; - vcpu->run->io.port = vcpu->arch.pio.port = port; - vcpu->arch.pio.in = in; - vcpu->arch.pio.string = 0; - vcpu->arch.pio.down = 0; - vcpu->arch.pio.rep = 0; - - if (!vcpu->arch.pio.in) { - val = kvm_register_read(vcpu, VCPU_REGS_RAX); - memcpy(vcpu->arch.pio_data, &val, 4); - } - - if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { - complete_pio(vcpu); - return 1; - } - return 0; -} -EXPORT_SYMBOL_GPL(kvm_emulate_pio); - -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in, - int size, unsigned long count, int down, - gva_t address, int rep, unsigned port) -{ - unsigned now, in_page; - int ret = 0; - - trace_kvm_pio(!in, port, size, count); - - vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; - vcpu->run->io.size = vcpu->arch.pio.size = size; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count; - vcpu->run->io.port = vcpu->arch.pio.port = port; - vcpu->arch.pio.in = in; - vcpu->arch.pio.string = 1; - vcpu->arch.pio.down = down; - vcpu->arch.pio.rep = rep; - - if (!count) { - kvm_x86_ops->skip_emulated_instruction(vcpu); - return 1; - } - - if (!down) - in_page = PAGE_SIZE - offset_in_page(address); - else - in_page = offset_in_page(address) + size; - now = min(count, (unsigned long)in_page / size); - if (!now) - now = 1; - if (down) { - /* - * String I/O in reverse. Yuck. Kill the guest, fix later. - */ - pr_unimpl(vcpu, "guest string pio down\n"); - kvm_inject_gp(vcpu, 0); - return 1; - } - vcpu->run->io.count = now; - vcpu->arch.pio.cur_count = now; - - if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count) - kvm_x86_ops->skip_emulated_instruction(vcpu); - - vcpu->arch.pio.guest_gva = address; - - if (!vcpu->arch.pio.in) { - /* string PIO write */ - ret = pio_copy_data(vcpu); - if (ret == X86EMUL_PROPAGATE_FAULT) - return 1; - if (ret == 0 && !pio_string_write(vcpu)) { - complete_pio(vcpu); - if (vcpu->arch.pio.count == 0) - ret = 1; - } - } - /* no string PIO read support yet */ - - return ret; -} -EXPORT_SYMBOL_GPL(kvm_emulate_pio_string); +EXPORT_SYMBOL_GPL(kvm_fast_pio_out); static void bounce_off(void *info) { @@ -3747,6 +4169,51 @@ static void kvm_timer_init(void) } } +static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu); + +static int kvm_is_in_guest(void) +{ + return percpu_read(current_vcpu) != NULL; +} + +static int kvm_is_user_mode(void) +{ + int user_mode = 3; + + if (percpu_read(current_vcpu)) + user_mode = kvm_x86_ops->get_cpl(percpu_read(current_vcpu)); + + return user_mode != 0; +} + +static unsigned long kvm_get_guest_ip(void) +{ + unsigned long ip = 0; + + if (percpu_read(current_vcpu)) + ip = kvm_rip_read(percpu_read(current_vcpu)); + + return ip; +} + +static struct perf_guest_info_callbacks kvm_guest_cbs = { + .is_in_guest = kvm_is_in_guest, + .is_user_mode = kvm_is_user_mode, + .get_guest_ip = kvm_get_guest_ip, +}; + +void kvm_before_handle_nmi(struct kvm_vcpu *vcpu) +{ + percpu_write(current_vcpu, vcpu); +} +EXPORT_SYMBOL_GPL(kvm_before_handle_nmi); + +void kvm_after_handle_nmi(struct kvm_vcpu *vcpu) +{ + percpu_write(current_vcpu, NULL); +} +EXPORT_SYMBOL_GPL(kvm_after_handle_nmi); + int kvm_arch_init(void *opaque) { int r; @@ -3783,6 +4250,11 @@ int kvm_arch_init(void *opaque) kvm_timer_init(); + perf_register_guest_info_callbacks(&kvm_guest_cbs); + + if (cpu_has_xsave) + host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + return 0; out: @@ -3791,6 +4263,8 @@ out: void kvm_arch_exit(void) { + perf_unregister_guest_info_callbacks(&kvm_guest_cbs); + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); @@ -3943,88 +4417,23 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu) kvm_x86_ops->patch_hypercall(vcpu, instruction); - return emulator_write_emulated(rip, instruction, 3, vcpu); -} - -static u64 mk_cr_64(u64 curr_cr, u32 new_val) -{ - return (curr_cr & ~((1ULL << 32) - 1)) | new_val; + return emulator_write_emulated(rip, instruction, 3, NULL, vcpu); } void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) { - struct descriptor_table dt = { limit, base }; + struct desc_ptr dt = { limit, base }; kvm_x86_ops->set_gdt(vcpu, &dt); } void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) { - struct descriptor_table dt = { limit, base }; + struct desc_ptr dt = { limit, base }; kvm_x86_ops->set_idt(vcpu, &dt); } -void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, - unsigned long *rflags) -{ - kvm_lmsw(vcpu, msw); - *rflags = kvm_get_rflags(vcpu); -} - -unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) -{ - unsigned long value; - - switch (cr) { - case 0: - value = kvm_read_cr0(vcpu); - break; - case 2: - value = vcpu->arch.cr2; - break; - case 3: - value = vcpu->arch.cr3; - break; - case 4: - value = kvm_read_cr4(vcpu); - break; - case 8: - value = kvm_get_cr8(vcpu); - break; - default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); - return 0; - } - - return value; -} - -void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, - unsigned long *rflags) -{ - switch (cr) { - case 0: - kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val)); - *rflags = kvm_get_rflags(vcpu); - break; - case 2: - vcpu->arch.cr2 = val; - break; - case 3: - kvm_set_cr3(vcpu, val); - break; - case 4: - kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val)); - break; - case 8: - kvm_set_cr8(vcpu, val & 0xfUL); - break; - default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); - } -} - static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) { struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; @@ -4088,9 +4497,13 @@ int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; + best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); + if (!best || best->eax < 0x80000008) + goto not_found; best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); if (best) return best->eax & 0xff; +not_found: return 36; } @@ -4204,9 +4617,13 @@ static void inject_pending_event(struct kvm_vcpu *vcpu) { /* try to reinject previous events if any */ if (vcpu->arch.exception.pending) { + trace_kvm_inj_exception(vcpu->arch.exception.nr, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code); kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr, vcpu->arch.exception.has_error_code, - vcpu->arch.exception.error_code); + vcpu->arch.exception.error_code, + vcpu->arch.exception.reinject); return; } @@ -4236,59 +4653,78 @@ static void inject_pending_event(struct kvm_vcpu *vcpu) } } +static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) +{ + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && + !vcpu->guest_xcr0_loaded) { + /* kvm_set_xcr() also depends on this */ + xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); + vcpu->guest_xcr0_loaded = 1; + } +} + +static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) +{ + if (vcpu->guest_xcr0_loaded) { + if (vcpu->arch.xcr0 != host_xcr0) + xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); + vcpu->guest_xcr0_loaded = 0; + } +} + static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && vcpu->run->request_interrupt_window; - if (vcpu->requests) - if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) - kvm_mmu_unload(vcpu); - - r = kvm_mmu_reload(vcpu); - if (unlikely(r)) - goto out; - if (vcpu->requests) { - if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests)) + if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) + kvm_mmu_unload(vcpu); + if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) __kvm_migrate_timers(vcpu); - if (test_and_clear_bit(KVM_REQ_KVMCLOCK_UPDATE, &vcpu->requests)) + if (kvm_check_request(KVM_REQ_KVMCLOCK_UPDATE, vcpu)) kvm_write_guest_time(vcpu); - if (test_and_clear_bit(KVM_REQ_MMU_SYNC, &vcpu->requests)) + if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu)) kvm_mmu_sync_roots(vcpu); - if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests)) + if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) kvm_x86_ops->tlb_flush(vcpu); - if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS, - &vcpu->requests)) { + if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; r = 0; goto out; } - if (test_and_clear_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests)) { + if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; r = 0; goto out; } - if (test_and_clear_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests)) { + if (kvm_check_request(KVM_REQ_DEACTIVATE_FPU, vcpu)) { vcpu->fpu_active = 0; kvm_x86_ops->fpu_deactivate(vcpu); } } + r = kvm_mmu_reload(vcpu); + if (unlikely(r)) + goto out; + preempt_disable(); kvm_x86_ops->prepare_guest_switch(vcpu); if (vcpu->fpu_active) kvm_load_guest_fpu(vcpu); + kvm_load_guest_xcr0(vcpu); - local_irq_disable(); + atomic_set(&vcpu->guest_mode, 1); + smp_wmb(); - clear_bit(KVM_REQ_KICK, &vcpu->requests); - smp_mb__after_clear_bit(); + local_irq_disable(); - if (vcpu->requests || need_resched() || signal_pending(current)) { - set_bit(KVM_REQ_KICK, &vcpu->requests); + if (!atomic_read(&vcpu->guest_mode) || vcpu->requests + || need_resched() || signal_pending(current)) { + atomic_set(&vcpu->guest_mode, 0); + smp_wmb(); local_irq_enable(); preempt_enable(); r = 1; @@ -4333,7 +4769,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (hw_breakpoint_active()) hw_breakpoint_restore(); - set_bit(KVM_REQ_KICK, &vcpu->requests); + atomic_set(&vcpu->guest_mode, 0); + smp_wmb(); local_irq_enable(); ++vcpu->stat.exits; @@ -4395,7 +4832,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests)) + if (kvm_check_request(KVM_REQ_UNHALT, vcpu)) { switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: @@ -4436,7 +4873,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) } srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - post_kvm_run_save(vcpu); vapic_exit(vcpu); @@ -4448,8 +4884,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int r; sigset_t sigsaved; - vcpu_load(vcpu); - if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); @@ -4464,26 +4898,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (!irqchip_in_kernel(vcpu->kvm)) kvm_set_cr8(vcpu, kvm_run->cr8); - if (vcpu->arch.pio.cur_count) { - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = complete_pio(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - if (r) - goto out; - } - if (vcpu->mmio_needed) { - memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); - vcpu->mmio_read_completed = 1; - vcpu->mmio_needed = 0; - + if (vcpu->arch.pio.count || vcpu->mmio_needed || + vcpu->arch.emulate_ctxt.restart) { + if (vcpu->mmio_needed) { + memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); + vcpu->mmio_read_completed = 1; + vcpu->mmio_needed = 0; + } vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0, - EMULTYPE_NO_DECODE); + r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - if (r == EMULATE_DO_MMIO) { - /* - * Read-modify-write. Back to userspace. - */ + if (r != EMULATE_DONE) { r = 0; goto out; } @@ -4495,17 +4920,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) r = __vcpu_run(vcpu); out: + post_kvm_run_save(vcpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &sigsaved, NULL); - vcpu_put(vcpu); return r; } int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { - vcpu_load(vcpu); - regs->rax = kvm_register_read(vcpu, VCPU_REGS_RAX); regs->rbx = kvm_register_read(vcpu, VCPU_REGS_RBX); regs->rcx = kvm_register_read(vcpu, VCPU_REGS_RCX); @@ -4528,15 +4951,11 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) regs->rip = kvm_rip_read(vcpu); regs->rflags = kvm_get_rflags(vcpu); - vcpu_put(vcpu); - return 0; } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { - vcpu_load(vcpu); - kvm_register_write(vcpu, VCPU_REGS_RAX, regs->rax); kvm_register_write(vcpu, VCPU_REGS_RBX, regs->rbx); kvm_register_write(vcpu, VCPU_REGS_RCX, regs->rcx); @@ -4561,17 +4980,9 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) vcpu->arch.exception.pending = false; - vcpu_put(vcpu); - return 0; } -void kvm_get_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - kvm_x86_ops->get_segment(vcpu, var, seg); -} - void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) { struct kvm_segment cs; @@ -4585,9 +4996,7 @@ EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits); int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - struct descriptor_table dt; - - vcpu_load(vcpu); + struct desc_ptr dt; kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); @@ -4600,11 +5009,11 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); kvm_x86_ops->get_idt(vcpu, &dt); - sregs->idt.limit = dt.limit; - sregs->idt.base = dt.base; + sregs->idt.limit = dt.size; + sregs->idt.base = dt.address; kvm_x86_ops->get_gdt(vcpu, &dt); - sregs->gdt.limit = dt.limit; - sregs->gdt.base = dt.base; + sregs->gdt.limit = dt.size; + sregs->gdt.base = dt.address; sregs->cr0 = kvm_read_cr0(vcpu); sregs->cr2 = vcpu->arch.cr2; @@ -4620,586 +5029,55 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, set_bit(vcpu->arch.interrupt.nr, (unsigned long *)sregs->interrupt_bitmap); - vcpu_put(vcpu); - return 0; } int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - vcpu_load(vcpu); mp_state->mp_state = vcpu->arch.mp_state; - vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - vcpu_load(vcpu); vcpu->arch.mp_state = mp_state->mp_state; - vcpu_put(vcpu); return 0; } -static void kvm_set_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - kvm_x86_ops->set_segment(vcpu, var, seg); -} - -static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector, - struct kvm_segment *kvm_desct) -{ - kvm_desct->base = get_desc_base(seg_desc); - kvm_desct->limit = get_desc_limit(seg_desc); - if (seg_desc->g) { - kvm_desct->limit <<= 12; - kvm_desct->limit |= 0xfff; - } - kvm_desct->selector = selector; - kvm_desct->type = seg_desc->type; - kvm_desct->present = seg_desc->p; - kvm_desct->dpl = seg_desc->dpl; - kvm_desct->db = seg_desc->d; - kvm_desct->s = seg_desc->s; - kvm_desct->l = seg_desc->l; - kvm_desct->g = seg_desc->g; - kvm_desct->avl = seg_desc->avl; - if (!selector) - kvm_desct->unusable = 1; - else - kvm_desct->unusable = 0; - kvm_desct->padding = 0; -} - -static void get_segment_descriptor_dtable(struct kvm_vcpu *vcpu, - u16 selector, - struct descriptor_table *dtable) -{ - if (selector & 1 << 2) { - struct kvm_segment kvm_seg; - - kvm_get_segment(vcpu, &kvm_seg, VCPU_SREG_LDTR); - - if (kvm_seg.unusable) - dtable->limit = 0; - else - dtable->limit = kvm_seg.limit; - dtable->base = kvm_seg.base; - } - else - kvm_x86_ops->get_gdt(vcpu, dtable); -} - -/* allowed just for 8 bytes segments */ -static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, - struct desc_struct *seg_desc) -{ - struct descriptor_table dtable; - u16 index = selector >> 3; - int ret; - u32 err; - gva_t addr; - - get_segment_descriptor_dtable(vcpu, selector, &dtable); - - if (dtable.limit < index * 8 + 7) { - kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc); - return X86EMUL_PROPAGATE_FAULT; - } - addr = dtable.base + index * 8; - ret = kvm_read_guest_virt_system(addr, seg_desc, sizeof(*seg_desc), - vcpu, &err); - if (ret == X86EMUL_PROPAGATE_FAULT) - kvm_inject_page_fault(vcpu, addr, err); - - return ret; -} - -/* allowed just for 8 bytes segments */ -static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, - struct desc_struct *seg_desc) -{ - struct descriptor_table dtable; - u16 index = selector >> 3; - - get_segment_descriptor_dtable(vcpu, selector, &dtable); - - if (dtable.limit < index * 8 + 7) - return 1; - return kvm_write_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu, NULL); -} - -static gpa_t get_tss_base_addr_write(struct kvm_vcpu *vcpu, - struct desc_struct *seg_desc) -{ - u32 base_addr = get_desc_base(seg_desc); - - return kvm_mmu_gva_to_gpa_write(vcpu, base_addr, NULL); -} - -static gpa_t get_tss_base_addr_read(struct kvm_vcpu *vcpu, - struct desc_struct *seg_desc) -{ - u32 base_addr = get_desc_base(seg_desc); - - return kvm_mmu_gva_to_gpa_read(vcpu, base_addr, NULL); -} - -static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg) -{ - struct kvm_segment kvm_seg; - - kvm_get_segment(vcpu, &kvm_seg, seg); - return kvm_seg.selector; -} - -static int kvm_load_realmode_segment(struct kvm_vcpu *vcpu, u16 selector, int seg) -{ - struct kvm_segment segvar = { - .base = selector << 4, - .limit = 0xffff, - .selector = selector, - .type = 3, - .present = 1, - .dpl = 3, - .db = 0, - .s = 1, - .l = 0, - .g = 0, - .avl = 0, - .unusable = 0, - }; - kvm_x86_ops->set_segment(vcpu, &segvar, seg); - return X86EMUL_CONTINUE; -} - -static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg) +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, + bool has_error_code, u32 error_code) { - return (seg != VCPU_SREG_LDTR) && - (seg != VCPU_SREG_TR) && - (kvm_get_rflags(vcpu) & X86_EFLAGS_VM); -} - -int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg) -{ - struct kvm_segment kvm_seg; - struct desc_struct seg_desc; - u8 dpl, rpl, cpl; - unsigned err_vec = GP_VECTOR; - u32 err_code = 0; - bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */ - int ret; - - if (is_vm86_segment(vcpu, seg) || !is_protmode(vcpu)) - return kvm_load_realmode_segment(vcpu, selector, seg); + struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode; + int cs_db, cs_l, ret; + cache_all_regs(vcpu); - /* NULL selector is not valid for TR, CS and SS */ - if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || seg == VCPU_SREG_TR) - && null_selector) - goto exception; + kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - /* TR should be in GDT only */ - if (seg == VCPU_SREG_TR && (selector & (1 << 2))) - goto exception; + vcpu->arch.emulate_ctxt.vcpu = vcpu; + vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); + vcpu->arch.emulate_ctxt.eip = kvm_rip_read(vcpu); + vcpu->arch.emulate_ctxt.mode = + (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : + (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM) + ? X86EMUL_MODE_VM86 : cs_l + ? X86EMUL_MODE_PROT64 : cs_db + ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; + memset(c, 0, sizeof(struct decode_cache)); + memcpy(c->regs, vcpu->arch.regs, sizeof c->regs); + + ret = emulator_task_switch(&vcpu->arch.emulate_ctxt, &emulate_ops, + tss_selector, reason, has_error_code, + error_code); - ret = load_guest_segment_descriptor(vcpu, selector, &seg_desc); if (ret) - return ret; - - seg_desct_to_kvm_desct(&seg_desc, selector, &kvm_seg); - - if (null_selector) { /* for NULL selector skip all following checks */ - kvm_seg.unusable = 1; - goto load; - } - - err_code = selector & 0xfffc; - err_vec = GP_VECTOR; - - /* can't load system descriptor into segment selecor */ - if (seg <= VCPU_SREG_GS && !kvm_seg.s) - goto exception; - - if (!kvm_seg.present) { - err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR; - goto exception; - } - - rpl = selector & 3; - dpl = kvm_seg.dpl; - cpl = kvm_x86_ops->get_cpl(vcpu); - - switch (seg) { - case VCPU_SREG_SS: - /* - * segment is not a writable data segment or segment - * selector's RPL != CPL or segment selector's RPL != CPL - */ - if (rpl != cpl || (kvm_seg.type & 0xa) != 0x2 || dpl != cpl) - goto exception; - break; - case VCPU_SREG_CS: - if (!(kvm_seg.type & 8)) - goto exception; - - if (kvm_seg.type & 4) { - /* conforming */ - if (dpl > cpl) - goto exception; - } else { - /* nonconforming */ - if (rpl > cpl || dpl != cpl) - goto exception; - } - /* CS(RPL) <- CPL */ - selector = (selector & 0xfffc) | cpl; - break; - case VCPU_SREG_TR: - if (kvm_seg.s || (kvm_seg.type != 1 && kvm_seg.type != 9)) - goto exception; - break; - case VCPU_SREG_LDTR: - if (kvm_seg.s || kvm_seg.type != 2) - goto exception; - break; - default: /* DS, ES, FS, or GS */ - /* - * segment is not a data or readable code segment or - * ((segment is a data or nonconforming code segment) - * and (both RPL and CPL > DPL)) - */ - if ((kvm_seg.type & 0xa) == 0x8 || - (((kvm_seg.type & 0xc) != 0xc) && (rpl > dpl && cpl > dpl))) - goto exception; - break; - } - - if (!kvm_seg.unusable && kvm_seg.s) { - /* mark segment as accessed */ - kvm_seg.type |= 1; - seg_desc.type |= 1; - save_guest_segment_descriptor(vcpu, selector, &seg_desc); - } -load: - kvm_set_segment(vcpu, &kvm_seg, seg); - return X86EMUL_CONTINUE; -exception: - kvm_queue_exception_e(vcpu, err_vec, err_code); - return X86EMUL_PROPAGATE_FAULT; -} - -static void save_state_to_tss32(struct kvm_vcpu *vcpu, - struct tss_segment_32 *tss) -{ - tss->cr3 = vcpu->arch.cr3; - tss->eip = kvm_rip_read(vcpu); - tss->eflags = kvm_get_rflags(vcpu); - tss->eax = kvm_register_read(vcpu, VCPU_REGS_RAX); - tss->ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); - tss->edx = kvm_register_read(vcpu, VCPU_REGS_RDX); - tss->ebx = kvm_register_read(vcpu, VCPU_REGS_RBX); - tss->esp = kvm_register_read(vcpu, VCPU_REGS_RSP); - tss->ebp = kvm_register_read(vcpu, VCPU_REGS_RBP); - tss->esi = kvm_register_read(vcpu, VCPU_REGS_RSI); - tss->edi = kvm_register_read(vcpu, VCPU_REGS_RDI); - tss->es = get_segment_selector(vcpu, VCPU_SREG_ES); - tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS); - tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS); - tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS); - tss->fs = get_segment_selector(vcpu, VCPU_SREG_FS); - tss->gs = get_segment_selector(vcpu, VCPU_SREG_GS); - tss->ldt_selector = get_segment_selector(vcpu, VCPU_SREG_LDTR); -} - -static void kvm_load_segment_selector(struct kvm_vcpu *vcpu, u16 sel, int seg) -{ - struct kvm_segment kvm_seg; - kvm_get_segment(vcpu, &kvm_seg, seg); - kvm_seg.selector = sel; - kvm_set_segment(vcpu, &kvm_seg, seg); -} - -static int load_state_from_tss32(struct kvm_vcpu *vcpu, - struct tss_segment_32 *tss) -{ - kvm_set_cr3(vcpu, tss->cr3); - - kvm_rip_write(vcpu, tss->eip); - kvm_set_rflags(vcpu, tss->eflags | 2); - - kvm_register_write(vcpu, VCPU_REGS_RAX, tss->eax); - kvm_register_write(vcpu, VCPU_REGS_RCX, tss->ecx); - kvm_register_write(vcpu, VCPU_REGS_RDX, tss->edx); - kvm_register_write(vcpu, VCPU_REGS_RBX, tss->ebx); - kvm_register_write(vcpu, VCPU_REGS_RSP, tss->esp); - kvm_register_write(vcpu, VCPU_REGS_RBP, tss->ebp); - kvm_register_write(vcpu, VCPU_REGS_RSI, tss->esi); - kvm_register_write(vcpu, VCPU_REGS_RDI, tss->edi); - - /* - * SDM says that segment selectors are loaded before segment - * descriptors - */ - kvm_load_segment_selector(vcpu, tss->ldt_selector, VCPU_SREG_LDTR); - kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES); - kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS); - kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS); - kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS); - kvm_load_segment_selector(vcpu, tss->fs, VCPU_SREG_FS); - kvm_load_segment_selector(vcpu, tss->gs, VCPU_SREG_GS); - - /* - * Now load segment descriptors. If fault happenes at this stage - * it is handled in a context of new task - */ - if (kvm_load_segment_descriptor(vcpu, tss->ldt_selector, VCPU_SREG_LDTR)) - return 1; + return EMULATE_FAIL; - if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->fs, VCPU_SREG_FS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->gs, VCPU_SREG_GS)) - return 1; - return 0; -} - -static void save_state_to_tss16(struct kvm_vcpu *vcpu, - struct tss_segment_16 *tss) -{ - tss->ip = kvm_rip_read(vcpu); - tss->flag = kvm_get_rflags(vcpu); - tss->ax = kvm_register_read(vcpu, VCPU_REGS_RAX); - tss->cx = kvm_register_read(vcpu, VCPU_REGS_RCX); - tss->dx = kvm_register_read(vcpu, VCPU_REGS_RDX); - tss->bx = kvm_register_read(vcpu, VCPU_REGS_RBX); - tss->sp = kvm_register_read(vcpu, VCPU_REGS_RSP); - tss->bp = kvm_register_read(vcpu, VCPU_REGS_RBP); - tss->si = kvm_register_read(vcpu, VCPU_REGS_RSI); - tss->di = kvm_register_read(vcpu, VCPU_REGS_RDI); - - tss->es = get_segment_selector(vcpu, VCPU_SREG_ES); - tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS); - tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS); - tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS); - tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR); -} - -static int load_state_from_tss16(struct kvm_vcpu *vcpu, - struct tss_segment_16 *tss) -{ - kvm_rip_write(vcpu, tss->ip); - kvm_set_rflags(vcpu, tss->flag | 2); - kvm_register_write(vcpu, VCPU_REGS_RAX, tss->ax); - kvm_register_write(vcpu, VCPU_REGS_RCX, tss->cx); - kvm_register_write(vcpu, VCPU_REGS_RDX, tss->dx); - kvm_register_write(vcpu, VCPU_REGS_RBX, tss->bx); - kvm_register_write(vcpu, VCPU_REGS_RSP, tss->sp); - kvm_register_write(vcpu, VCPU_REGS_RBP, tss->bp); - kvm_register_write(vcpu, VCPU_REGS_RSI, tss->si); - kvm_register_write(vcpu, VCPU_REGS_RDI, tss->di); - - /* - * SDM says that segment selectors are loaded before segment - * descriptors - */ - kvm_load_segment_selector(vcpu, tss->ldt, VCPU_SREG_LDTR); - kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES); - kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS); - kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS); - kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS); - - /* - * Now load segment descriptors. If fault happenes at this stage - * it is handled in a context of new task - */ - if (kvm_load_segment_descriptor(vcpu, tss->ldt, VCPU_SREG_LDTR)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS)) - return 1; - return 0; -} - -static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector, - u16 old_tss_sel, u32 old_tss_base, - struct desc_struct *nseg_desc) -{ - struct tss_segment_16 tss_segment_16; - int ret = 0; - - if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_16, - sizeof tss_segment_16)) - goto out; - - save_state_to_tss16(vcpu, &tss_segment_16); - - if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_16, - sizeof tss_segment_16)) - goto out; - - if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc), - &tss_segment_16, sizeof tss_segment_16)) - goto out; - - if (old_tss_sel != 0xffff) { - tss_segment_16.prev_task_link = old_tss_sel; - - if (kvm_write_guest(vcpu->kvm, - get_tss_base_addr_write(vcpu, nseg_desc), - &tss_segment_16.prev_task_link, - sizeof tss_segment_16.prev_task_link)) - goto out; - } - - if (load_state_from_tss16(vcpu, &tss_segment_16)) - goto out; - - ret = 1; -out: - return ret; -} - -static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector, - u16 old_tss_sel, u32 old_tss_base, - struct desc_struct *nseg_desc) -{ - struct tss_segment_32 tss_segment_32; - int ret = 0; - - if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_32, - sizeof tss_segment_32)) - goto out; - - save_state_to_tss32(vcpu, &tss_segment_32); - - if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_32, - sizeof tss_segment_32)) - goto out; - - if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc), - &tss_segment_32, sizeof tss_segment_32)) - goto out; - - if (old_tss_sel != 0xffff) { - tss_segment_32.prev_task_link = old_tss_sel; - - if (kvm_write_guest(vcpu->kvm, - get_tss_base_addr_write(vcpu, nseg_desc), - &tss_segment_32.prev_task_link, - sizeof tss_segment_32.prev_task_link)) - goto out; - } - - if (load_state_from_tss32(vcpu, &tss_segment_32)) - goto out; - - ret = 1; -out: - return ret; -} - -int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) -{ - struct kvm_segment tr_seg; - struct desc_struct cseg_desc; - struct desc_struct nseg_desc; - int ret = 0; - u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR); - u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR); - u32 desc_limit; - - old_tss_base = kvm_mmu_gva_to_gpa_write(vcpu, old_tss_base, NULL); - - /* FIXME: Handle errors. Failure to read either TSS or their - * descriptors should generate a pagefault. - */ - if (load_guest_segment_descriptor(vcpu, tss_selector, &nseg_desc)) - goto out; - - if (load_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc)) - goto out; - - if (reason != TASK_SWITCH_IRET) { - int cpl; - - cpl = kvm_x86_ops->get_cpl(vcpu); - if ((tss_selector & 3) > nseg_desc.dpl || cpl > nseg_desc.dpl) { - kvm_queue_exception_e(vcpu, GP_VECTOR, 0); - return 1; - } - } - - desc_limit = get_desc_limit(&nseg_desc); - if (!nseg_desc.p || - ((desc_limit < 0x67 && (nseg_desc.type & 8)) || - desc_limit < 0x2b)) { - kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc); - return 1; - } - - if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) { - cseg_desc.type &= ~(1 << 1); //clear the B flag - save_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc); - } - - if (reason == TASK_SWITCH_IRET) { - u32 eflags = kvm_get_rflags(vcpu); - kvm_set_rflags(vcpu, eflags & ~X86_EFLAGS_NT); - } - - /* set back link to prev task only if NT bit is set in eflags - note that old_tss_sel is not used afetr this point */ - if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE) - old_tss_sel = 0xffff; - - if (nseg_desc.type & 8) - ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_sel, - old_tss_base, &nseg_desc); - else - ret = kvm_task_switch_16(vcpu, tss_selector, old_tss_sel, - old_tss_base, &nseg_desc); - - if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) { - u32 eflags = kvm_get_rflags(vcpu); - kvm_set_rflags(vcpu, eflags | X86_EFLAGS_NT); - } - - if (reason != TASK_SWITCH_IRET) { - nseg_desc.type |= (1 << 1); - save_guest_segment_descriptor(vcpu, tss_selector, - &nseg_desc); - } - - kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0(vcpu) | X86_CR0_TS); - seg_desct_to_kvm_desct(&nseg_desc, tss_selector, &tr_seg); - tr_seg.type = 11; - kvm_set_segment(vcpu, &tr_seg, VCPU_SREG_TR); -out: - return ret; + memcpy(vcpu->arch.regs, c->regs, sizeof c->regs); + kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip); + kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + return EMULATE_DONE; } EXPORT_SYMBOL_GPL(kvm_task_switch); @@ -5208,15 +5086,13 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, { int mmu_reset_needed = 0; int pending_vec, max_bits; - struct descriptor_table dt; - - vcpu_load(vcpu); + struct desc_ptr dt; - dt.limit = sregs->idt.limit; - dt.base = sregs->idt.base; + dt.size = sregs->idt.limit; + dt.address = sregs->idt.base; kvm_x86_ops->set_idt(vcpu, &dt); - dt.limit = sregs->gdt.limit; - dt.base = sregs->gdt.base; + dt.size = sregs->gdt.limit; + dt.address = sregs->gdt.base; kvm_x86_ops->set_gdt(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; @@ -5271,8 +5147,6 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, !is_protmode(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; - vcpu_put(vcpu); - return 0; } @@ -5282,12 +5156,10 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, unsigned long rflags; int i, r; - vcpu_load(vcpu); - if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { r = -EBUSY; if (vcpu->arch.exception.pending) - goto unlock_out; + goto out; if (dbg->control & KVM_GUESTDBG_INJECT_DB) kvm_queue_exception(vcpu, DB_VECTOR); else @@ -5315,11 +5187,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK); } - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { - vcpu->arch.singlestep_cs = - get_segment_selector(vcpu, VCPU_SREG_CS); - vcpu->arch.singlestep_rip = kvm_rip_read(vcpu); - } + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) + + get_segment_base(vcpu, VCPU_SREG_CS); /* * Trigger an rflags update that will inject or remove the trace @@ -5331,34 +5201,12 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, r = 0; -unlock_out: - vcpu_put(vcpu); +out: return r; } /* - * fxsave fpu state. Taken from x86_64/processor.h. To be killed when - * we have asm/x86/processor.h - */ -struct fxsave { - u16 cwd; - u16 swd; - u16 twd; - u16 fop; - u64 rip; - u64 rdp; - u32 mxcsr; - u32 mxcsr_mask; - u32 st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */ -#ifdef CONFIG_X86_64 - u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg = 256 bytes */ -#else - u32 xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */ -#endif -}; - -/* * Translate a guest virtual address to a guest physical address. */ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, @@ -5368,7 +5216,6 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, gpa_t gpa; int idx; - vcpu_load(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL); srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -5376,16 +5223,14 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, tr->valid = gpa != UNMAPPED_GVA; tr->writeable = 1; tr->usermode = 0; - vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct fxsave *fxsave = (struct fxsave *)&vcpu->arch.guest_fx_image; - - vcpu_load(vcpu); + struct i387_fxsave_struct *fxsave = + &vcpu->arch.guest_fpu.state->fxsave; memcpy(fpu->fpr, fxsave->st_space, 128); fpu->fcw = fxsave->cwd; @@ -5396,16 +5241,13 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) fpu->last_dp = fxsave->rdp; memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space); - vcpu_put(vcpu); - return 0; } int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct fxsave *fxsave = (struct fxsave *)&vcpu->arch.guest_fx_image; - - vcpu_load(vcpu); + struct i387_fxsave_struct *fxsave = + &vcpu->arch.guest_fpu.state->fxsave; memcpy(fxsave->st_space, fpu->fpr, 128); fxsave->cwd = fpu->fcw; @@ -5416,61 +5258,63 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) fxsave->rdp = fpu->last_dp; memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space); - vcpu_put(vcpu); - return 0; } -void fx_init(struct kvm_vcpu *vcpu) +int fx_init(struct kvm_vcpu *vcpu) { - unsigned after_mxcsr_mask; + int err; + + err = fpu_alloc(&vcpu->arch.guest_fpu); + if (err) + return err; + + fpu_finit(&vcpu->arch.guest_fpu); /* - * Touch the fpu the first time in non atomic context as if - * this is the first fpu instruction the exception handler - * will fire before the instruction returns and it'll have to - * allocate ram with GFP_KERNEL. + * Ensure guest xcr0 is valid for loading */ - if (!used_math()) - kvm_fx_save(&vcpu->arch.host_fx_image); - - /* Initialize guest FPU by resetting ours and saving into guest's */ - preempt_disable(); - kvm_fx_save(&vcpu->arch.host_fx_image); - kvm_fx_finit(); - kvm_fx_save(&vcpu->arch.guest_fx_image); - kvm_fx_restore(&vcpu->arch.host_fx_image); - preempt_enable(); + vcpu->arch.xcr0 = XSTATE_FP; vcpu->arch.cr0 |= X86_CR0_ET; - after_mxcsr_mask = offsetof(struct i387_fxsave_struct, st_space); - vcpu->arch.guest_fx_image.mxcsr = 0x1f80; - memset((void *)&vcpu->arch.guest_fx_image + after_mxcsr_mask, - 0, sizeof(struct i387_fxsave_struct) - after_mxcsr_mask); + + return 0; } EXPORT_SYMBOL_GPL(fx_init); +static void fx_free(struct kvm_vcpu *vcpu) +{ + fpu_free(&vcpu->arch.guest_fpu); +} + void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { if (vcpu->guest_fpu_loaded) return; + /* + * Restore all possible states in the guest, + * and assume host would use all available bits. + * Guest xcr0 would be loaded later. + */ + kvm_put_guest_xcr0(vcpu); vcpu->guest_fpu_loaded = 1; - kvm_fx_save(&vcpu->arch.host_fx_image); - kvm_fx_restore(&vcpu->arch.guest_fx_image); + unlazy_fpu(current); + fpu_restore_checking(&vcpu->arch.guest_fpu); trace_kvm_fpu(1); } void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { + kvm_put_guest_xcr0(vcpu); + if (!vcpu->guest_fpu_loaded) return; vcpu->guest_fpu_loaded = 0; - kvm_fx_save(&vcpu->arch.guest_fx_image); - kvm_fx_restore(&vcpu->arch.host_fx_image); + fpu_save_init(&vcpu->arch.guest_fpu); ++vcpu->stat.fpu_reload; - set_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests); + kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); trace_kvm_fpu(0); } @@ -5481,6 +5325,8 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) vcpu->arch.time_page = NULL; } + free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); + fx_free(vcpu); kvm_x86_ops->vcpu_free(vcpu); } @@ -5494,9 +5340,6 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { int r; - /* We do fxsave: this must be aligned. */ - BUG_ON((unsigned long)&vcpu->arch.host_fx_image & 0xF); - vcpu->arch.mtrr_state.have_fixed = 1; vcpu_load(vcpu); r = kvm_arch_vcpu_reset(vcpu); @@ -5518,6 +5361,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_mmu_unload(vcpu); vcpu_put(vcpu); + fx_free(vcpu); kvm_x86_ops->vcpu_free(vcpu); } @@ -5611,7 +5455,12 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) } vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; + if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL)) + goto fail_free_mce_banks; + return 0; +fail_free_mce_banks: + kfree(vcpu->arch.mce_banks); fail_free_lapic: kvm_free_lapic(vcpu); fail_mmu_destroy: @@ -5641,12 +5490,6 @@ struct kvm *kvm_arch_create_vm(void) if (!kvm) return ERR_PTR(-ENOMEM); - kvm->arch.aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL); - if (!kvm->arch.aliases) { - kfree(kvm); - return ERR_PTR(-ENOMEM); - } - INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); @@ -5689,12 +5532,12 @@ static void kvm_free_vcpus(struct kvm *kvm) void kvm_arch_sync_events(struct kvm *kvm) { kvm_free_all_assigned_devices(kvm); + kvm_free_pit(kvm); } void kvm_arch_destroy_vm(struct kvm *kvm) { kvm_iommu_unmap_guest(kvm); - kvm_free_pit(kvm); kfree(kvm->arch.vpic); kfree(kvm->arch.vioapic); kvm_free_vcpus(kvm); @@ -5704,7 +5547,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm) if (kvm->arch.ept_identity_pagetable) put_page(kvm->arch.ept_identity_pagetable); cleanup_srcu_struct(&kvm->srcu); - kfree(kvm->arch.aliases); kfree(kvm); } @@ -5715,6 +5557,11 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, int user_alloc) { int npages = memslot->npages; + int map_flags = MAP_PRIVATE | MAP_ANONYMOUS; + + /* Prevent internal slot pages from being moved by fork()/COW. */ + if (memslot->id >= KVM_MEMORY_SLOTS) + map_flags = MAP_SHARED | MAP_ANONYMOUS; /*To keep backward compatibility with older userspace, *x86 needs to hanlde !user_alloc case. @@ -5727,7 +5574,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, userspace_addr = do_mmap(NULL, 0, npages * PAGE_SIZE, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, + map_flags, 0); up_write(¤t->mm->mmap_sem); @@ -5800,7 +5647,7 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) me = get_cpu(); if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) - if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests)) + if (atomic_xchg(&vcpu->guest_mode, 0)) smp_send_reschedule(cpu); put_cpu(); } @@ -5810,13 +5657,22 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) return kvm_x86_ops->interrupt_allowed(vcpu); } +bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip) +{ + unsigned long current_rip = kvm_rip_read(vcpu) + + get_segment_base(vcpu, VCPU_SREG_CS); + + return current_rip == linear_rip; +} +EXPORT_SYMBOL_GPL(kvm_is_linear_rip); + unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) { unsigned long rflags; rflags = kvm_x86_ops->get_rflags(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - rflags &= ~(unsigned long)(X86_EFLAGS_TF | X86_EFLAGS_RF); + rflags &= ~X86_EFLAGS_TF; return rflags; } EXPORT_SYMBOL_GPL(kvm_get_rflags); @@ -5824,10 +5680,8 @@ EXPORT_SYMBOL_GPL(kvm_get_rflags); void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && - vcpu->arch.singlestep_cs == - get_segment_selector(vcpu, VCPU_SREG_CS) && - vcpu->arch.singlestep_rip == kvm_rip_read(vcpu)) - rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; + kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip)) + rflags |= X86_EFLAGS_TF; kvm_x86_ops->set_rflags(vcpu, rflags); } EXPORT_SYMBOL_GPL(kvm_set_rflags); @@ -5843,3 +5697,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 2d101639bd8..b7a404722d2 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -65,4 +65,7 @@ static inline int is_paging(struct kvm_vcpu *vcpu) return kvm_read_cr0_bits(vcpu, X86_CR0_PG); } +void kvm_before_handle_nmi(struct kvm_vcpu *vcpu); +void kvm_after_handle_nmi(struct kvm_vcpu *vcpu); + #endif diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 2bdf628066b..9257510b483 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1390,7 +1390,6 @@ __init void lguest_init(void) #endif #ifdef CONFIG_ACPI acpi_disabled = 1; - acpi_ht = 0; #endif /* diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 419386c24b8..e10cf070ede 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -20,17 +20,19 @@ lib-y := delay.o lib-y += thunk_$(BITS).o lib-y += usercopy_$(BITS).o getuser.o putuser.o lib-y += memcpy_$(BITS).o -lib-$(CONFIG_KPROBES) += insn.o inat.o +lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o obj-y += msr.o msr-reg.o msr-reg-export.o ifeq ($(CONFIG_X86_32),y) obj-y += atomic64_32.o + lib-y += atomic64_cx8_32.o lib-y += checksum_32.o lib-y += strstr_32.o lib-y += semaphore_32.o string_32.o + lib-y += cmpxchg.o ifneq ($(CONFIG_X86_CMPXCHG64),y) - lib-y += cmpxchg8b_emu.o + lib-y += cmpxchg8b_emu.o atomic64_386_32.o endif lib-$(CONFIG_X86_USE_3DNOW) += mmx_32.o else diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c index 824fa0be55a..540179e8e9f 100644 --- a/arch/x86/lib/atomic64_32.c +++ b/arch/x86/lib/atomic64_32.c @@ -6,225 +6,54 @@ #include <asm/cmpxchg.h> #include <asm/atomic.h> -static noinline u64 cmpxchg8b(u64 *ptr, u64 old, u64 new) -{ - u32 low = new; - u32 high = new >> 32; - - asm volatile( - LOCK_PREFIX "cmpxchg8b %1\n" - : "+A" (old), "+m" (*ptr) - : "b" (low), "c" (high) - ); - return old; -} - -u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val) -{ - return cmpxchg8b(&ptr->counter, old_val, new_val); -} -EXPORT_SYMBOL(atomic64_cmpxchg); - -/** - * atomic64_xchg - xchg atomic64 variable - * @ptr: pointer to type atomic64_t - * @new_val: value to assign - * - * Atomically xchgs the value of @ptr to @new_val and returns - * the old value. - */ -u64 atomic64_xchg(atomic64_t *ptr, u64 new_val) -{ - /* - * Try first with a (possibly incorrect) assumption about - * what we have there. We'll do two loops most likely, - * but we'll get an ownership MESI transaction straight away - * instead of a read transaction followed by a - * flush-for-ownership transaction: - */ - u64 old_val, real_val = 0; - - do { - old_val = real_val; - - real_val = atomic64_cmpxchg(ptr, old_val, new_val); - - } while (real_val != old_val); - - return old_val; -} -EXPORT_SYMBOL(atomic64_xchg); - -/** - * atomic64_set - set atomic64 variable - * @ptr: pointer to type atomic64_t - * @new_val: value to assign - * - * Atomically sets the value of @ptr to @new_val. - */ -void atomic64_set(atomic64_t *ptr, u64 new_val) -{ - atomic64_xchg(ptr, new_val); -} -EXPORT_SYMBOL(atomic64_set); - -/** -EXPORT_SYMBOL(atomic64_read); - * atomic64_add_return - add and return - * @delta: integer value to add - * @ptr: pointer to type atomic64_t - * - * Atomically adds @delta to @ptr and returns @delta + *@ptr - */ -noinline u64 atomic64_add_return(u64 delta, atomic64_t *ptr) -{ - /* - * Try first with a (possibly incorrect) assumption about - * what we have there. We'll do two loops most likely, - * but we'll get an ownership MESI transaction straight away - * instead of a read transaction followed by a - * flush-for-ownership transaction: - */ - u64 old_val, new_val, real_val = 0; - - do { - old_val = real_val; - new_val = old_val + delta; - - real_val = atomic64_cmpxchg(ptr, old_val, new_val); - - } while (real_val != old_val); - - return new_val; -} -EXPORT_SYMBOL(atomic64_add_return); - -u64 atomic64_sub_return(u64 delta, atomic64_t *ptr) -{ - return atomic64_add_return(-delta, ptr); -} -EXPORT_SYMBOL(atomic64_sub_return); - -u64 atomic64_inc_return(atomic64_t *ptr) -{ - return atomic64_add_return(1, ptr); -} -EXPORT_SYMBOL(atomic64_inc_return); - -u64 atomic64_dec_return(atomic64_t *ptr) -{ - return atomic64_sub_return(1, ptr); -} -EXPORT_SYMBOL(atomic64_dec_return); - -/** - * atomic64_add - add integer to atomic64 variable - * @delta: integer value to add - * @ptr: pointer to type atomic64_t - * - * Atomically adds @delta to @ptr. - */ -void atomic64_add(u64 delta, atomic64_t *ptr) -{ - atomic64_add_return(delta, ptr); -} -EXPORT_SYMBOL(atomic64_add); - -/** - * atomic64_sub - subtract the atomic64 variable - * @delta: integer value to subtract - * @ptr: pointer to type atomic64_t - * - * Atomically subtracts @delta from @ptr. - */ -void atomic64_sub(u64 delta, atomic64_t *ptr) -{ - atomic64_add(-delta, ptr); -} -EXPORT_SYMBOL(atomic64_sub); - -/** - * atomic64_sub_and_test - subtract value from variable and test result - * @delta: integer value to subtract - * @ptr: pointer to type atomic64_t - * - * Atomically subtracts @delta from @ptr and returns - * true if the result is zero, or false for all - * other cases. - */ -int atomic64_sub_and_test(u64 delta, atomic64_t *ptr) -{ - u64 new_val = atomic64_sub_return(delta, ptr); - - return new_val == 0; -} -EXPORT_SYMBOL(atomic64_sub_and_test); - -/** - * atomic64_inc - increment atomic64 variable - * @ptr: pointer to type atomic64_t - * - * Atomically increments @ptr by 1. - */ -void atomic64_inc(atomic64_t *ptr) -{ - atomic64_add(1, ptr); -} -EXPORT_SYMBOL(atomic64_inc); - -/** - * atomic64_dec - decrement atomic64 variable - * @ptr: pointer to type atomic64_t - * - * Atomically decrements @ptr by 1. - */ -void atomic64_dec(atomic64_t *ptr) -{ - atomic64_sub(1, ptr); -} -EXPORT_SYMBOL(atomic64_dec); - -/** - * atomic64_dec_and_test - decrement and test - * @ptr: pointer to type atomic64_t - * - * Atomically decrements @ptr by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -int atomic64_dec_and_test(atomic64_t *ptr) -{ - return atomic64_sub_and_test(1, ptr); -} -EXPORT_SYMBOL(atomic64_dec_and_test); - -/** - * atomic64_inc_and_test - increment and test - * @ptr: pointer to type atomic64_t - * - * Atomically increments @ptr by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -int atomic64_inc_and_test(atomic64_t *ptr) -{ - return atomic64_sub_and_test(-1, ptr); -} -EXPORT_SYMBOL(atomic64_inc_and_test); - -/** - * atomic64_add_negative - add and test if negative - * @delta: integer value to add - * @ptr: pointer to type atomic64_t - * - * Atomically adds @delta to @ptr and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -int atomic64_add_negative(u64 delta, atomic64_t *ptr) -{ - s64 new_val = atomic64_add_return(delta, ptr); - - return new_val < 0; -} -EXPORT_SYMBOL(atomic64_add_negative); +long long atomic64_read_cx8(long long, const atomic64_t *v); +EXPORT_SYMBOL(atomic64_read_cx8); +long long atomic64_set_cx8(long long, const atomic64_t *v); +EXPORT_SYMBOL(atomic64_set_cx8); +long long atomic64_xchg_cx8(long long, unsigned high); +EXPORT_SYMBOL(atomic64_xchg_cx8); +long long atomic64_add_return_cx8(long long a, atomic64_t *v); +EXPORT_SYMBOL(atomic64_add_return_cx8); +long long atomic64_sub_return_cx8(long long a, atomic64_t *v); +EXPORT_SYMBOL(atomic64_sub_return_cx8); +long long atomic64_inc_return_cx8(long long a, atomic64_t *v); +EXPORT_SYMBOL(atomic64_inc_return_cx8); +long long atomic64_dec_return_cx8(long long a, atomic64_t *v); +EXPORT_SYMBOL(atomic64_dec_return_cx8); +long long atomic64_dec_if_positive_cx8(atomic64_t *v); +EXPORT_SYMBOL(atomic64_dec_if_positive_cx8); +int atomic64_inc_not_zero_cx8(atomic64_t *v); +EXPORT_SYMBOL(atomic64_inc_not_zero_cx8); +int atomic64_add_unless_cx8(atomic64_t *v, long long a, long long u); +EXPORT_SYMBOL(atomic64_add_unless_cx8); + +#ifndef CONFIG_X86_CMPXCHG64 +long long atomic64_read_386(long long, const atomic64_t *v); +EXPORT_SYMBOL(atomic64_read_386); +long long atomic64_set_386(long long, const atomic64_t *v); +EXPORT_SYMBOL(atomic64_set_386); +long long atomic64_xchg_386(long long, unsigned high); +EXPORT_SYMBOL(atomic64_xchg_386); +long long atomic64_add_return_386(long long a, atomic64_t *v); +EXPORT_SYMBOL(atomic64_add_return_386); +long long atomic64_sub_return_386(long long a, atomic64_t *v); +EXPORT_SYMBOL(atomic64_sub_return_386); +long long atomic64_inc_return_386(long long a, atomic64_t *v); +EXPORT_SYMBOL(atomic64_inc_return_386); +long long atomic64_dec_return_386(long long a, atomic64_t *v); +EXPORT_SYMBOL(atomic64_dec_return_386); +long long atomic64_add_386(long long a, atomic64_t *v); +EXPORT_SYMBOL(atomic64_add_386); +long long atomic64_sub_386(long long a, atomic64_t *v); +EXPORT_SYMBOL(atomic64_sub_386); +long long atomic64_inc_386(long long a, atomic64_t *v); +EXPORT_SYMBOL(atomic64_inc_386); +long long atomic64_dec_386(long long a, atomic64_t *v); +EXPORT_SYMBOL(atomic64_dec_386); +long long atomic64_dec_if_positive_386(atomic64_t *v); +EXPORT_SYMBOL(atomic64_dec_if_positive_386); +int atomic64_inc_not_zero_386(atomic64_t *v); +EXPORT_SYMBOL(atomic64_inc_not_zero_386); +int atomic64_add_unless_386(atomic64_t *v, long long a, long long u); +EXPORT_SYMBOL(atomic64_add_unless_386); +#endif diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S new file mode 100644 index 00000000000..4a5979aa688 --- /dev/null +++ b/arch/x86/lib/atomic64_386_32.S @@ -0,0 +1,174 @@ +/* + * atomic64_t for 386/486 + * + * Copyright © 2010 Luca Barbieri + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/linkage.h> +#include <asm/alternative-asm.h> +#include <asm/dwarf2.h> + +/* if you want SMP support, implement these with real spinlocks */ +.macro LOCK reg + pushfl + CFI_ADJUST_CFA_OFFSET 4 + cli +.endm + +.macro UNLOCK reg + popfl + CFI_ADJUST_CFA_OFFSET -4 +.endm + +.macro BEGIN func reg +$v = \reg + +ENTRY(atomic64_\func\()_386) + CFI_STARTPROC + LOCK $v + +.macro RETURN + UNLOCK $v + ret +.endm + +.macro END_ + CFI_ENDPROC +ENDPROC(atomic64_\func\()_386) +.purgem RETURN +.purgem END_ +.purgem END +.endm + +.macro END +RETURN +END_ +.endm +.endm + +BEGIN read %ecx + movl ($v), %eax + movl 4($v), %edx +END + +BEGIN set %esi + movl %ebx, ($v) + movl %ecx, 4($v) +END + +BEGIN xchg %esi + movl ($v), %eax + movl 4($v), %edx + movl %ebx, ($v) + movl %ecx, 4($v) +END + +BEGIN add %ecx + addl %eax, ($v) + adcl %edx, 4($v) +END + +BEGIN add_return %ecx + addl ($v), %eax + adcl 4($v), %edx + movl %eax, ($v) + movl %edx, 4($v) +END + +BEGIN sub %ecx + subl %eax, ($v) + sbbl %edx, 4($v) +END + +BEGIN sub_return %ecx + negl %edx + negl %eax + sbbl $0, %edx + addl ($v), %eax + adcl 4($v), %edx + movl %eax, ($v) + movl %edx, 4($v) +END + +BEGIN inc %esi + addl $1, ($v) + adcl $0, 4($v) +END + +BEGIN inc_return %esi + movl ($v), %eax + movl 4($v), %edx + addl $1, %eax + adcl $0, %edx + movl %eax, ($v) + movl %edx, 4($v) +END + +BEGIN dec %esi + subl $1, ($v) + sbbl $0, 4($v) +END + +BEGIN dec_return %esi + movl ($v), %eax + movl 4($v), %edx + subl $1, %eax + sbbl $0, %edx + movl %eax, ($v) + movl %edx, 4($v) +END + +BEGIN add_unless %ecx + addl %eax, %esi + adcl %edx, %edi + addl ($v), %eax + adcl 4($v), %edx + cmpl %eax, %esi + je 3f +1: + movl %eax, ($v) + movl %edx, 4($v) + movl $1, %eax +2: +RETURN +3: + cmpl %edx, %edi + jne 1b + xorl %eax, %eax + jmp 2b +END_ + +BEGIN inc_not_zero %esi + movl ($v), %eax + movl 4($v), %edx + testl %eax, %eax + je 3f +1: + addl $1, %eax + adcl $0, %edx + movl %eax, ($v) + movl %edx, 4($v) + movl $1, %eax +2: +RETURN +3: + testl %edx, %edx + jne 1b + jmp 2b +END_ + +BEGIN dec_if_positive %esi + movl ($v), %eax + movl 4($v), %edx + subl $1, %eax + sbbl $0, %edx + js 1f + movl %eax, ($v) + movl %edx, 4($v) +1: +END diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S new file mode 100644 index 00000000000..71e080de335 --- /dev/null +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -0,0 +1,224 @@ +/* + * atomic64_t for 586+ + * + * Copyright © 2010 Luca Barbieri + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/linkage.h> +#include <asm/alternative-asm.h> +#include <asm/dwarf2.h> + +.macro SAVE reg + pushl %\reg + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET \reg, 0 +.endm + +.macro RESTORE reg + popl %\reg + CFI_ADJUST_CFA_OFFSET -4 + CFI_RESTORE \reg +.endm + +.macro read64 reg + movl %ebx, %eax + movl %ecx, %edx +/* we need LOCK_PREFIX since otherwise cmpxchg8b always does the write */ + LOCK_PREFIX + cmpxchg8b (\reg) +.endm + +ENTRY(atomic64_read_cx8) + CFI_STARTPROC + + read64 %ecx + ret + CFI_ENDPROC +ENDPROC(atomic64_read_cx8) + +ENTRY(atomic64_set_cx8) + CFI_STARTPROC + +1: +/* we don't need LOCK_PREFIX since aligned 64-bit writes + * are atomic on 586 and newer */ + cmpxchg8b (%esi) + jne 1b + + ret + CFI_ENDPROC +ENDPROC(atomic64_set_cx8) + +ENTRY(atomic64_xchg_cx8) + CFI_STARTPROC + + movl %ebx, %eax + movl %ecx, %edx +1: + LOCK_PREFIX + cmpxchg8b (%esi) + jne 1b + + ret + CFI_ENDPROC +ENDPROC(atomic64_xchg_cx8) + +.macro addsub_return func ins insc +ENTRY(atomic64_\func\()_return_cx8) + CFI_STARTPROC + SAVE ebp + SAVE ebx + SAVE esi + SAVE edi + + movl %eax, %esi + movl %edx, %edi + movl %ecx, %ebp + + read64 %ebp +1: + movl %eax, %ebx + movl %edx, %ecx + \ins\()l %esi, %ebx + \insc\()l %edi, %ecx + LOCK_PREFIX + cmpxchg8b (%ebp) + jne 1b + +10: + movl %ebx, %eax + movl %ecx, %edx + RESTORE edi + RESTORE esi + RESTORE ebx + RESTORE ebp + ret + CFI_ENDPROC +ENDPROC(atomic64_\func\()_return_cx8) +.endm + +addsub_return add add adc +addsub_return sub sub sbb + +.macro incdec_return func ins insc +ENTRY(atomic64_\func\()_return_cx8) + CFI_STARTPROC + SAVE ebx + + read64 %esi +1: + movl %eax, %ebx + movl %edx, %ecx + \ins\()l $1, %ebx + \insc\()l $0, %ecx + LOCK_PREFIX + cmpxchg8b (%esi) + jne 1b + +10: + movl %ebx, %eax + movl %ecx, %edx + RESTORE ebx + ret + CFI_ENDPROC +ENDPROC(atomic64_\func\()_return_cx8) +.endm + +incdec_return inc add adc +incdec_return dec sub sbb + +ENTRY(atomic64_dec_if_positive_cx8) + CFI_STARTPROC + SAVE ebx + + read64 %esi +1: + movl %eax, %ebx + movl %edx, %ecx + subl $1, %ebx + sbb $0, %ecx + js 2f + LOCK_PREFIX + cmpxchg8b (%esi) + jne 1b + +2: + movl %ebx, %eax + movl %ecx, %edx + RESTORE ebx + ret + CFI_ENDPROC +ENDPROC(atomic64_dec_if_positive_cx8) + +ENTRY(atomic64_add_unless_cx8) + CFI_STARTPROC + SAVE ebp + SAVE ebx +/* these just push these two parameters on the stack */ + SAVE edi + SAVE esi + + movl %ecx, %ebp + movl %eax, %esi + movl %edx, %edi + + read64 %ebp +1: + cmpl %eax, 0(%esp) + je 4f +2: + movl %eax, %ebx + movl %edx, %ecx + addl %esi, %ebx + adcl %edi, %ecx + LOCK_PREFIX + cmpxchg8b (%ebp) + jne 1b + + movl $1, %eax +3: + addl $8, %esp + CFI_ADJUST_CFA_OFFSET -8 + RESTORE ebx + RESTORE ebp + ret +4: + cmpl %edx, 4(%esp) + jne 2b + xorl %eax, %eax + jmp 3b + CFI_ENDPROC +ENDPROC(atomic64_add_unless_cx8) + +ENTRY(atomic64_inc_not_zero_cx8) + CFI_STARTPROC + SAVE ebx + + read64 %esi +1: + testl %eax, %eax + je 4f +2: + movl %eax, %ebx + movl %edx, %ecx + addl $1, %ebx + adcl $0, %ecx + LOCK_PREFIX + cmpxchg8b (%esi) + jne 1b + + movl $1, %eax +3: + RESTORE ebx + ret +4: + testl %edx, %edx + jne 2b + jmp 3b + CFI_ENDPROC +ENDPROC(atomic64_inc_not_zero_cx8) diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index ebeafcce04a..aa4326bfb24 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -52,7 +52,7 @@ ENDPROC(clear_page) .align 8 .quad clear_page .quad 1b - .byte X86_FEATURE_REP_GOOD + .word X86_FEATURE_REP_GOOD .byte .Lclear_page_end - clear_page .byte 2b - 1b .previous diff --git a/arch/x86/kernel/cpu/cmpxchg.c b/arch/x86/lib/cmpxchg.c index 2056ccf572c..5d619f6df3e 100644 --- a/arch/x86/kernel/cpu/cmpxchg.c +++ b/arch/x86/lib/cmpxchg.c @@ -52,21 +52,3 @@ unsigned long cmpxchg_386_u32(volatile void *ptr, u32 old, u32 new) } EXPORT_SYMBOL(cmpxchg_386_u32); #endif - -#ifndef CONFIG_X86_CMPXCHG64 -unsigned long long cmpxchg_486_u64(volatile void *ptr, u64 old, u64 new) -{ - u64 prev; - unsigned long flags; - - /* Poor man's cmpxchg8b for 386 and 486. Unsuitable for SMP */ - local_irq_save(flags); - prev = *(u64 *)ptr; - if (prev == old) - *(u64 *)ptr = new; - local_irq_restore(flags); - return prev; -} -EXPORT_SYMBOL(cmpxchg_486_u64); -#endif - diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index 727a5d46d2f..6fec2d1cebe 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -113,7 +113,7 @@ ENDPROC(copy_page) .align 8 .quad copy_page .quad 1b - .byte X86_FEATURE_REP_GOOD + .word X86_FEATURE_REP_GOOD .byte .Lcopy_page_end - copy_page .byte 2b - 1b .previous diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 71100c98e33..a460158b5ac 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -29,7 +29,7 @@ .align 8 .quad 0b .quad 2b - .byte \feature /* when feature is set */ + .word \feature /* when feature is set */ .byte 5 .byte 5 .previous diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index f82e884928a..bcbcd1e0f7d 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -131,7 +131,7 @@ ENDPROC(__memcpy) .align 8 .quad memcpy .quad .Lmemcpy_c - .byte X86_FEATURE_REP_GOOD + .word X86_FEATURE_REP_GOOD /* * Replace only beginning, memcpy is used to apply alternatives, diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index e88d3b81644..09d34426965 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -121,7 +121,7 @@ ENDPROC(__memset) .align 8 .quad memset .quad .Lmemset_c - .byte X86_FEATURE_REP_GOOD + .word X86_FEATURE_REP_GOOD .byte .Lfinal - memset .byte .Lmemset_e - .Lmemset_c .previous diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c index aa098708877..dc8adad10a2 100644 --- a/arch/x86/math-emu/fpu_aux.c +++ b/arch/x86/math-emu/fpu_aux.c @@ -30,10 +30,10 @@ static void fclex(void) } /* Needs to be externally visible */ -void finit_task(struct task_struct *tsk) +void finit_soft_fpu(struct i387_soft_struct *soft) { - struct i387_soft_struct *soft = &tsk->thread.xstate->soft; struct address *oaddr, *iaddr; + memset(soft, 0, sizeof(*soft)); soft->cwd = 0x037f; soft->swd = 0; soft->ftop = 0; /* We don't keep top in the status word internally. */ @@ -52,7 +52,7 @@ void finit_task(struct task_struct *tsk) void finit(void) { - finit_task(current); + finit_soft_fpu(¤t->thread.fpu.state->soft); } /* diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 5d87f586f8d..7718541541d 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -681,7 +681,7 @@ int fpregs_soft_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct i387_soft_struct *s387 = &target->thread.xstate->soft; + struct i387_soft_struct *s387 = &target->thread.fpu.state->soft; void *space = s387->st_space; int ret; int offset, other, i, tags, regnr, tag, newtop; @@ -733,7 +733,7 @@ int fpregs_soft_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - struct i387_soft_struct *s387 = &target->thread.xstate->soft; + struct i387_soft_struct *s387 = &target->thread.fpu.state->soft; const void *space = s387->st_space; int ret; int offset = (S387->ftop & 7) * 10, other = 80 - offset; diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index 50fa0ec2c8a..2c614410a5f 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -31,7 +31,7 @@ #define SEG_EXPAND_DOWN(s) (((s).b & ((1 << 11) | (1 << 10))) \ == (1 << 10)) -#define I387 (current->thread.xstate) +#define I387 (current->thread.fpu.state) #define FPU_info (I387->soft.info) #define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs)) diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 06630d26e56..a4c768397ba 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -6,6 +6,7 @@ nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_physaddr.o := $(nostackp) CFLAGS_setup_nx.o := $(nostackp) +obj-$(CONFIG_X86_PAT) += pat_rbtree.o obj-$(CONFIG_SMP) += tlb.o obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index a725b7f760a..0002a3a3308 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -37,6 +37,28 @@ struct addr_marker { const char *name; }; +/* indices for address_markers; keep sync'd w/ address_markers below */ +enum address_markers_idx { + USER_SPACE_NR = 0, +#ifdef CONFIG_X86_64 + KERNEL_SPACE_NR, + LOW_KERNEL_NR, + VMALLOC_START_NR, + VMEMMAP_START_NR, + HIGH_KERNEL_NR, + MODULES_VADDR_NR, + MODULES_END_NR, +#else + KERNEL_SPACE_NR, + VMALLOC_START_NR, + VMALLOC_END_NR, +# ifdef CONFIG_HIGHMEM + PKMAP_BASE_NR, +# endif + FIXADDR_START_NR, +#endif +}; + /* Address space markers hints */ static struct addr_marker address_markers[] = { { 0, "User Space" }, @@ -331,14 +353,12 @@ static int pt_dump_init(void) #ifdef CONFIG_X86_32 /* Not a compile-time constant on x86-32 */ - address_markers[2].start_address = VMALLOC_START; - address_markers[3].start_address = VMALLOC_END; + address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; + address_markers[VMALLOC_END_NR].start_address = VMALLOC_END; # ifdef CONFIG_HIGHMEM - address_markers[4].start_address = PKMAP_BASE; - address_markers[5].start_address = FIXADDR_START; -# else - address_markers[4].start_address = FIXADDR_START; + address_markers[PKMAP_BASE_NR].start_address = PKMAP_BASE; # endif + address_markers[FIXADDR_START_NR].start_address = FIXADDR_START; #endif pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL, diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 63a6ba66cbe..5e8fa12ef86 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -53,7 +53,7 @@ void *kmap_atomic(struct page *page, enum km_type type) return kmap_atomic_prot(page, type, kmap_prot); } -void kunmap_atomic(void *kvaddr, enum km_type type) +void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type) { unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id(); @@ -102,7 +102,7 @@ struct page *kmap_atomic_to_page(void *ptr) EXPORT_SYMBOL(kmap); EXPORT_SYMBOL(kunmap); EXPORT_SYMBOL(kmap_atomic); -EXPORT_SYMBOL(kunmap_atomic); +EXPORT_SYMBOL(kunmap_atomic_notypecheck); EXPORT_SYMBOL(kmap_atomic_prot); EXPORT_SYMBOL(kmap_atomic_to_page); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ee41bba315d..9a6674689a2 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -2,7 +2,7 @@ * linux/arch/x86_64/mm/init.c * * Copyright (C) 1995 Linus Torvalds - * Copyright (C) 2000 Pavel Machek <pavel@suse.cz> + * Copyright (C) 2000 Pavel Machek <pavel@ucw.cz> * Copyright (C) 2002,2003 Andi Kleen <ak@suse.de> */ diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 12e4d2d3c11..3ba6e0608c5 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -62,8 +62,8 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, static void __iomem *__ioremap_caller(resource_size_t phys_addr, unsigned long size, unsigned long prot_val, void *caller) { - unsigned long pfn, offset, vaddr; - resource_size_t last_addr; + unsigned long offset, vaddr; + resource_size_t pfn, last_pfn, last_addr; const resource_size_t unaligned_phys_addr = phys_addr; const unsigned long unaligned_size = size; struct vm_struct *area; @@ -100,10 +100,8 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ - for (pfn = phys_addr >> PAGE_SHIFT; - (pfn << PAGE_SHIFT) < (last_addr & PAGE_MASK); - pfn++) { - + last_pfn = last_addr >> PAGE_SHIFT; + for (pfn = phys_addr >> PAGE_SHIFT; pfn <= last_pfn; pfn++) { int is_ram = page_is_ram(pfn); if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn))) @@ -115,7 +113,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, * Mappings have to be page-aligned */ offset = phys_addr & ~PAGE_MASK; - phys_addr &= PAGE_MASK; + phys_addr &= PHYSICAL_PAGE_MASK; size = PAGE_ALIGN(last_addr+1) - phys_addr; retval = reserve_memtype(phys_addr, (u64)phys_addr + size, @@ -613,7 +611,7 @@ void __init early_iounmap(void __iomem *addr, unsigned long size) return; } offset = virt_addr & ~PAGE_MASK; - nrpages = PAGE_ALIGN(offset + size - 1) >> PAGE_SHIFT; + nrpages = PAGE_ALIGN(offset + size) >> PAGE_SHIFT; idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; while (nrpages > 0) { diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 5d0e67fff1a..e5d5e2ce9f7 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -45,6 +45,8 @@ struct kmmio_fault_page { * Protected by kmmio_lock, when linked into kmmio_page_table. */ int count; + + bool scheduled_for_release; }; struct kmmio_delayed_release { @@ -398,8 +400,11 @@ static void release_kmmio_fault_page(unsigned long page, BUG_ON(f->count < 0); if (!f->count) { disarm_kmmio_fault_page(f); - f->release_next = *release_list; - *release_list = f; + if (!f->scheduled_for_release) { + f->release_next = *release_list; + *release_list = f; + f->scheduled_for_release = true; + } } } @@ -471,8 +476,10 @@ static void remove_kmmio_fault_pages(struct rcu_head *head) prevp = &f->release_next; } else { *prevp = f->release_next; + f->release_next = NULL; + f->scheduled_for_release = false; } - f = f->release_next; + f = *prevp; } spin_unlock_irqrestore(&kmmio_lock, flags); @@ -510,6 +517,9 @@ void unregister_kmmio_probe(struct kmmio_probe *p) kmmio_count--; spin_unlock_irqrestore(&kmmio_lock, flags); + if (!release_list) + return; + drelease = kmalloc(sizeof(*drelease), GFP_ATOMIC); if (!drelease) { pr_crit("leaking kmmio_fault_page objects.\n"); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 550df481acc..787c52ca49c 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -3,12 +3,6 @@ #include <linux/module.h> #include <linux/bootmem.h> -#ifdef CONFIG_DEBUG_PER_CPU_MAPS -# define DBG(x...) printk(KERN_DEBUG x) -#else -# define DBG(x...) -#endif - /* * Which logical CPUs are on which nodes */ diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 8948f47fde0..a7bcc23ef96 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -33,9 +33,6 @@ int numa_off __initdata; static unsigned long __initdata nodemap_addr; static unsigned long __initdata nodemap_size; -DEFINE_PER_CPU(int, node_number) = 0; -EXPORT_PER_CPU_SYMBOL(node_number); - /* * Map cpu index to node index */ @@ -809,7 +806,7 @@ void __cpuinit numa_set_node(int cpu, int node) per_cpu(x86_cpu_to_node_map, cpu) = node; if (node != NUMA_NO_NODE) - per_cpu(node_number, cpu) = node; + set_cpu_numa_node(cpu, node); } void __cpuinit numa_clear_node(int cpu) @@ -867,7 +864,7 @@ void __cpuinit numa_remove_cpu(int cpu) numa_set_cpumask(cpu, 0); } -int cpu_to_node(int cpu) +int __cpu_to_node(int cpu) { if (early_per_cpu_ptr(x86_cpu_to_node_map)) { printk(KERN_WARNING @@ -877,7 +874,7 @@ int cpu_to_node(int cpu) } return per_cpu(x86_cpu_to_node_map, cpu); } -EXPORT_SYMBOL(cpu_to_node); +EXPORT_SYMBOL(__cpu_to_node); /* * Same function as cpu_to_node() but used if called before the diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 28195c350b9..532e7933d60 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -997,7 +997,8 @@ out_err: } EXPORT_SYMBOL(set_memory_uc); -int set_memory_array_uc(unsigned long *addr, int addrinarray) +int _set_memory_array(unsigned long *addr, int addrinarray, + unsigned long new_type) { int i, j; int ret; @@ -1007,13 +1008,19 @@ int set_memory_array_uc(unsigned long *addr, int addrinarray) */ for (i = 0; i < addrinarray; i++) { ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE, - _PAGE_CACHE_UC_MINUS, NULL); + new_type, NULL); if (ret) goto out_free; } ret = change_page_attr_set(addr, addrinarray, __pgprot(_PAGE_CACHE_UC_MINUS), 1); + + if (!ret && new_type == _PAGE_CACHE_WC) + ret = change_page_attr_set_clr(addr, addrinarray, + __pgprot(_PAGE_CACHE_WC), + __pgprot(_PAGE_CACHE_MASK), + 0, CPA_ARRAY, NULL); if (ret) goto out_free; @@ -1025,8 +1032,19 @@ out_free: return ret; } + +int set_memory_array_uc(unsigned long *addr, int addrinarray) +{ + return _set_memory_array(addr, addrinarray, _PAGE_CACHE_UC_MINUS); +} EXPORT_SYMBOL(set_memory_array_uc); +int set_memory_array_wc(unsigned long *addr, int addrinarray) +{ + return _set_memory_array(addr, addrinarray, _PAGE_CACHE_WC); +} +EXPORT_SYMBOL(set_memory_array_wc); + int _set_memory_wc(unsigned long addr, int numpages) { int ret; @@ -1153,26 +1171,34 @@ int set_pages_uc(struct page *page, int numpages) } EXPORT_SYMBOL(set_pages_uc); -int set_pages_array_uc(struct page **pages, int addrinarray) +static int _set_pages_array(struct page **pages, int addrinarray, + unsigned long new_type) { unsigned long start; unsigned long end; int i; int free_idx; + int ret; for (i = 0; i < addrinarray; i++) { if (PageHighMem(pages[i])) continue; start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; - if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL)) + if (reserve_memtype(start, end, new_type, NULL)) goto err_out; } - if (cpa_set_pages_array(pages, addrinarray, - __pgprot(_PAGE_CACHE_UC_MINUS)) == 0) { - return 0; /* Success */ - } + ret = cpa_set_pages_array(pages, addrinarray, + __pgprot(_PAGE_CACHE_UC_MINUS)); + if (!ret && new_type == _PAGE_CACHE_WC) + ret = change_page_attr_set_clr(NULL, addrinarray, + __pgprot(_PAGE_CACHE_WC), + __pgprot(_PAGE_CACHE_MASK), + 0, CPA_PAGES_ARRAY, pages); + if (ret) + goto err_out; + return 0; /* Success */ err_out: free_idx = i; for (i = 0; i < free_idx; i++) { @@ -1184,8 +1210,19 @@ err_out: } return -EINVAL; } + +int set_pages_array_uc(struct page **pages, int addrinarray) +{ + return _set_pages_array(pages, addrinarray, _PAGE_CACHE_UC_MINUS); +} EXPORT_SYMBOL(set_pages_array_uc); +int set_pages_array_wc(struct page **pages, int addrinarray) +{ + return _set_pages_array(pages, addrinarray, _PAGE_CACHE_WC); +} +EXPORT_SYMBOL(set_pages_array_wc); + int set_pages_wb(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index edc8b95afc1..f6ff57b7efa 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -30,6 +30,8 @@ #include <asm/pat.h> #include <asm/io.h> +#include "pat_internal.h" + #ifdef CONFIG_X86_PAT int __read_mostly pat_enabled = 1; @@ -53,19 +55,15 @@ static inline void pat_disable(const char *reason) #endif -static int debug_enable; +int pat_debug_enable; static int __init pat_debug_setup(char *str) { - debug_enable = 1; + pat_debug_enable = 1; return 0; } __setup("debugpat", pat_debug_setup); -#define dprintk(fmt, arg...) \ - do { if (debug_enable) printk(KERN_INFO fmt, ##arg); } while (0) - - static u64 __read_mostly boot_pat_state; enum { @@ -132,84 +130,7 @@ void pat_init(void) #undef PAT -static char *cattr_name(unsigned long flags) -{ - switch (flags & _PAGE_CACHE_MASK) { - case _PAGE_CACHE_UC: return "uncached"; - case _PAGE_CACHE_UC_MINUS: return "uncached-minus"; - case _PAGE_CACHE_WB: return "write-back"; - case _PAGE_CACHE_WC: return "write-combining"; - default: return "broken"; - } -} - -/* - * The global memtype list keeps track of memory type for specific - * physical memory areas. Conflicting memory types in different - * mappings can cause CPU cache corruption. To avoid this we keep track. - * - * The list is sorted based on starting address and can contain multiple - * entries for each address (this allows reference counting for overlapping - * areas). All the aliases have the same cache attributes of course. - * Zero attributes are represented as holes. - * - * The data structure is a list that is also organized as an rbtree - * sorted on the start address of memtype range. - * - * memtype_lock protects both the linear list and rbtree. - */ - -struct memtype { - u64 start; - u64 end; - unsigned long type; - struct list_head nd; - struct rb_node rb; -}; - -static struct rb_root memtype_rbroot = RB_ROOT; -static LIST_HEAD(memtype_list); -static DEFINE_SPINLOCK(memtype_lock); /* protects memtype list */ - -static struct memtype *memtype_rb_search(struct rb_root *root, u64 start) -{ - struct rb_node *node = root->rb_node; - struct memtype *last_lower = NULL; - - while (node) { - struct memtype *data = container_of(node, struct memtype, rb); - - if (data->start < start) { - last_lower = data; - node = node->rb_right; - } else if (data->start > start) { - node = node->rb_left; - } else - return data; - } - - /* Will return NULL if there is no entry with its start <= start */ - return last_lower; -} - -static void memtype_rb_insert(struct rb_root *root, struct memtype *data) -{ - struct rb_node **new = &(root->rb_node); - struct rb_node *parent = NULL; - - while (*new) { - struct memtype *this = container_of(*new, struct memtype, rb); - - parent = *new; - if (data->start <= this->start) - new = &((*new)->rb_left); - else if (data->start > this->start) - new = &((*new)->rb_right); - } - - rb_link_node(&data->rb, parent, new); - rb_insert_color(&data->rb, root); -} +static DEFINE_SPINLOCK(memtype_lock); /* protects memtype accesses */ /* * Does intersection of PAT memory type and MTRR memory type and returns @@ -237,34 +158,7 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type) return req_type; } -static int -chk_conflict(struct memtype *new, struct memtype *entry, unsigned long *type) -{ - if (new->type != entry->type) { - if (type) { - new->type = entry->type; - *type = entry->type; - } else - goto conflict; - } - - /* check overlaps with more than one entry in the list */ - list_for_each_entry_continue(entry, &memtype_list, nd) { - if (new->end <= entry->start) - break; - else if (new->type != entry->type) - goto conflict; - } - return 0; - - conflict: - printk(KERN_INFO "%s:%d conflicting memory types " - "%Lx-%Lx %s<->%s\n", current->comm, current->pid, new->start, - new->end, cattr_name(new->type), cattr_name(entry->type)); - return -EBUSY; -} - -static int pat_pagerange_is_ram(unsigned long start, unsigned long end) +static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end) { int ram_page = 0, not_rampage = 0; unsigned long page_nr; @@ -296,8 +190,6 @@ static int pat_pagerange_is_ram(unsigned long start, unsigned long end) * Here we do two pass: * - Find the memtype of all the pages in the range, look for any conflicts * - In case of no conflicts, set the new memtype for pages in the range - * - * Caller must hold memtype_lock for atomicity. */ static int reserve_ram_pages_type(u64 start, u64 end, unsigned long req_type, unsigned long *new_type) @@ -364,9 +256,8 @@ static int free_ram_pages_type(u64 start, u64 end) int reserve_memtype(u64 start, u64 end, unsigned long req_type, unsigned long *new_type) { - struct memtype *new, *entry; + struct memtype *new; unsigned long actual_type; - struct list_head *where; int is_range_ram; int err = 0; @@ -404,16 +295,14 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, is_range_ram = pat_pagerange_is_ram(start, end); if (is_range_ram == 1) { - spin_lock(&memtype_lock); err = reserve_ram_pages_type(start, end, req_type, new_type); - spin_unlock(&memtype_lock); return err; } else if (is_range_ram < 0) { return -EINVAL; } - new = kmalloc(sizeof(struct memtype), GFP_KERNEL); + new = kzalloc(sizeof(struct memtype), GFP_KERNEL); if (!new) return -ENOMEM; @@ -423,42 +312,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, spin_lock(&memtype_lock); - /* Search for existing mapping that overlaps the current range */ - where = NULL; - list_for_each_entry(entry, &memtype_list, nd) { - if (end <= entry->start) { - where = entry->nd.prev; - break; - } else if (start <= entry->start) { /* end > entry->start */ - err = chk_conflict(new, entry, new_type); - if (!err) { - dprintk("Overlap at 0x%Lx-0x%Lx\n", - entry->start, entry->end); - where = entry->nd.prev; - } - break; - } else if (start < entry->end) { /* start > entry->start */ - err = chk_conflict(new, entry, new_type); - if (!err) { - dprintk("Overlap at 0x%Lx-0x%Lx\n", - entry->start, entry->end); - - /* - * Move to right position in the linked - * list to add this new entry - */ - list_for_each_entry_continue(entry, - &memtype_list, nd) { - if (start <= entry->start) { - where = entry->nd.prev; - break; - } - } - } - break; - } - } - + err = rbt_memtype_check_insert(new, new_type); if (err) { printk(KERN_INFO "reserve_memtype failed 0x%Lx-0x%Lx, " "track %s, req %s\n", @@ -469,13 +323,6 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, return err; } - if (where) - list_add(&new->nd, where); - else - list_add_tail(&new->nd, &memtype_list); - - memtype_rb_insert(&memtype_rbroot, new); - spin_unlock(&memtype_lock); dprintk("reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n", @@ -487,9 +334,9 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, int free_memtype(u64 start, u64 end) { - struct memtype *entry, *saved_entry; int err = -EINVAL; int is_range_ram; + struct memtype *entry; if (!pat_enabled) return 0; @@ -501,9 +348,7 @@ int free_memtype(u64 start, u64 end) is_range_ram = pat_pagerange_is_ram(start, end); if (is_range_ram == 1) { - spin_lock(&memtype_lock); err = free_ram_pages_type(start, end); - spin_unlock(&memtype_lock); return err; } else if (is_range_ram < 0) { @@ -511,56 +356,20 @@ int free_memtype(u64 start, u64 end) } spin_lock(&memtype_lock); - - entry = memtype_rb_search(&memtype_rbroot, start); - if (unlikely(entry == NULL)) - goto unlock_ret; - - /* - * Saved entry points to an entry with start same or less than what - * we searched for. Now go through the list in both directions to look - * for the entry that matches with both start and end, with list stored - * in sorted start address - */ - saved_entry = entry; - list_for_each_entry_from(entry, &memtype_list, nd) { - if (entry->start == start && entry->end == end) { - rb_erase(&entry->rb, &memtype_rbroot); - list_del(&entry->nd); - kfree(entry); - err = 0; - break; - } else if (entry->start > start) { - break; - } - } - - if (!err) - goto unlock_ret; - - entry = saved_entry; - list_for_each_entry_reverse(entry, &memtype_list, nd) { - if (entry->start == start && entry->end == end) { - rb_erase(&entry->rb, &memtype_rbroot); - list_del(&entry->nd); - kfree(entry); - err = 0; - break; - } else if (entry->start < start) { - break; - } - } -unlock_ret: + entry = rbt_memtype_erase(start, end); spin_unlock(&memtype_lock); - if (err) { + if (!entry) { printk(KERN_INFO "%s:%d freeing invalid memtype %Lx-%Lx\n", current->comm, current->pid, start, end); + return -EINVAL; } + kfree(entry); + dprintk("free_memtype request 0x%Lx-0x%Lx\n", start, end); - return err; + return 0; } @@ -583,10 +392,8 @@ static unsigned long lookup_memtype(u64 paddr) if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) { struct page *page; - spin_lock(&memtype_lock); page = pfn_to_page(paddr >> PAGE_SHIFT); rettype = get_page_memtype(page); - spin_unlock(&memtype_lock); /* * -1 from get_page_memtype() implies RAM page is in its * default state and not reserved, and hence of type WB @@ -599,7 +406,7 @@ static unsigned long lookup_memtype(u64 paddr) spin_lock(&memtype_lock); - entry = memtype_rb_search(&memtype_rbroot, paddr); + entry = rbt_memtype_lookup(paddr); if (entry != NULL) rettype = entry->type; else @@ -936,29 +743,25 @@ EXPORT_SYMBOL_GPL(pgprot_writecombine); #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT) -/* get Nth element of the linked list */ static struct memtype *memtype_get_idx(loff_t pos) { - struct memtype *list_node, *print_entry; - int i = 1; + struct memtype *print_entry; + int ret; - print_entry = kmalloc(sizeof(struct memtype), GFP_KERNEL); + print_entry = kzalloc(sizeof(struct memtype), GFP_KERNEL); if (!print_entry) return NULL; spin_lock(&memtype_lock); - list_for_each_entry(list_node, &memtype_list, nd) { - if (pos == i) { - *print_entry = *list_node; - spin_unlock(&memtype_lock); - return print_entry; - } - ++i; - } + ret = rbt_memtype_copy_nth_element(print_entry, pos); spin_unlock(&memtype_lock); - kfree(print_entry); - return NULL; + if (!ret) { + return print_entry; + } else { + kfree(print_entry); + return NULL; + } } static void *memtype_seq_start(struct seq_file *seq, loff_t *pos) diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h new file mode 100644 index 00000000000..77e5ba153fa --- /dev/null +++ b/arch/x86/mm/pat_internal.h @@ -0,0 +1,46 @@ +#ifndef __PAT_INTERNAL_H_ +#define __PAT_INTERNAL_H_ + +extern int pat_debug_enable; + +#define dprintk(fmt, arg...) \ + do { if (pat_debug_enable) printk(KERN_INFO fmt, ##arg); } while (0) + +struct memtype { + u64 start; + u64 end; + u64 subtree_max_end; + unsigned long type; + struct rb_node rb; +}; + +static inline char *cattr_name(unsigned long flags) +{ + switch (flags & _PAGE_CACHE_MASK) { + case _PAGE_CACHE_UC: return "uncached"; + case _PAGE_CACHE_UC_MINUS: return "uncached-minus"; + case _PAGE_CACHE_WB: return "write-back"; + case _PAGE_CACHE_WC: return "write-combining"; + default: return "broken"; + } +} + +#ifdef CONFIG_X86_PAT +extern int rbt_memtype_check_insert(struct memtype *new, + unsigned long *new_type); +extern struct memtype *rbt_memtype_erase(u64 start, u64 end); +extern struct memtype *rbt_memtype_lookup(u64 addr); +extern int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos); +#else +static inline int rbt_memtype_check_insert(struct memtype *new, + unsigned long *new_type) +{ return 0; } +static inline struct memtype *rbt_memtype_erase(u64 start, u64 end) +{ return NULL; } +static inline struct memtype *rbt_memtype_lookup(u64 addr) +{ return NULL; } +static inline int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos) +{ return 0; } +#endif + +#endif /* __PAT_INTERNAL_H_ */ diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c new file mode 100644 index 00000000000..8acaddd0fb2 --- /dev/null +++ b/arch/x86/mm/pat_rbtree.c @@ -0,0 +1,253 @@ +/* + * Handle caching attributes in page tables (PAT) + * + * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * Suresh B Siddha <suresh.b.siddha@intel.com> + * + * Interval tree (augmented rbtree) used to store the PAT memory type + * reservations. + */ + +#include <linux/seq_file.h> +#include <linux/debugfs.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/rbtree.h> +#include <linux/sched.h> +#include <linux/gfp.h> + +#include <asm/pgtable.h> +#include <asm/pat.h> + +#include "pat_internal.h" + +/* + * The memtype tree keeps track of memory type for specific + * physical memory areas. Without proper tracking, conflicting memory + * types in different mappings can cause CPU cache corruption. + * + * The tree is an interval tree (augmented rbtree) with tree ordered + * on starting address. Tree can contain multiple entries for + * different regions which overlap. All the aliases have the same + * cache attributes of course. + * + * memtype_lock protects the rbtree. + */ + +static struct rb_root memtype_rbroot = RB_ROOT; + +static int is_node_overlap(struct memtype *node, u64 start, u64 end) +{ + if (node->start >= end || node->end <= start) + return 0; + + return 1; +} + +static u64 get_subtree_max_end(struct rb_node *node) +{ + u64 ret = 0; + if (node) { + struct memtype *data = container_of(node, struct memtype, rb); + ret = data->subtree_max_end; + } + return ret; +} + +/* Update 'subtree_max_end' for a node, based on node and its children */ +static void memtype_rb_augment_cb(struct rb_node *node, void *__unused) +{ + struct memtype *data; + u64 max_end, child_max_end; + + if (!node) + return; + + data = container_of(node, struct memtype, rb); + max_end = data->end; + + child_max_end = get_subtree_max_end(node->rb_right); + if (child_max_end > max_end) + max_end = child_max_end; + + child_max_end = get_subtree_max_end(node->rb_left); + if (child_max_end > max_end) + max_end = child_max_end; + + data->subtree_max_end = max_end; +} + +/* Find the first (lowest start addr) overlapping range from rb tree */ +static struct memtype *memtype_rb_lowest_match(struct rb_root *root, + u64 start, u64 end) +{ + struct rb_node *node = root->rb_node; + struct memtype *last_lower = NULL; + + while (node) { + struct memtype *data = container_of(node, struct memtype, rb); + + if (get_subtree_max_end(node->rb_left) > start) { + /* Lowest overlap if any must be on left side */ + node = node->rb_left; + } else if (is_node_overlap(data, start, end)) { + last_lower = data; + break; + } else if (start >= data->start) { + /* Lowest overlap if any must be on right side */ + node = node->rb_right; + } else { + break; + } + } + return last_lower; /* Returns NULL if there is no overlap */ +} + +static struct memtype *memtype_rb_exact_match(struct rb_root *root, + u64 start, u64 end) +{ + struct memtype *match; + + match = memtype_rb_lowest_match(root, start, end); + while (match != NULL && match->start < end) { + struct rb_node *node; + + if (match->start == start && match->end == end) + return match; + + node = rb_next(&match->rb); + if (node) + match = container_of(node, struct memtype, rb); + else + match = NULL; + } + + return NULL; /* Returns NULL if there is no exact match */ +} + +static int memtype_rb_check_conflict(struct rb_root *root, + u64 start, u64 end, + unsigned long reqtype, unsigned long *newtype) +{ + struct rb_node *node; + struct memtype *match; + int found_type = reqtype; + + match = memtype_rb_lowest_match(&memtype_rbroot, start, end); + if (match == NULL) + goto success; + + if (match->type != found_type && newtype == NULL) + goto failure; + + dprintk("Overlap at 0x%Lx-0x%Lx\n", match->start, match->end); + found_type = match->type; + + node = rb_next(&match->rb); + while (node) { + match = container_of(node, struct memtype, rb); + + if (match->start >= end) /* Checked all possible matches */ + goto success; + + if (is_node_overlap(match, start, end) && + match->type != found_type) { + goto failure; + } + + node = rb_next(&match->rb); + } +success: + if (newtype) + *newtype = found_type; + + return 0; + +failure: + printk(KERN_INFO "%s:%d conflicting memory types " + "%Lx-%Lx %s<->%s\n", current->comm, current->pid, start, + end, cattr_name(found_type), cattr_name(match->type)); + return -EBUSY; +} + +static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata) +{ + struct rb_node **node = &(root->rb_node); + struct rb_node *parent = NULL; + + while (*node) { + struct memtype *data = container_of(*node, struct memtype, rb); + + parent = *node; + if (newdata->start <= data->start) + node = &((*node)->rb_left); + else if (newdata->start > data->start) + node = &((*node)->rb_right); + } + + rb_link_node(&newdata->rb, parent, node); + rb_insert_color(&newdata->rb, root); + rb_augment_insert(&newdata->rb, memtype_rb_augment_cb, NULL); +} + +int rbt_memtype_check_insert(struct memtype *new, unsigned long *ret_type) +{ + int err = 0; + + err = memtype_rb_check_conflict(&memtype_rbroot, new->start, new->end, + new->type, ret_type); + + if (!err) { + if (ret_type) + new->type = *ret_type; + + new->subtree_max_end = new->end; + memtype_rb_insert(&memtype_rbroot, new); + } + return err; +} + +struct memtype *rbt_memtype_erase(u64 start, u64 end) +{ + struct rb_node *deepest; + struct memtype *data; + + data = memtype_rb_exact_match(&memtype_rbroot, start, end); + if (!data) + goto out; + + deepest = rb_augment_erase_begin(&data->rb); + rb_erase(&data->rb, &memtype_rbroot); + rb_augment_erase_end(deepest, memtype_rb_augment_cb, NULL); +out: + return data; +} + +struct memtype *rbt_memtype_lookup(u64 addr) +{ + struct memtype *data; + data = memtype_rb_lowest_match(&memtype_rbroot, addr, addr + PAGE_SIZE); + return data; +} + +#if defined(CONFIG_DEBUG_FS) +int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos) +{ + struct rb_node *node; + int i = 1; + + node = rb_first(&memtype_rbroot); + while (node && pos != i) { + node = rb_next(node); + i++; + } + + if (node) { /* pos == i */ + struct memtype *this = container_of(node, struct memtype, rb); + *out = *this; + return 0; + } else { + return 1; + } +} +#endif diff --git a/arch/x86/mm/pf_in.c b/arch/x86/mm/pf_in.c index df3d5c861cd..38e6d174c49 100644 --- a/arch/x86/mm/pf_in.c +++ b/arch/x86/mm/pf_in.c @@ -34,22 +34,22 @@ /* IA32 Manual 3, 2-1 */ static unsigned char prefix_codes[] = { 0xF0, 0xF2, 0xF3, 0x2E, 0x36, 0x3E, 0x26, 0x64, - 0x65, 0x2E, 0x3E, 0x66, 0x67 + 0x65, 0x66, 0x67 }; /* IA32 Manual 3, 3-432*/ static unsigned int reg_rop[] = { 0x8A, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F }; -static unsigned int reg_wop[] = { 0x88, 0x89 }; +static unsigned int reg_wop[] = { 0x88, 0x89, 0xAA, 0xAB }; static unsigned int imm_wop[] = { 0xC6, 0xC7 }; /* IA32 Manual 3, 3-432*/ -static unsigned int rw8[] = { 0x88, 0x8A, 0xC6 }; +static unsigned int rw8[] = { 0x88, 0x8A, 0xC6, 0xAA }; static unsigned int rw32[] = { - 0x89, 0x8B, 0xC7, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F + 0x89, 0x8B, 0xC7, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F, 0xAB }; -static unsigned int mw8[] = { 0x88, 0x8A, 0xC6, 0xB60F, 0xBE0F }; +static unsigned int mw8[] = { 0x88, 0x8A, 0xC6, 0xB60F, 0xBE0F, 0xAA }; static unsigned int mw16[] = { 0xB70F, 0xBF0F }; -static unsigned int mw32[] = { 0x89, 0x8B, 0xC7 }; +static unsigned int mw32[] = { 0x89, 0x8B, 0xC7, 0xAB }; static unsigned int mw64[] = {}; #else /* not __i386__ */ static unsigned char prefix_codes[] = { @@ -63,20 +63,20 @@ static unsigned char prefix_codes[] = { static unsigned int reg_rop[] = { 0x8A, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F }; -static unsigned int reg_wop[] = { 0x88, 0x89 }; +static unsigned int reg_wop[] = { 0x88, 0x89, 0xAA, 0xAB }; static unsigned int imm_wop[] = { 0xC6, 0xC7 }; -static unsigned int rw8[] = { 0xC6, 0x88, 0x8A }; +static unsigned int rw8[] = { 0xC6, 0x88, 0x8A, 0xAA }; static unsigned int rw32[] = { - 0xC7, 0x89, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F + 0xC7, 0x89, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F, 0xAB }; /* 8 bit only */ -static unsigned int mw8[] = { 0xC6, 0x88, 0x8A, 0xB60F, 0xBE0F }; +static unsigned int mw8[] = { 0xC6, 0x88, 0x8A, 0xB60F, 0xBE0F, 0xAA }; /* 16 bit only */ static unsigned int mw16[] = { 0xB70F, 0xBF0F }; /* 16 or 32 bit */ static unsigned int mw32[] = { 0xC7 }; /* 16, 32 or 64 bit */ -static unsigned int mw64[] = { 0x89, 0x8B }; +static unsigned int mw64[] = { 0x89, 0x8B, 0xAB }; #endif /* not __i386__ */ struct prefix_bits { @@ -410,7 +410,6 @@ static unsigned long *get_reg_w32(int no, struct pt_regs *regs) unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs) { unsigned int opcode; - unsigned char mod_rm; int reg; unsigned char *p; struct prefix_bits prf; @@ -437,8 +436,13 @@ unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs) goto err; do_work: - mod_rm = *p; - reg = ((mod_rm >> 3) & 0x7) | (prf.rexr << 3); + /* for STOS, source register is fixed */ + if (opcode == 0xAA || opcode == 0xAB) { + reg = arg_AX; + } else { + unsigned char mod_rm = *p; + reg = ((mod_rm >> 3) & 0x7) | (prf.rexr << 3); + } switch (get_ins_reg_width(ins_addr)) { case 1: return *get_reg_w8(reg, prf.rex, regs); diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 792854003ed..cac71849925 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -9,7 +9,6 @@ #include <linux/pagemap.h> #include <linux/spinlock.h> #include <linux/module.h> -#include <linux/quicklist.h> #include <asm/system.h> #include <asm/pgtable.h> diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 38512d0c474..f9897f7a9ef 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -363,6 +363,54 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) for (i = 0; i < MAX_NUMNODES; i++) cutoff_node(i, start, end); + /* + * Join together blocks on the same node, holes between + * which don't overlap with memory on other nodes. + */ + for (i = 0; i < num_node_memblks; ++i) { + int j, k; + + for (j = i + 1; j < num_node_memblks; ++j) { + unsigned long start, end; + + if (memblk_nodeid[i] != memblk_nodeid[j]) + continue; + start = min(node_memblk_range[i].end, + node_memblk_range[j].end); + end = max(node_memblk_range[i].start, + node_memblk_range[j].start); + for (k = 0; k < num_node_memblks; ++k) { + if (memblk_nodeid[i] == memblk_nodeid[k]) + continue; + if (start < node_memblk_range[k].end && + end > node_memblk_range[k].start) + break; + } + if (k < num_node_memblks) + continue; + start = min(node_memblk_range[i].start, + node_memblk_range[j].start); + end = max(node_memblk_range[i].end, + node_memblk_range[j].end); + printk(KERN_INFO "SRAT: Node %d " + "[%Lx,%Lx) + [%Lx,%Lx) -> [%lx,%lx)\n", + memblk_nodeid[i], + node_memblk_range[i].start, + node_memblk_range[i].end, + node_memblk_range[j].start, + node_memblk_range[j].end, + start, end); + node_memblk_range[i].start = start; + node_memblk_range[i].end = end; + k = --num_node_memblks - j; + memmove(memblk_nodeid + j, memblk_nodeid + j+1, + k * sizeof(*memblk_nodeid)); + memmove(node_memblk_range + j, node_memblk_range + j+1, + k * sizeof(*node_memblk_range)); + --j; + } + } + memnode_shift = compute_hash_shift(node_memblk_range, num_node_memblks, memblk_nodeid); if (memnode_shift < 0) { diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c index 8565d944f7c..38868adf07e 100644 --- a/arch/x86/mm/testmmiotrace.c +++ b/arch/x86/mm/testmmiotrace.c @@ -90,6 +90,27 @@ static void do_test(unsigned long size) iounmap(p); } +/* + * Tests how mmiotrace behaves in face of multiple ioremap / iounmaps in + * a short time. We had a bug in deferred freeing procedure which tried + * to free this region multiple times (ioremap can reuse the same address + * for many mappings). + */ +static void do_test_bulk_ioremapping(void) +{ + void __iomem *p; + int i; + + for (i = 0; i < 10; ++i) { + p = ioremap_nocache(mmio_address, PAGE_SIZE); + if (p) + iounmap(p); + } + + /* Force freeing. If it will crash we will know why. */ + synchronize_rcu(); +} + static int __init init(void) { unsigned long size = (read_far) ? (8 << 20) : (16 << 10); @@ -104,6 +125,7 @@ static int __init init(void) "and writing 16 kB of rubbish in there.\n", size >> 10, mmio_address); do_test(size); + do_test_bulk_ioremapping(); pr_info("All done.\n"); return 0; } diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 426f3a1a64d..c03f14ab666 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -278,11 +278,9 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long va) static void do_flush_tlb_all(void *info) { - unsigned long cpu = smp_processor_id(); - __flush_tlb_all(); if (percpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY) - leave_mm(cpu); + leave_mm(smp_processor_id()); } void flush_tlb_all(void) diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 2c505ee7101..1ba67dc8006 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -31,8 +31,9 @@ static struct op_x86_model_spec *model; static DEFINE_PER_CPU(struct op_msrs, cpu_msrs); static DEFINE_PER_CPU(unsigned long, saved_lvtpc); -/* 0 == registered but off, 1 == registered and on */ -static int nmi_enabled = 0; +/* must be protected with get_online_cpus()/put_online_cpus(): */ +static int nmi_enabled; +static int ctr_running; struct op_counter_config counter_config[OP_MAX_COUNTER]; @@ -61,12 +62,16 @@ static int profile_exceptions_notify(struct notifier_block *self, { struct die_args *args = (struct die_args *)data; int ret = NOTIFY_DONE; - int cpu = smp_processor_id(); switch (val) { case DIE_NMI: case DIE_NMI_IPI: - model->check_ctrs(args->regs, &per_cpu(cpu_msrs, cpu)); + if (ctr_running) + model->check_ctrs(args->regs, &__get_cpu_var(cpu_msrs)); + else if (!nmi_enabled) + break; + else + model->stop(&__get_cpu_var(cpu_msrs)); ret = NOTIFY_STOP; break; default: @@ -95,24 +100,36 @@ static void nmi_cpu_save_registers(struct op_msrs *msrs) static void nmi_cpu_start(void *dummy) { struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs); - model->start(msrs); + if (!msrs->controls) + WARN_ON_ONCE(1); + else + model->start(msrs); } static int nmi_start(void) { + get_online_cpus(); on_each_cpu(nmi_cpu_start, NULL, 1); + ctr_running = 1; + put_online_cpus(); return 0; } static void nmi_cpu_stop(void *dummy) { struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs); - model->stop(msrs); + if (!msrs->controls) + WARN_ON_ONCE(1); + else + model->stop(msrs); } static void nmi_stop(void) { + get_online_cpus(); on_each_cpu(nmi_cpu_stop, NULL, 1); + ctr_running = 0; + put_online_cpus(); } #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX @@ -252,7 +269,10 @@ static int nmi_switch_event(void) if (nmi_multiplex_on() < 0) return -EINVAL; /* not necessary */ - on_each_cpu(nmi_cpu_switch, NULL, 1); + get_online_cpus(); + if (ctr_running) + on_each_cpu(nmi_cpu_switch, NULL, 1); + put_online_cpus(); return 0; } @@ -295,6 +315,7 @@ static void free_msrs(void) kfree(per_cpu(cpu_msrs, i).controls); per_cpu(cpu_msrs, i).controls = NULL; } + nmi_shutdown_mux(); } static int allocate_msrs(void) @@ -307,14 +328,21 @@ static int allocate_msrs(void) per_cpu(cpu_msrs, i).counters = kzalloc(counters_size, GFP_KERNEL); if (!per_cpu(cpu_msrs, i).counters) - return 0; + goto fail; per_cpu(cpu_msrs, i).controls = kzalloc(controls_size, GFP_KERNEL); if (!per_cpu(cpu_msrs, i).controls) - return 0; + goto fail; } + if (!nmi_setup_mux()) + goto fail; + return 1; + +fail: + free_msrs(); + return 0; } static void nmi_cpu_setup(void *dummy) @@ -336,49 +364,6 @@ static struct notifier_block profile_exceptions_nb = { .priority = 2 }; -static int nmi_setup(void) -{ - int err = 0; - int cpu; - - if (!allocate_msrs()) - err = -ENOMEM; - else if (!nmi_setup_mux()) - err = -ENOMEM; - else - err = register_die_notifier(&profile_exceptions_nb); - - if (err) { - free_msrs(); - nmi_shutdown_mux(); - return err; - } - - /* We need to serialize save and setup for HT because the subset - * of msrs are distinct for save and setup operations - */ - - /* Assume saved/restored counters are the same on all CPUs */ - model->fill_in_addresses(&per_cpu(cpu_msrs, 0)); - for_each_possible_cpu(cpu) { - if (!cpu) - continue; - - memcpy(per_cpu(cpu_msrs, cpu).counters, - per_cpu(cpu_msrs, 0).counters, - sizeof(struct op_msr) * model->num_counters); - - memcpy(per_cpu(cpu_msrs, cpu).controls, - per_cpu(cpu_msrs, 0).controls, - sizeof(struct op_msr) * model->num_controls); - - mux_clone(cpu); - } - on_each_cpu(nmi_cpu_setup, NULL, 1); - nmi_enabled = 1; - return 0; -} - static void nmi_cpu_restore_registers(struct op_msrs *msrs) { struct op_msr *counters = msrs->counters; @@ -412,20 +397,24 @@ static void nmi_cpu_shutdown(void *dummy) apic_write(APIC_LVTPC, per_cpu(saved_lvtpc, cpu)); apic_write(APIC_LVTERR, v); nmi_cpu_restore_registers(msrs); + if (model->cpu_down) + model->cpu_down(); } -static void nmi_shutdown(void) +static void nmi_cpu_up(void *dummy) { - struct op_msrs *msrs; + if (nmi_enabled) + nmi_cpu_setup(dummy); + if (ctr_running) + nmi_cpu_start(dummy); +} - nmi_enabled = 0; - on_each_cpu(nmi_cpu_shutdown, NULL, 1); - unregister_die_notifier(&profile_exceptions_nb); - nmi_shutdown_mux(); - msrs = &get_cpu_var(cpu_msrs); - model->shutdown(msrs); - free_msrs(); - put_cpu_var(cpu_msrs); +static void nmi_cpu_down(void *dummy) +{ + if (ctr_running) + nmi_cpu_stop(dummy); + if (nmi_enabled) + nmi_cpu_shutdown(dummy); } static int nmi_create_files(struct super_block *sb, struct dentry *root) @@ -457,7 +446,6 @@ static int nmi_create_files(struct super_block *sb, struct dentry *root) return 0; } -#ifdef CONFIG_SMP static int oprofile_cpu_notifier(struct notifier_block *b, unsigned long action, void *data) { @@ -465,10 +453,10 @@ static int oprofile_cpu_notifier(struct notifier_block *b, unsigned long action, switch (action) { case CPU_DOWN_FAILED: case CPU_ONLINE: - smp_call_function_single(cpu, nmi_cpu_start, NULL, 0); + smp_call_function_single(cpu, nmi_cpu_up, NULL, 0); break; case CPU_DOWN_PREPARE: - smp_call_function_single(cpu, nmi_cpu_stop, NULL, 1); + smp_call_function_single(cpu, nmi_cpu_down, NULL, 1); break; } return NOTIFY_DONE; @@ -477,7 +465,75 @@ static int oprofile_cpu_notifier(struct notifier_block *b, unsigned long action, static struct notifier_block oprofile_cpu_nb = { .notifier_call = oprofile_cpu_notifier }; -#endif + +static int nmi_setup(void) +{ + int err = 0; + int cpu; + + if (!allocate_msrs()) + return -ENOMEM; + + /* We need to serialize save and setup for HT because the subset + * of msrs are distinct for save and setup operations + */ + + /* Assume saved/restored counters are the same on all CPUs */ + err = model->fill_in_addresses(&per_cpu(cpu_msrs, 0)); + if (err) + goto fail; + + for_each_possible_cpu(cpu) { + if (!cpu) + continue; + + memcpy(per_cpu(cpu_msrs, cpu).counters, + per_cpu(cpu_msrs, 0).counters, + sizeof(struct op_msr) * model->num_counters); + + memcpy(per_cpu(cpu_msrs, cpu).controls, + per_cpu(cpu_msrs, 0).controls, + sizeof(struct op_msr) * model->num_controls); + + mux_clone(cpu); + } + + nmi_enabled = 0; + ctr_running = 0; + barrier(); + err = register_die_notifier(&profile_exceptions_nb); + if (err) + goto fail; + + get_online_cpus(); + register_cpu_notifier(&oprofile_cpu_nb); + on_each_cpu(nmi_cpu_setup, NULL, 1); + nmi_enabled = 1; + put_online_cpus(); + + return 0; +fail: + free_msrs(); + return err; +} + +static void nmi_shutdown(void) +{ + struct op_msrs *msrs; + + get_online_cpus(); + unregister_cpu_notifier(&oprofile_cpu_nb); + on_each_cpu(nmi_cpu_shutdown, NULL, 1); + nmi_enabled = 0; + ctr_running = 0; + put_online_cpus(); + barrier(); + unregister_die_notifier(&profile_exceptions_nb); + msrs = &get_cpu_var(cpu_msrs); + model->shutdown(msrs); + free_msrs(); + put_cpu_var(cpu_msrs); +} #ifdef CONFIG_PM @@ -578,6 +634,18 @@ static int __init ppro_init(char **cpu_type) if (force_arch_perfmon && cpu_has_arch_perfmon) return 0; + /* + * Documentation on identifying Intel processors by CPU family + * and model can be found in the Intel Software Developer's + * Manuals (SDM): + * + * http://www.intel.com/products/processor/manuals/ + * + * As of May 2010 the documentation for this was in the: + * "Intel 64 and IA-32 Architectures Software Developer's + * Manual Volume 3B: System Programming Guide", "Table B-1 + * CPUID Signature Values of DisplayFamily_DisplayModel". + */ switch (cpu_model) { case 0 ... 2: *cpu_type = "i386/ppro"; @@ -599,12 +667,12 @@ static int __init ppro_init(char **cpu_type) case 15: case 23: *cpu_type = "i386/core_2"; break; + case 0x1a: case 0x2e: - case 26: spec = &op_arch_perfmon_spec; *cpu_type = "i386/core_i7"; break; - case 28: + case 0x1c: *cpu_type = "i386/atom"; break; default: @@ -687,9 +755,6 @@ int __init op_nmi_init(struct oprofile_operations *ops) return -ENODEV; } -#ifdef CONFIG_SMP - register_cpu_notifier(&oprofile_cpu_nb); -#endif /* default values, can be overwritten by model */ ops->create_files = nmi_create_files; ops->setup = nmi_setup; @@ -716,12 +781,6 @@ int __init op_nmi_init(struct oprofile_operations *ops) void op_nmi_exit(void) { - if (using_nmi) { + if (using_nmi) exit_sysfs(); -#ifdef CONFIG_SMP - unregister_cpu_notifier(&oprofile_cpu_nb); -#endif - } - if (model->exit) - model->exit(); } diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index 090cbbec7db..b67a6b5aa8d 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -30,13 +30,10 @@ #include "op_counter.h" #define NUM_COUNTERS 4 -#define NUM_CONTROLS 4 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX #define NUM_VIRT_COUNTERS 32 -#define NUM_VIRT_CONTROLS 32 #else #define NUM_VIRT_COUNTERS NUM_COUNTERS -#define NUM_VIRT_CONTROLS NUM_CONTROLS #endif #define OP_EVENT_MASK 0x0FFF @@ -105,102 +102,6 @@ static u32 get_ibs_caps(void) return ibs_caps; } -#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX - -static void op_mux_switch_ctrl(struct op_x86_model_spec const *model, - struct op_msrs const * const msrs) -{ - u64 val; - int i; - - /* enable active counters */ - for (i = 0; i < NUM_COUNTERS; ++i) { - int virt = op_x86_phys_to_virt(i); - if (!reset_value[virt]) - continue; - rdmsrl(msrs->controls[i].addr, val); - val &= model->reserved; - val |= op_x86_get_ctrl(model, &counter_config[virt]); - wrmsrl(msrs->controls[i].addr, val); - } -} - -#endif - -/* functions for op_amd_spec */ - -static void op_amd_fill_in_addresses(struct op_msrs * const msrs) -{ - int i; - - for (i = 0; i < NUM_COUNTERS; i++) { - if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i)) - msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; - } - - for (i = 0; i < NUM_CONTROLS; i++) { - if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) - msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; - } -} - -static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, - struct op_msrs const * const msrs) -{ - u64 val; - int i; - - /* setup reset_value */ - for (i = 0; i < NUM_VIRT_COUNTERS; ++i) { - if (counter_config[i].enabled - && msrs->counters[op_x86_virt_to_phys(i)].addr) - reset_value[i] = counter_config[i].count; - else - reset_value[i] = 0; - } - - /* clear all counters */ - for (i = 0; i < NUM_CONTROLS; ++i) { - if (unlikely(!msrs->controls[i].addr)) { - if (counter_config[i].enabled && !smp_processor_id()) - /* - * counter is reserved, this is on all - * cpus, so report only for cpu #0 - */ - op_x86_warn_reserved(i); - continue; - } - rdmsrl(msrs->controls[i].addr, val); - if (val & ARCH_PERFMON_EVENTSEL_ENABLE) - op_x86_warn_in_use(i); - val &= model->reserved; - wrmsrl(msrs->controls[i].addr, val); - } - - /* avoid a false detection of ctr overflows in NMI handler */ - for (i = 0; i < NUM_COUNTERS; ++i) { - if (unlikely(!msrs->counters[i].addr)) - continue; - wrmsrl(msrs->counters[i].addr, -1LL); - } - - /* enable active counters */ - for (i = 0; i < NUM_COUNTERS; ++i) { - int virt = op_x86_phys_to_virt(i); - if (!reset_value[virt]) - continue; - - /* setup counter registers */ - wrmsrl(msrs->counters[i].addr, -(u64)reset_value[virt]); - - /* setup control registers */ - rdmsrl(msrs->controls[i].addr, val); - val &= model->reserved; - val |= op_x86_get_ctrl(model, &counter_config[virt]); - wrmsrl(msrs->controls[i].addr, val); - } -} - /* * 16-bit Linear Feedback Shift Register (LFSR) * @@ -365,6 +266,125 @@ static void op_amd_stop_ibs(void) wrmsrl(MSR_AMD64_IBSOPCTL, 0); } +#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX + +static void op_mux_switch_ctrl(struct op_x86_model_spec const *model, + struct op_msrs const * const msrs) +{ + u64 val; + int i; + + /* enable active counters */ + for (i = 0; i < NUM_COUNTERS; ++i) { + int virt = op_x86_phys_to_virt(i); + if (!reset_value[virt]) + continue; + rdmsrl(msrs->controls[i].addr, val); + val &= model->reserved; + val |= op_x86_get_ctrl(model, &counter_config[virt]); + wrmsrl(msrs->controls[i].addr, val); + } +} + +#endif + +/* functions for op_amd_spec */ + +static void op_amd_shutdown(struct op_msrs const * const msrs) +{ + int i; + + for (i = 0; i < NUM_COUNTERS; ++i) { + if (!msrs->counters[i].addr) + continue; + release_perfctr_nmi(MSR_K7_PERFCTR0 + i); + release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); + } +} + +static int op_amd_fill_in_addresses(struct op_msrs * const msrs) +{ + int i; + + for (i = 0; i < NUM_COUNTERS; i++) { + if (!reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i)) + goto fail; + if (!reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) { + release_perfctr_nmi(MSR_K7_PERFCTR0 + i); + goto fail; + } + /* both registers must be reserved */ + msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; + msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; + continue; + fail: + if (!counter_config[i].enabled) + continue; + op_x86_warn_reserved(i); + op_amd_shutdown(msrs); + return -EBUSY; + } + + return 0; +} + +static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, + struct op_msrs const * const msrs) +{ + u64 val; + int i; + + /* setup reset_value */ + for (i = 0; i < NUM_VIRT_COUNTERS; ++i) { + if (counter_config[i].enabled + && msrs->counters[op_x86_virt_to_phys(i)].addr) + reset_value[i] = counter_config[i].count; + else + reset_value[i] = 0; + } + + /* clear all counters */ + for (i = 0; i < NUM_COUNTERS; ++i) { + if (!msrs->controls[i].addr) + continue; + rdmsrl(msrs->controls[i].addr, val); + if (val & ARCH_PERFMON_EVENTSEL_ENABLE) + op_x86_warn_in_use(i); + val &= model->reserved; + wrmsrl(msrs->controls[i].addr, val); + /* + * avoid a false detection of ctr overflows in NMI + * handler + */ + wrmsrl(msrs->counters[i].addr, -1LL); + } + + /* enable active counters */ + for (i = 0; i < NUM_COUNTERS; ++i) { + int virt = op_x86_phys_to_virt(i); + if (!reset_value[virt]) + continue; + + /* setup counter registers */ + wrmsrl(msrs->counters[i].addr, -(u64)reset_value[virt]); + + /* setup control registers */ + rdmsrl(msrs->controls[i].addr, val); + val &= model->reserved; + val |= op_x86_get_ctrl(model, &counter_config[virt]); + wrmsrl(msrs->controls[i].addr, val); + } + + if (ibs_caps) + setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0); +} + +static void op_amd_cpu_shutdown(void) +{ + if (ibs_caps) + setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1); +} + static int op_amd_check_ctrs(struct pt_regs * const regs, struct op_msrs const * const msrs) { @@ -425,42 +445,16 @@ static void op_amd_stop(struct op_msrs const * const msrs) op_amd_stop_ibs(); } -static void op_amd_shutdown(struct op_msrs const * const msrs) -{ - int i; - - for (i = 0; i < NUM_COUNTERS; ++i) { - if (msrs->counters[i].addr) - release_perfctr_nmi(MSR_K7_PERFCTR0 + i); - } - for (i = 0; i < NUM_CONTROLS; ++i) { - if (msrs->controls[i].addr) - release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); - } -} - -static u8 ibs_eilvt_off; - -static inline void apic_init_ibs_nmi_per_cpu(void *arg) -{ - ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0); -} - -static inline void apic_clear_ibs_nmi_per_cpu(void *arg) -{ - setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1); -} - -static int init_ibs_nmi(void) +static int __init_ibs_nmi(void) { #define IBSCTL_LVTOFFSETVAL (1 << 8) #define IBSCTL 0x1cc struct pci_dev *cpu_cfg; int nodes; u32 value = 0; + u8 ibs_eilvt_off; - /* per CPU setup */ - on_each_cpu(apic_init_ibs_nmi_per_cpu, NULL, 1); + ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1); nodes = 0; cpu_cfg = NULL; @@ -490,22 +484,15 @@ static int init_ibs_nmi(void) return 0; } -/* uninitialize the APIC for the IBS interrupts if needed */ -static void clear_ibs_nmi(void) -{ - if (ibs_caps) - on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1); -} - /* initialize the APIC for the IBS interrupts if available */ -static void ibs_init(void) +static void init_ibs(void) { ibs_caps = get_ibs_caps(); if (!ibs_caps) return; - if (init_ibs_nmi()) { + if (__init_ibs_nmi()) { ibs_caps = 0; return; } @@ -514,14 +501,6 @@ static void ibs_init(void) (unsigned)ibs_caps); } -static void ibs_exit(void) -{ - if (!ibs_caps) - return; - - clear_ibs_nmi(); -} - static int (*create_arch_files)(struct super_block *sb, struct dentry *root); static int setup_ibs_files(struct super_block *sb, struct dentry *root) @@ -570,27 +549,22 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root) static int op_amd_init(struct oprofile_operations *ops) { - ibs_init(); + init_ibs(); create_arch_files = ops->create_files; ops->create_files = setup_ibs_files; return 0; } -static void op_amd_exit(void) -{ - ibs_exit(); -} - struct op_x86_model_spec op_amd_spec = { .num_counters = NUM_COUNTERS, - .num_controls = NUM_CONTROLS, + .num_controls = NUM_COUNTERS, .num_virt_counters = NUM_VIRT_COUNTERS, .reserved = MSR_AMD_EVENTSEL_RESERVED, .event_mask = OP_EVENT_MASK, .init = op_amd_init, - .exit = op_amd_exit, .fill_in_addresses = &op_amd_fill_in_addresses, .setup_ctrs = &op_amd_setup_ctrs, + .cpu_down = &op_amd_cpu_shutdown, .check_ctrs = &op_amd_check_ctrs, .start = &op_amd_start, .stop = &op_amd_stop, diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c index e6a160a4684..182558dd551 100644 --- a/arch/x86/oprofile/op_model_p4.c +++ b/arch/x86/oprofile/op_model_p4.c @@ -385,8 +385,26 @@ static unsigned int get_stagger(void) static unsigned long reset_value[NUM_COUNTERS_NON_HT]; +static void p4_shutdown(struct op_msrs const * const msrs) +{ + int i; -static void p4_fill_in_addresses(struct op_msrs * const msrs) + for (i = 0; i < num_counters; ++i) { + if (msrs->counters[i].addr) + release_perfctr_nmi(msrs->counters[i].addr); + } + /* + * some of the control registers are specially reserved in + * conjunction with the counter registers (hence the starting offset). + * This saves a few bits. + */ + for (i = num_counters; i < num_controls; ++i) { + if (msrs->controls[i].addr) + release_evntsel_nmi(msrs->controls[i].addr); + } +} + +static int p4_fill_in_addresses(struct op_msrs * const msrs) { unsigned int i; unsigned int addr, cccraddr, stag; @@ -468,6 +486,18 @@ static void p4_fill_in_addresses(struct op_msrs * const msrs) msrs->controls[i++].addr = MSR_P4_CRU_ESCR5; } } + + for (i = 0; i < num_counters; ++i) { + if (!counter_config[i].enabled) + continue; + if (msrs->controls[i].addr) + continue; + op_x86_warn_reserved(i); + p4_shutdown(msrs); + return -EBUSY; + } + + return 0; } @@ -668,26 +698,6 @@ static void p4_stop(struct op_msrs const * const msrs) } } -static void p4_shutdown(struct op_msrs const * const msrs) -{ - int i; - - for (i = 0; i < num_counters; ++i) { - if (msrs->counters[i].addr) - release_perfctr_nmi(msrs->counters[i].addr); - } - /* - * some of the control registers are specially reserved in - * conjunction with the counter registers (hence the starting offset). - * This saves a few bits. - */ - for (i = num_counters; i < num_controls; ++i) { - if (msrs->controls[i].addr) - release_evntsel_nmi(msrs->controls[i].addr); - } -} - - #ifdef CONFIG_SMP struct op_x86_model_spec op_p4_ht2_spec = { .num_counters = NUM_COUNTERS_HT2, diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index 2bf90fafa7b..d769cda5408 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -30,19 +30,46 @@ static int counter_width = 32; static u64 *reset_value; -static void ppro_fill_in_addresses(struct op_msrs * const msrs) +static void ppro_shutdown(struct op_msrs const * const msrs) { int i; - for (i = 0; i < num_counters; i++) { - if (reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i)) - msrs->counters[i].addr = MSR_P6_PERFCTR0 + i; + for (i = 0; i < num_counters; ++i) { + if (!msrs->counters[i].addr) + continue; + release_perfctr_nmi(MSR_P6_PERFCTR0 + i); + release_evntsel_nmi(MSR_P6_EVNTSEL0 + i); + } + if (reset_value) { + kfree(reset_value); + reset_value = NULL; } +} + +static int ppro_fill_in_addresses(struct op_msrs * const msrs) +{ + int i; for (i = 0; i < num_counters; i++) { - if (reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i)) - msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i; + if (!reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i)) + goto fail; + if (!reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i)) { + release_perfctr_nmi(MSR_P6_PERFCTR0 + i); + goto fail; + } + /* both registers must be reserved */ + msrs->counters[i].addr = MSR_P6_PERFCTR0 + i; + msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i; + continue; + fail: + if (!counter_config[i].enabled) + continue; + op_x86_warn_reserved(i); + ppro_shutdown(msrs); + return -EBUSY; } + + return 0; } @@ -78,26 +105,17 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model, /* clear all counters */ for (i = 0; i < num_counters; ++i) { - if (unlikely(!msrs->controls[i].addr)) { - if (counter_config[i].enabled && !smp_processor_id()) - /* - * counter is reserved, this is on all - * cpus, so report only for cpu #0 - */ - op_x86_warn_reserved(i); + if (!msrs->controls[i].addr) continue; - } rdmsrl(msrs->controls[i].addr, val); if (val & ARCH_PERFMON_EVENTSEL_ENABLE) op_x86_warn_in_use(i); val &= model->reserved; wrmsrl(msrs->controls[i].addr, val); - } - - /* avoid a false detection of ctr overflows in NMI handler */ - for (i = 0; i < num_counters; ++i) { - if (unlikely(!msrs->counters[i].addr)) - continue; + /* + * avoid a false detection of ctr overflows in NMI * + * handler + */ wrmsrl(msrs->counters[i].addr, -1LL); } @@ -189,25 +207,6 @@ static void ppro_stop(struct op_msrs const * const msrs) } } -static void ppro_shutdown(struct op_msrs const * const msrs) -{ - int i; - - for (i = 0; i < num_counters; ++i) { - if (msrs->counters[i].addr) - release_perfctr_nmi(MSR_P6_PERFCTR0 + i); - } - for (i = 0; i < num_counters; ++i) { - if (msrs->controls[i].addr) - release_evntsel_nmi(MSR_P6_EVNTSEL0 + i); - } - if (reset_value) { - kfree(reset_value); - reset_value = NULL; - } -} - - struct op_x86_model_spec op_ppro_spec = { .num_counters = 2, .num_controls = 2, @@ -239,11 +238,11 @@ static void arch_perfmon_setup_counters(void) if (eax.split.version_id == 0 && current_cpu_data.x86 == 6 && current_cpu_data.x86_model == 15) { eax.split.version_id = 2; - eax.split.num_events = 2; + eax.split.num_counters = 2; eax.split.bit_width = 40; } - num_counters = eax.split.num_events; + num_counters = eax.split.num_counters; op_arch_perfmon_spec.num_counters = num_counters; op_arch_perfmon_spec.num_controls = num_counters; diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h index ff82a755edd..89017fa1fd6 100644 --- a/arch/x86/oprofile/op_x86_model.h +++ b/arch/x86/oprofile/op_x86_model.h @@ -40,10 +40,10 @@ struct op_x86_model_spec { u64 reserved; u16 event_mask; int (*init)(struct oprofile_operations *ops); - void (*exit)(void); - void (*fill_in_addresses)(struct op_msrs * const msrs); + int (*fill_in_addresses)(struct op_msrs * const msrs); void (*setup_ctrs)(struct op_x86_model_spec const *model, struct op_msrs const * const msrs); + void (*cpu_down)(void); int (*check_ctrs)(struct pt_regs * const regs, struct op_msrs const * const msrs); void (*start)(struct op_msrs const * const msrs); diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index b110d97fb92..a0207a7fdf3 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -18,6 +18,8 @@ obj-$(CONFIG_X86_MRST) += mrst.o obj-y += common.o early.o obj-y += amd_bus.o bus_numa.o +obj-$(CONFIG_PCI_CNB20LE_QUIRK) += broadcom_bus.o + ifeq ($(CONFIG_PCI_DEBUG),y) EXTRA_CFLAGS += -DDEBUG endif diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 31930fd30ea..15466c096ba 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -34,6 +34,15 @@ static const struct dmi_system_id pci_use_crs_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "x3800"), }, }, + /* https://bugzilla.kernel.org/show_bug.cgi?id=16007 */ + /* 2006 AMD HT/VIA system with two host bridges */ + { + .callback = set_use_crs, + .ident = "ASRock ALiveSATA2-GLAN", + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "ALiveSATA2-GLAN"), + }, + }, {} }; @@ -207,10 +216,9 @@ get_current_resources(struct acpi_device *device, int busnum, if (!info.res) goto res_alloc_fail; - info.name = kmalloc(16, GFP_KERNEL); + info.name = kasprintf(GFP_KERNEL, "PCI Bus %04x:%02x", domain, busnum); if (!info.name) goto name_alloc_fail; - sprintf(info.name, "PCI Bus %04x:%02x", domain, busnum); info.res_num = 0; acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource, @@ -224,8 +232,11 @@ res_alloc_fail: return; } -struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int domain, int busnum) +struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root) { + struct acpi_device *device = root->device; + int domain = root->segment; + int busnum = root->secondary.start; struct pci_bus *bus; struct pci_sysdata *sd; int node; diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c new file mode 100644 index 00000000000..0846a5bbbfb --- /dev/null +++ b/arch/x86/pci/broadcom_bus.c @@ -0,0 +1,101 @@ +/* + * Read address ranges from a Broadcom CNB20LE Host Bridge + * + * Copyright (c) 2010 Ira W. Snyder <iws@ovro.caltech.edu> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/delay.h> +#include <linux/dmi.h> +#include <linux/pci.h> +#include <linux/init.h> +#include <asm/pci_x86.h> + +#include "bus_numa.h" + +static void __devinit cnb20le_res(struct pci_dev *dev) +{ + struct pci_root_info *info; + struct resource res; + u16 word1, word2; + u8 fbus, lbus; + int i; + + /* + * The x86_pci_root_bus_res_quirks() function already refuses to use + * this information if ACPI _CRS was used. Therefore, we don't bother + * checking if ACPI is enabled, and just generate the information + * for both the ACPI _CRS and no ACPI cases. + */ + + info = &pci_root_info[pci_root_num]; + pci_root_num++; + + /* read the PCI bus numbers */ + pci_read_config_byte(dev, 0x44, &fbus); + pci_read_config_byte(dev, 0x45, &lbus); + info->bus_min = fbus; + info->bus_max = lbus; + + /* + * Add the legacy IDE ports on bus 0 + * + * These do not exist anywhere in the bridge registers, AFAICT. I do + * not have the datasheet, so this is the best I can do. + */ + if (fbus == 0) { + update_res(info, 0x01f0, 0x01f7, IORESOURCE_IO, 0); + update_res(info, 0x03f6, 0x03f6, IORESOURCE_IO, 0); + update_res(info, 0x0170, 0x0177, IORESOURCE_IO, 0); + update_res(info, 0x0376, 0x0376, IORESOURCE_IO, 0); + update_res(info, 0xffa0, 0xffaf, IORESOURCE_IO, 0); + } + + /* read the non-prefetchable memory window */ + pci_read_config_word(dev, 0xc0, &word1); + pci_read_config_word(dev, 0xc2, &word2); + if (word1 != word2) { + res.start = (word1 << 16) | 0x0000; + res.end = (word2 << 16) | 0xffff; + res.flags = IORESOURCE_MEM; + update_res(info, res.start, res.end, res.flags, 0); + } + + /* read the prefetchable memory window */ + pci_read_config_word(dev, 0xc4, &word1); + pci_read_config_word(dev, 0xc6, &word2); + if (word1 != word2) { + res.start = (word1 << 16) | 0x0000; + res.end = (word2 << 16) | 0xffff; + res.flags = IORESOURCE_MEM | IORESOURCE_PREFETCH; + update_res(info, res.start, res.end, res.flags, 0); + } + + /* read the IO port window */ + pci_read_config_word(dev, 0xd0, &word1); + pci_read_config_word(dev, 0xd2, &word2); + if (word1 != word2) { + res.start = word1; + res.end = word2; + res.flags = IORESOURCE_IO; + update_res(info, res.start, res.end, res.flags, 0); + } + + /* print information about this host bridge */ + res.start = fbus; + res.end = lbus; + res.flags = IORESOURCE_BUS; + dev_info(&dev->dev, "CNB20LE PCI Host Bridge (domain %04x %pR)\n", + pci_domain_nr(dev->bus), &res); + + for (i = 0; i < info->res_num; i++) + dev_info(&dev->dev, "host bridge window %pR\n", &info->res[i]); +} + +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_LE, + cnb20le_res); + diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index cf2e93869c4..a0772af64ef 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -76,7 +76,7 @@ struct pci_ops pci_root_ops = { * This interrupt-safe spinlock protects all accesses to PCI * configuration space. */ -DEFINE_SPINLOCK(pci_config_lock); +DEFINE_RAW_SPINLOCK(pci_config_lock); static int __devinit can_skip_ioresource_align(const struct dmi_system_id *d) { @@ -125,6 +125,23 @@ void __init dmi_check_skip_isa_align(void) static void __devinit pcibios_fixup_device_resources(struct pci_dev *dev) { struct resource *rom_r = &dev->resource[PCI_ROM_RESOURCE]; + struct resource *bar_r; + int bar; + + if (pci_probe & PCI_NOASSIGN_BARS) { + /* + * If the BIOS did not assign the BAR, zero out the + * resource so the kernel doesn't attmept to assign + * it later on in pci_assign_unassigned_resources + */ + for (bar = 0; bar <= PCI_STD_RESOURCE_END; bar++) { + bar_r = &dev->resource[bar]; + if (bar_r->start == 0 && bar_r->end != 0) { + bar_r->flags = 0; + bar_r->end = 0; + } + } + } if (pci_probe & PCI_NOASSIGN_ROMS) { if (rom_r->parent) @@ -509,6 +526,9 @@ char * __devinit pcibios_setup(char *str) } else if (!strcmp(str, "norom")) { pci_probe |= PCI_NOASSIGN_ROMS; return NULL; + } else if (!strcmp(str, "nobar")) { + pci_probe |= PCI_NOASSIGN_BARS; + return NULL; } else if (!strcmp(str, "assign-busses")) { pci_probe |= PCI_ASSIGN_ALL_BUSSES; return NULL; diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c index 347d882b3bb..bd33620b007 100644 --- a/arch/x86/pci/direct.c +++ b/arch/x86/pci/direct.c @@ -27,7 +27,7 @@ static int pci_conf1_read(unsigned int seg, unsigned int bus, return -EINVAL; } - spin_lock_irqsave(&pci_config_lock, flags); + raw_spin_lock_irqsave(&pci_config_lock, flags); outl(PCI_CONF1_ADDRESS(bus, devfn, reg), 0xCF8); @@ -43,7 +43,7 @@ static int pci_conf1_read(unsigned int seg, unsigned int bus, break; } - spin_unlock_irqrestore(&pci_config_lock, flags); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return 0; } @@ -56,7 +56,7 @@ static int pci_conf1_write(unsigned int seg, unsigned int bus, if ((bus > 255) || (devfn > 255) || (reg > 4095)) return -EINVAL; - spin_lock_irqsave(&pci_config_lock, flags); + raw_spin_lock_irqsave(&pci_config_lock, flags); outl(PCI_CONF1_ADDRESS(bus, devfn, reg), 0xCF8); @@ -72,7 +72,7 @@ static int pci_conf1_write(unsigned int seg, unsigned int bus, break; } - spin_unlock_irqrestore(&pci_config_lock, flags); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return 0; } @@ -108,7 +108,7 @@ static int pci_conf2_read(unsigned int seg, unsigned int bus, if (dev & 0x10) return PCIBIOS_DEVICE_NOT_FOUND; - spin_lock_irqsave(&pci_config_lock, flags); + raw_spin_lock_irqsave(&pci_config_lock, flags); outb((u8)(0xF0 | (fn << 1)), 0xCF8); outb((u8)bus, 0xCFA); @@ -127,7 +127,7 @@ static int pci_conf2_read(unsigned int seg, unsigned int bus, outb(0, 0xCF8); - spin_unlock_irqrestore(&pci_config_lock, flags); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return 0; } @@ -147,7 +147,7 @@ static int pci_conf2_write(unsigned int seg, unsigned int bus, if (dev & 0x10) return PCIBIOS_DEVICE_NOT_FOUND; - spin_lock_irqsave(&pci_config_lock, flags); + raw_spin_lock_irqsave(&pci_config_lock, flags); outb((u8)(0xF0 | (fn << 1)), 0xCF8); outb((u8)bus, 0xCFA); @@ -166,7 +166,7 @@ static int pci_conf2_write(unsigned int seg, unsigned int bus, outb(0, 0xCF8); - spin_unlock_irqrestore(&pci_config_lock, flags); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return 0; } diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 97da2ba9344..55253095be8 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -96,6 +96,7 @@ EXPORT_SYMBOL(pcibios_align_resource); * the fact the PCI specs explicitly allow address decoders to be * shared between expansion ROMs and other resource regions, it's * at least dangerous) + * - bad resource sizes or overlaps with other regions * * Our solution: * (1) Allocate resources for all buses behind PCI-to-PCI bridges. @@ -136,6 +137,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list) * child resource allocations in this * range. */ + r->start = r->end = 0; r->flags = 0; } } @@ -182,6 +184,7 @@ static void __init pcibios_allocate_resources(int pass) idx, r, disabled, pass); if (pci_claim_resource(dev, idx) < 0) { /* We'll assign a new address later */ + dev->fw_addr[idx] = r->start; r->end -= r->start; r->start = 0; } diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 5d362b5ba06..f547ee05f71 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -589,8 +589,6 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route case PCI_DEVICE_ID_INTEL_ICH10_1: case PCI_DEVICE_ID_INTEL_ICH10_2: case PCI_DEVICE_ID_INTEL_ICH10_3: - case PCI_DEVICE_ID_INTEL_CPT_LPC1: - case PCI_DEVICE_ID_INTEL_CPT_LPC2: r->name = "PIIX/ICH"; r->get = pirq_piix_get; r->set = pirq_piix_set; @@ -605,6 +603,13 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route return 1; } + if ((device >= PCI_DEVICE_ID_INTEL_CPT_LPC_MIN) && + (device <= PCI_DEVICE_ID_INTEL_CPT_LPC_MAX)) { + r->name = "PIIX/ICH"; + r->get = pirq_piix_get; + r->set = pirq_piix_set; + return 1; + } return 0; } @@ -984,7 +989,7 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", msg, 'A' + pin - 1, irq); /* Update IRQ for all devices with the same pirq value */ - while ((dev2 = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev2)) != NULL) { + for_each_pci_dev(dev2) { pci_read_config_byte(dev2, PCI_INTERRUPT_PIN, &pin); if (!pin) continue; @@ -1023,7 +1028,7 @@ void __init pcibios_fixup_irqs(void) u8 pin; DBG(KERN_DEBUG "PCI: IRQ fixup\n"); - while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { + for_each_pci_dev(dev) { /* * If the BIOS has set an out of range IRQ number, just * ignore it. Also keep track of which IRQ's are @@ -1047,7 +1052,7 @@ void __init pcibios_fixup_irqs(void) return; dev = NULL; - while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { + for_each_pci_dev(dev) { pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); if (!pin) continue; diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c index 0db5eaf5456..c89266be604 100644 --- a/arch/x86/pci/legacy.c +++ b/arch/x86/pci/legacy.c @@ -11,28 +11,14 @@ */ static void __devinit pcibios_fixup_peer_bridges(void) { - int n, devfn; - long node; + int n; if (pcibios_last_bus <= 0 || pcibios_last_bus > 0xff) return; DBG("PCI: Peer bridge fixup\n"); - for (n=0; n <= pcibios_last_bus; n++) { - u32 l; - if (pci_find_bus(0, n)) - continue; - node = get_mp_bus_to_node(n); - for (devfn = 0; devfn < 256; devfn += 8) { - if (!raw_pci_read(0, n, devfn, PCI_VENDOR_ID, 2, &l) && - l != 0x0000 && l != 0xffff) { - DBG("Found device at %02x:%02x [%04x]\n", n, devfn, l); - printk(KERN_INFO "PCI: Discovered peer bus %02x\n", n); - pci_scan_bus_on_node(n, &pci_root_ops, node); - break; - } - } - } + for (n=0; n <= pcibios_last_bus; n++) + pcibios_scan_specific_bus(n); } int __init pci_legacy_init(void) @@ -50,6 +36,28 @@ int __init pci_legacy_init(void) return 0; } +void __devinit pcibios_scan_specific_bus(int busn) +{ + int devfn; + long node; + u32 l; + + if (pci_find_bus(0, busn)) + return; + + node = get_mp_bus_to_node(busn); + for (devfn = 0; devfn < 256; devfn += 8) { + if (!raw_pci_read(0, busn, devfn, PCI_VENDOR_ID, 2, &l) && + l != 0x0000 && l != 0xffff) { + DBG("Found device at %02x:%02x [%04x]\n", busn, devfn, l); + printk(KERN_INFO "PCI: Discovered peer bus %02x\n", busn); + pci_scan_bus_on_node(busn, &pci_root_ops, node); + return; + } + } +} +EXPORT_SYMBOL_GPL(pcibios_scan_specific_bus); + int __init pci_subsys_init(void) { /* diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 39b9ebe8f88..a918553ebc7 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -483,16 +483,17 @@ static void __init pci_mmcfg_reject_broken(int early) list_for_each_entry(cfg, &pci_mmcfg_list, list) { int valid = 0; - if (!early && !acpi_disabled) + if (!early && !acpi_disabled) { valid = is_mmconf_reserved(is_acpi_reserved, cfg, 0); - if (valid) - continue; - - if (!early) - printk(KERN_ERR FW_BUG PREFIX - "MMCONFIG at %pR not reserved in " - "ACPI motherboard resources\n", &cfg->res); + if (valid) + continue; + else + printk(KERN_ERR FW_BUG PREFIX + "MMCONFIG at %pR not reserved in " + "ACPI motherboard resources\n", + &cfg->res); + } /* Don't try to do this check unless configuration type 1 is available. how about type 2 ?*/ diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c index 90d5fd476ed..a3d9c54792a 100644 --- a/arch/x86/pci/mmconfig_32.c +++ b/arch/x86/pci/mmconfig_32.c @@ -64,7 +64,7 @@ err: *value = -1; if (!base) goto err; - spin_lock_irqsave(&pci_config_lock, flags); + raw_spin_lock_irqsave(&pci_config_lock, flags); pci_exp_set_dev_base(base, bus, devfn); @@ -79,7 +79,7 @@ err: *value = -1; *value = mmio_config_readl(mmcfg_virt_addr + reg); break; } - spin_unlock_irqrestore(&pci_config_lock, flags); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return 0; } @@ -97,7 +97,7 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus, if (!base) return -EINVAL; - spin_lock_irqsave(&pci_config_lock, flags); + raw_spin_lock_irqsave(&pci_config_lock, flags); pci_exp_set_dev_base(base, bus, devfn); @@ -112,7 +112,7 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus, mmio_config_writel(mmcfg_virt_addr + reg, value); break; } - spin_unlock_irqrestore(&pci_config_lock, flags); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return 0; } diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c index 1cdc02cf8fa..cb29191cee5 100644 --- a/arch/x86/pci/mrst.c +++ b/arch/x86/pci/mrst.c @@ -66,8 +66,9 @@ static int fixed_bar_cap(struct pci_bus *bus, unsigned int devfn) devfn, pos, 4, &pcie_cap)) return 0; - if (pcie_cap == 0xffffffff) - return 0; + if (PCI_EXT_CAP_ID(pcie_cap) == 0x0000 || + PCI_EXT_CAP_ID(pcie_cap) == 0xffff) + break; if (PCI_EXT_CAP_ID(pcie_cap) == PCI_EXT_CAP_ID_VNDR) { raw_pci_ext_ops->read(pci_domain_nr(bus), bus->number, @@ -76,7 +77,7 @@ static int fixed_bar_cap(struct pci_bus *bus, unsigned int devfn) return pos; } - pos = pcie_cap >> 20; + pos = PCI_EXT_CAP_NEXT(pcie_cap); } return 0; @@ -109,7 +110,7 @@ static int pci_device_update_fixed(struct pci_bus *bus, unsigned int devfn, decode++; decode = ~(decode - 1); } else { - decode = ~0; + decode = 0; } /* diff --git a/arch/x86/pci/numaq_32.c b/arch/x86/pci/numaq_32.c index 8223738ad80..5c9e2458df4 100644 --- a/arch/x86/pci/numaq_32.c +++ b/arch/x86/pci/numaq_32.c @@ -37,7 +37,7 @@ static int pci_conf1_mq_read(unsigned int seg, unsigned int bus, if (!value || (bus >= MAX_MP_BUSSES) || (devfn > 255) || (reg > 255)) return -EINVAL; - spin_lock_irqsave(&pci_config_lock, flags); + raw_spin_lock_irqsave(&pci_config_lock, flags); write_cf8(bus, devfn, reg); @@ -62,7 +62,7 @@ static int pci_conf1_mq_read(unsigned int seg, unsigned int bus, break; } - spin_unlock_irqrestore(&pci_config_lock, flags); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return 0; } @@ -76,7 +76,7 @@ static int pci_conf1_mq_write(unsigned int seg, unsigned int bus, if ((bus >= MAX_MP_BUSSES) || (devfn > 255) || (reg > 255)) return -EINVAL; - spin_lock_irqsave(&pci_config_lock, flags); + raw_spin_lock_irqsave(&pci_config_lock, flags); write_cf8(bus, devfn, reg); @@ -101,7 +101,7 @@ static int pci_conf1_mq_write(unsigned int seg, unsigned int bus, break; } - spin_unlock_irqrestore(&pci_config_lock, flags); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return 0; } diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 59a225c17b8..2492d165096 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -162,7 +162,7 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, if (!value || (bus > 255) || (devfn > 255) || (reg > 255)) return -EINVAL; - spin_lock_irqsave(&pci_config_lock, flags); + raw_spin_lock_irqsave(&pci_config_lock, flags); switch (len) { case 1: @@ -213,7 +213,7 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, break; } - spin_unlock_irqrestore(&pci_config_lock, flags); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return (int)((result & 0xff00) >> 8); } @@ -228,7 +228,7 @@ static int pci_bios_write(unsigned int seg, unsigned int bus, if ((bus > 255) || (devfn > 255) || (reg > 255)) return -EINVAL; - spin_lock_irqsave(&pci_config_lock, flags); + raw_spin_lock_irqsave(&pci_config_lock, flags); switch (len) { case 1: @@ -269,7 +269,7 @@ static int pci_bios_write(unsigned int seg, unsigned int bus, break; } - spin_unlock_irqrestore(&pci_config_lock, flags); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return (int)((result & 0xff00) >> 8); } diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 0a979f3e5b8..e7e8c5f5495 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -4,7 +4,7 @@ * Distribute under GPLv2 * * Copyright (c) 2007 Rafael J. Wysocki <rjw@sisk.pl> - * Copyright (c) 2002 Pavel Machek <pavel@suse.cz> + * Copyright (c) 2002 Pavel Machek <pavel@ucw.cz> * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org> */ @@ -105,6 +105,8 @@ static void __save_processor_state(struct saved_context *ctxt) ctxt->cr4 = read_cr4(); ctxt->cr8 = read_cr8(); #endif + ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE, + &ctxt->misc_enable); } /* Needed by apm.c */ @@ -152,6 +154,8 @@ static void fix_processor_context(void) */ static void __restore_processor_state(struct saved_context *ctxt) { + if (ctxt->misc_enable_saved) + wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable); /* * control registers */ diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index d24f983ba1e..460f314d13e 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -4,7 +4,7 @@ * Distribute under GPLv2 * * Copyright (c) 2007 Rafael J. Wysocki <rjw@sisk.pl> - * Copyright (c) 2002 Pavel Machek <pavel@suse.cz> + * Copyright (c) 2002 Pavel Machek <pavel@ucw.cz> * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org> */ diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 6b4ffedb93c..4a2afa1bac5 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -120,7 +120,8 @@ $(obj)/vdso32-syms.lds: $(vdso32.so-y:%=$(obj)/vdso32-%-syms.lds) FORCE quiet_cmd_vdso = VDSO $@ cmd_vdso = $(CC) -nostdlib -o $@ \ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ - -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) + -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ + sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) GCOV_PROFILE := n diff --git a/arch/x86/vdso/checkundef.sh b/arch/x86/vdso/checkundef.sh new file mode 100755 index 00000000000..7ee90a9b549 --- /dev/null +++ b/arch/x86/vdso/checkundef.sh @@ -0,0 +1,10 @@ +#!/bin/sh +nm="$1" +file="$2" +$nm "$file" | grep '^ *U' > /dev/null 2>&1 +if [ $? -eq 1 ]; then + exit 0 +else + echo "$file: undefined symbols found" >&2 + exit 1 +fi diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 02b442e9200..36df991985b 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -374,7 +374,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) #ifdef CONFIG_X86_64 -__initcall(sysenter_setup); +subsys_initcall(sysenter_setup); #ifdef CONFIG_SYSCTL /* Register vsyscall32 into the ABI table */ diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index ac74869b814..4b5d26f108b 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -67,6 +67,7 @@ static int __init init_vdso_vars(void) *(typeof(__ ## x) **) var_ref(VDSO64_SYMBOL(vbase, x), #x) = &__ ## x; #include "vextern.h" #undef VEXTERN + vunmap(vbase); return 0; oom: @@ -74,7 +75,7 @@ static int __init init_vdso_vars(void) vdso_enabled = 0; return -ENOMEM; } -__initcall(init_vdso_vars); +subsys_initcall(init_vdso_vars); struct linux_binprm; diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index b83e119fbeb..68128a1b401 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -13,6 +13,11 @@ config XEN kernel to boot in a paravirtualized environment under the Xen hypervisor. +config XEN_PVHVM + def_bool y + depends on XEN + depends on X86_LOCAL_APIC + config XEN_MAX_DOMAIN_MEMORY int "Maximum allowed size of a domain in gigabytes" default 8 if X86_32 diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 32af238055c..77938515891 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -12,7 +12,7 @@ CFLAGS_mmu.o := $(nostackp) obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ time.o xen-asm.o xen-asm_$(BITS).o \ - grant-table.o suspend.o + grant-table.o suspend.o platform-pci-unplug.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 3254e8bc4cd..7d46c844141 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -11,6 +11,7 @@ * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007 */ +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/smp.h> @@ -35,8 +36,10 @@ #include <xen/interface/version.h> #include <xen/interface/physdev.h> #include <xen/interface/vcpu.h> +#include <xen/interface/memory.h> #include <xen/features.h> #include <xen/page.h> +#include <xen/hvm.h> #include <xen/hvc-console.h> #include <asm/paravirt.h> @@ -55,7 +58,9 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/reboot.h> +#include <asm/setup.h> #include <asm/stackprotector.h> +#include <asm/hypervisor.h> #include "xen-ops.h" #include "mmu.h" @@ -76,6 +81,10 @@ struct shared_info xen_dummy_shared_info; void *xen_initial_gdt; +RESERVE_BRK(shared_info_page_brk, PAGE_SIZE); +__read_mostly int xen_have_vector_callback; +EXPORT_SYMBOL_GPL(xen_have_vector_callback); + /* * Point at some empty memory to start with. We map the real shared_info * page as soon as fixmap is up and running. @@ -97,6 +106,14 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; */ static int have_vcpu_info_placement = 1; +static void clamp_max_cpus(void) +{ +#ifdef CONFIG_SMP + if (setup_max_cpus > MAX_VIRT_CPUS) + setup_max_cpus = MAX_VIRT_CPUS; +#endif +} + static void xen_vcpu_setup(int cpu) { struct vcpu_register_vcpu_info info; @@ -104,13 +121,17 @@ static void xen_vcpu_setup(int cpu) struct vcpu_info *vcpup; BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); - per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; - if (!have_vcpu_info_placement) - return; /* already tested, not available */ + if (cpu < MAX_VIRT_CPUS) + per_cpu(xen_vcpu,cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; - vcpup = &per_cpu(xen_vcpu_info, cpu); + if (!have_vcpu_info_placement) { + if (cpu >= MAX_VIRT_CPUS) + clamp_max_cpus(); + return; + } + vcpup = &per_cpu(xen_vcpu_info, cpu); info.mfn = arbitrary_virt_to_mfn(vcpup); info.offset = offset_in_page(vcpup); @@ -125,6 +146,7 @@ static void xen_vcpu_setup(int cpu) if (err) { printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err); have_vcpu_info_placement = 0; + clamp_max_cpus(); } else { /* This cpu is using the registered vcpu info, even if later ones fail to. */ @@ -731,7 +753,6 @@ static void set_xen_basic_apic_ops(void) #endif - static void xen_clts(void) { struct multicall_space mcs; @@ -926,10 +947,6 @@ static const struct pv_init_ops xen_init_ops __initdata = { .patch = xen_patch, }; -static const struct pv_time_ops xen_time_ops __initdata = { - .sched_clock = xen_sched_clock, -}; - static const struct pv_cpu_ops xen_cpu_ops __initdata = { .cpuid = xen_cpuid, @@ -1028,6 +1045,23 @@ static void xen_crash_shutdown(struct pt_regs *regs) xen_reboot(SHUTDOWN_crash); } +static int +xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr) +{ + xen_reboot(SHUTDOWN_crash); + return NOTIFY_DONE; +} + +static struct notifier_block xen_panic_block = { + .notifier_call= xen_panic_event, +}; + +int xen_panic_handler_init(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, &xen_panic_block); + return 0; +} + static const struct machine_ops __initdata xen_machine_ops = { .restart = xen_restart, .halt = xen_machine_halt, @@ -1067,7 +1101,6 @@ asmlinkage void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; pv_init_ops = xen_init_ops; - pv_time_ops = xen_time_ops; pv_cpu_ops = xen_cpu_ops; pv_apic_ops = xen_apic_ops; @@ -1075,13 +1108,7 @@ asmlinkage void __init xen_start_kernel(void) x86_init.oem.arch_setup = xen_arch_setup; x86_init.oem.banner = xen_banner; - x86_init.timers.timer_init = xen_time_init; - x86_init.timers.setup_percpu_clockev = x86_init_noop; - x86_cpuinit.setup_percpu_clockev = x86_init_noop; - - x86_platform.calibrate_tsc = xen_tsc_khz; - x86_platform.get_wallclock = xen_get_wallclock; - x86_platform.set_wallclock = xen_set_wallclock; + xen_init_time_ops(); /* * Set up some pagetable state before starting to set any ptes. @@ -1210,3 +1237,139 @@ asmlinkage void __init xen_start_kernel(void) x86_64_start_reservations((char *)__pa_symbol(&boot_params)); #endif } + +static uint32_t xen_cpuid_base(void) +{ + uint32_t base, eax, ebx, ecx, edx; + char signature[13]; + + for (base = 0x40000000; base < 0x40010000; base += 0x100) { + cpuid(base, &eax, &ebx, &ecx, &edx); + *(uint32_t *)(signature + 0) = ebx; + *(uint32_t *)(signature + 4) = ecx; + *(uint32_t *)(signature + 8) = edx; + signature[12] = 0; + + if (!strcmp("XenVMMXenVMM", signature) && ((eax - base) >= 2)) + return base; + } + + return 0; +} + +static int init_hvm_pv_info(int *major, int *minor) +{ + uint32_t eax, ebx, ecx, edx, pages, msr, base; + u64 pfn; + + base = xen_cpuid_base(); + cpuid(base + 1, &eax, &ebx, &ecx, &edx); + + *major = eax >> 16; + *minor = eax & 0xffff; + printk(KERN_INFO "Xen version %d.%d.\n", *major, *minor); + + cpuid(base + 2, &pages, &msr, &ecx, &edx); + + pfn = __pa(hypercall_page); + wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + + xen_setup_features(); + + pv_info = xen_info; + pv_info.kernel_rpl = 0; + + xen_domain_type = XEN_HVM_DOMAIN; + + return 0; +} + +void xen_hvm_init_shared_info(void) +{ + int cpu; + struct xen_add_to_physmap xatp; + static struct shared_info *shared_info_page = 0; + + if (!shared_info_page) + shared_info_page = (struct shared_info *) + extend_brk(PAGE_SIZE, PAGE_SIZE); + xatp.domid = DOMID_SELF; + xatp.idx = 0; + xatp.space = XENMAPSPACE_shared_info; + xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT; + if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) + BUG(); + + HYPERVISOR_shared_info = (struct shared_info *)shared_info_page; + + /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info + * page, we use it in the event channel upcall and in some pvclock + * related functions. We don't need the vcpu_info placement + * optimizations because we don't use any pv_mmu or pv_irq op on + * HVM. + * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is + * online but xen_hvm_init_shared_info is run at resume time too and + * in that case multiple vcpus might be online. */ + for_each_online_cpu(cpu) { + per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; + } +} + +#ifdef CONFIG_XEN_PVHVM +static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + switch (action) { + case CPU_UP_PREPARE: + per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block __cpuinitdata xen_hvm_cpu_notifier = { + .notifier_call = xen_hvm_cpu_notify, +}; + +static void __init xen_hvm_guest_init(void) +{ + int r; + int major, minor; + + r = init_hvm_pv_info(&major, &minor); + if (r < 0) + return; + + xen_hvm_init_shared_info(); + + if (xen_feature(XENFEAT_hvm_callback_vector)) + xen_have_vector_callback = 1; + register_cpu_notifier(&xen_hvm_cpu_notifier); + xen_unplug_emulated_devices(); + have_vcpu_info_placement = 0; + x86_init.irqs.intr_init = xen_init_IRQ; + xen_hvm_init_time_ops(); + xen_hvm_init_mmu_ops(); +} + +static bool __init xen_hvm_platform(void) +{ + if (xen_pv_domain()) + return false; + + if (!xen_cpuid_base()) + return false; + + return true; +} + +const __refconst struct hypervisor_x86 x86_hyper_xen_hvm = { + .name = "Xen HVM", + .detect = xen_hvm_platform, + .init_platform = xen_hvm_guest_init, +}; +EXPORT_SYMBOL(x86_hyper_xen_hvm); +#endif diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index ef5728dde8f..42086ac406a 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -62,6 +62,7 @@ #include <xen/xen.h> #include <xen/page.h> #include <xen/interface/xen.h> +#include <xen/interface/hvm/hvm_op.h> #include <xen/interface/version.h> #include <xen/interface/memory.h> #include <xen/hvc-console.h> @@ -2224,6 +2225,40 @@ void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order) } EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region); +#ifdef CONFIG_XEN_PVHVM +static void xen_hvm_exit_mmap(struct mm_struct *mm) +{ + struct xen_hvm_pagetable_dying a; + int rc; + + a.domid = DOMID_SELF; + a.gpa = __pa(mm->pgd); + rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a); + WARN_ON_ONCE(rc < 0); +} + +static int is_pagetable_dying_supported(void) +{ + struct xen_hvm_pagetable_dying a; + int rc = 0; + + a.domid = DOMID_SELF; + a.gpa = 0x00; + rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a); + if (rc < 0) { + printk(KERN_DEBUG "HVMOP_pagetable_dying not supported\n"); + return 0; + } + return 1; +} + +void __init xen_hvm_init_mmu_ops(void) +{ + if (is_pagetable_dying_supported()) + pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap; +} +#endif + #ifdef CONFIG_XEN_DEBUG_FS static struct dentry *d_mmu_debug; diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index 5fe6bc7f5ec..fa938c4aa2f 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -60,4 +60,5 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, unsigned long xen_read_cr2_direct(void); extern void xen_init_mmu_ops(void); +extern void xen_hvm_init_mmu_ops(void); #endif /* _XEN_MMU_H */ diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c new file mode 100644 index 00000000000..554c002a1e1 --- /dev/null +++ b/arch/x86/xen/platform-pci-unplug.c @@ -0,0 +1,137 @@ +/****************************************************************************** + * platform-pci-unplug.c + * + * Xen platform PCI device driver + * Copyright (c) 2010, Citrix + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + */ + +#include <linux/init.h> +#include <linux/io.h> +#include <linux/module.h> + +#include <xen/platform_pci.h> + +#define XEN_PLATFORM_ERR_MAGIC -1 +#define XEN_PLATFORM_ERR_PROTOCOL -2 +#define XEN_PLATFORM_ERR_BLACKLIST -3 + +/* store the value of xen_emul_unplug after the unplug is done */ +int xen_platform_pci_unplug; +EXPORT_SYMBOL_GPL(xen_platform_pci_unplug); +#ifdef CONFIG_XEN_PVHVM +static int xen_emul_unplug; + +static int __init check_platform_magic(void) +{ + short magic; + char protocol; + + magic = inw(XEN_IOPORT_MAGIC); + if (magic != XEN_IOPORT_MAGIC_VAL) { + printk(KERN_ERR "Xen Platform PCI: unrecognised magic value\n"); + return XEN_PLATFORM_ERR_MAGIC; + } + + protocol = inb(XEN_IOPORT_PROTOVER); + + printk(KERN_DEBUG "Xen Platform PCI: I/O protocol version %d\n", + protocol); + + switch (protocol) { + case 1: + outw(XEN_IOPORT_LINUX_PRODNUM, XEN_IOPORT_PRODNUM); + outl(XEN_IOPORT_LINUX_DRVVER, XEN_IOPORT_DRVVER); + if (inw(XEN_IOPORT_MAGIC) != XEN_IOPORT_MAGIC_VAL) { + printk(KERN_ERR "Xen Platform: blacklisted by host\n"); + return XEN_PLATFORM_ERR_BLACKLIST; + } + break; + default: + printk(KERN_WARNING "Xen Platform PCI: unknown I/O protocol version"); + return XEN_PLATFORM_ERR_PROTOCOL; + } + + return 0; +} + +void __init xen_unplug_emulated_devices(void) +{ + int r; + + /* check the version of the xen platform PCI device */ + r = check_platform_magic(); + /* If the version matches enable the Xen platform PCI driver. + * Also enable the Xen platform PCI driver if the version is really old + * and the user told us to ignore it. */ + if (r && !(r == XEN_PLATFORM_ERR_MAGIC && + (xen_emul_unplug & XEN_UNPLUG_IGNORE))) + return; + /* Set the default value of xen_emul_unplug depending on whether or + * not the Xen PV frontends and the Xen platform PCI driver have + * been compiled for this kernel (modules or built-in are both OK). */ + if (!xen_emul_unplug) { + if (xen_must_unplug_nics()) { + printk(KERN_INFO "Netfront and the Xen platform PCI driver have " + "been compiled for this kernel: unplug emulated NICs.\n"); + xen_emul_unplug |= XEN_UNPLUG_ALL_NICS; + } + if (xen_must_unplug_disks()) { + printk(KERN_INFO "Blkfront and the Xen platform PCI driver have " + "been compiled for this kernel: unplug emulated disks.\n" + "You might have to change the root device\n" + "from /dev/hd[a-d] to /dev/xvd[a-d]\n" + "in your root= kernel command line option\n"); + xen_emul_unplug |= XEN_UNPLUG_ALL_IDE_DISKS; + } + } + /* Now unplug the emulated devices */ + if (!(xen_emul_unplug & XEN_UNPLUG_IGNORE)) + outw(xen_emul_unplug, XEN_IOPORT_UNPLUG); + xen_platform_pci_unplug = xen_emul_unplug; +} + +static int __init parse_xen_emul_unplug(char *arg) +{ + char *p, *q; + int l; + + for (p = arg; p; p = q) { + q = strchr(p, ','); + if (q) { + l = q - p; + q++; + } else { + l = strlen(p); + } + if (!strncmp(p, "all", l)) + xen_emul_unplug |= XEN_UNPLUG_ALL; + else if (!strncmp(p, "ide-disks", l)) + xen_emul_unplug |= XEN_UNPLUG_ALL_IDE_DISKS; + else if (!strncmp(p, "aux-ide-disks", l)) + xen_emul_unplug |= XEN_UNPLUG_AUX_IDE_DISKS; + else if (!strncmp(p, "nics", l)) + xen_emul_unplug |= XEN_UNPLUG_ALL_NICS; + else if (!strncmp(p, "ignore", l)) + xen_emul_unplug |= XEN_UNPLUG_IGNORE; + else + printk(KERN_WARNING "unrecognised option '%s' " + "in parameter 'xen_emul_unplug'\n", p); + } + return 0; +} +early_param("xen_emul_unplug", parse_xen_emul_unplug); +#endif diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index ad0047f47cd..328b0030542 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -20,6 +20,7 @@ #include <xen/page.h> #include <xen/interface/callback.h> #include <xen/interface/physdev.h> +#include <xen/interface/memory.h> #include <xen/features.h> #include "xen-ops.h" @@ -32,6 +33,73 @@ extern void xen_sysenter_target(void); extern void xen_syscall_target(void); extern void xen_syscall32_target(void); +static unsigned long __init xen_release_chunk(phys_addr_t start_addr, + phys_addr_t end_addr) +{ + struct xen_memory_reservation reservation = { + .address_bits = 0, + .extent_order = 0, + .domid = DOMID_SELF + }; + unsigned long start, end; + unsigned long len = 0; + unsigned long pfn; + int ret; + + start = PFN_UP(start_addr); + end = PFN_DOWN(end_addr); + + if (end <= start) + return 0; + + printk(KERN_INFO "xen_release_chunk: looking at area pfn %lx-%lx: ", + start, end); + for(pfn = start; pfn < end; pfn++) { + unsigned long mfn = pfn_to_mfn(pfn); + + /* Make sure pfn exists to start with */ + if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn) + continue; + + set_xen_guest_handle(reservation.extent_start, &mfn); + reservation.nr_extents = 1; + + ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, + &reservation); + WARN(ret != 1, "Failed to release memory %lx-%lx err=%d\n", + start, end, ret); + if (ret == 1) { + set_phys_to_machine(pfn, INVALID_P2M_ENTRY); + len++; + } + } + printk(KERN_CONT "%ld pages freed\n", len); + + return len; +} + +static unsigned long __init xen_return_unused_memory(unsigned long max_pfn, + const struct e820map *e820) +{ + phys_addr_t max_addr = PFN_PHYS(max_pfn); + phys_addr_t last_end = 0; + unsigned long released = 0; + int i; + + for (i = 0; i < e820->nr_map && last_end < max_addr; i++) { + phys_addr_t end = e820->map[i].addr; + end = min(max_addr, end); + + released += xen_release_chunk(last_end, end); + last_end = e820->map[i].addr + e820->map[i].size; + } + + if (last_end < max_addr) + released += xen_release_chunk(last_end, max_addr); + + printk(KERN_INFO "released %ld pages of unused memory\n", released); + return released; +} /** * machine_specific_memory_setup - Hook for machine specific memory setup. @@ -67,6 +135,8 @@ char * __init xen_memory_setup(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + xen_return_unused_memory(xen_start_info->nr_pages, &e820); + return "Xen"; } @@ -156,6 +226,8 @@ void __init xen_arch_setup(void) struct physdev_set_iopl set_iopl; int rc; + xen_panic_handler_init(); + HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments); HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index a29693fd313..25f232b18a8 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -394,6 +394,8 @@ static void stop_self(void *v) load_cr3(swapper_pg_dir); /* should set up a minimal gdt */ + set_cpu_online(cpu, false); + HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL); BUG(); } diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 987267f79bf..1d789d56877 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -26,6 +26,18 @@ void xen_pre_suspend(void) BUG(); } +void xen_hvm_post_suspend(int suspend_cancelled) +{ + int cpu; + xen_hvm_init_shared_info(); + xen_callback_vector(); + if (xen_feature(XENFEAT_hvm_safe_pvclock)) { + for_each_online_cpu(cpu) { + xen_setup_runstate_info(cpu); + } + } +} + void xen_post_suspend(int suspend_cancelled) { xen_build_mfn_list_list(); @@ -60,6 +72,6 @@ static void xen_vcpu_notify_restore(void *data) void xen_arch_resume(void) { - smp_call_function(xen_vcpu_notify_restore, - (void *)CLOCK_EVT_NOTIFY_RESUME, 1); + on_each_cpu(xen_vcpu_notify_restore, + (void *)CLOCK_EVT_NOTIFY_RESUME, 1); } diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 32764b8880b..1a5353a753f 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -20,6 +20,7 @@ #include <asm/xen/hypercall.h> #include <xen/events.h> +#include <xen/features.h> #include <xen/interface/xen.h> #include <xen/interface/vcpu.h> @@ -155,47 +156,8 @@ static void do_stolen_accounting(void) account_idle_ticks(ticks); } -/* - * Xen sched_clock implementation. Returns the number of unstolen - * nanoseconds, which is nanoseconds the VCPU spent in RUNNING+BLOCKED - * states. - */ -unsigned long long xen_sched_clock(void) -{ - struct vcpu_runstate_info state; - cycle_t now; - u64 ret; - s64 offset; - - /* - * Ideally sched_clock should be called on a per-cpu basis - * anyway, so preempt should already be disabled, but that's - * not current practice at the moment. - */ - preempt_disable(); - - now = xen_clocksource_read(); - - get_runstate_snapshot(&state); - - WARN_ON(state.state != RUNSTATE_running); - - offset = now - state.state_entry_time; - if (offset < 0) - offset = 0; - - ret = state.time[RUNSTATE_blocked] + - state.time[RUNSTATE_running] + - offset; - - preempt_enable(); - - return ret; -} - - /* Get the TSC speed from Xen */ -unsigned long xen_tsc_khz(void) +static unsigned long xen_tsc_khz(void) { struct pvclock_vcpu_time_info *info = &HYPERVISOR_shared_info->vcpu_info[0].time; @@ -230,7 +192,7 @@ static void xen_read_wallclock(struct timespec *ts) put_cpu_var(xen_vcpu); } -unsigned long xen_get_wallclock(void) +static unsigned long xen_get_wallclock(void) { struct timespec ts; @@ -238,7 +200,7 @@ unsigned long xen_get_wallclock(void) return ts.tv_sec; } -int xen_set_wallclock(unsigned long now) +static int xen_set_wallclock(unsigned long now) { /* do nothing for domU */ return -1; @@ -473,9 +435,14 @@ void xen_timer_resume(void) } } -__init void xen_time_init(void) +static const struct pv_time_ops xen_time_ops __initdata = { + .sched_clock = xen_clocksource_read, +}; + +static __init void xen_time_init(void) { int cpu = smp_processor_id(); + struct timespec tp; clocksource_register(&xen_clocksource); @@ -487,9 +454,8 @@ __init void xen_time_init(void) } /* Set initial system time with full resolution */ - xen_read_wallclock(&xtime); - set_normalized_timespec(&wall_to_monotonic, - -xtime.tv_sec, -xtime.tv_nsec); + xen_read_wallclock(&tp); + do_settimeofday(&tp); setup_force_cpu_cap(X86_FEATURE_TSC); @@ -497,3 +463,47 @@ __init void xen_time_init(void) xen_setup_timer(cpu); xen_setup_cpu_clockevents(); } + +__init void xen_init_time_ops(void) +{ + pv_time_ops = xen_time_ops; + + x86_init.timers.timer_init = xen_time_init; + x86_init.timers.setup_percpu_clockev = x86_init_noop; + x86_cpuinit.setup_percpu_clockev = x86_init_noop; + + x86_platform.calibrate_tsc = xen_tsc_khz; + x86_platform.get_wallclock = xen_get_wallclock; + x86_platform.set_wallclock = xen_set_wallclock; +} + +#ifdef CONFIG_XEN_PVHVM +static void xen_hvm_setup_cpu_clockevents(void) +{ + int cpu = smp_processor_id(); + xen_setup_runstate_info(cpu); + xen_setup_timer(cpu); + xen_setup_cpu_clockevents(); +} + +__init void xen_hvm_init_time_ops(void) +{ + /* vector callback is needed otherwise we cannot receive interrupts + * on cpu > 0 */ + if (!xen_have_vector_callback && num_present_cpus() > 1) + return; + if (!xen_feature(XENFEAT_hvm_safe_pvclock)) { + printk(KERN_INFO "Xen doesn't support pvclock on HVM," + "disable pv timer\n"); + return; + } + + pv_time_ops = xen_time_ops; + x86_init.timers.setup_percpu_clockev = xen_time_init; + x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents; + + x86_platform.calibrate_tsc = xen_tsc_khz; + x86_platform.get_wallclock = xen_get_wallclock; + x86_platform.set_wallclock = xen_set_wallclock; +} +#endif diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index f9153a300bc..7c8ab86163e 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -38,6 +38,10 @@ void xen_enable_sysenter(void); void xen_enable_syscall(void); void xen_vcpu_restore(void); +void xen_callback_vector(void); +void xen_hvm_init_shared_info(void); +void __init xen_unplug_emulated_devices(void); + void __init xen_build_dynamic_phys_to_machine(void); void xen_init_irq_ops(void); @@ -46,11 +50,8 @@ void xen_setup_runstate_info(int cpu); void xen_teardown_timer(int cpu); cycle_t xen_clocksource_read(void); void xen_setup_cpu_clockevents(void); -unsigned long xen_tsc_khz(void); -void __init xen_time_init(void); -unsigned long xen_get_wallclock(void); -int xen_set_wallclock(unsigned long time); -unsigned long long xen_sched_clock(void); +void __init xen_init_time_ops(void); +void __init xen_hvm_init_time_ops(void); irqreturn_t xen_debug_interrupt(int irq, void *dev_id); @@ -101,4 +102,6 @@ void xen_sysret32(void); void xen_sysret64(void); void xen_adjust_exception_frame(void); +extern int xen_panic_handler_init(void); + #endif /* XEN_OPS_H */ |